Merge tag 'locking-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - rtmutex cleanup & spring cleaning pass that removes ~400 lines of
   code

 - Futex simplifications & cleanups

 - Add debugging to the CSD code, to help track down a tenacious race
   (or hw problem)

 - Add lockdep_assert_not_held(), to allow code to require a lock to not
   be held, and propagate this into the ath10k driver

 - Misc LKMM documentation updates

 - Misc KCSAN updates: cleanups & documentation updates

 - Misc fixes and cleanups

 - Fix locktorture bugs with ww_mutexes

* tag 'locking-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  kcsan: Fix printk format string
  static_call: Relax static_call_update() function argument type
  static_call: Fix unused variable warn w/o MODULE
  locking/rtmutex: Clean up signal handling in __rt_mutex_slowlock()
  locking/rtmutex: Restrict the trylock WARN_ON() to debug
  locking/rtmutex: Fix misleading comment in rt_mutex_postunlock()
  locking/rtmutex: Consolidate the fast/slowpath invocation
  locking/rtmutex: Make text section and inlining consistent
  locking/rtmutex: Move debug functions as inlines into common header
  locking/rtmutex: Decrapify __rt_mutex_init()
  locking/rtmutex: Remove pointless CONFIG_RT_MUTEXES=n stubs
  locking/rtmutex: Inline chainwalk depth check
  locking/rtmutex: Move rt_mutex_debug_task_free() to rtmutex.c
  locking/rtmutex: Remove empty and unused debug stubs
  locking/rtmutex: Consolidate rt_mutex_init()
  locking/rtmutex: Remove output from deadlock detector
  locking/rtmutex: Remove rtmutex deadlock tester leftovers
  locking/rtmutex: Remove rt_mutex_timed_lock()
  MAINTAINERS: Add myself as futex reviewer
  locking/mutex: Remove repeated declaration
  ...

27 files changed, 707 insertions, 764 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 00febd6dea9c..c98b825da9cf 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -981,6 +981,7 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
  * p->pi_lock:
  *
  *	p->pi_state_list -> pi_state->list, relation
+ *	pi_mutex->owner -> pi_state->owner, relation
  *
  * pi_state->refcount:
  *
@@ -1494,13 +1495,14 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
 {
 	u32 curval, newval;
+	struct rt_mutex_waiter *top_waiter;
 	struct task_struct *new_owner;
 	bool postunlock = false;
 	DEFINE_WAKE_Q(wake_q);
 	int ret = 0;
 
-	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
-	if (WARN_ON_ONCE(!new_owner)) {
+	top_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
+	if (WARN_ON_ONCE(!top_waiter)) {
 		/*
 		 * As per the comment in futex_unlock_pi() this should not happen.
 		 *
@@ -1513,6 +1515,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 		goto out_unlock;
 	}
 
+	new_owner = top_waiter->task;
+
 	/*
 	 * We pass it to the next owner. The WAITERS bit is always kept
 	 * enabled while there is PI state around. We cleanup the owner
@@ -2315,19 +2319,15 @@ retry:
 
 /*
  * PI futexes can not be requeued and must remove themself from the
- * hash bucket. The hash bucket lock (i.e. lock_ptr) is held on entry
- * and dropped here.
+ * hash bucket. The hash bucket lock (i.e. lock_ptr) is held.
  */
 static void unqueue_me_pi(struct futex_q *q)
-	__releases(q->lock_ptr)
 {
 	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
 	put_pi_state(q->pi_state);
 	q->pi_state = NULL;
-
-	spin_unlock(q->lock_ptr);
 }
 
 static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
@@ -2909,8 +2909,8 @@ no_block:
 	if (res)
 		ret = (res < 0) ? res : 0;
 
-	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
+	spin_unlock(q.lock_ptr);
 	goto out;
 
 out_unlock_put_key:
@@ -3237,15 +3237,14 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * reference count.
 	 */
 
