X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ffutex.c;h=e7a35f1039e785464b318d3713557e9d2db6a591;hb=a49c65037146bfb2fe300b8277b10b4479fea5fc;hp=fcc94e7b40864afcb72170f19d832f8117e517fc;hpb=9f96cb1e8bca179a92afa40dfc3c49990f1cfc71;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/futex.c b/kernel/futex.c index fcc94e7..e7a35f1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -19,6 +19,10 @@ * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet * + * Requeue-PI support by Darren Hart + * Copyright (C) IBM Corporation, 2009 + * Thanks to Thomas Gleixner for conceptual design and careful reviews. + * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. @@ -52,10 +56,16 @@ #include #include #include +#include +#include +#include + #include #include "rtmutex_common.h" +int __read_mostly futex_cmpxchg_enabled; + #define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8) /* @@ -79,36 +89,43 @@ struct futex_pi_state { union futex_key key; }; -/* - * We use this hashed waitqueue instead of a normal wait_queue_t, so +/** + * struct futex_q - The hashed futex queue entry, one per waiting task + * @task: the task waiting on the futex + * @lock_ptr: the hash bucket lock + * @key: the key the futex is hashed on + * @pi_state: optional priority inheritance state + * @rt_waiter: rt_waiter storage for use with requeue_pi + * @requeue_pi_key: the requeue_pi target futex key + * @bitset: bitset for the optional bitmasked wakeup + * + * We use this hashed waitqueue, instead of a normal wait_queue_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakup is always to make the first condition true, then - * wake up q->waiters, then make the second condition true. + * the second. + * + * PI futexes are typically woken before they are removed from the hash list via + * the rt_mutex code. See unqueue_me_pi(). */ struct futex_q { struct plist_node list; - wait_queue_head_t waiters; - /* Which hash list lock to use: */ + struct task_struct *task; spinlock_t *lock_ptr; - - /* Key which the futex is hashed on: */ union futex_key key; - - /* For fd, sigio sent using these: */ - int fd; - struct file *filp; - - /* Optional priority inheritance state: */ struct futex_pi_state *pi_state; - struct task_struct *task; + struct rt_mutex_waiter *rt_waiter; + union futex_key *requeue_pi_key; + u32 bitset; }; /* - * Split the global futex_lock into every hash list lock. + * Hash buckets are shared by all the futex_keys that hash to the same + * location. Each key may have multiple futex_q structures, one for each task + * waiting on a futex. */ struct futex_hash_bucket { spinlock_t lock; @@ -117,27 +134,6 @@ struct futex_hash_bucket { static struct futex_hash_bucket futex_queues[1<mmap_sem, when futex is shared - */ -static inline void futex_lock_mm(struct rw_semaphore *fshared) -{ - if (fshared) - down_read(fshared); -} - -/* - * Release mm->mmap_sem, when the futex is shared - */ -static inline void futex_unlock_mm(struct rw_semaphore *fshared) -{ - if (fshared) - up_read(fshared); -} - /* * We hash on the keys returned from get_futex_key (see below). */ @@ -154,17 +150,59 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key) */ static inline int match_futex(union futex_key *key1, union futex_key *key2) { - return (key1->both.word == key2->both.word + return (key1 && key2 + && key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset); } +/* + * Take a reference to the resource addressed by a key. + * Can be called while holding spinlocks. + * + */ +static void get_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) + return; + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + atomic_inc(&key->shared.inode->i_count); + break; + case FUT_OFF_MMSHARED: + atomic_inc(&key->private.mm->mm_count); + break; + } +} + +/* + * Drop a reference to the resource addressed by a key. + * The hash bucket spinlock must not be held. + */ +static void drop_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) { + /* If we're here then we tried to put a key we failed to get */ + WARN_ON_ONCE(1); + return; + } + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + iput(key->shared.inode); + break; + case FUT_OFF_MMSHARED: + mmdrop(key->private.mm); + break; + } +} + /** - * get_futex_key - Get parameters which are the keys for a futex. - * @uaddr: virtual address of the futex - * @shared: NULL for a PROCESS_PRIVATE futex, - * ¤t->mm->mmap_sem for a PROCESS_SHARED futex - * @key: address where result is stored. + * get_futex_key() - Get parameters which are the keys for a futex + * @uaddr: virtual address of the futex + * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED + * @key: address where result is stored. * * Returns a negative error code or 0 * The key words are stored in *key on success. @@ -173,16 +211,13 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2) * offset_within_page). For private mappings, it's (uaddr, current->mm). * We can usually work out the index without swapping in the page. * - * fshared is NULL for PROCESS_PRIVATE futexes - * For other futexes, it points to ¤t->mm->mmap_sem and - * caller must have taken the reader lock. but NOT any spinlocks. + * lock_page() might sleep, the caller should not hold a spinlock. */ -int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, - union futex_key *key) +static int +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; struct page *page; int err; @@ -206,104 +241,96 @@ int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, return -EFAULT; key->private.mm = mm; key->private.address = address; + get_futex_key_refs(key); return 0; } - /* - * The futex is hashed differently depending on whether - * it's in a shared or private mapping. So check vma first. - */ - vma = find_extend_vma(mm, address); - if (unlikely(!vma)) - return -EFAULT; - /* - * Permissions. - */ - if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) - return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; +again: + err = get_user_pages_fast(address, 1, 1, &page); + if (err < 0) + return err; + + page = compound_head(page); + lock_page(page); + if (!page->mapping) { + unlock_page(page); + put_page(page); + goto again; + } /* * Private mappings are handled in a simple way. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to - * the object not the particular process. Therefore we use - * VM_MAYSHARE here, not VM_SHARED which is restricted to shared - * mappings of _writable_ handles. + * the object not the particular process. */ - if (likely(!(vma->vm_flags & VM_MAYSHARE))) { - key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */ + if (PageAnon(page)) { + key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; - return 0; + } else { + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ + key->shared.inode = page->mapping->host; + key->shared.pgoff = page->index; } - /* - * Linear file mappings are also simple. - */ - key->shared.inode = vma->vm_file->f_path.dentry->d_inode; - key->both.offset |= FUT_OFF_INODE; /* inode-based key. */ - if (likely(!(vma->vm_flags & VM_NONLINEAR))) { - key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT) - + vma->vm_pgoff); - return 0; - } + get_futex_key_refs(key); - /* - * We could walk the page table to read the non-linear - * pte, and get the page index without fetching the page - * from swap. But that's a lot of code to duplicate here - * for a rare case, so we simply fetch the page. - */ - err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL); - if (err >= 0) { - key->shared.pgoff = - page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - put_page(page); - return 0; - } - return err; + unlock_page(page); + put_page(page); + return 0; } -EXPORT_SYMBOL_GPL(get_futex_key); -/* - * Take a reference to the resource addressed by a key. - * Can be called while holding spinlocks. +static inline +void put_futex_key(int fshared, union futex_key *key) +{ + drop_futex_key_refs(key); +} + +/** + * fault_in_user_writeable() - Fault in user address and verify RW access + * @uaddr: pointer to faulting user space address + * + * Slow path to fixup the fault we just took in the atomic write + * access to @uaddr. * + * We have no generic implementation of a non destructive write to the + * user address. We know that we faulted in the atomic pagefault + * disabled section so we can as well avoid the #PF overhead by + * calling get_user_pages() right away. */ -inline void get_futex_key_refs(union futex_key *key) +static int fault_in_user_writeable(u32 __user *uaddr) { - if (key->both.ptr == 0) - return; - switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { - case FUT_OFF_INODE: - atomic_inc(&key->shared.inode->i_count); - break; - case FUT_OFF_MMSHARED: - atomic_inc(&key->private.mm->mm_count); - break; - } + struct mm_struct *mm = current->mm; + int ret; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, (unsigned long)uaddr, + 1, 1, 0, NULL, NULL); + up_read(&mm->mmap_sem); + + return ret < 0 ? ret : 0; } -EXPORT_SYMBOL_GPL(get_futex_key_refs); -/* - * Drop a reference to the resource addressed by a key. - * The hash bucket spinlock must not be held. +/** + * futex_top_waiter() - Return the highest priority waiter on a futex + * @hb: the hash bucket the futex_q's reside in + * @key: the