#include <linux/nsproxy.h>
#include <linux/ptrace.h>
#include <linux/sched/rt.h>
+#include <linux/freezer.h>
#include <asm/futex.h>
* @rw: mapping needs to be read/write (values: VERIFY_READ,
* VERIFY_WRITE)
*
- * Returns a negative error code or 0
+ * Return: a negative error code or 0
+ *
* The key words are stored in *key on success.
*
* For shared mappings, it's (page->index, file_inode(vma->vm_file),
raw_spin_unlock_irq(&curr->pi_lock);
}
+/*
+ * We need to check the following states:
+ *
+ * Waiter | pi_state | pi->owner | uTID | uODIED | ?
+ *
+ * [1] NULL | --- | --- | 0 | 0/1 | Valid
+ * [2] NULL | --- | --- | >0 | 0/1 | Valid
+ *
+ * [3] Found | NULL | -- | Any | 0/1 | Invalid
+ *
+ * [4] Found | Found | NULL | 0 | 1 | Valid
+ * [5] Found | Found | NULL | >0 | 1 | Invalid
+ *
+ * [6] Found | Found | task | 0 | 1 | Valid
+ *
+ * [7] Found | Found | NULL | Any | 0 | Invalid
+ *
+ * [8] Found | Found | task | ==taskTID | 0/1 | Valid
+ * [9] Found | Found | task | 0 | 0 | Invalid
+ * [10] Found | Found | task | !=taskTID | 0/1 | Invalid
+ *
+ * [1] Indicates that the kernel can acquire the futex atomically. We
+ * came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ *
+ * [2] Valid, if TID does not belong to a kernel thread. If no matching
+ * thread is found then it indicates that the owner TID has died.
+ *
+ * [3] Invalid. The waiter is queued on a non PI futex
+ *
+ * [4] Valid state after exit_robust_list(), which sets the user space
+ * value to FUTEX_WAITERS | FUTEX_OWNER_DIED.
+ *
+ * [5] The user space value got manipulated between exit_robust_list()
+ * and exit_pi_state_list()
+ *
+ * [6] Valid state after exit_pi_state_list() which sets the new owner in
+ * the pi_state but cannot access the user space value.
+ *
+ * [7] pi_state->owner can only be NULL when the OWNER_DIED bit is set.
+ *
+ * [8] Owner and user space value match
+ *
+ * [9] There is no transient state which sets the user space TID to 0
+ * except exit_robust_list(), but this is indicated by the
+ * FUTEX_OWNER_DIED bit. See [4]
+ *
+ * [10] There is no transient state which leaves owner and user space
+ * TID out of sync.
+ */
static int
lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
union futex_key *key, struct futex_pi_state **ps)
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex(&this->key, key)) {
/*
- * Another waiter already exists - bump up
- * the refcount and return its pi_state:
+ * Sanity check the waiter before increasing
+ * the refcount and attaching to it.
*/
pi_state = this->pi_state;
/*
- * Userspace might have messed up non-PI and PI futexes
+ * Userspace might have messed up non-PI and
+ * PI futexes [3]
*/
if (unlikely(!pi_state))
return -EINVAL;
WARN_ON(!atomic_read(&pi_state->refcount));
/*
- * When pi_state->owner is NULL then the owner died
- * and another waiter is on the fly. pi_state->owner
- * is fixed up by the task which acquires
- * pi_state->rt_mutex.
- *
- * We do not check for pid == 0 which can happen when
- * the owner died and robust_list_exit() cleared the
- * TID.
+ * Handle the owner died case:
*/
- if (pid && pi_state->owner) {
+ if (uval & FUTEX_OWNER_DIED) {
+ /*
+ * exit_pi_state_list sets owner to NULL and
+ * wakes the topmost waiter. The task which
+ * acquires the pi_state->rt_mutex will fixup
+ * owner.
+ */
+ if (!pi_state->owner) {
+ /*
+ * No pi state owner, but the user
+ * space TID is not 0. Inconsistent
+ * state. [5]
+ */
+ if (pid)
+ return -EINVAL;
+ /*
+ * Take a ref on the state and
+ * return. [4]
+ */
+ goto out_state;
+ }
+
+ /*
+ * If TID is 0, then either the dying owner
+ * has not yet executed exit_pi_state_list()
+ * or some waiter acquired the rtmutex in the
+ * pi state, but did not yet fixup the TID in
+ * user space.
+ *
+ * Take a ref on the state and return. [6]
+ */
+ if (!pid)
+ goto out_state;
+ } else {
/*
- * Bail out if user space manipulated the
- * futex value.
+ * If the owner died bit is not set,
+ * then the pi_state must have an
+ * owner. [7]
*/
- if (pid != task_pid_vnr(pi_state->owner))
+ if (!pi_state->owner)
return -EINVAL;
}
+ /*
+ * Bail out if user space manipulated the
+ * futex value. If pi state exists then the
+ * owner TID must be the same as the user
+ * space TID. [9/10]
+ */
+ if (pid != task_pid_vnr(pi_state->owner))
+ return -EINVAL;
+
+ out_state:
atomic_inc(&pi_state->refcount);
*ps = pi_state;
-
return 0;
}
}
/*
* We are the first waiter - try to look up the real owner and attach
- * the new pi_state to it, but bail out when TID = 0
+ * the new pi_state to it, but bail out when TID = 0 [1]
*/
if (!pid)
return -ESRCH;
return ret;
}
+ /*
+ * No existing pi state. First waiter. [2]
+ */
pi_state = alloc_pi_state();
/*
* be "current" except in the case of requeue pi.
* @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0)
*
- * Returns:
- * 0 - ready to wait
- * 1 - acquired the lock
+ * Return:
+ * 0 - ready to wait;
+ * 1 - acquired the lock;
* <0 - error
*
* The hb->lock and futex_key refs shall be held by the caller.
return -EDEADLK;
/*
- * Surprise - we got the lock. Just return to userspace:
+ * Surprise - we got the lock, but we do not trust user space at all.
*/
- if (unlikely(!curval))
- return 1;
+ if (unlikely(!curval)) {
+ /*
+ * We verify whether there is kernel state for this
+ * futex. If not, we can safely assume, that the 0 ->
+ * TID transition is correct. If state exists, we do
+ * not bother to fixup the user space state as it was
+ * corrupted already.
+ */
+ return futex_top_waiter(hb, key) ? -EINVAL : 1;
+ }
uval = curval;
struct task_struct *new_owner;
struct futex_pi_state *pi_state = this->pi_state;
u32 uninitialized_var(curval), newval;
+ int ret = 0;
if (!pi_state)
return -EINVAL;
new_owner = this->task;
/*
- * We pass it to the next owner. (The WAITERS bit is always
- * kept enabled while there is PI state around. We must also
- * preserve the owner died bit.)
+ * We pass it to the next owner. The WAITERS bit is always
+ * kept enabled while there is PI state around. We cleanup the
+ * owner died bit, because we are the owner.
*/
- if (!(uval & FUTEX_OWNER_DIED)) {
- int ret = 0;
-
- newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
+ newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
- ret = -EFAULT;
- else if (curval != uval)
- ret = -EINVAL;
- if (ret) {
- raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
- return ret;
- }
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+ ret = -EFAULT;
+ else if (curval != uval)
+ ret = -EINVAL;
+ if (ret) {
+ raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+ return ret;
}
raw_spin_lock_irq(&pi_state->owner->pi_lock);
* then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
* hb1 and hb2 must be held by the caller.
*
- * Returns:
- * 0 - failed to acquire the lock atomicly
- * 1 - acquired the lock
+ * Return:
+ * 0 - failed to acquire the lock atomically;
+ * 1 - acquired the lock;
* <0 - error
*/
static int futex_proxy_trylock_atomic(u32 __user *pifutex,
* Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
* uaddr2 atomically on behalf of the top waiter.
*
- * Returns:
- * >=0 - on success, the number of tasks requeued or woken
+ * Return:
+ * >=0 - on success, the number of tasks requeued or woken;
* <0 - on error
*/
static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
u32 curval2;
if (requeue_pi) {
+ /*
+ * Requeue PI only works on two distinct uaddrs. This
+ * check is only valid for private futexes. See below.
+ */
+ if (uaddr1 == uaddr2)
+ return -EINVAL;
+
/*
* requeue_pi requires a pi_state, try to allocate it now
* without any locks in case it fails.
if (unlikely(ret != 0))
goto out_put_key1;
+ /*
+ * The check above which compares uaddrs is not sufficient for
+ * shared futexes. We need to compare the keys:
+ */
+ if (requeue_pi && match_futex(&key1, &key2)) {
+ ret = -EINVAL;
+ goto out_put_keys;
+ }
+
hb1 = hash_futex(&key1);
hb2 = hash_futex(&key2);
* The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
* be paired with exactly one earlier call to queue_me().
*
- * Returns:
- * 1 - if the futex_q was still queued (and we removed unqueued it)
+ * Return:
+ * 1 - if the futex_q was still queued (and we removed unqueued it);
* 0 - if the futex_q was already removed by the waking thread
*/
static int unqueue_me(struct futex_q *q)
* the pi_state owner as well as handle race conditions that may allow us to
* acquire the lock. Must be called with the hb lock held.
*
- * Returns:
- * 1 - success, lock taken
- * 0 - success, lock not taken
+ * Return:
+ * 1 - success, lock taken;
+ * 0 - success, lock not taken;
* <0 - on error (-EFAULT)
*/
static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
* is no timeout, or if it has yet to expire.
*/
if (!timeout || timeout->task)
- schedule();
+ freezable_schedule();
}
__set_current_state(TASK_RUNNING);
}
* Return with the hb lock held and a q.key reference on success, and unlocked
* with no q.key reference on failure.
*
- * Returns:
- * 0 - uaddr contains val and hb has been locked
+ * Return:
+ * 0 - uaddr contains val and hb has been locked;
* <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,
/*
* To avoid races, try to do the TID -> 0 atomic transition
* again. If it succeeds then we can return without waking
- * anyone else up:
+ * anyone else up. We only try this if neither the waiters nor
+ * the owner died bit are set.
*/
- if (!(uval & FUTEX_OWNER_DIED) &&
+ if (!(uval & ~FUTEX_TID_MASK) &&
cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
goto pi_faulted;
/*
/*
* No waiters - kernel unlocks the futex:
*/
- if (!(uval & FUTEX_OWNER_DIED)) {
- ret = unlock_futex_pi(uaddr, uval);
- if (ret == -EFAULT)
- goto pi_faulted;
- }
+ ret = unlock_futex_pi(uaddr, uval);
+ if (ret == -EFAULT)
+ goto pi_faulted;
out_unlock:
spin_unlock(&hb->lock);
* the wakeup and return the appropriate error code to the caller. Must be
* called with the hb lock held.
*
- * Returns
- * 0 - no early wakeup detected
- * <0 - -ETIMEDOUT or -ERESTARTNOINTR
+ * Return:
+ * 0 = no early wakeup detected;
+ * <0 = -ETIMEDOUT or -ERESTARTNOINTR
*/
static inline
int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* @val: the expected value of uaddr
* @abs_time: absolute timeout
* @bitset: 32 bit wakeup bitset set by userspace, defaults to all
- * @clockrt: whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
* @uaddr2: the pi futex we will take prior to returning to user-space
*
* The caller will wait on uaddr and will be requeued by futex_requeue() to
* there was a need to.
*
* We call schedule in futex_wait_queue_me() when we enqueue and return there
- * via the following:
+ * via the following--
* 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
* 2) wakeup on uaddr2 after a requeue
* 3) signal
*
* If 4 or 7, we cleanup and return with -ETIMEDOUT.
*
- * Returns:
- * 0 - On success
+ * Return:
+ * 0 - On success;
* <0 - On error
*/
static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
if (ret)
goto out_key2;
+ /*
+ * The check above which compares uaddrs is not sufficient for
+ * shared futexes. We need to compare the keys:
+ */
+ if (match_futex(&q.key, &key2)) {
+ ret = -EINVAL;
+ goto out_put_keys;
+ }
+
/* Queue the futex_q, drop the hb lock, wait for wakeup. */
futex_wait_queue_me(hb, &q, to);