Merge tag 'locking-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking and atomics updates from Thomas Gleixner:
 "The regular pile:

   - A few improvements to the mutex code

   - Documentation updates for atomics to clarify the difference between
     cmpxchg() and try_cmpxchg() and to explain the forward progress
     expectations.

   - Simplification of the atomics fallback generator

   - The addition of arch_atomic_long*() variants and generic arch_*()
     bitops based on them.

   - Add the missing might_sleep() invocations to the down*() operations
     of semaphores.

  The PREEMPT_RT locking core:

   - Scheduler updates to support the state preserving mechanism for
     'sleeping' spin- and rwlocks on RT.

     This mechanism is carefully preserving the state of the task when
     blocking on a 'sleeping' spin- or rwlock and takes regular wake-ups
     targeted at the same task into account. The preserved or updated
     (via a regular wakeup) state is restored when the lock has been
     acquired.

   - Restructuring of the rtmutex code so it can be utilized and
     extended for the RT specific lock variants.

   - Restructuring of the ww_mutex code to allow sharing of the ww_mutex
     specific functionality for rtmutex based ww_mutexes.

   - Header file disentangling to allow substitution of the regular lock
     implementations with the PREEMPT_RT variants without creating an
     unmaintainable #ifdef mess.

   - Shared base code for the PREEMPT_RT specific rw_semaphore and
     rwlock implementations.

     Contrary to the regular rw_semaphores and rwlocks the PREEMPT_RT
     implementation is writer unfair because it is infeasible to do
     priority inheritance on multiple readers. Experience over the years
     has shown that real-time workloads are not the typical workloads
     which are sensitive to writer starvation.

     The alternative solution would be to allow only a single reader
     which has been tried and discarded as it is a major bottleneck
     especially for mmap_sem. Aside of that many of the writer
     starvation critical usage sites have been converted to a writer
     side mutex/spinlock and RCU read side protections in the past
     decade so that the issue is less prominent than it used to be.

   - The actual rtmutex based lock substitutions for PREEMPT_RT enabled
     kernels which affect mutex, ww_mutex, rw_semaphore, spinlock_t and
     rwlock_t. The spin/rw_lock*() functions disable migration across
     the critical section to preserve the existing semantics vs per-CPU
     variables.

   - Rework of the futex REQUEUE_PI mechanism to handle the case of
     early wake-ups which interleave with a re-queue operation to
     prevent the situation that a task would be blocked on both the
     rtmutex associated to the outer futex and the rtmutex based hash
     bucket spinlock.

     While this situation cannot happen on !RT enabled kernels the
     changes make the underlying concurrency problems easier to
     understand in general. As a result the difference between !RT and
     RT kernels is reduced to the handling of waiting for the critical
     section. !RT kernels simply spin-wait as before and RT kernels
     utilize rcu_wait().

   - The substitution of local_lock for PREEMPT_RT with a spinlock which
     protects the critical section while staying preemptible. The CPU
     locality is established by disabling migration.

  The underlying concepts of this code have been in use in PREEMPT_RT for
  way more than a decade. The code has been refactored several times over
  the years and this final incarnation has been optimized once again to be
  as non-intrusive as possible, i.e. the RT specific parts are mostly
  isolated.

  It has been extensively tested in the 5.14-rt patch series and it has
  been verified that !RT kernels are not affected by these changes"

