Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 392c7f2..45452fa 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -25,8 +25,7 @@
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
-obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
 obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
+obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o
diff --git a/kernel/locking/lock_events.c b/kernel/locking/lock_events.c
new file mode 100644
index 0000000..fa2c2f9
--- /dev/null
+++ b/kernel/locking/lock_events.c
@@ -0,0 +1,179 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <waiman.long@hpe.com>
+ */
+
+/*
+ * Collect locking event counts
+ */
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/fs.h>
+
+#include "lock_events.h"
+
+#undef  LOCK_EVENT
+#define LOCK_EVENT(name)	[LOCKEVENT_ ## name] = #name,
+
+#define LOCK_EVENTS_DIR		"lock_event_counts"
+
+/*
+ * When CONFIG_LOCK_EVENT_COUNTS is enabled, event counts of different
+ * types of locks will be reported under the <debugfs>/lock_event_counts/
+ * directory. See lock_events_list.h for the list of available locking
+ * events.
+ *
+ * Writing to the special ".reset_counts" file will reset all the above
+ * locking event counts. This is a very slow operation and so should not
+ * be done frequently.
+ *
+ * These event counts are implemented as per-cpu variables which are
+ * summed and computed whenever the corresponding debugfs files are read. This
+ * minimizes added overhead making the counts usable even in a production
+ * environment.
+ */
+static const char * const lockevent_names[lockevent_num + 1] = {
+
+#include "lock_events_list.h"
+
+	[LOCKEVENT_reset_cnts] = ".reset_counts",
+};
+
+/*
+ * Per-cpu counts
+ */
+DEFINE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * The lockevent_read() function can be overridden.
+ */
+ssize_t __weak lockevent_read(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	char buf[64];
+	int cpu, id, len;
+	u64 sum = 0;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	id = (long)file_inode(file)->i_private;
+
+	if (id >= lockevent_num)
+		return -EBADF;
+
+	for_each_possible_cpu(cpu)
+		sum += per_cpu(lockevents[id], cpu);
+	len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+/*
+ * Function to handle write request
+ *
+ * When idx = reset_cnts, reset all the counts.
+ */
+static ssize_t lockevent_write(struct file *file, const char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	int cpu;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	if ((long)file_inode(file)->i_private != LOCKEVENT_reset_cnts)
+		return count;
+
+	for_each_possible_cpu(cpu) {
+		int i;
+		unsigned long *ptr = per_cpu_ptr(lockevents, cpu);
+
+		for (i = 0 ; i < lockevent_num; i++)
+			WRITE_ONCE(ptr[i], 0);
+	}
+	return count;
+}
+
+/*
+ * Debugfs data structures
+ */
+static const struct file_operations fops_lockevent = {
+	.read = lockevent_read,
+	.write = lockevent_write,
+	.llseek = default_llseek,
+};
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#include <asm/paravirt.h>
+
+static bool __init skip_lockevent(const char *name)
+{
+	static int pv_on __initdata = -1;
+
+	if (pv_on < 0)
+		pv_on = !pv_is_native_spin_unlock();
+	/*
+	 * Skip PV qspinlock events on bare metal.
+	 */
+	if (!pv_on && !memcmp(name, "pv_", 3))
+		return true;
+	return false;
+}
+#else
+static inline bool skip_lockevent(const char *name)
+{
+	return false;
+}
+#endif
+
+/*
+ * Initialize debugfs for the locking event counts.
+ */
+static int __init init_lockevent_counts(void)
+{
+	struct dentry *d_counts = debugfs_create_dir(LOCK_EVENTS_DIR, NULL);
+	int i;
+
+	if (!d_counts)
+		goto out;
+
+	/*
+	 * Create the debugfs files
+	 *
+	 * As reading from and writing to the stat files can be slow, only
+	 * root is allowed to do the read/write to limit impact to system
+	 * performance.
+	 */
+	for (i = 0; i < lockevent_num; i++) {
+		if (skip_lockevent(lockevent_names[i]))
+			continue;
+		if (!debugfs_create_file(lockevent_names[i], 0400, d_counts,
+					 (void *)(long)i, &fops_lockevent))
+			goto fail_undo;
+	}
+
+	if (!debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200,
+				 d_counts, (void *)(long)LOCKEVENT_reset_cnts,
+				 &fops_lockevent))
+		goto fail_undo;
+
+	return 0;
+fail_undo:
+	debugfs_remove_recursive(d_counts);
+out:
+	pr_warn("Could not create '%s' debugfs entries\n", LOCK_EVENTS_DIR);
+	return -ENOMEM;
+}
+fs_initcall(init_lockevent_counts);
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
new file mode 100644
index 0000000..8c7e7d2
--- /dev/null
+++ b/kernel/locking/lock_events.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef __LOCKING_LOCK_EVENTS_H
+#define __LOCKING_LOCK_EVENTS_H
+
+enum lock_events {
+
+#include "lock_events_list.h"
+
+	lockevent_num,	/* Total number of lock event counts */
+	LOCKEVENT_reset_cnts = lockevent_num,
+};
+
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+/*
+ * Per-cpu counters
+ */
+DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * Increment the statistical counters. use raw_cpu_inc() because of lower
+ * overhead and we don't care if we loose the occasional update.
+ */
+static inline void __lockevent_inc(enum lock_events event, bool cond)
+{
+	if (cond)
+		raw_cpu_inc(lockevents[event]);
+}
+
+#define lockevent_inc(ev)	  __lockevent_inc(LOCKEVENT_ ##ev, true)
+#define lockevent_cond_inc(ev, c) __lockevent_inc(LOCKEVENT_ ##ev, c)
+
+static inline void __lockevent_add(enum lock_events event, int inc)
+{
+	raw_cpu_add(lockevents[event], inc);
+}
+
+#define lockevent_add(ev, c)	__lockevent_add(LOCKEVENT_ ##ev, c)
+
+#else  /* CONFIG_LOCK_EVENT_COUNTS */
+
+#define lockevent_inc(ev)
+#define lockevent_add(ev, c)
+#define lockevent_cond_inc(ev, c)
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
+#endif /* __LOCKING_LOCK_EVENTS_H */
diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
new file mode 100644
index 0000000..239039d
--- /dev/null
+++ b/kernel/locking/lock_events_list.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef LOCK_EVENT
+#define LOCK_EVENT(name)	LOCKEVENT_ ## name,
+#endif
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+/*
+ * Locking events for PV qspinlock.
+ */
+LOCK_EVENT(pv_hash_hops)	/* Average # of hops per hashing operation */
+LOCK_EVENT(pv_kick_unlock)	/* # of vCPU kicks issued at unlock time   */
+LOCK_EVENT(pv_kick_wake)	/* # of vCPU kicks for pv_latency_wake	   */
+LOCK_EVENT(pv_latency_kick)	/* Average latency (ns) of vCPU kick	   */
+LOCK_EVENT(pv_latency_wake)	/* Average latency (ns) of kick-to-wakeup  */
+LOCK_EVENT(pv_lock_stealing)	/* # of lock stealing operations	   */
+LOCK_EVENT(pv_spurious_wakeup)	/* # of spurious wakeups in non-head vCPUs */
+LOCK_EVENT(pv_wait_again)	/* # of wait's after queue head vCPU kick  */
+LOCK_EVENT(pv_wait_early)	/* # of early vCPU wait's		   */
+LOCK_EVENT(pv_wait_head)	/* # of vCPU wait's at the queue head	   */
+LOCK_EVENT(pv_wait_node)	/* # of vCPU wait's at non-head queue node */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+/*
+ * Locking events for qspinlock
+ *
+ * Subtracting lock_use_node[234] from lock_slowpath will give you
+ * lock_use_node1.
+ */
+LOCK_EVENT(lock_pending)	/* # of locking ops via pending code	     */
+LOCK_EVENT(lock_slowpath)	/* # of locking ops via MCS lock queue	     */
+LOCK_EVENT(lock_use_node2)	/* # of locking ops that use 2nd percpu node */
+LOCK_EVENT(lock_use_node3)	/* # of locking ops that use 3rd percpu node */
+LOCK_EVENT(lock_use_node4)	/* # of locking ops that use 4th percpu node */
+LOCK_EVENT(lock_no_node)	/* # of locking ops w/o using percpu node    */
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+/*
+ * Locking events for rwsem
+ */
+LOCK_EVENT(rwsem_sleep_reader)	/* # of reader sleeps			*/
+LOCK_EVENT(rwsem_sleep_writer)	/* # of writer sleeps			*/
+LOCK_EVENT(rwsem_wake_reader)	/* # of reader wakeups			*/
+LOCK_EVENT(rwsem_wake_writer)	/* # of writer wakeups			*/
+LOCK_EVENT(rwsem_opt_rlock)	/* # of opt-acquired read locks		*/
+LOCK_EVENT(rwsem_opt_wlock)	/* # of opt-acquired write locks	*/
+LOCK_EVENT(rwsem_opt_fail)	/* # of failed optspins			*/
+LOCK_EVENT(rwsem_opt_nospin)	/* # of disabled optspins		*/
+LOCK_EVENT(rwsem_opt_norspin)	/* # of disabled reader-only optspins	*/
+LOCK_EVENT(rwsem_opt_rlock2)	/* # of opt-acquired 2ndary read locks	*/
+LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
+LOCK_EVENT(rwsem_rlock_fast)	/* # of fast read locks acquired	*/
+LOCK_EVENT(rwsem_rlock_fail)	/* # of failed read lock acquisitions	*/
+LOCK_EVENT(rwsem_rlock_handoff)	/* # of read lock handoffs		*/
+LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
+LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
+LOCK_EVENT(rwsem_wlock_handoff)	/* # of write lock handoffs		*/
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 26b57e2..233459c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * kernel/lockdep.c
  *
@@ -45,11 +46,14 @@
 #include <linux/hash.h>
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
+#include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/gfp.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
 #include <linux/nmi.h>
+#include <linux/rcupdate.h>
+#include <linux/kprobes.h>
 
 #include <asm/sections.h>
 
@@ -81,6 +85,7 @@
  * code to recurse back into the lockdep code...
  */
 static arch_spinlock_t lockdep_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+static struct task_struct *lockdep_selftest_task_struct;
 
 static int graph_lock(void)
 {
@@ -130,26 +135,44 @@
 
 unsigned long nr_list_entries;
 static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
+static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
 
 /*
  * All data structures here are protected by the global debug_lock.
  *
- * Mutex key structs only get allocated, once during bootup, and never
- * get freed - this significantly simplifies the debugging code.
+ * nr_lock_classes is the number of elements of lock_classes[] that is
+ * in use.
  */
+#define KEYHASH_BITS		(MAX_LOCKDEP_KEYS_BITS - 1)
+#define KEYHASH_SIZE		(1UL << KEYHASH_BITS)
+static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
 unsigned long nr_lock_classes;
-static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+#ifndef CONFIG_DEBUG_LOCKDEP
+static
+#endif
+struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
 
 static inline struct lock_class *hlock_class(struct held_lock *hlock)
 {
-	if (!hlock->class_idx) {
+	unsigned int class_idx = hlock->class_idx;
+
+	/* Don't re-read hlock->class_idx, can't use READ_ONCE() on bitfield */
+	barrier();
+
+	if (!test_bit(class_idx, lock_classes_in_use)) {
 		/*
 		 * Someone passed in garbage, we give up.
 		 */
 		DEBUG_LOCKS_WARN_ON(1);
 		return NULL;
 	}
-	return lock_classes + hlock->class_idx - 1;
+
+	/*
+	 * At this point, if the passed hlock->class_idx is still garbage,
+	 * we just have to live with it
+	 */
+	return lock_classes + class_idx;
 }
 
 #ifdef CONFIG_LOCK_STAT
@@ -274,11 +297,42 @@
 #endif
 
 /*
- * We keep a global list of all lock classes. The list only grows,
- * never shrinks. The list is only accessed with the lockdep
- * spinlock lock held.
+ * We keep a global list of all lock classes. The list is only accessed with
+ * the lockdep spinlock lock held. free_lock_classes is a list with free
+ * elements. These elements are linked together by the lock_entry member in
+ * struct lock_class.
  */
 LIST_HEAD(all_lock_classes);
+static LIST_HEAD(free_lock_classes);
+
+/**
+ * struct pending_free - information about data structures about to be freed
+ * @zapped: Head of a list with struct lock_class elements.
+ * @lock_chains_being_freed: Bitmap that indicates which lock_chains[] elements
+ *	are about to be freed.
+ */
+struct pending_free {
+	struct list_head zapped;
+	DECLARE_BITMAP(lock_chains_being_freed, MAX_LOCKDEP_CHAINS);
+};
+
+/**
+ * struct delayed_free - data structures used for delayed freeing
+ *
+ * A data structure for delayed freeing of data structures that may be
+ * accessed by RCU readers at the time these were freed.
+ *
+ * @rcu_head:  Used to schedule an RCU callback for freeing data structures.
+ * @index:     Index of @pf to which freed data structures are added.
+ * @scheduled: Whether or not an RCU callback has been scheduled.
+ * @pf:        Array with information about data structures about to be freed.
+ */
+static struct delayed_free {
+	struct rcu_head		rcu_head;
+	int			index;
+	int			scheduled;
+	struct pending_free	pf[2];
+} delayed_free;
 
 /*
  * The lockdep classes are in a hash-table as well, for fast lookup:
@@ -316,6 +370,13 @@
 	return k0 | (u64)k1 << 32;
 }
 
+void lockdep_init_task(struct task_struct *task)
+{
+	task->lockdep_depth = 0; /* no locks held yet */
+	task->curr_chain_key = INITIAL_CHAIN_KEY;
+	task->lockdep_recursion = 0;
+}
+
 void lockdep_off(void)
 {
 	current->lockdep_recursion++;
@@ -328,6 +389,11 @@
 }
 EXPORT_SYMBOL(lockdep_on);
 
+void lockdep_set_selftest_task(struct task_struct *task)
+{
+	lockdep_selftest_task_struct = task;
+}
+
 /*
  * Debugging switches:
  */
@@ -371,13 +437,6 @@
 	return 0;
 }
 
-/*
- * Stack-trace: tightly packed array of stack backtrace
- * addresses. Protected by the graph_lock.
- */
-unsigned long nr_stack_trace_entries;
-static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
-
 static void print_lockdep_off(const char *bug_msg)
 {
 	printk(KERN_DEBUG "%s\n", bug_msg);
@@ -387,44 +446,107 @@
 #endif
 }
 
-static int save_trace(struct stack_trace *trace)
+unsigned long nr_stack_trace_entries;
+
+#ifdef CONFIG_PROVE_LOCKING
+/**
+ * struct lock_trace - single stack backtrace
+ * @hash_entry:	Entry in a stack_trace_hash[] list.
+ * @hash:	jhash() of @entries.
+ * @nr_entries:	Number of entries in @entries.
+ * @entries:	Actual stack backtrace.
+ */
+struct lock_trace {
+	struct hlist_node	hash_entry;
+	u32			hash;
+	u32			nr_entries;
+	unsigned long		entries[0] __aligned(sizeof(unsigned long));
+};
+#define LOCK_TRACE_SIZE_IN_LONGS				\
+	(sizeof(struct lock_trace) / sizeof(unsigned long))
+/*
+ * Stack-trace: sequence of lock_trace structures. Protected by the graph_lock.
+ */
+static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
+static struct hlist_head stack_trace_hash[STACK_TRACE_HASH_SIZE];
+
+static bool traces_identical(struct lock_trace *t1, struct lock_trace *t2)
 {
-	trace->nr_entries = 0;
-	trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
-	trace->entries = stack_trace + nr_stack_trace_entries;
+	return t1->hash == t2->hash && t1->nr_entries == t2->nr_entries &&
+		memcmp(t1->entries, t2->entries,
+		       t1->nr_entries * sizeof(t1->entries[0])) == 0;
+}
 
-	trace->skip = 3;
+static struct lock_trace *save_trace(void)
+{
+	struct lock_trace *trace, *t2;
+	struct hlist_head *hash_head;
+	u32 hash;
+	unsigned int max_entries;
 
-	save_stack_trace(trace);
+	BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE);
+	BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES);
 
-	/*
-	 * Some daft arches put -1 at the end to indicate its a full trace.
-	 *
-	 * <rant> this is buggy anyway, since it takes a whole extra entry so a
-	 * complete trace that maxes out the entries provided will be reported
-	 * as incomplete, friggin useless </rant>
-	 */
-	if (trace->nr_entries != 0 &&
-	    trace->entries[trace->nr_entries-1] == ULONG_MAX)
-		trace->nr_entries--;
+	trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries);
+	max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries -
+		LOCK_TRACE_SIZE_IN_LONGS;
+	trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
 
-	trace->max_entries = trace->nr_entries;
-
-	nr_stack_trace_entries += trace->nr_entries;
-
-	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
+	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES -
+	    LOCK_TRACE_SIZE_IN_LONGS - 1) {
 		if (!debug_locks_off_graph_unlock())
-			return 0;
+			return NULL;
 
 		print_lockdep_off("BUG: MAX_STACK_TRACE_ENTRIES too low!");
 		dump_stack();
 
-		return 0;
+		return NULL;
 	}
 
-	return 1;
+	hash = jhash(trace->entries, trace->nr_entries *
+		     sizeof(trace->entries[0]), 0);
+	trace->hash = hash;
+	hash_head = stack_trace_hash + (hash & (STACK_TRACE_HASH_SIZE - 1));
+	hlist_for_each_entry(t2, hash_head, hash_entry) {
+		if (traces_identical(trace, t2))
+			return t2;
+	}
+	nr_stack_trace_entries += LOCK_TRACE_SIZE_IN_LONGS + trace->nr_entries;
+	hlist_add_head(&trace->hash_entry, hash_head);
+
+	return trace;
 }
 
+/* Return the number of stack traces in the stack_trace[] array. */
+u64 lockdep_stack_trace_count(void)
+{
+	struct lock_trace *trace;
+	u64 c = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(stack_trace_hash); i++) {
+		hlist_for_each_entry(trace, &stack_trace_hash[i], hash_entry) {
+			c++;
+		}
+	}
+
+	return c;
+}
+
+/* Return the number of stack hash chains that have at least one stack trace. */
+u64 lockdep_stack_hash_count(void)
+{
+	u64 c = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(stack_trace_hash); i++)
+		if (!hlist_empty(&stack_trace_hash[i]))
+			c++;
+
+	return c;
+}
+#endif
+
 unsigned int nr_hardirq_chains;
 unsigned int nr_softirq_chains;
 unsigned int nr_process_chains;
@@ -437,6 +559,7 @@
 DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
 #endif
 
+#ifdef CONFIG_PROVE_LOCKING
 /*
  * Locking printouts:
  */
@@ -454,8 +577,9 @@
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
 };
+#endif
 
-const char * __get_key_name(struct lockdep_subclass_key *key, char *str)
+const char *__get_key_name(const struct lockdep_subclass_key *key, char *str)
 {
 	return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str);
 }
@@ -467,15 +591,26 @@
 
 static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit)
 {
+	/*
+	 * The usage character defaults to '.' (i.e., irqs disabled and not in
+	 * irq context), which is the safest usage category.
+	 */
 	char c = '.';
 
-	if (class->usage_mask & lock_flag(bit + 2))
+	/*
+	 * The order of the following usage checks matters, which will
+	 * result in the outcome character as follows:
+	 *
+	 * - '+': irq is enabled and not in irq context
+	 * - '-': in irq context and irq is disabled
+	 * - '?': in irq context and irq is enabled
+	 */
+	if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK)) {
 		c = '+';
-	if (class->usage_mask & lock_flag(bit)) {
-		c = '-';
-		if (class->usage_mask & lock_flag(bit + 2))
+		if (class->usage_mask & lock_flag(bit))
 			c = '?';
-	}
+	} else if (class->usage_mask & lock_flag(bit))
+		c = '-';
 
 	return c;
 }
@@ -539,19 +674,22 @@
 	/*
 	 * We can be called locklessly through debug_show_all_locks() so be
 	 * extra careful, the hlock might have been released and cleared.
+	 *
+	 * If this indeed happens, lets pretend it does not hurt to continue
+	 * to print the lock unless the hlock class_idx does not point to a
+	 * registered class. The rationale here is: since we don't attempt
+	 * to distinguish whether we are in this situation, if it just
+	 * happened we can't count on class_idx to tell either.
 	 */
-	unsigned int class_idx = hlock->class_idx;
+	struct lock_class *lock = hlock_class(hlock);
 
-	/* Don't re-read hlock->class_idx, can't use READ_ONCE() on bitfields: */
-	barrier();
-
-	if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) {
+	if (!lock) {
 		printk(KERN_CONT "<RELEASED>\n");
 		return;
 	}
 
-	printk(KERN_CONT "%p", hlock->instance);
-	print_lock_name(lock_classes + class_idx - 1);
+	printk(KERN_CONT "%px", hlock->instance);
+	print_lock_name(lock);
 	printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
 }
 
@@ -596,12 +734,15 @@
  * Is this the address of a static object:
  */
 #ifdef __KERNEL__
-static int static_obj(void *obj)
+static int static_obj(const void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
 		      end   = (unsigned long) &_end,
 		      addr  = (unsigned long) obj;
 
+	if (arch_is_kernel_initmem_freed(addr))
+		return 0;
+
 	/*
 	 * static variable?
 	 */
@@ -626,7 +767,8 @@
 
 /*
  * To make lock name printouts unique, we calculate a unique
- * class->name_version generation counter:
+ * class->name_version generation counter. The caller must hold the graph
+ * lock.
  */
 static int count_matching_names(struct lock_class *new_class)
 {
@@ -636,7 +778,7 @@
 	if (!new_class->name)
 		return 0;
 
-	list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
+	list_for_each_entry(class, &all_lock_classes, lock_entry) {
 		if (new_class->key - new_class->subclass == class->key)
 			return class->name_version;
 		if (class->name && !strcmp(class->name, new_class->name))
@@ -695,7 +837,8 @@
 			 * Huh! same key, different name? Did someone trample
 			 * on some memory? We're most confused.
 			 */
-			WARN_ON_ONCE(class->name != lock->name);
+			WARN_ON_ONCE(class->name != lock->name &&
+				     lock->key != &__lockdep_no_validate__);
 			return class;
 		}
 	}
@@ -712,6 +855,17 @@
 {
 	unsigned long can_addr, addr = (unsigned long)lock;
 
+#ifdef __KERNEL__
+	/*
+	 * lockdep_free_key_range() assumes that struct lock_class_key
+	 * objects do not overlap. Since we use the address of lock
+	 * objects as class key for static objects, check whether the
+	 * size of lock_class_key objects does not exceed the size of
+	 * the smallest lock object.
+	 */
+	BUILD_BUG_ON(sizeof(struct lock_class_key) > sizeof(raw_spinlock_t));
+#endif
+
 	if (__is_kernel_percpu_address(addr, &can_addr))
 		lock->key = (void *)can_addr;
 	else if (__is_module_percpu_address(addr, &can_addr))
@@ -731,6 +885,289 @@
 	return true;
 }
 
+#ifdef CONFIG_DEBUG_LOCKDEP
+
+/* Check whether element @e occurs in list @h */
+static bool in_list(struct list_head *e, struct list_head *h)
+{
+	struct list_head *f;
+
+	list_for_each(f, h) {
+		if (e == f)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Check whether entry @e occurs in any of the locks_after or locks_before
+ * lists.
+ */
+static bool in_any_class_list(struct list_head *e)
+{
+	struct lock_class *class;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+		class = &lock_classes[i];
+		if (in_list(e, &class->locks_after) ||
+		    in_list(e, &class->locks_before))
+			return true;
+	}
+	return false;
+}
+
+static bool class_lock_list_valid(struct lock_class *c, struct list_head *h)
+{
+	struct lock_list *e;
+
+	list_for_each_entry(e, h, entry) {
+		if (e->links_to != c) {
+			printk(KERN_INFO "class %s: mismatch for lock entry %ld; class %s <> %s",
+			       c->name ? : "(?)",
+			       (unsigned long)(e - list_entries),
+			       e->links_to && e->links_to->name ?
+			       e->links_to->name : "(?)",
+			       e->class && e->class->name ? e->class->name :
+			       "(?)");
+			return false;
+		}
+	}
+	return true;
+}
+
+#ifdef CONFIG_PROVE_LOCKING
+static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
+#endif
+
+static bool check_lock_chain_key(struct lock_chain *chain)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	u64 chain_key = INITIAL_CHAIN_KEY;
+	int i;
+
+	for (i = chain->base; i < chain->base + chain->depth; i++)
+		chain_key = iterate_chain_key(chain_key, chain_hlocks[i]);
+	/*
+	 * The 'unsigned long long' casts avoid that a compiler warning
+	 * is reported when building tools/lib/lockdep.
+	 */
+	if (chain->chain_key != chain_key) {
+		printk(KERN_INFO "chain %lld: key %#llx <> %#llx\n",
+		       (unsigned long long)(chain - lock_chains),
+		       (unsigned long long)chain->chain_key,
+		       (unsigned long long)chain_key);
+		return false;
+	}
+#endif
+	return true;
+}
+
+static bool in_any_zapped_class_list(struct lock_class *class)
+{
+	struct pending_free *pf;
+	int i;
+
+	for (i = 0, pf = delayed_free.pf; i < ARRAY_SIZE(delayed_free.pf); i++, pf++) {
+		if (in_list(&class->lock_entry, &pf->zapped))
+			return true;
+	}
+
+	return false;
+}
+
+static bool __check_data_structures(void)
+{
+	struct lock_class *class;
+	struct lock_chain *chain;
+	struct hlist_head *head;
+	struct lock_list *e;
+	int i;
+
+	/* Check whether all classes occur in a lock list. */
+	for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+		class = &lock_classes[i];
+		if (!in_list(&class->lock_entry, &all_lock_classes) &&
+		    !in_list(&class->lock_entry, &free_lock_classes) &&
+		    !in_any_zapped_class_list(class)) {
+			printk(KERN_INFO "class %px/%s is not in any class list\n",
+			       class, class->name ? : "(?)");
+			return false;
+		}
+	}
+
+	/* Check whether all classes have valid lock lists. */
+	for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+		class = &lock_classes[i];
+		if (!class_lock_list_valid(class, &class->locks_before))
+			return false;
+		if (!class_lock_list_valid(class, &class->locks_after))
+			return false;
+	}
+
+	/* Check the chain_key of all lock chains. */
+	for (i = 0; i < ARRAY_SIZE(chainhash_table); i++) {
+		head = chainhash_table + i;
+		hlist_for_each_entry_rcu(chain, head, entry) {
+			if (!check_lock_chain_key(chain))
+				return false;
+		}
+	}
+
+	/*
+	 * Check whether all list entries that are in use occur in a class
+	 * lock list.
+	 */
+	for_each_set_bit(i, list_entries_in_use, ARRAY_SIZE(list_entries)) {
+		e = list_entries + i;
+		if (!in_any_class_list(&e->entry)) {
+			printk(KERN_INFO "list entry %d is not in any class list; class %s <> %s\n",
+			       (unsigned int)(e - list_entries),
+			       e->class->name ? : "(?)",
+			       e->links_to->name ? : "(?)");
+			return false;
+		}
+	}
+
+	/*
+	 * Check whether all list entries that are not in use do not occur in
+	 * a class lock list.
+	 */
+	for_each_clear_bit(i, list_entries_in_use, ARRAY_SIZE(list_entries)) {
+		e = list_entries + i;
+		if (in_any_class_list(&e->entry)) {
+			printk(KERN_INFO "list entry %d occurs in a class list; class %s <> %s\n",
+			       (unsigned int)(e - list_entries),
+			       e->class && e->class->name ? e->class->name :
+			       "(?)",
+			       e->links_to && e->links_to->name ?
+			       e->links_to->name : "(?)");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+int check_consistency = 0;
+module_param(check_consistency, int, 0644);
+
+static void check_data_structures(void)
+{
+	static bool once = false;
+
+	if (check_consistency && !once) {
+		if (!__check_data_structures()) {
+			once = true;
+			WARN_ON(once);
+		}
+	}
+}
+
+#else /* CONFIG_DEBUG_LOCKDEP */
+
+static inline void check_data_structures(void) { }
+
+#endif /* CONFIG_DEBUG_LOCKDEP */
+
+/*
+ * Initialize the lock_classes[] array elements, the free_lock_classes list
+ * and also the delayed_free structure.
+ */
+static void init_data_structures_once(void)
+{
+	static bool ds_initialized, rcu_head_initialized;
+	int i;
+
+	if (likely(rcu_head_initialized))
+		return;
+
+	if (system_state >= SYSTEM_SCHEDULING) {
+		init_rcu_head(&delayed_free.rcu_head);
+		rcu_head_initialized = true;
+	}
+
+	if (ds_initialized)
+		return;
+
+	ds_initialized = true;
+
+	INIT_LIST_HEAD(&delayed_free.pf[0].zapped);
+	INIT_LIST_HEAD(&delayed_free.pf[1].zapped);
+
+	for (i = 0; i < ARRAY_SIZE(lock_classes); i++) {
+		list_add_tail(&lock_classes[i].lock_entry, &free_lock_classes);
+		INIT_LIST_HEAD(&lock_classes[i].locks_after);
+		INIT_LIST_HEAD(&lock_classes[i].locks_before);
+	}
+}
+
+static inline struct hlist_head *keyhashentry(const struct lock_class_key *key)
+{
+	unsigned long hash = hash_long((uintptr_t)key, KEYHASH_BITS);
+
+	return lock_keys_hash + hash;
+}
+
+/* Register a dynamically allocated key. */
+void lockdep_register_key(struct lock_class_key *key)
+{
+	struct hlist_head *hash_head;
+	struct lock_class_key *k;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(static_obj(key)))
+		return;
+	hash_head = keyhashentry(key);
+
+	raw_local_irq_save(flags);
+	if (!graph_lock())
+		goto restore_irqs;
+	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
+		if (WARN_ON_ONCE(k == key))
+			goto out_unlock;
+	}
+	hlist_add_head_rcu(&key->hash_entry, hash_head);
+out_unlock:
+	graph_unlock();
+restore_irqs:
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lockdep_register_key);
+
+/* Check whether a key has been registered as a dynamic key. */
+static bool is_dynamic_key(const struct lock_class_key *key)
+{
+	struct hlist_head *hash_head;
+	struct lock_class_key *k;
+	bool found = false;
+
+	if (WARN_ON_ONCE(static_obj(key)))
+		return false;
+
+	/*
+	 * If lock debugging is disabled lock_keys_hash[] may contain
+	 * pointers to memory that has already been freed. Avoid triggering
+	 * a use-after-free in that case by returning early.
+	 */
+	if (!debug_locks)
+		return true;
+
+	hash_head = keyhashentry(key);
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
+		if (k == key) {
+			found = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return found;
+}
+
 /*
  * Register a lock's class in the hash-table, if the class is not present
  * yet. Otherwise we look it up. We cache the result in the lock object
@@ -752,7 +1189,7 @@
 	if (!lock->key) {
 		if (!assign_lock_key(lock))
 			return NULL;
-	} else if (!static_obj(lock->key)) {
+	} else if (!static_obj(lock->key) && !is_dynamic_key(lock->key)) {
 		return NULL;
 	}
 
