Skip to contentSkip to conversation

futex priority based wakeup

PATCH In review Pierre Peiffer 3 participants 8 messages Jan 17, 2007 – Jan 18, 2007 1 message not in the archive

Subsystems (2)
lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

PATCH 1/4 futex priority based wakeup

Hi,

Today, all threads waiting for a given futex are woken in FIFO order (first waiter woken first) instead of priority order.

This patch makes use of plist (pirotity ordered lists) instead of simple list in futex_hash_bucket.

All non-RT threads are stored with priority MAX_RT_PRIO, causing them to be woken last, in FIFO order (RT-threads are woken first, in priority order).

---

 futex.c |   78 ++++++++++++++++++++++++++++++++++++++++------------------------
 1 file changed, 49 insertions(+), 29 deletions(-)

---

---

kernel/futex.c +49 -29
Index: linux-2.6/kernel/futex.c
===================================================================
@@ -106,12 +106,12 @@ struct futex_pi_state {
  * we can wake only the relevant ones (hashed queues may be shared).
  *
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
- * It is considered woken when list_empty(&q->list) || q->lock_ptr == 0.
+ * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
  * The order of wakup is always to make the first condition true, then
  * wake up q->waiters, then make the second condition true.
  */
 struct futex_q {
-	struct list_head list;
+	struct plist_node list;
 	wait_queue_head_t waiters;
 
 	/* Which hash list lock to use: */
@@ -133,8 +133,8 @@ struct futex_q {
  * Split the global futex_lock into every hash list lock.
  */
 struct futex_hash_bucket {
-       spinlock_t              lock;
-       struct list_head       chain;
+	spinlock_t lock;
+	struct plist_head chain;
 };
 
 static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
@@ -465,13 +465,13 @@ lookup_pi_state(u32 uval, struct futex_h
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;
-	struct list_head *head;
+	struct plist_head *head;
 	struct task_struct *p;
 	pid_t pid;
 
 	head = &hb->chain;
 
-	list_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex(&this->key, &me->key)) {
 			/*
 			 * Another waiter already exists - bump up
@@ -535,12 +535,12 @@ lookup_pi_state(u32 uval, struct futex_h
  */
 static void wake_futex(struct futex_q *q)
 {
-	list_del_init(&q->list);
+	plist_del(&q->list, &q->list.plist);
 	if (q->filp)
 		send_sigio(&q->filp->f_owner, q->fd, POLL_IN);
 	/*
 	 * The lock in wake_up_all() is a crucial memory barrier after the
-	 * list_del_init() and also before assigning to q->lock_ptr.
+	 * plist_del() and also before assigning to q->lock_ptr.
 	 */
 	wake_up_all(&q->waiters);
 	/*
@@ -653,7 +653,7 @@ static int futex_wake(u32 __user *uaddr,
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct list_head *head;
+	struct plist_head *head;
 	union futex_key key;
 	int ret;
 
@@ -667,7 +667,7 @@ static int futex_wake(u32 __user *uaddr,
 	spin_lock(&hb->lock);
 	head = &hb->chain;
 
-	list_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key)) {
 			if (this->pi_state) {
 				ret = -EINVAL;
@@ -695,7 +695,7 @@ futex_wake_op(u32 __user *uaddr1, u32 __
 {
 	union futex_key key1, key2;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct list_head *head;
+	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret, attempt = 0;
 
@@ -768,7 +768,7 @@ retry:
 
 	head = &hb1->chain;
 
-	list_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key1)) {
 			wake_futex(this);
 			if (++ret >= nr_wake)
@@ -780,7 +780,7 @@ retry:
 		head = &hb2->chain;
 
 		op_ret = 0;
-		list_for_each_entry_safe(this, next, head, list) {
+		plist_for_each_entry_safe(this, next, head, list) {
 			if (match_futex (&this->key, &key2)) {
 				wake_futex(this);
 				if (++op_ret >= nr_wake2)
@@ -807,7 +807,7 @@ static int futex_requeue(u32 __user *uad
 {
 	union futex_key key1, key2;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct list_head *head1;
+	struct plist_head *head1;
 	struct futex_q *this, *next;
 	int ret, drop_count = 0;
 
