Merge tag 'locking-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking and atomics updates from Thomas Gleixner:
 "The regular pile:

   - A few improvements to the mutex code

   - Documentation updates for atomics to clarify the difference between
     cmpxchg() and try_cmpxchg() and to explain the forward progress
     expectations.

   - Simplification of the atomics fallback generator

   - The addition of arch_atomic_long*() variants and generic arch_*()
     bitops based on them.

   - Add the missing might_sleep() invocations to the down*() operations
     of semaphores.

  The PREEMPT_RT locking core:

   - Scheduler updates to support the state preserving mechanism for
     'sleeping' spin- and rwlocks on RT.

     This mechanism is carefully preserving the state of the task when
     blocking on a 'sleeping' spin- or rwlock and takes regular wake-ups
     targeted at the same task into account. The preserved or updated
     (via a regular wakeup) state is restored when the lock has been
     acquired.

   - Restructuring of the rtmutex code so it can be utilized and
     extended for the RT specific lock variants.

   - Restructuring of the ww_mutex code to allow sharing of the ww_mutex
     specific functionality for rtmutex based ww_mutexes.

   - Header file disentangling to allow substitution of the regular lock
     implementations with the PREEMPT_RT variants without creating an
     unmaintainable #ifdef mess.

   - Shared base code for the PREEMPT_RT specific rw_semaphore and
     rwlock implementations.

     Contrary to the regular rw_semaphores and rwlocks the PREEMPT_RT
     implementation is writer unfair because it is infeasible to do
     priority inheritance on multiple readers. Experience over the years
     has shown that real-time workloads are not the typical workloads
     which are sensitive to writer starvation.

     The alternative solution would be to allow only a single reader
     which has been tried and discarded as it is a major bottleneck
     especially for mmap_sem. Aside of that many of the writer
     starvation critical usage sites have been converted to a writer
     side mutex/spinlock and RCU read side protections in the past
     decade so that the issue is less prominent than it used to be.

   - The actual rtmutex based lock substitutions for PREEMPT_RT enabled
     kernels which affect mutex, ww_mutex, rw_semaphore, spinlock_t and
     rwlock_t. The spin/rw_lock*() functions disable migration across
     the critical section to preserve the existing semantics vs per-CPU
     variables.

   - Rework of the futex REQUEUE_PI mechanism to handle the case of
     early wake-ups which interleave with a re-queue operation to
     prevent the situation that a task would be blocked on both the
     rtmutex associated to the outer futex and the rtmutex based hash
     bucket spinlock.

     While this situation cannot happen on !RT enabled kernels the
     changes make the underlying concurrency problems easier to
     understand in general. As a result the difference between !RT and
     RT kernels is reduced to the handling of waiting for the critical
     section. !RT kernels simply spin-wait as before and RT kernels
     utilize rcu_wait().

   - The substitution of local_lock for PREEMPT_RT with a spinlock which
     protects the critical section while staying preemptible. The CPU
     locality is established by disabling migration.

  The underlying concepts of this code have been in use in PREEMPT_RT for
  way more than a decade. The code has been refactored several times over
  the years and this final incarnation has been optimized once again to be
  as non-intrusive as possible, i.e. the RT specific parts are mostly
  isolated.

  It has been extensively tested in the 5.14-rt patch series and it has
  been verified that !RT kernels are not affected by these changes"

* tag 'locking-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (92 commits)
  locking/rtmutex: Return success on deadlock for ww_mutex waiters
  locking/rtmutex: Prevent spurious EDEADLK return caused by ww_mutexes
  locking/rtmutex: Dequeue waiter on ww_mutex deadlock
  locking/rtmutex: Dont dereference waiter lockless
  locking/semaphore: Add might_sleep() to down_*() family
  locking/ww_mutex: Initialize waiter.ww_ctx properly
  static_call: Update API documentation
  locking/local_lock: Add PREEMPT_RT support
  locking/spinlock/rt: Prepare for RT local_lock
  locking/rtmutex: Add adaptive spinwait mechanism
  locking/rtmutex: Implement equal priority lock stealing
  preempt: Adjust PREEMPT_LOCK_OFFSET for RT
  locking/rtmutex: Prevent lockdep false positive with PI futexes
  futex: Prevent requeue_pi() lock nesting issue on RT
  futex: Simplify handle_early_requeue_pi_wakeup()
  futex: Reorder sanity checks in futex_requeue()
  futex: Clarify comment in futex_requeue()
  futex: Restructure futex_requeue()
  futex: Correct the number of requeued waiters for PI
  futex: Remove bogus condition for requeue PI
  ...