* tag 'locking-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (92 commits)
  locking/rtmutex: Return success on deadlock for ww_mutex waiters
  locking/rtmutex: Prevent spurious EDEADLK return caused by ww_mutexes
  locking/rtmutex: Dequeue waiter on ww_mutex deadlock
  locking/rtmutex: Dont dereference waiter lockless
  locking/semaphore: Add might_sleep() to down_*() family
  locking/ww_mutex: Initialize waiter.ww_ctx properly
  static_call: Update API documentation
  locking/local_lock: Add PREEMPT_RT support
  locking/spinlock/rt: Prepare for RT local_lock
  locking/rtmutex: Add adaptive spinwait mechanism
  locking/rtmutex: Implement equal priority lock stealing
  preempt: Adjust PREEMPT_LOCK_OFFSET for RT
  locking/rtmutex: Prevent lockdep false positive with PI futexes
  futex: Prevent requeue_pi() lock nesting issue on RT
  futex: Simplify handle_early_requeue_pi_wakeup()
  futex: Reorder sanity checks in futex_requeue()
  futex: Clarify comment in futex_requeue()
  futex: Restructure futex_requeue()
  futex: Correct the number of requeued waiters for PI
  futex: Remove bogus condition for requeue PI
  ...

1 files changed, 263 insertions, 0 deletions

diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c
new file mode 100644
index 000000000000..d2912e44d61f
--- /dev/null
+++ b/kernel/locking/spinlock_rt.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PREEMPT_RT substitution for spin/rw_locks
+ *
+ * spinlocks and rwlocks on RT are based on rtmutexes, with a few twists to
+ * resemble the non RT semantics:
+ *
+ * - Contrary to plain rtmutexes, spinlocks and rwlocks are state
+ *   preserving. The task state is saved before blocking on the underlying
+ *   rtmutex, and restored when the lock has been acquired. Regular wakeups
+ *   during that time are redirected to the saved state so no wake up is
+ *   missed.
+ *
+ * - Non RT spin/rwlocks disable preemption and eventually interrupts.
+ *   Disabling preemption has the side effect of disabling migration and
+ *   preventing RCU grace periods.
+ *
+ *   The RT substitutions explicitly disable migration and take
+ *   rcu_read_lock() across the lock held section.
+ */
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#define RT_MUTEX_BUILD_SPINLOCKS
+#include "rtmutex.c"
+
+static __always_inline void rtlock_lock(struct rt_mutex_base *rtm)
+{
+	if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
+		rtlock_slowlock(rtm);
+}
+
+static __always_inline void __rt_spin_lock(spinlock_t *lock)
+{
+	___might_sleep(__FILE__, __LINE__, 0);
+	rtlock_lock(&lock->lock);
+	rcu_read_lock();
+	migrate_disable();
+}
+
+void __sched rt_spin_lock(spinlock_t *lock)
+{
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	__rt_spin_lock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __sched rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	__rt_spin_lock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock_nested);
+
+void __sched rt_spin_lock_nest_lock(spinlock_t *lock,
+				    struct lockdep_map *nest_lock)
+{
+	spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+	__rt_spin_lock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock_nest_lock);
+#endif
+
+void __sched rt_spin_unlock(spinlock_t *lock)
+{
+	spin_release(&lock->dep_map, _RET_IP_);
+	migrate_enable();
+	rcu_read_unlock();
+
+	if (unlikely(!rt_mutex_cmpxchg_release(&lock->lock, current, NULL)))
+		rt_mutex_slowunlock(&lock->lock);
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __sched rt_spin_lock_unlock(spinlock_t *lock)
+{
+	spin_lock(lock);
+	spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock_unlock);
+
+static __always_inline int __rt_spin_trylock(spinlock_t *lock)
+{
+	int ret = 1;
+
+	if (unlikely(!rt_mutex_cmpxchg_acquire(&lock->lock, NULL, current)))
+		ret = rt_mutex_slowtrylock(&lock->lock);
+
+	if (ret) {
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+		migrate_disable();
+	}
+	return ret;
+}
+
+int __sched rt_spin_trylock(spinlock_t *lock)