@@ -856,7 +856,7 @@ static int futex_requeue(u32 __user *uad
 	}
 
 	head1 = &hb1->chain;
-	list_for_each_entry_safe(this, next, head1, list) {
+	plist_for_each_entry_safe(this, next, head1, list) {
 		if (!match_futex (&this->key, &key1))
 			continue;
 		if (++ret <= nr_wake) {
@@ -867,9 +867,13 @@ static int futex_requeue(u32 __user *uad
 			 * requeue.
 			 */
 			if (likely(head1 != &hb2->chain)) {
-				list_move_tail(&this->list, &hb2->chain);
+				plist_del(&this->list, &hb1->chain);
+				plist_add(&this->list, &hb2->chain);
 				this->lock_ptr = &hb2->lock;
-			}
+#ifdef CONFIG_DEBUG_PI_LIST
+				this->list.plist.lock = &hb2->lock;
+#endif
+ 			}
 			this->key = key2;
 			get_key_refs(&key2);
 			drop_count++;
@@ -914,7 +918,23 @@ queue_lock(struct futex_q *q, int fd, st
 
 static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
-	list_add_tail(&q->list, &hb->chain);
+	int prio;
+
+	/*
+	 * The priority used to register this element is
+	 * - either the real thread-priority for the real-time threads
+	 * (i.e. threads with a priority lower than MAX_RT_PRIO)
+	 * - or MAX_RT_PRIO for non-RT threads.
+	 * Thus, all RT-threads are woken first in priority order, and
+	 * the others are woken last, in FIFO order.
+	 */
+	prio = min(current->normal_prio, MAX_RT_PRIO);
+
+	plist_node_init(&q->list, prio);
+#ifdef CONFIG_DEBUG_PI_LIST
+	q->list.plist.lock = &hb->lock;
+#endif
+	plist_add(&q->list, &hb->chain);
 	q->task = current;
 	spin_unlock(&hb->lock);
 }
@@ -969,8 +989,8 @@ static int unqueue_me(struct futex_q *q)
 			spin_unlock(lock_ptr);
 			goto retry;
 		}
-		WARN_ON(list_empty(&q->list));
-		list_del(&q->list);
+		WARN_ON(plist_node_empty(&q->list));
+		plist_del(&q->list, &q->list.plist);
 
 		BUG_ON(q->pi_state);
 
@@ -988,8 +1008,8 @@ static int unqueue_me(struct futex_q *q)
  */
 static void unqueue_me_pi(struct futex_q *q, struct futex_hash_bucket *hb)
 {
-	WARN_ON(list_empty(&q->list));
-	list_del(&q->list);
+	WARN_ON(plist_node_empty(&q->list));
+	plist_del(&q->list, &q->list.plist);
 
 	BUG_ON(!q->pi_state);
 	free_pi_state(q->pi_state);
@@ -1082,10 +1102,10 @@ static int futex_wait(u32 __user *uaddr,
 	__set_current_state(TASK_INTERRUPTIBLE);
 	add_wait_queue(&q.waiters, &wait);
 	/*
-	 * !list_empty() is safe here without any lock.
+	 * !plist_node_empty() is safe here without any lock.
 	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
 	 */
-	if (likely(!list_empty(&q.list)))
+	if (likely(!plist_node_empty(&q.list)))
 		time = schedule_timeout(time);
 	__set_current_state(TASK_RUNNING);
 
@@ -1358,7 +1378,7 @@ static int futex_unlock_pi(u32 __user *u
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	u32 uval;
-	struct list_head *head;
+	struct plist_head *head;
 	union futex_key key;
 	int ret, attempt = 0;
 
@@ -1409,7 +1429,7 @@ retry_locked:
 	 */
 	head = &hb->chain;
 
-	list_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, head, list) {
 		if (!match_futex (&this->key, &key))
 			continue;
 		ret = wake_futex_pi(uaddr, uval, this);
@@ -1483,10 +1503,10 @@ static unsigned int futex_poll(struct fi
 	poll_wait(filp, &q->waiters, wait);
 
 	/*
-	 * list_empty() is safe here without any lock.
+	 * plist_node_empty() is safe here without any lock.
 	 * q->lock_ptr != 0 is not safe, because of ordering against wakeup.
 	 */
-	if (list_empty(&q->list))
+	if (plist_node_empty(&q->list))
 		ret = POLLIN | POLLRDNORM;
 
 	return ret;
@@ -1869,7 +1889,7 @@ static int __init init(void)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
-		INIT_LIST_HEAD(&futex_queues[i].chain);
+		plist_head_init(&futex_queues[i].chain, &futex_queues[i].lock);
 		spin_lock_init(&futex_queues[i].lock);
 	}
 	return 0;
Signature · 1 line
Pierre
#2 lore raw

PATCH 2/4 Make futex_wait() use an hrtimer for timeout

In reply to a message not in the archive

Hi,

This patch modifies futex_wait() to use an hrtimer + schedule() in place of
schedule_timeout() in an RT kernel.

More details in the patch header.

--------------------------------------------------------------------------------

This patch modifies futex_wait() to use an hrtimer + schedule() in place of
schedule_timeout().

schedule_timeout() is tick based, therefore the timeout granularity is
the tick (1 ms, 4 ms or 10 ms depending on HZ). By using a high resolution timer for timeout wakeup, we can attain a much finer timeout granularity (in the microsecond range). This parallels what is already done for futex_lock_pi().

The timeout passed to the syscall is no longer converted to jiffies
and is therefore passed to do_futex() and futex_wait() as a timespec therefore keeping nanosecond resolution.

Also this removes the need to pass the nanoseconds timeout part to
futex_lock_pi() in val2.

In futex_wait(), if the timeout is zero then a regular schedule() is
performed. Otherwise, an hrtimer is fired before schedule() is called.

---
 include/linux/futex.h |    2 -
 kernel/futex.c        |   58 ++++++++++++++++++++++++++++++++------------------
 kernel/futex_compat.c |   11 +--------
 3 files changed, 41 insertions(+), 30 deletions(-)

---

---

kernel/futex.c +38 -20
Index: linux-2.6/kernel/futex.c
===================================================================
@@ -1020,7 +1020,7 @@ static void unqueue_me_pi(struct futex_q
 	drop_key_refs(&q->key);
 }
 
-static int futex_wait(u32 __user *uaddr, u32 val, unsigned long time)
+static int futex_wait(u32 __user *uaddr, u32 val, struct timespec *time)
 {
 	struct task_struct *curr = current;
 	DECLARE_WAITQUEUE(wait, curr);
@@ -1028,6 +1028,8 @@ static int futex_wait(u32 __user *uaddr,
 	struct futex_q q;
 	u32 uval;
 	int ret;
+	struct hrtimer_sleeper t;
+	int rem = 0;
 
 	q.pi_state = NULL;
  retry:
@@ -1105,8 +1107,31 @@ static int futex_wait(u32 __user *uaddr,
 	 * !plist_node_empty() is safe here without any lock.
 	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
 	 */
-	if (likely(!plist_node_empty(&q.list)))
-		time = schedule_timeout(time);
+	if (likely(!plist_node_empty(&q.list))) {
+		if (time->tv_sec == 0 && time->tv_nsec == 0)
+			schedule();
+		else {
+			hrtimer_init(&t.timer, CLOCK_MONOTONIC, HRTIMER_REL);
+			hrtimer_init_sleeper(&t, current);
+			t.timer.expires = timespec_to_ktime(*time);
+
+			hrtimer_start(&t.timer, t.timer.expires, HRTIMER_REL);
+
+			/*
+			 * the timer could have already expired, in which
+			 * case current would be flagged for rescheduling.
+			 * Don't bother calling schedule.
+			 */
+			if (likely(t.task))
+				schedule();
+
+			hrtimer_cancel(&t.timer);
+
+			/* Flag if a timeout occured */
+			rem = (t.task == NULL);
+		}
+	}
+
 	__set_current_state(TASK_RUNNING);
 
