path: root/SOURCES/0001-ntsync.patch

From 4e05dd5270a7e43940c9321c7be008d97143aca9 Mon Sep 17 00:00:00 2001
From: Peter Jung <admin@ptr1337.dev>
Date: Wed, 12 Jun 2024 18:20:30 +0200
Subject: [PATCH 09/11] ntsync

Signed-off-by: Peter Jung <admin@ptr1337.dev>
---
 Documentation/userspace-api/index.rst         |    1 +
 .../userspace-api/ioctl/ioctl-number.rst      |    2 +
 Documentation/userspace-api/ntsync.rst        |  398 +++++
 MAINTAINERS                                   |    9 +
 drivers/misc/Kconfig                          |   11 +
 drivers/misc/Makefile                         |    1 +
 drivers/misc/ntsync.c                         | 1232 +++++++++++++++
 include/uapi/linux/ntsync.h                   |   62 +
 tools/testing/selftests/Makefile              |    1 +
 .../selftests/drivers/ntsync/.gitignore       |    1 +
 .../testing/selftests/drivers/ntsync/Makefile |    7 +
 tools/testing/selftests/drivers/ntsync/config |    1 +
 .../testing/selftests/drivers/ntsync/ntsync.c | 1407 +++++++++++++++++
 13 files changed, 3133 insertions(+)
 create mode 100644 Documentation/userspace-api/ntsync.rst
 create mode 100644 drivers/misc/ntsync.c
 create mode 100644 include/uapi/linux/ntsync.h
 create mode 100644 tools/testing/selftests/drivers/ntsync/.gitignore
 create mode 100644 tools/testing/selftests/drivers/ntsync/Makefile
 create mode 100644 tools/testing/selftests/drivers/ntsync/config
 create mode 100644 tools/testing/selftests/drivers/ntsync/ntsync.c

diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index afecfe3cc4a86..d5745a500fa7b 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -62,6 +62,7 @@ Everything else
    vduse
    futex2
    perf_ring_buffer
+   ntsync
 
 .. only::  subproject and html
 
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index c472423412bf2..a141e8e65c5d3 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -174,6 +174,8 @@ Code  Seq#    Include File                                           Comments
 'M'   00-0F  drivers/video/fsl-diu-fb.h                              conflict!
 'N'   00-1F  drivers/usb/scanner.h
 'N'   40-7F  drivers/block/nvme.c
+'N'   80-8F  uapi/linux/ntsync.h                                     NT synchronization primitives
+                                                                     <mailto:wine-devel@winehq.org>
 'O'   00-06  mtd/ubi-user.h                                          UBI
 'P'   all    linux/soundcard.h                                       conflict!
 'P'   60-6F  sound/sscape_ioctl.h                                    conflict!
diff --git a/Documentation/userspace-api/ntsync.rst b/Documentation/userspace-api/ntsync.rst
new file mode 100644
index 0000000000000..767844637a7df
--- /dev/null
+++ b/Documentation/userspace-api/ntsync.rst
@@ -0,0 +1,398 @@
+===================================
+NT synchronization primitive driver
+===================================
+
+This page documents the user-space API for the ntsync driver.
+
+ntsync is a support driver for emulation of NT synchronization
+primitives by user-space NT emulators. It exists because implementation
+in user-space, using existing tools, cannot match Windows performance
+while offering accurate semantics. It is implemented entirely in
+software, and does not drive any hardware device.
+
+This interface is meant as a compatibility tool only, and should not
+be used for general synchronization. Instead use generic, versatile
+interfaces such as futex(2) and poll(2).
+
+Synchronization primitives
+==========================
+
+The ntsync driver exposes three types of synchronization primitives:
+semaphores, mutexes, and events.
+
+A semaphore holds a single volatile 32-bit counter, and a static 32-bit
+integer denoting the maximum value. It is considered signaled (that is,
+can be acquired without contention, or will wake up a waiting thread)
+when the counter is nonzero. The counter is decremented by one when a
+wait is satisfied. Both the initial and maximum count are established
+when the semaphore is created.
+
+A mutex holds a volatile 32-bit recursion count, and a volatile 32-bit
+identifier denoting its owner. A mutex is considered signaled when its
+owner is zero (indicating that it is not owned). The recursion count is
+incremented when a wait is satisfied, and ownership is set to the given
+identifier.
+
+A mutex also holds an internal flag denoting whether its previous owner
+has died; such a mutex is said to be abandoned. Owner death is not
+tracked automatically based on thread death, but rather must be
+communicated using ``NTSYNC_IOC_MUTEX_KILL``. An abandoned mutex is
+inherently considered unowned.
+
+Except for the "unowned" semantics of zero, the actual value of the
+owner identifier is not interpreted by the ntsync driver at all. The
+intended use is to store a thread identifier; however, the ntsync
+driver does not actually validate that a calling thread provides
+consistent or unique identifiers.
+
+An event is similar to a semaphore with a maximum count of one. It holds
+a volatile boolean state denoting whether it is signaled or not. There
+are two types of events, auto-reset and manual-reset. An auto-reset
+event is designaled when a wait is satisfied; a manual-reset event is
+not. The event type is specified when the event is created.
+
+Unless specified otherwise, all operations on an object are atomic and
+totally ordered with respect to other operations on the same object.
+
+Objects are represented by files. When all file descriptors to an
+object are closed, that object is deleted.
+
+Char device
+===========
+
+The ntsync driver creates a single char device /dev/ntsync. Each file
+description opened on the device represents a unique instance intended
+to back an individual NT virtual machine. Objects created by one ntsync
+instance may only be used with other objects created by the same
+instance.
+
+ioctl reference
+===============
+
+All operations on the device are done through ioctls. There are four
+structures used in ioctl calls::
+
+   struct ntsync_sem_args {
+   	__u32 sem;
+   	__u32 count;
+   	__u32 max;
+   };
+
+   struct ntsync_mutex_args {
+   	__u32 mutex;
+   	__u32 owner;
+   	__u32 count;
+   };
+
+   struct ntsync_event_args {
+   	__u32 event;
+   	__u32 signaled;
+   	__u32 manual;
+   };
+
+   struct ntsync_wait_args {
+   	__u64 timeout;
+   	__u64 objs;
+   	__u32 count;
+   	__u32 owner;
+   	__u32 index;
+   	__u32 alert;
+   	__u32 flags;
+   	__u32 pad;
+   };
+
+Depending on the ioctl, members of the structure may be used as input,
+output, or not at all. All ioctls return 0 on success.
+
+The ioctls on the device file are as follows:
+
+.. c:macro:: NTSYNC_IOC_CREATE_SEM
+
+  Create a semaphore object. Takes a pointer to struct
+  :c:type:`ntsync_sem_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``sem``
+       - On output, contains a file descriptor to the created semaphore.
+     * - ``count``
+       - Initial count of the semaphore.
+     * - ``max``
+       - Maximum count of the semaphore.
+
+  Fails with ``EINVAL`` if ``count`` is greater than ``max``.
+
+.. c:macro:: NTSYNC_IOC_CREATE_MUTEX
+
+  Create a mutex object. Takes a pointer to struct
+  :c:type:`ntsync_mutex_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``mutex``
+       - On output, contains a file descriptor to the created mutex.
+     * - ``count``
+       - Initial recursion count of the mutex.
+     * - ``owner``
+       - Initial owner of the mutex.
+
+  If ``owner`` is nonzero and ``count`` is zero, or if ``owner`` is
+  zero and ``count`` is nonzero, the function fails with ``EINVAL``.
+
+.. c:macro:: NTSYNC_IOC_CREATE_EVENT
+
+  Create an event object. Takes a pointer to struct
+  :c:type:`ntsync_event_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``event``
+       - On output, contains a file descriptor to the created event.
+     * - ``signaled``
+       - If nonzero, the event is initially signaled, otherwise
+         nonsignaled.
+     * - ``manual``
+       - If nonzero, the event is a manual-reset event, otherwise
+         auto-reset.
+
+The ioctls on the individual objects are as follows:
+
+.. c:macro:: NTSYNC_IOC_SEM_POST
+
+  Post to a semaphore object. Takes a pointer to a 32-bit integer,
+  which on input holds the count to be added to the semaphore, and on
+  output contains its previous count.
+
+  If adding to the semaphore's current count would raise the latter
+  past the semaphore's maximum count, the ioctl fails with
+  ``EOVERFLOW`` and the semaphore is not affected. If raising the
+  semaphore's count causes it to become signaled, eligible threads
+  waiting on this semaphore will be woken and the semaphore's count
+  decremented appropriately.
+
+.. c:macro:: NTSYNC_IOC_MUTEX_UNLOCK
+
+  Release a mutex object. Takes a pointer to struct
+  :c:type:`ntsync_mutex_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``mutex``
+       - Ignored.
+     * - ``owner``
+       - Specifies the owner trying to release this mutex.
+     * - ``count``
+       - On output, contains the previous recursion count.
+
+  If ``owner`` is zero, the ioctl fails with ``EINVAL``. If ``owner``
+  is not the current owner of the mutex, the ioctl fails with
+  ``EPERM``.
+
+  The mutex's count will be decremented by one. If decrementing the
+  mutex's count causes it to become zero, the mutex is marked as
+  unowned and signaled, and eligible threads waiting on it will be
+  woken as appropriate.
+
+.. c:macro:: NTSYNC_IOC_SET_EVENT
+
+  Signal an event object. Takes a pointer to a 32-bit integer, which on
+  output contains the previous state of the event.
+
+  Eligible threads will be woken, and auto-reset events will be
+  designaled appropriately.
+
+.. c:macro:: NTSYNC_IOC_RESET_EVENT
+
+  Designal an event object. Takes a pointer to a 32-bit integer, which
+  on output contains the previous state of the event.
