Linux-api Archive mirror
 help / color / mirror / Atom feed
From: Elizabeth Figura <zfigura@codeweavers.com>
To: Arnd Bergmann <arnd@arndb.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Jonathan Corbet <corbet@lwn.net>, Shuah Khan <shuah@kernel.org>
Cc: linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
	wine-devel@winehq.org, "André Almeida" <andrealmeid@igalia.com>,
	"Wolfram Sang" <wsa@kernel.org>,
	"Arkadiusz Hiler" <ahiler@codeweavers.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Andy Lutomirski" <luto@kernel.org>,
	linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org,
	"Elizabeth Figura" <zfigura@codeweavers.com>
Subject: [PATCH 04/31] ntsync: Introduce NTSYNC_IOC_WAIT_ANY.
Date: Wed, 14 Feb 2024 17:36:40 -0600	[thread overview]
Message-ID: <20240214233645.9273-5-zfigura@codeweavers.com> (raw)
In-Reply-To: <20240214233645.9273-1-zfigura@codeweavers.com>

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

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

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

A timeout is supported. The timeout is passed as a u64 nanosecond value, which
represents absolute time measured against the MONOTONIC clock. If U64_MAX is
passed, the ioctl waits indefinitely.

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

Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>
---
 drivers/misc/ntsync.c       | 237 ++++++++++++++++++++++++++++++++++++
 include/uapi/linux/ntsync.h |  12 ++
 2 files changed, 249 insertions(+)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 01556475f5cc..123af239f52e 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -6,11 +6,16 @@
  */
 
 #include <linux/anon_inodes.h>
+#include <linux/atomic.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/overflow.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <uapi/linux/ntsync.h>
@@ -36,12 +41,55 @@ struct ntsync_obj {
 			__u32 max;
 		} sem;
 	} u;
+
+	struct list_head any_waiters;
+};
+
+struct ntsync_q_entry {
+	struct list_head node;
+	struct ntsync_q *q;
+	struct ntsync_obj *obj;
+	__u32 index;
+};
+
+struct ntsync_q {
+	struct task_struct *task;
+	__u32 owner;
+
+	/*
+	 * Protected via atomic_cmpxchg(). Only the thread that wins the
+	 * compare-and-swap may actually change object states and wake this
+	 * task.
+	 */
+	atomic_t signaled;
+
+	__u32 count;
+	struct ntsync_q_entry entries[];
 };
 
 struct ntsync_device {
 	struct file *file;
 };
 
+static void try_wake_any_sem(struct ntsync_obj *sem)
+{
+	struct ntsync_q_entry *entry;
+
+	lockdep_assert_held(&sem->lock);
+
+	list_for_each_entry(entry, &sem->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+
+		if (!sem->u.sem.count)
+			break;
+
+		if (atomic_cmpxchg(&q->signaled, -1, entry->index) == -1) {
+			sem->u.sem.count--;
+			wake_up_process(q->task);
+		}
+	}
+}
+
 /*
  * Actually change the semaphore state, returning -EOVERFLOW if it is made
  * invalid.
@@ -77,6 +125,8 @@ static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp)
 
 	prev_count = sem->u.sem.count;
 	ret = post_sem_state(sem, args);
+	if (!ret)
+		try_wake_any_sem(sem);
 
 	spin_unlock(&sem->lock);
 
@@ -130,6 +180,7 @@ static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev,
 	obj->dev = dev;
 	get_file(dev->file);
 	spin_lock_init(&obj->lock);
+	INIT_LIST_HEAD(&obj->any_waiters);
 
 	return obj;
 }
@@ -180,6 +231,190 @@ static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp)
 	return put_user(fd, &user_args->sem);
 }
 