-	/* Check if the requeue code acquired the second futex for us. */
+	/*
+	 * Check if the requeue code acquired the second futex for us and do
+	 * any pertinent fixup.
+	 */
 	if (!q.rt_waiter) {
-		/*
-		 * Got the lock. We might not be the anticipated owner if we
-		 * did a lock-steal - fix up the PI-state in that case.
-		 */
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
-			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			ret = fixup_owner(uaddr2, &q, true);
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
@@ -3287,8 +3286,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
-		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
+		spin_unlock(q.lock_ptr);
 	}
 
 	if (ret == -EINTR) {
diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile
index 65ca5539c470..c2bb07f5bcc7 100644
--- a/kernel/kcsan/Makefile
+++ b/kernel/kcsan/Makefile
@@ -13,5 +13,5 @@ CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \
 obj-y := core.o debugfs.o report.o
 obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o
 
-CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer
-obj-$(CONFIG_KCSAN_TEST) += kcsan-test.o
+CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer
+obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o
diff --git a/kernel/kcsan/atomic.h b/kernel/kcsan/atomic.h
index 75fe701f4127..530ae1bda8e7 100644
--- a/kernel/kcsan/atomic.h
+++ b/kernel/kcsan/atomic.h
@@ -1,4 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Rules for implicitly atomic memory accesses.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #ifndef _KERNEL_KCSAN_ATOMIC_H
 #define _KERNEL_KCSAN_ATOMIC_H
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 3bf98db9c702..45c821d4e8bd 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -1,4 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN core runtime.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #define pr_fmt(fmt) "kcsan: " fmt
 
@@ -639,8 +644,6 @@ void __init kcsan_init(void)
 
 	BUG_ON(!in_task());
 
-	kcsan_debugfs_init();
-
 	for_each_possible_cpu(cpu)
 		per_cpu(kcsan_rand_state, cpu) = (u32)get_cycles();
 
diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c
index 3c8093a371b1..c1dd02f3be8b 100644
--- a/kernel/kcsan/debugfs.c
+++ b/kernel/kcsan/debugfs.c
@@ -1,4 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN debugfs interface.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #define pr_fmt(fmt) "kcsan: " fmt
 
@@ -261,7 +266,9 @@ static const struct file_operations debugfs_ops =
 	.release = single_release
 };
 
-void __init kcsan_debugfs_init(void)
+static void __init kcsan_debugfs_init(void)
 {
 	debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops);
 }
+
+late_initcall(kcsan_debugfs_init);
diff --git a/kernel/kcsan/encoding.h b/kernel/kcsan/encoding.h
index 7ee405524904..170a2bb22f53 100644
--- a/kernel/kcsan/encoding.h
+++ b/kernel/kcsan/encoding.h
@@ -1,4 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KCSAN watchpoint encoding.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #ifndef _KERNEL_KCSAN_ENCODING_H
 #define _KERNEL_KCSAN_ENCODING_H
diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h
index 8d4bf3431b3c..9881099d4179 100644
--- a/kernel/kcsan/kcsan.h
+++ b/kernel/kcsan/kcsan.h
@@ -1,8 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-
 /*
  * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please
  * see Documentation/dev-tools/kcsan.rst.
+ *
+ * Copyright (C) 2019, Google LLC.
  */
 
 #ifndef _KERNEL_KCSAN_KCSAN_H
@@ -31,11 +32,6 @@ void kcsan_save_irqtrace(struct task_struct *task);
 void kcsan_restore_irqtrace(struct task_struct *task);
 
 /*
- * Initialize debugfs file.
- */
-void kcsan_debugfs_init(void);
-
-/*
  * Statistics counters displayed via debugfs; should only be modified in
  * slow-paths.
  */
diff --git a/kernel/kcsan/kcsan-test.c b/kernel/kcsan/kcsan_test.c
index ebe7fd245104..8bcffbdef3d3 100644
--- a/kernel/kcsan/kcsan-test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -13,6 +13,8 @@
  * Author: Marco Elver <elver@google.com>
  */
 
