#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/magic.h>
#include <linux/pid.h>
#include <linux/nsproxy.h>
* @uaddr: virtual address of the futex
* @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
* @key: address where result is stored.
+ * @rw: mapping needs to be read/write (values: VERIFY_READ,
+ * VERIFY_WRITE)
*
* Returns a negative error code or 0
* The key words are stored in *key on success.
* lock_page() might sleep, the caller should not hold a spinlock.
*/
static int
-get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
+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;
- int err;
+ int err, ro = 0;
/*
* The futex address must be "naturally" aligned.
again:
err = get_user_pages_fast(address, 1, 1, &page);
+ /*
+ * If write access is not required (eg. FUTEX_WAIT), try
+ * and get read-only access.
+ */
+ if (err == -EFAULT && rw == VERIFY_READ) {
+ err = get_user_pages_fast(address, 1, 0, &page);
+ ro = 1;
+ }
if (err < 0)
return err;
+ else
+ err = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
page_head = page;
#endif
lock_page(page_head);
+
+ /*
+ * If page_head->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
+ * found it, but truncated or holepunched or subjected to
+ * invalidate_complete_page2 before we got the page lock (also
+ * cases which we are happy to fail). And we hold a reference,
+ * so refcount care in invalidate_complete_page's remove_mapping
+ * prevents drop_caches from setting mapping to NULL beneath us.
+ *
+ * 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.
+ */
if (!page_head->mapping) {
+ int shmem_swizzled = PageSwapCache(page_head);
unlock_page(page_head);
put_page(page_head);
- goto again;
+ if (shmem_swizzled)
+ goto again;
+ return -EFAULT;
}
/*
* the object not the particular process.
*/
if (PageAnon(page_head)) {
+ /*
+ * A RO anonymous page will never change and thus doesn't make
+ * sense for futex operations.
+ */
+ if (ro) {
+ err = -EFAULT;
+ goto out;
+ }
+
key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
key->private.mm = mm;
key->private.address = address;
get_futex_key_refs(key);
+out:
unlock_page(page_head);
put_page(page_head);
- return 0;
+ return err;
}
static inline void put_futex_key(union futex_key *key)
int ret;
down_read(&mm->mmap_sem);
- ret = get_user_pages(current, mm, (unsigned long)uaddr,
- 1, 1, 0, NULL, NULL);
+ ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
+ FAULT_FLAG_WRITE);
up_read(&mm->mmap_sem);
return ret < 0 ? ret : 0;
return NULL;
}
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+ u32 uval, u32 newval)
{
- u32 curval;
+ int ret;
pagefault_disable();
- curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+ ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
pagefault_enable();
- return curval;
+ return ret;
}
static int get_futex_value_locked(u32 *dest, u32 __user *from)
struct task_struct *task, int set_waiters)
{
int lock_taken, ret, ownerdied = 0;
- u32 uval, newval, curval;
+ u32 uval, newval, curval, vpid = task_pid_vnr(task);
retry:
ret = lock_taken = 0;
* (by doing a 0 -> TID atomic cmpxchg), while holding all
* the locks. It will most likely not succeed.
*/
- newval = task_pid_vnr(task);
+ newval = vpid;
if (set_waiters)
newval |= FUTEX_WAITERS;
- curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
- if (unlikely(curval == -EFAULT))
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
return -EFAULT;
/*
* Detect deadlocks.
