From: Peter Zijlstra <peterz@xxxxxxxxxxxxx> commit c74aef2d06a9f59cece89093eecc552933cba72a upstream. There was a reported suspicion about a race between exit_pi_state_list() and put_pi_state(). The same report mentioned the comment with put_pi_state() said it should be called with hb->lock held, and it no longer is in all places. As it turns out, the pi_state->owner serialization is indeed broken. As per the new rules: 734009e96d19 ("futex: Change locking rules") pi_state->owner should be serialized by pi_state->pi_mutex.wait_lock. For the sites setting pi_state->owner we already hold wait_lock (where required) but exit_pi_state_list() and put_pi_state() were not and raced on clearing it. Fixes: 734009e96d19 ("futex: Change locking rules") Reported-by: Gratian Crisan <gratian.crisan@xxxxxx> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: dvhart@xxxxxxxxxxxxx Cc: stable@xxxxxxxxxxxxxxx Link: https://lkml.kernel.org/r/20170922154806.jd3ffltfk24m4o4y@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx [bwh: Backported to 4.9: adjust context] Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx> --- kernel/futex.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index 77cec33ea112..a07f6080c8b0 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -868,8 +868,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -884,13 +882,15 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); pi_state_update_owner(pi_state, NULL); rt_mutex_proxy_unlock(&pi_state->pi_mutex); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -949,13 +949,14 @@ static void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -964,9 +965,10 @@ static void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1349,6 +1351,10 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -3027,6 +3033,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state);
Attachment:
signature.asc
Description: PGP signature