futex key (to distinguish it from other futex futex_q's) + * + * Must be called with the hb lock held. */ -void drop_futex_key_refs(union futex_key *key) +static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, + union futex_key *key) { - if (key->both.ptr == 0) - return; - switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { - case FUT_OFF_INODE: - iput(key->shared.inode); - break; - case FUT_OFF_MMSHARED: - mmdrop(key->private.mm); - break; + struct futex_q *this; + + plist_for_each_entry(this, &hb->chain, list) { + if (match_futex(&this->key, key)) + return this; } + return NULL; } -EXPORT_SYMBOL_GPL(drop_futex_key_refs); static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval) { @@ -327,45 +354,6 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from) return ret ? -EFAULT : 0; } -/* - * Fault handling. - * if fshared is non NULL, current->mm->mmap_sem is already held - */ -static int futex_handle_fault(unsigned long address, - struct rw_semaphore *fshared, int attempt) -{ - struct vm_area_struct * vma; - struct mm_struct *mm = current->mm; - int ret = -EFAULT; - - if (attempt > 2) - return ret; - - if (!fshared) - down_read(&mm->mmap_sem); - vma = find_vma(mm, address); - if (vma && address >= vma->vm_start && - (vma->vm_flags & VM_WRITE)) { - int fault; - fault = handle_mm_fault(mm, vma, address, 1); - if (unlikely((fault & VM_FAULT_ERROR))) { -#if 0 - /* XXX: let's do this when we verify it is OK */ - if (ret & VM_FAULT_OOM) - ret = -ENOMEM; -#endif - } else { - ret = 0; - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; - } - } - if (!fshared) - up_read(&mm->mmap_sem); - return ret; -} /* * PI code: @@ -386,6 +374,7 @@ static int refill_pi_state_cache(void) /* pi_mutex gets initialized later */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); + pi_state->key = FUTEX_KEY_INIT; current->pi_state_cache = pi_state; @@ -412,9 +401,9 @@ static void free_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - spin_lock_irq(&pi_state->owner->pi_lock); + raw_spin_lock_irq(&pi_state->owner->pi_lock); list_del_init(&pi_state->list); - spin_unlock_irq(&pi_state->owner->pi_lock); + raw_spin_unlock_irq(&pi_state->owner->pi_lock); rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); } @@ -440,14 +429,20 @@ static void free_pi_state(struct futex_pi_state *pi_state) static struct task_struct * futex_find_get_task(pid_t pid) { struct task_struct *p; + const struct cred *cred = current_cred(), *pcred; rcu_read_lock(); - p = find_task_by_pid(pid); - - if (!p || ((current->euid != p->euid) && (current->euid != p->uid))) + p = find_task_by_vpid(pid); + if (!p) { p = ERR_PTR(-ESRCH); - else - get_task_struct(p); + } else { + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid) + p = ERR_PTR(-ESRCH); + else + get_task_struct(p); + } rcu_read_unlock(); @@ -464,25 +459,27 @@ void exit_pi_state_list(struct task_struct *curr) struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; + if (!futex_cmpxchg_enabled) + return; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ - spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = hash_futex(&key); - spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: @@ -496,15 +493,15 @@ 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; - spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock_irq(&curr->pi_lock); rt_mutex_unlock(&pi_state->pi_mutex); spin_unlock(&hb->lock); - spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&curr->pi_lock); } - spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock_irq(&curr->pi_lock); } static int @@ -533,8 +530,25 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return -EINVAL; WARN_ON(!atomic_read(&pi_state->refcount)); - WARN_ON(pid && pi_state->owner && - pi_state->owner->pid != pid); + + /* + * 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. + */ + if (pid && pi_state->owner) { + /* + * Bail out if user space manipulated the + * futex value. + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; + } atomic_inc(&pi_state->refcount); *ps = pi_state; @@ -559,7 +573,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, * change of the task flags, we do this protected by * p->pi_lock: */ - spin_lock_irq(&p->pi_lock); + raw_spin_lock_irq(&p->pi_lock); if (unlikely(p->flags & PF_EXITING)) { /* * The task is on the way out. When PF_EXITPIDONE is @@ -568,7 +582,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, */ int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN; - spin_unlock_irq(&p->pi_lock); + raw_spin_unlock_irq(&p->pi_lock); put_task_struct(p); return ret; } @@ -587,7 +601,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); pi_state->owner = p; - spin_unlock_irq(&p->pi_lock); + raw_spin_unlock_irq(&p->pi_lock); put_task_struct(p); @@ -596,31 +610,160 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return 0; } +/** + * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex + * @uaddr: the pi futex user address + * @hb: the pi futex hash bucket + * @key: the futex key associated with uaddr and hb + * @ps: the pi_state pointer where we store the result of the + * lookup + * @task: the task to perform the atomic lock work for. This will + * be "current" except in the case of requeue pi. + * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) + * + * Returns: + * 0 - ready to wait + * 1 - acquired the lock + * <0 - error + * + * The hb->lock and futex_key refs shall be held by the caller. + */ +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) +{ + int lock_taken, ret, ownerdied = 0; + u32 uval, newval, curval; + +retry: + ret = lock_taken = 0; + + /* + * To avoid races, we attempt to take the lock here again + * (by doing a 0 -> TID atomic cmpxchg), while holding all + * the locks. It will most likely not succeed. + */ + newval = task_pid_vnr(task); + if (set_waiters) + newval |= FUTEX_WAITERS; + + curval = cmpxchg_futex_value_locked(uaddr, 0, newval); + + if (unlikely(curval == -EFAULT)) + return -EFAULT; + + /* + * Detect deadlocks. + */ + if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task)))) + return -EDEADLK; + + /* + * Surprise - we got the lock. Just return to userspace: + */ + if (unlikely(!curval)) + return 1; + + uval = curval; + + /* + * Set the FUTEX_WAITERS flag, so the owner will know it has someone + * to wake at the next unlock. + */ + 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 ! + */ + if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) { + /* Keep the OWNER_DIED bit */ + newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task); + ownerdied = 0; + lock_taken = 1; + } + + curval = cmpxchg_futex_value_locked(uaddr, uval, newval); + + if (unlikely(curval == -EFAULT)) + return -EFAULT; + if (unlikely(curval != uval)) + goto retry; + + /* + * We took the lock due to owner died take over. + */ + if (unlikely(lock_taken)) + return 1; + + /* + * 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); + + if (unlikely(ret)) { + 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. + */ + 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 (curval & FUTEX_OWNER_DIED) { + ownerdied = 1; + goto retry; + } + default: + break; + } + } + + return ret; +} + /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. */ static void wake_futex(struct futex_q *q) { - plist_del(&q->list, &q->list.plist); - if (q->filp) - send_sigio(&q->filp->f_owner, q->fd, POLL_IN); + struct task_struct *p = q->task; + /* - * The lock in wake_up_all() is a crucial memory barrier after the - * plist_del() and also before assigning to q->lock_ptr. + * 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 + * might exit and p would dereference a non existing task + * struct. Prevent this by holding a reference on p across the + * wake up. */ - wake_up_all(&q->waiters); + get_task_struct(p); + + plist_del(&q->list, &q->list.plist); /* - * The waiting task can free the futex_q as soon as this is written, - * without taking any locks. This must come last. - * - * A memory barrier is required here to prevent the following store - * to lock_ptr from getting ahead of the wakeup. Clearing the lock - * at the end of wake_up_all() does not prevent this store from - * moving. + * The waiting task can free the futex_q as soon as + * q->lock_ptr = NULL is written, without taking any locks. A + * memory barrier is required here to prevent the following + * store to lock_ptr from getting ahead of the plist_del. */ smp_wmb(); q->lock_ptr = NULL; + + wake_up_state(p, TASK_NORMAL); + put_task_struct(p); } static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) @@ -632,7 +775,14 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) if (!pi_state) return -EINVAL; - spin_lock(&pi_state->pi_mutex.wait_lock); + /* + * If current does not own the pi_state then the futex is + * inconsistent and user space fiddled with the futex value. + */ + if (pi_state->owner != current) + return -EINVAL; + + raw_spin_lock(&pi_state->pi_mutex.wait_lock); new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); /* @@ -652,32 +802,32 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) if (!