diff options
Diffstat (limited to 'ipc')
| -rw-r--r-- | ipc/mqueue.c | 19 | ||||
| -rw-r--r-- | ipc/namespace.c | 6 | ||||
| -rw-r--r-- | ipc/sem.c | 6 | ||||
| -rw-r--r-- | ipc/shm.c | 176 | ||||
| -rw-r--r-- | ipc/util.c | 12 |
5 files changed, 154 insertions, 65 deletions
diff --git a/ipc/mqueue.c b/ipc/mqueue.c index a94880dc9094..0a1afa17bf5f 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -305,7 +305,7 @@ err: static int mqueue_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - struct ipc_namespace *ns = data; + struct ipc_namespace *ns = sb->s_fs_info; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; @@ -326,17 +326,14 @@ static struct dentry *mqueue_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - if (!(flags & MS_KERNMOUNT)) { - struct ipc_namespace *ns = current->nsproxy->ipc_ns; - /* Don't allow mounting unless the caller has CAP_SYS_ADMIN - * over the ipc namespace. - */ - if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) - return ERR_PTR(-EPERM); - - data = ns; + struct ipc_namespace *ns; + if (flags & MS_KERNMOUNT) { + ns = data; + data = NULL; + } else { + ns = current->nsproxy->ipc_ns; } - return mount_ns(fs_type, flags, data, mqueue_fill_super); + return mount_ns(fs_type, flags, data, ns, ns->user_ns, mqueue_fill_super); } static void init_once(void *foo) diff --git a/ipc/namespace.c b/ipc/namespace.c index 068caf18d565..25b64530c042 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -166,10 +166,16 @@ static int ipcns_install(struct nsproxy *nsproxy, struct ns_common *new) return 0; } +static struct user_namespace *ipcns_owner(struct ns_common *ns) +{ + return to_ipc_ns(ns)->user_ns; +} + const struct proc_ns_operations ipcns_operations = { .name = "ipc", .type = CLONE_NEWIPC, .get = ipcns_get, .put = ipcns_put, .install = ipcns_install, + .owner = ipcns_owner, }; diff --git a/ipc/sem.c b/ipc/sem.c index 9862c3d1c26d..9963ed351b43 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2151,11 +2151,9 @@ void exit_sem(struct task_struct *tsk) ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); - /* we are the last process using this ulp, acquiring ulp->lock - * isn't required. Besides that, we are also protected against - * IPC_RMID as we hold sma->sem_perm lock now - */ + spin_lock(&ulp->lock); list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { diff --git a/ipc/shm.c b/ipc/shm.c index 5095eb3a6a6c..41e5e712da1c 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -90,6 +90,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); + WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; @@ -180,10 +181,43 @@ static void shm_rcu_free(struct rcu_head *head) ipc_rcu_free(head); } -static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) +/* + * It has to be called with shp locked. + * It must be called before ipc_rmid() + */ +static inline void shm_clist_rm(struct shmid_kernel *shp) { - list_del(&s->shm_clist); - ipc_rmid(&shm_ids(ns), &s->shm_perm); + struct task_struct *creator; + + /* ensure that shm_creator does not disappear */ + rcu_read_lock(); + + /* + * A concurrent exit_shm may do a list_del_init() as well. + * Just do nothing if exit_shm already did the work + */ + if (!list_empty(&shp->shm_clist)) { + /* + * shp->shm_creator is guaranteed to be valid *only* + * if shp->shm_clist is not empty. + */ + creator = shp->shm_creator; + + task_lock(creator); + /* + * list_del_init() is a nop if the entry was already removed + * from the list. + */ + list_del_init(&shp->shm_clist); + task_unlock(creator); + } + rcu_read_unlock(); +} + +static inline void shm_rmid(struct shmid_kernel *s) +{ + shm_clist_rm(s); + ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } @@ -238,7 +272,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; - shm_rmid(ns, shp); + shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_user); @@ -259,10 +293,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ -static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) +static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && - (ns->shm_rmid_forced || + (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } @@ -293,7 +327,7 @@ static void shm_close(struct vm_area_struct *vma) shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; - if (shm_may_destroy(ns, shp)) + if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); @@ -314,10 +348,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data) * * As shp->* are changed under rwsem, it's safe to skip shp locking. */ - if (shp->shm_creator != NULL) + if (!list_empty(&shp->shm_clist)) return 0; - if (shm_may_destroy(ns, shp)) { + if (shm_may_destroy(shp)) { shm_lock_by_ptr(shp); shm_destroy(ns, shp); } @@ -335,48 +369,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns) /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { - struct ipc_namespace *ns = task->nsproxy->ipc_ns; - struct shmid_kernel *shp, *n; + for (;;) { + struct shmid_kernel *shp; + struct ipc_namespace *ns; - if (list_empty(&task->sysvshm.shm_clist)) - return; + task_lock(task); + + if (list_empty(&task->sysvshm.shm_clist)) { + task_unlock(task); + break; + } + + shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, + shm_clist); - /* - * If kernel.shm_rmid_forced is not set then only keep track of - * which shmids are orphaned, so that a later set of the sysctl - * can clean them up. - */ - if (!ns->shm_rmid_forced) { - down_read(&shm_ids(ns).rwsem); - list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist) - shp->shm_creator = NULL; /* - * Only under read lock but we are only called on current - * so no entry on the list will be shared. + * 1) Get pointer to the ipc namespace. It is worth to say + * that this pointer is guaranteed to be valid because + * shp lifetime is always shorter than namespace lifetime + * in which shp lives. + * We taken task_lock it means that shp won't be freed. */ - list_del(&task->sysvshm.shm_clist); - up_read(&shm_ids(ns).rwsem); - return; - } + ns = shp->ns; - /* - * Destroy all already created segments, that were not yet mapped, - * and mark any mapped as orphan to cover the sysctl toggling. - * Destroy is skipped if shm_may_destroy() returns false. - */ - down_write(&shm_ids(ns).rwsem); - list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) { - shp->shm_creator = NULL; + /* + * 2) If kernel.shm_rmid_forced is not set then only keep track of + * which shmids are orphaned, so that a later set of the sysctl + * can clean them up. + */ + if (!ns->shm_rmid_forced) + goto unlink_continue; - if (shm_may_destroy(ns, shp)) { - shm_lock_by_ptr(shp); - shm_destroy(ns, shp); + /* + * 3) get a reference to the namespace. + * The refcount could be already 0. If it is 0, then + * the shm objects will be free by free_ipc_work(). + */ + ns = get_ipc_ns_not_zero(ns); + if (!ns) { +unlink_continue: + list_del_init(&shp->shm_clist); + task_unlock(task); + continue; } - } - /* Remove the list head from any segments still attached. */ - list_del(&task->sysvshm.shm_clist); - up_write(&shm_ids(ns).rwsem); + /* + * 4) get a reference to shp. + * This cannot fail: shm_clist_rm() is called before + * ipc_rmid(), thus the refcount cannot be 0. + */ + WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); + + /* + * 5) unlink the shm segment from the list of segments + * created by current. + * This must be done last. After unlinking, + * only the refcounts obtained above prevent IPC_RMID + * from destroying the segment or the namespace. + */ + list_del_init(&shp->shm_clist); + + task_unlock(task); + + /* + * 6) we have all references + * Thus lock & if needed destroy shp. + */ + down_write(&shm_ids(ns).rwsem); + shm_lock_by_ptr(shp); + /* + * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's + * safe to call ipc_rcu_putref here + */ + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); + + if (ipc_valid_object(&shp->shm_perm)) { + if (shm_may_destroy(shp)) + shm_destroy(ns, shp); + else + shm_unlock(shp); + } else { + /* + * Someone else deleted the shp from namespace + * idr/kht while we have waited. + * Just unlock and continue. + */ + shm_unlock(shp); + } + + up_write(&shm_ids(ns).rwsem); + put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ + } } static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) @@ -607,7 +690,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) goto no_id; } + shp->ns = ns; + + task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); + task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. @@ -1252,7 +1339,8 @@ out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; - if (shm_may_destroy(ns, shp)) + + if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); diff --git a/ipc/util.c b/ipc/util.c index 0f401d94b7c6..7af476b6dcdd 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -756,21 +756,21 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, total++; } + ipc = NULL; if (total >= ids->in_use) - return NULL; + goto out; for (; pos < IPCMNI; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { - *new_pos = pos + 1; rcu_read_lock(); ipc_lock_object(ipc); - return ipc; + break; } } - - /* Out of range - return NULL to terminate iteration */ - return NULL; +out: + *new_pos = pos + 1; + return ipc; } static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) |