1 files changed, 35 insertions, 8 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index a5d2e74c89e0..33664f70e2d2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct page *page;
+	struct page *page, *tail;
 	struct address_space *mapping;
 	int err, ro = 0;
 
@@ -530,7 +530,15 @@ again:
 	 * considered here and page lock forces unnecessarily serialization
 	 * From this point on, mapping will be re-verified if necessary and
 	 * page lock will be acquired only if it is unavoidable
-	 */
+	 *
+	 * Mapping checks require the head page for any compound page so the
+	 * head page and mapping is looked up now. For anonymous pages, it
+	 * does not matter if the page splits in the future as the key is
+	 * based on the address. For filesystem-backed pages, the tail is
+	 * required as the index of the page determines the key. For
+	 * base pages, there is no tail page and tail == page.
+	 */
+	tail = page;
 	page = compound_head(page);
 	mapping = READ_ONCE(page->mapping);
 
@@ -654,7 +662,7 @@ again:
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.inode = inode;
-		key->shared.pgoff = basepage_index(page);
+		key->shared.pgoff = basepage_index(tail);
 		rcu_read_unlock();
 	}
 
@@ -729,7 +737,7 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
 	int ret;
 
 	pagefault_disable();
-	ret = __copy_from_user_inatomic(dest, from, sizeof(u32));
+	ret = __get_user(*dest, from);
 	pagefault_enable();
 
 	return ret ? -EFAULT : 0;
@@ -1295,10 +1303,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
-	else if (curval != uval)
-		ret = -EINVAL;
+	} else if (curval != uval) {
+		/*
+		 * If a unconditional UNLOCK_PI operation (user space did not
+		 * try the TID->0 transition) raced with a waiter setting the
+		 * FUTEX_WAITERS flag between get_user() and locking the hash
+		 * bucket lock, retry the operation.
+		 */
+		if ((FUTEX_TID_MASK & curval) == uval)
+			ret = -EAGAIN;
+		else
+			ret = -EINVAL;
+	}
 	if (ret) {
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
@@ -1525,8 +1543,8 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 	if (likely(&hb1->chain != &hb2->chain)) {
 		plist_del(&q->list, &hb1->chain);
 		hb_waiters_dec(hb1);
-		plist_add(&q->list, &hb2->chain);
 		hb_waiters_inc(hb2);
+		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
 	}
 	get_futex_key_refs(key2);
@@ -2623,6 +2641,15 @@ retry:
 		if (ret == -EFAULT)
 			goto pi_faulted;
 		/*
+		 * A unconditional UNLOCK_PI op raced against a waiter
+		 * setting the FUTEX_WAITERS bit. Try again.
+		 */
+		if (ret == -EAGAIN) {
+			spin_unlock(&hb->lock);
+			put_futex_key(&key);
+			goto retry;
+		}
+		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */