summaryrefslogtreecommitdiff
path: root/kernel/locking
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/locking')
-rw-r--r--kernel/locking/lockdep.c39
-rw-r--r--kernel/locking/lockdep_internals.h18
-rw-r--r--kernel/locking/lockdep_proc.c2
-rw-r--r--kernel/locking/mutex-debug.c9
-rw-r--r--kernel/locking/mutex.c22
-rw-r--r--kernel/locking/mutex.h3
-rw-r--r--kernel/locking/rtmutex_api.c18
-rw-r--r--kernel/locking/rwsem.c35
-rw-r--r--kernel/locking/ww_mutex.h16
9 files changed, 114 insertions, 48 deletions
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dd2bbf73718b..2d4c5bab5af8 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -297,33 +297,30 @@ static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
dst->nr += src->nr;
}
-struct lock_class_stats lock_stats(struct lock_class *class)
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats)
{
- struct lock_class_stats stats;
int cpu, i;
- memset(&stats, 0, sizeof(struct lock_class_stats));
+ memset(stats, 0, sizeof(struct lock_class_stats));
for_each_possible_cpu(cpu) {
struct lock_class_stats *pcs =
&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
- for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
- stats.contention_point[i] += pcs->contention_point[i];
+ for (i = 0; i < ARRAY_SIZE(stats->contention_point); i++)
+ stats->contention_point[i] += pcs->contention_point[i];
- for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
- stats.contending_point[i] += pcs->contending_point[i];
+ for (i = 0; i < ARRAY_SIZE(stats->contending_point); i++)
+ stats->contending_point[i] += pcs->contending_point[i];
- lock_time_add(&pcs->read_waittime, &stats.read_waittime);
- lock_time_add(&pcs->write_waittime, &stats.write_waittime);
+ lock_time_add(&pcs->read_waittime, &stats->read_waittime);
+ lock_time_add(&pcs->write_waittime, &stats->write_waittime);
- lock_time_add(&pcs->read_holdtime, &stats.read_holdtime);
- lock_time_add(&pcs->write_holdtime, &stats.write_holdtime);
+ lock_time_add(&pcs->read_holdtime, &stats->read_holdtime);
+ lock_time_add(&pcs->write_holdtime, &stats->write_holdtime);
- for (i = 0; i < ARRAY_SIZE(stats.bounces); i++)
- stats.bounces[i] += pcs->bounces[i];
+ for (i = 0; i < ARRAY_SIZE(stats->bounces); i++)
+ stats->bounces[i] += pcs->bounces[i];
}
-
- return stats;
}
void clear_lock_stats(struct lock_class *class)
@@ -6619,8 +6616,16 @@ void lockdep_unregister_key(struct lock_class_key *key)
if (need_callback)
call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
- /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
- synchronize_rcu();
+ /*
+ * Wait until is_dynamic_key() has finished accessing k->hash_entry.
+ *
+ * Some operations like __qdisc_destroy() will call this in a debug
+ * kernel, and the network traffic is disabled while waiting, hence
+ * the delay of the wait matters in debugging cases. Currently use a
+ * synchronize_rcu_expedited() to speed up the wait at the cost of
+ * system IPIs. TODO: Replace RCU with hazptr for this.
+ */
+ synchronize_rcu_expedited();
}
EXPORT_SYMBOL_GPL(lockdep_unregister_key);
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 82156caf77d1..0e5e6ffe91a3 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -47,29 +47,31 @@ enum {
__LOCKF(USED_READ)
};
+enum {
#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE |
-static const unsigned long LOCKF_ENABLED_IRQ =
+ LOCKF_ENABLED_IRQ =
#include "lockdep_states.h"
- 0;
+ 0,
#undef LOCKDEP_STATE
#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE |
-static const unsigned long LOCKF_USED_IN_IRQ =
+ LOCKF_USED_IN_IRQ =
#include "lockdep_states.h"
- 0;
+ 0,
#undef LOCKDEP_STATE
#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE##_READ |
-static const unsigned long LOCKF_ENABLED_IRQ_READ =
+ LOCKF_ENABLED_IRQ_READ =
#include "lockdep_states.h"
- 0;
+ 0,
#undef LOCKDEP_STATE
#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE##_READ |
-static const unsigned long LOCKF_USED_IN_IRQ_READ =
+ LOCKF_USED_IN_IRQ_READ =
#include "lockdep_states.h"
- 0;
+ 0,
#undef LOCKDEP_STATE
+};
#define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ)
#define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ)
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index b52c07c4707c..1916db9aa46b 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -657,7 +657,7 @@ static int lock_stat_open(struct inode *inode, struct file *file)
if (!test_bit(idx, lock_classes_in_use))
continue;
iter->class = class;
- iter->stats = lock_stats(class);
+ lock_stats(class, &iter->stats);
iter++;
}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 6e6f6071cfa2..949103fd8e9b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -53,17 +53,18 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
{
lockdep_assert_held(&lock->wait_lock);
- /* Mark the current thread as blocked on the lock: */
- task->blocked_on = waiter;
+ /* Current thread can't be already blocked (since it's executing!) */
+ DEBUG_LOCKS_WARN_ON(__get_task_blocked_on(task));
}
void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