*/
- if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+ if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
return -EDEADLK;
/*
*/
if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
/* Keep the OWNER_DIED bit */
- newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+ newval = (curval & ~FUTEX_TID_MASK) | vpid;
ownerdied = 0;
lock_taken = 1;
}
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (unlikely(curval == -EFAULT))
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
return -EFAULT;
if (unlikely(curval != uval))
goto retry;
{
struct futex_hash_bucket *hb;
- if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
- || plist_node_empty(&q->list)))
+ if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr))
+ || WARN_ON(plist_node_empty(&q->list)))
return;
hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
{
struct task_struct *new_owner;
struct futex_pi_state *pi_state = this->pi_state;
- u32 curval, newval;
+ u32 uninitialized_var(curval), newval;
if (!pi_state)
return -EINVAL;
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
ret = -EFAULT;
else if (curval != uval)
ret = -EINVAL;
static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
{
- u32 oldval;
+ u32 uninitialized_var(oldval);
/*
* There is no waiter, so we unlock the futex. The owner died
* bit has not to be preserved here. We are the owner:
*/
- oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
- if (oldval == -EFAULT)
- return oldval;
+ if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+ return -EFAULT;
if (oldval != uval)
return -EAGAIN;
if (!bitset)
return -EINVAL;
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ);
if (unlikely(ret != 0))
goto out;
int ret, op_ret;
retry:
- ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
+ ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
if (unlikely(ret != 0))
goto out_put_key1;
pi_state = NULL;
}
- ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
+ ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
+ requeue_pi ? VERIFY_WRITE : VERIFY_READ);
if (unlikely(ret != 0))
goto out_put_key1;
u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
struct futex_pi_state *pi_state = q->pi_state;
struct task_struct *oldowner = pi_state->owner;
- u32 uval, curval, newval;
+ u32 uval, uninitialized_var(curval), newval;
int ret;
/* Owner died? */
/*
* We are here either because we stole the rtmutex from the
- * pending owner or we are the pending owner which failed to
- * get the rtmutex. We have to replace the pending owner TID
- * in the user space variable. This must be atomic as we have
- * to preserve the owner died bit here.
+ * previous highest priority waiter or we are the highest priority
+ * waiter but failed to get the rtmutex the first time.
+ * We have to replace the newowner TID in the user space variable.
+ * This must be atomic as we have to preserve the owner died bit here.
*
* Note: We write the user space value _before_ changing the pi_state
* because we can fault here. Imagine swapped out pages or a fork
while (1) {
newval = (uval & FUTEX_OWNER_DIED) | newtid;
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
goto handle_fault;
if (curval == uval)
break;
/*
* To handle the page fault we need to drop the hash bucket
- * lock here. That gives the other task (either the pending
- * owner itself or the task which stole the rtmutex) the
+ * lock here. That gives the other task (either the highest priority
+ * waiter itself or the task which stole the rtmutex) the
* chance to try the fixup of the pi_state. So once we are
* back from handling the fault we need to check the pi_state
* after reacquiring the hash bucket lock and before trying to
/*
* pi_state is incorrect, some other task did a lock steal and
* we returned due to timeout or signal without taking the
- * rt_mutex. Too late. We can access the rt_mutex_owner without
- * locking, as the other task is now blocked on the hash bucket
- * lock. Fix the state up.
+ * rt_mutex. Too late.
*/
+ raw_spin_lock(&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);
ret = fixup_pi_state_owner(uaddr, q, owner);
goto out;
}
/*
* Paranoia check. If we did not take the lock, then we should not be
- * the owner, nor the pending owner, of the rt_mutex.
+ * the owner of the rt_mutex.
*/
if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
*
* Returns:
* 0 - uaddr contains val and hb has been locked
- * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
+ * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked
*/
static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
struct futex_q *q, struct futex_hash_bucket **hb)
*
* The basic logical guarantee of a futex is that it blocks ONLY
* if cond(var) is known to be true at the time of blocking, for
- * any cond. If we queued after testing *uaddr, that would open
- * a race condition where we could block indefinitely with
+ * any cond. If we locked the hash-bucket after testing *uaddr, that
+ * would open a race condition where we could block indefinitely with
* cond(var) false, which would violate the guarantee.
*
- * A consequence is that futex_wait() can return zero and absorb
- * a wakeup when *uaddr != val on entry to the syscall. This is
- * rare, but normal.
+ * On the other hand, we insert q and release the hash-bucket only
+ * after testing *uaddr. This guarantees that futex_wait() will NOT
+ * absorb a wakeup if *uaddr does not match the desired values
+ * while the syscall executes.
*/
retry:
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, VERIFY_READ);
if (unlikely(ret != 0))
return ret;
restart->futex.val = val;
restart->futex.time = abs_time->tv64;
restart->futex.bitset = bitset;
- restart->futex.flags = flags;
+ restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
ret = -ERESTART_RESTARTBLOCK;
}
retry:
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, VERIFY_WRITE);
if (unlikely(ret != 0))
goto out;
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- u32 uval;
struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
+ u32 uval, vpid = task_pid_vnr(current);
int ret;
retry:
/*
* We release only a lock we actually own:
*/
- if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
+ if ((uval & FUTEX_TID_MASK) != vpid)
return -EPERM;
- ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
if (unlikely(ret != 0))
goto out;
* again. If it succeeds then we can return without waking
* anyone else up:
*/
- if (!(uval & FUTEX_OWNER_DIED))
- uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0);
-
-
- if (unlikely(uval == -EFAULT))
+ if (!(uval & FUTEX_OWNER_DIED) &&
+ cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
goto pi_faulted;
/*
* Rare case: we managed to release the lock atomically,
* no need to wake anyone else up:
*/
- if (unlikely(uval == task_pid_vnr(current)))
+ if (unlikely(uval == vpid))
goto out_unlock;
/*
debug_rt_mutex_init_waiter(&rt_waiter);
rt_waiter.task = NULL;
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
if (unlikely(ret != 0))
goto out;
goto err_unlock;
ret = -EPERM;
pcred = __task_cred(p);
+ /* If victim is in different user_ns, then uids are not
+ comparable, so we must have CAP_SYS_PTRACE */
+ if (cred->user->user_ns != pcred->user->user_ns) {
+ if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
+ goto err_unlock;
+ goto ok;
+ }
+ /* If victim is in same user_ns, then uids are comparable */
if (cred->euid != pcred->euid &&
cred->euid != pcred->uid &&
- !capable(CAP_SYS_PTRACE))
+ !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
goto err_unlock;
+ok:
head = p->robust_list;
rcu_read_unlock();
}
*/
int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
{
- u32 uval, nval, mval;
+ u32 uval, uninitialized_var(nval), mval;
retry:
if (get_user(uval, uaddr))
* userspace.
*/
mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
- nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
- if (nval == -EFAULT)
- return -1;
-
+ /*
+ * We are not holding a lock here, but we want to have
+ * the pagefault_disable/enable() protection because
+ * we want to handle the fault gracefully. If the
+ * access fails we try to fault in the futex with R/W
+ * verification via get_user_pages. get_user() above
+ * does not guarantee R/W access. If that fails we
+ * give up and leave the futex locked.
+ */
+ if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+ if (fault_in_user_writeable(uaddr))
+ return -1;
+ goto retry;
+ }
if (nval != uval)
goto retry;
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
- int ret = -ENOSYS, cmd = op & FUTEX_CMD_MASK;
+ int cmd = op & FUTEX_CMD_MASK;
unsigned int flags = 0;
if (!(op & FUTEX_PRIVATE_FLAG))
}
switch (cmd) {
+ case FUTEX_LOCK_PI:
+ case FUTEX_UNLOCK_PI:
+ case FUTEX_TRYLOCK_PI:
+ case FUTEX_WAIT_REQUEUE_PI:
+ case FUTEX_CMP_REQUEUE_PI:
+ if (!futex_cmpxchg_enabled)
+ return -ENOSYS;
+ }
+
+ switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAIT_BITSET:
- ret = futex_wait(uaddr, flags, val, timeout, val3);
- break;
+ return futex_wait(uaddr, flags, val, timeout, val3);
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAKE_BITSET:
- ret = futex_wake(uaddr, flags, val, val3);
- break;
+ return futex_wake(uaddr, flags, val, val3);
case FUTEX_REQUEUE:
- ret = futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
- break;
+ return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
case FUTEX_CMP_REQUEUE:
- ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
- break;
+ return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
case FUTEX_WAKE_OP:
- ret = futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
- break;
+ return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
case FUTEX_LOCK_PI:
- if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, flags, val, timeout, 0);
- break;
+ return futex_lock_pi(uaddr, flags, val, timeout, 0);
case FUTEX_UNLOCK_PI:
- if (futex_cmpxchg_enabled)
- ret = futex_unlock_pi(uaddr, flags);
- break;
+ return futex_unlock_pi(uaddr, flags);
case FUTEX_TRYLOCK_PI:
- if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, flags, 0, timeout, 1);
- break;
+ return futex_lock_pi(uaddr, flags, 0, timeout, 1);
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
- ret = futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
- uaddr2);
- break;
+ return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
+ uaddr2);
case FUTEX_CMP_REQUEUE_PI:
- ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
- break;
- default:
- ret = -ENOSYS;
+ return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
}
- return ret;
+ return -ENOSYS;
}
* implementation, the non-functional ones will return
* -ENOSYS.
*/
- curval = cmpxchg_futex_value_locked(NULL, 0, 0);
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
- plist_head_init(&futex_queues[i].chain, &futex_queues[i].lock);
+ plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
projects / linux-flexiantxendom0-3.2.10.git / blobdiff