summaryrefslogtreecommitdiff
path: root/kernel/futex.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/futex.c')
-rw-r--r--kernel/futex.c326
1 files changed, 282 insertions, 44 deletions
diff --git a/kernel/futex.c b/kernel/futex.c
index bd18f60e4c6c..03c518e9747e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -325,6 +325,12 @@ static inline bool should_fail_futex(bool fshared)
}
#endif /* CONFIG_FAIL_FUTEX */
+#ifdef CONFIG_COMPAT
+static void compat_exit_robust_list(struct task_struct *curr);
+#else
+static inline void compat_exit_robust_list(struct task_struct *curr) { }
+#endif
+
static inline void futex_get_mm(union futex_key *key)
{
mmgrab(key->private.mm);
@@ -890,7 +896,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
* Kernel cleans up PI-state, but userspace is likely hosed.
* (Robust-futex cleanup is separate and might save the day for userspace.)
*/
-void exit_pi_state_list(struct task_struct *curr)
+static void exit_pi_state_list(struct task_struct *curr)
{
struct list_head *next, *head = &curr->pi_state_list;
struct futex_pi_state *pi_state;
@@ -960,7 +966,8 @@ void exit_pi_state_list(struct task_struct *curr)
}
raw_spin_unlock_irq(&curr->pi_lock);
}
-
+#else
+static inline void exit_pi_state_list(struct task_struct *curr) { }
#endif
/*
@@ -1169,16 +1176,47 @@ out_error:
return ret;
}
+/**
+ * wait_for_owner_exiting - Block until the owner has exited
+ * @exiting: Pointer to the exiting task
+ *
+ * Caller must hold a refcount on @exiting.
+ */
+static void wait_for_owner_exiting(int ret, struct task_struct *exiting)
+{
+ if (ret != -EBUSY) {
+ WARN_ON_ONCE(exiting);
+ return;
+ }
+
+ if (WARN_ON_ONCE(ret == -EBUSY && !exiting))
+ return;
+
+ mutex_lock(&exiting->futex_exit_mutex);
+ /*
+ * No point in doing state checking here. If the waiter got here
+ * while the task was in exec()->exec_futex_release() then it can
+ * have any FUTEX_STATE_* value when the waiter has acquired the
+ * mutex. OK, if running, EXITING or DEAD if it reached exit()
+ * already. Highly unlikely and not a problem. Just one more round
+ * through the futex maze.
+ */
+ mutex_unlock(&exiting->futex_exit_mutex);
+
+ put_task_struct(exiting);
+}
+
static int handle_exit_race(u32 __user *uaddr, u32 uval,
struct task_struct *tsk)
{
u32 uval2;
/*
- * If PF_EXITPIDONE is not yet set, then try again.
+ * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the
+ * caller that the alleged owner is busy.
*/
- if (tsk && !(tsk->flags & PF_EXITPIDONE))
- return -EAGAIN;
+ if (tsk && tsk->futex_state != FUTEX_STATE_DEAD)
+ return -EBUSY;
/*
* Reread the user space value to handle the following situation:
@@ -1196,8 +1234,9 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
* *uaddr = 0xC0000000; tsk = get_task(PID);
* } if (!tsk->flags & PF_EXITING) {
* ... attach();
- * tsk->flags |= PF_EXITPIDONE; } else {
- * if (!(tsk->flags & PF_EXITPIDONE))
+ * tsk->futex_state = } else {
+ * FUTEX_STATE_DEAD; if (tsk->futex_state !=
+ * FUTEX_STATE_DEAD)
* return -EAGAIN;
* return -ESRCH; <--- FAIL
* }
@@ -1228,7 +1267,8 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
* it after doing proper sanity checks.