(uval & FUTEX_OWNER_DIED)) { int ret = 0; - newval = FUTEX_WAITERS | new_owner->pid; + newval = FUTEX_WAITERS | task_pid_vnr(new_owner); curval = cmpxchg_futex_value_locked(uaddr, uval, newval); if (curval == -EFAULT) ret = -EFAULT; - if (curval != uval) + else if (curval != uval) ret = -EINVAL; if (ret) { - spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); return ret; } } - spin_lock_irq(&pi_state->owner->pi_lock); + raw_spin_lock_irq(&pi_state->owner->pi_lock); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); - spin_unlock_irq(&pi_state->owner->pi_lock); + raw_spin_unlock_irq(&pi_state->owner->pi_lock); - spin_lock_irq(&new_owner->pi_lock); + raw_spin_lock_irq(&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; - spin_unlock_irq(&new_owner->pi_lock); + raw_spin_unlock_irq(&new_owner->pi_lock); - spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); rt_mutex_unlock(&pi_state->pi_mutex); return 0; @@ -717,20 +867,27 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) } } +static inline void +double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) +{ + spin_unlock(&hb1->lock); + if (hb1 != hb2) + spin_unlock(&hb2->lock); +} + /* - * Wake up all waiters hashed on the physical page that is mapped - * to this virtual address: + * Wake up waiters matching bitset queued on this futex (uaddr). */ -static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, - int nr_wake) +static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; struct plist_head *head; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; int ret; - futex_lock_mm(fshared); + if (!bitset) + return -EINVAL; ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) @@ -742,10 +899,15 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, plist_for_each_entry_safe(this, next, head, list) { if (match_futex (&this->key, &key)) { - if (this->pi_state) { + if (this->pi_state || this->rt_waiter) { ret = -EINVAL; break; } + + /* Check if one of the bits is set in both bitsets */ + if (!(this->bitset & bitset)) + continue; + wake_futex(this); if (++ret >= nr_wake) break; @@ -753,8 +915,8 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, } spin_unlock(&hb->lock); + put_futex_key(fshared, &key); out: - futex_unlock_mm(fshared); return ret; } @@ -763,39 +925,32 @@ out: * to this virtual address: */ static int -futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared, - u32 __user *uaddr2, +futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { - union futex_key key1, key2; + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct plist_head *head; struct futex_q *this, *next; - int ret, op_ret, attempt = 0; - -retryfull: - futex_lock_mm(fshared); + int ret, op_ret; +retry: ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) - goto out; + goto out_put_key1; hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); -retry: +retry_private: double_lock_hb(hb1, hb2); - op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { - u32 dummy; - spin_unlock(&hb1->lock); - if (hb1 != hb2) - spin_unlock(&hb2->lock); + double_unlock_hb(hb1, hb2); #ifndef CONFIG_MMU /* @@ -803,40 +958,24 @@ retry: * but we might get them from range checking */ ret = op_ret; - goto out; + goto out_put_keys; #endif if (unlikely(op_ret != -EFAULT)) { ret = op_ret; - goto out; + goto out_put_keys; } - /* - * futex_atomic_op_inuser needs to both read and write - * *(int __user *)uaddr2, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - */ - if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr2, - fshared, attempt); - if (ret) - goto out; - goto retry; - } + ret = fault_in_user_writeable(uaddr2); + if (ret) + goto out_put_keys; - /* - * If we would have faulted, release mmap_sem, - * fault it in and start all over again. - */ - futex_unlock_mm(fshared); + if (!fshared) + goto retry_private; - ret = get_user(dummy, uaddr2); - if (ret) - return ret; - - goto retryfull; + put_futex_key(fshared, &key2); + put_futex_key(fshared, &key1); + goto retry; } head = &hb1->chain; @@ -863,42 +1002,212 @@ retry: ret += op_ret; } - spin_unlock(&hb1->lock); - if (hb1 != hb2) - spin_unlock(&hb2->lock); + double_unlock_hb(hb1, hb2); +out_put_keys: + put_futex_key(fshared, &key2); +out_put_key1: + put_futex_key(fshared, &key1); out: - futex_unlock_mm(fshared); + return ret; +} + +/** + * requeue_futex() - Requeue a futex_q from one hb to another + * @q: the futex_q to requeue + * @hb1: the source hash_bucket + * @hb2: the target hash_bucket + * @key2: the new key for the requeued futex_q + */ +static inline +void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, + struct futex_hash_bucket *hb2, union futex_key *key2) +{ + + /* + * If key1 and key2 hash to the same bucket, no need to + * requeue. + */ + if (likely(&hb1->chain != &hb2->chain)) { + plist_del(&q->list, &hb1->chain); + plist_add(&q->list, &hb2->chain); + q->lock_ptr = &hb2->lock; +#ifdef CONFIG_DEBUG_PI_LIST + q->list.plist.spinlock = &hb2->lock; +#endif + } + get_futex_key_refs(key2); + q->key = *key2; +} + +/** + * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue + * @q: the futex_q + * @key: the key of the requeue target futex + * @hb: the hash_bucket of the requeue target futex + * + * During futex_requeue, with requeue_pi=1, it is possible to acquire the + * target futex if it is uncontended or via a lock steal. Set the futex_q key + * to the requeue target futex so the waiter can detect the wakeup on the right + * futex, but remove it from the hb and NULL the rt_waiter so it can detect + * atomic lock acquisition. Set the q->lock_ptr to the requeue target hb->lock + * to protect access to the pi_state to fixup the owner later. Must be called + * with both q->lock_ptr and hb->lock held. + */ +static inline +void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, + struct futex_hash_bucket *hb) +{ + get_futex_key_refs(key); + q->key = *key; + + WARN_ON(plist_node_empty(&q->list)); + plist_del(&q->list, &q->list.plist); + + WARN_ON(!q->rt_waiter); + q->rt_waiter = NULL; + + q->lock_ptr = &hb->lock; +#ifdef CONFIG_DEBUG_PI_LIST + q->list.plist.spinlock = &hb->lock; +#endif + + wake_up_state(q->task, TASK_NORMAL); +} + +/** + * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter + * @pifutex: the user address of the to futex + * @hb1: the from futex hash bucket, must be locked by the caller + * @hb2: the to futex hash bucket, must be locked by the caller + * @key1: the from futex key + * @key2: the to futex key + * @ps: address to store the pi_state pointer + * @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. + * Wake the top waiter if we succeed. If the caller specified set_waiters, + * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit. + * hb1 and hb2 must be held by the caller. + * + * Returns: + * 0 - failed to acquire the lock atomicly + * 1 - acquired the lock + * <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) +{ + struct futex_q *top_waiter = NULL; + u32 curval; + int ret; + + if (get_futex_value_locked(&curval, pifutex)) + return -EFAULT; + + /* + * Find the top_waiter and determine if there are additional waiters. + * If the caller intends to requeue more than 1 waiter to pifutex, + * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now, + * as we have means to handle the possible fault. If not, don't set + * the bit unecessarily as it will force the subsequent unlock to enter + * the kernel. + */ + top_waiter = futex_top_waiter(hb1, key1); + + /* There are no waiters, nothing for us to do. */ + if (!top_waiter) + return 0; + + /* Ensure we requeue to the expected futex. */ + if (!match_futex(top_waiter->requeue_pi_key, key2)) + return -EINVAL; + + /* + * Try to take the lock for top_waiter. Set the FUTEX_WAITERS bit in + * the contended case or if set_waiters is 1. The pi_state is returned + * in ps in contended cases. + */ + ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, + set_waiters); + if (ret == 1) + requeue_pi_wake_futex(top_waiter, key2, hb2); return ret; } -/* - * Requeue all waiters hashed on one physical page to another - * physical page. +/** + * futex_requeue() - Requeue waiters from uaddr1 to uaddr2 + * uaddr1: source futex user address + * uaddr2: target futex user address + * nr_wake: number of waiters to wake (must be 1 for requeue_pi) + * nr_requeue: number of waiters to requeue (0-INT_MAX) + * requeue_pi: if we are attempting to requeue from a non-pi futex to a + * pi futex (pi to pi requeue is not supported) + * + * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire + * uaddr2 atomically on behalf of the top waiter. + * + * Returns: + * >=0 - on success, the number of tasks requeued or woken + * <0 - on error */ -static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, - u32 __user *uaddr2, - int nr_wake, int nr_requeue, u32 *cmpval) +static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, + int nr_wake, int nr_requeue, u32 *cmpval, + int requeue_pi) { - union futex_key key1, key2; + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; + int drop_count = 0, task_count = 0, ret; + struct futex_pi_state *pi_state = NULL; struct futex_hash_bucket *hb1, *hb2; struct plist_head *head1; struct futex_q *this, *next; - int ret, drop_count = 0; + u32 curval2; - retry: - futex_lock_mm(fshared); + if (requeue_pi) { + /* + * requeue_pi requires a pi_state, try to allocate it now + * without any locks in case it fails. + */ + if (refill_pi_state_cache()) + return -ENOMEM; + /* + * requeue_pi must wake as many tasks as it can, up to nr_wake + * + nr_requeue, since it acquires the rt_mutex prior to + * returning to userspace, so as to not leave the rt_mutex with + * waiters and no owner. However, second and third wake-ups + * cannot be predicted as they involve race conditions with the + * first wake and a fault while looking up the pi_state. Both + * pthread_cond_signal() and pthread_cond_broadcast() should + * use nr_wake=1. + */ + if (nr_wake != 1) + return -EINVAL; + } + +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, fshared, &key1); if (unlikely(ret != 0)) goto out; ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) - goto out; + goto out_put_key1; hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); +retry_private: double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { @@ -907,22 +1216,18 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, ret = get_futex_value_locked(&curval, uaddr1); if (unlikely(ret)) { - spin_unlock(&hb1->lock); - if (hb1 != hb2) - spin_unlock(&hb2->lock); - - /* - * If we would have faulted, release mmap_sem, fault - * it in and start all over again. - */ - futex_unlock_mm(fshared); + double_unlock_hb(hb1, hb2); ret = get_user(curval, uaddr1); + if (ret) + goto out_put_keys; - if (!ret) - goto retry; + if (!fshared) + goto retry_private; - return ret; + put_futex_key(fshared, &key2); + put_futex_key(fshared, &key1); + goto retry; } if (curval != *cmpval) { ret = -EAGAIN; @@ -930,59 +1235,143 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, } } + if (requeue_pi && (task_count - nr_wake < nr_requeue)) { + /* + * Attempt to acquire uaddr2 and wake the top waiter. If we + * intend to requeue waiters, force setting the FUTEX_WAITERS + * bit. We force this here where we are able to easily handle + * faults rather in the requeue loop below. + */ + ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, + &key2, &pi_state, nr_requeue); + + /* + * 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. + */ + if (ret == 1) { + 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); + } + + switch (ret) { + case 0: + break; + case -EFAULT: + double_unlock_hb(hb1, hb2); + put_futex_key(fshared, &key2); + put_futex_key(fshared, &key1); + ret = fault_in_user_writeable(uaddr2); + if (!ret) + goto retry; + goto out; + case -EAGAIN: + /* The owner was exiting, try again. */ + double_unlock_hb(hb1, hb2); + put_futex_key(fshared, &key2); + put_futex_key(fshared, &key1); + cond_resched(); + goto retry; + default: + goto out_unlock; + } + } + head1 = &hb1->chain; plist_for_each_entry_safe(this, next, head1, list) { - if (!match_futex (&this->key, &key1)) + if (task_count - nr_wake >= nr_requeue) + break; + + if (!match_futex(&this->key, &key1)) continue; - if (++ret <= nr_wake) { + + /* + * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always + * be paired with each other and no other futex ops. + */ + if ((requeue_pi && !this->rt_waiter) || + (!requeue_pi && this->rt_waiter)) { + ret = -EINVAL; + break; + } + + /* + * Wake nr_wake waiters. For requeue_pi, if we acquired the + * lock, we already woke the top_waiter. If not, it will be + * woken by futex_unlock_pi(). + */ + if (++task_count <= nr_wake && !requeue_pi) { wake_futex(this); - } else { - /* - * If key1 and key2 hash to the same bucket, no need to - * requeue. - */ - if (likely(head1 != &hb2->chain)) { - plist_del(&this->list, &hb1->chain); - plist_add(&this->list, &hb2->chain); - this->lock_ptr = &hb2->lock; -#ifdef CONFIG_DEBUG_PI_LIST - this->list.plist.lock = &hb2->lock; -#endif - } - this->key = key2; - get_futex_key_refs(&key2); - drop_count++; + continue; + } - if (ret - nr_wake >= nr_requeue) - break; + /* Ensure we requeue to the expected futex for requeue_pi. */ + if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) { + ret = -EINVAL; + break; } + + /* + * Requeue nr_requeue waiters and possibly one more in the case + * of requeue_pi if we couldn't acquire the lock atomically. + */ + if (requeue_pi) { + /* Prepare the waiter to take the rt_mutex. */ + atomic_inc(&pi_state->refcount); + this->pi_state = pi_state; + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, + this->rt_waiter, + this->task, 1); + if (ret == 1) { + /* We got the lock. */ + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; + } else if (ret) { + /* -EDEADLK */ + this->pi_state = NULL; + free_pi_state(pi_state); + goto out_unlock; + } + } + requeue_futex(this, hb1, hb2, &key2); + drop_count++; } out_unlock: - spin_unlock(&hb1->lock); - if (hb1 != hb2) - spin_unlock(&hb2->lock); + double_unlock_hb(hb1, hb2); - /* drop_futex_key_refs() must be called outside the spinlocks. */ + /* + * drop_futex_key_refs() must be called outside the spinlocks. During + * the requeue we moved futex_q's from the hash bucket at key1 to the + * one at key2 and updated their key pointer. We no longer need to + * hold the references to key1. + */ while (--drop_count >= 0) drop_futex_key_refs(&key1); +out_put_keys: + put_futex_key(fshared, &key2); +out_put_key1: + put_futex_key(fshared, &key1); out: - futex_unlock_mm(fshared); - return ret; + if (pi_state != NULL) + free_pi_state(pi_state); + return ret ? ret : task_count; } /* The key must be already stored in q->key. */ -static inline struct futex_hash_bucket * -queue_lock(struct futex_q *q, int fd, struct file *filp) +static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) { struct futex_hash_bucket *hb; - q->fd = fd; - q->filp = filp; - - init_waitqueue_head(&q->waiters); - get_futex_key_refs(&q->key); hb = hash_futex(&q->key); q->lock_ptr = &hb->lock; @@ -991,7 +1380,26 @@ queue_lock(struct futex_q *q, int fd, struct file *filp) return hb; } -static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb) +static inline void +queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb) +{ + spin_unlock(&hb->lock); + drop_futex_key_refs(&q->key); +} + +/** + * queue_me() - Enqueue the futex_q on the futex_hash_bucket + * @q: The futex_q to enqueue + * @hb: The destination hash bucket + * + * The hb->lock must be held by the caller, and is released here. A call to + * queue_me() is typically paired with exactly one call to unqueue_me(). The + * exceptions involve the PI related operations, which may use unqueue_me_pi() + * or nothing if the unqueue is done as part of the wake process and the unqueue + * state is implicit in the state of woken task (see futex_wait_requeue_pi() for + * an example). + */ +static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; @@ -1007,45 +1415,34 @@ static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb) plist_node_init(&q->list, prio); #ifdef CONFIG_DEBUG_PI_LIST - q->list.plist.lock = &hb->lock; + q->list.plist.spinlock = &hb->lock; #endif plist_add(&q->list, &hb->chain); q->task = current; spin_unlock(&hb->lock); } -static inline void -queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb) -{ - spin_unlock(&hb->lock); - drop_futex_key_refs(&q->key); -} - -/* - * queue_me and unqueue_me must be called as a pair, each - * exactly once. They are called with the hashed spinlock held. +/** + * unqueue_me() - Remove the futex_q from its futex_hash_bucket + * @q: The futex_q to unqueue + * + * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must + * be paired with exactly one earlier call to queue_me(). + * + * Returns: + * 1 - if the futex_q was still queued (and we removed unqueued it) + * 0 - if the futex_q was already removed by the waking thread */ - -/* The key must be already stored in q->key. */ -static void queue_me(struct futex_q *q, int fd, struct file *filp) -{ - struct futex_hash_bucket *hb; - - hb = queue_lock(q, fd, filp); - __queue_me(q, hb); -} - -/* Return 1 if we were still queued (ie. 0 means we were woken) */ static int unqueue_me(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ - retry: +retry: lock_ptr = q->lock_ptr; barrier(); - if (lock_ptr != 0) { + if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and @@ -1097,88 +1494,254 @@ static void unqueue_me_pi(struct futex_q *q) } /* - * Fixup the pi_state owner with current. + * Fixup the pi_state owner with the new owner. * * Must be called with hash bucket lock held and mm->sem held for non * private futexes. */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *curr) + struct task_struct *newowner, int fshared) { - u32 newtid = curr->pid | FUTEX_WAITERS; + u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; + struct task_struct *oldowner = pi_state->owner; u32 uval, curval, newval; int ret; /* Owner died? */ - if (pi_state->owner != NULL) { - spin_lock_irq(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - spin_unlock_irq(&pi_state->owner->pi_lock); - } else + if (!pi_state->owner) newtid |= FUTEX_OWNER_DIED; - pi_state->owner = curr; - - spin_lock_irq(&curr->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &curr->pi_state_list); - spin_unlock_irq(&curr->pi_lock); - /* - * We own it, so we have to replace the pending owner - * TID. This must be atomic as we have preserve the - * owner died bit here. + * We are here either because we stole the rtmutex from the + * pending owner or we are the pending owner which failed to + * get the rtmutex. We have