struct task_struct *task)
{
+ struct mutex *blocked_on = __get_task_blocked_on(task);
+
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
DEBUG_LOCKS_WARN_ON(waiter->task != task);
- DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
- task->blocked_on = NULL;
+ DEBUG_LOCKS_WARN_ON(blocked_on && blocked_on != lock);
INIT_LIST_HEAD(&waiter->list);
waiter->task = NULL;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index a39ecccbd106..de7d6702cd96 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -191,9 +191,7 @@ static void
__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
struct list_head *list)
{
-#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
hung_task_set_blocker(lock, BLOCKER_TYPE_MUTEX);
-#endif
debug_mutex_add_waiter(lock, waiter, current);
list_add_tail(&waiter->list, list);
@@ -209,9 +207,7 @@ __mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
__mutex_clear_flag(lock, MUTEX_FLAGS);
debug_mutex_remove_waiter(lock, waiter, current);
-#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
hung_task_clear_blocker();
-#endif
}
/*
@@ -644,6 +640,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
goto err_early_kill;
}
+ __set_task_blocked_on(current, lock);
set_current_state(state);
trace_contention_begin(lock, LCB_F_MUTEX);
for (;;) {
@@ -680,6 +677,12 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
first = __mutex_waiter_is_first(lock, &waiter);
+ /*
+ * As we likely have been woken up by task
+ * that has cleared our blocked_on state, re-set
+ * it to the lock we are trying to acquire.
+ */
+ set_task_blocked_on(current, lock);
set_current_state(state);
/*
* Here we order against unlock; we must either see it change
@@ -691,8 +694,15 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
if (first) {
trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+ /*
+ * mutex_optimistic_spin() can call schedule(), so
+ * clear blocked on so we don't become unselectable
+ * to run.
+ */
+ clear_task_blocked_on(current, lock);
if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
break;
+ set_task_blocked_on(current, lock);
trace_contention_begin(lock, LCB_F_MUTEX);
}
@@ -700,6 +710,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
}
raw_spin_lock_irqsave(&lock->wait_lock, flags);
acquired:
+ __clear_task_blocked_on(current, lock);
__set_current_state(TASK_RUNNING);
if (ww_ctx) {
@@ -729,9 +740,11 @@ skip_wait:
return 0;
err:
+ __clear_task_blocked_on(current, lock);
__set_current_state(TASK_RUNNING);
__mutex_remove_waiter(lock, &waiter);
err_early_kill:
+ WARN_ON(__get_task_blocked_on(current));
trace_contention_end(lock, ret);
raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
debug_mutex_free_waiter(&waiter);
@@ -942,6 +955,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
next = waiter->task;
debug_mutex_wake_waiter(lock, waiter);
+ __clear_task_blocked_on(next, lock);
wake_q_add(&wake_q, next);
}
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index cbff35b9b7ae..2e8080a9bee3 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -6,7 +6,7 @@
*
* Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*/
-
+#ifndef CONFIG_PREEMPT_RT
/*
* This is the control structure for tasks blocked on mutex, which resides
* on the blocked task's kernel stack:
@@ -70,3 +70,4 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
# define debug_mutex_unlock(lock) do { } while (0)
# define debug_mutex_init(lock, name, key) do { } while (0)
#endif /* !CONFIG_DEBUG_MUTEXES */
+#endif /* CONFIG_PREEMPT_RT */
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index 2d933528a0fa..bafd5af98eae 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -13,6 +13,24 @@
*/
int max_lock_depth = 1024;
+static const struct ctl_table rtmutex_sysctl_table[] = {
+ {
+ .procname = "max_lock_depth",
+ .data = &max_lock_depth,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+};
+
+static int __init init_rtmutex_sysctl(void)
+{
+ register_sysctl_init("kernel", rtmutex_sysctl_table);
+ return 0;
+}
+
+subsys_initcall(init_rtmutex_sysctl);
+
/*
* Debug aware fast / slowpath lock,trylock,unlock
*
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 2ddb827e3bea..24df4d98f7d2 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -27,6 +27,7 @@
#include <linux/export.h>
#include <linux/rwsem.h>
#include <linux/atomic.h>
+#include <linux/hung_task.h>
#include <trace/events/lock.h>
#ifndef CONFIG_PREEMPT_RT
@@ -181,11 +182,11 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
__rwsem_set_reader_owned(sem, current);
}
-#ifdef CONFIG_DEBUG_RWSEMS
+#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER)
/*
* Return just the real task structure pointer of the owner
*/
-static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+struct task_struct *rwsem_owner(struct rw_semaphore *sem)
{
return (struct task_struct *)
(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
@@ -194,7 +195,7 @@ static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
/*
* Return true if the rwsem is owned by a reader.
