diff options
Diffstat (limited to 'ipc/sem.c')
| -rw-r--r-- | ipc/sem.c | 975 |
1 files changed, 627 insertions, 348 deletions
diff --git a/ipc/sem.c b/ipc/sem.c index 70480a3aa69..454f6c6020a 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -47,8 +47,7 @@ * Thus: Perfect SMP scaling between independent semaphore arrays. * If multiple semaphores in one array are used, then cache line * trashing on the semaphore array spinlock will limit the scaling. - * - semncnt and semzcnt are calculated on demand in count_semncnt() and - * count_semzcnt() + * - semncnt and semzcnt are calculated on demand in count_semcnt() * - the task that performs a successful semop() scans the list of all * sleeping tasks and completes any pending operations that can be fulfilled. * Semaphores are actively given to waiting tasks (necessary for FIFO). @@ -87,7 +86,7 @@ #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "util.h" /* One semaphore structure for each semaphore in the system. */ @@ -95,8 +94,12 @@ struct sem { int semval; /* current value */ int sempid; /* pid of last operation */ spinlock_t lock; /* spinlock for fine-grained semtimedop */ - struct list_head sem_pending; /* pending single-sop operations */ -}; + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; /* One queue for each sleeping process in the system. */ struct sem_queue { @@ -106,6 +109,7 @@ struct sem_queue { int pid; /* process id of requesting process */ int status; /* completion status of operation */ struct sembuf *sops; /* array of pending operations */ + struct sembuf *blocking; /* the operation that blocked */ int nsops; /* number of operations */ int alter; /* does *sops alter the array? */ }; @@ -150,12 +154,15 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); #define SEMOPM_FAST 64 /* ~ 372 bytes on stack */ /* - * linked list protection: + * Locking: * sem_undo.id_next, - * sem_array.sem_pending{,last}, - * sem_array.sem_undo: sem_lock() for read/write + * sem_array.complex_count, + * sem_array.pending{_alter,_cont}, + * sem_array.sem_undo: global sem_lock() for read/write * sem_undo.proc_next: only "current" is allowed to read/write that field. - * + * + * sem_array.sem_base[i].pending_{const,alter}: + * global or semaphore sem_lock() for read/write */ #define sc_semmsl sem_ctls[0] @@ -181,7 +188,7 @@ void sem_exit_ns(struct ipc_namespace *ns) } #endif -void __init sem_init (void) +void __init sem_init(void) { sem_init_ns(&init_ipc_ns); ipc_init_proc_interface("sysvipc/sem", @@ -189,77 +196,176 @@ void __init sem_init (void) IPC_SEM_IDS, sysvipc_sem_proc_show); } +/** + * unmerge_queues - unmerge queues, if possible. + * @sma: semaphore array + * + * The function unmerges the wait queues if complex_count is 0. + * It must be called prior to dropping the global semaphore array lock. + */ +static void unmerge_queues(struct sem_array *sma) +{ + struct sem_queue *q, *tq; + + /* complex operations still around? */ + if (sma->complex_count) + return; + /* + * We will switch back to simple mode. + * Move all pending operation back into the per-semaphore + * queues. + */ + list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { + struct sem *curr; + curr = &sma->sem_base[q->sops[0].sem_num]; + + list_add_tail(&q->list, &curr->pending_alter); + } + INIT_LIST_HEAD(&sma->pending_alter); +} + +/** + * merge_queues - merge single semop queues into global queue + * @sma: semaphore array + * + * This function merges all per-semaphore queues into the global queue. + * It is necessary to achieve FIFO ordering for the pending single-sop + * operations when a multi-semop operation must sleep. + * Only the alter operations must be moved, the const operations can stay. + */ +static void merge_queues(struct sem_array *sma) +{ + int i; + for (i = 0; i < sma->sem_nsems; i++) { + struct sem *sem = sma->sem_base + i; + + list_splice_init(&sem->pending_alter, &sma->pending_alter); + } +} + +static void sem_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct sem_array *sma = ipc_rcu_to_struct(p); + + security_sem_free(sma); + ipc_rcu_free(head); +} + +/* + * Wait until all currently ongoing simple ops have completed. + * Caller must own sem_perm.lock. + * New simple ops cannot start, because simple ops first check + * that sem_perm.lock is free. + * that a) sem_perm.lock is free and b) complex_count is 0. + */ +static void sem_wait_array(struct sem_array *sma) +{ + int i; + struct sem *sem; + + if (sma->complex_count) { + /* The thread that increased sma->complex_count waited on + * all sem->lock locks. Thus we don't need to wait again. + */ + return; + } + + for (i = 0; i < sma->sem_nsems; i++) { + sem = sma->sem_base + i; + spin_unlock_wait(&sem->lock); + } +} + /* * If the request contains only one semaphore operation, and there are * no complex transactions pending, lock only the semaphore involved. * Otherwise, lock the entire semaphore array, since we either have * multiple semaphores in our own semops, or we need to look at * semaphores from other pending complex operations. - * - * Carefully guard against sma->complex_count changing between zero - * and non-zero while we are spinning for the lock. The value of - * sma->complex_count cannot change while we are holding the lock, - * so sem_unlock should be fine. - * - * The global lock path checks that all the local locks have been released, - * checking each local lock once. This means that the local lock paths - * cannot start their critical sections while the global lock is held. */ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, int nsops) { - int locknum; - again: - if (nsops == 1 && !sma->complex_count) { - struct sem *sem = sma->sem_base + sops->sem_num; + struct sem *sem; - /* Lock just the semaphore we are interested in. */ - spin_lock(&sem->lock); + if (nsops != 1) { + /* Complex operation - acquire a full lock */ + ipc_lock_object(&sma->sem_perm); - /* - * If