@@ -771,11 +1208,12 @@
 			goto out_unlock_set;
 	}
 
-	/*
-	 * Allocate a new key from the static array, and add it to
-	 * the hash:
-	 */
-	if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
+	init_data_structures_once();
+
+	/* Allocate a new lock class and add it to the hash. */
+	class = list_first_entry_or_null(&free_lock_classes, typeof(*class),
+					 lock_entry);
+	if (!class) {
 		if (!debug_locks_off_graph_unlock()) {
 			return NULL;
 		}
@@ -784,14 +1222,14 @@
 		dump_stack();
 		return NULL;
 	}
-	class = lock_classes + nr_lock_classes++;
+	nr_lock_classes++;
+	__set_bit(class - lock_classes, lock_classes_in_use);
 	debug_atomic_inc(nr_unused_locks);
 	class->key = key;
 	class->name = lock->name;
 	class->subclass = subclass;
-	INIT_LIST_HEAD(&class->lock_entry);
-	INIT_LIST_HEAD(&class->locks_before);
-	INIT_LIST_HEAD(&class->locks_after);
+	WARN_ON_ONCE(!list_empty(&class->locks_before));
+	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	class->name_version = count_matching_names(class);
 	/*
 	 * We use RCU's safe list-add method to make
@@ -799,9 +1237,10 @@
 	 */
 	hlist_add_head_rcu(&class->hash_entry, hash_head);
 	/*
-	 * Add it to the global list of classes:
+	 * Remove the class from the free list and add it to the global list
+	 * of classes.
 	 */
-	list_add_tail_rcu(&class->lock_entry, &all_lock_classes);
+	list_move_tail(&class->lock_entry, &all_lock_classes);
 
 	if (verbose(class)) {
 		graph_unlock();
@@ -842,7 +1281,10 @@
  */
 static struct lock_list *alloc_list_entry(void)
 {
-	if (nr_list_entries >= MAX_LOCKDEP_ENTRIES) {
+	int idx = find_first_zero_bit(list_entries_in_use,
+				      ARRAY_SIZE(list_entries));
+
+	if (idx >= ARRAY_SIZE(list_entries)) {
 		if (!debug_locks_off_graph_unlock())
 			return NULL;
 
@@ -850,15 +1292,18 @@
 		dump_stack();
 		return NULL;
 	}
-	return list_entries + nr_list_entries++;
+	nr_list_entries++;
+	__set_bit(idx, list_entries_in_use);
+	return list_entries + idx;
 }
 
 /*
  * Add a new dependency to the head of the list:
  */
-static int add_lock_to_list(struct lock_class *this, struct list_head *head,
+static int add_lock_to_list(struct lock_class *this,
+			    struct lock_class *links_to, struct list_head *head,
 			    unsigned long ip, int distance,
-			    struct stack_trace *trace)
+			    const struct lock_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -870,8 +1315,9 @@
 		return 0;
 
 	entry->class = this;
+	entry->links_to = links_to;
 	entry->distance = distance;
-	entry->trace = *trace;
+	entry->trace = trace;
 	/*
 	 * Both allocation and removal are done under the graph lock; but
 	 * iteration is under RCU-sched; see look_up_lock_class() and
@@ -889,13 +1335,17 @@
 #define CQ_MASK				(MAX_CIRCULAR_QUEUE_SIZE-1)
 
 /*
- * The circular_queue and helpers is used to implement the
- * breadth-first search(BFS)algorithem, by which we can build
- * the shortest path from the next lock to be acquired to the
- * previous held lock if there is a circular between them.
+ * The circular_queue and helpers are used to implement graph
+ * breadth-first search (BFS) algorithm, by which we can determine
+ * whether there is a path from a lock to another. In deadlock checks,
+ * a path from the next lock to be acquired to a previous held lock
+ * indicates that adding the <prev> -> <next> lock dependency will
+ * produce a circle in the graph. Breadth-first search instead of
+ * depth-first search is used in order to find the shortest (circular)
+ * path.
  */
 struct circular_queue {
-	unsigned long element[MAX_CIRCULAR_QUEUE_SIZE];
+	struct lock_list *element[MAX_CIRCULAR_QUEUE_SIZE];
 	unsigned int  front, rear;
 };
 
@@ -921,7 +1371,7 @@
 	return ((cq->rear + 1) & CQ_MASK) == cq->front;
 }
 
-static inline int __cq_enqueue(struct circular_queue *cq, unsigned long elem)
+static inline int __cq_enqueue(struct circular_queue *cq, struct lock_list *elem)
 {
 	if (__cq_full(cq))
 		return -1;
@@ -931,14 +1381,21 @@
 	return 0;
 }
 
-static inline int __cq_dequeue(struct circular_queue *cq, unsigned long *elem)
+/*
+ * Dequeue an element from the circular_queue, return a lock_list if
+ * the queue is not empty, or NULL if otherwise.
+ */
+static inline struct lock_list * __cq_dequeue(struct circular_queue *cq)
 {
-	if (__cq_empty(cq))
-		return -1;
+	struct lock_list * lock;
 
-	*elem = cq->element[cq->front];
+	if (__cq_empty(cq))
+		return NULL;
+
+	lock = cq->element[cq->front];
 	cq->front = (cq->front + 1) & CQ_MASK;
-	return 0;
+
+	return lock;
 }
 
 static inline unsigned int  __cq_get_elem_count(struct circular_queue *cq)
@@ -952,7 +1409,7 @@
 	unsigned long nr;
 
 	nr = lock - list_entries;
-	WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */
+	WARN_ON(nr >= ARRAY_SIZE(list_entries)); /* Out-of-bounds, input fail */
 	lock->parent = parent;
 	lock->class->dep_gen_id = lockdep_dependency_gen_id;
 }
@@ -962,7 +1419,7 @@
 	unsigned long nr;
 
 	nr = lock - list_entries;
-	WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */
+	WARN_ON(nr >= ARRAY_SIZE(list_entries)); /* Out-of-bounds, input fail */
 	return lock->class->dep_gen_id == lockdep_dependency_gen_id;
 }
 
@@ -983,13 +1440,32 @@
 	return depth;
 }
 
+/*
+ * Return the forward or backward dependency list.
+ *
+ * @lock:   the lock_list to get its class's dependency list
+ * @offset: the offset to struct lock_class to determine whether it is
+ *          locks_after or locks_before
+ */
+static inline struct list_head *get_dep_list(struct lock_list *lock, int offset)
+{
+	void *lock_class = lock->class;
+
+	return lock_class + offset;
+}
+
+/*
+ * Forward- or backward-dependency search, used for both circular dependency
+ * checking and hardirq-unsafe/softirq-unsafe checking.
+ */
 static int __bfs(struct lock_list *source_entry,
 		 void *data,
 		 int (*match)(struct lock_list *entry, void *data),
 		 struct lock_list **target_entry,
-		 int forward)
+		 int offset)
 {
 	struct lock_list *entry;
+	struct lock_list *lock;
 	struct list_head *head;
 	struct circular_queue *cq = &lock_cq;
 	int ret = 1;
@@ -1000,31 +1476,21 @@
 		goto exit;
 	}
 
-	if (forward)
-		head = &source_entry->class->locks_after;
-	else
-		head = &source_entry->class->locks_before;
-
+	head = get_dep_list(source_entry, offset);
 	if (list_empty(head))
 		goto exit;
 
 	__cq_init(cq);
-	__cq_enqueue(cq, (unsigned long)source_entry);
+	__cq_enqueue(cq, source_entry);
 
-	while (!__cq_empty(cq)) {
-		struct lock_list *lock;
-
-		__cq_dequeue(cq, (unsigned long *)&lock);
+	while ((lock = __cq_dequeue(cq))) {
 
 		if (!lock->class) {
 			ret = -2;
 			goto exit;
 		}
 
-		if (forward)
-			head = &lock->class->locks_after;
-		else
-			head = &lock->class->locks_before;
+		head = get_dep_list(lock, offset);
 
 		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
@@ -1038,7 +1504,7 @@
 					goto exit;
 				}
 
-				if (__cq_enqueue(cq, (unsigned long)entry)) {
+				if (__cq_enqueue(cq, entry)) {
 					ret = -1;
 					goto exit;
 				}
@@ -1057,7 +1523,8 @@
 			int (*match)(struct lock_list *entry, void *data),
 			struct lock_list **target_entry)
 {
-	return __bfs(src_entry, data, match, target_entry, 1);
+	return __bfs(src_entry, data, match, target_entry,
+		     offsetof(struct lock_class, locks_after));
 
 }
 
@@ -1066,31 +1533,30 @@
 			int (*match)(struct lock_list *entry, void *data),
 			struct lock_list **target_entry)
 {
-	return __bfs(src_entry, data, match, target_entry, 0);
+	return __bfs(src_entry, data, match, target_entry,
+		     offsetof(struct lock_class, locks_before));
 
 }
 
-/*
- * Recursive, forwards-direction lock-dependency checking, used for
- * both noncyclic checking and for hardirq-unsafe/softirq-unsafe
- * checking.
- */
+static void print_lock_trace(const struct lock_trace *trace,
+			     unsigned int spaces)
+{
+	stack_trace_print(trace->entries, trace->nr_entries, spaces);
+}
 
 /*
  * Print a dependency chain entry (this is only done when a deadlock
  * has been detected):
  */
-static noinline int
+static noinline void
 print_circular_bug_entry(struct lock_list *target, int depth)
 {
 	if (debug_locks_silent)
-		return 0;
+		return;
 	printk("\n-> #%u", depth);
 	print_lock_name(target->class);
 	printk(KERN_CONT ":\n");
-	print_stack_trace(&target->trace, 6);
-
-	return 0;
+	print_lock_trace(target->trace, 6);
 }
 
 static void
@@ -1147,7 +1613,7 @@
  * When a circular dependency is detected, print the
  * header first:
  */
-static noinline int
+static noinline void
 print_circular_bug_header(struct lock_list *entry, unsigned int depth,
 			struct held_lock *check_src,
 			struct held_lock *check_tgt)
@@ -1155,7 +1621,7 @@
 	struct task_struct *curr = current;
 
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("======================================================\n");
@@ -1173,8 +1639,6 @@
 	pr_warn("\nthe existing dependency chain (in reverse order) is:\n");
 
 	print_circular_bug_entry(entry, depth);
-
-	return 0;
 }
 
 static inline int class_equal(struct lock_list *entry, void *data)
@@ -1182,11 +1646,10 @@
 	return entry->class == data;
 }
 
-static noinline int print_circular_bug(struct lock_list *this,
-				struct lock_list *target,
-				struct held_lock *check_src,
-				struct held_lock *check_tgt,
-				struct stack_trace *trace)
+static noinline void print_circular_bug(struct lock_list *this,
+					struct lock_list *target,
+					struct held_lock *check_src,
+					struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
 	struct lock_list *parent;
@@ -1194,10 +1657,11 @@
 	int depth;
 
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
-	if (!save_trace(&this->trace))
-		return 0;
+	this->trace = save_trace();
+	if (!this->trace)
+		return;
 
 	depth = get_lock_depth(target);
 
@@ -1219,21 +1683,17 @@
 
 	printk("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
-static noinline int print_bfs_bug(int ret)
+static noinline void print_bfs_bug(int ret)
 {
 	if (!debug_locks_off_graph_unlock())
-		return 0;
+		return;
 
 	/*
 	 * Breadth-first-search failed, graph got corrupted?
 	 */
 	WARN(1, "lockdep bfs error:%d\n", ret);
-
-	return 0;
 }
 
 static int noop_count(struct lock_list *entry, void *data)
@@ -1296,49 +1756,114 @@
 }
 
 /*
- * Prove that the dependency graph starting at <entry> can not
- * lead to <target>. Print an error and return 0 if it does.
+ * Check that the dependency graph starting at <src> can lead to
+ * <target> or not. Print an error and return 0 if it does.
  */
 static noinline int
-check_noncircular(struct lock_list *root, struct lock_class *target,
-		struct lock_list **target_entry)
+check_path(struct lock_class *target, struct lock_list *src_entry,
+	   struct lock_list **target_entry)
 {
-	int result;
+	int ret;
+
+	ret = __bfs_forwards(src_entry, (void *)target, class_equal,
+			     target_entry);
+
+	if (unlikely(ret < 0))
+		print_bfs_bug(ret);
+
+	return ret;
+}
+
+/*
+ * Prove that the dependency graph starting at <src> can not
+ * lead to <target>. If it can, there is a circle when adding
+ * <target> -> <src> dependency.
+ *
+ * Print an error and return 0 if it does.
+ */
+static noinline int
+check_noncircular(struct held_lock *src, struct held_lock *target,
+		  struct lock_trace **const trace)
+{
+	int ret;
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list src_entry = {
+		.class = hlock_class(src),
+		.parent = NULL,
+	};
 
 	debug_atomic_inc(nr_cyclic_checks);
 
-	result = __bfs_forwards(root, target, class_equal, target_entry);
+	ret = check_path(hlock_class(target), &src_entry, &target_entry);
 
-	return result;
+	if (unlikely(!ret)) {
+		if (!*trace) {
+			/*
+			 * If save_trace fails here, the printing might
+			 * trigger a WARN but because of the !nr_entries it
+			 * should not do bad things.
+			 */
+			*trace = save_trace();
+		}
+
+		print_circular_bug(&src_entry, target_entry, src, target);
+	}
+
+	return ret;
 }
 
+#ifdef CONFIG_LOCKDEP_SMALL
+/*
+ * Check that the dependency graph starting at <src> can lead to
+ * <target> or not. If it can, <src> -> <target> dependency is already
+ * in the graph.
+ *
+ * Print an error and return 2 if it does or 1 if it does not.
+ */
 static noinline int
-check_redundant(struct lock_list *root, struct lock_class *target,
-		struct lock_list **target_entry)
+check_redundant(struct held_lock *src, struct held_lock *target)
 {
-	int result;
+	int ret;
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list src_entry = {
+		.class = hlock_class(src),
+		.parent = NULL,
+	};
 
 	debug_atomic_inc(nr_redundant_checks);
 
-	result = __bfs_forwards(root, target, class_equal, target_entry);
+	ret = check_path(hlock_class(target), &src_entry, &target_entry);
 
-	return result;
+	if (!ret) {
+		debug_atomic_inc(nr_redundant);
+		ret = 2;
+	} else if (ret < 0)
+		ret = 0;
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+static inline int usage_accumulate(struct lock_list *entry, void *mask)
+{
+	*(unsigned long *)mask |= entry->class->usage_mask;
+
+	return 0;
 }
 
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 /*
  * Forwards and backwards subgraph searching, for the purposes of
  * proving that two subgraphs can be connected by a new dependency
  * without creating any illegal irq-safe -> irq-unsafe lock dependency.
  */
 
-static inline int usage_match(struct lock_list *entry, void *bit)
+static inline int usage_match(struct lock_list *entry, void *mask)
 {
-	return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit);
+	return entry->class->usage_mask & *(unsigned long *)mask;
 }
 
-
-
 /*
  * Find a node in the forwards-direction dependency sub-graph starting
  * at @root->class that matches @bit.
@@ -1350,14 +1875,14 @@
  * Return <0 on error.
  */
 static int
-find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_forwards(struct lock_list *root, unsigned long usage_mask,
 			struct lock_list **target_entry)
 {
 	int result;
 
 	debug_atomic_inc(nr_find_usage_forwards_checks);
 
-	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
+	result = __bfs_forwards(root, &usage_mask, usage_match, target_entry);
 
 	return result;
 }
@@ -1373,14 +1898,14 @@
  * Return <0 on error.
  */
 static int
-find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_backwards(struct lock_list *root, unsigned long usage_mask,
 			struct lock_list **target_entry)
 {
 	int result;
 
 	debug_atomic_inc(nr_find_usage_backwards_checks);
 
-	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
+	result = __bfs_backwards(root, &usage_mask, usage_match, target_entry);
 
 	return result;
 }
@@ -1391,7 +1916,9 @@
 
 	printk("%*s->", depth, "");
 	print_lock_name(class);
-	printk(KERN_CONT " ops: %lu", class->ops);
+#ifdef CONFIG_DEBUG_LOCKDEP
+	printk(KERN_CONT " ops: %lu", debug_class_ops_read(class));
+#endif
 	printk(KERN_CONT " {\n");
 
 	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
@@ -1400,7 +1927,7 @@
 
 			len += printk("%*s   %s", depth, "", usage_str[bit]);
 			len += printk(KERN_CONT " at:\n");
-			print_stack_trace(class->usage_traces + bit, len);
+			print_lock_trace(class->usage_traces[bit], len);
 		}
 	}
 	printk("%*s }\n", depth, "");
@@ -1414,7 +1941,7 @@
  */
 static void __used
 print_shortest_lock_dependencies(struct lock_list *leaf,
-				struct lock_list *root)
+				 struct lock_list *root)
 {
 	struct lock_list *entry = leaf;
 	int depth;
@@ -1425,7 +1952,7 @@
 	do {
 		print_lock_class_header(entry->class, depth);
 		printk("%*s ... acquired at:\n", depth, "");
-		print_stack_trace(&entry->trace, 2);
+		print_lock_trace(entry->trace, 2);
 		printk("\n");
 
 		if (depth == 0 && (entry != root)) {
@@ -1436,8 +1963,6 @@
 		entry = get_lock_parent(entry);
 		depth--;
 	} while (entry && (depth >= 0));
-
-	return;
 }
 
 static void
@@ -1496,7 +2021,7 @@
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
-static int
+static void
 print_bad_irq_dependency(struct task_struct *curr,
 			 struct lock_list *prev_root,
 			 struct lock_list *next_root,
@@ -1509,7 +2034,7 @@
 			 const char *irqclass)
 {
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("=====================================================\n");
@@ -1538,14 +2063,14 @@
 	print_lock_name(backwards_entry->class);
 	pr_warn("\n... which became %s-irq-safe at:\n", irqclass);
 
-	print_stack_trace(backwards_entry->class->usage_traces + bit1, 1);
+	print_lock_trace(backwards_entry->class->usage_traces[bit1], 1);
 
 	pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass);
 	print_lock_name(forwards_entry->class);
 	pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass);
 	pr_warn("...");
 
-	print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
+	print_lock_trace(forwards_entry->class->usage_traces[bit2], 1);
 
 	pr_warn("\nother info that might help us debug this:\n\n");
 	print_irq_lock_scenario(backwards_entry, forwards_entry,
@@ -1554,53 +2079,20 @@
 	lockdep_print_held_locks(curr);
 
 	pr_warn("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass);
-	if (!save_trace(&prev_root->trace))
-		return 0;
+	prev_root->trace = save_trace();
+	if (!prev_root->trace)
+		return;
 	print_shortest_lock_dependencies(backwards_entry, prev_root);
 
 	pr_warn("\nthe dependencies between the lock to be acquired");
 	pr_warn(" and %s-irq-unsafe lock:\n", irqclass);
-	if (!save_trace(&next_root->trace))
-		return 0;
+	next_root->trace = save_trace();
+	if (!next_root->trace)
+		return;
 	print_shortest_lock_dependencies(forwards_entry, next_root);
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
-}
-
-static int
-check_usage(struct task_struct *curr, struct held_lock *prev,
-	    struct held_lock *next, enum lock_usage_bit bit_backwards,
-	    enum lock_usage_bit bit_forwards, const char *irqclass)
-{
-	int ret;
-	struct lock_list this, that;
-	struct lock_list *uninitialized_var(target_entry);
-	struct lock_list *uninitialized_var(target_entry1);
-
-	this.parent = NULL;
-
-	this.class = hlock_class(prev);
-	ret = find_usage_backwards(&this, bit_backwards, &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
-	if (ret == 1)
-		return ret;
-
-	that.parent = NULL;
-	that.class = hlock_class(next);
-	ret = find_usage_forwards(&that, bit_forwards, &target_entry1);
-	if (ret < 0)
-		return print_bfs_bug(ret);
-	if (ret == 1)
-		return ret;
-
-	return print_bad_irq_dependency(curr, &this, &that,
-			target_entry, target_entry1,
-			prev, next,
-			bit_backwards, bit_forwards, irqclass);
 }
 
 static const char *state_names[] = {
@@ -1619,70 +2111,192 @@
 
 static inline const char *state_name(enum lock_usage_bit bit)
 {
-	return (bit & 1) ? state_rnames[bit >> 2] : state_names[bit >> 2];
+	if (bit & LOCK_USAGE_READ_MASK)
+		return state_rnames[bit >> LOCK_USAGE_DIR_MASK];
+	else
+		return state_names[bit >> LOCK_USAGE_DIR_MASK];
 }
 
+/*
+ * The bit number is encoded like:
+ *
+ *  bit0: 0 exclusive, 1 read lock
+ *  bit1: 0 used in irq, 1 irq enabled
+ *  bit2-n: state
+ */
 static int exclusive_bit(int new_bit)
 {
-	/*
-	 * USED_IN
-	 * USED_IN_READ
-	 * ENABLED
-	 * ENABLED_READ
-	 *
-	 * bit 0 - write/read
-	 * bit 1 - used_in/enabled
-	 * bit 2+  state
-	 */
-
-	int state = new_bit & ~3;
-	int dir = new_bit & 2;
+	int state = new_bit & LOCK_USAGE_STATE_MASK;
+	int dir = new_bit & LOCK_USAGE_DIR_MASK;
 
 	/*
 	 * keep state, bit flip the direction and strip read.
 	 */
-	return state | (dir ^ 2);
+	return state | (dir ^ LOCK_USAGE_DIR_MASK);
 }
 
+/*
+ * Observe that when given a bitmask where each bitnr is encoded as above, a
+ * right shift of the mask transforms the individual bitnrs as -1 and
+ * conversely, a left shift transforms into +1 for the individual bitnrs.
+ *
+ * So for all bits whose number have LOCK_ENABLED_* set (bitnr1 == 1), we can
+ * create the mask with those bit numbers using LOCK_USED_IN_* (bitnr1 == 0)
+ * instead by subtracting the bit number by 2, or shifting the mask right by 2.
+ *
+ * Similarly, bitnr1 == 0 becomes bitnr1 == 1 by adding 2, or shifting left 2.
+ *
+ * So split the mask (note that LOCKF_ENABLED_IRQ_ALL|LOCKF_USED_IN_IRQ_ALL is
+ * all bits set) and recompose with bitnr1 flipped.
+ */
+static unsigned long invert_dir_mask(unsigned long mask)
+{
+	unsigned long excl = 0;
+
+	/* Invert dir */
+	excl |= (mask & LOCKF_ENABLED_IRQ_ALL) >> LOCK_USAGE_DIR_MASK;
+	excl |= (mask & LOCKF_USED_IN_IRQ_ALL) << LOCK_USAGE_DIR_MASK;
+
+	return excl;
+}
+
+/*
+ * As above, we clear bitnr0 (LOCK_*_READ off) with bitmask ops. First, for all
+ * bits with bitnr0 set (LOCK_*_READ), add those with bitnr0 cleared (LOCK_*).
+ * And then mask out all bitnr0.
+ */
+static unsigned long exclusive_mask(unsigned long mask)
+{
+	unsigned long excl = invert_dir_mask(mask);
+
+	/* Strip read */
+	excl |= (excl & LOCKF_IRQ_READ) >> LOCK_USAGE_READ_MASK;
+	excl &= ~LOCKF_IRQ_READ;
+
+	return excl;
+}
+
+/*
+ * Retrieve the _possible_ original mask to which @mask is
+ * exclusive. Ie: this is the opposite of exclusive_mask().
+ * Note that 2 possible original bits can match an exclusive
+ * bit: one has LOCK_USAGE_READ_MASK set, the other has it
+ * cleared. So both are returned for each exclusive bit.
+ */
+static unsigned long original_mask(unsigned long mask)
+{
+	unsigned long excl = invert_dir_mask(mask);
+
+	/* Include read in existing usages */
+	excl |= (excl & LOCKF_IRQ) << LOCK_USAGE_READ_MASK;
+
+	return excl;
+}
+
+/*
+ * Find the first pair of bit match between an original
+ * usage mask and an exclusive usage mask.
+ */
+static int find_exclusive_match(unsigned long mask,
+				unsigned long excl_mask,
+				enum lock_usage_bit *bitp,
+				enum lock_usage_bit *excl_bitp)
+{
+	int bit, excl;
+
+	for_each_set_bit(bit, &mask, LOCK_USED) {
+		excl = exclusive_bit(bit);
+		if (excl_mask & lock_flag(excl)) {
+			*bitp = bit;
+			*excl_bitp = excl;
+			return 0;
+		}
+	}
+	return -1;
+}
+
+/*
+ * Prove that the new dependency does not connect a hardirq-safe(-read)
+ * lock with a hardirq-unsafe lock - to achieve this we search
+ * the backwards-subgraph starting at <prev>, and the
+ * forwards-subgraph starting at <next>:
+ */
 static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
-			   struct held_lock *next, enum lock_usage_bit bit)
+			   struct held_lock *next)
 {
-	/*
-	 * Prove that the new dependency does not connect a hardirq-safe
-	 * lock with a hardirq-unsafe lock - to achieve this we search
-	 * the backwards-subgraph starting at <prev>, and the
-	 * forwards-subgraph starting at <next>:
-	 */
-	if (!check_usage(curr, prev, next, bit,
-			   exclusive_bit(bit), state_name(bit)))
-		return 0;
-
-	bit++; /* _READ */
+	unsigned long usage_mask = 0, forward_mask, backward_mask;
+	enum lock_usage_bit forward_bit = 0, backward_bit = 0;
+	struct lock_list *uninitialized_var(target_entry1);
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list this, that;
+	int ret;
 
