* [PATCH v7 05/30] ntsync: Introduce NTSYNC_IOC_CREATE_MUTEX.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 74 +++++++++++++++++++++++++++++++++++--
include/uapi/linux/ntsync.h | 9 ++++-
2 files changed, 79 insertions(+), 4 deletions(-)
diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index c8beb5504bcc..a2826dbff2f4 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.
@@ -451,6 +489,30 @@ static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp)
return fd;
}
+static int ntsync_create_mutex(struct ntsync_device *dev, void __user *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;
+}
+
static struct ntsync_obj *get_obj(struct ntsync_device *dev, int fd)
{
struct file *file = fget(fd);
@@ -520,7 +582,7 @@ 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)
@@ -534,6 +596,7 @@ 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;
@@ -576,6 +639,9 @@ 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;
}
}
@@ -765,6 +831,8 @@ 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 d64420ffbcd7..bb7fb94f5856 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -15,6 +15,11 @@ struct ntsync_sem_args {
__u32 max;
};
+struct ntsync_mutex_args {
+ __u32 owner;
+ __u32 count;
+};
+
#define NTSYNC_WAIT_REALTIME 0x1
struct ntsync_wait_args {
@@ -23,7 +28,8 @@ struct ntsync_wait_args {
__u32 count;
__u32 index;
__u32 flags;
- __u32 pad[3];
+ __u32 owner;
+ __u32 pad[2];
};
#define NTSYNC_MAX_WAIT_COUNT 64
@@ -31,6 +37,7 @@ struct ntsync_wait_args {
#define NTSYNC_IOC_CREATE_SEM _IOW ('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 _IOW ('N', 0x84, struct ntsync_mutex_args)
#define NTSYNC_IOC_SEM_RELEASE _IOWR('N', 0x81, __u32)
--
2.45.2
^ permalink raw reply related
* [PATCH v7 13/30] ntsync: Introduce NTSYNC_IOC_MUTEX_READ.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 26 ++++++++++++++++++++++++++
include/uapi/linux/ntsync.h | 1 +
2 files changed, 27 insertions(+)
diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index b2043412c5cd..0047b13b6ebd 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -605,6 +605,30 @@ 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;
+
+ 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;
@@ -630,6 +654,8 @@ 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 e36b4cfb7d34..207646e63ef3 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -52,5 +52,6 @@ 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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 06/30] ntsync: Introduce NTSYNC_IOC_MUTEX_UNLOCK.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
This corresponds to the NT syscall NtReleaseMutant().
This syscall decrements the mutex's recursion count by one, and returns the
previous value. If the mutex is not owned by the current task, the function
instead fails and returns -EPERM.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
drivers/misc/ntsync.c | 53 +++++++++++++++++++++++++++++++++++++
include/uapi/linux/ntsync.h | 1 +
2 files changed, 54 insertions(+)
diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index a2826dbff2f4..33e26240d9e7 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -396,6 +396,57 @@ static int ntsync_sem_release(struct ntsync_obj *sem, void __user *argp)
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;
+}
+
static int ntsync_obj_release(struct inode *inode, struct file *file)
{
struct ntsync_obj *obj = file->private_data;
@@ -415,6 +466,8 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd,
switch (cmd) {
case NTSYNC_IOC_SEM_RELEASE:
return ntsync_sem_release(obj, argp);
+ case NTSYNC_IOC_MUTEX_UNLOCK:
+ return ntsync_mutex_unlock(obj, argp);
default:
return -ENOIOCTLCMD;
}
diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h
index bb7fb94f5856..9186304b253c 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -40,5 +40,6 @@ struct ntsync_wait_args {
#define NTSYNC_IOC_CREATE_MUTEX _IOW ('N', 0x84, struct ntsync_mutex_args)
#define NTSYNC_IOC_SEM_RELEASE _IOWR('N', 0x81, __u32)
+#define NTSYNC_IOC_MUTEX_UNLOCK _IOWR('N', 0x85, struct ntsync_mutex_args)
#endif
--
2.45.2
^ permalink raw reply related
* [PATCH v7 07/30] ntsync: Introduce NTSYNC_IOC_MUTEX_KILL.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 33e26240d9e7..03768ac25425 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_release(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;
}
@@ -652,6 +708,7 @@ 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++) {
@@ -760,7 +817,7 @@ 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;
@@ -841,7 +898,7 @@ 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 9186304b253c..633958d90be3 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -41,5 +41,6 @@ struct ntsync_wait_args {
#define NTSYNC_IOC_SEM_RELEASE _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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 14/30] ntsync: Introduce NTSYNC_IOC_EVENT_READ.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
This corresponds to the NT syscall NtQueryEvent().
This returns the signaled state of the event and whether it is manual-reset.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
drivers/misc/ntsync.c | 24 ++++++++++++++++++++++++
include/uapi/linux/ntsync.h | 1 +
2 files changed, 25 insertions(+)
diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 0047b13b6ebd..78dc405bb759 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -629,6 +629,28 @@ static int ntsync_mutex_read(struct ntsync_obj *mutex, void __user *argp)
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;
+
+ 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;
@@ -662,6 +684,8 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd,
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;
}
diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h
index 207646e63ef3..b9d208a8c00f 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -53,5 +53,6 @@ struct ntsync_wait_args {
#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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 15/30] ntsync: Introduce alertable waits.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 78dc405bb759..457ff28b789f 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -869,22 +869,29 @@ 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;
@@ -894,7 +901,7 @@ 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]);
@@ -944,10 +951,10 @@ 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)))
@@ -957,9 +964,13 @@ 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;
@@ -968,9 +979,15 @@ 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)
@@ -987,7 +1004,7 @@ 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;
@@ -1047,6 +1064,14 @@ 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 */
@@ -1054,6 +1079,21 @@ 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);
@@ -1079,6 +1119,18 @@ 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 b9d208a8c00f..6d06793512b1 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -34,7 +34,8 @@ struct ntsync_wait_args {
__u32 index;
__u32 flags;
__u32 owner;
- __u32 pad[2];
+ __u32 alert;
+ __u32 pad;
};
#define NTSYNC_MAX_WAIT_COUNT 64
--
2.45.2
^ permalink raw reply related
* [PATCH v7 16/30] selftests: ntsync: Add some tests for semaphore state.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Wine has tests for its synchronization primitives, but these are more accessible
to kernel developers, and also allow us to test some edge cases that Wine does
not care about.