+static struct ntsync_obj *get_obj(struct ntsync_device *dev, int fd)
+{
+	struct file *file = fget(fd);
+	struct ntsync_obj *obj;
+
+	if (file->f_op != &ntsync_obj_fops) {
+		fput(file);
+		return NULL;
+	}
+
+	obj = file->private_data;
+	if (obj->dev != dev) {
+		fput(file);
+		return NULL;
+	}
+
+	return obj;
+}
+
+static void put_obj(struct ntsync_obj *obj)
+{
+	fput(obj->file);
+}
+
+static int ntsync_schedule(const struct ntsync_q *q, const struct ntsync_wait_args *args)
+{
+	ktime_t timeout = ns_to_ktime(args->timeout);
+	ktime_t *timeout_ptr;
+	int ret = 0;
+
+	timeout_ptr = (args->timeout == U64_MAX ? NULL : &timeout);
+
+	do {
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (atomic_read(&q->signaled) != -1) {
+			ret = 0;
+			break;
+		}
+		ret = schedule_hrtimeout(timeout_ptr, HRTIMER_MODE_ABS);
+	} while (ret < 0);
+	__set_current_state(TASK_RUNNING);
+
+	return ret;
+}
+
+/*
+ * Allocate and initialize the ntsync_q structure, but do not queue us yet.
+ */
+static int setup_wait(struct ntsync_device *dev,
+		      const struct ntsync_wait_args *args,
+		      struct ntsync_q **ret_q)
+{
+	const __u32 count = args->count;
+	int fds[NTSYNC_MAX_WAIT_COUNT];
+	struct ntsync_q *q;
+	__u32 i, j;
+
+	if (!args->owner || args->pad)
+		return -EINVAL;
+
+	if (args->count > NTSYNC_MAX_WAIT_COUNT)
+		return -EINVAL;
+
+	if (copy_from_user(fds, u64_to_user_ptr(args->objs),
+			   array_size(count, sizeof(*fds))))
+		return -EFAULT;
+
+	q = kmalloc(struct_size(q, entries, count), GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+	q->task = current;
+	q->owner = args->owner;
+	atomic_set(&q->signaled, -1);
+	q->count = count;
+
+	for (i = 0; i < count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = get_obj(dev, fds[i]);
+
+		if (!obj)
+			goto err;
+
+		entry->obj = obj;
+		entry->q = q;
+		entry->index = i;
+	}
+
+	*ret_q = q;
+	return 0;
+
+err:
+	for (j = 0; j < i; j++)
+		put_obj(q->entries[j].obj);
+	kfree(q);
+	return -EINVAL;
+}
+
+static void try_wake_any_obj(struct ntsync_obj *obj)
+{
+	switch (obj->type) {
+	case NTSYNC_TYPE_SEM:
+		try_wake_any_sem(obj);
+		break;
+	}
+}
+
+static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_wait_args args;
+	struct ntsync_q *q;
+	int signaled;
+	__u32 i;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	ret = setup_wait(dev, &args, &q);
+	if (ret < 0)
+		return ret;
+
+	/* queue ourselves */
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		spin_lock(&obj->lock);
+		list_add_tail(&entry->node, &obj->any_waiters);
+		spin_unlock(&obj->lock);
+	}
+
+	/* check if we are already signaled */
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_obj *obj = q->entries[i].obj;
+
+		if (atomic_read(&q->signaled) != -1)
+			break;
+
+		spin_lock(&obj->lock);
+		try_wake_any_obj(obj);
+		spin_unlock(&obj->lock);
+	}
+
+	/* sleep */
+
+	ret = ntsync_schedule(q, &args);
+
+	/* and finally, unqueue */
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		spin_lock(&obj->lock);
+		list_del(&entry->node);
+		spin_unlock(&obj->lock);
+
+		put_obj(obj);
+	}
+
+	signaled = atomic_read(&q->signaled);
+	if (signaled != -1) {
+		struct ntsync_wait_args __user *user_args = argp;
+
+		/* even if we caught a signal, we need to communicate success */
+		ret = 0;
+
+		if (put_user(signaled, &user_args->index))
+			ret = -EFAULT;
+	} else if (!ret) {
+		ret = -ETIMEDOUT;
+	}
+
+	kfree(q);
+	return ret;
+}
+
 static int ntsync_char_open(struct inode *inode, struct file *file)
 {
 	struct ntsync_device *dev;
@@ -211,6 +446,8 @@ static long ntsync_char_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case NTSYNC_IOC_CREATE_SEM:
 		return ntsync_create_sem(dev, argp);
+	case NTSYNC_IOC_WAIT_ANY:
+		return ntsync_wait_any(dev, argp);
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h
index 878ec4f0f2e8..9cd1dd05d971 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -16,7 +16,19 @@ struct ntsync_sem_args {
 	__u32 max;
 };
 
+struct ntsync_wait_args {
+	__u64 timeout;
+	__u64 objs;
+	__u32 count;
+	__u32 owner;
+	__u32 index;
+	__u32 pad;
+};
+
+#define NTSYNC_MAX_WAIT_COUNT 64
+
 #define NTSYNC_IOC_CREATE_SEM		_IOWR('N', 0x80, struct ntsync_sem_args)
+#define NTSYNC_IOC_WAIT_ANY		_IOWR('N', 0x82, struct ntsync_wait_args)
 
 #define NTSYNC_IOC_SEM_POST		_IOWR('N', 0x81, __u32)
 