+
+.. c:macro:: NTSYNC_IOC_PULSE_EVENT
+
+  Wake threads waiting on an event object while leaving it in an
+  unsignaled state. Takes a pointer to a 32-bit integer, which on
+  output contains the previous state of the event.
+
+  A pulse operation can be thought of as a set followed by a reset,
+  performed as a single atomic operation. If two threads are waiting on
+  an auto-reset event which is pulsed, only one will be woken. If two
+  threads are waiting a manual-reset event which is pulsed, both will
+  be woken. However, in both cases, the event will be unsignaled
+  afterwards, and a simultaneous read operation will always report the
+  event as unsignaled.
+
+.. c:macro:: NTSYNC_IOC_READ_SEM
+
+  Read the current state of a semaphore object. Takes a pointer to
+  struct :c:type:`ntsync_sem_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``sem``
+       - Ignored.
+     * - ``count``
+       - On output, contains the current count of the semaphore.
+     * - ``max``
+       - On output, contains the maximum count of the semaphore.
+
+.. c:macro:: NTSYNC_IOC_READ_MUTEX
+
+  Read the current state of a mutex object. Takes a pointer to struct
+  :c:type:`ntsync_mutex_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``mutex``
+       - Ignored.
+     * - ``owner``
+       - On output, contains the current owner of the mutex, or zero
+         if the mutex is not currently owned.
+     * - ``count``
+       - On output, contains the current recursion count of the mutex.
+
+  If the mutex is marked as abandoned, the function fails with
+  ``EOWNERDEAD``. In this case, ``count`` and ``owner`` are set to
+  zero.
+
+.. c:macro:: NTSYNC_IOC_READ_EVENT
+
+  Read the current state of an event object. Takes a pointer to struct
+  :c:type:`ntsync_event_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``event``
+       - Ignored.
+     * - ``signaled``
+       - On output, contains the current state of the event.
+     * - ``manual``
+       - On output, contains 1 if the event is a manual-reset event,
+         and 0 otherwise.
+
+.. c:macro:: NTSYNC_IOC_KILL_OWNER
+
+  Mark a mutex as unowned and abandoned if it is owned by the given
+  owner. Takes an input-only pointer to a 32-bit integer denoting the
+  owner. If the owner is zero, the ioctl fails with ``EINVAL``. If the
+  owner does not own the mutex, the function fails with ``EPERM``.
+
+  Eligible threads waiting on the mutex will be woken as appropriate
+  (and such waits will fail with ``EOWNERDEAD``, as described below).
+
+.. c:macro:: NTSYNC_IOC_WAIT_ANY
+
+  Poll on any of a list of objects, atomically acquiring at most one.
+  Takes a pointer to struct :c:type:`ntsync_wait_args`, which is
+  used as follows:
+
+  .. list-table::
+
+     * - ``timeout``
+       - Absolute timeout in nanoseconds. If ``NTSYNC_WAIT_REALTIME``
+         is set, the timeout is measured against the REALTIME clock;
+         otherwise it is measured against the MONOTONIC clock. If the
+         timeout is equal to or earlier than the current time, the
+         function returns immediately without sleeping. If ``timeout``
+         is U64_MAX, the function will sleep until an object is
+         signaled, and will not fail with ``ETIMEDOUT``.
+     * - ``objs``
+       - Pointer to an array of ``count`` file descriptors
+         (specified as an integer so that the structure has the same
+         size regardless of architecture). If any object is
+         invalid, the function fails with ``EINVAL``.
+     * - ``count``
+       - Number of objects specified in the ``objs`` array.
+         If greater than ``NTSYNC_MAX_WAIT_COUNT``, the function fails
+         with ``EINVAL``.
+     * - ``owner``
+       - Mutex owner identifier. If any object in ``objs`` is a mutex,
+         the ioctl will attempt to acquire that mutex on behalf of
+         ``owner``. If ``owner`` is zero, the ioctl fails with
+         ``EINVAL``.
+     * - ``index``
+       - On success, contains the index (into ``objs``) of the object
+         which was signaled. If ``alert`` was signaled instead,
+         this contains ``count``.
+     * - ``alert``
+       - Optional event object file descriptor. If nonzero, this
+         specifies an "alert" event object which, if signaled, will
+         terminate the wait. If nonzero, the identifier must point to a
+         valid event.
+     * - ``flags``
+       - Zero or more flags. Currently the only flag is
+         ``NTSYNC_WAIT_REALTIME``, which causes the timeout to be
+         measured against the REALTIME clock instead of MONOTONIC.
+     * - ``pad``
+       - Unused, must be set to zero.
+
+  This function attempts to acquire one of the given objects. If unable
+  to do so, it sleeps until an object becomes signaled, subsequently
+  acquiring it, or the timeout expires. In the latter case the ioctl
+  fails with ``ETIMEDOUT``. The function only acquires one object, even
+  if multiple objects are signaled.
+
+  A semaphore is considered to be signaled if its count is nonzero, and
+  is acquired by decrementing its count by one. A mutex is considered
+  to be signaled if it is unowned or if its owner matches the ``owner``
+  argument, and is acquired by incrementing its recursion count by one
+  and setting its owner to the ``owner`` argument. An auto-reset event
+  is acquired by designaling it; a manual-reset event is not affected
+  by acquisition.
+
+  Acquisition is atomic and totally ordered with respect to other
+  operations on the same object. If two wait operations (with different
+  ``owner`` identifiers) are queued on the same mutex, only one is
+  signaled. If two wait operations are queued on the same semaphore,
+  and a value of one is posted to it, only one is signaled.
+
+  If an abandoned mutex is acquired, the ioctl fails with
+  ``EOWNERDEAD``. Although this is a failure return, the function may
+  otherwise be considered successful. The mutex is marked as owned by
+  the given owner (with a recursion count of 1) and as no longer
+  abandoned, and ``index`` is still set to the index of the mutex.
+
+  The ``alert`` argument is an "extra" event which can terminate the
+  wait, independently of all other objects.
+
+  It is valid to pass the same object more than once, including by
+  passing the same event in the ``objs`` array and in ``alert``. If a
+  wakeup occurs due to that object being signaled, ``index`` is set to
+  the lowest index corresponding to that object.
+
+  The function may fail with ``EINTR`` if a signal is received.
+
+.. c:macro:: NTSYNC_IOC_WAIT_ALL
+
+  Poll on a list of objects, atomically acquiring all of them. Takes a
+  pointer to struct :c:type:`ntsync_wait_args`, which is used
+  identically to ``NTSYNC_IOC_WAIT_ANY``, except that ``index`` is
+  always filled with zero on success if not woken via alert.
+
+  This function attempts to simultaneously acquire all of the given
+  objects. If unable to do so, it sleeps until all objects become
+  simultaneously signaled, subsequently acquiring them, or the timeout
+  expires. In the latter case the ioctl fails with ``ETIMEDOUT`` and no
+  objects are modified.
+
+  Objects may become signaled and subsequently designaled (through
+  acquisition by other threads) while this thread is sleeping. Only
+  once all objects are simultaneously signaled does the ioctl acquire
+  them and return. The entire acquisition is atomic and totally ordered
+  with respect to other operations on any of the given objects.
+
+  If an abandoned mutex is acquired, the ioctl fails with
+  ``EOWNERDEAD``. Similarly to ``NTSYNC_IOC_WAIT_ANY``, all objects are
+  nevertheless marked as acquired. Note that if multiple mutex objects
+  are specified, there is no way to know which were marked as
+  abandoned.
+
+  As with "any" waits, the ``alert`` argument is an "extra" event which
+  can terminate the wait. Critically, however, an "all" wait will
+  succeed if all members in ``objs`` are signaled, *or* if ``alert`` is
+  signaled. In the latter case ``index`` will be set to ``count``. As
+  with "any" waits, if both conditions are filled, the former takes
+  priority, and objects in ``objs`` will be acquired.
+
+  Unlike ``NTSYNC_IOC_WAIT_ANY``, it is not valid to pass the same
+  object more than once, nor is it valid to pass the same object in
+  ``objs`` and in ``alert``. If this is attempted, the function fails
+  with ``EINVAL``.
diff --git a/MAINTAINERS b/MAINTAINERS
index 28e20975c26f5..5845f3dd0488d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15721,6 +15721,15 @@ T:	git https://github.com/Paragon-Software-Group/linux-ntfs3.git
 F:	Documentation/filesystems/ntfs3.rst
 F:	fs/ntfs3/
 
+NTSYNC SYNCHRONIZATION PRIMITIVE DRIVER
+M:	Elizabeth Figura <zfigura@codeweavers.com>
+L:	wine-devel@winehq.org
+S:	Supported
+F:	Documentation/userspace-api/ntsync.rst
+F:	drivers/misc/ntsync.c
+F:	include/uapi/linux/ntsync.h
+F:	tools/testing/selftests/drivers/ntsync/
+
 NUBUS SUBSYSTEM
 M:	Finn Thain <fthain@linux-m68k.org>
 L:	linux-m68k@lists.linux-m68k.org
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 4fb291f0bf7c8..801ed229ed7dc 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -506,6 +506,17 @@ config OPEN_DICE
 
 	  If unsure, say N.
 
+config NTSYNC
+	tristate "NT synchronization primitive emulation"
+	help
+	  This module provides kernel support for emulation of Windows NT
+	  synchronization primitives. It is not a hardware driver.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ntsync.
+
+	  If unsure, say N.
+
 config VCPU_STALL_DETECTOR
 	tristate "Guest vCPU stall detector"
 	depends on OF && HAS_IOMEM
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index ea6ea5bbbc9c6..153a3f4837e8c 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_PVPANIC)   	+= pvpanic/
 obj-$(CONFIG_UACCE)		+= uacce/
 obj-$(CONFIG_XILINX_SDFEC)	+= xilinx_sdfec.o
 obj-$(CONFIG_HISI_HIKEY_USB)	+= hisi_hikey_usb.o
+obj-$(CONFIG_NTSYNC)		+= ntsync.o
 obj-$(CONFIG_HI6421V600_IRQ)	+= hi6421v600-irq.o
 obj-$(CONFIG_OPEN_DICE)		+= open-dice.o
 obj-$(CONFIG_GP_PCI1XXXX)	+= mchp_pci1xxxx/
diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
new file mode 100644
index 0000000000000..87a24798a5c7b
--- /dev/null
+++ b/drivers/misc/ntsync.c
@@ -0,0 +1,1232 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ntsync.c - Kernel driver for NT synchronization primitives
+ *
+ * Copyright (C) 2024 Elizabeth Figura <zfigura@codeweavers.com>
+ */
+
+#include <linux/anon_inodes.h>
+#include <linux/atomic.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <uapi/linux/ntsync.h>
+
+#define NTSYNC_NAME	"ntsync"
+
+enum ntsync_type {
+	NTSYNC_TYPE_SEM,
+	NTSYNC_TYPE_MUTEX,
+	NTSYNC_TYPE_EVENT,
+};
+
+/*
+ * Individual synchronization primitives are represented by
+ * struct ntsync_obj, and each primitive is backed by a file.
+ *
+ * The whole namespace is represented by a struct ntsync_device also
+ * backed by a file.
+ *
+ * Both rely on struct file for reference counting. Individual
+ * ntsync_obj objects take a reference to the device when created.
+ * Wait operations take a reference to each object being waited on for
+ * the duration of the wait.
+ */
+
+struct ntsync_obj {
+	spinlock_t lock;
+	int dev_locked;
+
+	enum ntsync_type type;
+
+	struct file *file;
+	struct ntsync_device *dev;
+
+	/* The following fields are protected by the object lock. */
+	union {
+		struct {
+			__u32 count;
+			__u32 max;
+		} sem;
+		struct {
+			__u32 count;
+			pid_t owner;
+			bool ownerdead;
+		} mutex;
+		struct {
+			bool manual;
+			bool signaled;
+		} event;
+	} u;
+
+	/*
+	 * any_waiters is protected by the object lock, but all_waiters is
+	 * protected by the device wait_all_lock.
+	 */
+	struct list_head any_waiters;
+	struct list_head all_waiters;
+
+	/*
+	 * Hint describing how many tasks are queued on this object in a
+	 * wait-all operation.
+	 *
+	 * Any time we do a wake, we may need to wake "all" waiters as well as
+	 * "any" waiters. In order to atomically wake "all" waiters, we must
+	 * lock all of the objects, and that means grabbing the wait_all_lock
+	 * below (and, due to lock ordering rules, before locking this object).
+	 * However, wait-all is a rare operation, and grabbing the wait-all
+	 * lock for every wake would create unnecessary contention.
+	 * Therefore we first check whether all_hint is zero, and, if it is,
+	 * we skip trying to wake "all" waiters.
+	 *
+	 * Since wait requests must originate from user-space threads, we're
+	 * limited here by PID_MAX_LIMIT, so there's no risk of overflow.
+	 */
+	atomic_t all_hint;
+};
+
+struct ntsync_q_entry {
+	struct list_head node;
+	struct ntsync_q *q;
+	struct ntsync_obj *obj;
+	__u32 index;
+};
+
+struct ntsync_q {
+	struct task_struct *task;
+	__u32 owner;
+
+	/*
+	 * Protected via atomic_try_cmpxchg(). Only the thread that wins the
+	 * compare-and-swap may actually change object states and wake this
+	 * task.
+	 */
+	atomic_t signaled;
+
+	bool all;
+	bool ownerdead;
+	__u32 count;
+	struct ntsync_q_entry entries[];
+};
+
+struct ntsync_device {
+	/*
+	 * Wait-all operations must atomically grab all objects, and be totally
+	 * ordered with respect to each other and wait-any operations.
+	 * If one thread is trying to acquire several objects, another thread
+	 * cannot touch the object at the same time.
+	 *
+	 * This device-wide lock is used to serialize wait-for-all
+	 * operations, and operations on an object that is involved in a
+	 * wait-for-all.
+	 */
+	struct mutex wait_all_lock;
+
+	struct file *file;
+};
+
+/*
+ * Single objects are locked using obj->lock.
+ *
+ * Multiple objects are 'locked' while holding dev->wait_all_lock.
+ * In this case however, individual objects are not locked by holding
+ * obj->lock, but by setting obj->dev_locked.
+ *
+ * This means that in order to lock a single object, the sequence is slightly
+ * more complicated than usual. Specifically it needs to check obj->dev_locked
+ * after acquiring obj->lock, if set, it needs to drop the lock and acquire
+ * dev->wait_all_lock in order to serialize against the multi-object operation.
+ */
+
+static void dev_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	lockdep_assert_held(&dev->wait_all_lock);
+	lockdep_assert(obj->dev == dev);
+	spin_lock(&obj->lock);
+	/*
+	 * By setting obj->dev_locked inside obj->lock, it is ensured that
+	 * anyone holding obj->lock must see the value.
+	 */
+	obj->dev_locked = 1;
+	spin_unlock(&obj->lock);
+}
+
+static void dev_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	lockdep_assert_held(&dev->wait_all_lock);
+	lockdep_assert(obj->dev == dev);
+	spin_lock(&obj->lock);
+	obj->dev_locked = 0;
+	spin_unlock(&obj->lock);
+}
+
+static void obj_lock(struct ntsync_obj *obj)
+{
+	struct ntsync_device *dev = obj->dev;
+
+	for (;;) {
+		spin_lock(&obj->lock);
+		if (likely(!obj->dev_locked))
+			break;
+
+		spin_unlock(&obj->lock);
+		mutex_lock(&dev->wait_all_lock);
+		spin_lock(&obj->lock);
+		/*
+		 * obj->dev_locked should be set and released under the same
+		 * wait_all_lock section, since we now own this lock, it should
+		 * be clear.
+		 */
+		lockdep_assert(!obj->dev_locked);
+		spin_unlock(&obj->lock);
+		mutex_unlock(&dev->wait_all_lock);
+	}
+}
+
+static void obj_unlock(struct ntsync_obj *obj)
+{
+	spin_unlock(&obj->lock);
+}
+
+static bool ntsync_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	bool all;
+
+	obj_lock(obj);
+	all = atomic_read(&obj->all_hint);
+	if (unlikely(all)) {
+		obj_unlock(obj);
+		mutex_lock(&dev->wait_all_lock);
+		dev_lock_obj(dev, obj);
+	}
+
+	return all;
+}
+
+static void ntsync_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj, bool all)
+{
+	if (all) {
+		dev_unlock_obj(dev, obj);
+		mutex_unlock(&dev->wait_all_lock);
+	} else {
+		obj_unlock(obj);
+	}
+}
+
+#define ntsync_assert_held(obj) \
+	lockdep_assert((lockdep_is_held(&(obj)->lock) != LOCK_STATE_NOT_HELD) || \
+		       ((lockdep_is_held(&(obj)->dev->wait_all_lock) != LOCK_STATE_NOT_HELD) && \
+			(obj)->dev_locked))
+
+static bool is_signaled(struct ntsync_obj *obj, __u32 owner)
+{
+	ntsync_assert_held(obj);
+
+	switch (obj->type) {
+	case NTSYNC_TYPE_SEM:
+		return !!obj->u.sem.count;
+	case NTSYNC_TYPE_MUTEX:
+		if (obj->u.mutex.owner && obj->u.mutex.owner != owner)
+			return false;
+		return obj->u.mutex.count < UINT_MAX;
+	case NTSYNC_TYPE_EVENT:
+		return obj->u.event.signaled;
+	}
+
+	WARN(1, "bad object type %#x\n", obj->type);
+	return false;
+}
+
+/*
+ * "locked_obj" is an optional pointer to an object which is already locked and
+ * should not be locked again. This is necessary so that changing an object's
+ * state and waking it can be a single atomic operation.
