This corresponds to part of the functionality of the NT syscall NtWaitForMultipleObjects(). Specifically, it implements the behaviour where the third argument (wait_any) is TRUE, and it does not handle alertable waits. Those features have been split out into separate patches to ease review.

This patch therefore implements the wait/wake infrastructure which comprises the core of ntsync's functionality.

NTSYNC_IOC_WAIT_ANY is a vectored wait function similar to poll(). Unlike poll(), it "consumes" objects when they are signaled. For semaphores, this means decreasing one from the internal counter. At most one object can be consumed by this function.

This wait/wake model is fundamentally different from that used anywhere else in the kernel, and for that reason ntsync does not use any existing infrastructure, such as futexes, kernel mutexes or semaphores, or wait_event().

Up to 64 objects can be waited on at once. As soon as one is signaled, the object with the lowest index is consumed, and that index is returned via the "index" field.

A timeout is supported. The timeout is passed as a u64 nanosecond value, which represents absolute time measured against either the MONOTONIC or REALTIME clock (controlled by the flags argument). If U64_MAX is passed, the ioctl waits indefinitely.

This ioctl validates that all objects belong to the relevant device. This is not necessary for any technical reason related to NTSYNC_IOC_WAIT_ANY, but will be necessary for NTSYNC_IOC_WAIT_ALL introduced in the following patch.

Some padding fields are added for alignment and for fields which will be added in future patches (split out to ease review).

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 245 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/ntsync.h | 14 +++ 2 files changed, 259 insertions(+)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 3c2f743c58b0..d5864891caf0 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -6,11 +6,16 @@ */

#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/overflow.h> +#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <uapi/linux/ntsync.h> @@ -30,6 +35,8 @@ enum ntsync_type { * * 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 { @@ -47,12 +54,55 @@ struct ntsync_obj { __u32 max; } sem; } u; + + struct list_head any_waiters; +}; + +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; + + /* + * 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; + + __u32 count; + struct ntsync_q_entry entries[]; };

struct ntsync_device { struct file *file; };

+static void try_wake_any_sem(struct ntsync_obj *sem) +{ + struct ntsync_q_entry *entry; + + lockdep_assert_held(&sem->lock); + + 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); + } + } +} + /* * Actually change the semaphore state, returning -EOVERFLOW if it is made * invalid. @@ -88,6 +138,8 @@ static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp)

prev_count = sem->u.sem.count; ret = post_sem_state(sem, args); + if (!ret) + try_wake_any_sem(sem);

spin_unlock(&sem->lock);

@@ -141,6 +193,7 @@ static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev, obj->dev = dev; get_file(dev->file); spin_lock_init(&obj->lock); + INIT_LIST_HEAD(&obj->any_waiters);

return obj; } @@ -191,6 +244,196 @@ static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp) return put_user(fd, &user_args->sem); }

+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, + struct ntsync_q **ret_q) +{ + const __u32 count = args->count; + int fds[NTSYNC_MAX_WAIT_COUNT]; + struct ntsync_q *q; + __u32 i, j; + + if (args->pad[0] || args->pad[1] || args->pad[2] || (args->flags & ~NTSYNC_WAIT_REALTIME)) + return -EINVAL; + + if (args->count > NTSYNC_MAX_WAIT_COUNT) + return -EINVAL; + + if (copy_from_user(fds, u64_to_user_ptr(args->objs), + array_size(count, sizeof(*fds)))) + return -EFAULT; + + q = kmalloc(struct_size(q, entries, count), GFP_KERNEL); + if (!q) + return -ENOMEM; + q->task = current; + atomic_set(&q->signaled, -1); + q->count = count; + + for (i = 0; i < count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = get_obj(dev, fds[i]); + + if (!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; + } +} + +static int ntsync_wait_any(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, &q); + if (ret < 0) + return ret; + + /* queue ourselves */ + + for (i = 0; i < args.count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = entry->obj; + + spin_lock(&obj->lock); + list_add_tail(&entry->node, &obj->any_waiters); + spin_unlock(&obj->lock); + } + + /* check if we are already signaled */ + + for (i = 0; i < args.count; i++) { + struct ntsync_obj *obj = q->entries[i].obj; + + if (atomic_read(&q->signaled) != -1) + break; + + spin_lock(&obj->lock); + try_wake_any_obj(obj); + spin_unlock(&obj->lock); + } + + /* sleep */ + + ret = ntsync_schedule(q, &args); + + /* and finally, unqueue */ + + for (i = 0; i < args.count; i++) { + struct ntsync_q_entry *entry = &q->entries[i]; + struct ntsync_obj *obj = entry->obj; + + spin_lock(&obj->lock); + list_del(&entry->node); + spin_unlock(&obj->lock); + + 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 = 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; @@ -222,6 +465,8 @@ static long ntsync_char_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case NTSYNC_IOC_CREATE_SEM: return ntsync_create_sem(dev, argp); + case NTSYNC_IOC_WAIT_ANY: + return ntsync_wait_any(dev, argp); default: return -ENOIOCTLCMD; } diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index dcfa38fdc93c..edc12c7a10dc 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -16,7 +16,21 @@ struct ntsync_sem_args { __u32 max; };

+#define NTSYNC_WAIT_REALTIME 0x1 + +struct ntsync_wait_args { + __u64 timeout; + __u64 objs; + __u32 count; + __u32 index; + __u32 flags; + __u32 pad[3]; +}; + +#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_SEM_POST _IOWR('N', 0x81, __u32)

This corresponds to the NT syscall NtCreateMutant().

An NT mutex is recursive, with a 32-bit recursion counter. When acquired via NtWaitForMultipleObjects(), the recursion counter is incremented by one. The OS records the thread which acquired it.

The OS records the thread which acquired it. However, in order to keep this driver self-contained, the owning thread ID is managed by user-space, and passed as a parameter to all relevant ioctls.

The initial owner and recursion count, if any, are specified when the mutex is created.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 77 +++++++++++++++++++++++++++++++++++-- include/uapi/linux/ntsync.h | 10 ++++- 2 files changed, 83 insertions(+), 4 deletions(-)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index a2f2dfadc3ee..cfe802c79d7d 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -25,6 +25,7 @@

enum ntsync_type { NTSYNC_TYPE_SEM, + NTSYNC_TYPE_MUTEX, };

/* @@ -55,6 +56,10 @@ struct ntsync_obj { __u32 count; __u32 max; } sem; + struct { + __u32 count; + pid_t owner; + } mutex; } u;

/* @@ -92,6 +97,7 @@ struct ntsync_q_entry {

struct ntsync_q { struct task_struct *task; + __u32 owner;

/* * Protected via atomic_try_cmpxchg(). Only the thread that wins the @@ -214,13 +220,17 @@ static void ntsync_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj, ((lockdep_is_held(&(obj)->dev->wait_all_lock) != LOCK_STATE_NOT_HELD) && \ (obj)->dev_locked))

-static bool is_signaled(struct ntsync_obj *obj) +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; }

WARN(1, "bad object type %#x\n", obj->type); @@ -250,7 +260,7 @@ static void try_wake_all(struct ntsync_device *dev, struct ntsync_q *q, }

for (i = 0; i < count; i++) { - if (!is_signaled(q->entries[i].obj)) { + if (!is_signaled(q->entries[i].obj, q->owner)) { can_wake = false; break; } @@ -264,6 +274,10 @@ static void try_wake_all(struct ntsync_device *dev, struct ntsync_q *q, case NTSYNC_TYPE_SEM: obj->u.sem.count--; break; + case NTSYNC_TYPE_MUTEX: + obj->u.mutex.count++; + obj->u.mutex.owner = q->owner; + break; } } wake_up_process(q->task); @@ -307,6 +321,30 @@ static void try_wake_any_sem(struct ntsync_obj *sem) } }

+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)) { + mutex->u.mutex.count++; + mutex->u.mutex.owner = q->owner; + wake_up_process(q->task); + } + } +} + /* * Actually change the semaphore state, returning -EOVERFLOW if it is made * invalid. @@ -455,6 +493,33 @@ static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp) 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 struct ntsync_obj *get_obj(struct ntsync_device *dev, int fd) { struct file *file = fget(fd); @@ -524,7 +589,7 @@ static int setup_wait(struct ntsync_device *dev, struct ntsync_q *q; __u32 i, j;

- if (args->pad[0] || args->pad[1] || args->pad[2] || (args->flags & ~NTSYNC_WAIT_REALTIME)) + if (args->pad[0] || args->pad[1] || (args->flags & ~NTSYNC_WAIT_REALTIME)) return -EINVAL;

if (args->count > NTSYNC_MAX_WAIT_COUNT) @@ -538,6 +603,7 @@ static int setup_wait(struct ntsync_device *dev, if (!q) return -ENOMEM; q->task = current; + q->owner = args->owner; atomic_set(&q->signaled, -1); q->all = all; q->count = count; @@ -580,6 +646,9 @@ static void try_wake_any_obj(struct ntsync_obj *obj) case NTSYNC_TYPE_SEM: try_wake_any_sem(obj); break; + case NTSYNC_TYPE_MUTEX: + try_wake_any_mutex(obj); + break; } }

@@ -769,6 +838,8 @@ static long ntsync_char_ioctl(struct file *file, unsigned int cmd, void __user *argp = (void __user *)parm;

switch (cmd) { + 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: diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index addf187b1573..d5e5a2fbcb4d 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -16,6 +16,12 @@ struct ntsync_sem_args { __u32 max; };

+struct ntsync_mutex_args { + __u32 mutex; + __u32 owner; + __u32 count; +}; + #define NTSYNC_WAIT_REALTIME 0x1

struct ntsync_wait_args { @@ -24,7 +30,8 @@ struct ntsync_wait_args { __u32 count; __u32 index; __u32 flags; - __u32 pad[3]; + __u32 owner; + __u32 pad[2]; };

#define NTSYNC_MAX_WAIT_COUNT 64 @@ -32,6 +39,7 @@ struct ntsync_wait_args { #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_SEM_POST _IOWR('N', 0x81, __u32)

This does not correspond to any NT syscall. Rather, when a thread dies, it should be called by the NT emulator for each mutex, with the TID of the dying thread.

NT mutexes are robust (in the pthread sense). When an NT thread dies, any mutexes it owned are immediately released. Acquisition of those mutexes by other threads will return a special value indicating that the mutex was abandoned, like EOWNERDEAD returned from pthread_mutex_lock(), and EOWNERDEAD is indeed used here for that purpose.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 61 +++++++++++++++++++++++++++++++++++-- include/uapi/linux/ntsync.h | 1 + 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index f00af9b15164..5aaf9dad76b6 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -59,6 +59,7 @@ struct ntsync_obj { struct { __u32 count; pid_t owner; + bool ownerdead; } mutex; } u;

@@ -107,6 +108,7 @@ struct ntsync_q { atomic_t signaled;

bool all; + bool ownerdead; __u32 count; struct ntsync_q_entry entries[]; }; @@ -275,6 +277,9 @@ static void try_wake_all(struct ntsync_device *dev, struct ntsync_q *q, 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; @@ -338,6 +343,9 @@ static void try_wake_any_mutex(struct ntsync_obj *mutex) 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); @@ -447,6 +455,52 @@ static int ntsync_mutex_unlock(struct ntsync_obj *mutex, void __user *argp) 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_obj_release(struct inode *inode, struct file *file) { struct ntsync_obj *obj = file->private_data; @@ -468,6 +522,8 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd, return ntsync_sem_post(obj, argp); case NTSYNC_IOC_MUTEX_UNLOCK: return ntsync_mutex_unlock(obj, argp); + case NTSYNC_IOC_MUTEX_KILL: + return ntsync_mutex_kill(obj, argp); default: return -ENOIOCTLCMD; } @@ -659,6 +715,7 @@ static int setup_wait(struct ntsync_device *dev, q->owner = args->owner; atomic_set(&q->signaled, -1); q->all = all; + q->ownerdead = false; q->count = count;

for (i = 0; i < count; i++) { @@ -767,7 +824,7 @@ static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp) struct ntsync_wait_args __user *user_args = argp;

/* even if we caught a signal, we need to communicate success */ - ret = 0; + ret = q->ownerdead ? -EOWNERDEAD : 0;

if (put_user(signaled, &user_args->index)) ret = -EFAULT; @@ -848,7 +905,7 @@ static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp) struct ntsync_wait_args __user *user_args = argp;

/* even if we caught a signal, we need to communicate success */ - ret = 0; + ret = q->ownerdead ? -EOWNERDEAD : 0;

if (put_user(signaled, &user_args->index)) ret = -EFAULT; diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index a633db34f284..d7996180c1d2 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -43,5 +43,6 @@ struct ntsync_wait_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)

#endif

This corresponds to the NT syscall NtSetEvent().

