X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=ipc%2Fsem.c;h=dbef95b1594122c2a6276d504d206805d39879f7;hb=436c109adb54433fff689abd71c23a6505e46bb0;hp=1f7e28d1d25d944b9316f329e8674b2552b34755;hpb=ed2ddbf88c0ddeeae4c78bb306a116dfd867c55c;p=safe%2Fjmp%2Flinux-2.6 diff --git a/ipc/sem.c b/ipc/sem.c index 1f7e28d..dbef95b 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -58,7 +58,7 @@ * SMP-threaded, sysctl's added * (c) 1999 Manfred Spraul * Enforced range limit on SEM_UNDO - * (c) 2001 Red Hat Inc + * (c) 2001 Red Hat Inc * Lockless wakeup * (c) 2003 Manfred Spraul * @@ -91,10 +91,9 @@ #define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm) #define sem_checkid(sma, semid) ipc_checkid(&sma->sem_perm, semid) -#define sem_buildid(id, seq) ipc_buildid(id, seq) static int newary(struct ipc_namespace *, struct ipc_params *); -static void freeary(struct ipc_namespace *, struct sem_array *); +static void freeary(struct ipc_namespace *, struct kern_ipc_perm *); #ifdef CONFIG_PROC_FS static int sysvipc_sem_proc_show(struct seq_file *s, void *it); #endif @@ -129,25 +128,8 @@ void sem_init_ns(struct ipc_namespace *ns) #ifdef CONFIG_IPC_NS void sem_exit_ns(struct ipc_namespace *ns) { - struct sem_array *sma; - struct kern_ipc_perm *perm; - int next_id; - int total, in_use; - - down_write(&sem_ids(ns).rw_mutex); - - in_use = sem_ids(ns).in_use; - - for (total = 0, next_id = 0; total < in_use; next_id++) { - perm = idr_find(&sem_ids(ns).ipcs_idr, next_id); - if (perm == NULL) - continue; - ipc_lock_by_ptr(perm); - sma = container_of(perm, struct sem_array, sem_perm); - freeary(ns, sma); - total++; - } - up_write(&sem_ids(ns).rw_mutex); + free_ipcs(ns, &sem_ids(ns), freeary); + idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr); } #endif @@ -160,21 +142,6 @@ void __init sem_init (void) } /* - * This routine is called in the paths where the rw_mutex is held to protect - * access to the idr tree. - */ -static inline struct sem_array *sem_lock_check_down(struct ipc_namespace *ns, - int id) -{ - struct kern_ipc_perm *ipcp = ipc_lock_check_down(&sem_ids(ns), id); - - if (IS_ERR(ipcp)) - return (struct sem_array *)ipcp; - - return container_of(ipcp, struct sem_array, sem_perm); -} - -/* * sem_lock_(check_) routines are called in the paths where the rw_mutex * is not held. */ @@ -199,6 +166,25 @@ static inline struct sem_array *sem_lock_check(struct ipc_namespace *ns, return container_of(ipcp, struct sem_array, sem_perm); } +static inline void sem_lock_and_putref(struct sem_array *sma) +{ + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); +} + +static inline void sem_getref_and_unlock(struct sem_array *sma) +{ + ipc_rcu_getref(sma); + ipc_unlock(&(sma)->sem_perm); +} + +static inline void sem_putref(struct sem_array *sma) +{ + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + ipc_unlock(&(sma)->sem_perm); +} + static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) { ipc_rmid(&sem_ids(ns), &s->sem_perm); @@ -255,6 +241,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) key_t key = params->key; int nsems = params->u.nsems; int semflg = params->flg; + int i; if (!nsems) return -EINVAL; @@ -286,11 +273,14 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) } ns->used_sems += nsems; - sma->sem_perm.id = sem_buildid(id, sma->sem_perm.seq); sma->sem_base = (struct sem *) &sma[1]; - /* sma->sem_pending = NULL; */ - sma->sem_pending_last = &sma->sem_pending; - /* sma->undo = NULL; */ + + for (i = 0; i < nsems; i++) + INIT_LIST_HEAD(&sma->sem_base[i].sem_pending); + + sma->complex_count = 0; + INIT_LIST_HEAD(&sma->sem_pending); + INIT_LIST_HEAD(&sma->list_id); sma->sem_nsems = nsems; sma->sem_ctime = get_seconds(); sem_unlock(sma); @@ -325,7 +315,7 @@ static inline int sem_more_checks(struct kern_ipc_perm *ipcp, return 0; } -asmlinkage long sys_semget(key_t key, int nsems, int semflg) +SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) { struct ipc_namespace *ns; struct ipc_ops sem_ops; @@ -347,38 +337,6 @@ asmlinkage long sys_semget(key_t key, int nsems, int semflg) return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params); } -/* Manage the doubly linked list sma->sem_pending as a FIFO: - * insert new queue elements at the tail sma->sem_pending_last. - */ -static inline void append_to_queue (struct sem_array * sma, - struct sem_queue * q) -{ - *(q->prev = sma->sem_pending_last) = q; - *(sma->sem_pending_last = &q->next) = NULL; -} - -static inline void prepend_to_queue (struct sem_array * sma, - struct sem_queue * q) -{ - q->next = sma->sem_pending; - *(q->prev = &sma->sem_pending) = q; - if (q->next) - q->next->prev = &q->next; - else /* sma->sem_pending_last == &sma->sem_pending */ - sma->sem_pending_last = &q->next; -} - -static inline void remove_from_queue (struct sem_array * sma, - struct sem_queue * q) -{ - *(q->prev) = q->next; - if (q->next) - q->next->prev = q->prev; - else /* sma->sem_pending_last == &q->next */ - sma->sem_pending_last = q->prev; - q->prev = NULL; /* mark as removed */ -} - /* * Determine whether a sequence of semaphore operations would succeed * all at once. Return 0 if yes, 1 if need to sleep, else return error code. @@ -446,49 +404,109 @@ undo: return result; } -/* Go through the pending queue for the indicated semaphore - * looking for tasks that can be completed. +/* + * Wake up a process waiting on the sem queue with a given error. + * The queue is invalid (may not be accessed) after the function returns. */ -static void update_queue (struct sem_array * sma) +static void wake_up_sem_queue(struct sem_queue *q, int error) { - int error; - struct sem_queue * q; + /* + * Hold preempt off so that we don't get preempted and have the + * wakee busy-wait until we're scheduled back on. We're holding + * locks here so it may not strictly be needed, however if the + * locks become preemptible then this prevents such a problem. + */ + preempt_disable(); + q->status = IN_WAKEUP; + wake_up_process(q->sleeper); + /* hands-off: q can disappear immediately after writing q->status. */ + smp_wmb(); + q->status = error; + preempt_enable(); +} + +static void unlink_queue(struct sem_array *sma, struct sem_queue *q) +{ + list_del(&q->list); + if (q->nsops == 1) + list_del(&q->simple_list); + else + sma->complex_count--; +} + + +/** + * update_queue(sma, semnum): Look for tasks that can be completed. + * @sma: semaphore array. + * @semnum: semaphore that was modified. + * + * update_queue must be called after a semaphore in a semaphore array + * was modified. If multiple semaphore were modified, then @semnum + * must be set to -1. + */ +static void update_queue(struct sem_array *sma, int semnum) +{ + struct sem_queue *q; + struct list_head *walk; + struct list_head *pending_list; + int offset; + + /* if there are complex operations around, then knowing the semaphore + * that was modified doesn't help us. Assume that multiple semaphores + * were modified. + */ + if (sma->complex_count) + semnum = -1; + + if (semnum == -1) { + pending_list = &sma->sem_pending; + offset = offsetof(struct sem_queue, list); + } else { + pending_list = &sma->sem_base[semnum].sem_pending; + offset = offsetof(struct sem_queue, simple_list); + } + +again: + walk = pending_list->next; + while (walk != pending_list) { + int error, alter; + + q = (struct sem_queue *)((char *)walk - offset); + walk = walk->next; + + /* If we are scanning the single sop, per-semaphore list of + * one semaphore and that semaphore is 0, then it is not + * necessary to scan the "alter" entries: simple increments + * that affect only one entry succeed immediately and cannot + * be in the per semaphore pending queue, and decrements + * cannot be successful if the value is already 0. + */ + if (semnum != -1 && sma->sem_base[semnum].semval == 0 && + q->alter) + break; - q = sma->sem_pending; - while(q) { error = try_atomic_semop(sma, q->sops, q->nsops, q->undo, q->pid); /* Does q->sleeper still need to sleep? */ - if (error <= 0) { - struct