+ */
+static void try_wake_all(struct ntsync_device *dev, struct ntsync_q *q,
+			 struct ntsync_obj *locked_obj)
+{
+	__u32 count = q->count;
+	bool can_wake = true;
+	int signaled = -1;
+	__u32 i;
+
+	lockdep_assert_held(&dev->wait_all_lock);
+	if (locked_obj)
+		lockdep_assert(locked_obj->dev_locked);
+
+	for (i = 0; i < count; i++) {
+		if (q->entries[i].obj != locked_obj)
+			dev_lock_obj(dev, q->entries[i].obj);
+	}
+
+	for (i = 0; i < count; i++) {
+		if (!is_signaled(q->entries[i].obj, q->owner)) {
+			can_wake = false;
+			break;
+		}
+	}
+
+	if (can_wake && atomic_try_cmpxchg(&q->signaled, &signaled, 0)) {
+		for (i = 0; i < count; i++) {
+			struct ntsync_obj *obj = q->entries[i].obj;
+
+			switch (obj->type) {
+			case NTSYNC_TYPE_SEM:
+				obj->u.sem.count--;
+				break;
+			case NTSYNC_TYPE_MUTEX:
+				if (obj->u.mutex.ownerdead)
+					q->ownerdead = true;
+				obj->u.mutex.ownerdead = false;
+				obj->u.mutex.count++;
+				obj->u.mutex.owner = q->owner;
+				break;
+			case NTSYNC_TYPE_EVENT:
+				if (!obj->u.event.manual)
+					obj->u.event.signaled = false;
+				break;
+			}
+		}
+		wake_up_process(q->task);
+	}
+
+	for (i = 0; i < count; i++) {
+		if (q->entries[i].obj != locked_obj)
+			dev_unlock_obj(dev, q->entries[i].obj);
+	}
+}
+
+static void try_wake_all_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	struct ntsync_q_entry *entry;
+
+	lockdep_assert_held(&dev->wait_all_lock);
+	lockdep_assert(obj->dev_locked);
+
+	list_for_each_entry(entry, &obj->all_waiters, node)
+		try_wake_all(dev, entry->q, obj);
+}
+
+static void try_wake_any_sem(struct ntsync_obj *sem)
+{
+	struct ntsync_q_entry *entry;
+
+	ntsync_assert_held(sem);
+	lockdep_assert(sem->type == NTSYNC_TYPE_SEM);
+
+	list_for_each_entry(entry, &sem->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+		int signaled = -1;
+
+		if (!sem->u.sem.count)
+			break;
+
+		if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) {
+			sem->u.sem.count--;
+			wake_up_process(q->task);
+		}
+	}
+}
+
+static void try_wake_any_mutex(struct ntsync_obj *mutex)
+{
+	struct ntsync_q_entry *entry;
+
+	ntsync_assert_held(mutex);
+	lockdep_assert(mutex->type == NTSYNC_TYPE_MUTEX);
+
+	list_for_each_entry(entry, &mutex->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+		int signaled = -1;
+
+		if (mutex->u.mutex.count == UINT_MAX)
+			break;
+		if (mutex->u.mutex.owner && mutex->u.mutex.owner != q->owner)
+			continue;
+
+		if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) {
+			if (mutex->u.mutex.ownerdead)
+				q->ownerdead = true;
+			mutex->u.mutex.ownerdead = false;
+			mutex->u.mutex.count++;
+			mutex->u.mutex.owner = q->owner;
+			wake_up_process(q->task);
+		}
+	}
+}
+
+static void try_wake_any_event(struct ntsync_obj *event)
+{
+	struct ntsync_q_entry *entry;
+
+	ntsync_assert_held(event);
+	lockdep_assert(event->type == NTSYNC_TYPE_EVENT);
+
+	list_for_each_entry(entry, &event->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+		int signaled = -1;
+
+		if (!event->u.event.signaled)
+			break;
+
+		if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) {
+			if (!event->u.event.manual)
+				event->u.event.signaled = false;
+			wake_up_process(q->task);
+		}
+	}
+}
+
+/*
+ * Actually change the semaphore state, returning -EOVERFLOW if it is made
+ * invalid.
+ */
+static int post_sem_state(struct ntsync_obj *sem, __u32 count)
+{
+	__u32 sum;
+
+	ntsync_assert_held(sem);
+
+	if (check_add_overflow(sem->u.sem.count, count, &sum) ||
+	    sum > sem->u.sem.max)
+		return -EOVERFLOW;
+
+	sem->u.sem.count = sum;
+	return 0;
+}
+
+static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp)
+{
+	struct ntsync_device *dev = sem->dev;
+	__u32 __user *user_args = argp;
+	__u32 prev_count;
+	__u32 args;
+	bool all;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	if (sem->type != NTSYNC_TYPE_SEM)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, sem);
+
+	prev_count = sem->u.sem.count;
+	ret = post_sem_state(sem, args);
+	if (!ret) {
+		if (all)
+			try_wake_all_obj(dev, sem);
+		try_wake_any_sem(sem);
+	}
+
+	ntsync_unlock_obj(dev, sem, all);
+
+	if (!ret && put_user(prev_count, user_args))
+		ret = -EFAULT;
+
+	return ret;
+}
+
+/*
+ * Actually change the mutex state, returning -EPERM if not the owner.
+ */
+static int unlock_mutex_state(struct ntsync_obj *mutex,
+			      const struct ntsync_mutex_args *args)
+{
+	ntsync_assert_held(mutex);
+
+	if (mutex->u.mutex.owner != args->owner)
+		return -EPERM;
+
+	if (!--mutex->u.mutex.count)
+		mutex->u.mutex.owner = 0;
+	return 0;
+}
+
+static int ntsync_mutex_unlock(struct ntsync_obj *mutex, void __user *argp)
+{
+	struct ntsync_mutex_args __user *user_args = argp;
+	struct ntsync_device *dev = mutex->dev;
+	struct ntsync_mutex_args args;
+	__u32 prev_count;
+	bool all;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+	if (!args.owner)
+		return -EINVAL;
+
+	if (mutex->type != NTSYNC_TYPE_MUTEX)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, mutex);
+
+	prev_count = mutex->u.mutex.count;
+	ret = unlock_mutex_state(mutex, &args);
+	if (!ret) {
+		if (all)
+			try_wake_all_obj(dev, mutex);
+		try_wake_any_mutex(mutex);
+	}
+
+	ntsync_unlock_obj(dev, mutex, all);
+
+	if (!ret && put_user(prev_count, &user_args->count))
+		ret = -EFAULT;
+
+	return ret;
+}
+
+/*
+ * Actually change the mutex state to mark its owner as dead,
+ * returning -EPERM if not the owner.
+ */
+static int kill_mutex_state(struct ntsync_obj *mutex, __u32 owner)
+{
+	ntsync_assert_held(mutex);
+
+	if (mutex->u.mutex.owner != owner)
+		return -EPERM;
+
+	mutex->u.mutex.ownerdead = true;
+	mutex->u.mutex.owner = 0;
+	mutex->u.mutex.count = 0;
+	return 0;
+}
+
+static int ntsync_mutex_kill(struct ntsync_obj *mutex, void __user *argp)
+{
+	struct ntsync_device *dev = mutex->dev;
+	__u32 owner;
+	bool all;
+	int ret;
+
+	if (get_user(owner, (__u32 __user *)argp))
+		return -EFAULT;
+	if (!owner)
+		return -EINVAL;
+
+	if (mutex->type != NTSYNC_TYPE_MUTEX)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, mutex);
+
+	ret = kill_mutex_state(mutex, owner);
+	if (!ret) {
+		if (all)
+			try_wake_all_obj(dev, mutex);
+		try_wake_any_mutex(mutex);
+	}
+
+	ntsync_unlock_obj(dev, mutex, all);
+
+	return ret;
+}
+
+static int ntsync_event_set(struct ntsync_obj *event, void __user *argp, bool pulse)
+{
+	struct ntsync_device *dev = event->dev;
+	__u32 prev_state;
+	bool all;
+
+	if (event->type != NTSYNC_TYPE_EVENT)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, event);
+
+	prev_state = event->u.event.signaled;
+	event->u.event.signaled = true;
+	if (all)
+		try_wake_all_obj(dev, event);
+	try_wake_any_event(event);
+	if (pulse)
+		event->u.event.signaled = false;
+
+	ntsync_unlock_obj(dev, event, all);
+
+	if (put_user(prev_state, (__u32 __user *)argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ntsync_event_reset(struct ntsync_obj *event, void __user *argp)
+{
+	struct ntsync_device *dev = event->dev;
+	__u32 prev_state;
+	bool all;
+
+	if (event->type != NTSYNC_TYPE_EVENT)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, event);
+
+	prev_state = event->u.event.signaled;
+	event->u.event.signaled = false;
+
+	ntsync_unlock_obj(dev, event, all);
+
+	if (put_user(prev_state, (__u32 __user *)argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ntsync_sem_read(struct ntsync_obj *sem, void __user *argp)
+{
+	struct ntsync_sem_args __user *user_args = argp;
+	struct ntsync_device *dev = sem->dev;
+	struct ntsync_sem_args args;
+	bool all;
+
+	if (sem->type != NTSYNC_TYPE_SEM)
+		return -EINVAL;
+
+	args.sem = 0;
+
+	all = ntsync_lock_obj(dev, sem);
+
+	args.count = sem->u.sem.count;
+	args.max = sem->u.sem.max;
+
+	ntsync_unlock_obj(dev, sem, all);
+
+	if (copy_to_user(user_args, &args, sizeof(args)))
+		return -EFAULT;
+	return 0;
+}
+
+static int ntsync_mutex_read(struct ntsync_obj *mutex, void __user *argp)
+{
+	struct ntsync_mutex_args __user *user_args = argp;
+	struct ntsync_device *dev = mutex->dev;
+	struct ntsync_mutex_args args;
+	bool all;
+	int ret;
+
+	if (mutex->type != NTSYNC_TYPE_MUTEX)
+		return -EINVAL;
+
+	args.mutex = 0;
+
+	all = ntsync_lock_obj(dev, mutex);
+
+	args.count = mutex->u.mutex.count;
+	args.owner = mutex->u.mutex.owner;
+	ret = mutex->u.mutex.ownerdead ? -EOWNERDEAD : 0;
+
+	ntsync_unlock_obj(dev, mutex, all);
+
+	if (copy_to_user(user_args, &args, sizeof(args)))
+		return -EFAULT;
+	return ret;
+}
+
+static int ntsync_event_read(struct ntsync_obj *event, void __user *argp)
+{
+	struct ntsync_event_args __user *user_args = argp;
+	struct ntsync_device *dev = event->dev;
+	struct ntsync_event_args args;
+	bool all;
+
+	if (event->type != NTSYNC_TYPE_EVENT)
+		return -EINVAL;
+
+	args.event = 0;
+
+	all = ntsync_lock_obj(dev, event);
+
+	args.manual = event->u.event.manual;
+	args.signaled = event->u.event.signaled;
+