 	/*
-	 * Prove that the new dependency does not connect a hardirq-safe-read
-	 * lock with a hardirq-unsafe lock - to achieve this we search
-	 * the backwards-subgraph starting at <prev>, and the
-	 * forwards-subgraph starting at <next>:
+	 * Step 1: gather all hard/soft IRQs usages backward in an
+	 * accumulated usage mask.
 	 */
-	if (!check_usage(curr, prev, next, bit,
-			   exclusive_bit(bit), state_name(bit)))
+	this.parent = NULL;
+	this.class = hlock_class(prev);
+
+	ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL);
+	if (ret < 0) {
+		print_bfs_bug(ret);
 		return 0;
+	}
 
-	return 1;
-}
+	usage_mask &= LOCKF_USED_IN_IRQ_ALL;
+	if (!usage_mask)
+		return 1;
 
-static int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
-		struct held_lock *next)
-{
-#define LOCKDEP_STATE(__STATE)						\
-	if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE))	\
+	/*
+	 * Step 2: find exclusive uses forward that match the previous
+	 * backward accumulated mask.
+	 */
+	forward_mask = exclusive_mask(usage_mask);
+
+	that.parent = NULL;
+	that.class = hlock_class(next);
+
+	ret = find_usage_forwards(&that, forward_mask, &target_entry1);
+	if (ret < 0) {
+		print_bfs_bug(ret);
 		return 0;
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
+	}
+	if (ret == 1)
+		return ret;
 
-	return 1;
+	/*
+	 * Step 3: we found a bad match! Now retrieve a lock from the backward
+	 * list whose usage mask matches the exclusive usage mask from the
+	 * lock found on the forward list.
+	 */
+	backward_mask = original_mask(target_entry1->class->usage_mask);
+
+	ret = find_usage_backwards(&this, backward_mask, &target_entry);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
+	if (DEBUG_LOCKS_WARN_ON(ret == 1))
+		return 1;
+
+	/*
+	 * Step 4: narrow down to a pair of incompatible usage bits
+	 * and report it.
+	 */
+	ret = find_exclusive_match(target_entry->class->usage_mask,
+				   target_entry1->class->usage_mask,
+				   &backward_bit, &forward_bit);
+	if (DEBUG_LOCKS_WARN_ON(ret == -1))
+		return 1;
+
+	print_bad_irq_dependency(curr, &this, &that,
+				 target_entry, target_entry1,
+				 prev, next,
+				 backward_bit, forward_bit,
+				 state_name(backward_bit));
+
+	return 0;
 }
 
 static void inc_chains(void)
@@ -1699,9 +2313,8 @@
 
 #else
 
-static inline int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
-		struct held_lock *next)
+static inline int check_irq_usage(struct task_struct *curr,
+				  struct held_lock *prev, struct held_lock *next)
 {
 	return 1;
 }
@@ -1711,11 +2324,10 @@
 	nr_process_chains++;
 }
 
-#endif
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 static void
-print_deadlock_scenario(struct held_lock *nxt,
-			     struct held_lock *prv)
+print_deadlock_scenario(struct held_lock *nxt, struct held_lock *prv)
 {
 	struct lock_class *next = hlock_class(nxt);
 	struct lock_class *prev = hlock_class(prv);
@@ -1733,12 +2345,12 @@
 	printk(" May be due to missing lock nesting notation\n\n");
 }
 
-static int
+static void
 print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 		   struct held_lock *next)
 {
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("============================================\n");
@@ -1757,8 +2369,6 @@
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 /*
@@ -1770,8 +2380,7 @@
  * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
  */
 static int
-check_deadlock(struct task_struct *curr, struct held_lock *next,
-	       struct lockdep_map *next_instance, int read)
+check_deadlock(struct task_struct *curr, struct held_lock *next)
 {
 	struct held_lock *prev;
 	struct held_lock *nest = NULL;
@@ -1790,7 +2399,7 @@
 		 * Allow read-after-read recursion of the same
 		 * lock class (i.e. read_lock(lock)+read_lock(lock)):
 		 */
-		if ((read == 2) && prev->read)
+		if ((next->read == 2) && prev->read)
 			return 2;
 
 		/*
@@ -1800,14 +2409,15 @@
 		if (nest)
 			return 2;
 
-		return print_deadlock_bug(curr, prev, next);
+		print_deadlock_bug(curr, prev, next);
+		return 0;
 	}
 	return 1;
 }
 
 /*
  * There was a chain-cache miss, and we are about to add a new dependency
- * to a previous lock. We recursively validate the following rules:
+ * to a previous lock. We validate the following rules:
  *
  *  - would the adding of the <prev> -> <next> dependency create a
  *    circular dependency in the graph? [== circular deadlock]
@@ -1829,41 +2439,45 @@
  */
 static int
 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 held_lock *next, int distance,
+	       struct lock_trace **const trace)
 {
-	struct lock_list *uninitialized_var(target_entry);
 	struct lock_list *entry;
-	struct lock_list this;
 	int ret;
 
+	if (!hlock_class(prev)->key || !hlock_class(next)->key) {
+		/*
+		 * The warning statements below may trigger a use-after-free
+		 * of the class name. It is better to trigger a use-after free
+		 * and to have the class name most of the time instead of not
+		 * having the class name available.
+		 */
+		WARN_ONCE(!debug_locks_silent && !hlock_class(prev)->key,
+			  "Detected use-after-free of lock class %px/%s\n",
+			  hlock_class(prev),
+			  hlock_class(prev)->name);
+		WARN_ONCE(!debug_locks_silent && !hlock_class(next)->key,
+			  "Detected use-after-free of lock class %px/%s\n",
+			  hlock_class(next),
+			  hlock_class(next)->name);
+		return 2;
+	}
+
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
 	 * create a circular dependency in the graph. (We do this by
-	 * forward-recursing into the graph starting at <next>, and
-	 * checking whether we can reach <prev>.)
+	 * a breadth-first search into the graph starting at <next>,
+	 * and check whether we can reach <prev>.)
 	 *
-	 * We are using global variables to control the recursion, to
-	 * keep the stackframe size of the recursive functions low:
+	 * The search is limited by the size of the circular queue (i.e.,
+	 * MAX_CIRCULAR_QUEUE_SIZE) which keeps track of a breadth of nodes
+	 * in the graph whose neighbours are to be checked.
 	 */
-	this.class = hlock_class(next);
-	this.parent = NULL;
-	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
-	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);
+	ret = check_noncircular(next, prev, trace);
+	if (unlikely(ret <= 0))
+		return 0;
 
-	if (!check_prev_add_irq(curr, prev, next))
+	if (!check_irq_usage(curr, prev, next))
 		return 0;
 
 	/*
@@ -1892,37 +2506,35 @@
 		}
 	}
 
+#ifdef CONFIG_LOCKDEP_SMALL
 	/*
 	 * Is the <prev> -> <next> link redundant?
 	 */
-	this.class = hlock_class(prev);
-	this.parent = NULL;
-	ret = check_redundant(&this, hlock_class(next), &target_entry);
-	if (!ret) {
-		debug_atomic_inc(nr_redundant);
-		return 2;
+	ret = check_redundant(prev, next);
+	if (ret != 1)
+		return ret;
+#endif
+
+	if (!*trace) {
+		*trace = save_trace();
+		if (!*trace)
+			return 0;
 	}
-	if (ret < 0)
-		return print_bfs_bug(ret);
-
-
-	if (!trace->entries && !save(trace))
-		return 0;
 
 	/*
 	 * Ok, all validations passed, add the new lock
 	 * to the previous lock's dependency list:
 	 */
-	ret = add_lock_to_list(hlock_class(next),
+	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
 			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance, trace);
+			       next->acquire_ip, distance, *trace);
 
 	if (!ret)
 		return 0;
 
-	ret = add_lock_to_list(hlock_class(prev),
+	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
 			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance, trace);
+			       next->acquire_ip, distance, *trace);
 	if (!ret)
 		return 0;
 
@@ -1938,14 +2550,9 @@
 static int
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
+	struct lock_trace *trace = NULL;
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.max_entries = 0,
-		.entries = NULL,
-		.skip = 0,
-	};
 
 	/*
 	 * Debugging checks.
@@ -1971,7 +2578,8 @@
 		 * added:
 		 */
 		if (hlock->read != 2 && hlock->check) {
-			int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace);
+			int ret = check_prev_add(curr, hlock, next, distance,
+						 &trace);
 			if (!ret)
 				return 0;
 
@@ -2013,8 +2621,8 @@
 	return 0;
 }
 
-unsigned long nr_lock_chains;
 struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
+static DECLARE_BITMAP(lock_chains_in_use, MAX_LOCKDEP_CHAINS);
 int nr_chain_hlocks;
 static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
 
@@ -2060,12 +2668,13 @@
 print_chain_keys_held_locks(struct task_struct *curr, struct held_lock *hlock_next)
 {
 	struct held_lock *hlock;
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 	int depth = curr->lockdep_depth;
-	int i;
+	int i = get_first_held_lock(curr, hlock_next);
 
-	printk("depth: %u\n", depth + 1);
-	for (i = get_first_held_lock(curr, hlock_next); i < depth; i++) {
+	printk("depth: %u (irq_context %u)\n", depth - i + 1,
+		hlock_next->irq_context);
+	for (; i < depth; i++) {
 		hlock = curr->held_locks + i;
 		chain_key = print_chain_key_iteration(hlock->class_idx, chain_key);
 
@@ -2079,13 +2688,13 @@
 static void print_chain_keys_chain(struct lock_chain *chain)
 {
 	int i;
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 	int class_id;
 
 	printk("depth: %u\n", chain->depth);
 	for (i = 0; i < chain->depth; i++) {
 		class_id = chain_hlocks[chain->base + i];
-		chain_key = print_chain_key_iteration(class_id + 1, chain_key);
+		chain_key = print_chain_key_iteration(class_id, chain_key);
 
 		print_lock_name(lock_classes + class_id);
 		printk("\n");
@@ -2136,7 +2745,7 @@
 	}
 
 	for (j = 0; j < chain->depth - 1; j++, i++) {
-		id = curr->held_locks[i].class_idx - 1;
+		id = curr->held_locks[i].class_idx;
 
 		if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) {
 			print_collision(curr, hlock, chain);
@@ -2148,73 +2757,30 @@
 }
 
 /*
- * This is for building a chain between just two different classes,
- * instead of adding a new hlock upon current, which is done by
- * add_chain_cache().
- *
- * This can be called in any context with two classes, while
- * add_chain_cache() must be done within the lock owener's context
- * since it uses hlock which might be racy in another context.
+ * Given an index that is >= -1, return the index of the next lock chain.
+ * Return -2 if there is no next lock chain.
  */
-static inline int add_chain_cache_classes(unsigned int prev,
-					  unsigned int next,
-					  unsigned int irq_context,
-					  u64 chain_key)
+long lockdep_next_lockchain(long i)
 {
-	struct hlist_head *hash_head = chainhashentry(chain_key);
-	struct lock_chain *chain;
+	i = find_next_bit(lock_chains_in_use, ARRAY_SIZE(lock_chains), i + 1);
+	return i < ARRAY_SIZE(lock_chains) ? i : -2;
+}
 
-	/*
-	 * Allocate a new chain entry from the static array, and add
-	 * it to the hash:
-	 */
+unsigned long lock_chain_count(void)
+{
+	return bitmap_weight(lock_chains_in_use, ARRAY_SIZE(lock_chains));
+}
 
-	/*
-	 * We might need to take the graph lock, ensure we've got IRQs
-	 * disabled to make this an IRQ-safe lock.. for recursion reasons
-	 * lockdep won't complain about its own locking errors.
-	 */
-	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
-		return 0;
+/* Must be called with the graph lock held. */
+static struct lock_chain *alloc_lock_chain(void)
+{
+	int idx = find_first_zero_bit(lock_chains_in_use,
+				      ARRAY_SIZE(lock_chains));
 
-	if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) {
-		if (!debug_locks_off_graph_unlock())
-			return 0;
-
-		print_lockdep_off("BUG: MAX_LOCKDEP_CHAINS too low!");
-		dump_stack();
-		return 0;
-	}
-
-	chain = lock_chains + nr_lock_chains++;
-	chain->chain_key = chain_key;
-	chain->irq_context = irq_context;
-	chain->depth = 2;
-	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
-		chain->base = nr_chain_hlocks;
-		nr_chain_hlocks += chain->depth;
-		chain_hlocks[chain->base] = prev - 1;
-		chain_hlocks[chain->base + 1] = next -1;
-	}
-#ifdef CONFIG_DEBUG_LOCKDEP
-	/*
-	 * Important for check_no_collision().
-	 */
-	else {
-		if (!debug_locks_off_graph_unlock())
-			return 0;
-
-		print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!");
-		dump_stack();
-		return 0;
-	}
-#endif
-
-	hlist_add_head_rcu(&chain->entry, hash_head);
-	debug_atomic_inc(chain_lookup_misses);
-	inc_chains();
-
-	return 1;
+	if (unlikely(idx >= ARRAY_SIZE(lock_chains)))
+		return NULL;
+	__set_bit(idx, lock_chains_in_use);
+	return lock_chains + idx;
 }
 
 /*
@@ -2234,19 +2800,15 @@
 	int i, j;
 
 	/*
-	 * Allocate a new chain entry from the static array, and add
-	 * it to the hash:
-	 */
-
-	/*
-	 * We might need to take the graph lock, ensure we've got IRQs
+	 * The caller must hold the graph lock, ensure we've got IRQs
 	 * disabled to make this an IRQ-safe lock.. for recursion reasons
 	 * lockdep won't complain about its own locking errors.
 	 */
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return 0;
 
-	if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) {
+	chain = alloc_lock_chain();
+	if (!chain) {
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
@@ -2254,7 +2816,6 @@
 		dump_stack();
 		return 0;
 	}
-	chain = lock_chains + nr_lock_chains++;
 	chain->chain_key = chain_key;
 	chain->irq_context = hlock->irq_context;
 	i = get_first_held_lock(curr, hlock);
@@ -2267,20 +2828,12 @@
 	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
 		chain->base = nr_chain_hlocks;
 		for (j = 0; j < chain->depth - 1; j++, i++) {
-			int lock_id = curr->held_locks[i].class_idx - 1;
+			int lock_id = curr->held_locks[i].class_idx;
 			chain_hlocks[chain->base + j] = lock_id;
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
-	}
-
-	if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS)
 		nr_chain_hlocks += chain->depth;
-
-#ifdef CONFIG_DEBUG_LOCKDEP
-	/*
-	 * Important for check_no_collision().
-	 */
-	if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
+	} else {
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
@@ -2288,7 +2841,6 @@
 		dump_stack();
 		return 0;
 	}
-#endif
 
 	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
@@ -2298,19 +2850,16 @@
 }
 
 /*
- * Look up a dependency chain.
+ * Look up a dependency chain. Must be called with either the graph lock or
+ * the RCU read lock held.
  */
 static inline struct lock_chain *lookup_chain_cache(u64 chain_key)
 {
 	struct hlist_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
 
-	/*
-	 * We can walk it lock-free, because entries only get added
-	 * to the hash:
-	 */
 	hlist_for_each_entry_rcu(chain, hash_head, entry) {
-		if (chain->chain_key == chain_key) {
+		if (READ_ONCE(chain->chain_key) == chain_key) {
 			debug_atomic_inc(chain_lookup_hits);
 			return chain;
 		}
@@ -2369,8 +2918,9 @@
 	return 1;
 }
 
-static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
-		struct held_lock *hlock, int chain_head, u64 chain_key)
+static int validate_chain(struct task_struct *curr,
+			  struct held_lock *hlock,
+			  int chain_head, u64 chain_key)
 {
 	/*
 	 * Trylock needs to maintain the stack of held locks, but it
@@ -2391,12 +2941,18 @@
 		 * - is softirq-safe, if this lock is hardirq-unsafe
 		 *
 		 * And check whether the new lock's dependency graph
-		 * could lead back to the previous lock.
+		 * could lead back to the previous lock:
 		 *
-		 * any of these scenarios could lead to a deadlock. If
-		 * All validations
+		 * - within the current held-lock stack
+		 * - across our accumulated lock dependency records
+		 *
+		 * any of these scenarios could lead to a deadlock.
 		 */
-		int ret = check_deadlock(curr, hlock, lock, hlock->read);
+		/*
+		 * The simple case: does the current hold the same lock
+		 * already?
+		 */
+		int ret = check_deadlock(curr, hlock);
 
 		if (!ret)
 			return 0;
@@ -2427,12 +2983,12 @@
 }
 #else
 static inline int validate_chain(struct task_struct *curr,
-	       	struct lockdep_map *lock, struct held_lock *hlock,
-		int chain_head, u64 chain_key)
+				 struct held_lock *hlock,
+				 int chain_head, u64 chain_key)
 {
 	return 1;
 }
-#endif
+#endif /* CONFIG_PROVE_LOCKING */
 
 /*
  * We are building curr_chain_key incrementally, so double-check
@@ -2443,7 +2999,7 @@
 #ifdef CONFIG_DEBUG_LOCKDEP
 	struct held_lock *hlock, *prev_hlock = NULL;
 	unsigned int i;
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 
 	for (i = 0; i < curr->lockdep_depth; i++) {
 		hlock = curr->held_locks + i;
@@ -2459,15 +3015,17 @@
 				(unsigned long long)hlock->prev_chain_key);
 			return;
 		}
+
 		/*
-		 * Whoops ran out of static storage again?
+		 * hlock->class_idx can't go beyond MAX_LOCKDEP_KEYS, but is
+		 * it registered lock class index?
 		 */
-		if (DEBUG_LOCKS_WARN_ON(hlock->class_idx > MAX_LOCKDEP_KEYS))
+		if (DEBUG_LOCKS_WARN_ON(!test_bit(hlock->class_idx, lock_classes_in_use)))
 			return;
 
 		if (prev_hlock && (prev_hlock->irq_context !=
 							hlock->irq_context))
-			chain_key = 0;
+			chain_key = INITIAL_CHAIN_KEY;
 		chain_key = iterate_chain_key(chain_key, hlock->class_idx);
 		prev_hlock = hlock;
 	}
@@ -2485,8 +3043,11 @@
 #endif
 }
 
-static void
-print_usage_bug_scenario(struct held_lock *lock)
+#ifdef CONFIG_PROVE_LOCKING
+static int mark_lock(struct task_struct *curr, struct held_lock *this,
+		     enum lock_usage_bit new_bit);
+
+static void print_usage_bug_scenario(struct held_lock *lock)
 {
 	struct lock_class *class = hlock_class(lock);
 
@@ -2503,12 +3064,12 @@
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
-static int
+static void
 print_usage_bug(struct task_struct *curr, struct held_lock *this,
 		enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit)
 {
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("================================\n");
@@ -2528,7 +3089,7 @@
 	print_lock(this);
 
 	pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]);
-	print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
+	print_lock_trace(hlock_class(this)->usage_traces[prev_bit], 1);
 
 	print_irqtrace_events(curr);
 	pr_warn("\nother info that might help us debug this:\n");
@@ -2538,8 +3099,6 @@
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 /*
@@ -2549,20 +3108,18 @@
 valid_state(struct task_struct *curr, struct held_lock *this,
 	    enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
 {
-	if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit)))
-		return print_usage_bug(curr, this, bad_bit, new_bit);
+	if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit))) {
+		print_usage_bug(curr, this, bad_bit, new_bit);
+		return 0;
+	}
 	return 1;
 }
 
-static int mark_lock(struct task_struct *curr, struct held_lock *this,
-		     enum lock_usage_bit new_bit);
-
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 
 /*
  * print irq inversion bug:
  */
-static int
+static void
 print_irq_inversion_bug(struct task_struct *curr,
 			struct lock_list *root, struct lock_list *other,
 			struct held_lock *this, int forwards,
@@ -2573,7 +3130,7 @@
 	int depth;
 
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("========================================================\n");
@@ -2613,14 +3170,13 @@
 	lockdep_print_held_locks(curr);
 
 	pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n");
-	if (!save_trace(&root->trace))
-		return 0;
+	root->trace = save_trace();
+	if (!root->trace)
+		return;
 	print_shortest_lock_dependencies(other, root);
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 /*
@@ -2637,14 +3193,17 @@
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
-	ret = find_usage_forwards(&root, bit, &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	ret = find_usage_forwards(&root, lock_flag(bit), &target_entry);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, &root, target_entry,
-					this, 1, irqclass);
+	print_irq_inversion_bug(curr, &root, target_entry,
+				this, 1, irqclass);
+	return 0;
 }
 
 /*
@@ -2661,14 +3220,17 @@
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
-	ret = find_usage_backwards(&root, bit, &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	ret = find_usage_backwards(&root, lock_flag(bit), &target_entry);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, &root, target_entry,
-					this, 0, irqclass);
+	print_irq_inversion_bug(curr, &root, target_entry,
+				this, 0, irqclass);
+	return 0;
 }
 
 void print_irqtrace_events(struct task_struct *curr)
@@ -2716,7 +3278,7 @@
 static inline int state_verbose(enum lock_usage_bit bit,
 				struct lock_class *class)
 {
-	return state_verbose_f[bit >> 2](class);
+	return state_verbose_f[bit >> LOCK_USAGE_DIR_MASK](class);
 }
 
 typedef int (*check_usage_f)(struct task_struct *, struct held_lock *,
@@ -2727,8 +3289,8 @@
 		enum lock_usage_bit new_bit)
 {
 	int excl_bit = exclusive_bit(new_bit);
-	int read = new_bit & 1;
-	int dir = new_bit & 2;
+	int read = new_bit & LOCK_USAGE_READ_MASK;
+	int dir = new_bit & LOCK_USAGE_DIR_MASK;
 
 	/*
 	 * mark USED_IN has to look forwards -- to ensure no dependency
@@ -2751,20 +3313,20 @@
 	 * Validate that the lock dependencies don't have conflicting usage
 	 * states.
 	 */
-	if ((!read || !dir || STRICT_READ_CHECKS) &&
-			!usage(curr, this, excl_bit, state_name(new_bit & ~1)))
+	if ((!read || STRICT_READ_CHECKS) &&
+			!usage(curr, this, excl_bit, state_name(new_bit & ~LOCK_USAGE_READ_MASK)))
 		return 0;
 
 	/*
 	 * Check for read in write conflicts
 	 */
 	if (!read) {
-		if (!valid_state(curr, this, new_bit, excl_bit + 1))
+		if (!valid_state(curr, this, new_bit, excl_bit + LOCK_USAGE_READ_MASK))
 			return 0;
 
 		if (STRICT_READ_CHECKS &&
-			!usage(curr, this, excl_bit + 1,
-				state_name(new_bit + 1)))
+			!usage(curr, this, excl_bit + LOCK_USAGE_READ_MASK,
+				state_name(new_bit + LOCK_USAGE_READ_MASK)))
 			return 0;
 	}
 
@@ -2774,35 +3336,28 @@
 	return 1;
 }
 
-enum mark_type {
-#define LOCKDEP_STATE(__STATE)	__STATE,
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
-};
-
 /*
  * Mark all held locks with a usage bit:
  */
 static int
-mark_held_locks(struct task_struct *curr, enum mark_type mark)
+mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
 {
-	enum lock_usage_bit usage_bit;
 	struct held_lock *hlock;
 	int i;
 
 	for (i = 0; i < curr->lockdep_depth; i++) {
+		enum lock_usage_bit hlock_bit = base_bit;
 		hlock = curr->held_locks + i;
 
-		usage_bit = 2 + (mark << 2); /* ENABLED */
 		if (hlock->read)
-			usage_bit += 1; /* READ */
+			hlock_bit += LOCK_USAGE_READ_MASK;
 
-		BUG_ON(usage_bit >= LOCK_USAGE_STATES);
+		BUG_ON(hlock_bit >= LOCK_USAGE_STATES);
 
 		if (!hlock->check)
 			continue;
 
-		if (!mark_lock(curr, hlock, usage_bit))
+		if (!mark_lock(curr, hlock, hlock_bit))
 			return 0;
 	}
 
@@ -2823,7 +3378,7 @@
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
 	 */
-	if (!mark_held_locks(curr, HARDIRQ))
+	if (!mark_held_locks(curr, LOCK_ENABLED_HARDIRQ))
 		return;
 	/*
 	 * If we have softirqs enabled, then set the usage
@@ -2831,7 +3386,7 @@
 	 * this bit from being set before)
 	 */
 	if (curr->softirqs_enabled)
-		if (!mark_held_locks(curr, SOFTIRQ))
+		if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
 			return;
 
 	curr->hardirq_enable_ip = ip;
@@ -2865,7 +3420,7 @@
 	/*
 	 * See the fine text that goes along with this variable definition.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled)))
+	if (DEBUG_LOCKS_WARN_ON(early_boot_irqs_disabled))
 		return;
 
 	/*
@@ -2879,6 +3434,7 @@
 	__trace_hardirqs_on_caller(ip);
 	current->lockdep_recursion = 0;
 }
+NOKPROBE_SYMBOL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
@@ -2908,6 +3464,7 @@
 	} else
 		debug_atomic_inc(redundant_hardirqs_off);
 }
+NOKPROBE_SYMBOL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
@@ -2945,7 +3502,7 @@
 	 * enabled too:
 	 */
 	if (curr->hardirqs_enabled)
-		mark_held_locks(curr, SOFTIRQ);
+		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 	current->lockdep_recursion = 0;
 }
 
@@ -2981,8 +3538,12 @@
 		debug_atomic_inc(redundant_softirqs_off);
 }
 
-static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
+static int
+mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 {
+	if (!check)
+		goto lock_used;
+
 	/*
 	 * If non-trylock use in a hardirq or softirq context, then
 	 * mark the lock as used in these contexts:
@@ -3026,6 +3587,11 @@
 		}
 	}
 
+lock_used:
+	/* mark it as used: */
+	if (!mark_lock(curr, hlock, LOCK_USED))
+		return 0;
+
 	return 1;
 }
 
@@ -3057,35 +3623,6 @@
 	return 0;
 }
 
-#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
-
-static inline
-int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
-		enum lock_usage_bit new_bit)
-{
-	WARN_ON(1); /* Impossible innit? when we don't have TRACE_IRQFLAG */
-	return 1;
-}
-
-static inline int mark_irqflags(struct task_struct *curr,
-		struct held_lock *hlock)
-{
-	return 1;
-}
-
-static inline unsigned int task_irq_context(struct task_struct *task)
-{
-	return 0;
-}
-
-static inline int separate_irq_context(struct task_struct *curr,
-		struct held_lock *hlock)
-{
-	return 0;
-}
-
-#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
-
 /*
  * Mark a lock with a usage bit, and validate the state transition:
  */
@@ -3094,6 +3631,11 @@
 {
 	unsigned int new_mask = 1 << new_bit, ret = 1;
 
+	if (new_bit >= LOCK_USAGE_STATES) {
+		DEBUG_LOCKS_WARN_ON(1);
+		return 0;
+	}
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3113,29 +3655,17 @@
 
 	hlock_class(this)->usage_mask |= new_mask;
 
-	if (!save_trace(hlock_class(this)->usage_traces + new_bit))
+	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
 		return 0;
 
 	switch (new_bit) {
-#define LOCKDEP_STATE(__STATE)			\
-	case LOCK_USED_IN_##__STATE:		\
-	case LOCK_USED_IN_##__STATE##_READ:	\
-	case LOCK_ENABLED_##__STATE:		\
-	case LOCK_ENABLED_##__STATE##_READ:
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
-		ret = mark_lock_irq(curr, this, new_bit);
-		if (!ret)
-			return 0;
-		break;
 	case LOCK_USED:
 		debug_atomic_dec(nr_unused_locks);
 		break;
 	default:
-		if (!debug_locks_off_graph_unlock())
+		ret = mark_lock_irq(curr, this, new_bit);
+		if (!ret)
 			return 0;
-		WARN_ON(1);
-		return 0;
 	}
 
 	graph_unlock();
@@ -3153,10 +3683,31 @@
 	return ret;
 }
 
+#else /* CONFIG_PROVE_LOCKING */
+
+static inline int
+mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
+{
+	return 1;
+}
+
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+	return 0;
+}
+
+static inline int separate_irq_context(struct task_struct *curr,
+		struct held_lock *hlock)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PROVE_LOCKING */
+
 /*
  * Initialize a lock instance's lock-class mapping info:
  */
-static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
+void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
 	int i;
@@ -3184,13 +3735,12 @@
 	if (DEBUG_LOCKS_WARN_ON(!key))
 		return;
 	/*
-	 * Sanity check, the lock-class key must be persistent:
+	 * Sanity check, the lock-class key must either have been allocated
+	 * statically or must have been registered as a dynamic key.
 	 */
-	if (!static_obj(key)) {
-		printk("BUG: key %px not in .data!\n", key);
-		/*
-		 * What it says above ^^^^^, I suggest you read it.
-		 */
+	if (!static_obj(key) && !is_dynamic_key(key)) {
+		if (debug_locks)
+			printk(KERN_ERR "BUG: key %px has not been registered!\n", key);
 		DEBUG_LOCKS_WARN_ON(1);
 		return;
 	}
@@ -3212,26 +3762,20 @@
 		raw_local_irq_restore(flags);
 	}
 }
-
-void lockdep_init_map(struct lockdep_map *lock, const char *name,
-		      struct lock_class_key *key, int subclass)
-{
-	__lockdep_init_map(lock, name, key, subclass);
-}
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
 struct lock_class_key __lockdep_no_validate__;
 EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
 
