Merge tag 'locking-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Thomas Gleixner:

 - Move futex code into kernel/futex/ and split up the kitchen sink into
   seperate files to make integration of sys_futex_waitv() simpler.

 - Add a new sys_futex_waitv() syscall which allows to wait on multiple
   futexes.

   The main use case is emulating Windows' WaitForMultipleObjects which
   allows Wine to improve the performance of Windows Games. Also native
   Linux games can benefit from this interface as this is a common wait
   pattern for this kind of applications.

 - Add context to ww_mutex_trylock() to provide a path for i915 to
   rework their eviction code step by step without making lockdep upset
   until the final steps of rework are completed. It's also useful for
   regulator and TTM to avoid dropping locks in the non contended path.

 - Lockdep and might_sleep() cleanups and improvements

 - A few improvements for the RT substitutions.

 - The usual small improvements and cleanups.

* tag 'locking-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  locking: Remove spin_lock_flags() etc
  locking/rwsem: Fix comments about reader optimistic lock stealing conditions
  locking: Remove rcu_read_{,un}lock() for preempt_{dis,en}able()
  locking/rwsem: Disable preemption for spinning region
  docs: futex: Fix kernel-doc references
  futex: Fix PREEMPT_RT build
  futex2: Documentation: Document sys_futex_waitv() uAPI
  selftests: futex: Test sys_futex_waitv() wouldblock
  selftests: futex: Test sys_futex_waitv() timeout
  selftests: futex: Add sys_futex_waitv() test
  futex,arm: Wire up sys_futex_waitv()
  futex,x86: Wire up sys_futex_waitv()
  futex: Implement sys_futex_waitv()
  futex: Simplify double_lock_hb()
  futex: Split out wait/wake
  futex: Split out requeue
  futex: Rename mark_wake_futex()
  futex: Rename: match_futex()
  futex: Rename: hb_waiter_{inc,dec,pending}()
  futex: Split out PI futex
  ...

Author: torvalds

Documentation/kernel-hacking/locking.rst

@@ -1352,7 +1352,19 @@ Mutex API reference
 Futex API reference
 ===================
 
-.. kernel-doc:: kernel/futex.c
+.. kernel-doc:: kernel/futex/core.c
+   :internal:
+
+.. kernel-doc:: kernel/futex/futex.h
+   :internal:
+
+.. kernel-doc:: kernel/futex/pi.c
+   :internal:
+
+.. kernel-doc:: kernel/futex/requeue.c
+   :internal:
+
+.. kernel-doc:: kernel/futex/waitwake.c
    :internal:
 
 Further reading

Documentation/translations/it_IT/kernel-hacking/locking.rst

@@ -1396,7 +1396,19 @@ Riferimento per l'API dei Mutex
 Riferimento per l'API dei Futex
 ===============================
 
-.. kernel-doc:: kernel/futex.c
+.. kernel-doc:: kernel/futex/core.c
+   :internal:
+
+.. kernel-doc:: kernel/futex/futex.h
+   :internal:
+
+.. kernel-doc:: kernel/futex/pi.c
+   :internal:
+
+.. kernel-doc:: kernel/futex/requeue.c
+   :internal:
+
+.. kernel-doc:: kernel/futex/waitwake.c
    :internal:
 
 Approfondimenti

Documentation/userspace-api/futex2.rst

@@ -0,0 +1,86 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======
+futex2
+======
+
+:Author: André Almeida <[email protected]>
+
+futex, or fast user mutex, is a set of syscalls to allow userspace to create
+performant synchronization mechanisms, such as mutexes, semaphores and
+conditional variables in userspace. C standard libraries, like glibc, uses it
+as a means to implement more high level interfaces like pthreads.
+
+futex2 is a followup version of the initial futex syscall, designed to overcome
+limitations of the original interface.
+
+User API
+========
+
+``futex_waitv()``
+-----------------
+
+Wait on an array of futexes, wake on any::
+
+  futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes,
+              unsigned int flags, struct timespec *timeout, clockid_t clockid)
+
+  struct futex_waitv {
+        __u64 val;
+        __u64 uaddr;
+        __u32 flags;
+        __u32 __reserved;
+  };
+
+Userspace sets an array of struct futex_waitv (up to a max of 128 entries),
+using ``uaddr`` for the address to wait for, ``val`` for the expected value
+and ``flags`` to specify the type (e.g. private) and size of futex.
+``__reserved`` needs to be 0, but it can be used for future extension. The
+pointer for the first item of the array is passed as ``waiters``. An invalid
+address for ``waiters`` or for any ``uaddr`` returns ``-EFAULT``.
+
+If userspace has 32-bit pointers, it should do a explicit cast to make sure
+the upper bits are zeroed. ``uintptr_t`` does the tricky and it works for
+both 32/64-bit pointers.
+
+``nr_futexes`` specifies the size of the array. Numbers out of [1, 128]
+interval will make the syscall return ``-EINVAL``.
+
+The ``flags`` argument of the syscall needs to be 0, but it can be used for
+future extension.
+
+For each entry in ``waiters`` array, the current value at ``uaddr`` is compared
+to ``val``. If it's different, the syscall undo all the work done so far and
+return ``-EAGAIN``. If all tests and verifications succeeds, syscall waits until
+one of the following happens:
+
+- The timeout expires, returning ``-ETIMEOUT``.
+- A signal was sent to the sleeping task, returning ``-ERESTARTSYS``.
+- Some futex at the list was woken, returning the index of some waked futex.
+
+An example of how to use the interface can be found at ``tools/testing/selftests/futex/functional/futex_waitv.c``.
+
+Timeout
+-------
+
+``struct timespec *timeout`` argument is an optional argument that points to an
+absolute timeout. You need to specify the type of clock being used at
+``clockid`` argument. ``CLOCK_MONOTONIC`` and ``CLOCK_REALTIME`` are supported.
+This syscall accepts only 64bit timespec structs.
+
+Types of futex
+--------------
+
+A futex can be either private or shared. Private is used for processes that
+shares the same memory space and the virtual address of the futex will be the
+same for all processes. This allows for optimizations in the kernel. To use
+private futexes, it's necessary to specify ``FUTEX_PRIVATE_FLAG`` in the futex
+flag. For processes that doesn't share the same memory space and therefore can
+have different virtual addresses for the same futex (using, for instance, a
+file-backed shared memory) requires different internal mechanisms to be get
+properly enqueued. This is the default behavior, and it works with both private
+and shared futexes.
+
+Futexes can be of different sizes: 8, 16, 32 or 64 bits. Currently, the only
+supported one is 32 bit sized futex, and it need to be specified using
+``FUTEX_32`` flag.

Documentation/userspace-api/index.rst

@@ -28,6 +28,7 @@ place where this information is gathered.
    media/index
    sysfs-platform_profile
    vduse
+   futex2
 
 .. only::  subproject and html
 

MAINTAINERS

@@ -7737,14 +7737,15 @@ M:	Ingo Molnar <[email protected]>
 R:	Peter Zijlstra <[email protected]>
 R:	Darren Hart <[email protected]>
 R:	Davidlohr Bueso <[email protected]>
+R:	André Almeida <[email protected]>
 L:	[email protected]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 F:	Documentation/locking/*futex*
 F:	include/asm-generic/futex.h
 F:	include/linux/futex.h
 F:	include/uapi/linux/futex.h
-F:	kernel/futex.c
+F:	kernel/futex/*
 F:	tools/perf/bench/futex*
 F:	tools/testing/selftests/futex/
 

arch/arm/tools/syscall.tbl

@@ -462,3 +462,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common	futex_waitv			sys_futex_waitv

arch/arm64/include/asm/unistd.h

@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		449
+#define __NR_compat_syscalls		450
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/arm64/include/asm/unistd32.h

@@ -903,6 +903,8 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/ia64/include/asm/spinlock.h

@@ -124,18 +124,13 @@ static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 	__ticket_spin_unlock(lock);
 }
 
-static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
-						  unsigned long flags)
-{
-	arch_spin_lock(lock);
-}
-#define arch_spin_lock_flags	arch_spin_lock_flags
-
 #ifdef ASM_SUPPORTED
 
 static __always_inline void
-arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
+arch_read_lock(arch_rwlock_t *lock)
 {
+	unsigned long flags = 0;
+
 	__asm__ __volatile__ (
 		"tbit.nz p6, p0 = %1,%2\n"
 		"br.few 3f\n"
@@ -157,13 +152,8 @@ arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 		: "p6", "p7", "r2", "memory");
 }
 
-#define arch_read_lock_flags arch_read_lock_flags
-#define arch_read_lock(lock) arch_read_lock_flags(lock, 0)
-
 #else /* !ASM_SUPPORTED */
 
-#define arch_read_lock_flags(rw, flags) arch_read_lock(rw)
-
 #define arch_read_lock(rw)								\
 do {											\
 	arch_rwlock_t *__read_lock_ptr = (rw);						\
@@ -186,8 +176,10 @@ do {								\
 #ifdef ASM_SUPPORTED
 
 static __always_inline void
-arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
+arch_write_lock(arch_rwlock_t *lock)
 {
+	unsigned long flags = 0;
+
 	__asm__ __volatile__ (
 		"tbit.nz p6, p0 = %1, %2\n"
 		"mov ar.ccv = r0\n"
@@ -210,9 +202,6 @@ arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 		: "ar.ccv", "p6", "p7", "r2", "r29", "memory");
 }
 
-#define arch_write_lock_flags arch_write_lock_flags
-#define arch_write_lock(rw) arch_write_lock_flags(rw, 0)
-
 #define arch_write_trylock(rw)							\
 ({										\
 	register long result;							\

arch/openrisc/include/asm/spinlock.h

@@ -19,9 +19,6 @@
 
 #include <asm/qrwlock.h>
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #define arch_spin_relax(lock)	cpu_relax()
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()