@@ -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)
{
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 is the core patch to support writing ring buffer backward, which would be introduced by following patch to support reading from overwritable ring buffer. In theory, this patch should not introduce any extra performance overhead since we use always_inline. When CONFIG_OPTIMIZE_INLINING is disabled, the output object is nearly identical to original one. See [1]. When CONFIG_OPTIMIZE_INLINING is enabled, the resuling object file becomes smaller: $ size kernel/events/ring_buffer.o* text data bss dec hex filename 4545 4 8 4557 11cd kernel/events/ring_buffer.o.new 4641 4 8 4653 122d kernel/events/ring_buffer.o.old Performance result: Calling 3000000 times of 'close(-1)', use gettimeofday() to check duration. Use 'perf record -o /dev/null -e raw_syscalls:*' to capture system calls. In ns. Testing environment: CPU : Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz Kernel : v4.5.0 MEAN STDVAR BASE 800214.950 2853.083 PRE 2253846.700 9997.014 POST 2257495.540 8516.293 Where 'BASE' is pure performance without capturing. 'PRE' is test result of pure 'v4.5.0' kernel. 'POST' is test result after this patch. See [4] for detail experimental setup. Considering the stdvar, this patch doesn't hurt performance. For the detail of testing method, please refer to [2]. [1] http://lkml.kernel.org/g/56F52E83.70409@huawei.com [2] http://lkml.kernel.org/g/56F89DCD.1040202@huawei.com 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 --- kernel/events/ring_buffer.c | 42 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 6 deletions(-) -- 1.8.3.4