| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20080221152712.4804.64576.stgit@novell1.haskins.net>
Date: Thu, 21 Feb 2008 10:27:12 -0500
From: Gregory Haskins <ghaskins@...ell.com>
To: mingo@...e.hu, a.p.zijlstra@...llo.nl, tglx@...utronix.de,
rostedt@...dmis.org, linux-rt-users@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, bill.huey@...il.com,
kevin@...man.org, cminyard@...sta.com, dsingleton@...sta.com,
dwalker@...sta.com, npiggin@...e.de, dsaxena@...xity.net,
ak@...e.de, gregkh@...e.de, sdietrich@...ell.com,
pmorreale@...ell.com, mkohari@...ell.com, ghaskins@...ell.com
Subject: [PATCH [RT] 09/14] adaptive mutexes
From: Peter W.Morreale <pmorreale@...ell.com>
This patch adds the adaptive spin lock busywait to rtmutexes. It adds
a new tunable: rtmutex_timeout, which is the companion to the
rtlock_timeout tunable.
Signed-off-by: Peter W. Morreale <pmorreale@...ell.com>
---
kernel/Kconfig.preempt | 37 +++++++++++++++++++++++++++++++++++++
kernel/rtmutex.c | 44 ++++++++++++++++++++++++++------------------
kernel/rtmutex_adaptive.h | 32 ++++++++++++++++++++++++++++++--
kernel/sysctl.c | 10 ++++++++++
4 files changed, 103 insertions(+), 20 deletions(-)
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index eebec19..d2b0daa 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -223,6 +223,43 @@ config RTLOCK_DELAY
tunable at runtime via a sysctl. A setting of 0 (zero) disables
the adaptive algorithm entirely.
+config ADAPTIVE_RTMUTEX
+ bool "Adaptive real-time mutexes"
+ default y
+ depends on ADAPTIVE_RTLOCK
+ help
+ This option adds the adaptive rtlock spin/sleep algorithm to
+ rtmutexes. In rtlocks, a significant gain in throughput
+ can be seen by allowing rtlocks to spin for a distinct
+ amount of time prior to going to sleep for deadlock avoidence.
+
+ Typically, mutexes are used when a critical section may need to
+ sleep due to a blocking operation. In the event the critical
+ section does not need to sleep, an additional gain in throughput
+ can be seen by avoiding the extra overhead of sleeping.
+
+ This option alters the rtmutex code to use an adaptive
+ spin/sleep algorithm. It will spin unless it determines it must
+ sleep to avoid deadlock. This offers a best of both worlds
+ solution since we achieve both high-throughput and low-latency.
+
+ If unsure, say Y
+
+config RTMUTEX_DELAY
+ int "Default delay (in loops) for adaptive mutexes"
+ range 0 10000000
+ depends on ADAPTIVE_RTMUTEX
+ default "3000"
+ help
+ This allows you to specify the maximum delay a task will use
+ to wait for a rt mutex before going to sleep. Note that that
+ although the delay is implemented as a preemptable loop, tasks
+ of like priority cannot preempt each other and this setting can
+ result in increased latencies.
+
+ The value is tunable at runtime via a sysctl. A setting of 0
+ (zero) disables the adaptive algorithm entirely.
+
config SPINLOCK_BKL
bool "Old-Style Big Kernel Lock"
depends on (PREEMPT || SMP) && !PREEMPT_RT
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 4a7423f..a7ed7b2 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -24,6 +24,10 @@
int rtlock_timeout __read_mostly = CONFIG_RTLOCK_DELAY;
#endif
+#ifdef CONFIG_ADAPTIVE_RTMUTEX
+int rtmutex_timeout __read_mostly = CONFIG_RTMUTEX_DELAY;
+#endif
+
/*
* lock->owner state tracking:
*
@@ -521,17 +525,16 @@ static void wakeup_next_waiter(struct rt_mutex *lock, int savestate)
* Do the wakeup before the ownership change to give any spinning
* waiter grantees a headstart over the other threads that will
* trigger once owner changes.
+ *
+ * This may appear to be a race, but the barriers close the
+ * window.
*/
- if (!savestate)
- wake_up_process(pendowner);
- else {
- smp_mb();
- /*
- * This may appear to be a race, but the barriers close the
- * window.
