From: kan.liang@intel.com
To: acme@kernel.org, peterz@infradead.org, mingo@redhat.com,
        linux-kernel@vger.kernel.org
Cc: jolsa@kernel.org, wangnan0@huawei.com, namhyung@kernel.org,
        ak@linux.intel.com, yao.jin@linux.intel.com,
        Kan Liang <kan.liang@intel.com>
Subject: [PATCH V2 2/8] perf tools: rewrite perf mmap read for overwrite
Date: Wed,  6 Dec 2017 15:32:57 -0800
Message-Id: <1512603183-42754-3-git-send-email-kan.liang@intel.com>
In-Reply-To: <1512603183-42754-1-git-send-email-kan.liang@intel.com>
References: <1512603183-42754-1-git-send-email-kan.liang@intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 6152
Lines: 187

From: Kan Liang <kan.liang@intel.com>

perf_mmap__read_catchup and perf_mmap__read_backward are used to read
events one by one from ring buffer under overwrite mode.
It always read the stale buffer which is already processed.
Because the previous location of processed ring buffer is discarded.

Introducing the perf_mmap__read_done, which update the map->prev to
indicate the position of processed buffer.

Refining perf_mmap__read_catchup to calculate the start and the end of
ring buffer. It only need to do the calculation once at the beginning,
because the ring buffer is paused in overwrite mode.
Doesn't need to do the calculation in perf_mmap__read_backward.

For now, the only user is backward-ring-buffer in perf test.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/tests/backward-ring-buffer.c |  9 +++-
 tools/perf/util/mmap.c                  | 88 +++++++++++++++++++--------------
 tools/perf/util/mmap.h                  |  7 ++-
 3 files changed, 63 insertions(+), 41 deletions(-)

diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 4035d43..66d9e54 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,10 +31,14 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	int i;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct perf_mmap *map = &evlist->overwrite_mmap[i];
 		union perf_event *event;
+		unsigned long size;
+		u64 start, end;
 
-		perf_mmap__read_catchup(&evlist->overwrite_mmap[i]);
-		while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) {
+		perf_mmap__read_catchup(map, true, &start, &end, &size);
+		while ((event = perf_mmap__read_backward(map, &start, end)) !=
+		       NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
@@ -49,6 +53,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 				return TEST_FAIL;
 			}
 		}
+		perf_mmap__read_done(map);
 	}
 	return TEST_OK;
 }
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 05076e6..bf67460 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -85,51 +85,65 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 	return perf_mmap__read(map, old, head, &map->prev);
 }
 
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map,
+					   u64 *start, u64 end)
 {
-	u64 head, end;
-	u64 start = map->prev;
-
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&map->refcnt))
-		return NULL;
-
-	head = perf_mmap__read_head(map);
-	if (!head)
-		return NULL;
+	union perf_event *event = NULL;
 
-	/*
-	 * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-	 * it each time when kernel writes to it, so in fact 'head' is
-	 * negative. 'end' pointer is made manually by adding the size of
-	 * the ring buffer to 'head' pointer, means the validate data can
-	 * read is the whole ring buffer. If 'end' is positive, the ring
-	 * buffer has not fully filled, so we must adjust 'end' to 0.
-	 *
-	 * However, since both 'head' and 'end' is unsigned, we can't
-	 * simply compare 'end' against 0. Here we compare '-head' and
-	 * the size of the ring buffer, where -head is the number of bytes
-	 * kernel write to the ring buffer.
-	 */
-	if (-head < (u64)(map->mask + 1))
-		end = 0;
-	else
-		end = head + map->mask + 1;
+	event = perf_mmap__read(map, *start, end, &map->prev);
+	*start = map->prev;
 
-	return perf_mmap__read(map, start, end, &map->prev);
+	return event;
 }
 
-void perf_mmap__read_catchup(struct perf_mmap *map)
+static int overwrite_rb_find_range(void *buf, int mask, u64 head,
+				   u64 *start, u64 *end);
+
+int perf_mmap__read_catchup(struct perf_mmap *map,
+			    bool overwrite,
+			    u64 *start, u64 *end,
+			    unsigned long *size)
 {
-	u64 head;
+	u64 head = perf_mmap__read_head(map);
+	u64 old = map->prev;
+	unsigned char *data = map->base + page_size;
 
-	if (!refcount_read(&map->refcnt))
-		return;
+	*start = overwrite ? head : old;
+	*end = overwrite ? old : head;
 
-	head = perf_mmap__read_head(map);
-	map->prev = head;
+	if (*start == *end)
+		return 0;
+
+	*size = *end - *start;
+	if (*size > (unsigned long)(map->mask) + 1) {
+		if (!overwrite) {
+			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+
+			map->prev = head;
+			perf_mmap__consume(map, overwrite);
+			return 0;
+		}
+
+		/*
+		 * Backward ring buffer is full. We still have a chance to read
+		 * most of data from it.
+		 */
+		if (overwrite_rb_find_range(data, map->mask, head, start, end))
+			return -1;
+	}
+
+	return 1;
+}
+
+/*
+ * Mandatory for overwrite mode
+ * The direction of overwrite mode is backward.
+ * The last mmap__read_event will set tail to map->prev.
+ * Need to correct the map->prev to head which is the end of next read.
+ */
+void perf_mmap__read_done(struct perf_mmap *map)
+{
+	map->prev = perf_mmap__read_head(map);
 }
 
 static bool perf_mmap__empty(struct perf_mmap *map)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index d640273..a91222e 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -65,7 +65,9 @@ void perf_mmap__put(struct perf_mmap *map);
 
 void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
 
-void perf_mmap__read_catchup(struct perf_mmap *md);
+int perf_mmap__read_catchup(struct perf_mmap *map, bool overwrite,
+			    u64 *start, u64 *end, unsigned long *size);
+void perf_mmap__read_done(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
@@ -87,7 +89,8 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 }
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map,
+					   u64 *start, u64 end);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,
 		    void *to, int push(void *to, void *buf, size_t size));
-- 
2.5.5