 	/*
@@ -1117,7 +1142,7 @@ static int futex_wait(u32 __user *uaddr,
 	/* If we were woken (and unqueued), we succeeded, whatever. */
 	if (!unqueue_me(&q))
 		return 0;
-	if (time == 0)
+	if (rem)
 		return -ETIMEDOUT;
 	/*
 	 * We expect signal_pending(current), but another thread may
@@ -1139,8 +1164,8 @@ static int futex_wait(u32 __user *uaddr,
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
-			 long nsec, int trylock)
+static int futex_lock_pi(u32 __user *uaddr, int detect, struct timespec *time,
+			 int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct task_struct *curr = current;
@@ -1152,11 +1177,11 @@ static int futex_lock_pi(u32 __user *uad
 	if (refill_pi_state_cache())
 		return -ENOMEM;
 
-	if (sec != MAX_SCHEDULE_TIMEOUT) {
+	if (time->tv_sec || time->tv_nsec) {
 		to = &timeout;
 		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
 		hrtimer_init_sleeper(to, current);
-		to->timer.expires = ktime_set(sec, nsec);
+		to->timer.expires = timespec_to_ktime(*time);
 	}
 
 	q.pi_state = NULL;
@@ -1792,7 +1817,7 @@ void exit_robust_list(struct task_struct
 	}
 }
 
-long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout,
+long do_futex(u32 __user *uaddr, int op, u32 val, struct timespec *timeout,
 		u32 __user *uaddr2, u32 val2, u32 val3)
 {
 	int ret;
@@ -1818,13 +1843,13 @@ long do_futex(u32 __user *uaddr, int op,
 		ret = futex_wake_op(uaddr, uaddr2, val, val2, val3);
 		break;
 	case FUTEX_LOCK_PI:
-		ret = futex_lock_pi(uaddr, val, timeout, val2, 0);
+		ret = futex_lock_pi(uaddr, val, timeout, 0);
 		break;
 	case FUTEX_UNLOCK_PI:
 		ret = futex_unlock_pi(uaddr);
 		break;
 	case FUTEX_TRYLOCK_PI:
-		ret = futex_lock_pi(uaddr, 0, timeout, val2, 1);
+		ret = futex_lock_pi(uaddr, 0, timeout, 1);
 		break;
 	default:
 		ret = -ENOSYS;
@@ -1837,8 +1862,7 @@ asmlinkage long sys_futex(u32 __user *ua
 			  struct timespec __user *utime, u32 __user *uaddr2,
 			  u32 val3)
 {
-	struct timespec t;
-	unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
+	struct timespec t = {.tv_sec = 0, .tv_nsec = 0};
 	u32 val2 = 0;
 
 	if (utime && (op == FUTEX_WAIT || op == FUTEX_LOCK_PI)) {
@@ -1846,12 +1870,6 @@ asmlinkage long sys_futex(u32 __user *ua
 			return -EFAULT;
 		if (!timespec_valid(&t))
 			return -EINVAL;
-		if (op == FUTEX_WAIT)
-			timeout = timespec_to_jiffies(&t) + 1;
-		else {
-			timeout = t.tv_sec;
-			val2 = t.tv_nsec;
-		}
 	}
 	/*
 	 * requeue parameter in 'utime' if op == FUTEX_REQUEUE.
@@ -1859,7 +1877,7 @@ asmlinkage long sys_futex(u32 __user *ua
 	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
 		val2 = (u32) (unsigned long) utime;
 