*/
static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
- struct futex_pi_state **ps)
+ struct futex_pi_state **ps,
+ struct task_struct **exiting)
{
pid_t pid = uval & FUTEX_TID_MASK;
struct futex_pi_state *pi_state;
@@ -1253,22 +1293,33 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
}
/*
- * We need to look at the task state flags to figure out,
- * whether the task is exiting. To protect against the do_exit
- * change of the task flags, we do this protected by
- * p->pi_lock:
+ * We need to look at the task state to figure out, whether the
+ * task is exiting. To protect against the change of the task state
+ * in futex_exit_release(), we do this protected by p->pi_lock:
*/
raw_spin_lock_irq(&p->pi_lock);
- if (unlikely(p->flags & PF_EXITING)) {
+ if (unlikely(p->futex_state != FUTEX_STATE_OK)) {
/*
- * The task is on the way out. When PF_EXITPIDONE is
- * set, we know that the task has finished the
- * cleanup:
+ * The task is on the way out. When the futex state is
+ * FUTEX_STATE_DEAD, we know that the task has finished
+ * the cleanup:
*/
int ret = handle_exit_race(uaddr, uval, p);
raw_spin_unlock_irq(&p->pi_lock);
- put_task_struct(p);
+ /*
+ * If the owner task is between FUTEX_STATE_EXITING and
+ * FUTEX_STATE_DEAD then store the task pointer and keep
+ * the reference on the task struct. The calling code will
+ * drop all locks, wait for the task to reach
+ * FUTEX_STATE_DEAD and then drop the refcount. This is
+ * required to prevent a live lock when the current task
+ * preempted the exiting task between the two states.
+ */
+ if (ret == -EBUSY)
+ *exiting = p;
+ else
+ put_task_struct(p);
return ret;
}
@@ -1307,7 +1358,8 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
static int lookup_pi_state(u32 __user *uaddr, u32 uval,
struct futex_hash_bucket *hb,
- union futex_key *key, struct futex_pi_state **ps)
+ union futex_key *key, struct futex_pi_state **ps,
+ struct task_struct **exiting)
{
struct futex_q *top_waiter = futex_top_waiter(hb, key);
@@ -1322,7 +1374,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
* We are the first waiter - try to look up the owner based on
* @uval and attach to it.
*/
- return attach_to_pi_owner(uaddr, uval, key, ps);
+ return attach_to_pi_owner(uaddr, uval, key, ps, exiting);
}
static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
@@ -1350,6 +1402,8 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
* lookup
* @task: the task to perform the atomic lock work for. This will
* be "current" except in the case of requeue pi.
+ * @exiting: Pointer to store the task pointer of the owner task
+ * which is in the middle of exiting
* @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0)
*
* Return:
@@ -1358,11 +1412,17 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
* - <0 - error
*
* The hb->lock and futex_key refs shall be held by the caller.
+ *
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
*/
static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
union futex_key *key,
struct futex_pi_state **ps,
- struct task_struct *task, int set_waiters)
+ struct task_struct *task,
+ struct task_struct **exiting,
+ int set_waiters)
{
u32 uval, newval, vpid = task_pid_vnr(task);
struct futex_q *top_waiter;
@@ -1432,7 +1492,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
* attach to the owner. If that fails, no harm done, we only
* set the FUTEX_WAITERS bit in the user space variable.
*/
- return attach_to_pi_owner(uaddr, newval, key, ps);
+ return attach_to_pi_owner(uaddr, newval, key, ps, exiting);
}
/**
@@ -1480,7 +1540,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
/*
* Queue the task for later wakeup for after we've released
- * the hb->lock. wake_q_add() grabs reference to p.
+ * the hb->lock.
*/
wake_q_add_safe(wake_q, p);
}
@@ -1850,6 +1910,8 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
* @key1: the from futex key
* @key2: the to futex key
* @ps: address to store the pi_state pointer
+ * @exiting: Pointer to store the task pointer of the owner task
+ * which is in the middle of exiting
* @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0)
*
* Try and get the lock on behalf of the top waiter if we can do it atomically.