28 files changed, 2611 insertions, 1291 deletions

diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
deleted file mode 100644
index 073cf40f431b..000000000000
--- a/include/asm-generic/atomic-long.h
+++ /dev/null
@@ -1,1014 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-// Generated by scripts/atomic/gen-atomic-long.sh
-// DO NOT MODIFY THIS FILE DIRECTLY
-
-#ifndef _ASM_GENERIC_ATOMIC_LONG_H
-#define _ASM_GENERIC_ATOMIC_LONG_H
-
-#include <linux/compiler.h>
-#include <asm/types.h>
-
-#ifdef CONFIG_64BIT
-typedef atomic64_t atomic_long_t;
-#define ATOMIC_LONG_INIT(i)		ATOMIC64_INIT(i)
-#define atomic_long_cond_read_acquire	atomic64_cond_read_acquire
-#define atomic_long_cond_read_relaxed	atomic64_cond_read_relaxed
-#else
-typedef atomic_t atomic_long_t;
-#define ATOMIC_LONG_INIT(i)		ATOMIC_INIT(i)
-#define atomic_long_cond_read_acquire	atomic_cond_read_acquire
-#define atomic_long_cond_read_relaxed	atomic_cond_read_relaxed
-#endif
-
-#ifdef CONFIG_64BIT
-
-static __always_inline long
-atomic_long_read(const atomic_long_t *v)
-{
-	return atomic64_read(v);
-}
-
-static __always_inline long
-atomic_long_read_acquire(const atomic_long_t *v)
-{
-	return atomic64_read_acquire(v);
-}
-
-static __always_inline void
-atomic_long_set(atomic_long_t *v, long i)
-{
-	atomic64_set(v, i);
-}
-
-static __always_inline void
-atomic_long_set_release(atomic_long_t *v, long i)
-{
-	atomic64_set_release(v, i);
-}
-
-static __always_inline void
-atomic_long_add(long i, atomic_long_t *v)
-{
-	atomic64_add(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return(long i, atomic_long_t *v)
-{
-	return atomic64_add_return(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_add_return_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return_release(long i, atomic_long_t *v)
-{
-	return atomic64_add_return_release(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_add_return_relaxed(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_add(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_add_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_release(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_add_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_add_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_sub(long i, atomic_long_t *v)
-{
-	atomic64_sub(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return(long i, atomic_long_t *v)
-{
-	return atomic64_sub_return(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_sub_return_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return_release(long i, atomic_long_t *v)
-{
-	return atomic64_sub_return_release(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_sub_return_relaxed(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_sub(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_sub_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub_release(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_sub_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_sub_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_inc(atomic_long_t *v)
-{
-	atomic64_inc(v);
-}
-
-static __always_inline long
-atomic_long_inc_return(atomic_long_t *v)
-{
-	return atomic64_inc_return(v);
-}
-
-static __always_inline long
-atomic_long_inc_return_acquire(atomic_long_t *v)
-{
-	return atomic64_inc_return_acquire(v);
-}
-
-static __always_inline long
-atomic_long_inc_return_release(atomic_long_t *v)
-{
-	return atomic64_inc_return_release(v);
-}
-
-static __always_inline long
-atomic_long_inc_return_relaxed(atomic_long_t *v)
-{
-	return atomic64_inc_return_relaxed(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc(atomic_long_t *v)
-{
-	return atomic64_fetch_inc(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc_acquire(atomic_long_t *v)
-{
-	return atomic64_fetch_inc_acquire(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc_release(atomic_long_t *v)
-{
-	return atomic64_fetch_inc_release(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc_relaxed(atomic_long_t *v)
-{
-	return atomic64_fetch_inc_relaxed(v);
-}
-
-static __always_inline void
-atomic_long_dec(atomic_long_t *v)
-{
-	atomic64_dec(v);
-}
-
-static __always_inline long
-atomic_long_dec_return(atomic_long_t *v)
-{
-	return atomic64_dec_return(v);
-}
-
-static __always_inline long
-atomic_long_dec_return_acquire(atomic_long_t *v)
-{
-	return atomic64_dec_return_acquire(v);
-}
-
-static __always_inline long
-atomic_long_dec_return_release(atomic_long_t *v)
-{
-	return atomic64_dec_return_release(v);
-}
-
-static __always_inline long
-atomic_long_dec_return_relaxed(atomic_long_t *v)
-{
-	return atomic64_dec_return_relaxed(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec(atomic_long_t *v)
-{
-	return atomic64_fetch_dec(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec_acquire(atomic_long_t *v)
-{
-	return atomic64_fetch_dec_acquire(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec_release(atomic_long_t *v)
-{
-	return atomic64_fetch_dec_release(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec_relaxed(atomic_long_t *v)
-{
-	return atomic64_fetch_dec_relaxed(v);
-}
-
-static __always_inline void
-atomic_long_and(long i, atomic_long_t *v)
-{
-	atomic64_and(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_and(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_and_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and_release(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_and_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_and_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_andnot(long i, atomic_long_t *v)
-{
-	atomic64_andnot(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_andnot(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_andnot_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_andnot_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_andnot_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_or(long i, atomic_long_t *v)
-{
-	atomic64_or(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_or(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_or_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or_release(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_or_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_or_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_xor(long i, atomic_long_t *v)
-{
-	atomic64_xor(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_xor(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_xor_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor_release(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_xor_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
-{
-	return atomic64_fetch_xor_relaxed(i, v);
-}
-
-static __always_inline long
-atomic_long_xchg(atomic_long_t *v, long i)
-{
-	return atomic64_xchg(v, i);
-}
-
-static __always_inline long
-atomic_long_xchg_acquire(atomic_long_t *v, long i)
-{
-	return atomic64_xchg_acquire(v, i);
-}
-
-static __always_inline long
-atomic_long_xchg_release(atomic_long_t *v, long i)
-{
-	return atomic64_xchg_release(v, i);
-}
-
-static __always_inline long
-atomic_long_xchg_relaxed(atomic_long_t *v, long i)
-{
-	return atomic64_xchg_relaxed(v, i);
-}
-
-static __always_inline long
-atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
-{
-	return atomic64_cmpxchg(v, old, new);
-}
-
-static __always_inline long
-atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
-{
-	return atomic64_cmpxchg_acquire(v, old, new);
-}
-
-static __always_inline long
-atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
-{
-	return atomic64_cmpxchg_release(v, old, new);
-}
-
-static __always_inline long
-atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
-{
-	return atomic64_cmpxchg_relaxed(v, old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
-{
-	return atomic64_try_cmpxchg(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
-{
-	return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
-{
-	return atomic64_try_cmpxchg_release(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
-{
-	return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-atomic_long_sub_and_test(long i, atomic_long_t *v)
-{
-	return atomic64_sub_and_test(i, v);
-}
-
-static __always_inline bool
-atomic_long_dec_and_test(atomic_long_t *v)
-{
-	return atomic64_dec_and_test(v);
-}
-
-static __always_inline bool
-atomic_long_inc_and_test(atomic_long_t *v)
-{
-	return atomic64_inc_and_test(v);
-}
-
-static __always_inline bool
-atomic_long_add_negative(long i, atomic_long_t *v)
-{
-	return atomic64_add_negative(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
-{
-	return atomic64_fetch_add_unless(v, a, u);
-}
-
-static __always_inline bool
-atomic_long_add_unless(atomic_long_t *v, long a, long u)
-{
-	return atomic64_add_unless(v, a, u);
-}
-
-static __always_inline bool
-atomic_long_inc_not_zero(atomic_long_t *v)
-{
-	return atomic64_inc_not_zero(v);
-}
-
-static __always_inline bool
-atomic_long_inc_unless_negative(atomic_long_t *v)
-{
-	return atomic64_inc_unless_negative(v);
-}
-
-static __always_inline bool
-atomic_long_dec_unless_positive(atomic_long_t *v)
-{
-	return atomic64_dec_unless_positive(v);
-}
-
-static __always_inline long
-atomic_long_dec_if_positive(atomic_long_t *v)
-{
-	return atomic64_dec_if_positive(v);
-}
-
-#else /* CONFIG_64BIT */
-
-static __always_inline long
-atomic_long_read(const atomic_long_t *v)
-{
-	return atomic_read(v);
-}
-
-static __always_inline long
-atomic_long_read_acquire(const atomic_long_t *v)
-{
-	return atomic_read_acquire(v);
-}
-
-static __always_inline void
-atomic_long_set(atomic_long_t *v, long i)
-{
-	atomic_set(v, i);
-}
-
-static __always_inline void
-atomic_long_set_release(atomic_long_t *v, long i)
-{
-	atomic_set_release(v, i);
-}
-
-static __always_inline void
-atomic_long_add(long i, atomic_long_t *v)
-{
-	atomic_add(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return(long i, atomic_long_t *v)
-{
-	return atomic_add_return(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return_acquire(long i, atomic_long_t *v)
-{
-	return atomic_add_return_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return_release(long i, atomic_long_t *v)
-{
-	return atomic_add_return_release(i, v);
-}
-
-static __always_inline long
-atomic_long_add_return_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_add_return_relaxed(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add(long i, atomic_long_t *v)
-{
-	return atomic_fetch_add(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
-{
-	return atomic_fetch_add_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_release(long i, atomic_long_t *v)
-{
-	return atomic_fetch_add_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_fetch_add_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_sub(long i, atomic_long_t *v)
-{
-	atomic_sub(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return(long i, atomic_long_t *v)
-{
-	return atomic_sub_return(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return_acquire(long i, atomic_long_t *v)
-{
-	return atomic_sub_return_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return_release(long i, atomic_long_t *v)
-{
-	return atomic_sub_return_release(i, v);
-}
-
-static __always_inline long
-atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_sub_return_relaxed(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub(long i, atomic_long_t *v)
-{
-	return atomic_fetch_sub(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
-{
-	return atomic_fetch_sub_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub_release(long i, atomic_long_t *v)
-{
-	return atomic_fetch_sub_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_fetch_sub_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_inc(atomic_long_t *v)
-{
-	atomic_inc(v);
-}
-
-static __always_inline long
-atomic_long_inc_return(atomic_long_t *v)
-{
-	return atomic_inc_return(v);
-}
-
-static __always_inline long
-atomic_long_inc_return_acquire(atomic_long_t *v)
-{
-	return atomic_inc_return_acquire(v);
-}
-
-static __always_inline long
-atomic_long_inc_return_release(atomic_long_t *v)
-{
-	return atomic_inc_return_release(v);
-}
-
-static __always_inline long
-atomic_long_inc_return_relaxed(atomic_long_t *v)
-{
-	return atomic_inc_return_relaxed(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc(atomic_long_t *v)
-{
-	return atomic_fetch_inc(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc_acquire(atomic_long_t *v)
-{
-	return atomic_fetch_inc_acquire(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc_release(atomic_long_t *v)
-{
-	return atomic_fetch_inc_release(v);
-}
-
-static __always_inline long
-atomic_long_fetch_inc_relaxed(atomic_long_t *v)
-{
-	return atomic_fetch_inc_relaxed(v);
-}
-
-static __always_inline void
-atomic_long_dec(atomic_long_t *v)
-{
-	atomic_dec(v);
-}
-
-static __always_inline long
-atomic_long_dec_return(atomic_long_t *v)
-{
-	return atomic_dec_return(v);
-}
-
-static __always_inline long
-atomic_long_dec_return_acquire(atomic_long_t *v)
-{
-	return atomic_dec_return_acquire(v);
-}
-
-static __always_inline long
-atomic_long_dec_return_release(atomic_long_t *v)
-{
-	return atomic_dec_return_release(v);
-}
-
-static __always_inline long
-atomic_long_dec_return_relaxed(atomic_long_t *v)
-{
-	return atomic_dec_return_relaxed(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec(atomic_long_t *v)
-{
-	return atomic_fetch_dec(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec_acquire(atomic_long_t *v)
-{
-	return atomic_fetch_dec_acquire(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec_release(atomic_long_t *v)
-{
-	return atomic_fetch_dec_release(v);
-}
-
-static __always_inline long
-atomic_long_fetch_dec_relaxed(atomic_long_t *v)
-{
-	return atomic_fetch_dec_relaxed(v);
-}
-
-static __always_inline void
-atomic_long_and(long i, atomic_long_t *v)
-{
-	atomic_and(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and(long i, atomic_long_t *v)
-{
-	return atomic_fetch_and(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
-{
-	return atomic_fetch_and_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and_release(long i, atomic_long_t *v)
-{
-	return atomic_fetch_and_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_fetch_and_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_andnot(long i, atomic_long_t *v)
-{
-	atomic_andnot(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot(long i, atomic_long_t *v)
-{
-	return atomic_fetch_andnot(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
-{
-	return atomic_fetch_andnot_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
-{
-	return atomic_fetch_andnot_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_fetch_andnot_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_or(long i, atomic_long_t *v)
-{
-	atomic_or(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or(long i, atomic_long_t *v)
-{
-	return atomic_fetch_or(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
-{
-	return atomic_fetch_or_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or_release(long i, atomic_long_t *v)
-{
-	return atomic_fetch_or_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_fetch_or_relaxed(i, v);
-}
-
-static __always_inline void
-atomic_long_xor(long i, atomic_long_t *v)
-{
-	atomic_xor(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor(long i, atomic_long_t *v)
-{
-	return atomic_fetch_xor(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
-{
-	return atomic_fetch_xor_acquire(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor_release(long i, atomic_long_t *v)
-{
-	return atomic_fetch_xor_release(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
-{
-	return atomic_fetch_xor_relaxed(i, v);
-}
-
-static __always_inline long
-atomic_long_xchg(atomic_long_t *v, long i)
-{
-	return atomic_xchg(v, i);
-}
-
-static __always_inline long
-atomic_long_xchg_acquire(atomic_long_t *v, long i)
-{
-	return atomic_xchg_acquire(v, i);
-}
-
-static __always_inline long
-atomic_long_xchg_release(atomic_long_t *v, long i)
-{
-	return atomic_xchg_release(v, i);
-}
-
-static __always_inline long
-atomic_long_xchg_relaxed(atomic_long_t *v, long i)
-{
-	return atomic_xchg_relaxed(v, i);
-}
-
-static __always_inline long
-atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
-{
-	return atomic_cmpxchg(v, old, new);
-}
-
-static __always_inline long
-atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
-{
-	return atomic_cmpxchg_acquire(v, old, new);
-}
-
-static __always_inline long
-atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
-{
-	return atomic_cmpxchg_release(v, old, new);
-}
-
-static __always_inline long
-atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
-{
-	return atomic_cmpxchg_relaxed(v, old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
-{
-	return atomic_try_cmpxchg(v, (int *)old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
-{
-	return atomic_try_cmpxchg_acquire(v, (int *)old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
-{
-	return atomic_try_cmpxchg_release(v, (int *)old, new);
-}
-
-static __always_inline bool
-atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
-{
-	return atomic_try_cmpxchg_relaxed(v, (int *)old, new);
-}
-
-static __always_inline bool
-atomic_long_sub_and_test(long i, atomic_long_t *v)
-{
-	return atomic_sub_and_test(i, v);
-}
-
-static __always_inline bool
-atomic_long_dec_and_test(atomic_long_t *v)
-{
-	return atomic_dec_and_test(v);
-}
-
-static __always_inline bool
-atomic_long_inc_and_test(atomic_long_t *v)
-{
-	return atomic_inc_and_test(v);
-}
-
-static __always_inline bool
-atomic_long_add_negative(long i, atomic_long_t *v)
-{
-	return atomic_add_negative(i, v);
-}
-
-static __always_inline long
-atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
-{
-	return atomic_fetch_add_unless(v, a, u);
-}
-
-static __always_inline bool
-atomic_long_add_unless(atomic_long_t *v, long a, long u)
-{
-	return atomic_add_unless(v, a, u);
-}
-
-static __always_inline bool
-atomic_long_inc_not_zero(atomic_long_t *v)
-{
-	return atomic_inc_not_zero(v);
-}
-
-static __always_inline bool
-atomic_long_inc_unless_negative(atomic_long_t *v)
-{
-	return atomic_inc_unless_negative(v);
-}
-
-static __always_inline bool
-atomic_long_dec_unless_positive(atomic_long_t *v)
-{
-	return atomic_dec_unless_positive(v);
-}
-
-static __always_inline long
-atomic_long_dec_if_positive(atomic_long_t *v)
-{
-	return atomic_dec_if_positive(v);
-}
-
-#endif /* CONFIG_64BIT */
-#endif /* _ASM_GENERIC_ATOMIC_LONG_H */
-// a624200981f552b2c6be4f32fe44da8289f30d87
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 0e7316a86240..3096f086b5a3 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -11,25 +11,29 @@
  * See Documentation/atomic_bitops.txt for details.
  */
 
-static __always_inline void set_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void
+arch_set_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
+	arch_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static __always_inline void clear_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void
+arch_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
+	arch_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static __always_inline void change_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void
+arch_change_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
+	arch_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline int
+arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
@@ -38,11 +42,12 @@ static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 	if (READ_ONCE(*p) & mask)
 		return 1;
 
-	old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_or(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
-static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline int
+arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
@@ -51,18 +56,21 @@ static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 	if (!(READ_ONCE(*p) & mask))
 		return 0;
 
-	old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
-static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline int
+arch_test_and_change_bit(unsigned int nr, volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_xor(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
+#include <asm-generic/bitops/instrumented-atomic.h>
+
 #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 3ae021368f48..630f2f6b9595 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -7,7 +7,7 @@
 #include <asm/barrier.h>
 
 /**
- * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -15,8 +15,8 @@
  * the returned value is 0.
  * It can be used to implement bit locks.
  */
-static inline int test_and_set_bit_lock(unsigned int nr,
-					volatile unsigned long *p)
+static __always_inline int
+arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
@@ -25,26 +25,27 @@ static inline int test_and_set_bit_lock(unsigned int nr,
 	if (READ_ONCE(*p) & mask)
 		return 1;
 
-	old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
 
 /**
- * clear_bit_unlock - Clear a bit in memory, for unlock
+ * arch_clear_bit_unlock - Clear a bit in memory, for unlock
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
  * This operation is atomic and provides release barrier semantics.
  */
-static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+static __always_inline void
+arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+	arch_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
 /**
- * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * arch___clear_bit_unlock - Clear a bit in memory, for unlock
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -54,38 +55,40 @@ static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
  *
  * See for example x86's implementation.
  */
-static inline void __clear_bit_unlock(unsigned int nr,
-				      volatile unsigned long *p)
+static inline void
+arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 {
 	unsigned long old;
 
 	p += BIT_WORD(nr);
 	old = READ_ONCE(*p);
 	old &= ~BIT_MASK(nr);
-	atomic_long_set_release((atomic_long_t *)p, old);
+	arch_atomic_long_set_release((atomic_long_t *)p, old);
 }
 
 /**
- * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
- *                                     byte is negative, for unlock.
+ * arch_clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                          byte is negative, for unlock.
  * @nr: the bit to clear
  * @addr: the address to start counting from
  *
  * This is a bit of a one-trick-pony for the filemap code, which clears
  * PG_locked and tests PG_waiters,
  */
-#ifndef clear_bit_unlock_is_negative_byte
-static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
-						     volatile unsigned long *p)
+#ifndef arch_clear_bit_unlock_is_negative_byte
+static inline bool arch_clear_bit_unlock_is_negative_byte(unsigned int nr,
+							  volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
 	return !!(old & BIT(7));
 }
-#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#define arch_clear_bit_unlock_is_negative_byte arch_clear_bit_unlock_is_negative_byte
 #endif
 
+#include <asm-generic/bitops/instrumented-lock.h>
+
 #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 7e10c4b50c5d..365377fb104b 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -5,7 +5,7 @@
 #include <asm/types.h>
 
 /**
- * __set_bit - Set a bit in memory
+ * arch___set_bit - Set a bit in memory
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -13,24 +13,28 @@
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p  |= mask;
 }
+#define __set_bit arch___set_bit
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p &= ~mask;
 }
+#define __clear_bit arch___clear_bit
 
 /**
- * __change_bit - Toggle a bit in memory
+ * arch___change_bit - Toggle a bit in memory
  * @nr: the bit to change
  * @addr: the address to start counting from
  *
@@ -38,16 +42,18 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline
+void arch___change_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p ^= mask;
 }
+#define __change_bit arch___change_bit
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -55,7 +61,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline int
+arch___test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -64,9 +71,10 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 	*p = old | mask;
 	return (old & mask) != 0;
 }
+#define __test_and_set_bit arch___test_and_set_bit
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
@@ -74,7 +82,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline int
+arch___test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -83,10 +92,11 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 	*p = old & ~mask;
 	return (old & mask) != 0;
 }
+#define __test_and_clear_bit arch___test_and_clear_bit
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-					    volatile unsigned long *addr)
+static __always_inline int
+arch___test_and_change_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -95,15 +105,18 @@ static inline int __test_and_change_bit(int nr,
 	*p = old ^ mask;
 	return (old & mask) != 0;
 }
+#define __test_and_change_bit arch___test_and_change_bit
 
 /**
- * test_bit - Determine whether a bit is set
+ * arch_test_bit - Determine whether a bit is set
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline int
+arch_test_bit(int nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
+#define test_bit arch_test_bit
 
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index ed1d3ffd5b9d..8dd57c3a99e9 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -77,9 +77,8 @@
 	__ret;								\
 })
 
-#include <linux/atomic-arch-fallback.h>
-#include <asm-generic/atomic-instrumented.h>
-
-#include <asm-generic/atomic-long.h>
+#include <linux/atomic/atomic-arch-fallback.h>
+#include <linux/atomic/atomic-long.h>
+#include <linux/atomic/atomic-instrumented.h>
 
 #endif /* _LINUX_ATOMIC_H */
diff --git a/include/linux/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h
index a3dba31df01e..a3dba31df01e 100644
--- a/include/linux/atomic-arch-fallback.h
+++ b/include/linux/atomic/atomic-arch-fallback.h
diff --git a/include/asm-generic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h
index bc45af52c93b..a0f654370da3 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/linux/atomic/atomic-instrumented.h
@@ -14,8 +14,8 @@
  * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid
  * double instrumentation.
  */
-#ifndef _ASM_GENERIC_ATOMIC_INSTRUMENTED_H
-#define _ASM_GENERIC_ATOMIC_INSTRUMENTED_H
+#ifndef _LINUX_ATOMIC_INSTRUMENTED_H
+#define _LINUX_ATOMIC_INSTRUMENTED_H
 
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
@@ -1177,6 +1177,584 @@ atomic64_dec_if_positive(atomic64_t *v)
 	return arch_atomic64_dec_if_positive(v);
 }
 
+static __always_inline long
+atomic_long_read(const atomic_long_t *v)
+{
+	instrument_atomic_read(v, sizeof(*v));
+	return arch_atomic_long_read(v);
+}
+
+static __always_inline long
+atomic_long_read_acquire(const atomic_long_t *v)
+{
+	instrument_atomic_read(v, sizeof(*v));
+	return arch_atomic_long_read_acquire(v);
+}
+
+static __always_inline void
+atomic_long_set(atomic_long_t *v, long i)
+{
+	instrument_atomic_write(v, sizeof(*v));
+	arch_atomic_long_set(v, i);
+}
+
+static __always_inline void
+atomic_long_set_release(atomic_long_t *v, long i)
+{
+	instrument_atomic_write(v, sizeof(*v));
+	arch_atomic_long_set_release(v, i);
+}
+
+static __always_inline void
+atomic_long_add(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_add(i, v);
+}
+
+static __always_inline long
+atomic_long_add_return(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_return(i, v);
+}
+
+static __always_inline long
+atomic_long_add_return_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_return_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_add_return_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_return_release(i, v);
+}
+
+static __always_inline long
+atomic_long_add_return_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_return_relaxed(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_add(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_add(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_add_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_add_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_add_release(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_add_relaxed(i, v);
+}
+
+static __always_inline void
+atomic_long_sub(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_sub(i, v);
+}
+
+static __always_inline long
+atomic_long_sub_return(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_sub_return(i, v);
+}
+
+static __always_inline long
+atomic_long_sub_return_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_sub_return_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_sub_return_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_sub_return_release(i, v);
+}
+
+static __always_inline long
+atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_sub_return_relaxed(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_sub(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_sub(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_sub_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_sub_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_sub_release(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_sub_relaxed(i, v);
+}
+
+static __always_inline void
+atomic_long_inc(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_inc(v);
+}
+
+static __always_inline long
+atomic_long_inc_return(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_return(v);
+}
+
+static __always_inline long
+atomic_long_inc_return_acquire(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_return_acquire(v);
+}
+
+static __always_inline long
+atomic_long_inc_return_release(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_return_release(v);
+}
+
+static __always_inline long
+atomic_long_inc_return_relaxed(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_return_relaxed(v);
+}
+
+static __always_inline long
+atomic_long_fetch_inc(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_inc(v);
+}
+
+static __always_inline long
+atomic_long_fetch_inc_acquire(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_inc_acquire(v);
+}
+
+static __always_inline long
+atomic_long_fetch_inc_release(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_inc_release(v);
+}
+
+static __always_inline long
+atomic_long_fetch_inc_relaxed(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_inc_relaxed(v);
+}
+
+static __always_inline void
+atomic_long_dec(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_dec(v);
+}
+
+static __always_inline long
+atomic_long_dec_return(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_return(v);
+}
+
+static __always_inline long
+atomic_long_dec_return_acquire(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_return_acquire(v);
+}
+
+static __always_inline long
+atomic_long_dec_return_release(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_return_release(v);
+}
+
+static __always_inline long
+atomic_long_dec_return_relaxed(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_return_relaxed(v);
+}
+
+static __always_inline long
+atomic_long_fetch_dec(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_dec(v);
+}
+
+static __always_inline long
+atomic_long_fetch_dec_acquire(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_dec_acquire(v);
+}
+
+static __always_inline long
+atomic_long_fetch_dec_release(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_dec_release(v);
+}
+
+static __always_inline long
+atomic_long_fetch_dec_relaxed(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_dec_relaxed(v);
+}
+
+static __always_inline void
+atomic_long_and(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_and(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_and(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_and(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_and_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_and_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_and_release(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_and_relaxed(i, v);
+}
+
+static __always_inline void
+atomic_long_andnot(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_andnot(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_andnot(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_andnot(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_andnot_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_andnot_release(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_andnot_relaxed(i, v);
+}
+
+static __always_inline void
+atomic_long_or(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_or(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_or(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_or(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_or_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_or_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_or_release(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_or_relaxed(i, v);
+}
+
+static __always_inline void
+atomic_long_xor(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	arch_atomic_long_xor(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_xor(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_xor(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_xor_acquire(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_xor_release(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_xor_release(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_xor_relaxed(i, v);
+}
+
+static __always_inline long
+atomic_long_xchg(atomic_long_t *v, long i)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_xchg(v, i);
+}
+
+static __always_inline long
+atomic_long_xchg_acquire(atomic_long_t *v, long i)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_xchg_acquire(v, i);
+}
+
+static __always_inline long
+atomic_long_xchg_release(atomic_long_t *v, long i)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_xchg_release(v, i);
+}
+
+static __always_inline long
+atomic_long_xchg_relaxed(atomic_long_t *v, long i)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_xchg_relaxed(v, i);
+}
+
+static __always_inline long
+atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_cmpxchg(v, old, new);
+}
+
+static __always_inline long
+atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_cmpxchg_acquire(v, old, new);
+}
+
+static __always_inline long
+atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_cmpxchg_release(v, old, new);
+}
+
+static __always_inline long
+atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_cmpxchg_relaxed(v, old, new);
+}
+
+static __always_inline bool
+atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
+	return arch_atomic_long_try_cmpxchg(v, old, new);
+}
+
+static __always_inline bool
+atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
+	return arch_atomic_long_try_cmpxchg_acquire(v, old, new);
+}
+
+static __always_inline bool
+atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
+	return arch_atomic_long_try_cmpxchg_release(v, old, new);
+}
+
+static __always_inline bool
+atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
+	return arch_atomic_long_try_cmpxchg_relaxed(v, old, new);
+}
+
+static __always_inline bool
+atomic_long_sub_and_test(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_sub_and_test(i, v);
+}
+
+static __always_inline bool
+atomic_long_dec_and_test(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_and_test(v);
+}
+
+static __always_inline bool
+atomic_long_inc_and_test(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_and_test(v);
+}
+
+static __always_inline bool
+atomic_long_add_negative(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_negative(i, v);
+}
+
+static __always_inline long
+atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_fetch_add_unless(v, a, u);
+}
+
+static __always_inline bool
+atomic_long_add_unless(atomic_long_t *v, long a, long u)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_unless(v, a, u);
+}
+
+static __always_inline bool
+atomic_long_inc_not_zero(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_not_zero(v);
+}
+
+static __always_inline bool
+atomic_long_inc_unless_negative(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_inc_unless_negative(v);
+}
+
+static __always_inline bool
+atomic_long_dec_unless_positive(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_unless_positive(v);
+}
+
+static __always_inline long
+atomic_long_dec_if_positive(atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_dec_if_positive(v);
+}
+
 #define xchg(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
@@ -1333,5 +1911,5 @@ atomic64_dec_if_positive(atomic64_t *v)
 	arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \
 })
 
