linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wang Nan <wangnan0@huawei.com>
To: Alexei Starovoitov <ast@kernel.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: "Adrian Hunter" <adrian.hunter@intel.com>,
	"Cody P Schafer" <dev@codyps.com>,
	"David S. Miller" <davem@davemloft.net>,
	"He Kuang" <hekuang@huawei.com>,
	"Jérémie Galarneau" <jeremie.galarneau@efficios.com>,
	"Jiri Olsa" <jolsa@kernel.org>,
	"Kirill Smelkov" <kirr@nexedi.com>,
	"Li Zefan" <lizefan@huawei.com>,
	"Masami Hiramatsu" <masami.hiramatsu.pt@hitachi.com>,
	"Namhyung Kim" <namhyung@kernel.org>,
	"Peter Zijlstra" <peterz@infradead.org>,
	pi3orama@163.com, "Wang Nan" <wangnan0@huawei.com>,
	linux-kernel@vger.kernel.org
Subject: [PATCH 22/54] perf core: Add backward attribute to perf event
Date: Fri, 5 Feb 2016 14:01:47 +0000	[thread overview]
Message-ID: <1454680939-24963-23-git-send-email-wangnan0@huawei.com> (raw)
In-Reply-To: <1454680939-24963-1-git-send-email-wangnan0@huawei.com>

In perf_event_attr a new bit 'write_backward' is appended to indicate
this event should write ring buffer from its end to beginning.

In perf_output_begin(), prepare ring buffer according this bit.

This patch introduces small overhead into perf_output_begin():
an extra memory read and a conditional branch. Further patch can remove
this overhead by using custom output handler.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
---
 include/linux/perf_event.h      | 5 +++++
 include/uapi/linux/perf_event.h | 3 ++-
 kernel/events/core.c            | 7 +++++++
 kernel/events/ring_buffer.c     | 2 ++
 4 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b35a61a..0ce1015 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1029,6 +1029,11 @@ static inline bool has_aux(struct perf_event *event)
 	return event->pmu->setup_aux;
 }
 
+static inline bool is_write_backward(struct perf_event *event)
+{
+	return !!event->attr.write_backward;
+}
+
 extern int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_event *event, unsigned int size);
 extern void perf_output_end(struct perf_output_handle *handle);
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index a3c1903..43fc8d2 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -340,7 +340,8 @@ struct perf_event_attr {
 				comm_exec      :  1, /* flag comm events that are due to an exec */
 				use_clockid    :  1, /* use @clockid for time fields */
 				context_switch :  1, /* context switch data */
-				__reserved_1   : 37;
+				write_backward :  1, /* Write ring buffer from end to beginning */
+				__reserved_1   : 36;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 77a6475..b12de05 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8102,6 +8102,13 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 		goto out;
 
 	/*
+	 * Either writing ring buffer from beginning or from end.
+	 * Mixing is not allowed.
+	 */
+	if (is_write_backward(output_event) != is_write_backward(event))
+		goto out;
+
+	/*
 	 * If both events generate aux data, they must be on the same PMU
 	 */
 	if (has_aux(event) && has_aux(output_event) &&
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 37c11c6..80b1fa7 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -233,6 +233,8 @@ out:
 int perf_output_begin(struct perf_output_handle *handle,
 		      struct perf_event *event, unsigned int size)
 {
+	if (unlikely(is_write_backward(event)))
+		return __perf_output_begin(handle, event, size, true);
 	return __perf_output_begin(handle, event, size, false);
 }
 
-- 
1.8.3.4

  parent reply	other threads:[~2016-02-05 14:16 UTC|newest]