-static int
+static void
 print_lock_nested_lock_not_held(struct task_struct *curr,
 				struct held_lock *hlock,
 				unsigned long ip)
 {
 	if (!debug_locks_off())
-		return 0;
+		return;
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("==================================\n");
@@ -3253,8 +3797,6 @@
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static int __lock_is_held(const struct lockdep_map *lock, int read);
@@ -3262,6 +3804,10 @@
 /*
  * This gets called for every mutex_lock*()/spin_lock*() operation.
  * We maintain the dependency maps and validate the locking attempt:
+ *
+ * The callers must make sure that IRQs are disabled before calling it,
+ * otherwise we could get an interrupt which would want to take locks,
+ * which would end up in lockdep again.
  */
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			  int trylock, int read, int check, int hardirqs_off,
@@ -3279,14 +3825,6 @@
 	if (unlikely(!debug_locks))
 		return 0;
 
-	/*
-	 * Lockdep should run with IRQs disabled, otherwise we could
-	 * get an interrupt which would want to take locks, which would
-	 * end up in lockdep and have you got a head-ache already?
-	 */
-	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
-		return 0;
-
 	if (!prove_locking || lock->key == &__lockdep_no_validate__)
 		check = 0;
 
@@ -3300,7 +3838,9 @@
 		if (!class)
 			return 0;
 	}
-	atomic_inc((atomic_t *)&class->ops);
+
+	debug_class_ops_inc(class);
+
 	if (very_verbose(class)) {
 		printk("\nacquire class [%px] %s", class->key, class->name);
 		if (class->name_version > 1)
@@ -3321,24 +3861,24 @@
 	if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH))
 		return 0;
 
-	class_idx = class - lock_classes + 1;
+	class_idx = class - lock_classes;
 
 	if (depth) {
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
-			if (hlock->references) {
-				/*
-				 * Check: unsigned int references:12, overflow.
-				 */
-				if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
-					return 0;
+			if (!references)
+				references++;
 
+			if (!hlock->references)
 				hlock->references++;
-			} else {
-				hlock->references = 2;
-			}
 
-			return 1;
+			hlock->references += references;
+
+			/* Overflow */
+			if (DEBUG_LOCKS_WARN_ON(hlock->references < references))
+				return 0;
+
+			return 2;
 		}
 	}
 
@@ -3365,11 +3905,8 @@
 #endif
 	hlock->pin_count = pin_count;
 
-	if (check && !mark_irqflags(curr, hlock))
-		return 0;
-
-	/* mark it as used: */
-	if (!mark_lock(curr, hlock, LOCK_USED))
+	/* Initialize the lock usage bit */
+	if (!mark_usage(curr, hlock, check))
 		return 0;
 
 	/*
@@ -3383,9 +3920,9 @@
 	 * the hash, not class->key.
 	 */
 	/*
-	 * Whoops, we did it again.. ran straight out of our static allocation.
+	 * Whoops, we did it again.. class_idx is invalid.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(class_idx > MAX_LOCKDEP_KEYS))
+	if (DEBUG_LOCKS_WARN_ON(!test_bit(class_idx, lock_classes_in_use)))
 		return 0;
 
 	chain_key = curr->curr_chain_key;
@@ -3393,22 +3930,29 @@
 		/*
 		 * How can we have a chain hash when we ain't got no keys?!
 		 */
-		if (DEBUG_LOCKS_WARN_ON(chain_key != 0))
+		if (DEBUG_LOCKS_WARN_ON(chain_key != INITIAL_CHAIN_KEY))
 			return 0;
 		chain_head = 1;
 	}
 
 	hlock->prev_chain_key = chain_key;
 	if (separate_irq_context(curr, hlock)) {
-		chain_key = 0;
+		chain_key = INITIAL_CHAIN_KEY;
 		chain_head = 1;
 	}
 	chain_key = iterate_chain_key(chain_key, class_idx);
 
-	if (nest_lock && !__lock_is_held(nest_lock, -1))
-		return print_lock_nested_lock_not_held(curr, hlock, ip);
+	if (nest_lock && !__lock_is_held(nest_lock, -1)) {
+		print_lock_nested_lock_not_held(curr, hlock, ip);
+		return 0;
+	}
 
-	if (!validate_chain(curr, lock, hlock, chain_head, chain_key))
+	if (!debug_locks_silent) {
+		WARN_ON_ONCE(depth && !hlock_class(hlock - 1)->key);
+		WARN_ON_ONCE(!hlock_class(hlock)->key);
+	}
+
+	if (!validate_chain(curr, hlock, chain_head, chain_key))
 		return 0;
 
 	curr->curr_chain_key = chain_key;
@@ -3437,14 +3981,14 @@
 	return 1;
 }
 
-static int
-print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
-			   unsigned long ip)
+static void print_unlock_imbalance_bug(struct task_struct *curr,
+				       struct lockdep_map *lock,
+				       unsigned long ip)
 {
 	if (!debug_locks_off())
-		return 0;
+		return;
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("=====================================\n");
@@ -3462,8 +4006,6 @@
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static int match_held_lock(const struct held_lock *hlock,
@@ -3495,7 +4037,7 @@
 		if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock))
 			return 0;
 
-		if (hlock->class_idx == class - lock_classes + 1)
+		if (hlock->class_idx == class - lock_classes)
 			return 1;
 	}
 
@@ -3539,19 +4081,33 @@
 }
 
 static int reacquire_held_locks(struct task_struct *curr, unsigned int depth,
-			      int idx)
+				int idx, unsigned int *merged)
 {
 	struct held_lock *hlock;
+	int first_idx = idx;
+
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return 0;
 
 	for (hlock = curr->held_locks + idx; idx < depth; idx++, hlock++) {
-		if (!__lock_acquire(hlock->instance,
+		switch (__lock_acquire(hlock->instance,
 				    hlock_class(hlock)->subclass,
 				    hlock->trylock,
 				    hlock->read, hlock->check,
 				    hlock->hardirqs_off,
 				    hlock->nest_lock, hlock->acquire_ip,
-				    hlock->references, hlock->pin_count))
+				    hlock->references, hlock->pin_count)) {
+		case 0:
 			return 1;
+		case 1:
+			break;
+		case 2:
+			*merged += (idx == first_idx);
+			break;
+		default:
+			WARN_ON(1);
+			return 0;
+		}
 	}
 	return 0;
 }
@@ -3562,11 +4118,14 @@
 		 unsigned long ip)
 {
 	struct task_struct *curr = current;
+	unsigned int depth, merged = 0;
 	struct held_lock *hlock;
 	struct lock_class *class;
-	unsigned int depth;
 	int i;
 
+	if (unlikely(!debug_locks))
+		return 0;
+
 	depth = curr->lockdep_depth;
 	/*
 	 * This function is about (re)setting the class of a held lock,
@@ -3576,24 +4135,26 @@
 		return 0;
 
 	hlock = find_held_lock(curr, lock, depth, &i);
-	if (!hlock)
-		return print_unlock_imbalance_bug(curr, lock, ip);
+	if (!hlock) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	lockdep_init_map(lock, name, key, 0);
 	class = register_lock_class(lock, subclass, 0);
-	hlock->class_idx = class - lock_classes + 1;
+	hlock->class_idx = class - lock_classes;
 
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
-	if (reacquire_held_locks(curr, depth, i))
+	if (reacquire_held_locks(curr, depth, i, &merged))
 		return 0;
 
 	/*
 	 * I took it apart and put it back together again, except now I have
 	 * these 'spare' parts.. where shall I put them.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - merged))
 		return 0;
 	return 1;
 }
@@ -3601,10 +4162,13 @@
 static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
+	unsigned int depth, merged = 0;
 	struct held_lock *hlock;
-	unsigned int depth;
 	int i;
 
+	if (unlikely(!debug_locks))
+		return 0;
+
 	depth = curr->lockdep_depth;
 	/*
 	 * This function is about (re)setting the class of a held lock,
@@ -3614,8 +4178,10 @@
 		return 0;
 
 	hlock = find_held_lock(curr, lock, depth, &i);
-	if (!hlock)
-		return print_unlock_imbalance_bug(curr, lock, ip);
+	if (!hlock) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
@@ -3624,7 +4190,11 @@
 	hlock->read = 1;
 	hlock->acquire_ip = ip;
 
-	if (reacquire_held_locks(curr, depth, i))
+	if (reacquire_held_locks(curr, depth, i, &merged))
+		return 0;
+
+	/* Merging can't happen with unchanged classes.. */
+	if (DEBUG_LOCKS_WARN_ON(merged))
 		return 0;
 
 	/*
@@ -3633,6 +4203,7 @@
 	 */
 	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
 		return 0;
+
 	return 1;
 }
 
@@ -3644,11 +4215,11 @@
  * @nested is an hysterical artifact, needs a tree wide cleanup.
  */
 static int
-__lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
+__lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
+	unsigned int depth, merged = 1;
 	struct held_lock *hlock;
-	unsigned int depth;
 	int i;
 
 	if (unlikely(!debug_locks))
@@ -3659,16 +4230,20 @@
 	 * So we're all set to release this lock.. wait what lock? We don't
 	 * own any locks, you've been drinking again?
 	 */
-	if (DEBUG_LOCKS_WARN_ON(depth <= 0))
-		 return print_unlock_imbalance_bug(curr, lock, ip);
+	if (depth <= 0) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	/*
 	 * Check whether the lock exists in the current stack
 	 * of held locks:
 	 */
 	hlock = find_held_lock(curr, lock, depth, &i);
-	if (!hlock)
-		return print_unlock_imbalance_bug(curr, lock, ip);
+	if (!hlock) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	if (hlock->instance == lock)
 		lock_release_holdtime(hlock);
@@ -3696,20 +4271,33 @@
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
-	if (reacquire_held_locks(curr, depth, i + 1))
+	/*
+	 * The most likely case is when the unlock is on the innermost
+	 * lock. In this case, we are done!
+	 */
+	if (i == depth-1)
+		return 1;
+
+	if (reacquire_held_locks(curr, depth, i + 1, &merged))
 		return 0;
 
 	/*
 	 * We had N bottles of beer on the wall, we drank one, but now
 	 * there's not N-1 bottles of beer left on the wall...
+	 * Pouring two of the bottles together is acceptable.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - 1))
-		return 0;
+	DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - merged);
 
-	return 1;
+	/*
+	 * Since reacquire_held_locks() would have called check_chain_key()
+	 * indirectly via __lock_acquire(), we don't need to do it again
+	 * on return.
+	 */
+	return 0;
 }
 
-static int __lock_is_held(const struct lockdep_map *lock, int read)
+static nokprobe_inline
+int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
 	int i;
@@ -3808,8 +4396,7 @@
  */
 static void check_flags(unsigned long flags)
 {
-#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \
-    defined(CONFIG_TRACE_IRQFLAGS)
+#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP)
 	if (!debug_locks)
 		return;
 
@@ -3916,7 +4503,7 @@
 	check_flags(flags);
 	current->lockdep_recursion = 1;
 	trace_lock_release(lock, ip);
-	if (__lock_release(lock, nested, ip))
+	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -3942,6 +4529,7 @@
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lock_is_held_type);
+NOKPROBE_SYMBOL(lock_is_held_type);
 
 struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 {
@@ -3998,14 +4586,14 @@
 EXPORT_SYMBOL_GPL(lock_unpin_lock);
 
 #ifdef CONFIG_LOCK_STAT
-static int
-print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
-			   unsigned long ip)
+static void print_lock_contention_bug(struct task_struct *curr,
+				      struct lockdep_map *lock,
+				      unsigned long ip)
 {
 	if (!debug_locks_off())
-		return 0;
+		return;
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("=================================\n");
@@ -4023,8 +4611,6 @@
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static void
@@ -4169,9 +4755,7 @@
 	int i;
 
 	raw_local_irq_save(flags);
-	current->curr_chain_key = 0;
-	current->lockdep_depth = 0;
-	current->lockdep_recursion = 0;
+	lockdep_init_task(current);
 	memset(current->held_locks, 0, MAX_LOCK_DEPTH*sizeof(struct held_lock));
 	nr_hardirq_chains = 0;
 	nr_softirq_chains = 0;
@@ -4182,26 +4766,132 @@
 	raw_local_irq_restore(flags);
 }
 
-static void zap_class(struct lock_class *class)
+/* Remove a class from a lock chain. Must be called with the graph lock held. */
+static void remove_class_from_lock_chain(struct pending_free *pf,
+					 struct lock_chain *chain,
+					 struct lock_class *class)
 {
+#ifdef CONFIG_PROVE_LOCKING
+	struct lock_chain *new_chain;
+	u64 chain_key;
 	int i;
 
+	for (i = chain->base; i < chain->base + chain->depth; i++) {
+		if (chain_hlocks[i] != class - lock_classes)
+			continue;
+		/* The code below leaks one chain_hlock[] entry. */
+		if (--chain->depth > 0) {
+			memmove(&chain_hlocks[i], &chain_hlocks[i + 1],
+				(chain->base + chain->depth - i) *
+				sizeof(chain_hlocks[0]));
+		}
+		/*
+		 * Each lock class occurs at most once in a lock chain so once
+		 * we found a match we can break out of this loop.
+		 */
+		goto recalc;
+	}
+	/* Since the chain has not been modified, return. */
+	return;
+
+recalc:
+	chain_key = INITIAL_CHAIN_KEY;
+	for (i = chain->base; i < chain->base + chain->depth; i++)
+		chain_key = iterate_chain_key(chain_key, chain_hlocks[i]);
+	if (chain->depth && chain->chain_key == chain_key)
+		return;
+	/* Overwrite the chain key for concurrent RCU readers. */
+	WRITE_ONCE(chain->chain_key, chain_key);
+	/*
+	 * Note: calling hlist_del_rcu() from inside a
+	 * hlist_for_each_entry_rcu() loop is safe.
+	 */
+	hlist_del_rcu(&chain->entry);
+	__set_bit(chain - lock_chains, pf->lock_chains_being_freed);
+	if (chain->depth == 0)
+		return;
+	/*
+	 * If the modified lock chain matches an existing lock chain, drop
+	 * the modified lock chain.
+	 */
+	if (lookup_chain_cache(chain_key))
+		return;
+	new_chain = alloc_lock_chain();
+	if (WARN_ON_ONCE(!new_chain)) {
+		debug_locks_off();
+		return;
+	}
+	*new_chain = *chain;
+	hlist_add_head_rcu(&new_chain->entry, chainhashentry(chain_key));
+#endif
+}
+
+/* Must be called with the graph lock held. */
+static void remove_class_from_lock_chains(struct pending_free *pf,
+					  struct lock_class *class)
+{
+	struct lock_chain *chain;
+	struct hlist_head *head;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(chainhash_table); i++) {
+		head = chainhash_table + i;
+		hlist_for_each_entry_rcu(chain, head, entry) {
+			remove_class_from_lock_chain(pf, chain, class);
+		}
+	}
+}
+
+/*
+ * Remove all references to a lock class. The caller must hold the graph lock.
+ */
+static void zap_class(struct pending_free *pf, struct lock_class *class)
+{
+	struct lock_list *entry;
+	int i;
+
+	WARN_ON_ONCE(!class->key);
+
 	/*
 	 * Remove all dependencies this lock is
 	 * involved in:
 	 */
-	for (i = 0; i < nr_list_entries; i++) {
-		if (list_entries[i].class == class)
-			list_del_rcu(&list_entries[i].entry);
+	for_each_set_bit(i, list_entries_in_use, ARRAY_SIZE(list_entries)) {
+		entry = list_entries + i;
+		if (entry->class != class && entry->links_to != class)
+			continue;
+		__clear_bit(i, list_entries_in_use);
+		nr_list_entries--;
+		list_del_rcu(&entry->entry);
 	}
-	/*
-	 * Unhash the class and remove it from the all_lock_classes list:
-	 */
-	hlist_del_rcu(&class->hash_entry);
-	list_del_rcu(&class->lock_entry);
+	if (list_empty(&class->locks_after) &&
+	    list_empty(&class->locks_before)) {
+		list_move_tail(&class->lock_entry, &pf->zapped);
+		hlist_del_rcu(&class->hash_entry);
+		WRITE_ONCE(class->key, NULL);
+		WRITE_ONCE(class->name, NULL);
+		nr_lock_classes--;
+		__clear_bit(class - lock_classes, lock_classes_in_use);
+	} else {
+		WARN_ONCE(true, "%s() failed for class %s\n", __func__,
+			  class->name);
+	}
 
-	RCU_INIT_POINTER(class->key, NULL);
-	RCU_INIT_POINTER(class->name, NULL);
+	remove_class_from_lock_chains(pf, class);
+}
+
+static void reinit_class(struct lock_class *class)
+{
+	void *const p = class;
+	const unsigned int offset = offsetof(struct lock_class, key);
+
+	WARN_ON_ONCE(!class->lock_entry.next);
+	WARN_ON_ONCE(!list_empty(&class->locks_after));
+	WARN_ON_ONCE(!list_empty(&class->locks_before));
+	memset(p + offset, 0, sizeof(*class) - offset);
+	WARN_ON_ONCE(!class->lock_entry.next);
+	WARN_ON_ONCE(!list_empty(&class->locks_after));
+	WARN_ON_ONCE(!list_empty(&class->locks_before));
 }
 
 static inline int within(const void *addr, void *start, unsigned long size)
@@ -4209,66 +4899,201 @@
 	return addr >= start && addr < start + size;
 }
 
+static bool inside_selftest(void)
+{
+	return current == lockdep_selftest_task_struct;
+}
+
+/* The caller must hold the graph lock. */
+static struct pending_free *get_pending_free(void)
+{
+	return delayed_free.pf + delayed_free.index;
+}
+
+static void free_zapped_rcu(struct rcu_head *cb);
+
+/*
+ * Schedule an RCU callback if no RCU callback is pending. Must be called with
+ * the graph lock held.
+ */
+static void call_rcu_zapped(struct pending_free *pf)
+{
+	WARN_ON_ONCE(inside_selftest());
+
+	if (list_empty(&pf->zapped))
+		return;
+
+	if (delayed_free.scheduled)
+		return;
+
+	delayed_free.scheduled = true;
+
+	WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf);
+	delayed_free.index ^= 1;
+
+	call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+}
+
+/* The caller must hold the graph lock. May be called from RCU context. */
+static void __free_zapped_classes(struct pending_free *pf)
+{
+	struct lock_class *class;
+
+	check_data_structures();
+
+	list_for_each_entry(class, &pf->zapped, lock_entry)
+		reinit_class(class);
+
+	list_splice_init(&pf->zapped, &free_lock_classes);
+
+#ifdef CONFIG_PROVE_LOCKING
+	bitmap_andnot(lock_chains_in_use, lock_chains_in_use,
+		      pf->lock_chains_being_freed, ARRAY_SIZE(lock_chains));
+	bitmap_clear(pf->lock_chains_being_freed, 0, ARRAY_SIZE(lock_chains));
+#endif
+}
+
+static void free_zapped_rcu(struct rcu_head *ch)
+{
+	struct pending_free *pf;
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(ch != &delayed_free.rcu_head))
+		return;
+
+	raw_local_irq_save(flags);
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
+
+	/* closed head */
+	pf = delayed_free.pf + (delayed_free.index ^ 1);
+	__free_zapped_classes(pf);
+	delayed_free.scheduled = false;
+
+	/*
+	 * If there's anything on the open list, close and start a new callback.
+	 */
+	call_rcu_zapped(delayed_free.pf + delayed_free.index);
+
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
+	raw_local_irq_restore(flags);
+}
+
+/*
+ * Remove all lock classes from the class hash table and from the
+ * all_lock_classes list whose key or name is in the address range [start,
+ * start + size). Move these lock classes to the zapped_classes list. Must
+ * be called with the graph lock held.
+ */
+static void __lockdep_free_key_range(struct pending_free *pf, void *start,
+				     unsigned long size)
+{
+	struct lock_class *class;
+	struct hlist_head *head;
+	int i;
+
+	/* Unhash all classes that were created by a module. */
+	for (i = 0; i < CLASSHASH_SIZE; i++) {
+		head = classhash_table + i;
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
+			if (!within(class->key, start, size) &&
+			    !within(class->name, start, size))
+				continue;
+			zap_class(pf, class);
+		}
+	}
+}
+
 /*
  * Used in module.c to remove lock classes from memory that is going to be
  * freed; and possibly re-used by other modules.
  *
- * We will have had one sync_sched() before getting here, so we're guaranteed
- * nobody will look up these exact classes -- they're properly dead but still
- * allocated.
+ * We will have had one synchronize_rcu() before getting here, so we're
+ * guaranteed nobody will look up these exact classes -- they're properly dead
+ * but still allocated.
  */
-void lockdep_free_key_range(void *start, unsigned long size)
+static void lockdep_free_key_range_reg(void *start, unsigned long size)
 {
-	struct lock_class *class;
-	struct hlist_head *head;
+	struct pending_free *pf;
 	unsigned long flags;
-	int i;
-	int locked;
+
+	init_data_structures_once();
 
 	raw_local_irq_save(flags);
-	locked = graph_lock();
-
-	/*
-	 * Unhash all classes that were created by this module:
-	 */
-	for (i = 0; i < CLASSHASH_SIZE; i++) {
-		head = classhash_table + i;
-		hlist_for_each_entry_rcu(class, head, hash_entry) {
-			if (within(class->key, start, size))
-				zap_class(class);
-			else if (within(class->name, start, size))
-				zap_class(class);
-		}
-	}
-
-	if (locked)
-		graph_unlock();
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
+	pf = get_pending_free();
+	__lockdep_free_key_range(pf, start, size);
+	call_rcu_zapped(pf);
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
 	raw_local_irq_restore(flags);
 
 	/*
 	 * Wait for any possible iterators from look_up_lock_class() to pass
 	 * before continuing to free the memory they refer to.
-	 *
-	 * sync_sched() is sufficient because the read-side is IRQ disable.
 	 */
-	synchronize_sched();
-
-	/*
-	 * XXX at this point we could return the resources to the pool;
-	 * instead we leak them. We would need to change to bitmap allocators
-	 * instead of the linear allocators we have now.
-	 */
+	synchronize_rcu();
 }
 
-void lockdep_reset_lock(struct lockdep_map *lock)
+/*
+ * Free all lockdep keys in the range [start, start+size). Does not sleep.
+ * Ignores debug_locks. Must only be used by the lockdep selftests.
+ */
+static void lockdep_free_key_range_imm(void *start, unsigned long size)
+{
+	struct pending_free *pf = delayed_free.pf;
+	unsigned long flags;
+
+	init_data_structures_once();
+
+	raw_local_irq_save(flags);
+	arch_spin_lock(&lockdep_lock);
+	__lockdep_free_key_range(pf, start, size);
+	__free_zapped_classes(pf);
+	arch_spin_unlock(&lockdep_lock);
+	raw_local_irq_restore(flags);
+}
+
+void lockdep_free_key_range(void *start, unsigned long size)
+{
+	init_data_structures_once();
+
+	if (inside_selftest())
+		lockdep_free_key_range_imm(start, size);
+	else
+		lockdep_free_key_range_reg(start, size);
+}
+
+/*
+ * Check whether any element of the @lock->class_cache[] array refers to a
+ * registered lock class. The caller must hold either the graph lock or the
+ * RCU read lock.
+ */
+static bool lock_class_cache_is_registered(struct lockdep_map *lock)
 {
 	struct lock_class *class;
 	struct hlist_head *head;
-	unsigned long flags;
 	int i, j;
-	int locked;
 
-	raw_local_irq_save(flags);
+	for (i = 0; i < CLASSHASH_SIZE; i++) {
+		head = classhash_table + i;
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
+			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
+				if (lock->class_cache[j] == class)
+					return true;
+		}
+	}
+	return false;
+}
+
+/* The caller must hold the graph lock. Does not sleep. */
+static void __lockdep_reset_lock(struct pending_free *pf,
+				 struct lockdep_map *lock)
+{
+	struct lock_class *class;
+	int j;
 
 	/*
 	 * Remove all classes this lock might have:
@@ -4279,39 +5104,105 @@
 		 */
 		class = look_up_lock_class(lock, j);
 		if (class)
-			zap_class(class);
+			zap_class(pf, class);
 	}
 	/*
 	 * Debug check: in the end all mapped classes should
 	 * be gone.
 	 */
+	if (WARN_ON_ONCE(lock_class_cache_is_registered(lock)))
+		debug_locks_off();
+}
+
+/*
+ * Remove all information lockdep has about a lock if debug_locks == 1. Free
+ * released data structures from RCU context.
+ */
+static void lockdep_reset_lock_reg(struct lockdep_map *lock)
+{
+	struct pending_free *pf;
+	unsigned long flags;
+	int locked;
+
+	raw_local_irq_save(flags);
 	locked = graph_lock();
-	for (i = 0; i < CLASSHASH_SIZE; i++) {
-		head = classhash_table + i;
-		hlist_for_each_entry_rcu(class, head, hash_entry) {
-			int match = 0;
+	if (!locked)
+		goto out_irq;
 
-			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
-				match |= class == lock->class_cache[j];
+	pf = get_pending_free();
+	__lockdep_reset_lock(pf, lock);
+	call_rcu_zapped(pf);
 
-			if (unlikely(match)) {
-				if (debug_locks_off_graph_unlock()) {
-					/*
-					 * We all just reset everything, how did it match?
-					 */
-					WARN_ON(1);
-				}
-				goto out_restore;
-			}
-		}
-	}
-	if (locked)
-		graph_unlock();
-
-out_restore:
+	graph_unlock();
+out_irq:
 	raw_local_irq_restore(flags);
 }
 
+/*
+ * Reset a lock. Does not sleep. Ignores debug_locks. Must only be used by the
+ * lockdep selftests.
+ */
+static void lockdep_reset_lock_imm(struct lockdep_map *lock)
+{
+	struct pending_free *pf = delayed_free.pf;
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	arch_spin_lock(&lockdep_lock);
+	__lockdep_reset_lock(pf, lock);
+	__free_zapped_classes(pf);
+	arch_spin_unlock(&lockdep_lock);
+	raw_local_irq_restore(flags);
+}
+
+void lockdep_reset_lock(struct lockdep_map *lock)
+{
+	init_data_structures_once();
+
+	if (inside_selftest())
+		lockdep_reset_lock_imm(lock);
+	else
+		lockdep_reset_lock_reg(lock);
+}
+
+/* Unregister a dynamically allocated key. */
+void lockdep_unregister_key(struct lock_class_key *key)
+{
+	struct hlist_head *hash_head = keyhashentry(key);
+	struct lock_class_key *k;
+	struct pending_free *pf;
+	unsigned long flags;
+	bool found = false;
+
+	might_sleep();
+
+	if (WARN_ON_ONCE(static_obj(key)))
+		return;
+
+	raw_local_irq_save(flags);
+	if (!graph_lock())
+		goto out_irq;
+
+	pf = get_pending_free();
+	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
+		if (k == key) {
+			hlist_del_rcu(&k->hash_entry);
+			found = true;
+			break;
+		}
+	}
+	WARN_ON_ONCE(!found);
+	__lockdep_free_key_range(pf, key, 1);
+	call_rcu_zapped(pf);
+	graph_unlock();
+out_irq:
+	raw_local_irq_restore(flags);
+
+	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(lockdep_unregister_key);
+
 void __init lockdep_init(void)
 {
 	printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
@@ -4324,20 +5215,31 @@
 	printk("... MAX_LOCKDEP_CHAINS:      %lu\n", MAX_LOCKDEP_CHAINS);
 	printk("... CHAINHASH_SIZE:          %lu\n", CHAINHASH_SIZE);
 