This patch adds tests for semaphore-specific ioctls NTSYNC_IOC_SEM_POST and
NTSYNC_IOC_SEM_READ, and waiting on semaphores.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
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 | 145 ++++++++++++++++++
5 files changed, 155 insertions(+)
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/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 2401e973c359..a8c9648e5adc 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -18,6 +18,7 @@ TARGETS += devices/error_logs
TARGETS += devices/probe
TARGETS += dmabuf-heaps
TARGETS += drivers/dma-buf
+TARGETS += drivers/ntsync
TARGETS += drivers/s390x/uvdevice
TARGETS += drivers/net
TARGETS += drivers/net/bonding
diff --git a/tools/testing/selftests/drivers/ntsync/.gitignore b/tools/testing/selftests/drivers/ntsync/.gitignore
new file mode 100644
index 000000000000..848573a3d3ea
--- /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 000000000000..dbf2b055c0b2
--- /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 000000000000..60539c826d06
--- /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 000000000000..cc72da0a91de
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -0,0 +1,145 @@
+// 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 release_sem(int sem, __u32 *count)
+{
+ return ioctl(sem, NTSYNC_IOC_SEM_RELEASE, count);
+}
+
+static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __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;
+ ret = ioctl(fd, NTSYNC_IOC_WAIT_ANY, &args);
+ *index = args.index;
+ return ret;
+}
+
+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 = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_EQ(-1, sem);
+ EXPECT_EQ(EINVAL, errno);
+
+ sem_args.count = 2;
+ sem_args.max = 2;
+ sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, sem);
+ check_sem_state(sem, 2, 2);
+
+ count = 0;
+ ret = release_sem(sem, &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(2, count);
+ check_sem_state(sem, 2, 2);
+
+ count = 1;
+ ret = release_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 = release_sem(sem, &count);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EOVERFLOW, errno);
+ check_sem_state(sem, 0, 2);
+
+ count = 2;
+ ret = release_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 = release_sem(sem, &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, count);
+ check_sem_state(sem, 1, 2);
+
+ count = ~0u;
+ ret = release_sem(sem, &count);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EOVERFLOW, errno);
+ check_sem_state(sem, 1, 2);
+
+ close(sem);
+
+ close(fd);
+}
+
+TEST_HARNESS_MAIN
--
2.45.2
^ permalink raw reply related
* [PATCH v7 17/30] selftests: ntsync: Add some tests for mutex state.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 187 ++++++++++++++++++
1 file changed, 187 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index cc72da0a91de..4db65490b6a1 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -40,6 +40,39 @@ static int release_sem(int sem, __u32 *count)
return ioctl(sem, NTSYNC_IOC_SEM_RELEASE, 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};
@@ -142,4 +175,158 @@ 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;
+ mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_EQ(-1, mutex);
+ EXPECT_EQ(EINVAL, errno);
+
+ mutex_args.owner = 0;
+ mutex_args.count = 2;
+ mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_EQ(-1, mutex);
+ EXPECT_EQ(EINVAL, errno);
+
+ mutex_args.owner = 123;
+ mutex_args.count = 2;
+ mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, 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 = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, 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 = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, 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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 18/30] selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ANY.
From: Elizabeth Figura @ 2024-12-13 19:34 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Test basic synchronous functionality of NTSYNC_IOC_WAIT_ANY, when objects are
considered signaled or not signaled, and how they are affected by a successful
wait.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
.../testing/selftests/drivers/ntsync/ntsync.c | 114 ++++++++++++++++++
1 file changed, 114 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 4db65490b6a1..9781a74253ee 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -329,4 +329,118 @@ TEST(mutex_state)
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;
+ objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[0]);
+
+ mutex_args.owner = 0;
+ mutex_args.count = 0;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, objs[1]);
+
+ ret = wait_any(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+ check_sem_state(objs[0], 1, 3);
+ check_mutex_state(objs[1], 0, 0);
+
+ ret = wait_any(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+ check_sem_state(objs[0], 0, 3);
+ check_mutex_state(objs[1], 0, 0);
+
+ ret = wait_any(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, index);
+ check_sem_state(objs[0], 0, 3);
+ check_mutex_state(objs[1], 1, 123);
+
+ count = 1;
+ ret = release_sem(objs[0], &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(objs[0], 0, 3);
+ check_mutex_state(objs[1], 1, 123);
+
+ ret = wait_any(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, index);
+ check_sem_state(objs[0], 0, 3);
+ check_mutex_state(objs[1], 2, 123);
+
+ ret = wait_any(fd, 2, objs, 456, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+
+ owner = 123;
+ ret = ioctl(objs[1], 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);
+
+ close(objs[1]);
+
+ /* test waiting on the same object twice */
+
+ count = 2;
+ ret = release_sem(objs[0], &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, count);
+
+ objs[1] = objs[0];
+ ret = wait_any(fd, 2, objs, 456, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+ check_sem_state(objs[0], 1, 3);
+
+ ret = wait_any(fd, 0, NULL, 456, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+
+ for (i = 1; i < NTSYNC_MAX_WAIT_COUNT + 1; ++i)
+ objs[i] = objs[0];
+
+ 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(objs[0]);
+
+ close(fd);
+}
+
TEST_HARNESS_MAIN
--
2.45.2
^ permalink raw reply related
* [PATCH v7 19/30] selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ALL.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 93 ++++++++++++++++++-
1 file changed, 91 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 9781a74253ee..aba11eaf9a7c 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;
@@ -443,4 +454,82 @@ 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;
+ objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[0]);
+
+ mutex_args.owner = 0;
+ mutex_args.count = 0;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, objs[1]);
+
+ ret = wait_all(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+ check_sem_state(objs[0], 1, 3);
+ check_mutex_state(objs[1], 1, 123);
+
+ ret = wait_all(fd, 2, objs, 456, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+ check_sem_state(objs[0], 1, 3);
+ check_mutex_state(objs[1], 1, 123);
+
+ ret = wait_all(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+ check_sem_state(objs[0], 0, 3);
+ check_mutex_state(objs[1], 2, 123);
+
+ ret = wait_all(fd, 2, objs, 123, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+ check_sem_state(objs[0], 0, 3);
+ check_mutex_state(objs[1], 2, 123);
+
+ count = 3;
+ ret = release_sem(objs[0], &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(objs[0], 2, 3);
+ check_mutex_state(objs[1], 3, 123);
+
+ owner = 123;
+ ret = ioctl(objs[1], 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(objs[0], 1, 3);
+ check_mutex_state(objs[1], 1, 123);
+
+ close(objs[1]);
+
+ /* test waiting on the same object twice */
+ objs[1] = objs[0];
+ ret = wait_all(fd, 2, objs, 123, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EINVAL, errno);
+
+ close(objs[0]);
+
+ close(fd);
+}
+
TEST_HARNESS_MAIN
--
2.45.2
^ permalink raw reply related
* [PATCH v7 20/30] selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ANY.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Test contended "wait-for-any" waits, to make sure that scheduling and wakeup
logic works correctly.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
.../testing/selftests/drivers/ntsync/ntsync.c | 143 ++++++++++++++++++
1 file changed, 143 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index aba11eaf9a7c..ad3f031c0b92 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -532,4 +532,147 @@ TEST(test_wait_all)
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_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;
+ objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[0]);
+
+ mutex_args.owner = 123;
+ mutex_args.count = 1;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, objs[1]);
+
+ /* 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 = release_sem(objs[0], &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, count);
+ check_sem_state(objs[0], 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, &objs[1], 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(objs[1], 123, &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(2, count);
+
+ ret = pthread_tryjoin_np(thread, NULL);
+ EXPECT_EQ(EBUSY, ret);
+
+ ret = unlock_mutex(objs[1], 123, &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, mutex_args.count);
+ check_mutex_state(objs[1], 1, 456);
+
