Avoid the indirect call for xor_generation by using a static_call.
Signed-off-by: Christoph Hellwig <[email protected]>
---
lib/raid/xor/xor-32regs.c | 2 +-
lib/raid/xor/xor-core.c | 29 ++++++++++++++---------------
lib/raid/xor/xor_impl.h | 4 ++++
3 files changed, 19 insertions(+), 16 deletions(-)
diff --git a/lib/raid/xor/xor-32regs.c b/lib/raid/xor/xor-32regs.c
index acb4a10d1e95..759a31f76414 100644
--- a/lib/raid/xor/xor-32regs.c
+++ b/lib/raid/xor/xor-32regs.c
@@ -209,7 +209,7 @@ xor_32regs_5(unsigned long bytes, unsigned long *
__restrict p1,
} while (--lines > 0);
}
-DO_XOR_BLOCKS(32regs, xor_32regs_2, xor_32regs_3, xor_32regs_4, xor_32regs_5);
+__DO_XOR_BLOCKS(32regs, xor_32regs_2, xor_32regs_3, xor_32regs_4,
xor_32regs_5);
struct xor_block_template xor_block_32regs = {
.name = "32regs",
diff --git a/lib/raid/xor/xor-core.c b/lib/raid/xor/xor-core.c
index f18dcc57004b..2ab03dd294bf 100644
--- a/lib/raid/xor/xor-core.c
+++ b/lib/raid/xor/xor-core.c
@@ -11,10 +11,14 @@
#include <linux/raid/xor.h>
#include <linux/jiffies.h>
#include <linux/preempt.h>
+#include <linux/static_call.h>
#include "xor_impl.h"
-/* The xor routine to use. */
-static struct xor_block_template *active_template;
+/*
+ * Provide a temporary default until the fastest or forced implementation is
+ * picked.
+ */
+DEFINE_STATIC_CALL(xor_gen_impl, xor_gen_32regs);
/**
* xor_gen - generate RAID-style XOR information
@@ -32,13 +36,13 @@ static struct xor_block_template *active_template;
void xor_gen(void *dest, void **srcs, unsigned int src_cnt, unsigned int bytes)
{
WARN_ON_ONCE(in_interrupt());
- active_template->xor_gen(dest, srcs, src_cnt, bytes);
+ static_call(xor_gen_impl)(dest, srcs, src_cnt, bytes);
}
EXPORT_SYMBOL(xor_gen);
/* Set of all registered templates. */
static struct xor_block_template *__initdata template_list;
-static int __initdata xor_forced = false;
+static struct xor_block_template *forced_template;
/**
* xor_register - register a XOR template
@@ -64,7 +68,7 @@ void __init xor_register(struct xor_block_template *tmpl)
*/
void __init xor_force(struct xor_block_template *tmpl)
{
- active_template = tmpl;
+ forced_template = tmpl;
}
#define BENCH_SIZE 4096
@@ -106,7 +110,7 @@ static int __init calibrate_xor_blocks(void)
void *b1, *b2;
struct xor_block_template *f, *fastest;
- if (xor_forced)
+ if (forced_template)
return 0;
b1 = (void *) __get_free_pages(GFP_KERNEL, 2);
@@ -123,7 +127,7 @@ static int __init calibrate_xor_blocks(void)
if (f->speed > fastest->speed)
fastest = f;
}
- active_template = fastest;
+ static_call_update(xor_gen_impl, fastest->xor_gen);
pr_info("xor: using function: %s (%d MB/sec)\n",
fastest->name, fastest->speed);
@@ -151,21 +155,16 @@ static int __init xor_init(void)
* If this arch/cpu has a short-circuited selection, don't loop through
* all the possible functions, just use the best one.
*/
- if (active_template) {
+ if (forced_template) {
pr_info("xor: automatically using best checksumming function
%-10s\n",
- active_template->name);
- xor_forced = true;
+ forced_template->name);
+ static_call_update(xor_gen_impl, forced_template->xor_gen);
return 0;
}
#ifdef MODULE
return calibrate_xor_blocks();
#else
- /*
- * Pick the first template as the temporary default until calibration
- * happens.
- */
- active_template = template_list;
return 0;
#endif
}
diff --git a/lib/raid/xor/xor_impl.h b/lib/raid/xor/xor_impl.h
index 968dd07df627..f11910162b08 100644
--- a/lib/raid/xor/xor_impl.h
+++ b/lib/raid/xor/xor_impl.h
@@ -50,6 +50,10 @@ extern struct xor_block_template xor_block_32regs;
extern struct xor_block_template xor_block_8regs_p;
extern struct xor_block_template xor_block_32regs_p;
+/* default call until updated */
+void xor_gen_32regs(void *dest, void **srcs, unsigned int src_cnt,
+ unsigned int bytes);
+
void __init xor_register(struct xor_block_template *tmpl);
void __init xor_force(struct xor_block_template *tmpl);
--
2.47.3
