Re: [PATCH v12 2/3]: perf record: enable asynchronous trace writing

[Jiri Olsa <jolsa@redhat.com>]

On Tue, Oct 09, 2018 at 11:58:53AM +0300, Alexey Budankov wrote:

SNIP

> +#ifdef HAVE_AIO_SUPPORT
> +int perf_mmap__aio_push(struct perf_mmap *md, void *to,
> +			int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off),
> +			off_t *off)
> +{
> +	u64 head = perf_mmap__read_head(md);
> +	unsigned char *data = md->base + page_size;
> +	unsigned long size, size0 = 0;
> +	void *buf;
> +	int rc = 0;
> +
> +	rc = perf_mmap__read_init(md);
> +	if (rc < 0)
> +		return (rc == -EAGAIN) ? 0 : -1;
> +
> +	/*
> +	 * md->base data is copied into md->data buffer to
> +	 * release space in the kernel buffer as fast as possible,
> +	 * thru perf_mmap__consume() below.
> +	 *
> +	 * That lets the kernel to proceed with storing more
> +	 * profiling data into the kernel buffer earlier than other
> +	 * per-cpu kernel buffers are handled.
> +	 *
> +	 * Coping can be done in two steps in case the chunk of
> +	 * profiling data crosses the upper bound of the kernel buffer.
> +	 * In this case we first move part of data from md->start
> +	 * till the upper bound and then the reminder from the
> +	 * beginning of the kernel buffer till the end of
> +	 * the data chunk.
> +	 */
> +
> +	size = md->end - md->start;
> +
> +	if ((md->start & md->mask) + size != (md->end & md->mask)) {
> +		buf = &data[md->start & md->mask];
> +		size = md->mask + 1 - (md->start & md->mask);
> +		md->start += size;
> +		memcpy(md->aio.data, buf, size);
> +		size0 = size;
> +	}
> +
> +	buf = &data[md->start & md->mask];
> +	size = md->end - md->start;
> +	md->start += size;
> +	memcpy(md->aio.data + size0, buf, size);
> +
> +	/*
> +	 * Increment md->refcount to guard md->data buffer
> +	 * from premature deallocation because md object can be
> +	 * released earlier than aio write request started
> +	 * on mmap->data is complete.
> +	 *
> +	 * perf_mmap__put() is done at record__aio_complete()
> +	 * after started request completion.
> +	 */
> +	perf_mmap__get(md);
> +
> +	md->prev = head;
> +	perf_mmap__consume(md);
> +
> +	rc = push(to, &(md->aio.cblock), md->aio.data, size0 + size, *off);
> +	if (!rc) {
> +		*off += size0 + size;
> +	} else {
> +		/*
> +		 * Decrement md->refcount back if aio write
> +		 * operation failed to start.
> +		 */
> +		perf_mmap__put(md);
> +	}
> +
> +	return rc;
> +}
> +#else
> +int perf_mmap__aio_push(struct perf_mmap *md __maybe_unused, void *to __maybe_unused,
> +	int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off) __maybe_unused,
> +	off_t *off __maybe_unused)
> +{
> +	return 0;
> +}

I think you need to put this one in the header as static inline
otherwise it'd still appear in the NO_AIO=1 build, like:
  [jolsa@krava perf]$ make NO_AIO=1
  ...
  [jolsa@krava perf]$ nm -D perf | grep perf_mmap__aio_push
  00000000004c2be0 T perf_mmap__aio_push

change below makes it disappear completely

jirka


---
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index b176d88b3fcb..8c7516696891 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -445,13 +445,6 @@ int perf_mmap__aio_push(struct perf_mmap *md, void *to,
 
 	return rc;
 }
-#else
-int perf_mmap__aio_push(struct perf_mmap *md __maybe_unused, void *to __maybe_unused,
-	int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off) __maybe_unused,
-	off_t *off __maybe_unused)
-{
-	return 0;
-}
 #endif
 
 /*
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 04ff4d2ffdbe..3ccf8c925002 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -105,10 +105,21 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
 		    int push(struct perf_mmap *map, void *to, void *buf, size_t size));
+
+#ifdef HAVE_AIO_SUPPORT
 int perf_mmap__aio_push(struct perf_mmap *md, void *to,
 			int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off),
 			off_t *off);
 
+#else
+static inline int perf_mmap__aio_push(struct perf_mmap *md __maybe_unused, void *to __maybe_unused,
+	int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off) __maybe_unused,
+	off_t *off __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
 int perf_mmap__read_init(struct perf_mmap *md);