diff options
Diffstat (limited to 'ipc')
| -rw-r--r-- | ipc/mqueue.c | 14 | ||||
| -rw-r--r-- | ipc/msg.c | 5 | ||||
| -rw-r--r-- | ipc/sem.c | 130 | ||||
| -rw-r--r-- | ipc/shm.c | 41 |
4 files changed, 120 insertions, 70 deletions
diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 161a1807e6ef..46436543ad28 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -747,7 +747,7 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir, } mode &= ~current_umask(); - ret = vfs_create(dir, path->dentry, mode, true); + ret = vfs_create2(path->mnt, dir, path->dentry, mode, true); path->dentry->d_fsdata = NULL; if (ret) return ERR_PTR(ret); @@ -763,7 +763,7 @@ static struct file *do_open(struct path *path, int oflag) if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) return ERR_PTR(-EINVAL); acc = oflag2acc[oflag & O_ACCMODE]; - if (inode_permission(d_inode(path->dentry), acc)) + if (inode_permission2(path->mnt, d_inode(path->dentry), acc)) return ERR_PTR(-EACCES); return dentry_open(path, oflag, current_cred()); } @@ -796,7 +796,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, ro = mnt_want_write(mnt); /* we'll drop it in any case */ error = 0; mutex_lock(&d_inode(root)->i_mutex); - path.dentry = lookup_one_len(name->name, root, strlen(name->name)); + path.dentry = lookup_one_len2(name->name, mnt, root, strlen(name->name)); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; @@ -867,7 +867,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) if (err) goto out_name; mutex_lock_nested(&d_inode(mnt->mnt_root)->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name->name, mnt->mnt_root, + dentry = lookup_one_len2(name->name, mnt, mnt->mnt_root, strlen(name->name)); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); @@ -879,7 +879,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) err = -ENOENT; } else { ihold(inode); - err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL); + err = vfs_unlink2(mnt, d_inode(dentry->d_parent), dentry, NULL); } dput(dentry); @@ -1251,8 +1251,10 @@ retry: timeo = MAX_SCHEDULE_TIMEOUT; ret = netlink_attachskb(sock, nc, &timeo, NULL); - if (ret == 1) + if (ret == 1) { + sock = NULL; goto retry; + } if (ret) { sock = NULL; nc = NULL; diff --git a/ipc/msg.c b/ipc/msg.c index c6521c205cb4..f993f441f852 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -742,7 +742,10 @@ static inline int convert_mode(long *msgtyp, int msgflg) if (*msgtyp == 0) return SEARCH_ANY; if (*msgtyp < 0) { - *msgtyp = -*msgtyp; + if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */ + *msgtyp = LONG_MAX; + else + *msgtyp = -*msgtyp; return SEARCH_LESSEQUAL; } if (msgflg & MSG_EXCEPT) diff --git a/ipc/sem.c b/ipc/sem.c index 20d07008ad5e..9862c3d1c26d 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -155,14 +155,21 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); /* * Locking: + * a) global sem_lock() for read/write * sem_undo.id_next, * 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.complex_mode + * sem_array.pending{_alter,_const}, + * sem_array.sem_undo * + * b) global or semaphore sem_lock() for read/write: * sem_array.sem_base[i].pending_{const,alter}: - * global or semaphore sem_lock() for read/write + * sem_array.complex_mode (for read) + * + * c) special: + * sem_undo_list.list_proc: + * * undo_list->lock for write + * * rcu for read */ #define sc_semmsl sem_ctls[0] @@ -263,24 +270,25 @@ static void sem_rcu_free(struct rcu_head *head) #define ipc_smp_acquire__after_spin_is_unlocked() smp_rmb() /* - * Wait until all currently ongoing simple ops have completed. + * Enter the mode suitable for non-simple operations: * 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) +static void complexmode_enter(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. - */ + if (sma->complex_mode) { + /* We are already in complex_mode. Nothing to do */ return; } + /* We need a full barrier after seting complex_mode: + * The write to complex_mode must be visible + * before we read the first sem->lock spinlock state. + */ + smp_store_mb(sma->complex_mode, true); + for (i = 0; i < sma->sem_nsems; i++) { sem = sma->sem_base + i; spin_unlock_wait(&sem->lock); @@ -289,6 +297,28 @@ static void sem_wait_array(struct sem_array *sma) } /* + * Try to leave the mode that disallows simple operations: + * Caller must own sem_perm.lock. + */ +static void complexmode_tryleave(struct sem_array *sma) +{ + if (sma->complex_count) { + /* Complex ops are sleeping. + * We must stay in complex mode + */ + return; + } + /* + * Immediately after setting complex_mode to false, + * a simple op can start. Thus: all memory writes + * performed by the current operation must be visible + * before we set complex_mode to false. + */ + smp_store_release(&sma->complex_mode, false); +} + +#define SEM_GLOBAL_LOCK (-1) +/* * 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 @@ -304,56 +334,42 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Complex operation - acquire a full lock */ ipc_lock_object(&sma->sem_perm); - /* And wait until all simple ops that are processed - * right now have dropped their locks. - */ - sem_wait_array(sma); - return -1; + /* Prevent parallel simple ops */ + complexmode_enter(sma); + return