+	ntsync_unlock_obj(dev, event, all);
+
+	if (copy_to_user(user_args, &args, sizeof(args)))
+		return -EFAULT;
+	return 0;
+}
+
+static int ntsync_obj_release(struct inode *inode, struct file *file)
+{
+	struct ntsync_obj *obj = file->private_data;
+
+	fput(obj->dev->file);
+	kfree(obj);
+
+	return 0;
+}
+
+static long ntsync_obj_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long parm)
+{
+	struct ntsync_obj *obj = file->private_data;
+	void __user *argp = (void __user *)parm;
+
+	switch (cmd) {
+	case NTSYNC_IOC_SEM_POST:
+		return ntsync_sem_post(obj, argp);
+	case NTSYNC_IOC_SEM_READ:
+		return ntsync_sem_read(obj, argp);
+	case NTSYNC_IOC_MUTEX_UNLOCK:
+		return ntsync_mutex_unlock(obj, argp);
+	case NTSYNC_IOC_MUTEX_KILL:
+		return ntsync_mutex_kill(obj, argp);
+	case NTSYNC_IOC_MUTEX_READ:
+		return ntsync_mutex_read(obj, argp);
+	case NTSYNC_IOC_EVENT_SET:
+		return ntsync_event_set(obj, argp, false);
+	case NTSYNC_IOC_EVENT_RESET:
+		return ntsync_event_reset(obj, argp);
+	case NTSYNC_IOC_EVENT_PULSE:
+		return ntsync_event_set(obj, argp, true);
+	case NTSYNC_IOC_EVENT_READ:
+		return ntsync_event_read(obj, argp);
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+static const struct file_operations ntsync_obj_fops = {
+	.owner		= THIS_MODULE,
+	.release	= ntsync_obj_release,
+	.unlocked_ioctl	= ntsync_obj_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+	.llseek		= no_llseek,
+};
+
+static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev,
+					   enum ntsync_type type)
+{
+	struct ntsync_obj *obj;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return NULL;
+	obj->type = type;
+	obj->dev = dev;
+	get_file(dev->file);
+	spin_lock_init(&obj->lock);
+	INIT_LIST_HEAD(&obj->any_waiters);
+	INIT_LIST_HEAD(&obj->all_waiters);
+	atomic_set(&obj->all_hint, 0);
+
+	return obj;
+}
+
+static int ntsync_obj_get_fd(struct ntsync_obj *obj)
+{
+	struct file *file;
+	int fd;
+
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+	file = anon_inode_getfile("ntsync", &ntsync_obj_fops, obj, O_RDWR);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		return PTR_ERR(file);
+	}
+	obj->file = file;
+	fd_install(fd, file);
+
+	return fd;
+}
+
+static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_sem_args __user *user_args = argp;
+	struct ntsync_sem_args args;
+	struct ntsync_obj *sem;
+	int fd;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	if (args.count > args.max)
+		return -EINVAL;
+
+	sem = ntsync_alloc_obj(dev, NTSYNC_TYPE_SEM);
+	if (!sem)
+		return -ENOMEM;
+	sem->u.sem.count = args.count;
+	sem->u.sem.max = args.max;
+	fd = ntsync_obj_get_fd(sem);
+	if (fd < 0) {
+		kfree(sem);
+		return fd;
+	}
+
+	return put_user(fd, &user_args->sem);
+}
+
+static int ntsync_create_mutex(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_mutex_args __user *user_args = argp;
+	struct ntsync_mutex_args args;
+	struct ntsync_obj *mutex;
+	int fd;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	if (!args.owner != !args.count)
+		return -EINVAL;
+
+	mutex = ntsync_alloc_obj(dev, NTSYNC_TYPE_MUTEX);
+	if (!mutex)
+		return -ENOMEM;
+	mutex->u.mutex.count = args.count;
+	mutex->u.mutex.owner = args.owner;
+	fd = ntsync_obj_get_fd(mutex);
+	if (fd < 0) {
+		kfree(mutex);
+		return fd;
+	}
+
+	return put_user(fd, &user_args->mutex);
+}
+
+static int ntsync_create_event(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_event_args __user *user_args = argp;
+	struct ntsync_event_args args;
+	struct ntsync_obj *event;
+	int fd;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	event = ntsync_alloc_obj(dev, NTSYNC_TYPE_EVENT);
+	if (!event)
+		return -ENOMEM;
+	event->u.event.manual = args.manual;
+	event->u.event.signaled = args.signaled;
+	fd = ntsync_obj_get_fd(event);
+	if (fd < 0) {
+		kfree(event);
+		return fd;
+	}
+
+	return put_user(fd, &user_args->event);
+}
+
+static struct ntsync_obj *get_obj(struct ntsync_device *dev, int fd)
+{
+	struct file *file = fget(fd);
+	struct ntsync_obj *obj;
+
+	if (!file)
+		return NULL;
+
+	if (file->f_op != &ntsync_obj_fops) {
+		fput(file);
+		return NULL;
+	}
+
+	obj = file->private_data;
+	if (obj->dev != dev) {
+		fput(file);
+		return NULL;
+	}
+
+	return obj;
+}
+
+static void put_obj(struct ntsync_obj *obj)
+{
+	fput(obj->file);
+}
+
+static int ntsync_schedule(const struct ntsync_q *q, const struct ntsync_wait_args *args)
+{
+	ktime_t timeout = ns_to_ktime(args->timeout);
+	clockid_t clock = CLOCK_MONOTONIC;
+	ktime_t *timeout_ptr;
+	int ret = 0;
+
+	timeout_ptr = (args->timeout == U64_MAX ? NULL : &timeout);
+
+	if (args->flags & NTSYNC_WAIT_REALTIME)
+		clock = CLOCK_REALTIME;
+
+	do {
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (atomic_read(&q->signaled) != -1) {
+			ret = 0;
+			break;
+		}
+		ret = schedule_hrtimeout_range_clock(timeout_ptr, 0, HRTIMER_MODE_ABS, clock);
+	} while (ret < 0);
+	__set_current_state(TASK_RUNNING);
+
+	return ret;
+}
+
+/*
+ * Allocate and initialize the ntsync_q structure, but do not queue us yet.
+ */
+static int setup_wait(struct ntsync_device *dev,
+		      const struct ntsync_wait_args *args, bool all,
+		      struct ntsync_q **ret_q)
+{
+	int fds[NTSYNC_MAX_WAIT_COUNT + 1];
+	const __u32 count = args->count;
+	struct ntsync_q *q;
+	__u32 total_count;
+	__u32 i, j;
+
+	if (args->pad || (args->flags & ~NTSYNC_WAIT_REALTIME))
+		return -EINVAL;
+
+	if (args->count > NTSYNC_MAX_WAIT_COUNT)
+		return -EINVAL;
+
+	total_count = count;
+	if (args->alert)
+		total_count++;
+
+	if (copy_from_user(fds, u64_to_user_ptr(args->objs),
+			   array_size(count, sizeof(*fds))))
+		return -EFAULT;
+	if (args->alert)
+		fds[count] = args->alert;
+
+	q = kmalloc(struct_size(q, entries, total_count), GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+	q->task = current;
+	q->owner = args->owner;
+	atomic_set(&q->signaled, -1);
+	q->all = all;
+	q->ownerdead = false;
+	q->count = count;
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = get_obj(dev, fds[i]);
+
+		if (!obj)
+			goto err;
+
+		if (all) {
+			/* Check that the objects are all distinct. */
+			for (j = 0; j < i; j++) {
+				if (obj == q->entries[j].obj) {
+					put_obj(obj);
+					goto err;
+				}
+			}
+		}
+
+		entry->obj = obj;
+		entry->q = q;
+		entry->index = i;
+	}
+
+	*ret_q = q;
+	return 0;
+
+err:
+	for (j = 0; j < i; j++)
+		put_obj(q->entries[j].obj);
+	kfree(q);
+	return -EINVAL;
+}
+
+static void try_wake_any_obj(struct ntsync_obj *obj)
+{
+	switch (obj->type) {
+	case NTSYNC_TYPE_SEM:
+		try_wake_any_sem(obj);
+		break;
+	case NTSYNC_TYPE_MUTEX:
+		try_wake_any_mutex(obj);
+		break;
+	case NTSYNC_TYPE_EVENT:
+		try_wake_any_event(obj);
+		break;
+	}
+}
+
+static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_wait_args args;
+	__u32 i, total_count;
+	struct ntsync_q *q;
+	int signaled;
+	bool all;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	ret = setup_wait(dev, &args, false, &q);
+	if (ret < 0)
+		return ret;
+
+	total_count = args.count;
+	if (args.alert)
+		total_count++;
+
+	/* queue ourselves */
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		all = ntsync_lock_obj(dev, obj);
+		list_add_tail(&entry->node, &obj->any_waiters);
+		ntsync_unlock_obj(dev, obj, all);
+	}
+
+	/*
+	 * Check if we are already signaled.
+	 *
+	 * Note that the API requires that normal objects are checked before
+	 * the alert event. Hence we queue the alert event last, and check
+	 * objects in order.
+	 */
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_obj *obj = q->entries[i].obj;
+
+		if (atomic_read(&q->signaled) != -1)
+			break;
+
+		all = ntsync_lock_obj(dev, obj);
+		try_wake_any_obj(obj);
+		ntsync_unlock_obj(dev, obj, all);
+	}
+
+	/* sleep */
+
+	ret = ntsync_schedule(q, &args);
+
+	/* and finally, unqueue */
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		all = ntsync_lock_obj(dev, obj);
+		list_del(&entry->node);
+		ntsync_unlock_obj(dev, obj, all);
+
+		put_obj(obj);
+	}
+
+	signaled = atomic_read(&q->signaled);
+	if (signaled != -1) {
+		struct ntsync_wait_args __user *user_args = argp;
+
+		/* even if we caught a signal, we need to communicate success */
+		ret = q->ownerdead ? -EOWNERDEAD : 0;
+
+		if (put_user(signaled, &user_args->index))
+			ret = -EFAULT;
+	} else if (!ret) {
+		ret = -ETIMEDOUT;
+	}
+
+	kfree(q);
+	return ret;
+}
+
+static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_wait_args args;
+	struct ntsync_q *q;
+	int signaled;
+	__u32 i;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	ret = setup_wait(dev, &args, true, &q);
+	if (ret < 0)
+		return ret;
+
+	/* queue ourselves */
+
+	mutex_lock(&dev->wait_all_lock);
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		atomic_inc(&obj->all_hint);
+
+		/*
+		 * obj->all_waiters is protected by dev->wait_all_lock rather
+		 * than obj->lock, so there is no need to acquire obj->lock
+		 * here.