-- 
2.43.0


  parent reply	other threads:[~2024-02-14 23:53 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-14 23:36 [PATCH 00/31] NT synchronization primitive driver Elizabeth Figura
2024-02-14 23:36 ` [PATCH 01/31] ntsync: Introduce the ntsync driver and character device Elizabeth Figura
2024-02-15  1:57   ` Randy Dunlap
2024-02-15 19:04     ` Elizabeth Figura
2024-02-14 23:36 ` [PATCH 02/31] ntsync: Introduce NTSYNC_IOC_CREATE_SEM Elizabeth Figura
2024-02-15  7:28   ` Greg Kroah-Hartman
2024-02-15 19:22     ` Elizabeth Figura
2024-02-17  8:03       ` Greg Kroah-Hartman
2024-02-19 19:02         ` Elizabeth Figura
2024-02-14 23:36 ` [PATCH 03/31] ntsync: Introduce NTSYNC_IOC_SEM_POST Elizabeth Figura
2024-02-14 23:36 ` Elizabeth Figura [this message]
2024-02-14 23:36 ` [PATCH 05/31] ntsync: Introduce NTSYNC_IOC_WAIT_ALL Elizabeth Figura
2024-02-14 23:36 ` [PATCH 06/31] ntsync: Introduce NTSYNC_IOC_CREATE_MUTEX Elizabeth Figura
2024-02-14 23:36 ` [PATCH 07/31] ntsync: Introduce NTSYNC_IOC_MUTEX_UNLOCK Elizabeth Figura
2024-02-14 23:36 ` [PATCH 08/31] ntsync: Introduce NTSYNC_IOC_MUTEX_KILL Elizabeth Figura
2024-02-14 23:36 ` [PATCH 09/31] ntsync: Introduce NTSYNC_IOC_CREATE_EVENT Elizabeth Figura
2024-02-14 23:52 ` [PATCH 10/31] ntsync: Introduce NTSYNC_IOC_EVENT_SET Elizabeth Figura
2024-02-14 23:52   ` [PATCH 11/31] ntsync: Introduce NTSYNC_IOC_EVENT_RESET Elizabeth Figura
2024-02-14 23:52   ` [PATCH 12/31] ntsync: Introduce NTSYNC_IOC_EVENT_PULSE Elizabeth Figura
2024-02-14 23:52   ` [PATCH 13/31] ntsync: Introduce NTSYNC_IOC_SEM_READ Elizabeth Figura
2024-02-14 23:52   ` [PATCH 14/31] ntsync: Introduce NTSYNC_IOC_MUTEX_READ Elizabeth Figura
2024-02-14 23:52   ` [PATCH 15/31] ntsync: Introduce NTSYNC_IOC_EVENT_READ Elizabeth Figura
2024-02-14 23:52   ` [PATCH 16/31] ntsync: Introduce alertable waits Elizabeth Figura
2024-02-14 23:52   ` [PATCH 17/31] ntsync: Allow waits to use the REALTIME clock Elizabeth Figura
2024-02-14 23:52   ` [PATCH 18/31] selftests: ntsync: Add some tests for semaphore state Elizabeth Figura
2024-02-14 23:52   ` [PATCH 19/31] selftests: ntsync: Add some tests for mutex state Elizabeth Figura
2024-02-14 23:52   ` [PATCH 20/31] selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ANY Elizabeth Figura
2024-02-14 23:52   ` [PATCH 21/31] selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ALL Elizabeth Figura
2024-02-14 23:52   ` [PATCH 22/31] selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ANY Elizabeth Figura
2024-02-14 23:52   ` [PATCH 23/31] selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ALL Elizabeth Figura
2024-02-14 23:52   ` [PATCH 24/31] selftests: ntsync: Add some tests for manual-reset event state Elizabeth Figura
2024-02-14 23:53   ` [PATCH 25/31] selftests: ntsync: Add some tests for auto-reset " Elizabeth Figura
2024-02-14 23:53   ` [PATCH 26/31] selftests: ntsync: Add some tests for wakeup signaling with events Elizabeth Figura
2024-02-14 23:53   ` [PATCH 27/31] selftests: ntsync: Add tests for alertable waits Elizabeth Figura
2024-02-14 23:53   ` [PATCH 28/31] selftests: ntsync: Add some tests for wakeup signaling via alerts Elizabeth Figura
2024-02-14 23:53   ` [PATCH 29/31] selftests: ntsync: Add a stress test for contended waits Elizabeth Figura
2024-02-14 23:53   ` [PATCH 30/31] maintainers: Add an entry for ntsync Elizabeth Figura
2024-02-14 23:53   ` [PATCH 31/31] docs: ntsync: Add documentation for the ntsync uAPI Elizabeth Figura
2024-02-15  0:01 ` [PATCH 00/31] NT synchronization primitive driver Elizabeth Figura
2024-02-15  7:24   ` Greg Kroah-Hartman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240214233645.9273-5-zfigura@codeweavers.com \
    --to=zfigura@codeweavers.com \
    --cc=ahiler@codeweavers.com \
    --cc=andrealmeid@igalia.com \
    --cc=arnd@arndb.de \
    --cc=corbet@lwn.net \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=shuah@kernel.org \
    --cc=wine-devel@winehq.org \
    --cc=wsa@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).