to replace the pending owner TID + * in the user space variable. This must be atomic as we have + * to preserve the owner died bit here. + * + * Note: We write the user space value _before_ changing the pi_state + * because we can fault here. Imagine swapped out pages or a fork + * that marked all the anonymous memory readonly for cow. + * + * Modifying pi_state _before_ the user space value would + * leave the pi_state in an inconsistent state when we fault + * here, because we need to drop the hash bucket lock to + * handle the fault. This might be observed in the PID check + * in lookup_pi_state. */ - ret = get_futex_value_locked(&uval, uaddr); +retry: + if (get_futex_value_locked(&uval, uaddr)) + goto handle_fault; - while (!ret) { + while (1) { newval = (uval & FUTEX_OWNER_DIED) | newtid; curval = cmpxchg_futex_value_locked(uaddr, uval, newval); if (curval == -EFAULT) - ret = -EFAULT; + goto handle_fault; if (curval == uval) break; uval = curval; } - return ret; + + /* + * We fixed up user space. Now we need to fix the pi_state + * itself. + */ + if (pi_state->owner != NULL) { + raw_spin_lock_irq(&pi_state->owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock_irq(&pi_state->owner->pi_lock); + } + + pi_state->owner = newowner; + + raw_spin_lock_irq(&newowner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &newowner->pi_state_list); + raw_spin_unlock_irq(&newowner->pi_lock); + return 0; + + /* + * To handle the page fault we need to drop the hash bucket + * lock here. That gives the other task (either the pending + * owner itself or the task which stole the rtmutex) the + * chance to try the fixup of the pi_state. So once we are + * back from handling the fault we need to check the pi_state + * after reacquiring the hash bucket lock and before trying to + * do another fixup. When the fixup has been done already we + * simply return. + */ +handle_fault: + spin_unlock(q->lock_ptr); + + ret = fault_in_user_writeable(uaddr); + + spin_lock(q->lock_ptr); + + /* + * Check if someone else fixed it for us: + */ + if (pi_state->owner != oldowner) + return 0; + + if (ret) + return ret; + + goto retry; } /* * In case we must use restart_block to restart a futex_wait, - * we encode in the 'arg3' shared capability + * we encode in the 'flags' shared capability */ -#define ARG3_SHARED 1 +#define FLAGS_SHARED 0x01 +#define FLAGS_CLOCKRT 0x02 +#define FLAGS_HAS_TIMEOUT 0x04 static long futex_wait_restart(struct restart_block *restart); -static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, - u32 val, ktime_t *abs_time) +/** + * fixup_owner() - Post lock pi_state and corner case management + * @uaddr: user address of the futex + * @fshared: whether the futex is shared (1) or not (0) + * @q: futex_q (contains pi_state and access to the rt_mutex) + * @locked: if the attempt to take the rt_mutex succeeded (1) or not (0) + * + * After attempting to lock an rt_mutex, this function is called to cleanup + * the pi_state owner as well as handle race conditions that may allow us to + * acquire the lock. Must be called with the hb lock held. + * + * Returns: + * 1 - success, lock taken + * 0 - success, lock not taken + * <0 - on error (-EFAULT) + */ +static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q, + int locked) { - struct task_struct *curr = current; - DECLARE_WAITQUEUE(wait, curr); - struct futex_hash_bucket *hb; - struct futex_q q; - u32 uval; - int ret; - struct hrtimer_sleeper t; - int rem = 0; + struct task_struct *owner; + int ret = 0; - q.pi_state = NULL; - retry: - futex_lock_mm(fshared); + if (locked) { + /* + * Got the lock. We might not be the anticipated owner if we + * did a lock-steal - fix up the PI-state in that case: + */ + if (q->pi_state->owner != current) + ret = fixup_pi_state_owner(uaddr, q, current, fshared); + goto out; + } - ret = get_futex_key(uaddr, fshared, &q.key); - if (unlikely(ret != 0)) - goto out_release_sem; + /* + * Catch the rare case, where the lock was released when we were on the + * way back before we locked the hash bucket. + */ + if (q->pi_state->owner == current) { + /* + * Try to get the rt_mutex now. This might fail as some other + * task acquired the rt_mutex after we removed ourself from the + * rt_mutex waiters list. + */ + if (rt_mutex_trylock(&q->pi_state->pi_mutex)) { + locked = 1; + goto out; + } + + /* + * pi_state is incorrect, some other task did a lock steal and + * we returned due to timeout or signal without taking the + * rt_mutex. Too late. We can access the rt_mutex_owner without + * locking, as the other task is now blocked on the hash bucket + * lock. Fix the state up. + */ + owner = rt_mutex_owner(&q->pi_state->pi_mutex); + ret = fixup_pi_state_owner(uaddr, q, owner, fshared); + goto out; + } + + /* + * Paranoia check. If we did not take the lock, then we should not be + * the owner, nor the pending owner, of the rt_mutex. + */ + 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); + +out: + return ret ? ret : locked; +} + +/** + * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal + * @hb: the futex hash bucket, must be locked by the caller + * @q: the futex_q to queue up on + * @timeout: the prepared hrtimer_sleeper, or null for no timeout + */ +static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, + struct hrtimer_sleeper *timeout) +{ + /* + * The task state is guaranteed to be set before another task can + * wake it. set_current_state() is implemented using set_mb() and + * queue_me() calls spin_unlock() upon completion, both serializing + * access to the hash list and forcing another memory barrier. + */ + set_current_state(TASK_INTERRUPTIBLE); + queue_me(q, hb); + + /* Arm the timer */ + if (timeout) { + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + if (!hrtimer_active(&timeout->timer)) + timeout->task = NULL; + } + + /* + * If we have been removed from the hash list, then another task + * has tried to wake us, and we can skip the call to schedule(). + */ + if (likely(!plist_node_empty(&q->list))) { + /* + * If the timer has already expired, current will already be + * flagged for rescheduling. Only call schedule if there + * is no timeout, or if it has yet to expire. + */ + if (!timeout || timeout->task) + schedule(); + } + __set_current_state(TASK_RUNNING); +} - hb = queue_lock(&q, -1, NULL); +/** + * futex_wait_setup() - Prepare to wait on a futex + * @uaddr: the futex userspace address + * @val: the expected value + * @fshared: whether the futex is shared (1) or not (0) + * @q: the associated futex_q + * @hb: storage for hash_bucket pointer to be returned to caller + * + * Setup the futex_q and locate the hash_bucket. Get the futex value and + * compare it with the expected value. Handle atomic faults internally. + * Return with the hb lock held and a q.key reference on success, and unlocked + * with no q.key reference on failure. + * + * Returns: + * 0 - uaddr contains val and hb has been locked + * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked + */ +static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared, + struct futex_q *q, struct futex_hash_bucket **hb) +{ + u32 uval; + int ret; /* - * Access the page AFTER the futex is queued. + * Access the page AFTER the hash-bucket is locked. * Order is important: * * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); @@ -1193,132 +1756,142 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, * A consequence is that futex_wait() can return zero and absorb * a wakeup when *uaddr != val on entry to the syscall. This is * rare, but normal. - * - * for shared futexes, we hold the mmap semaphore, so the mapping - * cannot have changed since we looked it up in get_futex_key. */ - ret = get_futex_value_locked(&uval, uaddr); +retry: + q->key = FUTEX_KEY_INIT; + ret = get_futex_key(uaddr, fshared, &q->key); + if (unlikely(ret != 0)) + return ret; - if (unlikely(ret)) { - queue_unlock(&q, hb); +retry_private: + *hb = queue_lock(q); - /* - * If we would have faulted, release mmap_sem, fault it in and - * start all over again. - */ - futex_unlock_mm(fshared); + ret = get_futex_value_locked(&uval, uaddr); - ret = get_user(uval, uaddr); + if (ret) { + queue_unlock(q, *hb); - if (!ret) - goto retry; - return ret; - } - ret = -EWOULDBLOCK; - if (uval != val) - goto out_unlock_release_sem; + ret = get_user(uval, uaddr); + if (ret) + goto out; - /* Only actually queue if *uaddr contained val. */ - __queue_me(&q, hb); + if (!fshared) + goto retry_private; - /* - * Now the futex is queued and we have checked the data, we - * don't want to hold mmap_sem while we sleep. - */ - futex_unlock_mm(fshared); + put_futex_key(fshared, &q->key); + goto retry; + } - /* - * There might have been scheduling since the queue_me(), as we - * cannot hold a spinlock across the get_user() in case it - * faults, and we cannot just set TASK_INTERRUPTIBLE state when - * queueing ourselves into the futex hash. This code thus has to - * rely on the futex_wake() code removing us from hash when it - * wakes us up. - */ + if (uval != val) { + queue_unlock(q, *hb); + ret = -EWOULDBLOCK; + } - /* add_wait_queue is the barrier after __set_current_state. */ - __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&q.waiters, &wait); - /* - * !plist_node_empty() is