-	printk(" memory used by lock dependency info: %lu kB\n",
-		(sizeof(struct lock_class) * MAX_LOCKDEP_KEYS +
-		sizeof(struct list_head) * CLASSHASH_SIZE +
-		sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES +
-		sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS +
-		sizeof(struct list_head) * CHAINHASH_SIZE
+	printk(" memory used by lock dependency info: %zu kB\n",
+	       (sizeof(lock_classes) +
+		sizeof(lock_classes_in_use) +
+		sizeof(classhash_table) +
+		sizeof(list_entries) +
+		sizeof(list_entries_in_use) +
+		sizeof(chainhash_table) +
+		sizeof(delayed_free)
 #ifdef CONFIG_PROVE_LOCKING
-		+ sizeof(struct circular_queue)
+		+ sizeof(lock_cq)
+		+ sizeof(lock_chains)
+		+ sizeof(lock_chains_in_use)
+		+ sizeof(chain_hlocks)
 #endif
 		) / 1024
 		);
 
-	printk(" per task-struct memory footprint: %lu bytes\n",
-		sizeof(struct held_lock) * MAX_LOCK_DEPTH);
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+	printk(" memory used for stack traces: %zu kB\n",
+	       (sizeof(stack_trace) + sizeof(stack_trace_hash)) / 1024
+	       );
+#endif
+
+	printk(" per task-struct memory footprint: %zu bytes\n",
+	       sizeof(((struct task_struct *)NULL)->held_locks));
 }
 
 static void
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index d459d62..18d85ae 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -22,6 +22,10 @@
 	LOCK_USAGE_STATES
 };
 
+#define LOCK_USAGE_READ_MASK 1
+#define LOCK_USAGE_DIR_MASK  2
+#define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
+
 /*
  * Usage-state bitmasks:
  */
@@ -38,13 +42,35 @@
 	__LOCKF(USED)
 };
 
-#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ)
-#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
+static const unsigned long LOCKF_ENABLED_IRQ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
 
-#define LOCKF_ENABLED_IRQ_READ \
-		(LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ)
-#define LOCKF_USED_IN_IRQ_READ \
-		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE |
+static const unsigned long LOCKF_USED_IN_IRQ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE##_READ |
+static const unsigned long LOCKF_ENABLED_IRQ_READ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE##_READ |
+static const unsigned long LOCKF_USED_IN_IRQ_READ =
+#include "lockdep_states.h"
+	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)
+
+#define LOCKF_IRQ (LOCKF_ENABLED_IRQ | LOCKF_USED_IN_IRQ)
+#define LOCKF_IRQ_READ (LOCKF_ENABLED_IRQ_READ | LOCKF_USED_IN_IRQ_READ)
 
 /*
  * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
@@ -66,6 +92,7 @@
 #define MAX_LOCKDEP_ENTRIES	16384UL
 #define MAX_LOCKDEP_CHAINS_BITS	15
 #define MAX_STACK_TRACE_ENTRIES	262144UL
+#define STACK_TRACE_HASH_SIZE	8192
 #else
 #define MAX_LOCKDEP_ENTRIES	32768UL
 
@@ -76,6 +103,7 @@
  * addresses. Protected by the hash_lock.
  */
 #define MAX_STACK_TRACE_ENTRIES	524288UL
+#define STACK_TRACE_HASH_SIZE	16384
 #endif
 
 #define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
@@ -90,13 +118,15 @@
 extern void get_usage_chars(struct lock_class *class,
 			    char usage[LOCK_USAGE_CHARS]);
 
-extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str);
+extern const char *__get_key_name(const struct lockdep_subclass_key *key,
+				  char *str);
 
 struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i);
 
 extern unsigned long nr_lock_classes;
 extern unsigned long nr_list_entries;
-extern unsigned long nr_lock_chains;
+long lockdep_next_lockchain(long i);
+unsigned long lock_chain_count(void);
 extern int nr_chain_hlocks;
 extern unsigned long nr_stack_trace_entries;
 
@@ -104,13 +134,16 @@
 extern unsigned int nr_softirq_chains;
 extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
-extern unsigned int max_recursion_depth;
 
 extern unsigned int max_bfs_queue_depth;
 
 #ifdef CONFIG_PROVE_LOCKING
 extern unsigned long lockdep_count_forward_deps(struct lock_class *);
 extern unsigned long lockdep_count_backward_deps(struct lock_class *);
+#ifdef CONFIG_TRACE_IRQFLAGS
+u64 lockdep_stack_trace_count(void);
+u64 lockdep_stack_hash_count(void);
+#endif
 #else
 static inline unsigned long
 lockdep_count_forward_deps(struct lock_class *class)
@@ -133,28 +166,31 @@
  * and we want to avoid too much cache bouncing.
  */
 struct lockdep_stats {
-	int	chain_lookup_hits;
-	int	chain_lookup_misses;
-	int	hardirqs_on_events;
-	int	hardirqs_off_events;
-	int	redundant_hardirqs_on;
-	int	redundant_hardirqs_off;
-	int	softirqs_on_events;
-	int	softirqs_off_events;
-	int	redundant_softirqs_on;
-	int	redundant_softirqs_off;
-	int	nr_unused_locks;
-	int	nr_redundant_checks;
-	int	nr_redundant;
-	int	nr_cyclic_checks;
-	int	nr_cyclic_check_recursions;
-	int	nr_find_usage_forwards_checks;
-	int	nr_find_usage_forwards_recursions;
-	int	nr_find_usage_backwards_checks;
-	int	nr_find_usage_backwards_recursions;
+	unsigned long  chain_lookup_hits;
+	unsigned int   chain_lookup_misses;
+	unsigned long  hardirqs_on_events;
+	unsigned long  hardirqs_off_events;
+	unsigned long  redundant_hardirqs_on;
+	unsigned long  redundant_hardirqs_off;
+	unsigned long  softirqs_on_events;
+	unsigned long  softirqs_off_events;
+	unsigned long  redundant_softirqs_on;
+	unsigned long  redundant_softirqs_off;
+	int            nr_unused_locks;
+	unsigned int   nr_redundant_checks;
+	unsigned int   nr_redundant;
+	unsigned int   nr_cyclic_checks;
+	unsigned int   nr_find_usage_forwards_checks;
+	unsigned int   nr_find_usage_backwards_checks;
+
+	/*
+	 * Per lock class locking operation stat counts
+	 */
+	unsigned long lock_class_ops[MAX_LOCKDEP_KEYS];
 };
 
 DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
+extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
 #define __debug_atomic_inc(ptr)					\
 	this_cpu_inc(lockdep_stats.ptr);
@@ -179,9 +215,30 @@
 	}								\
 	__total;							\
 })
+
+static inline void debug_class_ops_inc(struct lock_class *class)
+{
+	int idx;
+
+	idx = class - lock_classes;
+	__debug_atomic_inc(lock_class_ops[idx]);
+}
+
+static inline unsigned long debug_class_ops_read(struct lock_class *class)
+{
+	int idx, cpu;
+	unsigned long ops = 0;
+
+	idx = class - lock_classes;
+	for_each_possible_cpu(cpu)
+		ops += per_cpu(lockdep_stats.lock_class_ops[idx], cpu);
+	return ops;
+}
+
 #else
 # define __debug_atomic_inc(ptr)	do { } while (0)
 # define debug_atomic_inc(ptr)		do { } while (0)
 # define debug_atomic_dec(ptr)		do { } while (0)
 # define debug_atomic_read(ptr)		0
+# define debug_class_ops_inc(ptr)	do { } while (0)
 #endif
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 3dd980d..dadb7b7 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -68,7 +68,7 @@
 
 	seq_printf(m, "%p", class->key);
 #ifdef CONFIG_DEBUG_LOCKDEP
-	seq_printf(m, " OPS:%8ld", class->ops);
+	seq_printf(m, " OPS:%8ld", debug_class_ops_read(class));
 #endif
 #ifdef CONFIG_PROVE_LOCKING
 	seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class));
@@ -104,18 +104,18 @@
 #ifdef CONFIG_PROVE_LOCKING
 static void *lc_start(struct seq_file *m, loff_t *pos)
 {
+	if (*pos < 0)
+		return NULL;
+
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	if (*pos - 1 < nr_lock_chains)
-		return lock_chains + (*pos - 1);
-
-	return NULL;
+	return lock_chains + (*pos - 1);
 }
 
 static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	(*pos)++;
+	*pos = lockdep_next_lockchain(*pos - 1) + 1;
 	return lc_start(m, pos);
 }
 
@@ -200,7 +200,6 @@
 
 static int lockdep_stats_show(struct seq_file *m, void *v)
 {
-	struct lock_class *class;
 	unsigned long nr_unused = 0, nr_uncategorized = 0,
 		      nr_irq_safe = 0, nr_irq_unsafe = 0,
 		      nr_softirq_safe = 0, nr_softirq_unsafe = 0,
@@ -210,6 +209,9 @@
 		      nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0,
 		      sum_forward_deps = 0;
 
+#ifdef CONFIG_PROVE_LOCKING
+	struct lock_class *class;
+
 	list_for_each_entry(class, &all_lock_classes, lock_entry) {
 
 		if (class->usage_mask == 0)
@@ -241,13 +243,13 @@
 		if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ)
 			nr_hardirq_read_unsafe++;
 
-#ifdef CONFIG_PROVE_LOCKING
 		sum_forward_deps += lockdep_count_forward_deps(class);
-#endif
 	}
 #ifdef CONFIG_DEBUG_LOCKDEP
 	DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
 #endif
+
+#endif
 	seq_printf(m, " lock-classes:                  %11lu [max: %lu]\n",
 			nr_lock_classes, MAX_LOCKDEP_KEYS);
 	seq_printf(m, " direct dependencies:           %11lu [max: %lu]\n",
@@ -268,7 +270,7 @@
 
 #ifdef CONFIG_PROVE_LOCKING
 	seq_printf(m, " dependency chains:             %11lu [max: %lu]\n",
-			nr_lock_chains, MAX_LOCKDEP_CHAINS);
+			lock_chain_count(), MAX_LOCKDEP_CHAINS);
 	seq_printf(m, " dependency chain hlocks:       %11d [max: %lu]\n",
 			nr_chain_hlocks, MAX_LOCKDEP_CHAIN_HLOCKS);
 #endif
@@ -283,6 +285,12 @@
 			nr_process_chains);
 	seq_printf(m, " stack-trace entries:           %11lu [max: %lu]\n",
 			nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES);
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+	seq_printf(m, " number of stack traces:        %llu\n",
+		   lockdep_stack_trace_count());
+	seq_printf(m, " number of stack hash chains:   %llu\n",
+		   lockdep_stack_hash_count());
+#endif
 	seq_printf(m, " combined max dependencies:     %11u\n",
 			(nr_hardirq_chains + 1) *
 			(nr_softirq_chains + 1) *
@@ -397,7 +405,7 @@
 
 static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 {
-	struct lockdep_subclass_key *ckey;
+	const struct lockdep_subclass_key *ckey;
 	struct lock_class_stats *stats;
 	struct lock_class *class;
 	const char *cname;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 7d0b0ed..c513031 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Module-based torture test facility for locking
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
  * Copyright (C) IBM Corporation, 2014
  *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
  *          Davidlohr Bueso <dave@stgolabs.net>
  *	Based on kernel/rcu/torture.c.
  */
@@ -45,7 +32,7 @@
 #include <linux/torture.h>
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 
 torture_param(int, nwriters_stress, -1,
 	     "Number of write-locking stress-test threads");
@@ -842,7 +829,9 @@
 						"End of test: SUCCESS");
 
 	kfree(cxt.lwsa);
+	cxt.lwsa = NULL;
 	kfree(cxt.lrsa);
+	cxt.lrsa = NULL;
 
 end:
 	torture_cleanup_end();
@@ -970,7 +959,7 @@
 	/* Prepare torture context. */
 	if (onoff_interval > 0) {
 		firsterr = torture_onoff_init(onoff_holdoff * HZ,
-					      onoff_interval * HZ);
+					      onoff_interval * HZ, NULL);
 		if (firsterr)
 			goto unwind;
 	}
@@ -986,7 +975,7 @@
 			goto unwind;
 	}
 	if (stutter > 0) {
-		firsterr = torture_stutter_init(stutter);
+		firsterr = torture_stutter_init(stutter, stutter);
 		if (firsterr)
 			goto unwind;
 	}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 9aa7136..771d4ca 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -36,7 +36,7 @@
 
 void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter)
 {
-	SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+	lockdep_assert_held(&lock->wait_lock);
 	DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list));
 	DEBUG_LOCKS_WARN_ON(waiter->magic != waiter);
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
@@ -51,7 +51,7 @@
 void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			    struct task_struct *task)
 {
-	SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+	lockdep_assert_held(&lock->wait_lock);
 
 	/* Mark the current thread as blocked on the lock: */
 	task->blocked_on = waiter;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 3f8a351..468a9b8 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * kernel/locking/mutex.c
  *
@@ -15,7 +16,7 @@
  *    by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
  *    and Sven Dietrich.
  *
- * Also see Documentation/locking/mutex-design.txt.
+ * Also see Documentation/locking/mutex-design.rst.
  */
 #include <linux/mutex.h>
 #include <linux/ww_mutex.h>
@@ -64,11 +65,37 @@
 
 #define MUTEX_FLAGS		0x07
 
+/*
+ * Internal helper function; C doesn't allow us to hide it :/
+ *
+ * DO NOT USE (outside of mutex code).
+ */
+static inline struct task_struct *__mutex_owner(struct mutex *lock)
+{
+	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~MUTEX_FLAGS);
+}
+
 static inline struct task_struct *__owner_task(unsigned long owner)
 {
 	return (struct task_struct *)(owner & ~MUTEX_FLAGS);
 }
 
+bool mutex_is_locked(struct mutex *lock)
+{
+	return __mutex_owner(lock) != NULL;
+}
+EXPORT_SYMBOL(mutex_is_locked);
+
+__must_check enum mutex_trylock_recursive_enum
+mutex_trylock_recursive(struct mutex *lock)
+{
+	if (unlikely(__mutex_owner(lock) == current))
+		return MUTEX_TRYLOCK_RECURSIVE;
+
+	return mutex_trylock(lock);
+}
+EXPORT_SYMBOL(mutex_trylock_recursive);
+
 static inline unsigned long __owner_flags(unsigned long owner)
 {
 	return owner & MUTEX_FLAGS;
@@ -907,6 +934,10 @@
 
 	might_sleep();
 
+#ifdef CONFIG_DEBUG_MUTEXES
+	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
+#endif
+
 	ww = container_of(lock, struct ww_mutex, base);
 	if (use_ww_ctx && ww_ctx) {
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
@@ -987,7 +1018,7 @@
 		 * wait_lock. This ensures the lock cancellation is ordered
 		 * against mutex_unlock() and wake-ups do not go missing.
 		 */
-		if (unlikely(signal_pending_state(state, current))) {
+		if (signal_pending_state(state, current)) {
 			ret = -EINTR;
 			goto err;
 		}
@@ -1378,8 +1409,13 @@
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	bool locked = __mutex_trylock(lock);
+	bool locked;
 
+#ifdef CONFIG_DEBUG_MUTEXES
+	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
+#endif
+
+	locked = __mutex_trylock(lock);
 	if (locked)
 		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 883cf1b..364d38a 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 #include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
@@ -7,6 +8,8 @@
 #include <linux/sched.h>
 #include <linux/errno.h>
 
+#include "rwsem.h"
+
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
 			const char *name, struct lock_class_key *rwsem_key)
 {
@@ -15,7 +18,7 @@
 		return -ENOMEM;
 
 	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
-	rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
+	rcu_sync_init(&sem->rss);
 	__init_rwsem(&sem->rw_sem, name, rwsem_key);
 	rcuwait_init(&sem->writer);
 	sem->readers_block = 0;
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index c7471c3..fe9ca92 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Queued read/write locks
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
  *
  * Authors: Waiman Long <waiman.long@hp.com>
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index edd75e0..2473f10 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Queued spinlock
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
  * (C) Copyright 2013-2014,2018 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
@@ -74,12 +65,24 @@
  */
 
 #include "mcs_spinlock.h"
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-#define MAX_NODES	8
-#else
 #define MAX_NODES	4
+
+/*
+ * On 64-bit architectures, the mcs_spinlock structure will be 16 bytes in
+ * size and four of them will fit nicely in one 64-byte cacheline. For
+ * pvqspinlock, however, we need more space for extra data. To accommodate
+ * that, we insert two more long words to pad it up to 32 bytes. IOW, only
+ * two of them can fit in a cacheline in this case. That is OK as it is rare
+ * to have more than 2 levels of slowpath nesting in actual use. We don't
+ * want to penalize pvqspinlocks to optimize for a rare case in native
+ * qspinlocks.
+ */
+struct qnode {
+	struct mcs_spinlock mcs;
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+	long reserved[2];
 #endif
+};
 
 /*
  * The pending bit spinning loop count.
@@ -101,7 +104,7 @@
  *
  * PV doubles the storage and uses the second cacheline for PV state.
  */
-static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
+static DEFINE_PER_CPU_ALIGNED(struct qnode, qnodes[MAX_NODES]);
 
 /*
  * We must be able to distinguish between no-tail and the tail at 0:0,
@@ -112,9 +115,6 @@
 {
 	u32 tail;
 
-#ifdef CONFIG_DEBUG_SPINLOCK
-	BUG_ON(idx > 3);
-#endif
 	tail  = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
 	tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
 
@@ -126,7 +126,13 @@
 	int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
 	int idx = (tail &  _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
 
-	return per_cpu_ptr(&mcs_nodes[idx], cpu);
+	return per_cpu_ptr(&qnodes[idx].mcs, cpu);
+}
+
+static inline __pure
+struct mcs_spinlock *grab_mcs_node(struct mcs_spinlock *base, int idx)
+{
+	return &((struct qnode *)base + idx)->mcs;
 }
 
 #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
@@ -340,17 +346,23 @@
 	/*
 	 * trylock || pending
 	 *
-	 * 0,0,0 -> 0,0,1 ; trylock
-	 * 0,0,1 -> 0,1,1 ; pending
+	 * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock
 	 */
 	val = queued_fetch_set_pending_acquire(lock);
 
 	/*
-	 * If we observe any contention; undo and queue.
+	 * If we observe contention, there is a concurrent locker.
+	 *
+	 * Undo and queue; our setting of PENDING might have made the
+	 * n,0,0 -> 0,0,0 transition fail and it will now be waiting
+	 * on @next to become !NULL.
 	 */
 	if (unlikely(val & ~_Q_LOCKED_MASK)) {
+
+		/* Undo PENDING if we set it. */
 		if (!(val & _Q_PENDING_MASK))
 			clear_pending(lock);
+
 		goto queue;
 	}
 
@@ -374,7 +386,7 @@
 	 * 0,1,0 -> 0,0,1
 	 */
 	clear_pending_set_locked(lock);
-	qstat_inc(qstat_lock_pending, true);
+	lockevent_inc(lock_pending);
 	return;
 
 	/*
@@ -382,13 +394,34 @@
 	 * queuing.
 	 */
 queue:
-	qstat_inc(qstat_lock_slowpath, true);
+	lockevent_inc(lock_slowpath);
 pv_queue:
-	node = this_cpu_ptr(&mcs_nodes[0]);
+	node = this_cpu_ptr(&qnodes[0].mcs);
 	idx = node->count++;
 	tail = encode_tail(smp_processor_id(), idx);
 
-	node += idx;
+	/*
+	 * 4 nodes are allocated based on the assumption that there will
+	 * not be nested NMIs taking spinlocks. That may not be true in
+	 * some architectures even though the chance of needing more than
+	 * 4 nodes will still be extremely unlikely. When that happens,
+	 * we fall back to spinning on the lock directly without using
+	 * any MCS node. This is not the most elegant solution, but is
+	 * simple enough.
+	 */
+	if (unlikely(idx >= MAX_NODES)) {
+		lockevent_inc(lock_no_node);
+		while (!queued_spin_trylock(lock))
+			cpu_relax();
+		goto release;
+	}
+
+	node = grab_mcs_node(node, idx);
+
+	/*
+	 * Keep counts of non-zero index values:
+	 */
+	lockevent_cond_inc(lock_use_node2 + idx - 1, idx);
 
 	/*
 	 * Ensure that we increment the head node->count before initialising
@@ -489,16 +522,25 @@
 	 */
 
 	/*
-	 * In the PV case we might already have _Q_LOCKED_VAL set.
+	 * In the PV case we might already have _Q_LOCKED_VAL set, because
+	 * of lock stealing; therefore we must also allow:
 	 *
-	 * The atomic_cond_read_acquire() call above has provided the
-	 * necessary acquire semantics required for locking.
+	 * n,0,1 -> 0,0,1
+	 *
+	 * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the
+	 *       above wait condition, therefore any concurrent setting of
+	 *       PENDING will make the uncontended transition fail.
 	 */
-	if (((val & _Q_TAIL_MASK) == tail) &&
-	    atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
-		goto release; /* No contention */
+	if ((val & _Q_TAIL_MASK) == tail) {
+		if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+			goto release; /* No contention */
+	}
 
-	/* Either somebody is queued behind us or _Q_PENDING_VAL is set */
+	/*
+	 * Either somebody is queued behind us or _Q_PENDING_VAL got set
+	 * which will then detect the remaining tail and queue behind us
+	 * ensuring we'll see a @next.
+	 */
 	set_locked(lock);
 
 	/*
@@ -514,7 +556,7 @@
 	/*
 	 * release the node
 	 */
-	__this_cpu_dec(mcs_nodes[0].count);
+	__this_cpu_dec(qnodes[0].mcs.count);
 }
 EXPORT_SYMBOL(queued_spin_lock_slowpath);
 
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 5a0cf5f..e84d21a 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -4,7 +4,7 @@
 #endif
 
 #include <linux/hash.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/debug_locks.h>
 
 /*
@@ -49,8 +49,6 @@
 
 struct pv_node {
 	struct mcs_spinlock	mcs;
-	struct mcs_spinlock	__res[3];
-
 	int			cpu;
 	u8			state;
 };
@@ -91,7 +89,7 @@
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
 		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
-			qstat_inc(qstat_pv_lock_stealing, true);
+			lockevent_inc(pv_lock_stealing);
 			return true;
 		}
 		if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
@@ -221,7 +219,7 @@
 		hopcnt++;
 		if (!cmpxchg(&he->lock, NULL, lock)) {
 			WRITE_ONCE(he->node, node);
-			qstat_hop(hopcnt);
+			lockevent_pv_hop(hopcnt);
 			return &he->lock;
 		}
 	}
@@ -271,7 +269,7 @@
 	if ((loop & PV_PREV_CHECK_MASK) != 0)
 		return false;
 
-	return READ_ONCE(prev->state) != vcpu_running || vcpu_is_preempted(prev->cpu);
+	return READ_ONCE(prev->state) != vcpu_running;
 }
 
 /*
@@ -281,7 +279,7 @@
 {
 	struct pv_node *pn = (struct pv_node *)node;
 
-	BUILD_BUG_ON(sizeof(struct pv_node) > 5*sizeof(struct mcs_spinlock));
+	BUILD_BUG_ON(sizeof(struct pv_node) > sizeof(struct qnode));
 
 	pn->cpu = smp_processor_id();
 	pn->state = vcpu_running;
@@ -322,8 +320,8 @@
 		smp_store_mb(pn->state, vcpu_halted);
 
 		if (!READ_ONCE(node->locked)) {
-			qstat_inc(qstat_pv_wait_node, true);
-			qstat_inc(qstat_pv_wait_early, wait_early);
+			lockevent_inc(pv_wait_node);
+			lockevent_cond_inc(pv_wait_early, wait_early);
 			pv_wait(&pn->state, vcpu_halted);
 		}
 
@@ -341,7 +339,8 @@
 		 * So it is better to spin for a while in the hope that the
 		 * MCS lock will be released soon.
 		 */
-		qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked));
+		lockevent_cond_inc(pv_spurious_wakeup,
+				  !READ_ONCE(node->locked));
 	}
 
 	/*
@@ -418,7 +417,7 @@
 	/*
 	 * Tracking # of slowpath locking operations
 	 */
-	qstat_inc(qstat_lock_slowpath, true);
+	lockevent_inc(lock_slowpath);
 
 	for (;; waitcnt++) {
 		/*
@@ -466,8 +465,8 @@
 			}
 		}
 		WRITE_ONCE(pn->state, vcpu_hashed);
-		qstat_inc(qstat_pv_wait_head, true);
-		qstat_inc(qstat_pv_wait_again, waitcnt);
+		lockevent_inc(pv_wait_head);
+		lockevent_cond_inc(pv_wait_again, waitcnt);
 		pv_wait(&lock->locked, _Q_SLOW_VAL);
 
 		/*
@@ -530,7 +529,7 @@
 	 * vCPU is harmless other than the additional latency in completing
 	 * the unlock.
 	 */
-	qstat_inc(qstat_pv_kick_unlock, true);
+	lockevent_inc(pv_kick_unlock);
 	pv_kick(node->cpu);
 }
 
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 6bd78c0..e625bb4 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -1,255 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Authors: Waiman Long <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
  */
 
-/*
- * When queued spinlock statistical counters are enabled, the following
- * debugfs files will be created for reporting the counter values:
- *
- * <debugfs>/qlockstat/
- *   pv_hash_hops	- average # of hops per hashing operation
- *   pv_kick_unlock	- # of vCPU kicks issued at unlock time
- *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
- *   pv_latency_kick	- average latency (ns) of vCPU kick operation
- *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
- *   pv_lock_stealing	- # of lock stealing operations
- *   pv_spurious_wakeup	- # of spurious wakeups in non-head vCPUs
- *   pv_wait_again	- # of wait's after a queue head vCPU kick
- *   pv_wait_early	- # of early vCPU wait's
- *   pv_wait_head	- # of vCPU wait's at the queue head
- *   pv_wait_node	- # of vCPU wait's at a non-head queue node
- *   lock_pending	- # of locking operations via pending code
- *   lock_slowpath	- # of locking operations via MCS lock queue
- *
- * Writing to the "reset_counters" file will reset all the above counter
- * values.
- *
- * These statistical counters are implemented as per-cpu variables which are
- * summed and computed whenever the corresponding debugfs files are read. This
- * minimizes added overhead making the counters usable even in a production
- * environment.
- *
- * There may be slight difference between pv_kick_wake and pv_kick_unlock.
- */
-enum qlock_stats {
-	qstat_pv_hash_hops,
-	qstat_pv_kick_unlock,
-	qstat_pv_kick_wake,
-	qstat_pv_latency_kick,
-	qstat_pv_latency_wake,
-	qstat_pv_lock_stealing,
-	qstat_pv_spurious_wakeup,
-	qstat_pv_wait_again,
-	qstat_pv_wait_early,
-	qstat_pv_wait_head,
-	qstat_pv_wait_node,
-	qstat_lock_pending,
-	qstat_lock_slowpath,
-	qstat_num,	/* Total number of statistical counters */
-	qstat_reset_cnts = qstat_num,
-};
+#include "lock_events.h"
 
-#ifdef CONFIG_QUEUED_LOCK_STAT
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
 /*
- * Collect pvqspinlock statistics
+ * Collect pvqspinlock locking event counts
  */
-#include <linux/debugfs.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/fs.h>
 
-static const char * const qstat_names[qstat_num + 1] = {
-	[qstat_pv_hash_hops]	   = "pv_hash_hops",
-	[qstat_pv_kick_unlock]     = "pv_kick_unlock",
-	[qstat_pv_kick_wake]       = "pv_kick_wake",
-	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
-	[qstat_pv_latency_kick]	   = "pv_latency_kick",
-	[qstat_pv_latency_wake]    = "pv_latency_wake",
-	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
-	[qstat_pv_wait_again]      = "pv_wait_again",
-	[qstat_pv_wait_early]      = "pv_wait_early",
-	[qstat_pv_wait_head]       = "pv_wait_head",
-	[qstat_pv_wait_node]       = "pv_wait_node",
-	[qstat_lock_pending]       = "lock_pending",
-	[qstat_lock_slowpath]      = "lock_slowpath",
-	[qstat_reset_cnts]         = "reset_counters",
-};
+#define EVENT_COUNT(ev)	lockevents[LOCKEVENT_ ## ev]
 
 /*
- * Per-cpu counters
+ * PV specific per-cpu counter
  */
-static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]);
 static DEFINE_PER_CPU(u64, pv_kick_time);
 
 /*
- * Function to read and return the qlock statistical counter values
+ * Function to read and return the PV qspinlock counts.
  *
  * The following counters are handled specially:
- * 1. qstat_pv_latency_kick
+ * 1. pv_latency_kick
  *    Average kick latency (ns) = pv_latency_kick/pv_kick_unlock
- * 2. qstat_pv_latency_wake
+ * 2. pv_latency_wake
  *    Average wake latency (ns) = pv_latency_wake/pv_kick_wake
- * 3. qstat_pv_hash_hops
+ * 3. pv_hash_hops
  *    Average hops/hash = pv_hash_hops/pv_kick_unlock
  */
-static ssize_t qstat_read(struct file *file, char __user *user_buf,
-			  size_t count, loff_t *ppos)
+ssize_t lockevent_read(struct file *file, char __user *user_buf,
+		       size_t count, loff_t *ppos)
 {
 	char buf[64];
-	int cpu, counter, len;
-	u64 stat = 0, kicks = 0;
+	int cpu, id, len;
+	u64 sum = 0, kicks = 0;
 
 	/*
 	 * Get the counter ID stored in file->f_inode->i_private
 	 */
-	counter = (long)file_inode(file)->i_private;
+	id = (long)file_inode(file)->i_private;
 
-	if (counter >= qstat_num)
+	if (id >= lockevent_num)
 		return -EBADF;
 
 	for_each_possible_cpu(cpu) {
-		stat += per_cpu(qstats[counter], cpu);
+		sum += per_cpu(lockevents[id], cpu);
 		/*
-		 * Need to sum additional counter for some of them
+		 * Need to sum additional counters for some of them
 		 */
-		switch (counter) {
+		switch (id) {
 
-		case qstat_pv_latency_kick:
-		case qstat_pv_hash_hops:
-			kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu);
+		case LOCKEVENT_pv_latency_kick:
+		case LOCKEVENT_pv_hash_hops:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_unlock), cpu);
 			break;
 
-		case qstat_pv_latency_wake:
-			kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu);
+		case LOCKEVENT_pv_latency_wake:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_wake), cpu);
 			break;
 		}
 	}
 
-	if (counter == qstat_pv_hash_hops) {
+	if (id == LOCKEVENT_pv_hash_hops) {
 		u64 frac = 0;
 
 		if (kicks) {
-			frac = 100ULL * do_div(stat, kicks);
+			frac = 100ULL * do_div(sum, kicks);
 			frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
 		}
 
 		/*
 		 * Return a X.XX decimal number
 		 */
-		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac);
+		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n",
+			       sum, frac);
 	} else {
 		/*
 		 * Round to the nearest ns
 		 */
-		if ((counter == qstat_pv_latency_kick) ||
-		    (counter == qstat_pv_latency_wake)) {
+		if ((id == LOCKEVENT_pv_latency_kick) ||
+		    (id == LOCKEVENT_pv_latency_wake)) {
 			if (kicks)
-				stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
+				sum = DIV_ROUND_CLOSEST_ULL(sum, kicks);
 		}
-		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat);
+		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
 	}
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
 /*
- * Function to handle write request
- *
- * When counter = reset_cnts, reset all the counter values.
- * Since the counter updates aren't atomic, the resetting is done twice
- * to make sure that the counters are very likely to be all cleared.
- */
-static ssize_t qstat_write(struct file *file, const char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	int cpu;
-
-	/*
-	 * Get the counter ID stored in file->f_inode->i_private
-	 */
-	if ((long)file_inode(file)->i_private != qstat_reset_cnts)
-		return count;
-
-	for_each_possible_cpu(cpu) {
-		int i;
-		unsigned long *ptr = per_cpu_ptr(qstats, cpu);
-
-		for (i = 0 ; i < qstat_num; i++)
-			WRITE_ONCE(ptr[i], 0);
-	}
-	return count;
-}
-
-/*
- * Debugfs data structures
- */
-static const struct file_operations fops_qstat = {
-	.read = qstat_read,
-	.write = qstat_write,
-	.llseek = default_llseek,
-};
-
-/*
- * Initialize debugfs for the qspinlock statistical counters
- */
-static int __init init_qspinlock_stat(void)
-{
-	struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL);
-	int i;
-
-	if (!d_qstat)
-		goto out;
-
-	/*
-	 * Create the debugfs files
-	 *
-	 * As reading from and writing to the stat files can be slow, only
-	 * root is allowed to do the read/write to limit impact to system
-	 * performance.
-	 */
-	for (i = 0; i < qstat_num; i++)
-		if (!debugfs_create_file(qstat_names[i], 0400, d_qstat,
-					 (void *)(long)i, &fops_qstat))
-			goto fail_undo;
-
-	if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
-				 (void *)(long)qstat_reset_cnts, &fops_qstat))
-		goto fail_undo;
-
-	return 0;
-fail_undo:
-	debugfs_remove_recursive(d_qstat);
-out:
-	pr_warn("Could not create 'qlockstat' debugfs entries\n");
-	return -ENOMEM;
-}
-fs_initcall(init_qspinlock_stat);
-
-/*
- * Increment the PV qspinlock statistical counters
- */
-static inline void qstat_inc(enum qlock_stats stat, bool cond)
-{
-	if (cond)
-		this_cpu_inc(qstats[stat]);
-}
-
-/*
  * PV hash hop count
  */
-static inline void qstat_hop(int hopcnt)
+static inline void lockevent_pv_hop(int hopcnt)
 {
-	this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt);
+	this_cpu_add(EVENT_COUNT(pv_hash_hops), hopcnt);
 }
 
 /*
@@ -261,7 +111,7 @@
 
 	per_cpu(pv_kick_time, cpu) = start;
 	pv_kick(cpu);
-	this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start);
+	this_cpu_add(EVENT_COUNT(pv_latency_kick), sched_clock() - start);
 }
 
 /*
@@ -274,18 +124,19 @@
 	*pkick_time = 0;
 	pv_wait(ptr, val);
 	if (*pkick_time) {
-		this_cpu_add(qstats[qstat_pv_latency_wake],
+		this_cpu_add(EVENT_COUNT(pv_latency_wake),
 			     sched_clock() - *pkick_time);
-		qstat_inc(qstat_pv_kick_wake, true);
+		lockevent_inc(pv_kick_wake);
 	}
 }
 
 #define pv_kick(c)	__pv_kick(c)
 #define pv_wait(p, v)	__pv_wait(p, v)
 
-#else /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
 
-static inline void qstat_inc(enum qlock_stats stat, bool cond)	{ }
-static inline void qstat_hop(int hopcnt)			{ }
+#else /* CONFIG_LOCK_EVENT_COUNTS */
 
-#endif /* CONFIG_QUEUED_LOCK_STAT */
+static inline void lockevent_pv_hop(int hopcnt)	{ }
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2823d41..2874bf5 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * RT-Mutexes: simple blocking mutual exclusion locks with PI support
  *
@@ -8,7 +9,7 @@
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
  *
- *  See Documentation/locking/rt-mutex-design.txt for details.
+ *  See Documentation/locking/rt-mutex-design.rst for details.
  */
 #include <linux/spinlock.h>
 #include <linux/export.h>
@@ -627,8 +628,7 @@
 		}
 
 		/* [10] Grab the next task, i.e. owner of @lock */
-		task = rt_mutex_owner(lock);
-		get_task_struct(task);
+		task = get_task_struct(rt_mutex_owner(lock));
 		raw_spin_lock(&task->pi_lock);
 
 		/*
@@ -708,8 +708,7 @@
 	}
 
 	/* [10] Grab the next task, i.e. the owner of @lock */
-	task = rt_mutex_owner(lock);
-	get_task_struct(task);
+	task = get_task_struct(rt_mutex_owner(lock));
 	raw_spin_lock(&task->pi_lock);
 
 	/* [11] requeue the pi waiters if necessary */
@@ -1485,9 +1484,9 @@
 	__rt_mutex_lock(lock, subclass);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
-#endif
 
-#ifndef CONFIG_DEBUG_LOCK_ALLOC
+#else /* !CONFIG_DEBUG_LOCK_ALLOC */
+
 /**
  * rt_mutex_lock - lock a rt_mutex
  *
@@ -1726,12 +1725,33 @@
 	rt_mutex_set_owner(lock, NULL);
 }
 
+/**
+ * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: does _NOT_ remove the @waiter on failure; must either call
+ * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for PI-futex support.
+ */
 int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
 
@@ -1749,9 +1769,6 @@
 		ret = 0;
 	}
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
@@ -1763,12 +1780,18 @@
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
  *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
+ * on failure.
+ *
  * Returns:
  *  0 - task blocked on lock
  *  1 - acquired the lock for task, caller should wake it up
  * <0 - error
  *
- * Special API call for FUTEX_REQUEUE_PI support.
+ * Special API call for PI-futex support.
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
@@ -1778,6 +1801,8 @@
 
 	raw_spin_lock_irq(&lock->wait_lock);
 	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
@@ -1845,7 +1870,8 @@
  * @lock:		the rt_mutex we were woken on
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
+ * rt_mutex_wait_proxy_lock().
  *
  * Unless we acquired the lock; we're still enqueued on the wait-list and can
  * in fact still be granted ownership until we're removed. Therefore we can
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
deleted file mode 100644
index a7ffb2a..0000000
--- a/kernel/locking/rwsem-spinlock.c
+++ /dev/null
@@ -1,339 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
- * generic spinlock implementation
- *
- * Copyright (c) 2001   David Howells (dhowells@redhat.com).
- * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-#include <linux/rwsem.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/debug.h>
-#include <linux/export.h>
-
-enum rwsem_waiter_type {
-	RWSEM_WAITING_FOR_WRITE,
-	RWSEM_WAITING_FOR_READ
-};
-
-struct rwsem_waiter {
-	struct list_head list;
-	struct task_struct *task;
-	enum rwsem_waiter_type type;
-};
-
-int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	int ret = 1;
-	unsigned long flags;
-
-	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
-		ret = (sem->count != 0);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(rwsem_is_locked);
-
-/*
- * initialise the semaphore
- */
-void __init_rwsem(struct rw_semaphore *sem, const char *name,
-		  struct lock_class_key *key)
-{
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	/*
-	 * Make sure we are not reinitializing a held semaphore:
-	 */
-	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
-	lockdep_init_map(&sem->dep_map, name, key, 0);
-#endif
-	sem->count = 0;
-	raw_spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-EXPORT_SYMBOL(__init_rwsem);
-
-/*
- * handle the lock release when processes blocked on it that can now run
- * - if we come here, then:
- *   - the 'active count' _reached_ zero
- *   - the 'waiting count' is non-zero
- * - the spinlock must be held by the caller
- * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if wakewrite is non-zero
- */
-static inline struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
-{
-	struct rwsem_waiter *waiter;
-	struct task_struct *tsk;
-	int woken;
-
-	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-
-	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
-		if (wakewrite)
-			/* Wake up a writer. Note that we do not grant it the
-			 * lock - it will have to acquire it when it runs. */
-			wake_up_process(waiter->task);
-		goto out;
-	}
-
-	/* grant an infinite number of read locks to the front of the queue */
-	woken = 0;
-	do {
-		struct list_head *next = waiter->list.next;
-
-		list_del(&waiter->list);
-		tsk = waiter->task;
-		/*
-		 * Make sure we do not wakeup the next reader before
-		 * setting the nil condition to grant the next reader;
-		 * otherwise we could miss the wakeup on the other
-		 * side and end up sleeping again. See the pairing
-		 * in rwsem_down_read_failed().
-		 */
-		smp_mb();
-		waiter->task = NULL;
-		wake_up_process(tsk);
-		put_task_struct(tsk);
-		woken++;
-		if (next == &sem->wait_list)
-			break;
-		waiter = list_entry(next, struct rwsem_waiter, list);
-	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
-
-	sem->count += woken;
-
- out:
-	return sem;
-}
-
-/*
- * wake a single writer
- */
-static inline struct rw_semaphore *
-__rwsem_wake_one_writer(struct rw_semaphore *sem)
-{
-	struct rwsem_waiter *waiter;
-
-	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-	wake_up_process(waiter->task);
-
-	return sem;
-}
-
-/*
- * get a read lock on the semaphore
- */
-int __sched __down_read_common(struct rw_semaphore *sem, int state)
-{
-	struct rwsem_waiter waiter;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
-		/* granted */
-		sem->count++;
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		goto out;
-	}
-
-	/* set up my own style of waitqueue */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-	get_task_struct(current);
-
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* wait to be given the lock */
-	for (;;) {
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current))
-			goto out_nolock;
-		set_current_state(state);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		schedule();
-		raw_spin_lock_irqsave(&sem->wait_lock, flags);
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- out:
-	return 0;
-
-out_nolock:
-	/*
-	 * We didn't take the lock, so that there is a writer, which
-	 * is owner or the first waiter of the sem. If it's a waiter,
-	 * it will be woken by current owner. Not need to wake anybody.
-	 */
-	list_del(&waiter.list);
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	return -EINTR;
-}
-
-void __sched __down_read(struct rw_semaphore *sem)
-{
-	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_read_killable(struct rw_semaphore *sem)
-{
-	return __down_read_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-int __down_read_trylock(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	int ret = 0;
-
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
-		/* granted */
-		sem->count++;
-		ret = 1;
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-}
-
-/*
- * get a write lock on the semaphore
- */
-int __sched __down_write_common(struct rw_semaphore *sem, int state)
-{
-	struct rwsem_waiter waiter;
-	unsigned long flags;
-	int ret = 0;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	/* set up my own style of waitqueue */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_WRITE;
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* wait for someone to release the lock */
-	for (;;) {
-		/*
-		 * That is the key to support write lock stealing: allows the
-		 * task already on CPU to get the lock soon rather than put
-		 * itself into sleep and waiting for system woke it or someone
-		 * else in the head of the wait list up.
-		 */
-		if (sem->count == 0)
-			break;
-		if (signal_pending_state(state, current))
-			goto out_nolock;
-
-		set_current_state(state);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		schedule();
-		raw_spin_lock_irqsave(&sem->wait_lock, flags);
-	}
-	/* got the lock */
-	sem->count = -1;
-	list_del(&waiter.list);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-
-out_nolock:
-	list_del(&waiter.list);
-	if (!list_empty(&sem->wait_list) && sem->count >= 0)
-		__rwsem_do_wake(sem, 0);
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return -EINTR;
-}
-
-void __sched __down_write(struct rw_semaphore *sem)
-{
-	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_write_killable(struct rw_semaphore *sem)
-{
-	return __down_write_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-int __down_write_trylock(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count == 0) {
-		/* got the lock */
-		sem->count = -1;
-		ret = 1;
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-}
-
-/*
- * release a read lock on the semaphore
- */
-void __up_read(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (--sem->count == 0 && !list_empty(&sem->wait_list))
-		sem = __rwsem_wake_one_writer(sem);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * release a write lock on the semaphore
- */
-void __up_write(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	sem->count = 0;
-	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, 1);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * downgrade a write lock into a read lock
- * - just wake up any readers at the front of the queue
- */
-void __downgrade_write(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	sem->count = 1;
-	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, 0);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
deleted file mode 100644
index 3064c50..0000000
--- a/kernel/locking/rwsem-xadd.c
+++ /dev/null
@@ -1,707 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* rwsem.c: R/W semaphores: contention handling functions
- *
- * Written by David Howells (dhowells@redhat.com).
- * Derived from arch/i386/kernel/semaphore.c
- *
- * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
- * and Michel Lespinasse <walken@google.com>
- *
- * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
- * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
- */
-#include <linux/rwsem.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/rt.h>
-#include <linux/sched/wake_q.h>
-#include <linux/sched/debug.h>
-#include <linux/osq_lock.h>
-
-#include "rwsem.h"
-
-/*
- * Guide to the rw_semaphore's count field for common values.
- * (32-bit case illustrated, similar for 64-bit)
- *
- * 0x0000000X	(1) X readers active or attempting lock, no writer waiting
- *		    X = #active_readers + #readers attempting to lock
- *		    (X*ACTIVE_BIAS)
- *
- * 0x00000000	rwsem is unlocked, and no one is waiting for the lock or
- *		attempting to read lock or write lock.
- *
- * 0xffff000X	(1) X readers active or attempting lock, with waiters for lock
- *		    X = #active readers + # readers attempting lock
- *		    (X*ACTIVE_BIAS + WAITING_BIAS)
- *		(2) 1 writer attempting lock, no waiters for lock
- *		    X-1 = #active readers + #readers attempting lock
- *		    ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
- *		(3) 1 writer active, no waiters for lock
- *		    X-1 = #active readers + #readers attempting lock
- *		    ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
- *
- * 0xffff0001	(1) 1 reader active or attempting lock, waiters for lock
- *		    (WAITING_BIAS + ACTIVE_BIAS)
- *		(2) 1 writer active or attempting lock, no waiters for lock
- *		    (ACTIVE_WRITE_BIAS)
- *
- * 0xffff0000	(1) There are writers or readers queued but none active
- *		    or in the process of attempting lock.
- *		    (WAITING_BIAS)
- *		Note: writer can attempt to steal lock for this count by adding
- *		ACTIVE_WRITE_BIAS in cmpxchg and checking the old count
- *
- * 0xfffe0001	(1) 1 writer active, or attempting lock. Waiters on queue.
- *		    (ACTIVE_WRITE_BIAS + WAITING_BIAS)
- *
- * Note: Readers attempt to lock by adding ACTIVE_BIAS in down_read and checking
- *	 the count becomes more than 0 for successful lock acquisition,
- *	 i.e. the case where there are only readers or nobody has lock.
- *	 (1st and 2nd case above).
- *
- *	 Writers attempt to lock by adding ACTIVE_WRITE_BIAS in down_write and
- *	 checking the count becomes ACTIVE_WRITE_BIAS for successful lock
- *	 acquisition (i.e. nobody else has lock or attempts lock).  If
- *	 unsuccessful, in rwsem_down_write_failed, we'll check to see if there
- *	 are only waiters but none active (5th case above), and attempt to
- *	 steal the lock.
- *
- */
-
-/*
- * Initialize an rwsem:
- */
-void __init_rwsem(struct rw_semaphore *sem, const char *name,
-		  struct lock_class_key *key)
-{
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	/*
-	 * Make sure we are not reinitializing a held semaphore:
-	 */
-	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
-	lockdep_init_map(&sem->dep_map, name, key, 0);
-#endif
-	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
-	raw_spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	sem->owner = NULL;
-	osq_lock_init(&sem->osq);
-#endif
-}
-
-EXPORT_SYMBOL(__init_rwsem);
-
-enum rwsem_waiter_type {
-	RWSEM_WAITING_FOR_WRITE,
-	RWSEM_WAITING_FOR_READ
-};
-
-struct rwsem_waiter {
-	struct list_head list;
-	struct task_struct *task;
-	enum rwsem_waiter_type type;
-};
-
-enum rwsem_wake_type {
-	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
-	RWSEM_WAKE_READERS,	/* Wake readers only */
-	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
-};
-
-/*
- * handle the lock release when processes blocked on it that can now run
- * - if we come here from up_xxxx(), then:
- *   - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
- *   - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
- * - there must be someone on the queue
- * - the wait_lock must be held by the caller
- * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
- *   to actually wakeup the blocked task(s) and drop the reference count,
- *   preferably when the wait_lock is released
- * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only marked woken if downgrading is false
- */
-static void __rwsem_mark_wake(struct rw_semaphore *sem,
-			      enum rwsem_wake_type wake_type,
-			      struct wake_q_head *wake_q)
-{
-	struct rwsem_waiter *waiter, *tmp;
-	long oldcount, woken = 0, adjustment = 0;
-
-	/*
-	 * Take a peek at the queue head waiter such that we can determine
-	 * the wakeup(s) to perform.
-	 */
-	waiter = list_first_entry(&sem->wait_list, struct rwsem_waiter, list);
-
-	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
-		if (wake_type == RWSEM_WAKE_ANY) {
-			/*
-			 * Mark writer at the front of the queue for wakeup.
-			 * Until the task is actually later awoken later by
-			 * the caller, other writers are able to steal it.
-			 * Readers, on the other hand, will block as they
-			 * will notice the queued writer.
-			 */
-			wake_q_add(wake_q, waiter->task);
-		}
-
-		return;
-	}
-
-	/*
-	 * Writers might steal the lock before we grant it to the next reader.
-	 * We prefer to do the first reader grant before counting readers
-	 * so we can bail out early if a writer stole the lock.
-	 */
-	if (wake_type != RWSEM_WAKE_READ_OWNED) {
-		adjustment = RWSEM_ACTIVE_READ_BIAS;
- try_reader_grant:
-		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
-		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
-			/*
-			 * If the count is still less than RWSEM_WAITING_BIAS
-			 * after removing the adjustment, it is assumed that
-			 * a writer has stolen the lock. We have to undo our
-			 * reader grant.
-			 */
-			if (atomic_long_add_return(-adjustment, &sem->count) <
-			    RWSEM_WAITING_BIAS)
-				return;
-
-			/* Last active locker left. Retry waking readers. */
-			goto try_reader_grant;
-		}
-		/*
-		 * It is not really necessary to set it to reader-owned here,
-		 * but it gives the spinners an early indication that the
-		 * readers now have the lock.
-		 */
-		rwsem_set_reader_owned(sem);
-	}
-
-	/*
-	 * Grant an infinite number of read locks to the readers at the front
-	 * of the queue. We know that woken will be at least 1 as we accounted
-	 * for above. Note we increment the 'active part' of the count by the
-	 * number of readers before waking any processes up.
-	 */
-	list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) {
-		struct task_struct *tsk;
-
-		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
-			break;
-
-		woken++;
-		tsk = waiter->task;
-
-		wake_q_add(wake_q, tsk);
-		list_del(&waiter->list);
-		/*
-		 * Ensure that the last operation is setting the reader
-		 * waiter to nil such that rwsem_down_read_failed() cannot
-		 * race with do_exit() by always holding a reference count
-		 * to the task to wakeup.
-		 */
-		smp_store_release(&waiter->task, NULL);
-	}
-
-	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
-	if (list_empty(&sem->wait_list)) {
-		/* hit end of list above */
-		adjustment -= RWSEM_WAITING_BIAS;
-	}
-
-	if (adjustment)
-		atomic_long_add(adjustment, &sem->count);
-}
-
-/*
- * Wait for the read lock to be granted
- */
-static inline struct rw_semaphore __sched *
-__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
-	struct rwsem_waiter waiter;
-	DEFINE_WAKE_Q(wake_q);
-
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-
-	raw_spin_lock_irq(&sem->wait_lock);
-	if (list_empty(&sem->wait_list))
-		adjustment += RWSEM_WAITING_BIAS;
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* we're now waiting on the lock, but no longer actively locking */
-	count = atomic_long_add_return(adjustment, &sem->count);
-
-	/*
-	 * If there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (count == RWSEM_WAITING_BIAS ||
-	    (count > RWSEM_WAITING_BIAS &&
-	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-
-	/* wait to be given the lock */
-	while (true) {
-		set_current_state(state);
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current)) {
-			raw_spin_lock_irq(&sem->wait_lock);
-			if (waiter.task)
-				goto out_nolock;
-			raw_spin_unlock_irq(&sem->wait_lock);
-			break;
-		}
-		schedule();
-	}
-
-	__set_current_state(TASK_RUNNING);
-	return sem;
-out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	__set_current_state(TASK_RUNNING);
-	return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed_killable);
-
-/*
- * This function must be called with the sem->wait_lock held to prevent
- * race conditions between checking the rwsem wait list and setting the
- * sem->count accordingly.
- */
-static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
-{
-	/*
-	 * Avoid trying to acquire write lock if count isn't RWSEM_WAITING_BIAS.
-	 */
-	if (count != RWSEM_WAITING_BIAS)
-		return false;
-
-	/*
-	 * Acquire the lock by trying to set it to ACTIVE_WRITE_BIAS. If there
-	 * are other tasks on the wait list, we need to add on WAITING_BIAS.
-	 */
-	count = list_is_singular(&sem->wait_list) ?
-			RWSEM_ACTIVE_WRITE_BIAS :
-			RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS;
-
-	if (atomic_long_cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count)
-							== RWSEM_WAITING_BIAS) {
-		rwsem_set_owner(sem);
-		return true;
-	}
-
-	return false;
-}
-
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-/*
- * Try to acquire write lock before the writer has been put on wait queue.
- */
-static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
-{
-	long old, count = atomic_long_read(&sem->count);
-
-	while (true) {
-		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
-			return false;
-
-		old = atomic_long_cmpxchg_acquire(&sem->count, count,
-				      count + RWSEM_ACTIVE_WRITE_BIAS);
-		if (old == count) {
-			rwsem_set_owner(sem);
-			return true;
-		}
-
-		count = old;
-	}
-}
-
-static inline bool owner_on_cpu(struct task_struct *owner)
-{
-	/*
-	 * As lock holder preemption issue, we both skip spinning if
-	 * task is not on cpu or its cpu is preempted
-	 */
-	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-}
-
-static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
-{
-	struct task_struct *owner;
-	bool ret = true;
-
-	BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
-
-	if (need_resched())
-		return false;
-
-	rcu_read_lock();
-	owner = READ_ONCE(sem->owner);
-	if (owner) {
-		ret = is_rwsem_owner_spinnable(owner) &&
-		      owner_on_cpu(owner);
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
-/*
- * Return true only if we can still spin on the owner field of the rwsem.
- */
-static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
-{
-	struct task_struct *owner = READ_ONCE(sem->owner);
-
-	if (!is_rwsem_owner_spinnable(owner))
-		return false;
-
-	rcu_read_lock();
-	while (owner && (READ_ONCE(sem->owner) == owner)) {
-		/*
-		 * Ensure we emit the owner->on_cpu, dereference _after_
-		 * checking sem->owner still matches owner, if that fails,
-		 * owner might point to free()d memory, if it still matches,
-		 * the rcu_read_lock() ensures the memory stays valid.
-		 */
-		barrier();
-
-		/*
-		 * abort spinning when need_resched or owner is not running or
-		 * owner's cpu is preempted.
-		 */
-		if (need_resched() || !owner_on_cpu(owner)) {
-			rcu_read_unlock();
-			return false;
-		}
-
-		cpu_relax();
-	}
-	rcu_read_unlock();
-
-	/*
-	 * If there is a new owner or the owner is not set, we continue
-	 * spinning.
-	 */
-	return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
-}
-
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
-{
-	bool taken = false;
-
-	preempt_disable();
-
-	/* sem->wait_lock should not be held when doing optimistic spinning */
-	if (!rwsem_can_spin_on_owner(sem))
-		goto done;
-
-	if (!osq_lock(&sem->osq))
-		goto done;
-
-	/*
-	 * Optimistically spin on the owner field and attempt to acquire the
-	 * lock whenever the owner changes. Spinning will be stopped when:
-	 *  1) the owning writer isn't running; or
-	 *  2) readers own the lock as we can't determine if they are
-	 *     actively running or not.
-	 */
-	while (rwsem_spin_on_owner(sem)) {
-		/*
-		 * Try to acquire the lock
-		 */
-		if (rwsem_try_write_lock_unqueued(sem)) {
-			taken = true;
-			break;
-		}
-
-		/*
-		 * When there's no owner, we might have preempted between the
-		 * owner acquiring the lock and setting the owner field. If
-		 * we're an RT task that will live-lock because we won't let
-		 * the owner complete.
-		 */
-		if (!sem->owner && (need_resched() || rt_task(current)))
-			break;
-
-		/*
-		 * The cpu_relax() call is a compiler barrier which forces
-		 * everything in this loop to be re-loaded. We don't need
-		 * memory barriers as we'll eventually observe the right
-		 * values at the cost of a few extra spins.
-		 */
-		cpu_relax();
-	}
-	osq_unlock(&sem->osq);
-done:
-	preempt_enable();
-	return taken;
-}
-
-/*
- * Return true if the rwsem has active spinner
- */
-static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
-{
-	return osq_is_locked(&sem->osq);
-}
-
-#else
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
-{
-	return false;
-}
-
-static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
-{
-	return false;
-}
-#endif
-
-/*
- * Wait until we successfully acquire the write lock
- */
-static inline struct rw_semaphore *
-__rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count;
-	bool waiting = true; /* any queued threads before us */
-	struct rwsem_waiter waiter;
-	struct rw_semaphore *ret = sem;
-	DEFINE_WAKE_Q(wake_q);
-
-	/* undo write bias from down_write operation, stop active locking */
-	count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count);
-
-	/* do optimistic spinning and steal lock if possible */
-	if (rwsem_optimistic_spin(sem))
-		return sem;
-
-	/*
-	 * Optimistic spinning failed, proceed to the slowpath
-	 * and block until we can acquire the sem.
-	 */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_WRITE;
-
-	raw_spin_lock_irq(&sem->wait_lock);
-
-	/* account for this before adding a new element to the list */
-	if (list_empty(&sem->wait_list))
-		waiting = false;
-
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* we're now waiting on the lock, but no longer actively locking */
-	if (waiting) {
-		count = atomic_long_read(&sem->count);
-
-		/*
-		 * If there were already threads queued before us and there are
-		 * no active writers, the lock must be read owned; so we try to
-		 * wake any read locks that were queued ahead of us.
-		 */
-		if (count > RWSEM_WAITING_BIAS) {
-			__rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
-			/*
-			 * The wakeup is normally called _after_ the wait_lock
-			 * is released, but given that we are proactively waking
-			 * readers we can deal with the wake_q overhead as it is
-			 * similar to releasing and taking the wait_lock again
-			 * for attempting rwsem_try_write_lock().
-			 */
-			wake_up_q(&wake_q);
-
-			/*
-			 * Reinitialize wake_q after use.
-			 */
-			wake_q_init(&wake_q);
-		}
-
-	} else
-		count = atomic_long_add_return(RWSEM_WAITING_BIAS, &sem->count);
-
-	/* wait until we successfully acquire the lock */
-	set_current_state(state);
-	while (true) {
-		if (rwsem_try_write_lock(count, sem))
-			break;
-		raw_spin_unlock_irq(&sem->wait_lock);
-
-		/* Block until there are no active lockers. */
-		do {
-			if (signal_pending_state(state, current))
-				goto out_nolock;
-
-			schedule();
-			set_current_state(state);
-		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
-
-		raw_spin_lock_irq(&sem->wait_lock);
-	}
-	__set_current_state(TASK_RUNNING);
-	list_del(&waiter.list);
-	raw_spin_unlock_irq(&sem->wait_lock);
-
-	return ret;
-
-out_nolock:
-	__set_current_state(TASK_RUNNING);
-	raw_spin_lock_irq(&sem->wait_lock);
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	else
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-
-	return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_write_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_write_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_write_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_write_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_write_failed_killable);
-
-/*
- * handle waking up a waiter on the semaphore
- * - up_read/up_write has decremented the active part of count if we come here
- */
-__visible
-struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	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
-	 * unlock operation.
-	 *
-	 *    spinning writer		up_write/up_read caller
-	 *    ---------------		-----------------------
-	 * [S]   osq_unlock()		[L]   osq
-	 *	 MB			      RMB
-	 * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
-	 *
-	 * Here, it is important to make sure that there won't be a missed
-	 * wakeup while the rwsem is free and the only spinning writer goes
-	 * to sleep without taking the rwsem. Even when the spinning writer
-	 * is just going to break out of the waiting loop, it will still do
-	 * a trylock in rwsem_down_write_failed() before sleeping. IOW, if
-	 * rwsem_has_spinner() is true, it will guarantee at least one
-	 * trylock attempt on the rwsem later on.
-	 */
-	if (rwsem_has_spinner(sem)) {
-		/*
-		 * The smp_rmb() here is to make sure that the spinner
-		 * state is consulted before reading the wait_lock.
-		 */
-		smp_rmb();
-		if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
-			return sem;
-		goto locked;
-	}
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-locked:
-
-	if (!list_empty(&sem->wait_list))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	wake_up_q(&wake_q);
-
-	return sem;
-}
-EXPORT_SYMBOL(rwsem_wake);
-
-/*
- * downgrade a write lock into a read lock
- * - caller incremented waiting part of count and discovered it still negative
- * - just wake up any readers at the front of the queue
- */
-__visible
-struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	DEFINE_WAKE_Q(wake_q);
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (!list_empty(&sem->wait_list))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	wake_up_q(&wake_q);
-
-	return sem;
-}
-EXPORT_SYMBOL(rwsem_downgrade_wake);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 776308d..eef0455 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -3,17 +3,1488 @@
  *
  * Written by David Howells (dhowells@redhat.com).
  * Derived from asm-i386/semaphore.h
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
+ * and Michel Lespinasse <walken@google.com>
+ *
+ * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
+ * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
+ *
+ * Rwsem count bit fields re-definition and rwsem rearchitecture by
+ * Waiman Long <longman@redhat.com> and
+ * Peter Zijlstra <peterz@infradead.org>.
  */
 
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/task.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/clock.h>
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
 
 #include "rwsem.h"
+#include "lock_events.h"
+
+/*
+ * The least significant 3 bits of the owner value has the following
+ * meanings when set.
+ *  - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers
+ *  - Bit 1: RWSEM_RD_NONSPINNABLE - Readers cannot spin on this lock.
+ *  - Bit 2: RWSEM_WR_NONSPINNABLE - Writers cannot spin on this lock.
+ *
+ * When the rwsem is either owned by an anonymous writer, or it is
+ * reader-owned, but a spinning writer has timed out, both nonspinnable
+ * bits will be set to disable optimistic spinning by readers and writers.
+ * In the later case, the last unlocking reader should then check the
+ * writer nonspinnable bit and clear it only to give writers preference
+ * to acquire the lock via optimistic spinning, but not readers. Similar
+ * action is also done in the reader slowpath.
+
+ * When a writer acquires a rwsem, it puts its task_struct pointer
+ * into the owner field. It is cleared after an unlock.
+ *
+ * When a reader acquires a rwsem, it will also puts its task_struct
+ * pointer into the owner field with the RWSEM_READER_OWNED bit set.
+ * On unlock, the owner field will largely be left untouched. So
+ * for a free or reader-owned rwsem, the owner value may contain
+ * information about the last reader that acquires the rwsem.
+ *
+ * That information may be helpful in debugging cases where the system
+ * seems to hang on a reader owned rwsem especially if only one reader
+ * is involved. Ideally we would like to track all the readers that own
+ * a rwsem, but the overhead is simply too big.
+ *
+ * Reader optimistic spinning is helpful when the reader critical section
+ * is short and there aren't that many readers around. It makes readers
+ * relatively more preferred than writers. When a writer times out spinning
+ * on a reader-owned lock and set the nospinnable bits, there are two main
+ * reasons for that.
+ *
+ *  1) The reader critical section is long, perhaps the task sleeps after
+ *     acquiring the read lock.
+ *  2) There are just too many readers contending the lock causing it to
+ *     take a while to service all of them.
+ *
+ * In the former case, long reader critical section will impede the progress
+ * of writers which is usually more important for system performance. In
+ * the later case, reader optimistic spinning tends to make the reader
+ * groups that contain readers that acquire the lock together smaller
+ * leading to more of them. That may hurt performance in some cases. In
+ * other words, the setting of nonspinnable bits indicates that reader
+ * optimistic spinning may not be helpful for those workloads that cause
+ * it.
+ *
+ * Therefore, any writers that had observed the setting of the writer
+ * nonspinnable bit for a given rwsem after they fail to acquire the lock
+ * via optimistic spinning will set the reader nonspinnable bit once they
+ * acquire the write lock. Similarly, readers that observe the setting
+ * of reader nonspinnable bit at slowpath entry will set the reader
+ * nonspinnable bits when they acquire the read lock via the wakeup path.
+ *
+ * Once the reader nonspinnable bit is on, it will only be reset when
+ * a writer is able to acquire the rwsem in the fast path or somehow a
+ * reader or writer in the slowpath doesn't observe the nonspinable bit.
+ *
+ * This is to discourage reader optmistic spinning on that particular
+ * rwsem and make writers more preferred. This adaptive disabling of reader
+ * optimistic spinning will alleviate the negative side effect of this
+ * feature.
+ */
+#define RWSEM_READER_OWNED	(1UL << 0)
+#define RWSEM_RD_NONSPINNABLE	(1UL << 1)
+#define RWSEM_WR_NONSPINNABLE	(1UL << 2)
+#define RWSEM_NONSPINNABLE	(RWSEM_RD_NONSPINNABLE | RWSEM_WR_NONSPINNABLE)
+#define RWSEM_OWNER_FLAGS_MASK	(RWSEM_READER_OWNED | RWSEM_NONSPINNABLE)
+
+#ifdef CONFIG_DEBUG_RWSEMS
+# define DEBUG_RWSEMS_WARN_ON(c, sem)	do {			\
+	if (!debug_locks_silent &&				\
+	    WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, magic = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
+		#c, atomic_long_read(&(sem)->count),		\
+		(unsigned long) sem->magic,			\
+		atomic_long_read(&(sem)->owner), (long)current,	\
+		list_empty(&(sem)->wait_list) ? "" : "not "))	\
+			debug_locks_off();			\
+	} while (0)
+#else
+# define DEBUG_RWSEMS_WARN_ON(c, sem)
+#endif
+
+/*
+ * On 64-bit architectures, the bit definitions of the count are:
+ *
+ * Bit  0    - writer locked bit
+ * Bit  1    - waiters present bit
+ * Bit  2    - lock handoff bit
+ * Bits 3-7  - reserved
+ * Bits 8-62 - 55-bit reader count
+ * Bit  63   - read fail bit
+ *
+ * On 32-bit architectures, the bit definitions of the count are:
+ *
+ * Bit  0    - writer locked bit
+ * Bit  1    - waiters present bit
+ * Bit  2    - lock handoff bit
+ * Bits 3-7  - reserved
+ * Bits 8-30 - 23-bit reader count
+ * Bit  31   - read fail bit
+ *
+ * It is not likely that the most significant bit (read fail bit) will ever
+ * be set. This guard bit is still checked anyway in the down_read() fastpath
+ * just in case we need to use up more of the reader bits for other purpose
+ * in the future.
+ *
+ * atomic_long_fetch_add() is used to obtain reader lock, whereas
+ * atomic_long_cmpxchg() will be used to obtain writer lock.
+ *
+ * There are three places where the lock handoff bit may be set or cleared.
+ * 1) rwsem_mark_wake() for readers.
+ * 2) rwsem_try_write_lock() for writers.
+ * 3) Error path of rwsem_down_write_slowpath().
+ *
+ * For all the above cases, wait_lock will be held. A writer must also
+ * be the first one in the wait_list to be eligible for setting the handoff
+ * bit. So concurrent setting/clearing of handoff bit is not possible.
+ */
+#define RWSEM_WRITER_LOCKED	(1UL << 0)
+#define RWSEM_FLAG_WAITERS	(1UL << 1)
+#define RWSEM_FLAG_HANDOFF	(1UL << 2)
+#define RWSEM_FLAG_READFAIL	(1UL << (BITS_PER_LONG - 1))
+
+#define RWSEM_READER_SHIFT	8
+#define RWSEM_READER_BIAS	(1UL << RWSEM_READER_SHIFT)
+#define RWSEM_READER_MASK	(~(RWSEM_READER_BIAS - 1))
+#define RWSEM_WRITER_MASK	RWSEM_WRITER_LOCKED
+#define RWSEM_LOCK_MASK		(RWSEM_WRITER_MASK|RWSEM_READER_MASK)
+#define RWSEM_READ_FAILED_MASK	(RWSEM_WRITER_MASK|RWSEM_FLAG_WAITERS|\
+				 RWSEM_FLAG_HANDOFF|RWSEM_FLAG_READFAIL)
+
+/*
+ * All writes to owner are protected by WRITE_ONCE() to make sure that
+ * store tearing can't happen as optimistic spinners may read and use
+ * the owner value concurrently without lock. Read from owner, however,
+ * may not need READ_ONCE() as long as the pointer value is only used
+ * for comparison and isn't being dereferenced.
+ */
+static inline void rwsem_set_owner(struct rw_semaphore *sem)
+{
+	atomic_long_set(&sem->owner, (long)current);
+}
+
+static inline void rwsem_clear_owner(struct rw_semaphore *sem)
+{
+	atomic_long_set(&sem->owner, 0);
+}
+
+/*
+ * Test the flags in the owner field.
+ */
+static inline bool rwsem_test_oflags(struct rw_semaphore *sem, long flags)
+{
+	return atomic_long_read(&sem->owner) & flags;
+}
+
+/*
+ * The task_struct pointer of the last owning reader will be left in
+ * the owner field.
+ *
+ * Note that the owner value just indicates the task has owned the rwsem
+ * previously, it may not be the real owner or one of the real owners
+ * anymore when that field is examined, so take it with a grain of salt.
+ *
+ * The reader non-spinnable bit is preserved.
+ */
+static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
+					    struct task_struct *owner)
+{
+	unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED |
+		(atomic_long_read(&sem->owner) & RWSEM_RD_NONSPINNABLE);
+
+	atomic_long_set(&sem->owner, val);
+}
+
+static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
+{
+	__rwsem_set_reader_owned(sem, current);
+}
+
+/*
+ * Return true if the rwsem is owned by a reader.
+ */
+static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
+{
+#ifdef CONFIG_DEBUG_RWSEMS
+	/*
+	 * Check the count to see if it is write-locked.
+	 */
+	long count = atomic_long_read(&sem->count);
+
+	if (count & RWSEM_WRITER_MASK)
+		return false;
+#endif
+	return rwsem_test_oflags(sem, RWSEM_READER_OWNED);
+}
+
+#ifdef CONFIG_DEBUG_RWSEMS
+/*
+ * 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().
+ */
+static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
+{
+	unsigned long val = atomic_long_read(&sem->owner);
+
+	while ((val & ~RWSEM_OWNER_FLAGS_MASK) == (unsigned long)current) {
+		if (atomic_long_try_cmpxchg(&sem->owner, &val,
+					    val & RWSEM_OWNER_FLAGS_MASK))
+			return;
+	}
+}
+#else
+static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
+{
+}
+#endif
+
+/*
+ * Set the RWSEM_NONSPINNABLE bits if the RWSEM_READER_OWNED flag
+ * remains set. Otherwise, the operation will be aborted.
+ */
+static inline void rwsem_set_nonspinnable(struct rw_semaphore *sem)
+{
+	unsigned long owner = atomic_long_read(&sem->owner);
+
+	do {
+		if (!(owner & RWSEM_READER_OWNED))
+			break;
+		if (owner & RWSEM_NONSPINNABLE)
+			break;
+	} while (!atomic_long_try_cmpxchg(&sem->owner, &owner,
+					  owner | RWSEM_NONSPINNABLE));
+}
+
+static inline bool rwsem_read_trylock(struct rw_semaphore *sem)
+{
+	long cnt = atomic_long_add_return_acquire(RWSEM_READER_BIAS, &sem->count);
+	if (WARN_ON_ONCE(cnt < 0))
+		rwsem_set_nonspinnable(sem);
+	return !(cnt & RWSEM_READ_FAILED_MASK);
+}
+
+/*
+ * Return just the real task structure pointer of the owner
+ */
+static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+{
+	return (struct task_struct *)
+		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
+}
+
+/*
+ * Return the real task structure pointer of the owner and the embedded
+ * flags in the owner. pflags must be non-NULL.
+ */
+static inline struct task_struct *
+rwsem_owner_flags(struct rw_semaphore *sem, unsigned long *pflags)
+{
+	unsigned long owner = atomic_long_read(&sem->owner);
+
+	*pflags = owner & RWSEM_OWNER_FLAGS_MASK;
+	return (struct task_struct *)(owner & ~RWSEM_OWNER_FLAGS_MASK);
+}
+
+/*
+ * Guide to the rw_semaphore's count field.
+ *
+ * When the RWSEM_WRITER_LOCKED bit in count is set, the lock is owned
+ * by a writer.
+ *
+ * The lock is owned by readers when
+ * (1) the RWSEM_WRITER_LOCKED isn't set in count,
+ * (2) some of the reader bits are set in count, and
+ * (3) the owner field has RWSEM_READ_OWNED bit set.
+ *
+ * Having some reader bits set is not enough to guarantee a readers owned
+ * lock as the readers may be in the process of backing out from the count
+ * and a writer has just released the lock. So another writer may steal
+ * the lock immediately after that.
+ */
+
+/*
+ * Initialize an rwsem:
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+#ifdef CONFIG_DEBUG_RWSEMS
+	sem->magic = sem;
+#endif
+	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
+	raw_spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+	atomic_long_set(&sem->owner, 0L);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	osq_lock_init(&sem->osq);
+#endif
+}
+EXPORT_SYMBOL(__init_rwsem);
+
+enum rwsem_waiter_type {
+	RWSEM_WAITING_FOR_WRITE,
+	RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	enum rwsem_waiter_type type;
+	unsigned long timeout;
+	unsigned long last_rowner;
+};
+#define rwsem_first_waiter(sem) \
+	list_first_entry(&sem->wait_list, struct rwsem_waiter, list)
+
+enum rwsem_wake_type {
+	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
+	RWSEM_WAKE_READERS,	/* Wake readers only */
+	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
+};
+
+enum writer_wait_state {
+	WRITER_NOT_FIRST,	/* Writer is not first in wait list */
+	WRITER_FIRST,		/* Writer is first in wait list     */
+	WRITER_HANDOFF		/* Writer is first & handoff needed */
+};
+
+/*
+ * The typical HZ value is either 250 or 1000. So set the minimum waiting
+ * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait
+ * queue before initiating the handoff protocol.
+ */
+#define RWSEM_WAIT_TIMEOUT	DIV_ROUND_UP(HZ, 250)
+
+/*
+ * Magic number to batch-wakeup waiting readers, even when writers are
+ * also present in the queue. This both limits the amount of work the
+ * waking thread must do and also prevents any potential counter overflow,
+ * however unlikely.
+ */
+#define MAX_READERS_WAKEUP	0x100
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must
+ *   have been set.
+ * - there must be someone on the queue
+ * - the wait_lock must be held by the caller
+ * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
+ *   to actually wakeup the blocked task(s) and drop the reference count,
+ *   preferably when the wait_lock is released
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only marked woken if downgrading is false
+ */
+static void rwsem_mark_wake(struct rw_semaphore *sem,
+			    enum rwsem_wake_type wake_type,
+			    struct wake_q_head *wake_q)
+{
+	struct rwsem_waiter *waiter, *tmp;
+	long oldcount, woken = 0, adjustment = 0;
+	struct list_head wlist;
+
+	lockdep_assert_held(&sem->wait_lock);
+
+	/*
+	 * Take a peek at the queue head waiter such that we can determine
+	 * the wakeup(s) to perform.
+	 */
+	waiter = rwsem_first_waiter(sem);
+
+	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+		if (wake_type == RWSEM_WAKE_ANY) {
+			/*
+			 * Mark writer at the front of the queue for wakeup.
+			 * Until the task is actually later awoken later by
+			 * the caller, other writers are able to steal it.
+			 * Readers, on the other hand, will block as they
+			 * will notice the queued writer.
+			 */
+			wake_q_add(wake_q, waiter->task);
+			lockevent_inc(rwsem_wake_writer);
+		}
+
+		return;
+	}
+
+	/*
+	 * No reader wakeup if there are too many of them already.
+	 */
+	if (unlikely(atomic_long_read(&sem->count) < 0))
+		return;
+
+	/*
+	 * Writers might steal the lock before we grant it to the next reader.
+	 * We prefer to do the first reader grant before counting readers
+	 * so we can bail out early if a writer stole the lock.
+	 */
+	if (wake_type != RWSEM_WAKE_READ_OWNED) {
+		struct task_struct *owner;
+
+		adjustment = RWSEM_READER_BIAS;
+		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
+		if (unlikely(oldcount & RWSEM_WRITER_MASK)) {
+			/*
+			 * When we've been waiting "too" long (for writers
+			 * to give up the lock), request a HANDOFF to
+			 * force the issue.
+			 */
+			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
+			    time_after(jiffies, waiter->timeout)) {
+				adjustment -= RWSEM_FLAG_HANDOFF;
+				lockevent_inc(rwsem_rlock_handoff);
+			}
+
+			atomic_long_add(-adjustment, &sem->count);
+			return;
+		}
+		/*
+		 * Set it to reader-owned to give spinners an early
+		 * indication that readers now have the lock.
+		 * The reader nonspinnable bit seen at slowpath entry of
+		 * the reader is copied over.
+		 */
+		owner = waiter->task;
+		if (waiter->last_rowner & RWSEM_RD_NONSPINNABLE) {
+			owner = (void *)((unsigned long)owner | RWSEM_RD_NONSPINNABLE);
+			lockevent_inc(rwsem_opt_norspin);
+		}
+		__rwsem_set_reader_owned(sem, owner);
+	}
+
+	/*
+	 * Grant up to MAX_READERS_WAKEUP read locks to all the readers in the
+	 * queue. We know that the woken will be at least 1 as we accounted
+	 * for above. Note we increment the 'active part' of the count by the
+	 * number of readers before waking any processes up.
+	 *
+	 * This is an adaptation of the phase-fair R/W locks where at the
+	 * reader phase (first waiter is a reader), all readers are eligible
+	 * to acquire the lock at the same time irrespective of their order
+	 * in the queue. The writers acquire the lock according to their
+	 * order in the queue.
+	 *
+	 * We have to do wakeup in 2 passes to prevent the possibility that
+	 * the reader count may be decremented before it is incremented. It
+	 * is because the to-be-woken waiter may not have slept yet. So it
+	 * may see waiter->task got cleared, finish its critical section and
+	 * do an unlock before the reader count increment.
+	 *
+	 * 1) Collect the read-waiters in a separate list, count them and
+	 *    fully increment the reader count in rwsem.
+	 * 2) For each waiters in the new list, clear waiter->task and
+	 *    put them into wake_q to be woken up later.
+	 */
+	INIT_LIST_HEAD(&wlist);
+	list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) {
+		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
+			continue;
+
+		woken++;
+		list_move_tail(&waiter->list, &wlist);
+
+		/*
+		 * Limit # of readers that can be woken up per wakeup call.
+		 */
+		if (woken >= MAX_READERS_WAKEUP)
+			break;
+	}
+
+	adjustment = woken * RWSEM_READER_BIAS - adjustment;
+	lockevent_cond_inc(rwsem_wake_reader, woken);
+	if (list_empty(&sem->wait_list)) {
+		/* hit end of list above */
+		adjustment -= RWSEM_FLAG_WAITERS;
+	}
+
+	/*
+	 * When we've woken a reader, we no longer need to force writers
+	 * to give up the lock and we can clear HANDOFF.
+	 */
+	if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF))
+		adjustment -= RWSEM_FLAG_HANDOFF;
+
+	if (adjustment)
+		atomic_long_add(adjustment, &sem->count);
+
+	/* 2nd pass */
+	list_for_each_entry_safe(waiter, tmp, &wlist, list) {
+		struct task_struct *tsk;
+
+		tsk = waiter->task;
+		get_task_struct(tsk);
+
+		/*
+		 * Ensure calling get_task_struct() before setting the reader
+		 * waiter to nil such that rwsem_down_read_slowpath() cannot
+		 * race with do_exit() by always holding a reference count
+		 * to the task to wakeup.
+		 */
+		smp_store_release(&waiter->task, NULL);
+		/*
+		 * Ensure issuing the wakeup (either by us or someone else)
+		 * after setting the reader waiter to nil.
+		 */
+		wake_q_add_safe(wake_q, tsk);
+	}
+}
+
+/*
+ * This function must be called with the sem->wait_lock held to prevent
+ * race conditions between checking the rwsem wait list and setting the
+ * sem->count accordingly.
+ *
+ * If wstate is WRITER_HANDOFF, it will make sure that either the handoff
+ * bit is set or the lock is acquired with handoff bit cleared.
+ */
+static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
+					enum writer_wait_state wstate)
+{
+	long count, new;
+
+	lockdep_assert_held(&sem->wait_lock);
+
+	count = atomic_long_read(&sem->count);
+	do {
+		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
+
+		if (has_handoff && wstate == WRITER_NOT_FIRST)
+			return false;
+
+		new = count;
+
+		if (count & RWSEM_LOCK_MASK) {
+			if (has_handoff || (wstate != WRITER_HANDOFF))
+				return false;
+
+			new |= RWSEM_FLAG_HANDOFF;
+		} else {
+			new |= RWSEM_WRITER_LOCKED;
+			new &= ~RWSEM_FLAG_HANDOFF;
+
+			if (list_is_singular(&sem->wait_list))
+				new &= ~RWSEM_FLAG_WAITERS;
+		}
+	} while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new));
+
+	/*
+	 * We have either acquired the lock with handoff bit cleared or
+	 * set the handoff bit.
+	 */
+	if (new & RWSEM_FLAG_HANDOFF)
+		return false;
+
+	rwsem_set_owner(sem);
+	return true;
+}
+
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+/*
+ * Try to acquire read lock before the reader is put on wait queue.
+ * Lock acquisition isn't allowed if the rwsem is locked or a writer handoff
+ * is ongoing.
+ */
+static inline bool rwsem_try_read_lock_unqueued(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+
+	if (count & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))
+		return false;
+
+	count = atomic_long_fetch_add_acquire(RWSEM_READER_BIAS, &sem->count);
+	if (!(count & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+		rwsem_set_reader_owned(sem);
+		lockevent_inc(rwsem_opt_rlock);
+		return true;
+	}
+
+	/* Back out the change */
+	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
+	return false;
+}
+
+/*
+ * Try to acquire write lock before the writer has been put on wait queue.
+ */
+static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+
+	while (!(count & (RWSEM_LOCK_MASK|RWSEM_FLAG_HANDOFF))) {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
+					count | RWSEM_WRITER_LOCKED)) {
+			rwsem_set_owner(sem);
+			lockevent_inc(rwsem_opt_wlock);
+			return true;
+		}
+	}
+	return false;
+}
+
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+	/*
+	 * As lock holder preemption issue, we both skip spinning if
+	 * task is not on cpu or its cpu is preempted
+	 */
+	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
+static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem,
+					   unsigned long nonspinnable)
+{
+	struct task_struct *owner;
+	unsigned long flags;
+	bool ret = true;
+
+	BUILD_BUG_ON(!(RWSEM_OWNER_UNKNOWN & RWSEM_NONSPINNABLE));
+
+	if (need_resched()) {
+		lockevent_inc(rwsem_opt_fail);
+		return false;
+	}
+
+	preempt_disable();
+	rcu_read_lock();
+	owner = rwsem_owner_flags(sem, &flags);
+	/*
+	 * Don't check the read-owner as the entry may be stale.
+	 */
+	if ((flags & nonspinnable) ||
+	    (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner)))
+		ret = false;
+	rcu_read_unlock();
+	preempt_enable();
+
+	lockevent_cond_inc(rwsem_opt_fail, !ret);
+	return ret;
+}
+
+/*
+ * The rwsem_spin_on_owner() function returns the folowing 4 values
+ * depending on the lock owner state.
+ *   OWNER_NULL  : owner is currently NULL
+ *   OWNER_WRITER: when owner changes and is a writer
+ *   OWNER_READER: when owner changes and the new owner may be a reader.
+ *   OWNER_NONSPINNABLE:
+ *		   when optimistic spinning has to stop because either the
+ *		   owner stops running, is unknown, or its timeslice has
+ *		   been used up.
+ */
+enum owner_state {
+	OWNER_NULL		= 1 << 0,
+	OWNER_WRITER		= 1 << 1,
+	OWNER_READER		= 1 << 2,
+	OWNER_NONSPINNABLE	= 1 << 3,
+};
+#define OWNER_SPINNABLE		(OWNER_NULL | OWNER_WRITER | OWNER_READER)
+
+static inline enum owner_state
+rwsem_owner_state(struct task_struct *owner, unsigned long flags, unsigned long nonspinnable)
+{
+	if (flags & nonspinnable)
+		return OWNER_NONSPINNABLE;
+
+	if (flags & RWSEM_READER_OWNED)
+		return OWNER_READER;
+
+	return owner ? OWNER_WRITER : OWNER_NULL;
+}
+
+static noinline enum owner_state
+rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable)
+{
+	struct task_struct *new, *owner;
+	unsigned long flags, new_flags;
+	enum owner_state state;
+
+	owner = rwsem_owner_flags(sem, &flags);
+	state = rwsem_owner_state(owner, flags, nonspinnable);
+	if (state != OWNER_WRITER)
+		return state;
+
+	rcu_read_lock();
+	for (;;) {
+		/*
+		 * When a waiting writer set the handoff flag, it may spin
+		 * on the owner as well. Once that writer acquires the lock,
+		 * we can spin on it. So we don't need to quit even when the
+		 * handoff bit is set.
+		 */
+		new = rwsem_owner_flags(sem, &new_flags);
+		if ((new != owner) || (new_flags != flags)) {
+			state = rwsem_owner_state(new, new_flags, nonspinnable);
+			break;
+		}
+
+		/*
+		 * Ensure we emit the owner->on_cpu, dereference _after_
+		 * checking sem->owner still matches owner, if that fails,
+		 * owner might point to free()d memory, if it still matches,
+		 * the rcu_read_lock() ensures the memory stays valid.
+		 */
+		barrier();
+
+		if (need_resched() || !owner_on_cpu(owner)) {
+			state = OWNER_NONSPINNABLE;
+			break;
+		}
+
+		cpu_relax();
+	}
+	rcu_read_unlock();
+
+	return state;
+}
+
+/*
+ * Calculate reader-owned rwsem spinning threshold for writer
+ *
+ * The more readers own the rwsem, the longer it will take for them to
+ * wind down and free the rwsem. So the empirical formula used to
+ * determine the actual spinning time limit here is:
+ *
+ *   Spinning threshold = (10 + nr_readers/2)us
+ *
+ * The limit is capped to a maximum of 25us (30 readers). This is just
+ * a heuristic and is subjected to change in the future.
+ */
+static inline u64 rwsem_rspin_threshold(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+	int readers = count >> RWSEM_READER_SHIFT;
+	u64 delta;
+
+	if (readers > 30)
+		readers = 30;
+	delta = (20 + readers) * NSEC_PER_USEC / 2;
+
+	return sched_clock() + delta;
+}
+
+static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
+{
+	bool taken = false;
+	int prev_owner_state = OWNER_NULL;
+	int loop = 0;
+	u64 rspin_threshold = 0;
+	unsigned long nonspinnable = wlock ? RWSEM_WR_NONSPINNABLE
+					   : RWSEM_RD_NONSPINNABLE;
+
+	preempt_disable();
+
+	/* sem->wait_lock should not be held when doing optimistic spinning */
+	if (!osq_lock(&sem->osq))
+		goto done;
+
+	/*
+	 * Optimistically spin on the owner field and attempt to acquire the
+	 * lock whenever the owner changes. Spinning will be stopped when:
+	 *  1) the owning writer isn't running; or
+	 *  2) readers own the lock and spinning time has exceeded limit.
+	 */
+	for (;;) {
+		enum owner_state owner_state;
+
+		owner_state = rwsem_spin_on_owner(sem, nonspinnable);
+		if (!(owner_state & OWNER_SPINNABLE))
+			break;
+
+		/*
+		 * Try to acquire the lock
+		 */
+		taken = wlock ? rwsem_try_write_lock_unqueued(sem)
+			      : rwsem_try_read_lock_unqueued(sem);
+
+		if (taken)
+			break;
+
+		/*
+		 * Time-based reader-owned rwsem optimistic spinning
+		 */
+		if (wlock && (owner_state == OWNER_READER)) {
+			/*
+			 * Re-initialize rspin_threshold every time when
+			 * the owner state changes from non-reader to reader.
+			 * This allows a writer to steal the lock in between
+			 * 2 reader phases and have the threshold reset at
+			 * the beginning of the 2nd reader phase.
+			 */
+			if (prev_owner_state != OWNER_READER) {
+				if (rwsem_test_oflags(sem, nonspinnable))
+					break;
+				rspin_threshold = rwsem_rspin_threshold(sem);
+				loop = 0;
+			}
+
+			/*
+			 * Check time threshold once every 16 iterations to
+			 * avoid calling sched_clock() too frequently so
+			 * as to reduce the average latency between the times
+			 * when the lock becomes free and when the spinner
+			 * is ready to do a trylock.
+			 */
+			else if (!(++loop & 0xf) && (sched_clock() > rspin_threshold)) {
+				rwsem_set_nonspinnable(sem);
+				lockevent_inc(rwsem_opt_nospin);
+				break;
+			}
+		}
+
+		/*
+		 * An RT task cannot do optimistic spinning if it cannot
+		 * be sure the lock holder is running or live-lock may
+		 * happen if the current task and the lock holder happen
+		 * to run in the same CPU. However, aborting optimistic
+		 * spinning while a NULL owner is detected may miss some
+		 * opportunity where spinning can continue without causing
+		 * problem.
+		 *
+		 * There are 2 possible cases where an RT task may be able
+		 * to continue spinning.
+		 *
+		 * 1) The lock owner is in the process of releasing the
+		 *    lock, sem->owner is cleared but the lock has not
+		 *    been released yet.
+		 * 2) The lock was free and owner cleared, but another
+		 *    task just comes in and acquire the lock before
+		 *    we try to get it. The new owner may be a spinnable
+		 *    writer.
+		 *
+		 * To take advantage of two scenarios listed agove, the RT
+		 * task is made to retry one more time to see if it can
+		 * acquire the lock or continue spinning on the new owning
+		 * writer. Of course, if the time lag is long enough or the
+		 * new owner is not a writer or spinnable, the RT task will
+		 * quit spinning.
+		 *
+		 * If the owner is a writer, the need_resched() check is
+		 * done inside rwsem_spin_on_owner(). If the owner is not
+		 * a writer, need_resched() check needs to be done here.
+		 */
+		if (owner_state != OWNER_WRITER) {
+			if (need_resched())
+				break;
+			if (rt_task(current) &&
+			   (prev_owner_state != OWNER_WRITER))
+				break;
+		}
+		prev_owner_state = owner_state;
+
+		/*
+		 * The cpu_relax() call is a compiler barrier which forces
+		 * everything in this loop to be re-loaded. We don't need
+		 * memory barriers as we'll eventually observe the right
+		 * values at the cost of a few extra spins.
+		 */
+		cpu_relax();
+	}
+	osq_unlock(&sem->osq);
+done:
+	preempt_enable();
+	lockevent_cond_inc(rwsem_opt_fail, !taken);
+	return taken;
+}
+
+/*
+ * Clear the owner's RWSEM_WR_NONSPINNABLE bit if it is set. This should
+ * only be called when the reader count reaches 0.
+ *
+ * This give writers better chance to acquire the rwsem first before
+ * readers when the rwsem was being held by readers for a relatively long
+ * period of time. Race can happen that an optimistic spinner may have
+ * just stolen the rwsem and set the owner, but just clearing the
+ * RWSEM_WR_NONSPINNABLE bit will do no harm anyway.
+ */
+static inline void clear_wr_nonspinnable(struct rw_semaphore *sem)
+{
+	if (rwsem_test_oflags(sem, RWSEM_WR_NONSPINNABLE))
+		atomic_long_andnot(RWSEM_WR_NONSPINNABLE, &sem->owner);
+}
+
+/*
+ * This function is called when the reader fails to acquire the lock via
+ * optimistic spinning. In this case we will still attempt to do a trylock
+ * when comparing the rwsem state right now with the state when entering
+ * the slowpath indicates that the reader is still in a valid reader phase.
+ * This happens when the following conditions are true:
+ *
+ * 1) The lock is currently reader owned, and
+ * 2) The lock is previously not reader-owned or the last read owner changes.
+ *
+ * In the former case, we have transitioned from a writer phase to a
+ * reader-phase while spinning. In the latter case, it means the reader
+ * phase hasn't ended when we entered the optimistic spinning loop. In
+ * both cases, the reader is eligible to acquire the lock. This is the
+ * secondary path where a read lock is acquired optimistically.
+ *
+ * The reader non-spinnable bit wasn't set at time of entry or it will
+ * not be here at all.
+ */
+static inline bool rwsem_reader_phase_trylock(struct rw_semaphore *sem,
+					      unsigned long last_rowner)
+{
+	unsigned long owner = atomic_long_read(&sem->owner);
+
+	if (!(owner & RWSEM_READER_OWNED))
+		return false;
+
+	if (((owner ^ last_rowner) & ~RWSEM_OWNER_FLAGS_MASK) &&
+	    rwsem_try_read_lock_unqueued(sem)) {
+		lockevent_inc(rwsem_opt_rlock2);
+		lockevent_add(rwsem_opt_fail, -1);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem,
+					   unsigned long nonspinnable)
+{
+	return false;
+}
+
+static inline bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
+{
+	return false;
+}
+
+static inline void clear_wr_nonspinnable(struct rw_semaphore *sem) { }
+
+static inline bool rwsem_reader_phase_trylock(struct rw_semaphore *sem,
+					      unsigned long last_rowner)
+{
+	return false;
+}
+
+static inline int
+rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable)
+{
+	return 0;
+}
+#define OWNER_NULL	1
+#endif
+
+/*
+ * Wait for the read lock to be granted
+ */
+static struct rw_semaphore __sched *
+rwsem_down_read_slowpath(struct rw_semaphore *sem, int state)
+{
+	long count, adjustment = -RWSEM_READER_BIAS;
+	struct rwsem_waiter waiter;
+	DEFINE_WAKE_Q(wake_q);
+	bool wake = false;
+
+	/*
+	 * Save the current read-owner of rwsem, if available, and the
+	 * reader nonspinnable bit.
+	 */
+	waiter.last_rowner = atomic_long_read(&sem->owner);
+	if (!(waiter.last_rowner & RWSEM_READER_OWNED))
+		waiter.last_rowner &= RWSEM_RD_NONSPINNABLE;
+
+	if (!rwsem_can_spin_on_owner(sem, RWSEM_RD_NONSPINNABLE))
+		goto queue;
+
+	/*
+	 * Undo read bias from down_read() and do optimistic spinning.
+	 */
+	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
+	adjustment = 0;
+	if (rwsem_optimistic_spin(sem, false)) {
+		/* rwsem_optimistic_spin() implies ACQUIRE on success */
+		/*
+		 * Wake up other readers in the wait list if the front
+		 * waiter is a reader.
+		 */
+		if ((atomic_long_read(&sem->count) & RWSEM_FLAG_WAITERS)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (!list_empty(&sem->wait_list))
+				rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED,
+						&wake_q);
+			raw_spin_unlock_irq(&sem->wait_lock);
+			wake_up_q(&wake_q);
+		}
+		return sem;
+	} else if (rwsem_reader_phase_trylock(sem, waiter.last_rowner)) {
+		/* rwsem_reader_phase_trylock() implies ACQUIRE on success */
+		return sem;
+	}
+
+queue:
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list)) {
+		/*
+		 * In case the wait queue is empty and the lock isn't owned
+		 * by a writer or has the handoff bit set, this reader can
+		 * exit the slowpath and return immediately as its
+		 * RWSEM_READER_BIAS has already been set in the count.
+		 */
+		if (adjustment && !(atomic_long_read(&sem->count) &
+		     (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+			/* Provide lock ACQUIRE */
+			smp_acquire__after_ctrl_dep();
+			raw_spin_unlock_irq(&sem->wait_lock);
+			rwsem_set_reader_owned(sem);
+			lockevent_inc(rwsem_rlock_fast);
+			return sem;
+		}
+		adjustment += RWSEM_FLAG_WAITERS;
+	}
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	if (adjustment)
+		count = atomic_long_add_return(adjustment, &sem->count);
+	else
+		count = atomic_long_read(&sem->count);
+
+	/*
+	 * If there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (!(count & RWSEM_LOCK_MASK)) {
+		clear_wr_nonspinnable(sem);
+		wake = true;
+	}
+	if (wake || (!(count & RWSEM_WRITER_MASK) &&
+		    (adjustment & RWSEM_FLAG_WAITERS)))
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+
+	/* 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;
+		}
+		if (signal_pending_state(state, current)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (waiter.task)
+				goto out_nolock;
+			raw_spin_unlock_irq(&sem->wait_lock);
+			/* Ordered by sem->wait_lock against rwsem_mark_wake(). */
+			break;
+		}
+		schedule();
+		lockevent_inc(rwsem_sleep_reader);
+	}
+
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock);
+	return sem;
+
+out_nolock:
+	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list)) {
+		atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF,
+				   &sem->count);
+	}
+	raw_spin_unlock_irq(&sem->wait_lock);
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock_fail);
+	return ERR_PTR(-EINTR);
+}
+
+/*
+ * This function is called by the a write lock owner. So the owner value
+ * won't get changed by others.
+ */
+static inline void rwsem_disable_reader_optspin(struct rw_semaphore *sem,
+						bool disable)
+{
+	if (unlikely(disable)) {
+		atomic_long_or(RWSEM_RD_NONSPINNABLE, &sem->owner);
+		lockevent_inc(rwsem_opt_norspin);
+	}
+}
+
+/*
+ * Wait until we successfully acquire the write lock
+ */
+static struct rw_semaphore *
+rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
+{
+	long count;
+	bool disable_rspin;
+	enum writer_wait_state wstate;
+	struct rwsem_waiter waiter;
+	struct rw_semaphore *ret = sem;
+	DEFINE_WAKE_Q(wake_q);
+
+	/* do optimistic spinning and steal lock if possible */
+	if (rwsem_can_spin_on_owner(sem, RWSEM_WR_NONSPINNABLE) &&
+	    rwsem_optimistic_spin(sem, true)) {
+		/* rwsem_optimistic_spin() implies ACQUIRE on success */
+		return sem;
+	}
+
+	/*
+	 * Disable reader optimistic spinning for this rwsem after
+	 * acquiring the write lock when the setting of the nonspinnable
+	 * bits are observed.
+	 */
+	disable_rspin = atomic_long_read(&sem->owner) & RWSEM_NONSPINNABLE;
+
+	/*
+	 * Optimistic spinning failed, proceed to the slowpath
+	 * and block until we can acquire the sem.
+	 */
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_WRITE;
+	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+
+	/* account for this before adding a new element to the list */
+	wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST;
+
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock */
+	if (wstate == WRITER_NOT_FIRST) {
+		count = atomic_long_read(&sem->count);
+
+		/*
+		 * If there were already threads queued before us and:
+		 *  1) there are no no active locks, wake the front
+		 *     queued process(es) as the handoff bit might be set.
+		 *  2) there are no active writers and some readers, the lock
+		 *     must be read owned; so we try to wake any read lock
+		 *     waiters that were queued ahead of us.
+		 */
+		if (count & RWSEM_WRITER_MASK)
+			goto wait;
+
+		rwsem_mark_wake(sem, (count & RWSEM_READER_MASK)
+					? RWSEM_WAKE_READERS
+					: RWSEM_WAKE_ANY, &wake_q);
+
+		if (!wake_q_empty(&wake_q)) {
+			/*
+			 * We want to minimize wait_lock hold time especially
+			 * when a large number of readers are to be woken up.
+			 */
+			raw_spin_unlock_irq(&sem->wait_lock);
+			wake_up_q(&wake_q);
+			wake_q_init(&wake_q);	/* Used again, reinit */
+			raw_spin_lock_irq(&sem->wait_lock);
+		}
+	} else {
+		atomic_long_or(RWSEM_FLAG_WAITERS, &sem->count);
+	}
+
+wait:
+	/* wait until we successfully acquire the lock */
+	set_current_state(state);
+	for (;;) {
+		if (rwsem_try_write_lock(sem, wstate)) {
+			/* rwsem_try_write_lock() implies ACQUIRE on success */
+			break;
+		}
+
+		raw_spin_unlock_irq(&sem->wait_lock);
+
+		/*
+		 * After setting the handoff bit and failing to acquire
+		 * the lock, attempt to spin on owner to accelerate lock
+		 * transfer. If the previous owner is a on-cpu writer and it
+		 * has just released the lock, OWNER_NULL will be returned.
+		 * In this case, we attempt to acquire the lock again
+		 * without sleeping.
+		 */
+		if ((wstate == WRITER_HANDOFF) &&
+		    (rwsem_spin_on_owner(sem, 0) == OWNER_NULL))
+			goto trylock_again;
+
+		/* Block until there are no active lockers. */
+		for (;;) {
+			if (signal_pending_state(state, current))
+				goto out_nolock;
+
+			schedule();
+			lockevent_inc(rwsem_sleep_writer);
+			set_current_state(state);
+			/*
+			 * If HANDOFF bit is set, unconditionally do
+			 * a trylock.
+			 */
+			if (wstate == WRITER_HANDOFF)
+				break;
+
+			if ((wstate == WRITER_NOT_FIRST) &&
+			    (rwsem_first_waiter(sem) == &waiter))
+				wstate = WRITER_FIRST;
+
+			count = atomic_long_read(&sem->count);
+			if (!(count & RWSEM_LOCK_MASK))
+				break;
+
+			/*
+			 * The setting of the handoff bit is deferred
+			 * until rwsem_try_write_lock() is called.
+			 */
+			if ((wstate == WRITER_FIRST) && (rt_task(current) ||
+			    time_after(jiffies, waiter.timeout))) {
+				wstate = WRITER_HANDOFF;
+				lockevent_inc(rwsem_wlock_handoff);
+				break;
+			}
+		}
+trylock_again:
+		raw_spin_lock_irq(&sem->wait_lock);
+	}
+	__set_current_state(TASK_RUNNING);
+	list_del(&waiter.list);
+	rwsem_disable_reader_optspin(sem, disable_rspin);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	lockevent_inc(rwsem_wlock);
+
+	return ret;
+
+out_nolock:
+	__set_current_state(TASK_RUNNING);
+	raw_spin_lock_irq(&sem->wait_lock);
+	list_del(&waiter.list);
+
+	if (unlikely(wstate == WRITER_HANDOFF))
+		atomic_long_add(-RWSEM_FLAG_HANDOFF,  &sem->count);
+
+	if (list_empty(&sem->wait_list))
+		atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count);
+	else
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+	lockevent_inc(rwsem_wlock_fail);
+
+	return ERR_PTR(-EINTR);
+}
+
+/*
+ * handle waking up a waiter on the semaphore
+ * - up_read/up_write has decremented the active part of count if we come here
+ */
+static struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem, long count)
+{
+	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (!list_empty(&sem->wait_list))
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	wake_up_q(&wake_q);
+
+	return sem;
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - caller incremented waiting part of count and discovered it still negative
+ * - just wake up any readers at the front of the queue
+ */
+static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (!list_empty(&sem->wait_list))
+		rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	wake_up_q(&wake_q);
+
+	return sem;
+}
+
+/*
+ * lock for reading
+ */
+inline void __down_read(struct rw_semaphore *sem)
+{
+	if (!rwsem_read_trylock(sem)) {
+		rwsem_down_read_slowpath(sem, TASK_UNINTERRUPTIBLE);
+		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (!rwsem_read_trylock(sem)) {
+		if (IS_ERR(rwsem_down_read_slowpath(sem, TASK_KILLABLE)))
+			return -EINTR;
+		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+	return 0;
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
+
+	/*
+	 * Optimize for the case when the rwsem is not locked at all.
+	 */
+	tmp = RWSEM_UNLOCKED_VALUE;
+	do {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					tmp + RWSEM_READER_BIAS)) {
+			rwsem_set_reader_owned(sem);
+			return 1;
+		}
+	} while (!(tmp & RWSEM_READ_FAILED_MASK));
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	if (unlikely(!atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+						      RWSEM_WRITER_LOCKED)))
+		rwsem_down_write_slowpath(sem, TASK_UNINTERRUPTIBLE);
+	else
+		rwsem_set_owner(sem);
+}
+
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	if (unlikely(!atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+						      RWSEM_WRITER_LOCKED))) {
+		if (IS_ERR(rwsem_down_write_slowpath(sem, TASK_KILLABLE)))
+			return -EINTR;
+	} else {
+		rwsem_set_owner(sem);
+	}
+	return 0;
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
+
+	tmp  = RWSEM_UNLOCKED_VALUE;
+	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					    RWSEM_WRITER_LOCKED)) {
+		rwsem_set_owner(sem);
+		return true;
+	}
+	return false;
+}
+
+/*
+ * unlock after reading
+ */
+inline void __up_read(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
+	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+
+	rwsem_clear_reader_owned(sem);
+	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
+	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
+	if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) ==
+		      RWSEM_FLAG_WAITERS)) {
+		clear_wr_nonspinnable(sem);
+		rwsem_wake(sem, tmp);
+	}
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
+	/*
+	 * sem->owner may differ from current if the ownership is transferred
+	 * to an anonymous writer by setting the RWSEM_NONSPINNABLE bits.
+	 */
+	DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
+			    !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);
+
+	rwsem_clear_owner(sem);
+	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
+	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
+		rwsem_wake(sem, tmp);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	/*
+	 * When downgrading from exclusive to shared ownership,
+	 * anything inside the write-locked region cannot leak
+	 * into the read side. In contrast, anything in the
+	 * read-locked region is ok to be re-ordered into the
+	 * write side. As such, rely on RELEASE semantics.
+	 */
+	DEBUG_RWSEMS_WARN_ON(rwsem_owner(sem) != current, sem);
+	tmp = atomic_long_fetch_add_release(
+		-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
+	rwsem_set_reader_owned(sem);
+	if (tmp & RWSEM_FLAG_WAITERS)
+		rwsem_downgrade_wake(sem);
+}
 