+#define pr_fmt(fmt) "kcsan_test: " fmt
+
 #include <kunit/test.h>
 #include <linux/jiffies.h>
 #include <linux/kcsan-checks.h>
@@ -951,22 +953,53 @@ static void test_atomic_builtins(struct kunit *test)
 }
 
 /*
- * Each test case is run with different numbers of threads. Until KUnit supports
- * passing arguments for each test case, we encode #threads in the test case
- * name (read by get_num_threads()). [The '-' was chosen as a stylistic
- * preference to separate test name and #threads.]
+ * Generate thread counts for all test cases. Values generated are in interval
+ * [2, 5] followed by exponentially increasing thread counts from 8 to 32.
  *
  * The thread counts are chosen to cover potentially interesting boundaries and
- * corner cases (range 2-5), and then stress the system with larger counts.
+ * corner cases (2 to 5), and then stress the system with larger counts.
  */
-#define KCSAN_KUNIT_CASE(test_name)                                            \
-	{ .run_case = test_name, .name = #test_name "-02" },                   \
-	{ .run_case = test_name, .name = #test_name "-03" },                   \
-	{ .run_case = test_name, .name = #test_name "-04" },                   \
-	{ .run_case = test_name, .name = #test_name "-05" },                   \
-	{ .run_case = test_name, .name = #test_name "-08" },                   \
-	{ .run_case = test_name, .name = #test_name "-16" }
+static const void *nthreads_gen_params(const void *prev, char *desc)
+{
+	long nthreads = (long)prev;
+
+	if (nthreads < 0 || nthreads >= 32)
+		nthreads = 0; /* stop */
+	else if (!nthreads)
+		nthreads = 2; /* initial value */
+	else if (nthreads < 5)
+		nthreads++;
+	else if (nthreads == 5)
+		nthreads = 8;
+	else
+		nthreads *= 2;
 
+	if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) {
+		/*
+		 * Without any preemption, keep 2 CPUs free for other tasks, one
+		 * of which is the main test case function checking for
+		 * completion or failure.
+		 */
+		const long min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0;
+		const long min_required_cpus = 2 + min_unused_cpus;
+
+		if (num_online_cpus() < min_required_cpus) {
+			pr_err_once("Too few online CPUs (%u < %ld) for test\n",
+				    num_online_cpus(), min_required_cpus);
+			nthreads = 0;
+		} else if (nthreads >= num_online_cpus() - min_unused_cpus) {
+			/* Use negative value to indicate last param. */
+			nthreads = -(num_online_cpus() - min_unused_cpus);
+			pr_warn_once("Limiting number of threads to %ld (only %d online CPUs)\n",
+				     -nthreads, num_online_cpus());
+		}
+	}
+
+	snprintf(desc, KUNIT_PARAM_DESC_SIZE, "threads=%ld", abs(nthreads));
+	return (void *)nthreads;
+}
+
+#define KCSAN_KUNIT_CASE(test_name) KUNIT_CASE_PARAM(test_name, nthreads_gen_params)
 static struct kunit_case kcsan_test_cases[] = {
 	KCSAN_KUNIT_CASE(test_basic),
 	KCSAN_KUNIT_CASE(test_concurrent_races),
@@ -996,24 +1029,6 @@ static struct kunit_case kcsan_test_cases[] = {
 
 /* ===== End test cases ===== */
 
-/* Get number of threads encoded in test name. */
-static bool __no_kcsan
-get_num_threads(const char *test, int *nthreads)
-{
-	int len = strlen(test);
-
-	if (WARN_ON(len < 3))
-		return false;
-
-	*nthreads = test[len - 1] - '0';
-	*nthreads += (test[len - 2] - '0') * 10;
-
-	if (WARN_ON(*nthreads < 0))
-		return false;
-
-	return true;
-}
-
 /* Concurrent accesses from interrupts. */
 __no_kcsan
 static void access_thread_timer(struct timer_list *timer)
@@ -1076,9 +1091,6 @@ static int test_init(struct kunit *test)
 	if (!torture_init_begin((char *)test->name, 1))
 		return -EBUSY;
 
-	if (!get_num_threads(test->name, &nthreads))
-		goto err;
-
 	if (WARN_ON(threads))
 		goto err;
 
