Resguardo inicial

linux-7.2.3/kernel/locking/Makefile

@@ -0,0 +1,40 @@
+# SPDX-License-Identifier: GPL-2.0
+# Any varying coverage in these files is non-deterministic
+# and is generally not a function of system call inputs.
+KCOV_INSTRUMENT		:= n
+
+CONTEXT_ANALYSIS_mutex.o := y
+CONTEXT_ANALYSIS_rtmutex_api.o := y
+CONTEXT_ANALYSIS_ww_rt_mutex.o := y
+CONTEXT_ANALYSIS_rwsem.o := y
+
+obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+
+# Avoid recursion lockdep -> sanitizer -> ... -> lockdep & improve performance.
+KASAN_SANITIZE_lockdep.o := n
+KCSAN_SANITIZE_lockdep.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_lockdep_proc.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE)
+endif
+
+obj-$(CONFIG_DEBUG_IRQFLAGS) += irqflag-debug.o
+obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+obj-$(CONFIG_LOCKDEP) += lockdep.o
+ifeq ($(CONFIG_PROC_FS),y)
+obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
+endif
+obj-$(CONFIG_SMP) += spinlock.o
+obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
+obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
+obj-$(CONFIG_RT_MUTEXES) += rtmutex_api.o
+obj-$(CONFIG_PREEMPT_RT) += spinlock_rt.o ww_rt_mutex.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.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

linux-7.2.3/kernel/locking/irqflag-debug.c

@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/irqflags.h>
+
+noinstr void warn_bogus_irq_restore(void)
+{
+	instrumentation_begin();
+	WARN_ONCE(1, "raw_local_irq_restore() called with IRQs enabled\n");
+	instrumentation_end();
+}
+EXPORT_SYMBOL(warn_bogus_irq_restore);

linux-7.2.3/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 (IS_ERR(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 (IS_ERR(debugfs_create_file(lockevent_names[i], 0400, d_counts,
+					 (void *)(long)i, &fops_lockevent)))
+			goto fail_undo;
+	}
+
+	if (IS_ERR(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);

linux-7.2.3/kernel/locking/lock_events.h

@@ -0,0 +1,64 @@
+/* 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)		do { (void)(c); } while (0)
+#define lockevent_cond_inc(ev, c)	do { (void)(c); } while (0)
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
+
+ssize_t lockevent_read(struct file *file, char __user *user_buf,
+		       size_t count, loff_t *ppos);
+
+#endif /* __LOCKING_LOCK_EVENTS_H */

linux-7.2.3/kernel/locking/lock_events_list.h

@@ -0,0 +1,102 @@
+/* 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 Resilient Queued Spin Lock
+ */
+LOCK_EVENT(rqspinlock_lock_timeout)	/* # of locking ops that timeout	*/
+
+/*
+ * 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_lock)	/* # of opt-acquired write locks	*/
+LOCK_EVENT(rwsem_opt_fail)	/* # of failed optspins			*/
+LOCK_EVENT(rwsem_opt_nospin)	/* # of disabled optspins		*/
+LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
+LOCK_EVENT(rwsem_rlock_steal)	/* # of read locks by lock stealing	*/
+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		*/
+
+/*
+ * Locking events for rtlock_slowlock()
+ */
+LOCK_EVENT(rtlock_slowlock)	/* # of rtlock_slowlock() calls		*/
+LOCK_EVENT(rtlock_slow_acq1)	/* # of locks acquired after wait_lock	*/
+LOCK_EVENT(rtlock_slow_acq2)	/* # of locks acquired in for loop	*/
+LOCK_EVENT(rtlock_slow_sleep)	/* # of sleeps				*/
+LOCK_EVENT(rtlock_slow_wake)	/* # of wakeup's			*/
+
+/*
+ * Locking events for rt_mutex_slowlock()
+ */
+LOCK_EVENT(rtmutex_slowlock)	/* # of rt_mutex_slowlock() calls	*/
+LOCK_EVENT(rtmutex_slow_block)	/* # of rt_mutex_slowlock_block() calls	*/
+LOCK_EVENT(rtmutex_slow_acq1)	/* # of locks acquired after wait_lock	*/
+LOCK_EVENT(rtmutex_slow_acq2)	/* # of locks acquired at the end	*/
+LOCK_EVENT(rtmutex_slow_acq3)	/* # of locks acquired in *block()	*/
+LOCK_EVENT(rtmutex_slow_sleep)	/* # of sleeps				*/
+LOCK_EVENT(rtmutex_slow_wake)	/* # of wakeup's			*/
+LOCK_EVENT(rtmutex_deadlock)	/* # of rt_mutex_handle_deadlock()'s	*/
+
+/*
+ * Locking events for lockdep
+ */
+LOCK_EVENT(lockdep_acquire)
+LOCK_EVENT(lockdep_lock)
+LOCK_EVENT(lockdep_nocheck)

linux-7.2.3/kernel/locking/lockdep_internals.h

@@ -0,0 +1,265 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * kernel/lockdep_internals.h
+ *
+ * Runtime locking correctness validator
+ *
+ * lockdep subsystem internal functions and variables.
+ */
+
+/*
+ * Lock-class usage-state bits:
+ */
+enum lock_usage_bit {
+#define LOCKDEP_STATE(__STATE)		\
+	LOCK_USED_IN_##__STATE,		\
+	LOCK_USED_IN_##__STATE##_READ,	\
+	LOCK_ENABLED_##__STATE,		\
+	LOCK_ENABLED_##__STATE##_READ,
+#include "lockdep_states.h"
+#undef LOCKDEP_STATE
+	LOCK_USED,
+	LOCK_USED_READ,
+	LOCK_USAGE_STATES,
+};
+
+/* states after LOCK_USED_READ are not traced and printed */
+static_assert(LOCK_TRACE_STATES == 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:
+ */
+#define __LOCKF(__STATE)	LOCKF_##__STATE = (1 << LOCK_##__STATE),
+
+enum {
+#define LOCKDEP_STATE(__STATE)						\
+	__LOCKF(USED_IN_##__STATE)					\
+	__LOCKF(USED_IN_##__STATE##_READ)				\
+	__LOCKF(ENABLED_##__STATE)					\
+	__LOCKF(ENABLED_##__STATE##_READ)
+#include "lockdep_states.h"
+#undef LOCKDEP_STATE
+	__LOCKF(USED)
+	__LOCKF(USED_READ)
+};
+
+enum {
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
+	LOCKF_ENABLED_IRQ =
+#include "lockdep_states.h"
+	0,
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE |
+	LOCKF_USED_IN_IRQ =
+#include "lockdep_states.h"
+	0,
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE##_READ |
+	LOCKF_ENABLED_IRQ_READ =
+#include "lockdep_states.h"
+	0,
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE##_READ |
+	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,
+ * .data and .bss to fit in required 32MB limit for the kernel. With
+ * CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems.
+ * So, reduce the static allocations for lockdeps related structures so that
+ * everything fits in current required size limit.
+ */
+#ifdef CONFIG_LOCKDEP_SMALL
+/*
+ * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies
+ * we track.
+ *
+ * We use the per-lock dependency maps in two ways: we grow it by adding
+ * every to-be-taken lock to all currently held lock's own dependency
+ * table (if it's not there yet), and we check it for lock order
+ * conflicts and deadlocks.
+ */
+#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	(1UL << CONFIG_LOCKDEP_BITS)
+
+#define MAX_LOCKDEP_CHAINS_BITS	CONFIG_LOCKDEP_CHAINS_BITS
+
+/*
+ * Stack-trace: tightly packed array of stack backtrace
+ * addresses. Protected by the hash_lock.
+ */
+#define MAX_STACK_TRACE_ENTRIES	(1UL << CONFIG_LOCKDEP_STACK_TRACE_BITS)
+#define STACK_TRACE_HASH_SIZE	(1 << CONFIG_LOCKDEP_STACK_TRACE_HASH_BITS)
+#endif
+
+/*
+ * Bit definitions for lock_chain.irq_context
+ */
+#define LOCK_CHAIN_SOFTIRQ_CONTEXT	(1 << 0)
+#define LOCK_CHAIN_HARDIRQ_CONTEXT	(1 << 1)
+
+#define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
+
+#define AVG_LOCKDEP_CHAIN_DEPTH		5
+#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS * AVG_LOCKDEP_CHAIN_DEPTH)
+
+extern struct lock_chain lock_chains[];
+
+#define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
+
+extern void get_usage_chars(struct lock_class *class,
+			    char usage[LOCK_USAGE_CHARS]);
+
+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_zapped_classes;
+extern unsigned long nr_zapped_lock_chains;
+extern unsigned long nr_list_entries;
+extern unsigned long nr_dynamic_keys;
+long lockdep_next_lockchain(long i);
+unsigned long lock_chain_count(void);
+extern unsigned long nr_stack_trace_entries;
+
+extern unsigned int nr_hardirq_chains;
+extern unsigned int nr_softirq_chains;
+extern unsigned int nr_process_chains;
+extern unsigned int nr_free_chain_hlocks;
+extern unsigned int nr_lost_chain_hlocks;
+extern unsigned int nr_large_chain_blocks;
+
+extern unsigned int max_lockdep_depth;
+extern unsigned int max_bfs_queue_depth;
+extern unsigned long max_lock_class_idx;
+
+extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+extern unsigned long lock_classes_in_use[];
+
+#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)
+{
+	return 0;
+}
+static inline unsigned long
+lockdep_count_backward_deps(struct lock_class *class)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_DEBUG_LOCKDEP
+
+#include <asm/local.h>
+/*
+ * Various lockdep statistics.
+ * We want them per cpu as they are often accessed in fast path
+ * and we want to avoid too much cache bouncing.
+ */
+struct lockdep_stats {
+	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);
+
+#define __debug_atomic_inc(ptr)					\
+	this_cpu_inc(lockdep_stats.ptr);
+
+#define debug_atomic_inc(ptr)			{		\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__this_cpu_inc(lockdep_stats.ptr);			\
+}
+
+#define debug_atomic_dec(ptr)			{		\
+	WARN_ON_ONCE(!irqs_disabled());				\
+	__this_cpu_dec(lockdep_stats.ptr);			\
+}
+
+#define debug_atomic_read(ptr)		({				\
+	struct lockdep_stats *__cpu_lockdep_stats;			\
+	unsigned long long __total = 0;					\
+	int __cpu;							\
+	for_each_possible_cpu(__cpu) {					\
+		__cpu_lockdep_stats = &per_cpu(lockdep_stats, __cpu);	\
+		__total += __cpu_lockdep_stats->ptr;			\
+	}								\
+	__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

linux-7.2.3/kernel/locking/lockdep_proc.c

@@ -0,0 +1,732 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kernel/lockdep_proc.c
+ *
+ * Runtime locking correctness validator
+ *
+ * Started by Ingo Molnar:
+ *
+ *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ * Code for /proc/lockdep and /proc/lockdep_stats:
+ *
+ */
+#include <linux/export.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/debug_locks.h>
+#include <linux/vmalloc.h>
+#include <linux/sort.h>
+#include <linux/uaccess.h>
+#include <asm/div64.h>
+
+#include "lockdep_internals.h"
+
+/*
+ * Since iteration of lock_classes is done without holding the lockdep lock,
+ * it is not safe to iterate all_lock_classes list directly as the iteration
+ * may branch off to free_lock_classes or the zapped list. Iteration is done
+ * directly on the lock_classes array by checking the lock_classes_in_use
+ * bitmap and max_lock_class_idx.
+ */
+#define iterate_lock_classes(idx, class)				\
+	for (idx = 0, class = lock_classes; idx <= max_lock_class_idx;	\
+	     idx++, class++)
+
+static void *l_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct lock_class *class = v;
+
+	++class;
+	*pos = class - lock_classes;
+	return (*pos > max_lock_class_idx) ? NULL : class;
+}
+
+static void *l_start(struct seq_file *m, loff_t *pos)
+{
+	unsigned long idx = *pos;
+
+	if (idx > max_lock_class_idx)
+		return NULL;
+	return lock_classes + idx;
+}
+
+static void l_stop(struct seq_file *m, void *v)
+{
+}
+
+static void print_name(struct seq_file *m, struct lock_class *class)
+{
+	char str[KSYM_NAME_LEN];
+	const char *name = class->name;
+
+	if (!name) {
+		name = __get_key_name(class->key, str);
+		seq_printf(m, "%s", name);
+	} else{
+		seq_printf(m, "%s", name);
+		if (class->name_version > 1)
+			seq_printf(m, "#%d", class->name_version);
+		if (class->subclass)
+			seq_printf(m, "/%d", class->subclass);
+	}
+}
+
+static int l_show(struct seq_file *m, void *v)
+{
+	struct lock_class *class = v;
+	struct lock_list *entry;
+	char usage[LOCK_USAGE_CHARS];
+	int idx = class - lock_classes;
+
+	if (v == lock_classes)
+		seq_printf(m, "all lock classes:\n");
+
+	if (!test_bit(idx, lock_classes_in_use))
+		return 0;
+
+	seq_printf(m, "%p", class->key);
+#ifdef CONFIG_DEBUG_LOCKDEP
+	seq_printf(m, " OPS:%8ld", debug_class_ops_read(class));
+#endif
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class));
+		seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class));
+
+		get_usage_chars(class, usage);
+		seq_printf(m, " %s", usage);
+	}
+
+	seq_printf(m, ": ");
+	print_name(m, class);
+	seq_puts(m, "\n");
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		list_for_each_entry(entry, &class->locks_after, entry) {
+			if (entry->distance == 1) {
+				seq_printf(m, " -> [%p] ", entry->class->key);
+				print_name(m, entry->class);
+				seq_puts(m, "\n");
+			}
+		}
+		seq_puts(m, "\n");
+	}
+
+	return 0;
+}
+
+static const struct seq_operations lockdep_ops = {
+	.start	= l_start,
+	.next	= l_next,
+	.stop	= l_stop,
+	.show	= l_show,
+};
+
+#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;
+
+	return lock_chains + (*pos - 1);
+}
+
+static void *lc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	*pos = lockdep_next_lockchain(*pos - 1) + 1;
+	return lc_start(m, pos);
+}
+
+static void lc_stop(struct seq_file *m, void *v)
+{
+}
+
+static int lc_show(struct seq_file *m, void *v)
+{
+	struct lock_chain *chain = v;
+	struct lock_class *class;
+	int i;
+	static const char * const irq_strs[] = {
+		[0]			     = "0",
+		[LOCK_CHAIN_HARDIRQ_CONTEXT] = "hardirq",
+		[LOCK_CHAIN_SOFTIRQ_CONTEXT] = "softirq",
+		[LOCK_CHAIN_SOFTIRQ_CONTEXT|
+		 LOCK_CHAIN_HARDIRQ_CONTEXT] = "hardirq|softirq",
+	};
+
+	if (v == SEQ_START_TOKEN) {
+		if (!nr_free_chain_hlocks)
+			seq_printf(m, "(buggered) ");
+		seq_printf(m, "all lock chains:\n");
+		return 0;
+	}
+
+	seq_printf(m, "irq_context: %s\n", irq_strs[chain->irq_context]);
+
+	for (i = 0; i < chain->depth; i++) {
+		class = lock_chain_get_class(chain, i);
+		if (!class->key)
+			continue;
+
+		seq_printf(m, "[%p] ", class->key);
+		print_name(m, class);
+		seq_puts(m, "\n");
+	}
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+static const struct seq_operations lockdep_chains_ops = {
+	.start	= lc_start,
+	.next	= lc_next,
+	.stop	= lc_stop,
+	.show	= lc_show,
+};
+#endif /* CONFIG_PROVE_LOCKING */
+
+static void lockdep_stats_debug_show(struct seq_file *m)
+{
+#ifdef CONFIG_DEBUG_LOCKDEP
+	unsigned long long hi1 = debug_atomic_read(hardirqs_on_events),
+			   hi2 = debug_atomic_read(hardirqs_off_events),
+			   hr1 = debug_atomic_read(redundant_hardirqs_on),
+			   hr2 = debug_atomic_read(redundant_hardirqs_off),
+			   si1 = debug_atomic_read(softirqs_on_events),
+			   si2 = debug_atomic_read(softirqs_off_events),
+			   sr1 = debug_atomic_read(redundant_softirqs_on),
+			   sr2 = debug_atomic_read(redundant_softirqs_off);
+
+	seq_printf(m, " chain lookup misses:           %11llu\n",
+		debug_atomic_read(chain_lookup_misses));
+	seq_printf(m, " chain lookup hits:             %11llu\n",
+		debug_atomic_read(chain_lookup_hits));
+	seq_printf(m, " cyclic checks:                 %11llu\n",
+		debug_atomic_read(nr_cyclic_checks));
+	seq_printf(m, " redundant checks:              %11llu\n",
+		debug_atomic_read(nr_redundant_checks));
+	seq_printf(m, " redundant links:               %11llu\n",
+		debug_atomic_read(nr_redundant));
+	seq_printf(m, " find-mask forwards checks:     %11llu\n",
+		debug_atomic_read(nr_find_usage_forwards_checks));
+	seq_printf(m, " find-mask backwards checks:    %11llu\n",
+		debug_atomic_read(nr_find_usage_backwards_checks));
+
+	seq_printf(m, " hardirq on events:             %11llu\n", hi1);
+	seq_printf(m, " hardirq off events:            %11llu\n", hi2);
+	seq_printf(m, " redundant hardirq ons:         %11llu\n", hr1);
+	seq_printf(m, " redundant hardirq offs:        %11llu\n", hr2);
+	seq_printf(m, " softirq on events:             %11llu\n", si1);
+	seq_printf(m, " softirq off events:            %11llu\n", si2);
+	seq_printf(m, " redundant softirq ons:         %11llu\n", sr1);
+	seq_printf(m, " redundant softirq offs:        %11llu\n", sr2);
+#endif
+}
+
+static int lockdep_stats_show(struct seq_file *m, void *v)
+{
+	unsigned long nr_unused = 0, nr_uncategorized = 0,
+		      nr_irq_safe = 0, nr_irq_unsafe = 0,
+		      nr_softirq_safe = 0, nr_softirq_unsafe = 0,
+		      nr_hardirq_safe = 0, nr_hardirq_unsafe = 0,
+		      nr_irq_read_safe = 0, nr_irq_read_unsafe = 0,
+		      nr_softirq_read_safe = 0, nr_softirq_read_unsafe = 0,
+		      nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0,
+		      sum_forward_deps = 0;
+
+#ifdef CONFIG_PROVE_LOCKING
+	struct lock_class *class;
+	unsigned long idx;
+
+	iterate_lock_classes(idx, class) {
+		if (!test_bit(idx, lock_classes_in_use))
+			continue;
+
+		if (class->usage_mask == 0)
+			nr_unused++;
+		if (class->usage_mask == LOCKF_USED)
+			nr_uncategorized++;
+		if (class->usage_mask & LOCKF_USED_IN_IRQ)
+			nr_irq_safe++;
+		if (class->usage_mask & LOCKF_ENABLED_IRQ)
+			nr_irq_unsafe++;
+		if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ)
+			nr_softirq_safe++;
+		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ)
+			nr_softirq_unsafe++;
+		if (class->usage_mask & LOCKF_USED_IN_HARDIRQ)
+			nr_hardirq_safe++;
+		if (class->usage_mask & LOCKF_ENABLED_HARDIRQ)
+			nr_hardirq_unsafe++;
+		if (class->usage_mask & LOCKF_USED_IN_IRQ_READ)
+			nr_irq_read_safe++;
+		if (class->usage_mask & LOCKF_ENABLED_IRQ_READ)
+			nr_irq_read_unsafe++;
+		if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ)
+			nr_softirq_read_safe++;
+		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ_READ)
+			nr_softirq_read_unsafe++;
+		if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ)
+			nr_hardirq_read_safe++;
+		if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ)
+			nr_hardirq_read_unsafe++;
+
+		sum_forward_deps += lockdep_count_forward_deps(class);
+	}
+
+#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, " dynamic-keys:                  %11lu\n",
+			nr_dynamic_keys);
+	seq_printf(m, " direct dependencies:           %11lu [max: %lu]\n",
+			nr_list_entries, MAX_LOCKDEP_ENTRIES);
+	seq_printf(m, " indirect dependencies:         %11lu\n",
+			sum_forward_deps);
+
+	/*
+	 * Total number of dependencies:
+	 *
+	 * All irq-safe locks may nest inside irq-unsafe locks,
+	 * plus all the other known dependencies:
+	 */
+	seq_printf(m, " all direct dependencies:       %11lu\n",
+			nr_irq_unsafe * nr_irq_safe +
+			nr_hardirq_unsafe * nr_hardirq_safe +
+			nr_list_entries);
+
+#ifdef CONFIG_PROVE_LOCKING
+	seq_printf(m, " dependency chains:             %11lu [max: %lu]\n",
+			lock_chain_count(), MAX_LOCKDEP_CHAINS);
+	seq_printf(m, " dependency chain hlocks used:  %11lu [max: %lu]\n",
+			MAX_LOCKDEP_CHAIN_HLOCKS -
+			(nr_free_chain_hlocks + nr_lost_chain_hlocks),
+			MAX_LOCKDEP_CHAIN_HLOCKS);
+	seq_printf(m, " dependency chain hlocks lost:  %11u\n",
+			nr_lost_chain_hlocks);
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	seq_printf(m, " in-hardirq chains:             %11u\n",
+			nr_hardirq_chains);
+	seq_printf(m, " in-softirq chains:             %11u\n",
+			nr_softirq_chains);
+#endif
+	seq_printf(m, " in-process chains:             %11u\n",
+			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:        %11llu\n",
+		   lockdep_stack_trace_count());
+	seq_printf(m, " number of stack hash chains:   %11llu\n",
+		   lockdep_stack_hash_count());
+#endif
+	seq_printf(m, " combined max dependencies:     %11u\n",
+			(nr_hardirq_chains + 1) *
+			(nr_softirq_chains + 1) *
+			(nr_process_chains + 1)
+	);
+	seq_printf(m, " hardirq-safe locks:            %11lu\n",
+			nr_hardirq_safe);
+	seq_printf(m, " hardirq-unsafe locks:          %11lu\n",
+			nr_hardirq_unsafe);
+	seq_printf(m, " softirq-safe locks:            %11lu\n",
+			nr_softirq_safe);
+	seq_printf(m, " softirq-unsafe locks:          %11lu\n",
+			nr_softirq_unsafe);
+	seq_printf(m, " irq-safe locks:                %11lu\n",
+			nr_irq_safe);
+	seq_printf(m, " irq-unsafe locks:              %11lu\n",
+			nr_irq_unsafe);
+
+	seq_printf(m, " hardirq-read-safe locks:       %11lu\n",
+			nr_hardirq_read_safe);
+	seq_printf(m, " hardirq-read-unsafe locks:     %11lu\n",
+			nr_hardirq_read_unsafe);
+	seq_printf(m, " softirq-read-safe locks:       %11lu\n",
+			nr_softirq_read_safe);
+	seq_printf(m, " softirq-read-unsafe locks:     %11lu\n",
+			nr_softirq_read_unsafe);
+	seq_printf(m, " irq-read-safe locks:           %11lu\n",
+			nr_irq_read_safe);
+	seq_printf(m, " irq-read-unsafe locks:         %11lu\n",
+			nr_irq_read_unsafe);
+
+	seq_printf(m, " uncategorized locks:           %11lu\n",
+			nr_uncategorized);
+	seq_printf(m, " unused locks:                  %11lu\n",
+			nr_unused);
+	seq_printf(m, " max locking depth:             %11u\n",
+			max_lockdep_depth);
+#ifdef CONFIG_PROVE_LOCKING
+	seq_printf(m, " max bfs queue depth:           %11u\n",
+			max_bfs_queue_depth);
+#endif
+	seq_printf(m, " max lock class index:          %11lu\n",
+			max_lock_class_idx);
+	lockdep_stats_debug_show(m);
+	seq_printf(m, " debug_locks:                   %11u\n",
+			debug_locks);
+
+	/*
+	 * Zapped classes and lockdep data buffers reuse statistics.
+	 */
+	seq_puts(m, "\n");
+	seq_printf(m, " zapped classes:                %11lu\n",
+			nr_zapped_classes);
+#ifdef CONFIG_PROVE_LOCKING
+	seq_printf(m, " zapped lock chains:            %11lu\n",
+			nr_zapped_lock_chains);
+	seq_printf(m, " large chain blocks:            %11u\n",
+			nr_large_chain_blocks);
+#endif
+	return 0;
+}
+
+#ifdef CONFIG_LOCK_STAT
+
+struct lock_stat_data {
+	struct lock_class *class;
+	struct lock_class_stats stats;
+};
+
+struct lock_stat_seq {
+	struct lock_stat_data *iter_end;
+	struct lock_stat_data stats[MAX_LOCKDEP_KEYS];
+};
+
+/*
+ * sort on absolute number of contentions
+ */
+static int lock_stat_cmp(const void *l, const void *r)
+{
+	const struct lock_stat_data *dl = l, *dr = r;
+	unsigned long nl, nr;
+
+	nl = dl->stats.read_waittime.nr + dl->stats.write_waittime.nr;
+	nr = dr->stats.read_waittime.nr + dr->stats.write_waittime.nr;
+
+	return nr - nl;
+}
+
+static void seq_line(struct seq_file *m, char c, int offset, int length)
+{
+	int i;
+
+	for (i = 0; i < offset; i++)
+		seq_puts(m, " ");
+	for (i = 0; i < length; i++)
+		seq_putc(m, c);
+	seq_puts(m, "\n");
+}
+
+static void snprint_time(char *buf, size_t bufsiz, s64 nr)
+{
+	s64 div;
+	s32 rem;
+
+	nr += 5; /* for display rounding */
+	div = div_s64_rem(nr, 1000, &rem);
+	snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10);
+}
+
+static void seq_time(struct seq_file *m, s64 time)
+{
+	char num[22];
+
+	snprint_time(num, sizeof(num), time);
+	seq_printf(m, " %14s", num);
+}
+
+static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
+{
+	seq_printf(m, "%14lu", lt->nr);
+	seq_time(m, lt->min);
+	seq_time(m, lt->max);
+	seq_time(m, lt->total);
+	seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0);
+}
+
+static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
+{
+	const struct lockdep_subclass_key *ckey;
+	struct lock_class_stats *stats;
+	struct lock_class *class;
+	const char *cname;
+	int i, namelen;
+	char name[39];
+
+	class = data->class;
+	stats = &data->stats;
+
+	namelen = 38;
+	if (class->name_version > 1)
+		namelen -= 2; /* XXX truncates versions > 9 */
+	if (class->subclass)
+		namelen -= 2;
+
+	rcu_read_lock_sched();
+	cname = rcu_dereference_sched(class->name);
+	ckey  = rcu_dereference_sched(class->key);
+
+	if (!cname && !ckey) {
+		rcu_read_unlock_sched();
+		return;
+
+	} else if (!cname) {
+		char str[KSYM_NAME_LEN];
+		const char *key_name;
+
+		key_name = __get_key_name(ckey, str);
+		snprintf(name, namelen, "%s", key_name);
+	} else {
+		snprintf(name, namelen, "%s", cname);
+	}
+	rcu_read_unlock_sched();
+
+	namelen = strlen(name);
+	if (class->name_version > 1) {
+		snprintf(name+namelen, 3, "#%d", class->name_version);
+		namelen += 2;
+	}
+	if (class->subclass) {
+		snprintf(name+namelen, 3, "/%d", class->subclass);
+		namelen += 2;
+	}
+
+	if (stats->write_holdtime.nr) {
+		if (stats->read_holdtime.nr)
+			seq_printf(m, "%38s-W:", name);
+		else
+			seq_printf(m, "%40s:", name);
+
+		seq_printf(m, "%14lu ", stats->bounces[bounce_contended_write]);
+		seq_lock_time(m, &stats->write_waittime);
+		seq_printf(m, " %14lu ", stats->bounces[bounce_acquired_write]);
+		seq_lock_time(m, &stats->write_holdtime);
+		seq_puts(m, "\n");
+	}
+
+	if (stats->read_holdtime.nr) {
+		seq_printf(m, "%38s-R:", name);
+		seq_printf(m, "%14lu ", stats->bounces[bounce_contended_read]);
+		seq_lock_time(m, &stats->read_waittime);
+		seq_printf(m, " %14lu ", stats->bounces[bounce_acquired_read]);
+		seq_lock_time(m, &stats->read_holdtime);
+		seq_puts(m, "\n");
+	}
+
+	if (stats->read_waittime.nr + stats->write_waittime.nr == 0)
+		return;
+
+	if (stats->read_holdtime.nr)
+		namelen += 2;
+
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		char ip[32];
+
+		if (class->contention_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contention_point[i]);
+		seq_printf(m, "%40s %14lu %29s %pS\n",
+			   name, stats->contention_point[i],
+			   ip, (void *)class->contention_point[i]);
+	}
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		char ip[32];
+
+		if (class->contending_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contending_point[i]);
+		seq_printf(m, "%40s %14lu %29s %pS\n",
+			   name, stats->contending_point[i],
+			   ip, (void *)class->contending_point[i]);
+	}
+	if (i) {
+		seq_puts(m, "\n");
+		seq_line(m, '.', 0, 40 + 1 + 12 * (14 + 1));
+		seq_puts(m, "\n");
+	}
+}
+
+static void seq_header(struct seq_file *m)
+{
+	seq_puts(m, "lock_stat version 0.4\n");
+
+	if (unlikely(!debug_locks))
+		seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n");
+
+	seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1));
+	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s %14s %14s "
+			"%14s %14s\n",
+			"class name",
+			"con-bounces",
+			"contentions",
+			"waittime-min",
+			"waittime-max",
+			"waittime-total",
+			"waittime-avg",
+			"acq-bounces",
+			"acquisitions",
+			"holdtime-min",
+			"holdtime-max",
+			"holdtime-total",
+			"holdtime-avg");
+	seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1));
+	seq_printf(m, "\n");
+}
+
+static void *ls_start(struct seq_file *m, loff_t *pos)
+{
+	struct lock_stat_seq *data = m->private;
+	struct lock_stat_data *iter;
+
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	iter = data->stats + (*pos - 1);
+	if (iter >= data->iter_end)
+		iter = NULL;
+
+	return iter;
+}
+
+static void *ls_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return ls_start(m, pos);
+}
+
+static void ls_stop(struct seq_file *m, void *v)
+{
+}
+
+static int ls_show(struct seq_file *m, void *v)
+{
+	if (v == SEQ_START_TOKEN)
+		seq_header(m);
+	else
+		seq_stats(m, v);
+
+	return 0;
+}
+
+static const struct seq_operations lockstat_ops = {
+	.start	= ls_start,
+	.next	= ls_next,
+	.stop	= ls_stop,
+	.show	= ls_show,
+};
+
+static int lock_stat_open(struct inode *inode, struct file *file)
+{
+	int res;
+	struct lock_class *class;
+	struct lock_stat_seq *data = vmalloc(sizeof(struct lock_stat_seq));
+
+	if (!data)
+		return -ENOMEM;
+
+	res = seq_open(file, &lockstat_ops);
+	if (!res) {
+		struct lock_stat_data *iter = data->stats;
+		struct seq_file *m = file->private_data;
+		unsigned long idx;
+
+		iterate_lock_classes(idx, class) {
+			if (!test_bit(idx, lock_classes_in_use))
+				continue;
+			iter->class = class;
+			lock_stats(class, &iter->stats);
+			iter++;
+		}
+
+		data->iter_end = iter;
+
+		sort(data->stats, data->iter_end - data->stats,
+				sizeof(struct lock_stat_data),
+				lock_stat_cmp, NULL);
+
+		m->private = data;
+	} else
+		vfree(data);
+
+	return res;
+}
+
+static ssize_t lock_stat_write(struct file *file, const char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct lock_class *class;
+	unsigned long idx;
+	char c;
+
+	if (count) {
+		if (get_user(c, buf))
+			return -EFAULT;
+
+		if (c != '0')
+			return count;
+
+		iterate_lock_classes(idx, class) {
+			if (!test_bit(idx, lock_classes_in_use))
+				continue;
+			clear_lock_stats(class);
+		}
+	}
+	return count;
+}
+
+static int lock_stat_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+
+	vfree(seq->private);
+	return seq_release(inode, file);
+}
+
+static const struct proc_ops lock_stat_proc_ops = {
+	.proc_open	= lock_stat_open,
+	.proc_write	= lock_stat_write,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= lock_stat_release,
+};
+#endif /* CONFIG_LOCK_STAT */
+
+static int __init lockdep_proc_init(void)
+{
+	proc_create_seq("lockdep", S_IRUSR, NULL, &lockdep_ops);
+#ifdef CONFIG_PROVE_LOCKING
+	proc_create_seq("lockdep_chains", S_IRUSR, NULL, &lockdep_chains_ops);
+#endif
+	proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show);
+#ifdef CONFIG_LOCK_STAT
+	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, &lock_stat_proc_ops);
+#endif
+
+	return 0;
+}
+
+__initcall(lockdep_proc_init);
+

linux-7.2.3/kernel/locking/lockdep_states.h

@@ -0,0 +1,8 @@
+/*
+ * Lockdep states,
+ *
+ * please update XXX_LOCK_USAGE_STATES in include/linux/lockdep.h whenever
+ * you add one, or come up with a nice dynamic solution.
+ */
+LOCKDEP_STATE(HARDIRQ)
+LOCKDEP_STATE(SOFTIRQ)

linux-7.2.3/kernel/locking/mcs_spinlock.h

@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * MCS lock defines
+ *
+ * This file contains the main data structure and API definitions of MCS lock.
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bounces that common test-and-set spin-lock
+ * implementations incur.
+ */
+#ifndef __LINUX_MCS_SPINLOCK_H
+#define __LINUX_MCS_SPINLOCK_H
+
+#include <asm/mcs_spinlock.h>
+
+#ifndef arch_mcs_spin_lock_contended
+/*
+ * Using smp_cond_load_acquire() provides the acquire semantics
+ * required so that subsequent operations happen after the
+ * lock is acquired. Additionally, some architectures such as
+ * ARM64 would like to do spin-waiting instead of purely
+ * spinning, and smp_cond_load_acquire() provides that behavior.
+ */
+#define arch_mcs_spin_lock_contended(l)					\
+	smp_cond_load_acquire(l, VAL)
+#endif
+
+#ifndef arch_mcs_spin_unlock_contended
+/*
+ * smp_store_release() provides a memory barrier to ensure all
+ * operations in the critical section has been completed before
+ * unlocking.
+ */
+#define arch_mcs_spin_unlock_contended(l)				\
+	smp_store_release((l), 1)
+#endif
+
+/*
+ * Note: the smp_load_acquire/smp_store_release pair is not
+ * sufficient to form a full memory barrier across
+ * cpus for many architectures (except x86) for mcs_unlock and mcs_lock.
+ * For applications that need a full barrier across multiple cpus
+ * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be
+ * used after mcs_lock.
+ */
+
+/*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
+ */
+static inline
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	/*
+	 * We rely on the full barrier with global transitivity implied by the
+	 * below xchg() to order the initialization stores above against any
+	 * observation of @node. And to provide the ACQUIRE ordering associated
+	 * with a LOCK primitive.
+	 */
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/*
+		 * Lock acquired, don't need to set node->locked to 1. Threads
+		 * only spin on its own node->locked value for lock acquisition.
+		 * However, since this thread can immediately acquire the lock
+		 * and does not proceed to spin on its own node->locked, this
+		 * value won't be used. If a debug mode is needed to
+		 * audit lock status, then set node->locked value here.
+		 */
+		return;
+	}
+	WRITE_ONCE(prev->next, node);
+
+	/* Wait until the lock holder passes the lock down. */
+	arch_mcs_spin_lock_contended(&node->locked);
+}
+
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
+static inline
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+	struct mcs_spinlock *next = READ_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * Release the lock by setting it to NULL
+		 */
+		if (likely(cmpxchg_release(lock, node, NULL) == node))
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = READ_ONCE(node->next)))
+			cpu_relax();
+	}
+
+	/* Pass lock to next waiter. */
+	arch_mcs_spin_unlock_contended(&next->locked);
+}
+
+#endif /* __LINUX_MCS_SPINLOCK_H */

linux-7.2.3/kernel/locking/mutex-debug.c

@@ -0,0 +1,108 @@
+/*
+ * Debugging code for mutexes
+ *
+ * Started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * lock debugging, locking tree, deadlock detection started by:
+ *
+ *  Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey
+ *  Released under the General Public License (GPL).
+ */
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/poison.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/kallsyms.h>
+#include <linux/interrupt.h>
+#include <linux/debug_locks.h>
+
+#include "mutex.h"
+
+/*
+ * Must be called with lock->wait_lock held.
+ */
+void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter)
+{
+	memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter));
+	waiter->magic = waiter;
+	INIT_LIST_HEAD(&waiter->list);
+	waiter->ww_ctx = MUTEX_POISON_WW_CTX;
+}
+
+void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter)
+{
+	lockdep_assert_held(&lock->wait_lock);
+	DEBUG_LOCKS_WARN_ON(!lock->first_waiter);
+	DEBUG_LOCKS_WARN_ON(waiter->magic != waiter);
+}
+
+void debug_mutex_free_waiter(struct mutex_waiter *waiter)
+{
+	DEBUG_LOCKS_WARN_ON(!list_empty(&waiter->list));
+	memset(waiter, MUTEX_DEBUG_FREE, sizeof(*waiter));
+}
+
+void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+			    struct task_struct *task)
+{
+	lockdep_assert_held(&lock->wait_lock);
+
+	/* Current thread can't be already blocked (since it's executing!) */
+	DEBUG_LOCKS_WARN_ON(get_task_blocked_on(task));
+}
+
+void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+			 struct task_struct *task)
+{
+	struct mutex *blocked_on = get_task_blocked_on(task);
+
+	DEBUG_LOCKS_WARN_ON(waiter->task != task);
+	DEBUG_LOCKS_WARN_ON(blocked_on && blocked_on != lock);
+
+	INIT_LIST_HEAD(&waiter->list);
+	waiter->task = NULL;
+}
+
+void debug_mutex_unlock(struct mutex *lock)
+{
+	if (likely(debug_locks)) {
+		DEBUG_LOCKS_WARN_ON(lock->magic != lock);
+	}
+}
+
+void debug_mutex_init(struct mutex *lock)
+{
+	lock->magic = lock;
+}
+
+static void devm_mutex_release(void *res)
+{
+	mutex_destroy(res);
+}
+
+int __devm_mutex_init(struct device *dev, struct mutex *lock)
+{
+	return devm_add_action_or_reset(dev, devm_mutex_release, lock);
+}
+EXPORT_SYMBOL_GPL(__devm_mutex_init);
+
+/***
+ * mutex_destroy - mark a mutex unusable
+ * @lock: the mutex to be destroyed
+ *
+ * This function marks the mutex uninitialized, and any subsequent
+ * use of the mutex is forbidden. The mutex must not be locked when
+ * this function is called.
+ */
+void mutex_destroy(struct mutex *lock)
+{
+	DEBUG_LOCKS_WARN_ON(mutex_is_locked(lock));
+	lock->magic = NULL;
+}
+
+EXPORT_SYMBOL_GPL(mutex_destroy);

linux-7.2.3/kernel/locking/mutex.h

@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Mutexes: blocking mutual exclusion locks
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef CONFIG_PREEMPT_RT
+#include <linux/mutex.h>
+/*
+ * This is the control structure for tasks blocked on mutex, which resides
+ * on the blocked task's kernel stack:
+ */
+struct mutex_waiter {
+	struct list_head	list;
+	struct task_struct	*task;
+	struct ww_acquire_ctx	*ww_ctx;
+#ifdef CONFIG_DEBUG_MUTEXES
+	void			*magic;
+#endif
+};
+
+/*
+ * @owner: contains: 'struct task_struct *' to the current lock owner,
+ * NULL means not owned. Since task_struct pointers are aligned at
+ * at least L1_CACHE_BYTES, we have low bits to store extra state.
+ *
+ * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
+ * Bit1 indicates unlock needs to hand the lock to the top-waiter
+ * Bit2 indicates handoff has been done and we're waiting for pickup.
+ */
+#define MUTEX_FLAG_WAITERS	0x01
+#define MUTEX_FLAG_HANDOFF	0x02
+#define MUTEX_FLAG_PICKUP	0x04
+
+#define MUTEX_FLAGS		0x07
+
+/*
+ * Internal helper function; C doesn't allow us to hide it :/
+ *
+ * DO NOT USE (outside of mutex & scheduler code).
+ */
+static inline struct task_struct *__mutex_owner(struct mutex *lock)
+{
+	if (!lock)
+		return NULL;
+	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~MUTEX_FLAGS);
+}
+
+static inline struct mutex *get_task_blocked_on(struct task_struct *p)
+{
+	guard(raw_spinlock_irqsave)(&p->blocked_lock);
+	return __get_task_blocked_on(p);
+}
+
+#ifdef CONFIG_DEBUG_MUTEXES
+extern void debug_mutex_lock_common(struct mutex *lock,
+				    struct mutex_waiter *waiter);
+extern void debug_mutex_wake_waiter(struct mutex *lock,
+				    struct mutex_waiter *waiter);
+extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
+extern void debug_mutex_add_waiter(struct mutex *lock,
+				   struct mutex_waiter *waiter,
+				   struct task_struct *task);
+extern void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+				      struct task_struct *task);
+extern void debug_mutex_unlock(struct mutex *lock);
+extern void debug_mutex_init(struct mutex *lock);
+#else /* CONFIG_DEBUG_MUTEXES */
+# define debug_mutex_lock_common(lock, waiter)		do { } while (0)
+# define debug_mutex_wake_waiter(lock, waiter)		do { } while (0)
+# define debug_mutex_free_waiter(waiter)		do { } while (0)
+# define debug_mutex_add_waiter(lock, waiter, ti)	do { } while (0)
+# define debug_mutex_remove_waiter(lock, waiter, ti)	do { } while (0)
+# define debug_mutex_unlock(lock)			do { } while (0)
+# define debug_mutex_init(lock)				do { } while (0)
+#endif /* !CONFIG_DEBUG_MUTEXES */
+#endif /* CONFIG_PREEMPT_RT */

linux-7.2.3/kernel/locking/osq_lock.c

@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/osq_lock.h>
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ *
+ * Using a single mcs node per CPU is safe because sleeping locks should not be
+ * called from interrupt context and we have preemption disabled while
+ * spinning.
+ */
+
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
+	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # + 1 value */
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
+
+/*
+ * We use the value 0 to represent "no CPU", thus the encoded value
+ * will be the CPU number incremented by 1.
+ */
+static inline int encode_cpu(int cpu_nr)
+{
+	return cpu_nr + 1;
+}
+
+static inline int node_cpu(struct optimistic_spin_node *node)
+{
+	return node->cpu - 1;
+}
+
+static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
+{
+	int cpu_nr = encoded_cpu_val - 1;
+
+	return per_cpu_ptr(&osq_node, cpu_nr);
+}
+
+/*
+ * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
+ * Can return NULL in case we were the last queued and we updated @lock instead.
+ *
+ * If osq_lock() is being cancelled there must be a previous node
+ * and 'old_cpu' is its CPU #.
+ * For osq_unlock() there is never a previous node and old_cpu is
+ * set to OSQ_UNLOCKED_VAL.
+ */
+static inline struct optimistic_spin_node *
+osq_wait_next(struct optimistic_spin_queue *lock,
+	      struct optimistic_spin_node *node,
+	      int old_cpu)
+{
+	int curr = encode_cpu(smp_processor_id());
+
+	for (;;) {
+		if (atomic_read(&lock->tail) == curr &&
+		    atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) {
+			/*
+			 * We were the last queued, we moved @lock back. @prev
+			 * will now observe @lock and will complete its
+			 * unlock()/unqueue().
+			 */
+			return NULL;
+		}
+
+		/*
+		 * We must xchg() the @node->next value, because if we were to
+		 * leave it in, a concurrent unlock()/unqueue() from
+		 * @node->next might complete Step-A and think its @prev is
+		 * still valid.
+		 *
+		 * If the concurrent unlock()/unqueue() wins the race, we'll
+		 * wait for either @lock to point to us, through its Step-B, or
+		 * wait for a new @node->next from its Step-C.
+		 */
+		if (node->next) {
+			struct optimistic_spin_node *next;
+
+			next = xchg(&node->next, NULL);
+			if (next)
+				return next;
+		}
+
+		cpu_relax();
+	}
+}
+
+bool osq_lock(struct optimistic_spin_queue *lock)
+{
+	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
+	struct optimistic_spin_node *prev, *next;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
+
+	node->locked = 0;
+	node->next = NULL;
+	node->cpu = curr;
+
+	/*
+	 * We need both ACQUIRE (pairs with corresponding RELEASE in
+	 * unlock() uncontended, or fastpath) and RELEASE (to publish
+	 * the node fields we just initialised) semantics when updating
+	 * the lock tail.
+	 */
+	old = atomic_xchg(&lock->tail, curr);
+	if (old == OSQ_UNLOCKED_VAL)
+		return true;
+
+	prev = decode_cpu(old);
+	node->prev = prev;
+
+	/*
+	 * osq_lock()			unqueue
+	 *
+	 * node->prev = prev		osq_wait_next()
+	 * WMB				MB
+	 * prev->next = node		next->prev = prev // unqueue-C
+	 *
+	 * Here 'node->prev' and 'next->prev' are the same variable and we need
+	 * to ensure these stores happen in-order to avoid corrupting the list.
+	 */
+	smp_wmb();
+
+	WRITE_ONCE(prev->next, node);
+
+	/*
+	 * Normally @prev is untouchable after the above store; because at that
+	 * moment unlock can proceed and wipe the node element from stack.
+	 *
+	 * However, since our nodes are static per-cpu storage, we're
+	 * guaranteed their existence -- this allows us to apply
+	 * cmpxchg in an attempt to undo our queueing.
+	 */
+
+	/*
+	 * Wait to acquire the lock or cancellation. Note that need_resched()
+	 * will come with an IPI, which will wake smp_cond_load_relaxed() if it
+	 * is implemented with a monitor-wait. vcpu_is_preempted() relies on
+	 * polling, be careful.
+	 */
+	if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() ||
+				  vcpu_is_preempted(node_cpu(node->prev))))
+		return true;
+
+	/* unqueue */
+	/*
+	 * Step - A  -- stabilize @prev
+	 *
+	 * Undo our @prev->next assignment; this will make @prev's
+	 * unlock()/unqueue() wait for a next pointer since @lock points to us
+	 * (or later).
+	 */
+
+	for (;;) {
+		/*
+		 * cpu_relax() below implies a compiler barrier which would
+		 * prevent this comparison being optimized away.
+		 */
+		if (data_race(prev->next) == node &&
+		    cmpxchg(&prev->next, node, NULL) == node)
+			break;
+
+		/*
+		 * We can only fail the cmpxchg() racing against an unlock(),
+		 * in which case we should observe @node->locked becoming
+		 * true.
+		 */
+		if (smp_load_acquire(&node->locked))
+			return true;
+
+		cpu_relax();
+
+		/*
+		 * Or we race against a concurrent unqueue()'s step-B, in which
+		 * case its step-C will write us a new @node->prev pointer.
+		 */
+		prev = READ_ONCE(node->prev);
+	}
+
+	/*
+	 * Step - B -- stabilize @next
+	 *
+	 * Similar to unlock(), wait for @node->next or move @lock from @node
+	 * back to @prev.
+	 */
+
+	next = osq_wait_next(lock, node, prev->cpu);
+	if (!next)
+		return false;
+
+	/*
+	 * Step - C -- unlink
+	 *
+	 * @prev is stable because its still waiting for a new @prev->next
+	 * pointer, @next is stable because our @node->next pointer is NULL and
+	 * it will wait in Step-A.
+	 */
+
+	WRITE_ONCE(next->prev, prev);
+	WRITE_ONCE(prev->next, next);
+
+	return false;
+}
+
+void osq_unlock(struct optimistic_spin_queue *lock)
+{
+	struct optimistic_spin_node *node, *next;
+	int curr = encode_cpu(smp_processor_id());
+
+	/*
+	 * Fast path for the uncontended case.
+	 */
+	if (atomic_try_cmpxchg_release(&lock->tail, &curr, OSQ_UNLOCKED_VAL))
+		return;
+
+	/*
+	 * Second most likely case.
+	 */
+	node = this_cpu_ptr(&osq_node);
+	next = xchg(&node->next, NULL);
+	if (next) {
+		WRITE_ONCE(next->locked, 1);
+		return;
+	}
+
+	next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL);
+	if (next)
+		WRITE_ONCE(next->locked, 1);
+}

