diff --git a/Documentation/core-api/cleanup.rst b/Documentation/core-api/cleanup.rst
new file mode 100644
index 0000000..527eb2f
--- /dev/null
+++ b/Documentation/core-api/cleanup.rst
@@ -0,0 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+Scope-based Cleanup Helpers
+===========================
+
+.. kernel-doc:: include/linux/cleanup.h
+   :doc: scope-based cleanup helpers
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index e18a2ff..a331d2c 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -35,6 +35,7 @@
 
    kobject
    kref
+   cleanup
    assoc_array
    xarray
    maple_tree
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 8db2ec4..1f650b4 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -163,20 +163,18 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
 
-static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
 			       ASM_NO_INPUT_CLOBBER("memory"));
-	return i;
 }
 
-static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
 			       ASM_NO_INPUT_CLOBBER("memory"));
-	return i;
 }
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 90afb48..b2eff07 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -16,6 +16,11 @@
 	cmpxchg8b (\reg)
 .endm
 
+.macro read64_nonatomic reg
+	movl (\reg), %eax
+	movl 4(\reg), %edx
+.endm
+
 SYM_FUNC_START(atomic64_read_cx8)
 	read64 %ecx
 	RET
@@ -51,7 +56,7 @@
 	movl %edx, %edi
 	movl %ecx, %ebp
 
-	read64 %ecx
+	read64_nonatomic %ecx
 1:
 	movl %eax, %ebx
 	movl %edx, %ecx
@@ -79,7 +84,7 @@
 SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	pushl %ebx
 
-	read64 %esi
+	read64_nonatomic %esi
 1:
 	movl %eax, %ebx
 	movl %edx, %ecx
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index a3d3e88..038b2d5 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -4,6 +4,142 @@
 