@@ -1857,16 +1919,20 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
* then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
* hb1 and hb2 must be held by the caller.
*
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
+ *
* Return:
* - 0 - failed to acquire the lock atomically;
* - >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_hash_bucket *hb1,
- struct futex_hash_bucket *hb2,
- union futex_key *key1, union futex_key *key2,
- struct futex_pi_state **ps, int set_waiters)
+static int
+futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
+ struct futex_hash_bucket *hb2, union futex_key *key1,
+ union futex_key *key2, struct futex_pi_state **ps,
+ struct task_struct **exiting, int set_waiters)
{
struct futex_q *top_waiter = NULL;
u32 curval;
@@ -1903,7 +1969,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
*/
vpid = task_pid_vnr(top_waiter->task);
ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
- set_waiters);
+ exiting, set_waiters);
if (ret == 1) {
requeue_pi_wake_futex(top_waiter, key2, hb2);
return vpid;
@@ -2032,6 +2098,8 @@ retry_private:
}
if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+ struct task_struct *exiting = NULL;
+
/*
* Attempt to acquire uaddr2 and wake the top waiter. If we
* intend to requeue waiters, force setting the FUTEX_WAITERS
@@ -2039,7 +2107,8 @@ retry_private:
* faults rather in the requeue loop below.
*/
ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
- &key2, &pi_state, nr_requeue);
+ &key2, &pi_state,
+ &exiting, nr_requeue);
/*
* At this point the top_waiter has either taken uaddr2 or is
@@ -2066,7 +2135,8 @@ retry_private:
* If that call succeeds then we have pi_state and an
* initial refcount on it.
*/
- ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
+ ret = lookup_pi_state(uaddr2, ret, hb2, &key2,
+ &pi_state, &exiting);
}
switch (ret) {
@@ -2084,17 +2154,24 @@ retry_private:
if (!ret)
goto retry;
goto out;
+ case -EBUSY:
case -EAGAIN:
/*
* Two reasons for this:
- * - Owner is exiting and we just wait for the
+ * - EBUSY: Owner is exiting and we just wait for the
* exit to complete.
- * - The user space value changed.
+ * - EAGAIN: The user space value changed.
*/
double_unlock_hb(hb1, hb2);
hb_waiters_dec(hb2);
put_futex_key(&key2);
put_futex_key(&key1);
+ /*
+ * Handle the case where the owner is in the middle of
+ * exiting. Wait for the exit to complete otherwise
+ * this task might loop forever, aka. live lock.
+ */
+ wait_for_owner_exiting(ret, exiting);
cond_resched();
goto retry;
default:
@@ -2801,6 +2878,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
{
struct hrtimer_sleeper timeout, *to;
struct futex_pi_state *pi_state = NULL;
+ struct task_struct *exiting = NULL;
struct rt_mutex_waiter rt_waiter;
struct futex_hash_bucket *hb;
struct futex_q q = futex_q_init;
@@ -2822,7 +2900,8 @@ retry:
retry_private:
hb = queue_lock(&q);
- ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
+ ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current,
+ &exiting, 0);
if (unlikely(ret)) {
/*
* Atomic work succeeded and we got the lock,
@@ -2835,15 +2914,22 @@ retry_private:
goto out_unlock_put_key;
case -EFAULT:
goto uaddr_faulted;
+ case -EBUSY:
case -EAGAIN:
/*
* Two reasons for this:
- * - Task is exiting and we just wait for the
+ * - EBUSY: Task is exiting and we just wait for the
* exit to complete.
- * - The user space value changed.
+ * - EAGAIN: The user space value changed.
*/
queue_unlock(hb);
put_futex_key(&q.key);
+ /*
+ * Handle the case where the owner is in the middle of
+ * exiting. Wait for the exit to complete otherwise
+ * this task might loop forever, aka. live lock.
