diff options
Diffstat (limited to 'kernel/futex.c')
| -rw-r--r-- | kernel/futex.c | 2857 |
1 files changed, 1870 insertions, 987 deletions
diff --git a/kernel/futex.c b/kernel/futex.c index e43945e995f..b632b5f3f09 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -19,6 +19,10 @@ * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * + * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> + * 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. @@ -51,18 +55,133 @@ #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/signal.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/magic.h> #include <linux/pid.h> #include <linux/nsproxy.h> +#include <linux/ptrace.h> +#include <linux/sched/rt.h> +#include <linux/hugetlb.h> +#include <linux/freezer.h> +#include <linux/bootmem.h> #include <asm/futex.h> -#include "rtmutex_common.h" +#include "locking/rtmutex_common.h" +/* + * READ this before attempting to hack on futexes! + * + * Basic futex operation and ordering guarantees + * ============================================= + * + * The waiter reads the futex value in user space and calls + * futex_wait(). This function computes the hash bucket and acquires + * the hash bucket lock. After that it reads the futex user space value + * again and verifies that the data has not changed. If it has not changed + * it enqueues itself into the hash bucket, releases the hash bucket lock + * and schedules. + * + * The waker side modifies the user space value of the futex and calls + * futex_wake(). This function computes the hash bucket and acquires the + * hash bucket lock. Then it looks for waiters on that futex in the hash + * bucket and wakes them. + * + * In futex wake up scenarios where no tasks are blocked on a futex, taking + * the hb spinlock can be avoided and simply return. In order for this + * optimization to work, ordering guarantees must exist so that the waiter + * being added to the list is acknowledged when the list is concurrently being + * checked by the waker, avoiding scenarios like the following: + * + * CPU 0 CPU 1 + * val = *futex; + * sys_futex(WAIT, futex, val); + * futex_wait(futex, val); + * uval = *futex; + * *futex = newval; + * sys_futex(WAKE, futex); + * futex_wake(futex); + * if (queue_empty()) + * return; + * if (uval == val) + * lock(hash_bucket(futex)); + * queue(); + * unlock(hash_bucket(futex)); + * schedule(); + * + * This would cause the waiter on CPU 0 to wait forever because it + * missed the transition of the user space value from val to newval + * and the waker did not find the waiter in the hash bucket queue. + * + * The correct serialization ensures that a waiter either observes + * the changed user space value before blocking or is woken by a + * concurrent waker: + * + * CPU 0 CPU 1 + * val = *futex; + * sys_futex(WAIT, futex, val); + * futex_wait(futex, val); + * + * waiters++; (a) + * mb(); (A) <-- paired with -. + * | + * lock(hash_bucket(futex)); | + * | + * uval = *futex; | + * | *futex = newval; + * | sys_futex(WAKE, futex); + * | futex_wake(futex); + * | + * `-------> mb(); (B) + * if (uval == val) + * queue(); + * unlock(hash_bucket(futex)); + * schedule(); if (waiters) + * lock(hash_bucket(futex)); + * else wake_waiters(futex); + * waiters--; (b) unlock(hash_bucket(futex)); + * + * Where (A) orders the waiters increment and the futex value read through + * atomic operations (see hb_waiters_inc) and where (B) orders the write + * to futex and the waiters read -- this is done by the barriers in + * get_futex_key_refs(), through either ihold or atomic_inc, depending on the + * futex type. + * + * This yields the following case (where X:=waiters, Y:=futex): + * + * X = Y = 0 + * + * w[X]=1 w[Y]=1 + * MB MB + * r[Y]=y r[X]=x + * + * Which guarantees that x==0 && y==0 is impossible; which translates back into + * the guarantee that we cannot both miss the futex variable change and the + * enqueue. + * + * Note that a new waiter is accounted for in (a) even when it is possible that + * the wait call can return error, in which case we backtrack from it in (b). + * Refer to the comment in queue_lock(). + * + * Similarly, in order to account for waiters being requeued on another + * address we always increment the waiters for the destination bucket before + * acquiring the lock. It then decrements them again after releasing it - + * the code that actually moves the futex(es) between hash buckets (requeue_futex) + * will do the additional required waiter count housekeeping. This is done for + * double_lock_hb() and double_unlock_hb(), respectively. + */ + +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG int __read_mostly futex_cmpxchg_enabled; +#endif -#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8) +/* + * Futex flags used to encode options to functions and preserve them across + * restarts. + */ +#define FLAGS_SHARED 0x01 +#define FLAGS_CLOCKRT 0x02 +#define FLAGS_HAS_TIMEOUT 0x04 /* * Priority Inheritance state: @@ -85,66 +204,104 @@ 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 + * @list: priority-sorted list of tasks waiting on this futex + * @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 order of wakeup is always to make the first condition true, then + * 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; - - /* Bitset for the optional bitmasked wakeup */ + struct rt_mutex_waiter *rt_waiter; + union futex_key *requeue_pi_key; u32 bitset; }; +static const struct futex_q futex_q_init = { + /* list gets initialized in queue_me()*/ + .key = FUTEX_KEY_INIT, + .bitset = FUTEX_BITSET_MATCH_ANY +}; + /* - * 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 { + atomic_t waiters; spinlock_t lock; struct plist_head chain; -}; +} ____cacheline_aligned_in_smp; -static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS]; +static unsigned long __read_mostly futex_hashsize; -/* Futex-fs vfsmount entry: */ -static struct vfsmount *futex_mnt; +static struct futex_hash_bucket *futex_queues; + +static inline void futex_get_mm(union futex_key *key) +{ + atomic_inc(&key->private.mm->mm_count); + /* + * Ensure futex_get_mm() implies a full barrier such that + * get_futex_key() implies a full barrier. This is relied upon + * as full barrier (B), see the ordering comment above. + */ + smp_mb__after_atomic(); +} /* - * Take mm->mmap_sem, when futex is shared + * Reflects a new waiter being added to the waitqueue. */ -static inline void futex_lock_mm(struct rw_semaphore *fshared) +static inline void hb_waiters_inc(struct futex_hash_bucket *hb) { - if (fshared) - down_read(fshared); +#ifdef CONFIG_SMP + atomic_inc(&hb->waiters); + /* + * Full barrier (A), see the ordering comment above. + */ + smp_mb__after_atomic(); +#endif } /* - * Release mm->mmap_sem, when the futex is shared + * Reflects a waiter being removed from the waitqueue by wakeup + * paths. */ -static inline void futex_unlock_mm(struct rw_semaphore *fshared) +static inline void