From: Gregory Haskins <ghaskins@novell.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: peterz@infradead.org, Lin Ming <ming.m.lin@intel.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
yanmin_zhang@linux.intel.com, mingo@elte.hu
Subject: [PATCH 1/4] revert "sched: sched_cacheflush is now unused"
Date: Thu, 04 Sep 2008 09:50:18 -0400 [thread overview]
Message-ID: <20080904135018.26109.74483.stgit@dev.haskins.net> (raw)
In-Reply-To: <20080904134959.26109.90529.stgit@dev.haskins.net>
revert c41917df8a1adde34864116ce2231a7fe308d2ff
Author: Ralf Baechle <ralf@linux-mips.org>
Date: Thu Jul 19 21:28:35 2007 +0200
[PATCH] sched: sched_cacheflush is now unused
Since Ingo's recent scheduler rewrite which was merged as commit
0437e109e1841607f2988891eaa36c531c6aa6ac sched_cacheflush is unused.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We want to restore sd->cache_hot_time for better migration decisions.
Signed-off-by: Gregory Haskins <ghaskins@novell.com>
---
arch/ia64/kernel/setup.c | 9 +++++++++
include/asm-m32r/system.h | 10 ++++++++++
include/asm-mips/system.h | 10 ++++++++++
include/asm-parisc/system.h | 11 +++++++++++
include/asm-x86/system.h | 9 +++++++++
5 files changed, 49 insertions(+), 0 deletions(-)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index c27d5b2..c0050ab 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -1051,6 +1051,15 @@ cpu_init (void)
pm_idle = default_idle;
}
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible.
+ */
+void sched_cacheflush(void)
+{
+ ia64_sal_cache_flush(3);
+}
+
void __init
check_bugs (void)
{
diff --git a/include/asm-m32r/system.h b/include/asm-m32r/system.h
index 70a57c8..d2f9559 100644
--- a/include/asm-m32r/system.h
+++ b/include/asm-m32r/system.h
@@ -54,6 +54,16 @@
); \
} while(0)
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible.
+ *
+ * TODO: fill this in!
+ */
+static inline void sched_cacheflush(void)
+{
+}
+
/* Interrupt Control */
#if !defined(CONFIG_CHIP_M32102) && !defined(CONFIG_CHIP_M32104)
#define local_irq_enable() \
diff --git a/include/asm-mips/system.h b/include/asm-mips/system.h
index a944eda..aaba821 100644
--- a/include/asm-mips/system.h
+++ b/include/asm-mips/system.h
@@ -78,6 +78,16 @@ do { \
write_c0_userlocal(current_thread_info()->tp_value); \
} while (0)
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible.
+ *
+ * TODO: fill this in!
+ */
+static inline void sched_cacheflush(void)
+{
+}
+
static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
{
__u32 retval;
diff --git a/include/asm-parisc/system.h b/include/asm-parisc/system.h
index ee80c92..21fbfc5 100644
--- a/include/asm-parisc/system.h
+++ b/include/asm-parisc/system.h
@@ -48,6 +48,17 @@ extern struct task_struct *_switch_to(struct task_struct *, struct task_struct *
(last) = _switch_to(prev, next); \
} while(0)
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible.
+ *
+ * TODO: fill this in!
+ */
+static inline void sched_cacheflush(void)
+{
+}
+
+
/* interrupt control */
#define local_save_flags(x) __asm__ __volatile__("ssm 0, %0" : "=r" (x) : : "memory")
#define local_irq_disable() __asm__ __volatile__("rsm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
index 983ce37..7847702 100644
--- a/include/asm-x86/system.h
+++ b/include/asm-x86/system.h
@@ -306,6 +306,15 @@ void enable_hlt(void);
void cpu_idle_wait(void);
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible:
+ */
+static inline void sched_cacheflush(void)
+{
+ wbinvd();
+}
+
extern unsigned long arch_align_stack(unsigned long sp);
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
next prev parent reply other threads:[~2008-09-04 13:53 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-09-04 8:51 oltp ~10% regression with 2.6.27-rc5 on stoakley machine Lin Ming
2008-09-04 9:03 ` Peter Zijlstra
2008-09-04 10:52 ` Lin Ming
2008-09-04 11:06 ` Peter Zijlstra
2008-09-04 12:12 ` Lin Ming
2008-09-04 12:26 ` Peter Zijlstra
2008-09-04 12:42 ` Lin Ming
2008-09-04 13:50 ` Gregory Haskins
2008-09-04 13:50 ` Gregory Haskins [this message]
2008-09-04 13:50 ` [PATCH 2/4] Revert "[PATCH] sched: remove cache_hot_time" Gregory Haskins
2008-09-04 13:50 ` [PATCH 3/4] Revert "sched: zap the migration init / cache-hot balancing code" Gregory Haskins
2008-09-04 13:50 ` [PATCH 4/4] sched: make task_hot() once again use sd->cache_hot_time Gregory Haskins
2008-09-04 11:09 ` oltp ~10% regression with 2.6.27-rc5 on stoakley machine Ingo Molnar
2008-09-04 11:30 ` Lin Ming
2008-09-04 11:35 ` Ingo Molnar
2008-09-04 12:19 ` Lin Ming
2008-09-05 1:26 ` Lin Ming
2008-09-20 21:38 ` Peter Zijlstra
2008-09-26 2:00 ` Lin Ming
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20080904135018.26109.74483.stgit@dev.haskins.net \
--to=ghaskins@novell.com \
--cc=a.p.zijlstra@chello.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.m.lin@intel.com \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=yanmin_zhang@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox