From e204193b138af347fbbbe026e68cb3385112f387 Mon Sep 17 00:00:00 2001
From: Xiu Jianfeng <xiujianfeng@huawei.com>
Date: Mon, 13 Dec 2021 21:26:18 +0800
Subject: lockdep: Use memset_startat() helper in reinit_class()

use memset_startat() helper to simplify the code, there is no functional
change in this patch.

Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211213132618.105737-1-xiujianfeng@huawei.com
---
 kernel/locking/lockdep.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4a882f83aeb9..89b3df51fd98 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6011,13 +6011,10 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 
 static void reinit_class(struct lock_class *class)
 {
-	void *const p = class;
-	const unsigned int offset = offsetof(struct lock_class, key);
-
 	WARN_ON_ONCE(!class->lock_entry.next);
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
-	memset(p + offset, 0, sizeof(*class) - offset);
+	memset_startat(class, 0, key);
 	WARN_ON_ONCE(!class->lock_entry.next);
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
-- 
cgit v1.2.3


From 61cc4534b6550997c97a03759ab46b29d44c0017 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sun, 2 Jan 2022 21:35:58 -0500
Subject: locking/lockdep: Avoid potential access of invalid memory in
 lock_class

It was found that reading /proc/lockdep after a lockdep splat may
potentially cause an access to freed memory if lockdep_unregister_key()
is called after the splat but before access to /proc/lockdep [1]. This
is due to the fact that graph_lock() call in lockdep_unregister_key()
fails after the clearing of debug_locks by the splat process.

After lockdep_unregister_key() is called, the lock_name may be freed
but the corresponding lock_class structure still have a reference to
it. That invalid memory pointer will then be accessed when /proc/lockdep
is read by a user and a use-after-free (UAF) error will be reported if
KASAN is enabled.

To fix this problem, lockdep_unregister_key() is now modified to always
search for a matching key irrespective of the debug_locks state and
zap the corresponding lock class if a matching one is found.

[1] https://lore.kernel.org/lkml/77f05c15-81b6-bddd-9650-80d5f23fe330@i-love.sakura.ne.jp/

Fixes: 8b39adbee805 ("locking/lockdep: Make lockdep_unregister_key() honor 'debug_locks' again")
Reported-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lkml.kernel.org/r/20220103023558.1377055-1-longman@redhat.com
---
 kernel/locking/lockdep.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 89b3df51fd98..2e6892ec3756 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6287,7 +6287,13 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 		lockdep_reset_lock_reg(lock);
 }
 
-/* Unregister a dynamically allocated key. */
+/*
+ * Unregister a dynamically allocated key.
+ *
+ * Unlike lockdep_register_key(), a search is always done to find a matching
+ * key irrespective of debug_locks to avoid potential invalid access to freed
+ * memory in lock_class entry.
+ */
 void lockdep_unregister_key(struct lock_class_key *key)
 {
 	struct hlist_head *hash_head = keyhashentry(key);
@@ -6302,10 +6308,8 @@ void lockdep_unregister_key(struct lock_class_key *key)
 		return;
 
 	raw_local_irq_save(flags);
-	if (!graph_lock())
-		goto out_irq;
+	lockdep_lock();
 
-	pf = get_pending_free();
 	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
 		if (k == key) {
 			hlist_del_rcu(&k->hash_entry);
@@ -6313,11 +6317,13 @@ void lockdep_unregister_key(struct lock_class_key *key)
 			break;
 		}
 	}
-	WARN_ON_ONCE(!found);
-	__lockdep_free_key_range(pf, key, 1);
-	call_rcu_zapped(pf);
-	graph_unlock();
-out_irq:
+	WARN_ON_ONCE(!found && debug_locks);
+	if (found) {
+		pf = get_pending_free();
+		__lockdep_free_key_range(pf, key, 1);
+		call_rcu_zapped(pf);
+	}
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
 	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
-- 
cgit v1.2.3


From c441e934b604a3b5f350a9104124cf6a3ba07a34 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 15 Jan 2022 15:16:57 -0800
Subject: locking: Add missing __sched attributes

This patch adds __sched attributes to a few missing places
to show blocked function rather than locking function
in get_wchan.

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220115231657.84828-1-minchan@kernel.org
---
 kernel/locking/percpu-rwsem.c | 5 +++--
 kernel/locking/rwsem.c        | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 70a32a576f3f..c9fdae94e098 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -7,6 +7,7 @@
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/debug.h>
 #include <linux/errno.h>
 
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
@@ -162,7 +163,7 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	__set_current_state(TASK_RUNNING);
 }
 
-bool __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
+bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 {
 	if (__percpu_down_read_trylock(sem))
 		return true;
@@ -211,7 +212,7 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem)
 	return true;
 }
 
-void percpu_down_write(struct percpu_rw_semaphore *sem)
+void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 69aba4abe104..acde5d6f1254 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1048,7 +1048,7 @@ out_nolock:
 /*
  * Wait until we successfully acquire the write lock
  */
-static struct rw_semaphore *
+static struct rw_semaphore __sched *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
 	long count;
-- 
cgit v1.2.3


From fb7275acd6fb988313dddd8d3d19efa70d9015ad Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 10 Feb 2022 22:55:26 -0500
Subject: locking/lockdep: Iterate lock_classes directly when reading lockdep
 files

When dumping lock_classes information via /proc/lockdep, we can't take
the lockdep lock as the lock hold time is indeterminate. Iterating
over all_lock_classes without holding lock can be dangerous as there
is a slight chance that it may branch off to other lists leading to
infinite loop or even access invalid memory if changes are made to
all_lock_classes list in parallel.

To avoid this problem, iteration of lock classes is now done directly
on the lock_classes array itself. The lock_classes_in_use bitmap is
checked to see if the lock class is being used. To avoid iterating
the full array all the times, a new max_lock_class_idx value is added
to track the maximum lock_class index that is currently being used.