-#endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */
-// 1d7c3a25aca5c7fb031c307be4c3d24c7b48fcd5
+#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
+// 2a9553f0a9d5619f19151092df5cabbbf16ce835
diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h
new file mode 100644
index 000000000000..800b8c35992d
--- /dev/null
+++ b/include/linux/atomic/atomic-long.h
@@ -0,0 +1,1014 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Generated by scripts/atomic/gen-atomic-long.sh
+// DO NOT MODIFY THIS FILE DIRECTLY
+
+#ifndef _LINUX_ATOMIC_LONG_H
+#define _LINUX_ATOMIC_LONG_H
+
+#include <linux/compiler.h>
+#include <asm/types.h>
+
+#ifdef CONFIG_64BIT
+typedef atomic64_t atomic_long_t;
+#define ATOMIC_LONG_INIT(i)		ATOMIC64_INIT(i)
+#define atomic_long_cond_read_acquire	atomic64_cond_read_acquire
+#define atomic_long_cond_read_relaxed	atomic64_cond_read_relaxed
+#else
+typedef atomic_t atomic_long_t;
+#define ATOMIC_LONG_INIT(i)		ATOMIC_INIT(i)
+#define atomic_long_cond_read_acquire	atomic_cond_read_acquire
+#define atomic_long_cond_read_relaxed	atomic_cond_read_relaxed
+#endif
+
+#ifdef CONFIG_64BIT
+
+static __always_inline long
+arch_atomic_long_read(const atomic_long_t *v)
+{
+	return arch_atomic64_read(v);
+}
+
+static __always_inline long
+arch_atomic_long_read_acquire(const atomic_long_t *v)
+{
+	return arch_atomic64_read_acquire(v);
+}
+
+static __always_inline void
+arch_atomic_long_set(atomic_long_t *v, long i)
+{
+	arch_atomic64_set(v, i);
+}
+
+static __always_inline void
+arch_atomic_long_set_release(atomic_long_t *v, long i)
+{
+	arch_atomic64_set_release(v, i);
+}
+
+static __always_inline void
+arch_atomic_long_add(long i, atomic_long_t *v)
+{
+	arch_atomic64_add(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_return(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_return_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_return_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_return_relaxed(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_add(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_add_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_add_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_add_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_sub(long i, atomic_long_t *v)
+{
+	arch_atomic64_sub(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return(long i, atomic_long_t *v)
+{
+	return arch_atomic64_sub_return(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_sub_return_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_sub_return_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_sub_return_relaxed(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_sub(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_sub_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_sub_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_sub_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_inc(atomic_long_t *v)
+{
+	arch_atomic64_inc(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return(atomic_long_t *v)
+{
+	return arch_atomic64_inc_return(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return_acquire(atomic_long_t *v)
+{
+	return arch_atomic64_inc_return_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return_release(atomic_long_t *v)
+{
+	return arch_atomic64_inc_return_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return_relaxed(atomic_long_t *v)
+{
+	return arch_atomic64_inc_return_relaxed(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_inc(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc_acquire(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_inc_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc_release(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_inc_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_inc_relaxed(v);
+}
+
+static __always_inline void
+arch_atomic_long_dec(atomic_long_t *v)
+{
+	arch_atomic64_dec(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return(atomic_long_t *v)
+{
+	return arch_atomic64_dec_return(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return_acquire(atomic_long_t *v)
+{
+	return arch_atomic64_dec_return_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return_release(atomic_long_t *v)
+{
+	return arch_atomic64_dec_return_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return_relaxed(atomic_long_t *v)
+{
+	return arch_atomic64_dec_return_relaxed(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_dec(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec_acquire(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_dec_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec_release(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_dec_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v)
+{
+	return arch_atomic64_fetch_dec_relaxed(v);
+}
+
+static __always_inline void
+arch_atomic_long_and(long i, atomic_long_t *v)
+{
+	arch_atomic64_and(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_and(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_and_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_and_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_and_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_andnot(long i, atomic_long_t *v)
+{
+	arch_atomic64_andnot(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_andnot(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_andnot_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_andnot_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_andnot_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_or(long i, atomic_long_t *v)
+{
+	arch_atomic64_or(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_or(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_or_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_or_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_or_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_xor(long i, atomic_long_t *v)
+{
+	arch_atomic64_xor(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_xor(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_xor_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_xor_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_fetch_xor_relaxed(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_xchg(atomic_long_t *v, long i)
+{
+	return arch_atomic64_xchg(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_xchg_acquire(atomic_long_t *v, long i)
+{
+	return arch_atomic64_xchg_acquire(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_xchg_release(atomic_long_t *v, long i)
+{
+	return arch_atomic64_xchg_release(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i)
+{
+	return arch_atomic64_xchg_relaxed(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic64_cmpxchg(v, old, new);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic64_cmpxchg_acquire(v, old, new);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic64_cmpxchg_release(v, old, new);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic64_cmpxchg_relaxed(v, old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic64_try_cmpxchg(v, (s64 *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic64_try_cmpxchg_release(v, (s64 *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_sub_and_test(long i, atomic_long_t *v)
+{
+	return arch_atomic64_sub_and_test(i, v);
+}
+
+static __always_inline bool
+arch_atomic_long_dec_and_test(atomic_long_t *v)
+{
+	return arch_atomic64_dec_and_test(v);
+}
+
+static __always_inline bool
+arch_atomic_long_inc_and_test(atomic_long_t *v)
+{
+	return arch_atomic64_inc_and_test(v);
+}
+
+static __always_inline bool
+arch_atomic_long_add_negative(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_negative(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
+{
+	return arch_atomic64_fetch_add_unless(v, a, u);
+}
+
+static __always_inline bool
+arch_atomic_long_add_unless(atomic_long_t *v, long a, long u)
+{
+	return arch_atomic64_add_unless(v, a, u);
+}
+
+static __always_inline bool
+arch_atomic_long_inc_not_zero(atomic_long_t *v)
+{
+	return arch_atomic64_inc_not_zero(v);
+}
+
+static __always_inline bool
+arch_atomic_long_inc_unless_negative(atomic_long_t *v)
+{
+	return arch_atomic64_inc_unless_negative(v);
+}
+
+static __always_inline bool
+arch_atomic_long_dec_unless_positive(atomic_long_t *v)
+{
+	return arch_atomic64_dec_unless_positive(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_if_positive(atomic_long_t *v)
+{
+	return arch_atomic64_dec_if_positive(v);
+}
+
+#else /* CONFIG_64BIT */
+
+static __always_inline long
+arch_atomic_long_read(const atomic_long_t *v)
+{
+	return arch_atomic_read(v);
+}
+
+static __always_inline long
+arch_atomic_long_read_acquire(const atomic_long_t *v)
+{
+	return arch_atomic_read_acquire(v);
+}
+
+static __always_inline void
+arch_atomic_long_set(atomic_long_t *v, long i)
+{
+	arch_atomic_set(v, i);
+}
+
+static __always_inline void
+arch_atomic_long_set_release(atomic_long_t *v, long i)
+{
+	arch_atomic_set_release(v, i);
+}
+
+static __always_inline void
+arch_atomic_long_add(long i, atomic_long_t *v)
+{
+	arch_atomic_add(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_return(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_return_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_return_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_return_relaxed(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_add(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_add_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_add_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_add_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_sub(long i, atomic_long_t *v)
+{
+	arch_atomic_sub(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return(long i, atomic_long_t *v)
+{
+	return arch_atomic_sub_return(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_sub_return_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_sub_return_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_sub_return_relaxed(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_sub(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_sub_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_sub_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_sub_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_inc(atomic_long_t *v)
+{
+	arch_atomic_inc(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return(atomic_long_t *v)
+{
+	return arch_atomic_inc_return(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return_acquire(atomic_long_t *v)
+{
+	return arch_atomic_inc_return_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return_release(atomic_long_t *v)
+{
+	return arch_atomic_inc_return_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_inc_return_relaxed(atomic_long_t *v)
+{
+	return arch_atomic_inc_return_relaxed(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc(atomic_long_t *v)
+{
+	return arch_atomic_fetch_inc(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc_acquire(atomic_long_t *v)
+{
+	return arch_atomic_fetch_inc_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc_release(atomic_long_t *v)
+{
+	return arch_atomic_fetch_inc_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v)
+{
+	return arch_atomic_fetch_inc_relaxed(v);
+}
+
+static __always_inline void
+arch_atomic_long_dec(atomic_long_t *v)
+{
+	arch_atomic_dec(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return(atomic_long_t *v)
+{
+	return arch_atomic_dec_return(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return_acquire(atomic_long_t *v)
+{
+	return arch_atomic_dec_return_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return_release(atomic_long_t *v)
+{
+	return arch_atomic_dec_return_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_return_relaxed(atomic_long_t *v)
+{
+	return arch_atomic_dec_return_relaxed(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec(atomic_long_t *v)
+{
+	return arch_atomic_fetch_dec(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec_acquire(atomic_long_t *v)
+{
+	return arch_atomic_fetch_dec_acquire(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec_release(atomic_long_t *v)
+{
+	return arch_atomic_fetch_dec_release(v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v)
+{
+	return arch_atomic_fetch_dec_relaxed(v);
+}
+
+static __always_inline void
+arch_atomic_long_and(long i, atomic_long_t *v)
+{
+	arch_atomic_and(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_and(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_and_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_and_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_and_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_andnot(long i, atomic_long_t *v)
+{
+	arch_atomic_andnot(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_andnot(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_andnot_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_andnot_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_andnot_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_or(long i, atomic_long_t *v)
+{
+	arch_atomic_or(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_or(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_or_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_or_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_or_relaxed(i, v);
+}
+
+static __always_inline void
+arch_atomic_long_xor(long i, atomic_long_t *v)
+{
+	arch_atomic_xor(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_xor(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_xor_acquire(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_xor_release(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_fetch_xor_relaxed(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_xchg(atomic_long_t *v, long i)
+{
+	return arch_atomic_xchg(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_xchg_acquire(atomic_long_t *v, long i)
+{
+	return arch_atomic_xchg_acquire(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_xchg_release(atomic_long_t *v, long i)
+{
+	return arch_atomic_xchg_release(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i)
+{
+	return arch_atomic_xchg_relaxed(v, i);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic_cmpxchg(v, old, new);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic_cmpxchg_acquire(v, old, new);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic_cmpxchg_release(v, old, new);
+}
+
+static __always_inline long
+arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
+{
+	return arch_atomic_cmpxchg_relaxed(v, old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic_try_cmpxchg(v, (int *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic_try_cmpxchg_acquire(v, (int *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic_try_cmpxchg_release(v, (int *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
+{
+	return arch_atomic_try_cmpxchg_relaxed(v, (int *)old, new);
+}
+
+static __always_inline bool
+arch_atomic_long_sub_and_test(long i, atomic_long_t *v)
+{
+	return arch_atomic_sub_and_test(i, v);
+}
+
+static __always_inline bool
+arch_atomic_long_dec_and_test(atomic_long_t *v)
+{
+	return arch_atomic_dec_and_test(v);
+}
+
+static __always_inline bool
+arch_atomic_long_inc_and_test(atomic_long_t *v)
+{
+	return arch_atomic_inc_and_test(v);
+}
+
+static __always_inline bool
+arch_atomic_long_add_negative(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_negative(i, v);
+}
+
+static __always_inline long
+arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
+{
+	return arch_atomic_fetch_add_unless(v, a, u);
+}
+
+static __always_inline bool
+arch_atomic_long_add_unless(atomic_long_t *v, long a, long u)
+{
+	return arch_atomic_add_unless(v, a, u);
+}
+
+static __always_inline bool
+arch_atomic_long_inc_not_zero(atomic_long_t *v)
+{
+	return arch_atomic_inc_not_zero(v);
+}
+
+static __always_inline bool
+arch_atomic_long_inc_unless_negative(atomic_long_t *v)
+{
+	return arch_atomic_inc_unless_negative(v);
+}
+
+static __always_inline bool
+arch_atomic_long_dec_unless_positive(atomic_long_t *v)
+{
+	return arch_atomic_dec_unless_positive(v);
+}
+
+static __always_inline long
+arch_atomic_long_dec_if_positive(atomic_long_t *v)
+{
+	return arch_atomic_dec_if_positive(v);
+}
+
+#endif /* CONFIG_64BIT */
+#endif /* _LINUX_ATOMIC_LONG_H */
+// e8f0e08ff072b74d180eabe2ad001282b38c2c88
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index edb5c186b0b7..3f49e65169c6 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -3,8 +3,7 @@
 #define __LINUX_DEBUG_LOCKING_H
 
 #include <linux/atomic.h>
-#include <linux/bug.h>
-#include <linux/printk.h>
+#include <linux/cache.h>
 
 struct task_struct;
 
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index ded90b097e6e..975e33b793a7 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -6,6 +6,8 @@
 #include <linux/percpu-defs.h>
 #include <linux/lockdep.h>
 
+#ifndef CONFIG_PREEMPT_RT
+
 typedef struct {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
@@ -14,29 +16,14 @@ typedef struct {
 } local_lock_t;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define LL_DEP_MAP_INIT(lockname)			\
+# define LOCAL_LOCK_DEBUG_INIT(lockname)		\
 	.dep_map = {					\
 		.name = #lockname,			\
 		.wait_type_inner = LD_WAIT_CONFIG,	\
-		.lock_type = LD_LOCK_PERCPU,			\
-	}
-#else
-# define LL_DEP_MAP_INIT(lockname)
-#endif
-
-#define INIT_LOCAL_LOCK(lockname)	{ LL_DEP_MAP_INIT(lockname) }
-
-#define __local_lock_init(lock)					\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
-	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \
-			      LD_WAIT_CONFIG, LD_WAIT_INV,	\
-			      LD_LOCK_PERCPU);			\
-} while (0)
+		.lock_type = LD_LOCK_PERCPU,		\
+	},						\
+	.owner = NULL,
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
 static inline void local_lock_acquire(local_lock_t *l)
 {
 	lock_map_acquire(&l->dep_map);
@@ -51,11 +38,30 @@ static inline void local_lock_release(local_lock_t *l)
 	lock_map_release(&l->dep_map);
 }
 