-	return do_futex(uaddr, op, val, timeout, uaddr2, val2, val3);
+	return do_futex(uaddr, op, val, &t, uaddr2, val2, val3);
 }
 
 static int futexfs_get_sb(struct file_system_type *fs_type,
kernel/futex_compat.c +2 -9
Index: linux-2.6/kernel/futex_compat.c
===================================================================
@@ -141,8 +141,7 @@ asmlinkage long compat_sys_futex(u32 __u
 		struct compat_timespec __user *utime, u32 __user *uaddr2,
 		u32 val3)
 {
-	struct timespec t;
-	unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
+	struct timespec t = {.tv_sec = 0, .tv_nsec = 0};
 	int val2 = 0;
 
 	if (utime && (op == FUTEX_WAIT || op == FUTEX_LOCK_PI)) {
@@ -150,15 +149,9 @@ asmlinkage long compat_sys_futex(u32 __u
 			return -EFAULT;
 		if (!timespec_valid(&t))
 			return -EINVAL;
-		if (op == FUTEX_WAIT)
-			timeout = timespec_to_jiffies(&t) + 1;
-		else {
-			timeout = t.tv_sec;
-			val2 = t.tv_nsec;
-		}
 	}
 	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
 		val2 = (int) (unsigned long) utime;
 
-	return do_futex(uaddr, op, val, timeout, uaddr2, val2, val3);
+	return do_futex(uaddr, op, val, &t, uaddr2, val2, val3);
 }
include/linux/futex.h +1 -1
Index: linux-2.6/include/linux/futex.h
===================================================================
@@ -94,7 +94,7 @@ struct robust_list_head {
 #define ROBUST_LIST_LIMIT	2048
 
 #ifdef __KERNEL__
-long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout,
+long do_futex(u32 __user *uaddr, int op, u32 val, struct timespec *timeout,
 	      u32 __user *uaddr2, u32 val2, u32 val3);
 
 extern int
Signature · 1 line
Pierre
#3 lore raw

PATCH 3/4 futex_requeue_pi optimization

In reply to a message not in the archive

Hi,

This patch provides the futex_requeue_pi functionality.

This provides an optimization, already used for (normal) futexes, to be used for PI-futexes.

This optimization is currently used by the glibc in pthread_broadcast, when using "normal" mutexes. With futex_requeue_pi, it can be used with PRIO_INHERIT mutexes too.

---

 include/linux/futex.h   |    8
 kernel/futex.c          |  557 +++++++++++++++++++++++++++++++++++++++++++-----
 kernel/futex_compat.c   |    3
 kernel/rtmutex.c        |   41 ---
 kernel/rtmutex_common.h |   34 ++
 5 files changed, 555 insertions(+), 88 deletions(-)

---

---

include/linux/futex.h +7 -1
Index: linux-2.6/include/linux/futex.h
===================================================================
@@ -15,6 +15,7 @@
 #define FUTEX_LOCK_PI		6
 #define FUTEX_UNLOCK_PI		7
 #define FUTEX_TRYLOCK_PI	8
+#define FUTEX_CMP_REQUEUE_PI	9
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
@@ -83,9 +84,14 @@ struct robust_list_head {
 #define FUTEX_OWNER_DIED	0x40000000
 
 /*
+ * Some processes have been requeued on this PI-futex
+ */
+#define FUTEX_WAITER_REQUEUED	0x20000000
+
+/*
  * The rest of the robust-futex field is for the TID:
  */
-#define FUTEX_TID_MASK		0x3fffffff
+#define FUTEX_TID_MASK		0x0fffffff
 
 /*
  * This limit protects against a deliberately circular list.
kernel/futex.c +503 -54

728 lines not on this page · raw message

kernel/rtmutex.c +9 -32

71 lines not on this page · raw message

kernel/rtmutex_common.h +34 -0
Index: linux-2.6/kernel/rtmutex_common.h
===================================================================
@@ -113,6 +113,29 @@ static inline unsigned long rt_mutex_own
 }
 