We can theoretically take the lockdep lock for iterating all_lock_classes
when other lockdep files (lockdep_stats and lock_stat) are accessed as
the lock hold time will be shorter for them. For consistency, they are
also modified to iterate the lock_classes array directly.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220211035526.1329503-2-longman@redhat.com
---
 kernel/locking/lockdep.c           | 14 +++++++----
 kernel/locking/lockdep_internals.h |  6 +++--
 kernel/locking/lockdep_proc.c      | 51 ++++++++++++++++++++++++++++++++------
 3 files changed, 56 insertions(+), 15 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 2e6892ec3756..50036c10b518 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -183,11 +183,9 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
 static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
 unsigned long nr_lock_classes;
 unsigned long nr_zapped_classes;
-#ifndef CONFIG_DEBUG_LOCKDEP
-static
-#endif
+unsigned long max_lock_class_idx;
 struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
-static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
+DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
 
 static inline struct lock_class *hlock_class(struct held_lock *hlock)
 {
@@ -338,7 +336,7 @@ static inline void lock_release_holdtime(struct held_lock *hlock)
  * elements. These elements are linked together by the lock_entry member in
  * struct lock_class.
  */
-LIST_HEAD(all_lock_classes);
+static LIST_HEAD(all_lock_classes);
 static LIST_HEAD(free_lock_classes);
 
 /**
@@ -1252,6 +1250,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	struct lockdep_subclass_key *key;
 	struct hlist_head *hash_head;
 	struct lock_class *class;
+	int idx;
 
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
@@ -1317,6 +1316,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * of classes.
 	 */
 	list_move_tail(&class->lock_entry, &all_lock_classes);
+	idx = class - lock_classes;
+	if (idx > max_lock_class_idx)
+		max_lock_class_idx = idx;
 
 	if (verbose(class)) {
 		graph_unlock();
@@ -6000,6 +6002,8 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 		WRITE_ONCE(class->name, NULL);
 		nr_lock_classes--;
 		__clear_bit(class - lock_classes, lock_classes_in_use);
+		if (class - lock_classes == max_lock_class_idx)
+			max_lock_class_idx--;
 	} else {
 		WARN_ONCE(true, "%s() failed for class %s\n", __func__,
 			  class->name);
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index ecb8662e7a4e..bbe9000260d0 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -121,7 +121,6 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 
 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
 
-extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
 #define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
@@ -151,6 +150,10 @@ 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 *);
@@ -205,7 +208,6 @@ struct lockdep_stats {
 };
 
 DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
-extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
 #define __debug_atomic_inc(ptr)					\
 	this_cpu_inc(lockdep_stats.ptr);
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index b8d9a050c337..15fdc7fa5c68 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -24,14 +24,33 @@
 
 #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)
 {
-	return seq_list_next(v, &all_lock_classes, 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)
 {
-	return seq_list_start_head(&all_lock_classes, *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)
@@ -57,14 +76,16 @@ static void print_name(struct seq_file *m, struct lock_class *class)
 
 static int l_show(struct seq_file *m, void *v)
 {
-	struct lock_class *class = list_entry(v, struct lock_class, lock_entry);
+	struct lock_class *class = v;
 	struct lock_list *entry;
 	char usage[LOCK_USAGE_CHARS];
+	int idx = class - lock_classes;
 
-	if (v == &all_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
@@ -220,8 +241,11 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class;
+	unsigned long idx;
 
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
+	iterate_lock_classes(idx, class) {
+		if (!test_bit(idx, lock_classes_in_use))
+			continue;
 
 		if (class->usage_mask == 0)
 			nr_unused++;
@@ -254,6 +278,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 
 		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
@@ -345,6 +370,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 	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);
@@ -622,12 +649,16 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 	if (!res) {
 		struct lock_stat_data *iter = data->stats;
 		struct seq_file *m = file->private_data;
+		unsigned long idx;
 
-		list_for_each_entry(class, &all_lock_classes, lock_entry) {
+		iterate_lock_classes(idx, class) {
+			if (!test_bit(idx, lock_classes_in_use))
+				continue;
 			iter->class = class;
 			iter->stats = lock_stats(class);
 			iter++;
 		}
+
 		data->iter_end = iter;
 
 		sort(data->stats, data->iter_end - data->stats,
@@ -645,6 +676,7 @@ 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) {
@@ -654,8 +686,11 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf,
 		if (c != '0')
 			return count;
 
-		list_for_each_entry(class, &all_lock_classes, lock_entry)
+		iterate_lock_classes(idx, class) {
+			if (!test_bit(idx, lock_classes_in_use))
+				continue;
 			clear_lock_stats(class);
+		}
 	}
 	return count;
 }
-- 
cgit v1.2.3


From 8b023accc8df70e72f7704d29fead7ca914d6837 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Mon, 14 Mar 2022 15:19:03 -0700
Subject: lockdep: Fix -Wunused-parameter for _THIS_IP_

While looking into a bug related to the compiler's handling of addresses
of labels, I noticed some uses of _THIS_IP_ seemed unused in lockdep.
Drive by cleanup.

-Wunused-parameter:
kernel/locking/lockdep.c:1383:22: warning: unused parameter 'ip'
kernel/locking/lockdep.c:4246:48: warning: unused parameter 'ip'
kernel/locking/lockdep.c:4844:19: warning: unused parameter 'ip'

Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20220314221909.2027027-1-ndesaulniers@google.com
---
 arch/arm64/kernel/entry-common.c |  8 ++++----
 include/linux/irqflags.h         |  4 ++--
 include/linux/kvm_host.h         |  2 +-
 kernel/entry/common.c            |  6 +++---
 kernel/locking/lockdep.c         | 22 ++++++++--------------
 kernel/sched/idle.c              |  2 +-
 kernel/trace/trace_preemptirq.c  |  4 ++--
 7 files changed, 21 insertions(+), 27 deletions(-)

(limited to 'kernel/locking')