+		 */
+		list_add_tail(&entry->node, &obj->all_waiters);
+	}
+	if (args.alert) {
+		struct ntsync_q_entry *entry = &q->entries[args.count];
+		struct ntsync_obj *obj = entry->obj;
+
+		dev_lock_obj(dev, obj);
+		list_add_tail(&entry->node, &obj->any_waiters);
+		dev_unlock_obj(dev, obj);
+	}
+
+	/* check if we are already signaled */
+
+	try_wake_all(dev, q, NULL);
+
+	mutex_unlock(&dev->wait_all_lock);
+
+	/*
+	 * Check if the alert event is signaled, making sure to do so only
+	 * after checking if the other objects are signaled.
+	 */
+
+	if (args.alert) {
+		struct ntsync_obj *obj = q->entries[args.count].obj;
+
+		if (atomic_read(&q->signaled) == -1) {
+			bool all = ntsync_lock_obj(dev, obj);
+			try_wake_any_obj(obj);
+			ntsync_unlock_obj(dev, obj, all);
+		}
+	}
+
+	/* sleep */
+
+	ret = ntsync_schedule(q, &args);
+
+	/* and finally, unqueue */
+
+	mutex_lock(&dev->wait_all_lock);
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		/*
+		 * obj->all_waiters is protected by dev->wait_all_lock rather
+		 * than obj->lock, so there is no need to acquire it here.
+		 */
+		list_del(&entry->node);
+
+		atomic_dec(&obj->all_hint);
+
+		put_obj(obj);
+	}
+
+	mutex_unlock(&dev->wait_all_lock);
+
+	if (args.alert) {
+		struct ntsync_q_entry *entry = &q->entries[args.count];
+		struct ntsync_obj *obj = entry->obj;
+		bool all;
+
+		all = ntsync_lock_obj(dev, obj);
+		list_del(&entry->node);
+		ntsync_unlock_obj(dev, obj, all);
+
+		put_obj(obj);
+	}
+
+	signaled = atomic_read(&q->signaled);
+	if (signaled != -1) {
+		struct ntsync_wait_args __user *user_args = argp;
+
+		/* even if we caught a signal, we need to communicate success */
+		ret = q->ownerdead ? -EOWNERDEAD : 0;
+
+		if (put_user(signaled, &user_args->index))
+			ret = -EFAULT;
+	} else if (!ret) {
+		ret = -ETIMEDOUT;
+	}
+
+	kfree(q);
+	return ret;
+}
+
+static int ntsync_char_open(struct inode *inode, struct file *file)
+{
+	struct ntsync_device *dev;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	mutex_init(&dev->wait_all_lock);
+
+	file->private_data = dev;
+	dev->file = file;
+	return nonseekable_open(inode, file);
+}
+
+static int ntsync_char_release(struct inode *inode, struct file *file)
+{
+	struct ntsync_device *dev = file->private_data;
+
+	kfree(dev);
+
+	return 0;
+}
+
+static long ntsync_char_ioctl(struct file *file, unsigned int cmd,
+			      unsigned long parm)
+{
+	struct ntsync_device *dev = file->private_data;
+	void __user *argp = (void __user *)parm;
+
+	switch (cmd) {
+	case NTSYNC_IOC_CREATE_EVENT:
+		return ntsync_create_event(dev, argp);
+	case NTSYNC_IOC_CREATE_MUTEX:
+		return ntsync_create_mutex(dev, argp);
+	case NTSYNC_IOC_CREATE_SEM:
+		return ntsync_create_sem(dev, argp);
+	case NTSYNC_IOC_WAIT_ALL:
+		return ntsync_wait_all(dev, argp);
+	case NTSYNC_IOC_WAIT_ANY:
+		return ntsync_wait_any(dev, argp);
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+static const struct file_operations ntsync_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ntsync_char_open,
+	.release	= ntsync_char_release,
+	.unlocked_ioctl	= ntsync_char_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice ntsync_misc = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= NTSYNC_NAME,
+	.fops		= &ntsync_fops,
+};
+
+module_misc_device(ntsync_misc);
+
+MODULE_AUTHOR("Elizabeth Figura <zfigura@codeweavers.com>");
+MODULE_DESCRIPTION("Kernel driver for NT synchronization primitives");
+MODULE_LICENSE("GPL");
diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h
new file mode 100644
index 0000000000000..4a8095a3fc34c
--- /dev/null
+++ b/include/uapi/linux/ntsync.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Kernel support for NT synchronization primitive emulation
+ *
+ * Copyright (C) 2021-2022 Elizabeth Figura <zfigura@codeweavers.com>
+ */
+
+#ifndef __LINUX_NTSYNC_H
+#define __LINUX_NTSYNC_H
+
+#include <linux/types.h>
+
+struct ntsync_sem_args {
+	__u32 sem;
+	__u32 count;
+	__u32 max;
+};
+
+struct ntsync_mutex_args {
+	__u32 mutex;
+	__u32 owner;
+	__u32 count;
+};
+
+struct ntsync_event_args {
+	__u32 event;
+	__u32 manual;
+	__u32 signaled;
+};
+
+#define NTSYNC_WAIT_REALTIME	0x1
+
+struct ntsync_wait_args {
+	__u64 timeout;
+	__u64 objs;
+	__u32 count;
+	__u32 index;
+	__u32 flags;
+	__u32 owner;
+	__u32 alert;
+	__u32 pad;
+};
+
+#define NTSYNC_MAX_WAIT_COUNT 64
+
+#define NTSYNC_IOC_CREATE_SEM		_IOWR('N', 0x80, struct ntsync_sem_args)
+#define NTSYNC_IOC_WAIT_ANY		_IOWR('N', 0x82, struct ntsync_wait_args)
+#define NTSYNC_IOC_WAIT_ALL		_IOWR('N', 0x83, struct ntsync_wait_args)
+#define NTSYNC_IOC_CREATE_MUTEX		_IOWR('N', 0x84, struct ntsync_sem_args)
+#define NTSYNC_IOC_CREATE_EVENT		_IOWR('N', 0x87, struct ntsync_event_args)
+
+#define NTSYNC_IOC_SEM_POST		_IOWR('N', 0x81, __u32)
+#define NTSYNC_IOC_MUTEX_UNLOCK		_IOWR('N', 0x85, struct ntsync_mutex_args)
+#define NTSYNC_IOC_MUTEX_KILL		_IOW ('N', 0x86, __u32)
+#define NTSYNC_IOC_EVENT_SET		_IOR ('N', 0x88, __u32)
+#define NTSYNC_IOC_EVENT_RESET		_IOR ('N', 0x89, __u32)
+#define NTSYNC_IOC_EVENT_PULSE		_IOR ('N', 0x8a, __u32)
+#define NTSYNC_IOC_SEM_READ		_IOR ('N', 0x8b, struct ntsync_sem_args)
+#define NTSYNC_IOC_MUTEX_READ		_IOR ('N', 0x8c, struct ntsync_mutex_args)
+#define NTSYNC_IOC_EVENT_READ		_IOR ('N', 0x8d, struct ntsync_event_args)
+
+#endif
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index e1504833654db..6f95206325e1f 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -16,6 +16,7 @@ TARGETS += damon
 TARGETS += devices
 TARGETS += dmabuf-heaps
 TARGETS += drivers/dma-buf
+TARGETS += drivers/ntsync
 TARGETS += drivers/s390x/uvdevice
 TARGETS += drivers/net/bonding
 TARGETS += drivers/net/team
diff --git a/tools/testing/selftests/drivers/ntsync/.gitignore b/tools/testing/selftests/drivers/ntsync/.gitignore
new file mode 100644
index 0000000000000..848573a3d3eaf
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/.gitignore
@@ -0,0 +1 @@
+ntsync
diff --git a/tools/testing/selftests/drivers/ntsync/Makefile b/tools/testing/selftests/drivers/ntsync/Makefile
new file mode 100644
index 0000000000000..dbf2b055c0b28
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/Makefile
@@ -0,0 +1,7 @@
+# SPDX-LICENSE-IDENTIFIER: GPL-2.0-only
+TEST_GEN_PROGS := ntsync
+
+CFLAGS += $(KHDR_INCLUDES)
+LDLIBS += -lpthread
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/drivers/ntsync/config b/tools/testing/selftests/drivers/ntsync/config
new file mode 100644
index 0000000000000..60539c826d062
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/config
@@ -0,0 +1 @@
+CONFIG_WINESYNC=y
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
new file mode 100644
index 0000000000000..5fa2c9a0768c0
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -0,0 +1,1407 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Various unit tests for the "ntsync" synchronization primitive driver.
+ *
+ * Copyright (C) 2021-2022 Elizabeth Figura <zfigura@codeweavers.com>
+ */
+
+#define _GNU_SOURCE
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/ntsync.h>
+#include "../../kselftest_harness.h"
+
+static int read_sem_state(int sem, __u32 *count, __u32 *max)
+{
+	struct ntsync_sem_args args;
+	int ret;
+
+	memset(&args, 0xcc, sizeof(args));
+	ret = ioctl(sem, NTSYNC_IOC_SEM_READ, &args);
+	*count = args.count;
+	*max = args.max;
+	return ret;
+}
+
+#define check_sem_state(sem, count, max) \
+	({ \
+		__u32 __count, __max; \
+		int ret = read_sem_state((sem), &__count, &__max); \
+		EXPECT_EQ(0, ret); \
+		EXPECT_EQ((count), __count); \
+		EXPECT_EQ((max), __max); \
+	})
+
+static int post_sem(int sem, __u32 *count)
+{
+	return ioctl(sem, NTSYNC_IOC_SEM_POST, count);
+}
+
+static int read_mutex_state(int mutex, __u32 *count, __u32 *owner)
+{
+	struct ntsync_mutex_args args;
+	int ret;
+
+	memset(&args, 0xcc, sizeof(args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &args);
+	*count = args.count;
+	*owner = args.owner;
+	return ret;
+}
+
+#define check_mutex_state(mutex, count, owner) \
+	({ \
+		__u32 __count, __owner; \
+		int ret = read_mutex_state((mutex), &__count, &__owner); \
+		EXPECT_EQ(0, ret); \
+		EXPECT_EQ((count), __count); \
+		EXPECT_EQ((owner), __owner); \
+	})
+
+static int unlock_mutex(int mutex, __u32 owner, __u32 *count)
+{
+	struct ntsync_mutex_args args;
+	int ret;
+
+	args.owner = owner;
+	args.count = 0xdeadbeef;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_UNLOCK, &args);
+	*count = args.count;
+	return ret;
+}
+
+static int read_event_state(int event, __u32 *signaled, __u32 *manual)
+{
+	struct ntsync_event_args args;
+	int ret;
+
+	memset(&args, 0xcc, sizeof(args));
+	ret = ioctl(event, NTSYNC_IOC_EVENT_READ, &args);
+	*signaled = args.signaled;
+	*manual = args.manual;
+	return ret;
+}
+
+#define check_event_state(event, signaled, manual) \
+	({ \
+		__u32 __signaled, __manual; \
+		int ret = read_event_state((event), &__signaled, &__manual); \
+		EXPECT_EQ(0, ret); \
+		EXPECT_EQ((signaled), __signaled); \
+		EXPECT_EQ((manual), __manual); \
+	})
+
+static int wait_objs(int fd, unsigned long request, __u32 count,
+		     const int *objs, __u32 owner, int alert, __u32 *index)
+{
+	struct ntsync_wait_args args = {0};
+	struct timespec timeout;
+	int ret;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	args.timeout = timeout.tv_sec * 1000000000 + timeout.tv_nsec;
+	args.count = count;
+	args.objs = (uintptr_t)objs;
+	args.owner = owner;
+	args.index = 0xdeadbeef;
+	args.alert = alert;
+	ret = ioctl(fd, request, &args);
+	*index = args.index;
+	return ret;
+}
+
+static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ANY, count, objs, owner, 0, index);
+}
+
+static int wait_all(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ALL, count, objs, owner, 0, index);
+}
+
+static int wait_any_alert(int fd, __u32 count, const int *objs,
+			  __u32 owner, int alert, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ANY,
+			 count, objs, owner, alert, index);
+}
+
+static int wait_all_alert(int fd, __u32 count, const int *objs,
+			  __u32 owner, int alert, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ALL,
+			 count, objs, owner, alert, index);
+}
+
+TEST(semaphore_state)
+{
+	struct ntsync_sem_args sem_args;
+	struct timespec timeout;
+	__u32 count, index;
+	int fd, ret, sem;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 3;
+	sem_args.max = 2;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	sem_args.count = 2;
+	sem_args.max = 2;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+	sem = sem_args.sem;
+	check_sem_state(sem, 2, 2);
+
+	count = 0;
+	ret = post_sem(sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+	check_sem_state(sem, 2, 2);
+
+	count = 1;
+	ret = post_sem(sem, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOVERFLOW, errno);
+	check_sem_state(sem, 2, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem, 1, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem, 0, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	count = 3;
+	ret = post_sem(sem, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOVERFLOW, errno);
+	check_sem_state(sem, 0, 2);
+
+	count = 2;
+	ret = post_sem(sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(sem, 2, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+
+	count = 1;
+	ret = post_sem(sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(sem, 1, 2);
+
+	count = ~0u;
+	ret = post_sem(sem, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOVERFLOW, errno);
+	check_sem_state(sem, 1, 2);
+
+	close(sem);
+
+	close(fd);
+}
+
+TEST(mutex_state)
+{
+	struct ntsync_mutex_args mutex_args;
+	__u32 owner, count, index;
+	struct timespec timeout;
+	int fd, ret, mutex;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 0;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 2;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 2;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+	mutex = mutex_args.mutex;
+	check_mutex_state(mutex, 2, 123);
+
+	ret = unlock_mutex(mutex, 0, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	ret = unlock_mutex(mutex, 456, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EPERM, errno);
+	check_mutex_state(mutex, 2, 123);
+
+	ret = unlock_mutex(mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+	check_mutex_state(mutex, 1, 123);
+
+	ret = unlock_mutex(mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, count);
+	check_mutex_state(mutex, 0, 0);
+
+	ret = unlock_mutex(mutex, 123, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EPERM, errno);
+
+	ret = wait_any(fd, 1, &mutex, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 456);
+
+	ret = wait_any(fd, 1, &mutex, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 2, 456);
+
+	ret = unlock_mutex(mutex, 456, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+	check_mutex_state(mutex, 1, 456);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	owner = 0;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	owner = 123;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EPERM, errno);
+	check_mutex_state(mutex, 1, 456);
+
+	owner = 456;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	memset(&mutex_args, 0xcc, sizeof(mutex_args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, mutex_args.count);
+	EXPECT_EQ(0, mutex_args.owner);
+
+	memset(&mutex_args, 0xcc, sizeof(mutex_args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, mutex_args.count);
+	EXPECT_EQ(0, mutex_args.owner);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 123);
+
+	owner = 123;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	memset(&mutex_args, 0xcc, sizeof(mutex_args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, mutex_args.count);
+	EXPECT_EQ(0, mutex_args.owner);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 123);
+
+	close(mutex);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+	mutex = mutex_args.mutex;
+	check_mutex_state(mutex, 0, 0);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 123);
+
+	close(mutex);
+
+	mutex_args.owner = 123;
+	mutex_args.count = ~0u;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+	mutex = mutex_args.mutex;
+	check_mutex_state(mutex, ~0u, 123);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	close(mutex);
+
+	close(fd);
+}
+
+TEST(manual_event_state)
+{
+	struct ntsync_event_args event_args;
+	__u32 index, signaled;
+	int fd, event, ret;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	event_args.manual = 1;
+	event_args.signaled = 0;
+	event_args.event = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, event_args.event);
+	event = event_args.event;
+	check_event_state(event, 0, 1);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 1, 1);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 1, 1);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_event_state(event, 1, 1);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 0, 1);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 1);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 0, 1);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 1);
+
+	close(event);
+
+	close(fd);
+}
+
+TEST(auto_event_state)
+{
+	struct ntsync_event_args event_args;
+	__u32 index, signaled;
+	int fd, event, ret;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	event_args.manual = 0;
+	event_args.signaled = 1;
+	event_args.event = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, event_args.event);
+	event = event_args.event;
+
+	check_event_state(event, 1, 0);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 1, 0);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_event_state(event, 0, 0);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 0);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 0, 0);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 0);
+
+	close(event);
+
+	close(fd);
+}
+
+TEST(test_wait_any)
+{
+	int objs[NTSYNC_MAX_WAIT_COUNT + 1], fd, ret;
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	__u32 owner, index, count, i;
+	struct timespec timeout;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 2;
+	sem_args.max = 3;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+
+	objs[0] = sem_args.sem;
+	objs[1] = mutex_args.mutex;
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 1, 3);
+	check_mutex_state(mutex_args.mutex, 0, 0);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_mutex_state(mutex_args.mutex, 0, 0);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_mutex_state(mutex_args.mutex, 1, 123);
+
+	count = 1;
+	ret = post_sem(sem_args.sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_mutex_state(mutex_args.mutex, 1, 123);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_mutex_state(mutex_args.mutex, 2, 123);
+
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	owner = 123;
+	ret = ioctl(mutex_args.mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(1, index);
+
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+
+	/* test waiting on the same object twice */
+	count = 2;
+	ret = post_sem(sem_args.sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	objs[0] = objs[1] = sem_args.sem;
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 1, 3);
+
+	ret = wait_any(fd, 0, NULL, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	for (i = 0; i < NTSYNC_MAX_WAIT_COUNT + 1; ++i)
+		objs[i] = sem_args.sem;
+
+	ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT + 1, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	ret = wait_any(fd, -1, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	close(sem_args.sem);
+	close(mutex_args.mutex);
+
+	close(fd);
+}
+
+TEST(test_wait_all)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	__u32 owner, index, count;
+	int objs[2], fd, ret;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 2;
+	sem_args.max = 3;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+
+	event_args.manual = true;
+	event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	objs[0] = sem_args.sem;
+	objs[1] = mutex_args.mutex;
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 1, 3);
+	check_mutex_state(mutex_args.mutex, 1, 123);
+
+	ret = wait_all(fd, 2, objs, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+	check_sem_state(sem_args.sem, 1, 3);
+	check_mutex_state(mutex_args.mutex, 1, 123);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_mutex_state(mutex_args.mutex, 2, 123);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_mutex_state(mutex_args.mutex, 2, 123);
+
+	count = 3;