+ */
+ wait_for_owner_exiting(ret, exiting);
cond_resched();
goto retry;
default:
@@ -3452,11 +3538,16 @@ err_unlock:
return ret;
}
+/* Constants for the pending_op argument of handle_futex_death */
+#define HANDLE_DEATH_PENDING true
+#define HANDLE_DEATH_LIST false
+
/*
* Process a futex-list entry, check whether it's owned by the
* dying task, and do notification if so:
*/
-static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
+static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
+ bool pi, bool pending_op)
{
u32 uval, uninitialized_var(nval), mval;
int err;
@@ -3469,6 +3560,42 @@ retry:
if (get_user(uval, uaddr))
return -1;
+ /*
+ * Special case for regular (non PI) futexes. The unlock path in
+ * user space has two race scenarios:
+ *
+ * 1. The unlock path releases the user space futex value and
+ * before it can execute the futex() syscall to wake up
+ * waiters it is killed.
+ *
+ * 2. A woken up waiter is killed before it can acquire the
+ * futex in user space.
+ *
+ * In both cases the TID validation below prevents a wakeup of
+ * potential waiters which can cause these waiters to block
+ * forever.
+ *
+ * In both cases the following conditions are met:
+ *
+ * 1) task->robust_list->list_op_pending != NULL
+ * @pending_op == true
+ * 2) User space futex value == 0
+ * 3) Regular futex: @pi == false
+ *
+ * If these conditions are met, it is safe to attempt waking up a
+ * potential waiter without touching the user space futex value and
+ * trying to set the OWNER_DIED bit. The user space futex value is
+ * uncontended and the rest of the user space mutex state is
+ * consistent, so a woken waiter will just take over the
+ * uncontended futex. Setting the OWNER_DIED bit would create
+ * inconsistent state and malfunction of the user space owner died
+ * handling.
+ */
+ if (pending_op && !pi && !uval) {
+ futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+ return 0;
+ }
+
if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
return 0;
@@ -3547,7 +3674,7 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
*
* We silently return on any sign of list-walking problem.
*/
-void exit_robust_list(struct task_struct *curr)
+static void exit_robust_list(struct task_struct *curr)
{
struct robust_list_head __user *head = curr->robust_list;
struct robust_list __user *entry, *next_entry, *pending;
@@ -3588,10 +3715,11 @@ void exit_robust_list(struct task_struct *curr)
* A pending lock might already be on the list, so
* don't process it twice:
*/
- if (entry != pending)
+ if (entry != pending) {
if (handle_futex_death((void __user *)entry + futex_offset,
- curr, pi))
+ curr, pi, HANDLE_DEATH_LIST))
return;
+ }
if (rc)
return;
entry = next_entry;
@@ -3605,9 +3733,118 @@ void exit_robust_list(struct task_struct *curr)
cond_resched();
}
- if (pending)
+ if (pending) {
handle_futex_death((void __user *)pending + futex_offset,
- curr, pip);
+ curr, pip, HANDLE_DEATH_PENDING);
+ }
+}
+
+static void futex_cleanup(struct task_struct *tsk)
+{
+ if (unlikely(tsk->robust_list)) {
+ exit_robust_list(tsk);
+ tsk->robust_list = NULL;
+ }
+
+#ifdef CONFIG_COMPAT
+ if (unlikely(tsk->compat_robust_list)) {
+ compat_exit_robust_list(tsk);
+ tsk->compat_robust_list = NULL;
+ }
+#endif
+
+ if (unlikely(!list_empty(&tsk->pi_state_list)))
+ exit_pi_state_list(tsk);
+}
+
+/**
+ * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD
+ * @tsk: task to set the state on
+ *
+ * Set the futex exit state of the task lockless. The futex waiter code
+ * observes that state when a task is exiting and loops until the task has
+ * actually finished the futex cleanup. The worst case for this is that the
+ * waiter runs through the wait loop until the state becomes visible.
+ *
+ * This is called from the recursive fault handling path in do_exit().