+ ret = wait_for_thread(thread, 100);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, thread_args.ret);
+ EXPECT_EQ(1, wait_args.index);
+
+ /* 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(objs[0]);
+ close(objs[1]);
+
+ 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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 21/30] selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ALL.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 91 +++++++++++++++++++
1 file changed, 91 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index ad3f031c0b92..6bf0f10679d8 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -675,4 +675,95 @@ 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;
+ objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[0]);
+
+ mutex_args.owner = 123;
+ mutex_args.count = 1;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, objs[1]);
+
+ 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 = release_sem(objs[0], &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, count);
+
+ ret = pthread_tryjoin_np(thread, NULL);
+ EXPECT_EQ(EBUSY, ret);
+
+ check_sem_state(objs[0], 1, 3);
+
+ ret = wait_any(fd, 1, &objs[0], 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+
+ ret = unlock_mutex(objs[1], 123, &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, count);
+
+ ret = pthread_tryjoin_np(thread, NULL);
+ EXPECT_EQ(EBUSY, ret);
+
+ check_mutex_state(objs[1], 0, 0);
+
+ count = 2;
+ ret = release_sem(objs[0], &count);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, count);
+ check_sem_state(objs[0], 1, 3);
+ check_mutex_state(objs[1], 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(objs[0]);
+ close(objs[1]);
+
+ 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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 22/30] selftests: ntsync: Add some tests for manual-reset event state.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Test event-specific ioctls NTSYNC_IOC_EVENT_SET, NTSYNC_IOC_EVENT_RESET,
NTSYNC_IOC_EVENT_PULSE, NTSYNC_IOC_EVENT_READ for manual-reset events, and
waiting on manual-reset events.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
.../testing/selftests/drivers/ntsync/ntsync.c | 86 +++++++++++++++++++
1 file changed, 86 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 6bf0f10679d8..4024a5c48bbb 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -73,6 +73,27 @@ static int unlock_mutex(int mutex, __u32 owner, __u32 *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, __u32 *index)
{
@@ -340,6 +361,71 @@ TEST(mutex_state)
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 = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, 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(test_wait_any)
{
int objs[NTSYNC_MAX_WAIT_COUNT + 1], fd, ret;
--
2.45.2
^ permalink raw reply related
* [PATCH v7 23/30] selftests: ntsync: Add some tests for auto-reset event state.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 56 +++++++++++++++++++
1 file changed, 56 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 4024a5c48bbb..66a096cb2045 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -426,6 +426,62 @@ 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 = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, 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;
--
2.45.2
^ permalink raw reply related
* [PATCH v7 24/30] selftests: ntsync: Add some tests for wakeup signaling with events.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Expand the contended wait tests, which previously only covered events and
semaphores, to cover events as well.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
.../testing/selftests/drivers/ntsync/ntsync.c | 145 +++++++++++++++++-
1 file changed, 141 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 66a096cb2045..33348f0b621f 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -598,6 +598,7 @@ TEST(test_wait_any)
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;
@@ -663,6 +664,19 @@ TEST(test_wait_all)
close(objs[1]);
+ event_args.manual = true;
+ event_args.signaled = true;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, objs[1]);
+
+ ret = wait_all(fd, 2, objs, 123, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+ check_sem_state(objs[0], 0, 3);
+ check_event_state(objs[1], 1, 1);
+
+ close(objs[1]);
+
/* test waiting on the same object twice */
objs[1] = objs[0];
ret = wait_all(fd, 2, objs, 123, &index);
@@ -716,12 +730,13 @@ static int wait_for_thread(pthread_t thread, unsigned int ms)
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;
- __u32 count, index;
pthread_t thread;
fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
@@ -796,6 +811,94 @@ TEST(wake_any)
EXPECT_EQ(0, thread_args.ret);
EXPECT_EQ(1, wait_args.index);
+ close(objs[1]);
+
+ /* test waking events */
+
+ event_args.manual = false;
+ event_args.signaled = false;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, objs[1]);
+
+ 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(objs[1], NTSYNC_IOC_EVENT_SET, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, signaled);
+ check_event_state(objs[1], 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(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, signaled);
+ check_event_state(objs[1], 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(objs[1]);
+
+ event_args.manual = true;
+ event_args.signaled = false;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, objs[1]);
+
+ 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(objs[1], NTSYNC_IOC_EVENT_SET, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, signaled);
+ check_event_state(objs[1], 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(objs[1], 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(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, signaled);
+ check_event_state(objs[1], 0, 1);
+
+ ret = wait_for_thread(thread, 100);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, thread_args.ret);
+ EXPECT_EQ(1, wait_args.index);
+
/* delete an object while it's being waited on */
wait_args.timeout = get_abs_timeout(200);
@@ -819,12 +922,14 @@ TEST(wake_any)
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;
- int objs[2], fd, ret;
- __u32 count, index;
+ __u32 count, index, signaled;
+ int objs[4], fd, ret;
pthread_t thread;
fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
@@ -840,9 +945,19 @@ TEST(wake_all)
objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
EXPECT_LE(0, objs[1]);
+ manual_event_args.manual = true;
+ manual_event_args.signaled = true;
+ objs[2] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &manual_event_args);
+ EXPECT_LE(0, objs[2]);
+
+ auto_event_args.manual = false;
+ auto_event_args.signaled = true;
+ objs[3] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &auto_event_args);
+ EXPECT_EQ(0, objs[3]);
+
wait_args.timeout = get_abs_timeout(1000);
wait_args.objs = (uintptr_t)objs;
- wait_args.count = 2;
+ wait_args.count = 4;
wait_args.owner = 456;
thread_args.fd = fd;
thread_args.args = &wait_args;
@@ -876,12 +991,32 @@ TEST(wake_all)
check_mutex_state(objs[1], 0, 0);
+ ret = ioctl(objs[2], NTSYNC_IOC_EVENT_RESET, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, signaled);
+
count = 2;
ret = release_sem(objs[0], &count);
EXPECT_EQ(0, ret);
EXPECT_EQ(0, count);
+ check_sem_state(objs[0], 2, 3);
+
+ ret = ioctl(objs[3], NTSYNC_IOC_EVENT_RESET, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, signaled);
+
+ ret = ioctl(objs[2], NTSYNC_IOC_EVENT_SET, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, signaled);
+
+ ret = ioctl(objs[3], NTSYNC_IOC_EVENT_SET, &signaled);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, signaled);
+
check_sem_state(objs[0], 1, 3);
check_mutex_state(objs[1], 1, 456);
+ check_event_state(objs[2], 1, 1);
+ check_event_state(objs[3], 0, 0);
ret = wait_for_thread(thread, 100);
EXPECT_EQ(0, ret);
@@ -899,6 +1034,8 @@ TEST(wake_all)
close(objs[0]);
close(objs[1]);
+ close(objs[2]);
+ close(objs[3]);
ret = wait_for_thread(thread, 200);
EXPECT_EQ(0, ret);
--
2.45.2
^ permalink raw reply related
* [PATCH v7 25/30] selftests: ntsync: Add tests for alertable waits.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 167 +++++++++++++++++-
1 file changed, 164 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 33348f0b621f..72f078dde444 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)
@@ -1045,4 +1060,150 @@ 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], event, fd, ret;
+
+ fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+ ASSERT_LE(0, fd);
+
+ sem_args.count = 0;
+ sem_args.max = 2;
+ objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[0]);
+
+ sem_args.count = 1;
+ sem_args.max = 2;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[1]);
+
+ event_args.manual = true;
+ event_args.signaled = true;
+ event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, event);
+
+ ret = wait_any_alert(fd, 0, NULL, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+
+ ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+ EXPECT_EQ(0, ret);
+
+ ret = wait_any_alert(fd, 0, NULL, 123, event, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+
+ ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+ EXPECT_EQ(0, ret);
+
+ ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(1, index);
+
+ ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(2, index);
+
+ close(event);
+
+ /* test with an auto-reset event */
+
+ event_args.manual = false;
+ event_args.signaled = true;
+ event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, event);
+
+ count = 1;
+ ret = release_sem(objs[0], &count);
+ EXPECT_EQ(0, ret);
+
+ ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+
+ ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(2, index);
+
+ ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+
+ close(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], event, fd, ret;
+
+ fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+ ASSERT_LE(0, fd);
+
+ sem_args.count = 2;
+ sem_args.max = 2;
+ objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[0]);
+
+ sem_args.count = 1;
+ sem_args.max = 2;
+ objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+ EXPECT_LE(0, objs[1]);
+
+ event_args.manual = true;
+ event_args.signaled = true;
+ event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, event);
+
+ ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+
+ ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(2, index);
+
+ close(event);
+
+ /* test with an auto-reset event */
+
+ event_args.manual = false;
+ event_args.signaled = true;
+ event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, event);
+
+ count = 2;
+ ret = release_sem(objs[1], &count);
+ EXPECT_EQ(0, ret);
+
+ ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, index);
+
+ ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(2, index);
+
+ ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(ETIMEDOUT, errno);
+
+ close(event);
+
+ close(objs[0]);
+ close(objs[1]);
+
+ close(fd);
+}
+
TEST_HARNESS_MAIN
--
2.45.2
^ permalink raw reply related
* [PATCH v7 26/30] selftests: ntsync: Add some tests for wakeup signaling via alerts.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Expand the alert tests to cover alerting a thread mid-wait, to test that the
relevant scheduling logic works correctly.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
.../testing/selftests/drivers/ntsync/ntsync.c | 62 +++++++++++++++++++
1 file changed, 62 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 72f078dde444..298b279729aa 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -1063,9 +1063,12 @@ TEST(wake_all)
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], event, fd, ret;
+ pthread_t thread;
fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
ASSERT_LE(0, fd);
@@ -1107,6 +1110,34 @@ TEST(alert_any)
EXPECT_EQ(0, ret);
EXPECT_EQ(2, index);
+ /* test wakeup via alert */
+
+ ret = ioctl(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;
+ 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, 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);
/* test with an auto-reset event */
@@ -1143,9 +1174,12 @@ TEST(alert_any)
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], event, fd, ret;
+ pthread_t thread;
fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
ASSERT_LE(0, fd);
@@ -1173,6 +1207,34 @@ TEST(alert_all)
EXPECT_EQ(0, ret);
EXPECT_EQ(2, index);
+ /* test wakeup via alert */
+
+ ret = ioctl(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;
+ 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, 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);
/* test with an auto-reset event */
--
2.45.2
^ permalink raw reply related
* [PATCH v7 27/30] selftests: ntsync: Add a stress test for contended waits.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 72 +++++++++++++++++++
1 file changed, 72 insertions(+)
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
index 298b279729aa..3aad311574c4 100644
--- a/tools/testing/selftests/drivers/ntsync/ntsync.c
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -1268,4 +1268,76 @@ 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;
+ stress_mutex = ioctl(stress_device, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+ EXPECT_LE(0, stress_mutex);
+
+ event_args.manual = 1;
+ event_args.signaled = 0;
+ stress_start_event = ioctl(stress_device, NTSYNC_IOC_CREATE_EVENT, &event_args);
+ EXPECT_LE(0, stress_start_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
^ permalink raw reply related
* [PATCH v7 28/30] maintainers: Add an entry for ntsync.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
Add myself as maintainer, supported by CodeWeavers.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
MAINTAINERS | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 1e930c7a58b1..8c3dd9077fc2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16708,6 +16708,15 @@ 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
--
2.45.2
^ permalink raw reply related
* [PATCH v7 29/30] docs: ntsync: Add documentation for the ntsync uAPI.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
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 | 385 +++++++++++++++++++++++++
2 files changed, 386 insertions(+)
create mode 100644 Documentation/userspace-api/ntsync.rst
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 274cc7546efc..9c1b15cd89ab 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -63,6 +63,7 @@ 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..25e7c4aef968
--- /dev/null
+++ b/Documentation/userspace-api/ntsync.rst
@@ -0,0 +1,385 @@
+===================================
+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 count;
+ __u32 max;
+ };
+
+ struct ntsync_mutex_args {
+ __u32 owner;
+ __u32 count;
+ };
+
+ struct ntsync_event_args {
+ __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.
+
+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::
+
+ * - ``count``
+ - Initial count of the semaphore.
+ * - ``max``
+ - Maximum count of the semaphore.
+
+ Fails with ``EINVAL`` if ``count`` is greater than ``max``.
+ On success, returns a file descriptor the created semaphore.
+
+.. 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::
+
+ * - ``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``.
+ On success, returns a file descriptor the created mutex.
+
+.. 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::
+
+ * - ``signaled``
+ - If nonzero, the event is initially signaled, otherwise
+ nonsignaled.
+ * - ``manual``
+ - If nonzero, the event is a manual-reset event, otherwise
+ auto-reset.
+
+ On success, returns a file descriptor the created event.
+
+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::
+
+ * - ``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::
+
+ * - ``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::
+
+ * - ``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::
+
+ * - ``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``.
--
2.45.2
^ permalink raw reply related
* [PATCH v7 30/30] ntsync: No longer depend on BROKEN.
From: Elizabeth Figura @ 2024-12-13 19:35 UTC (permalink / raw)
To: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan
Cc: linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Peter Zijlstra, Andy Lutomirski,
linux-doc, linux-kselftest, Randy Dunlap, Ingo Molnar,
Will Deacon, Waiman Long, Boqun Feng, Elizabeth Figura
In-Reply-To: <20241213193511.457338-1-zfigura@codeweavers.com>
f5b335dc025cfee90957efa90dc72fada0d5abb4 ("misc: ntsync: mark driver as "broken"
to prevent from building") was committed to avoid the driver being used while
only part of its functionality was released. Since the rest of the functionality
has now been committed, revert this.
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
drivers/misc/Kconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 09cbe3f0ab1e..fb772bfe27c3 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -517,7 +517,6 @@ config OPEN_DICE
config NTSYNC
tristate "NT synchronization primitive emulation"
- depends on BROKEN
help
This module provides kernel support for emulation of Windows NT
synchronization primitives. It is not a hardware driver.
--
2.45.2
^ permalink raw reply related
* [PATCH v3 0/3] futex: Create set_robust_list2
From: André Almeida @ 2024-12-17 17:49 UTC (permalink / raw)
To: Thomas Gleixner, Ingo Molnar, Peter Zijlstra, Darren Hart,
Davidlohr Bueso, Arnd Bergmann, sonicadvance1
Cc: linux-kernel, kernel-dev, linux-api, Nathan Chancellor,
Vinicius Peixoto, André Almeida
This patch adds a new robust_list() syscall. The current syscall
can't be expanded to cover the following use case, so a new one is
needed. This new syscall allows users to set multiple robust lists per
process and to have either 32bit or 64bit pointers in the list.
* Use case
FEX-Emu[1] is an application that runs x86 and x86-64 binaries on an
AArch64 Linux host. One of the tasks of FEX-Emu is to translate syscalls
from one platform to another. Existing set_robust_list() can't be easily
translated because of two limitations:
1) x86 apps can have 32bit pointers robust lists. For a x86-64 kernel
this is not a problem, because of the compat entry point. But there's
no such compat entry point for AArch64, so the kernel would do the
pointer arithmetic wrongly. Is also unviable to userspace to keep
track every addition/removal to the robust list and keep a 64bit
version of it somewhere else to feed the kernel. Thus, the new
interface has an option of telling the kernel if the list is filled
with 32bit or 64bit pointers.
2) Apps can set just one robust list (in theory, x86-64 can set two if
they also use the compat entry point). That means that when a x86 app
asks FEX-Emu to call set_robust_list(), FEX have two options: to
overwrite their own robust list pointer and make the app robust, or
to ignore the app robust list and keep the emulator robust. The new
interface allows for multiple robust lists per application, solving
this.
