2002-01-10 09:57:48

by Rainer Keller

[permalink] [raw]
Subject: Small optimizations for UP (sched and prefetch)

diff -ru linux-2.4.17/include/asm-i386/processor.h linux-2.4.17-mine/include/asm-i386/processor.h
--- linux-2.4.17/include/asm-i386/processor.h Thu Nov 22 20:46:19 2001
+++ linux-2.4.17-mine/include/asm-i386/processor.h Wed Jan 9 19:38:45 2002
@@ -478,8 +478,8 @@

#define cpu_relax() rep_nop()

-/* Prefetch instructions for Pentium III and AMD Athlon */
-#ifdef CONFIG_MPENTIUMIII
+/* Prefetch instructions for Pentium III, Pentium 4 and AMD Athlon */
+#if defined(CONFIG_MPENTIUMIII) || defined(CONFIG_MPENTIUM4)

#define ARCH_HAS_PREFETCH
extern inline void prefetch(const void *x)
@@ -502,7 +502,12 @@
{
__asm__ __volatile__ ("prefetchw (%0)" : : "r"(x));
}
-#define spin_lock_prefetch(x) prefetchw(x)
+
+#ifndef CONFIG_SMP
+#define spin_lock_prefetch(x)
+#else
+#define spin_lock_prefetch(x) prefetchw(x)
+#endif

#endif

diff -ru linux-2.4.17/include/linux/prefetch.h linux-2.4.17-mine/include/linux/prefetch.h
--- linux-2.4.17/include/linux/prefetch.h Thu Nov 22 20:46:19 2001
+++ linux-2.4.17-mine/include/linux/prefetch.h Wed Jan 9 19:37:31 2002
@@ -10,6 +10,7 @@
#ifndef _LINUX_PREFETCH_H
#define _LINUX_PREFETCH_H

+#include <linux/config.h>
#include <asm/processor.h>
#include <asm/cache.h>

@@ -26,7 +27,9 @@

prefetch(x) - prefetches the cacheline at "x" for read
prefetchw(x) - prefetches the cacheline at "x" for write
- spin_lock_prefetch(x) - prefectches the spinlock *x for taking
+ spin_lock_prefetch(x) - prefetches the spinlock *x for taking,
+ if on SMP, otherwise not needed
+ (except for debugging reasons -- slow anyway).

there is also PREFETCH_STRIDE which is the architecure-prefered
"lookahead" size for prefetching streamed operations.
@@ -50,7 +53,11 @@

#ifndef ARCH_HAS_SPINLOCK_PREFETCH
#define ARCH_HAS_SPINLOCK_PREFETCH
+#ifndef CONFIG_SMP
+#define spin_lock_prefetch(x)
+#else
#define spin_lock_prefetch(x) prefetchw(x)
+#endif
#endif

#ifndef PREFETCH_STRIDE
diff -ru linux-2.4.17/kernel/sched.c linux-2.4.17-mine/kernel/sched.c
--- linux-2.4.17/kernel/sched.c Fri Dec 21 18:42:04 2001
+++ linux-2.4.17-mine/kernel/sched.c Thu Jan 10 10:24:16 2002
@@ -117,11 +117,13 @@
#define idle_task(cpu) (init_tasks[cpu_number_map(cpu)])
#define can_schedule(p,cpu) \
((p)->cpus_runnable & (p)->cpus_allowed & (1 << cpu))
+#define processor_of_tsk(tsk) (tsk)->processor

#else

#define idle_task(cpu) (&init_task)
#define can_schedule(p,cpu) (1)
+#define processor_of_tsk(tsk) 0

#endif

@@ -172,7 +174,7 @@
#ifdef CONFIG_SMP
/* Give a largish advantage to the same processor... */
/* (this is equivalent to penalizing other processors) */
- if (p->processor == this_cpu)
+ if (processor_of_tsk(p) == this_cpu)
weight += PROC_CHANGE_PENALTY;
#endif

@@ -221,7 +223,7 @@
* shortcut if the woken up task's last CPU is
* idle now.
*/
- best_cpu = p->processor;
+ best_cpu = processor_of_tsk(p);
if (can_schedule(p, best_cpu)) {
tsk = idle_task(best_cpu);
if (cpu_curr(best_cpu) == tsk) {
@@ -295,18 +297,18 @@
tsk = target_tsk;
if (tsk) {
if (oldest_idle != -1ULL) {
- best_cpu = tsk->processor;
+ best_cpu = processor_of_tsk(tsk);
goto send_now_idle;
}
tsk->need_resched = 1;
- if (tsk->processor != this_cpu)
- smp_send_reschedule(tsk->processor);
+ if (processor_of_tsk(tsk) != this_cpu)
+ smp_send_reschedule(processor_of_tsk(tsk));
}
return;


#else /* UP */
- int this_cpu = smp_processor_id();
+ const int this_cpu = smp_processor_id();
struct task_struct *tsk;

tsk = cpu_curr(this_cpu);
@@ -559,7 +561,7 @@
if (!current->active_mm) BUG();
need_resched_back:
prev = current;
- this_cpu = prev->processor;
+ this_cpu = processor_of_tsk(prev);

if (unlikely(in_interrupt())) {
printk("Scheduling in interrupt\n");


Attachments:
patch_prefetch_sched.diff (3.73 kB)

2002-01-10 10:57:40

by Arjan van de Ven

[permalink] [raw]
Subject: Re: Small optimizations for UP (sched and prefetch)

> +
> +#ifndef CONFIG_SMP
> +#define spin_lock_prefetch(x)
> +#else
> +#define spin_lock_prefetch(x) prefetchw(x)
> +#endif
>

please make it
+#define spin_lock_prefetch(x) do {} while (0)

instead of an empty define...