@@ -1087,38 +1099,18 @@ static int test_init(struct kunit *test)
 			goto err;
 	}
 
-	if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) {
-		/*
-		 * Without any preemption, keep 2 CPUs free for other tasks, one
-		 * of which is the main test case function checking for
-		 * completion or failure.
-		 */
-		const int min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0;
-		const int min_required_cpus = 2 + min_unused_cpus;
+	nthreads = abs((long)test->param_value);
+	if (WARN_ON(!nthreads))
+		goto err;
 
-		if (num_online_cpus() < min_required_cpus) {
-			pr_err("%s: too few online CPUs (%u < %d) for test",
-			       test->name, num_online_cpus(), min_required_cpus);
-			goto err;
-		} else if (nthreads > num_online_cpus() - min_unused_cpus) {
-			nthreads = num_online_cpus() - min_unused_cpus;
-			pr_warn("%s: limiting number of threads to %d\n",
-				test->name, nthreads);
-		}
-	}
+	threads = kcalloc(nthreads + 1, sizeof(struct task_struct *), GFP_KERNEL);
+	if (WARN_ON(!threads))
+		goto err;
 
-	if (nthreads) {
-		threads = kcalloc(nthreads + 1, sizeof(struct task_struct *),
-				  GFP_KERNEL);
-		if (WARN_ON(!threads))
+	threads[nthreads] = NULL;
+	for (i = 0; i < nthreads; ++i) {
+		if (torture_create_kthread(access_thread, NULL, threads[i]))
 			goto err;
-
-		threads[nthreads] = NULL;
-		for (i = 0; i < nthreads; ++i) {
-			if (torture_create_kthread(access_thread, NULL,
-						   threads[i]))
-				goto err;
-		}
 	}
 
 	torture_init_end();
@@ -1156,7 +1148,7 @@ static void test_exit(struct kunit *test)
 }
 
 static struct kunit_suite kcsan_test_suite = {
-	.name = "kcsan-test",
+	.name = "kcsan",
 	.test_cases = kcsan_test_cases,
 	.init = test_init,
 	.exit = test_exit,
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index d3bf87e6007c..13dce3c664d6 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -1,4 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN reporting.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #include <linux/debug_locks.h>
 #include <linux/delay.h>
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index 9014a3a82cf9..7f29cb0f5e63 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -1,4 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN short boot-time selftests.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #define pr_fmt(fmt) "kcsan: " fmt
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 8838f1d7c4a2..3572808223e4 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -12,7 +12,6 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_lockdep_proc.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
 endif
 
 obj-$(CONFIG_DEBUG_IRQFLAGS) += irqflag-debug.o
@@ -26,7 +25,6 @@ obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
-obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ef28a0b9cf1e..48d736aa03b2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -54,6 +54,7 @@
 #include <linux/nmi.h>
 #include <linux/rcupdate.h>
 #include <linux/kprobes.h>
+#include <linux/lockdep.h>
 
 #include <asm/sections.h>
 
@@ -1747,7 +1748,7 @@ static enum bfs_result __bfs(struct lock_list *source_entry,
 
 		/*
 		 * Step 4: if not match, expand the path by adding the
-		 *         forward or backwards dependencis in the search
+		 *         forward or backwards dependencies in the search
 		 *
 		 */
 		first = true;
@@ -1916,7 +1917,7 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
  * -> B is -(ER)-> or -(EN)->, then we don't need to add A -> B into the
  * dependency graph, as any strong path ..-> A -> B ->.. we can get with
  * having dependency A -> B, we could already get a equivalent path ..-> A ->
- * .. -> B -> .. with A -> .. -> B. Therefore A -> B is reduntant.
+ * .. -> B -> .. with A -> .. -> B. Therefore A -> B is redundant.
  *
  * We need to make sure both the start and the end of A -> .. -> B is not
  * weaker than A -> B. For the start part, please see the comment in
@@ -5253,13 +5254,13 @@ int __lock_is_held(const struct lockdep_map *lock, int read)
 
 		if (match_held_lock(hlock, lock)) {
 			if (read == -1 || hlock->read == read)
-				return 1;
+				return LOCK_STATE_HELD;
 