- */
- if ((pendowner->state != TASK_RUNNING)
- && (pendowner->state != TASK_RUNNING_MUTEX))
+ smp_mb();
+ if ((pendowner->state != TASK_RUNNING)
+ && (pendowner->state != TASK_RUNNING_MUTEX)) {
+ if (!savestate)
+ wake_up_process(pendowner);
+ else
wake_up_process_mutex(pendowner);
}
@@ -764,7 +767,7 @@ rt_spin_lock_slowlock(struct rt_mutex *lock)
debug_rt_mutex_print_deadlock(&waiter);
/* adaptive_wait() returns 1 if we need to sleep */
- if (adaptive_wait(lock, &waiter, &adaptive)) {
+ if (adaptive_wait(lock, 0, &waiter, &adaptive)) {
update_current(TASK_UNINTERRUPTIBLE, &saved_state);
if (waiter.task)
schedule_rt_mutex(lock);
@@ -975,6 +978,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
int ret = 0, saved_lock_depth = -1;
struct rt_mutex_waiter waiter;
unsigned long flags;
+ DECLARE_ADAPTIVE_MUTEX_WAITER(adaptive);
debug_rt_mutex_init_waiter(&waiter);
waiter.task = NULL;
@@ -995,8 +999,6 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
if (unlikely(current->lock_depth >= 0))
saved_lock_depth = rt_release_bkl(lock, flags);
- set_current_state(state);
-
/* Setup the timer, when timeout != NULL */
if (unlikely(timeout))
hrtimer_start(&timeout->timer, timeout->timer.expires,
@@ -1049,6 +1051,9 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
if (unlikely(ret))
break;
}
+
+ mutex_prepare_adaptive_wait(lock, &adaptive);
+
saved_flags = current->flags & PF_NOSCHED;
current->flags &= ~PF_NOSCHED;
@@ -1056,17 +1061,20 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
debug_rt_mutex_print_deadlock(&waiter);
- if (waiter.task)
- schedule_rt_mutex(lock);
+ if (mutex_adaptive_wait(lock,
+ (state == TASK_INTERRUPTIBLE),
+ &waiter, &adaptive)) {
+ set_current_state(state);
+ if (waiter.task)
+ schedule_rt_mutex(lock);
+ set_current_state(TASK_RUNNING);
+ }
spin_lock_irq(&lock->wait_lock);
current->flags |= saved_flags;
- set_current_state(state);
}
- set_current_state(TASK_RUNNING);
-
if (unlikely(waiter.task))
remove_waiter(lock, &waiter, flags);
diff --git a/kernel/rtmutex_adaptive.h b/kernel/rtmutex_adaptive.h
index b7e282b..72f8def 100644
--- a/kernel/rtmutex_adaptive.h
+++ b/kernel/rtmutex_adaptive.h
@@ -56,7 +56,8 @@ struct adaptive_waiter {
*
*/
static inline int
-adaptive_wait(struct rt_mutex *lock, struct rt_mutex_waiter *waiter,
+adaptive_wait(struct rt_mutex *lock, int interruptible,
+ struct rt_mutex_waiter *waiter,
struct adaptive_waiter *adaptive)
{
int sleep = 0;
@@ -77,6 +78,14 @@ adaptive_wait(struct rt_mutex *lock, struct rt_mutex_waiter *waiter,
if (adaptive->owner != rt_mutex_owner(lock))
break;
+#ifdef CONFIG_ADAPTIVE_RTMUTEX
+ /*
+ * Mutexes may need to check for signals...
+ */
+ if (interruptible && signal_pending(current))
+ break;
+#endif
+
/*
* If we got here, presumably the lock ownership is still
* current. We will use it to our advantage to be able to
@@ -132,10 +141,29 @@ extern int rtlock_timeout;
#define DECLARE_ADAPTIVE_WAITER(name)
-#define adaptive_wait(lock, waiter, busy) 1
+#define adaptive_wait(lock, intr, waiter, busy) 1
#define prepare_adaptive_wait(lock, busy) {}
#endif /* CONFIG_ADAPTIVE_RTLOCK */
+#ifdef CONFIG_ADAPTIVE_RTMUTEX
+
+#define mutex_adaptive_wait adaptive_wait
+#define mutex_prepare_adaptive_wait prepare_adaptive_wait
+
+extern int rtmutex_timeout;
+
+#define DECLARE_ADAPTIVE_MUTEX_WAITER(name) \
+ struct adaptive_waiter name = { .owner = NULL, \
+ .timeout = rtmutex_timeout, }
+
+#else
+
+#define DECLARE_ADAPTIVE_MUTEX_WAITER(name)
+
+#define mutex_adaptive_wait(lock, intr, waiter, busy) 1
+#define mutex_prepare_adaptive_wait(lock, busy) {}
+
+#endif /* CONFIG_ADAPTIVE_RTMUTEX */
#endif /* __KERNEL_RTMUTEX_ADAPTIVE_H */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 36259e4..3465af2 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -976,6 +976,16 @@ static struct ctl_table kern_table[] = {
.proc_handler = &proc_dointvec,
},
#endif
+#ifdef CONFIG_ADAPTIVE_RTMUTEX
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "rtmutex_timeout",
+ .data = &rtmutex_timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+#endif
#ifdef CONFIG_PROC_FS
{
.ctl_name = CTL_UNNUMBERED,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists