Merge tag 'locking-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Thomas Gleixner:

 - Move futex code into kernel/futex/ and split up the kitchen sink into
   seperate files to make integration of sys_futex_waitv() simpler.

 - Add a new sys_futex_waitv() syscall which allows to wait on multiple
   futexes.

   The main use case is emulating Windows' WaitForMultipleObjects which
   allows Wine to improve the performance of Windows Games. Also native
   Linux games can benefit from this interface as this is a common wait
   pattern for this kind of applications.

 - Add context to ww_mutex_trylock() to provide a path for i915 to
   rework their eviction code step by step without making lockdep upset
   until the final steps of rework are completed. It's also useful for
   regulator and TTM to avoid dropping locks in the non contended path.

 - Lockdep and might_sleep() cleanups and improvements

 - A few improvements for the RT substitutions.

 - The usual small improvements and cleanups.

* tag 'locking-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  locking: Remove spin_lock_flags() etc
  locking/rwsem: Fix comments about reader optimistic lock stealing conditions
  locking: Remove rcu_read_{,un}lock() for preempt_{dis,en}able()
  locking/rwsem: Disable preemption for spinning region
  docs: futex: Fix kernel-doc references
  futex: Fix PREEMPT_RT build
  futex2: Documentation: Document sys_futex_waitv() uAPI
  selftests: futex: Test sys_futex_waitv() wouldblock
  selftests: futex: Test sys_futex_waitv() timeout
  selftests: futex: Add sys_futex_waitv() test
  futex,arm: Wire up sys_futex_waitv()
  futex,x86: Wire up sys_futex_waitv()
  futex: Implement sys_futex_waitv()
  futex: Simplify double_lock_hb()
  futex: Split out wait/wake
  futex: Split out requeue
  futex: Rename mark_wake_futex()
  futex: Rename: match_futex()
  futex: Rename: hb_waiter_{inc,dec,pending}()
  futex: Split out PI futex
  ...

1 files changed, 56 insertions, 7 deletions

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d456579d0952..db1913611192 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -94,6 +94,9 @@ static inline unsigned long __owner_flags(unsigned long owner)
 	return owner & MUTEX_FLAGS;
 }
 
+/*
+ * Returns: __mutex_owner(lock) on failure or NULL on success.
+ */
 static inline struct task_struct *__mutex_trylock_common(struct mutex *lock, bool handoff)
 {
 	unsigned long owner, curr = (unsigned long)current;
@@ -348,13 +351,16 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
 {
 	bool ret = true;
 
-	rcu_read_lock();
+	lockdep_assert_preemption_disabled();
+
 	while (__mutex_owner(lock) == owner) {
 		/*
 		 * Ensure we emit the owner->on_cpu, dereference _after_
-		 * checking lock->owner still matches owner. If that fails,
-		 * owner might point to freed memory. If it still matches,
-		 * the rcu_read_lock() ensures the memory stays valid.
+		 * checking lock->owner still matches owner. And we already
+		 * disabled preemption which is equal to the RCU read-side
+		 * crital section in optimistic spinning code. Thus the
+		 * task_strcut structure won't go away during the spinning
+		 * period
 		 */
 		barrier();
 
@@ -374,7 +380,6 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
 
 		cpu_relax();
 	}
-	rcu_read_unlock();
 
 	return ret;
 }
@@ -387,19 +392,25 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 	struct task_struct *owner;
 	int retval = 1;
 
+	lockdep_assert_preemption_disabled();
+
 	if (need_resched())
 		return 0;
 
-	rcu_read_lock();
+	/*
+	 * We already disabled preemption which is equal to the RCU read-side
+	 * crital section in optimistic spinning code. Thus the task_strcut
+	 * structure won't go away during the spinning period.
+	 */
 	owner = __mutex_owner(lock);
 
 	/*
 	 * As lock holder preemption issue, we both skip spinning if task is not
 	 * on cpu or its cpu is preempted
 	 */
+
 	if (owner)
 		retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-	rcu_read_unlock();
 
 	/*
 	 * If lock->owner is not set, the mutex has been released. Return true
@@ -736,6 +747,44 @@ __ww_mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass,
 	return __mutex_lock_common(lock, state, subclass, NULL, ip, ww_ctx, true);
 }
 
+/**
+ * ww_mutex_trylock - tries to acquire the w/w mutex with optional acquire context
+ * @ww: mutex to lock
+ * @ww_ctx: optional w/w acquire context
+ *
+ * Trylocks a mutex with the optional acquire context; no deadlock detection is
+ * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise.
+ *
+ * Unlike ww_mutex_lock, no deadlock handling is performed. However, if a @ctx is
+ * specified, -EALREADY handling may happen in calls to ww_mutex_trylock.
+ *
+ * A mutex acquired with this function must be released with ww_mutex_unlock.
+ */
+int ww_mutex_trylock(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
+{
+	if (!ww_ctx)
+		return mutex_trylock(&ww->base);
+
+	MUTEX_WARN_ON(ww->base.magic != &ww->base);
+
+	/*
+	 * Reset the wounded flag after a kill. No other process can
+	 * race and wound us here, since they can't have a valid owner
+	 * pointer if we don't have any locks held.
+	 */
+	if (ww_ctx->acquired == 0)
+		ww_ctx->wounded = 0;
+
+	if (__mutex_trylock(&ww->base)) {
+		ww_mutex_set_context_fastpath(ww, ww_ctx);
+		mutex_acquire_nest(&ww->base.dep_map, 0, 1, &ww_ctx->dep_map, _RET_IP_);
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ww_mutex_trylock);
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void __sched
 mutex_lock_nested(struct mutex *lock, unsigned int subclass)