sem_queue *n; - remove_from_queue(sma,q); - q->status = IN_WAKEUP; - /* - * Continue scanning. The next operation - * that must be checked depends on the type of the - * completed operation: - * - if the operation modified the array, then - * restart from the head of the queue and - * check for threads that might be waiting - * for semaphore values to become 0. - * - if the operation didn't modify the array, - * then just continue. - */ - if (q->alter) - n = sma->sem_pending; - else - n = q->next; - wake_up_process(q->sleeper); - /* hands-off: q will disappear immediately after - * writing q->status. - */ - smp_wmb(); - q->status = error; - q = n; - } else { - q = q->next; - } + if (error > 0) + continue; + + unlink_queue(sma, q); + + /* + * The next operation that must be checked depends on the type + * of the completed operation: + * - if the operation modified the array, then restart from the + * head of the queue and check for threads that might be + * waiting for the new semaphore values. + * - if the operation didn't modify the array, then just + * continue. + */ + alter = q->alter; + wake_up_sem_queue(q, error); + if (alter && !error) + goto again; } } @@ -507,7 +525,7 @@ static int count_semncnt (struct sem_array * sma, ushort semnum) struct sem_queue * q; semncnt = 0; - for (q = sma->sem_pending; q; q = q->next) { + list_for_each_entry(q, &sma->sem_pending, list) { struct sembuf * sops = q->sops; int nsops = q->nsops; int i; @@ -519,13 +537,14 @@ static int count_semncnt (struct sem_array * sma, ushort semnum) } return semncnt; } + static int count_semzcnt (struct sem_array * sma, ushort semnum) { int semzcnt; struct sem_queue * q; semzcnt = 0; - for (q = sma->sem_pending; q; q = q->next) { + list_for_each_entry(q, &sma->sem_pending, list) { struct sembuf * sops = q->sops; int nsops = q->nsops; int i; @@ -538,34 +557,37 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum) return semzcnt; } +static void free_un(struct rcu_head *head) +{ + struct sem_undo *un = container_of(head, struct sem_undo, rcu); + kfree(un); +} + /* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex * remains locked on exit. */ -static void freeary(struct ipc_namespace *ns, struct sem_array *sma) +static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { - struct sem_undo *un; - struct sem_queue *q; - - /* Invalidate the existing undo structures for this semaphore set. - * (They will be freed without any further action in exit_sem() - * or during the next semop.) - */ - for (un = sma->undo; un; un = un->id_next) + struct sem_undo *un, *tu; + struct sem_queue *q, *tq; + struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); + + /* Free the existing undo structures for this semaphore set. */ + assert_spin_locked(&sma->sem_perm.lock); + list_for_each_entry_safe(un, tu, &sma->list_id, list_id) { + list_del(&un->list_id); + spin_lock(&un->ulp->lock); un->semid = -1; + list_del_rcu(&un->list_proc); + spin_unlock(&un->ulp->lock); + call_rcu(&un->rcu, free_un); + } /* Wake up all pending processes and let them fail with EIDRM. */ - q = sma->sem_pending; - while(q) { - struct sem_queue *n; - /* lazy remove_from_queue: we are killing the whole queue */ - q->prev = NULL; - n = q->next; - q->status = IN_WAKEUP; - wake_up_process(q->sleeper); /* doesn't sleep */ - smp_wmb(); - q->status = -EIDRM; /* hands-off q */ - q = n; + list_for_each_entry_safe(q, tq, &sma->sem_pending, list) { + unlink_queue(sma, q); + wake_up_sem_queue(q, -EIDRM); } /* Remove the semaphore set from the IDR */ @@ -602,7 +624,7 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, static int semctl_nolock(struct ipc_namespace *ns, int semid, int cmd, int version, union semun arg) { - int err = -EINVAL; + int err; struct sem_array *sma; switch(cmd) { @@ -679,7 +701,6 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid, default: return -EINVAL; } - return err; out_unlock: sem_unlock(sma); return err; @@ -717,19 +738,15 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int