Thread overview: 75+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-05 14:01 [PATCH 00/54] perf tools: Bugfix, BPF improvements and overwrite ring buffer support Wang Nan
2016-02-05 14:01 ` [PATCH 01/54] perf tools: Fix dangling pointers in parse_events__free_terms Wang Nan
2016-02-16  7:53   ` [tip:perf/core] perf tools: Unlink entries from terms list tip-bot for Wang Nan
2016-02-16  7:54   ` [tip:perf/core] perf tools: Free the terms list_head in parse_events__free_terms() tip-bot for Wang Nan
2016-02-05 14:01 ` [PATCH 02/54] perf tools: Fix symbols searching for offline module in buildid-cache Wang Nan
2016-02-16  7:52   ` [tip:perf/core] perf symbols: Fix symbols searching for " tip-bot for Wang Nan
2016-02-05 14:01 ` [PATCH 03/54] perf tools: Record text offset in dso to calculate objdump address Wang Nan
2016-02-05 14:01 ` [PATCH 04/54] perf tools: Adjust symbol for shared objects Wang Nan
2016-02-05 14:01 ` [PATCH 05/54] perf data: Fix releasing event_class Wang Nan
     [not found]   ` <20160211220413.GF32168@kernel.org>
2016-02-12 12:19     ` Jiri Olsa
2016-02-12 15:42       ` Arnaldo Carvalho de Melo
2016-02-16  7:55   ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-05 14:01 ` [PATCH 06/54] perf tools: Add API to config maps in bpf object Wang Nan
2016-02-05 14:01 ` [PATCH 07/54] perf tools: Enable BPF object configure syntax Wang Nan
2016-02-12 14:09   ` Jiri Olsa
2016-02-18  6:17     ` Wangnan (F)
2016-02-05 14:01 ` [PATCH 08/54] perf record: Apply config to BPF objects before recording Wang Nan
2016-02-12 20:55   ` Arnaldo Carvalho de Melo
2016-02-05 14:01 ` [PATCH 09/54] perf tools: Enable passing event to BPF object Wang Nan
2016-02-12 14:05   ` Jiri Olsa
2016-02-05 14:01 ` [PATCH 10/54] perf stat: Forbid user passing improper config terms Wang Nan
2016-02-12 13:49   ` Jiri Olsa
2016-02-12 15:45     ` Arnaldo Carvalho de Melo
2016-02-12 15:50       ` Jiri Olsa
2016-02-05 14:01 ` [PATCH 11/54] perf tools: Rename and move pmu_event_name to get_config_name Wang Nan
2016-02-05 14:01 ` [PATCH 12/54] perf tools: Enable config raw and numeric events Wang Nan
2016-02-12 13:52   ` Jiri Olsa
2016-02-12 13:56     ` pi3orama
2016-02-12 13:56     ` Jiri Olsa
2016-02-12 14:10   ` Jiri Olsa
2016-02-12 14:12   ` Jiri Olsa
2016-02-05 14:01 ` [PATCH 13/54] perf tools: Enable config and setting names for legacy cache events Wang Nan
2016-02-05 14:01 ` [PATCH 14/54] perf tools: Support setting different slots in a BPF map separately Wang Nan
2016-02-12 14:23   ` Jiri Olsa
2016-02-12 14:34     ` pi3orama
2016-02-05 14:01 ` [PATCH 15/54] perf tools: Enable indices setting syntax for BPF maps Wang Nan
2016-02-05 14:01 ` [PATCH 16/54] perf tools: Pass tracepoint options to BPF script Wang Nan
2016-02-05 14:01 ` [PATCH 17/54] perf tools: Introduce bpf-output event Wang Nan
2016-02-05 14:01 ` [PATCH 18/54] perf data: Support converting data from bpf_perf_event_output() Wang Nan
2016-02-05 14:01 ` [PATCH 19/54] perf core: Introduce new ioctl options to pause and resume ring buffer Wang Nan
2016-02-05 14:01 ` [PATCH 20/54] perf core: Set event's default overflow_handler Wang Nan
2016-02-05 14:01 ` [PATCH 21/54] perf core: Prepare writing into ring buffer from end Wang Nan
2016-02-05 14:01 ` Wang Nan [this message]
2016-02-05 14:01 ` [PATCH 23/54] perf core: Reduce perf event output overhead by new overflow handler Wang Nan
2016-02-05 14:01 ` [PATCH 24/54] perf tools: Only validate is_pos for tracking evsels Wang Nan