linux-7.2.3/kernel/locking/percpu-rwsem.c

@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <linux/wait.h>
+#include <linux/lockdep.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/debug.h>
+#include <linux/errno.h>
+#include <trace/events/lock.h>
+
+int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
+			const char *name, struct lock_class_key *key)
+{
+	sem->read_count = alloc_percpu(int);
+	if (unlikely(!sem->read_count))
+		return -ENOMEM;
+
+	rcu_sync_init(&sem->rss);
+	rcuwait_init(&sem->writer);
+	init_waitqueue_head(&sem->waiters);
+	atomic_set(&sem->block, 0);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__percpu_init_rwsem);
+
+void percpu_free_rwsem(struct percpu_rw_semaphore *sem)
+{
+	/*
+	 * XXX: temporary kludge. The error path in alloc_super()
+	 * assumes that percpu_free_rwsem() is safe after kzalloc().
+	 */
+	if (!sem->read_count)
+		return;
+
+	rcu_sync_dtor(&sem->rss);
+	free_percpu(sem->read_count);
+	sem->read_count = NULL; /* catch use after free bugs */
+}
+EXPORT_SYMBOL_GPL(percpu_free_rwsem);
+
+static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
+{
+	this_cpu_inc(*sem->read_count);
+
+	/*
+	 * Due to having preemption disabled the decrement happens on
+	 * the same CPU as the increment, avoiding the
+	 * increment-on-one-CPU-and-decrement-on-another problem.
+	 *
+	 * If the reader misses the writer's assignment of sem->block, then the
+	 * writer is guaranteed to see the reader's increment.
+	 *
+	 * Conversely, any readers that increment their sem->read_count after
+	 * the writer looks are guaranteed to see the sem->block value, which
+	 * in turn means that they are guaranteed to immediately decrement
+	 * their sem->read_count, so that it doesn't matter that the writer
+	 * missed them.
+	 */
+
+	smp_mb(); /* A matches D */
+
+	/*
+	 * If !sem->block the critical section starts here, matched by the
+	 * release in percpu_up_write().
+	 */
+	if (likely(!atomic_read_acquire(&sem->block)))
+		return true;
+
+	this_cpu_dec(*sem->read_count);
+
+	/* Prod writer to re-evaluate readers_active_check() */
+	rcuwait_wake_up(&sem->writer);
+
+	return false;
+}
+
+static inline bool __percpu_down_write_trylock(struct percpu_rw_semaphore *sem)
+{
+	if (atomic_read(&sem->block))
+		return false;
+
+	return atomic_xchg(&sem->block, 1) == 0;
+}
+
+static bool __percpu_rwsem_trylock(struct percpu_rw_semaphore *sem, bool reader)
+{
+	if (reader) {
+		bool ret;
+
+		preempt_disable();
+		ret = __percpu_down_read_trylock(sem);
+		preempt_enable();
+
+		return ret;
+	}
+	return __percpu_down_write_trylock(sem);
+}
+
+/*
+ * The return value of wait_queue_entry::func means:
+ *
+ *  <0 - error, wakeup is terminated and the error is returned
+ *   0 - no wakeup, a next waiter is tried
+ *  >0 - woken, if EXCLUSIVE, counted towards @nr_exclusive.
+ *
+ * We use EXCLUSIVE for both readers and writers to preserve FIFO order,
+ * and play games with the return value to allow waking multiple readers.
+ *
+ * Specifically, we wake readers until we've woken a single writer, or until a
+ * trylock fails.
+ */
+static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry,
+				      unsigned int mode, int wake_flags,
+				      void *key)
+{
+	bool reader = wq_entry->flags & WQ_FLAG_CUSTOM;
+	struct percpu_rw_semaphore *sem = key;
+	struct task_struct *p;
+
+	/* concurrent against percpu_down_write(), can get stolen */
+	if (!__percpu_rwsem_trylock(sem, reader))
+		return 1;
+
+	p = get_task_struct(wq_entry->private);
+	list_del_init(&wq_entry->entry);
+	smp_store_release(&wq_entry->private, NULL);
+
+	wake_up_process(p);
+	put_task_struct(p);
+
+	return !reader; /* wake (readers until) 1 writer */
+}
+
+static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader,
+			      bool freeze)
+{
+	DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function);
+	bool wait;
+
+	spin_lock_irq(&sem->waiters.lock);
+	/*
+	 * Serialize against the wakeup in percpu_up_write(), if we fail
+	 * the trylock, the wakeup must see us on the list.
+	 */
+	wait = !__percpu_rwsem_trylock(sem, reader);
+	if (wait) {
+		wq_entry.flags |= WQ_FLAG_EXCLUSIVE | reader * WQ_FLAG_CUSTOM;
+		__add_wait_queue_entry_tail(&sem->waiters, &wq_entry);
+	}
+	spin_unlock_irq(&sem->waiters.lock);
+
+	while (wait) {
+		set_current_state(TASK_UNINTERRUPTIBLE |
+				  (freeze ? TASK_FREEZABLE : 0));
+		if (!smp_load_acquire(&wq_entry.private))
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try,
+				bool freeze)
+{
+	if (__percpu_down_read_trylock(sem))
+		return true;
+
+	if (try)
+		return false;
+
+	trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_READ);
+	preempt_enable();
+	percpu_rwsem_wait(sem, /* .reader = */ true, freeze);
+	preempt_disable();
+	trace_contention_end(sem, 0);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(__percpu_down_read);
+
+#define per_cpu_sum(var)						\
+({									\
+	TYPEOF_UNQUAL(var) __sum = 0;					\
+	int cpu;							\
+	compiletime_assert_atomic_type(__sum);				\
+	for_each_possible_cpu(cpu)					\
+		__sum += per_cpu(var, cpu);				\
+	__sum;								\
+})
+
+bool percpu_is_read_locked(struct percpu_rw_semaphore *sem)
+{
+	return per_cpu_sum(*sem->read_count) != 0 && !atomic_read(&sem->block);
+}
+EXPORT_SYMBOL_GPL(percpu_is_read_locked);
+
+/*
+ * Return true if the modular sum of the sem->read_count per-CPU variable is
+ * zero.  If this sum is zero, then it is stable due to the fact that if any
+ * newly arriving readers increment a given counter, they will immediately
+ * decrement that same counter.
+ *
+ * Assumes sem->block is set.
+ */
+static bool readers_active_check(struct percpu_rw_semaphore *sem)
+{
+	if (per_cpu_sum(*sem->read_count) != 0)
+		return false;
+
+	/*
+	 * If we observed the decrement; ensure we see the entire critical
+	 * section.
+	 */
+
+	smp_mb(); /* C matches B */
+
+	return true;
+}
+
+void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
+{
+	bool contended = false;
+
+	might_sleep();
+	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
+
+	/* Notify readers to take the slow path. */
+	rcu_sync_enter(&sem->rss);
+
+	/*
+	 * Try set sem->block; this provides writer-writer exclusion.
+	 * Having sem->block set makes new readers block.
+	 */
+	if (!__percpu_down_write_trylock(sem)) {
+		trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE);
+		percpu_rwsem_wait(sem, /* .reader = */ false, false);
+		contended = true;
+	}
+
+	/* smp_mb() implied by __percpu_down_write_trylock() on success -- D matches A */
+
+	/*
+	 * If they don't see our store of sem->block, then we are guaranteed to
+	 * see their sem->read_count increment, and therefore will wait for
+	 * them.
+	 */
+
+	/* Wait for all active readers to complete. */
+	rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE);
+	if (contended)
+		trace_contention_end(sem, 0);
+}
+EXPORT_SYMBOL_GPL(percpu_down_write);
+
+void percpu_up_write(struct percpu_rw_semaphore *sem)
+{
+	rwsem_release(&sem->dep_map, _RET_IP_);
+
+	if (trace_contended_release_enabled() && wq_has_sleeper(&sem->waiters))
+		trace_call__contended_release(sem);
+
+	/*
+	 * Signal the writer is done, no fast path yet.
+	 *
+	 * One reason that we cannot just immediately flip to readers_fast is
+	 * that new readers might fail to see the results of this writer's
+	 * critical section.
+	 *
+	 * Therefore we force it through the slow path which guarantees an
+	 * acquire and thereby guarantees the critical section's consistency.
+	 */
+	atomic_set_release(&sem->block, 0);
+
+	/*
+	 * Prod any pending reader/writer to make progress.
+	 */
+	__wake_up(&sem->waiters, TASK_NORMAL, 1, sem);
+
+	/*
+	 * Once this completes (at least one RCU-sched grace period hence) the
+	 * reader fast path will be available again. Safe to use outside the
+	 * exclusive write lock because its counting.
+	 */
+	rcu_sync_exit(&sem->rss);
+}
+EXPORT_SYMBOL_GPL(percpu_up_write);
+
+void __percpu_up_read(struct percpu_rw_semaphore *sem)
+{
+	lockdep_assert_preemption_disabled();
+	/*
+	 * After percpu_up_write() completes, rcu_sync_is_idle() can still
+	 * return false during the grace period, forcing readers into this
+	 * slowpath. Only trace when a writer is actually waiting for
+	 * readers to drain.
+	 */
+	if (trace_contended_release_enabled() && rcuwait_active(&sem->writer))
+		trace_call__contended_release(sem);
+	/*
+	 * slowpath; reader will only ever wake a single blocked
+	 * writer.
+	 */
+	smp_mb(); /* B matches C */
+	/*
+	 * In other words, if they see our decrement (presumably to
+	 * aggregate zero, as that is the only time it matters) they
+	 * will also see our critical section.
+	 */
+	this_cpu_dec(*sem->read_count);
+	rcuwait_wake_up(&sem->writer);
+}
+EXPORT_SYMBOL_GPL(__percpu_up_read);

linux-7.2.3/kernel/locking/qrwlock.c

@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Queued read/write locks
+ *
+ * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#include <linux/smp.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/spinlock.h>
+#include <trace/events/lock.h>
+
+/**
+ * queued_read_lock_slowpath - acquire read lock of a queued rwlock
+ * @lock: Pointer to queued rwlock structure
+ */
+void __lockfunc queued_read_lock_slowpath(struct qrwlock *lock)
+{
+	/*
+	 * Readers come here when they cannot get the lock without waiting
+	 */
+	if (unlikely(in_interrupt())) {
+		/*
+		 * Readers in interrupt context will get the lock immediately
+		 * if the writer is just waiting (not holding the lock yet),
+		 * so spin with ACQUIRE semantics until the lock is available
+		 * without waiting in the queue.
+		 */
+		atomic_cond_read_acquire(&lock->cnts, !(VAL & _QW_LOCKED));
+		return;
+	}
+	atomic_sub(_QR_BIAS, &lock->cnts);
+
+	trace_contention_begin(lock, LCB_F_SPIN | LCB_F_READ);
+
+	/*
+	 * Put the reader into the wait queue
+	 */
+	arch_spin_lock(&lock->wait_lock);
+	atomic_add(_QR_BIAS, &lock->cnts);
+
+	/*
+	 * The ACQUIRE semantics of the following spinning code ensure
+	 * that accesses can't leak upwards out of our subsequent critical
+	 * section in the case that the lock is currently held for write.
+	 */
+	atomic_cond_read_acquire(&lock->cnts, !(VAL & _QW_LOCKED));
+
+	/*
+	 * Signal the next one in queue to become queue head
+	 */
+	arch_spin_unlock(&lock->wait_lock);
+
+	trace_contention_end(lock, 0);
+}
+EXPORT_SYMBOL(queued_read_lock_slowpath);
+
+/**
+ * queued_write_lock_slowpath - acquire write lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
+ */
+void __lockfunc queued_write_lock_slowpath(struct qrwlock *lock)
+{
+	int cnts;
+
+	trace_contention_begin(lock, LCB_F_SPIN | LCB_F_WRITE);
+
+	/* Put the writer into the wait queue */
+	arch_spin_lock(&lock->wait_lock);
+
+	/* Try to acquire the lock directly if no reader is present */
+	if (!(cnts = atomic_read(&lock->cnts)) &&
+	    atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED))
+		goto unlock;
+
+	/* Set the waiting flag to notify readers that a writer is pending */
+	atomic_or(_QW_WAITING, &lock->cnts);
+
+	/* When no more readers or writers, set the locked flag */
+	do {
+		cnts = atomic_cond_read_relaxed(&lock->cnts, VAL == _QW_WAITING);
+	} while (!atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED));
+unlock:
+	arch_spin_unlock(&lock->wait_lock);
+
+	trace_contention_end(lock, 0);
+}
+EXPORT_SYMBOL(queued_write_lock_slowpath);

linux-7.2.3/kernel/locking/qspinlock.c

@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Queued spinlock
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2013-2014,2018 Red Hat, Inc.
+ * (C) Copyright 2015 Intel Corp.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ *          Peter Zijlstra <peterz@infradead.org>
+ */
+
+#ifndef _GEN_PV_LOCK_SLOWPATH
+
+#include <linux/smp.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/mutex.h>
+#include <linux/prefetch.h>
+#include <asm/byteorder.h>
+#include <asm/qspinlock.h>
+#include <trace/events/lock.h>
+
+/*
+ * Include queued spinlock definitions and statistics code
+ */
+#include "qspinlock.h"
+#include "qspinlock_stat.h"
+
+/*
+ * The basic principle of a queue-based spinlock can best be understood
+ * by studying a classic queue-based spinlock implementation called the
+ * MCS lock. A copy of the original MCS lock paper ("Algorithms for Scalable
+ * Synchronization on Shared-Memory Multiprocessors by Mellor-Crummey and
+ * Scott") is available at
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=206115
+ *
+ * This queued spinlock implementation is based on the MCS lock, however to
+ * make it fit the 4 bytes we assume spinlock_t to be, and preserve its
+ * existing API, we must modify it somehow.
+ *
+ * In particular; where the traditional MCS lock consists of a tail pointer
+ * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to
+ * unlock the next pending (next->locked), we compress both these: {tail,
+ * next->locked} into a single u32 value.
+ *
+ * Since a spinlock disables recursion of its own context and there is a limit
+ * to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there
+ * are at most 4 nesting levels, it can be encoded by a 2-bit number. Now
+ * we can encode the tail by combining the 2-bit nesting level with the cpu
+ * number. With one byte for the lock value and 3 bytes for the tail, only a
+ * 32-bit word is now needed. Even though we only need 1 bit for the lock,
+ * we extend it to a full byte to achieve better performance for architectures
+ * that support atomic byte write.
+ *
+ * We also change the first spinner to spin on the lock bit instead of its
+ * node; whereby avoiding the need to carry a node from lock to unlock, and
+ * preserving existing lock API. This also makes the unlock code simpler and
+ * faster.
+ *
+ * N.B. The current implementation only supports architectures that allow
+ *      atomic operations on smaller 8-bit and 16-bit data types.
+ *
+ */
+
+#include "mcs_spinlock.h"
+
+/*
+ * Per-CPU queue node structures; we can never have more than 4 nested
+ * contexts: task, softirq, hardirq, nmi.
+ *
+ * Exactly fits one 64-byte cacheline on a 64-bit architecture.
+ *
+ * PV doubles the storage and uses the second cacheline for PV state.
+ */
+static DEFINE_PER_CPU_ALIGNED(struct qnode, qnodes[_Q_MAX_NODES]);
+
+/*
+ * Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for
+ * all the PV callbacks.
+ */
+
+static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_wait_node(struct mcs_spinlock *node,
+					   struct mcs_spinlock *prev) { }
+static __always_inline void __pv_kick_node(struct qspinlock *lock,
+					   struct mcs_spinlock *node) { }
+static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
+						   struct mcs_spinlock *node)
+						   { return 0; }
+
+#define pv_enabled()		false
+
+#define pv_init_node		__pv_init_node
+#define pv_wait_node		__pv_wait_node
+#define pv_kick_node		__pv_kick_node
+#define pv_wait_head_or_lock	__pv_wait_head_or_lock
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
+#endif
+
+#endif /* _GEN_PV_LOCK_SLOWPATH */
+
+/**
+ * queued_spin_lock_slowpath - acquire the queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ * @val: Current value of the queued spinlock 32-bit word
+ *
+ * (queue tail, pending bit, lock value)
+ *
+ *              fast     :    slow                                  :    unlock
+ *                       :                                          :
+ * uncontended  (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0)
+ *                       :       | ^--------.------.             /  :
+ *                       :       v           \      \            |  :
+ * pending               :    (0,1,1) +--> (0,1,0)   \           |  :
+ *                       :       | ^--'              |           |  :
+ *                       :       v                   |           |  :
+ * uncontended           :    (n,x,y) +--> (n,0,0) --'           |  :
+ *   queue               :       | ^--'                          |  :
+ *                       :       v                               |  :
+ * contended             :    (*,x,y) +--> (*,0,0) ---> (*,0,1) -'  :
+ *   queue               :         ^--'                             :
+ */
+void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	struct mcs_spinlock *prev, *next, *node;
+	u32 old, tail;
+	int idx;
+
+	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
+
+	if (pv_enabled())
+		goto pv_queue;
+
+	if (virt_spin_lock(lock))
+		return;
+
+	/*
+	 * Wait for in-progress pending->locked hand-overs with a bounded
+	 * number of spins so that we guarantee forward progress.
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	if (val == _Q_PENDING_VAL) {
+		int cnt = _Q_PENDING_LOOPS;
+		val = atomic_cond_read_relaxed(&lock->val,
+					       (VAL != _Q_PENDING_VAL) || !cnt--);
+	}
+
+	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
+	/*
+	 * trylock || pending
+	 *
+	 * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock
+	 */
+	val = queued_fetch_set_pending_acquire(lock);
+
+	/*
+	 * 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;
+	}
+
+	/*
+	 * We're pending, wait for the owner to go away.
+	 *
+	 * 0,1,1 -> *,1,0
+	 *
+	 * this wait loop must be a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because not all
+	 * clear_pending_set_locked() implementations imply full
+	 * barriers.
+	 */
+	if (val & _Q_LOCKED_MASK)
+		smp_cond_load_acquire(&lock->locked, !VAL);
+
+	/*
+	 * take ownership and clear the pending bit.
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	clear_pending_set_locked(lock);
+	lockevent_inc(lock_pending);
+	return;
+
+	/*
+	 * End of pending bit optimistic spinning and beginning of MCS
+	 * queuing.
+	 */
+queue:
+	lockevent_inc(lock_slowpath);
+pv_queue:
+	node = this_cpu_ptr(&qnodes[0].mcs);
+	idx = node->count++;
+	tail = encode_tail(smp_processor_id(), idx);
+
+	trace_contention_begin(lock, LCB_F_SPIN);
+
+	/*
+	 * 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 >= _Q_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
+	 * the actual node. If the compiler is kind enough to reorder these
+	 * stores, then an IRQ could overwrite our assignments.
+	 */
+	barrier();
+
+	node->locked = 0;
+	node->next = NULL;
+	pv_init_node(node);
+
+	/*
+	 * We touched a (possibly) cold cacheline in the per-cpu queue node;
+	 * attempt the trylock once more in the hope someone let go while we
+	 * weren't watching.
+	 */
+	if (queued_spin_trylock(lock))
+		goto release;
+
+	/*
+	 * Ensure that the initialisation of @node is complete before we
+	 * publish the updated tail via xchg_tail() and potentially link
+	 * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+	 */
+	smp_wmb();
+
+	/*
+	 * Publish the updated tail.
+	 * We have already touched the queueing cacheline; don't bother with
+	 * pending stuff.
+	 *
+	 * p,*,* -> n,*,*
+	 */
+	old = xchg_tail(lock, tail);
+	next = NULL;
+
+	/*
+	 * if there was a previous node; link it and wait until reaching the
+	 * head of the waitqueue.
+	 */
+	if (old & _Q_TAIL_MASK) {
+		prev = decode_tail(old, qnodes);
+
+		/* Link @node into the waitqueue. */
+		WRITE_ONCE(prev->next, node);
+
+		pv_wait_node(node, prev);
+		arch_mcs_spin_lock_contended(&node->locked);
+
+		/*
+		 * While waiting for the MCS lock, the next pointer may have
+		 * been set by another lock waiter. We optimistically load
+		 * the next pointer & prefetch the cacheline for writing
+		 * to reduce latency in the upcoming MCS unlock operation.
+		 */
+		next = READ_ONCE(node->next);
+		if (next)
+			prefetchw(next);
+	}
+
+	/*
+	 * we're at the head of the waitqueue, wait for the owner & pending to
+	 * go away.
+	 *
+	 * *,x,y -> *,0,0
+	 *
+	 * this wait loop must use a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because the set_locked() function below
+	 * does not imply a full barrier.
+	 *
+	 * The PV pv_wait_head_or_lock function, if active, will acquire
+	 * the lock and return a non-zero value. So we have to skip the
+	 * atomic_cond_read_acquire() call. As the next PV queue head hasn't
+	 * been designated yet, there is no way for the locked value to become
+	 * _Q_SLOW_VAL. So both the set_locked() and the
+	 * atomic_cmpxchg_relaxed() calls will be safe.
+	 *
+	 * If PV isn't active, 0 will be returned instead.
+	 *
+	 */
+	if ((val = pv_wait_head_or_lock(lock, node)))
+		goto locked;
+
+	val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK));
+
+locked:
+	/*
+	 * claim the lock:
+	 *
+	 * n,0,0 -> 0,0,1 : lock, uncontended
+	 * *,*,0 -> *,*,1 : lock, contended
+	 *
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
+	 */
+
+	/*
+	 * In the PV case we might already have _Q_LOCKED_VAL set, because
+	 * of lock stealing; therefore we must also allow:
+	 *
+	 * 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) {
+		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 got set
+	 * which will then detect the remaining tail and queue behind us
+	 * ensuring we'll see a @next.
+	 */
+	set_locked(lock);
+
+	/*
+	 * contended path; wait for next if not observed yet, release.
+	 */
+	if (!next)
+		next = smp_cond_load_relaxed(&node->next, (VAL));
+
+	arch_mcs_spin_unlock_contended(&next->locked);
+	pv_kick_node(lock, next);
+
+release:
+	trace_contention_end(lock, 0);
+
+	/*
+	 * release the node
+	 */
+	__this_cpu_dec(qnodes[0].mcs.count);
+}
+EXPORT_SYMBOL(queued_spin_lock_slowpath);
+
+/*
+ * Generate the paravirt code for queued_spin_unlock_slowpath().
+ */
+#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#define _GEN_PV_LOCK_SLOWPATH
+
+#undef  pv_enabled
+#define pv_enabled()	true
+
+#undef pv_init_node
+#undef pv_wait_node
+#undef pv_kick_node
+#undef pv_wait_head_or_lock
+
+#undef  queued_spin_lock_slowpath
+#define queued_spin_lock_slowpath	__pv_queued_spin_lock_slowpath
+
+#include "qspinlock_paravirt.h"
+#include "qspinlock.c"
+
+bool nopvspin;
+static __init int parse_nopvspin(char *arg)
+{
+	nopvspin = true;
+	return 0;
+}
+early_param("nopvspin", parse_nopvspin);
+#endif

linux-7.2.3/kernel/locking/qspinlock.h

@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Queued spinlock defines
+ *
+ * This file contains macro definitions and functions shared between different
+ * qspinlock slow path implementations.
+ */
+#ifndef __LINUX_QSPINLOCK_H
+#define __LINUX_QSPINLOCK_H
+
+#include <asm-generic/percpu.h>
+#include <linux/percpu-defs.h>
+#include <asm-generic/qspinlock.h>
+#include <asm-generic/mcs_spinlock.h>
+
+#define _Q_MAX_NODES	4
+
+/*
+ * The pending bit spinning loop count.
+ * This heuristic is used to limit the number of lockword accesses
+ * made by atomic_cond_read_relaxed when waiting for the lock to
+ * transition out of the "== _Q_PENDING_VAL" state. We don't spin
+ * indefinitely because there's no guarantee that we'll make forward
+ * progress.
+ */
+#ifndef _Q_PENDING_LOOPS
+#define _Q_PENDING_LOOPS	1
+#endif
+
+/*
+ * 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
+};
+
+/*
+ * We must be able to distinguish between no-tail and the tail at 0:0,
+ * therefore increment the cpu number by one.
+ */
+
+static inline __pure u32 encode_tail(int cpu, int idx)
+{
+	u32 tail;
+
+	tail  = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+	tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+	return tail;
+}
+
+static inline __pure struct mcs_spinlock *decode_tail(u32 tail,
+						      struct qnode __percpu *qnodes)
+{
+	int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+	int idx = (tail &  _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+	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)
+
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
+}
+
+/*
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail), which heads an address dependency
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+	/*
+	 * We can use relaxed semantics since the caller ensures that the
+	 * MCS node is properly initialized before updating the tail.
+	 */
+	return (u32)xchg_relaxed(&lock->tail,
+				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+}
+
+#else /* _Q_PENDING_BITS == 8 */
+
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
+}
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+	atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
+}
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+	u32 old, new;
+
+	old = atomic_read(&lock->val);
+	do {
+		new = (old & _Q_LOCKED_PENDING_MASK) | tail;
+		/*
+		 * We can use relaxed semantics since the caller ensures that
+		 * the MCS node is properly initialized before updating the
+		 * tail.
+		 */
+	} while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new));
+
+	return old;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/**
+ * queued_fetch_set_pending_acquire - fetch the whole lock value and set pending
+ * @lock : Pointer to queued spinlock structure
+ * Return: The previous lock value
+ *
+ * *,*,* -> *,1,*
+ */
+#ifndef queued_fetch_set_pending_acquire
+static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
+{
+	return atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+}
+#endif
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
+}
+
+#endif /* __LINUX_QSPINLOCK_H */