i; if(nsems > SEMMSL_FAST) { - ipc_rcu_getref(sma); - sem_unlock(sma); + sem_getref_and_unlock(sma); sem_io = ipc_alloc(sizeof(ushort)*nsems); if(sem_io == NULL) { - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); - sem_unlock(sma); + sem_putref(sma); return -ENOMEM; } - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); + sem_lock_and_putref(sma); if (sma->sem_perm.deleted) { sem_unlock(sma); err = -EIDRM; @@ -750,38 +767,30 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int i; struct sem_undo *un; - ipc_rcu_getref(sma); - sem_unlock(sma); + sem_getref_and_unlock(sma); if(nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); if(sem_io == NULL) { - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); - sem_unlock(sma); + sem_putref(sma); return -ENOMEM; } } if (copy_from_user (sem_io, arg.array, nsems*sizeof(ushort))) { - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); - sem_unlock(sma); + sem_putref(sma); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); - sem_unlock(sma); + sem_putref(sma); err = -ERANGE; goto out_free; } } - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); + sem_lock_and_putref(sma); if (sma->sem_perm.deleted) { sem_unlock(sma); err = -EIDRM; @@ -790,12 +799,15 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, for (i = 0; i < nsems; i++) sma->sem_base[i].semval = sem_io[i]; - for (un = sma->undo; un; un = un->id_next) + + assert_spin_locked(&sma->sem_perm.lock); + list_for_each_entry(un, &sma->list_id, list_id) { for (i = 0; i < nsems; i++) un->semadj[i] = 0; + } sma->sem_ctime = get_seconds(); /* maybe some queued-up processes were waiting for this */ - update_queue(sma); + update_queue(sma, -1); err = 0; goto out_unlock; } @@ -824,17 +836,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, { int val = arg.val; struct sem_undo *un; + err = -ERANGE; if (val > SEMVMX || val < 0) goto out_unlock; - for (un = sma->undo; un; un = un->id_next) + assert_spin_locked(&sma->sem_perm.lock); + list_for_each_entry(un, &sma->list_id, list_id) un->semadj[semnum] = 0; + curr->semval = val; curr->sempid = task_tgid_vnr(current); sma->sem_ctime = get_seconds(); /* maybe some queued-up processes were waiting for this */ - update_queue(sma); + update_queue(sma, semnum); err = 0; goto out_unlock; } @@ -847,28 +862,14 @@ out_free: return err; } -struct sem_setbuf { - uid_t uid; - gid_t gid; - mode_t mode; -}; - -static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __user *buf, int version) +static inline unsigned long +copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { switch(version) { case IPC_64: - { - struct semid64_ds tbuf; - - if(copy_from_user(&tbuf, buf, sizeof(tbuf))) + if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; - - out->uid = tbuf.sem_perm.uid; - out->gid = tbuf.sem_perm.gid; - out->mode = tbuf.sem_perm.mode; - return 0; - } case IPC_OLD: { struct semid_ds tbuf_old; @@ -876,9 +877,9 @@ static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __ if(copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; - out->uid = tbuf_old.sem_perm.uid; - out->gid = tbuf_old.sem_perm.gid; - out->mode = tbuf_old.sem_perm.mode; + out->sem_perm.uid = tbuf_old.sem_perm.uid; + out->sem_perm.gid = tbuf_old.sem_perm.gid; + out->sem_perm.mode = tbuf_old.sem_perm.mode; return 0; } @@ -887,38 +888,29 @@ static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __ } } -static int semctl_down(struct ipc_namespace *ns, int semid, int semnum, - int cmd, int version, union semun arg) +/* + * This function handles some semctl commands which require the rw_mutex + * to be held in write mode. + * NOTE: no locks must be held, the rw_mutex is taken inside this function. + */ +static int semctl_down(struct ipc_namespace *ns, int semid, + int cmd, int version, union semun arg) { struct sem_array *sma; int err; - struct sem_setbuf uninitialized_var(setbuf); + struct semid64_ds semid64; struct kern_ipc_perm *ipcp; if(cmd == IPC_SET) { - if(copy_semid_from_user (&setbuf, arg.buf, version)) + if (copy_semid_from_user(&semid64, arg.buf, version)) return -EFAULT; } - sma = sem_lock_check_down(ns, semid); - if (IS_ERR(sma)) - return PTR_ERR(sma); - ipcp = &sma->sem_perm; - - err = audit_ipc_obj(ipcp); - if (err) - goto out_unlock; + ipcp = ipcctl_pre_down(&sem_ids(ns), semid, cmd, &semid64.sem_perm, 0); + if (IS_ERR(ipcp)) + return PTR_ERR(ipcp); - if (cmd == IPC_SET) { - err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode); - if (err) - goto out_unlock; - } - if (current->euid != ipcp->cuid && - current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) { - err=-EPERM; - goto out_unlock; - } + sma = container_of(ipcp, struct sem_array, sem_perm); err = security_sem_semctl(sma, cmd); if (err) @@ -926,31 +918,24 @@ static int semctl_down(struct ipc_namespace *ns, int semid, int semnum, switch(cmd){ case IPC_RMID: - freeary(ns, sma); - err = 0; - break; + freeary(ns, ipcp); + goto out_up; case IPC_SET: - ipcp->uid = setbuf.uid; - ipcp->gid = setbuf.gid; - ipcp->mode = (ipcp->mode & ~S_IRWXUGO) - | (setbuf.mode & S_IRWXUGO); + ipc_update_perm(&semid64.sem_perm, ipcp); sma->sem_ctime = get_seconds(); - sem_unlock(sma); - err = 0; break; default: - sem_unlock(sma); err = -EINVAL; - break; } - return err; out_unlock: sem_unlock(sma); +out_up: + up_write(&sem_ids(ns).rw_mutex); return err; } -asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) +SYSCALL_DEFINE(semctl)(int semid, int semnum, int cmd, union semun arg) { int err = -EINVAL; int version; @@ -980,14 +965,19 @@ asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) return err; case IPC_RMID: case IPC_SET: - down_write(&sem_ids(ns).rw_mutex); - err = semctl_down(ns,semid,semnum,cmd,version,arg); - up_write(&sem_ids(ns).rw_mutex); + err = semctl_down(ns, semid, cmd, version, arg); return err; default: return -EINVAL; } } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_semctl(int semid, int semnum, int cmd, union semun arg) +{ + return SYSC_semctl((int) semid, (int) semnum, (int) cmd, arg); +} +SYSCALL_ALIAS(sys_semctl, SyS_semctl); +#endif /* If the task doesn't already have a undo_list, then allocate one * here. We guarantee there is only one thread using this undo list, @@ -1011,33 +1001,51 @@ static inline int get_undo_list(struct sem_undo_list **undo_listp) return -ENOMEM; spin_lock_init(&undo_list->lock); atomic_set(&undo_list->refcnt, 1); + INIT_LIST_HEAD(&undo_list->list_proc); + current->sysvsem.undo_list = undo_list; } *undo_listp = undo_list; return 0; } +static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid) +{ + struct sem_undo *un; + + list_for_each_entry_rcu(un, &ulp->list_proc, list_proc) { + if (un->semid == semid) + return un; + } + return NULL; +} + static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) { - struct sem_undo **last, *un; + struct sem_undo *un; - last = &ulp->proc_list; - un = *last; - while(un != NULL) { - if(un->semid==semid) - break; - if(un->semid==-1) { - *last=un->proc_next; - kfree(un); - } else { - last=&un->proc_next; - } - un=*last; + assert_spin_locked(&ulp->lock); + + un = __lookup_undo(ulp, semid); + if (un) { + list_del_rcu(&un->list_proc); + list_add_rcu(&un->list_proc, &ulp->list_proc); } return un; } -static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid) +/** + * find_alloc_undo - Lookup (and if not present create) undo array + * @ns: namespace + * @semid: semaphore array id + * + * The function looks up (and if not present creates) the undo structure. + * The size of the undo structure depends on the size of the semaphore + * array, thus the alloc path is not that straightforward. + * Lifetime-rules: sem_undo is rcu-protected, on success, the function + * performs a rcu_read_lock(). + */ +static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) { struct sem_array *sma; struct sem_undo_list *ulp; @@ -1049,63 +1057,68 @@ static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid) if (error) return ERR_PTR(error); + rcu_read_lock(); spin_lock(&ulp->lock); un = lookup_undo(ulp, semid); spin_unlock(&ulp->lock); if (likely(un!