/* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * 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. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */#include <linux/slab.h>#include <linux/poll.h>#include <linux/fs.h>#include <linux/file.h>#include <linux/jhash.h>#include <linux/init.h>#include <linux/futex.h>#include <linux/mount.h>#include <linux/pagemap.h>#include <linux/syscalls.h>#include <linux/signal.h>#include <asm/futex.h> #include "rtmutex_common.h" #define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8) /* * Futexes are matched on equal values of this key. * The key type depends on whether it's a shared or private mapping. * Don't rearrange members without looking at hash_futex(). * * offset is aligned to a multiple of sizeof(u32) (== 4) by definition. * We set bit 0 to indicate if it's an inode-based key. */union futex_key { struct { unsigned long pgoff; struct inode *inode; int offset; } shared; struct { unsigned long address; struct mm_struct *mm; int offset; } private; struct { unsigned long word; void *ptr; int offset; } both;}; /* * Priority Inheritance state: */struct futex_pi_state { /* * list of 'owned' pi_state instances - these have to be * cleaned up in do_exit() if the task exits prematurely: */ struct list_head list; /* * The PI object: */ struct rt_mutex pi_mutex; struct task_struct *owner; atomic_t refcount; union futex_key key;}; /* * 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 list_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. */struct futex_q { struct list_head list; wait_queue_head_t waiters; /* Which hash list lock to use: */ 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;}; /* * Split the global futex_lock into every hash list lock. */struct futex_hash_bucket { spinlock_t lock; struct list_head chain;}; static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS]; /* Futex-fs vfsmount entry: */static struct vfsmount *futex_mnt; /* * We hash on the keys returned from get_futex_key (see below). */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 1 if two futex_keys are equal, 0 otherwise. */static inline int match_futex(union futex_key *key1, union futex_key *key2){ return (key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset);} /* * Get parameters which are the keys for a futex. * * For shared mappings, it's (page->index, vma->vm_file->f_path.dentry->d_inode, * offset_within_page). For private mappings, it's (uaddr, current->mm). * We can usually work out the index without swapping in the page. * * Returns: 0, or negative error code. * The key words are stored in *key on success. * * Should be called with ¤t->mm->mmap_sem but NOT any spinlocks. */static int get_futex_key(u32 __user *uaddr, union futex_key *key){ unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct page *page; int err; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((key->both.offset % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; /* * The futex is hashed differently depending on whether * it's in a shared or private mapping. So check vma first. */ vma = find_extend_vma(mm, address); if (unlikely(!vma)) return -EFAULT; /* * Permissions. */ if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; /* * 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. */ if (likely(!(vma->vm_flags & VM_MAYSHARE))) { key->private.mm = mm; key->private.address = address; return 0; } /* * Linear file mappings are also simple. */ key->shared.inode = vma->vm_file->f_path.dentry->d_inode; key->both.offset++; /* Bit 0 of offset indicates inode-based key. */ if (likely(!(vma->vm_flags & VM_NONLINEAR))) { key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff); return 0; } /* * We could walk the page table to read the non-linear * pte, and get the page index without fetching the page * from swap. But that's a lot of code to duplicate here * for a rare case, so we simply fetch the page. */ err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL); if (err >= 0) { key->shared.pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); put_page(page); return 0; } return err;} /* * Take a reference to the resource addressed by a key. * Can be called while holding spinlocks. * * NOTE: mmap_sem MUST be held between get_futex_key() and calling this * function, if it is called at all. mmap_sem keeps key->shared.inode valid. */static inline void get_key_refs(union futex_key *key){ if (key->both.ptr != 0) { if (key->both.offset & 1) atomic_inc(&key->shared.inode->i_count); else atomic_inc(&key->private.mm->mm_count); }} /* * Drop a reference to the resource addressed by a key. * The hash bucket spinlock must not be held. */static void drop_key_refs(union futex_key *key){ if (key->both.ptr != 0) { if (key->both.offset & 1) iput(key->shared.inode); else mmdrop(key->private.mm); }} static inline int get_futex_value_locked(u32 *dest, u32 __user *from){ int ret; pagefault_disable(); ret = __copy_from_user_inatomic(dest, from, sizeof(u32)); pagefault_enable(); return ret ? -EFAULT : 0;} /* * Fault handling. Called with current->mm->mmap_sem held. */static int futex_handle_fault(unsigned long address, int attempt){ struct vm_area_struct * vma; struct mm_struct *mm = current->mm; if (attempt > 2 || !(vma = find_vma(mm, address)) || vma->vm_start > address || !