linux-7.2.3/kernel/locking/qspinlock_paravirt.h

@@ -0,0 +1,557 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _GEN_PV_LOCK_SLOWPATH
+#error "do not include this file"
+#endif
+
+#include <linux/hash.h>
+#include <linux/memblock.h>
+#include <linux/debug_locks.h>
+
+/*
+ * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
+ * of spinning them.
+ *
+ * This relies on the architecture to provide two paravirt hypercalls:
+ *
+ *   pv_wait(u8 *ptr, u8 val) -- suspends the vcpu if *ptr == val
+ *   pv_kick(cpu)             -- wakes a suspended vcpu
+ *
+ * Using these we implement __pv_queued_spin_lock_slowpath() and
+ * __pv_queued_spin_unlock() to replace native_queued_spin_lock_slowpath() and
+ * native_queued_spin_unlock().
+ */
+
+#define _Q_SLOW_VAL	(3U << _Q_LOCKED_OFFSET)
+
+/*
+ * Queue Node Adaptive Spinning
+ *
+ * A queue node vCPU will stop spinning if the vCPU in the previous node is
+ * not running. The one lock stealing attempt allowed at slowpath entry
+ * mitigates the slight slowdown for non-overcommitted guest with this
+ * aggressive wait-early mechanism.
+ *
+ * The status of the previous node will be checked at fixed interval
+ * controlled by PV_PREV_CHECK_MASK. This is to ensure that we won't
+ * pound on the cacheline of the previous node too heavily.
+ */
+#define PV_PREV_CHECK_MASK	0xff
+
+/*
+ * Queue node uses: VCPU_RUNNING & VCPU_HALTED.
+ * Queue head uses: VCPU_RUNNING & VCPU_HASHED.
+ */
+enum vcpu_state {
+	VCPU_RUNNING = 0,
+	VCPU_HALTED,		/* Used only in pv_wait_node */
+	VCPU_HASHED,		/* = pv_hash'ed + VCPU_HALTED */
+};
+
+struct pv_node {
+	struct mcs_spinlock	mcs;
+	int			cpu;
+	u8			state;
+};
+
+/*
+ * Hybrid PV queued/unfair lock
+ *
+ * By replacing the regular queued_spin_trylock() with the function below,
+ * it will be called once when a lock waiter enter the PV slowpath before
+ * being queued.
+ *
+ * The pending bit is set by the queue head vCPU of the MCS wait queue in
+ * pv_wait_head_or_lock() to signal that it is ready to spin on the lock.
+ * When that bit becomes visible to the incoming waiters, no lock stealing
+ * is allowed. The function will return immediately to make the waiters
+ * enter the MCS wait queue. So lock starvation shouldn't happen as long
+ * as the queued mode vCPUs are actively running to set the pending bit
+ * and hence disabling lock stealing.
+ *
+ * When the pending bit isn't set, the lock waiters will stay in the unfair
+ * mode spinning on the lock unless the MCS wait queue is empty. In this
+ * case, the lock waiters will enter the queued mode slowpath trying to
+ * become the queue head and set the pending bit.
+ *
+ * This hybrid PV queued/unfair lock combines the best attributes of a
+ * queued lock (no lock starvation) and an unfair lock (good performance
+ * on not heavily contended locks).
+ */
+#define queued_spin_trylock(l)	pv_hybrid_queued_unfair_trylock(l)
+static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
+{
+	/*
+	 * Stay in unfair lock mode as long as queued mode waiters are
+	 * present in the MCS wait queue but the pending bit isn't set.
+	 */
+	for (;;) {
+		int val = atomic_read(&lock->val);
+		u8 old = 0;
+
+		if (!(val & _Q_LOCKED_PENDING_MASK) &&
+		    try_cmpxchg_acquire(&lock->locked, &old, _Q_LOCKED_VAL)) {
+			lockevent_inc(pv_lock_stealing);
+			return true;
+		}
+		if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
+			break;
+
+		cpu_relax();
+	}
+
+	return false;
+}
+
+/*
+ * The pending bit is used by the queue head vCPU to indicate that it
+ * is actively spinning on the lock and no lock stealing is allowed.
+ */
+#if _Q_PENDING_BITS == 8
+static __always_inline void set_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 1);
+}
+
+/*
+ * The pending bit check in pv_queued_spin_steal_lock() isn't a memory
+ * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the
+ * lock just to be sure that it will get it.
+ */
+static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
+{
+	u16 old = _Q_PENDING_VAL;
+
+	return !READ_ONCE(lock->locked) &&
+	       try_cmpxchg_acquire(&lock->locked_pending, &old, _Q_LOCKED_VAL);
+}
+#else /* _Q_PENDING_BITS == 8 */
+static __always_inline void set_pending(struct qspinlock *lock)
+{
+	atomic_or(_Q_PENDING_VAL, &lock->val);
+}
+
+static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
+{
+	int old, new;
+
+	old = atomic_read(&lock->val);
+	do {
+		if (old & _Q_LOCKED_MASK)
+			return false;
+		/*
+		 * Try to clear pending bit & set locked bit
+		 */
+		new = (old & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
+	} while (!atomic_try_cmpxchg_acquire (&lock->val, &old, new));
+
+	return true;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/*
+ * Lock and MCS node addresses hash table for fast lookup
+ *
+ * Hashing is done on a per-cacheline basis to minimize the need to access
+ * more than one cacheline.
+ *
+ * Dynamically allocate a hash table big enough to hold at least 4X the
+ * number of possible cpus in the system. Allocation is done on page
+ * granularity. So the minimum number of hash buckets should be at least
+ * 256 (64-bit) or 512 (32-bit) to fully utilize a 4k page.
+ *
+ * Since we should not be holding locks from NMI context (very rare indeed) the
+ * max load factor is 0.75, which is around the point where open addressing
+ * breaks down.
+ *
+ */
+struct pv_hash_entry {
+	struct qspinlock *lock;
+	struct pv_node   *node;
+};
+
+#define PV_HE_PER_LINE	(SMP_CACHE_BYTES / sizeof(struct pv_hash_entry))
+#define PV_HE_MIN	(PAGE_SIZE / sizeof(struct pv_hash_entry))
+
+static struct pv_hash_entry *pv_lock_hash;
+static unsigned int pv_lock_hash_bits __read_mostly;
+
+/*
+ * Allocate memory for the PV qspinlock hash buckets
+ *
+ * This function should be called from the paravirt spinlock initialization
+ * routine.
+ */
+void __init __pv_init_lock_hash(void)
+{
+	int pv_hash_size = ALIGN(4 * num_possible_cpus(), PV_HE_PER_LINE);
+
+	if (pv_hash_size < PV_HE_MIN)
+		pv_hash_size = PV_HE_MIN;
+
+	/*
+	 * Allocate space from bootmem which should be page-size aligned
+	 * and hence cacheline aligned.
+	 */
+	pv_lock_hash = alloc_large_system_hash("PV qspinlock",
+					       sizeof(struct pv_hash_entry),
+					       pv_hash_size, 0,
+					       HASH_EARLY | HASH_ZERO,
+					       &pv_lock_hash_bits, NULL,
+					       pv_hash_size, pv_hash_size);
+}
+
+#define for_each_hash_entry(he, offset, hash)						\
+	for (hash &= ~(PV_HE_PER_LINE - 1), he = &pv_lock_hash[hash], offset = 0;	\
+	     offset < (1 << pv_lock_hash_bits);						\
+	     offset++, he = &pv_lock_hash[(hash + offset) & ((1 << pv_lock_hash_bits) - 1)])
+
+static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
+{
+	unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+	struct pv_hash_entry *he;
+	int hopcnt = 0;
+
+	for_each_hash_entry(he, offset, hash) {
+		struct qspinlock *old = NULL;
+		hopcnt++;
+		if (try_cmpxchg(&he->lock, &old, lock)) {
+			WRITE_ONCE(he->node, node);
+			lockevent_pv_hop(hopcnt);
+			return &he->lock;
+		}
+	}
+	/*
+	 * Hard assume there is a free entry for us.
+	 *
+	 * This is guaranteed by ensuring every blocked lock only ever consumes
+	 * a single entry, and since we only have 4 nesting levels per CPU
+	 * and allocated 4*nr_possible_cpus(), this must be so.
+	 *
+	 * The single entry is guaranteed by having the lock owner unhash
+	 * before it releases.
+	 */
+	BUG();
+}
+
+static struct pv_node *pv_unhash(struct qspinlock *lock)
+{
+	unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+	struct pv_hash_entry *he;
+	struct pv_node *node;
+
+	for_each_hash_entry(he, offset, hash) {
+		if (READ_ONCE(he->lock) == lock) {
+			node = READ_ONCE(he->node);
+			WRITE_ONCE(he->lock, NULL);
+			return node;
+		}
+	}
+	/*
+	 * Hard assume we'll find an entry.
+	 *
+	 * This guarantees a limited lookup time and is itself guaranteed by
+	 * having the lock owner do the unhash -- IFF the unlock sees the
+	 * SLOW flag, there MUST be a hash entry.
+	 */
+	BUG();
+}
+
+/*
+ * Return true if when it is time to check the previous node which is not
+ * in a running state.
+ */
+static inline bool
+pv_wait_early(struct pv_node *prev, int loop)
+{
+	if ((loop & PV_PREV_CHECK_MASK) != 0)
+		return false;
+
+	return READ_ONCE(prev->state) != VCPU_RUNNING;
+}
+
+/*
+ * Initialize the PV part of the mcs_spinlock node.
+ */
+static void pv_init_node(struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+
+	BUILD_BUG_ON(sizeof(struct pv_node) > sizeof(struct qnode));
+
+	pn->cpu = smp_processor_id();
+	pn->state = VCPU_RUNNING;
+}
+
+/*
+ * Wait for node->locked to become true, halt the vcpu after a short spin.
+ * pv_kick_node() is used to set _Q_SLOW_VAL and fill in hash table on its
+ * behalf.
+ */
+static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+	struct pv_node *pp = (struct pv_node *)prev;
+	bool wait_early;
+	int loop;
+
+	for (;;) {
+		for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) {
+			if (READ_ONCE(node->locked))
+				return;
+			if (pv_wait_early(pp, loop)) {
+				wait_early = true;
+				break;
+			}
+			cpu_relax();
+		}
+
+		/*
+		 * Order pn->state vs pn->locked thusly:
+		 *
+		 * [S] pn->state = VCPU_HALTED	  [S] next->locked = 1
+		 *     MB			      MB
+		 * [L] pn->locked		[RmW] pn->state = VCPU_HASHED
+		 *
+		 * Matches the cmpxchg() from pv_kick_node().
+		 */
+		smp_store_mb(pn->state, VCPU_HALTED);
+
+		if (!READ_ONCE(node->locked)) {
+			lockevent_inc(pv_wait_node);
+			lockevent_cond_inc(pv_wait_early, wait_early);
+			pv_wait(&pn->state, VCPU_HALTED);
+		}
+
+		/*
+		 * If pv_kick_node() changed us to VCPU_HASHED, retain that
+		 * value so that pv_wait_head_or_lock() knows to not also try
+		 * to hash this lock.
+		 */
+		cmpxchg(&pn->state, VCPU_HALTED, VCPU_RUNNING);
+
+		/*
+		 * If the locked flag is still not set after wakeup, it is a
+		 * spurious wakeup and the vCPU should wait again. However,
+		 * there is a pretty high overhead for CPU halting and kicking.
+		 * So it is better to spin for a while in the hope that the
+		 * MCS lock will be released soon.
+		 */
+		lockevent_cond_inc(pv_spurious_wakeup,
+				  !READ_ONCE(node->locked));
+	}
+
+	/*
+	 * By now our node->locked should be 1 and our caller will not actually
+	 * spin-wait for it. We do however rely on our caller to do a
+	 * load-acquire for us.
+	 */
+}
+
+/*
+ * Called after setting next->locked = 1 when we're the lock owner.
+ *
+ * Instead of waking the waiters stuck in pv_wait_node() advance their state
+ * such that they're waiting in pv_wait_head_or_lock(), this avoids a
+ * wake/sleep cycle.
+ */
+static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+	u8 old = VCPU_HALTED;
+	/*
+	 * If the vCPU is indeed halted, advance its state to match that of
+	 * pv_wait_node(). If OTOH this fails, the vCPU was running and will
+	 * observe its next->locked value and advance itself.
+	 *
+	 * Matches with smp_store_mb() and cmpxchg() in pv_wait_node()
+	 *
+	 * The write to next->locked in arch_mcs_spin_unlock_contended()
+	 * must be ordered before the read of pn->state in the cmpxchg()
+	 * below for the code to work correctly. To guarantee full ordering
+	 * irrespective of the success or failure of the cmpxchg(),
+	 * a relaxed version with explicit barrier is used. The control
+	 * dependency will order the reading of pn->state before any
+	 * subsequent writes.
+	 */
+	smp_mb__before_atomic();
+	if (!try_cmpxchg_relaxed(&pn->state, &old, VCPU_HASHED))
+		return;
+
+	/*
+	 * Put the lock into the hash table and set the _Q_SLOW_VAL.
+	 *
+	 * As this is the same vCPU that will check the _Q_SLOW_VAL value and
+	 * the hash table later on at unlock time, no atomic instruction is
+	 * needed.
+	 */
+	WRITE_ONCE(lock->locked, _Q_SLOW_VAL);
+	(void)pv_hash(lock, pn);
+}
+
+/*
+ * Wait for l->locked to become clear and acquire the lock;
+ * halt the vcpu after a short spin.
+ * __pv_queued_spin_unlock() will wake us.
+ *
+ * The current value of the lock will be returned for additional processing.
+ */
+static u32
+pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
+{
+	struct pv_node *pn = (struct pv_node *)node;
+	struct qspinlock **lp = NULL;
+	int waitcnt = 0;
+	int loop;
+
+	/*
+	 * If pv_kick_node() already advanced our state, we don't need to
+	 * insert ourselves into the hash table anymore.
+	 */
+	if (READ_ONCE(pn->state) == VCPU_HASHED)
+		lp = (struct qspinlock **)1;
+
+	/*
+	 * Tracking # of slowpath locking operations
+	 */
+	lockevent_inc(lock_slowpath);
+
+	for (;; waitcnt++) {
+		/*
+		 * Set correct vCPU state to be used by queue node wait-early
+		 * mechanism.
+		 */
+		WRITE_ONCE(pn->state, VCPU_RUNNING);
+
+		/*
+		 * Set the pending bit in the active lock spinning loop to
+		 * disable lock stealing before attempting to acquire the lock.
+		 */
+		set_pending(lock);
+		for (loop = SPIN_THRESHOLD; loop; loop--) {
+			if (trylock_clear_pending(lock))
+				goto gotlock;
+			cpu_relax();
+		}
+		clear_pending(lock);
+
+
+		if (!lp) { /* ONCE */
+			lp = pv_hash(lock, pn);
+
+			/*
+			 * We must hash before setting _Q_SLOW_VAL, such that
+			 * when we observe _Q_SLOW_VAL in __pv_queued_spin_unlock()
+			 * we'll be sure to be able to observe our hash entry.
+			 *
+			 *   [S] <hash>                 [Rmw] l->locked == _Q_SLOW_VAL
+			 *       MB                           RMB
+			 * [RmW] l->locked = _Q_SLOW_VAL  [L] <unhash>
+			 *
+			 * Matches the smp_rmb() in __pv_queued_spin_unlock().
+			 */
+			if (xchg(&lock->locked, _Q_SLOW_VAL) == 0) {
+				/*
+				 * The lock was free and now we own the lock.
+				 * Change the lock value back to _Q_LOCKED_VAL
+				 * and unhash the table.
+				 */
+				WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
+				WRITE_ONCE(*lp, NULL);
+				goto gotlock;
+			}
+		}
+		WRITE_ONCE(pn->state, VCPU_HASHED);
+		lockevent_inc(pv_wait_head);
+		lockevent_cond_inc(pv_wait_again, waitcnt);
+		pv_wait(&lock->locked, _Q_SLOW_VAL);
+
+		/*
+		 * Because of lock stealing, the queue head vCPU may not be
+		 * able to acquire the lock before it has to wait again.
+		 */
+	}
+
+	/*
+	 * The cmpxchg() or xchg() call before coming here provides the
+	 * acquire semantics for locking. The dummy ORing of _Q_LOCKED_VAL
+	 * here is to indicate to the compiler that the value will always
+	 * be nozero to enable better code optimization.
+	 */
+gotlock:
+	return (u32)(atomic_read(&lock->val) | _Q_LOCKED_VAL);
+}
+
+/*
+ * Include the architecture specific callee-save thunk of the
+ * __pv_queued_spin_unlock(). This thunk is put together with
+ * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
+ * function close to each other sharing consecutive instruction cachelines.
+ * Alternatively, architecture specific version of __pv_queued_spin_unlock()
+ * can be defined.
+ */
+#include <asm/qspinlock_paravirt.h>
+
+/*
+ * PV versions of the unlock fastpath and slowpath functions to be used
+ * instead of queued_spin_unlock().
+ */
+__visible __lockfunc void
+__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
+{
+	struct pv_node *node;
+
+	if (unlikely(locked != _Q_SLOW_VAL)) {
+		WARN(!debug_locks_silent,
+		     "pvqspinlock: lock 0x%lx has corrupted value 0x%x!\n",
+		     (unsigned long)lock, atomic_read(&lock->val));
+		return;
+	}
+
+	/*
+	 * A failed cmpxchg doesn't provide any memory-ordering guarantees,
+	 * so we need a barrier to order the read of the node data in
+	 * pv_unhash *after* we've read the lock being _Q_SLOW_VAL.
+	 *
+	 * Matches the cmpxchg() in pv_wait_head_or_lock() setting _Q_SLOW_VAL.
+	 */
+	smp_rmb();
+
+	/*
+	 * Since the above failed to release, this must be the SLOW path.
+	 * Therefore start by looking up the blocked node and unhashing it.
+	 */
+	node = pv_unhash(lock);
+
+	/*
+	 * Now that we have a reference to the (likely) blocked pv_node,
+	 * release the lock.
+	 */
+	smp_store_release(&lock->locked, 0);
+
+	/*
+	 * At this point the memory pointed at by lock can be freed/reused,
+	 * however we can still use the pv_node to kick the CPU.
+	 * The other vCPU may not really be halted, but kicking an active
+	 * vCPU is harmless other than the additional latency in completing
+	 * the unlock.
+	 */
+	lockevent_inc(pv_kick_unlock);
+	pv_kick(node->cpu);
+}
+
+#ifndef __pv_queued_spin_unlock
+__visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	u8 locked = _Q_LOCKED_VAL;
+
+	/*
+	 * We must not unlock if SLOW, because in that case we must first
+	 * unhash. Otherwise it would be possible to have multiple @lock
+	 * entries, which would be BAD.
+	 */
+	if (try_cmpxchg_release(&lock->locked, &locked, 0))
+		return;
+
+	__pv_queued_spin_unlock_slowpath(lock, locked);
+}
+#endif /* __pv_queued_spin_unlock */

linux-7.2.3/kernel/locking/qspinlock_stat.h

@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#include "lock_events.h"
+
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+/*
+ * Collect pvqspinlock locking event counts
+ */
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/fs.h>
+
+#define EVENT_COUNT(ev)	lockevents[LOCKEVENT_ ## ev]
+
+/*
+ * PV specific per-cpu counter
+ */
+static DEFINE_PER_CPU(u64, pv_kick_time);
+
+/*
+ * Function to read and return the PV qspinlock counts.
+ *
+ * The following counters are handled specially:
+ * 1. pv_latency_kick
+ *    Average kick latency (ns) = pv_latency_kick/pv_kick_unlock
+ * 2. pv_latency_wake
+ *    Average wake latency (ns) = pv_latency_wake/pv_kick_wake
+ * 3. pv_hash_hops
+ *    Average hops/hash = pv_hash_hops/pv_kick_unlock
+ */
+ssize_t 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, kicks = 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);
+		/*
+		 * Need to sum additional counters for some of them
+		 */
+		switch (id) {
+
+		case LOCKEVENT_pv_latency_kick:
+		case LOCKEVENT_pv_hash_hops:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_unlock), cpu);
+			break;
+
+		case LOCKEVENT_pv_latency_wake:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_wake), cpu);
+			break;
+		}
+	}
+
+	if (id == LOCKEVENT_pv_hash_hops) {
+		u64 frac = 0;
+
+		if (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",
+			       sum, frac);
+	} else {
+		/*
+		 * Round to the nearest ns
+		 */
+		if ((id == LOCKEVENT_pv_latency_kick) ||
+		    (id == LOCKEVENT_pv_latency_wake)) {
+			if (kicks)
+				sum = DIV_ROUND_CLOSEST_ULL(sum, kicks);
+		}
+		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
+	}
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+/*
+ * PV hash hop count
+ */
+static inline void lockevent_pv_hop(int hopcnt)
+{
+	this_cpu_add(EVENT_COUNT(pv_hash_hops), hopcnt);
+}
+
+/*
+ * Replacement function for pv_kick()
+ */
+static inline void __pv_kick(int cpu)
+{
+	u64 start = sched_clock();
+
+	per_cpu(pv_kick_time, cpu) = start;
+	pv_kick(cpu);
+	this_cpu_add(EVENT_COUNT(pv_latency_kick), sched_clock() - start);
+}
+
+/*
+ * Replacement function for pv_wait()
+ */
+static inline void __pv_wait(u8 *ptr, u8 val)
+{
+	u64 *pkick_time = this_cpu_ptr(&pv_kick_time);
+
+	*pkick_time = 0;
+	pv_wait(ptr, val);
+	if (*pkick_time) {
+		this_cpu_add(EVENT_COUNT(pv_latency_wake),
+			     sched_clock() - *pkick_time);
+		lockevent_inc(pv_kick_wake);
+	}
+}
+
+#define pv_kick(c)	__pv_kick(c)
+#define pv_wait(p, v)	__pv_wait(p, v)
+
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_LOCK_EVENT_COUNTS */
+
+static inline void lockevent_pv_hop(int hopcnt)	{ }
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */

linux-7.2.3/kernel/locking/rtmutex_api.c

@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rtmutex API
+ */
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#define RT_MUTEX_BUILD_MUTEX
+#include "rtmutex.c"
+
+/*
+ * Max number of times we'll walk the boosting chain:
+ */
+int max_lock_depth = 1024;
+
+static const struct ctl_table rtmutex_sysctl_table[] = {
+	{
+		.procname	= "max_lock_depth",
+		.data		= &max_lock_depth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+static int __init init_rtmutex_sysctl(void)
+{
+	register_sysctl_init("kernel", rtmutex_sysctl_table);
+	return 0;
+}
+
+subsys_initcall(init_rtmutex_sysctl);
+
+/*
+ * Debug aware fast / slowpath lock,trylock,unlock
+ *
+ * The atomic acquire/release ops are compiled away, when either the
+ * architecture does not support cmpxchg or when debugging is enabled.
+ */
+static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock,
+						  unsigned int state,
+						  struct lockdep_map *nest_lock,
+						  unsigned int subclass)
+	__cond_acquires(0, lock)
+{
+	int ret;
+
+	might_sleep();
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, _RET_IP_);
+	ret = __rt_mutex_lock(&lock->rtmutex, state);
+	if (ret)
+		mutex_release(&lock->dep_map, _RET_IP_);
+	return ret;
+}
+
+void rt_mutex_base_init(struct rt_mutex_base *rtb)
+{
+	__rt_mutex_base_init(rtb);
+}
+EXPORT_SYMBOL(rt_mutex_base_init);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+	if (__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, subclass) == 0)
+		return;
+	/*
+	 * The code below is never reached because __rt_mutex_lock_common() only
+	 * returns an error code if interrupted by a signal or upon a timeout.
+	 */
+	WARN_ON_ONCE(true);
+	__acquire(lock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+
+void __sched _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock)
+{
+	if (__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, nest_lock, 0) == 0)
+		return;
+	/*
+	 * The code below is never reached because __rt_mutex_lock_common() only
+	 * returns an error code if interrupted by a signal or upon a timeout.
+	 */
+	WARN_ON_ONCE(true);
+	__acquire(lock);
+}
+EXPORT_SYMBOL_GPL(_rt_mutex_lock_nest_lock);
+
+#else /* !CONFIG_DEBUG_LOCK_ALLOC */
+
+/**
+ * rt_mutex_lock - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ */
+void __sched rt_mutex_lock(struct rt_mutex *lock)
+{
+	if (__rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, 0) == 0)
+		return;
+	/*
+	 * The code below is never reached because __rt_mutex_lock_common() only
+	 * returns an error code if interrupted by a signal or upon a timeout.
+	 */
+	WARN_ON_ONCE(true);
+	__acquire(lock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
+
+/**
+ * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
+ *
+ * @lock:		the rt_mutex to be locked
+ *
+ * Returns:
+ *  0		on success
+ * -EINTR	when interrupted by a signal
+ */
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
+{
+	return __rt_mutex_lock_common(lock, TASK_INTERRUPTIBLE, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
+
+/**
+ * rt_mutex_lock_killable - lock a rt_mutex killable
+ *
+ * @lock:		the rt_mutex to be locked
+ *
+ * Returns:
+ *  0		on success
+ * -EINTR	when interrupted by a signal
+ */
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
+{
+	return __rt_mutex_lock_common(lock, TASK_KILLABLE, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
+
+/**
+ * rt_mutex_trylock - try to lock a rt_mutex
+ *
+ * @lock:	the rt_mutex to be locked
+ *
+ * This function can only be called in thread context. It's safe to call it
+ * from atomic regions, but not from hard or soft interrupt context.
+ *
+ * Returns:
+ *  1 on success
+ *  0 on contention
+ */
+int __sched rt_mutex_trylock(struct rt_mutex *lock)
+{
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
+		return 0;
+
+	ret = __rt_mutex_trylock(&lock->rtmutex);
+	if (ret)
+		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rt_mutex_trylock);
+
+/**
+ * rt_mutex_unlock - unlock a rt_mutex
+ *
+ * @lock: the rt_mutex to be unlocked
+ */
+void __sched rt_mutex_unlock(struct rt_mutex *lock)
+{
+	mutex_release(&lock->dep_map, _RET_IP_);
+	__rt_mutex_unlock(&lock->rtmutex);
+	__release(lock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_unlock);
+
+/*
+ * Futex variants, must not use fastpath.
+ */
+int __sched rt_mutex_futex_trylock(struct rt_mutex_base *lock)
+{
+	return rt_mutex_slowtrylock(lock);
+}
+
+int __sched __rt_mutex_futex_trylock(struct rt_mutex_base *lock)
+{
+	return __rt_mutex_slowtrylock(lock);
+}
+
+/**
+ * __rt_mutex_futex_unlock - Futex variant, that since futex variants
+ * do not use the fast-path, can be simple and will not need to retry.
+ *
+ * @lock:	The rt_mutex to be unlocked
+ * @wqh:	The wake queue head from which to get the next lock waiter
+ */
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex_base *lock,
+				     struct rt_wake_q_head *wqh)
+	__must_hold(&lock->wait_lock)
+{
+	lockdep_assert_held(&lock->wait_lock);
+
+	debug_rt_mutex_unlock(lock);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		return false; /* done */
+	}
+
+	/*
+	 * mark_wakeup_next_waiter() deboosts and retains preemption
+	 * disabled when dropping the wait_lock, to avoid inversion prior
+	 * to the wakeup.  preempt_disable() therein pairs with the
+	 * preempt_enable() in rt_mutex_postunlock().
+	 */
+	mark_wakeup_next_waiter(wqh, lock);
+
+	return true; /* call postunlock() */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex_base *lock)
+{
+	DEFINE_RT_WAKE_Q(wqh);
+	unsigned long flags;
+	bool postunlock;
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	postunlock = __rt_mutex_futex_unlock(lock, &wqh);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+	if (postunlock)
+		rt_mutex_postunlock(&wqh);
+}
+
+/**
+ * __rt_mutex_init - initialize the rt_mutex
+ *
+ * @lock:	The rt_mutex to be initialized
+ * @name:	The lock name used for debugging
+ * @key:	The lock class key used for debugging
+ *
+ * Initialize the rt_mutex to unlocked state.
+ *
+ * Initializing of a locked rt_mutex is not allowed
+ */
+void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name,
+			     struct lock_class_key *key)
+{
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	__rt_mutex_base_init(&lock->rtmutex);
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
+}
+EXPORT_SYMBOL_GPL(__rt_mutex_init);
+
+/**
+ * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
+ *				proxy owner
+ *
+ * @lock:	the rt_mutex to be locked
+ * @proxy_owner:the task to set as owner
+ *
+ * No locking. Caller has to do serializing itself
+ *
+ * Special API call for PI-futex support. This initializes the rtmutex and
+ * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
+ * possible at this point because the pi_state which contains the rtmutex
+ * is not yet visible to other tasks.
+ */
+void __sched rt_mutex_init_proxy_locked(struct rt_mutex_base *lock,
+					struct task_struct *proxy_owner)
+{
+	static struct lock_class_key pi_futex_key;
+
+	__rt_mutex_base_init(lock);
+	/*
+	 * On PREEMPT_RT the futex hashbucket spinlock becomes 'sleeping'
+	 * and rtmutex based. That causes a lockdep false positive, because
+	 * some of the futex functions invoke spin_unlock(&hb->lock) with
+	 * the wait_lock of the rtmutex associated to the pi_futex held.
+	 * spin_unlock() in turn takes wait_lock of the rtmutex on which
+	 * the spinlock is based, which makes lockdep notice a lock
+	 * recursion. Give the futex/rtmutex wait_lock a separate key.
+	 */
+	lockdep_set_class(&lock->wait_lock, &pi_futex_key);
+	rt_mutex_set_owner(lock, proxy_owner);
+}
+
+/**
+ * rt_mutex_proxy_unlock - release a lock on behalf of owner
+ *
+ * @lock:	the rt_mutex to be locked
+ *
+ * No locking. Caller has to do serializing itself
+ *
+ * Special API call for PI-futex support. This just cleans up the rtmutex
+ * (debugging) state. Concurrent operations on this rt_mutex are not
+ * possible because it belongs to the pi_state which is about to be freed
+ * and it is not longer visible to other tasks.
+ */
+void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
+{
+	debug_rt_mutex_proxy_unlock(lock);
+	rt_mutex_clear_owner(lock);
+}
+
+/**
+ * __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
+ * @wake_q:		the wake_q to wake tasks after we release the wait_lock
+ *
+ * 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 __sched __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
+					struct rt_mutex_waiter *waiter,
+					struct task_struct *task,
+					struct wake_q_head *wake_q)
+	__must_hold(&lock->wait_lock)
+{
+	int ret;
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	if (try_to_take_rt_mutex(lock, task, NULL))
+		return 1;
+
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, NULL,
+				      RT_MUTEX_FULL_CHAINWALK, wake_q);
+
+	if (ret && !rt_mutex_owner(lock)) {
+		/*
+		 * Reset the return value. We might have
+		 * returned with -EDEADLK and the owner
+		 * released the lock while we were walking the
+		 * pi chain.  Let the waiter sort it out.
+		 */
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * 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: 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 PI-futex support.
+ */
+int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
+				      struct rt_mutex_waiter *waiter,
+				      struct task_struct *task)
+{
+	int ret;
+	DEFINE_WAKE_Q(wake_q);
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	ret = __rt_mutex_start_proxy_lock(lock, waiter, task, &wake_q);
+	if (unlikely(ret < 0))
+		remove_waiter(lock, waiter);
+	preempt_disable();
+	raw_spin_unlock_irq(&lock->wait_lock);
+	wake_up_q(&wake_q);
+	preempt_enable();
+
+	return ret;
+}
+
+/**
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @to:			the timeout, null if none. hrtimer should already have
+ *			been started.
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * Wait for the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
+ *
+ * Returns:
+ *  0 - success
+ * <0 - error, one of -EINTR, -ETIMEDOUT
+ *
+ * Special API call for PI-futex support
+ */
+int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
+				     struct hrtimer_sleeper *to,
+				     struct rt_mutex_waiter *waiter)
+{
+	int ret;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	/* sleep on the mutex */
+	set_current_state(TASK_INTERRUPTIBLE);
+	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL);
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock, true);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * 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
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ *  true  - did the cleanup, we done.
+ *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ *          caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock,
+					 struct rt_mutex_waiter *waiter)
+{
+	bool cleanup = false;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	/*
+	 * Do an unconditional try-lock, this deals with the lock stealing
+	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
+	 * sets a NULL owner.
+	 *
+	 * We're not interested in the return value, because the subsequent
+	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
+	 * we will own the lock and it will have removed the waiter. If we
+	 * failed the trylock, we're still not owner and we need to remove
+	 * ourselves.
+	 */
+	try_to_take_rt_mutex(lock, current, waiter);
+	/*
+	 * Unless we're the owner; we're still enqueued on the wait_list.
+	 * So check if we became owner, if not, take us off the wait_list.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		remove_waiter(lock, waiter);
+		cleanup = true;
+	}
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock, false);
+
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return cleanup;
+}
+
+/*
+ * Recheck the pi chain, in case we got a priority setting
+ *
+ * Called from sched_setscheduler
+ */
+void __sched rt_mutex_adjust_pi(struct task_struct *task)
+{
+	struct rt_mutex_waiter *waiter;
+	struct rt_mutex_base *next_lock;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+	waiter = task->pi_blocked_on;
+	if (!waiter || rt_waiter_node_equal(&waiter->tree, task_to_waiter_node(task))) {
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		return;
+	}
+	next_lock = waiter->lock;
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+	/* gets dropped in rt_mutex_adjust_prio_chain()! */
+	get_task_struct(task);
+
+	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
+				   next_lock, NULL, task);
+}
+
+/*
+ * Performs the wakeup of the top-waiter and re-enables preemption.
+ */
+void __sched rt_mutex_postunlock(struct rt_wake_q_head *wqh)
+{
+	rt_mutex_wake_up_q(wqh);
+}
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+void rt_mutex_debug_task_free(struct task_struct *task)
+{
+	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters.rb_root));
+	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
+}
+#endif
+
+#ifdef CONFIG_PREEMPT_RT
+/* Mutexes */
+static void __mutex_rt_init_generic(struct mutex *mutex)
+{
+	rt_mutex_base_init(&mutex->rtmutex);
+	debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
+}
+
+static __always_inline int __mutex_lock_common(struct mutex *lock,
+					       unsigned int state,
+					       unsigned int subclass,
+					       struct lockdep_map *nest_lock,
+					       unsigned long ip)
+	__acquires(lock) __no_context_analysis
+{
+	int ret;
+
+	might_sleep();
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
+	ret = __rt_mutex_lock(&lock->rtmutex, state);
+	if (ret)
+		mutex_release(&lock->dep_map, ip);
+	else
+		lock_acquired(&lock->dep_map, ip);
+	return ret;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void mutex_rt_init_lockdep(struct mutex *mutex, const char *name, struct lock_class_key *key)
+{
+	__mutex_rt_init_generic(mutex);
+	lockdep_init_map_wait(&mutex->dep_map, name, key, 0, LD_WAIT_SLEEP);
+}
+EXPORT_SYMBOL(mutex_rt_init_lockdep);
+
+void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass)
+{
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_nested);
+
+void __sched _mutex_lock_nest_lock(struct mutex *lock,
+				   struct lockdep_map *nest_lock)
+{
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest_lock, _RET_IP_);
+}
+EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
+
+int __sched mutex_lock_interruptible_nested(struct mutex *lock,
+					    unsigned int subclass)
+{
+	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
+
+int __sched _mutex_lock_killable(struct mutex *lock, unsigned int subclass,
+				 struct lockdep_map *nest_lock)
+{
+	return __mutex_lock_common(lock, TASK_KILLABLE, subclass, nest_lock, _RET_IP_);
+}
+EXPORT_SYMBOL_GPL(_mutex_lock_killable);
+
+void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
+{
+	int token;
+
+	might_sleep();
+
+	token = io_schedule_prepare();
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io_nested);
+
+int __sched _mutex_trylock_nest_lock(struct mutex *lock,
+				     struct lockdep_map *nest_lock)
+{
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
+		return 0;
+
+	ret = __rt_mutex_trylock(&lock->rtmutex);
+	if (ret)
+		mutex_acquire_nest(&lock->dep_map, 0, 1, nest_lock, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(_mutex_trylock_nest_lock);
+#else /* CONFIG_DEBUG_LOCK_ALLOC */
+
+void mutex_rt_init_generic(struct mutex *mutex)
+{
+	__mutex_rt_init_generic(mutex);
+}
+EXPORT_SYMBOL(mutex_rt_init_generic);
+
+void __sched mutex_lock(struct mutex *lock)
+{
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
+}
+EXPORT_SYMBOL(mutex_lock);
+
+int __sched mutex_lock_interruptible(struct mutex *lock)
+{
+	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
+}
+EXPORT_SYMBOL(mutex_lock_interruptible);
+
+int __sched mutex_lock_killable(struct mutex *lock)
+{
+	return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
+}
+EXPORT_SYMBOL(mutex_lock_killable);
+
+void __sched mutex_lock_io(struct mutex *lock)
+{
+	int token = io_schedule_prepare();
+
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL(mutex_lock_io);
+
+int __sched mutex_trylock(struct mutex *lock)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
+		return 0;
+
+	return __rt_mutex_trylock(&lock->rtmutex);
+}
+EXPORT_SYMBOL(mutex_trylock);
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
+
+void __sched mutex_unlock(struct mutex *lock)
+	__releases(lock) __no_context_analysis
+{
+	mutex_release(&lock->dep_map, _RET_IP_);
+	__rt_mutex_unlock(&lock->rtmutex);
+}
+EXPORT_SYMBOL(mutex_unlock);
+
+#endif /* CONFIG_PREEMPT_RT */

linux-7.2.3/kernel/locking/rtmutex_common.h

@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RT Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains the private data structure and API definitions.
+ */
+
+#ifndef __KERNEL_RTMUTEX_COMMON_H
+#define __KERNEL_RTMUTEX_COMMON_H
+
+#include <linux/debug_locks.h>
+#include <linux/rtmutex.h>
+#include <linux/sched/wake_q.h>
+
+
+/*
+ * This is a helper for the struct rt_mutex_waiter below. A waiter goes in two
+ * separate trees and they need their own copy of the sort keys because of
+ * different locking requirements.
+ *
+ * @entry:		rbtree node to enqueue into the waiters tree
+ * @prio:		Priority of the waiter
+ * @deadline:		Deadline of the waiter if applicable
+ *
+ * See rt_waiter_node_less() and waiter_*_prio().
+ */
+struct rt_waiter_node {
+	struct rb_node	entry;
+	int		prio;
+	u64		deadline;
+};
+
+/*
+ * This is the control structure for tasks blocked on a rt_mutex,
+ * which is allocated on the kernel stack on of the blocked task.
+ *
+ * @tree:		node to enqueue into the mutex waiters tree
+ * @pi_tree:		node to enqueue into the mutex owner waiters tree
+ * @task:		task reference to the blocked task
+ * @lock:		Pointer to the rt_mutex on which the waiter blocks
+ * @wake_state:		Wakeup state to use (TASK_NORMAL or TASK_RTLOCK_WAIT)
+ * @ww_ctx:		WW context pointer
+ *
+ * @tree is ordered by @lock->wait_lock
+ * @pi_tree is ordered by rt_mutex_owner(@lock)->pi_lock
+ */
+struct rt_mutex_waiter {
+	struct rt_waiter_node	tree;
+	struct rt_waiter_node	pi_tree;
+	struct task_struct	*task;
+	struct rt_mutex_base	*lock;
+	unsigned int		wake_state;
+	struct ww_acquire_ctx	*ww_ctx;
+};
+
+/**
+ * struct rt_wake_q_head - Wrapper around regular wake_q_head to support
+ *			   "sleeping" spinlocks on RT
+ * @head:		The regular wake_q_head for sleeping lock variants
+ * @rtlock_task:	Task pointer for RT lock (spin/rwlock) wakeups
+ */
+struct rt_wake_q_head {
+	struct wake_q_head	head;
+	struct task_struct	*rtlock_task;
+};
+
+#define DEFINE_RT_WAKE_Q(name)						\
+	struct rt_wake_q_head name = {					\
+		.head		= WAKE_Q_HEAD_INITIALIZER(name.head),	\
+		.rtlock_task	= NULL,					\
+	}
+
+/*
+ * PI-futex support (proxy locking functions, etc.):
+ */
+extern void rt_mutex_init_proxy_locked(struct rt_mutex_base *lock,
+				       struct task_struct *proxy_owner)
+	__must_hold(&lock->wait_lock);
+
+extern void rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
+	__must_hold(&lock->wait_lock);
+
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task,
+				     struct wake_q_head *)
+	__must_hold(&lock->wait_lock);
+
+extern int rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock,
+				 struct rt_mutex_waiter *waiter);
+
+extern int rt_mutex_futex_trylock(struct rt_mutex_base *lock);
+extern int __rt_mutex_futex_trylock(struct rt_mutex_base *lock)
+	__must_hold(&lock->wait_lock);
+
+extern void rt_mutex_futex_unlock(struct rt_mutex_base *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex_base *lock,
+				struct rt_wake_q_head *wqh);
+
+extern void rt_mutex_postunlock(struct rt_wake_q_head *wqh);
+
+/*
+ * Must be guarded because this header is included from rcu/tree_plugin.h
+ * unconditionally.
+ */
+#ifdef CONFIG_RT_MUTEXES
+static inline int rt_mutex_has_waiters(struct rt_mutex_base *lock)
+	__must_hold(&lock->wait_lock)
+{
+	return !RB_EMPTY_ROOT(&lock->waiters.rb_root);
+}
+
+/*
+ * Lockless speculative check whether @waiter is still the top waiter on
+ * @lock. This is solely comparing pointers and not derefencing the
+ * leftmost entry which might be about to vanish.
+ */
+static inline bool rt_mutex_waiter_is_top_waiter(struct rt_mutex_base *lock,
+						 struct rt_mutex_waiter *waiter)
+	__must_hold(&lock->wait_lock)
+{
+	struct rb_node *leftmost = rb_first_cached(&lock->waiters);
+
+	return rb_entry(leftmost, struct rt_mutex_waiter, tree.entry) == waiter;
+}
+
+static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *lock)
+	__must_hold(&lock->wait_lock)
+{
+	struct rb_node *leftmost = rb_first_cached(&lock->waiters);
+	struct rt_mutex_waiter *w = NULL;
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	if (leftmost) {
+		w = rb_entry(leftmost, struct rt_mutex_waiter, tree.entry);
+		BUG_ON(w->lock != lock);
+	}
+	return w;
+}
+
+static inline int task_has_pi_waiters(struct task_struct *p)
+{
+	return !RB_EMPTY_ROOT(&p->pi_waiters.rb_root);
+}
+
+static inline struct rt_mutex_waiter *task_top_pi_waiter(struct task_struct *p)
+{
+	lockdep_assert_held(&p->pi_lock);
+
+	return rb_entry(p->pi_waiters.rb_leftmost, struct rt_mutex_waiter,
+			pi_tree.entry);
+}
+
+/*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK:	Stops the lock chain walk when there are
+ *				no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK:	Invoke deadlock detection with a full
+ *				walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+	RT_MUTEX_MIN_CHAINWALK,
+	RT_MUTEX_FULL_CHAINWALK,
+};
+
+static inline void __rt_mutex_base_init(struct rt_mutex_base *lock)
+{
+	scoped_guard (raw_spinlock_init, &lock->wait_lock) {
+		lock->waiters = RB_ROOT_CACHED;
+		lock->owner = NULL;
+	}
+}
+
+/* Debug functions */
+static inline void debug_rt_mutex_unlock(struct rt_mutex_base *lock)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES))
+		DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current);
+}
+
+static inline void debug_rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES))
+		DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock));
+}
+
+static inline void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES))
+		memset(waiter, 0x11, sizeof(*waiter));
+}
+
+static inline void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES))
+		memset(waiter, 0x22, sizeof(*waiter));
+}
+
+static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	RB_CLEAR_NODE(&waiter->pi_tree.entry);
+	RB_CLEAR_NODE(&waiter->tree.entry);
+	waiter->wake_state = TASK_NORMAL;
+	waiter->task = NULL;
+}
+
+static inline void rt_mutex_init_rtlock_waiter(struct rt_mutex_waiter *waiter)
+{
+	rt_mutex_init_waiter(waiter);
+	waiter->wake_state = TASK_RTLOCK_WAIT;
+}
+
+#else /* CONFIG_RT_MUTEXES */
+/* Used in rcu/tree_plugin.h */
+static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock)
+{
+	return NULL;
+}
+#endif  /* !CONFIG_RT_MUTEXES */
+
+#endif

linux-7.2.3/kernel/locking/rwbase_rt.c

@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * RT-specific reader/writer semaphores and reader/writer locks
+ *
+ * down_write/write_lock()
+ *  1) Lock rtmutex
+ *  2) Remove the reader BIAS to force readers into the slow path
+ *  3) Wait until all readers have left the critical section
+ *  4) Mark it write locked
+ *
+ * up_write/write_unlock()
+ *  1) Remove the write locked marker
+ *  2) Set the reader BIAS, so readers can use the fast path again
+ *  3) Unlock rtmutex, to release blocked readers
+ *
+ * down_read/read_lock()
+ *  1) Try fast path acquisition (reader BIAS is set)
+ *  2) Take tmutex::wait_lock, which protects the writelocked flag
+ *  3) If !writelocked, acquire it for read
+ *  4) If writelocked, block on tmutex
+ *  5) unlock rtmutex, goto 1)
+ *
+ * up_read/read_unlock()
+ *  1) Try fast path release (reader count != 1)
+ *  2) Wake the writer waiting in down_write()/write_lock() #3
+ *
+ * down_read/read_lock()#3 has the consequence, that rw semaphores and rw
+ * locks on RT are not writer fair, but writers, which should be avoided in
+ * RT tasks (think mmap_sem), are subject to the rtmutex priority/DL
+ * inheritance mechanism.
+ *
+ * It's possible to make the rw primitives writer fair by keeping a list of
+ * active readers. A blocked writer would force all newly incoming readers
+ * to block on the rtmutex, but the rtmutex would have to be proxy locked
+ * for one reader after the other. We can't use multi-reader inheritance
+ * because there is no way to support that with SCHED_DEADLINE.
+ * Implementing the one by one reader boosting/handover mechanism is a
+ * major surgery for a very dubious value.
+ *
+ * The risk of writer starvation is there, but the pathological use cases
+ * which trigger it are not necessarily the typical RT workloads.
+ *
+ * Fast-path orderings:
+ * The lock/unlock of readers can run in fast paths: lock and unlock are only
+ * atomic ops, and there is no inner lock to provide ACQUIRE and RELEASE
+ * semantics of rwbase_rt. Atomic ops should thus provide _acquire()
+ * and _release() (or stronger).
+ *
+ * Common code shared between RT rw_semaphore and rwlock
+ */
+
+static __always_inline int rwbase_read_trylock(struct rwbase_rt *rwb)
+{
+	int r;
+
+	/*
+	 * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is
+	 * set.
+	 */
+	for (r = atomic_read(&rwb->readers); r < 0;) {
+		if (likely(atomic_try_cmpxchg_acquire(&rwb->readers, &r, r + 1)))
+			return 1;
+	}
+	return 0;
+}
+
+static int __sched __rwbase_read_lock(struct rwbase_rt *rwb,
+				      unsigned int state)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+	DEFINE_WAKE_Q(wake_q);
+	int ret;
+
+	rwbase_pre_schedule();
+	raw_spin_lock_irq(&rtm->wait_lock);
+
+	/*
+	 * Call into the slow lock path with the rtmutex->wait_lock
+	 * held, so this can't result in the following race:
+	 *
+	 * Reader1		Reader2		Writer
+	 *			down_read()
+	 *					down_write()
+	 *					rtmutex_lock(m)
+	 *					wait()
+	 * down_read()
+	 * unlock(m->wait_lock)
+	 *			up_read()
+	 *			wake(Writer)
+	 *					lock(m->wait_lock)
+	 *					sem->writelocked=true
+	 *					unlock(m->wait_lock)
+	 *
+	 *					up_write()
+	 *					sem->writelocked=false
+	 *					rtmutex_unlock(m)
+	 *			down_read()
+	 *					down_write()
+	 *					rtmutex_lock(m)
+	 *					wait()
+	 * rtmutex_lock(m)
+	 *
+	 * That would put Reader1 behind the writer waiting on
+	 * Reader2 to call up_read(), which might be unbound.
+	 */
+
+	trace_contention_begin(rwb, LCB_F_RT | LCB_F_READ);
+
+	/*
+	 * For rwlocks this returns 0 unconditionally, so the below
+	 * !ret conditionals are optimized out.
+	 */
+	ret = rwbase_rtmutex_slowlock_locked(rtm, state, &wake_q);
+
+	/*
+	 * On success the rtmutex is held, so there can't be a writer
+	 * active. Increment the reader count and immediately drop the
+	 * rtmutex again.
+	 *
+	 * rtmutex->wait_lock has to be unlocked in any case of course.
+	 */
+	if (!ret)
+		atomic_inc(&rwb->readers);
+
+	preempt_disable();
+	raw_spin_unlock_irq(&rtm->wait_lock);
+	wake_up_q(&wake_q);
+	preempt_enable();
+
+	if (!ret)
+		rwbase_rtmutex_unlock(rtm);
+
+	trace_contention_end(rwb, ret);
+	rwbase_post_schedule();
+	return ret;
+}
+
+static __always_inline int rwbase_read_lock(struct rwbase_rt *rwb,
+					    unsigned int state)
+{
+	lockdep_assert(!current->pi_blocked_on);
+
+	if (rwbase_read_trylock(rwb))
+		return 0;
+
+	return __rwbase_read_lock(rwb, state);
+}
+
+static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb,
+					 unsigned int state)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+	struct task_struct *owner;
+	DEFINE_RT_WAKE_Q(wqh);
+
+	raw_spin_lock_irq(&rtm->wait_lock);
+	/*
+	 * Wake the writer, i.e. the rtmutex owner. It might release the
+	 * rtmutex concurrently in the fast path (due to a signal), but to
+	 * clean up rwb->readers it needs to acquire rtm->wait_lock. The
+	 * worst case which can happen is a spurious wakeup.
+	 */
+	owner = rt_mutex_owner(rtm);
+	if (owner)
+		rt_mutex_wake_q_add_task(&wqh, owner, state);
+
+	/* Pairs with the preempt_enable in rt_mutex_wake_up_q() */
+	preempt_disable();
+	raw_spin_unlock_irq(&rtm->wait_lock);
+	rt_mutex_wake_up_q(&wqh);
+}
+
+static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb,
+					       unsigned int state)
+{
+	if (trace_contended_release_enabled() && rt_mutex_owner(&rwb->rtmutex))
+		trace_call__contended_release(rwb);
+	/*
+	 * rwb->readers can only hit 0 when a writer is waiting for the
+	 * active readers to leave the critical section.
+	 *
+	 * dec_and_test() is fully ordered, provides RELEASE.
+	 */
+	if (unlikely(atomic_dec_and_test(&rwb->readers)))
+		__rwbase_read_unlock(rwb, state);
+}
+
+static inline void __rwbase_write_unlock(struct rwbase_rt *rwb, int bias,
+					 unsigned long flags)
+	__releases(&rwb->rtmutex.wait_lock)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+
+	/*
+	 * _release() is needed in case that reader is in fast path, pairing
+	 * with atomic_try_cmpxchg_acquire() in rwbase_read_trylock().
+	 */
+	(void)atomic_add_return_release(READER_BIAS - bias, &rwb->readers);
+	raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+	rwbase_rtmutex_unlock(rtm);
+}
+
+static inline void rwbase_write_unlock(struct rwbase_rt *rwb)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+	if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm))
+		trace_call__contended_release(rwb);
+	__rwbase_write_unlock(rwb, WRITER_BIAS, flags);
+}
+
+static inline void rwbase_write_downgrade(struct rwbase_rt *rwb)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+	if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm))
+		trace_call__contended_release(rwb);
+	/* Release it and account current as reader */
+	__rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags);
+}
+
+static inline bool __rwbase_write_trylock(struct rwbase_rt *rwb)
+{
+	/* Can do without CAS because we're serialized by wait_lock. */
+	lockdep_assert_held(&rwb->rtmutex.wait_lock);
+
+	/*
+	 * _acquire is needed in case the reader is in the fast path, pairing
+	 * with rwbase_read_unlock(), provides ACQUIRE.
+	 */
+	if (!atomic_read_acquire(&rwb->readers)) {
+		atomic_set(&rwb->readers, WRITER_BIAS);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
+				     unsigned int state)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+	unsigned long flags;
+
+	/* Take the rtmutex as a first step */
+	if (rwbase_rtmutex_lock_state(rtm, state))
+		return -EINTR;
+
+	/* Force readers into slow path */
+	atomic_sub(READER_BIAS, &rwb->readers);
+
+	rwbase_pre_schedule();
+
+	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+	if (__rwbase_write_trylock(rwb))
+		goto out_unlock;
+
+	rwbase_set_and_save_current_state(state);
+	trace_contention_begin(rwb, LCB_F_RT | LCB_F_WRITE);
+	for (;;) {
+		/* Optimized out for rwlocks */
+		if (rwbase_signal_pending_state(state, current)) {
+			rwbase_restore_current_state();
+			__rwbase_write_unlock(rwb, 0, flags);
+			rwbase_post_schedule();
+			trace_contention_end(rwb, -EINTR);
+			return -EINTR;
+		}
+
+		if (__rwbase_write_trylock(rwb))
+			break;
+
+		raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+		rwbase_schedule();
+		raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+
+		set_current_state(state);
+	}
+	rwbase_restore_current_state();
+	trace_contention_end(rwb, 0);
+
+out_unlock:
+	raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+	rwbase_post_schedule();
+	return 0;
+}
+
+static inline int rwbase_write_trylock(struct rwbase_rt *rwb)
+{
+	struct rt_mutex_base *rtm = &rwb->rtmutex;
+	unsigned long flags;
+
+	if (!rwbase_rtmutex_trylock(rtm))
+		return 0;
+
+	atomic_sub(READER_BIAS, &rwb->readers);
+
+	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+	if (__rwbase_write_trylock(rwb)) {
+		raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+		return 1;
+	}
+	__rwbase_write_unlock(rwb, 0, flags);
+	return 0;
+}

linux-7.2.3/kernel/locking/semaphore.c

@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2008 Intel Corporation
+ * Author: Matthew Wilcox <willy@linux.intel.com>
+ *
+ * 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
+ * rules which allow code to be debugged more easily.
+ */
+
+/*
+ * Some notes on the implementation:
+ *
+ * The spinlock controls access to the other members of the semaphore.
+ * down_trylock() and up() can be called from interrupt context, so we
+ * have to disable interrupts when taking the lock.  It turns out various
+ * parts of the kernel expect to be able to use down() on a semaphore in
+ * interrupt context when they know it will succeed, so we have to use
+ * irqsave variants for down(), down_interruptible() and down_killable()
+ * too.
+ *
+ * The ->count variable represents how many more tasks can acquire this
+ * semaphore.  If it's zero, there may be waiters.
+ */
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
+#include <linux/semaphore.h>
+#include <linux/spinlock.h>
+#include <linux/ftrace.h>
+#include <trace/events/lock.h>
+#include <linux/hung_task.h>
+
+static noinline void __down(struct semaphore *sem);
+static noinline int __down_interruptible(struct semaphore *sem);
+static noinline int __down_killable(struct semaphore *sem);
+static noinline int __down_timeout(struct semaphore *sem, long timeout);
+static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+static inline void hung_task_sem_set_holder(struct semaphore *sem)
+{
+	WRITE_ONCE((sem)->last_holder, (unsigned long)current);
+}
+
+static inline void hung_task_sem_clear_if_holder(struct semaphore *sem)
+{
+	if (READ_ONCE((sem)->last_holder) == (unsigned long)current)
+		WRITE_ONCE((sem)->last_holder, 0UL);
+}
+
+unsigned long sem_last_holder(struct semaphore *sem)
+{
+	return READ_ONCE(sem->last_holder);
+}
+#else
+static inline void hung_task_sem_set_holder(struct semaphore *sem)
+{
+}
+static inline void hung_task_sem_clear_if_holder(struct semaphore *sem)
+{
+}
+unsigned long sem_last_holder(struct semaphore *sem)
+{
+	return 0UL;
+}
+#endif
+
+static inline void __sem_acquire(struct semaphore *sem)
+{
+	sem->count--;
+	hung_task_sem_set_holder(sem);
+}
+
+/**
+ * down - acquire the semaphore
+ * @sem: the semaphore to be acquired
+ *
+ * Acquires the semaphore.  If no more tasks are allowed to acquire the
+ * semaphore, calling this function will put the task to sleep until the
+ * semaphore is released.
+ *
+ * Use of this function is deprecated, please use down_interruptible() or
+ * down_killable() instead.
+ */
+void __sched down(struct semaphore *sem)
+{
+	unsigned long flags;
+
+	might_sleep();
+	raw_spin_lock_irqsave(&sem->lock, flags);
+	if (likely(sem->count > 0))
+		__sem_acquire(sem);
+	else
+		__down(sem);
+	raw_spin_unlock_irqrestore(&sem->lock, flags);
+}
+EXPORT_SYMBOL(down);
+
+/**
+ * down_interruptible - acquire the semaphore unless interrupted
+ * @sem: the semaphore to be acquired
+ *
+ * Attempts to acquire the semaphore.  If no more tasks are allowed to
+ * acquire the semaphore, calling this function will put the task to sleep.
+ * If the sleep is interrupted by a signal, this function will return -EINTR.
+ * If the semaphore is successfully acquired, this function returns 0.
+ */
+int __sched down_interruptible(struct semaphore *sem)
+{
+	unsigned long flags;
+	int result = 0;
+
+	might_sleep();
+	raw_spin_lock_irqsave(&sem->lock, flags);
+	if (likely(sem->count > 0))
+		__sem_acquire(sem);
+	else
+		result = __down_interruptible(sem);
+	raw_spin_unlock_irqrestore(&sem->lock, flags);
+
+	return result;
+}
+EXPORT_SYMBOL(down_interruptible);
+
+/**
+ * down_killable - acquire the semaphore unless killed
+ * @sem: the semaphore to be acquired
+ *
+ * Attempts to acquire the semaphore.  If no more tasks are allowed to
+ * acquire the semaphore, calling this function will put the task to sleep.
+ * If the sleep is interrupted by a fatal signal, this function will return
+ * -EINTR.  If the semaphore is successfully acquired, this function returns
+ * 0.
+ */
+int __sched down_killable(struct semaphore *sem)
+{
+	unsigned long flags;
+	int result = 0;
+
+	might_sleep();
+	raw_spin_lock_irqsave(&sem->lock, flags);
+	if (likely(sem->count > 0))
+		__sem_acquire(sem);
+	else
+		result = __down_killable(sem);
+	raw_spin_unlock_irqrestore(&sem->lock, flags);
+
+	return result;
+}
+EXPORT_SYMBOL(down_killable);
+
+/**
+ * down_trylock - try to acquire the semaphore, without waiting
+ * @sem: the semaphore to be acquired
+ *
+ * Try to acquire the semaphore atomically.  Returns 0 if the semaphore has
+ * been acquired successfully or 1 if it cannot be acquired.
+ *
+ * NOTE: This return value is inverted from both spin_trylock and
+ * mutex_trylock!  Be careful about this when converting code.
+ *
+ * Unlike mutex_trylock, this function can be used from interrupt context,
+ * and the semaphore can be released by any task or interrupt.
+ */
+int __sched down_trylock(struct semaphore *sem)
+{
+	unsigned long flags;
+	int count;
+
+	raw_spin_lock_irqsave(&sem->lock, flags);
+	count = sem->count - 1;
+	if (likely(count >= 0))
+		__sem_acquire(sem);
+	raw_spin_unlock_irqrestore(&sem->lock, flags);
+
+	return (count < 0);
+}
+EXPORT_SYMBOL(down_trylock);
+
+/**
+ * down_timeout - acquire the semaphore within a specified time
+ * @sem: the semaphore to be acquired
+ * @timeout: how long to wait before failing
+ *
+ * Attempts to acquire the semaphore.  If no more tasks are allowed to
+ * acquire the semaphore, calling this function will put the task to sleep.
+ * If the semaphore is not released within the specified number of jiffies,
+ * this function returns -ETIME.  It returns 0 if the semaphore was acquired.
+ */
+int __sched down_timeout(struct semaphore *sem, long timeout)
+{
+	unsigned long flags;
+	int result = 0;
+
+	might_sleep();
+	raw_spin_lock_irqsave(&sem->lock, flags);
+	if (likely(sem->count > 0))
+		__sem_acquire(sem);
+	else
+		result = __down_timeout(sem, timeout);
+	raw_spin_unlock_irqrestore(&sem->lock, flags);
+
+	return result;
+}
+EXPORT_SYMBOL(down_timeout);
+
+/**
+ * up - release the semaphore
+ * @sem: the semaphore to release
+ *
+ * Release the semaphore.  Unlike mutexes, up() may be called from any
+ * context and even by tasks which have never called down().
+ */
+void __sched up(struct semaphore *sem)
+{
+	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	raw_spin_lock_irqsave(&sem->lock, flags);
+
+	hung_task_sem_clear_if_holder(sem);
+
+	if (likely(!sem->first_waiter))
+		sem->count++;
+	else
+		__up(sem, &wake_q);
+
+	if (trace_contended_release_enabled() && !wake_q_empty(&wake_q))
+		trace_call__contended_release(sem);
+
+	raw_spin_unlock_irqrestore(&sem->lock, flags);
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
+}
+EXPORT_SYMBOL(up);
+
+/* Functions for the contended case */
+
+struct semaphore_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	bool up;
+};
+
+static inline
+void sem_del_waiter(struct semaphore *sem, struct semaphore_waiter *waiter)
+{
+	if (list_empty(&waiter->list)) {
+		sem->first_waiter = NULL;
+		return;
+	}
+
+	if (sem->first_waiter == waiter) {
+		sem->first_waiter = list_first_entry(&waiter->list,
+						     struct semaphore_waiter, list);
+	}
+	list_del(&waiter->list);
+}
+
+/*
+ * Because this function is inlined, the 'state' parameter will be
+ * constant, and thus optimised away by the compiler.  Likewise the
+ * 'timeout' parameter for the cases without timeouts.
+ */
+static inline int __sched ___down_common(struct semaphore *sem, long state,
+								long timeout)
+{
+	struct semaphore_waiter waiter, *first;
+
+	first = sem->first_waiter;
+	if (first) {
+		list_add_tail(&waiter.list, &first->list);
+	} else {
+		INIT_LIST_HEAD(&waiter.list);
+		sem->first_waiter = &waiter;
+	}
+	waiter.task = current;
+	waiter.up = false;
+
+	for (;;) {
+		if (signal_pending_state(state, current))
+			goto interrupted;
+		if (unlikely(timeout <= 0))
+			goto timed_out;
+		__set_current_state(state);
+		raw_spin_unlock_irq(&sem->lock);
+		timeout = schedule_timeout(timeout);
+		raw_spin_lock_irq(&sem->lock);
+		if (waiter.up) {
+			hung_task_sem_set_holder(sem);
+			return 0;
+		}
+	}
+
+ timed_out:
+	sem_del_waiter(sem, &waiter);
+	return -ETIME;
+
+ interrupted:
+	sem_del_waiter(sem, &waiter);
+	return -EINTR;
+}
+
+static inline int __sched __down_common(struct semaphore *sem, long state,
+					long timeout)
+{
+	int ret;
+
+	hung_task_set_blocker(sem, BLOCKER_TYPE_SEM);
+
+	trace_contention_begin(sem, 0);
+	ret = ___down_common(sem, state, timeout);
+	trace_contention_end(sem, ret);
+
+	hung_task_clear_blocker();
+
+	return ret;
+}
+
+static noinline void __sched __down(struct semaphore *sem)
+{
+	__down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+
+static noinline int __sched __down_interruptible(struct semaphore *sem)
+{
+	return __down_common(sem, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+
+static noinline int __sched __down_killable(struct semaphore *sem)
+{
+	return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT);
+}
+
+static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
+{
+	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
+}
+
+static noinline void __sched __up(struct semaphore *sem,
+				  struct wake_q_head *wake_q)
+{
+	struct semaphore_waiter *waiter = sem->first_waiter;
+
+	sem_del_waiter(sem, waiter);
+	waiter->up = true;
+	wake_q_add(wake_q, waiter->task);
+}

linux-7.2.3/kernel/locking/spinlock.c

@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (2004) Linus Torvalds
+ *
+ * Author: Zwane Mwaikambo <zwane@fsmlabs.com>
+ *
+ * Copyright (2004, 2005) Ingo Molnar
+ *
+ * This file contains the spinlock/rwlock implementations for the
+ * SMP and the DEBUG_SPINLOCK cases. (UP-nondebug inlines them)
+ *
+ * Note that some architectures have special knowledge about the
+ * stack frames of these functions in their profile_pc. If you
+ * change anything significant here that could change the stack
+ * frame contact the architecture maintainers.
+ */
+
+#include <linux/linkage.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#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
+ * not re-enabled during lock-acquire (which the preempt-spin-ops do):
+ */
+#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
+/*
+ * The __lock_function inlines are taken from
+ * spinlock : include/linux/spinlock_api_smp.h
+ * rwlock   : include/linux/rwlock_api_smp.h
+ */
+#else
+
+/*
+ * Some architectures can relax in favour of the CPU owning the lock.
+ */
+#ifndef arch_read_relax
+# define arch_read_relax(l)	cpu_relax()
+#endif
+#ifndef arch_write_relax
+# define arch_write_relax(l)	cpu_relax()
+#endif
+#ifndef arch_spin_relax
+# define arch_spin_relax(l)	cpu_relax()
+#endif
+
+/*
+ * We build the __lock_function inlines here. They are too large for
+ * inlining all over the place, but here is only one user per function
+ * which embeds them into the calling _lock_function below.
+ *
+ * This could be a long-held lock. We both prepare to spin for a long
+ * time (making _this_ CPU preemptible if possible), and we also signal
+ * towards that other CPU that it should break the lock ASAP.
+ */
+#define BUILD_LOCK_OPS(op, locktype, lock_ctx_op)			\
+static void __lockfunc __raw_##op##_lock(locktype##_t *lock)		\
+	lock_ctx_op(lock)						\
+{									\
+	for (;;) {							\
+		preempt_disable();					\
+		if (likely(do_raw_##op##_trylock(lock)))		\
+			break;						\
+		preempt_enable();					\
+									\
+		arch_##op##_relax(&lock->raw_lock);			\
+	}								\
+}									\
+									\
+static unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
+	lock_ctx_op(lock)						\
+{									\
+	unsigned long flags;						\
+									\
+	for (;;) {							\
+		preempt_disable();					\
+		local_irq_save(flags);					\
+		if (likely(do_raw_##op##_trylock(lock)))		\
+			break;						\
+		local_irq_restore(flags);				\
+		preempt_enable();					\
+									\
+		arch_##op##_relax(&lock->raw_lock);			\
+	}								\
+									\
+	return flags;							\
+}									\
+									\
+static void __lockfunc __raw_##op##_lock_irq(locktype##_t *lock)	\
+	lock_ctx_op(lock)						\
+{									\
+	_raw_##op##_lock_irqsave(lock);					\
+}									\
+									\
+static void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock)		\
+	lock_ctx_op(lock)						\
+{									\
+	unsigned long flags;						\
+									\
+	/*							*/	\
+	/* Careful: we must exclude softirqs too, hence the	*/	\
+	/* irq-disabling. We use the generic preemption-aware	*/	\
+	/* function:						*/	\
+	/**/								\
+	flags = _raw_##op##_lock_irqsave(lock);				\
+	local_bh_disable();						\
+	local_irq_restore(flags);					\
+}									\
+
+/*
+ * Build preemption-friendly versions of the following
+ * lock-spinning functions:
+ *
+ *         __[spin|read|write]_lock()
+ *         __[spin|read|write]_lock_irq()
+ *         __[spin|read|write]_lock_irqsave()
+ *         __[spin|read|write]_lock_bh()
+ */
+BUILD_LOCK_OPS(spin, raw_spinlock, __acquires);
+
+#ifndef CONFIG_PREEMPT_RT
+BUILD_LOCK_OPS(read, rwlock, __acquires_shared);
+BUILD_LOCK_OPS(write, rwlock, __acquires);
+#endif
+
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK
+noinline int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock)
+{
+	return __raw_spin_trylock(lock);
+}
+EXPORT_SYMBOL(_raw_spin_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH
+noinline int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock)
+{
+	return __raw_spin_trylock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_spin_trylock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK
+noinline void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)
+{
+	__raw_spin_lock(lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
+noinline unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
+{
+	return __raw_spin_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
+noinline void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
+{
+	__raw_spin_lock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_LOCK_BH
+noinline void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
+{
+	__raw_spin_lock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_bh);
+#endif
+
+#ifdef CONFIG_UNINLINE_SPIN_UNLOCK
+noinline void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
+{
+	__raw_spin_unlock(lock);
+}
+EXPORT_SYMBOL(_raw_spin_unlock);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
+noinline void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
+{
+	__raw_spin_unlock_irqrestore(lock, flags);
+}
+EXPORT_SYMBOL(_raw_spin_unlock_irqrestore);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
+noinline void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
+{
+	__raw_spin_unlock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_spin_unlock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
+noinline void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
+{
+	__raw_spin_unlock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_spin_unlock_bh);
+#endif
+
+#ifndef CONFIG_PREEMPT_RT
+
+#ifndef CONFIG_INLINE_READ_TRYLOCK
+noinline int __lockfunc _raw_read_trylock(rwlock_t *lock)
+{
+	return __raw_read_trylock(lock);
+}
+EXPORT_SYMBOL(_raw_read_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK
+noinline void __lockfunc _raw_read_lock(rwlock_t *lock)
+{
+	__raw_read_lock(lock);
+}
+EXPORT_SYMBOL(_raw_read_lock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE
+noinline unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
+{
+	return __raw_read_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_raw_read_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_IRQ
+noinline void __lockfunc _raw_read_lock_irq(rwlock_t *lock)
+{
+	__raw_read_lock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_read_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_READ_LOCK_BH
+noinline void __lockfunc _raw_read_lock_bh(rwlock_t *lock)
+{
+	__raw_read_lock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_read_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_READ_UNLOCK
+noinline void __lockfunc _raw_read_unlock(rwlock_t *lock)
+{
+	__raw_read_unlock(lock);
+}
+EXPORT_SYMBOL(_raw_read_unlock);
+#endif
+
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE
+noinline void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+{
+	__raw_read_unlock_irqrestore(lock, flags);
+}
+EXPORT_SYMBOL(_raw_read_unlock_irqrestore);
+#endif
+
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ
+noinline void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)
+{
+	__raw_read_unlock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_read_unlock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_READ_UNLOCK_BH
+noinline void __lockfunc _raw_read_unlock_bh(rwlock_t *lock)
+{
+	__raw_read_unlock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_read_unlock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_TRYLOCK
+noinline int __lockfunc _raw_write_trylock(rwlock_t *lock)
+{
+	return __raw_write_trylock(lock);
+}
+EXPORT_SYMBOL(_raw_write_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK
+noinline void __lockfunc _raw_write_lock(rwlock_t *lock)
+{
+	__raw_write_lock(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock);
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
+#define __raw_write_lock_nested(lock, subclass)	__raw_write_lock(((void)(subclass), (lock)))
+#endif
+
+void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass)
+{
+	__raw_write_lock_nested(lock, subclass);
+}
+EXPORT_SYMBOL(_raw_write_lock_nested);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE
+noinline unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
+{
+	return __raw_write_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ
+noinline void __lockfunc _raw_write_lock_irq(rwlock_t *lock)
+{
+	__raw_write_lock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_BH
+noinline void __lockfunc _raw_write_lock_bh(rwlock_t *lock)
+{
+	__raw_write_lock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK
+noinline void __lockfunc _raw_write_unlock(rwlock_t *lock)
+{
+	__raw_write_unlock(lock);
+}
+EXPORT_SYMBOL(_raw_write_unlock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE
+noinline void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+{
+	__raw_write_unlock_irqrestore(lock, flags);
+}
+EXPORT_SYMBOL(_raw_write_unlock_irqrestore);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ
+noinline void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)
+{
+	__raw_write_unlock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_write_unlock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH
+noinline void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
+{
+	__raw_write_unlock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_write_unlock_bh);
+#endif
+
+#endif /* !CONFIG_PREEMPT_RT */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
+{
+	preempt_disable();
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_nested);
+
+unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock,
+						   int subclass)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+	return flags;
+}
+EXPORT_SYMBOL(_raw_spin_lock_irqsave_nested);
+
+void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock,
+				     struct lockdep_map *nest_lock)
+{
+	preempt_disable();
+	spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_nest_lock);
+
+#endif
+
+notrace int in_lock_functions(unsigned long addr)
+{
+	/* Linker adds these: start and end of __lockfunc functions */
+	extern char __lock_text_start[], __lock_text_end[];
+
+	return addr >= (unsigned long)__lock_text_start
+	&& addr < (unsigned long)__lock_text_end;
+}
+EXPORT_SYMBOL(in_lock_functions);
+
+#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_PREEMPT_RT)
+void notrace lockdep_assert_in_softirq_func(void)
+{
+	lockdep_assert_in_softirq();
+}
+EXPORT_SYMBOL(lockdep_assert_in_softirq_func);
+#endif

linux-7.2.3/kernel/locking/spinlock_debug.c

@@ -0,0 +1,236 @@
+/*
+ * Copyright 2005, Red Hat, Inc., Ingo Molnar
+ * Released under the General Public License (GPL).
+ *
+ * This file contains the spinlock/rwlock implementations for
+ * DEBUG_SPINLOCK.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/nmi.h>
+#include <linux/interrupt.h>
+#include <linux/debug_locks.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/pid.h>
+
+void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
+			  struct lock_class_key *key, short inner)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, inner);
+#endif
+	lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+	lock->magic = SPINLOCK_MAGIC;
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__raw_spin_lock_init);
+
+#ifndef CONFIG_PREEMPT_RT
+void __rwlock_init(rwlock_t *lock, const char *name,
+		   struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG);
+#endif
+	lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED;
+	lock->magic = RWLOCK_MAGIC;
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__rwlock_init);
+#endif
+
+static void spin_dump(raw_spinlock_t *lock, const char *msg)
+{
+	struct task_struct *owner = READ_ONCE(lock->owner);
+
+	if (owner == SPINLOCK_OWNER_INIT)
+		owner = NULL;
+	printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
+		msg, raw_smp_processor_id(),
+		current->comm, task_pid_nr(current));
+	printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
+			".owner_cpu: %d\n",
+		lock, READ_ONCE(lock->magic),
+		owner ? owner->comm : "<none>",
+		owner ? task_pid_nr(owner) : -1,
+		READ_ONCE(lock->owner_cpu));
+	dump_stack();
+}
+
+static void spin_bug(raw_spinlock_t *lock, const char *msg)
+{
+	if (!debug_locks_off())
+		return;
+
+	spin_dump(lock, msg);
+}
+
+#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
+
+static inline void
+debug_spin_lock_before(raw_spinlock_t *lock)
+{
+	SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion");
+	SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_spin_lock_after(raw_spinlock_t *lock)
+{
+	WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+	WRITE_ONCE(lock->owner, current);
+}
+
+static inline void debug_spin_unlock(raw_spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(!raw_spin_is_locked(lock), lock, "already unlocked");
+	SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
+	SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+	WRITE_ONCE(lock->owner_cpu, -1);
+}
+
+/*
+ * We are now relying on the NMI watchdog to detect lockup instead of doing
+ * the detection here with an unfair lock which can cause problem of its own.
+ */
+void do_raw_spin_lock(raw_spinlock_t *lock)
+{
+	debug_spin_lock_before(lock);
+	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
+	debug_spin_lock_after(lock);
+}
+
+int do_raw_spin_trylock(raw_spinlock_t *lock)
+{
+	int ret = arch_spin_trylock(&lock->raw_lock);
+
+	if (ret) {
+		mmiowb_spin_lock();
+		debug_spin_lock_after(lock);
+	}
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	SPIN_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void do_raw_spin_unlock(raw_spinlock_t *lock)
+{
+	mmiowb_spin_unlock();
+	debug_spin_unlock(lock);
+	arch_spin_unlock(&lock->raw_lock);
+}
+
+#ifndef CONFIG_PREEMPT_RT
+static void rwlock_bug(rwlock_t *lock, const char *msg)
+{
+	if (!debug_locks_off())
+		return;
+
+	printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n",
+		msg, raw_smp_processor_id(), current->comm,
+		task_pid_nr(current), lock);
+	dump_stack();
+}
+
+#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
+
+void do_raw_read_lock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	arch_read_lock(&lock->raw_lock);
+}
+
+int do_raw_read_trylock(rwlock_t *lock)
+{
+	int ret = arch_read_trylock(&lock->raw_lock);
+
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void do_raw_read_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	arch_read_unlock(&lock->raw_lock);
+}
+
+static inline void debug_write_lock_before(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion");
+	RWLOCK_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_write_lock_after(rwlock_t *lock)
+{
+	WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+	WRITE_ONCE(lock->owner, current);
+}
+
+static inline void debug_write_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
+	RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+	WRITE_ONCE(lock->owner_cpu, -1);
+}
+
+void do_raw_write_lock(rwlock_t *lock)
+{
+	debug_write_lock_before(lock);
+	arch_write_lock(&lock->raw_lock);
+	debug_write_lock_after(lock);
+}
+
+int do_raw_write_trylock(rwlock_t *lock)
+{
+	int ret = arch_write_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_write_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void do_raw_write_unlock(rwlock_t *lock)
+{
+	debug_write_unlock(lock);
+	arch_write_unlock(&lock->raw_lock);
+}
+
+#endif /* !CONFIG_PREEMPT_RT */