=NULL)) goto out; + rcu_read_unlock(); /* no undo structure around - allocate one. */ + /* step 1: figure out the size of the semaphore array */ sma = sem_lock_check(ns, semid); if (IS_ERR(sma)) return ERR_PTR(PTR_ERR(sma)); nsems = sma->sem_nsems; - ipc_rcu_getref(sma); - sem_unlock(sma); + sem_getref_and_unlock(sma); + /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); - sem_unlock(sma); + sem_putref(sma); return ERR_PTR(-ENOMEM); } - new->semadj = (short *) &new[1]; - new->semid = semid; - spin_lock(&ulp->lock); - un = lookup_undo(ulp, semid); - if (un) { - spin_unlock(&ulp->lock); - kfree(new); - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); - sem_unlock(sma); - goto out; - } - ipc_lock_by_ptr(&sma->sem_perm); - ipc_rcu_putref(sma); + /* step 3: Acquire the lock on semaphore array */ + sem_lock_and_putref(sma); if (sma->sem_perm.deleted) { sem_unlock(sma); - spin_unlock(&ulp->lock); kfree(new); un = ERR_PTR(-EIDRM); goto out; } - new->proc_next = ulp->proc_list; - ulp->proc_list = new; - new->id_next = sma->undo; - sma->undo = new; - sem_unlock(sma); + spin_lock(&ulp->lock); + + /* + * step 4: check for races: did someone else allocate the undo struct? + */ + un = lookup_undo(ulp, semid); + if (un) { + kfree(new); + goto success; + } + /* step 5: initialize & link new undo structure */ + new->semadj = (short *) &new[1]; + new->ulp = ulp; + new->semid = semid; + assert_spin_locked(&ulp->lock); + list_add_rcu(&new->list_proc, &ulp->list_proc); + assert_spin_locked(&sma->sem_perm.lock); + list_add(&new->list_id, &sma->list_id); un = new; + +success: spin_unlock(&ulp->lock); + rcu_read_lock(); + sem_unlock(sma); out: return un; } -asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops, - unsigned nsops, const struct timespec __user *timeout) +SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops, const struct timespec __user *, timeout) { int error = -EINVAL; struct sem_array *sma; @@ -1155,9 +1168,8 @@ asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops, alter = 1; } -retry_undos: if (undos) { - un = find_undo(ns, semid); + un = find_alloc_undo(ns, semid); if (IS_ERR(un)) { error = PTR_ERR(un); goto out_free; @@ -1167,19 +1179,37 @@ retry_undos: sma = sem_lock_check(ns, semid); if (IS_ERR(sma)) { + if (un) + rcu_read_unlock(); error = PTR_ERR(sma); goto out_free; } /* - * semid identifiers are not unique - find_undo may have + * semid identifiers are not unique - find_alloc_undo may have * allocated an undo structure, it was invalidated by an RMID - * and now a new array with received the same id. Check and retry. + * and now a new array with received the same id. Check and fail. + * This case can be detected checking un->semid. The existance of + * "un" itself is guaranteed by rcu. */ - if (un && un->semid == -1) { - sem_unlock(sma); - goto retry_undos; + error = -EIDRM; + if (un) { + if (un->semid == -1) { + rcu_read_unlock(); + goto out_unlock_free; + } else { + /* + * rcu lock can be released, "un" cannot disappear: + * - sem_lock is acquired, thus IPC_RMID is + * impossible. + * - exit_sem is impossible, it always operates on + * current (or a dead task). + */ + + rcu_read_unlock(); + } } + error = -EFBIG; if (max >= sma->sem_nsems) goto out_unlock_free; @@ -1195,7 +1225,8 @@ retry_undos: error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current)); if (error <= 0) { if (alter && error == 0) - update_queue (sma); + update_queue(sma, (nsops == 1) ? sops[0].sem_num : -1); + goto out_unlock_free; } @@ -1203,17 +1234,28 @@ retry_undos: * task into the pending queue and go to sleep. */ - queue.sma = sma; queue.sops = sops; queue.nsops = nsops; queue.undo = un; queue.pid = task_tgid_vnr(current); - queue.id = semid; queue.alter = alter; if (alter) - append_to_queue(sma ,&queue); + list_add_tail(&queue.list, &sma->sem_pending); else - prepend_to_queue(sma ,&queue); + list_add(&queue.list, &sma->sem_pending); + + if (nsops == 1) { + struct sem *curr; + curr = &sma->sem_base[sops->sem_num]; + + if (alter) + list_add_tail(&queue.simple_list, &curr->sem_pending); + else + list_add(&queue.simple_list, &curr->sem_pending); + } else { + INIT_LIST_HEAD(&queue.simple_list); + sma->complex_count++; + } queue.status = -EINTR; queue.sleeper = current; @@ -1239,7 +1281,6 @@ retry_undos: sma = sem_lock(ns, semid); if (IS_ERR(sma)) { - BUG_ON(queue.prev != NULL); error = -EIDRM; goto out_free; } @@ -1257,8 +1298,7 @@ retry_undos: */ if (timeout && jiffies_left == 0) error = -EAGAIN; - remove_from_queue(sma,&queue); - goto out_unlock_free; + unlink_queue(sma, &queue); out_unlock_free: sem_unlock(sma); @@ -1268,7 +1308,8 @@ out_free: return error; } -asmlinkage long sys_semop (int semid, struct sembuf __user *tsops, unsigned nsops) +SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops) { return sys_semtimedop(semid, tsops, nsops, NULL); } @@ -1308,55 +1349,62 @@ int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) */ void exit_sem(struct task_struct *tsk) { - struct sem_undo_list *undo_list; - struct sem_undo *u, **up; - struct ipc_namespace *ns; + struct sem_undo_list *ulp; - undo_list = tsk->sysvsem.undo_list; - if (!undo_list) + ulp = tsk->sysvsem.undo_list; + if (!ulp) return; + tsk->sysvsem.undo_list = NULL; - if (!atomic_dec_and_test(&undo_list->refcnt)) + if (!atomic_dec_and_test(&ulp->refcnt)) return; - ns = tsk->nsproxy->ipc_ns; - /* There's no need to hold the semundo list lock, as current - * is the last task exiting for this undo list. - */ - for (up = &undo_list->proc_list; (u = *up); *up = u->proc_next, kfree(u)) { + for (;;) { struct sem_array *sma; - int nsems, i; - struct sem_undo *un, **unp; + struct sem_undo *un; int semid; - - semid = u->semid; + int i; - if(semid == -1) - continue; - sma = sem_lock(ns, semid); + rcu_read_lock(); + un = list_entry_rcu(ulp->list_proc.next, + struct sem_undo, list_proc); + if (&un->list_proc == &ulp->list_proc) + semid = -1; + else + semid = un->semid; + rcu_read_unlock(); + + if (semid == -1) + break; + + sma = sem_lock_check(tsk->nsproxy->ipc_ns, un->semid); + + /* exit_sem raced with IPC_RMID, nothing to do */ if (IS_ERR(sma)) continue; - if (u->semid == -1) - goto next_entry; + un = __lookup_undo(ulp, semid); + if (un == NULL) { + /* exit_sem raced with IPC_RMID+semget() that created + * exactly the same semid. Nothing to do. + */ + sem_unlock(sma); + continue; + } + + /* remove un from the linked lists */ + assert_spin_locked(&sma->sem_perm.lock); + list_del(&un->list_id); - BUG_ON(sem_checkid(sma, u->semid)); + spin_lock(&ulp->lock); + list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); - /* remove u from the sma->undo list */ - for (unp = &sma->undo; (un = *unp); unp = &un->id_next) { - if (u == un) - goto found; - } - printk ("exit_sem undo list error id=%d\n", u->semid); - goto next_entry; -found: - *unp = un->id_next; - /* perform adjustments registered in u */ - nsems = sma->sem_nsems; - for (i = 0; i < nsems; i++) { + /* perform adjustments registered in un */ + for (i = 0; i < sma->sem_nsems; i++) { struct sem * semaphore = &sma->sem_base[i]; - if (u->semadj[i]) { - semaphore->semval += u->semadj[i]; + if (un->semadj[i]) { + semaphore->semval += un->semadj[i]; /* * Range checks of the new semaphore value, * not defined by sus: @@ -1379,11 +1427,12 @@ found: } sma->sem_otime = get_seconds(); /* maybe some queued-up processes were waiting for this */ - update_queue(sma); -next_entry: + update_queue(sma, -1); sem_unlock(sma); + + call_rcu(&un->rcu, free_un); } - kfree(undo_list); + kfree(ulp); } #ifdef CONFIG_PROC_FS @@ -1392,7 +1441,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) struct sem_array *sma = it; return seq_printf(s, - "%10d %10d %4o %10lu %5u %5u %5u %5u %10lu %10lu\n", + "%10d %10d %4o %10u %5u %5u %5u %5u %10lu %10lu\n", sma->sem_perm.key, sma->sem_perm.id, sma->sem_perm.mode,