safe here without any lock. - * q.lock_ptr != 0 is not safe, because of ordering against wakeup. - */ - if (likely(!plist_node_empty(&q.list))) { - if (!abs_time) - schedule(); - else { - hrtimer_init(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - hrtimer_init_sleeper(&t, current); - t.timer.expires = *abs_time; +out: + if (ret) + put_futex_key(fshared, &q->key); + return ret; +} - hrtimer_start(&t.timer, t.timer.expires, HRTIMER_MODE_ABS); +static int futex_wait(u32 __user *uaddr, int fshared, + u32 val, ktime_t *abs_time, u32 bitset, int clockrt) +{ + struct hrtimer_sleeper timeout, *to = NULL; + struct restart_block *restart; + struct futex_hash_bucket *hb; + struct futex_q q; + int ret; - /* - * the timer could have already expired, in which - * case current would be flagged for rescheduling. - * Don't bother calling schedule. - */ - if (likely(t.task)) - schedule(); + if (!bitset) + return -EINVAL; - hrtimer_cancel(&t.timer); + q.pi_state = NULL; + q.bitset = bitset; + q.rt_waiter = NULL; + q.requeue_pi_key = NULL; - /* Flag if a timeout occured */ - rem = (t.task == NULL); - } + if (abs_time) { + to = &timeout; + + hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME : + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init_sleeper(to, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); } - __set_current_state(TASK_RUNNING); - /* - * NOTE: we don't remove ourselves from the waitqueue because - * we are the only user of it. - */ +retry: + /* Prepare to wait on uaddr. */ + ret = futex_wait_setup(uaddr, val, fshared, &q, &hb); + if (ret) + goto out; + + /* queue_me and wait for wakeup, timeout, or a signal. */ + futex_wait_queue_me(hb, &q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ + ret = 0; if (!unqueue_me(&q)) - return 0; - if (rem) - return -ETIMEDOUT; + goto out_put_key; + ret = -ETIMEDOUT; + if (to && !to->task) + goto out_put_key; /* - * We expect signal_pending(current), but another thread may - * have handled it for us already. + * We expect signal_pending(current), but we might be the + * victim of a spurious wakeup as well. */ - if (!abs_time) - return -ERESTARTSYS; - else { - struct restart_block *restart; - restart = ¤t_thread_info()->restart_block; - restart->fn = futex_wait_restart; - restart->arg0 = (unsigned long)uaddr; - restart->arg1 = (unsigned long)val; - restart->arg2 = (unsigned long)abs_time; - restart->arg3 = 0; - if (fshared) - restart->arg3 |= ARG3_SHARED; - return -ERESTART_RESTARTBLOCK; + if (!signal_pending(current)) { + put_futex_key(fshared, &q.key); + goto retry; } - out_unlock_release_sem: - queue_unlock(&q, hb); + ret = -ERESTARTSYS; + if (!abs_time) + goto out_put_key; + + restart = ¤t_thread_info()->restart_block; + restart->fn = futex_wait_restart; + restart->futex.uaddr = (u32 *)uaddr; + restart->futex.val = val; + restart->futex.time = abs_time->tv64; + restart->futex.bitset = bitset; + restart->futex.flags = FLAGS_HAS_TIMEOUT; + + if (fshared) + restart->futex.flags |= FLAGS_SHARED; + if (clockrt) + restart->futex.flags |= FLAGS_CLOCKRT; + + ret = -ERESTART_RESTARTBLOCK; - out_release_sem: - futex_unlock_mm(fshared); +out_put_key: + put_futex_key(fshared, &q.key); +out: + if (to) { + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); + } return ret; } static long futex_wait_restart(struct restart_block *restart) { - u32 __user *uaddr = (u32 __user *)restart->arg0; - u32 val = (u32)restart->arg1; - ktime_t *abs_time = (ktime_t *)restart->arg2; - struct rw_semaphore *fshared = NULL; + u32 __user *uaddr = (u32 __user *)restart->futex.uaddr; + int fshared = 0; + ktime_t t, *tp = NULL; + if (restart->futex.flags & FLAGS_HAS_TIMEOUT) { + t.tv64 = restart->futex.time; + tp = &t; + } restart->fn = do_no_restart_syscall; - if (restart->arg3 & ARG3_SHARED) - fshared = ¤t->mm->mmap_sem; - return (long)futex_wait(uaddr, fshared, val, abs_time); + if (restart->futex.flags & FLAGS_SHARED) + fshared = 1; + return (long)futex_wait(uaddr, fshared, restart->futex.val, tp, + restart->futex.bitset, + restart->futex.flags & FLAGS_CLOCKRT); } @@ -1328,155 +1901,64 @@ static long futex_wait_restart(struct restart_block *restart) * if there are waiters then it will block, it does PI, etc. (Due to * races the kernel might see a 0 value of the futex too.) */ -static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, +static int futex_lock_pi(u32 __user *uaddr, int fshared, int detect, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to = NULL; - struct task_struct *curr = current; struct futex_hash_bucket *hb; - u32 uval, newval, curval; struct futex_q q; - int ret, lock_taken, ownerdied = 0, attempt = 0; + int res, ret; if (refill_pi_state_cache()) return -ENOMEM; if (time) { to = &timeout; - hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); + hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, + HRTIMER_MODE_ABS); hrtimer_init_sleeper(to, current); - to->timer.expires = *time; + hrtimer_set_expires(&to->timer, *time); } q.pi_state = NULL; - retry: - futex_lock_mm(fshared); - + q.rt_waiter = NULL; + q.requeue_pi_key = NULL; +retry: + q.key = FUTEX_KEY_INIT; ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) - goto out_release_sem; - - retry_unlocked: - hb = queue_lock(&q, -1, NULL); - - retry_locked: - ret = lock_taken = 0; - - /* - * To avoid races, we attempt to take the lock here again - * (by doing a 0 -> TID atomic cmpxchg), while holding all - * the locks. It will most likely not succeed. - */ - newval = current->pid; - - curval = cmpxchg_futex_value_locked(uaddr, 0, newval); - - if (unlikely(curval == -EFAULT)) - goto uaddr_faulted; - - /* - * Detect deadlocks. In case of REQUEUE_PI this is a valid - * situation and we return success to user space. - */ - if (unlikely((curval & FUTEX_TID_MASK) == current->pid)) { - ret = -EDEADLK; - goto out_unlock_release_sem; - } - - /* - * Surprise - we got the lock. Just return to userspace: - */ - if (unlikely(!curval)) - goto out_unlock_release_sem; - - uval = curval; - - /* - * Set the WAITERS flag, so the owner will know it has someone - * to wake at next unlock - */ - 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 ! - */ - if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) { - /* Keep the OWNER_DIED bit */ - newval = (curval & ~FUTEX_TID_MASK) | current->pid; - ownerdied = 0; - lock_taken = 1; - } - - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); - - if (unlikely(curval == -EFAULT)) - goto uaddr_faulted; - if (unlikely(curval != uval)) - goto retry_locked; - - /* - * We took the lock due to owner died take over. - */ - if (unlikely(lock_taken)) - goto out_unlock_release_sem; + goto out; - /* - * 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, &q.key, &q.pi_state); +retry_private: + hb = queue_lock(&q); + ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0); if (unlikely(ret)) { switch (ret) { - + case 1: + /* We got the lock. */ + ret = 0; + goto out_unlock_put_key; + case -EFAULT: + goto uaddr_faulted; case -EAGAIN: /* * Task is exiting and we just wait for the * exit to complete. */ queue_unlock(&q, hb); - futex_unlock_mm(fshared); + put_futex_key(fshared, &q.key); cond_resched(); goto retry; - - 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. - */ - if (get_futex_value_locked(&curval, uaddr)) - goto uaddr_faulted; - - /* - * We simply start over in case of a robust - * futex. The code above will take the futex - * and return happy. - */ - if (curval & FUTEX_OWNER_DIED) { - ownerdied = 1; - goto retry_locked; - } default: - goto out_unlock_release_sem; + goto out_unlock_put_key; } } /* * Only actually queue now that the atomic ops are done: */ - __queue_me(&q, hb); - - /* - * Now the futex is queued and we have checked the data, we - * don't want to hold mmap_sem while we sleep. - */ - futex_unlock_mm(fshared); + queue_me(&q, hb); WARN_ON(!q.pi_state); /* @@ -1490,80 +1972,53 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, ret = ret ? 0 : -EWOULDBLOCK; } - futex_lock_mm(fshared); spin_lock(q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. + */ + res = fixup_owner(uaddr, fshared, &q, !ret); + /* + * If fixup_owner() returned an error, proprogate that. If it acquired + * the lock, clear our -ETIMEDOUT or -EINTR. + */ + if (res) + ret = (res < 0) ? res : 0; - if (!ret) { - /* - * Got the lock. We might not be the anticipated owner - * if we did a lock-steal - fix up the PI-state in - * that case: - */ - if (q.pi_state->owner != curr) - ret = fixup_pi_state_owner(uaddr, &q, curr); - } else { - /* - * Catch the rare case, where the lock was released - * when we were on the way back before we locked the - * hash bucket. - */ - if (q.pi_state->owner == curr && - rt_mutex_trylock(&q.pi_state->pi_mutex)) { - ret = 0; - } else { - /* - * Paranoia check. If we did not take the lock - * in the trylock above, then we should not be - * the owner of the rtmutex, neither the real - * nor the pending one: - */ - if (rt_mutex_owner(&q.pi_state->pi_mutex) == curr) - printk(KERN_ERR "futex_lock_pi: ret = %d " - "pi-mutex: %p pi-state %p\n", ret, - q.pi_state->pi_mutex.owner, - q.pi_state->owner); - } - } + /* + * 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)) + rt_mutex_unlock(&q.pi_state->pi_mutex); /* Unqueue and drop the lock */ unqueue_me_pi(&q); - futex_unlock_mm(fshared); - return ret != -EINTR ? ret : -ERESTARTNOINTR; + goto out_put_key; - out_unlock_release_sem: +out_unlock_put_key: queue_unlock(&q, hb); - out_release_sem: - futex_unlock_mm(fshared); - return ret; +out_put_key: + put_futex_key(fshared, &q.key); +out: + if (to) + destroy_hrtimer_on_stack(&to->timer); + return ret != -EINTR ? ret : -ERESTARTNOINTR; - uaddr_faulted: - /* - * We have to r/w *(int __user *)uaddr, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - * - * ... and hb->lock. :-) --ANK - */ +uaddr_faulted: queue_unlock(&q, hb); - if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); - if (ret) - goto out_release_sem; - goto retry_unlocked; - } + ret = fault_in_user_writeable(uaddr); + if (ret) + goto out_put_key; - futex_unlock_mm(fshared); - - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) - goto retry; + if (!fshared) + goto retry_private; - return ret; + put_futex_key(fshared, &q.key); + goto retry; } /* @@ -1571,14 +2026,14 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * This is the in-kernel slowpath: we look up the PI state (if any), * and do the rt-mutex unlock. */ -static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared) +static int futex_unlock_pi(u32 __user *uaddr, int fshared) { struct futex_hash_bucket *hb; struct futex_q *this, *next; u32 uval; struct plist_head *head; - union futex_key key; - int ret, attempt = 0; + union futex_key key = FUTEX_KEY_INIT; + int ret; retry: if (get_user(uval, uaddr)) @@ -1586,19 +2041,14 @@ retry: /* * We release only a lock we actually own: */ - if ((uval & FUTEX_TID_MASK) != current->pid) + if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - /* - * First take all the futex related locks: - */ - futex_lock_mm(fshared); ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; hb = hash_futex(&key); -retry_unlocked: spin_lock(&hb->lock); /* @@ -1607,7 +2057,7 @@ retry_unlocked: * anyone else up: */ if (!(uval & FUTEX_OWNER_DIED)) - uval = cmpxchg_futex_value_locked(uaddr, current->pid, 0); + uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0); if (unlikely(uval == -EFAULT)) @@ -1616,7 +2066,7 @@ retry_unlocked: * Rare case: we managed to release the lock atomically, * no need to wake anyone else up: */ - if (unlikely(uval == current->pid)) + if (unlikely(uval == task_pid_vnr(current))) goto out_unlock; /* @@ -1649,153 +2099,242 @@ retry_unlocked: out_unlock: spin_unlock(&hb->lock); -out: - futex_unlock_mm(fshared); + put_futex_key(fshared, &key); +out: return ret; pi_faulted: - /* - * We have to r/w *(int __user *)uaddr, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - * - * ... and hb->lock. --ANK - */ spin_unlock(&hb->lock); + put_futex_key(fshared, &key); - if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); - if (ret) - goto out; - uval = 0; - goto retry_unlocked; - } - - futex_unlock_mm(fshared); - - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) + ret = fault_in_user_writeable(uaddr); + if (!ret) goto retry; return ret; } -static int futex_close(struct inode *inode, struct file *filp) -{ - struct futex_q *q = filp->private_data; - - unqueue_me(q); - kfree(q); - - return 0; -} - -/* This is one-shot: once it's gone off you need a new fd */ -static unsigned int futex_poll(struct file *filp, - struct poll_table_struct *wait) +/** + * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex + * @hb: the hash_bucket futex_q was original enqueued on + * @q: the futex_q woken while waiting to be requeued + * @key2: the futex_key of the requeue target futex + * @timeout: the timeout associated with the wait (NULL if none) + * + * Detect if the task was woken on the initial futex as opposed to the requeue + * target futex. If so, determine if it was a timeout or a signal that caused + * the wakeup and return the appropriate error code to the caller. Must be + * called with the hb lock held. + * + * Returns + * 0 - no early wakeup detected + * <0 - -ETIMEDOUT or -ERESTARTNOINTR + */ +static inline +int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, + struct futex_q *q, union futex_key *key2, + struct hrtimer_sleeper *timeout) { - struct futex_q *q = filp->private_data; int ret = 0; - poll_wait(filp, &q->waiters, wait); - /* - * plist_node_empty() is safe here without any lock. - * q->lock_ptr != 0 is not safe, because of ordering against wakeup. + * With the hb lock held, we avoid races while we process the wakeup. + * We only need to hold hb (and not hb2) to ensure atomicity as the + * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb. + * It can't be requeued from uaddr2 to something else since we don't + * support a PI aware source futex for requeue. */ - if (plist_node_empty(&q->list)) - ret = POLLIN | POLLRDNORM; + if (!match_futex(&q->key, key2)) { + WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr)); + /* + * We were woken prior to requeue by a timeout or a signal. + * Unqueue the futex_q and determine which it was. + */ + plist_del(&q->list, &q->list.plist); + /* Handle spurious wakeups gracefully */ + ret = -EWOULDBLOCK; + if (timeout && !timeout->task) + ret = -ETIMEDOUT; + else if (signal_pending(current)) + ret = -ERESTARTNOINTR; + } return ret; } -static const struct file_operations futex_fops = { - .release = futex_close, - .poll = futex_poll, -}; - -/* - * Signal allows caller to avoid the race which would occur if they - * set the sigio stuff up afterwards. +/** + * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2 + * @uaddr: the futex we initially wait on (non-pi) + * @fshared: whether the futexes are shared (1) or not (0). They must be + * the same type, no requeueing from private to shared, etc. + * @val: the expected value of uaddr + * @abs_time: absolute timeout + * @bitset: 32 bit wakeup bitset set by userspace, defaults to all + * @clockrt: whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0) + * @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. + * + * We call schedule in futex_wait_queue_me() when we enqueue and return there + * via the following: + * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue() + * 2) wakeup on uaddr2 after a requeue + * 3) signal + * 4) timeout + * + * If 3, cleanup and return -ERESTARTNOINTR. + * + * If 2, we may then block on trying to take the rt_mutex and return via: + * 5) successful lock + * 6) signal + * 7) timeout + * 8) other lock acquisition failure + * + * If 6, return -EWOULDBLOCK (restarting the syscall would do the same). + * + * If 4 or 7, we cleanup and return with -ETIMEDOUT. + * + * Returns: + * 0 - On success + * <0 - On error */ -static int futex_fd(u32 __user *uaddr, int signal) +static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared, + u32 val, ktime_t *abs_time, u32 bitset, + int clockrt, u32 __user *uaddr2) { - struct futex_q *q; - struct file *filp; - int ret, err; - struct rw_semaphore *fshared; - static unsigned long printk_interval; - - if (printk_timed_ratelimit(&printk_interval, 60 * 60 * 1000)) { - printk(KERN_WARNING "Process `%s' used FUTEX_FD, which " - "will be removed from the kernel in June 2007\n", - current->comm); + 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; + struct futex_q q; + int res, ret; + + if (!bitset) + return -EINVAL; + + if (abs_time) { + to = &timeout; + hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME : + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init_sleeper(to, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); } - ret = -EINVAL; - if (!valid_signal(signal)) - goto out; + /* + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ + debug_rt_mutex_init_waiter(&rt_waiter); + rt_waiter.task = NULL; - ret = get_unused_fd(); - if (ret < 0) - goto out; - filp = get_empty_filp(); - if (!filp) { - put_unused_fd(ret); - ret = -ENFILE; + key2 = FUTEX_KEY_INIT; + ret = get_futex_key(uaddr2, fshared, &key2); + if (unlikely(ret != 0)) goto out; - } - filp->f_op = &futex_fops; - filp->f_path.mnt = mntget(futex_mnt); - filp->f_path.dentry = dget(futex_mnt->mnt_root); - filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping; - - if (signal) { - err = __f_setown(filp, task_pid(current), PIDTYPE_PID, 1); - if (err < 0) { - goto error; - } - filp->f_owner.signum = signal; - } - q = kmalloc(sizeof(*q), GFP_KERNEL); - if (!q) { - err = -ENOMEM; - goto error; - } - q->pi_state = NULL; + q.pi_state = NULL; + q.bitset = bitset; + q.rt_waiter = &rt_waiter; + q.requeue_pi_key = &key2; + + /* Prepare to wait on uaddr. */ + ret = futex_wait_setup(uaddr, val, fshared, &q, &hb); + if (ret) + goto out_key2; + + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + + spin_lock(&hb->lock); + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); + spin_unlock(&hb->lock); + if (ret) + goto out_put_keys; + + /* + * In order for us to be here, we know our q.key == key2, and since + * we took the hb->lock above, we also know that futex_requeue() has + * completed and we no longer have to concern ourselves with a wakeup + * race with the atomic proxy lock acquition by the requeue code. + */ + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { + /* + * Got the lock. We might not be the anticipated owner if we + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { + spin_lock(q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current, + fshared); + spin_unlock(q.lock_ptr); + } + } else { + /* + * 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); + 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); - fshared = ¤t->mm->mmap_sem; - down_read(fshared); - err = get_futex_key(uaddr, fshared, &q->key); + spin_lock(q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. + */ + res = fixup_owner(uaddr2, fshared, &q, !ret); + /* + * If fixup_owner() returned an error, proprogate that. If it + * acquired the lock, clear -ETIMEDOUT or -EINTR. + */ + if (res) + ret = (res < 0) ? res : 0; - if (unlikely(err != 0)) { - up_read(fshared); - kfree(q); - goto error; + /* Unqueue and drop the lock. */ + unqueue_me_pi(&q); } /* - * queue_me() must be called before releasing mmap_sem, because - * key->shared.inode needs to be referenced while holding it. + * If fixup_pi_state_owner() faulted and was unable to handle the + * fault, unlock the rt_mutex and return the fault to userspace. */ - filp->private_data = q; + if (ret == -EFAULT) { + if (rt_mutex_owner(pi_mutex) == current) + rt_mutex_unlock(pi_mutex); + } else if (ret == -EINTR) { + /* + * We've already been requeued, but cannot restart by calling + * futex_lock_pi() directly. We could restart this syscall, but + * it would detect that the user space "val" changed and return + * -EWOULDBLOCK. Save the overhead of the restart and return + * -EWOULDBLOCK directly. + */ + ret = -EWOULDBLOCK; + } - queue_me(q, ret, filp); - up_read(fshared); +out_put_keys: + put_futex_key(fshared, &q.key); +out_key2: + put_futex_key(fshared, &key2); - /* Now we map fd to filp, so userspace can access it */ - fd_install(ret, filp); out: + if (to) { + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); + } return ret; -error: - put_unused_fd(ret); - put_filp(filp); - ret = err; - goto out; } /* @@ -1814,14 +2353,15 @@ error: */ /** - * sys_set_robust_list - set the robust-futex list head of a task - * @head: pointer to the list-head - * @len: length of the list-head, as userspace expects + * sys_set_robust_list() - Set the robust-futex list head of a task + * @head: pointer to the list-head + * @len: length of the list-head, as userspace expects */ -asmlinkage long -sys_set_robust_list(struct robust_list_head __user *head, - size_t len) +SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, + size_t, len) { + if (!futex_cmpxchg_enabled) + return -ENOSYS; /* * The kernel knows only one size for now: */ @@ -1834,17 +2374,21 @@ sys_set_robust_list(struct robust_list_head __user *head, } /** - * sys_get_robust_list - get the robust-futex list head of a task - * @pid: pid of the process [zero for current task] - * @head_ptr: pointer to a list-head pointer, the kernel fills it in - * @len_ptr: pointer to a length field, the kernel fills in the header size + * sys_get_robust_list() - Get the robust-futex list head of a task + * @pid: pid of the process [zero for current task] + * @head_ptr: pointer to a list-head pointer, the kernel fills it in + * @len_ptr: pointer to a length field, the kernel fills in the header size */ -asmlinkage long -sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, - size_t __user *len_ptr) +SYSCALL_DEFINE3(get_robust_list, int, pid, + struct robust_list_head __user * __user *, head_ptr, + size_t __user *, len_ptr) { struct robust_list_head __user *head; unsigned long ret; + const struct cred *cred = current_cred(), *pcred; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; if (!pid) head = current->robust_list; @@ -1853,12 +2397,14 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, ret = -ESRCH; rcu_read_lock(); - p = find_task_by_pid(pid); + p = find_task_by_vpid(pid); if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_PTRACE)) + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid && + !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); @@ -1886,7 +2432,7 @@ retry: if (get_user(uval, uaddr)) return -1; - if ((uval & FUTEX_TID_MASK) == curr->pid) { + if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) { /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically @@ -1911,7 +2457,7 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, &curr->mm->mmap_sem, 1); + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } @@ -1948,6 +2494,9 @@ void exit_robust_list(struct task_struct *curr) unsigned long futex_offset; int rc; + if (!futex_cmpxchg_enabled) + return; + /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): @@ -2002,41 +2551,58 @@ void exit_robust_list(struct task_struct *curr) long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { - int ret; + int clockrt, ret = -ENOSYS; int cmd = op & FUTEX_CMD_MASK; - struct rw_semaphore *fshared = NULL; + int fshared = 0; if (!(op & FUTEX_PRIVATE_FLAG)) - fshared = ¤t->mm->mmap_sem; + fshared = 1; + + clockrt = op & FUTEX_CLOCK_REALTIME; + if (clockrt && cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) + return -ENOSYS; switch (cmd) { case FUTEX_WAIT: - ret = futex_wait(uaddr, fshared, val, timeout); + val3 = FUTEX_BITSET_MATCH_ANY; + case FUTEX_WAIT_BITSET: + ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt); break; case FUTEX_WAKE: - ret = futex_wake(uaddr, fshared, val); - break; - case FUTEX_FD: - /* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */ - ret = futex_fd(uaddr, val); + val3 = FUTEX_BITSET_MATCH_ANY; + case FUTEX_WAKE_BITSET: + ret = futex_wake(uaddr, fshared, val, val3); break; case FUTEX_REQUEUE: - ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL); + ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL, 0); break; case FUTEX_CMP_REQUEUE: - ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3); + ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3, + 0); break; case FUTEX_WAKE_OP: ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3); break; case FUTEX_LOCK_PI: - ret = futex_lock_pi(uaddr, fshared, val, timeout, 0); + if (futex_cmpxchg_enabled) + ret = futex_lock_pi(uaddr, fshared, val, timeout, 0); break; case FUTEX_UNLOCK_PI: - ret = futex_unlock_pi(uaddr, fshared); + if (futex_cmpxchg_enabled) + ret = futex_unlock_pi(uaddr, fshared); break; case FUTEX_TRYLOCK_PI: - ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1); + if (futex_cmpxchg_enabled) + ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1); + break; + case FUTEX_WAIT_REQUEUE_PI: + val3 = FUTEX_BITSET_MATCH_ANY; + ret = futex_wait_requeue_pi(uaddr, fshared, val, timeout, val3, + clockrt, uaddr2); + break; + case FUTEX_CMP_REQUEUE_PI: + ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3, + 1); break; default: ret = -ENOSYS; @@ -2045,16 +2611,18 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, } -asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, - struct timespec __user *utime, u32 __user *uaddr2, - u32 val3) +SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + struct timespec __user *, utime, u32 __user *, uaddr2, + u32, val3) { struct timespec ts; ktime_t t, *tp = NULL; u32 val2 = 0; int cmd = op & FUTEX_CMD_MASK; - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) { + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { if (copy_from_user(&ts, utime, sizeof(ts)) != 0) return -EFAULT; if (!timespec_valid(&ts)) @@ -2062,50 +2630,44 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, t = timespec_to_ktime(ts); if (cmd == FUTEX_WAIT) - t = ktime_add(ktime_get(), t); + t = ktime_add_safe(ktime_get(), t); tp = &t; } /* - * requeue parameter in 'utime' if cmd == FUTEX_REQUEUE. + * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*. * number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP. */ if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || - cmd == FUTEX_WAKE_OP) + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) val2 = (u32) (unsigned long) utime; return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); } -static int futexfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) -{ - return get_sb_pseudo(fs_type, "futex", NULL, 0xBAD1DEA, mnt); -} - -static struct file_system_type futex_fs_type = { - .name = "futexfs", - .get_sb = futexfs_get_sb, - .kill_sb = kill_anon_super, -}; - -static int __init init(void) +static int __init futex_init(void) { - int i = register_filesystem(&futex_fs_type); - - if (i) - return i; + u32 curval; + int i; - futex_mnt = kern_mount(&futex_fs_type); - if (IS_ERR(futex_mnt)) { - unregister_filesystem(&futex_fs_type); - return PTR_ERR(futex_mnt); - } + /* + * This will fail and we want it. Some arch implementations do + * runtime detection of the futex_atomic_cmpxchg_inatomic() + * functionality. We want to know that before we call in any + * of the complex code paths. Also we want to prevent + * registration of robust lists in that case. NULL is + * guaranteed to fault and we get -EFAULT on functional + * implementation, the non functional ones will return + * -ENOSYS. + */ + curval = cmpxchg_futex_value_locked(NULL, 0, 0); + if (curval == -EFAULT) + futex_cmpxchg_enabled = 1; for (i = 0; i < ARRAY_SIZE(futex_queues); i++) { plist_head_init(&futex_queues[i].chain, &futex_queues[i].lock); spin_lock_init(&futex_queues[i].lock); } + return 0; } -__initcall(init); +__initcall(futex_init);