This sets the event to the signaled state, and returns its previous state.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 27 +++++++++++++++++++++++++++ include/uapi/linux/ntsync.h | 1 + 2 files changed, 28 insertions(+)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 2bce03187c17..97d9b6047fbe 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -534,6 +534,31 @@ static int ntsync_mutex_kill(struct ntsync_obj *mutex, void __user *argp) return ret; }

+static int ntsync_event_set(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 = true; + if (all) + try_wake_all_obj(dev, event); + try_wake_any_event(event); + + ntsync_unlock_obj(dev, event, all); + + if (put_user(prev_state, (__u32 __user *)argp)) + return -EFAULT; + + return 0; +} + static int ntsync_obj_release(struct inode *inode, struct file *file) { struct ntsync_obj *obj = file->private_data; @@ -557,6 +582,8 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd, return ntsync_mutex_unlock(obj, argp); case NTSYNC_IOC_MUTEX_KILL: return ntsync_mutex_kill(obj, argp); + case NTSYNC_IOC_EVENT_SET: + return ntsync_event_set(obj, argp); default: return -ENOIOCTLCMD; } diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index 4c0c4271c7de..36d903521bbe 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -51,5 +51,6 @@ struct ntsync_wait_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)

#endif

This corresponds to the NT syscall NtPulseEvent().

This wakes up any waiters as if the event had been set, but does not set the event, instead resetting it if it had been signalled. Thus, for a manual-reset event, all waiters are woken, whereas for an auto-reset event, at most one waiter is woken.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 8 ++++++-- include/uapi/linux/ntsync.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index b070ceccc3af..b0c1d644f0af 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -534,7 +534,7 @@ static int ntsync_mutex_kill(struct ntsync_obj *mutex, void __user *argp) return ret; }

-static int ntsync_event_set(struct ntsync_obj *event, void __user *argp) +static int ntsync_event_set(struct ntsync_obj *event, void __user *argp, bool pulse) { struct ntsync_device *dev = event->dev; __u32 prev_state; @@ -550,6 +550,8 @@ static int ntsync_event_set(struct ntsync_obj *event, void __user *argp) 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);

@@ -605,9 +607,11 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd, case NTSYNC_IOC_MUTEX_KILL: return ntsync_mutex_kill(obj, argp); case NTSYNC_IOC_EVENT_SET: - return ntsync_event_set(obj, argp); + 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); default: return -ENOIOCTLCMD; } diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index 7fdf79729b20..5586fadd9bdd 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -53,5 +53,6 @@ struct ntsync_wait_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)

#endif

This corresponds to the NT syscall NtQueryMutant().

This returns the recursion count, owner, and abandoned state of the mutex.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 28 ++++++++++++++++++++++++++++ include/uapi/linux/ntsync.h | 1 + 2 files changed, 29 insertions(+)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 4c680a2b8353..622be0075ba4 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -607,6 +607,32 @@ static int ntsync_sem_read(struct ntsync_obj *sem, void __user *argp) 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_obj_release(struct inode *inode, struct file *file) { struct ntsync_obj *obj = file->private_data; @@ -632,6 +658,8 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd, 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: diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index 5e922703686f..eced73d08783 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -55,5 +55,6 @@ struct ntsync_wait_args { #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)

#endif

NT waits can optionally be made "alertable". This is a special channel for thread wakeup that is mildly similar to SIGIO. A thread has an internal single bit of "alerted" state, and if a thread is alerted while an alertable wait, the wait will return a special value, consume the "alerted" state, and will not consume any of its objects.