+static inline void local_lock_debug_init(local_lock_t *l)
+{
+	l->owner = NULL;
+}
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
+# define LOCAL_LOCK_DEBUG_INIT(lockname)
 static inline void local_lock_acquire(local_lock_t *l) { }
 static inline void local_lock_release(local_lock_t *l) { }
+static inline void local_lock_debug_init(local_lock_t *l) { }
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
+#define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }
+
+#define __local_lock_init(lock)					\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key,  \
+			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_PERCPU);			\
+	local_lock_debug_init(lock);				\
+} while (0)
+
 #define __local_lock(lock)					\
 	do {							\
 		preempt_disable();				\
@@ -91,3 +97,45 @@ static inline void local_lock_release(local_lock_t *l) { }
 		local_lock_release(this_cpu_ptr(lock));		\
 		local_irq_restore(flags);			\
 	} while (0)
+
+#else /* !CONFIG_PREEMPT_RT */
+
+/*
+ * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the
+ * critical section while staying preemptible.
+ */
+typedef spinlock_t local_lock_t;
+
+#define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
+
+#define __local_lock_init(l)					\
+	do {							\
+		local_spin_lock_init((l));			\
+	} while (0)
+
+#define __local_lock(__lock)					\
+	do {							\
+		migrate_disable();				\
+		spin_lock(this_cpu_ptr((__lock)));		\
+	} while (0)
+
+#define __local_lock_irq(lock)			__local_lock(lock)
+
+#define __local_lock_irqsave(lock, flags)			\
+	do {							\
+		typecheck(unsigned long, flags);		\
+		flags = 0;					\
+		__local_lock(lock);				\
+	} while (0)
+
+#define __local_unlock(__lock)					\
+	do {							\
+		spin_unlock(this_cpu_ptr((__lock)));		\
+		migrate_enable();				\
+	} while (0)
+
+#define __local_unlock_irq(lock)		__local_unlock(lock)
+
+#define __local_unlock_irqrestore(lock, flags)	__local_unlock(lock)
+
+#endif /* CONFIG_PREEMPT_RT */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index e19323521f9c..8f226d460f51 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -20,8 +20,17 @@
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
 
-struct ww_class;
-struct ww_acquire_ctx;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname)			\
+		, .dep_map = {					\
+			.name = #lockname,			\
+			.wait_type_inner = LD_WAIT_SLEEP,	\
+		}
+#else
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
+#endif
+
+#ifndef CONFIG_PREEMPT_RT
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -53,7 +62,7 @@ struct ww_acquire_ctx;
  */
 struct mutex {
 	atomic_long_t		owner;
-	spinlock_t		wait_lock;
+	raw_spinlock_t		wait_lock;
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
@@ -66,27 +75,6 @@ struct mutex {
 #endif
 };
 
-struct ww_mutex {
-	struct mutex base;
-	struct ww_acquire_ctx *ctx;
-#ifdef CONFIG_DEBUG_MUTEXES
-	struct ww_class *ww_class;
-#endif
-};
-
-/*
- * 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
-};
-
 #ifdef CONFIG_DEBUG_MUTEXES
 
 #define __DEBUG_MUTEX_INITIALIZER(lockname)				\
@@ -117,19 +105,9 @@ do {									\
 	__mutex_init((mutex), #mutex, &__key);				\
 } while (0)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname)			\
-		, .dep_map = {					\
-			.name = #lockname,			\
-			.wait_type_inner = LD_WAIT_SLEEP,	\
-		}
-#else
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
-#endif
-
 #define __MUTEX_INITIALIZER(lockname) \
 		{ .owner = ATOMIC_LONG_INIT(0) \
-		, .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
+		, .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
 		, .wait_list = LIST_HEAD_INIT(lockname.wait_list) \
 		__DEBUG_MUTEX_INITIALIZER(lockname) \
 		__DEP_MAP_MUTEX_INITIALIZER(lockname) }
@@ -148,6 +126,50 @@ extern void __mutex_init(struct mutex *lock, const char *name,
  */
 extern bool mutex_is_locked(struct mutex *lock);
 
+#else /* !CONFIG_PREEMPT_RT */
+/*
+ * Preempt-RT variant based on rtmutexes.
+ */
+#include <linux/rtmutex.h>
+
+struct mutex {
+	struct rt_mutex_base	rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __MUTEX_INITIALIZER(mutexname)					\
+{									\
+	.rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex)	\
+	__DEP_MAP_MUTEX_INITIALIZER(mutexname)				\
+}
+
+#define DEFINE_MUTEX(mutexname)						\
+	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
+
+extern void __mutex_rt_init(struct mutex *lock, const char *name,
+			    struct lock_class_key *key);
+extern int mutex_trylock(struct mutex *lock);
+
+static inline void mutex_destroy(struct mutex *lock) { }
+
+#define mutex_is_locked(l)	rt_mutex_base_is_locked(&(l)->rtmutex)
+
+#define __mutex_init(mutex, name, key)			\
+do {							\
+	rt_mutex_base_init(&(mutex)->rtmutex);		\
+	__mutex_rt_init((mutex), name, key);		\
+} while (0)
+
+#define mutex_init(mutex)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	__mutex_init((mutex), #mutex, &__key);		\
+} while (0)
+#endif /* CONFIG_PREEMPT_RT */
+
 /*
  * See kernel/locking/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/locking/mutex-design.rst.
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 9881eac0698f..4d244e295e85 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -121,7 +121,11 @@
 /*
  * The preempt_count offset after spin_lock()
  */
+#if !defined(CONFIG_PREEMPT_RT)
 #define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+#else
+#define PREEMPT_LOCK_OFFSET	0
+#endif
 
 /*
  * The preempt_count offset needed for things like:
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index d31ecaf4fdd3..235047d7a1b5 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -17,24 +17,14 @@
 #ifndef	_LINUX_RBTREE_H
 #define	_LINUX_RBTREE_H
 
+#include <linux/rbtree_types.h>
+
 #include <linux/kernel.h>
 #include <linux/stddef.h>
 #include <linux/rcupdate.h>
 
-struct rb_node {
-	unsigned long  __rb_parent_color;
-	struct rb_node *rb_right;
-	struct rb_node *rb_left;
-} __attribute__((aligned(sizeof(long))));
-    /* The alignment might seem pointless, but allegedly CRIS needs it */
-
-struct rb_root {
-	struct rb_node *rb_node;
-};
-
 #define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
 
-#define RB_ROOT	(struct rb_root) { NULL, }
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
 #define RB_EMPTY_ROOT(root)  (READ_ONCE((root)->rb_node) == NULL)
@@ -112,23 +102,6 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent
 			typeof(*pos), field); 1; }); \
 	     pos = n)
 
-/*
- * Leftmost-cached rbtrees.
- *
- * We do not cache the rightmost node based on footprint
- * size vs number of potential users that could benefit
- * from O(1) rb_last(). Just not worth it, users that want
- * this feature can always implement the logic explicitly.
- * Furthermore, users that want to cache both pointers may
- * find it a bit asymmetric, but that's ok.
- */
-struct rb_root_cached {
-	struct rb_root rb_root;
-	struct rb_node *rb_leftmost;
-};
-
-#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
-
 /* Same as rb_first(), but O(1) */
 #define rb_first_cached(root) (root)->rb_leftmost
 
diff --git a/include/linux/rbtree_types.h b/include/linux/rbtree_types.h
new file mode 100644
index 000000000000..45b6ecde3665
--- /dev/null
+++ b/include/linux/rbtree_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_RBTREE_TYPES_H
+#define _LINUX_RBTREE_TYPES_H
+
+struct rb_node {
+	unsigned long  __rb_parent_color;
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+/* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+	struct rb_node *rb_node;
+};
+
+/*
+ * Leftmost-cached rbtrees.
+ *
+ * We do not cache the rightmost node based on footprint
+ * size vs number of potential users that could benefit
+ * from O(1) rb_last(). Just not worth it, users that want
+ * this feature can always implement the logic explicitly.
+ * Furthermore, users that want to cache both pointers may
+ * find it a bit asymmetric, but that's ok.
+ */
+struct rb_root_cached {
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+};
+
+#define RB_ROOT (struct rb_root) { NULL, }
+#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
+
+#endif
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index d1672de9ca89..9deedfeec2b1 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -13,12 +13,39 @@
 #ifndef __LINUX_RT_MUTEX_H
 #define __LINUX_RT_MUTEX_H
 
+#include <linux/compiler.h>
 #include <linux/linkage.h>
-#include <linux/rbtree.h>
-#include <linux/spinlock_types.h>
+#include <linux/rbtree_types.h>
+#include <linux/spinlock_types_raw.h>
 
 extern int max_lock_depth; /* for sysctl */
 
+struct rt_mutex_base {
+	raw_spinlock_t		wait_lock;
+	struct rb_root_cached   waiters;
+	struct task_struct	*owner;
+};
+
+#define __RT_MUTEX_BASE_INITIALIZER(rtbasename)				\
+{									\
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(rtbasename.wait_lock),	\
+	.waiters = RB_ROOT_CACHED,					\
+	.owner = NULL							\
+}
+
+/**
+ * rt_mutex_base_is_locked - is the rtmutex locked
+ * @lock: the mutex to be queried
+ *
+ * Returns true if the mutex is locked, false if unlocked.
+ */
+static inline bool rt_mutex_base_is_locked(struct rt_mutex_base *lock)
+{
+	return READ_ONCE(lock->owner) != NULL;
+}
+
+extern void rt_mutex_base_init(struct rt_mutex_base *rtb);
+
 /**
  * The rt_mutex structure
  *
@@ -28,9 +55,7 @@ extern int max_lock_depth; /* for sysctl */
  * @owner:	the mutex owner
  */
 struct rt_mutex {
-	raw_spinlock_t		wait_lock;
-	struct rb_root_cached   waiters;
-	struct task_struct	*owner;
+	struct rt_mutex_base	rtmutex;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -52,32 +77,24 @@ do { \
 } while (0)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \
-	, .dep_map = { .name = #mutexname }
+#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)	\
+	.dep_map = {					\
+		.name = #mutexname,			\
+		.wait_type_inner = LD_WAIT_SLEEP,	\
+	}
 #else
 #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)
 #endif
 
-#define __RT_MUTEX_INITIALIZER(mutexname) \
-	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
-	, .waiters = RB_ROOT_CACHED \
-	, .owner = NULL \
-	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)}
+#define __RT_MUTEX_INITIALIZER(mutexname)				\
+{									\
+	.rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex),	\
+	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)			\
+}
 
 #define DEFINE_RT_MUTEX(mutexname) \
 	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
 