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 878c65aa7206..e04602ea4629 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -75,7 +75,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs)
 	if (interrupts_enabled(regs)) {
 		if (regs->exit_rcu) {
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			rcu_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
 			return;
@@ -121,7 +121,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
 static __always_inline void __exit_to_user_mode(void)
 {
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	user_enter_irqoff();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
@@ -179,7 +179,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 	ftrace_nmi_exit();
 	if (restore) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 
 	rcu_nmi_exit();
@@ -215,7 +215,7 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
 
 	if (restore) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 
 	rcu_nmi_exit();
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 4b140938b03e..5ec0fa71399e 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -20,13 +20,13 @@
 #ifdef CONFIG_PROVE_LOCKING
   extern void lockdep_softirqs_on(unsigned long ip);
   extern void lockdep_softirqs_off(unsigned long ip);
-  extern void lockdep_hardirqs_on_prepare(unsigned long ip);
+  extern void lockdep_hardirqs_on_prepare(void);
   extern void lockdep_hardirqs_on(unsigned long ip);
   extern void lockdep_hardirqs_off(unsigned long ip);
 #else
   static inline void lockdep_softirqs_on(unsigned long ip) { }
   static inline void lockdep_softirqs_off(unsigned long ip) { }
-  static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { }
+  static inline void lockdep_hardirqs_on_prepare(void) { }
   static inline void lockdep_hardirqs_on(unsigned long ip) { }
   static inline void lockdep_hardirqs_off(unsigned long ip) { }
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3f9b22c4983a..e1b2413750c0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -450,7 +450,7 @@ static __always_inline void guest_state_enter_irqoff(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	guest_context_enter_irqoff();
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e57a224d6b79..2eef7b22e02a 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -126,7 +126,7 @@ static __always_inline void __exit_to_user_mode(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	user_enter_irqoff();
@@ -416,7 +416,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 			instrumentation_begin();
 			/* Tell the tracer that IRET will enable interrupts */
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			instrumentation_end();
 			rcu_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
@@ -465,7 +465,7 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
 	ftrace_nmi_exit();
 	if (irq_state.lockdep) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 	instrumentation_end();
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c06cab6546ed..3cbd49216174 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1380,7 +1380,7 @@ static struct lock_list *alloc_list_entry(void)
  */
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
-			    unsigned long ip, u16 distance, u8 dep,
+			    u16 distance, u8 dep,
 			    const struct lock_trace *trace)
 {
 	struct lock_list *entry;
@@ -3133,19 +3133,15 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * to the previous lock's dependency list:
 	 */
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
-			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance,
-			       calc_dep(prev, next),
-			       *trace);
+			       &hlock_class(prev)->locks_after, distance,
+			       calc_dep(prev, next), *trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
-			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance,
-			       calc_depb(prev, next),
-			       *trace);
+			       &hlock_class(next)->locks_before, distance,
+			       calc_depb(prev, next), *trace);
 	if (!ret)
 		return 0;
 
@@ -4236,14 +4232,13 @@ static void __trace_hardirqs_on_caller(void)
 
 /**
  * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
- * @ip:		Caller address
  *
  * Invoked before a possible transition to RCU idle from exit to user or
  * guest mode. This ensures that all RCU operations are done before RCU
  * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
  * invoked to set the final state.
  */
-void lockdep_hardirqs_on_prepare(unsigned long ip)
+void lockdep_hardirqs_on_prepare(void)
 {
 	if (unlikely(!debug_locks))
 		return;
@@ -4840,8 +4835,7 @@ EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
 
 static void
 print_lock_nested_lock_not_held(struct task_struct *curr,
-				struct held_lock *hlock,
-				unsigned long ip)
+				struct held_lock *hlock)
 {
 	if (!debug_locks_off())
 		return;
@@ -5017,7 +5011,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	chain_key = iterate_chain_key(chain_key, hlock_id(hlock));
 
 	if (nest_lock && !__lock_is_held(nest_lock, -1)) {
-		print_lock_nested_lock_not_held(curr, hlock, ip);
+		print_lock_nested_lock_not_held(curr, hlock);
 		return 0;
 	}
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f8b5020e76a..3984dd21a5aa 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -102,7 +102,7 @@ void __cpuidle default_idle_call(void)
 		 * last -- this is very similar to the entry code.
 		 */
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(_THIS_IP_);
+		lockdep_hardirqs_on_prepare();
 		rcu_idle_enter();
 		lockdep_hardirqs_on(_THIS_IP_);
 
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f4938040c228..95b58bd757ce 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -46,7 +46,7 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
@@ -94,7 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
-- 
cgit v1.2.3


From f9e21aa9e6fb11355e54c8949a390d49ca21cde1 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 22 Mar 2022 11:20:57 -0400
Subject: locking/rwsem: No need to check for handoff bit if wait queue empty

Since commit d257cc8cb8d5 ("locking/rwsem: Make handoff bit handling
more consistent"), the handoff bit is always cleared if the wait queue
becomes empty. There is no need to check for RWSEM_FLAG_HANDOFF when
the wait list is known to be empty.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220322152059.2182333-2-longman@redhat.com
---
 kernel/locking/rwsem.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index acde5d6f1254..b077b1b2d4b3 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -977,12 +977,11 @@ queue:
 	if (list_empty(&sem->wait_list)) {
 		/*
 		 * In case the wait queue is empty and the lock isn't owned
-		 * by a writer or has the handoff bit set, this reader can
-		 * exit the slowpath and return immediately as its
-		 * RWSEM_READER_BIAS has already been set in the count.
+		 * by a writer, this reader can exit the slowpath and return
+		 * immediately as its RWSEM_READER_BIAS has already been set
+		 * in the count.
 		 */
-		if (!(atomic_long_read(&sem->count) &
-		     (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+		if (!(atomic_long_read(&sem->count) & RWSEM_WRITER_MASK)) {
 			/* Provide lock ACQUIRE */
 			smp_acquire__after_ctrl_dep();
 			raw_spin_unlock_irq(&sem->wait_lock);
-- 
cgit v1.2.3


From 54c1ee4d614d52844cf24c46d8415bf1392021d0 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 22 Mar 2022 11:20:58 -0400
Subject: locking/rwsem: Conditionally wake waiters in reader/writer slowpaths

In an analysis of a recent vmcore, a reader-owned rwsem was found with
385 readers but no writer in the wait queue. That is kind of unusual
but it may be caused by some race conditions that we have not fully
understood yet. In such a case, all the readers in the wait queue should
join the other reader-owners and acquire the read lock.