(vma->vm_flags & VM_WRITE)) return -EFAULT; switch (handle_mm_fault(mm, vma, address, 1)) { case VM_FAULT_MINOR: current->min_flt++; break; case VM_FAULT_MAJOR: current->maj_flt++; break; default: return -EFAULT; } return 0;} /* * PI code: */static int refill_pi_state_cache(void){ struct futex_pi_state *pi_state; if (likely(current->pi_state_cache)) return 0; pi_state = kzalloc(sizeof(*pi_state), GFP_KERNEL); if (!pi_state) return -ENOMEM; INIT_LIST_HEAD(&pi_state->list); /* pi_mutex gets initialized later */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); current->pi_state_cache = pi_state; return 0;} static struct futex_pi_state * alloc_pi_state(void){ struct futex_pi_state *pi_state = current->pi_state_cache; WARN_ON(!pi_state); current->pi_state_cache = NULL; return pi_state;} static void free_pi_state(struct futex_pi_state *pi_state){ if (!atomic_dec_and_test(&pi_state->refcount)) return; /* * If pi_state->owner is NULL, the owner is most probably dying * and has cleaned up the pi_state already */ if (pi_state->owner) { spin_lock_irq(&pi_state->owner->pi_lock); list_del_init(&pi_state->list); spin_unlock_irq(&pi_state->owner->pi_lock); rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); } if (current->pi_state_cache) kfree(pi_state); else { /* * pi_state->list is already empty. * clear pi_state->owner. * refcount is at 0 - put it back to 1. */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); current->pi_state_cache = pi_state; }} /* * Look up the task based on what TID userspace gave us. * We dont trust it. */static struct task_struct * futex_find_get_task(pid_t pid){ struct task_struct *p; rcu_read_lock(); p = find_task_by_pid(pid); if (!p) goto out_unlock; if ((current->euid != p->euid) && (current->euid != p->uid)) { p = NULL; goto out_unlock; } if (p->exit_state != 0) { p = NULL; goto out_unlock; } get_task_struct(p);out_unlock: rcu_read_unlock(); return p;} /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */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; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ spin_lock_irq(&curr->pi_lock); 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); spin_lock(&hb->lock); spin_lock_irq(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { spin_unlock(&hb->lock); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; spin_unlock_irq(&curr->pi_lock); rt_mutex_unlock(&pi_state->pi_mutex); spin_unlock(&hb->lock); spin_lock_irq(&curr->pi_lock); } spin_unlock_irq(&curr->pi_lock);} static intlookup_pi_state(u32 uval, struct futex_hash_bucket *hb, struct futex_q *me){ struct futex_pi_state *pi_state = NULL; struct futex_q *this, *next; struct list_head *head; struct task_struct *p; pid_t pid; head = &hb->chain; list_for_each_entry_safe(this, next, head, list) { if (match_futex(&this->key, &me->key)) { /* * Another waiter already exists - bump up * the refcount and return its pi_state: */ pi_state = this->pi_state; /* * Userspace might have messed up non PI and PI futexes */ if (unlikely(!pi_state)) return -EINVAL; WARN_ON(!atomic_read(&pi_state->refcount)); atomic_inc(&pi_state->refcount); me->pi_state = 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 the owner died bit is set * and TID = 0: */Lines 1–500 of 1879. Load more
/* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * 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. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/slab.h> #include <linux/poll.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/jhash.h> #include <linux/init.h> #include <linux/futex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <asm/futex.h> #include "rtmutex_common.h" #define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8) /* * Futexes are matched on equal values of this key. * The key type depends on whether it's a shared or private mapping. * Don't rearrange members without looking at hash_futex(). * * offset is aligned to a multiple of sizeof(u32) (== 4) by definition. * We set bit 0 to indicate if it's an inode-based key. */ union futex_key { struct { unsigned long pgoff; struct inode *inode; int offset; } shared; struct { unsigned long address; struct mm_struct *mm; int offset; } private; struct { unsigned long word; void *ptr; int offset; } both; }; /* * Priority Inheritance state: */ struct futex_pi_state { /* * list of 'owned' pi_state instances - these have to be * cleaned up in do_exit() if the task exits prematurely: */ struct list_head list; /* * The PI object: */ struct rt_mutex pi_mutex; struct task_struct *owner; atomic_t refcount; union futex_key key; }; /* * 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 list_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. */ struct futex_q { struct list_head list; wait_queue_head_t waiters; /* Which hash list lock to use: */ 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; }; /* * Split the global futex_lock into every hash list lock. */ struct futex_hash_bucket { spinlock_t lock; struct list_head chain; }; static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS]; /* Futex-fs vfsmount entry: */ static struct vfsmount *futex_mnt; /* * We hash on the keys returned from get_futex_key (see below). */ 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 1 if two futex_keys are equal, 0 otherwise. */ static inline int match_futex(union futex_key *key1, union futex_key *key2) { return (key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset); } /* * Get parameters which are the keys for a futex. * * For shared mappings, it's (page->index, vma->vm_file->f_path.dentry->d_inode, * offset_within_page). For private mappings, it's (uaddr, current->mm). * We can usually work out the index without swapping in the page. * * Returns: 0, or negative error code. * The key words are stored in *key on success. * * Should be called with ¤t->mm->mmap_sem but NOT any spinlocks. */ static int get_futex_key(u32 __user *uaddr, union futex_key *key) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct page *page; int err; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((key->both.offset % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; /* * The futex is hashed differently depending on whether * it's in a shared or private mapping. So check vma first. */ vma = find_extend_vma(mm, address); if (unlikely(!vma)) return -EFAULT; /* * Permissions. */ if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; /* * 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. */ if (likely(!(vma->vm_flags & VM_MAYSHARE))) { key->private.mm = mm; key->private.address = address; return 0; } /* * Linear file mappings are also simple. */ key->shared.inode = vma->vm_file->f_path.dentry->d_inode; key->both.offset++; /* Bit 0 of offset indicates inode-based key. */ if (likely(!(vma->vm_flags & VM_NONLINEAR))) { key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff); return 0; } /* * We could walk the page table to read the non-linear * pte, and get the page index without fetching the page * from swap. But that's a lot of code to duplicate here * for a rare case, so we simply fetch the page. */ err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL); if (err >= 0) { key->shared.pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); put_page(page); return 0; } return err; } /* * Take a reference to the resource addressed by a key. * Can be called while holding spinlocks. * * NOTE: mmap_sem MUST be held between get_futex_key() and calling this * function, if it is called at all. mmap_sem keeps key->shared.inode valid. */ static inline void get_key_refs(union futex_key *key) { if (key->both.ptr != 0) { if (key->both.offset & 1) atomic_inc(&key->shared.inode->i_count); else atomic_inc(&key->private.mm->mm_count); } } /* * Drop a reference to the resource addressed by a key. * The hash bucket spinlock must not be held. */ static void drop_key_refs(union futex_key *key) { if (key->both.ptr != 0) { if (key->both.offset & 1) iput(key->shared.inode); else mmdrop(key->private.mm); } } static inline int get_futex_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = __copy_from_user_inatomic(dest, from, sizeof(u32)); pagefault_enable(); return ret ? -EFAULT : 0; } /* * Fault handling. Called with current->mm->mmap_sem held. */ static int futex_handle_fault(unsigned long address, int attempt) { struct vm_area_struct * vma; struct mm_struct *mm = current->mm; if (attempt > 2 || !(vma = find_vma(mm, address)) || vma->vm_start > address || !(vma->vm_flags & VM_WRITE)) return -EFAULT; switch (handle_mm_fault(mm, vma, address, 1)) { case VM_FAULT_MINOR: current->min_flt++; break; case VM_FAULT_MAJOR: current->maj_flt++; break; default: return -EFAULT; } return 0; } /* * PI code: */ static int refill_pi_state_cache(void) { struct futex_pi_state *pi_state; if (likely(current->pi_state_cache)) return 0; pi_state = kzalloc(sizeof(*pi_state), GFP_KERNEL); if (!pi_state) return -ENOMEM; INIT_LIST_HEAD(&pi_state->list); /* pi_mutex gets initialized later */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); current->pi_state_cache = pi_state; return 0; } static struct futex_pi_state * alloc_pi_state(void) { struct futex_pi_state *pi_state = current->pi_state_cache; WARN_ON(!pi_state); current->pi_state_cache = NULL; return pi_state; } static void free_pi_state(struct futex_pi_state *pi_state) { if (!atomic_dec_and_test(&pi_state->refcount)) return; /* * If pi_state->owner is NULL, the owner is most probably dying * and has cleaned up the pi_state already */ if (pi_state->owner) { spin_lock_irq(&pi_state->owner->pi_lock); list_del_init(&pi_state->list); spin_unlock_irq(&pi_state->owner->pi_lock); rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); } if (current->pi_state_cache) kfree(pi_state); else { /* * pi_state->list is already empty. * clear pi_state->owner. * refcount is at 0 - put it back to 1. */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); current->pi_state_cache = pi_state; } } /* * Look up the task based on what TID userspace gave us. * We dont trust it. */ static struct task_struct * futex_find_get_task(pid_t pid) { struct task_struct *p; rcu_read_lock(); p = find_task_by_pid(pid); if (!p) goto out_unlock; if ((current->euid != p->euid) && (current->euid != p->uid)) { p = NULL; goto out_unlock; } if (p->exit_state != 0) { p = NULL; goto out_unlock; } get_task_struct(p); out_unlock: rcu_read_unlock(); return p; } /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ 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; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ spin_lock_irq(&curr->pi_lock); 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); spin_lock(&hb->lock); spin_lock_irq(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { spin_unlock(&hb->lock); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; spin_unlock_irq(&curr->pi_lock); rt_mutex_unlock(&pi_state->pi_mutex); spin_unlock(&hb->lock); spin_lock_irq(&curr->pi_lock); } spin_unlock_irq(&curr->pi_lock); } static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, struct futex_q *me) { struct futex_pi_state *pi_state = NULL; struct futex_q *this, *next; struct list_head *head; struct task_struct *p; pid_t pid; head = &hb->chain; list_for_each_entry_safe(this, next, head, list) { if (match_futex(&this->key, &me->key)) { /* * Another waiter already exists - bump up * the refcount and return its pi_state: */ pi_state = this->pi_state; /* * Userspace might have messed up non PI and PI futexes */ if (unlikely(!pi_state)) return -EINVAL; WARN_ON(!atomic_read(&pi_state->refcount)); atomic_inc(&pi_state->refcount); me->pi_state = 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 the owner died bit is set * and TID = 0: */