linux-kernel - [RESEND PATCH 3/5] perf core: Prepare writing into ring buffer from end

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1457322619-170254-4-git-send-email-wangnan0@huawei.com>
Date:	Mon, 7 Mar 2016 03:50:17 +0000
From:	Wang Nan <wangnan0@...wei.com>
To:	<peterz@...radead.org>, <mingo@...hat.com>
CC:	<linux-kernel@...r.kernel.org>, Wang Nan <wangnan0@...wei.com>,
	He Kuang <hekuang@...wei.com>,
	Alexei Starovoitov <ast@...nel.org>,
	"Arnaldo Carvalho de Melo" <acme@...hat.com>,
	Brendan Gregg <brendan.d.gregg@...il.com>,
	"Jiri Olsa" <jolsa@...nel.org>,
	Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>,
	Namhyung Kim <namhyung@...nel.org>,
	Zefan Li <lizefan@...wei.com>, <pi3orama@....com>
Subject: [RESEND PATCH 3/5] perf core: Prepare writing into ring buffer from end

Convert perf_output_begin to __perf_output_begin and make the later
function able to write records from the end of the ring buffer.
Following commits will utilize the 'backward' flag.

This patch doesn't introduce any extra performance overhead since we
use always_inline.

Signed-off-by: Wang Nan <wangnan0@...wei.com>
Cc: He Kuang <hekuang@...wei.com>
Cc: Alexei Starovoitov <ast@...nel.org>
Cc: Arnaldo Carvalho de Melo <acme@...hat.com>
Cc: Brendan Gregg <brendan.d.gregg@...il.com>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Jiri Olsa <jolsa@...nel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Zefan Li <lizefan@...wei.com>
Cc: pi3orama@....com
---
 kernel/events/ring_buffer.c | 42 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 22e1a47..37c11c6 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -102,8 +102,21 @@ out:
 	preempt_enable();
 }
 
-int perf_output_begin(struct perf_output_handle *handle,
-		      struct perf_event *event, unsigned int size)
+static bool __always_inline
+ring_buffer_has_space(unsigned long head, unsigned long tail,
+		      unsigned long data_size, unsigned int size,
+		      bool backward)
+{
+	if (!backward)
+		return CIRC_SPACE(head, tail, data_size) >= size;
+	else
+		return CIRC_SPACE(tail, head, data_size) >= size;
+}
+
+static int __always_inline
+__perf_output_begin(struct perf_output_handle *handle,
+		    struct perf_event *event, unsigned int size,
+		    bool backward)
 {
 	struct ring_buffer *rb;
 	unsigned long tail, offset, head;
@@ -146,9 +159,12 @@ int perf_output_begin(struct perf_output_handle *handle,
 	do {
 		tail = READ_ONCE(rb->user_page->data_tail);
 		offset = head = local_read(&rb->head);
-		if (!rb->overwrite &&
-		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
-			goto fail;
+		if (!rb->overwrite) {
+			if (unlikely(!ring_buffer_has_space(head, tail,
+							    perf_data_size(rb),
+							    size, backward)))
+				goto fail;
+		}
 
 		/*
 		 * The above forms a control dependency barrier separating the
@@ -162,9 +178,17 @@ int perf_output_begin(struct perf_output_handle *handle,
 		 * See perf_output_put_handle().
 		 */
 
-		head += size;
+		if (!backward)
+			head += size;
+		else
+			head -= size;
 	} while (local_cmpxchg(&rb->head, offset, head) != offset);
 
+	if (backward) {
+		offset = head;
+		head = (u64)(-head);
+	}
+
 	/*
 	 * We rely on the implied barrier() by local_cmpxchg() to ensure
 	 * none of the data stores below can be lifted up by the compiler.
@@ -206,6 +230,12 @@ out:
 	return -ENOSPC;
 }
 
+int perf_output_begin(struct perf_output_handle *handle,
+		      struct perf_event *event, unsigned int size)
+{
+	return __perf_output_begin(handle, event, size, false);
+}
+
 unsigned int perf_output_copy(struct perf_output_handle *handle,
 		      const void *buf, unsigned int len)
 {
-- 
1.8.3.4