1 files changed, 168 insertions, 42 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 80ba086f021d..44a1261cb9ff 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,14 +63,101 @@
 #include <linux/sched/rt.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
+#include <linux/bootmem.h>
 
 #include <asm/futex.h>
 
 #include "locking/rtmutex_common.h"
 
-int __read_mostly futex_cmpxchg_enabled;
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0                               CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *   uval = *futex;
+ *                                     *futex = newval;
+ *                                     sys_futex(WAKE, futex);
+ *                                       futex_wake(futex);
+ *                                       if (queue_empty())
+ *                                         return;
+ *   if (uval == val)
+ *      lock(hash_bucket(futex));
+ *      queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0                                 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *
+ *   waiters++;
+ *   mb(); (A) <-- paired with -.
+ *                              |
+ *   lock(hash_bucket(futex));  |
+ *                              |
+ *   uval = *futex;             |
+ *                              |        *futex = newval;
+ *                              |        sys_futex(WAKE, futex);
+ *                              |          futex_wake(futex);
+ *                              |
+ *                              `------->  mb(); (B)
+ *   if (uval == val)
+ *     queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();                         if (waiters)
+ *                                           lock(hash_bucket(futex));
+ *                                           wake_waiters(futex);
+ *                                           unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ *	X = Y = 0
+ *
+ *	w[X]=1		w[Y]=1
+ *	MB		MB
+ *	r[Y]=y		r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ */
 
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
+int __read_mostly futex_cmpxchg_enabled;
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -149,9 +236,41 @@ static const struct futex_q futex_q_init = {
 struct futex_hash_bucket {
 	spinlock_t lock;
 	struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
+
+static unsigned long __read_mostly futex_hashsize;
+
+static struct futex_hash_bucket *futex_queues;
+
+static inline void futex_get_mm(union futex_key *key)
+{
+	atomic_inc(&key->private.mm->mm_count);
+	/*
+	 * Ensure futex_get_mm() implies a full barrier such that
+	 * get_futex_key() implies a full barrier. This is relied upon
+	 * as full barrier (B), see the ordering comment above.
+	 */
+	smp_mb__after_atomic_inc();
+}
+
+static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Tasks trying to enter the critical region are most likely
+	 * potential waiters that will be added to the plist. Ensure
+	 * that wakers won't miss to-be-slept tasks in the window between
+	 * the wait call and the actual plist_add.
+	 */
+	if (spin_is_locked(&hb->lock))
+		return true;
+	smp_rmb(); /* Make sure we check the lock state first */
 
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+	return !plist_head_empty(&hb->chain);
+#else
+	return true;
+#endif
+}
 
 /*
  * We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +280,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
 	u32 hash = jhash2((u32*)&key->both.word,
 			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
 			  key->both.offset);
-	return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
 /*
@@ -187,10 +306,10 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode);
+		ihold(key->shared.inode); /* implies MB (B) */
 		break;
 	case FUT_OFF_MMSHARED:
-		atomic_inc(&key->private.mm->mm_count);
+		futex_get_mm(key); /* implies MB (B) */
 		break;
 	}
 }
@@ -251,6 +370,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 		return -EINVAL;
 	address -= key->both.offset;
 
+	if (unlikely(!access_ok(rw, uaddr, sizeof(u32))))
+		return -EFAULT;
+
 	/*
 	 * PROCESS_PRIVATE futexes are fast.
 	 * As the mm cannot disappear under us and the 'key' only needs
@@ -259,11 +381,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	 *        but access_ok() should be faster than find_vma()
 	 */
 	if (!fshared) {
-		if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
-			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);
+		get_futex_key_refs(key);  /* implies MB (B) */
 		return 0;
 	}
 
@@ -288,7 +408,7 @@ again:
 		put_page(page);
 		/* serialize against __split_huge_page_splitting() */
 		local_irq_disable();
-		if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+		if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
 			page_head = compound_head(page);
 			/*
 			 * page_head is valid pointer but we must pin
@@ -370,7 +490,7 @@ again:
 		key->shared.pgoff = basepage_index(page);
 	}
 
-	get_futex_key_refs(key);
+	get_futex_key_refs(key); /* implies MB (B) */
 
 out:
 	unlock_page(page_head);
@@ -597,13 +717,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex(&this->key, key)) {
 			/*
 			 * Another waiter already exists - bump up
@@ -985,7 +1102,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
@@ -997,10 +1113,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 		goto out;
 
 	hb = hash_futex(&key);
+
+	/* Make sure we really have tasks to wakeup */
+	if (!hb_waiters_pending(hb))
+		goto out_put_key;
+
 	spin_lock(&hb->lock);
-	head = &hb->chain;
 
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex (&this->key, &key)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1018,6 +1138,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	}
 
 	spin_unlock(&hb->lock);
+out_put_key:
 	put_futex_key(&key);
 out:
 	return ret;
@@ -1033,7 +1154,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret;
 
@@ -1081,9 +1201,7 @@ retry_private:
 		goto retry;
 	}
 
-	head = &hb1->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (match_futex (&this->key, &key1)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1096,10 +1214,8 @@ retry_private:
 	}
 
 	if (op_ret > 0) {
-		head = &hb2->chain;
-
 		op_ret = 0;
-		plist_for_each_entry_safe(this, next, head, list) {
+		plist_for_each_entry_safe(this, next, &hb2->chain, list) {
 			if (match_futex (&this->key, &key2)) {
 				if (this->pi_state || this->rt_waiter) {
 					ret = -EINVAL;
@@ -1269,7 +1385,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	int drop_count = 0, task_count = 0, ret;
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head1;
 	struct futex_q *this, *next;
 	u32 curval2;
 
@@ -1392,8 +1507,7 @@ retry_private:
 		}
 	}
 
-	head1 = &hb1->chain;
-	plist_for_each_entry_safe(this, next, head1, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (task_count - nr_wake >= nr_requeue)
 			break;
 
@@ -1488,12 +1602,12 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock);
+	spin_lock(&hb->lock); /* implies MB (A) */
 	return hb;
 }
 
 static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
@@ -1866,7 +1980,7 @@ retry_private:
 	ret = get_futex_value_locked(&uval, uaddr);
 
 	if (ret) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
@@ -1880,7 +1994,7 @@ retry_private:
 	}
 
 	if (uval != val) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 		ret = -EWOULDBLOCK;
 	}
 
@@ -2028,7 +2142,7 @@ retry_private:
 			 * Task is exiting and we just wait for the
 			 * exit to complete.
 			 */
-			queue_unlock(&q, hb);
+			queue_unlock(hb);
 			put_futex_key(&q.key);
 			cond_resched();
 			goto retry;
@@ -2080,7 +2194,7 @@ retry_private:
 	goto out_put_key;
 
 out_unlock_put_key:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 out_put_key:
 	put_futex_key(&q.key);
@@ -2090,7 +2204,7 @@ out:
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 	ret = fault_in_user_writeable(uaddr);
 	if (ret)
@@ -2112,7 +2226,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	u32 uval, vpid = task_pid_vnr(current);
 	int ret;
@@ -2152,9 +2265,7 @@ retry:
 	 * Ok, other tasks may need to be woken up - check waiters
 	 * and do the wakeup if necessary:
 	 */
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (!match_futex (&this->key, &key))
 			continue;
 		ret = wake_futex_pi(uaddr, uval, this);
@@ -2315,6 +2426,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * code while we sleep on uaddr.
 	 */
 	debug_rt_mutex_init_waiter(&rt_waiter);
+	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&rt_waiter.tree_entry);
 	rt_waiter.task = NULL;
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
@@ -2733,8 +2846,21 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 static int __init futex_init(void)
 {
 	u32 curval;
-	int i;
+	unsigned int futex_shift;
+	unsigned long i;
+
+#if CONFIG_BASE_SMALL
+	futex_hashsize = 16;
+#else
+	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
 
+	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+					       futex_hashsize, 0,
+					       futex_hashsize < 256 ? HASH_SMALL : 0,
+					       &futex_shift, NULL,
+					       futex_hashsize, futex_hashsize);
+	futex_hashsize = 1UL << futex_shift;
 	/*
 	 * This will fail and we want it. Some arch implementations do
 	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
@@ -2748,7 +2874,7 @@ static int __init futex_init(void)
 	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
-	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+	for (i = 0; i < futex_hashsize; i++) {
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}