 /*
+ * We can speed up the acquire/release, if the architecture
+ * supports cmpxchg and if there's no debugging state to be set up
+ */
+#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+# define rt_mutex_cmpxchg(l,c,n)	(cmpxchg(&l->owner, c, n) == c)
+static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	unsigned long owner, *p = (unsigned long *) &lock->owner;
+
+	do {
+		owner = *p;
+	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
+}
+#else
+# define rt_mutex_cmpxchg(l,c,n)	(0)
+static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	lock->owner = (struct task_struct *)
+			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
+}
+#endif
+
+/*
  * PI-futex support (proxy locking functions, etc.):
  */
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
@@ -120,4 +143,15 @@ extern void rt_mutex_init_proxy_locked(s
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
+
+extern void rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
+			       unsigned long mask);
+extern void __rt_mutex_adjust_prio(struct task_struct *task);
+extern int rt_mutex_adjust_prio_chain(struct task_struct *task,
+				      int deadlock_detect,
+				      struct rt_mutex *orig_lock,
+				      struct rt_mutex_waiter *orig_waiter,
+				      struct task_struct *top_task);
+extern void remove_waiter(struct rt_mutex *lock,
+			  struct rt_mutex_waiter *waiter);
 #endif
kernel/futex_compat.c +2 -1
Index: linux-2.6/kernel/futex_compat.c
===================================================================
@@ -150,7 +150,8 @@ asmlinkage long compat_sys_futex(u32 __u
 		if (!timespec_valid(&t))
 			return -EINVAL;
 	}
-	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
+	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE
+	    || op == FUTEX_CMP_REQUEUE_PI)
 		val2 = (int) (unsigned long) utime;
 
 	return do_futex(uaddr, op, val, &t, uaddr2, val2, val3);
Signature · 1 line
Pierre
#4 lore raw

PATCH 4/4 sys_futex64 : allows 64bit futexes

In reply to a message not in the archive

Hi,

This latest patch is an adaptation of the sys_futex64 syscall provided in -rt patch (originally written by Ingo). It allows the use of 64bit futex.

I have re-worked most of the code to avoid the duplication of the code.

It does not provide the functionality for all architectures, and thus, it can not be applied "as is".
Feedbacks and comments are welcome.

---
 include/asm-x86_64/futex.h  |  113 ++++++++++++++++++++
 include/asm-x86_64/unistd.h |    4
 include/linux/futex.h       |    5
 include/linux/syscalls.h    |    3
 kernel/futex.c              |  247 ++++++++++++++++++++++++++++++--------------
 kernel/futex_compat.c       |    3
 kernel/sys_ni.c             |    1
 7 files changed, 299 insertions(+), 77 deletions(-)

---

---

include/asm-x86_64/futex.h +113 -0
Index: linux-2.6/include/asm-x86_64/futex.h
===================================================================
@@ -41,6 +41,39 @@
 	  "=&r" (tem)						\
 	: "r" (oparg), "i" (-EFAULT), "m" (*uaddr), "1" (0))
 
+#define __futex_atomic_op1_64(insn, ret, oldval, uaddr, oparg) \
+  __asm__ __volatile (						\
+"1:	" insn "\n"						\
+"2:	.section .fixup,\"ax\"\n\
+3:	movq	%3, %1\n\
+	jmp	2b\n\
+	.previous\n\
+	.section __ex_table,\"a\"\n\
+	.align	8\n\
+	.quad	1b,3b\n\
+	.previous"						\
+	: "=r" (oldval), "=r" (ret), "=m" (*uaddr)		\
+	: "i" (-EFAULT), "m" (*uaddr), "0" (oparg), "1" (0))
+
+#define __futex_atomic_op2_64(insn, ret, oldval, uaddr, oparg) \
+  __asm__ __volatile (						\
+"1:	movq	%2, %0\n\
+	movq	%0, %3\n"					\
+	insn "\n"						\
+"2:	" LOCK_PREFIX "cmpxchgq %3, %2\n\
+	jnz	1b\n\
+3:	.section .fixup,\"ax\"\n\
+4:	movq	%5, %1\n\
+	jmp	3b\n\
+	.previous\n\
+	.section __ex_table,\"a\"\n\
+	.align	8\n\
+	.quad	1b,4b,2b,4b\n\
+	.previous"						\
+	: "=&a" (oldval), "=&r" (ret), "=m" (*uaddr),		\
+	  "=&r" (tem)						\
+	: "r" (oparg), "i" (-EFAULT), "m" (*uaddr), "1" (0))
+
 static inline int
 futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 {
@@ -95,6 +128,60 @@ futex_atomic_op_inuser (int encoded_op,
 }
 
