diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/block_dev.c | 5 | ||||
-rw-r--r-- | fs/buffer.c | 57 | ||||
-rw-r--r-- | fs/char_dev.c | 13 | ||||
-rw-r--r-- | fs/debugfs/inode.c | 12 | ||||
-rw-r--r-- | fs/dquot.c | 16 | ||||
-rw-r--r-- | fs/eventpoll.c | 195 | ||||
-rw-r--r-- | fs/exec.c | 23 | ||||
-rw-r--r-- | fs/ext2/acl.c | 12 | ||||
-rw-r--r-- | fs/ext2/acl.h | 2 | ||||
-rw-r--r-- | fs/ext3/acl.c | 12 | ||||
-rw-r--r-- | fs/ext3/acl.h | 2 | ||||
-rw-r--r-- | fs/ext3/namei.c | 12 | ||||
-rw-r--r-- | fs/ext3/super.c | 18 | ||||
-rw-r--r-- | fs/file_table.c | 57 | ||||
-rw-r--r-- | fs/fs-writeback.c | 64 | ||||
-rw-r--r-- | fs/inode.c | 16 | ||||
-rw-r--r-- | fs/jfs/acl.c | 11 | ||||
-rw-r--r-- | fs/jfs/jfs_acl.h | 2 | ||||
-rw-r--r-- | fs/jfs/super.c | 1 | ||||
-rw-r--r-- | fs/jfs/xattr.c | 7 | ||||
-rw-r--r-- | fs/namei.c | 20 | ||||
-rw-r--r-- | fs/nfs/direct.c | 5 | ||||
-rw-r--r-- | fs/nfsd/vfs.c | 9 | ||||
-rw-r--r-- | fs/open.c | 41 | ||||
-rw-r--r-- | fs/proc/base.c | 6 | ||||
-rw-r--r-- | fs/proc/proc_misc.c | 2 | ||||
-rw-r--r-- | fs/quota.c | 60 | ||||
-rw-r--r-- | fs/read_write.c | 20 | ||||
-rw-r--r-- | fs/reiserfs/super.c | 21 | ||||
-rw-r--r-- | fs/reiserfs/xattr_acl.c | 26 | ||||
-rw-r--r-- | fs/super.c | 83 | ||||
-rw-r--r-- | fs/sysfs/dir.c | 5 | ||||
-rw-r--r-- | fs/sysfs/file.c | 5 | ||||
-rw-r--r-- | fs/sysfs/group.c | 4 | ||||
-rw-r--r-- | fs/sysfs/inode.c | 10 | ||||
-rw-r--r-- | fs/sysfs/sysfs.h | 1 |
36 files changed, 434 insertions, 421 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c index c0cbd1bc1a02..e0df94c37b7e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -777,8 +777,7 @@ static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf, return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); } -static int block_ioctl(struct inode *inode, struct file *file, unsigned cmd, - unsigned long arg) +static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); } @@ -803,7 +802,7 @@ struct file_operations def_blk_fops = { .aio_write = blkdev_file_aio_write, .mmap = generic_file_mmap, .fsync = block_fsync, - .ioctl = block_ioctl, + .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif diff --git a/fs/buffer.c b/fs/buffer.c index 0befa724ab98..13e5938a64f6 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -331,7 +331,7 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync) return ret; } -asmlinkage long sys_fsync(unsigned int fd) +static long do_fsync(unsigned int fd, int datasync) { struct file * file; struct address_space *mapping; @@ -342,14 +342,14 @@ asmlinkage long sys_fsync(unsigned int fd) if (!file) goto out; - mapping = file->f_mapping; - ret = -EINVAL; if (!file->f_op || !file->f_op->fsync) { /* Why? We can still call filemap_fdatawrite */ goto out_putf; } + mapping = file->f_mapping; + current->flags |= PF_SYNCWRITE; ret = filemap_fdatawrite(mapping); @@ -358,7 +358,7 @@ asmlinkage long sys_fsync(unsigned int fd) * which could cause livelocks in fsync_buffers_list */ down(&mapping->host->i_sem); - err = file->f_op->fsync(file, file->f_dentry, 0); + err = file->f_op->fsync(file, file->f_dentry, datasync); if (!ret) ret = err; up(&mapping->host->i_sem); @@ -373,39 +373,14 @@ out: return ret; } -asmlinkage long sys_fdatasync(unsigned int fd) +asmlinkage long sys_fsync(unsigned int fd) { - struct file * file; - struct address_space *mapping; - int ret, err; - - ret = -EBADF; - file = fget(fd); - if (!file) - goto out; - - ret = -EINVAL; - if (!file->f_op || !file->f_op->fsync) - goto out_putf; - - mapping = file->f_mapping; - - current->flags |= PF_SYNCWRITE; - ret = filemap_fdatawrite(mapping); - down(&mapping->host->i_sem); - err = file->f_op->fsync(file, file->f_dentry, 1); - if (!ret) - ret = err; - up(&mapping->host->i_sem); - err = filemap_fdatawait(mapping); - if (!ret) - ret = err; - current->flags &= ~PF_SYNCWRITE; + return do_fsync(fd, 0); +} -out_putf: - fput(file); -out: - return ret; +asmlinkage long sys_fdatasync(unsigned int fd) +{ + return do_fsync(fd, 1); } /* @@ -1951,7 +1926,6 @@ static int __block_prepare_write(struct inode *inode, struct page *page, if (err) break; if (buffer_new(bh)) { - clear_buffer_new(bh); unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); if (PageUptodate(page)) { @@ -1993,9 +1967,14 @@ static int __block_prepare_write(struct inode *inode, struct page *page, if (!buffer_uptodate(*wait_bh)) err = -EIO; } - if (!err) - return err; - + if (!err) { + bh = head; + do { + if (buffer_new(bh)) + clear_buffer_new(bh); + } while ((bh = bh->b_this_page) != head); + return 0; + } /* Error case: */ /* * Zero out any newly allocated blocks to avoid exposing stale diff --git a/fs/char_dev.c b/fs/char_dev.c index c1e3537909fc..e82aac9cc2f5 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -56,10 +56,21 @@ int get_chrdev_list(char *page) down(&chrdevs_lock); for (i = 0; i < ARRAY_SIZE(chrdevs) ; i++) { - for (cd = chrdevs[i]; cd; cd = cd->next) + for (cd = chrdevs[i]; cd; cd = cd->next) { + /* + * if the current name, plus the 5 extra characters + * in the device line for this entry + * would run us off the page, we're done + */ + if ((len+strlen(cd->name) + 5) >= PAGE_SIZE) + goto page_full; + + len += sprintf(page+len, "%3d %s\n", cd->major, cd->name); + } } +page_full: up(&chrdevs_lock); return len; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b529786699e7..a86ac4aeaedb 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -110,16 +110,6 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent) return simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); } -static struct dentry * get_dentry(struct dentry *parent, const char *name) -{ - struct qstr qstr; - - qstr.name = name; - qstr.len = strlen(name); - qstr.hash = full_name_hash(name,qstr.len); - return lookup_hash(&qstr,parent); -} - static struct super_block *debug_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) @@ -157,7 +147,7 @@ static int debugfs_create_by_name(const char *name, mode_t mode, *dentry = NULL; down(&parent->d_inode->i_sem); - *dentry = get_dentry (parent, name); + *dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry)) { if ((mode & S_IFMT) == S_IFDIR) error = debugfs_mkdir(parent->d_inode, *dentry, mode); diff --git a/fs/dquot.c b/fs/dquot.c index 3995ce7907cc..37212b039a4a 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -1519,14 +1519,22 @@ out_path: * This function is used when filesystem needs to initialize quotas * during mount time. */ -int vfs_quota_on_mount(int type, int format_id, struct dentry *dentry) +int vfs_quota_on_mount(struct super_block *sb, char *qf_name, + int format_id, int type) { + struct dentry *dentry; int error; + dentry = lookup_one_len(qf_name, sb->s_root, strlen(qf_name)); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + error = security_quota_on(dentry); - if (error) - return error; - return vfs_quota_on_inode(dentry->d_inode, type, format_id); + if (!error) + error = vfs_quota_on_inode(dentry->d_inode, type, format_id); + + dput(dentry); + return error; } /* Generic routine for getting common part of quota structure */ diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9900e333655a..6ab1dd0ca904 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -101,57 +101,6 @@ /* Maximum number of poll wake up nests we are allowing */ #define EP_MAX_POLLWAKE_NESTS 4 -/* Macro to allocate a "struct epitem" from the slab cache */ -#define EPI_MEM_ALLOC() (struct epitem *) kmem_cache_alloc(epi_cache, SLAB_KERNEL) - -/* Macro to free a "struct epitem" to the slab cache */ -#define EPI_MEM_FREE(p) kmem_cache_free(epi_cache, p) - -/* Macro to allocate a "struct eppoll_entry" from the slab cache */ -#define PWQ_MEM_ALLOC() (struct eppoll_entry *) kmem_cache_alloc(pwq_cache, SLAB_KERNEL) - -/* Macro to free a "struct eppoll_entry" to the slab cache */ -#define PWQ_MEM_FREE(p) kmem_cache_free(pwq_cache, p) - -/* Fast test to see if the file is an evenpoll file */ -#define IS_FILE_EPOLL(f) ((f)->f_op == &eventpoll_fops) - -/* Setup the structure that is used as key for the rb-tree */ -#define EP_SET_FFD(p, f, d) do { (p)->file = (f); (p)->fd = (d); } while (0) - -/* Compare rb-tree keys */ -#define EP_CMP_FFD(p1, p2) ((p1)->file > (p2)->file ? +1: \ - ((p1)->file < (p2)->file ? -1: (p1)->fd - (p2)->fd)) - -/* Special initialization for the rb-tree node to detect linkage */ -#define EP_RB_INITNODE(n) (n)->rb_parent = (n) - -/* Removes a node from the rb-tree and marks it for a fast is-linked check */ -#define EP_RB_ERASE(n, r) do { rb_erase(n, r); (n)->rb_parent = (n); } while (0) - -/* Fast check to verify that the item is linked to the main rb-tree */ -#define EP_RB_LINKED(n) ((n)->rb_parent != (n)) - -/* - * Remove the item from the list and perform its initialization. - * This is useful for us because we can test if the item is linked - * using "EP_IS_LINKED(p)". - */ -#define EP_LIST_DEL(p) do { list_del(p); INIT_LIST_HEAD(p); } while (0) - -/* Tells us if the item is currently linked */ -#define EP_IS_LINKED(p) (!list_empty(p)) - -/* Get the "struct epitem" from a wait queue pointer */ -#define EP_ITEM_FROM_WAIT(p) ((struct epitem *) container_of(p, struct eppoll_entry, wait)->base) - -/* Get the "struct epitem" from an epoll queue wrapper */ -#define EP_ITEM_FROM_EPQUEUE(p) (container_of(p, struct ep_pqueue, pt)->epi) - -/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ -#define EP_OP_HASH_EVENT(op) ((op) != EPOLL_CTL_DEL) - - struct epoll_filefd { struct file *file; int fd; @@ -357,6 +306,82 @@ static struct dentry_operations