*/
-static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
+bool is_rwsem_reader_owned(struct rw_semaphore *sem)
{
/*
* Check the count to see if it is write-locked.
@@ -207,10 +208,10 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
}
/*
- * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
- * is a task pointer in owner of a reader-owned rwsem, it will be the
- * real owner or one of the real owners. The only exception is when the
- * unlock is done by up_read_non_owner().
+ * With CONFIG_DEBUG_RWSEMS or CONFIG_DETECT_HUNG_TASK_BLOCKER configured,
+ * it will make sure that the owner field of a reader-owned rwsem either
+ * points to a real reader-owner(s) or gets cleared. The only exception is
+ * when the unlock is done by up_read_non_owner().
*/
static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
{
@@ -727,8 +728,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
return ret;
}
-#define OWNER_SPINNABLE (OWNER_NULL | OWNER_WRITER | OWNER_READER)
-
static inline enum owner_state
rwsem_owner_state(struct task_struct *owner, unsigned long flags)
{
@@ -835,7 +834,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
enum owner_state owner_state;
owner_state = rwsem_spin_on_owner(sem);
- if (!(owner_state & OWNER_SPINNABLE))
+ if (owner_state == OWNER_NONSPINNABLE)
break;
/*
@@ -1065,10 +1064,13 @@ queue:
wake_up_q(&wake_q);
trace_contention_begin(sem, LCB_F_READ);
+ set_current_state(state);
+
+ if (state == TASK_UNINTERRUPTIBLE)
+ hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_READER);
/* wait to be given the lock */
for (;;) {
- set_current_state(state);
if (!smp_load_acquire(&waiter.task)) {
/* Matches rwsem_mark_wake()'s smp_store_release(). */
break;
@@ -1083,8 +1085,12 @@ queue:
}
schedule_preempt_disabled();
lockevent_inc(rwsem_sleep_reader);
+ set_current_state(state);
}
+ if (state == TASK_UNINTERRUPTIBLE)
+ hung_task_clear_blocker();
+
__set_current_state(TASK_RUNNING);
lockevent_inc(rwsem_rlock);
trace_contention_end(sem, 0);
@@ -1146,6 +1152,9 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
set_current_state(state);
trace_contention_begin(sem, LCB_F_WRITE);
+ if (state == TASK_UNINTERRUPTIBLE)
+ hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_WRITER);
+
for (;;) {
if (rwsem_try_write_lock(sem, &waiter)) {
/* rwsem_try_write_lock() implies ACQUIRE on success */
@@ -1179,6 +1188,10 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
trylock_again:
raw_spin_lock_irq(&sem->wait_lock);
}
+
+ if (state == TASK_UNINTERRUPTIBLE)
+ hung_task_clear_blocker();
+
__set_current_state(TASK_RUNNING);
raw_spin_unlock_irq(&sem->wait_lock);
lockevent_inc(rwsem_wlock);
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 37f025a096c9..086fd5487ca7 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -284,6 +284,12 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
#ifndef WW_RT
debug_mutex_wake_waiter(lock, waiter);
#endif
+ /*
+ * When waking up the task to die, be sure to clear the
+ * blocked_on pointer. Otherwise we can see circular
+ * blocked_on relationships that can't resolve.
+ */
+ __clear_task_blocked_on(waiter->task, lock);
wake_q_add(wake_q, waiter->task);
}
@@ -331,9 +337,15 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
* it's wounded in __ww_mutex_check_kill() or has a
* wakeup pending to re-read the wounded state.
*/
- if (owner != current)
+ if (owner != current) {
+ /*
+ * When waking up the task to wound, be sure to clear the
+ * blocked_on pointer. Otherwise we can see circular
+ * blocked_on relationships that can't resolve.
+ */
+ __clear_task_blocked_on(owner, lock);
wake_q_add(wake_q, owner);
-
+ }
return true;
}
generated by cgit (git 2.34.1) at 2025-08-04 15:14:55 +0000