From e9c243a5a6de0be8e584c604d353412584b592f8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Jun 2014 12:27:06 +0000 Subject: futex-prevent-requeue-pi-on-same-futex.patch futex: Forbid uaddr == uaddr2 in futex_requeue(..., requeue_pi=1) If uaddr == uaddr2, then we have broken the rule of only requeueing from a non-pi futex to a pi futex with this call. If we attempt this, then dangling pointers may be left for rt_waiter resulting in an exploitable condition. This change brings futex_requeue() in line with futex_wait_requeue_pi() which performs the same check as per commit 6f7b0a2a5c0f ("futex: Forbid uaddr == uaddr2 in futex_wait_requeue_pi()") [ tglx: Compare the resulting keys as well, as uaddrs might be different depending on the mapping ] Fixes CVE-2014-3153. Reported-by: Pinkie Pie Signed-off-by: Will Drewry Signed-off-by: Kees Cook Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner Reviewed-by: Darren Hart Signed-off-by: Linus Torvalds --- kernel/futex.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 81dbe773ce4c..663ea2b84a38 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1441,6 +1441,13 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_q *this, *next; 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. @@ -1479,6 +1486,15 @@ retry: 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); @@ -2525,6 +2541,15 @@ 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); -- cgit v1.2.3-58-ga151 From b3eaa9fc5cd0a4d74b18f6b8dc617aeaf1873270 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Jun 2014 12:27:06 +0000 Subject: futex: Validate atomic acquisition in futex_lock_pi_atomic() We need to protect the atomic acquisition in the kernel against rogue user space which sets the user space futex to 0, so the kernel side acquisition succeeds while there is existing state in the kernel associated to the real owner. Verify whether the futex has waiters associated with kernel state. If it has, return -EINVAL. The state is corrupted already, so no point in cleaning it up. Subsequent calls will fail as well. Not our problem. [ tglx: Use futex_top_waiter() and explain why we do not need to try restoring the already corrupted user space state. ] Signed-off-by: Darren Hart Cc: Kees Cook Cc: Will Drewry Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner Signed-off-by: Linus Torvalds --- kernel/futex.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 663ea2b84a38..520e7b23bf3c 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -910,10 +910,18 @@ 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; -- cgit v1.2.3-58-ga151 From 13fbca4c6ecd96ec1a1cfa2e4f2ce191fe928a5e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Jun 2014 12:27:07 +0000 Subject: futex: Always cleanup owner tid in unlock_pi If the owner died bit is set at futex_unlock_pi, we currently do not cleanup the user space futex. So the owner TID of the current owner (the unlocker) persists. That's observable inconsistant state, especially when the ownership of the pi state got transferred. Clean it up unconditionally. Signed-off-by: Thomas Gleixner Cc: Kees Cook Cc: Will Drewry Cc: Darren Hart Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- kernel/futex.c | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 520e7b23bf3c..e1cb1baa23fb 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1052,6 +1052,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) 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; @@ -1075,23 +1076,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) 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); @@ -2351,9 +2348,10 @@ retry: /* * 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; /* @@ -2383,11 +2381,9 @@ retry: /* * 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); -- cgit v1.2.3-58-ga151 From 54a217887a7b658e2650c3feff22756ab80c7339 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Jun 2014 12:27:08 +0000 Subject: futex: Make lookup_pi_state more robust The current implementation of lookup_pi_state has ambigous handling of the TID value 0 in the user space futex. We can get into the kernel even if the TID value is 0, because either there is a stale waiters bit or the owner died bit is set or we are called from the requeue_pi path or from user space just for fun. The current code avoids an explicit sanity check for pid = 0 in case that kernel internal state (waiters) are found for the user space address. This can lead to state leakage and worse under some circumstances. Handle the cases explicit: 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. Signed-off-by: Thomas Gleixner Cc: Kees Cook Cc: Will Drewry Cc: Darren Hart Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- kernel/futex.c | 134 +++++++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 106 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index e1cb1baa23fb..de938d20df19 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -743,10 +743,58 @@ void exit_pi_state_list(struct task_struct *curr) 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, - struct task_struct *task) + union futex_key *key, struct futex_pi_state **ps) { struct futex_pi_state *pi_state = NULL; struct futex_q *this, *next; @@ -756,12 +804,13 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, plist_for_each_entry_safe(this, next, &hb->chain, 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; @@ -769,44 +818,70 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, 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; } /* - * Protect against a corrupted uval. If uval - * is 0x80000000 then pid is 0 and the waiter - * bit is set. So the deadlock check in the - * calling code has failed and we did not fall - * into the check above due to !pid. + * 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 (task && pi_state->owner == task) - return -EDEADLK; + 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; @@ -839,6 +914,9 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return ret; } + /* + * No existing pi state. First waiter. [2] + */ pi_state = alloc_pi_state(); /* @@ -959,7 +1037,7 @@ retry: * We dont have the lock. Look up the PI state (or create it if * we are the first waiter): */ - ret = lookup_pi_state(uval, hb, key, ps, task); + ret = lookup_pi_state(uval, hb, key, ps); if (unlikely(ret)) { switch (ret) { @@ -1565,7 +1643,7 @@ retry_private: * rereading and handing potential crap to * lookup_pi_state. */ - ret = lookup_pi_state(ret, hb2, &key2, &pi_state, NULL); + ret = lookup_pi_state(ret, hb2, &key2, &pi_state); } switch (ret) { -- cgit v1.2.3-58-ga151