[PATCH openEuler-1.0-LTS 1/7] futex: Ensure the correct return value from futex_lock_pi()
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit 72f38fffa4758b878f819f8a47761b3f03443f36 CVE: CVE-2021-3347
--------------------------------
commit 12bb3f7f1b03d5913b3f9d4236a488aa7774dfe9 upstream
In case that futex_lock_pi() was aborted by a signal or a timeout and the task returned without acquiring the rtmutex, but is the designated owner of the futex due to a concurrent futex_unlock_pi() fixup_owner() is invoked to establish consistent state. In that case it invokes fixup_pi_state_owner() which in turn tries to acquire the rtmutex again. If that succeeds then it does not propagate this success to fixup_owner() and futex_lock_pi() returns -EINTR or -ETIMEOUT despite having the futex locked.
Return success from fixup_pi_state_owner() in all cases where the current task owns the rtmutex and therefore the futex and propagate it correctly through fixup_owner(). Fixup the other callsite which does not expect a positive return value.
Fixes: c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex") Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index 28b321e23053..ca9389bd110f 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2414,8 +2414,8 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, }
if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { - /* We got the lock after all, nothing to fix. */ - ret = 0; + /* We got the lock. pi_state is correct. Tell caller. */ + ret = 1; goto out_unlock; }
@@ -2431,7 +2431,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; + ret = 1; goto out_unlock; } newowner = argowner; @@ -2477,7 +2477,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, raw_spin_unlock(&newowner->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
- return 0; + return argowner == current;
/* * In order to reschedule or handle a page fault, we need to drop the @@ -2519,7 +2519,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * Check if someone else fixed it for us: */ if (pi_state->owner != oldowner) { - ret = 0; + ret = argowner == current; goto out_unlock; }
@@ -2552,8 +2552,6 @@ static long futex_wait_restart(struct restart_block *restart); */ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) { - int ret = 0; - if (locked) { /* * Got the lock. We might not be the anticipated owner if we @@ -2564,8 +2562,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) - ret = fixup_pi_state_owner(uaddr, q, current); - goto out; + return fixup_pi_state_owner(uaddr, q, current); + return 1; }
/* @@ -2576,10 +2574,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Another speculative read; pi_state->owner == current is unstable * but needs our attention. */ - if (q->pi_state->owner == current) { - ret = fixup_pi_state_owner(uaddr, q, NULL); - goto out; - } + if (q->pi_state->owner == current) + return fixup_pi_state_owner(uaddr, q, NULL);
/* * Paranoia check. If we did not take the lock, then we should not be @@ -2592,8 +2588,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) q->pi_state->owner); }
-out: - return ret ? ret : locked; + return 0; }
/** @@ -3315,7 +3310,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { + if (ret < 0 && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { pi_state = q.pi_state; get_pi_state(pi_state); } @@ -3325,6 +3320,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ put_pi_state(q.pi_state); spin_unlock(q.lock_ptr); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. + */ + ret = ret < 0 ? ret : 0; } } else { struct rt_mutex *pi_mutex;
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit f03b21494da1ebf4ecfcb34ab647f35dc7fb7d92 CVE: CVE-2021-3347
--------------------------------
commit 04b79c55201f02ffd675e1231d731365e335c307 upstream
If that unexpected case of inconsistent arguments ever happens then the futex state is left completely inconsistent and the printk is not really helpful. Replace it with a warning and make the state consistent.
Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index ca9389bd110f..8be1feef5b7a 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2579,14 +2579,10 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
/* * Paranoia check. If we did not take the lock, then we should not be - * the owner of the rt_mutex. + * the owner of the rt_mutex. Warn and establish consistent state. */ - if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) { - printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p " - "pi-state %p\n", ret, - q->pi_state->pi_mutex.owner, - q->pi_state->owner); - } + if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current)) + return fixup_pi_state_owner(uaddr, q, current);
return 0; }
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit 0e1501f7b1eea94991e60cc51fadb3838bb2c7cb CVE: CVE-2021-3347
--------------------------------
commit c5cade200ab9a2a3be9e7f32a752c8d86b502ec7 upstream
Updating pi_state::owner is done at several places with the same code. Provide a function for it and use that at the obvious places.
This is also a preparation for a bug fix to avoid yet another copy of the same code or alternatively introducing a completely unpenetratable mess of gotos.