* Interface
This is the proposed interface:
long set_robust_list2(void *head, int index, unsigned int flags)
`head` is the head of the userspace struct robust_list_head, just as old
set_robust_list(). It needs to be a void pointer since it can point to a normal
robust_list_head or a compat_robust_list_head.
`flags` can be used for defining the list type:
enum robust_list_type {
ROBUST_LIST_32BIT,
ROBUST_LIST_64BIT,
};
`index` is the index in the internal robust_list's linked list (the naming
starts to get confusing, I reckon). If `index == -1`, that means that user wants
to set a new robust_list, and the kernel will append it in the end of the list,
assign a new index and return this index to the user. If `index >= 0`, that
means that user wants to re-set `*head` of an already existing list (similarly
to what happens when you call set_robust_list() twice with different `*head`).
If `index` is out of range, or it points to a non-existing robust_list, or if
the internal list is full, an error is returned.
* Implementation
The implementation re-uses most of the existing robust list interface as
possible. The new task_struct member `struct list_head robust_list2` is just a
linked list where new lists are appended as the user requests more lists, and by
futex_cleanup(), the kernel walks through the internal list feeding
exit_robust_list() with the robust_list's.
This implementation supports up to 10 lists (defined at ROBUST_LISTS_PER_TASK),
but it was an arbitrary number for this RFC. For the described use case above, 4
should be enough, I'm not sure which should be the limit.
It doesn't support list removal (should it support?). It doesn't have a proper
get_robust_list2() yet as well, but I can add it in a next revision. We could
also have a generic robust_list() syscall that can be used to set/get and be
controlled by flags.
The new interface has a `unsigned int flags` argument, making it
extensible for future use cases as well.
* Testing
I will provide a selftest similar to the one I proposed for the current
interface here:
https://lore.kernel.org/lkml/20241010011142.905297-1-andrealmeid@igalia.com/
Also, FEX-Emu added support for this interface to validate it:
https://github.com/FEX-Emu/FEX/pull/3966
Feedback is very welcomed!
Thanks,
André
[1] https://github.com/FEX-Emu/FEX
Changelog:
- Old syscall set_robust_list() adds new head to the internal linked list of
robust lists pointers, instead of having a field just for them. Remove
tsk->robust_list and use only tsk->robust_list2
v2: https://lore.kernel.org/lkml/20241101162147.284993-1-andrealmeid@igalia.com/
- Added a patch to properly deal with exit_robust_list() in 64bit vs 32bit
- Wired-up syscall for all archs
- Added more of the cover letter to the commit message
v1: https://lore.kernel.org/lkml/20241024145735.162090-1-andrealmeid@igalia.com/
André Almeida (3):
futex: Use explicit sizes for compat_exit_robust_list
futex: Create set_robust_list2
futex: Wire up set_robust_list2 syscall
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
arch/arm/tools/syscall.tbl | 1 +
arch/m68k/kernel/syscalls/syscall.tbl | 1 +
arch/microblaze/kernel/syscalls/syscall.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n32.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n64.tbl | 1 +
arch/mips/kernel/syscalls/syscall_o32.tbl | 1 +
arch/parisc/kernel/syscalls/syscall.tbl | 1 +
arch/powerpc/kernel/syscalls/syscall.tbl | 1 +
arch/s390/kernel/syscalls/syscall.tbl | 1 +
arch/sh/kernel/syscalls/syscall.tbl | 1 +
arch/sparc/kernel/syscalls/syscall.tbl | 1 +
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
arch/xtensa/kernel/syscalls/syscall.tbl | 1 +
include/linux/compat.h | 12 +-
include/linux/futex.h | 16 ++-
include/linux/sched.h | 5 +-
include/uapi/asm-generic/unistd.h | 4 +-
include/uapi/linux/futex.h | 24 ++++
kernel/futex/core.c | 130 ++++++++++++++++----
kernel/futex/futex.h | 5 +
kernel/futex/syscalls.c | 82 +++++++++++-
kernel/sys_ni.c | 1 +
scripts/syscall.tbl | 1 +
25 files changed, 249 insertions(+), 46 deletions(-)
--
2.47.1
^ permalink raw reply
* [PATCH v3 1/3] futex: Use explicit sizes for compat_exit_robust_list
From: André Almeida @ 2024-12-17 17:49 UTC (permalink / raw)
To: Thomas Gleixner, Ingo Molnar, Peter Zijlstra, Darren Hart,
Davidlohr Bueso, Arnd Bergmann, sonicadvance1
Cc: linux-kernel, kernel-dev, linux-api, Nathan Chancellor,
Vinicius Peixoto, André Almeida
In-Reply-To: <20241217174958.477692-1-andrealmeid@igalia.com>
There are two functions for handling robust lists during the task
exit: exit_robust_list() and compat_exit_robust_list(). The first one
handles either 64bit or 32bit lists, depending if it's a 64bit or 32bit
kernel. The compat_exit_robust_list() only exists in 64bit kernels that
supports 32bit syscalls, and handles 32bit lists.
For the new syscall set_robust_list2(), 64bit kernels need to be able to
handle 32bit lists despite having or not support for 32bit syscalls, so
make compat_exit_robust_list() exist regardless of compat_ config.
Also, use explicitly sizing, otherwise in a 32bit kernel both
exit_robust_list() and compat_exit_robust_list() would be the exactly
same function, with none of them dealing with 64bit robust lists.
Signed-off-by: André Almeida <andrealmeid@igalia.com>
---
include/linux/compat.h | 12 +----------
include/linux/futex.h | 11 +++++++++++
include/linux/sched.h | 2 +-
kernel/futex/core.c | 44 ++++++++++++++++++++++++++---------------
kernel/futex/syscalls.c | 4 ++--
5 files changed, 43 insertions(+), 30 deletions(-)
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 56cebaff0c91..968a9135ff48 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -385,16 +385,6 @@ struct compat_ifconf {
compat_caddr_t ifcbuf;
};
-struct compat_robust_list {
- compat_uptr_t next;
-};
-
-struct compat_robust_list_head {
- struct compat_robust_list list;
- compat_long_t futex_offset;
- compat_uptr_t list_op_pending;
-};
-
#ifdef CONFIG_COMPAT_OLD_SIGACTION
struct compat_old_sigaction {
compat_uptr_t sa_handler;
@@ -672,7 +662,7 @@ asmlinkage long compat_sys_waitid(int, compat_pid_t,
struct compat_siginfo __user *, int,
struct compat_rusage __user *);
asmlinkage long
-compat_sys_set_robust_list(struct compat_robust_list_head __user *head,
+compat_sys_set_robust_list(struct robust_list_head32 __user *head,
compat_size_t len);
asmlinkage long
compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
diff --git a/include/linux/futex.h b/include/linux/futex.h
index b70df27d7e85..8217b5ebdd9c 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -53,6 +53,17 @@ union futex_key {
#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } }
#ifdef CONFIG_FUTEX
+
+struct robust_list32 {
+ u32 next;
+};
+
+struct robust_list_head32 {
+ struct robust_list32 list;
+ s32 futex_offset;
+ u32 list_op_pending;
+};
+
enum {
FUTEX_STATE_OK,
FUTEX_STATE_EXITING,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 66b311fbd5d6..da573c16e93e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1292,7 +1292,7 @@ struct task_struct {
#ifdef CONFIG_FUTEX
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
- struct compat_robust_list_head __user *compat_robust_list;
+ struct robust_list_head32 __user *compat_robust_list;
#endif
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index ebdd76b4ecbb..cc2d0f00cd6b 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -768,13 +768,14 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
return 0;
}
+#ifdef CONFIG_64BIT
/*
* Walk curr->robust_list (very carefully, it's a userspace list!)
* and mark any locks found there dead, and notify any waiters.
*
* We silently return on any sign of list-walking problem.
*/
-static void exit_robust_list(struct task_struct *curr)
+static void exit_robust_list64(struct task_struct *curr)
{
struct robust_list_head __user *head = curr->robust_list;
struct robust_list __user *entry, *next_entry, *pending;
@@ -835,8 +836,13 @@ static void exit_robust_list(struct task_struct *curr)
curr, pip, HANDLE_DEATH_PENDING);
}
}
+#else
+static void exit_robust_list64(struct task_struct *curr)
+{
+ pr_warn("32bit kernel should not allow ROBUST_LIST_64BIT");
+}
+#endif
-#ifdef CONFIG_COMPAT
static void __user *futex_uaddr(struct robust_list __user *entry,
compat_long_t futex_offset)
{
@@ -850,13 +856,13 @@ static void __user *futex_uaddr(struct robust_list __user *entry,
* Fetch a robust-list pointer. Bit 0 signals PI futexes:
*/
static inline int
-compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
- compat_uptr_t __user *head, unsigned int *pi)
+fetch_robust_entry32(u32 *uentry, struct robust_list __user **entry,
+ u32 __user *head, unsigned int *pi)
{
if (get_user(*uentry, head))
return -EFAULT;
- *entry = compat_ptr((*uentry) & ~1);
+ *entry = (void __user *)(unsigned long)((*uentry) & ~1);
*pi = (unsigned int)(*uentry) & 1;
return 0;
@@ -868,21 +874,21 @@ compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **ent
*
* We silently return on any sign of list-walking problem.
*/
-static void compat_exit_robust_list(struct task_struct *curr)
+static void exit_robust_list32(struct task_struct *curr)
{
- struct compat_robust_list_head __user *head = curr->compat_robust_list;
+ struct robust_list_head32 __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
- compat_uptr_t uentry, next_uentry, upending;
- compat_long_t futex_offset;
+ u32 uentry, next_uentry, upending;
+ s32 futex_offset;
int rc;
/*
* Fetch the list head (which was registered earlier, via
* sys_set_robust_list()):
*/
- if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
+ if (fetch_robust_entry32((u32 *)&uentry, &entry, (u32 *)&head->list.next, &pi))
return;
/*
* Fetch the relative futex offset:
@@ -893,7 +899,7 @@ static void compat_exit_robust_list(struct task_struct *curr)
* Fetch any possibly pending lock-add first, and handle it
* if it exists:
*/
- if (compat_fetch_robust_entry(&upending, &pending,
+ if (fetch_robust_entry32(&upending, &pending,
&head->list_op_pending, &pip))
return;
@@ -903,8 +909,8 @@ static void compat_exit_robust_list(struct task_struct *curr)
* Fetch the next entry in the list before calling
* handle_futex_death:
*/
- rc = compat_fetch_robust_entry(&next_uentry, &next_entry,
- (compat_uptr_t __user *)&entry->next, &next_pi);
+ rc = fetch_robust_entry32(&next_uentry, &next_entry,
+ (u32 __user *)&entry->next, &next_pi);
/*
* A pending lock might already be on the list, so
* dont process it twice:
@@ -935,7 +941,6 @@ static void compat_exit_robust_list(struct task_struct *curr)
handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING);
}
}
-#endif
#ifdef CONFIG_FUTEX_PI
@@ -1018,14 +1023,21 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
static void futex_cleanup(struct task_struct *tsk)
{
+#ifdef CONFIG_64BIT
if (unlikely(tsk->robust_list)) {
- exit_robust_list(tsk);
+ exit_robust_list64(tsk);
tsk->robust_list = NULL;
}
+#else
+ if (unlikely(tsk->robust_list)) {
+ exit_robust_list32(tsk);
+ tsk->robust_list = NULL;
+ }
+#endif
#ifdef CONFIG_COMPAT
if (unlikely(tsk->compat_robust_list)) {
- compat_exit_robust_list(tsk);
+ exit_robust_list32(tsk);
tsk->compat_robust_list = NULL;
}
#endif
diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c
index 4b6da9116aa6..dba193dfd216 100644
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -440,7 +440,7 @@ SYSCALL_DEFINE4(futex_requeue,
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(set_robust_list,
- struct compat_robust_list_head __user *, head,
+ struct robust_list_head32 __user *, head,
compat_size_t, len)
{
if (unlikely(len != sizeof(*head)))
@@ -455,7 +455,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
compat_uptr_t __user *, head_ptr,
compat_size_t __user *, len_ptr)
{
- struct compat_robust_list_head __user *head;
+ struct robust_list_head32 __user *head;
unsigned long ret;
struct task_struct *p;
--
2.47.1
^ permalink raw reply related
* [PATCH v3 3/3] futex: Wire up set_robust_list2 syscall
From: André Almeida @ 2024-12-17 17:49 UTC (permalink / raw)
To: Thomas Gleixner, Ingo Molnar, Peter Zijlstra, Darren Hart,
Davidlohr Bueso, Arnd Bergmann, sonicadvance1
Cc: linux-kernel, kernel-dev, linux-api, Nathan Chancellor,
Vinicius Peixoto, André Almeida
In-Reply-To: <20241217174958.477692-1-andrealmeid@igalia.com>
Wire up the new set_robust_list2 syscall in all available architectures.