linux-7.2.3/kernel/locking/spinlock_rt.c

@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PREEMPT_RT substitution for spin/rw_locks
+ *
+ * spinlocks and rwlocks on RT are based on rtmutexes, with a few twists to
+ * resemble the non RT semantics:
+ *
+ * - Contrary to plain rtmutexes, spinlocks and rwlocks are state
+ *   preserving. The task state is saved before blocking on the underlying
+ *   rtmutex, and restored when the lock has been acquired. Regular wakeups
+ *   during that time are redirected to the saved state so no wake up is
+ *   missed.
+ *
+ * - Non RT spin/rwlocks disable preemption and eventually interrupts.
+ *   Disabling preemption has the side effect of disabling migration and
+ *   preventing RCU grace periods.
+ *
+ *   The RT substitutions explicitly disable migration and take
+ *   rcu_read_lock() across the lock held section.
+ */
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#define RT_MUTEX_BUILD_SPINLOCKS
+#include "rtmutex.c"
+
+/*
+ * __might_resched() skips the state check as rtlocks are state
+ * preserving. Take RCU nesting into account as spin/read/write_lock() can
+ * legitimately nest into an RCU read side critical section.
+ */
+#define RTLOCK_RESCHED_OFFSETS						\
+	(rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT)
+
+#define rtlock_might_resched()						\
+	__might_resched(__FILE__, __LINE__, RTLOCK_RESCHED_OFFSETS)
+
+static __always_inline void rtlock_lock(struct rt_mutex_base *rtm)
+{
+	lockdep_assert(!current->pi_blocked_on);
+
+	if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
+		rtlock_slowlock(rtm);
+}
+
+static __always_inline void __rt_spin_lock(spinlock_t *lock)
+{
+	rtlock_might_resched();
+	rtlock_lock(&lock->lock);
+	rcu_read_lock();
+	migrate_disable();
+}
+
+void __sched rt_spin_lock(spinlock_t *lock) __acquires(RCU)
+{
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	__rt_spin_lock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __sched rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	__rt_spin_lock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock_nested);
+
+void __sched rt_spin_lock_nest_lock(spinlock_t *lock,
+				    struct lockdep_map *nest_lock)
+{
+	spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+	__rt_spin_lock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock_nest_lock);
+#endif
+
+void __sched rt_spin_unlock(spinlock_t *lock) __releases(RCU)
+{
+	spin_release(&lock->dep_map, _RET_IP_);
+	migrate_enable();
+
+	if (unlikely(!rt_mutex_cmpxchg_release(&lock->lock, current, NULL)))
+		rt_mutex_slowunlock(&lock->lock);
+
+	/*
+	 * This must be last to prevent the following UAF:
+	 *
+	 * T1					T2
+	 * spin_lock(&p->lock);			rcu_read_lock();
+	 * invalidate(p);			p = rcu_dereference(ptr);
+	 * rcu_assign_pointer(ptr, NULL);	if (!p) return;
+	 * spin_unlock(&p->lock);		spin_lock(&p->lock);
+	 * kfree_rcu(p);			rcu_read_unlock();
+	 *					....
+	 *					spin_unlock(&p->lock)
+	 *					  rcu_read_unlock(); // Ends grace period
+	 * rcu_do_batch()
+	 *   kfree(p);
+	 *			    UAF ->	  rt_mutex_cmpxchg_release(&p->lock.lock...)
+	 */
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __sched rt_spin_lock_unlock(spinlock_t *lock)
+{
+	spin_lock(lock);
+	spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_lock_unlock);
+
+static __always_inline int __rt_spin_trylock(spinlock_t *lock)
+{
+	int ret = 1;
+
+	if (unlikely(!rt_mutex_cmpxchg_acquire(&lock->lock, NULL, current)))
+		ret = rt_mutex_slowtrylock(&lock->lock);
+
+	if (ret) {
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+		migrate_disable();
+	}
+	return ret;
+}
+
+int __sched rt_spin_trylock(spinlock_t *lock)
+{
+	return __rt_spin_trylock(lock);
+}
+EXPORT_SYMBOL(rt_spin_trylock);
+
+int __sched rt_spin_trylock_bh(spinlock_t *lock)
+{
+	int ret;
+
+	local_bh_disable();
+	ret = __rt_spin_trylock(lock);
+	if (!ret)
+		local_bh_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_bh);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __rt_spin_lock_init(spinlock_t *lock, const char *name,
+			 struct lock_class_key *key, bool percpu)
+{
+	u8 type = percpu ? LD_LOCK_PERCPU : LD_LOCK_NORMAL;
+
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map_type(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG,
+			      LD_WAIT_INV, type);
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+#endif
+
+/*
+ * RT-specific reader/writer locks
+ */
+#define rwbase_set_and_save_current_state(state)	\
+	current_save_and_set_rtlock_wait_state()
+
+#define rwbase_restore_current_state()			\
+	current_restore_rtlock_saved_state()
+
+static __always_inline int
+rwbase_rtmutex_lock_state(struct rt_mutex_base *rtm, unsigned int state)
+{
+	if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
+		rtlock_slowlock(rtm);
+	return 0;
+}
+
+static __always_inline int
+rwbase_rtmutex_slowlock_locked(struct rt_mutex_base *rtm, unsigned int state,
+			       struct wake_q_head *wake_q)
+{
+	rtlock_slowlock_locked(rtm, wake_q);
+	return 0;
+}
+
+static __always_inline void rwbase_rtmutex_unlock(struct rt_mutex_base *rtm)
+{
+	if (likely(rt_mutex_cmpxchg_acquire(rtm, current, NULL)))
+		return;
+
+	rt_mutex_slowunlock(rtm);
+}
+
+static __always_inline int  rwbase_rtmutex_trylock(struct rt_mutex_base *rtm)
+{
+	if (likely(rt_mutex_cmpxchg_acquire(rtm, NULL, current)))
+		return 1;
+
+	return rt_mutex_slowtrylock(rtm);
+}
+
+#define rwbase_signal_pending_state(state, current)	(0)
+
+#define rwbase_pre_schedule()
+
+#define rwbase_schedule()				\
+	schedule_rtlock()
+
+#define rwbase_post_schedule()
+
+#include "rwbase_rt.c"
+/*
+ * The common functions which get wrapped into the rwlock API.
+ */
+int __sched rt_read_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	ret = rwbase_read_trylock(&rwlock->rwbase);
+	if (ret) {
+		rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+		migrate_disable();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_read_trylock);
+
+int __sched rt_write_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	ret = rwbase_write_trylock(&rwlock->rwbase);
+	if (ret) {
+		rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+		migrate_disable();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock);
+
+void __sched rt_read_lock(rwlock_t *rwlock) __acquires(RCU)
+{
+	rtlock_might_resched();
+	rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
+	rwbase_read_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+	rcu_read_lock();
+	migrate_disable();
+}
+EXPORT_SYMBOL(rt_read_lock);
+
+void __sched rt_write_lock(rwlock_t *rwlock) __acquires(RCU)
+{
+	rtlock_might_resched();
+	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+	rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+	rcu_read_lock();
+	migrate_disable();
+}
+EXPORT_SYMBOL(rt_write_lock);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) __acquires(RCU)
+{
+	rtlock_might_resched();
+	rwlock_acquire(&rwlock->dep_map, subclass, 0, _RET_IP_);
+	rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+	rcu_read_lock();
+	migrate_disable();
+}
+EXPORT_SYMBOL(rt_write_lock_nested);
+#endif
+
+void __sched rt_read_unlock(rwlock_t *rwlock) __releases(RCU)
+{
+	rwlock_release(&rwlock->dep_map, _RET_IP_);
+	migrate_enable();
+	rwbase_read_unlock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+
+	/* This must be last. See comment in rt_spin_unlock() */
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(rt_read_unlock);
+
+void __sched rt_write_unlock(rwlock_t *rwlock) __releases(RCU)
+{
+	rwlock_release(&rwlock->dep_map, _RET_IP_);
+	migrate_enable();
+	rwbase_write_unlock(&rwlock->rwbase);
+
+	/* This must be last. See comment in rt_spin_unlock() */
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(rt_write_unlock);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __rt_rwlock_init(rwlock_t *rwlock, const char *name,
+		      struct lock_class_key *key)
+{
+	debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock));
+	lockdep_init_map_wait(&rwlock->dep_map, name, key, 0, LD_WAIT_CONFIG);
+}
+EXPORT_SYMBOL(__rt_rwlock_init);
+#endif

linux-7.2.3/kernel/locking/test-ww_mutex.c

@@ -0,0 +1,777 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module-based API test facility for ww_mutexes
+ */
+
+#include <linux/kernel.h>
+
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/prandom.h>
+#include <linux/slab.h>
+#include <linux/ww_mutex.h>
+
+static DEFINE_WD_CLASS(wd_class);
+static DEFINE_WW_CLASS(ww_class);
+struct workqueue_struct *wq;
+
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+#define ww_acquire_init_noinject(a, b) do { \
+		ww_acquire_init((a), (b)); \
+		(a)->deadlock_inject_countdown = ~0U; \
+	} while (0)
+#else
+#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b))
+#endif
+
+struct test_mutex {
+	struct work_struct work;
+	struct ww_mutex mutex;
+	struct completion ready, go, done;
+	unsigned int flags;
+};
+
+#define TEST_MTX_SPIN BIT(0)
+#define TEST_MTX_TRY BIT(1)
+#define TEST_MTX_CTX BIT(2)
+#define __TEST_MTX_LAST BIT(3)
+
+static void test_mutex_work(struct work_struct *work)
+{
+	struct test_mutex *mtx = container_of(work, typeof(*mtx), work);
+
+	complete(&mtx->ready);
+	wait_for_completion(&mtx->go);
+
+	if (mtx->flags & TEST_MTX_TRY) {
+		while (!ww_mutex_trylock(&mtx->mutex, NULL))
+			cond_resched();
+	} else {
+		ww_mutex_lock(&mtx->mutex, NULL);
+	}
+	complete(&mtx->done);
+	ww_mutex_unlock(&mtx->mutex);
+}
+
+static int __test_mutex(struct ww_class *class, unsigned int flags)
+{
+#define TIMEOUT (HZ / 16)
+	struct test_mutex mtx;
+	struct ww_acquire_ctx ctx;
+	int ret;
+
+	ww_mutex_init(&mtx.mutex, class);
+	if (flags & TEST_MTX_CTX)
+		ww_acquire_init(&ctx, class);
+
+	INIT_WORK_ONSTACK(&mtx.work, test_mutex_work);
+	init_completion(&mtx.ready);
+	init_completion(&mtx.go);
+	init_completion(&mtx.done);
+	mtx.flags = flags;
+
+	queue_work(wq, &mtx.work);
+
+	wait_for_completion(&mtx.ready);
+	ww_mutex_lock(&mtx.mutex, (flags & TEST_MTX_CTX) ? &ctx : NULL);
+	complete(&mtx.go);
+	if (flags & TEST_MTX_SPIN) {
+		unsigned long timeout = jiffies + TIMEOUT;
+
+		ret = 0;
+		do {
+			if (completion_done(&mtx.done)) {
+				ret = -EINVAL;
+				break;
+			}
+			cond_resched();
+		} while (time_before(jiffies, timeout));
+	} else {
+		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
+	}
+	ww_mutex_unlock(&mtx.mutex);
+	if (flags & TEST_MTX_CTX)
+		ww_acquire_fini(&ctx);
+
+	if (ret) {
+		pr_err("%s(flags=%x): mutual exclusion failure\n",
+		       __func__, flags);
+		ret = -EINVAL;
+	}
+
+	flush_work(&mtx.work);
+	destroy_work_on_stack(&mtx.work);
+	return ret;
+#undef TIMEOUT
+}
+
+static int test_mutex(struct ww_class *class)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < __TEST_MTX_LAST; i++) {
+		ret = __test_mutex(class, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int test_aa(struct ww_class *class, bool trylock)
+{
+	struct ww_mutex mutex;
+	struct ww_acquire_ctx ctx;
+	int ret;
+	const char *from = trylock ? "trylock" : "lock";
+
+	ww_mutex_init(&mutex, class);
+	ww_acquire_init(&ctx, class);
+
+	if (!trylock) {
+		ret = ww_mutex_lock(&mutex, &ctx);
+		if (ret) {
+			pr_err("%s: initial lock failed!\n", __func__);
+			goto out;
+		}
+	} else {
+		ret = !ww_mutex_trylock(&mutex, &ctx);
+		if (ret) {
+			pr_err("%s: initial trylock failed!\n", __func__);
+			goto out;
+		}
+	}
+
+	if (ww_mutex_trylock(&mutex, NULL))  {
+		pr_err("%s: trylocked itself without context from %s!\n", __func__, from);
+		ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (ww_mutex_trylock(&mutex, &ctx))  {
+		pr_err("%s: trylocked itself with context from %s!\n", __func__, from);
+		ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = ww_mutex_lock(&mutex, &ctx);
+	if (ret != -EALREADY) {
+		pr_err("%s: missed deadlock for recursing, ret=%d from %s\n",
+		       __func__, ret, from);
+		if (!ret)
+			ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ww_mutex_unlock(&mutex);
+	ret = 0;
+out:
+	ww_acquire_fini(&ctx);
+	return ret;
+}
+
+struct test_abba {
+	struct work_struct work;
+	struct ww_class *class;
+	struct ww_mutex a_mutex;
+	struct ww_mutex b_mutex;
+	struct completion a_ready;
+	struct completion b_ready;
+	bool resolve, trylock;
+	int result;
+};
+
+static void test_abba_work(struct work_struct *work)
+{
+	struct test_abba *abba = container_of(work, typeof(*abba), work);
+	struct ww_acquire_ctx ctx;
+	int err;
+
+	ww_acquire_init_noinject(&ctx, abba->class);
+	if (!abba->trylock)
+		ww_mutex_lock(&abba->b_mutex, &ctx);
+	else
+		WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx));
+
+	WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx);
+
+	complete(&abba->b_ready);
+	wait_for_completion(&abba->a_ready);
+
+	err = ww_mutex_lock(&abba->a_mutex, &ctx);
+	if (abba->resolve && err == -EDEADLK) {
+		ww_mutex_unlock(&abba->b_mutex);
+		ww_mutex_lock_slow(&abba->a_mutex, &ctx);
+		err = ww_mutex_lock(&abba->b_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(&abba->a_mutex);
+	ww_mutex_unlock(&abba->b_mutex);
+	ww_acquire_fini(&ctx);
+
+	abba->result = err;
+}
+
+static int test_abba(struct ww_class *class, bool trylock, bool resolve)
+{
+	struct test_abba abba;
+	struct ww_acquire_ctx ctx;
+	int err, ret;
+
+	ww_mutex_init(&abba.a_mutex, class);
+	ww_mutex_init(&abba.b_mutex, class);
+	INIT_WORK_ONSTACK(&abba.work, test_abba_work);
+	init_completion(&abba.a_ready);
+	init_completion(&abba.b_ready);
+	abba.class = class;
+	abba.trylock = trylock;
+	abba.resolve = resolve;
+
+	queue_work(wq, &abba.work);
+
+	ww_acquire_init_noinject(&ctx, class);
+	if (!trylock)
+		ww_mutex_lock(&abba.a_mutex, &ctx);
+	else
+		WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx));
+
+	WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx);
+
+	complete(&abba.a_ready);
+	wait_for_completion(&abba.b_ready);
+
+	err = ww_mutex_lock(&abba.b_mutex, &ctx);
+	if (resolve && err == -EDEADLK) {
+		ww_mutex_unlock(&abba.a_mutex);
+		ww_mutex_lock_slow(&abba.b_mutex, &ctx);
+		err = ww_mutex_lock(&abba.a_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(&abba.b_mutex);
+	ww_mutex_unlock(&abba.a_mutex);
+	ww_acquire_fini(&ctx);
+
+	flush_work(&abba.work);
+	destroy_work_on_stack(&abba.work);
+
+	ret = 0;
+	if (resolve) {
+		if (err || abba.result) {
+			pr_err("%s: failed to resolve ABBA deadlock, A err=%d, B err=%d\n",
+			       __func__, err, abba.result);
+			ret = -EINVAL;
+		}
+	} else {
+		if (err != -EDEADLK && abba.result != -EDEADLK) {
+			pr_err("%s: missed ABBA deadlock, A err=%d, B err=%d\n",
+			       __func__, err, abba.result);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+struct test_cycle {
+	struct work_struct work;
+	struct ww_class *class;
+	struct ww_mutex a_mutex;
+	struct ww_mutex *b_mutex;
+	struct completion *a_signal;
+	struct completion b_signal;
+	int result;
+};
+
+static void test_cycle_work(struct work_struct *work)
+{
+	struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
+	struct ww_acquire_ctx ctx;
+	int err, erra = 0;
+
+	ww_acquire_init_noinject(&ctx, cycle->class);
+	ww_mutex_lock(&cycle->a_mutex, &ctx);
+
+	complete(cycle->a_signal);
+	wait_for_completion(&cycle->b_signal);
+
+	err = ww_mutex_lock(cycle->b_mutex, &ctx);
+	if (err == -EDEADLK) {
+		err = 0;
+		ww_mutex_unlock(&cycle->a_mutex);
+		ww_mutex_lock_slow(cycle->b_mutex, &ctx);
+		erra = ww_mutex_lock(&cycle->a_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(cycle->b_mutex);
+	if (!erra)
+		ww_mutex_unlock(&cycle->a_mutex);
+	ww_acquire_fini(&ctx);
+
+	cycle->result = err ?: erra;
+}
+
+static int __test_cycle(struct ww_class *class, unsigned int nthreads)
+{
+	struct test_cycle *cycles;
+	unsigned int n, last = nthreads - 1;
+	int ret;
+
+	cycles = kmalloc_objs(*cycles, nthreads);
+	if (!cycles)
+		return -ENOMEM;
+
+	for (n = 0; n < nthreads; n++) {
+		struct test_cycle *cycle = &cycles[n];
+
+		cycle->class = class;
+		ww_mutex_init(&cycle->a_mutex, class);
+		if (n == last)
+			cycle->b_mutex = &cycles[0].a_mutex;
+		else
+			cycle->b_mutex = &cycles[n + 1].a_mutex;
+
+		if (n == 0)
+			cycle->a_signal = &cycles[last].b_signal;
+		else
+			cycle->a_signal = &cycles[n - 1].b_signal;
+		init_completion(&cycle->b_signal);
+
+		INIT_WORK(&cycle->work, test_cycle_work);
+		cycle->result = 0;
+	}
+
+	for (n = 0; n < nthreads; n++)
+		queue_work(wq, &cycles[n].work);
+
+	flush_workqueue(wq);
+
+	ret = 0;
+	for (n = 0; n < nthreads; n++) {
+		struct test_cycle *cycle = &cycles[n];
+
+		if (!cycle->result)
+			continue;
+
+		pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n",
+		       n, nthreads, cycle->result);
+		ret = -EINVAL;
+		break;
+	}
+
+	for (n = 0; n < nthreads; n++)
+		ww_mutex_destroy(&cycles[n].a_mutex);
+	kfree(cycles);
+	return ret;
+}
+
+static int test_cycle(struct ww_class *class, unsigned int ncpus)
+{
+	unsigned int n;
+	int ret;
+
+	for (n = 2; n <= ncpus + 1; n++) {
+		ret = __test_cycle(class, n);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct stress {
+	struct work_struct work;
+	struct ww_mutex *locks;
+	struct ww_class *class;
+	unsigned long timeout;
+	int nlocks;
+};
+
+struct rnd_state rng;
+DEFINE_SPINLOCK(rng_lock);
+
+static inline u32 prandom_u32_below(u32 ceil)
+{
+	u32 ret;
+
+	spin_lock(&rng_lock);
+	ret = prandom_u32_state(&rng) % ceil;
+	spin_unlock(&rng_lock);
+	return ret;
+}
+
+static int *get_random_order(int count)
+{
+	int *order;
+	int n, r;
+
+	order = kmalloc_objs(*order, count);
+	if (!order)
+		return order;
+
+	for (n = 0; n < count; n++)
+		order[n] = n;
+
+	for (n = count - 1; n > 1; n--) {
+		r = prandom_u32_below(n + 1);
+		if (r != n)
+			swap(order[n], order[r]);
+	}
+
+	return order;
+}
+
+static void dummy_load(struct stress *stress)
+{
+	usleep_range(1000, 2000);
+}
+
+static void stress_inorder_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	const int nlocks = stress->nlocks;
+	struct ww_mutex *locks = stress->locks;
+	struct ww_acquire_ctx ctx;
+	int *order;
+
+	order = get_random_order(nlocks);
+	if (!order)
+		return;
+
+	do {
+		int contended = -1;
+		int n, err;
+
+		ww_acquire_init(&ctx, stress->class);
+retry:
+		err = 0;
+		for (n = 0; n < nlocks; n++) {
+			if (n == contended)
+				continue;
+
+			err = ww_mutex_lock(&locks[order[n]], &ctx);
+			if (err < 0)
+				break;
+		}
+		if (!err)
+			dummy_load(stress);
+
+		if (contended > n)
+			ww_mutex_unlock(&locks[order[contended]]);
+		contended = n;
+		while (n--)
+			ww_mutex_unlock(&locks[order[n]]);
+
+		if (err == -EDEADLK) {
+			if (!time_after(jiffies, stress->timeout)) {
+				ww_mutex_lock_slow(&locks[order[contended]], &ctx);
+				goto retry;
+			}
+		}
+
+		ww_acquire_fini(&ctx);
+		if (err) {
+			pr_err_once("stress (%s) failed with %d\n",
+				    __func__, err);
+			break;
+		}
+	} while (!time_after(jiffies, stress->timeout));
+
+	kfree(order);
+}
+
+struct reorder_lock {
+	struct list_head link;
+	struct ww_mutex *lock;
+};
+
+static void stress_reorder_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	LIST_HEAD(locks);
+	struct ww_acquire_ctx ctx;
+	struct reorder_lock *ll, *ln;
+	int *order;
+	int n, err;
+
+	order = get_random_order(stress->nlocks);
+	if (!order)
+		return;
+
+	for (n = 0; n < stress->nlocks; n++) {
+		ll = kmalloc_obj(*ll);
+		if (!ll)
+			goto out;
+
+		ll->lock = &stress->locks[order[n]];
+		list_add(&ll->link, &locks);
+	}
+	kfree(order);
+	order = NULL;
+
+	do {
+		ww_acquire_init(&ctx, stress->class);
+
+		list_for_each_entry(ll, &locks, link) {
+			err = ww_mutex_lock(ll->lock, &ctx);
+			if (!err)
+				continue;
+
+			ln = ll;
+			list_for_each_entry_continue_reverse(ln, &locks, link)
+				ww_mutex_unlock(ln->lock);
+
+			if (err != -EDEADLK) {
+				pr_err_once("stress (%s) failed with %d\n",
+					    __func__, err);
+				break;
+			}
+
+			ww_mutex_lock_slow(ll->lock, &ctx);
+			list_move(&ll->link, &locks); /* restarts iteration */
+		}
+
+		dummy_load(stress);
+		list_for_each_entry(ll, &locks, link)
+			ww_mutex_unlock(ll->lock);
+
+		ww_acquire_fini(&ctx);
+	} while (!time_after(jiffies, stress->timeout));
+
+out:
+	list_for_each_entry_safe(ll, ln, &locks, link)
+		kfree(ll);
+	kfree(order);
+}
+
+static void stress_one_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	const int nlocks = stress->nlocks;
+	struct ww_mutex *lock = stress->locks + get_random_u32_below(nlocks);
+	int err;
+
+	do {
+		err = ww_mutex_lock(lock, NULL);
+		if (!err) {
+			dummy_load(stress);
+			ww_mutex_unlock(lock);
+		} else {
+			pr_err_once("stress (%s) failed with %d\n",
+				    __func__, err);
+			break;
+		}
+	} while (!time_after(jiffies, stress->timeout));
+}
+
+#define STRESS_INORDER BIT(0)
+#define STRESS_REORDER BIT(1)
+#define STRESS_ONE BIT(2)
+#define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE)
+
+static int stress(struct ww_class *class, int nlocks, int nthreads, unsigned int flags)
+{
+	struct ww_mutex *locks;
+	struct stress *stress_array;
+	int n, count;
+
+	locks = kmalloc_objs(*locks, nlocks);
+	if (!locks)
+		return -ENOMEM;
+
+	stress_array = kmalloc_objs(*stress_array, nthreads);
+	if (!stress_array) {
+		kfree(locks);
+		return -ENOMEM;
+	}
+
+	for (n = 0; n < nlocks; n++)
+		ww_mutex_init(&locks[n], class);
+
+	count = 0;
+	for (n = 0; nthreads; n++) {
+		struct stress *stress;
+		void (*fn)(struct work_struct *work);
+
+		fn = NULL;
+		switch (n & 3) {
+		case 0:
+			if (flags & STRESS_INORDER)
+				fn = stress_inorder_work;
+			break;
+		case 1:
+			if (flags & STRESS_REORDER)
+				fn = stress_reorder_work;
+			break;
+		case 2:
+			if (flags & STRESS_ONE)
+				fn = stress_one_work;
+			break;
+		}
+
+		if (!fn)
+			continue;
+
+		stress = &stress_array[count++];
+
+		INIT_WORK(&stress->work, fn);
+		stress->class = class;
+		stress->locks = locks;
+		stress->nlocks = nlocks;
+		stress->timeout = jiffies + 2*HZ;
+
+		queue_work(wq, &stress->work);
+		nthreads--;
+	}
+
+	flush_workqueue(wq);
+
+	for (n = 0; n < nlocks; n++)
+		ww_mutex_destroy(&locks[n]);
+	kfree(stress_array);
+	kfree(locks);
+
+	return 0;
+}
+
+static int run_tests(struct ww_class *class)
+{
+	int ncpus = num_online_cpus();
+	int ret, i;
+
+	ret = test_mutex(class);
+	if (ret)
+		return ret;
+
+	ret = test_aa(class, false);
+	if (ret)
+		return ret;
+
+	ret = test_aa(class, true);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 4; i++) {
+		ret = test_abba(class, i & 1, i & 2);
+		if (ret)
+			return ret;
+	}
+
+	ret = test_cycle(class, ncpus);
+	if (ret)
+		return ret;
+
+	ret = stress(class, 16, 2 * ncpus, STRESS_INORDER);
+	if (ret)
+		return ret;
+
+	ret = stress(class, 16, 2 * ncpus, STRESS_REORDER);
+	if (ret)
+		return ret;
+
+	ret = stress(class, 2046, hweight32(STRESS_ALL) * ncpus, STRESS_ALL);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int run_test_classes(void)
+{
+	int ret;
+
+	pr_info("Beginning ww (wound) mutex selftests\n");
+
+	ret = run_tests(&ww_class);
+	if (ret)
+		return ret;
+
+	pr_info("Beginning ww (die) mutex selftests\n");
+	ret = run_tests(&wd_class);
+	if (ret)
+		return ret;
+
+	pr_info("All ww mutex selftests passed\n");
+	return 0;
+}
+
+static DEFINE_MUTEX(run_lock);
+
+static ssize_t run_tests_store(struct kobject *kobj, struct kobj_attribute *attr,
+			       const char *buf, size_t count)
+{
+	if (!mutex_trylock(&run_lock)) {
+		pr_err("Test already running\n");
+		return count;
+	}
+
+	run_test_classes();
+	mutex_unlock(&run_lock);
+
+	return count;
+}
+
+static struct kobj_attribute run_tests_attribute =
+	__ATTR(run_tests, 0664, NULL, run_tests_store);
+
+static struct attribute *attrs[] = {
+	&run_tests_attribute.attr,
+	NULL,   /* need to NULL terminate the list of attributes */
+};
+
+static struct attribute_group attr_group = {
+	.attrs = attrs,
+};
+
+static struct kobject *test_ww_mutex_kobj;
+
+static int __init test_ww_mutex_init(void)
+{
+	int ret;
+
+	prandom_seed_state(&rng, get_random_u64());
+
+	wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0);
+	if (!wq)
+		return -ENOMEM;
+
+	test_ww_mutex_kobj = kobject_create_and_add("test_ww_mutex", kernel_kobj);
+	if (!test_ww_mutex_kobj) {
+		destroy_workqueue(wq);
+		return -ENOMEM;
+	}
+
+	/* Create the files associated with this kobject */
+	ret = sysfs_create_group(test_ww_mutex_kobj, &attr_group);
+	if (ret) {
+		kobject_put(test_ww_mutex_kobj);
+		destroy_workqueue(wq);
+		return ret;
+	}
+
+	mutex_lock(&run_lock);
+	ret = run_test_classes();
+	mutex_unlock(&run_lock);
+
+	return ret;
+}
+
+static void __exit test_ww_mutex_exit(void)
+{
+	kobject_put(test_ww_mutex_kobj);
+	destroy_workqueue(wq);
+}
+
+module_init(test_ww_mutex_init);
+module_exit(test_ww_mutex_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("API test facility for ww_mutexes");