Originally-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 66 +++++++++++++++++++++++++------------------------- 1 file changed, 33 insertions(+), 33 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index 8be1feef5b7a..98c3bf3636f8 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -838,6 +838,29 @@ static struct futex_pi_state *alloc_pi_state(void) return pi_state; }
+static void pi_state_update_owner(struct futex_pi_state *pi_state, + struct task_struct *new_owner) +{ + struct task_struct *old_owner = pi_state->owner; + + lockdep_assert_held(&pi_state->pi_mutex.wait_lock); + + if (old_owner) { + raw_spin_lock(&old_owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock(&old_owner->pi_lock); + } + + if (new_owner) { + raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + } +} + static void get_pi_state(struct futex_pi_state *pi_state) { WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount)); @@ -1539,26 +1562,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ ret = -EINVAL; }
- if (ret) - goto out_unlock; - - /* - * This is a point of no return; once we modify the uval there is no - * going back and subsequent operations must not fail. - */ - - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - - raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; - raw_spin_unlock(&new_owner->pi_lock); - - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + if (!ret) { + /* + * This is a point of no return; once we modified the uval + * there is no going back and subsequent operations must + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + }
out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); @@ -2462,19 +2474,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * We fixed up user space. Now we need to fix the pi_state * itself. */ - if (pi_state->owner != NULL) { - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - } - - pi_state->owner = newowner; - - raw_spin_lock(&newowner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &newowner->pi_state_list); - raw_spin_unlock(&newowner->pi_lock); + pi_state_update_owner(pi_state, newowner); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
return argowner == current;
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit 29013e4f4b73e2f5ef39a443b05c231ac29c690f CVE: CVE-2021-3347
--------------------------------
commit 2156ac1934166d6deb6cd0f6ffc4c1076ec63697 upstream
Nothing uses the argument. Remove it as preparation to use pi_state_update_owner().
Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 2 +- kernel/locking/rtmutex.c | 3 +-- kernel/locking/rtmutex_common.h | 3 +-- 3 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index 98c3bf3636f8..edd6023e91b6 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -892,7 +892,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) list_del_init(&pi_state->list); raw_spin_unlock(&owner->pi_lock); } - rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + rt_mutex_proxy_unlock(&pi_state->pi_mutex); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); }
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 9562aaa2afdc..a5ec4f68527e 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1719,8 +1719,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, * possible because it belongs to the pi_state which is about to be freed * and it is not longer visible to other tasks. */ -void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner) +void rt_mutex_proxy_unlock(struct rt_mutex *lock) { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index d1d62f942be2..ca6fb489007b 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -133,8 +133,7 @@ enum rtmutex_chainwalk { extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); -extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner); +extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter,
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit 9d5dbf57d66f410d35da822a115dfd57531950dc CVE: CVE-2021-3347
--------------------------------
commit 6ccc84f917d33312eb2846bd7b567639f585ad6d upstream
No point in open coding it. This way it gains the extra sanity checks.
Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index edd6023e91b6..ac252985af06 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -883,15 +883,9 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - struct task_struct *owner;
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); - owner = pi_state->owner; - if (owner) { - raw_spin_lock(&owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock(&owner->pi_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); }
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit a4649185a98eb7adbdbdfdbf61237d518861e877 CVE: CVE-2021-3347
--------------------------------
commit f2dac39d93987f7de1e20b3988c8685523247ae2 upstream
Too many gotos already and an upcoming fix would make it even more unreadable.
Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 53 +++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 27 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index ac252985af06..fc8d3f059b5e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2370,18 +2370,13 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); }
-static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *argowner) +static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) { + u32 uval, uninitialized_var(curval), newval, newtid; struct futex_pi_state *pi_state = q->pi_state; - u32 uval, uninitialized_var(curval), newval; struct task_struct *oldowner, *newowner; - u32 newtid; - int ret, err = 0; - - lockdep_assert_held(q->lock_ptr); - - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + int err = 0;
oldowner = pi_state->owner;
@@ -2415,14 +2410,12 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 0; }
if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { /* We got the lock. pi_state is correct. Tell caller. */ - ret = 1; - goto out_unlock; + return 1; }
/* @@ -2437,8 +2430,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 1; - goto out_unlock; + return 1; } newowner = argowner; } @@ -2469,7 +2461,6 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * itself. */ pi_state_update_owner(pi_state, newowner); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
return argowner == current;
@@ -2492,17 +2483,16 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
switch (err) { case -EFAULT: - ret = fault_in_user_writeable(uaddr); + err = fault_in_user_writeable(uaddr); break;
case -EAGAIN: cond_resched(); - ret = 0; + err = 0; break;
default: WARN_ON_ONCE(1); - ret = err; break; }
@@ -2512,17 +2502,26 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, /* * Check if someone else fixed it for us: */ - if (pi_state->owner != oldowner) { - ret = argowner == current; - goto out_unlock; - } + if (pi_state->owner != oldowner) + return argowner == current;
- if (ret) - goto out_unlock; + /* Retry if err was -EAGAIN or the fault in succeeded */ + if (!err) + goto retry;
- goto retry; + return err; +}
-out_unlock: +static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) +{ + struct futex_pi_state *pi_state = q->pi_state; + int ret; + + lockdep_assert_held(q->lock_ptr); + + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + ret = __fixup_pi_state_owner(uaddr, q, argowner); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; }
From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.172 commit 6e7bfa046de83596c2a50f72e8ced1ee327db654 CVE: CVE-2021-3347
--------------------------------
commit 34b1a1ce1458f50ef27c54e28eb9b1947012907a upstream
fixup_pi_state_owner() tries to ensure that the state of the rtmutex, pi_state and the user space value related to the PI futex are consistent before returning to user space. In case that the user space value update faults and the fault cannot be resolved by faulting the page in via fault_in_user_writeable() the function returns with -EFAULT and leaves the rtmutex and pi_state owner state inconsistent.
A subsequent futex_unlock_pi() operates on the inconsistent pi_state and releases the rtmutex despite not owning it which can corrupt the RB tree of the rtmutex and cause a subsequent kernel stack use after free.
It was suggested to loop forever in fixup_pi_state_owner() if the fault cannot be resolved, but that results in runaway tasks which is especially undesired when the problem happens due to a programming error and not due to malice.
As the user space value cannot be fixed up, the proper solution is to make the rtmutex and the pi_state consistent so both have the same owner. This leaves the user space value out of sync. Any subsequent operation on the futex will fail because the 10th rule of PI futexes (pi_state owner and user space value are consistent) has been violated.
As a consequence this removes the inept attempts of 'fixing' the situation in case that the current task owns the rtmutex when returning with an unresolvable fault by unlocking the rtmutex which left pi_state::owner and rtmutex::owner out of sync in a different and only slightly less dangerous way.
Fixes: 1b7558e457ed ("futexes: fix fault handling in futex_lock_pi") Reported-by: gzobqq@gmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/futex.c | 56 ++++++++++++++++++-------------------------------- 1 file changed, 20 insertions(+), 36 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c index fc8d3f059b5e..a1ac8fc68991 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1031,7 +1031,8 @@ void exit_pi_state_list(struct task_struct *curr) * FUTEX_OWNER_DIED bit. See [4] * * [10] There is no transient state which leaves owner and user space - * TID out of sync. + * TID out of sync. Except one error case where the kernel is denied + * write access to the user address, see fixup_pi_state_owner(). * * * Serialization and lifetime rules: @@ -2509,6 +2510,24 @@ static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, if (!err) goto retry;
+ /* + * fault_in_user_writeable() failed so user state is immutable. At + * best we can make the kernel state consistent but user state will + * be most likely hosed and any subsequent unlock operation will be + * rejected due to PI futex rule [10]. + * + * Ensure that the rtmutex owner is also the pi_state owner despite + * the user space value claiming something different. There is no + * point in unlocking the rtmutex if current is the owner as it + * would need to wait until the next waiter has taken the rtmutex + * to guarantee consistent state. Keep it simple. Userspace asked + * for this wreckaged state. + * + * The rtmutex has an owner - either current or some other + * task. See the EAGAIN loop above. + */ + pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex)); + return err; }
@@ -2798,7 +2817,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to = NULL; - struct futex_pi_state *pi_state = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; struct futex_q q = futex_q_init; @@ -2932,23 +2950,9 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0;
- /* - * If fixup_owner() faulted and was unable to handle the fault, unlock - * it and return the fault to userspace. - */ - if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock */ unqueue_me_pi(&q);
- if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - goto out_put_key;
out_unlock_put_key: @@ -3214,7 +3218,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 __user *uaddr2) { struct hrtimer_sleeper timeout, *to = NULL; - struct futex_pi_state *pi_state = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; @@ -3299,10 +3302,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - if (ret < 0 && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. @@ -3344,25 +3343,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, 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(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock. */ unqueue_me_pi(&q); }
- if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling
-
Yang Yingliang