In rwsem_down_write_slowpath(), an incoming writer will try to
wake up the front readers under such circumstance. That is not
the case for rwsem_down_read_slowpath(), add a new helper function
rwsem_cond_wake_waiter() to do wakeup and use it in both reader and
writer slowpaths to have a consistent and correct behavior.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220322152059.2182333-3-longman@redhat.com
---
 kernel/locking/rwsem.c | 68 ++++++++++++++++++++++++--------------------------
 1 file changed, 32 insertions(+), 36 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index b077b1b2d4b3..03cb97a8e4cd 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -901,7 +901,7 @@ done:
  */
 static inline void clear_nonspinnable(struct rw_semaphore *sem)
 {
-	if (rwsem_test_oflags(sem, RWSEM_NONSPINNABLE))
+	if (unlikely(rwsem_test_oflags(sem, RWSEM_NONSPINNABLE)))
 		atomic_long_andnot(RWSEM_NONSPINNABLE, &sem->owner);
 }
 
@@ -925,6 +925,31 @@ rwsem_spin_on_owner(struct rw_semaphore *sem)
 }
 #endif
 
+/*
+ * Prepare to wake up waiter(s) in the wait queue by putting them into the
+ * given wake_q if the rwsem lock owner isn't a writer. If rwsem is likely
+ * reader-owned, wake up read lock waiters in queue front or wake up any
+ * front waiter otherwise.
+
+ * This is being called from both reader and writer slow paths.
+ */
+static inline void rwsem_cond_wake_waiter(struct rw_semaphore *sem, long count,
+					  struct wake_q_head *wake_q)
+{
+	enum rwsem_wake_type wake_type;
+
+	if (count & RWSEM_WRITER_MASK)
+		return;
+
+	if (count & RWSEM_READER_MASK) {
+		wake_type = RWSEM_WAKE_READERS;
+	} else {
+		wake_type = RWSEM_WAKE_ANY;
+		clear_nonspinnable(sem);
+	}
+	rwsem_mark_wake(sem, wake_type, wake_q);
+}
+
 /*
  * Wait for the read lock to be granted
  */
@@ -935,7 +960,6 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 	long rcnt = (count >> RWSEM_READER_SHIFT);
 	struct rwsem_waiter waiter;
 	DEFINE_WAKE_Q(wake_q);
-	bool wake = false;
 
 	/*
 	 * To prevent a constant stream of readers from starving a sleeping
@@ -996,22 +1020,11 @@ queue:
 	/* we're now waiting on the lock, but no longer actively locking */
 	count = atomic_long_add_return(adjustment, &sem->count);
 
-	/*
-	 * If there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (!(count & RWSEM_LOCK_MASK)) {
-		clear_nonspinnable(sem);
-		wake = true;
-	}
-	if (wake || (!(count & RWSEM_WRITER_MASK) &&
-		    (adjustment & RWSEM_FLAG_WAITERS)))
-		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
+	rwsem_cond_wake_waiter(sem, count, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
+
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -1050,7 +1063,6 @@ out_nolock:
 static struct rw_semaphore __sched *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
-	long count;
 	struct rwsem_waiter waiter;
 	DEFINE_WAKE_Q(wake_q);
 
@@ -1074,23 +1086,8 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 
 	/* we're now waiting on the lock */
 	if (rwsem_first_waiter(sem) != &waiter) {
-		count = atomic_long_read(&sem->count);
-
-		/*
-		 * If there were already threads queued before us and:
-		 *  1) there are no active locks, wake the front
-		 *     queued process(es) as the handoff bit might be set.
-		 *  2) there are no active writers and some readers, the lock
-		 *     must be read owned; so we try to wake any read lock
-		 *     waiters that were queued ahead of us.
-		 */
-		if (count & RWSEM_WRITER_MASK)
-			goto wait;
-
-		rwsem_mark_wake(sem, (count & RWSEM_READER_MASK)
-					? RWSEM_WAKE_READERS
-					: RWSEM_WAKE_ANY, &wake_q);
-
+		rwsem_cond_wake_waiter(sem, atomic_long_read(&sem->count),
+				       &wake_q);
 		if (!wake_q_empty(&wake_q)) {
 			/*
 			 * We want to minimize wait_lock hold time especially
@@ -1105,7 +1102,6 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 		atomic_long_or(RWSEM_FLAG_WAITERS, &sem->count);
 	}
 
-wait:
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
 	for (;;) {
-- 
cgit v1.2.3


From 1ee326196c66583006b0c95356a4b7dc51bf3531 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 22 Mar 2022 11:20:59 -0400
Subject: locking/rwsem: Always try to wake waiters in out_nolock path

For writers, the out_nolock path will always attempt to wake up waiters.
This may not be really necessary if the waiter to be removed is not the
first one.

For readers, no attempt to wake up waiter is being made. However, if
the HANDOFF bit is set and the reader to be removed is the first waiter,
the waiter behind it will inherit the HANDOFF bit and for a write lock
waiter waking it up will allow it to spin on the lock to acquire it
faster. So it can be beneficial to do a wakeup in this case.

Add a new rwsem_del_wake_waiter() helper function to do that consistently
for both reader and writer out_nolock paths.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220322152059.2182333-4-longman@redhat.com
---
 kernel/locking/rwsem.c | 44 ++++++++++++++++++++++++++++++++++----------
 1 file changed, 34 insertions(+), 10 deletions(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 03cb97a8e4cd..16b532bb5b92 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -375,16 +375,19 @@ rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
  *
  * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of
  * this function. Modify with care.
+ *
+ * Return: true if wait_list isn't empty and false otherwise
  */
-static inline void
+static inline bool
 rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
 {
 	lockdep_assert_held(&sem->wait_lock);
 	list_del(&waiter->list);
 	if (likely(!list_empty(&sem->wait_list)))
-		return;
+		return true;
 
 	atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count);
+	return false;
 }
 
 /*
@@ -558,6 +561,33 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 	}
 }
 
+/*
+ * Remove a waiter and try to wake up other waiters in the wait queue
+ * This function is called from the out_nolock path of both the reader and
+ * writer slowpaths with wait_lock held. It releases the wait_lock and
+ * optionally wake up waiters before it returns.
+ */
+static inline void
+rwsem_del_wake_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter,
+		      struct wake_q_head *wake_q)
+		      __releases(&sem->wait_lock)
+{
+	bool first = rwsem_first_waiter(sem) == waiter;
+
+	wake_q_init(wake_q);
+
+	/*
+	 * If the wait_list isn't empty and the waiter to be deleted is
+	 * the first waiter, we wake up the remaining waiters as they may
+	 * be eligible to acquire or spin on the lock.
+	 */
+	if (rwsem_del_waiter(sem, waiter) && first)
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, wake_q);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	if (!wake_q_empty(wake_q))
+		wake_up_q(wake_q);
+}
+
 /*
  * This function must be called with the sem->wait_lock held to prevent
  * race conditions between checking the rwsem wait list and setting the
@@ -1050,8 +1080,7 @@ queue:
 	return sem;
 