eventpollfs_dentry_operations = { +/* Fast test to see if the file is an evenpoll file */ +static inline int is_file_epoll(struct file *f) +{ + return f->f_op == &eventpoll_fops; +} + +/* Setup the structure that is used as key for the rb-tree */ +static inline void ep_set_ffd(struct epoll_filefd *ffd, + struct file *file, int fd) +{ + ffd->file = file; + ffd->fd = fd; +} + +/* Compare rb-tree keys */ +static inline int ep_cmp_ffd(struct epoll_filefd *p1, + struct epoll_filefd *p2) +{ + return (p1->file > p2->file ? +1: + (p1->file < p2->file ? -1 : p1->fd - p2->fd)); +} + +/* Special initialization for the rb-tree node to detect linkage */ +static inline void ep_rb_initnode(struct rb_node *n) +{ + n->rb_parent = n; +} + +/* Removes a node from the rb-tree and marks it for a fast is-linked check */ +static inline void ep_rb_erase(struct rb_node *n, struct rb_root *r) +{ + rb_erase(n, r); + n->rb_parent = n; +} + +/* Fast check to verify that the item is linked to the main rb-tree */ +static inline int ep_rb_linked(struct rb_node *n) +{ + return n->rb_parent != n; +} + +/* + * Remove the item from the list and perform its initialization. + * This is useful for us because we can test if the item is linked + * using "ep_is_linked(p)". + */ +static inline void ep_list_del(struct list_head *p) +{ + list_del(p); + INIT_LIST_HEAD(p); +} + +/* Tells us if the item is currently linked */ +static inline int ep_is_linked(struct list_head *p) +{ + return !list_empty(p); +} + +/* Get the "struct epitem" from a wait queue pointer */ +static inline struct epitem * ep_item_from_wait(wait_queue_t *p) +{ + return container_of(p, struct eppoll_entry, wait)->base; +} + +/* Get the "struct epitem" from an epoll queue wrapper */ +static inline struct epitem * ep_item_from_epqueue(poll_table *p) +{ + return container_of(p, struct ep_pqueue, pt)->epi; +} + +/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ +static inline int ep_op_hash_event(int op) +{ + return op != EPOLL_CTL_DEL; +} + /* Initialize the poll safe wake up structure */ static void ep_poll_safewake_init(struct poll_safewake *psw) { @@ -456,7 +481,7 @@ void eventpoll_release_file(struct file *file) epi = list_entry(lsthead->next, struct epitem, fllink); ep = epi->ep; - EP_LIST_DEL(&epi->fllink); + ep_list_del(&epi->fllink); down_write(&ep->sem); ep_remove(ep, epi); up_write(&ep->sem); @@ -534,7 +559,7 @@ sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event) current, epfd, op, fd, event)); error = -EFAULT; - if (EP_OP_HASH_EVENT(op) && + if (ep_op_hash_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) goto eexit_1; @@ -560,7 +585,7 @@ sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event) * adding an epoll file descriptor inside itself. */ error = -EINVAL; - if (file == tfile || !IS_FILE_EPOLL(file)) + if (file == tfile || !is_file_epoll(file)) goto eexit_3; /* @@ -656,7 +681,7 @@ asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, * the user passed to us _is_ an eventpoll file. */ error = -EINVAL; - if (!IS_FILE_EPOLL(file)) + if (!is_file_epoll(file)) goto eexit_2; /* @@ -831,11 +856,11 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) struct epitem *epi, *epir = NULL; struct epoll_filefd ffd; - EP_SET_FFD(&ffd, file, fd); + ep_set_ffd(&ffd, file, fd); read_lock_irqsave(&ep->lock, flags); for (rbp = ep->rbr.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); - kcmp = EP_CMP_FFD(&ffd, &epi->ffd); + kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) @@ -875,7 +900,7 @@ static void ep_release_epitem(struct epitem *epi) { if (atomic_dec_and_test(&epi->usecnt)) - EPI_MEM_FREE(epi); + kmem_cache_free(epi_cache, epi); } @@ -886,10 +911,10 @@ static void ep_release_epitem(struct epitem *epi) static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { - struct epitem *epi = EP_ITEM_FROM_EPQUEUE(pt); + struct epitem *epi = ep_item_from_epqueue(pt); struct eppoll_entry *pwq; - if (epi->nwait >= 0 && (pwq = PWQ_MEM_ALLOC())) { + if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, SLAB_KERNEL))) { init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; @@ -912,7 +937,7 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); - kcmp = EP_CMP_FFD(&epi->ffd, &epic->ffd); + kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) p = &parent->rb_right; else @@ -932,17 +957,17 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, struct ep_pqueue epq; error = -ENOMEM; - if (!(epi = EPI_MEM_ALLOC())) + if (!