Author: ian
Date: Wed Jan 21 20:12:35 2015
New Revision: 277512
URL: https://svnweb.freebsd.org/changeset/base/277512
Log:
Micro-optimize the new arm inline bus_space implementation by grouping all
the data the inline functions access together at the start of the bus_space
struct. The start-of part isn't so important, it's the grouping-together
that's the point: now all the most-accessed data should be in one cache line.
Suggested by: cognet
Modified:
head/sys/arm/arm/bus_space_base.c
head/sys/arm/include/bus.h
Modified: head/sys/arm/arm/bus_space_base.c
==============================================================================
--- head/sys/arm/arm/bus_space_base.c Wed Jan 21 20:08:24 2015 (r277511)
+++ head/sys/arm/arm/bus_space_base.c Wed Jan 21 20:12:35 2015 (r277512)
@@ -150,7 +150,7 @@ static struct bus_space arm_base_bus_spa
.bs_wr_2_s = generic_bs_wr_2,
.bs_wr_4_s = generic_bs_wr_4,
.bs_wr_8_s = BS_UNIMPLEMENTED,
-};
+} __aligned(CACHE_LINE_SIZE);
#ifdef FDT
bus_space_tag_t fdtbus_bs_tag = &arm_base_bus_space;
Modified: head/sys/arm/include/bus.h
==============================================================================
--- head/sys/arm/include/bus.h Wed Jan 21 20:08:24 2015 (r277511)
+++ head/sys/arm/include/bus.h Wed Jan 21 20:12:35 2015 (r277512)
@@ -79,9 +79,27 @@
#define BUS_SPACE_MAP_LINEAR 0x02
#define BUS_SPACE_MAP_PREFETCHABLE 0x04
+/*
+ * Bus space for ARM.
+ *
+ * The functions used most often are grouped together at the beginning to ensure
+ * that all the data fits into a single cache line. The inline implementations
+ * of single read/write access these values a lot.
+ */
struct bus_space {
- /* cookie */
- void *bs_privdata;
+ /* Read/write single and barrier: the most commonly used functions. */
+ uint8_t (*bs_r_1)(bus_space_tag_t, bus_space_handle_t, bus_size_t);
+ uint32_t (*bs_r_4)(bus_space_tag_t, bus_space_handle_t, bus_size_t);
+ void (*bs_w_1)(bus_space_tag_t, bus_space_handle_t,
+ bus_size_t, uint8_t);
+ void (*bs_w_4)(bus_space_tag_t, bus_space_handle_t,
+ bus_size_t, uint32_t);
+ void (*bs_barrier)(bus_space_tag_t, bus_space_handle_t,
+ bus_size_t, bus_size_t, int);
+
+ /* Backlink to parent (if copied), and implementation private data. */
+ struct bus_space *bs_parent;
+ void *bs_privdata;
/* mapping/unmapping */
int (*bs_map) (bus_space_tag_t, bus_addr_t, bus_size_t,
@@ -97,15 +115,8 @@ struct bus_space {
void (*bs_free) (bus_space_tag_t, bus_space_handle_t,
bus_size_t);
- /* get kernel virtual address */
- /* barrier */
- void (*bs_barrier) (bus_space_tag_t, bus_space_handle_t,
- bus_size_t, bus_size_t, int);
-
- /* read (single) */
- uint8_t (*bs_r_1) (bus_space_tag_t, bus_space_handle_t, bus_size_t);
+ /* Read single, the less commonly used functions. */
uint16_t (*bs_r_2) (bus_space_tag_t, bus_space_handle_t, bus_size_t);
- uint32_t (*bs_r_4) (bus_space_tag_t, bus_space_handle_t, bus_size_t);
uint64_t (*bs_r_8) (bus_space_tag_t, bus_space_handle_t, bus_size_t);
/* read multiple */
@@ -128,13 +139,9 @@ struct bus_space {
void (*bs_rr_8) (bus_space_tag_t, bus_space_handle_t,
bus_size_t, uint64_t *, bus_size_t);
- /* write (single) */
- void (*bs_w_1) (bus_space_tag_t, bus_space_handle_t,
- bus_size_t, uint8_t);
+ /* Write single, the less commonly used functions. */
void (*bs_w_2) (bus_space_tag_t, bus_space_handle_t,
bus_size_t, uint16_t);
- void (*bs_w_4) (bus_space_tag_t, bus_space_handle_t,
- bus_size_t, uint32_t);
void (*bs_w_8) (bus_space_tag_t, bus_space_handle_t,
bus_size_t, uint64_t);