linux-kernel - [PATCH] perf tools: fix write

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-next>] [day] [month] [year] [list]

Message-ID: <4B570657.5090105@cn.fujitsu.com>
Date:	Wed, 20 Jan 2010 21:34:15 +0800
From:	Xiao Guangrong <xiaoguangrong@...fujitsu.com>
To:	Ingo Molnar <mingo@...e.hu>
CC:	Peter Zijlstra <peterz@...radead.org>,
	Paul Mackerras <paulus@...ba.org>,
	Frederic Weisbecker <fweisbec@...il.com>,
	LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH] perf tools: fix write_event()

We parse the event while it's read from mmap buffer in
write_event(), but sometimes the event will straddles the
mmap boundary, we should handle this case

And if we record events(such as perf kmem/sched) for long
times, Ctrl + C can't interrupt it just for this reason

Signed-off-by: Xiao Guangrong <xiaoguangrong@...fujitsu.com>
---
 tools/perf/builtin-record.c |   62 +++++++++++++++++++++++++++++++++---------
 1 files changed, 48 insertions(+), 14 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7bb9ca1..97573b7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -111,28 +111,62 @@ static void write_output(void *buf, size_t size)
 	}
 }
 
-static void write_event(event_t *buf, size_t size)
+static void write_event(void *buf, size_t size)
 {
-	size_t processed_size = buf->header.size;
-	event_t *ev = buf;
+	event_t *ev;
+	struct mmap_event mmap_ev;
+	static void *rec_buf;
+	static unsigned long rec_len;
 
-	do {
-		/*
-		* Add it to the list of DSOs, so that when we finish this
-		 * record session we can pick the available build-ids.
-		 */
+	write_output(buf, size);
+
+	while (size > 0) {
+		if (rec_buf) {
+			int len;
+
+			memcpy(&mmap_ev, rec_buf, rec_len);
+			len = sizeof(mmap_ev.header) - rec_len;
+			if (len > 0) {
+				memcpy(&mmap_ev + rec_len, buf, len);
+				buf += len;
+				size -= len;
+				rec_len = sizeof((mmap_ev.header));
+			}
+
+			len = mmap_ev.header.size - rec_len;
+			if (mmap_ev.header.type == PERF_RECORD_MMAP)
+				memcpy(&mmap_ev + rec_len, buf, len);
+
+			buf += len;
+			size -= len;
+
+			rec_buf = NULL;
+			rec_len = 0;
+
+			ev = (event_t *)&mmap_ev;
+			goto handle_mmap;
+		}
+
+		ev = (event_t *)buf;
+		if (size < sizeof(struct perf_event_header) ||
+		    ev->header.size > size) {
+			rec_buf = buf;
+			rec_len = size;
+			break;
+		}
+
+		buf += ev->header.size;
+		size -= ev->header.size;
+
+handle_mmap:
 		if (ev->header.type == PERF_RECORD_MMAP) {
 			struct list_head *head = &dsos__user;
 			if (ev->header.misc == 1)
 				head = &dsos__kernel;
 			__dsos__findnew(head, ev->mmap.filename);
 		}
+	}
 
-		ev = ((void *)ev) + ev->header.size;
-		processed_size += ev->header.size;
-	} while (processed_size < size);
-
-	write_output(buf, size);
 }
 
 static int process_synthesized_event(event_t *event,
-- 
1.6.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/