 static inline int
+futex_atomic_op_inuser64 (int encoded_op, u64 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	u64 oparg = (encoded_op << 8) >> 20;
+	u64 cmparg = (encoded_op << 20) >> 20;
+	u64 oldval = 0, ret, tem;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u64)))
+		return -EFAULT;
+
+	inc_preempt_count();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op1_64("xchgq %0, %2", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op1_64(LOCK_PREFIX "xaddq %0, %2", ret, oldval,
+				   uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op2_64("orq %4, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op2_64("andq %4, %3", ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op2_64("xorq %4, %3", ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	dec_preempt_count();
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+static inline int
 futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 {
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
@@ -121,5 +208,31 @@ futex_atomic_cmpxchg_inatomic(int __user
 	return oldval;
 }
 
+static inline u64
+futex_atomic_cmpxchg_inatomic64(u64 __user *uaddr, u64 oldval, u64 newval)
+{
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u64)))
+		return -EFAULT;
+
+	__asm__ __volatile__(
+		"1:	" LOCK_PREFIX "cmpxchgq %3, %1		\n"
+
+		"2:	.section .fixup, \"ax\"			\n"
+		"3:	mov     %2, %0				\n"
+		"	jmp     2b				\n"
+		"	.previous				\n"
+
+		"	.section __ex_table, \"a\"		\n"
+		"	.align  8				\n"
+		"	.quad   1b,3b				\n"
+		"	.previous				\n"
+
+		: "=a" (oldval), "=m" (*uaddr)
+		: "i" (-EFAULT), "r" (newval), "0" (oldval)
+		: "memory"
+	);
+
+	return oldval;
+}
 #endif
 #endif
include/asm-x86_64/unistd.h +3 -1
Index: linux-2.6/include/asm-x86_64/unistd.h
===================================================================
@@ -619,8 +619,10 @@ __SYSCALL(__NR_sync_file_range, sys_sync
 __SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_move_pages		279
 __SYSCALL(__NR_move_pages, sys_move_pages)
+#define __NR_futex64		280
+__SYSCALL(__NR_futex64, sys_futex64)
 
-#define __NR_syscall_max __NR_move_pages
+#define __NR_syscall_max __NR_futex64
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
include/linux/syscalls.h +3 -0
Index: linux-2.6/include/linux/syscalls.h
===================================================================
@@ -178,6 +178,9 @@ asmlinkage long sys_set_tid_address(int
 asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
 			struct timespec __user *utime, u32 __user *uaddr2,
 			u32 val3);
+asmlinkage long sys_futex64(u64 __user *uaddr, int op, u64 val,
+			struct timespec __user *utime, u64 __user *uaddr2,
+			u64 val3);
 
 asmlinkage long sys_init_module(void __user *umod, unsigned long len,
 				const char __user *uargs);
kernel/futex.c +174 -73

567 lines not on this page · raw message

kernel/sys_ni.c +1 -0
Index: linux-2.6/kernel/sys_ni.c
===================================================================
@@ -41,6 +41,7 @@ cond_syscall(sys_sendmsg);
 cond_syscall(sys_recvmsg);
 cond_syscall(sys_socketcall);
 cond_syscall(sys_futex);
+cond_syscall(sys_futex64);
 cond_syscall(compat_sys_futex);
 cond_syscall(sys_set_robust_list);
 cond_syscall(compat_sys_set_robust_list);
include/linux/futex.h +3 -2
Index: linux-2.6/include/linux/futex.h
===================================================================
@@ -100,8 +100,9 @@ struct robust_list_head {
 #define ROBUST_LIST_LIMIT	2048
 
 #ifdef __KERNEL__
-long do_futex(u32 __user *uaddr, int op, u32 val, struct timespec *timeout,
-	      u32 __user *uaddr2, u32 val2, u32 val3);
+long do_futex(unsigned long __user *uaddr, int op, unsigned long val,
+	      struct timespec *timeout, unsigned long __user *uaddr2,
+	      unsigned long val2, unsigned long val3, int futex64);
 
 extern int
 handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi);
kernel/futex_compat.c +2 -1
Index: linux-2.6/kernel/futex_compat.c
===================================================================
@@ -154,5 +154,6 @@ asmlinkage long compat_sys_futex(u32 __u
 	    || op == FUTEX_CMP_REQUEUE_PI)
 		val2 = (int) (unsigned long) utime;
 