-/**
- * rt_mutex_is_locked - is the mutex locked
- * @lock: the mutex to be queried
- *
- * Returns 1 if the mutex is locked, 0 if unlocked.
- */
-static inline int rt_mutex_is_locked(struct rt_mutex *lock)
-{
-	return lock->owner != NULL;
-}
-
 extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h
new file mode 100644
index 000000000000..1d264dd08625
--- /dev/null
+++ b/include/linux/rwbase_rt.h
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef _LINUX_RWBASE_RT_H
+#define _LINUX_RWBASE_RT_H
+
+#include <linux/rtmutex.h>
+#include <linux/atomic.h>
+
+#define READER_BIAS		(1U << 31)
+#define WRITER_BIAS		(1U << 30)
+
+struct rwbase_rt {
+	atomic_t		readers;
+	struct rt_mutex_base	rtmutex;
+};
+
+#define __RWBASE_INITIALIZER(name)				\
+{								\
+	.readers = ATOMIC_INIT(READER_BIAS),			\
+	.rtmutex = __RT_MUTEX_BASE_INITIALIZER(name.rtmutex),	\
+}
+
+#define init_rwbase_rt(rwbase)					\
+	do {							\
+		rt_mutex_base_init(&(rwbase)->rtmutex);		\
+		atomic_set(&(rwbase)->readers, READER_BIAS);	\
+	} while (0)
+
+
+static __always_inline bool rw_base_is_locked(struct rwbase_rt *rwb)
+{
+	return atomic_read(&rwb->readers) != READER_BIAS;
+}
+
+static __always_inline bool rw_base_is_contended(struct rwbase_rt *rwb)
+{
+	return atomic_read(&rwb->readers) > 0;
+}
+
+#endif /* _LINUX_RWBASE_RT_H */
diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h
new file mode 100644
index 000000000000..49c1f3842ed5
--- /dev/null
+++ b/include/linux/rwlock_rt.h
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef __LINUX_RWLOCK_RT_H
+#define __LINUX_RWLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_RT_H
+#error Do not #include directly. Use <linux/spinlock.h>.
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void __rt_rwlock_init(rwlock_t *rwlock, const char *name,
+			     struct lock_class_key *key);
+#else
+static inline void __rt_rwlock_init(rwlock_t *rwlock, char *name,
+				    struct lock_class_key *key)
+{
+}
+#endif
+
+#define rwlock_init(rwl)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	init_rwbase_rt(&(rwl)->rwbase);			\
+	__rt_rwlock_init(rwl, #rwl, &__key);		\
+} while (0)
+
+extern void rt_read_lock(rwlock_t *rwlock);
+extern int rt_read_trylock(rwlock_t *rwlock);
+extern void rt_read_unlock(rwlock_t *rwlock);
+extern void rt_write_lock(rwlock_t *rwlock);
+extern int rt_write_trylock(rwlock_t *rwlock);
+extern void rt_write_unlock(rwlock_t *rwlock);
+
+static __always_inline void read_lock(rwlock_t *rwlock)
+{
+	rt_read_lock(rwlock);
+}
+
+static __always_inline void read_lock_bh(rwlock_t *rwlock)
+{
+	local_bh_disable();
+	rt_read_lock(rwlock);
+}
+
+static __always_inline void read_lock_irq(rwlock_t *rwlock)
+{
+	rt_read_lock(rwlock);
+}
+
+#define read_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		rt_read_lock(lock);			\
+		flags = 0;				\
+	} while (0)
+
+#define read_trylock(lock)	__cond_lock(lock, rt_read_trylock(lock))
+
+static __always_inline void read_unlock(rwlock_t *rwlock)
+{
+	rt_read_unlock(rwlock);
+}
+
+static __always_inline void read_unlock_bh(rwlock_t *rwlock)
+{
+	rt_read_unlock(rwlock);
+	local_bh_enable();
+}
+
+static __always_inline void read_unlock_irq(rwlock_t *rwlock)
+{
+	rt_read_unlock(rwlock);
+}
+
+static __always_inline void read_unlock_irqrestore(rwlock_t *rwlock,
+						   unsigned long flags)
+{
+	rt_read_unlock(rwlock);
+}
+
+static __always_inline void write_lock(rwlock_t *rwlock)
+{
+	rt_write_lock(rwlock);
+}
+
+static __always_inline void write_lock_bh(rwlock_t *rwlock)
+{
+	local_bh_disable();
+	rt_write_lock(rwlock);
+}
+
+static __always_inline void write_lock_irq(rwlock_t *rwlock)
+{
+	rt_write_lock(rwlock);
+}
+
+#define write_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		rt_write_lock(lock);			\
+		flags = 0;				\
+	} while (0)
+
+#define write_trylock(lock)	__cond_lock(lock, rt_write_trylock(lock))
+
+#define write_trylock_irqsave(lock, flags)		\
+({							\
+	int __locked;					\
+							\
+	typecheck(unsigned long, flags);		\
+	flags = 0;					\
+	__locked = write_trylock(lock);			\
+	__locked;					\
+})
+
+static __always_inline void write_unlock(rwlock_t *rwlock)
+{
+	rt_write_unlock(rwlock);
+}
+
+static __always_inline void write_unlock_bh(rwlock_t *rwlock)
+{
+	rt_write_unlock(rwlock);
+	local_bh_enable();
+}
+
+static __always_inline void write_unlock_irq(rwlock_t *rwlock)
+{
+	rt_write_unlock(rwlock);
+}
+
+static __always_inline void write_unlock_irqrestore(rwlock_t *rwlock,
+						    unsigned long flags)
+{
+	rt_write_unlock(rwlock);
+}
+
+#define rwlock_is_contended(lock)		(((void)(lock), 0))
+
+#endif /* __LINUX_RWLOCK_RT_H */
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index 3bd03e18061c..1948442e7750 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -1,9 +1,23 @@
 #ifndef __LINUX_RWLOCK_TYPES_H
 #define __LINUX_RWLOCK_TYPES_H
 
+#if !defined(__LINUX_SPINLOCK_TYPES_H)
+# error "Do not include directly, include spinlock_types.h"
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define RW_DEP_MAP_INIT(lockname)					\
+	.dep_map = {							\
+		.name = #lockname,					\
+		.wait_type_inner = LD_WAIT_CONFIG,			\
+	}
+#else
+# define RW_DEP_MAP_INIT(lockname)
+#endif
+
+#ifndef CONFIG_PREEMPT_RT
 /*
- * include/linux/rwlock_types.h - generic rwlock type definitions
- *				  and initializers
+ * generic rwlock type definitions and initializers
  *
  * portions Copyright 2005, Red Hat, Inc., Ingo Molnar
  * Released under the General Public License (GPL).
@@ -21,16 +35,6 @@ typedef struct {
 
 #define RWLOCK_MAGIC		0xdeaf1eed
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define RW_DEP_MAP_INIT(lockname)					\
-	.dep_map = {							\
-		.name = #lockname,					\
-		.wait_type_inner = LD_WAIT_CONFIG,			\
-	}
-#else
-# define RW_DEP_MAP_INIT(lockname)
-#endif
-
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define __RW_LOCK_UNLOCKED(lockname)					\
 	(rwlock_t)	{	.raw_lock = __ARCH_RW_LOCK_UNLOCKED,	\
@@ -46,4 +50,29 @@ typedef struct {
 
 #define DEFINE_RWLOCK(x)	rwlock_t x = __RW_LOCK_UNLOCKED(x)
 
+#else /* !CONFIG_PREEMPT_RT */
+
+#include <linux/rwbase_rt.h>
+
+typedef struct {
+	struct rwbase_rt	rwbase;
+	atomic_t		readers;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+} rwlock_t;
+
+#define __RWLOCK_RT_INITIALIZER(name)					\
+{									\
+	.rwbase = __RWBASE_INITIALIZER(name),				\
+	RW_DEP_MAP_INIT(name)						\
+}
+
+#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name)
+
+#define DEFINE_RWLOCK(name)						\
+	rwlock_t name = __RW_LOCK_UNLOCKED(name)
+
+#endif /* CONFIG_PREEMPT_RT */
+
 #endif /* __LINUX_RWLOCK_TYPES_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index a66038d88878..426e98e0b675 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -16,6 +16,19 @@
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <linux/err.h>
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname)			\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_SLEEP,	\
+	},
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+#ifndef CONFIG_PREEMPT_RT
+
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 #include <linux/osq_lock.h>
 #endif
@@ -64,16 +77,6 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 
 /* Common initializer macros and functions */
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname)			\
-	.dep_map = {					\
-		.name = #lockname,			\
-		.wait_type_inner = LD_WAIT_SLEEP,	\
-	},
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
 #ifdef CONFIG_DEBUG_RWSEMS
 # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname,
 #else
@@ -119,6 +122,61 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
 	return !list_empty(&sem->wait_list);
 }
 
+#else /* !CONFIG_PREEMPT_RT */
+
+#include <linux/rwbase_rt.h>
+
+struct rw_semaphore {
+	struct rwbase_rt	rwbase;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __RWSEM_INITIALIZER(name)				\
+	{							\
+		.rwbase = __RWBASE_INITIALIZER(name),		\
+		__RWSEM_DEP_MAP_INIT(name)			\
+	}
+
+#define DECLARE_RWSEM(lockname) \
+	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+			  struct lock_class_key *key);
+#else
+static inline void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+				 struct lock_class_key *key)
+{
+}
+#endif
+
+#define init_rwsem(sem)						\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	init_rwbase_rt(&(sem)->rwbase);			\
+	__rwsem_init((sem), #sem, &__key);			\
+} while (0)
+
+static __always_inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return rw_base_is_locked(&sem->rwbase);
+}
+
+static __always_inline int rwsem_is_contended(struct rw_semaphore *sem)
+{
+	return rw_base_is_contended(&sem->rwbase);
+}
+
+#endif /* CONFIG_PREEMPT_RT */
+
+/*
+ * The functions below are the same for all rwsem implementations including
+ * the RT specific variant.
+ */
+
 /*
  * lock for reading
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7c6a77da8b10..af7179f8572c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -95,7 +95,9 @@ struct task_group;
 #define TASK_WAKING			0x0200
 #define TASK_NOLOAD			0x0400
 #define TASK_NEW			0x0800
-#define TASK_STATE_MAX			0x1000
+/* RT specific auxilliary flag to mark RT lock waiters */
+#define TASK_RTLOCK_WAIT		0x1000
+#define TASK_STATE_MAX			0x2000
 
 /* Convenience macros for the sake of set_current_state: */
 #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
@@ -121,8 +123,6 @@ struct task_group;
 
 #define task_is_stopped_or_traced(task)	((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 
-#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-
 /*
  * Special states are those that do not use the normal wait-loop pattern. See
  * the comment with set_special_state().
@@ -130,30 +130,37 @@ struct task_group;
 #define is_special_task_state(state)				\
 	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
 
-#define __set_current_state(state_value)			\
-	do {							\
-		WARN_ON_ONCE(is_special_task_state(state_value));\
-		current->task_state_change = _THIS_IP_;		\
-		WRITE_ONCE(current->__state, (state_value));	\
-	} while (0)
-
-#define set_current_state(state_value)				\
-	do {							\
-		WARN_ON_ONCE(is_special_task_state(state_value));\
-		current->task_state_change = _THIS_IP_;		\
-		smp_store_mb(current->__state, (state_value));	\
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+# define debug_normal_state_change(state_value)				\
+	do {								\
+		WARN_ON_ONCE(is_special_task_state(state_value));	\
+		current->task_state_change = _THIS_IP_;			\
 	} while (0)
 
-#define set_special_state(state_value)					\
+# define debug_special_state_change(state_value)			\
 	do {								\
-		unsigned long flags; /* may shadow */			\
 		WARN_ON_ONCE(!is_special_task_state(state_value));	\
-		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
 		current->task_state_change = _THIS_IP_;			\
-		WRITE_ONCE(current->__state, (state_value));		\
-		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
+
+# define debug_rtlock_wait_set_state()					\
+	do {								 \
+		current->saved_state_change = current->task_state_change;\
+		current->task_state_change = _THIS_IP_;			 \
+	} while (0)
+
+# define debug_rtlock_wait_restore_state()				\
+	do {								 \
+		current->task_state_change = current->saved_state_change;\
+	} while (0)
+
 #else
+# define debug_normal_state_change(cond)	do { } while (0)
+# define debug_special_state_change(cond)	do { } while (0)
+# define debug_rtlock_wait_set_state()		do { } while (0)
+# define debug_rtlock_wait_restore_state()	do { } while (0)
+#endif
+
 /*
  * set_current_state() includes a barrier so that the write of current->state
  * is correctly serialised wrt the caller's subsequent test of whether to
@@ -192,26 +199,77 @@ struct task_group;
  * Also see the comments of try_to_wake_up().
  */
 #define __set_current_state(state_value)				\
-	WRITE_ONCE(current->__state, (state_value))
+	do {								\
+		debug_normal_state_change((state_value));		\
+		WRITE_ONCE(current->__state, (state_value));		\
+	} while (0)
 