(epi = kmem_cache_alloc(epi_cache, SLAB_KERNEL))) goto eexit_1; /* Item initialization follow here ... */ - EP_RB_INITNODE(&epi->rbn); + ep_rb_initnode(&epi->rbn); INIT_LIST_HEAD(&epi->rdllink); INIT_LIST_HEAD(&epi->fllink); INIT_LIST_HEAD(&epi->txlink); INIT_LIST_HEAD(&epi->pwqlist); epi->ep = ep; - EP_SET_FFD(&epi->ffd, tfile, fd); + ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; atomic_set(&epi->usecnt, 1); epi->nwait = 0; @@ -978,7 +1003,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, ep_rbtree_insert(ep, epi); /* If the file is already "ready" we drop it inside the ready list */ - if ((revents & event->events) && !EP_IS_LINKED(&epi->rdllink)) { + if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); /* Notify waiting tasks that events are available */ @@ -1007,11 +1032,11 @@ eexit_2: * allocated wait queue. */ write_lock_irqsave(&ep->lock, flags); - if (EP_IS_LINKED(&epi->rdllink)) - EP_LIST_DEL(&epi->rdllink); + if (ep_is_linked(&epi->rdllink)) + ep_list_del(&epi->rdllink); write_unlock_irqrestore(&ep->lock, flags); - EPI_MEM_FREE(epi); + kmem_cache_free(epi_cache, epi); eexit_1: return error; } @@ -1050,14 +1075,14 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * If the item is not linked to the hash it means that it's on its * way toward the removal. Do nothing in this case. */ - if (EP_RB_LINKED(&epi->rbn)) { + if (ep_rb_linked(&epi->rbn)) { /* * If the item is "hot" and it is not registered inside the ready * list, push it inside. If the item is not "hot" and it is currently * registered inside the ready list, unlink it. */ if (revents & event->events) { - if (!EP_IS_LINKED(&epi->rdllink)) { + if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); /* Notify waiting tasks that events are available */ @@ -1097,9 +1122,9 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) while (!list_empty(lsthead)) { pwq = list_entry(lsthead->next, struct eppoll_entry, llink); - EP_LIST_DEL(&pwq->llink); + ep_list_del(&pwq->llink); remove_wait_queue(pwq->whead, &pwq->wait); - PWQ_MEM_FREE(pwq); + kmem_cache_free(pwq_cache, pwq); } } } @@ -1118,7 +1143,7 @@ static int ep_unlink(struct eventpoll *ep, struct epitem *epi) * The check protect us from doing a double unlink ( crash ). */ error = -ENOENT; - if (!EP_RB_LINKED(&epi->rbn)) + if (!ep_rb_linked(&epi->rbn)) goto eexit_1; /* @@ -1133,14 +1158,14 @@ static int ep_unlink(struct eventpoll *ep, struct epitem *epi) * This operation togheter with the above check closes the door to * double unlinks. */ - EP_RB_ERASE(&epi->rbn, &ep->rbr); + ep_rb_erase(&epi->rbn, &ep->rbr); /* * If the item we are going to remove is inside the ready file descriptors * we want to remove it from this list to avoid stale events. */ - if (EP_IS_LINKED(&epi->rdllink)) - EP_LIST_DEL(&epi->rdllink); + if (ep_is_linked(&epi->rdllink)) + ep_list_del(&epi->rdllink); error = 0; eexit_1: @@ -1174,8 +1199,8 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_ep_lock); - if (EP_IS_LINKED(&epi->fllink)) - EP_LIST_DEL(&epi->fllink); + if (ep_is_linked(&epi->fllink)) + ep_list_del(&epi->fllink); spin_unlock(&file->f_ep_lock); /* We need to acquire the write IRQ lock before calling ep_unlink() */ @@ -1210,7 +1235,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k { int pwake = 0; unsigned long flags; - struct epitem *epi = EP_ITEM_FROM_WAIT(wait); + struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n", @@ -1228,7 +1253,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k goto is_disabled; /* If this file is already in the ready list we exit soon */ - if (EP_IS_LINKED(&epi->rdllink)) + if (ep_is_linked(&epi->rdllink)) goto is_linked; list_add_tail(&epi->rdllink, &ep->rdllist); @@ -1307,7 +1332,7 @@ static int ep_collect_ready_items(struct eventpoll *ep, struct list_head *txlist lnk = lnk->next; /* If this file is already in the ready list we exit soon */ - if (!EP_IS_LINKED(&epi->txlink)) { + if (!ep_is_linked(&epi->txlink)) { /* * This is initialized in this way so that the default * behaviour of the reinjecting code will be to push back @@ -1322,7 +1347,7 @@ static int ep_collect_ready_items(struct eventpoll *ep, struct list_head *txlist /* * Unlink the item from the ready list. */ - EP_LIST_DEL(&epi->rdllink); + ep_list_del(&epi->rdllink); } } @@ -1401,7 +1426,7 @@ static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist) epi = list_entry(txlist->next, struct epitem, txlink); /* Unlink the current item from the transfer list */ - EP_LIST_DEL(&epi->txlink); + ep_list_del(&epi->txlink); /* * If the item is no more linked to the interest set, we don't @@ -1410,8 +1435,8 @@ static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist) * item is set to have an Edge Triggered behaviour, we don't have * to push it back either. */ - if (EP_RB_LINKED(&epi->rbn) && !(epi->event.events & EPOLLET) && - (epi->revents & epi->event.events) && !EP_IS_LINKED(&epi->rdllink)) { + if (ep_rb_linked(&epi->rbn) && !(epi->event.events & EPOLLET) && + (epi->revents & epi->event.events) && !ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); ricnt++; } diff --git a/fs/exec.c b/fs/exec.c index 3a4b35a14c0d..48871917d363 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -58,6 +58,9 @@ int core_uses_pid; char core_pattern[65] = "core"; +int suid_dumpable = 0; + +EXPORT_SYMBOL(suid_dumpable); /* The maximal length of core_pattern is also specified in sysctl.c */ static struct linux_binfmt *formats; @@ -864,6 +867,9 @@ int flush_old_exec(struct linux_binprm * bprm) if (current->euid == current->uid && current->egid == current->gid) current->mm->dumpable = 1; + else + current->mm->dumpable = suid_dumpable; + name = bprm->filename; /* Copies the binary name from after last slash */ @@ -884,7 +890,7 @@ int flush_old_exec(struct linux_binprm * bprm) permission(bprm->file->f_dentry->d_inode,MAY_READ, NULL) || (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) { suid_keys(current); - current->mm->dumpable = 0; + current->mm->dumpable = suid_dumpable; } /* An exec changes our domain. We are no longer part of the thread @@ -1432,6 +1438,8 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) struct inode * inode; struct file * file; int retval = 0; + int fsuid = current->fsuid; + int flag = 0; binfmt = current->binfmt; if (!binfmt || !binfmt->core_dump) @@ -1441,6 +1449,16 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) up_write(&mm->mmap_sem); goto fail; } + + /* + * We cannot trust fsuid as being the "true" uid of the + * process nor do we know its entire history. We only know it + * was tainted so we dump it as root in mode 2. + */ + if (mm->dumpable == 2) { /* Setuid core dump mode */ + flag = O_EXCL; /* Stop rewrite attacks */ + current->fsuid = 0; /* Dump root private */ + } mm->dumpable = 0; init_completion(&mm->core_done); spin_lock_irq(¤t->sighand->siglock); @@ -1466,7 +1484,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) lock_kernel(); format_corename(corename, core_pattern, signr); unlock_kernel(); - file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE, 0600); + file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600); if (IS_ERR(file)) goto fail_unlock; inode = file->f_dentry->d_inode; @@ -1491,6 +1509,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) close_fail: filp_close(file, NULL); fail_unlock: + current->fsuid = fsuid; complete_all(&mm->core_done); fail: return retval; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 25f4a64fd6bc..213148c36ebe 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -396,12 +396,12 @@ static size_t ext2_xattr_list_acl_access(struct inode *inode, char *list, size_t list_size, const char *name, size_t name_len) { - const size_t size = sizeof(XATTR_NAME_ACL_ACCESS); + const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS); if (!test_opt(inode->i_sb, POSIX_ACL)) return 0; if (list && size <= list_size) - memcpy(list, XATTR_NAME_ACL_ACCESS, size); + memcpy(list, POSIX_ACL_XATTR_ACCESS, size); return size; } @@ -409,12 +409,12 @@ static size_t ext2_xattr_list_acl_default(struct inode *inode, char *list, size_t list_size, const char *name, size_t name_len) { - const size_t size = sizeof(XATTR_NAME_ACL_DEFAULT); + const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT); if (!test_opt(inode->i_sb, POSIX_ACL)) return 0; if (list && size <= list_size) - memcpy(list, XATTR_NAME_ACL_DEFAULT, size); + memcpy(list, POSIX_ACL_XATTR_DEFAULT, size); return size; } @@ -506,14 +506,14 @@ ext2_xattr_set_acl_default(struct inode *inode, const char *name, } struct xattr_handler ext2_xattr_acl_access_handler = { - .prefix = XATTR_NAME_ACL_ACCESS, + .prefix = POSIX_ACL_XATTR_ACCESS, .list = ext2_xattr_list_acl_access, .get = ext2_xattr_get_acl_access, .set = ext2_xattr_set_acl_access, }; struct xattr_handler ext2_xattr_acl_default_handler = { - .prefix = XATTR_NAME_ACL_DEFAULT, + .prefix = POSIX_ACL_XATTR_DEFAULT, .list = ext2_xattr_list_acl_default, .get = ext2_xattr_get_acl_default, .set = ext2_xattr_set_acl_default, diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h index fed96ae81a7d..0bde85bafe38 100644 --- a/fs/ext2/acl.h +++ b/fs/ext2/acl.h @@ -4,7 +4,7 @@ (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ -#include <linux/xattr_acl.h> +#include <linux/posix_acl_xattr.h> #define EXT2_ACL_VERSION 0x0001 diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 638c13a26c03..133f5aa581bb 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -417,12 +417,12 @@ static size_t ext3_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len, const char *name, size_t name_len) { - const size_t size = sizeof(XATTR_NAME_ACL_ACCESS); + const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS); if (!test_opt(inode->i_sb, POSIX_ACL)) return 0; if (list && size <= list_len) - memcpy(list, XATTR_NAME_ACL_ACCESS, size); + memcpy(list, POSIX_ACL_XATTR_ACCESS, size); return