ARM: locks: prefetch the destination word for write prior to strex
The cost of changing a cacheline from shared to exclusive state can be
significant, especially when this is triggered by an exclusive store,
since it may result in having to retry the transaction.
This patch prefixes our {spin,read,write}_[try]lock implementations with
pldw instructions (on CPUs which support them) to try and grab the line
in exclusive state from the start. arch_rwlock_t is changed to avoid
using a volatile member, since this generates compiler warnings when
falling back on the __builtin_prefetch intrinsic which expects a const
void * argument.
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index e1ce452..4999007 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -5,7 +5,7 @@
#error SMP not supported on pre-ARMv6 CPUs
#endif
-#include <asm/processor.h>
+#include <linux/prefetch.h>
/*
* sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K
@@ -70,6 +70,7 @@
u32 newval;
arch_spinlock_t lockval;
+ prefetchw(&lock->slock);
__asm__ __volatile__(
"1: ldrex %0, [%3]\n"
" add %1, %0, %4\n"
@@ -93,6 +94,7 @@
unsigned long contended, res;
u32 slock;
+ prefetchw(&lock->slock);
do {
__asm__ __volatile__(
" ldrex %0, [%3]\n"
@@ -145,6 +147,7 @@
{
unsigned long tmp;
+ prefetchw(&rw->lock);
__asm__ __volatile__(
"1: ldrex %0, [%1]\n"
" teq %0, #0\n"
@@ -163,6 +166,7 @@
{
unsigned long contended, res;
+ prefetchw(&rw->lock);
do {
__asm__ __volatile__(
" ldrex %0, [%2]\n"
@@ -196,7 +200,7 @@
}
/* write_can_lock - would write_trylock() succeed? */
-#define arch_write_can_lock(x) ((x)->lock == 0)
+#define arch_write_can_lock(x) (ACCESS_ONCE((x)->lock) == 0)
/*
* Read locks are a bit more hairy:
@@ -214,6 +218,7 @@
{
unsigned long tmp, tmp2;
+ prefetchw(&rw->lock);
__asm__ __volatile__(
"1: ldrex %0, [%2]\n"
" adds %0, %0, #1\n"
@@ -234,6 +239,7 @@
smp_mb();
+ prefetchw(&rw->lock);
__asm__ __volatile__(
"1: ldrex %0, [%2]\n"
" sub %0, %0, #1\n"
@@ -252,6 +258,7 @@
{
unsigned long contended, res;
+ prefetchw(&rw->lock);
do {
__asm__ __volatile__(
" ldrex %0, [%2]\n"
@@ -273,7 +280,7 @@
}
/* read_can_lock - would read_trylock() succeed? */
-#define arch_read_can_lock(x) ((x)->lock < 0x80000000)
+#define arch_read_can_lock(x) (ACCESS_ONCE((x)->lock) < 0x80000000)
#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)