sma->complex_count was set while we were spinning, - * we may need to look at things we did not lock here. + /* And wait until all simple ops that are processed + * right now have dropped their locks. */ - if (unlikely(sma->complex_count)) { - spin_unlock(&sem->lock); - goto lock_array; - } + sem_wait_array(sma); + return -1; + } + /* + * Only one semaphore affected - try to optimize locking. + * The rules are: + * - optimized locking is possible if no complex operation + * is either enqueued or processed right now. + * - The test for enqueued complex ops is simple: + * sma->complex_count != 0 + * - Testing for complex ops that are processed right now is + * a bit more difficult. Complex ops acquire the full lock + * and first wait that the running simple ops have completed. + * (see above) + * Thus: If we own a simple lock and the global lock is free + * and complex_count is now 0, then it will stay 0 and + * thus just locking sem->lock is sufficient. + */ + sem = sma->sem_base + sops->sem_num; + + if (sma->complex_count == 0) { /* - * Another process is holding the global lock on the - * sem_array; we cannot enter our critical section, - * but have to wait for the global lock to be released. + * It appears that no complex operation is around. + * Acquire the per-semaphore lock. */ - if (unlikely(spin_is_locked(&sma->sem_perm.lock))) { - spin_unlock(&sem->lock); - spin_unlock_wait(&sma->sem_perm.lock); - goto again; + spin_lock(&sem->lock); + + /* Then check that the global lock is free */ + if (!spin_is_locked(&sma->sem_perm.lock)) { + /* spin_is_locked() is not a memory barrier */ + smp_mb(); + + /* Now repeat the test of complex_count: + * It can't change anymore until we drop sem->lock. + * Thus: if is now 0, then it will stay 0. + */ + if (sma->complex_count == 0) { + /* fast path successful! */ + return sops->sem_num; + } } + spin_unlock(&sem->lock); + } + + /* slow path: acquire the full lock */ + ipc_lock_object(&sma->sem_perm); - locknum = sops->sem_num; + if (sma->complex_count == 0) { + /* False alarm: + * There is no complex operation, thus we can switch + * back to the fast path. + */ + spin_lock(&sem->lock); + ipc_unlock_object(&sma->sem_perm); + return sops->sem_num; } else { - int i; - /* - * Lock the semaphore array, and wait for all of the - * individual semaphore locks to go away. The code - * above ensures no new single-lock holders will enter - * their critical section while the array lock is held. + /* Not a false alarm, thus complete the sequence for a + * full lock. */ - lock_array: - spin_lock(&sma->sem_perm.lock); - for (i = 0; i < sma->sem_nsems; i++) { - struct sem *sem = sma->sem_base + i; - spin_unlock_wait(&sem->lock); - } - locknum = -1; + sem_wait_array(sma); + return -1; } - return locknum; } static inline void sem_unlock(struct sem_array *sma, int locknum) { if (locknum == -1) { - spin_unlock(&sma->sem_perm.lock); + unmerge_queues(sma); + ipc_unlock_object(&sma->sem_perm); } else { struct sem *sem = sma->sem_base + locknum; spin_unlock(&sem->lock); @@ -267,7 +373,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum) } /* - * sem_lock_(check_) routines are called in the paths where the rw_mutex + * sem_lock_(check_) routines are called in the paths where the rwsem * is not held. * * The caller holds the RCU read lock. @@ -288,7 +394,7 @@ static inline struct sem_array *sem_obtain_lock(struct ipc_namespace *ns, /* ipc_rmid() may have already freed the ID while sem_lock * was spinning: verify that the structure is still valid */ - if (!ipcp->deleted) + if (ipc_valid_object(ipcp)) return container_of(ipcp, struct sem_array, sem_perm); sem_unlock(sma, *locknum); @@ -319,12 +425,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma); -} - -static inline void sem_putref(struct sem_array *sma) -{ - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -337,18 +438,18 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) * Without the check/retry algorithm a lockless wakeup is possible: * - queue.status is initialized to -EINTR before blocking. * - wakeup is performed by - * * unlinking the queue entry from sma->sem_pending + * * unlinking the queue entry from the pending list * * setting queue.status to IN_WAKEUP * This is the notification for the blocked thread that a * result value is imminent. * * call wake_up_process * * set queue.status to the final value. * - the previously blocked thread checks queue.status: - * * if it's IN_WAKEUP, then it must wait until the value changes - * * if it's not -EINTR, then the operation was completed by - * update_queue. semtimedop can return queue.status without - * performing any operation on the sem array. - * * otherwise it must acquire the spinlock and check what's up. + * * if it's IN_WAKEUP, then it must wait until the value changes + * * if it's not -EINTR, then the operation was completed by + * update_queue. semtimedop can return queue.status without + * performing any operation on the sem array. + * * otherwise it must acquire the spinlock and check what's up. * * The two-stage algorithm is necessary to protect against the following * races: @@ -371,9 +472,8 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) * @ns: namespace * @params: ptr to the structure that contains key, semflg and nsems * - * Called with sem_ids.rw_mutex held (as a writer) + * Called with sem_ids.rwsem held (as a writer) */ - static int newary(struct ipc_namespace *ns, struct ipc_params *params) { int id; @@ -390,12 +490,12 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; - size = sizeof (*sma) + nsems * sizeof (struct sem); + size = sizeof(*sma) + nsems * sizeof(struct sem); sma = ipc_rcu_alloc(size); - if (!sma) { + if (!sma) return -ENOMEM; - } - memset (sma, 0, size); + + memset(sma, 0, size); sma->sem_perm.mode = (semflg & S_IRWXUGO); sma->sem_perm.key = key; @@ -403,14 +503,13 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return