 #include <linux/compiler.h>
 
+/**
+ * DOC: scope-based cleanup helpers
+ *
+ * The "goto error" pattern is notorious for introducing subtle resource
+ * leaks. It is tedious and error prone to add new resource acquisition
+ * constraints into code paths that already have several unwind
+ * conditions. The "cleanup" helpers enable the compiler to help with
+ * this tedium and can aid in maintaining LIFO (last in first out)
+ * unwind ordering to avoid unintentional leaks.
+ *
+ * As drivers make up the majority of the kernel code base, here is an
+ * example of using these helpers to clean up PCI drivers. The target of
+ * the cleanups are occasions where a goto is used to unwind a device
+ * reference (pci_dev_put()), or unlock the device (pci_dev_unlock())
+ * before returning.
+ *
+ * The DEFINE_FREE() macro can arrange for PCI device references to be
+ * dropped when the associated variable goes out of scope::
+ *
+ *	DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
+ *	...
+ *	struct pci_dev *dev __free(pci_dev_put) =
+ *		pci_get_slot(parent, PCI_DEVFN(0, 0));
+ *
+ * The above will automatically call pci_dev_put() if @dev is non-NULL
+ * when @dev goes out of scope (automatic variable scope). If a function
+ * wants to invoke pci_dev_put() on error, but return @dev (i.e. without
+ * freeing it) on success, it can do::
+ *
+ *	return no_free_ptr(dev);
+ *
+ * ...or::
+ *
+ *	return_ptr(dev);
+ *
+ * The DEFINE_GUARD() macro can arrange for the PCI device lock to be
+ * dropped when the scope where guard() is invoked ends::
+ *
+ *	DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T))
+ *	...
+ *	guard(pci_dev)(dev);
+ *
+ * The lifetime of the lock obtained by the guard() helper follows the
+ * scope of automatic variable declaration. Take the following example::
+ *
+ *	func(...)
+ *	{
+ *		if (...) {
+ *			...
+ *			guard(pci_dev)(dev); // pci_dev_lock() invoked here
+ *			...
+ *		} // <- implied pci_dev_unlock() triggered here
+ *	}
+ *
+ * Observe the lock is held for the remainder of the "if ()" block not
+ * the remainder of "func()".
+ *
+ * Now, when a function uses both __free() and guard(), or multiple
+ * instances of __free(), the LIFO order of variable definition order
+ * matters. GCC documentation says:
+ *
+ * "When multiple variables in the same scope have cleanup attributes,
+ * at exit from the scope their associated cleanup functions are run in
+ * reverse order of definition (last defined, first cleanup)."
+ *
+ * When the unwind order matters it requires that variables be defined
+ * mid-function scope rather than at the top of the file.  Take the
+ * following example and notice the bug highlighted by "!!"::
+ *
+ *	LIST_HEAD(list);
+ *	DEFINE_MUTEX(lock);
+ *
+ *	struct object {
+ *	        struct list_head node;
+ *	};
+ *
+ *	static struct object *alloc_add(void)
+ *	{
+ *	        struct object *obj;
+ *
+ *	        lockdep_assert_held(&lock);
+ *	        obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+ *	        if (obj) {
+ *	                LIST_HEAD_INIT(&obj->node);
+ *	                list_add(obj->node, &list):
+ *	        }
+ *	        return obj;
+ *	}
+ *
+ *	static void remove_free(struct object *obj)
+ *	{
+ *	        lockdep_assert_held(&lock);
+ *	        list_del(&obj->node);
+ *	        kfree(obj);
+ *	}
+ *
+ *	DEFINE_FREE(remove_free, struct object *, if (_T) remove_free(_T))
+ *	static int init(void)
+ *	{
+ *	        struct object *obj __free(remove_free) = NULL;
+ *	        int err;
+ *
+ *	        guard(mutex)(&lock);
+ *	        obj = alloc_add();
+ *
+ *	        if (!obj)
+ *	                return -ENOMEM;
+ *
+ *	        err = other_init(obj);
+ *	        if (err)
+ *	                return err; // remove_free() called without the lock!!
+ *
+ *	        no_free_ptr(obj);
+ *	        return 0;
+ *	}
+ *
+ * That bug is fixed by changing init() to call guard() and define +
+ * initialize @obj in this order::
+ *
+ *	guard(mutex)(&lock);
+ *	struct object *obj __free(remove_free) = alloc_add();
+ *
+ * Given that the "__free(...) = NULL" pattern for variables defined at
+ * the top of the function poses this potential interdependency problem
+ * the recommendation is to always define and assign variables in one
+ * statement and not group variable definitions at the top of the
+ * function when __free() is used.
+ *
+ * Lastly, given that the benefit of cleanup helpers is removal of
+ * "goto", and that the "goto" statement can jump between scopes, the
+ * expectation is that usage of "goto" and cleanup helpers is never
+ * mixed in the same function. I.e. for a given routine, convert all
+ * resources that need a "goto" cleanup to scope-based cleanup, or
+ * convert none of them.
+ */
+
 /*
  * DEFINE_FREE(name, type, free):
  *	simple helper macro that defines the required wrapper for a __free()
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 6dc76b5..93a822d 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -168,7 +168,7 @@ bool static_key_slow_inc_cpuslocked(struct static_key *key)
 		jump_label_update(key);
 		/*
 		 * Ensure that when static_key_fast_inc_not_disabled() or
-		 * static_key_slow_try_dec() observe the positive value,
+		 * static_key_dec_not_one() observe the positive value,
 		 * they must also observe all the text changes.
 		 */
 		atomic_set_release(&key->enabled, 1);
@@ -250,7 +250,7 @@ void static_key_disable(struct static_key *key)
 }
 EXPORT_SYMBOL_GPL(static_key_disable);
 
-static bool static_key_slow_try_dec(struct static_key *key)
+static bool static_key_dec_not_one(struct static_key *key)
 {
 	int v;
 
@@ -274,6 +274,14 @@ static bool static_key_slow_try_dec(struct static_key *key)
 		 * enabled. This suggests an ordering problem on the user side.
 		 */
 		WARN_ON_ONCE(v < 0);
+
+		/*
+		 * Warn about underflow, and lie about success in an attempt to
+		 * not make things worse.
+		 */
+		if (WARN_ON_ONCE(v == 0))
+			return true;
+
 		if (v <= 1)
 			return false;
 	} while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1)));
@@ -284,15 +292,27 @@ static bool static_key_slow_try_dec(struct static_key *key)
 static void __static_key_slow_dec_cpuslocked(struct static_key *key)
 {
 	lockdep_assert_cpus_held();
+	int val;
 