 #define set_current_state(state_value)					\
-	smp_store_mb(current->__state, (state_value))
+	do {								\
+		debug_normal_state_change((state_value));		\
+		smp_store_mb(current->__state, (state_value));		\
+	} while (0)
 
 /*
  * set_special_state() should be used for those states when the blocking task
  * can not use the regular condition based wait-loop. In that case we must
- * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
- * will not collide with our state change.
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING
+ * stores will not collide with our state change.
  */
 #define set_special_state(state_value)					\
 	do {								\
 		unsigned long flags; /* may shadow */			\
+									\
 		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
+		debug_special_state_change((state_value));		\
 		WRITE_ONCE(current->__state, (state_value));		\
 		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
 
-#endif
+/*
+ * PREEMPT_RT specific variants for "sleeping" spin/rwlocks
+ *
+ * RT's spin/rwlock substitutions are state preserving. The state of the
+ * task when blocking on the lock is saved in task_struct::saved_state and
+ * restored after the lock has been acquired.  These operations are
+ * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT
+ * lock related wakeups while the task is blocked on the lock are
+ * redirected to operate on task_struct::saved_state to ensure that these
+ * are not dropped. On restore task_struct::saved_state is set to
+ * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail.
+ *
+ * The lock operation looks like this:
+ *
+ *	current_save_and_set_rtlock_wait_state();
+ *	for (;;) {
+ *		if (try_lock())
+ *			break;
+ *		raw_spin_unlock_irq(&lock->wait_lock);
+ *		schedule_rtlock();
+ *		raw_spin_lock_irq(&lock->wait_lock);
+ *		set_current_state(TASK_RTLOCK_WAIT);
+ *	}
+ *	current_restore_rtlock_saved_state();
+ */
+#define current_save_and_set_rtlock_wait_state()			\
+	do {								\
+		lockdep_assert_irqs_disabled();				\
+		raw_spin_lock(&current->pi_lock);			\
+		current->saved_state = current->__state;		\
+		debug_rtlock_wait_set_state();				\
+		WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT);		\
+		raw_spin_unlock(&current->pi_lock);			\
+	} while (0);
+
+#define current_restore_rtlock_saved_state()				\
+	do {								\
+		lockdep_assert_irqs_disabled();				\
+		raw_spin_lock(&current->pi_lock);			\
+		debug_rtlock_wait_restore_state();			\
+		WRITE_ONCE(current->__state, current->saved_state);	\
+		current->saved_state = TASK_RUNNING;			\
+		raw_spin_unlock(&current->pi_lock);			\
+	} while (0);
 
 #define get_current_state()	READ_ONCE(current->__state)
 
@@ -230,6 +288,9 @@ extern long schedule_timeout_idle(long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 asmlinkage void preempt_schedule_irq(void);
+#ifdef CONFIG_PREEMPT_RT
+ extern void schedule_rtlock(void);
+#endif
 
 extern int __must_check io_schedule_prepare(void);
 extern void io_schedule_finish(int token);
@@ -668,6 +729,11 @@ struct task_struct {
 #endif
 	unsigned int			__state;
 
+#ifdef CONFIG_PREEMPT_RT
+	/* saved state for "spinlock sleepers" */
+	unsigned int			saved_state;
+#endif
+
 	/*
 	 * This begins the randomizable portion of task_struct. Only
 	 * scheduling-critical items should be added above here.
@@ -1362,6 +1428,9 @@ struct task_struct {
 	struct kmap_ctrl		kmap_ctrl;
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long			task_state_change;
+# ifdef CONFIG_PREEMPT_RT
+	unsigned long			saved_state_change;
+# endif
 #endif
 	int				pagefault_disabled;
 #ifdef CONFIG_MMU
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 26a2013ac39c..06cd8fb2f409 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -42,8 +42,11 @@ struct wake_q_head {
 
 #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
 
-#define DEFINE_WAKE_Q(name)				\
-	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+#define WAKE_Q_HEAD_INITIALIZER(name)				\
+	{ WAKE_Q_TAIL, &name.first }
+
+#define DEFINE_WAKE_Q(name)					\
+	struct wake_q_head name = WAKE_Q_HEAD_INITIALIZER(name)
 
 static inline void wake_q_init(struct wake_q_head *head)
 {
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 79897841a2cc..45310ea1b1d7 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -12,6 +12,8 @@
  *  asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the
  *                        initializers
  *
+ *  linux/spinlock_types_raw:
+ *			  The raw types and initializers
  *  linux/spinlock_types.h:
  *                        defines the generic type and initializers
  *
@@ -31,6 +33,8 @@
  *                        contains the generic, simplified UP spinlock type.
  *                        (which is an empty structure on non-debug builds)
  *
+ *  linux/spinlock_types_raw:
+ *			  The raw RT types and initializers
  *  linux/spinlock_types.h:
  *                        defines the generic type and initializers
  *
@@ -308,8 +312,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 	1 : ({ local_irq_restore(flags); 0; }); \
 })
 
-/* Include rwlock functions */
+#ifndef CONFIG_PREEMPT_RT
+/* Include rwlock functions for !RT */
 #include <linux/rwlock.h>
+#endif
 
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
@@ -320,6 +326,9 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # include <linux/spinlock_api_up.h>
 #endif
 
+/* Non PREEMPT_RT kernel, map to raw spinlocks: */
+#ifndef CONFIG_PREEMPT_RT
+
 /*
  * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
  */
@@ -454,6 +463,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 
 #define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
 
+#else  /* !CONFIG_PREEMPT_RT */
+# include <linux/spinlock_rt.h>
+#endif /* CONFIG_PREEMPT_RT */
+
 /*
  * Pull the atomic_t declaration:
  * (asm-mips/atomic.h needs above definitions)
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 19a9be9d97ee..6b8e1a0b137b 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -187,6 +187,9 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
 	return 0;
 }
 
+/* PREEMPT_RT has its own rwlock implementation */
+#ifndef CONFIG_PREEMPT_RT
 #include <linux/rwlock_api_smp.h>
+#endif
 
 #endif /* __LINUX_SPINLOCK_API_SMP_H */
diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
new file mode 100644
index 000000000000..835aedaf68ac
--- /dev/null
+++ b/include/linux/spinlock_rt.h
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef __LINUX_SPINLOCK_RT_H
+#define __LINUX_SPINLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void __rt_spin_lock_init(spinlock_t *lock, const char *name,
+				struct lock_class_key *key, bool percpu);
+#else
+static inline void __rt_spin_lock_init(spinlock_t *lock, const char *name,
+				struct lock_class_key *key, bool percpu)
+{
+}
+#endif
+
+#define spin_lock_init(slock)					\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	rt_mutex_base_init(&(slock)->lock);			\
+	__rt_spin_lock_init(slock, #slock, &__key, false);	\
+} while (0)
+
+#define local_spin_lock_init(slock)				\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	rt_mutex_base_init(&(slock)->lock);			\
+	__rt_spin_lock_init(slock, #slock, &__key, true);	\
+} while (0)
+
+extern void rt_spin_lock(spinlock_t *lock);
+extern void rt_spin_lock_nested(spinlock_t *lock, int subclass);
+extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock);
+extern void rt_spin_unlock(spinlock_t *lock);
+extern void rt_spin_lock_unlock(spinlock_t *lock);
+extern int rt_spin_trylock_bh(spinlock_t *lock);
+extern int rt_spin_trylock(spinlock_t *lock);
+
+static __always_inline void spin_lock(spinlock_t *lock)
+{
+	rt_spin_lock(lock);
+}
+
+#ifdef CONFIG_LOCKDEP
+# define __spin_lock_nested(lock, subclass)				\
+	rt_spin_lock_nested(lock, subclass)
+
+# define __spin_lock_nest_lock(lock, nest_lock)				\
+	do {								\
+		typecheck(struct lockdep_map *, &(nest_lock)->dep_map);	\
+		rt_spin_lock_nest_lock(lock, &(nest_lock)->dep_map);	\
+	} while (0)
+# define __spin_lock_irqsave_nested(lock, flags, subclass)	\
+	do {							\
+		typecheck(unsigned long, flags);		\
+		flags = 0;					\
+		__spin_lock_nested(lock, subclass);		\
+	} while (0)
+
+#else
+ /*
+  * Always evaluate the 'subclass' argument to avoid that the compiler
+  * warns about set-but-not-used variables when building with
+  * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1.
+  */
+# define __spin_lock_nested(lock, subclass)	spin_lock(((void)(subclass), (lock)))
+# define __spin_lock_nest_lock(lock, subclass)	spin_lock(((void)(subclass), (lock)))
+# define __spin_lock_irqsave_nested(lock, flags, subclass)	\
+	spin_lock_irqsave(((void)(subclass), (lock)), flags)
+#endif
+
+#define spin_lock_nested(lock, subclass)		\
+	__spin_lock_nested(lock, subclass)
+
+#define spin_lock_nest_lock(lock, nest_lock)		\
+	__spin_lock_nest_lock(lock, nest_lock)
+
+#define spin_lock_irqsave_nested(lock, flags, subclass)	\
+	__spin_lock_irqsave_nested(lock, flags, subclass)
+
+static __always_inline void spin_lock_bh(spinlock_t *lock)
+{
+	/* Investigate: Drop bh when blocking ? */
+	local_bh_disable();
+	rt_spin_lock(lock);
+}
+
+static __always_inline void spin_lock_irq(spinlock_t *lock)
+{
+	rt_spin_lock(lock);
+}
+
+#define spin_lock_irqsave(lock, flags)			 \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		spin_lock(lock);			 \
+	} while (0)
+
+static __always_inline void spin_unlock(spinlock_t *lock)
+{
+	rt_spin_unlock(lock);
+}
+
+static __always_inline void spin_unlock_bh(spinlock_t *lock)
+{
+	rt_spin_unlock(lock);
+	local_bh_enable();
+}
+
+static __always_inline void spin_unlock_irq(spinlock_t *lock)
+{
+	rt_spin_unlock(lock);
+}
+
+static __always_inline void spin_unlock_irqrestore(spinlock_t *lock,
+						   unsigned long flags)
+{
+	rt_spin_unlock(lock);
+}
+
+#define spin_trylock(lock)				\
+	__cond_lock(lock, rt_spin_trylock(lock))
+
+#define spin_trylock_bh(lock)				\
+	__cond_lock(lock, rt_spin_trylock_bh(lock))
+
+#define spin_trylock_irq(lock)				\
+	__cond_lock(lock, rt_spin_trylock(lock))
+
+#define __spin_trylock_irqsave(lock, flags)		\
+({							\
+	int __locked;					\
+							\
+	typecheck(unsigned long, flags);		\
+	flags = 0;					\
+	__locked = spin_trylock(lock);			\
+	__locked;					\
+})
+
+#define spin_trylock_irqsave(lock, flags)		\
+	__cond_lock(lock, __spin_trylock_irqsave(lock, flags))
+
+#define spin_is_contended(lock)		(((void)(lock), 0))
+
+static inline int spin_is_locked(spinlock_t *lock)
+{
+	return rt_mutex_base_is_locked(&lock->lock);
+}
+
+#define assert_spin_locked(lock) BUG_ON(!spin_is_locked(lock))
+
+#include <linux/rwlock_rt.h>
+
+#endif
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index b981caafe8bf..2dfa35ffec76 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -9,65 +9,11 @@
  * Released under the General Public License (GPL).
  */
 
-#if defined(CONFIG_SMP)
-# include <asm/spinlock_types.h>
-#else
-# include <linux/spinlock_types_up.h>
-#endif
-
-#include <linux/lockdep_types.h>
+#include <linux/spinlock_types_raw.h>
 