 /*
  * lock for reading
@@ -24,9 +1495,7 @@
 	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
-	rwsem_set_reader_owned(sem);
 }
-
 EXPORT_SYMBOL(down_read);
 
 int __sched down_read_killable(struct rw_semaphore *sem)
@@ -39,10 +1508,8 @@
 		return -EINTR;
 	}
 
-	rwsem_set_reader_owned(sem);
 	return 0;
 }
-
 EXPORT_SYMBOL(down_read_killable);
 
 /*
@@ -52,13 +1519,10 @@
 {
 	int ret = __down_read_trylock(sem);
 
-	if (ret == 1) {
+	if (ret == 1)
 		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
-		rwsem_set_reader_owned(sem);
-	}
 	return ret;
 }
-
 EXPORT_SYMBOL(down_read_trylock);
 
 /*
@@ -68,11 +1532,8 @@
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
-
 EXPORT_SYMBOL(down_write);
 
 /*
@@ -83,15 +1544,14 @@
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
-	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
+				  __down_write_killable)) {
 		rwsem_release(&sem->dep_map, 1, _RET_IP_);
 		return -EINTR;
 	}
 
-	rwsem_set_owner(sem);
 	return 0;
 }
-
 EXPORT_SYMBOL(down_write_killable);
 
 /*
@@ -101,14 +1561,11 @@
 {
 	int ret = __down_write_trylock(sem);
 
-	if (ret == 1) {
+	if (ret == 1)
 		rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);
-		rwsem_set_owner(sem);
-	}
 
 	return ret;
 }
-
 EXPORT_SYMBOL(down_write_trylock);
 
 /*
@@ -117,11 +1574,8 @@
 void up_read(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != RWSEM_READER_OWNED);
-
 	__up_read(sem);
 }
-
 EXPORT_SYMBOL(up_read);
 
 /*
@@ -130,12 +1584,8 @@
 void up_write(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current);
-
-	rwsem_clear_owner(sem);
 	__up_write(sem);
 }
-
 EXPORT_SYMBOL(up_write);
 
 /*
@@ -144,12 +1594,8 @@
 void downgrade_write(struct rw_semaphore *sem)
 {
 	lock_downgrade(&sem->dep_map, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current);
-
-	rwsem_set_reader_owned(sem);
 	__downgrade_write(sem);
 }
-
 EXPORT_SYMBOL(downgrade_write);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -158,43 +1604,32 @@
 {
 	might_sleep();
 	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
-	rwsem_set_reader_owned(sem);
 }
-
 EXPORT_SYMBOL(down_read_nested);
 
 void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 {
 	might_sleep();
 	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
-
 EXPORT_SYMBOL(_down_write_nest_lock);
 
 void down_read_non_owner(struct rw_semaphore *sem)
 {
 	might_sleep();
-
 	__down_read(sem);
-	rwsem_set_reader_owned(sem);
+	__rwsem_set_reader_owned(sem, NULL);
 }
-
 EXPORT_SYMBOL(down_read_non_owner);
 
 void down_write_nested(struct rw_semaphore *sem, int subclass)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
-
 EXPORT_SYMBOL(down_write_nested);
 
 int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
@@ -202,23 +1637,21 @@
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
 
-	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
+				  __down_write_killable)) {
 		rwsem_release(&sem->dep_map, 1, _RET_IP_);
 		return -EINTR;
 	}
 
-	rwsem_set_owner(sem);
 	return 0;
 }
-
 EXPORT_SYMBOL(down_write_killable_nested);
 
 void up_read_non_owner(struct rw_semaphore *sem)
 {
-	DEBUG_RWSEMS_WARN_ON(sem->owner != RWSEM_READER_OWNED);
+	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 	__up_read(sem);
 }
-
 EXPORT_SYMBOL(up_read_non_owner);
 
 #endif
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index b9d0e72..2534ce4 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,87 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * The owner field of the rw_semaphore structure will be set to
- * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear
- * the owner field when it unlocks. A reader, on the other hand, will
- * not touch the owner field when it unlocks.
- *
- * In essence, the owner field now has the following 4 states:
- *  1) 0
- *     - lock is free or the owner hasn't set the field yet
- *  2) RWSEM_READER_OWNED
- *     - lock is currently or previously owned by readers (lock is free
- *       or not set by owner yet)
- *  3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well
- *     - lock is owned by an anonymous writer, so spinning on the lock
- *       owner should be disabled.
- *  4) Other non-zero value
- *     - a writer owns the lock and other writers can spin on the lock owner.
- */
-#define RWSEM_ANONYMOUSLY_OWNED	(1UL << 0)
-#define RWSEM_READER_OWNED	((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED)
 
-#ifdef CONFIG_DEBUG_RWSEMS
-# define DEBUG_RWSEMS_WARN_ON(c)	DEBUG_LOCKS_WARN_ON(c)
-#else
-# define DEBUG_RWSEMS_WARN_ON(c)
-#endif
+#ifndef __INTERNAL_RWSEM_H
+#define __INTERNAL_RWSEM_H
+#include <linux/rwsem.h>
 
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-/*
- * All writes to owner are protected by WRITE_ONCE() to make sure that
- * store tearing can't happen as optimistic spinners may read and use
- * the owner value concurrently without lock. Read from owner, however,
- * may not need READ_ONCE() as long as the pointer value is only used
- * for comparison and isn't being dereferenced.
- */
-static inline void rwsem_set_owner(struct rw_semaphore *sem)
-{
-	WRITE_ONCE(sem->owner, current);
-}
+extern void __down_read(struct rw_semaphore *sem);
+extern void __up_read(struct rw_semaphore *sem);
 
-static inline void rwsem_clear_owner(struct rw_semaphore *sem)
-{
-	WRITE_ONCE(sem->owner, NULL);
-}
-
-static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
-{
-	/*
-	 * We check the owner value first to make sure that we will only
-	 * do a write to the rwsem cacheline when it is really necessary
-	 * to minimize cacheline contention.
-	 */
-	if (READ_ONCE(sem->owner) != RWSEM_READER_OWNED)
-		WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
-}
-
-/*
- * Return true if the a rwsem waiter can spin on the rwsem's owner
- * and steal the lock, i.e. the lock is not anonymously owned.
- * N.B. !owner is considered spinnable.
- */
-static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
-{
-	return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
-}
-
-/*
- * Return true if rwsem is owned by an anonymous writer or readers.
- */
-static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
-{
-	return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
-}
-#else
-static inline void rwsem_set_owner(struct rw_semaphore *sem)
-{
-}
-
-static inline void rwsem_clear_owner(struct rw_semaphore *sem)
-{
-}
-
-static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
-{
-}
-#endif
+#endif /* __INTERNAL_RWSEM_H */
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 561acdd..d9dd94d 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2008 Intel Corporation
  * Author: Matthew Wilcox <willy@linux.intel.com>
  *
- * Distributed under the terms of the GNU GPL, version 2
- *
  * This file implements counting semaphores.
  * A counting semaphore may be acquired 'n' times before sleeping.
  * See mutex.c for single-acquisition sleeping locks which enforce
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 936f3d1..0ff0838 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -22,6 +22,13 @@
 #include <linux/debug_locks.h>
 #include <linux/export.h>
 
+#ifdef CONFIG_MMIOWB
+#ifndef arch_mmiowb_state
+DEFINE_PER_CPU(struct mmiowb_state, __mmiowb_state);
+EXPORT_PER_CPU_SYMBOL(__mmiowb_state);
+#endif
+#endif
+
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
  * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 9aa0fcc..399669f 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -111,6 +111,7 @@
 {
 	debug_spin_lock_before(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 	debug_spin_lock_after(lock);
 }
 
@@ -118,8 +119,10 @@
 {
 	int ret = arch_spin_trylock(&lock->raw_lock);
 
-	if (ret)
+	if (ret) {
+		mmiowb_spin_lock();
 		debug_spin_lock_after(lock);
+	}
 #ifndef CONFIG_SMP
 	/*
 	 * Must not happen on UP:
@@ -131,6 +134,7 @@
 
 void do_raw_spin_unlock(raw_spinlock_t *lock)
 {
+	mmiowb_spin_unlock();
 	debug_spin_unlock(lock);
 	arch_spin_unlock(&lock->raw_lock);
 }
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 65a3b7e..3e82f44 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Module-based API test facility for ww_mutexes
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
  */
 
 #include <linux/kernel.h>