+	ret = post_sem(sem_args.sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 2, 3);
+	check_mutex_state(mutex_args.mutex, 3, 123);
+
+	owner = 123;
+	ret = ioctl(mutex_args.mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	check_sem_state(sem_args.sem, 1, 3);
+	check_mutex_state(mutex_args.mutex, 1, 123);
+
+	objs[0] = sem_args.sem;
+	objs[1] = event_args.event;
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem_args.sem, 0, 3);
+	check_event_state(event_args.event, 1, 1);
+
+	/* test waiting on the same object twice */
+	objs[0] = objs[1] = sem_args.sem;
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	close(sem_args.sem);
+	close(mutex_args.mutex);
+	close(event_args.event);
+
+	close(fd);
+}
+
+struct wake_args {
+	int fd;
+	int obj;
+};
+
+struct wait_args {
+	int fd;
+	unsigned long request;
+	struct ntsync_wait_args *args;
+	int ret;
+	int err;
+};
+
+static void *wait_thread(void *arg)
+{
+	struct wait_args *args = arg;
+
+	args->ret = ioctl(args->fd, args->request, args->args);
+	args->err = errno;
+	return NULL;
+}
+
+static __u64 get_abs_timeout(unsigned int ms)
+{
+	struct timespec timeout;
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+	return (timeout.tv_sec * 1000000000) + timeout.tv_nsec + (ms * 1000000);
+}
+
+static int wait_for_thread(pthread_t thread, unsigned int ms)
+{
+	struct timespec timeout;
+
+	clock_gettime(CLOCK_REALTIME, &timeout);
+	timeout.tv_nsec += ms * 1000000;
+	timeout.tv_sec += (timeout.tv_nsec / 1000000000);
+	timeout.tv_nsec %= 1000000000;
+	return pthread_timedjoin_np(thread, NULL, &timeout);
+}
+
+TEST(wake_any)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	struct wait_args thread_args;
+	__u32 count, index, signaled;
+	int objs[2], fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 0;
+	sem_args.max = 3;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 1;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+
+	objs[0] = sem_args.sem;
+	objs[1] = mutex_args.mutex;
+
+	/* test waking the semaphore */
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 2;
+	wait_args.owner = 456;
+	wait_args.index = 0xdeadbeef;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ANY;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	count = 1;
+	ret = post_sem(sem_args.sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(sem_args.sem, 0, 3);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(0, wait_args.index);
+
+	/* test waking the mutex */
+
+	/* first grab it again for owner 123 */
+	ret = wait_any(fd, 1, &mutex_args.mutex, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.owner = 456;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = unlock_mutex(mutex_args.mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+
+	ret = pthread_tryjoin_np(thread, NULL);
+	EXPECT_EQ(EBUSY, ret);
+
+	ret = unlock_mutex(mutex_args.mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, mutex_args.count);
+	check_mutex_state(mutex_args.mutex, 1, 456);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	/* test waking events */
+
+	event_args.manual = false;
+	event_args.signaled = false;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	objs[1] = event_args.event;
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event_args.event, 0, 0);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event_args.event, 0, 0);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	close(event_args.event);
+
+	event_args.manual = true;
+	event_args.signaled = false;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	objs[1] = event_args.event;
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event_args.event, 1, 1);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event_args.event, 0, 1);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	close(event_args.event);
+
+	/* delete an object while it's being waited on */
+
+	wait_args.timeout = get_abs_timeout(200);
+	wait_args.owner = 123;
+	objs[1] = mutex_args.mutex;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	close(sem_args.sem);
+	close(mutex_args.mutex);
+
+	ret = wait_for_thread(thread, 200);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(-1, thread_args.ret);
+	EXPECT_EQ(ETIMEDOUT, thread_args.err);
+
+	close(fd);
+}
+
+TEST(wake_all)
+{
+	struct ntsync_event_args manual_event_args = {0};
+	struct ntsync_event_args auto_event_args = {0};
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	struct wait_args thread_args;
+	__u32 count, index, signaled;
+	int objs[4], fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 0;
+	sem_args.max = 3;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 1;
+	mutex_args.mutex = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, mutex_args.mutex);
+
+	manual_event_args.manual = true;
+	manual_event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &manual_event_args);
+	EXPECT_EQ(0, ret);
+
+	auto_event_args.manual = false;
+	auto_event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &auto_event_args);
+	EXPECT_EQ(0, ret);
+
+	objs[0] = sem_args.sem;
+	objs[1] = mutex_args.mutex;
+	objs[2] = manual_event_args.event;
+	objs[3] = auto_event_args.event;
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 4;
+	wait_args.owner = 456;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ALL;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	count = 1;
+	ret = post_sem(sem_args.sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	ret = pthread_tryjoin_np(thread, NULL);
+	EXPECT_EQ(EBUSY, ret);
+
+	check_sem_state(sem_args.sem, 1, 3);
+
+	ret = wait_any(fd, 1, &sem_args.sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = unlock_mutex(mutex_args.mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, count);
+
+	ret = pthread_tryjoin_np(thread, NULL);
+	EXPECT_EQ(EBUSY, ret);
+
+	check_mutex_state(mutex_args.mutex, 0, 0);
+
+	ret = ioctl(manual_event_args.event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+
+	count = 2;
+	ret = post_sem(sem_args.sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(sem_args.sem, 2, 3);
+
+	ret = ioctl(auto_event_args.event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+
+	ret = ioctl(manual_event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	ret = ioctl(auto_event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	check_sem_state(sem_args.sem, 1, 3);
+	check_mutex_state(mutex_args.mutex, 1, 456);
+	check_event_state(manual_event_args.event, 1, 1);
+	check_event_state(auto_event_args.event, 0, 0);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+
+	/* delete an object while it's being waited on */
+
+	wait_args.timeout = get_abs_timeout(200);
+	wait_args.owner = 123;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	close(sem_args.sem);
+	close(mutex_args.mutex);
+	close(manual_event_args.event);
+	close(auto_event_args.event);
+
+	ret = wait_for_thread(thread, 200);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(-1, thread_args.ret);
+	EXPECT_EQ(ETIMEDOUT, thread_args.err);
+
+	close(fd);
+}
+
+TEST(alert_any)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	__u32 index, count, signaled;
+	struct wait_args thread_args;
+	int objs[2], fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 0;
+	sem_args.max = 2;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+	objs[0] = sem_args.sem;
+
+	sem_args.count = 1;
+	sem_args.max = 2;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+	objs[1] = sem_args.sem;
+
+	event_args.manual = true;
+	event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 0, NULL, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 0, NULL, 123, event_args.event, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	/* test wakeup via alert */
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 2;
+	wait_args.owner = 123;
+	wait_args.index = 0xdeadbeef;
+	wait_args.alert = event_args.event;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ANY;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(2, wait_args.index);
+
+	close(event_args.event);
+
+	/* test with an auto-reset event */
+
+	event_args.manual = false;
+	event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	count = 1;
+	ret = post_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	close(event_args.event);
+
+	close(objs[0]);
+	close(objs[1]);
+
+	close(fd);
+}
+
+TEST(alert_all)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	struct wait_args thread_args;
+	__u32 index, count, signaled;
+	int objs[2], fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 2;
+	sem_args.max = 2;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+	objs[0] = sem_args.sem;
+
+	sem_args.count = 1;
+	sem_args.max = 2;
+	sem_args.sem = 0xdeadbeef;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(0, ret);
+	EXPECT_NE(0xdeadbeef, sem_args.sem);
+	objs[1] = sem_args.sem;
+
+	event_args.manual = true;
+	event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	/* test wakeup via alert */
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 2;
+	wait_args.owner = 123;
+	wait_args.index = 0xdeadbeef;
+	wait_args.alert = event_args.event;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ALL;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event_args.event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(2, wait_args.index);
+
+	close(event_args.event);
+
+	/* test with an auto-reset event */
+
+	event_args.manual = false;
+	event_args.signaled = true;
+	ret = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+
+	count = 2;
+	ret = post_sem(objs[1], &count);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event_args.event, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	close(event_args.event);
+
+	close(objs[0]);
+	close(objs[1]);
+
+	close(fd);
+}
+
+#define STRESS_LOOPS 10000
+#define STRESS_THREADS 4
+
+static unsigned int stress_counter;
+static int stress_device, stress_start_event, stress_mutex;
+
+static void *stress_thread(void *arg)
+{
+	struct ntsync_wait_args wait_args = {0};
+	__u32 index, count, i;
+	int ret;
+
+	wait_args.timeout = UINT64_MAX;
+	wait_args.count = 1;
+	wait_args.objs = (uintptr_t)&stress_start_event;
+	wait_args.owner = gettid();
+	wait_args.index = 0xdeadbeef;
+
+	ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args);
+
+	wait_args.objs = (uintptr_t)&stress_mutex;
+
+	for (i = 0; i < STRESS_LOOPS; ++i) {
+		ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args);
+
+		++stress_counter;
+
+		unlock_mutex(stress_mutex, wait_args.owner, &count);
+	}
+
+	return NULL;
+}
+
+TEST(stress_wait)
+{
+	struct ntsync_event_args event_args;
+	struct ntsync_mutex_args mutex_args;
+	pthread_t threads[STRESS_THREADS];
+	__u32 signaled, i;
+	int ret;
+
+	stress_device = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, stress_device);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	ret = ioctl(stress_device, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(0, ret);
+	stress_mutex = mutex_args.mutex;
+
+	event_args.manual = 1;
+	event_args.signaled = 0;
+	ret = ioctl(stress_device, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_EQ(0, ret);
+	stress_start_event = event_args.event;
+
+	for (i = 0; i < STRESS_THREADS; ++i)
+		pthread_create(&threads[i], NULL, stress_thread, NULL);
+
+	ret = ioctl(stress_start_event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	for (i = 0; i < STRESS_THREADS; ++i) {
+		ret = pthread_join(threads[i], NULL);
+		EXPECT_EQ(0, ret);
+	}
+
+	EXPECT_EQ(STRESS_LOOPS * STRESS_THREADS, stress_counter);
+
+	close(stress_start_event);
+	close(stress_mutex);
+	close(stress_device);
+}
+
+TEST_HARNESS_MAIN
-- 
2.45.2