2016-02-05 14:01 ` [PATCH 25/54] perf tools: Print write_backward value in perf_event_attr__fprintf Wang Nan
2016-02-05 14:01 ` [PATCH 26/54] perf tools: Make ordered_events reusable Wang Nan
2016-02-05 14:01 ` [PATCH 27/54] perf record: Extract synthesize code to record__synthesize() Wang Nan
2016-02-05 14:01 ` [PATCH 28/54] perf tools: Add perf_data_file__switch() helper Wang Nan
2016-02-05 14:01 ` [PATCH 29/54] perf record: Turns auxtrace_snapshot_enable into 3 states Wang Nan
2016-02-05 14:01 ` [PATCH 30/54] perf record: Introduce record__finish_output() to finish a perf.data Wang Nan
2016-02-05 14:01 ` [PATCH 31/54] perf record: Add '--timestamp-filename' option to append timestamp to output filename Wang Nan
2016-02-05 14:01 ` [PATCH 32/54] perf record: Split output into multiple files via '--switch-output' Wang Nan
2016-02-05 14:01 ` [PATCH 33/54] perf record: Force enable --timestamp-filename when --switch-output is provided Wang Nan
2016-02-05 14:01 ` [PATCH 34/54] perf record: Disable buildid cache options by default in switch output mode Wang Nan
2016-02-05 14:02 ` [PATCH 35/54] perf record: Re-synthesize tracking events after output switching Wang Nan
2016-02-05 14:02 ` [PATCH 36/54] perf record: Generate tracking events for process forked by perf Wang Nan
2016-02-05 14:02 ` [PATCH 37/54] perf record: Ensure return non-zero rc when mmap fail Wang Nan
2016-02-05 14:02 ` [PATCH 38/54] perf record: Prevent reading invalid data in record__mmap_read Wang Nan
2016-02-05 14:02 ` [PATCH 39/54] perf tools: Add evlist channel helpers Wang Nan
2016-02-05 14:02 ` [PATCH 40/54] perf tools: Automatically add new channel according to evlist Wang Nan
2016-02-05 14:02 ` [PATCH 41/54] perf tools: Operate multiple channels Wang Nan
2016-02-05 14:02 ` [PATCH 42/54] perf tools: Squash overwrite setting into channel Wang Nan
2016-02-05 14:02 ` [PATCH 43/54] perf record: Don't read from and poll overwrite channel Wang Nan
2016-02-05 14:02 ` [PATCH 44/54] perf record: Don't poll on " Wang Nan
2016-02-05 14:02 ` [PATCH 45/54] perf tools: Detect avalibility of write_backward Wang Nan
2016-02-05 14:02 ` [PATCH 46/54] perf tools: Enable overwrite settings Wang Nan
2016-02-05 14:02 ` [PATCH 47/54] perf tools: Set write_backward attribut bit for overwrite events Wang Nan
2016-02-05 14:02 ` [PATCH 48/54] perf tools: Record fd into perf_mmap Wang Nan
2016-02-05 14:02 ` [PATCH 49/54] perf tools: Add API to pause a channel Wang Nan
2016-02-05 14:02 ` [PATCH 50/54] perf record: Toggle overwrite ring buffer for reading Wang Nan
2016-02-05 14:02 ` [PATCH 51/54] perf record: Rename variable to make code clear Wang Nan
2016-02-05 14:02 ` [PATCH 52/54] perf record: Read from backward ring buffer Wang Nan
2016-02-05 14:02 ` [PATCH 53/54] perf record: Allow generate tracking events at the end of output Wang Nan
2016-02-05 14:02 ` [PATCH 54/54] perf tools: Don't warn about out of order event if write_backward is used Wang Nan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1454680939-24963-23-git-send-email-wangnan0@huawei.com \
    --to=wangnan0@huawei.com \
    --cc=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=ast@kernel.org \
    --cc=brendan.d.gregg@gmail.com \
    --cc=davem@davemloft.net \
    --cc=dev@codyps.com \
    --cc=hekuang@huawei.com \
    --cc=jeremie.galarneau@efficios.com \
    --cc=jolsa@kernel.org \
    --cc=kirr@nexedi.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=masami.hiramatsu.pt@hitachi.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=pi3orama@163.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).