Alerts are implemented using events; the user-space NT emulator is expected to create an internal ntsync event for each thread and pass that event to wait functions.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- drivers/misc/ntsync.c | 70 ++++++++++++++++++++++++++++++++----- include/uapi/linux/ntsync.h | 3 +- 2 files changed, 63 insertions(+), 10 deletions(-)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index a11fe2469841..87a24798a5c7 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -885,22 +885,29 @@ 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; - int fds[NTSYNC_MAX_WAIT_COUNT]; struct ntsync_q *q; + __u32 total_count; __u32 i, j;

- if (args->pad[0] || args->pad[1] || (args->flags & ~NTSYNC_WAIT_REALTIME)) + 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, count), GFP_KERNEL); + q = kmalloc(struct_size(q, entries, total_count), GFP_KERNEL); if (!q) return -ENOMEM; q->task = current; @@ -910,7 +917,7 @@ static int setup_wait(struct ntsync_device *dev, q->ownerdead = false; q->count = count;

- for (i = 0; i < count; i++) { + for (i = 0; i < total_count; i++) { struct ntsync_q_entry *entry = &q->entries[i]; struct ntsync_obj *obj = get_obj(dev, fds[i]);

@@ -960,10 +967,10 @@ static void try_wake_any_obj(struct ntsync_obj *obj) 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; - __u32 i; int ret;

if (copy_from_user(&args, argp, sizeof(args))) @@ -973,9 +980,13 @@ static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp) if (ret < 0) return ret;

+ total_count = args.count; + if (args.alert) + total_count++; + /* queue ourselves */

- for (i = 0; i < args.count; i++) { + for (i = 0; i < total_count; i++) { struct ntsync_q_entry *entry = &q->entries[i]; struct ntsync_obj *obj = entry->obj;

@@ -984,9 +995,15 @@ static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp) ntsync_unlock_obj(dev, obj, all); }

- /* check if we are already signaled */ + /* + * 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 < args.count; i++) { + for (i = 0; i < total_count; i++) { struct ntsync_obj *obj = q->entries[i].obj;

if (atomic_read(&q->signaled) != -1) @@ -1003,7 +1020,7 @@ static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp)

/* and finally, unqueue */

- for (i = 0; i < args.count; i++) { + for (i = 0; i < total_count; i++) { struct ntsync_q_entry *entry = &q->entries[i]; struct ntsync_obj *obj = entry->obj;

@@ -1063,6 +1080,14 @@ static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp) */ 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 */

@@ -1070,6 +1095,21 @@ static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp)

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); @@ -1095,6 +1135,18 @@ static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp)

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; diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h index 74abeba832f7..4a8095a3fc34 100644 --- a/include/uapi/linux/ntsync.h +++ b/include/uapi/linux/ntsync.h @@ -37,7 +37,8 @@ struct ntsync_wait_args { __u32 index; __u32 flags; __u32 owner; - __u32 pad[2]; + __u32 alert; + __u32 pad; };

#define NTSYNC_MAX_WAIT_COUNT 64

Test mutex-specific ioctls NTSYNC_IOC_MUTEX_UNLOCK and NTSYNC_IOC_MUTEX_READ, and waiting on mutexes.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- .../testing/selftests/drivers/ntsync/ntsync.c | 196 ++++++++++++++++++ 1 file changed, 196 insertions(+)

diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index 1e145c6dfded..7cd0f40594fd 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -40,6 +40,39 @@ 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 wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index) { struct ntsync_wait_args args = {0}; @@ -146,4 +179,167 @@ TEST(semaphore_state) 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_HARNESS_MAIN

Test basic synchronous functionality of NTSYNC_IOC_WAIT_ALL, and when objects are considered simultaneously signaled.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- .../testing/selftests/drivers/ntsync/ntsync.c | 99 ++++++++++++++++++- 1 file changed, 97 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index 40ad8cbd3138..c0f372167557 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -73,7 +73,8 @@ static int unlock_mutex(int mutex, __u32 owner, __u32 *count) return ret; }