-	return do_futex(uaddr, op, val, &t, uaddr2, val2, val3);
+	return do_futex((unsigned long __user*)uaddr, op, val, &t,
+			(unsigned long __user*)uaddr2, val2, val3, 0);
 }
Signature · 1 line
Pierre
#5 lore raw

Re: [PATCH 2.6.20-rc5 4/4] sys_futex64 : allows 64bit futexes

Quoted 5 lines · Pierre Peiffer

Hi,

This latest patch is an adaptation of the sys_futex64 syscall provided in -rt
patch (originally written by Ingo). It allows the use of 64bit futex.

Big NACK here, we don't need yet another goddamn multiplexer. Please make this individual syscalls for the actual operations.

include/asm-x86_64/futex.h futex_atomic_op_inuser (int encoded_op, · line 173

Quoted 4 lines
include/asm-x86_64/futex.h +4 -0
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;

Please indent this properly, the ret = .. and reak need to go onto a line on it's own.

#6 lore raw

Re: [PATCH 2.6.20-rc5 4/4] sys_futex64 : allows 64bit futexes

Quoted 9 lines · Christoph Hellwig
Quoted 5 lines · Pierre Peiffer

Hi,

This latest patch is an adaptation of the sys_futex64 syscall provided in -rt patch (originally written by Ingo). It allows the use of 64bit futex.

Big NACK here, we don't need yet another goddamn multiplexer. Please make this individual syscalls for the actual operations.

actually, we have a big multiplexer there already, so it's only symmetric. Nothing is served by doing it half-assed. I raised the issue of the multiplexer back when the first futex API was merged (years ago), and it was rejected. Now whether you like it or not we've got to live with that decision. You are certainly free to introduce a patchset with a completely new set of syscall vectors to demultiplex all futex APIs, but to just start a half-done demultiplexing makes zero sense.

Quoted 7 lines

include/asm-x86_64/futex.h futex_atomic_op_inuser (int encoded_op, · line 173

Quoted 4 lines
include/asm-x86_64/futex.h +4 -0
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;

Please indent this properly, the ret = .. and reak need to go onto a line on it's own.

this is the standard (already upstream) arithmetics style there for the futex cmp ops, and it expresses things in a compact way. See include/asm-i386/futex.h:

                switch (cmp) {
                case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
                case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
                case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
                case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
                case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
                case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
                default: ret = -ENOSYS;
                }

Pierre correctly matched the existing style.

Ingo

#7 lore raw

Re: [PATCH 2.6.20-rc5 4/4] sys_futex64 : allows 64bit futexes

Quoted 12 lines · Ingo Molnar

include/asm-i386/futex.h:

                switch (cmp) {
                case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
                case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
                case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
                case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
                case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
                case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
                default: ret = -ENOSYS;
                }
Quoted 1 line

Pierre correctly matched the existing style.

Old code doing things wrong is no excuse for new code doing the same mistake. Much better send a patch to fix up the previous unreadable mess aswell. Then again some indentation fixups won't help that much to make futrsx not the totally unreadable spaghetti code it's now ;-)

#8 lore raw

Re: [PATCH 2.6.20-rc5 4/4] sys_futex64 : allows 64bit futexes

In reply to Ingo Molnar
Quoted 7 lines · Ingo Molnar

actually, we have a big multiplexer there already, so it's only symmetric. Nothing is served by doing it half-assed. I raised the issue of the multiplexer back when the first futex API was merged (years ago), and it was rejected. Now whether you like it or not we've got to live with that decision. You are certainly free to introduce a patchset with a completely new set of syscall vectors to demultiplex all futex APIs, but to just start a half-done demultiplexing makes zero sense.

dding new syscalls for the old functionality is totally pointless as we have to support the old entry point forever anyway. And new code is using the new entry point, so let's get that right.