 out_nolock:
-	rwsem_del_waiter(sem, &waiter);
-	raw_spin_unlock_irq(&sem->wait_lock);
+	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock_fail);
 	return ERR_PTR(-EINTR);
@@ -1095,7 +1124,6 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 			 */
 			raw_spin_unlock_irq(&sem->wait_lock);
 			wake_up_q(&wake_q);
-			wake_q_init(&wake_q);	/* Used again, reinit */
 			raw_spin_lock_irq(&sem->wait_lock);
 		}
 	} else {
@@ -1148,11 +1176,7 @@ trylock_again:
 out_nolock:
 	__set_current_state(TASK_RUNNING);
 	raw_spin_lock_irq(&sem->wait_lock);
-	rwsem_del_waiter(sem, &waiter);
-	if (!list_empty(&sem->wait_list))
-		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
+	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
 	lockevent_inc(rwsem_wlock_fail);
 	return ERR_PTR(-EINTR);
 }
-- 
cgit v1.2.3


From 16edd9b511a13e7760ed4b92ba4e39bacda5c86f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 22 Mar 2022 11:57:08 -0700
Subject: locking: Add lock contention tracepoints

This adds two new lock contention tracepoints like below:

 * lock:contention_begin
 * lock:contention_end

The lock:contention_begin takes a flags argument to classify locks.  I
found it useful to identify what kind of locks it's tracing like if
it's spinning or sleeping, reader-writer lock, real-time, and per-cpu.

Move tracepoint definitions into mutex.c so that we can use them
without lockdep.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Link: https://lkml.kernel.org/r/20220322185709.141236-2-namhyung@kernel.org
---
 include/trace/events/lock.h | 61 ++++++++++++++++++++++++++++++++++++++++++---
 kernel/locking/lockdep.c    |  1 -
 kernel/locking/mutex.c      |  3 +++
 3 files changed, 61 insertions(+), 4 deletions(-)

(limited to 'kernel/locking')

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index d7512129a324..b9b6e3edd518 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -5,11 +5,21 @@
 #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_LOCK_H
 
-#include <linux/lockdep.h>
+#include <linux/sched.h>
 #include <linux/tracepoint.h>
 
+/* flags for lock:contention_begin */
+#define LCB_F_SPIN	(1U << 0)
+#define LCB_F_READ	(1U << 1)
+#define LCB_F_WRITE	(1U << 2)
+#define LCB_F_RT	(1U << 3)
+#define LCB_F_PERCPU	(1U << 4)
+
+
 #ifdef CONFIG_LOCKDEP
 
+#include <linux/lockdep.h>
+
 TRACE_EVENT(lock_acquire,
 
 	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
@@ -78,8 +88,53 @@ DEFINE_EVENT(lock, lock_acquired,
 	TP_ARGS(lock, ip)
 );
 
-#endif
-#endif
+#endif /* CONFIG_LOCK_STAT */
+#endif /* CONFIG_LOCKDEP */
+
+TRACE_EVENT(contention_begin,
+
+	TP_PROTO(void *lock, unsigned int flags),
+
+	TP_ARGS(lock, flags),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->flags = flags;
+	),
+
+	TP_printk("%p (flags=%s)", __entry->lock_addr,
+		  __print_flags(__entry->flags, "|",
+				{ LCB_F_SPIN,		"SPIN" },
+				{ LCB_F_READ,		"READ" },
+				{ LCB_F_WRITE,		"WRITE" },
+				{ LCB_F_RT,		"RT" },
+				{ LCB_F_PERCPU,		"PERCPU" }
+			  ))
+);
+
+TRACE_EVENT(contention_end,
+
+	TP_PROTO(void *lock, int ret),
+
+	TP_ARGS(lock, ret),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->ret = ret;
+	),
+
+	TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret)
+);
 
 #endif /* _TRACE_LOCK_H */
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 3cbd49216174..a6e671b8608d 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -60,7 +60,6 @@
 
 #include "lockdep_internals.h"
 
-#define CREATE_TRACE_POINTS
 #include <trace/events/lock.h>
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 5e3585950ec8..ee2fd7614a93 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -30,6 +30,9 @@
 #include <linux/debug_locks.h>
 #include <linux/osq_lock.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/lock.h>
+
 #ifndef CONFIG_PREEMPT_RT
 #include "mutex.h"
 
-- 
cgit v1.2.3


From ee042be16cb455116d0fe99b77c6bc8baf87c8c6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 22 Mar 2022 11:57:09 -0700
Subject: locking: Apply contention tracepoints in the slow path

Adding the lock contention tracepoints in various lock function slow
paths.  Note that each arch can define spinlock differently, I only
added it only to the generic qspinlock for now.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Link: https://lkml.kernel.org/r/20220322185709.141236-3-namhyung@kernel.org
---
 kernel/locking/mutex.c        |  3 +++
 kernel/locking/percpu-rwsem.c |  5 +++++
 kernel/locking/qrwlock.c      |  9 +++++++++
 kernel/locking/qspinlock.c    |  5 +++++
 kernel/locking/rtmutex.c      | 11 +++++++++++
 kernel/locking/rwbase_rt.c    |  7 +++++++
 kernel/locking/rwsem.c        |  9 +++++++++
 kernel/locking/semaphore.c    | 15 ++++++++++++++-
 8 files changed, 63 insertions(+), 1 deletion(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index ee2fd7614a93..c88deda77cf2 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -644,6 +644,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 
 	set_current_state(state);
+	trace_contention_begin(lock, 0);
 	for (;;) {
 		bool first;
 
@@ -710,6 +711,7 @@ acquired:
 skip_wait:
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
+	trace_contention_end(lock, 0);
 
 	if (ww_ctx)
 		ww_mutex_lock_acquired(ww, ww_ctx);
@@ -721,6 +723,7 @@ skip_wait:
 err:
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
+	trace_contention_end(lock, ret);
 err_early_kill:
 	raw_spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index c9fdae94e098..5fe4c5495ba3 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -9,6 +9,7 @@
 #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)
@@ -171,9 +172,11 @@ bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 	if (try)
 		return false;
 