retval; } id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if (id < 0) { - security_sem_free(sma); - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, sem_rcu_free); return id; } ns->used_sems += nsems; @@ -418,12 +517,14 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_base = (struct sem *) &sma[1]; for (i = 0; i < nsems; i++) { - INIT_LIST_HEAD(&sma->sem_base[i].sem_pending); + INIT_LIST_HEAD(&sma->sem_base[i].pending_alter); + INIT_LIST_HEAD(&sma->sem_base[i].pending_const); spin_lock_init(&sma->sem_base[i].lock); } sma->complex_count = 0; - INIT_LIST_HEAD(&sma->sem_pending); + INIT_LIST_HEAD(&sma->pending_alter); + INIT_LIST_HEAD(&sma->pending_const); INIT_LIST_HEAD(&sma->list_id); sma->sem_nsems = nsems; sma->sem_ctime = get_seconds(); @@ -435,7 +536,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) /* - * Called with sem_ids.rw_mutex and ipcp locked. + * Called with sem_ids.rwsem and ipcp locked. */ static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg) { @@ -446,7 +547,7 @@ static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg) } /* - * Called with sem_ids.rw_mutex and ipcp locked. + * Called with sem_ids.rwsem and ipcp locked. */ static inline int sem_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) @@ -463,7 +564,11 @@ static inline int sem_more_checks(struct kern_ipc_perm *ipcp, SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) { struct ipc_namespace *ns; - struct ipc_ops sem_ops; + static const struct ipc_ops sem_ops = { + .getnew = newary, + .associate = sem_security, + .more_checks = sem_more_checks, + }; struct ipc_params sem_params; ns = current->nsproxy->ipc_ns; @@ -471,10 +576,6 @@ SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) if (nsems < 0 || nsems > ns->sc_semmsl) return -EINVAL; - sem_ops.getnew = newary; - sem_ops.associate = sem_security; - sem_ops.more_checks = sem_more_checks; - sem_params.key = key; sem_params.flg = semflg; sem_params.u.nsems = nsems; @@ -482,23 +583,32 @@ SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params); } -/* - * 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. +/** + * perform_atomic_semop - Perform (if possible) a semaphore operation + * @sma: semaphore array + * @q: struct sem_queue that describes the operation + * + * Returns 0 if the operation was possible. + * Returns 1 if the operation is impossible, the caller must sleep. + * Negative values are error codes. */ - -static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops, - int nsops, struct sem_undo *un, int pid) +static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) { - int result, sem_op; + int result, sem_op, nsops, pid; struct sembuf *sop; - struct sem * curr; + struct sem *curr; + struct sembuf *sops; + struct sem_undo *un; + + sops = q->sops; + nsops = q->nsops; + un = q->undo; for (sop = sops; sop < sops + nsops; sop++) { curr = sma->sem_base + sop->sem_num; sem_op = sop->sem_op; result = curr->semval; - + if (!sem_op && result) goto would_block; @@ -507,25 +617,25 @@ static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops, goto would_block; if (result > SEMVMX) goto out_of_range; + if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; - /* - * Exceeding the undo range is an error. - */ + /* Exceeding the undo range is an error. */ if (undo < (-SEMAEM - 1) || undo > SEMAEM) goto out_of_range; + un->semadj[sop->sem_num] = undo; } + curr->semval = result; } sop--; + pid = q->pid; while (sop >= sops) { sma->sem_base[sop->sem_num].sempid = pid; - if (sop->sem_flg & SEM_UNDO) - un->semadj[sop->sem_num] -= sop->sem_op; sop--; } - + return 0; out_of_range: @@ -533,6 +643,8 @@ out_of_range: goto undo; would_block: + q->blocking = sop; + if (sop->sem_flg & IPC_NOWAIT) result = -EAGAIN; else @@ -541,7 +653,10 @@ would_block: undo: sop--; while (sop >= sops) { - sma->sem_base[sop->sem_num].semval -= sop->sem_op; + sem_op = sop->sem_op; + sma->sem_base[sop->sem_num].semval -= sem_op; + if (sop->sem_flg & SEM_UNDO) + un->semadj[sop->sem_num] += sem_op; sop--; } @@ -571,7 +686,7 @@ static void wake_up_sem_queue_prepare(struct list_head *pt, } /** - * wake_up_sem_queue_do(pt) - do the actual wake-up + * wake_up_sem_queue_do - do the actual wake-up * @pt: list of tasks to be woken up * * Do the actual wake-up. @@ -609,65 +724,135 @@ static void unlink_queue(struct sem_array *sma, struct sem_queue *q) * update_queue is O(N^2) when it restarts scanning the whole queue of * waiting operations. Therefore this function checks if the restart is * really necessary. It is called after a previously waiting operation - * was completed. + * modified the array. + * Note that wait-for-zero operations are handled without restart. */ static int check_restart(struct sem_array *sma, struct sem_queue *q) { - struct sem *curr; - struct sem_queue *h; - - /* if the operation didn't modify the array, then no restart */ - if (q->alter == 0) - return 0; - - /* pending complex operations are too difficult to analyse */ - if (sma->complex_count) + /* pending complex alter operations are too difficult to analyse */ + if (!list_empty(&sma->pending_alter)) return 1; /* we were a sleeping complex operation. Too difficult */ if (q->nsops > 1) return 1; - curr = sma->sem_base + q->sops[0].sem_num; + /* It is impossible that someone waits for the new value: + * - complex operations always restart. + * - wait-for-zero are handled seperately. + * - q is a previously sleeping simple operation that + * altered the array. It must be a decrement, because + * simple increments never sleep. + * - If there are older (higher priority) decrements + * in the queue, then they have observed the original + * semval value and couldn't proceed. The operation + * decremented to value - thus they won't proceed either. + */ + return 0; +} - /* No-one waits on this queue */ - if (list_empty(&curr->sem_pending)) - return 0; +/** + * wake_const_ops - wake up