hb_waiters_dec(struct futex_hash_bucket *hb) { - if (fshared) - up_read(fshared); +#ifdef CONFIG_SMP + atomic_dec(&hb->waiters); +#endif +} + +static inline int hb_waiters_pending(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + return atomic_read(&hb->waiters); +#else + return 1; +#endif } /* @@ -155,7 +312,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key) u32 hash = jhash2((u32*)&key->both.word, (sizeof(key->both.word)+sizeof(key->both.ptr))/4, key->both.offset); - return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)]; + return &futex_queues[hash & (futex_hashsize - 1)]; } /* @@ -163,37 +320,79 @@ 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: + ihold(key->shared.inode); /* implies MB (B) */ + break; + case FUT_OFF_MMSHARED: + futex_get_mm(key); /* implies MB (B) */ + 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. + * @rw: mapping needs to be read/write (values: VERIFY_READ, + * VERIFY_WRITE) + * + * Return: a negative error code or 0 * - * Returns a negative error code or 0 * The key words are stored in *key on success. * - * For shared mappings, it's (page->index, vma->vm_file->f_path.dentry->d_inode, + * For shared mappings, it's (page->index, file_inode(vma->vm_file), * 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. */ -static 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, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - struct page *page; - int err; + struct page *page, *page_head; + int err, ro = 0; /* * The futex address must be "naturally" aligned. @@ -203,6 +402,9 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, return -EINVAL; address -= key->both.offset; + if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) + return -EFAULT; + /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs @@ -211,115 +413,182 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, * but access_ok() should be faster than find_vma() */ if (!fshared) { - if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) - return -EFAULT; key->private.mm = mm; key->private.address = address; + get_futex_key_refs(key); /* implies MB (B) */ return 0; } + +again: + err = get_user_pages_fast(address, 1, 1, &page); /* - * The futex is hashed differently depending on whether - * it's in a shared or private mapping. So check vma first. + * If write access is not required (eg. FUTEX_WAIT), try + * and get read-only access. */ - vma = find_extend_vma(mm, address); - if (unlikely(!vma)) - return -EFAULT; + if (err == -EFAULT && rw == VERIFY_READ) { + err = get_user_pages_fast(address, 1, 0, &page); + ro = 1; + } + if (err < 0) + return err; + else + err = 0; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + page_head = page; + if (unlikely(PageTail(page))) { + put_page(page); + /* serialize against __split_huge_page_splitting() */ + local_irq_disable(); + if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) { + page_head = compound_head(page); + /* + * page_head is valid pointer but we must pin + * it before taking the PG_lock and/or + * PG_compound_lock. The moment we re-enable + * irqs __split_huge_page_splitting() can + * return and the head page can be freed from + * under us. We can't take the PG_lock and/or + * PG_compound_lock on a page that could be + * freed from under us. + */ + if (page != page_head) { + get_page(page_head); + put_page(page); + } + local_irq_enable(); + } else { + local_irq_enable(); + goto again; + } + } +#else + page_head = compound_head(page); + if (page != page_head) { + get_page(page_head); + put_page(page); + } +#endif + + lock_page(page_head); /* - * Permissions. + * If page_head->mapping is NULL, then it cannot be a PageAnon + * page; but it might be the ZERO_PAGE or in the gate area or + * in a special mapping (all cases which we are happy to fail); + * or it may have been a good file page when get_user_pages_fast + * found it, but truncated or holepunched or subjected to + * invalidate_complete_page2 before we got the page lock (also + * cases which we are happy to fail). And we hold a reference, + * so refcount care in invalidate_complete_page's remove_mapping + * prevents drop_caches from setting mapping to NULL beneath us. + * + * The case we do have to guard against is when memory pressure made + * shmem_writepage move it from filecache to swapcache beneath us: + * an unlikely race, but we do need to retry for page_head->mapping. */ - if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) - return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; + if (!page_head->mapping) { + int shmem_swizzled = PageSwapCache(page_head); + unlock_page(page_head); + put_page(page_head); + if (shmem_swizzled) + goto again; + return -EFAULT; + } /* * 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_head)) { + /* + * A RO anonymous page will never change and thus doesn't make + * sense for futex operations. + */ + if (ro) { + err = -EFAULT; + goto out; + } + + 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_head->mapping->host; + key->shared.pgoff = basepage_index(page); } - /* - * 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); /* implies MB (B) */ - /* - * 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; - } +out: + unlock_page(page_head); + put_page(page_head); return err; } -/* - * Take a reference to the resource addressed by a key. - * Can be called while holding spinlocks. +static inline void put_futex_key(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. */ -static void get_futex_key_refs(union futex_key *key) +static int fault_in_user_writeable(u32 __user *uaddr) { - if (key->both.ptr == NULL) - 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 = fixup_user_fault(current, mm, (unsigned long)uaddr, + FAULT_FLAG_WRITE); + up_read(&mm->mmap_sem); + + return ret < 0 ? ret : 0; } -/* - * 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. */ -static 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) - 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; } -static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval) +static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr, + u32 uval, u32 newval) { - u32 curval; + int ret; pagefault_disable(); - curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval); + ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); - return curval; + return ret; } static int get_futex_value_locked(u32 *dest, u32 __user *from) @@ -333,45 +602,6 @@ 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: @@ -392,6 +622,7 @@ 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; @@ -418,9 +649,9 @@ 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); } @@ -449,9 +680,7 @@ static struct task_struct * futex_find_get_task(pid_t pid) rcu_read_lock(); p = find_task_by_vpid(pid); - if (!p || ((current->euid != p->euid) && (current->euid != p->uid))) - p = ERR_PTR(-ESRCH); - else + if (p) get_task_struct(p); rcu_read_unlock(); @@ -469,7 +698,7 @@ 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; @@ -478,18 +707,18 @@ void exit_pi_state_list(struct task_struct *curr) * 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: @@ -503,62 +732,167 @@ 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); } +/* + * We need to check the following states: + * + * Waiter | pi_state | pi->owner | uTID | uODIED | ? + * + * [1] NULL | --- | --- | 0 | 0/1 | Valid + * [2] NULL | --- | --- | >0 | 0/1 | Valid + * + * [3] Found | NULL | -- | Any | 0/1 | Invalid + * + * [4] Found | Found | NULL | 0 | 1 | Valid + * [5] Found | Found | NULL | >0 | 1 | Invalid + * + * [6] Found | Found | task | 0 | 1 | Valid + * + * [7] Found | Found | NULL | Any | 0 | Invalid + * + * [8] Found | Found | task | ==taskTID | 0/1 | Valid + * [9] Found | Found | task | 0 | 0 | Invalid + * [10] Found | Found | task | !