Signed-off-by: André Almeida <andrealmeid@igalia.com>
---
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
arch/arm/tools/syscall.tbl | 1 +
arch/m68k/kernel/syscalls/syscall.tbl | 1 +
arch/microblaze/kernel/syscalls/syscall.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n32.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n64.tbl | 1 +
arch/mips/kernel/syscalls/syscall_o32.tbl | 1 +
arch/parisc/kernel/syscalls/syscall.tbl | 1 +
arch/powerpc/kernel/syscalls/syscall.tbl | 1 +
arch/s390/kernel/syscalls/syscall.tbl | 1 +
arch/sh/kernel/syscalls/syscall.tbl | 1 +
arch/sparc/kernel/syscalls/syscall.tbl | 1 +
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
arch/xtensa/kernel/syscalls/syscall.tbl | 1 +
kernel/sys_ni.c | 1 +
scripts/syscall.tbl | 1 +
17 files changed, 17 insertions(+)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index c59d53d6d3f3..d1193a7f948e 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -506,3 +506,4 @@
574 common getxattrat sys_getxattrat
575 common listxattrat sys_listxattrat
576 common removexattrat sys_removexattrat
+577 common set_robust_list2 sys_robust_list2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 49eeb2ad8dbd..269721f54a5c 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -481,3 +481,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index f5ed71f1910d..75a387585b3a 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -466,3 +466,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 680f568b77f2..176f84b79c1c 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -472,3 +472,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 0b9b7e25b69a..47e28d67ca8a 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -405,3 +405,4 @@
464 n32 getxattrat sys_getxattrat
465 n32 listxattrat sys_listxattrat
466 n32 removexattrat sys_removexattrat
+467 n32 set_robust_list2 sys_set_robust_list2
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index c844cd5cda62..488c1bca7715 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -381,3 +381,4 @@
464 n64 getxattrat sys_getxattrat
465 n64 listxattrat sys_listxattrat
466 n64 removexattrat sys_removexattrat
+467 n64 set_robust_list2 sys_set_robust_list2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 349b8aad1159..f983086695a8 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -454,3 +454,4 @@
464 o32 getxattrat sys_getxattrat
465 o32 listxattrat sys_listxattrat
466 o32 removexattrat sys_removexattrat
+467 o32 set_robust_list2 sys_set_robust_list2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index d9fc94c86965..f8735cb8046b 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -465,3 +465,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index d8b4ab78bef0..1da55a6a3bb5 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -557,3 +557,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index e9115b4d8b63..93bda0d6580b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -469,3 +469,4 @@
464 common getxattrat sys_getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2 sys_set_robust_list2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index c8cad33bf250..dd591da98af5 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -470,3 +470,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 727f99d333b3..a4ee76e234a3 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -512,3 +512,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 4d0fb2fba7e2..8d609abda75b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -472,3 +472,4 @@
464 i386 getxattrat sys_getxattrat
465 i386 listxattrat sys_listxattrat
466 i386 removexattrat sys_removexattrat
+467 i386 set_robust_list2 sys_set_robust_list2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5eb708bff1c7..2c6461df154b 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -390,6 +390,7 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 37effc1b134e..fa46635d7380 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c00a86931f8c..71fbac6176c8 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -195,6 +195,7 @@ COND_SYSCALL(move_pages);
COND_SYSCALL(set_mempolicy_home_node);
COND_SYSCALL(cachestat);
COND_SYSCALL(mseal);
+COND_SYSCALL(set_robust_list2);
COND_SYSCALL(perf_event_open);
COND_SYSCALL(accept4);
diff --git a/scripts/syscall.tbl b/scripts/syscall.tbl
index ebbdb3c42e9f..615a3043c982 100644
--- a/scripts/syscall.tbl
+++ b/scripts/syscall.tbl
@@ -407,3 +407,4 @@
464 common getxattrat sys_getxattrat
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
+467 common set_robust_list2 sys_set_robust_list2
--
2.47.1
^ permalink raw reply related
* [PATCH v3 2/3] futex: Create set_robust_list2
From: André Almeida @ 2024-12-17 17:49 UTC (permalink / raw)
To: Thomas Gleixner, Ingo Molnar, Peter Zijlstra, Darren Hart,
Davidlohr Bueso, Arnd Bergmann, sonicadvance1
Cc: linux-kernel, kernel-dev, linux-api, Nathan Chancellor,
Vinicius Peixoto, André Almeida
In-Reply-To: <20241217174958.477692-1-andrealmeid@igalia.com>
Create a new robust_list() syscall. The current syscall can't be
expanded to cover the following use case, so a new one is needed. This
new syscall allows users to set multiple robust lists per process and to
have either 32bit or 64bit pointers in the list.
* Interface
This is the proposed interface:
long set_robust_list2(void *head, int index, unsigned int flags)
`head` is the head of the userspace struct robust_list_head, just as old
set_robust_list(). It needs to be a void pointer since it can point to a
normal robust_list_head or a compat_robust_list_head.
`flags` can be used for defining the list type:
enum robust_list_type {
ROBUST_LIST_32BIT,
ROBUST_LIST_64BIT,
};
`index` is the index in the internal robust_list's linked list (the
naming starts to get confusing, I reckon). If `index == -1`, that means
that user wants to set a new robust_list, and the kernel will append it
in the end of the list, assign a new index and return this index to the
user. If `index >= 0`, that means that user wants to re-set `*head` of
an already existing list (similarly to what happens when you call
set_robust_list() twice with different `*head`).
If `index` is out of range, or it points to a non-existing robust_list,
or if the internal list is full, an error is returned.
User cannot remove lists.
* Implementation
The old syscall's set/get_robust_list() are converted to use the linked
list as well. When using only the old syscalls user shouldn't any
difference as the internal code will handle the linked list insertion as
usual. When mixing old and new interfaces users should be aware that one
of the elements of the list was created by another syscall and they
should have special care handling this element index.
On exit, the linked list is parsed and all robust lists regardless of
which interface it was used to create them are handled.
Signed-off-by: André Almeida <andrealmeid@igalia.com>
---
include/linux/futex.h | 5 +-
include/linux/sched.h | 5 +-
include/uapi/asm-generic/unistd.h | 4 +-
include/uapi/linux/futex.h | 24 +++++++
kernel/futex/core.c | 111 ++++++++++++++++++++++++------
kernel/futex/futex.h | 5 ++
kernel/futex/syscalls.c | 78 +++++++++++++++++++--
7 files changed, 202 insertions(+), 30 deletions(-)
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 8217b5ebdd9c..39335f21aea6 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -72,10 +72,11 @@ enum {
static inline void futex_init_task(struct task_struct *tsk)
{
- tsk->robust_list = NULL;
+ tsk->robust_list_index = -1;
#ifdef CONFIG_COMPAT
- tsk->compat_robust_list = NULL;
+ tsk->compat_robust_list_index = -1;
#endif
+ INIT_LIST_HEAD(&tsk->robust_list2);
INIT_LIST_HEAD(&tsk->pi_state_list);
tsk->pi_state_cache = NULL;
tsk->futex_state = FUTEX_STATE_OK;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index da573c16e93e..1324f103db3d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1290,10 +1290,11 @@ struct task_struct {
u32 rmid;
#endif
#ifdef CONFIG_FUTEX
- struct robust_list_head __user *robust_list;
+ int robust_list_index;
#ifdef CONFIG_COMPAT
- struct robust_list_head32 __user *compat_robust_list;
+ int compat_robust_list_index;
#endif
+ struct list_head robust_list2;
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
struct mutex futex_exit_mutex;
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 88dc393c2bca..477cce02ed72 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -850,8 +850,10 @@ __SYSCALL(__NR_listxattrat, sys_listxattrat)
#define __NR_removexattrat 466
__SYSCALL(__NR_removexattrat, sys_removexattrat)
+#define __NR_set_robust_list2 467
+
#undef __NR_syscalls
-#define __NR_syscalls 467
+#define __NR_syscalls 468
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index d2ee625ea189..13903a278b71 100644
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -146,6 +146,30 @@ struct robust_list_head {
struct robust_list __user *list_op_pending;
};
+#define ROBUST_LISTS_PER_TASK 10
+
+enum robust_list2_type {
+ ROBUST_LIST_32BIT,
+ ROBUST_LIST_64BIT,
+};
+
+#define ROBUST_LIST_TYPE_MASK (ROBUST_LIST_32BIT | ROBUST_LIST_64BIT)
+
+/*
+ * This is an entry of a linked list of robust lists.
+ *
+ * @head: can point to a 64bit list or a 32bit list
+ * @list_type: determine the size of the futex pointers in the list
+ * @index: the index of this entry in the list
+ * @list: linked list element
+ */
+struct robust_list2_entry {
+ void __user *head;
+ enum robust_list2_type list_type;
+ unsigned int index;
+ struct list_head list;
+};
+
/*
* Are there any waiters for this robust futex:
*/
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index cc2d0f00cd6b..f8962bc27c90 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -775,9 +775,9 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
*
* We silently return on any sign of list-walking problem.
*/
-static void exit_robust_list64(struct task_struct *curr)
+static void exit_robust_list64(struct task_struct *curr,
+ struct robust_list_head __user *head)
{
- struct robust_list_head __user *head = curr->robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
@@ -837,7 +837,8 @@ static void exit_robust_list64(struct task_struct *curr)
}
}
#else
-static void exit_robust_list64(struct task_struct *curr)
+static void exit_robust_list64(struct task_struct *curr,
+ struct robust_list_head __user *head)
{
pr_warn("32bit kernel should not allow ROBUST_LIST_64BIT");
}
@@ -874,9 +875,9 @@ fetch_robust_entry32(u32 *uentry, struct robust_list __user **entry,
*
* We silently return on any sign of list-walking problem.
