1 files changed, 192 insertions, 101 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 684d7549825a..a5d2e74c89e0 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -124,16 +124,16 @@
  *   futex_wait(futex, val);
  *
  *   waiters++; (a)
- *   mb(); (A) <-- paired with -.
- *                              |
- *   lock(hash_bucket(futex));  |
- *                              |
- *   uval = *futex;             |
- *                              |        *futex = newval;
- *                              |        sys_futex(WAKE, futex);
- *                              |          futex_wake(futex);
- *                              |
- *                              `------->  mb(); (B)
+ *   smp_mb(); (A) <-- paired with -.
+ *                                  |
+ *   lock(hash_bucket(futex));      |
+ *                                  |
+ *   uval = *futex;                 |
+ *                                  |        *futex = newval;
+ *                                  |        sys_futex(WAKE, futex);
+ *                                  |          futex_wake(futex);
+ *                                  |
+ *                                  `--------> smp_mb(); (B)
  *   if (uval == val)
  *     queue();
  *     unlock(hash_bucket(futex));
@@ -334,7 +334,7 @@ static inline void futex_get_mm(union futex_key *key)
 	/*
 	 * 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.
+	 * as smp_mb(); (B), see the ordering comment above.
 	 */
 	smp_mb__after_atomic();
 }
@@ -407,10 +407,10 @@ 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); /* implies MB (B) */
+		ihold(key->shared.inode); /* implies smp_mb(); (B) */
 		break;
 	case FUT_OFF_MMSHARED:
-		futex_get_mm(key); /* implies MB (B) */
+		futex_get_mm(key); /* implies smp_mb(); (B) */
 		break;
 	default:
 		/*
@@ -418,7 +418,7 @@ static void get_futex_key_refs(union futex_key *key)
 		 * mm, therefore the only purpose of calling get_futex_key_refs
 		 * is because we need the barrier for the lockless waiter check.
 		 */
-		smp_mb(); /* explicit MB (B) */
+		smp_mb(); /* explicit smp_mb(); (B) */
 	}
 }
 
@@ -469,7 +469,8 @@ 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, *page_head;
+	struct page *page;
+	struct address_space *mapping;
 	int err, ro = 0;
 
 	/*
@@ -496,7 +497,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	if (!fshared) {
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);  /* implies MB (B) */
+		get_futex_key_refs(key);  /* implies smp_mb(); (B) */
 		return 0;
 	}
 
@@ -519,46 +520,22 @@ again:
 	else
 		err = 0;
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	page_head = page;
-	if (unlikely(PageTail(page))) {
-		put_page(page);
-		/* serialize against __split_huge_page_splitting() */
-		local_irq_disable();
-		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
-			 * it before taking the PG_lock and/or
-			 * PG_compound_lock. The moment we re-enable
-			 * irqs __split_huge_page_splitting() can
-			 * return and the head page can be freed from
-			 * under us. We can't take the PG_lock and/or
-			 * PG_compound_lock on a page that could be
-			 * freed from under us.
-			 */
-			if (page != page_head) {
-				get_page(page_head);
-				put_page(page);
-			}
-			local_irq_enable();
-		} else {
-			local_irq_enable();
-			goto again;
-		}
-	}
-#else
-	page_head = compound_head(page);
-	if (page != page_head) {
-		get_page(page_head);
-		put_page(page);
-	}
-#endif
-
-	lock_page(page_head);
+	/*
+	 * The treatment of mapping from this point on is critical. The page
+	 * lock protects many things but in this context the page lock
+	 * stabilizes mapping, prevents inode freeing in the shared
+	 * file-backed region case and guards against movement to swap cache.
+	 *
+	 * Strictly speaking the page lock is not needed in all cases being
+	 * 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
+	 */
+	page = compound_head(page);
+	mapping = READ_ONCE(page->mapping);
 
 	/*
-	 * If page_head->mapping is NULL, then it cannot be a PageAnon
+	 * If page->mapping is NULL, then it cannot be a PageAnon
 	 * page; but it might be the ZERO_PAGE or in the gate area or
 	 * in a special mapping (all cases which we are happy to fail);
 	 * or it may have been a good file page when get_user_pages_fast
@@ -570,25 +547,38 @@ again:
 	 *
 	 * The case we do have to guard against is when memory pressure made
 	 * shmem_writepage move it from filecache to swapcache beneath us:
-	 * an unlikely race, but we do need to retry for page_head->mapping.
+	 * an unlikely race, but we do need to retry for page->mapping.
 	 */
-	if (!page_head->mapping) {
-		int shmem_swizzled = PageSwapCache(page_head);
-		unlock_page(page_head);
-		put_page(page_head);
+	if (unlikely(!mapping)) {
+		int shmem_swizzled;
+
+		/*
+		 * Page lock is required to identify which special case above
+		 * applies. If this is really a shmem page then the page lock
+		 * will prevent unexpected transitions.
+		 */
+		lock_page(page);
+		shmem_swizzled = PageSwapCache(page) || page->mapping;
+		unlock_page(page);
+		put_page(page);
+
 		if (shmem_swizzled)
 			goto again;
+
 		return -EFAULT;
 	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
+	 * If the futex key is stored on an anonymous page, then the associated
+	 * object is the mm which is implicitly pinned by the calling process.
+	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
 	 * the object not the particular process.
 	 */
-	if (PageAnon(page_head)) {
+	if (PageAnon(page)) {
 		/*
 		 * A RO anonymous page will never change and thus doesn't make
 		 * sense for futex operations.
@@ -601,17 +591,75 @@ again:
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
+
+		get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
 	} else {
+		struct inode *inode;
+
+		/*
+		 * The associated futex object in this case is the inode and
+		 * the page->mapping must be traversed. Ordinarily this should
+		 * be stabilised under page lock but it's not strictly
+		 * necessary in this case as we just want to pin the inode, not
+		 * update the radix tree or anything like that.
+		 *
+		 * The RCU read lock is taken as the inode is finally freed
+		 * under RCU. If the mapping still matches expectations then the
+		 * mapping->host can be safely accessed as being a valid inode.
+		 */
+		rcu_read_lock();
+
+		if (READ_ONCE(page->mapping) != mapping) {
+			rcu_read_unlock();
+			put_page(page);
+
+			goto again;
+		}
+
+		inode = READ_ONCE(mapping->host);
+		if (!inode) {
+			rcu_read_unlock();
+			put_page(page);
+
+			goto again;
+		}
+
+		/*
+		 * Take a reference unless it is about to be freed. Previously
+		 * this reference was taken by ihold under the page lock
+		 * pinning the inode in place so i_lock was unnecessary. The
+		 * only way for this check to fail is if the inode was
+		 * truncated in parallel so warn for now if this happens.
+		 *
+		 * We are not calling into get_futex_key_refs() in file-backed
+		 * cases, therefore a successful atomic_inc return below will
+		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
+		 */
+		if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+			rcu_read_unlock();
+			put_page(page);
+
+			goto again;
+		}
+
+		/* Should be impossible but lets be paranoid for now */
+		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
+			err = -EFAULT;
+			rcu_read_unlock();
+			iput(inode);
+
+			goto out;
+		}
+
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = page_head->mapping->host;
+		key->shared.inode = inode;
 		key->shared.pgoff = basepage_index(page);
+		rcu_read_unlock();
 	}
 
-	get_futex_key_refs(key); /* implies MB (B) */
-
 out:
-	unlock_page(page_head);
-	put_page(page_head);
+	put_page(page);
 	return err;
 }
 
@@ -639,7 +687,7 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 
 	down_read(&mm->mmap_sem);
 	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
-			       FAULT_FLAG_WRITE);
+			       FAULT_FLAG_WRITE, NULL);
 	up_read(&mm->mmap_sem);
 
 	return ret < 0 ? ret : 0;
@@ -725,9 +773,12 @@ static struct futex_pi_state * alloc_pi_state(void)
 }
 
 /*
+ * Drops a reference to the pi_state object and frees or caches it
+ * when the last reference is gone.
+ *
  * Must be called with the hb lock held.
  */
-static void free_pi_state(struct futex_pi_state *pi_state)
+static void put_pi_state(struct futex_pi_state *pi_state)
 {
 	if (!pi_state)
 		return;
@@ -1223,7 +1274,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	if (pi_state->owner != current)
 		return -EINVAL;
 
-	raw_spin_lock(&pi_state->pi_mutex.wait_lock);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
@@ -1249,22 +1300,22 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	else if (curval != uval)
 		ret = -EINVAL;
 	if (ret) {
-		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
 	}
 
-	raw_spin_lock_irq(&pi_state->owner->pi_lock);
+	raw_spin_lock(&pi_state->owner->pi_lock);
 	WARN_ON(list_empty(&pi_state->list));
 	list_del_init(&pi_state->list);
-	raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+	raw_spin_unlock(&pi_state->owner->pi_lock);
 
-	raw_spin_lock_irq(&new_owner->pi_lock);
+	raw_spin_lock(&new_owner->pi_lock);
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &new_owner->pi_state_list);
 	pi_state->owner = new_owner;
-	raw_spin_unlock_irq(&new_owner->pi_lock);
+	raw_spin_unlock(&new_owner->pi_lock);
 
-	raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
 	deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
 