linux-7.2.3/kernel/locking/ww_mutex.h

@@ -0,0 +1,635 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef WW_RT
+
+#define MUTEX		mutex
+#define MUTEX_WAITER	mutex_waiter
+#define WAIT_LOCK	wait_lock
+
+/*
+ *           +--------+
+ *           | first  |
+ *           +--------+
+ *                |
+ *                v
+ *  +----+     +----+     +----+
+ *  | W3 | <-> | W1 | <-> | W2 |
+ *  +----+     +----+     +----+
+ *    ^                     ^
+ *    +---------------------+
+ */
+
+static inline struct mutex_waiter *
+__ww_waiter_first(struct mutex *lock)
+	__must_hold(&lock->wait_lock)
+{
+	return lock->first_waiter;
+}
+
+/*
+ * for (cur = __ww_waiter_first(); cur; cur = __ww_waiter_next())
+ *
+ * Should iterate like: W1, W2, W3
+ */
+static inline struct mutex_waiter *
+__ww_waiter_next(struct mutex *lock, struct mutex_waiter *w)
+	__must_hold(&lock->wait_lock)
+{
+	w = list_next_entry(w, list);
+	/*
+	 * Terminate if the next entry is the first again, that has already
+	 * been observed.
+	 */
+	if (lock->first_waiter == w)
+		return NULL;
+
+	return w;
+}
+
+/*
+ * for (cur = __ww_waiter_last(); cur; cur = __ww_waiter_prev())
+ *
+ * Should iterate like: W3, W2, W1
+ */
+static inline struct mutex_waiter *
+__ww_waiter_prev(struct mutex *lock, struct mutex_waiter *w)
+	__must_hold(&lock->wait_lock)
+{
+	/*
+	 * Terminate at the first entry, the previous entry of first is the
+	 * last and that has already been observed.
+	 */
+	if (lock->first_waiter == w)
+		return NULL;
+
+	return list_prev_entry(w, list);
+}
+
+static inline struct mutex_waiter *
+__ww_waiter_last(struct mutex *lock)
+	__must_hold(&lock->wait_lock)
+{
+	struct mutex_waiter *w = lock->first_waiter;
+
+	if (w)
+		w = list_prev_entry(w, list);
+	return w;
+}
+
+static inline void
+__ww_waiter_add(struct mutex *lock, struct mutex_waiter *waiter, struct mutex_waiter *pos)
+	__must_hold(&lock->wait_lock)
+{
+	__mutex_add_waiter(lock, waiter, pos);
+}
+
+static inline struct task_struct *
+__ww_mutex_owner(struct mutex *lock)
+{
+	return __mutex_owner(lock);
+}
+
+static inline bool
+__ww_mutex_has_waiters(struct mutex *lock)
+{
+	return atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS;
+}
+
+static inline void lock_wait_lock(struct mutex *lock, unsigned long *flags)
+	__acquires(&lock->wait_lock)
+{
+	raw_spin_lock_irqsave(&lock->wait_lock, *flags);
+}
+
+static inline void unlock_wait_lock(struct mutex *lock, unsigned long *flags)
+	__releases(&lock->wait_lock)
+{
+	raw_spin_unlock_irqrestore(&lock->wait_lock, *flags);
+}
+
+static inline void lockdep_assert_wait_lock_held(struct mutex *lock)
+	__must_hold(&lock->wait_lock)
+{
+	lockdep_assert_held(&lock->wait_lock);
+}
+
+#else /* WW_RT */
+
+#define MUTEX		rt_mutex
+#define MUTEX_WAITER	rt_mutex_waiter
+#define WAIT_LOCK	rtmutex.wait_lock
+
+static inline struct rt_mutex_waiter *
+__ww_waiter_first(struct rt_mutex *lock)
+	__must_hold(&lock->rtmutex.wait_lock)
+{
+	struct rb_node *n = rb_first(&lock->rtmutex.waiters.rb_root);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
+}
+
+static inline struct rt_mutex_waiter *
+__ww_waiter_next(struct rt_mutex *lock, struct rt_mutex_waiter *w)
+{
+	struct rb_node *n = rb_next(&w->tree.entry);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
+}
+
+static inline struct rt_mutex_waiter *
+__ww_waiter_prev(struct rt_mutex *lock, struct rt_mutex_waiter *w)
+{
+	struct rb_node *n = rb_prev(&w->tree.entry);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
+}
+
+static inline struct rt_mutex_waiter *
+__ww_waiter_last(struct rt_mutex *lock)
+	__must_hold(&lock->rtmutex.wait_lock)
+{
+	struct rb_node *n = rb_last(&lock->rtmutex.waiters.rb_root);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct rt_mutex_waiter, tree.entry);
+}
+
+static inline void
+__ww_waiter_add(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct rt_mutex_waiter *pos)
+{
+	/* RT unconditionally adds the waiter first and then removes it on error */
+}
+
+static inline struct task_struct *
+__ww_mutex_owner(struct rt_mutex *lock)
+{
+	return rt_mutex_owner(&lock->rtmutex);
+}
+
+static inline bool
+__ww_mutex_has_waiters(struct rt_mutex *lock)
+	__must_hold(&lock->rtmutex.wait_lock)
+{
+	return rt_mutex_has_waiters(&lock->rtmutex);
+}
+
+static inline void lock_wait_lock(struct rt_mutex *lock, unsigned long *flags)
+	__acquires(&lock->rtmutex.wait_lock)
+{
+	raw_spin_lock_irqsave(&lock->rtmutex.wait_lock, *flags);
+}
+
+static inline void unlock_wait_lock(struct rt_mutex *lock, unsigned long *flags)
+	__releases(&lock->rtmutex.wait_lock)
+{
+	raw_spin_unlock_irqrestore(&lock->rtmutex.wait_lock, *flags);
+}
+
+static inline void lockdep_assert_wait_lock_held(struct rt_mutex *lock)
+	__must_hold(&lock->rtmutex.wait_lock)
+{
+	lockdep_assert_held(&lock->rtmutex.wait_lock);
+}
+
+#endif /* WW_RT */
+
+/*
+ * Wait-Die:
+ *   The newer transactions are killed when:
+ *     It (the new transaction) makes a request for a lock being held
+ *     by an older transaction.
+ *
+ * Wound-Wait:
+ *   The newer transactions are wounded when:
+ *     An older transaction makes a request for a lock being held by
+ *     the newer transaction.
+ */
+
+/*
+ * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired
+ * it.
+ */
+static __always_inline void
+ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
+{
+#ifdef DEBUG_WW_MUTEXES
+	/*
+	 * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+	 * but released with a normal mutex_unlock in this call.
+	 *
+	 * This should never happen, always use ww_mutex_unlock.
+	 */
+	DEBUG_LOCKS_WARN_ON(ww->ctx);
+
+	/*
+	 * Not quite done after calling ww_acquire_done() ?
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+	if (ww_ctx->contending_lock) {
+		/*
+		 * After -EDEADLK you tried to
+		 * acquire a different ww_mutex? Bad!
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+		/*
+		 * You called ww_mutex_lock after receiving -EDEADLK,
+		 * but 'forgot' to unlock everything else first?
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+		ww_ctx->contending_lock = NULL;
+	}
+
+	/*
+	 * Naughty, using a different class will lead to undefined behavior!
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+	ww_ctx->acquired++;
+	ww->ctx = ww_ctx;
+}
+
+/*
+ * Determine if @a is 'less' than @b. IOW, either @a is a lower priority task
+ * or, when of equal priority, a younger transaction than @b.
+ *
+ * Depending on the algorithm, @a will either need to wait for @b, or die.
+ */
+static inline bool
+__ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
+{
+/*
+ * Can only do the RT prio for WW_RT, because task->prio isn't stable due to PI,
+ * so the wait_list ordering will go wobbly. rt_mutex re-queues the waiter and
+ * isn't affected by this.
+ */
+#ifdef WW_RT
+	/* kernel prio; less is more */
+	int a_prio = a->task->prio;
+	int b_prio = b->task->prio;
+
+	if (rt_or_dl_prio(a_prio) || rt_or_dl_prio(b_prio)) {
+
+		if (a_prio > b_prio)
+			return true;
+
+		if (a_prio < b_prio)
+			return false;
+
+		/* equal static prio */
+
+		if (dl_prio(a_prio)) {
+			if (dl_time_before(b->task->dl.deadline,
+					   a->task->dl.deadline))
+				return true;
+
+			if (dl_time_before(a->task->dl.deadline,
+					   b->task->dl.deadline))
+				return false;
+		}
+
+		/* equal prio */
+	}
+#endif
+
+	/* FIFO order tie break -- bigger is younger */
+	return (signed long)(a->stamp - b->stamp) > 0;
+}
+
+/*
+ * Wait-Die; wake a lesser waiter context (when locks held) such that it can
+ * die.
+ *
+ * Among waiters with context, only the first one can have other locks acquired
+ * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and
+ * __ww_mutex_check_kill() wake any but the earliest context.
+ */
+static bool
+__ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
+	       struct ww_acquire_ctx *ww_ctx, struct wake_q_head *wake_q)
+{
+	if (!ww_ctx->is_wait_die)
+		return false;
+
+	if (waiter->ww_ctx->acquired > 0 && __ww_ctx_less(waiter->ww_ctx, ww_ctx)) {
+#ifndef WW_RT
+		debug_mutex_wake_waiter(lock, waiter);
+#endif
+		/*
+		 * When waking up the task to die, be sure to set the
+		 * blocked_on to PROXY_WAKING. Otherwise we can see
+		 * circular blocked_on relationships that can't resolve.
+		 */
+		clear_task_blocked_on(waiter->task, lock);
+		wake_q_add(wake_q, waiter->task);
+	}
+
+	return true;
+}
+
+/*
+ * Wound-Wait; wound a lesser @hold_ctx if it holds the lock.
+ *
+ * Wound the lock holder if there are waiters with more important transactions
+ * than the lock holders. Even if multiple waiters may wound the lock holder,
+ * it's sufficient that only one does.
+ */
+static bool __ww_mutex_wound(struct MUTEX *lock,
+			     struct ww_acquire_ctx *ww_ctx,
+			     struct ww_acquire_ctx *hold_ctx,
+			     struct wake_q_head *wake_q)
+	__must_hold(&lock->WAIT_LOCK)
+{
+	struct task_struct *owner = __ww_mutex_owner(lock);
+
+	lockdep_assert_wait_lock_held(lock);
+
+	/*
+	 * Possible through __ww_mutex_add_waiter() when we race with
+	 * ww_mutex_set_context_fastpath(). In that case we'll get here again
+	 * through __ww_mutex_check_waiters().
+	 */
+	if (!hold_ctx)
+		return false;
+
+	/*
+	 * Can have !owner because of __mutex_unlock_slowpath(), but if owner,
+	 * it cannot go away because we'll have FLAG_WAITERS set and hold
+	 * wait_lock.
+	 */
+	if (!owner)
+		return false;
+
+	if (ww_ctx->acquired > 0 && __ww_ctx_less(hold_ctx, ww_ctx)) {
+		hold_ctx->wounded = 1;
+
+		/*
+		 * wake_up_process() paired with set_current_state()
+		 * inserts sufficient barriers to make sure @owner either sees
+		 * it's wounded in __ww_mutex_check_kill() or has a
+		 * wakeup pending to re-read the wounded state.
+		 */
+		if (owner != current) {
+			/*
+			 * When waking up the task to wound, be sure to set the
+			 * blocked_on to PROXY_WAKING. Otherwise we can see
+			 * circular blocked_on relationships that can't resolve.
+			 *
+			 * NOTE: We pass NULL here instead of lock, because we
+			 * are waking the mutex owner, who may be currently
+			 * blocked on a different mutex.
+			 */
+			clear_task_blocked_on(owner, NULL);
+			wake_q_add(wake_q, owner);
+		}
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * We just acquired @lock under @ww_ctx, if there are more important contexts
+ * waiting behind us on the wait-list, check if they need to die, or wound us.
+ *
+ * See __ww_mutex_add_waiter() for the list-order construction; basically the
+ * list is ordered by stamp, smallest (oldest) first.
+ *
+ * This relies on never mixing wait-die/wound-wait on the same wait-list;
+ * which is currently ensured by that being a ww_class property.
+ *
+ * The current task must not be on the wait list.
+ */
+static void
+__ww_mutex_check_waiters(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx,
+			 struct wake_q_head *wake_q)
+	__must_hold(&lock->WAIT_LOCK)
+{
+	struct MUTEX_WAITER *cur;
+
+	lockdep_assert_wait_lock_held(lock);
+
+	for (cur = __ww_waiter_first(lock); cur;
+	     cur = __ww_waiter_next(lock, cur)) {
+
+		if (!cur->ww_ctx)
+			continue;
+
+		if (__ww_mutex_die(lock, cur, ww_ctx, wake_q) ||
+		    __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx, wake_q))
+			break;
+	}
+}
+
+/*
+ * After acquiring lock with fastpath, where we do not hold wait_lock, set ctx
+ * and wake up any waiters so they can recheck.
+ */
+static __always_inline void
+ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	DEFINE_WAKE_Q(wake_q);
+	unsigned long flags;
+	bool has_waiters;
+
+	ww_mutex_lock_acquired(lock, ctx);
+
+	/*
+	 * The lock->ctx update should be visible on all cores before
+	 * the WAITERS check is done, otherwise contended waiters might be
+	 * missed. The contended waiters will either see ww_ctx == NULL
+	 * and keep spinning, or it will acquire wait_lock, add itself
+	 * to waiter list and sleep.
+	 */
+	smp_mb(); /* See comments above and below. */
+
+	/*
+	 * [W] ww->ctx = ctx	    [W] MUTEX_FLAG_WAITERS
+	 *     MB		        MB
+	 * [R] MUTEX_FLAG_WAITERS   [R] ww->ctx
+	 *
+	 * The memory barrier above pairs with the memory barrier in
+	 * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx
+	 * and/or !empty list.
+	 */
+	has_waiters = data_race(__ww_mutex_has_waiters(&lock->base));
+	if (likely(!has_waiters))
+		return;
+
+	/*
+	 * Uh oh, we raced in fastpath, check if any of the waiters need to
+	 * die or wound us.
+	 */
+	lock_wait_lock(&lock->base, &flags);
+	__ww_mutex_check_waiters(&lock->base, ctx, &wake_q);
+	preempt_disable();
+	unlock_wait_lock(&lock->base, &flags);
+	wake_up_q(&wake_q);
+	preempt_enable();
+}
+
+static __always_inline int
+__ww_mutex_kill(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	if (ww_ctx->acquired > 0) {
+#ifdef DEBUG_WW_MUTEXES
+		struct ww_mutex *ww;
+
+		ww = container_of(lock, struct ww_mutex, base);
+		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
+		ww_ctx->contending_lock = ww;
+#endif
+		return -EDEADLK;
+	}
+
+	return 0;
+}
+
+/*
+ * Check the wound condition for the current lock acquire.
+ *
+ * Wound-Wait: If we're wounded, kill ourself.
+ *
+ * Wait-Die: If we're trying to acquire a lock already held by an older
+ *           context, kill ourselves.
+ *
+ * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to
+ * look at waiters before us in the wait-list.
+ */
+static inline int
+__ww_mutex_check_kill(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
+		      struct ww_acquire_ctx *ctx)
+	__must_hold(&lock->WAIT_LOCK)
+{
+	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+	struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
+	struct MUTEX_WAITER *cur;
+
+	if (ctx->acquired == 0)
+		return 0;
+
+	if (!ctx->is_wait_die) {
+		if (ctx->wounded)
+			return __ww_mutex_kill(lock, ctx);
+
+		return 0;
+	}
+
+	if (hold_ctx && __ww_ctx_less(ctx, hold_ctx))
+		return __ww_mutex_kill(lock, ctx);
+
+	/*
+	 * If there is a waiter in front of us that has a context, then its
+	 * stamp is earlier than ours and we must kill ourself.
+	 */
+	for (cur = __ww_waiter_prev(lock, waiter); cur;
+	     cur = __ww_waiter_prev(lock, cur)) {
+
+		if (!cur->ww_ctx)
+			continue;
+
+		return __ww_mutex_kill(lock, ctx);
+	}
+
+	return 0;
+}
+
+/*
+ * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest
+ * first. Such that older contexts are preferred to acquire the lock over
+ * younger contexts.
+ *
+ * Waiters without context are interspersed in FIFO order.
+ *
+ * Furthermore, for Wait-Die kill ourself immediately when possible (there are
+ * older contexts already waiting) to avoid unnecessary waiting and for
+ * Wound-Wait ensure we wound the owning context when it is younger.
+ */
+static inline int
+__ww_mutex_add_waiter(struct MUTEX_WAITER *waiter,
+		      struct MUTEX *lock,
+		      struct ww_acquire_ctx *ww_ctx,
+		      struct wake_q_head *wake_q)
+	__must_hold(&lock->WAIT_LOCK)
+{
+	struct MUTEX_WAITER *cur, *pos = NULL;
+	bool is_wait_die;
+
+	if (!ww_ctx) {
+		__ww_waiter_add(lock, waiter, NULL);
+		return 0;
+	}
+
+	is_wait_die = ww_ctx->is_wait_die;
+
+	/*
+	 * Add the waiter before the first waiter with a higher stamp.
+	 * Waiters without a context are skipped to avoid starving
+	 * them. Wait-Die waiters may die here. Wound-Wait waiters
+	 * never die here, but they are sorted in stamp order and
+	 * may wound the lock holder.
+	 */
+	for (cur = __ww_waiter_last(lock); cur;
+	     cur = __ww_waiter_prev(lock, cur)) {
+
+		if (!cur->ww_ctx)
+			continue;
+
+		if (__ww_ctx_less(ww_ctx, cur->ww_ctx)) {
+			/*
+			 * Wait-Die: if we find an older context waiting, there
+			 * is no point in queueing behind it, as we'd have to
+			 * die the moment it would acquire the lock.
+			 */
+			if (is_wait_die) {
+				int ret = __ww_mutex_kill(lock, ww_ctx);
+
+				if (ret)
+					return ret;
+			}
+
+			break;
+		}
+
+		pos = cur;
+
+		/* Wait-Die: ensure younger waiters die. */
+		__ww_mutex_die(lock, cur, ww_ctx, wake_q);
+	}
+
+	__ww_waiter_add(lock, waiter, pos);
+
+	/*
+	 * Wound-Wait: if we're blocking on a mutex owned by a younger context,
+	 * wound that such that we might proceed.
+	 */
+	if (!is_wait_die) {
+		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+
+		/*
+		 * See ww_mutex_set_context_fastpath(). Orders setting
+		 * MUTEX_FLAG_WAITERS vs the ww->ctx load,
+		 * such that either we or the fastpath will wound @ww->ctx.
+		 */
+		smp_mb();
+		__ww_mutex_wound(lock, ww_ctx, ww->ctx, wake_q);
+	}
+
+	return 0;
+}
+
+static inline void __ww_mutex_unlock(struct ww_mutex *lock)
+{
+	if (lock->ctx) {
+#ifdef DEBUG_WW_MUTEXES
+		DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
+#endif
+		if (lock->ctx->acquired > 0)
+			lock->ctx->acquired--;
+		lock->ctx = NULL;
+	}
+}

linux-7.2.3/kernel/locking/ww_rt_mutex.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rtmutex API
+ */
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#define RT_MUTEX_BUILD_MUTEX
+#define WW_RT
+#include "rtmutex.c"
+
+int ww_mutex_trylock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	struct rt_mutex *rtm = &lock->base;
+
+	if (!ww_ctx)
+		return rt_mutex_trylock(rtm);
+
+	/*
+	 * Reset the wounded flag after a kill. No other process can
+	 * race and wound us here, since they can't have a valid owner
+	 * pointer if we don't have any locks held.
+	 */
+	if (ww_ctx->acquired == 0)
+		ww_ctx->wounded = 0;
+
+	if (__rt_mutex_trylock(&rtm->rtmutex)) {
+		ww_mutex_set_context_fastpath(lock, ww_ctx);
+		mutex_acquire_nest(&rtm->dep_map, 0, 1, &ww_ctx->dep_map, _RET_IP_);
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ww_mutex_trylock);
+
+static int __sched
+__ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx,
+		   unsigned int state, unsigned long ip)
+{
+	struct lockdep_map __maybe_unused *nest_lock = NULL;
+	struct rt_mutex *rtm = &lock->base;
+	int ret;
+
+	might_sleep();
+
+	if (ww_ctx) {
+		if (unlikely(ww_ctx == READ_ONCE(lock->ctx)))
+			return -EALREADY;
+
+		/*
+		 * Reset the wounded flag after a kill. No other process can
+		 * race and wound us here, since they can't have a valid owner
+		 * pointer if we don't have any locks held.
+		 */
+		if (ww_ctx->acquired == 0)
+			ww_ctx->wounded = 0;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+		nest_lock = &ww_ctx->dep_map;
+#endif
+	}
+	mutex_acquire_nest(&rtm->dep_map, 0, 0, nest_lock, ip);
+
+	if (likely(rt_mutex_try_acquire(&rtm->rtmutex))) {
+		if (ww_ctx)
+			ww_mutex_set_context_fastpath(lock, ww_ctx);
+		return 0;
+	}
+
+	ret = rt_mutex_slowlock(&rtm->rtmutex, ww_ctx, state);
+
+	if (ret)
+		mutex_release(&rtm->dep_map, ip);
+	return ret;
+}
+
+int __sched
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	return __ww_rt_mutex_lock(lock, ctx, TASK_UNINTERRUPTIBLE, _RET_IP_);
+}
+EXPORT_SYMBOL(ww_mutex_lock);
+
+int __sched
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	return __ww_rt_mutex_lock(lock, ctx, TASK_INTERRUPTIBLE, _RET_IP_);
+}
+EXPORT_SYMBOL(ww_mutex_lock_interruptible);
+
+void __sched ww_mutex_unlock(struct ww_mutex *lock)
+	__no_context_analysis
+{
+	struct rt_mutex *rtm = &lock->base;
+
+	__ww_mutex_unlock(lock);
+
+	mutex_release(&rtm->dep_map, _RET_IP_);
+	__rt_mutex_unlock(&rtm->rtmutex);
+}
+EXPORT_SYMBOL(ww_mutex_unlock);