+	trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_READ);
 	preempt_enable();
 	percpu_rwsem_wait(sem, /* .reader = */ true);
 	preempt_disable();
+	trace_contention_end(sem, 0);
 
 	return true;
 }
@@ -216,6 +219,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
+	trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE);
 
 	/* Notify readers to take the slow path. */
 	rcu_sync_enter(&sem->rss);
@@ -237,6 +241,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 
 	/* Wait for all active readers to complete. */
 	rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE);
+	trace_contention_end(sem, 0);
 }
 EXPORT_SYMBOL_GPL(percpu_down_write);
 
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index ec36b73f4733..7f42e52a648f 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -12,6 +12,7 @@
 #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 queue rwlock
@@ -34,6 +35,8 @@ void queued_read_lock_slowpath(struct qrwlock *lock)
 	}
 	atomic_sub(_QR_BIAS, &lock->cnts);
 
+	trace_contention_begin(lock, LCB_F_SPIN | LCB_F_READ);
+
 	/*
 	 * Put the reader into the wait queue
 	 */
@@ -51,6 +54,8 @@ void queued_read_lock_slowpath(struct qrwlock *lock)
 	 * 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);
 
@@ -62,6 +67,8 @@ void 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);
 
@@ -79,5 +86,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
 	} 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);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index cbff6ba53d56..65a9a10caa6f 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -22,6 +22,7 @@
 #include <linux/prefetch.h>
 #include <asm/byteorder.h>
 #include <asm/qspinlock.h>
+#include <trace/events/lock.h>
 
 /*
  * Include queued spinlock statistics code
@@ -401,6 +402,8 @@ pv_queue:
 	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
@@ -554,6 +557,8 @@ locked:
 	pv_kick_node(lock, next);
 
 release:
+	trace_contention_end(lock, 0);
+
 	/*
 	 * release the node
 	 */
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 8555c4efe97c..7779ee8abc2a 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -24,6 +24,8 @@
 #include <linux/sched/wake_q.h>
 #include <linux/ww_mutex.h>
 
+#include <trace/events/lock.h>
+
 #include "rtmutex_common.h"
 
 #ifndef WW_RT
@@ -1579,6 +1581,8 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 
 	set_current_state(state);
 
+	trace_contention_begin(lock, LCB_F_RT);
+
 	ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk);
 	if (likely(!ret))
 		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter);
@@ -1601,6 +1605,9 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 	 * unconditionally. We might have to fix that up.
 	 */
 	fixup_rt_mutex_waiters(lock);
+
+	trace_contention_end(lock, ret);
+
 	return ret;
 }
 
@@ -1683,6 +1690,8 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock)
 	/* Save current state and set state to TASK_RTLOCK_WAIT */
 	current_save_and_set_rtlock_wait_state();
 
+	trace_contention_begin(lock, LCB_F_RT);
+
 	task_blocks_on_rt_mutex(lock, &waiter, current, NULL, RT_MUTEX_MIN_CHAINWALK);
 
 	for (;;) {
@@ -1712,6 +1721,8 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock)
 	 */
 	fixup_rt_mutex_waiters(lock);
 	debug_rt_mutex_free_waiter(&waiter);
+
+	trace_contention_end(lock, 0);
 }
 
 static __always_inline void __sched rtlock_slowlock(struct rt_mutex_base *lock)
diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c
index 6fd3162e4098..c201aadb9301 100644
--- a/kernel/locking/rwbase_rt.c
+++ b/kernel/locking/rwbase_rt.c
@@ -112,6 +112,8 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb,
 	 * 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.
@@ -130,6 +132,8 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb,
 	raw_spin_unlock_irq(&rtm->wait_lock);
 	if (!ret)
 		rwbase_rtmutex_unlock(rtm);
+
+	trace_contention_end(rwb, ret);
 	return ret;
 }
 
@@ -247,11 +251,13 @@ static int __sched rwbase_write_lock(struct rwbase_rt *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);
+			trace_contention_end(rwb, -EINTR);
 			return -EINTR;
 		}
 
@@ -265,6 +271,7 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
 		set_current_state(state);
 	}
 	rwbase_restore_current_state();
+	trace_contention_end(rwb, 0);
 
 out_unlock:
 	raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 16b532bb5b92..9d1db4a54d34 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -27,6 +27,7 @@
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <trace/events/lock.h>
 
 #ifndef CONFIG_PREEMPT_RT
 #include "lock_events.h"
@@ -1056,6 +1057,8 @@ queue:
 	if (!wake_q_empty(&wake_q))
 		wake_up_q(&wake_q);
 
+	trace_contention_begin(sem, LCB_F_READ);
+
 	/* wait to be given the lock */
 	for (;;) {
 		set_current_state(state);
@@ -1077,12 +1080,14 @@ queue:
 
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock);
+	trace_contention_end(sem, 0);
 	return sem;
 
 out_nolock:
 	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock_fail);
+	trace_contention_end(sem, -EINTR);
 	return ERR_PTR(-EINTR);
 }
 
@@ -1132,6 +1137,8 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
+	trace_contention_begin(sem, LCB_F_WRITE);
+
 	for (;;) {
 		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
@@ -1171,6 +1178,7 @@ trylock_again:
 	__set_current_state(TASK_RUNNING);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
+	trace_contention_end(sem, 0);
 	return sem;
 
 out_nolock:
@@ -1178,6 +1186,7 @@ out_nolock:
 	raw_spin_lock_irq(&sem->wait_lock);
 	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
 	lockevent_inc(rwsem_wlock_fail);
+	trace_contention_end(sem, -EINTR);
 	return ERR_PTR(-EINTR);
 }
 
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 9ee381e4d2a4..f2654d2fe43a 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -32,6 +32,7 @@
 #include <linux/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>
+#include <trace/events/lock.h>
 
 static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
@@ -205,7 +206,7 @@ struct semaphore_waiter {
  * 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,
+static inline int __sched ___down_common(struct semaphore *sem, long state,
 								long timeout)
 {
 	struct semaphore_waiter waiter;
@@ -236,6 +237,18 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
 	return -EINTR;
 }
 
+static inline int __sched __down_common(struct semaphore *sem, long state,
+					long timeout)
+{
+	int ret;
+
+	trace_contention_begin(sem, 0);
+	ret = ___down_common(sem, state, timeout);
+	trace_contention_end(sem, ret);
+
+	return ret;
+}
+
 static noinline void __sched __down(struct semaphore *sem)
 {
 	__down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-- 
cgit v1.2.3


From dc1f7893a70fe403983bd8492f177bf993940e2c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 30 Mar 2022 13:06:54 +0200
Subject: locking/mutex: Make contention tracepoints more consistent wrt
 adaptive spinning

Have the trace_contention_*() tracepoints consistently include
adaptive spinning. In order to differentiate between the spinning and
non-spinning states add LCB_F_MUTEX and combine with LCB_F_SPIN.