@@ -1706,31 +1757,35 @@ retry_private:
 		 * exist yet, look it up one more time to ensure we have a
 		 * reference to it. If the lock was taken, ret contains the
 		 * vpid of the top waiter task.
+		 * If the lock was not taken, we have pi_state and an initial
+		 * refcount on it. In case of an error we have nothing.
 		 */
 		if (ret > 0) {
 			WARN_ON(pi_state);
 			drop_count++;
 			task_count++;
 			/*
-			 * If we acquired the lock, then the user
-			 * space value of uaddr2 should be vpid. It
-			 * cannot be changed by the top waiter as it
-			 * is blocked on hb2 lock if it tries to do
-			 * so. If something fiddled with it behind our
-			 * back the pi state lookup might unearth
-			 * it. So we rather use the known value than
-			 * rereading and handing potential crap to
-			 * lookup_pi_state.
+			 * If we acquired the lock, then the user space value
+			 * of uaddr2 should be vpid. It cannot be changed by
+			 * the top waiter as it is blocked on hb2 lock if it
+			 * tries to do so. If something fiddled with it behind
+			 * our back the pi state lookup might unearth it. So
+			 * we rather use the known value than rereading and
+			 * handing potential crap to lookup_pi_state.
+			 *
+			 * If that call succeeds then we have pi_state and an
+			 * initial refcount on it.
 			 */
 			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
 		case 0:
+			/* We hold a reference on the pi state. */
 			break;
+
+			/* If the above failed, then pi_state is NULL */
 		case -EFAULT:
-			free_pi_state(pi_state);
-			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1746,8 +1801,6 @@ retry_private:
 			 *   exit to complete.
 			 * - The user space value changed.
 			 */
-			free_pi_state(pi_state);
-			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1801,30 +1854,58 @@ retry_private:
 		 * of requeue_pi if we couldn't acquire the lock atomically.
 		 */
 		if (requeue_pi) {
-			/* Prepare the waiter to take the rt_mutex. */
+			/*
+			 * Prepare the waiter to take the rt_mutex. Take a
+			 * refcount on the pi_state and store the pointer in
+			 * the futex_q object of the waiter.
+			 */
 			atomic_inc(&pi_state->refcount);
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
 							this->task);
 			if (ret == 1) {
-				/* We got the lock. */
+				/*
+				 * We got the lock. We do neither drop the
+				 * refcount on pi_state nor clear
+				 * this->pi_state because the waiter needs the
+				 * pi_state for cleaning up the user space
+				 * value. It will drop the refcount after
+				 * doing so.
+				 */
 				requeue_pi_wake_futex(this, &key2, hb2);
 				drop_count++;
 				continue;
 			} else if (ret) {
-				/* -EDEADLK */
+				/*
+				 * rt_mutex_start_proxy_lock() detected a
+				 * potential deadlock when we tried to queue
+				 * that waiter. Drop the pi_state reference
+				 * which we took above and remove the pointer
+				 * to the state from the waiters futex_q
+				 * object.
+				 */
 				this->pi_state = NULL;
-				free_pi_state(pi_state);
-				goto out_unlock;
+				put_pi_state(pi_state);
+				/*
+				 * We stop queueing more waiters and let user
+				 * space deal with the mess.
+				 */
+				break;
 			}
 		}
 		requeue_futex(this, hb1, hb2, &key2);
 		drop_count++;
 	}
 
+	/*
+	 * We took an extra initial reference to the pi_state either
+	 * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We
+	 * need to drop it here again.
+	 */
+	put_pi_state(pi_state);
+
 out_unlock:
-	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
 	wake_up_q(&wake_q);
 	hb_waiters_dec(hb2);
@@ -1866,7 +1947,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock); /* implies MB (A) */
+	spin_lock(&hb->lock); /* implies smp_mb(); (A) */
 	return hb;
 }
 
@@ -1929,8 +2010,12 @@ static int unqueue_me(struct futex_q *q)
 
 	/* In the common case we don't take the spinlock, which is nice. */
 retry:
-	lock_ptr = q->lock_ptr;
-	barrier();
+	/*
+	 * q->lock_ptr can change between this read and the following spin_lock.
+	 * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and
+	 * optimizing lock_ptr out of the logic below.
+	 */
+	lock_ptr = READ_ONCE(q->lock_ptr);
 	if (lock_ptr != NULL) {
 		spin_lock(lock_ptr);
 		/*
@@ -1973,7 +2058,7 @@ static void unqueue_me_pi(struct futex_q *q)
 	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
-	free_pi_state(q->pi_state);
+	put_pi_state(q->pi_state);
 	q->pi_state = NULL;
 
 	spin_unlock(q->lock_ptr);
@@ -2129,11 +2214,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * we returned due to timeout or signal without taking the
 		 * rt_mutex. Too late.
 		 */
-		raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
 		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
 		if (!owner)
 			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
 		ret = fixup_pi_state_owner(uaddr, q, owner);
 		goto out;
 	}
@@ -2755,6 +2840,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			/*
+			 * Drop the reference to the pi state which
+			 * the requeue_pi() code acquired for us.
+			 */
+			put_pi_state(q.pi_state);
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
@@ -2881,7 +2971,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
 	}
 
 	ret = -EPERM;
-	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
 		goto err_unlock;
 
 	head = p->robust_list;
@@ -3046,7 +3136,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
 	if (op & FUTEX_CLOCK_REALTIME) {
 		flags |= FLAGS_CLOCKRT;
-		if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
+		if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \
+		    cmd != FUTEX_WAIT_REQUEUE_PI)
 			return -ENOSYS;
 	}