-			return 0;
+			return LOCK_STATE_NOT_HELD;
 		}
 	}
 
-	return 0;
+	return LOCK_STATE_NOT_HELD;
 }
 
 static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock)
@@ -5538,10 +5539,14 @@ EXPORT_SYMBOL_GPL(lock_release);
 noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 {
 	unsigned long flags;
-	int ret = 0;
+	int ret = LOCK_STATE_NOT_HELD;
 
+	/*
+	 * Avoid false negative lockdep_assert_held() and
+	 * lockdep_assert_not_held().
+	 */
 	if (unlikely(!lockdep_enabled()))
-		return 1; /* avoid false negative lockdep_assert_held() */
+		return LOCK_STATE_UNKNOWN;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 02ef87f50df2..806978314496 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -348,7 +348,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 			debug_locks);
 
 	/*
-	 * Zappped classes and lockdep data buffers reuse statistics.
+	 * Zapped classes and lockdep data buffers reuse statistics.
 	 */
 	seq_puts(m, "\n");
 	seq_printf(m, " zapped classes:                %11lu\n",
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 0ab94e1f1276..b3adb40549bf 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -76,13 +76,13 @@ static void lock_torture_cleanup(void);
 struct lock_torture_ops {
 	void (*init)(void);
 	void (*exit)(void);
-	int (*writelock)(void);
+	int (*writelock)(int tid);
 	void (*write_delay)(struct torture_random_state *trsp);
 	void (*task_boost)(struct torture_random_state *trsp);
-	void (*writeunlock)(void);
-	int (*readlock)(void);
+	void (*writeunlock)(int tid);
+	int (*readlock)(int tid);
 	void (*read_delay)(struct torture_random_state *trsp);
-	void (*readunlock)(void);
+	void (*readunlock)(int tid);
 
 	unsigned long flags; /* for irq spinlocks */
 	const char *name;
@@ -105,7 +105,7 @@ static struct lock_torture_cxt cxt = { 0, 0, false, false,
  * Definitions for lock torture testing.
  */
 
-static int torture_lock_busted_write_lock(void)
+static int torture_lock_busted_write_lock(int tid __maybe_unused)
 {
 	return 0;  /* BUGGY, do not use in real life!!! */
 }
@@ -122,7 +122,7 @@ static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
 		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
-static void torture_lock_busted_write_unlock(void)
+static void torture_lock_busted_write_unlock(int tid __maybe_unused)
 {
 	  /* BUGGY, do not use in real life!!! */
 }
@@ -145,7 +145,8 @@ static struct lock_torture_ops lock_busted_ops = {
 
 static DEFINE_SPINLOCK(torture_spinlock);
 
-static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
+static int torture_spin_lock_write_lock(int tid __maybe_unused)
+__acquires(torture_spinlock)
 {
 	spin_lock(&torture_spinlock);
 	return 0;
@@ -169,7 +170,8 @@ static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
 		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
-static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
+static void torture_spin_lock_write_unlock(int tid __maybe_unused)
+__releases(torture_spinlock)
 {
 	spin_unlock(&torture_spinlock);
 }
@@ -185,7 +187,7 @@ static struct lock_torture_ops spin_lock_ops = {
 	.name		= "spin_lock"
 };
 
-static int torture_spin_lock_write_lock_irq(void)
+static int torture_spin_lock_write_lock_irq(int tid __maybe_unused)
 __acquires(torture_spinlock)
 {
 	unsigned long flags;
@@ -195,7 +197,7 @@ __acquires(torture_spinlock)
 	return 0;
 }
 
-static void torture_lock_spin_write_unlock_irq(void)
+static void torture_lock_spin_write_unlock_irq(int tid __maybe_unused)
 __releases(torture_spinlock)
 {
 	spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags);
@@ -214,7 +216,8 @@ static struct lock_torture_ops spin_lock_irq_ops = {
 
 static DEFINE_RWLOCK(torture_rwlock);
 