The consequence is that a mutex contention can now triggler multiple
_begin() tracepoints before triggering an _end().

Additionally, this fixes one path where mutex would trigger _end()
without ever seeing a _begin().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/trace/events/lock.h |  4 +++-
 kernel/locking/mutex.c      | 16 ++++++++++++----
 2 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'kernel/locking')

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index b9b6e3edd518..9ebd081e057e 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -14,6 +14,7 @@
 #define LCB_F_WRITE	(1U << 2)
 #define LCB_F_RT	(1U << 3)
 #define LCB_F_PERCPU	(1U << 4)
+#define LCB_F_MUTEX	(1U << 5)
 
 
 #ifdef CONFIG_LOCKDEP
@@ -113,7 +114,8 @@ TRACE_EVENT(contention_begin,
 				{ LCB_F_READ,		"READ" },
 				{ LCB_F_WRITE,		"WRITE" },
 				{ LCB_F_RT,		"RT" },
-				{ LCB_F_PERCPU,		"PERCPU" }
+				{ LCB_F_PERCPU,		"PERCPU" },
+				{ LCB_F_MUTEX,		"MUTEX" }
 			  ))
 );
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index c88deda77cf2..d973fe6041bf 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -602,12 +602,14 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
+	trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
 	if (__mutex_trylock(lock) ||
 	    mutex_optimistic_spin(lock, ww_ctx, NULL)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
 		if (ww_ctx)
 			ww_mutex_set_context_fastpath(ww, ww_ctx);
+		trace_contention_end(lock, 0);
 		preempt_enable();
 		return 0;
 	}
@@ -644,7 +646,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 
 	set_current_state(state);
-	trace_contention_begin(lock, 0);
+	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
 		bool first;
 
@@ -684,10 +686,16 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		 * state back to RUNNING and fall through the next schedule(),
 		 * or we must see its unlock and acquire.
 		 */
-		if (__mutex_trylock_or_handoff(lock, first) ||
-		    (first && mutex_optimistic_spin(lock, ww_ctx, &waiter)))
+		if (__mutex_trylock_or_handoff(lock, first))
 			break;
 
+		if (first) {
+			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
+				break;
+			trace_contention_begin(lock, LCB_F_MUTEX);
+		}
+
 		raw_spin_lock(&lock->wait_lock);
 	}
 	raw_spin_lock(&lock->wait_lock);
@@ -723,8 +731,8 @@ skip_wait:
 err:
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
-	trace_contention_end(lock, ret);
 err_early_kill:
+	trace_contention_end(lock, ret);
 	raw_spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, ip);
-- 
cgit v1.2.3


From f79c9b8ae8bde10126586c1bb55b5fd027276d8e Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Fri, 18 Feb 2022 18:58:57 +0800
Subject: kernel/lockdep: move lockdep sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the prove_locking and lock_stat sysctls
to its own file, kernel/lockdep.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/lockdep.h  |  4 ----
 kernel/locking/lockdep.c | 35 +++++++++++++++++++++++++++++++++--
 kernel/sysctl.c          | 21 ---------------------
 3 files changed, 33 insertions(+), 27 deletions(-)

(limited to 'kernel/locking')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 467b94257105..37951c17908e 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -16,10 +16,6 @@
 
 struct task_struct;
 
-/* for sysctl */
-extern int prove_locking;
-extern int lock_stat;
-
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c06cab6546ed..a4382ae1be59 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -64,19 +64,50 @@
 #include <trace/events/lock.h>
 
 #ifdef CONFIG_PROVE_LOCKING
-int prove_locking = 1;
+static int prove_locking = 1;
 module_param(prove_locking, int, 0644);
 #else
 #define prove_locking 0
 #endif
 
 #ifdef CONFIG_LOCK_STAT
-int lock_stat = 1;
+static int lock_stat = 1;
 module_param(lock_stat, int, 0644);
 #else
 #define lock_stat 0
 #endif
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_lockdep_table[] = {
+#ifdef CONFIG_PROVE_LOCKING
+	{
+		.procname       = "prove_locking",
+		.data           = &prove_locking,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif /* CONFIG_PROVE_LOCKING */
+#ifdef CONFIG_LOCK_STAT
+	{
+		.procname       = "lock_stat",
+		.data           = &lock_stat,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif /* CONFIG_LOCK_STAT */
+	{ }
+};
+
+static __init int kernel_lockdep_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_lockdep_table);
+	return 0;
+}
+late_initcall(kernel_lockdep_sysctls_init);
+#endif /* CONFIG_SYSCTL */
+
 DEFINE_PER_CPU(unsigned int, lockdep_recursion);
 EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 36bfe1c92d44..95380d250c8c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -88,9 +88,6 @@
 #ifdef CONFIG_RT_MUTEXES
 #include <linux/rtmutex.h>
 #endif
-#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT)
-#include <linux/lockdep.h>
-#endif
 
 #if defined(CONFIG_SYSCTL)
 
@@ -1679,24 +1676,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-#ifdef CONFIG_PROVE_LOCKING
-	{
-		.procname	= "prove_locking",
-		.data		= &prove_locking,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
-#ifdef CONFIG_LOCK_STAT
-	{
-		.procname	= "lock_stat",
-		.data		= &lock_stat,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 	{
 		.procname	= "panic",
 		.data		= &panic_timeout,
-- 
cgit v1.2.3


From 434e09e7575b02e014931bc5672289fabd7a825c Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 10 May 2022 15:21:33 -0400
Subject: locking/qrwlock: Change "queue rwlock" to "queued rwlock"

