linux/debian/patches/features/all/rt/rtmutex-add-a-first-shot-of...

425 lines
12 KiB
Diff

From: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Date: Mon, 28 Oct 2013 09:36:37 +0100
Subject: rtmutex: Add RT aware ww locks
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.9/older/patches-4.9-rt1.tar.xz
lockdep says:
| --------------------------------------------------------------------------
| | Wound/wait tests |
| ---------------------
| ww api failures: ok | ok | ok |
| ww contexts mixing: ok | ok |
| finishing ww context: ok | ok | ok | ok |
| locking mismatches: ok | ok | ok |
| EDEADLK handling: ok | ok | ok | ok | ok | ok | ok | ok | ok | ok |
| spinlock nest unlocked: ok |
| -----------------------------------------------------
| |block | try |context|
| -----------------------------------------------------
| context: ok | ok | ok |
| try: ok | ok | ok |
| block: ok | ok | ok |
| spinlock: ok | ok | ok |
Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
---
kernel/locking/rtmutex.c | 251 ++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 226 insertions(+), 25 deletions(-)
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -21,6 +21,7 @@
#include <linux/sched/rt.h>
#include <linux/sched/deadline.h>
#include <linux/timer.h>
+#include <linux/ww_mutex.h>
#include "rtmutex_common.h"
@@ -1360,6 +1361,40 @@ EXPORT_SYMBOL(__rt_spin_lock_init);
#endif /* PREEMPT_RT_FULL */
+#ifdef CONFIG_PREEMPT_RT_FULL
+ static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+ struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx);
+
+ if (!hold_ctx)
+ return 0;
+
+ if (unlikely(ctx == hold_ctx))
+ return -EALREADY;
+
+ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
+ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+#ifdef CONFIG_DEBUG_MUTEXES
+ DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+ ctx->contending_lock = ww;
+#endif
+ return -EDEADLK;
+ }
+
+ return 0;
+}
+#else
+ static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+ BUG();
+ return 0;
+}
+
+#endif
+
static inline int
try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
struct rt_mutex_waiter *waiter)
@@ -1614,7 +1649,8 @@ void rt_mutex_adjust_pi(struct task_stru
static int __sched
__rt_mutex_slowlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- struct rt_mutex_waiter *waiter)
+ struct rt_mutex_waiter *waiter,
+ struct ww_acquire_ctx *ww_ctx)
{
int ret = 0;
@@ -1637,6 +1673,12 @@ static int __sched
break;
}
+ if (ww_ctx && ww_ctx->acquired > 0) {
+ ret = __mutex_lock_check_stamp(lock, ww_ctx);
+ if (ret)
+ break;
+ }
+
raw_spin_unlock_irq(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
@@ -1671,13 +1713,90 @@ static void rt_mutex_handle_deadlock(int
}
}
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+ struct ww_acquire_ctx *ww_ctx)
+{
+#ifdef CONFIG_DEBUG_MUTEXES
+ /*
+ * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+ * but released with a normal mutex_unlock in this call.
+ *
+ * This should never happen, always use ww_mutex_unlock.
+ */
+ DEBUG_LOCKS_WARN_ON(ww->ctx);
+
+ /*
+ * Not quite done after calling ww_acquire_done() ?
+ */
+ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+ if (ww_ctx->contending_lock) {
+ /*
+ * After -EDEADLK you tried to
+ * acquire a different ww_mutex? Bad!
+ */
+ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+ /*
+ * You called ww_mutex_lock after receiving -EDEADLK,
+ * but 'forgot' to unlock everything else first?
+ */
+ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+ ww_ctx->contending_lock = NULL;
+ }
+
+ /*
+ * Naughty, using a different class will lead to undefined behavior!
+ */
+ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+ ww_ctx->acquired++;
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+ struct ww_acquire_ctx *ww_ctx)
+{
+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+ struct rt_mutex_waiter *waiter, *n;
+
+ /*
+ * This branch gets optimized out for the common case,
+ * and is only important for ww_mutex_lock.
+ */
+ ww_mutex_lock_acquired(ww, ww_ctx);
+ ww->ctx = ww_ctx;
+
+ /*
+ * Give any possible sleeping processes the chance to wake up,
+ * so they can recheck if they have to back off.
+ */
+ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters,
+ tree_entry) {
+ /* XXX debug rt mutex waiter wakeup */
+
+ BUG_ON(waiter->lock != lock);
+ rt_mutex_wake_waiter(waiter);
+ }
+}
+
+#else
+
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+ struct ww_acquire_ctx *ww_ctx)
+{
+ BUG();
+}
+#endif
+
/*
* Slow path lock function:
*/
static int __sched
rt_mutex_slowlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- enum rtmutex_chainwalk chwalk)
+ enum rtmutex_chainwalk chwalk,
+ struct ww_acquire_ctx *ww_ctx)
{
struct rt_mutex_waiter waiter;
unsigned long flags;
@@ -1697,6 +1816,8 @@ rt_mutex_slowlock(struct rt_mutex *lock,
/* Try to acquire the lock again: */
if (try_to_take_rt_mutex(lock, current, NULL)) {
+ if (ww_ctx)
+ ww_mutex_account_lock(lock, ww_ctx);
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
return 0;
}
@@ -1711,13 +1832,23 @@ rt_mutex_slowlock(struct rt_mutex *lock,
if (likely(!ret))
/* sleep on the mutex */
- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
+ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
+ ww_ctx);
+ else if (ww_ctx) {
+ /* ww_mutex received EDEADLK, let it become EALREADY */
+ ret = __mutex_lock_check_stamp(lock, ww_ctx);
+ BUG_ON(!ret);
+ }
if (unlikely(ret)) {
__set_current_state(TASK_RUNNING);
if (rt_mutex_has_waiters(lock))
remove_waiter(lock, &waiter);
- rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+ /* ww_mutex want to report EDEADLK/EALREADY, let them */
+ if (!ww_ctx)
+ rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+ } else if (ww_ctx) {
+ ww_mutex_account_lock(lock, ww_ctx);
}
/*
@@ -1850,31 +1981,36 @@ static bool __sched rt_mutex_slowunlock(
*/
static inline int
rt_mutex_fastlock(struct rt_mutex *lock, int state,
+ struct ww_acquire_ctx *ww_ctx,
int (*slowfn)(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- enum rtmutex_chainwalk chwalk))
+ enum rtmutex_chainwalk chwalk,
+ struct ww_acquire_ctx *ww_ctx))
{
if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
rt_mutex_deadlock_account_lock(lock, current);
return 0;
} else
- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK,
+ ww_ctx);
}
static inline int
rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
enum rtmutex_chainwalk chwalk,
+ struct ww_acquire_ctx *ww_ctx,
int (*slowfn)(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- enum rtmutex_chainwalk chwalk))
+ enum rtmutex_chainwalk chwalk,
+ struct ww_acquire_ctx *ww_ctx))
{
if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
rt_mutex_deadlock_account_lock(lock, current);
return 0;
} else
- return slowfn(lock, state, timeout, chwalk);
+ return slowfn(lock, state, timeout, chwalk, ww_ctx);
}
static inline int
@@ -1921,7 +2057,7 @@ void __sched rt_mutex_lock(struct rt_mut
{
might_sleep();
- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
@@ -1938,7 +2074,7 @@ int __sched rt_mutex_lock_interruptible(
{
might_sleep();
- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
+ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
@@ -1951,7 +2087,7 @@ int rt_mutex_timed_futex_lock(struct rt_
might_sleep();
return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- RT_MUTEX_FULL_CHAINWALK,
+ RT_MUTEX_FULL_CHAINWALK, NULL,
rt_mutex_slowlock);
}
@@ -1970,7 +2106,7 @@ int __sched rt_mutex_lock_killable(struc
{
might_sleep();
- return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock);
+ return rt_mutex_fastlock(lock, TASK_KILLABLE, NULL, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
@@ -1994,6 +2130,7 @@ rt_mutex_timed_lock(struct rt_mutex *loc
return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
RT_MUTEX_MIN_CHAINWALK,
+ NULL,
rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
@@ -2248,7 +2385,7 @@ int rt_mutex_finish_proxy_lock(struct rt
set_current_state(TASK_INTERRUPTIBLE);
/* sleep on the mutex */
- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL);
if (unlikely(ret))
remove_waiter(lock, waiter);
@@ -2264,24 +2401,88 @@ int rt_mutex_finish_proxy_lock(struct rt
return ret;
}
-#ifdef CONFIG_PREEMPT_RT_FULL
-struct ww_mutex {
-};
-struct ww_acquire_ctx {
-};
-int __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
+static inline int
+ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
- BUG();
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+ unsigned tmp;
+
+ if (ctx->deadlock_inject_countdown-- == 0) {
+ tmp = ctx->deadlock_inject_interval;
+ if (tmp > UINT_MAX/4)
+ tmp = UINT_MAX;
+ else
+ tmp = tmp*2 + tmp + tmp/2;
+
+ ctx->deadlock_inject_interval = tmp;
+ ctx->deadlock_inject_countdown = tmp;
+ ctx->contending_lock = lock;
+
+ ww_mutex_unlock(lock);
+
+ return -EDEADLK;
+ }
+#endif
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(__ww_mutex_lock);
-int __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+int __sched
+__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
{
- BUG();
+ int ret;
+
+ might_sleep();
+
+ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
+ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx);
+ if (ret)
+ mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+ else if (!ret && ww_ctx->acquired > 1)
+ return ww_mutex_deadlock_injection(lock, ww_ctx);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
+
+int __sched
+__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+ int ret;
+
+ might_sleep();
+
+ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
+ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx);
+ if (ret)
+ mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+ else if (!ret && ww_ctx->acquired > 1)
+ return ww_mutex_deadlock_injection(lock, ww_ctx);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__ww_mutex_lock);
+
void __sched ww_mutex_unlock(struct ww_mutex *lock)
{
- BUG();
+ int nest = !!lock->ctx;
+
+ /*
+ * The unlocking fastpath is the 0->1 transition from 'locked'
+ * into 'unlocked' state:
+ */
+ if (nest) {
+#ifdef CONFIG_DEBUG_MUTEXES
+ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
+#endif
+ if (lock->ctx->acquired > 0)
+ lock->ctx->acquired--;
+ lock->ctx = NULL;
+ }
+
+ mutex_release(&lock->base.dep_map, nest, _RET_IP_);
+ rt_mutex_unlock(&lock->base.lock);
}
-EXPORT_SYMBOL_GPL(ww_mutex_unlock);
+EXPORT_SYMBOL(ww_mutex_unlock);
#endif