-static int torture_rwlock_write_lock(void) __acquires(torture_rwlock)
+static int torture_rwlock_write_lock(int tid __maybe_unused)
+__acquires(torture_rwlock)
 {
 	write_lock(&torture_rwlock);
 	return 0;
@@ -235,12 +238,14 @@ static void torture_rwlock_write_delay(struct torture_random_state *trsp)
 		udelay(shortdelay_us);
 }
 
-static void torture_rwlock_write_unlock(void) __releases(torture_rwlock)
+static void torture_rwlock_write_unlock(int tid __maybe_unused)
+__releases(torture_rwlock)
 {
 	write_unlock(&torture_rwlock);
 }
 
-static int torture_rwlock_read_lock(void) __acquires(torture_rwlock)
+static int torture_rwlock_read_lock(int tid __maybe_unused)
+__acquires(torture_rwlock)
 {
 	read_lock(&torture_rwlock);
 	return 0;
@@ -261,7 +266,8 @@ static void torture_rwlock_read_delay(struct torture_random_state *trsp)
 		udelay(shortdelay_us);
 }
 
-static void torture_rwlock_read_unlock(void) __releases(torture_rwlock)
+static void torture_rwlock_read_unlock(int tid __maybe_unused)
+__releases(torture_rwlock)
 {
 	read_unlock(&torture_rwlock);
 }
@@ -277,7 +283,8 @@ static struct lock_torture_ops rw_lock_ops = {
 	.name		= "rw_lock"
 };
 
-static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock)
+static int torture_rwlock_write_lock_irq(int tid __maybe_unused)
+__acquires(torture_rwlock)
 {
 	unsigned long flags;
 
@@ -286,13 +293,14 @@ static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock)
 	return 0;
 }
 
-static void torture_rwlock_write_unlock_irq(void)
+static void torture_rwlock_write_unlock_irq(int tid __maybe_unused)
 __releases(torture_rwlock)
 {
 	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
 }
 
-static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
+static int torture_rwlock_read_lock_irq(int tid __maybe_unused)
+__acquires(torture_rwlock)
 {
 	unsigned long flags;
 
@@ -301,7 +309,7 @@ static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
 	return 0;
 }
 
-static void torture_rwlock_read_unlock_irq(void)
+static void torture_rwlock_read_unlock_irq(int tid __maybe_unused)
 __releases(torture_rwlock)
 {
 	read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
@@ -320,7 +328,8 @@ static struct lock_torture_ops rw_lock_irq_ops = {
 
 static DEFINE_MUTEX(torture_mutex);
 
-static int torture_mutex_lock(void) __acquires(torture_mutex)
+static int torture_mutex_lock(int tid __maybe_unused)
+__acquires(torture_mutex)
 {
 	mutex_lock(&torture_mutex);
 	return 0;
@@ -340,7 +349,8 @@ static void torture_mutex_delay(struct torture_random_state *trsp)
 		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
-static void torture_mutex_unlock(void) __releases(torture_mutex)
+static void torture_mutex_unlock(int tid __maybe_unused)
+__releases(torture_mutex)
 {
 	mutex_unlock(&torture_mutex);
 }
@@ -357,12 +367,34 @@ static struct lock_torture_ops mutex_lock_ops = {
 };
 
 #include <linux/ww_mutex.h>
+/*
+ * The torture ww_mutexes should belong to the same lock class as
+ * torture_ww_class to avoid lockdep problem. The ww_mutex_init()
+ * function is called for initialization to ensure that.
+ */
 static DEFINE_WD_CLASS(torture_ww_class);
-static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
-static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
-static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);
+static struct ww_mutex torture_ww_mutex_0, torture_ww_mutex_1, torture_ww_mutex_2;
+static struct ww_acquire_ctx *ww_acquire_ctxs;
+
+static void torture_ww_mutex_init(void)
+{
+	ww_mutex_init(&torture_ww_mutex_0, &torture_ww_class);
+	ww_mutex_init(&torture_ww_mutex_1, &torture_ww_class);
+	ww_mutex_init(&torture_ww_mutex_2, &torture_ww_class);
+
+	ww_acquire_ctxs = kmalloc_array(cxt.nrealwriters_stress,
+					sizeof(*ww_acquire_ctxs),
+					GFP_KERNEL);
+	if (!ww_acquire_ctxs)
+		VERBOSE_TOROUT_STRING("ww_acquire_ctx: Out of memory");
+}
+
+static void torture_ww_mutex_exit(void)
+{
+	kfree(ww_acquire_ctxs);
+}
 