Queued rwlock was originally named "queue rwlock" which wasn't quite
grammatically correct. However there are still some "queue rwlock"
references in the code. Change those to "queued rwlock" for consistency.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220510192134.434753-1-longman@redhat.com
---
 include/asm-generic/qrwlock.h       | 28 ++++++++++++++--------------
 include/asm-generic/qrwlock_types.h |  2 +-
 kernel/locking/qrwlock.c            |  8 ++++----
 3 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'kernel/locking')

diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 7ae0ece07b4e..d4cd4cc4389c 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -33,8 +33,8 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock);
 extern void queued_write_lock_slowpath(struct qrwlock *lock);
 
 /**
- * queued_read_trylock - try to acquire read lock of a queue rwlock
- * @lock : Pointer to queue rwlock structure
+ * queued_read_trylock - try to acquire read lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
  * Return: 1 if lock acquired, 0 if failed
  */
 static inline int queued_read_trylock(struct qrwlock *lock)
@@ -52,8 +52,8 @@ static inline int queued_read_trylock(struct qrwlock *lock)
 }
 
 /**
- * queued_write_trylock - try to acquire write lock of a queue rwlock
- * @lock : Pointer to queue rwlock structure
+ * queued_write_trylock - try to acquire write lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
  * Return: 1 if lock acquired, 0 if failed
  */
 static inline int queued_write_trylock(struct qrwlock *lock)
@@ -68,8 +68,8 @@ static inline int queued_write_trylock(struct qrwlock *lock)
 				_QW_LOCKED));
 }
 /**
- * queued_read_lock - acquire read lock of a queue rwlock
- * @lock: Pointer to queue rwlock structure
+ * queued_read_lock - acquire read lock of a queued rwlock
+ * @lock: Pointer to queued rwlock structure
  */
 static inline void queued_read_lock(struct qrwlock *lock)
 {
@@ -84,8 +84,8 @@ static inline void queued_read_lock(struct qrwlock *lock)
 }
 
 /**
- * queued_write_lock - acquire write lock of a queue rwlock
- * @lock : Pointer to queue rwlock structure
+ * queued_write_lock - acquire write lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
  */
 static inline void queued_write_lock(struct qrwlock *lock)
 {
@@ -98,8 +98,8 @@ static inline void queued_write_lock(struct qrwlock *lock)
 }
 
 /**
- * queued_read_unlock - release read lock of a queue rwlock
- * @lock : Pointer to queue rwlock structure
+ * queued_read_unlock - release read lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
  */
 static inline void queued_read_unlock(struct qrwlock *lock)
 {
@@ -110,8 +110,8 @@ static inline void queued_read_unlock(struct qrwlock *lock)
 }
 
 /**
- * queued_write_unlock - release write lock of a queue rwlock
- * @lock : Pointer to queue rwlock structure
+ * queued_write_unlock - release write lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
@@ -120,7 +120,7 @@ static inline void queued_write_unlock(struct qrwlock *lock)
 
 /**
  * queued_rwlock_is_contended - check if the lock is contended
- * @lock : Pointer to queue rwlock structure
+ * @lock : Pointer to queued rwlock structure
  * Return: 1 if lock contended, 0 otherwise
  */
 static inline int queued_rwlock_is_contended(struct qrwlock *lock)
@@ -130,7 +130,7 @@ static inline int queued_rwlock_is_contended(struct qrwlock *lock)
 
 /*
  * Remapping rwlock architecture specific functions to the corresponding
- * queue rwlock functions.
+ * queued rwlock functions.
  */
 #define arch_read_lock(l)		queued_read_lock(l)
 #define arch_write_lock(l)		queued_write_lock(l)
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
index c36f1d5a2572..12392c14c4d0 100644
--- a/include/asm-generic/qrwlock_types.h
+++ b/include/asm-generic/qrwlock_types.h
@@ -7,7 +7,7 @@
 #include <asm/spinlock_types.h>
 
 /*
- * The queue read/write lock data structure
+ * The queued read/write lock data structure
  */
 
 typedef struct qrwlock {
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 7f42e52a648f..2e1600906c9f 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -15,8 +15,8 @@
 #include <trace/events/lock.h>
 
 /**
- * queued_read_lock_slowpath - acquire read lock of a queue rwlock
- * @lock: Pointer to queue rwlock structure
+ * queued_read_lock_slowpath - acquire read lock of a queued rwlock
+ * @lock: Pointer to queued rwlock structure
  */
 void queued_read_lock_slowpath(struct qrwlock *lock)
 {
@@ -60,8 +60,8 @@ void queued_read_lock_slowpath(struct qrwlock *lock)
 EXPORT_SYMBOL(queued_read_lock_slowpath);
 
 /**
- * queued_write_lock_slowpath - acquire write lock of a queue rwlock
- * @lock : Pointer to queue rwlock structure
+ * queued_write_lock_slowpath - acquire write lock of a queued rwlock
+ * @lock : Pointer to queued rwlock structure
  */
 void queued_write_lock_slowpath(struct qrwlock *lock)
 {
-- 
cgit v1.2.3


From 4051a81774d6d8e28192742c26999d6f29bc0e68 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 17 May 2022 11:16:14 +0200
Subject: locking/lockdep: Use sched_clock() for random numbers

Since the rewrote of prandom_u32(), in the commit mentioned below, the
function uses sleeping locks which extracing random numbers and filling
the batch.
This breaks lockdep on PREEMPT_RT because lock_pin_lock() disables
interrupts while calling __lock_pin_lock(). This can't be moved earlier
because the main user of the function (rq_pin_lock()) invokes that
function after disabling interrupts in order to acquire the lock.

The cookie does not require random numbers as its goal is to provide a
random value in order to notice unexpected "unlock + lock" sites.

Use sched_clock() to provide random numbers.

Fixes: a0103f4d86f88 ("random32: use real rng for non-deterministic randomness")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/YoNn3pTkm5+QzE5k@linutronix.de
---
 kernel/locking/lockdep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/locking')

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 81e87280513e..f06b91ca6482 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -5432,7 +5432,7 @@ static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock)
 			 * be guessable and still allows some pin nesting in
 			 * our u32 pin_count.
 			 */
-			cookie.val = 1 + (prandom_u32() >> 16);
+			cookie.val = 1 + (sched_clock() & 0xffff);
 			hlock->pin_count += cookie.val;
 			return cookie;
 		}
-- 
cgit v1.2.3