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;
/*
}
#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
* 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_head);
+ shmem_swizzled = PageSwapCache(page_head) || page_head->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.
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;
}
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(&pi_state->pi_mutex.wait_lock);
return ret;
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:
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);
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
/* 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);
/*
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.
*/
{
struct hrtimer_sleeper timeout, *to = NULL;
struct rt_mutex_waiter rt_waiter;
- struct rt_mutex *pi_mutex = NULL;
struct futex_hash_bucket *hb;
union futex_key key2 = FUTEX_KEY_INIT;
struct futex_q q = futex_q_init;
if (q.pi_state && (q.pi_state->owner != current)) {
spin_lock(q.lock_ptr);
ret = fixup_pi_state_owner(uaddr2, &q, current);
+ if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
+ rt_mutex_unlock(&q.pi_state->pi_mutex);
+ /*
+ * Drop the reference to the pi state which
+ * the requeue_pi() code acquired for us.
+ */
+ free_pi_state(q.pi_state);
spin_unlock(q.lock_ptr);
}
} else {
+ struct rt_mutex *pi_mutex;
+
/*
* We have been woken up by futex_unlock_pi(), a timeout, or a
* signal. futex_unlock_pi() will not destroy the lock_ptr nor
*/
WARN_ON(!q.pi_state);
pi_mutex = &q.pi_state->pi_mutex;
- ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
- debug_rt_mutex_free_waiter(&rt_waiter);
+ ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
spin_lock(q.lock_ptr);
+ if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+ ret = 0;
+
+ debug_rt_mutex_free_waiter(&rt_waiter);
/*
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
if (res)
ret = (res < 0) ? res : 0;
+ /*
+ * If fixup_pi_state_owner() faulted and was unable to handle
+ * the fault, unlock the rt_mutex and return the fault to
+ * userspace.
+ */
+ if (ret && rt_mutex_owner(pi_mutex) == current)
+ rt_mutex_unlock(pi_mutex);
+
/* Unqueue and drop the lock. */
unqueue_me_pi(&q);
}
- /*
- * If fixup_pi_state_owner() faulted and was unable to handle the
- * fault, unlock the rt_mutex and return the fault to userspace.
- */
- if (ret == -EFAULT) {
- if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
- rt_mutex_unlock(pi_mutex);
- } else if (ret == -EINTR) {
+ if (ret == -EINTR) {
/*
* We've already been requeued, but cannot restart by calling
* futex_lock_pi() directly. We could restart this syscall, but
}
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;
{
u32 uval, uninitialized_var(nval), mval;
+ /* Futex address must be 32bit aligned */
+ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
+ return -1;
+
retry:
if (get_user(uval, uaddr))
return -1;
return 0;
}
-__initcall(futex_init);
+core_initcall(futex_init);