-	if (static_key_slow_try_dec(key))
+	if (static_key_dec_not_one(key))
 		return;
 
 	guard(mutex)(&jump_label_mutex);
-	if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
+	val = atomic_read(&key->enabled);
+	/*
+	 * It should be impossible to observe -1 with jump_label_mutex held,
+	 * see static_key_slow_inc_cpuslocked().
+	 */
+	if (WARN_ON_ONCE(val == -1))
+		return;
+	/*
+	 * Cannot already be 0, something went sideways.
+	 */
+	if (WARN_ON_ONCE(val == 0))
+		return;
+
+	if (atomic_dec_and_test(&key->enabled))
 		jump_label_update(key);
-	else
-		WARN_ON_ONCE(!static_key_slow_try_dec(key));
 }
 
 static void __static_key_slow_dec(struct static_key *key)
@@ -329,7 +349,7 @@ void __static_key_slow_dec_deferred(struct static_key *key,
 {
 	STATIC_KEY_CHECK_USE(key);
 
-	if (static_key_slow_try_dec(key))
+	if (static_key_dec_not_one(key))
 		return;
 
 	schedule_delayed_work(work, timeout);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 7963dea..536bd47 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -788,7 +788,7 @@ static void lockdep_print_held_locks(struct task_struct *p)
 		printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p));
 	else
 		printk("%d lock%s held by %s/%d:\n", depth,
-		       depth > 1 ? "s" : "", p->comm, task_pid_nr(p));
+		       str_plural(depth), p->comm, task_pid_nr(p));
 	/*
 	 * It's not reliable to print a task's held locks if it's not sleeping
 	 * and it's not the current task.
@@ -2084,6 +2084,9 @@ static noinline void print_bfs_bug(int ret)
 	/*
 	 * Breadth-first-search failed, graph got corrupted?
 	 */
+	if (ret == BFS_EQUEUEFULL)
+		pr_warn("Increase LOCKDEP_CIRCULAR_QUEUE_BITS to avoid this warning:\n");
+
 	WARN(1, "lockdep bfs error:%d\n", ret);
 }
 
@@ -6263,25 +6266,27 @@ static struct pending_free *get_pending_free(void)
 static void free_zapped_rcu(struct rcu_head *cb);
 
 /*
- * Schedule an RCU callback if no RCU callback is pending. Must be called with
- * the graph lock held.
- */
-static void call_rcu_zapped(struct pending_free *pf)
+* See if we need to queue an RCU callback, must called with
+* the lockdep lock held, returns false if either we don't have
+* any pending free or the callback is already scheduled.
+* Otherwise, a call_rcu() must follow this function call.
+*/
+static bool prepare_call_rcu_zapped(struct pending_free *pf)
 {
 	WARN_ON_ONCE(inside_selftest());
 
 	if (list_empty(&pf->zapped))
-		return;
+		return false;
 
 	if (delayed_free.scheduled)
-		return;
+		return false;
 
 	delayed_free.scheduled = true;
 
 	WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf);
 	delayed_free.index ^= 1;
 
-	call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+	return true;
 }
 
 /* The caller must hold the graph lock. May be called from RCU context. */
@@ -6307,6 +6312,7 @@ static void free_zapped_rcu(struct rcu_head *ch)
 {
 	struct pending_free *pf;
 	unsigned long flags;
+	bool need_callback;
 
 	if (WARN_ON_ONCE(ch != &delayed_free.rcu_head))
 		return;
@@ -6318,14 +6324,18 @@ static void free_zapped_rcu(struct rcu_head *ch)
 	pf = delayed_free.pf + (delayed_free.index ^ 1);
 	__free_zapped_classes(pf);
 	delayed_free.scheduled = false;
-
-	/*
-	 * If there's anything on the open list, close and start a new callback.
-	 */
-	call_rcu_zapped(delayed_free.pf + delayed_free.index);
-
+	need_callback =
+		prepare_call_rcu_zapped(delayed_free.pf + delayed_free.index);
 	lockdep_unlock();
 	raw_local_irq_restore(flags);
+
+	/*
+	* If there's pending free and its callback has not been scheduled,
+	* queue an RCU callback.
+	*/
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+
 }
 
 /*
@@ -6365,6 +6375,7 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
 {
 	struct pending_free *pf;
 	unsigned long flags;
+	bool need_callback;
 
 	init_data_structures_once();
 
@@ -6372,10 +6383,11 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
 	lockdep_lock();
 	pf = get_pending_free();
 	__lockdep_free_key_range(pf, start, size);
-	call_rcu_zapped(pf);
+	need_callback = prepare_call_rcu_zapped(pf);
 	lockdep_unlock();
 	raw_local_irq_restore(flags);
-
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
 	/*
 	 * Wait for any possible iterators from look_up_lock_class() to pass
 	 * before continuing to free the memory they refer to.
@@ -6469,6 +6481,7 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock)
 	struct pending_free *pf;
 	unsigned long flags;
 	int locked;
+	bool need_callback = false;
 
 	raw_local_irq_save(flags);
 	locked = graph_lock();
@@ -6477,11 +6490,13 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock)
 
 	pf = get_pending_free();
 	__lockdep_reset_lock(pf, lock);
-	call_rcu_zapped(pf);
+	need_callback = prepare_call_rcu_zapped(pf);
 
 	graph_unlock();
 out_irq:
 	raw_local_irq_restore(flags);
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
 }
 
 /*
@@ -6525,6 +6540,7 @@ void lockdep_unregister_key(struct lock_class_key *key)
 	struct pending_free *pf;
 	unsigned long flags;
 	bool found = false;
+	bool need_callback = false;
 
 	might_sleep();
 
@@ -6545,11 +6561,14 @@ void lockdep_unregister_key(struct lock_class_key *key)
 	if (found) {
 		pf = get_pending_free();
 		__lockdep_free_key_range(pf, key, 1);
-		call_rcu_zapped(pf);
+		need_callback = prepare_call_rcu_zapped(pf);
 	}
 	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+
 	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
 	synchronize_rcu();
 }
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index e2bfb1d..6db0f43 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -424,7 +424,7 @@ static void seq_line(struct seq_file *m, char c, int offset, int length)
 	for (i = 0; i < offset; i++)
 		seq_puts(m, " ");
 	for (i = 0; i < length; i++)
-		seq_printf(m, "%c", c);
+		seq_putc(m, c);
 	seq_puts(m, "\n");
 }
 
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 5ded7df..2bbb6ec 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -181,12 +181,21 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 	__rwsem_set_reader_owned(sem, current);
 }
 
+#ifdef CONFIG_DEBUG_RWSEMS
+/*
+ * Return just the real task structure pointer of the owner
+ */
+static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+{
+	return (struct task_struct *)
+		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
+}
+
 /*
  * Return true if the rwsem is owned by a reader.
  */
 static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 {
-#ifdef CONFIG_DEBUG_RWSEMS
 	/*
 	 * Check the count to see if it is write-locked.
 	 */
@@ -194,11 +203,9 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 
 	if (count & RWSEM_WRITER_MASK)
 		return false;
-#endif
 	return rwsem_test_oflags(sem, RWSEM_READER_OWNED);
 }
 
-#ifdef CONFIG_DEBUG_RWSEMS
 /*
  * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
  * is a task pointer in owner of a reader-owned rwsem, it will be the
@@ -266,15 +273,6 @@ static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
 }
 
 /*
- * Return just the real task structure pointer of the owner
- */
-static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
-{
-	return (struct task_struct *)
-		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
-}
-
-/*
  * Return the real task structure pointer of the owner and the embedded
  * flags in the owner. pflags must be non-NULL.
  */
diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c
index 639397b..5259cda 100644
--- a/kernel/static_call_inline.c
+++ b/kernel/static_call_inline.c
@@ -411,6 +411,17 @@ static void static_call_del_module(struct module *mod)
 
 	for (site = start; site < stop; site++) {
 		key = static_call_key(site);
+
+		/*
+		 * If the key was not updated due to a memory allocation
+		 * failure in __static_call_init() then treating key::sites
+		 * as key::mods in the code below would cause random memory
+		 * access and #GP. In that case all subsequent sites have
+		 * not been touched either, so stop iterating.
+		 */
+		if (!static_call_key_has_mods(key))
+			break;
+
 		if (key == prev_key)
 			continue;
 
@@ -442,7 +453,7 @@ static int static_call_module_notify(struct notifier_block *nb,
 	case MODULE_STATE_COMING:
 		ret = static_call_add_module(mod);
 		if (ret) {
-			WARN(1, "Failed to allocate memory for static calls");
+			pr_warn("Failed to allocate memory for static calls\n");
 			static_call_del_module(mod);
 		}
 		break;