[tip:perf/core] perf: Optimize perf_output_begin() -- address calculation

From: tip-bot for Peter Zijlstra
Date: Wed Nov 06 2013 - 08:24:33 EST


Commit-ID: 524feca5e9da9e5f9e5aa5d5613b1d762db9509e
Gitweb: http://git.kernel.org/tip/524feca5e9da9e5f9e5aa5d5613b1d762db9509e
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Thu, 31 Oct 2013 17:36:25 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 6 Nov 2013 12:34:22 +0100

perf: Optimize perf_output_begin() -- address calculation

Rewrite the handle address calculation code to be clearer.

Saves 8 bytes on x86_64-defconfig.

Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxx>
Cc: Michael Ellerman <michael@xxxxxxxxxxxxxx>
Cc: Michael Neuling <mikey@xxxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: james.hogan@xxxxxxxxxx
Cc: Vince Weaver <vince@xxxxxxxxxx>
Cc: Victor Kaplansky <VICTORK@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Anton Blanchard <anton@xxxxxxxxx>
Link: http://lkml.kernel.org/n/tip-3trb2n2henb9m27tncef3ag7@xxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
kernel/events/ring_buffer.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e4d70f3..c52a32f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -105,7 +105,7 @@ int perf_output_begin(struct perf_output_handle *handle,
{
struct ring_buffer *rb;
unsigned long tail, offset, head;
- int have_lost;
+ int have_lost, page_shift;
struct {
struct perf_event_header header;
u64 id;
@@ -159,12 +159,12 @@ int perf_output_begin(struct perf_output_handle *handle,
if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
local_add(rb->watermark, &rb->wakeup);

- handle->page = offset >> (PAGE_SHIFT + page_order(rb));
- handle->page &= rb->nr_pages - 1;
- handle->size = offset & ((PAGE_SIZE << page_order(rb)) - 1);
- handle->addr = rb->data_pages[handle->page];
- handle->addr += handle->size;
- handle->size = (PAGE_SIZE << page_order(rb)) - handle->size;
+ page_shift = PAGE_SHIFT + page_order(rb);
+
+ handle->page = (offset >> page_shift) & (rb->nr_pages - 1);
+ offset &= (1UL << page_shift) - 1;
+ handle->addr = rb->data_pages[handle->page] + offset;
+ handle->size = (1UL << page_shift) - offset;

if (unlikely(have_lost)) {
struct perf_sample_data sample_data;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/