-typedef struct raw_spinlock {
-	arch_spinlock_t raw_lock;
-#ifdef CONFIG_DEBUG_SPINLOCK
-	unsigned int magic, owner_cpu;
-	void *owner;
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-} raw_spinlock_t;
-
-#define SPINLOCK_MAGIC		0xdead4ead
-
-#define SPINLOCK_OWNER_INIT	((void *)-1L)
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define RAW_SPIN_DEP_MAP_INIT(lockname)		\
-	.dep_map = {					\
-		.name = #lockname,			\
-		.wait_type_inner = LD_WAIT_SPIN,	\
-	}
-# define SPIN_DEP_MAP_INIT(lockname)			\
-	.dep_map = {					\
-		.name = #lockname,			\
-		.wait_type_inner = LD_WAIT_CONFIG,	\
-	}
-#else
-# define RAW_SPIN_DEP_MAP_INIT(lockname)
-# define SPIN_DEP_MAP_INIT(lockname)
-#endif
-
-#ifdef CONFIG_DEBUG_SPINLOCK
-# define SPIN_DEBUG_INIT(lockname)		\
-	.magic = SPINLOCK_MAGIC,		\
-	.owner_cpu = -1,			\
-	.owner = SPINLOCK_OWNER_INIT,
-#else
-# define SPIN_DEBUG_INIT(lockname)
-#endif
-
-#define __RAW_SPIN_LOCK_INITIALIZER(lockname)	\
-	{					\
-	.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
-	SPIN_DEBUG_INIT(lockname)		\
-	RAW_SPIN_DEP_MAP_INIT(lockname) }
-
-#define __RAW_SPIN_LOCK_UNLOCKED(lockname)	\
-	(raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
-
-#define DEFINE_RAW_SPINLOCK(x)	raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
+#ifndef CONFIG_PREEMPT_RT
 
+/* Non PREEMPT_RT kernels map spinlock to raw_spinlock */
 typedef struct spinlock {
 	union {
 		struct raw_spinlock rlock;
@@ -96,6 +42,35 @@ typedef struct spinlock {
 
 #define DEFINE_SPINLOCK(x)	spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
 
+#else /* !CONFIG_PREEMPT_RT */
+
+/* PREEMPT_RT kernels map spinlock to rt_mutex */
+#include <linux/rtmutex.h>
+
+typedef struct spinlock {
+	struct rt_mutex_base	lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+} spinlock_t;
+
+#define __SPIN_LOCK_UNLOCKED(name)				\
+	{							\
+		.lock = __RT_MUTEX_BASE_INITIALIZER(name.lock),	\
+		SPIN_DEP_MAP_INIT(name)				\
+	}
+
+#define __LOCAL_SPIN_LOCK_UNLOCKED(name)			\
+	{							\
+		.lock = __RT_MUTEX_BASE_INITIALIZER(name.lock),	\
+		LOCAL_SPIN_DEP_MAP_INIT(name)			\
+	}
+
+#define DEFINE_SPINLOCK(name)					\
+	spinlock_t name = __SPIN_LOCK_UNLOCKED(name)
+
+#endif /* CONFIG_PREEMPT_RT */
+
 #include <linux/rwlock_types.h>
 
 #endif /* __LINUX_SPINLOCK_TYPES_H */
diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h
new file mode 100644
index 000000000000..91cb36b65a17
--- /dev/null
+++ b/include/linux/spinlock_types_raw.h
@@ -0,0 +1,73 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
+#define __LINUX_SPINLOCK_TYPES_RAW_H
+
+#include <linux/types.h>
+
+#if defined(CONFIG_SMP)
+# include <asm/spinlock_types.h>
+#else
+# include <linux/spinlock_types_up.h>
+#endif
+
+#include <linux/lockdep_types.h>
+
+typedef struct raw_spinlock {
+	arch_spinlock_t raw_lock;
+#ifdef CONFIG_DEBUG_SPINLOCK
+	unsigned int magic, owner_cpu;
+	void *owner;
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+} raw_spinlock_t;
+
+#define SPINLOCK_MAGIC		0xdead4ead
+
+#define SPINLOCK_OWNER_INIT	((void *)-1L)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define RAW_SPIN_DEP_MAP_INIT(lockname)		\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_SPIN,	\
+	}
+# define SPIN_DEP_MAP_INIT(lockname)			\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_CONFIG,	\
+	}
+
+# define LOCAL_SPIN_DEP_MAP_INIT(lockname)		\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_CONFIG,	\
+		.lock_type = LD_LOCK_PERCPU,		\
+	}
+#else
+# define RAW_SPIN_DEP_MAP_INIT(lockname)
+# define SPIN_DEP_MAP_INIT(lockname)
+# define LOCAL_SPIN_DEP_MAP_INIT(lockname)
+#endif
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+# define SPIN_DEBUG_INIT(lockname)		\
+	.magic = SPINLOCK_MAGIC,		\
+	.owner_cpu = -1,			\
+	.owner = SPINLOCK_OWNER_INIT,
+#else
+# define SPIN_DEBUG_INIT(lockname)
+#endif
+
+#define __RAW_SPIN_LOCK_INITIALIZER(lockname)	\
+{						\
+	.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
+	SPIN_DEBUG_INIT(lockname)		\
+	RAW_SPIN_DEP_MAP_INIT(lockname) }
+
+#define __RAW_SPIN_LOCK_UNLOCKED(lockname)	\
+	(raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
+
+#define DEFINE_RAW_SPINLOCK(x)  raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
+
+#endif /* __LINUX_SPINLOCK_TYPES_RAW_H */
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index fc94faa53b5b..3e56a9751c06 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -17,11 +17,17 @@
  *   DECLARE_STATIC_CALL(name, func);
  *   DEFINE_STATIC_CALL(name, func);
  *   DEFINE_STATIC_CALL_NULL(name, typename);
+ *   DEFINE_STATIC_CALL_RET0(name, typename);
+ *
+ *   __static_call_return0;
+ *
  *   static_call(name)(args...);
  *   static_call_cond(name)(args...);
  *   static_call_update(name, func);
  *   static_call_query(name);
  *
+ *   EXPORT_STATIC_CALL{,_TRAMP}{,_GPL}()
+ *
  * Usage example:
  *
  *   # Start with the following functions (with identical prototypes):
@@ -96,6 +102,33 @@
  *   To query which function is currently set to be called, use:
  *
  *   func = static_call_query(name);
+ *
+ *
+ * DEFINE_STATIC_CALL_RET0 / __static_call_return0:
+ *
+ *   Just like how DEFINE_STATIC_CALL_NULL() / static_call_cond() optimize the
+ *   conditional void function call, DEFINE_STATIC_CALL_RET0 /
+ *   __static_call_return0 optimize the do nothing return 0 function.
+ *
+ *   This feature is strictly UB per the C standard (since it casts a function
+ *   pointer to a different signature) and relies on the architecture ABI to
+ *   make things work. In particular it relies on Caller Stack-cleanup and the
+ *   whole return register being clobbered for short return values. All normal
+ *   CDECL style ABIs conform.
+ *
+ *   In particular the x86_64 implementation replaces the 5 byte CALL
+ *   instruction at the callsite with a 5 byte clear of the RAX register,
+ *   completely eliding any function call overhead.
+ *
+ *   Notably argument setup is unconditional.
+ *
+ *
+ * EXPORT_STATIC_CALL() vs EXPORT_STATIC_CALL_TRAMP():
+ *
+ *   The difference is that the _TRAMP variant tries to only export the
+ *   trampoline with the result that a module can use static_call{,_cond}() but
+ *   not static_call_update().
+ *
  */
 
 #include <linux/types.h>
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index b77f39f319ad..29db736af86d 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -18,6 +18,24 @@
 #define __LINUX_WW_MUTEX_H
 
 #include <linux/mutex.h>
+#include <linux/rtmutex.h>
+
+#if defined(CONFIG_DEBUG_MUTEXES) || \
+   (defined(CONFIG_PREEMPT_RT) && defined(CONFIG_DEBUG_RT_MUTEXES))
+#define DEBUG_WW_MUTEXES
+#endif
+
+#ifndef CONFIG_PREEMPT_RT
+#define WW_MUTEX_BASE			mutex
+#define ww_mutex_base_init(l,n,k)	__mutex_init(l,n,k)
+#define ww_mutex_base_trylock(l)	mutex_trylock(l)
+#define ww_mutex_base_is_locked(b)	mutex_is_locked((b))
+#else
+#define WW_MUTEX_BASE			rt_mutex
+#define ww_mutex_base_init(l,n,k)	__rt_mutex_init(l,n,k)
+#define ww_mutex_base_trylock(l)	rt_mutex_trylock(l)
+#define ww_mutex_base_is_locked(b)	rt_mutex_base_is_locked(&(b)->rtmutex)
+#endif
 
 struct ww_class {
 	atomic_long_t stamp;
@@ -28,16 +46,24 @@ struct ww_class {
 	unsigned int is_wait_die;
 };
 
+struct ww_mutex {
+	struct WW_MUTEX_BASE base;
+	struct ww_acquire_ctx *ctx;
+#ifdef DEBUG_WW_MUTEXES
+	struct ww_class *ww_class;
+#endif
+};
+
 struct ww_acquire_ctx {
 	struct task_struct *task;
 	unsigned long stamp;
 	unsigned int acquired;
 	unsigned short wounded;
 	unsigned short is_wait_die;
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	unsigned int done_acquire;
 	struct ww_class *ww_class;
-	struct ww_mutex *contending_lock;
+	void *contending_lock;
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
@@ -74,9 +100,9 @@ struct ww_acquire_ctx {
 static inline void ww_mutex_init(struct ww_mutex *lock,
 				 struct ww_class *ww_class)
 {
-	__mutex_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key);
+	ww_mutex_base_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key);
 	lock->ctx = NULL;
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	lock->ww_class = ww_class;
 #endif
 }
@@ -113,7 +139,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
 	ctx->acquired = 0;
 	ctx->wounded = false;
 	ctx->is_wait_die = ww_class->is_wait_die;
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	ctx->ww_class = ww_class;
 	ctx->done_acquire = 0;
 	ctx->contending_lock = NULL;
@@ -143,7 +169,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
  */
 static inline void ww_acquire_done(struct ww_acquire_ctx *ctx)
 {
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	lockdep_assert_held(ctx);
 
 	DEBUG_LOCKS_WARN_ON(ctx->done_acquire);
@@ -163,7 +189,7 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	mutex_release(&ctx->dep_map, _THIS_IP_);
 #endif
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	DEBUG_LOCKS_WARN_ON(ctx->acquired);
 	if (!IS_ENABLED(CONFIG_PROVE_LOCKING))
 		/*
@@ -269,7 +295,7 @@ static inline void
 ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	int ret;
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	DEBUG_LOCKS_WARN_ON(!ctx->contending_lock);
 #endif
 	ret = ww_mutex_lock(lock, ctx);
@@ -305,7 +331,7 @@ static inline int __must_check
 ww_mutex_lock_slow_interruptible(struct ww_mutex *lock,
 				 struct ww_acquire_ctx *ctx)
 {
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef DEBUG_WW_MUTEXES
 	DEBUG_LOCKS_WARN_ON(!ctx->contending_lock);
 #endif
 	return ww_mutex_lock_interruptible(lock, ctx);
@@ -322,7 +348,7 @@ extern void ww_mutex_unlock(struct ww_mutex *lock);
  */
 static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock)
 {
-	return mutex_trylock(&lock->base);
+	return ww_mutex_base_trylock(&lock->base);
 }
 
 /***
@@ -335,7 +361,9 @@ static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock)
  */
 static inline void ww_mutex_destroy(struct ww_mutex *lock)
 {
+#ifndef CONFIG_PREEMPT_RT
 	mutex_destroy(&lock->base);
+#endif
 }
 
 /**
@@ -346,7 +374,7 @@ static inline void ww_mutex_destroy(struct ww_mutex *lock)
  */
 static inline bool ww_mutex_is_locked(struct ww_mutex *lock)
 {
-	return mutex_is_locked(&lock->base);
+	return ww_mutex_base_is_locked(&lock->base);
 }
 
 #endif