+{
+	return __rt_spin_trylock(lock);
+}
+EXPORT_SYMBOL(rt_spin_trylock);
+
+int __sched rt_spin_trylock_bh(spinlock_t *lock)
+{
+	int ret;
+
+	local_bh_disable();
+	ret = __rt_spin_trylock(lock);
+	if (!ret)
+		local_bh_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_bh);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __rt_spin_lock_init(spinlock_t *lock, const char *name,
+			 struct lock_class_key *key, bool percpu)
+{
+	u8 type = percpu ? LD_LOCK_PERCPU : LD_LOCK_NORMAL;
+
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map_type(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG,
+			      LD_WAIT_INV, type);
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+#endif
+
+/*
+ * RT-specific reader/writer locks
+ */
+#define rwbase_set_and_save_current_state(state)	\
+	current_save_and_set_rtlock_wait_state()
+
+#define rwbase_restore_current_state()			\
+	current_restore_rtlock_saved_state()
+
+static __always_inline int
+rwbase_rtmutex_lock_state(struct rt_mutex_base *rtm, unsigned int state)
+{
+	if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
+		rtlock_slowlock(rtm);
+	return 0;
+}
+
+static __always_inline int
+rwbase_rtmutex_slowlock_locked(struct rt_mutex_base *rtm, unsigned int state)
+{
+	rtlock_slowlock_locked(rtm);
+	return 0;
+}
+
+static __always_inline void rwbase_rtmutex_unlock(struct rt_mutex_base *rtm)
+{
+	if (likely(rt_mutex_cmpxchg_acquire(rtm, current, NULL)))
+		return;
+
+	rt_mutex_slowunlock(rtm);
+}
+
+static __always_inline int  rwbase_rtmutex_trylock(struct rt_mutex_base *rtm)
+{
+	if (likely(rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
+		return 1;
+
+	return rt_mutex_slowtrylock(rtm);
+}
+
+#define rwbase_signal_pending_state(state, current)	(0)
+
+#define rwbase_schedule()				\
+	schedule_rtlock()
+
+#include "rwbase_rt.c"
+/*
+ * The common functions which get wrapped into the rwlock API.
+ */
+int __sched rt_read_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	ret = rwbase_read_trylock(&rwlock->rwbase);
+	if (ret) {
+		rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+		migrate_disable();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_read_trylock);
+
+int __sched rt_write_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	ret = rwbase_write_trylock(&rwlock->rwbase);
+	if (ret) {
+		rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+		migrate_disable();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock);
+
+void __sched rt_read_lock(rwlock_t *rwlock)
+{
+	___might_sleep(__FILE__, __LINE__, 0);
+	rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
+	rwbase_read_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+	rcu_read_lock();
+	migrate_disable();
+}
+EXPORT_SYMBOL(rt_read_lock);
+
+void __sched rt_write_lock(rwlock_t *rwlock)
+{
+	___might_sleep(__FILE__, __LINE__, 0);
+	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+	rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+	rcu_read_lock();
+	migrate_disable();
+}
+EXPORT_SYMBOL(rt_write_lock);
+
+void __sched rt_read_unlock(rwlock_t *rwlock)
+{
+	rwlock_release(&rwlock->dep_map, _RET_IP_);
+	migrate_enable();
+	rcu_read_unlock();
+	rwbase_read_unlock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+}
+EXPORT_SYMBOL(rt_read_unlock);
+
+void __sched rt_write_unlock(rwlock_t *rwlock)
+{
+	rwlock_release(&rwlock->dep_map, _RET_IP_);
+	rcu_read_unlock();
+	migrate_enable();
+	rwbase_write_unlock(&rwlock->rwbase);
+}
+EXPORT_SYMBOL(rt_write_unlock);
+
+int __sched rt_rwlock_is_contended(rwlock_t *rwlock)
+{
+	return rw_base_is_contended(&rwlock->rwbase);
+}
+EXPORT_SYMBOL(rt_rwlock_is_contended);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __rt_rwlock_init(rwlock_t *rwlock, const char *name,
+		      struct lock_class_key *key)
+{
+	debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock));
+	lockdep_init_map_wait(&rwlock->dep_map, name, key, 0, LD_WAIT_CONFIG);
+}
+EXPORT_SYMBOL(__rt_rwlock_init);
+#endif