=taskTID | 0/1 | Invalid + * + * [1] Indicates that the kernel can acquire the futex atomically. We + * came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit. + * + * [2] Valid, if TID does not belong to a kernel thread. If no matching + * thread is found then it indicates that the owner TID has died. + * + * [3] Invalid. The waiter is queued on a non PI futex + * + * [4] Valid state after exit_robust_list(), which sets the user space + * value to FUTEX_WAITERS | FUTEX_OWNER_DIED. + * + * [5] The user space value got manipulated between exit_robust_list() + * and exit_pi_state_list() + * + * [6] Valid state after exit_pi_state_list() which sets the new owner in + * the pi_state but cannot access the user space value. + * + * [7] pi_state->owner can only be NULL when the OWNER_DIED bit is set. + * + * [8] Owner and user space value match + * + * [9] There is no transient state which sets the user space TID to 0 + * except exit_robust_list(), but this is indicated by the + * FUTEX_OWNER_DIED bit. See [4] + * + * [10] There is no transient state which leaves owner and user space + * TID out of sync. + */ static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps) { struct futex_pi_state *pi_state = NULL; struct futex_q *this, *next; - struct plist_head *head; struct task_struct *p; pid_t pid = uval & FUTEX_TID_MASK; - head = &hb->chain; - - plist_for_each_entry_safe(this, next, head, list) { + plist_for_each_entry_safe(this, next, &hb->chain, list) { if (match_futex(&this->key, key)) { /* - * Another waiter already exists - bump up - * the refcount and return its pi_state: + * Sanity check the waiter before increasing + * the refcount and attaching to it. */ pi_state = this->pi_state; /* - * Userspace might have messed up non PI and PI futexes + * Userspace might have messed up non-PI and + * PI futexes [3] */ if (unlikely(!pi_state)) return -EINVAL; WARN_ON(!atomic_read(&pi_state->refcount)); - WARN_ON(pid && pi_state->owner && - pi_state->owner->pid != pid); + /* + * Handle the owner died case: + */ + if (uval & FUTEX_OWNER_DIED) { + /* + * exit_pi_state_list sets owner to NULL and + * wakes the topmost waiter. The task which + * acquires the pi_state->rt_mutex will fixup + * owner. + */ + if (!pi_state->owner) { + /* + * No pi state owner, but the user + * space TID is not 0. Inconsistent + * state. [5] + */ + if (pid) + return -EINVAL; + /* + * Take a ref on the state and + * return. [4] + */ + goto out_state; + } + + /* + * If TID is 0, then either the dying owner + * has not yet executed exit_pi_state_list() + * or some waiter acquired the rtmutex in the + * pi state, but did not yet fixup the TID in + * user space. + * + * Take a ref on the state and return. [6] + */ + if (!pid) + goto out_state; + } else { + /* + * If the owner died bit is not set, + * then the pi_state must have an + * owner. [7] + */ + if (!pi_state->owner) + return -EINVAL; + } + + /* + * Bail out if user space manipulated the + * futex value. If pi state exists then the + * owner TID must be the same as the user + * space TID. [9/10] + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; + + out_state: atomic_inc(&pi_state->refcount); *ps = pi_state; - return 0; } } /* * We are the first waiter - try to look up the real owner and attach - * the new pi_state to it, but bail out when TID = 0 + * the new pi_state to it, but bail out when TID = 0 [1] */ if (!pid) return -ESRCH; p = futex_find_get_task(pid); - if (IS_ERR(p)) - return PTR_ERR(p); + if (!p) + return -ESRCH; + + if (!p->mm) { + put_task_struct(p); + return -EPERM; + } /* * We need to look at the task state flags to figure out, @@ -566,7 +900,7 @@ 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 @@ -575,11 +909,14 @@ 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; } + /* + * No existing pi state. First waiter. [2] + */ pi_state = alloc_pi_state(); /* @@ -594,7 +931,7 @@ 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); @@ -603,88 +940,247 @@ 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) + * + * Return: + * 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, force_take = 0; + u32 uval, newval, curval, vpid = task_pid_vnr(task); + +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 = vpid; + if (set_waiters) + newval |= FUTEX_WAITERS; + + if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval))) + return -EFAULT; + + /* + * Detect deadlocks. + */ + if ((unlikely((curval & FUTEX_TID_MASK) == vpid))) + return -EDEADLK; + + /* + * Surprise - we got the lock, but we do not trust user space at all. + */ + if (unlikely(!curval)) { + /* + * We verify whether there is kernel state for this + * futex. If not, we can safely assume, that the 0 -> + * TID transition is correct. If state exists, we do + * not bother to fixup the user space state as it was + * corrupted already. + */ + return futex_top_waiter(hb, key) ? -EINVAL : 1; + } + + uval = curval; + + /* + * Set the FUTEX_WAITERS flag, so the owner will know it has someone + * to wake at the next unlock. + */ + newval = curval | FUTEX_WAITERS; + + /* + * Should we force take the futex? See below. + */ + if (unlikely(force_take)) { + /* + * Keep the OWNER_DIED and the WAITERS bit and set the + * new TID value. + */ + newval = (curval & ~FUTEX_TID_MASK) | vpid; + force_take = 0; + lock_taken = 1; + } + + if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) + return -EFAULT; + if (unlikely(curval != uval)) + goto retry; + + /* + * We took the lock due to forced 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: + /* + * We failed to find an owner for this + * futex. So we have no pi_state to block + * on. This can happen in two cases: + * + * 1) The owner died + * 2) A stale FUTEX_WAITERS bit + * + * Re-read the futex value. + */ + if (get_futex_value_locked(&curval, uaddr)) + return -EFAULT; + + /* + * If the owner died or we have a stale + * WAITERS bit the owner TID in the user space + * futex is 0. + */ + if (!