From: Christoph Lameter <clameter@sgi.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: linux-kernel@vger.kernel.org, Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: Spinlocks: Factor our GENERIC_LOCKBREAK in order to avoid spin with irqs disable
Date: Wed, 7 May 2008 11:49:49 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0805071148240.8441@schroedinger.engr.sgi.com> (raw)
In-Reply-To: <Pine.LNX.4.64.0805071022230.3173@schroedinger.engr.sgi.com>
Subject: Spinlocks: Factor our GENERIC_LOCKBREAK in order to avoid spin with irqs disabled
The nice spinlock functions that enable interrupts while spinning are only
usable if GENERIC_LOCKBREAK is set (and we do not debug locks but lock
debugging would not be used for a production configuration).
Factor out the dependencies on the ->lock_break field from the nice functions
into a set of BREAKLOCK macros (cannot be functions since the type of the lock
variable varies).
The nice spinlock function can then also be used if !GENERIC_LOCKBREAK
Signed-off-by: Christoph Lameter <clameter@sgi.com>
---
kernel/spinlock.c | 40 ++++++++++++++++++++++++++++++----------
1 file changed, 30 insertions(+), 10 deletions(-)
Index: linux-2.6/kernel/spinlock.c
===================================================================
--- linux-2.6.orig/kernel/spinlock.c 2008-05-07 11:19:31.000000000 -0700
+++ linux-2.6/kernel/spinlock.c 2008-05-07 11:40:56.000000000 -0700
@@ -65,7 +65,7 @@ EXPORT_SYMBOL(_write_trylock);
* even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
* not re-enabled during lock-acquire (which the preempt-spin-ops do):
*/
-#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
void __lockfunc _read_lock(rwlock_t *lock)
{
@@ -192,7 +192,7 @@ void __lockfunc _write_lock(rwlock_t *lo
EXPORT_SYMBOL(_write_lock);
-#else /* CONFIG_PREEMPT: */
+#else /* CONFIG_DEBUG_LOCK_ALLOC: */
/*
* This could be a long-held lock. We both prepare to spin for a long
@@ -201,6 +201,28 @@ EXPORT_SYMBOL(_write_lock);
*
* (We do this in a function because inlining it would be excessive.)
*/
+#ifdef CONFIG_GENERIC_LOCKBREAK
+
+#define BREAKLOCK(lock) (lock)->break_lock
+
+#define BREAKLOCK_ENABLE(lock) \
+do { \
+ if (!(lock)->break_lock) \
+ (lock)->break_lock = 1; \
+} while (0)
+
+#define BREAKLOCK_DISABLE(lock) \
+do { \
+ (lock)->break_lock = 0; \
+} while (0)
+
+#else
+
+#define BREAKLOCK(lock) 0
+#define BREAKLOCK_ENABLE(lock) do { } while (0)
+#define BREAKLOCK_DISABLE(lock) do { } while (0)
+
+#endif
#define BUILD_LOCK_OPS(op, locktype) \
void __lockfunc _##op##_lock(locktype##_t *lock) \
@@ -211,12 +233,11 @@ void __lockfunc _##op##_lock(locktype##_
break; \
preempt_enable(); \
\
- if (!(lock)->break_lock) \
- (lock)->break_lock = 1; \
- while (!op##_can_lock(lock) && (lock)->break_lock) \
+ BREAKLOCK_ENABLE(lock); \
+ while (!op##_can_lock(lock) && BREAKLOCK(lock)) \
_raw_##op##_relax(&lock->raw_lock); \
} \
- (lock)->break_lock = 0; \
+ BREAKLOCK_DISABLE(lock); \
} \
\
EXPORT_SYMBOL(_##op##_lock); \
@@ -233,12 +254,11 @@ unsigned long __lockfunc _##op##_lock_ir
local_irq_restore(flags); \
preempt_enable(); \
\
- if (!(lock)->break_lock) \
- (lock)->break_lock = 1; \
- while (!op##_can_lock(lock) && (lock)->break_lock) \
+ BREAKLOCK_ENABLE(lock); \
+ while (!op##_can_lock(lock) && BREAKLOCK(lock)) \
_raw_##op##_relax(&lock->raw_lock); \
} \
- (lock)->break_lock = 0; \
+ BREAKLOCK_DISABLE(lock); \
return flags; \
} \
\
next prev parent reply other threads:[~2008-05-07 18:50 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-06 19:26 Spinlocks waiting with interrupts disabled / preempt disabled Christoph Lameter
2008-05-07 7:30 ` Ingo Molnar
2008-05-07 17:04 ` Christoph Lameter
2008-05-07 17:24 ` Christoph Lameter
2008-05-07 18:49 ` Christoph Lameter [this message]
2008-05-09 10:26 ` Spinlocks: Factor our GENERIC_LOCKBREAK in order to avoid spin with irqs disable Ingo Molnar
2008-05-09 16:28 ` Christoph Lameter
2008-06-23 17:19 ` Petr Tesarik
2008-06-23 17:54 ` Peter Zijlstra
2008-06-23 18:20 ` Christoph Lameter
2008-06-23 20:39 ` Peter Zijlstra
2008-06-23 20:45 ` Christoph Lameter
2008-06-23 20:58 ` Peter Zijlstra
2008-06-26 2:51 ` Jeremy Fitzhardinge
2008-06-26 6:51 ` Peter Zijlstra
2008-06-26 15:49 ` Jeremy Fitzhardinge
2008-06-26 9:17 ` Petr Tesarik
2008-06-26 17:02 ` Christoph Lameter
2008-06-26 17:48 ` Peter Zijlstra
2008-07-07 11:50 ` Nick Piggin
2008-07-07 11:52 ` Nick Piggin
2008-07-07 15:56 ` Jeremy Fitzhardinge
2008-07-08 2:08 ` Nick Piggin
2008-07-07 15:53 ` Jeremy Fitzhardinge
2008-07-07 19:46 ` Rik van Riel
2008-07-07 20:14 ` Jeremy Fitzhardinge
2008-07-08 2:07 ` Nick Piggin
2008-07-08 5:57 ` Jeremy Fitzhardinge
2008-07-08 8:41 ` Nick Piggin
2008-07-08 15:58 ` Jeremy Fitzhardinge
2008-05-09 16:35 ` Spinlocks waiting with interrupts disabled / preempt disabled Olaf Weber
2008-05-09 17:56 ` Peter Zijlstra
2008-05-09 18:00 ` Christoph Lameter
2008-05-09 18:06 ` Peter Zijlstra
2008-05-09 20:01 ` Olaf Weber
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=Pine.LNX.4.64.0805071148240.8441@schroedinger.engr.sgi.com \
--to=clameter@sgi.com \
--cc=a.p.zijlstra@chello.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
/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
all inboxes | Powered by JetHome®