#include <linux/magic.h>
#include <linux/pid.h>
#include <linux/nsproxy.h>
+#include <linux/ptrace.h>
+#include <linux/hugetlb.h>
#include <asm/futex.h>
put_page(page);
/* serialize against __split_huge_page_splitting() */
local_irq_disable();
- if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+ 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
#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);
- /*
- * ZERO_PAGE pages don't have a mapping. Avoid a busy loop
- * trying to find one. RW mapping would have COW'd (and thus
- * have a mapping) so this page is RO and won't ever change.
- */
- if ((page_head == ZERO_PAGE(address)))
- return -EFAULT;
- goto again;
+ if (shmem_swizzled)
+ goto again;
+ return -EFAULT;
}
/*
} else {
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.inode = page_head->mapping->host;
- key->shared.pgoff = page_head->index;
+ key->shared.pgoff = basepage_index(page);
}
get_futex_key_refs(key);
return pi_state;
}
+/*
+ * Must be called with the hb lock held.
+ */
static void free_pi_state(struct futex_pi_state *pi_state)
{
+ if (!pi_state)
+ return;
+
if (!atomic_dec_and_test(&pi_state->refcount))
return;
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) {
/*
- * Bail out if user space manipulated the
- * futex value.
+ * 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 (pid != task_pid_vnr(pi_state->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 {
+ /*
+ * If the owner died bit is not set,
+ * then the pi_state must have an
+ * owner. [7]
+ */
+ 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;
if (!p)
return -ESRCH;
+ if (!p->mm) {
+ put_task_struct(p);
+ return -EPERM;
+ }
+
/*
* We need to look at the task state flags to figure out,
* whether the task is exiting. To protect against the do_exit
return ret;
}
+ /*
+ * No existing pi state. First waiter. [2]
+ */
pi_state = alloc_pi_state();
/*
struct futex_pi_state **ps,
struct task_struct *task, int set_waiters)
{
- int lock_taken, ret, ownerdied = 0;
+ int lock_taken, ret, force_take = 0;
u32 uval, newval, curval, vpid = task_pid_vnr(task);
retry:
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;
newval = curval | FUTEX_WAITERS;
/*
- * There are two cases, where a futex might have no owner (the
- * owner TID is 0): OWNER_DIED. We take over the futex in this
- * case. We also do an unconditional take over, when the owner
- * of the futex died.
- *
- * This is safe as we are protected by the hash bucket lock !
+ * Should we force take the futex? See below.
*/
- if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
- /* Keep the OWNER_DIED bit */
+ if (unlikely(force_take)) {
+ /*
+ * Keep the OWNER_DIED and the WAITERS bit and set the
+ * new TID value.
+ */
newval = (curval & ~FUTEX_TID_MASK) | vpid;
- ownerdied = 0;
+ force_take = 0;
lock_taken = 1;
}
goto retry;
/*
- * We took the lock due to owner died take over.
+ * We took the lock due to forced take over.
*/
if (unlikely(lock_taken))
return 1;
switch (ret) {
case -ESRCH:
/*
- * No owner found for this futex. Check if the
- * OWNER_DIED bit is set to figure out whether
- * this is a robust futex or not.
+ * We failed to find an owner for this
+ * futex. So we have no pi_state to block
+ * on. This can happen in two cases:
+ *
+ * 1) The owner died
+ * 2) A stale FUTEX_WAITERS bit
+ *
+ * Re-read the futex value.
*/
if (get_futex_value_locked(&curval, uaddr))
return -EFAULT;
/*
- * We simply start over in case of a robust
- * futex. The code above will take the futex
- * and return happy.
+ * If the owner died or we have a stale
+ * WAITERS bit the owner TID in the user space
+ * futex is 0.
*/
- if (curval & FUTEX_OWNER_DIED) {
- ownerdied = 1;
+ if (!(curval & FUTEX_TID_MASK)) {
+ force_take = 1;
goto retry;
}
default:
{
struct task_struct *p = q->task;
+ if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
+ return;
+
/*
* We set q->lock_ptr = NULL _before_ we wake up the task. If
* a non-futex wake up happens on another CPU then the task
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);
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex (&this->key, &key1)) {
+ if (this->pi_state || this->rt_waiter) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
wake_futex(this);
if (++ret >= nr_wake)
break;
op_ret = 0;
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex (&this->key, &key2)) {
+ if (this->pi_state || this->rt_waiter) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
wake_futex(this);
if (++op_ret >= nr_wake2)
break;
ret += op_ret;
}
+out_unlock:
double_unlock_hb(hb1, hb2);
out_put_keys:
put_futex_key(&key2);
*
* Returns:
* 0 - failed to acquire the lock atomicly
- * 1 - acquired the lock
+ * >0 - acquired the lock, return value is vpid of the top_waiter
* <0 - error
*/
static int futex_proxy_trylock_atomic(u32 __user *pifutex,
{
struct futex_q *top_waiter = NULL;
u32 curval;
- int ret;
+ int ret, vpid;
if (get_futex_value_locked(&curval, pifutex))
return -EFAULT;
* the contended case or if set_waiters is 1. The pi_state is returned
* in ps in contended cases.
*/
+ vpid = task_pid_vnr(top_waiter->task);
ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
set_waiters);
- if (ret == 1)
+ if (ret == 1) {
requeue_pi_wake_futex(top_waiter, key2, hb2);
-
+ return vpid;
+ }
return ret;
}
struct futex_hash_bucket *hb1, *hb2;
struct plist_head *head1;
struct futex_q *this, *next;
- 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.
}
retry:
- if (pi_state != NULL) {
- /*
- * We will have to lookup the pi_state again, so free this one
- * to keep the accounting correct.
- */
- free_pi_state(pi_state);
- pi_state = NULL;
- }
-
ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
if (unlikely(ret != 0))
goto out;
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);
* At this point the top_waiter has either taken uaddr2 or is
* waiting on it. If the former, then the pi_state will not
* exist yet, look it up one more time to ensure we have a
- * reference to it.
+ * reference to it. If the lock was taken, ret contains the
+ * vpid of the top waiter task.
*/
- if (ret == 1) {
+ if (ret > 0) {
WARN_ON(pi_state);
drop_count++;
task_count++;
- ret = get_futex_value_locked(&curval2, uaddr2);
- if (!ret)
- ret = lookup_pi_state(curval2, hb2, &key2,
- &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.
+ */
+ ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
}
switch (ret) {
case 0:
break;
case -EFAULT:
+ free_pi_state(pi_state);
+ pi_state = NULL;
double_unlock_hb(hb1, hb2);
put_futex_key(&key2);
put_futex_key(&key1);
goto out;
case -EAGAIN:
/* The owner was exiting, try again. */
+ free_pi_state(pi_state);
+ pi_state = NULL;
double_unlock_hb(hb1, hb2);
put_futex_key(&key2);
put_futex_key(&key1);
/*
* FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
* be paired with each other and no other futex ops.
+ *
+ * We should never be requeueing a futex_q with a pi_state,
+ * which is awaiting a futex_unlock_pi().
*/
if ((requeue_pi && !this->rt_waiter) ||
- (!requeue_pi && this->rt_waiter)) {
+ (!requeue_pi && this->rt_waiter) ||
+ this->pi_state) {
ret = -EINVAL;
break;
}
}
out_unlock:
+ free_pi_state(pi_state);
double_unlock_hb(hb1, hb2);
/*
out_put_key1:
put_futex_key(&key1);
out:
- if (pi_state != NULL)
- free_pi_state(pi_state);
return ret ? ret : task_count;
}
/*
* 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);
* @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
- * uaddr2 which must be PI aware. Normal wakeup will wake on uaddr2 and
- * complete the acquisition of the rt_mutex prior to returning to userspace.
- * This ensures the rt_mutex maintains an owner when it has waiters; without
- * one, the pi logic wouldn't know which task to boost/deboost, if there was a
- * need to.
+ * uaddr2 which must be PI aware and unique from uaddr. Normal wakeup will wake
+ * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to
+ * userspace. This ensures the rt_mutex maintains an owner when it has waiters;
+ * without one, the pi logic would not know which task to boost/deboost, if
+ * there was a need to.
*
* We call schedule in futex_wait_queue_me() when we enqueue and return there
* via the following:
{
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;
int res, ret;
+ if (uaddr == uaddr2)
+ return -EINVAL;
+
if (!bitset)
return -EINVAL;
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)) {
+ queue_unlock(&q, hb);
+ ret = -EINVAL;
+ goto out_put_keys;
+ }
+
/* Queue the futex_q, drop the hb lock, wait for wakeup. */
futex_wait_queue_me(hb, &q, to);
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.
+ */
+ 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
* the pi_state.
*/
- WARN_ON(!&q.pi_state);
+ WARN_ON(!q.pi_state);
pi_mutex = &q.pi_state->pi_mutex;
ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
debug_rt_mutex_free_waiter(&rt_waiter);
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 (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
{
struct robust_list_head __user *head;
unsigned long ret;
- const struct cred *cred = current_cred(), *pcred;
+ struct task_struct *p;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
+ rcu_read_lock();
+
+ ret = -ESRCH;
if (!pid)
- head = current->robust_list;
+ p = current;
else {
- struct task_struct *p;
-
- ret = -ESRCH;
- rcu_read_lock();
p = find_task_by_vpid(pid);
if (!p)
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 &&
- !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
- goto err_unlock;
-ok:
- head = p->robust_list;
- rcu_read_unlock();
}
+ ret = -EPERM;
+ if (!ptrace_may_access(p, PTRACE_MODE_READ))
+ goto err_unlock;
+
+ head = p->robust_list;
+ rcu_read_unlock();
+
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(head, head_ptr);
return -ENOSYS;
}
+ 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;
ret = futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
break;
case FUTEX_LOCK_PI:
- if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, flags, val, timeout, 0);
+ ret = futex_lock_pi(uaddr, flags, val, timeout, 0);
break;
case FUTEX_UNLOCK_PI:
- if (futex_cmpxchg_enabled)
- ret = futex_unlock_pi(uaddr, flags);
+ ret = futex_unlock_pi(uaddr, flags);
break;
case FUTEX_TRYLOCK_PI:
- if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, flags, 0, timeout, 1);
+ ret = futex_lock_pi(uaddr, flags, 0, timeout, 1);
break;
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
return 0;
}
-__initcall(futex_init);
+core_initcall(futex_init);
git.openpandora.org / pandora-kernel.git / blobdiff