SEM_GLOBAL_LOCK; } /* * 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. + * Optimized locking is possible if no complex operation + * is either enqueued or processed right now. + * + * Both facts are tracked by complex_mode. */ sem = sma->sem_base + sops->sem_num; - if (sma->complex_count == 0) { + /* + * Initial check for complex_mode. Just an optimization, + * no locking, no memory barrier. + */ + if (!sma->complex_mode) { /* * It appears that no complex operation is around. * Acquire the per-semaphore lock. */ spin_lock(&sem->lock); - /* Then check that the global lock is free */ - if (!spin_is_locked(&sma->sem_perm.lock)) { - /* - * We need a memory barrier with acquire semantics, - * otherwise we can race with another thread that does: - * complex_count++; - * spin_unlock(sem_perm.lock); - */ - ipc_smp_acquire__after_spin_is_unlocked(); + /* + * See 51d7d5205d33 + * ("powerpc: Add smp_mb() to arch_spin_is_locked()"): + * A full barrier is required: the write of sem->lock + * must be visible before the read is executed + */ + 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; - } + if (!smp_load_acquire(&sma->complex_mode)) { + /* fast path successful! */ + return sops->sem_num; } spin_unlock(&sem->lock); } @@ -373,15 +389,16 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Not a false alarm, thus complete the sequence for a * full lock. */ - sem_wait_array(sma); - return -1; + complexmode_enter(sma); + return SEM_GLOBAL_LOCK; } } static inline void sem_unlock(struct sem_array *sma, int locknum) { - if (locknum == -1) { + if (locknum == SEM_GLOBAL_LOCK) { unmerge_queues(sma); + complexmode_tryleave(sma); ipc_unlock_object(&sma->sem_perm); } else { struct sem *sem = sma->sem_base + locknum; @@ -533,6 +550,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) } sma->complex_count = 0; + sma->complex_mode = true; /* dropped by sem_unlock below */ INIT_LIST_HEAD(&sma->pending_alter); INIT_LIST_HEAD(&sma->pending_const); INIT_LIST_HEAD(&sma->list_id); @@ -2186,10 +2204,10 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) /* * 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. + * In order to stay compatible with sem_lock(), we must + * enter / leave complex_mode. */ - sem_wait_array(sma); + complexmode_enter(sma); sem_otime = get_semotime(sma); @@ -2206,6 +2224,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) sem_otime, sma->sem_ctime); + complexmode_tryleave(sma); + return 0; } #endif diff --git a/ipc/shm.c b/ipc/shm.c index 3174634ca4e5..32974cfe5947 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -198,6 +198,12 @@ static int __shm_open(struct vm_area_struct *vma) if (IS_ERR(shp)) return PTR_ERR(shp); + if (shp->shm_file != sfd->file) { + /* ID was reused */ + shm_unlock(shp); + return -EINVAL; + } + shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; @@ -414,8 +420,9 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) int ret; /* - * In case of remap_file_pages() emulation, the file can represent - * removed IPC ID: propogate shm_lock() error to caller. + * In case of remap_file_pages() emulation, the file can represent an + * IPC ID that was removed, and possibly even reused by another shm + * segment already. Propagate this case as an error to caller. */ ret =__shm_open(vma); if (ret) @@ -439,6 +446,7 @@ static int shm_release(struct inode *ino, struct file *file) struct shm_file_data *sfd = shm_file_data(file); put_ipc_ns(sfd->ns); + fput(sfd->file); shm_file_data(file) = NULL; kfree(sfd); return 0; @@ -1083,8 +1091,8 @@ out_unlock1: * "raddr" thing points to kernel space, and there has to be a wrapper around * this. */ -long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, - unsigned long shmlba) +long do_shmat(int shmid, char __user *shmaddr, int shmflg, + ulong *raddr, unsigned long shmlba) { struct shmid_kernel *shp; unsigned long addr; @@ -1105,9 +1113,17 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, goto out; else if ((addr = (ulong)shmaddr)) { if (addr & (shmlba - 1)) { - if (shmflg & SHM_RND) - addr &= ~(shmlba - 1); /* round down */ - else + if (shmflg & SHM_RND) { + addr &= ~(shmlba - 1); /* round down */ + + /* + * Ensure that the round-down is non-nil + * when remapping. This can happen for + * cases when addr < shmlba. + */ + if (!addr && (shmflg & SHM_REMAP)) + goto out; + } else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) #endif @@ -1193,7 +1209,16 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, file->f_mapping = shp->shm_file->f_mapping; sfd->id = shp->shm_perm.id; sfd->ns = get_ipc_ns(ns); - sfd->file = shp->shm_file; + /* + * We need to take a reference to the real shm file to prevent the + * pointer from becoming stale in cases where the lifetime of the outer + * file extends beyond that of the shm segment. It's not usually + * possible, but it can happen during remap_file_pages() emulation as + * that unmaps the memory, then does ->mmap() via file reference only. + * We'll deny the ->mmap() if the shm segment was since removed, but to + * detect shm ID reuse we need to compare the file pointers. + */ + sfd->file = get_file(shp->shm_file); sfd->vm_ops = NULL; err = security_mmap_file(file, prot, flags); |