-static int torture_ww_mutex_lock(void)
+static int torture_ww_mutex_lock(int tid)
 __acquires(torture_ww_mutex_0)
 __acquires(torture_ww_mutex_1)
 __acquires(torture_ww_mutex_2)
@@ -372,7 +404,7 @@ __acquires(torture_ww_mutex_2)
 		struct list_head link;
 		struct ww_mutex *lock;
 	} locks[3], *ll, *ln;
-	struct ww_acquire_ctx ctx;
+	struct ww_acquire_ctx *ctx = &ww_acquire_ctxs[tid];
 
 	locks[0].lock = &torture_ww_mutex_0;
 	list_add(&locks[0].link, &list);
@@ -383,12 +415,12 @@ __acquires(torture_ww_mutex_2)
 	locks[2].lock = &torture_ww_mutex_2;
 	list_add(&locks[2].link, &list);
 
-	ww_acquire_init(&ctx, &torture_ww_class);
+	ww_acquire_init(ctx, &torture_ww_class);
 
 	list_for_each_entry(ll, &list, link) {
 		int err;
 
-		err = ww_mutex_lock(ll->lock, &ctx);
+		err = ww_mutex_lock(ll->lock, ctx);
 		if (!err)
 			continue;
 
@@ -399,25 +431,29 @@ __acquires(torture_ww_mutex_2)
 		if (err != -EDEADLK)
 			return err;
 
-		ww_mutex_lock_slow(ll->lock, &ctx);
+		ww_mutex_lock_slow(ll->lock, ctx);
 		list_move(&ll->link, &list);
 	}
 
-	ww_acquire_fini(&ctx);
 	return 0;
 }
 
-static void torture_ww_mutex_unlock(void)
+static void torture_ww_mutex_unlock(int tid)
 __releases(torture_ww_mutex_0)
 __releases(torture_ww_mutex_1)
 __releases(torture_ww_mutex_2)
 {
+	struct ww_acquire_ctx *ctx = &ww_acquire_ctxs[tid];
+
 	ww_mutex_unlock(&torture_ww_mutex_0);
 	ww_mutex_unlock(&torture_ww_mutex_1);
 	ww_mutex_unlock(&torture_ww_mutex_2);
+	ww_acquire_fini(ctx);
 }
 
 static struct lock_torture_ops ww_mutex_lock_ops = {
+	.init		= torture_ww_mutex_init,
+	.exit		= torture_ww_mutex_exit,
 	.writelock	= torture_ww_mutex_lock,
 	.write_delay	= torture_mutex_delay,
 	.task_boost     = torture_boost_dummy,
@@ -431,7 +467,8 @@ static struct lock_torture_ops ww_mutex_lock_ops = {
 #ifdef CONFIG_RT_MUTEXES
 static DEFINE_RT_MUTEX(torture_rtmutex);
 
-static int torture_rtmutex_lock(void) __acquires(torture_rtmutex)
+static int torture_rtmutex_lock(int tid __maybe_unused)
+__acquires(torture_rtmutex)
 {
 	rt_mutex_lock(&torture_rtmutex);
 	return 0;
@@ -487,7 +524,8 @@ static void torture_rtmutex_delay(struct torture_random_state *trsp)
 		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
-static void torture_rtmutex_unlock(void) __releases(torture_rtmutex)
+static void torture_rtmutex_unlock(int tid __maybe_unused)
+__releases(torture_rtmutex)
 {
 	rt