-static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index) +static int wait_objs(int fd, unsigned long request, __u32 count, + const int *objs, __u32 owner, __u32 *index) { struct ntsync_wait_args args = {0}; struct timespec timeout; @@ -86,11 +87,21 @@ static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *in args.objs = (uintptr_t)objs; args.owner = owner; args.index = 0xdeadbeef; - ret = ioctl(fd, NTSYNC_IOC_WAIT_ANY, &args); + 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, 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, index); +} + TEST(semaphore_state) { struct ntsync_sem_args sem_args; @@ -461,4 +472,88 @@ TEST(test_wait_any) close(fd); }

+TEST(test_wait_all) +{ + 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); + + 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); + + /* 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(fd); +} + TEST_HARNESS_MAIN

Test contended "wait-for-all" waits, to make sure that scheduling and wakeup logic works correctly, and that the wait only exits once objects are all simultaneously signaled.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- .../testing/selftests/drivers/ntsync/ntsync.c | 98 +++++++++++++++++++ 1 file changed, 98 insertions(+)

diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index 993f5db23768..b77fb0b2c4b1 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -706,4 +706,102 @@ TEST(wake_any) close(fd); }

+TEST(wake_all) +{ + 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; + int objs[2], fd, ret; + __u32 count, index; + 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; + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + 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); + + count = 2; + ret = post_sem(sem_args.sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(sem_args.sem, 1, 3); + check_mutex_state(mutex_args.mutex, 1, 456); + + 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); + + 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_HARNESS_MAIN

Test event-specific ioctls NTSYNC_IOC_EVENT_SET, NTSYNC_IOC_EVENT_RESET, NTSYNC_IOC_EVENT_PULSE, NTSYNC_IOC_EVENT_READ for auto-reset events, and waiting on auto-reset events.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- .../testing/selftests/drivers/ntsync/ntsync.c | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+)

diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index b6481c2b85cc..12ccb4ec28e4 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -442,6 +442,65 @@ TEST(manual_event_state) 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;

Test the "alert" functionality of NTSYNC_IOC_WAIT_ALL and NTSYNC_IOC_WAIT_ANY, when a wait is woken with an alert and when it is woken by an object.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- .../testing/selftests/drivers/ntsync/ntsync.c | 179 +++++++++++++++++- 1 file changed, 176 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index 5d17eff6a370..5465a16d38b3 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -95,7 +95,7 @@ static int read_event_state(int event, __u32 *signaled, __u32 *manual) })

static int wait_objs(int fd, unsigned long request, __u32 count, - const int *objs, __u32 owner, __u32 *index) + const int *objs, __u32 owner, int alert, __u32 *index) { struct ntsync_wait_args args = {0}; struct timespec timeout; @@ -108,6 +108,7 @@ static int wait_objs(int fd, unsigned long request, __u32 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; @@ -115,12 +116,26 @@ static int wait_objs(int fd, unsigned long request, __u32 count,

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, 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, 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) @@ -1095,4 +1110,162 @@ TEST(wake_all) close(fd); }

+TEST(alert_any) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 index, count, signaled; + int objs[2], fd, ret; + + 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); + + 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_sem_args sem_args = {0}; + __u32 index, count, signaled; + int objs[2], fd, ret; + + 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); + + 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); +} + TEST_HARNESS_MAIN

Test a more realistic usage pattern, and one with heavy contention, in order to actually exercise ntsync's internal synchronization.

This test has several threads in a tight loop acquiring a mutex, modifying some shared data, and then releasing the mutex. At the end we check if the data is consistent.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- .../testing/selftests/drivers/ntsync/ntsync.c | 74 +++++++++++++++++++ 1 file changed, 74 insertions(+)

diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index 968874d7e325..5fa2c9a0768c 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -1330,4 +1330,78 @@ TEST(alert_all) 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

Add an overall explanation of the driver architecture, and complete and precise specification for its intended behaviour.

Signed-off-by: Elizabeth Figura zfigura@codeweavers.com --- Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/ntsync.rst | 398 +++++++++++++++++++++++++ 2 files changed, 399 insertions(+) create mode 100644 Documentation/userspace-api/ntsync.rst

diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index afecfe3cc4a8..d5745a500fa7 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/ntsync.rst b/Documentation/userspace-api/ntsync.rst new file mode 100644 index 000000000000..767844637a7d --- /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``.