non-alter tasks + * @sma: semaphore array. + * @semnum: semaphore that was modified. + * @pt: list head for the tasks that must be woken up. + * + * wake_const_ops must be called after a semaphore in a semaphore array + * was set to 0. If complex const operations are pending, wake_const_ops must + * be called with semnum = -1, as well as with the number of each modified + * semaphore. + * The tasks that must be woken up are added to @pt. The return code + * is stored in q->pid. + * The function returns 1 if at least one operation was completed successfully. + */ +static int wake_const_ops(struct sem_array *sma, int semnum, + struct list_head *pt) +{ + struct sem_queue *q; + struct list_head *walk; + struct list_head *pending_list; + int semop_completed = 0; + + if (semnum == -1) + pending_list = &sma->pending_const; + else + pending_list = &sma->sem_base[semnum].pending_const; + + walk = pending_list->next; + while (walk != pending_list) { + int error; - /* the new semaphore value */ - if (curr->semval) { - /* It is impossible that someone waits for the new value: - * - q is a previously sleeping simple operation that - * altered the array. It must be a decrement, because - * simple increments never sleep. - * - The value is not 0, thus wait-for-zero won't proceed. - * - If there are older (higher priority) decrements - * in the queue, then they have observed the original - * semval value and couldn't proceed. The operation - * decremented to value - thus they won't proceed either. + q = container_of(walk, struct sem_queue, list); + walk = walk->next; + + error = perform_atomic_semop(sma, q); + + if (error <= 0) { + /* operation completed, remove from queue & wakeup */ + + unlink_queue(sma, q); + + wake_up_sem_queue_prepare(pt, q, error); + if (error == 0) + semop_completed = 1; + } + } + return semop_completed; +} + +/** + * do_smart_wakeup_zero - wakeup all wait for zero tasks + * @sma: semaphore array + * @sops: operations that were performed + * @nsops: number of operations + * @pt: list head of the tasks that must be woken up. + * + * Checks all required queue for wait-for-zero operations, based + * on the actual changes that were performed on the semaphore array. + * The function returns 1 if at least one operation was completed successfully. + */ +static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, + int nsops, struct list_head *pt) +{ + int i; + int semop_completed = 0; + int got_zero = 0; + + /* first: the per-semaphore queues, if known */ + if (sops) { + for (i = 0; i < nsops; i++) { + int num = sops[i].sem_num; + + if (sma->sem_base[num].semval == 0) { + got_zero = 1; + semop_completed |= wake_const_ops(sma, num, pt); + } + } + } else { + /* + * No sops means modified semaphores not known. + * Assume all were changed. */ - BUG_ON(q->sops[0].sem_op >= 0); - return 0; + for (i = 0; i < sma->sem_nsems; i++) { + if (sma->sem_base[i].semval == 0) { + got_zero = 1; + semop_completed |= wake_const_ops(sma, i, pt); + } + } } /* - * semval is 0. Check if there are wait-for-zero semops. - * They must be the first entries in the per-semaphore queue + * If one of the modified semaphores got 0, + * then check the global queue, too. */ - h = list_first_entry(&curr->sem_pending, struct sem_queue, list); - BUG_ON(h->nsops != 1); - BUG_ON(h->sops[0].sem_num != q->sops[0].sem_num); - - /* Yes, there is a wait-for-zero semop. Restart */ - if (h->sops[0].sem_op == 0) - return 1; + if (got_zero) + semop_completed |= wake_const_ops(sma, -1, pt); - /* Again - no-one is waiting for the new value. */ - return 0; + return semop_completed; } /** - * update_queue(sma, semnum): Look for tasks that can be completed. + * update_queue - look for tasks that can be completed. * @sma: semaphore array. * @semnum: semaphore that was modified. * @pt: list head for the tasks that must be woken up. @@ -678,6 +863,8 @@ static int check_restart(struct sem_array *sma, struct sem_queue *q) * semaphore. * The tasks that must be woken up are added to @pt. The return code * is stored in q->pid. + * The function internally checks if const operations can now succeed. + * * The function return 1 if at least one semop was completed successfully. */ static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt) @@ -688,9 +875,9 @@ static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt) int semop_completed = 0; if (semnum == -1) - pending_list = &sma->sem_pending; + pending_list = &sma->pending_alter; else - pending_list = &sma->sem_base[semnum].sem_pending; + pending_list = &sma->sem_base[semnum].pending_alter; again: walk = pending_list->next; @@ -702,17 +889,15 @@ again: /* 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 + * necessary to scan further: 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) + if (semnum != -1 && sma->sem_base[semnum].semval == 0) break; - error = try_atomic_semop(sma, q->sops, q->nsops, - q->undo, q->pid); + error = perform_atomic_semop(sma, q); /* Does q->sleeper still need to sleep? */ if (error > 0) @@ -724,6 +909,7 @@ again: restart = 0; } else { semop_completed = 1; + do_smart_wakeup_zero(sma, q->sops, q->nsops, pt); restart = check_restart(sma, q); } @@ -735,15 +921,33 @@ again: } /** - * do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue + * set_semotime - set sem_otime + * @sma: semaphore array + * @sops: operations that modified the array, may be NULL + * + * sem_otime is replicated to avoid cache line trashing. + * This function sets one instance to the current time. + */ +static void set_semotime(struct sem_array *sma, struct sembuf *sops) +{ + if (sops == NULL) { + sma->sem_base[0].sem_otime = get_seconds(); + } else { + sma->sem_base[sops[0].sem_num].sem_otime = + get_seconds(); + } +} + +/** + * do_smart_update - optimized update_queue * @sma: semaphore array * @sops: operations that were performed * @nsops: number of operations * @otime: force setting otime * @pt: list head of the tasks that must be woken up. * - * do_smart_update() does the required called to update_queue, based on the - * actual changes that were performed on the semaphore array. + * do_smart_update() does the required calls to update_queue and wakeup_zero, + * based on the actual changes that were performed on the semaphore array. * Note that the function does not do the actual wake-up: the caller is * responsible for calling wake_up_sem_queue_do(@pt). * It is safe to perform this call after dropping all locks. @@ -752,115 +956,114 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop int otime, struct list_head *pt) { int i; - int progress; - - progress = 1; -retry_global: - if (sma->complex_count) { - if (update_queue(sma, -1, pt)) { - progress = 1; - otime = 1; - sops = NULL; - } - } - if (!progress) - goto done; - if (!sops) { - /* No semops; something special is going on. */ - for (i = 0; i < sma->sem_nsems; i++) { - if (update_queue(sma, i, pt)) { - otime = 1; - progress = 1; - } - } - goto done_checkretry; - } + otime |= do_smart_wakeup_zero(sma, sops, nsops, pt); - /* Check the semaphores that were modified. */ - for (i = 0; i < nsops; i++) { - if (sops[i].sem_op > 0 || - (sops[i].sem_op < 0 && - sma->sem_base[sops[i].sem_num].semval == 0)) - if (update_queue(sma, sops[i].sem_num, pt)) { - otime = 1; - progress = 1; + if (!list_empty(&sma->pending_alter)) { + /* semaphore array uses the global queue - just process it. */ + otime |= update_queue(sma, -1, pt); + } else { + if (!sops) { + /* + * No sops, thus the modified semaphores are not + * known. Check all. + */ + for (i = 0; i < sma->sem_nsems; i++) + otime |= update_queue(sma, i, pt); + } else { + /* + * Check the semaphores that were increased: + * - No complex ops, thus all sleeping ops are + * decrease. + * - if we decreased the value, then any sleeping + * semaphore ops wont be able to run: If the + * previous value was too small, then the new + * value will be too small, too. + */ + for (i = 0; i < nsops; i++) { + if (sops[i].sem_op > 0) { + otime |= update_queue(sma, + sops[i].sem_num, pt); + } } + } } -done_checkretry: - if (progress) { - progress = 0; - goto retry_global; - } -done: if (otime) - sma->sem_otime = get_seconds(); + set_semotime(sma, sops); } +/* + * check_qop: Test if a queued operation sleeps on the semaphore semnum + */ +static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q, + bool count_zero) +{ + struct sembuf *sop = q->blocking; + + /* + * Linux always (since 0.99.10) reported a task as sleeping on all + * semaphores. This violates SUS, therefore it was changed to the + * standard compliant behavior. + * Give the administrators a chance to notice that an application + * might misbehave because it relies on the Linux behavior. + */ + pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.\n" + "The task %s (%d) triggered the difference, watch for misbehavior.\n", + current->comm, task_pid_nr(current)); + + if (sop->sem_num != semnum) + return 0; + + if (count_zero && sop->sem_op == 0) + return 1; + if (!count_zero && sop->sem_op < 0) + return 1; + + return 0; +} /* The following counts are associated to each semaphore: * semncnt number of tasks waiting on semval being nonzero * semzcnt number of tasks waiting on semval being zero - * This model assumes that a task waits on exactly one semaphore. - * Since semaphore operations are to be performed atomically, tasks actually - * wait on a whole sequence of semaphores simultaneously. - * The counts we return here are a rough approximation, but still - * warrant that semncnt+semzcnt>0 if the task is on the pending queue. + * + * Per definition, a task waits only on the semaphore of the first semop + * that cannot proceed, even if additional operation would block, too. */ -static int count_semncnt (struct sem_array * sma, ushort semnum) +static int count_semcnt(struct sem_array *sma, ushort semnum, + bool count_zero) { - int semncnt; - struct sem_queue * q; + struct list_head *l; + struct sem_queue *q; + int semcnt; - semncnt = 0; - list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) { - struct sembuf * sops = q->sops; - BUG_ON(sops->sem_num != semnum); - if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT)) - semncnt++; - } + semcnt = 0; + /* First: check the simple operations. They are easy to evaluate */ + if (count_zero) + l = &sma->sem_base[semnum].pending_const; + else + l = &sma->sem_base[semnum].pending_alter; - list_for_each_entry(q, &sma->sem_pending, list) { - struct sembuf * sops = q->sops; - int nsops = q->nsops; - int i; - for (i = 0; i < nsops; i++) - if (sops[i].sem_num == semnum - && (sops[i].sem_op < 0) - && !(sops[i].sem_flg & IPC_NOWAIT)) - semncnt++; + list_for_each_entry(q, l, list) { + /* all task on a per-semaphore list sleep on exactly + * that semaphore + */ + semcnt++; } - return semncnt; -} - -static int count_semzcnt (struct sem_array * sma, ushort semnum) -{ - int semzcnt; - struct sem_queue * q; - semzcnt = 0; - list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) { - struct sembuf * sops = q->sops; - BUG_ON(sops->sem_num != semnum); - if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT)) - semzcnt++; + /* Then: check the complex operations. */ + list_for_each_entry(q, &sma->pending_alter, list) { + semcnt += check_qop(sma, semnum, q, count_zero); } - - list_for_each_entry(q, &sma->sem_pending, list) { - struct sembuf * sops = q->sops; - int nsops = q->nsops; - int i; - for (i = 0; i < nsops; i++) - if (sops[i].sem_num == semnum - && (sops[i].sem_op == 0) - && !(sops[i].sem_flg & IPC_NOWAIT)) - semzcnt++; + if (count_zero) { + list_for_each_entry(q, &sma->pending_const, list) { + semcnt += check_qop(sma, semnum, q, count_zero); + } } - return semzcnt; + return semcnt; } -/* 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 +/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked + * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem * remains locked on exit. */ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) @@ -872,7 +1075,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) int i; /* Free the existing undo structures for this semaphore set. */ - assert_spin_locked(&sma->sem_perm.lock); + ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry_safe(un, tu, &sma->list_id, list_id) { list_del(&un->list_id); spin_lock(&un->ulp->lock); @@ -884,13 +1087,22 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) /* Wake up all pending processes and let them fail with EIDRM. */ INIT_LIST_HEAD(&tasks); - list_for_each_entry_safe(q, tq, &sma->sem_pending, list) { + list_for_each_entry_safe(q, tq, &sma->pending_const, list) { + unlink_queue(sma, q); + wake_up_sem_queue_prepare(&tasks, q, -EIDRM); + } + + list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(&tasks, q, -EIDRM); } for (i = 0; i < sma->sem_nsems; i++) { struct sem *sem = sma->sem_base + i; - list_for_each_entry_safe(q, tq, &sem->sem_pending, list) { + list_for_each_entry_safe(q, tq, &sem->pending_const, list) { + unlink_queue(sma, q); + wake_up_sem_queue_prepare(&tasks, q, -EIDRM); + } + list_for_each_entry_safe(q, tq, &sem->pending_alter, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(&tasks, q, -EIDRM); } @@ -903,13 +1115,12 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_sem_queue_do(&tasks); ns->used_sems -= sma->sem_nsems; - security_sem_free(sma); - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) { - switch(version) { + switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: @@ -931,13 +1142,28 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, } } +static time_t get_semotime(struct sem_array *sma) +{ + int i; + time_t res; + + res = sma->sem_base[0].sem_otime; + for (i = 1; i < sma->sem_nsems; i++) { + time_t to = sma->sem_base[i].sem_otime; + + if (to > res) + res = to; + } + return res; +} + static int semctl_nolock(struct ipc_namespace *ns, int semid, int cmd, int version, void __user *p) { int err; struct sem_array *sma; - switch(cmd) { + switch (cmd) { case IPC_INFO: case SEM_INFO: { @@ -947,8 +1173,8 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid, err = security_sem_semctl(NULL, cmd); if (err) return err; - - memset(&seminfo,0,sizeof(seminfo)); + + memset(&seminfo, 0, sizeof(seminfo)); seminfo.semmni = ns->sc_semmni; seminfo.semmns = ns->sc_semmns; seminfo.semmsl = ns->sc_semmsl; @@ -957,7 +1183,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid, seminfo.semmnu = SEMMNU; seminfo.semmap = SEMMAP; seminfo.semume = SEMUME; - down_read(&sem_ids(ns).rw_mutex); + down_read(&sem_ids(ns).rwsem); if (cmd == SEM_INFO) { seminfo.semusz = sem_ids(ns).in_use; seminfo.semaem = ns->used_sems; @@ -966,10 +1192,10 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid, seminfo.semaem = SEMAEM; } max_id = ipc_get_maxid(&sem_ids(ns)); - up_read(&sem_ids(ns).rw_mutex); - if (copy_to_user(p, &seminfo, sizeof(struct seminfo))) + up_read(&sem_ids(ns).rwsem); + if (copy_to_user(p, &seminfo, sizeof(struct seminfo))) return -EFAULT; - return (max_id < 0) ? 0: max_id; + return (max_id < 0) ? 0 : max_id; } case IPC_STAT: case SEM_STAT: @@ -1004,9 +1230,9 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid, goto out_unlock; kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm); - tbuf.sem_otime = sma->sem_otime; - tbuf.sem_ctime = sma->sem_ctime; - tbuf.sem_nsems = sma->sem_nsems; + tbuf.sem_otime = get_semotime(sma); + tbuf.sem_ctime = sma->sem_ctime; + tbuf.sem_nsems = sma->sem_nsems; rcu_read_unlock(); if (copy_semid_to_user(p, &tbuf, version)) return -EFAULT; @@ -1025,7 +1251,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, { struct sem_undo *un; struct sem_array *sma; - struct sem* curr; + struct sem *curr; int err; struct list_head tasks; int val; @@ -1068,9 +1294,15 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, sem_lock(sma, NULL, -1); + if (!ipc_valid_object(&sma->sem_perm)) { + sem_unlock(sma, -1); + rcu_read_unlock(); + return -EIDRM; + } + curr = &sma->sem_base[semnum]; - assert_spin_locked(&sma->sem_perm.lock); + ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) un->semadj[semnum] = 0; @@ -1089,10 +1321,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int cmd, void __user *p) { struct sem_array *sma; - struct sem* curr; + struct sem *curr; int err, nsems; ushort fast_sem_io[SEMMSL_FAST]; - ushort* sem_io = fast_sem_io; + ushort *sem_io = fast_sem_io; struct list_head tasks; INIT_LIST_HEAD(&tasks); @@ -1122,28 +1354,28 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int i; sem_lock(sma, NULL, -1); - if(nsems > SEMMSL_FAST) { + if (!ipc_valid_object(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } + if (nsems > SEMMSL_FAST) { if (!ipc_rcu_getref(sma)) { - sem_unlock(sma, -1); - rcu_read_unlock(); err = -EIDRM; - goto out_free; + goto out_unlock; } sem_unlock(sma, -1); rcu_read_unlock(); sem_io = ipc_alloc(sizeof(ushort)*nsems); - if(sem_io == NULL) { - sem_putref(sma); + if (sem_io == NULL) { + ipc_rcu_putref(sma, ipc_rcu_free); return -ENOMEM; } rcu_read_lock(); sem_lock_and_putref(sma); - if (sma->sem_perm.deleted) { - sem_unlock(sma, -1); - rcu_read_unlock(); + if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; - goto out_free; + goto out_unlock; } } for (i = 0; i < sma->sem_nsems; i++) @@ -1151,7 +1383,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, sem_unlock(sma, -1); rcu_read_unlock(); err = 0; - if(copy_to_user(array, sem_io, nsems*sizeof(ushort))) + if (copy_to_user(array, sem_io, nsems*sizeof(ushort))) err = -EFAULT; goto out_free; } @@ -1161,45 +1393,43 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, struct sem_undo *un; if (!ipc_rcu_getref(sma)) { - rcu_read_unlock(); - return -EIDRM; + err = -EIDRM; + goto out_rcu_wakeup; } rcu_read_unlock(); - if(nsems > SEMMSL_FAST) { + if (nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); - if(sem_io == NULL) { - sem_putref(sma); + if (sem_io == NULL) { + ipc_rcu_putref(sma, ipc_rcu_free); return -ENOMEM; } } - if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) { - sem_putref(sma); + if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { + ipc_rcu_putref(sma, ipc_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); err = -ERANGE; goto out_free; } } rcu_read_lock(); sem_lock_and_putref(sma); - if (sma->sem_perm.deleted) { - sem_unlock(sma, -1); - rcu_read_unlock(); + if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; - goto out_free; + goto out_unlock; } for (i = 0; i < nsems; i++) sma->sem_base[i].semval = sem_io[i]; - assert_spin_locked(&sma->sem_perm.lock); + ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) { for (i = 0; i < nsems; i++) un->semadj[i] = 0; @@ -1217,6 +1447,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, goto out_rcu_wakeup; sem_lock(sma, NULL, -1); + if (!ipc_valid_object(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } curr = &sma->sem_base[semnum]; switch (cmd) { @@ -1227,10 +1461,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, err = curr->sempid; goto out_unlock; case GETNCNT: - err = count_semncnt(sma,semnum); + err = count_semcnt(sma, semnum, 0); goto out_unlock; case GETZCNT: - err = count_semzcnt(sma,semnum); + err = count_semcnt(sma, semnum, 1); goto out_unlock; } @@ -1240,7 +1474,7 @@ out_rcu_wakeup: rcu_read_unlock(); wake_up_sem_queue_do(&tasks); out_free: - if(sem_io != fast_sem_io) + if (sem_io != fast_sem_io) ipc_free(sem_io, sizeof(ushort)*nsems); return err; } @@ -1248,7 +1482,7 @@ out_free: static inline unsigned long copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { - switch(version) { + switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; @@ -1257,7 +1491,7 @@ copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { struct semid_ds tbuf_old; - if(copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->sem_perm.uid = tbuf_old.sem_perm.uid; @@ -1272,9 +1506,9 @@ copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) } /* - * This function handles some semctl commands which require the rw_mutex + * This function handles some semctl commands which require the rwsem * to be held in write mode. - * NOTE: no locks must be held, the rw_mutex is taken inside this function. + * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int semctl_down(struct ipc_namespace *ns, int semid, int cmd, int version, void __user *p) @@ -1284,47 +1518,51 @@ static int semctl_down(struct ipc_namespace *ns, int semid, struct semid64_ds semid64; struct kern_ipc_perm *ipcp; - if(cmd == IPC_SET) { + if (cmd == IPC_SET) { if (copy_semid_from_user(&semid64, p, version)) return -EFAULT; } + down_write(&sem_ids(ns).rwsem); + rcu_read_lock(); + ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd, &semid64.sem_perm, 0); - if (IS_ERR(ipcp)) - return PTR_ERR(ipcp); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto out_unlock1; + } sma = container_of(ipcp, struct sem_array, sem_perm); err = security_sem_semctl(sma, cmd); - if (err) { - rcu_read_unlock(); - goto out_up; - } + if (err) + goto out_unlock1; - switch(cmd){ + switch (cmd) { case IPC_RMID: sem_lock(sma, NULL, -1); + /* freeary unlocks the ipc object and rcu */ freeary(ns, ipcp); goto out_up; case IPC_SET: sem_lock(sma, NULL, -1); err = ipc_update_perm(&semid64.sem_perm, ipcp); if (err) - goto out_unlock; + goto out_unlock0; sma->sem_ctime = get_seconds(); break; default: - rcu_read_unlock(); err = -EINVAL; - goto out_up; + goto out_unlock1; } -out_unlock: +out_unlock0: sem_unlock(sma, -1); +out_unlock1: rcu_read_unlock(); out_up: - up_write(&sem_ids(ns).rw_mutex); + up_write(&sem_ids(ns).rwsem); return err; } @@ -1340,7 +1578,7 @@ SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) version = ipc_parse_version(&cmd); ns = current->nsproxy->ipc_ns; - switch(cmd) { + switch (cmd) { case IPC_INFO: case SEM_INFO: case IPC_STAT: @@ -1408,7 +1646,7 @@ static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) { struct sem_undo *un; - assert_spin_locked(&ulp->lock); + assert_spin_locked(&ulp->lock); un = __lookup_undo(ulp, semid); if (un) { @@ -1419,7 +1657,7 @@ static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) } /** - * find_alloc_undo - Lookup (and if not present create) undo array + * find_alloc_undo - lookup (and if not present create) undo array * @ns: namespace * @semid: semaphore array id * @@ -1444,7 +1682,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) spin_lock(&ulp->lock); un = lookup_undo(ulp, semid); spin_unlock(&ulp->lock); - if (likely(un!=NULL)) + if (likely(un != NULL)) goto out; /* no undo structure around - allocate one. */ @@ -1466,14 +1704,14 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return ERR_PTR(-ENOMEM); } /* step 3: Acquire the lock on semaphore array */ rcu_read_lock(); sem_lock_and_putref(sma); - if (sma->sem_perm.deleted) { + if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); kfree(new); @@ -1496,7 +1734,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) new->semid = semid; assert_spin_locked(&ulp->lock); list_add_rcu(&new->list_proc, &ulp->list_proc); - assert_spin_locked(&sma->sem_perm.lock); + ipc_assert_locked_object(&sma->sem_perm); list_add(&new->list_id, &sma->list_id); un = new; @@ -1509,7 +1747,7 @@ out: /** - * get_queue_result - Retrieve the result code from sem_queue + * get_queue_result - retrieve the result code from sem_queue * @q: Pointer to queue structure * * Retrieve the return code from the pending queue. If IN_WAKEUP is found in @@ -1533,14 +1771,13 @@ static int get_queue_result(struct sem_queue *q) return error; } - SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, unsigned, nsops, const struct timespec __user *, timeout) { int error = -EINVAL; struct sem_array *sma; struct sembuf fast_sops[SEMOPM_FAST]; - struct sembuf* sops = fast_sops, *sop; + struct sembuf *sops = fast_sops, *sop; struct sem_undo *un; int undos = 0, alter = 0, max, locknum; struct sem_queue queue; @@ -1554,13 +1791,13 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, return -EINVAL; if (nsops > ns->sc_semopm) return -E2BIG; - if(nsops > SEMOPM_FAST) { - sops = kmalloc(sizeof(*sops)*nsops,GFP_KERNEL); - if(sops==NULL) + if (nsops > SEMOPM_FAST) { + sops = kmalloc(sizeof(*sops)*nsops, GFP_KERNEL); + if (sops == NULL) return -ENOMEM; } - if (copy_from_user (sops, tsops, nsops * sizeof(*tsops))) { - error=-EFAULT; + if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) { + error = -EFAULT; goto out_free; } if (timeout) { @@ -1619,6 +1856,18 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, if (error) goto out_rcu_wakeup; + error = -EIDRM; + locknum = sem_lock(sma, sops, nsops); + /* + * We eventually might perform the following check in a lockless + * fashion, considering ipc_valid_object() locking constraints. + * If nsops == 1 and there is no contention for sem_perm.lock, then + * only a per-semaphore lock is held and it's OK to proceed with the + * check below. More details on the fine grained locking scheme + * entangled here and why it's RMID race safe on comments at sem_lock() + */ + if (!ipc_valid_object(&sma->sem_perm)) + goto out_unlock_free; /* * semid identifiers are not unique - find_alloc_undo may have * allocated an undo structure, it was invalidated by an RMID @@ -1626,42 +1875,57 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, * This case can be detected checking un->semid. The existence of * "un" itself is guaranteed by rcu. */ - error = -EIDRM; - locknum = sem_lock(sma, sops, nsops); if (un && un->semid == -1) goto out_unlock_free; - error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current)); - if (error <= 0) { - if (alter && error == 0) - do_smart_update(sma, sops, nsops, 1, &tasks); + queue.sops = sops; + queue.nsops = nsops; + queue.undo = un; + queue.pid = task_tgid_vnr(current); + queue.alter = alter; - goto out_unlock_free; + error = perform_atomic_semop(sma, &queue); + if (error == 0) { + /* If the operation was successful, then do + * the required updates. + */ + if (alter) + do_smart_update(sma, sops, nsops, 1, &tasks); + else + set_semotime(sma, sops); } + if (error <= 0) + goto out_unlock_free; /* We need to sleep on this operation, so we put the current * task into the pending queue and go to sleep. */ - - queue.sops = sops; - queue.nsops = nsops; - queue.undo = un; - queue.pid = task_tgid_vnr(current); - queue.alter = alter; if (nsops == 1) { struct sem *curr; curr = &sma->sem_base[sops->sem_num]; - if (alter) - list_add_tail(&queue.list, &curr->sem_pending); - else - list_add(&queue.list, &curr->sem_pending); + if (alter) { + if (sma->complex_count) { + list_add_tail(&queue.list, + &sma->pending_alter); + } else { + + list_add_tail(&queue.list, + &curr->pending_alter); + } + } else { + list_add_tail(&queue.list, &curr->pending_const); + } } else { + if (!sma->complex_count) + merge_queues(sma); + if (alter) - list_add_tail(&queue.list, &sma->sem_pending); + list_add_tail(&queue.list, &sma->pending_alter); else - list_add(&queue.list, &sma->sem_pending); + list_add_tail(&queue.list, &sma->pending_const); + sma->complex_count++; } @@ -1714,10 +1978,8 @@ sleep_again: * If queue.status != -EINTR we are woken up by another process. * Leave without unlink_queue(), but with sem_unlock(). */ - - if (error != -EINTR) { + if (error != -EINTR) goto out_unlock_free; - } /* * If an interrupt occurred we have to clean up the queue @@ -1739,7 +2001,7 @@ out_rcu_wakeup: rcu_read_unlock(); wake_up_sem_queue_do(&tasks); out_free: - if(sops != fast_sops) + if (sops != fast_sops) kfree(sops); return error; } @@ -1765,7 +2027,7 @@ int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) return error; atomic_inc(&undo_list->refcnt); tsk->sysvsem.undo_list = undo_list; - } else + } else tsk->sysvsem.undo_list = NULL; return 0; @@ -1822,6 +2084,12 @@ void exit_sem(struct task_struct *tsk) } sem_lock(sma, NULL, -1); + /* exit_sem raced with IPC_RMID, nothing to do */ + if (!ipc_valid_object(&sma->sem_perm)) { + sem_unlock(sma, -1); + rcu_read_unlock(); + continue; + } un = __lookup_undo(ulp, semid); if (un == NULL) { /* exit_sem raced with IPC_RMID+semget() that created @@ -1833,7 +2101,7 @@ void exit_sem(struct task_struct *tsk) } /* remove un from the linked lists */ - assert_spin_locked(&sma->sem_perm.lock); + ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); spin_lock(&ulp->lock); @@ -1842,7 +2110,7 @@ void exit_sem(struct task_struct *tsk) /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { - struct sem * semaphore = &sma->sem_base[i]; + struct sem *semaphore = &sma->sem_base[i]; if (un->semadj[i]) { semaphore->semval += un->semadj[i]; /* @@ -1856,7 +2124,7 @@ void exit_sem(struct task_struct *tsk) * Linux caps the semaphore value, both at 0 * and at SEMVMX. * - * Manfred <manfred@colorfullife.com> + * Manfred <manfred@colorfullife.com> */ if (semaphore->semval < 0) semaphore->semval = 0; @@ -1882,6 +2150,17 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) { struct user_namespace *user_ns = seq_user_ns(s); struct sem_array *sma = it; + time_t sem_otime; + + /* + * The proc interface isn't aware of sem_lock(), it calls + * ipc_lock_object() directly (in sysvipc_find_ipc). + * In order to stay compatible with sem_lock(), we must wait until + * all simple semop() calls have left their critical regions. + */ + sem_wait_array(sma); + + sem_otime = get_semotime(sma); return seq_printf(s, "%10d %10d %4o %10u %5u %5u %5u %5u %10lu %10lu\n", @@ -1893,7 +2172,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) from_kgid_munged(user_ns, sma->sem_perm.gid), from_kuid_munged(user_ns, sma->sem_perm.cuid), from_kgid_munged(user_ns, sma->sem_perm.cgid), - sma->sem_otime, + sem_otime, sma->sem_ctime); } #endif |