1 files changed, 134 insertions, 7 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index fc68462801de..a26d217c99fe 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -470,6 +470,7 @@ 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, *page_head;
+	struct address_space *mapping;
 	int err, ro = 0;
 
 	/*
@@ -555,7 +556,19 @@ again:
 	}
 #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
+	 */
+
+	mapping = READ_ONCE(page_head->mapping);
 
 	/*
 	 * If page_head->mapping is NULL, then it cannot be a PageAnon
@@ -572,18 +585,31 @@ again:
 	 * shmem_writepage move it from filecache to swapcache beneath us:
 	 * an unlikely race, but we do need to retry for page_head->mapping.
 	 */
-	if (!page_head->mapping) {
-		int shmem_swizzled = PageSwapCache(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_head);
 		put_page(page_head);
+
 		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.
@@ -601,16 +627,75 @@ 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_head->mapping) != mapping) {
+			rcu_read_unlock();
+			put_page(page_head);
+
+			goto again;
+		}
+
+		inode = READ_ONCE(mapping->host);
+		if (!inode) {
+			rcu_read_unlock();
+			put_page(page_head);
+
+			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 which is almost certainly an
+		 * application bug. In such a case, just retry.
+		 *
+		 * 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 (!atomic_inc_not_zero(&inode->i_count)) {
+			rcu_read_unlock();
+			put_page(page_head);
+
+			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);
 	return err;
 }
@@ -1368,6 +1453,45 @@ out:
 	return ret;
 }
 
+static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
+{
+	unsigned int op =	  (encoded_op & 0x70000000) >> 28;
+	unsigned int cmp =	  (encoded_op & 0x0f000000) >> 24;
+	int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11);
+	int cmparg = sign_extend32(encoded_op & 0x00000fff, 11);
+	int oldval, ret;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
+		if (oparg < 0 || oparg > 31)
+			return -EINVAL;
+		oparg = 1 << oparg;
+	}
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
+	if (ret)
+		return ret;
+
+	switch (cmp) {
+	case FUTEX_OP_CMP_EQ:
+		return oldval == cmparg;
+	case FUTEX_OP_CMP_NE:
+		return oldval != cmparg;
+	case FUTEX_OP_CMP_LT:
+		return oldval < cmparg;
+	case FUTEX_OP_CMP_GE:
+		return oldval >= cmparg;
+	case FUTEX_OP_CMP_LE:
+		return oldval <= cmparg;
+	case FUTEX_OP_CMP_GT:
+		return oldval > cmparg;
+	default:
+		return -ENOSYS;
+	}
+}
+
 /*
  * Wake up all waiters hashed on the physical page that is mapped
  * to this virtual address:
@@ -1621,6 +1745,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_q *this, *next;
 	WAKE_Q(wake_q);
 
+	if (nr_wake < 0 || nr_requeue < 0)
+		return -EINVAL;
+
 	if (requeue_pi) {
 		/*
 		 * Requeue PI only works on two distinct uaddrs. This