(curval & FUTEX_TID_MASK)) { + force_take = 1; + goto retry; + } + default: + break; + } + } + + return ret; +} + +/** + * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket + * @q: The futex_q to unqueue + * + * The q->lock_ptr must not be NULL and must be held by the caller. + */ +static void __unqueue_futex(struct futex_q *q) +{ + struct futex_hash_bucket *hb; + + if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr)) + || WARN_ON(plist_node_empty(&q->list))) + return; + + hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); + plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); +} + /* * 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; + + if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) + return; + /* - * 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); + + __unqueue_futex(q); /* - * 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) { struct task_struct *new_owner; struct futex_pi_state *pi_state = this->pi_state; - u32 curval, newval; + u32 uninitialized_var(curval), newval; + int ret = 0; 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); /* - * This happens when we have stolen the lock and the original - * pending owner did not enqueue itself back on the rt_mutex. - * Thats not a tragedy. We know that way, that a lock waiter - * is on the fly. We make the futex_q waiter the pending owner. + * It is possible that the next waiter (the one that brought + * this owner to the kernel) timed out and is no longer + * waiting on the lock. */ if (!new_owner) new_owner = this->task; /* - * We pass it to the next owner. (The WAITERS bit is always - * kept enabled while there is PI state around. We must also - * preserve the owner died bit.) + * We pass it to the next owner. The WAITERS bit is always + * kept enabled while there is PI state around. We cleanup the + * owner died bit, because we are the owner. */ - if (!(uval & FUTEX_OWNER_DIED)) { - int ret = 0; - - newval = FUTEX_WAITERS | task_pid_vnr(new_owner); - - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); - - if (curval == -EFAULT) - ret = -EFAULT; - else if (curval != uval) - ret = -EINVAL; - if (ret) { - spin_unlock(&pi_state->pi_mutex.wait_lock); - return ret; - } + newval = FUTEX_WAITERS | task_pid_vnr(new_owner); + + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) + ret = -EFAULT; + else if (curval != uval) + ret = -EINVAL; + if (ret) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + return ret; } - 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; @@ -692,16 +1188,14 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) static int unlock_futex_pi(u32 __user *uaddr, u32 uval) { - u32 oldval; + u32 uninitialized_var(oldval); /* * There is no waiter, so we unlock the futex. The owner died * bit has not to be preserved here. We are the owner: */ - oldval = cmpxchg_futex_value_locked(uaddr, uval, 0); - - if (oldval == -EFAULT) - return oldval; + if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0)) + return -EFAULT; if (oldval != uval) return -EAGAIN; @@ -724,35 +1218,43 @@ 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, u32 bitset) +static int +futex_wake(u32 __user *uaddr, unsigned int flags, 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; if (!bitset) return -EINVAL; - futex_lock_mm(fshared); - - ret = get_futex_key(uaddr, fshared, &key); + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ); if (unlikely(ret != 0)) goto out; hb = hash_futex(&key); + + /* Make sure we really have tasks to wakeup */ + if (!hb_waiters_pending(hb)) + goto out_put_key; + spin_lock(&hb->lock); - head = &hb->chain; - plist_for_each_entry_safe(this, next, head, list) { + plist_for_each_entry_safe(this, next, &hb->chain, list) { if (match_futex (&this->key, &key)) { - if (this->pi_state) { + if (this->pi_state || this->rt_waiter) { ret = -EINVAL; break; } @@ -768,8 +1270,9 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, } spin_unlock(&hb->lock); +out_put_key: + put_futex_key(&key); out: - futex_unlock_mm(fshared); return ret; } @@ -778,39 +1281,31 @@ 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, unsigned int flags, 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; + int ret, op_ret; -retryfull: - futex_lock_mm(fshared); - - ret = get_futex_key(uaddr1, fshared, &key1); +retry: + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2); + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); 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 /* @@ -818,46 +1313,32 @@ 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; - } - - /* - * If we would have faulted, release mmap_sem, - * fault it in and start all over again. - */ - futex_unlock_mm(fshared); - - ret = get_user(dummy, uaddr2); + ret = fault_in_user_writeable(uaddr2); if (ret) - return ret; + goto out_put_keys; - goto retryfull; - } + if (!(flags & FLAGS_SHARED)) + goto retry_private; - head = &hb1->chain; + put_futex_key(&key2); + put_futex_key(&key1); + goto retry; + } - plist_for_each_entry_safe(this, next, head, list) { + plist_for_each_entry_safe(this, next, &hb1->chain, list) { if (match_futex (&this->key, &key1)) { + if (this->pi_state || this->rt_waiter) { + ret = -EINVAL; + goto out_unlock; + } wake_futex(this); if (++ret >= nr_wake) break; @@ -865,11 +1346,13 @@ retry: } if (op_ret > 0) { - head = &hb2->chain; - op_ret = 0; - plist_for_each_entry_safe(this, next, head, list) { + plist_for_each_entry_safe(this, next, &hb2->chain, list) { if (match_futex (&this->key, &key2)) { + if (this->pi_state || this->rt_waiter) { + ret = -EINVAL; + goto out_unlock; + } wake_futex(this); if (++op_ret >= nr_wake2) break; @@ -878,42 +1361,228 @@ retry: ret += op_ret; } - spin_unlock(&hb1->lock); - if (hb1 != hb2) - spin_unlock(&hb2->lock); +out_unlock: + double_unlock_hb(hb1, hb2); +out_put_keys: + put_futex_key(&key2); +out_put_key1: + put_futex_key(&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); + hb_waiters_dec(hb1); + plist_add(&q->list, &hb2->chain); + hb_waiters_inc(hb2); + q->lock_ptr = &hb2->lock; + } + 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; + + __unqueue_futex(q); + WARN_ON(!q->rt_waiter); + q->rt_waiter = NULL; + + q->lock_ptr = &hb->lock; + + 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. + * + * Return: + * 0 - failed to acquire the lock atomically; + * >0 - acquired the lock, return value is vpid of the top_waiter + * <0 - error + */ +static int futex_proxy_trylock_atomic(u32 __user *pifutex, + struct futex_hash_bucket *hb1, + struct futex_hash_bucket *hb2, + union futex_key *key1, union futex_key *key2, + struct futex_pi_state **ps, int set_waiters) +{ + struct futex_q *top_waiter = NULL; + u32 curval; + int ret, vpid; + + 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. + */ + vpid = task_pid_vnr(top_waiter->task); + 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 vpid; + } 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 + * @flags: futex flags (FLAGS_SHARED, etc.) + * @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) + * @cmpval: @uaddr1 expected value (or %NULL) + * @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. + * + * Return: + * >=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, unsigned int flags, + 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; - retry: - futex_lock_mm(fshared); + if (requeue_pi) { + /* + * Requeue PI only works on two distinct uaddrs. This + * check is only valid for private futexes. See below. + */ + if (uaddr1 == uaddr2) + return -EINVAL; + + /* + * requeue_pi requires a pi_state, try to allocate it now + * without any locks in case it fails. + */ + 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); + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2); + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, + requeue_pi ? VERIFY_WRITE : VERIFY_READ); if (unlikely(ret != 0)) - goto out; + goto out_put_key1; + + /* + * The check above which compares uaddrs is not sufficient for + * shared futexes. We need to compare the keys: + */ + if (requeue_pi && match_futex(&key1, &key2)) { + ret = -EINVAL; + goto out_put_keys; + } hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); +retry_private: + hb_waiters_inc(hb2); double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { @@ -922,22 +1591,19 @@ 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); + hb_waiters_dec(hb2); ret = get_user(curval, uaddr1); + if (ret) + goto out_put_keys; - if (!ret) - goto retry; + if (!(flags & FLAGS_SHARED)) + goto retry_private; - return ret; + put_futex_key(&key2); + put_futex_key(&key1); + goto retry; } if (curval != *cmpval) { ret = -EAGAIN; @@ -945,68 +1611,199 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, } } - head1 = &hb1->chain; - plist_for_each_entry_safe(this, next, head1, list) { - if (!match_futex (&this->key, &key1)) - continue; - if (++ret <= nr_wake) { - wake_futex(this); - } else { + 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 the lock was taken, ret contains the + * vpid of the top waiter task. + */ + if (ret > 0) { + WARN_ON(pi_state); + drop_count++; + task_count++; /* - * If key1 and key2 hash to the same bucket, no need to - * requeue. + * If we acquired the lock, then the user + * space value of uaddr2 should be vpid. It + * cannot be changed by the top waiter as it + * is blocked on hb2 lock if it tries to do + * so. If something fiddled with it behind our + * back the pi state lookup might unearth + * it. So we rather use the known value than + * rereading and handing potential crap to + * lookup_pi_state. */ - 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++; + ret = lookup_pi_state(ret, hb2, &key2, &pi_state); + } - if (ret - nr_wake >= nr_requeue) - break; + switch (ret) { + case 0: + break; + case -EFAULT: + double_unlock_hb(hb1, hb2); + hb_waiters_dec(hb2); + put_futex_key(&key2); + put_futex_key(&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); + hb_waiters_dec(hb2); + put_futex_key(&key2); + put_futex_key(&key1); + cond_resched(); + goto retry; + default: + goto out_unlock; } } + plist_for_each_entry_safe(this, next, &hb1->chain, list) { + if (task_count - nr_wake >= nr_requeue) + break; + + if (!match_futex(&this->key, &key1)) + continue; + + /* + * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always + * be paired with each other and no other futex ops. + * + * We should never be requeueing a futex_q with a pi_state, + * which is awaiting a futex_unlock_pi(). + */ + if ((requeue_pi && !this->rt_waiter) || + (!requeue_pi && this->rt_waiter) || + this->pi_state) { + 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); + continue; + } + + /* 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); + hb_waiters_dec(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(&key2); +out_put_key1: + put_futex_key(&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) + __acquires(&hb->lock) { struct futex_hash_bucket *hb; - q->fd = fd; - q->filp = filp; + hb = hash_futex(&q->key); - init_waitqueue_head(&q->waiters); + /* + * Increment the counter before taking the lock so that + * a potential waker won't miss a to-be-slept task that is + * waiting for the spinlock. This is safe as all queue_lock() + * users end up calling queue_me(). Similarly, for housekeeping, + * decrement the counter at queue_unlock() when some error has + * occurred and we don't end up adding the task to the list. + */ + hb_waiters_inc(hb); - get_futex_key_refs(&q->key); - hb = hash_futex(&q->key); q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); + spin_lock(&hb->lock); /* implies MB (A) */ return hb; } -static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb) +static inline void +queue_unlock(struct futex_hash_bucket *hb) + __releases(&hb->lock) +{ + spin_unlock(&hb->lock); + hb_waiters_dec(hb); +} + +/** + * 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) + __releases(&hb->lock) { int prio; @@ -1021,43 +1818,29 @@ static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb) prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); -#ifdef CONFIG_DEBUG_PI_LIST - q->list.plist.lock = &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(). + * + * Return: + * 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 != NULL) { @@ -1079,8 +1862,7 @@ static int unqueue_me(struct futex_q *q) spin_unlock(lock_ptr); goto retry; } - WARN_ON(plist_node_empty(&q->list)); - plist_del(&q->list, &q->list.plist); + __unqueue_futex(q); BUG_ON(q->pi_state); @@ -1098,17 +1880,15 @@ static int unqueue_me(struct futex_q *q) * and dropped here. */ static void unqueue_me_pi(struct futex_q *q) + __releases(q->lock_ptr) { - WARN_ON(plist_node_empty(&q->list)); - plist_del(&q->list, &q->list.plist); + __unqueue_futex(q); BUG_ON(!q->pi_state); free_pi_state(q->pi_state); q->pi_state = NULL; spin_unlock(q->lock_ptr); - - drop_futex_key_refs(&q->key); } /* @@ -1122,82 +1902,234 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, { u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; - u32 uval, curval, newval; + struct task_struct *oldowner = pi_state->owner; + u32 uval, uninitialized_var(curval), newval; int ret; /* Owner died? */ + if (!pi_state->owner) + newtid |= FUTEX_OWNER_DIED; + + /* + * We are here either because we stole the rtmutex from the + * previous highest priority waiter or we are the highest priority + * waiter but failed to get the rtmutex the first time. + * We have to replace the newowner 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. + */ +retry: + if (get_futex_value_locked(&uval, uaddr)) + goto handle_fault; + + while (1) { + newval = (uval & FUTEX_OWNER_DIED) | newtid; + + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) + goto handle_fault; + if (curval == uval) + break; + uval = curval; + } + + /* + * We fixed up user space. Now we need to fix the pi_state + * itself. + */ if (pi_state->owner != NULL) { - 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); - } else - newtid |= FUTEX_OWNER_DIED; + raw_spin_unlock_irq(&pi_state->owner->pi_lock); + } pi_state->owner = newowner; - spin_lock_irq(&newowner->pi_lock); + raw_spin_lock_irq(&newowner->pi_lock); WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &newowner->pi_state_list); - spin_unlock_irq(&newowner->pi_lock); + raw_spin_unlock_irq(&newowner->pi_lock); + return 0; /* - * 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. + * To handle the page fault we need to drop the hash bucket + * lock here. That gives the other task (either the highest priority + * waiter 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. */ - ret = get_futex_value_locked(&uval, uaddr); +handle_fault: + spin_unlock(q->lock_ptr); - while (!ret) { - newval = (uval & FUTEX_OWNER_DIED) | newtid; + ret = fault_in_user_writeable(uaddr); - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); + spin_lock(q->lock_ptr); - if (curval == -EFAULT) - ret = -EFAULT; - if (curval == uval) - break; - uval = curval; - } - return ret; -} + /* + * Check if someone else fixed it for us: + */ + if (pi_state->owner != oldowner) + return 0; -/* - * In case we must use restart_block to restart a futex_wait, - * we encode in the 'flags' shared capability - */ -#define FLAGS_SHARED 1 + if (ret) + return ret; + + goto retry; +} 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, u32 bitset) +/** + * fixup_owner() - Post lock pi_state and corner case management + * @uaddr: user address of the futex + * @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. + * + * Return: + * 1 - success, lock taken; + * 0 - success, lock not taken; + * <0 - on error (-EFAULT) + */ +static int fixup_owner(u32 __user *uaddr, 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; - if (!bitset) - return -EINVAL; + 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); + goto out; + } - q.pi_state = NULL; - q.bitset = bitset; - retry: - futex_lock_mm(fshared); + /* + * 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; + } - ret = get_futex_key(uaddr, fshared, &q.key); - if (unlikely(ret != 0)) - goto out_release_sem; + /* + * 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. + */ + raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); + owner = rt_mutex_owner(&q->pi_state->pi_mutex); + if (!owner) + owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); + raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); + ret = fixup_pi_state_owner(uaddr, q, owner); + goto out; + } - hb = queue_lock(&q, -1, NULL); + /* + * Paranoia check. If we did not take the lock, then we should not be + * the 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; + } /* - * Access the page AFTER the futex is queued. + * 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) + freezable_schedule(); + } + __set_current_state(TASK_RUNNING); +} + +/** + * futex_wait_setup() - Prepare to wait on a futex + * @uaddr: the futex userspace address + * @val: the expected value + * @flags: futex flags (FLAGS_SHARED, etc.) + * @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. + * + * Return: + * 0 - uaddr contains val and hb has been locked; + * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked + */ +static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, + struct futex_q *q, struct futex_hash_bucket **hb) +{ + u32 uval; + int ret; + + /* + * Access the page AFTER the hash-bucket is locked. * Order is important: * * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); @@ -1205,144 +2137,138 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, * * The basic logical guarantee of a futex is that it blocks ONLY * if cond(var) is known to be true at the time of blocking, for - * any cond. If we queued after testing *uaddr, that would open - * a race condition where we could block indefinitely with + * any cond. If we locked the hash-bucket after testing *uaddr, that + * would open a race condition where we could block indefinitely with * cond(var) false, which would violate the guarantee. * - * 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. + * On the other hand, we insert q and release the hash-bucket only + * after testing *uaddr. This guarantees that futex_wait() will NOT + * absorb a wakeup if *uaddr does not match the desired values + * while the syscall executes. */ - ret = get_futex_value_locked(&uval, uaddr); +retry: + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, VERIFY_READ); + 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(*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 (!(flags & FLAGS_SHARED)) + 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(&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(*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(&q->key); + return ret; +} - hrtimer_start(&t.timer, t.timer.expires, HRTIMER_MODE_ABS); - if (!hrtimer_active(&t.timer)) - t.task = NULL; +static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, + ktime_t *abs_time, u32 bitset) +{ + struct hrtimer_sleeper timeout, *to = NULL; + struct restart_block *restart; + struct futex_hash_bucket *hb; + struct futex_q q = futex_q_init; + 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; + q.bitset = bitset; - hrtimer_cancel(&t.timer); + if (abs_time) { + to = &timeout; - /* Flag if a timeout occured */ - rem = (t.task == NULL); - } + hrtimer_init_on_stack(&to->timer, (flags & FLAGS_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); +retry: /* - * NOTE: we don't remove ourselves from the waitqueue because - * we are the only user of it. + * Prepare to wait on uaddr. On success, holds hb lock and increments + * q.key refs. */ + ret = futex_wait_setup(uaddr, val, flags, &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; + /* unqueue_me() drops q.key ref */ if (!unqueue_me(&q)) - return 0; - if (rem) - return -ETIMEDOUT; + goto out; + ret = -ETIMEDOUT; + if (to && !to->task) + goto out; /* - * 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 (!signal_pending(current)) + goto retry; + + ret = -ERESTARTSYS; if (!abs_time) - return -ERESTARTSYS; - else { - struct restart_block *restart; - 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 = 0; - - if (fshared) - restart->futex.flags |= FLAGS_SHARED; - return -ERESTART_RESTARTBLOCK; - } + goto out; + + restart = ¤t_thread_info()->restart_block; + restart->fn = futex_wait_restart; + restart->futex.uaddr = uaddr; + restart->futex.val = val; + restart->futex.time = abs_time->tv64; + restart->futex.bitset = bitset; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; - out_unlock_release_sem: - queue_unlock(&q, hb); + ret = -ERESTART_RESTARTBLOCK; - out_release_sem: - futex_unlock_mm(fshared); +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->futex.uaddr; - struct rw_semaphore *fshared = NULL; - ktime_t t; + u32 __user *uaddr = restart->futex.uaddr; + ktime_t t, *tp = NULL; - t.tv64 = restart->futex.time; + if (restart->futex.flags & FLAGS_HAS_TIMEOUT) { + t.tv64 = restart->futex.time; + tp = &t; + } restart->fn = do_no_restart_syscall; - if (restart->futex.flags & FLAGS_SHARED) - fshared = ¤t->mm->mmap_sem; - return (long)futex_wait(uaddr, fshared, restart->futex.val, &t, - restart->futex.bitset); + + return (long)futex_wait(uaddr, restart->futex.flags, + restart->futex.val, tp, restart->futex.bitset); } @@ -1352,155 +2278,60 @@ 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, - int detect, ktime_t *time, int trylock) +static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, 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; + struct futex_q q = futex_q_init; + 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); - - ret = get_futex_key(uaddr, fshared, &q.key); +retry: + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, VERIFY_WRITE); 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 = task_pid_vnr(current); - - 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) == task_pid_vnr(current))) { - 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) | task_pid_vnr(current); - ownerdied = 0; - lock_taken = 1; - } - - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); + goto out; - 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; - - /* - * 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); + queue_unlock(hb); + put_futex_key(&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); /* @@ -1514,108 +2345,53 @@ 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, &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) { - /* - * 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)) - ret = 0; - else { - /* - * 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. - */ - struct task_struct *owner; - int res; - - owner = rt_mutex_owner(&q.pi_state->pi_mutex); - res = fixup_pi_state_owner(uaddr, &q, owner); - - /* propagate -EFAULT, if the fixup failed */ - if (res) - ret = res; - } - } 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: - queue_unlock(&q, hb); +out_unlock_put_key: + queue_unlock(hb); - out_release_sem: - futex_unlock_mm(fshared); - return ret; - - 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 - */ - queue_unlock(&q, hb); +out_put_key: + put_futex_key(&q.key); +out: + if (to) + destroy_hrtimer_on_stack(&to->timer); + return ret != -EINTR ? ret : -ERESTARTNOINTR; - if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); - if (ret) - goto out_release_sem; - goto retry_unlocked; - } +uaddr_faulted: + queue_unlock(hb); - futex_unlock_mm(fshared); + ret = fault_in_user_writeable(uaddr); + if (ret) + goto out_put_key; - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) - goto retry; + if (!(flags & FLAGS_SHARED)) + goto retry_private; - return ret; + put_futex_key(&q.key); + goto retry; } /* @@ -1623,14 +2399,13 @@ 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, unsigned int flags) { 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; + u32 uval, vpid = task_pid_vnr(current); + int ret; retry: if (get_user(uval, uaddr)) @@ -1638,46 +2413,37 @@ retry: /* * We release only a lock we actually own: */ - if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) + if ((uval & FUTEX_TID_MASK) != vpid) return -EPERM; - /* - * First take all the futex related locks: - */ - futex_lock_mm(fshared); - ret = get_futex_key(uaddr, fshared, &key); + ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE); if (unlikely(ret != 0)) goto out; hb = hash_futex(&key); -retry_unlocked: spin_lock(&hb->lock); /* * To avoid races, try to do the TID -> 0 atomic transition * again. If it succeeds then we can return without waking - * anyone else up: + * anyone else up. We only try this if neither the waiters nor + * the owner died bit are set. */ - if (!(uval & FUTEX_OWNER_DIED)) - uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0); - - - if (unlikely(uval == -EFAULT)) + if (!(uval & ~FUTEX_TID_MASK) && + cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0)) goto pi_faulted; /* * Rare case: we managed to release the lock atomically, * no need to wake anyone else up: */ - if (unlikely(uval == task_pid_vnr(current))) + if (unlikely(uval == vpid)) goto out_unlock; /* * Ok, other tasks may need to be woken up - check waiters * and do the wakeup if necessary: */ - head = &hb->chain; - - plist_for_each_entry_safe(this, next, head, list) { + plist_for_each_entry_safe(this, next, &hb->chain, list) { if (!match_futex (&this->key, &key)) continue; ret = wake_futex_pi(uaddr, uval, this); @@ -1693,161 +2459,265 @@ retry_unlocked: /* * No waiters - kernel unlocks the futex: */ - if (!(uval & FUTEX_OWNER_DIED)) { - ret = unlock_futex_pi(uaddr, uval); - if (ret == -EFAULT) - goto pi_faulted; - } + ret = unlock_futex_pi(uaddr, uval); + if (ret == -EFAULT) + goto pi_faulted; out_unlock: spin_unlock(&hb->lock); -out: - futex_unlock_mm(fshared); + put_futex_key(&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(&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. + * + * Return: + * 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, &hb->chain); + hb_waiters_dec(hb); + + /* 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) + * @flags: futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), 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 + * @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 and unique from uaddr. 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 would not 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. + * + * Return: + * 0 - On success; + * <0 - On error */ -static int futex_fd(u32 __user *uaddr, int signal) +static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + u32 val, ktime_t *abs_time, u32 bitset, + 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 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; + + if (uaddr == uaddr2) + return -EINVAL; + + if (!bitset) + return -EINVAL; + + if (abs_time) { + to = &timeout; + hrtimer_init_on_stack(&to->timer, (flags & FLAGS_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); + RB_CLEAR_NODE(&rt_waiter.pi_tree_entry); + RB_CLEAR_NODE(&rt_waiter.tree_entry); + 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; + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + 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.bitset = bitset; + q.rt_waiter = &rt_waiter; + q.requeue_pi_key = &key2; + + /* + * Prepare to wait on uaddr. On success, increments q.key (key1) ref + * count. + */ + ret = futex_wait_setup(uaddr, val, flags, &q, &hb); + if (ret) + goto out_key2; + + /* + * The check above which compares uaddrs is not sufficient for + * shared futexes. We need to compare the keys: + */ + if (match_futex(&q.key, &key2)) { + ret = -EINVAL; + goto out_put_keys; } - q->pi_state = NULL; - fshared = ¤t->mm->mmap_sem; - down_read(fshared); - err = get_futex_key(uaddr, fshared, &q->key); + /* 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 acquisition by the requeue code. The + * futex_requeue dropped our key1 reference and incremented our key2 + * reference count. + */ + + /* 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); + 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); - if (unlikely(err != 0)) { - up_read(fshared); - kfree(q); - goto error; + spin_lock(q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. + */ + res = fixup_owner(uaddr2, &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; + + /* 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 (pi_mutex && 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(&q.key); +out_key2: + put_futex_key(&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; } /* @@ -1866,13 +2736,12 @@ 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; @@ -1888,39 +2757,40 @@ 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; + struct task_struct *p; if (!futex_cmpxchg_enabled) return -ENOSYS; + rcu_read_lock(); + + ret = -ESRCH; if (!pid) - head = current->robust_list; + p = current; else { - struct task_struct *p; - - ret = -ESRCH; - rcu_read_lock(); 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)) - goto err_unlock; - head = p->robust_list; - rcu_read_unlock(); } + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ)) + goto err_unlock; + + head = p->robust_list; + rcu_read_unlock(); + if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); @@ -1937,7 +2807,7 @@ err_unlock: */ int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { - u32 uval, nval, mval; + u32 uval, uninitialized_var(nval), mval; retry: if (get_user(uval, uaddr)) @@ -1955,11 +2825,20 @@ retry: * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; - nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval); - - if (nval == -EFAULT) - return -1; - + /* + * We are not holding a lock here, but we want to have + * the pagefault_disable/enable() protection because + * we want to handle the fault gracefully. If the + * access fails we try to fault in the futex with R/W + * verification via get_user_pages. get_user() above + * does not guarantee R/W access. If that fails we + * give up and leave the futex locked. + */ + if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) { + if (fault_in_user_writeable(uaddr)) + return -1; + goto retry; + } if (nval != uval) goto retry; @@ -1968,8 +2847,7 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, &curr->mm->mmap_sem, 1, - FUTEX_BITSET_MATCH_ANY); + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } @@ -1979,7 +2857,7 @@ retry: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, - int *pi) + unsigned int *pi) { unsigned long uentry; @@ -2002,7 +2880,8 @@ void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip; + unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; + unsigned int uninitialized_var(next_pi); unsigned long futex_offset; int rc; @@ -2063,59 +2942,63 @@ 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 = -ENOSYS; int cmd = op & FUTEX_CMD_MASK; - struct rw_semaphore *fshared = NULL; + unsigned int flags = 0; if (!(op & FUTEX_PRIVATE_FLAG)) - fshared = ¤t->mm->mmap_sem; + flags |= FLAGS_SHARED; + + if (op & FUTEX_CLOCK_REALTIME) { + flags |= FLAGS_CLOCKRT; + if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) + return -ENOSYS; + } + + switch (cmd) { + case FUTEX_LOCK_PI: + case FUTEX_UNLOCK_PI: + case FUTEX_TRYLOCK_PI: + case FUTEX_WAIT_REQUEUE_PI: + case FUTEX_CMP_REQUEUE_PI: + if (!futex_cmpxchg_enabled) + return -ENOSYS; + } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAIT_BITSET: - ret = futex_wait(uaddr, fshared, val, timeout, val3); - break; + return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAKE_BITSET: - ret = futex_wake(uaddr, fshared, val, val3); - break; - case FUTEX_FD: - /* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */ - ret = futex_fd(uaddr, val); - break; + return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: - ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL); - break; + return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: - ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3); - break; + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); case FUTEX_WAKE_OP: - ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3); - break; + return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_lock_pi(uaddr, fshared, val, timeout, 0); - break; + return futex_lock_pi(uaddr, flags, val, timeout, 0); case FUTEX_UNLOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_unlock_pi(uaddr, fshared); - break; + return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1); - break; - default: - ret = -ENOSYS; + return futex_lock_pi(uaddr, flags, 0, timeout, 1); + case FUTEX_WAIT_REQUEUE_PI: + val3 = FUTEX_BITSET_MATCH_ANY; + return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, + uaddr2); + case FUTEX_CMP_REQUEUE_PI: + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); } - return ret; + return -ENOSYS; } -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; @@ -2123,7 +3006,8 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, int cmd = op & FUTEX_CMD_MASK; if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET)) { + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { if (copy_from_user(&ts, utime, sizeof(ts)) != 0) return -EFAULT; if (!timespec_valid(&ts)) @@ -2135,33 +3019,20 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, 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, FUTEXFS_SUPER_MAGIC, mnt); -} - -static struct file_system_type futex_fs_type = { - .name = "futexfs", - .get_sb = futexfs_get_sb, - .kill_sb = kill_anon_super, -}; - -static int __init futex_init(void) +static void __init futex_detect_cmpxchg(void) { +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG u32 curval; - int i; /* * This will fail and we want it. Some arch implementations do @@ -2170,26 +3041,38 @@ static int __init futex_init(void) * 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 + * implementation, the non-functional ones will return * -ENOSYS. */ - curval = cmpxchg_futex_value_locked(NULL, 0, 0); - if (curval == -EFAULT) + if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) futex_cmpxchg_enabled = 1; +#endif +} - 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); - } +static int __init futex_init(void) +{ + unsigned int futex_shift; + unsigned long i; - i = register_filesystem(&futex_fs_type); - if (i) - return i; +#if CONFIG_BASE_SMALL + futex_hashsize = 16; +#else + futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); +#endif - futex_mnt = kern_mount(&futex_fs_type); - if (IS_ERR(futex_mnt)) { - unregister_filesystem(&futex_fs_type); - return PTR_ERR(futex_mnt); + futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), + futex_hashsize, 0, + futex_hashsize < 256 ? HASH_SMALL : 0, + &futex_shift, NULL, + futex_hashsize, futex_hashsize); + futex_hashsize = 1UL << futex_shift; + + futex_detect_cmpxchg(); + + for (i = 0; i < futex_hashsize; i++) { + atomic_set(&futex_queues[i].waiters, 0); + plist_head_init(&futex_queues[i].chain); + spin_lock_init(&futex_queues[i].lock); } return 0; |