+ *
+ * This is best effort. Either the futex exit code has run already or
+ * not. If the OWNER_DIED bit has been set on the futex then the waiter can
+ * take it over. If not, the problem is pushed back to user space. If the
+ * futex exit code did not run yet, then an already queued waiter might
+ * block forever, but there is nothing which can be done about that.
+ */
+void futex_exit_recursive(struct task_struct *tsk)
+{
+ /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */
+ if (tsk->futex_state == FUTEX_STATE_EXITING)
+ mutex_unlock(&tsk->futex_exit_mutex);
+ tsk->futex_state = FUTEX_STATE_DEAD;
+}
+
+static void futex_cleanup_begin(struct task_struct *tsk)
+{
+ /*
+ * Prevent various race issues against a concurrent incoming waiter
+ * including live locks by forcing the waiter to block on
+ * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in
+ * attach_to_pi_owner().
+ */
+ mutex_lock(&tsk->futex_exit_mutex);
+
+ /*
+ * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock.
+ *
+ * This ensures that all subsequent checks of tsk->futex_state in
+ * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with
+ * tsk->pi_lock held.
+ *
+ * It guarantees also that a pi_state which was queued right before
+ * the state change under tsk->pi_lock by a concurrent waiter must
+ * be observed in exit_pi_state_list().
+ */
+ raw_spin_lock_irq(&tsk->pi_lock);
+ tsk->futex_state = FUTEX_STATE_EXITING;
+ raw_spin_unlock_irq(&tsk->pi_lock);
+}
+
+static void futex_cleanup_end(struct task_struct *tsk, int state)
+{
+ /*
+ * Lockless store. The only side effect is that an observer might
+ * take another loop until it becomes visible.
+ */
+ tsk->futex_state = state;
+ /*
+ * Drop the exit protection. This unblocks waiters which observed
+ * FUTEX_STATE_EXITING to reevaluate the state.
+ */
+ mutex_unlock(&tsk->futex_exit_mutex);
+}
+
+void futex_exec_release(struct task_struct *tsk)
+{
+ /*
+ * The state handling is done for consistency, but in the case of
+ * exec() there is no way to prevent futher damage as the PID stays
+ * the same. But for the unlikely and arguably buggy case that a
+ * futex is held on exec(), this provides at least as much state
+ * consistency protection which is possible.
+ */
+ futex_cleanup_begin(tsk);
+ futex_cleanup(tsk);
+ /*
+ * Reset the state to FUTEX_STATE_OK. The task is alive and about
+ * exec a new binary.
+ */
+ futex_cleanup_end(tsk, FUTEX_STATE_OK);
+}
+
+void futex_exit_release(struct task_struct *tsk)
+{
+ futex_cleanup_begin(tsk);
+ futex_cleanup(tsk);
+ futex_cleanup_end(tsk, FUTEX_STATE_DEAD);
}
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
@@ -3737,7 +3974,7 @@ static void __user *futex_uaddr(struct robust_list __user *entry,
*
* We silently return on any sign of list-walking problem.
*/
-void compat_exit_robust_list(struct task_struct *curr)
+static void compat_exit_robust_list(struct task_struct *curr)
{
struct compat_robust_list_head __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
@@ -3784,7 +4021,8 @@ void compat_exit_robust_list(struct task_struct *curr)
if (entry != pending) {
void __user *uaddr = futex_uaddr(entry, futex_offset);
- if (handle_futex_death(uaddr, curr, pi))
+ if (handle_futex_death(uaddr, curr, pi,
+ HANDLE_DEATH_LIST))
return;
}
if (rc)
@@ -3803,7 +4041,7 @@ void compat_exit_robust_list(struct task_struct *curr)
if (pending) {
void __user *uaddr = futex_uaddr(pending, futex_offset);
- handle_futex_death(uaddr, curr, pip);
+ handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING);
}
}