*/
-static void exit_robust_list32(struct task_struct *curr)
+static void exit_robust_list32(struct task_struct *curr,
+ struct robust_list_head32 __user *head)
{
- struct robust_list_head32 __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
@@ -942,6 +943,70 @@ static void exit_robust_list32(struct task_struct *curr)
}
}
+long do_set_robust_list2(struct robust_list_head __user *head,
+ int index, unsigned int type)
+{
+ struct list_head *list2 = ¤t->robust_list2;
+ struct robust_list2_entry *prev, *new = NULL;
+
+ if (index == -1) {
+ if (list_empty(list2)) {
+ index = 0;
+ } else {
+ prev = list_last_entry(list2, struct robust_list2_entry, list);
+ index = prev->index + 1;
+ }
+
+ if (index >= ROBUST_LISTS_PER_TASK)
+ return -EINVAL;
+
+ new = kmalloc(sizeof(struct robust_list2_entry), GFP_KERNEL);
+ if (!new)
+ return -ENOMEM;
+
+ list_add_tail(&new->list, list2);
+ new->index = index;
+
+ } else if (index >= 0) {
+ struct robust_list2_entry *curr;
+
+ if (list_empty(list2))
+ return -ENOENT;
+
+ list_for_each_entry(curr, list2, list) {
+ if (index == curr->index) {
+ new = curr;
+ break;
+ }
+ }
+
+ if (!new)
+ return -ENOENT;
+ }
+
+ BUG_ON(!new);
+ new->head = head;
+ new->list_type = type;
+
+ return index;
+}
+
+struct robust_list_head __user *get_robust_list2(int index)
+{
+ struct list_head *list2 = ¤t->robust_list2;
+ struct robust_list2_entry *curr;
+
+ if (list_empty(list2) || index == -1)
+ return NULL;
+
+ list_for_each_entry(curr, list2, list) {
+ if (index == curr->index)
+ return curr->head;
+ }
+
+ return NULL;
+}
+
#ifdef CONFIG_FUTEX_PI
/*
@@ -1023,24 +1088,28 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
static void futex_cleanup(struct task_struct *tsk)
{
-#ifdef CONFIG_64BIT
- if (unlikely(tsk->robust_list)) {
- exit_robust_list64(tsk);
- tsk->robust_list = NULL;
- }
-#else
- if (unlikely(tsk->robust_list)) {
- exit_robust_list32(tsk);
- tsk->robust_list = NULL;
- }
-#endif
+ struct robust_list2_entry *curr, *n;
+ struct list_head *list2 = &tsk->robust_list2;
-#ifdef CONFIG_COMPAT
- if (unlikely(tsk->compat_robust_list)) {
- exit_robust_list32(tsk);
- tsk->compat_robust_list = NULL;
+ /*
+ * Walk through the linked list, parsing robust lists and freeing the
+ * allocated lists
+ */
+ if (unlikely(!list_empty(list2))) {
+ list_for_each_entry_safe(curr, n, list2, list) {
+ if (curr->head != NULL) {
+ if (curr->list_type == ROBUST_LIST_64BIT)
+ exit_robust_list64(tsk, curr->head);
+ else if (curr->list_type == ROBUST_LIST_32BIT)
+ exit_robust_list32(tsk, curr->head);
+ curr->head = NULL;
+ }
+ list_del_init(&curr->list);
+ kfree(curr);
+ }
}
-#endif
+
+ tsk->robust_list_index = -1;
if (unlikely(!list_empty(&tsk->pi_state_list)))
exit_pi_state_list(tsk);
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 99b32e728c4a..07cbc9c1634a 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -404,6 +404,11 @@ extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
ktime_t *abs_time, u32 bitset);
+extern long do_set_robust_list2(struct robust_list_head __user *head,
+ int index, unsigned int type);
+
+extern struct robust_list_head __user *get_robust_list2(int index);
+
/**
* struct futex_vector - Auxiliary struct for futex_waitv()
* @w: Userspace provided data
diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c
index dba193dfd216..b6fbaf8d9422 100644
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -20,6 +20,18 @@
* the list. There can only be one such pending lock.
*/
+#ifdef CONFIG_64BIT
+static inline int robust_list_native_type(void)
+{
+ return ROBUST_LIST_64BIT;
+}
+#else
+static inline int robust_list_native_type(void)
+{
+ return ROBUST_LIST_32BIT;
+}
+#endif
+
/**
* sys_set_robust_list() - Set the robust-futex list head of a task
* @head: pointer to the list-head
@@ -28,17 +40,60 @@
SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
size_t, len)
{
+ unsigned int type = robust_list_native_type();
+ int ret;
+
/*
* The kernel knows only one size for now:
*/
if (unlikely(len != sizeof(*head)))
return -EINVAL;
- current->robust_list = head;
+ ret = do_set_robust_list2(head, current->robust_list_index, type);
+ if (ret < 0)
+ return ret;
+
+ current->robust_list_index = ret;
return 0;
}
+#define ROBUST_LIST_FLAGS ROBUST_LIST_TYPE_MASK
+
+/*
+ * sys_set_robust_list2()
+ *
+ * When index == -1, create a new list for user. When index >= 0, try to find
+ * the corresponding list and re-set the head there.
+ *
+ * Return values:
+ * >= 0: success, index of the robust list
+ * -EINVAL: invalid flags, invalid index
+ * -ENOENT: requested index no where to be found
+ * -ENOMEM: error allocating new list
+ * -ESRCH: too many allocated lists
+ */
+SYSCALL_DEFINE3(set_robust_list2, struct robust_list_head __user *, head,
+ int, index, unsigned int, flags)
+{
+ unsigned int type;
+
+ type = flags & ROBUST_LIST_TYPE_MASK;
+
+ if (index < -1 || index >= ROBUST_LISTS_PER_TASK)
+ return -EINVAL;
+
+ if ((flags & ~ROBUST_LIST_FLAGS) != 0)
+ return -EINVAL;
+
+#ifndef CONFIG_64BIT
+ if (type == ROBUST_LIST_64BIT)
+ return -EINVAL;
+#endif
+
+ return do_set_robust_list2(head, index, type);
+}
+
/**
* sys_get_robust_list() - Get the robust-futex list head of a task
* @pid: pid of the process [zero for current task]
@@ -52,6 +107,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
struct robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
+ int index;
rcu_read_lock();
@@ -68,9 +124,11 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
- head = p->robust_list;
+ index = p->robust_list_index;
rcu_read_unlock();
+ head = get_robust_list2(index);
+
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(head, head_ptr);
@@ -443,10 +501,19 @@ COMPAT_SYSCALL_DEFINE2(set_robust_list,
struct robust_list_head32 __user *, head,
compat_size_t, len)
{
+ unsigned int type = ROBUST_LIST_32BIT;
+ int ret;
+
if (unlikely(len != sizeof(*head)))
return -EINVAL;
- current->compat_robust_list = head;
+ ret = do_set_robust_list2((struct robust_list_head __user *) head,
+ current->robust_list_index, type);
+ if (ret < 0)
+ return ret;
+
+ current->robust_list_index = ret;
+
return 0;
}
@@ -458,6 +525,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
struct robust_list_head32 __user *head;
unsigned long ret;
struct task_struct *p;
+ int index;
rcu_read_lock();
@@ -474,9 +542,11 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
- head = p->compat_robust_list;
+ index = p->compat_robust_list_index;
rcu_read_unlock();
+ head = (struct robust_list_head32 __user *) get_robust_list2(index);
+
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(ptr_to_compat(head), head_ptr);
--
2.47.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox