19 files changed, 157 insertions, 119 deletions

diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 760158d9d98d..392c7f23af76 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Any varying coverage in these files is non-deterministic
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 44c8d0d17170..9776da8db180 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -47,7 +47,6 @@
 #include <linux/stringify.h>
 #include <linux/bitops.h>
 #include <linux/gfp.h>
-#include <linux/kmemcheck.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
 
@@ -76,6 +75,19 @@ module_param(lock_stat, int, 0644);
 #define lock_stat 0
 #endif
 
+#ifdef CONFIG_BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK
+static int crossrelease_fullstack = 1;
+#else
+static int crossrelease_fullstack;
+#endif
+static int __init allow_crossrelease_fullstack(char *str)
+{
+	crossrelease_fullstack = 1;
+	return 0;
+}
+
+early_param("crossrelease_fullstack", allow_crossrelease_fullstack);
+
 /*
  * lockdep_lock: protects the lockdep graph, the hashes and the
  *               class/list/hash allocators.
@@ -1873,10 +1885,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	       struct held_lock *next, int distance, struct stack_trace *trace,
 	       int (*save)(struct stack_trace *trace))
 {
+	struct lock_list *uninitialized_var(target_entry);
 	struct lock_list *entry;
-	int ret;
 	struct lock_list this;
-	struct lock_list *uninitialized_var(target_entry);
+	int ret;
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1890,8 +1902,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	this.class = hlock_class(next);
 	this.parent = NULL;
 	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
-	if (unlikely(!ret))
+	if (unlikely(!ret)) {
+		if (!trace->entries) {
+			/*
+			 * If @save fails here, the printing might trigger
+			 * a WARN but because of the !nr_entries it should
+			 * not do bad things.
+			 */
+			save(trace);
+		}
 		return print_circular_bug(&this, target_entry, next, prev, trace);
+	}
 	else if (unlikely(ret < 0))
 		return print_bfs_bug(ret);
 
@@ -1938,7 +1959,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		return print_bfs_bug(ret);
 
 
-	if (save && !save(trace))
+	if (!trace->entries && !save(trace))
 		return 0;
 
 	/*
@@ -1958,20 +1979,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	if (!ret)
 		return 0;
 
-	/*
-	 * Debugging printouts:
-	 */
-	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
-		graph_unlock();
-		printk("\n new dependency: ");
-		print_lock_name(hlock_class(prev));
-		printk(KERN_CONT " => ");
-		print_lock_name(hlock_class(next));
-		printk(KERN_CONT "\n");
-		dump_stack();
-		if (!graph_lock())
-			return 0;
-	}
 	return 2;
 }
 
@@ -1986,8 +1993,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace;
-	int (*save)(struct stack_trace *trace) = save_trace;
+	struct stack_trace trace = {
+		.nr_entries = 0,
+		.max_entries = 0,
+		.entries = NULL,
+		.skip = 0,
+	};
 
 	/*
 	 * Debugging checks.
@@ -2018,18 +2029,11 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 			 */
 			if (hlock->read != 2 && hlock->check) {
 				int ret = check_prev_add(curr, hlock, next,
-							 distance, &trace, save);
+							 distance, &trace, save_trace);
 				if (!ret)
 					return 0;
 
 				/*
-				 * Stop saving stack_trace if save_trace() was
-				 * called at least once:
-				 */
-				if (save && ret == 2)
-					save = NULL;
-
-				/*
 				 * Stop after the first non-trylock entry,
 				 * as non-trylock entries have added their
 				 * own direct dependencies already, so this
@@ -3233,8 +3237,6 @@ static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
 {
 	int i;
 
-	kmemcheck_mark_initialized(lock, sizeof(*lock));
-
 	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
 		lock->class_cache[i] = NULL;
 
@@ -4871,8 +4873,14 @@ static void add_xhlock(struct held_lock *hlock)
 	xhlock->trace.nr_entries = 0;
 	xhlock->trace.max_entries = MAX_XHLOCK_TRACE_ENTRIES;
 	xhlock->trace.entries = xhlock->trace_entries;
-	xhlock->trace.skip = 3;
-	save_stack_trace(&xhlock->trace);
+
+	if (crossrelease_fullstack) {
+		xhlock->trace.skip = 3;
+		save_stack_trace(&xhlock->trace);
+	} else {
+		xhlock->trace.nr_entries = 1;
+		xhlock->trace.entries[0] = hlock->acquire_ip;
+	}
 }
 
 static inline int same_context_xhlock(struct hist_lock *xhlock)
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 1da4669d57a7..d459d624ba2a 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * kernel/lockdep_internals.h
  *
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 68d9e267ccd4..ad69bbc9bd28 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/lockdep_proc.c
  *
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 6a385aabcce7..f046b7ce9dd6 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * MCS lock defines
  *
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 4174417d5309..1edd3f45a4ec 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Mutexes: blocking mutual exclusion locks
  *
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 6ebc1902f779..1c2287d3fa71 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Mutexes: blocking mutual exclusion locks
  *
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index a74ee6abd039..6ef600aa0f47 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/osq_lock.h>
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 2655f26ec882..c7471c3fb798 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -23,49 +23,11 @@
 #include <linux/spinlock.h>
 #include <asm/qrwlock.h>
 
-/*
- * This internal data structure is used for optimizing access to some of
- * the subfields within the atomic_t cnts.
- */
-struct __qrwlock {
-	union {
-		atomic_t cnts;
-		struct {
-#ifdef __LITTLE_ENDIAN
-			u8 wmode;	/* Writer mode   */
-			u8 rcnts[3];	/* Reader counts */
-#else
-			u8 rcnts[3];	/* Reader counts */
-			u8 wmode;	/* Writer mode   */
-#endif
-		};
-	};
-	arch_spinlock_t	lock;
-};
-
-/**
- * rspin_until_writer_unlock - inc reader count & spin until writer is gone
- * @lock  : Pointer to queue rwlock structure
- * @writer: Current queue rwlock writer status byte
- *
- * In interrupt context or at the head of the queue, the reader will just
- * increment the reader count & wait until the writer releases the lock.
- */
-static __always_inline void
-rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
-{
-	while ((cnts & _QW_WMASK) == _QW_LOCKED) {
-		cpu_relax();
-		cnts = atomic_read_acquire(&lock->cnts);
-	}
-}
-
 /**
  * queued_read_lock_slowpath - acquire read lock of a queue rwlock
  * @lock: Pointer to queue rwlock structure
- * @cnts: Current qrwlock lock value
  */
-void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
+void queued_read_lock_slowpath(struct qrwlock *lock)
 {
 	/*
 	 * Readers come here when they cannot get the lock without waiting
@@ -73,13 +35,11 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
 	if (unlikely(in_interrupt())) {
 		/*
 		 * Readers in interrupt context will get the lock immediately
-		 * if the writer is just waiting (not holding the lock yet).
-		 * The rspin_until_writer_unlock() function returns immediately
-		 * in this case. Otherwise, they will spin (with ACQUIRE
-		 * semantics) until the lock is available without waiting in
-		 * the queue.
+		 * if the writer is just waiting (not holding the lock yet),
+		 * so spin with ACQUIRE semantics until the lock is available
+		 * without waiting in the queue.
 		 */
-		rspin_until_writer_unlock(lock, cnts);
+		atomic_cond_read_acquire(&lock->cnts, !(VAL & _QW_LOCKED));
 		return;
 	}
 	atomic_sub(_QR_BIAS, &lock->cnts);
@@ -88,14 +48,14 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
 	 * Put the reader into the wait queue
 	 */
 	arch_spin_lock(&lock->wait_lock);
+	atomic_add(_QR_BIAS, &lock->cnts);
 
 	/*
 	 * The ACQUIRE semantics of the following spinning code ensure
 	 * that accesses can't leak upwards out of our subsequent critical
 	 * section in the case that the lock is currently held for write.
 	 */
-	cnts = atomic_fetch_add_acquire(_QR_BIAS, &lock->cnts);
-	rspin_until_writer_unlock(lock, cnts);
+	atomic_cond_read_acquire(&lock->cnts, !(VAL & _QW_LOCKED));
 
 	/*
 	 * Signal the next one in queue to become queue head
@@ -110,8 +70,6 @@ EXPORT_SYMBOL(queued_read_lock_slowpath);
  */
 void queued_write_lock_slowpath(struct qrwlock *lock)
 {
-	u32 cnts;
-
 	/* Put the writer into the wait queue */
 	arch_spin_lock(&lock->wait_lock);
 
@@ -120,30 +78,14 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
 	    (atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0))
 		goto unlock;
 
-	/*
-	 * Set the waiting flag to notify readers that a writer is pending,
-	 * or wait for a previous writer to go away.
-	 */
-	for (;;) {
-		struct __qrwlock *l = (struct __qrwlock *)lock;
-
-		if (!READ_ONCE(l->wmode) &&
-		   (cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0))
-			break;
+	/* Set the waiting flag to notify readers that a writer is pending */
+	atomic_add(_QW_WAITING, &lock->cnts);
 
-		cpu_relax();
-	}
-
-	/* When no more readers, set the locked flag */
-	for (;;) {
-		cnts = atomic_read(&lock->cnts);
-		if ((cnts == _QW_WAITING) &&
-		    (atomic_cmpxchg_acquire(&lock->cnts, _QW_WAITING,
-					    _QW_LOCKED) == _QW_WAITING))
-			break;
-
-		cpu_relax();
-	}
+	/* When no more readers or writers, set the locked flag */
+	do {
+		atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING);
+	} while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING,
+					_QW_LOCKED) != _QW_WAITING);
 unlock:
 	arch_spin_unlock(&lock->wait_lock);
 }
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 43555681c40b..6ee477765e6c 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _GEN_PV_LOCK_SLOWPATH
 #error "do not include this file"
 #endif
@@ -60,21 +61,50 @@ struct pv_node {
 #include "qspinlock_stat.h"
 
 /*
+ * Hybrid PV queued/unfair lock
+ *
  * By replacing the regular queued_spin_trylock() with the function below,
  * it will be called once when a lock waiter enter the PV slowpath before
- * being queued. By allowing one lock stealing attempt here when the pending
- * bit is off, it helps to reduce the performance impact of lock waiter
- * preemption without the drawback of lock starvation.
+ * being queued.
+ *
+ * The pending bit is set by the queue head vCPU of the MCS wait queue in
+ * pv_wait_head_or_lock() to signal that it is ready to spin on the lock.
+ * When that bit becomes visible to the incoming waiters, no lock stealing
+ * is allowed. The function will return immediately to make the waiters
+ * enter the MCS wait queue. So lock starvation shouldn't happen as long
+ * as the queued mode vCPUs are actively running to set the pending bit
+ * and hence disabling lock stealing.
+ *
+ * When the pending bit isn't set, the lock waiters will stay in the unfair
+ * mode spinning on the lock unless the MCS wait queue is empty. In this
+ * case, the lock waiters will enter the queued mode slowpath trying to
+ * become the queue head and set the pending bit.
+ *
+ * This hybrid PV queued/unfair lock combines the best attributes of a
+ * queued lock (no lock starvation) and an unfair lock (good performance
+ * on not heavily contended locks).
  */
-#define queued_spin_trylock(l)	pv_queued_spin_steal_lock(l)
-static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
+#define queued_spin_trylock(l)	pv_hybrid_queued_unfair_trylock(l)
+static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 {
 	struct __qspinlock *l = (void *)lock;
 
-	if (!(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
-	    (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
-		qstat_inc(qstat_pv_lock_stealing, true);
-		return true;
+	/*
+	 * Stay in unfair lock mode as long as queued mode waiters are
+	 * present in the MCS wait queue but the pending bit isn't set.
+	 */
+	for (;;) {
+		int val = atomic_read(&lock->val);
+
+		if (!(val & _Q_LOCKED_PENDING_MASK) &&
+		   (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+			qstat_inc(qstat_pv_lock_stealing, true);
+			return true;
+		}
+		if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
+			break;
+
+		cpu_relax();
 	}
 
 	return false;
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index f4a74e78d467..fd4fe1f5b458 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 5078c6ddf4a5..fc549713bba3 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index 5c253caffe91..732f96abf462 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 7453be0485a5..124e98ca0b17 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 0848634c5512..a7ffb2a96ede 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* rwsem-spinlock.c: R/W semaphores: contention handling functions for
  * generic spinlock implementation
  *
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 02f660666ab8..e795908f3607 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* rwsem.c: R/W semaphores: contention handling functions
  *
  * Written by David Howells (dhowells@redhat.com).
@@ -613,6 +614,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 	DEFINE_WAKE_Q(wake_q);
 
 	/*
+	* __rwsem_down_write_failed_common(sem)
+	*   rwsem_optimistic_spin(sem)
+	*     osq_unlock(sem->osq)
+	*   ...
+	*   atomic_long_add_return(&sem->count)
+	*
+	*      - VS -
+	*
+	*              __up_write()
+	*                if (atomic_long_sub_return_release(&sem->count) < 0)
+	*                  rwsem_wake(sem)
+	*                    osq_is_locked(&sem->osq)
+	*
+	* And __up_write() must observe !osq_is_locked() when it observes the
+	* atomic_long_add_return() in order to not miss a wakeup.
+	*
+	* This boils down to:
+	*
+	* [S.rel] X = 1                [RmW] r0 = (Y += 0)
+	*         MB                         RMB
+	* [RmW]   Y += 1               [L]   r1 = X
+	*
+	* exists (r0=1 /\ r1=0)
+	*/
+	smp_rmb();
+
+	/*
 	 * If a spinner is present, it is not necessary to do the wakeup.
 	 * Try to do wakeup only if the trylock succeeds to minimize
 	 * spinlock contention which may introduce too much delay in the
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 4d48b1c4870d..f549c552dbf1 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* kernel/rwsem.c: R/W semaphores, public implementation
  *
  * Written by David Howells (dhowells@redhat.com).
@@ -28,6 +29,22 @@ void __sched down_read(struct rw_semaphore *sem)
 
 EXPORT_SYMBOL(down_read);
 
+int __sched down_read_killable(struct rw_semaphore *sem)
+{
+	might_sleep();
+	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
+
+	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
+		rwsem_release(&sem->dep_map, 1, _RET_IP_);
+		return -EINTR;
+	}
+
+	rwsem_set_reader_owned(sem);
+	return 0;
+}
+
+EXPORT_SYMBOL(down_read_killable);
+
 /*
  * trylock for reading -- returns 1 if successful, 0 if contention
  */
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index a699f4048ba1..a883b8f1fdc6 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * The owner field of the rw_semaphore structure will be set to
  * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 4b082b5cac9e..1fd1a7543cdd 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (2004) Linus Torvalds
  *
@@ -29,11 +30,10 @@
 #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
 /*
  * The __lock_function inlines are taken from
- * include/linux/spinlock_api_smp.h
+ * spinlock : include/linux/spinlock_api_smp.h
+ * rwlock   : include/linux/rwlock_api_smp.h
  */
 #else
-#define raw_read_can_lock(l)	read_can_lock(l)
-#define raw_write_can_lock(l)	write_can_lock(l)
 
 /*
  * Some architectures can relax in favour of the CPU owning the lock.
@@ -68,7 +68,7 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock)			\
 									\
 		if (!(lock)->break_lock)				\
 			(lock)->break_lock = 1;				\
-		while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\
+		while ((lock)->break_lock)				\
 			arch_##op##_relax(&lock->raw_lock);		\
 	}								\
 	(lock)->break_lock = 0;						\
@@ -88,7 +88,7 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock)	\
 									\
 		if (!(lock)->break_lock)				\
 			(lock)->break_lock = 1;				\
-		while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\
+		while ((lock)->break_lock)				\
 			arch_##op##_relax(&lock->raw_lock);		\
 	}								\
 	(lock)->break_lock = 0;						\