size; } @@ -430,12 +430,12 @@ static size_t ext3_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len, const char *name, size_t name_len) { - const size_t size = sizeof(XATTR_NAME_ACL_DEFAULT); + const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT); if (!test_opt(inode->i_sb, POSIX_ACL)) return 0; if (list && size <= list_len) - memcpy(list, XATTR_NAME_ACL_DEFAULT, size); + memcpy(list, POSIX_ACL_XATTR_DEFAULT, size); return size; } @@ -535,14 +535,14 @@ ext3_xattr_set_acl_default(struct inode *inode, const char *name, } struct xattr_handler ext3_xattr_acl_access_handler = { - .prefix = XATTR_NAME_ACL_ACCESS, + .prefix = POSIX_ACL_XATTR_ACCESS, .list = ext3_xattr_list_acl_access, .get = ext3_xattr_get_acl_access, .set = ext3_xattr_set_acl_access, }; struct xattr_handler ext3_xattr_acl_default_handler = { - .prefix = XATTR_NAME_ACL_DEFAULT, + .prefix = POSIX_ACL_XATTR_DEFAULT, .list = ext3_xattr_list_acl_default, .get = ext3_xattr_get_acl_default, .set = ext3_xattr_set_acl_default, diff --git a/fs/ext3/acl.h b/fs/ext3/acl.h index 98af0c0d0ba9..92d50b53a933 100644 --- a/fs/ext3/acl.h +++ b/fs/ext3/acl.h @@ -4,7 +4,7 @@ (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ -#include <linux/xattr_acl.h> +#include <linux/posix_acl_xattr.h> #define EXT3_ACL_VERSION 0x0001 diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 79742d824a0a..60e44e6dd7a6 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -932,8 +932,16 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry, struct inode *dir = dentry->d_parent->d_inode; sb = dir->i_sb; - if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err))) - return NULL; + /* NFS may look up ".." - look at dx_root directory block */ + if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){ + if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err))) + return NULL; + } else { + frame = frames; + frame->bh = NULL; /* for dx_release() */ + frame->at = (struct dx_entry *)frames; /* hack for zero entry*/ + dx_set_block(frame->at, 0); /* dx_root block is 0 */ + } hash = hinfo.hash; do { block = dx_get_block(frame->at); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 981ccb233ef5..9630fbfdc24a 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2348,22 +2348,8 @@ static int ext3_write_info(struct super_block *sb, int type) */ static int ext3_quota_on_mount(struct super_block *sb, int type) { - int err; - struct dentry *dentry; - struct qstr name = { .name = EXT3_SB(sb)->s_qf_names[type], - .hash = 0, - .len = strlen(EXT3_SB(sb)->s_qf_names[type])}; - - dentry = lookup_hash(&name, sb->s_root); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - err = vfs_quota_on_mount(type, EXT3_SB(sb)->s_jquota_fmt, dentry); - /* Now invalidate and put the dentry - quota got its own reference - * to inode and dentry has at least wrong hash so we had better - * throw it away */ - d_invalidate(dentry); - dput(dentry); - return err; + return vfs_quota_on_mount(sb, EXT3_SB(sb)->s_qf_names[type], + EXT3_SB(sb)->s_jquota_fmt, type); } /* diff --git a/fs/file_table.c b/fs/file_table.c index 03d83cb686b1..fa7849fae134 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -63,42 +63,45 @@ static inline void file_free(struct file *f) */ struct file *get_empty_filp(void) { -static int old_max; + static int old_max; struct file * f; /* * Privileged users can go above max_files */ - if (files_stat.nr_files < files_stat.max_files || - capable(CAP_SYS_ADMIN)) { - f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); - if (f) { - memset(f, 0, sizeof(*f)); - if (security_file_alloc(f)) { - file_free(f); - goto fail; - } - eventpoll_init_file(f); - atomic_set(&f->f_count, 1); - f->f_uid = current->fsuid; - f->f_gid = current->fsgid; - rwlock_init(&f->f_owner.lock); - /* f->f_version: 0 */ - INIT_LIST_HEAD(&f->f_list); - f->f_maxcount = INT_MAX; - return f; - } - } - + if (files_stat.nr_files >= files_stat.max_files && + !capable(CAP_SYS_ADMIN)) + goto over; + + f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); + if (f == NULL) + goto fail; + + memset(f, 0, sizeof(*f)); + if (security_file_alloc(f)) + goto fail_sec; + + eventpoll_init_file(f); + atomic_set(&f->f_count, 1); + f->f_uid = current->fsuid; + f->f_gid = current->fsgid; + rwlock_init(&f->f_owner.lock); + /* f->f_version: 0 */ + INIT_LIST_HEAD(&f->f_list); + f->f_maxcount = INT_MAX; + return f; + +over: /* Ran out of filps - report that */ - if (files_stat.max_files >= old_max) { + if (files_stat.nr_files > old_max) { printk(KERN_INFO "VFS: file-max limit %d reached\n", files_stat.max_files); - old_max = files_stat.max_files; - } else { - /* Big problems... */ - printk(KERN_WARNING "VFS: filp allocation failed\n"); + old_max = files_stat.nr_files; } + goto fail; + +fail_sec: + file_free(f); fail: return NULL; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8e050fa58218..e94ab398b717 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -485,32 +485,6 @@ static void set_sb_syncing(int val) spin_unlock(&sb_lock); } -/* - * Find a superblock with inodes that need to be synced - */ -static struct super_block *get_super_to_sync(void) -{ - struct super_block *sb; -restart: - spin_lock(&sb_lock); - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { - if (sb->s_syncing) - continue; - sb->s_syncing = 1; - sb->s_count++; - spin_unlock(&sb_lock); - down_read(&sb->s_umount); - if (!sb->s_root) { - drop_super(sb); - goto restart; - } - return sb; - } - spin_unlock(&sb_lock); - return NULL; -} - /** * sync_inodes - writes all inodes to disk * @wait: wait for completion @@ -530,23 +504,39 @@ restart: * outstanding dirty inodes, the writeback goes block-at-a-time within the * filesystem's write_inode(). This is extremely slow. */ -void sync_inodes(int wait) +static void __sync_inodes(int wait) { struct super_block *sb; - set_sb_syncing(0); - while ((sb = get_super_to_sync()) != NULL) { - sync_inodes_sb(sb, 0); - sync_blockdev(sb->s_bdev); - drop_super(sb); + spin_lock(&sb_lock); +restart: + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_syncing) + continue; + sb->s_syncing = 1; + sb->s_count++; + spin_unlock(&sb_lock); + down_read(&sb->s_umount); + if (sb->s_root) { + sync_inodes_sb(sb, wait); + sync_blockdev(sb->s_bdev); + } + up_read(&sb->s_umount); + spin_lock(&sb_lock); + if (__put_super_and_need_restart(sb)) + goto restart; } + spin_unlock(&sb_lock); +} + +void sync_inodes(int wait) +{ + set_sb_syncing(0); + __sync_inodes(0); + if (wait) { set_sb_syncing(0); - while ((sb = get_super_to_sync()) != NULL) { - sync_inodes_sb(sb, 1); - sync_blockdev(sb->s_bdev); - drop_super(sb); - } + __sync_inodes(1); } } diff --git a/fs/inode.c b/fs/inode.c index 801fe7f36280..1f9a3a2b89bc 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -500,7 +500,7 @@ repeat: continue; if (!test(inode, data)) continue; - if (inode->i_state & (I_FREEING|I_CLEAR)) { + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } @@ -525,7 +525,7 @@ repeat: continue; if (inode->i_sb != sb) continue; - if (inode->i_state & (I_FREEING|I_CLEAR)) { + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } @@ -727,7 +727,7 @@ EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode_lock); - if (!(inode->i_state & I_FREEING)) + if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) __iget(inode); else /* @@ -1024,17 +1024,21 @@ static void generic_forget_inode(struct inode *inode) if (!(inode->i_state & (I_DIRTY|I_LOCK))) list_move(&inode->i_list, &inode_unused); inodes_stat.nr_unused++; - spin_unlock(&inode_lock); - if (!sb || (sb->s_flags & MS_ACTIVE)) + if (!sb || (sb->s_flags & MS_ACTIVE)) { + spin_unlock(&inode_lock); return; + } + inode->i_state |= I_WILL_FREE; + spin_unlock(&inode_lock); write_inode_now(inode, 1); spin_lock(&inode_lock); + inode->i_state &= ~I_WILL_FREE; inodes_stat.nr_unused--; hlist_del_init(&inode->i_hash); } list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); - inode->i_state|=I_FREEING; + inode->i_state |= I_FREEING; inodes_stat.nr_inodes--; spin_unlock(&inode_lock); if (inode->i_data.nrpages) diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 30a2bf9eeda5..e892dab40c26 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -21,6 +21,7 @@ #include <linux/sched.h> #include <linux/fs.h> #include <linux/quotaops.h> +#include <linux/posix_acl_xattr.h> #include "jfs_incore.h" #include "jfs_xattr.h" #include "jfs_acl.h" @@ -36,11 +37,11 @@ static struct posix_acl *jfs_get_acl(struct inode *inode, int type) switch(type) { case ACL_TYPE_ACCESS: - ea_name = XATTR_NAME_ACL_ACCESS; + ea_name = POSIX_ACL_XATTR_ACCESS; p_acl = &ji->i_acl; break; case ACL_TYPE_DEFAULT: - ea_name = XATTR_NAME_ACL_DEFAULT; + ea_name = POSIX_ACL_XATTR_DEFAULT; p_acl = &ji->i_default_acl; break; default: @@ -88,11 +89,11 @@ static int jfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) switch(type) { case ACL_TYPE_ACCESS: - ea_name = XATTR_NAME_ACL_ACCESS; + ea_name = POSIX_ACL_XATTR_ACCESS; p_acl = &ji->i_acl; break; case ACL_TYPE_DEFAULT: - ea_name = XATTR_NAME_ACL_DEFAULT; + ea_name = POSIX_ACL_XATTR_DEFAULT; p_acl = &ji->i_default_acl; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; @@ -101,7 +102,7 @@ static int jfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) return -EINVAL; } if (acl) { - size = xattr_acl_size(acl->a_count); + size = posix_acl_xattr_size(acl->a_count); value = kmalloc(size, GFP_KERNEL); if (!value) return -ENOMEM; diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index d2ae430adecf..a3acd3eec059 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -20,8 +20,6 @@ #ifdef CONFIG_JFS_POSIX_ACL -#include <linux/xattr_acl.h> - int jfs_permission(struct inode *, int, struct nameidata *); int jfs_init_acl(struct inode *, struct inode *); int jfs_setattr(struct dentry *, struct iattr *); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 810a3653d8b3..ee32211288ce 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -24,6 +24,7 @@ #include <linux/completion.h> #include <linux/vfs.h> #include <linux/moduleparam.h> +#include <linux/posix_acl.h> #include <asm/uaccess.h> #include "jfs_incore.h" diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 6016373701a3..ee438d429d45 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -19,6 +19,7 @@ #include <linux/fs.h> #include <linux/xattr.h> +#include <linux/posix_acl_xattr.h> #include <linux/quotaops.h> #include "jfs_incore.h" #include "jfs_superblock.h" @@ -718,9 +719,9 @@ static int can_set_system_xattr(struct inode *inode, const char *name, return -EPERM; /* - * XATTR_NAME_ACL_ACCESS is tied to i_mode + * POSIX_ACL_XATTR_ACCESS is tied to i_mode */ - if (strcmp(name, XATTR_NAME_ACL_ACCESS) == 0) { + if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0) { acl = posix_acl_from_xattr(value, value_len); if (IS_ERR(acl)) { rc = PTR_ERR(acl); @@ -750,7 +751,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, JFS_IP(inode)->i_acl = JFS_ACL_NOT_CACHED; return 0; - } else if (strcmp(name, XATTR_NAME_ACL_DEFAULT) == 0) { + } else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0) { acl = posix_acl_from_xattr(value, value_len); if (IS_ERR(acl)) { rc = PTR_ERR(acl); diff --git a/fs/namei.c b/fs/namei.c index a7f7f44119b3..fa8df81ce8ca 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1577,19 +1577,35 @@ do_link: * * Simple function to lookup and return a dentry and create it * if it doesn't exist. Is SMP-safe. + * + * Returns with nd->dentry->d_inode->i_sem locked. */ struct dentry *lookup_create(struct nameidata *nd, int is_dir) { - struct dentry *dentry; + struct dentry *dentry = ERR_PTR(-EEXIST); down(&nd->dentry->d_inode->i_sem); - dentry = ERR_PTR(-EEXIST); + /* + * Yucky last component or no last component at all? + * (foo/., foo/.., /////) + */ if (nd->last_type != LAST_NORM) goto fail; nd->flags &= ~LOOKUP_PARENT; + + /* + * Do the final lookup. + */ dentry = lookup_hash(&nd->last, nd->dentry); if (IS_ERR(dentry)) goto fail; + + /* + * Special case - lookup gave negative, but... we had foo/bar/ + * From the vfs_mknod() POV we just have a negative dentry - + * all is fine. Let's be bastards - you had / on the end, you've + * been asking for (non-existent) directory. -ENOENT for you. + */ if (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode) goto enoent; return dentry; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index d6a30c844de3..6537f2c4ae44 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -751,11 +751,6 @@ nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t count, retval = -EFAULT; if (!access_ok(VERIFY_READ, iov.iov_base, iov.iov_len)) goto out; - if (file->f_error) { - retval = file->f_error; - file->f_error = 0; - goto out; - } retval = -EFBIG; if (limit != RLIM_INFINITY) { if (pos >= limit) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ae3940dc85cc..de340ffd33c3 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -50,7 +50,6 @@ #include <linux/posix_acl.h> #ifdef CONFIG_NFSD_V4 #include <linux/posix_acl_xattr.h> -#include <linux/xattr_acl.h> #include <linux/xattr.h> #include <linux/nfs4.h> #include <linux/nfs4_acl.h> @@ -425,13 +424,13 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; if (pacl) { - error = set_nfsv4_acl_one(dentry, pacl, XATTR_NAME_ACL_ACCESS); + error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS); if (error < 0) goto out_nfserr; } if (dpacl) { - error = set_nfsv4_acl_one(dentry, dpacl, XATTR_NAME_ACL_DEFAULT); + error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT); if (error < 0) goto out_nfserr; } @@ -498,7 +497,7 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_ac struct posix_acl *pacl = NULL, *dpacl = NULL; unsigned int flags = 0; - pacl = _get_posix_acl(dentry, XATTR_NAME_ACL_ACCESS); + pacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_ACCESS); if (IS_ERR(pacl) && PTR_ERR(pacl) == -ENODATA) pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL); if (IS_ERR(pacl)) { @@ -508,7 +507,7 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_ac } if (S_ISDIR(inode->i_mode)) { - dpacl = _get_posix_acl(dentry, XATTR_NAME_ACL_DEFAULT); + dpacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_DEFAULT); if (IS_ERR(dpacl) && PTR_ERR(dpacl) == -ENODATA) dpacl = NULL; else if (IS_ERR(dpacl)) { diff --git a/fs/open.c b/fs/open.c index 963bd81a44c8..8ec63f735918 100644 --- a/fs/open.c +++ b/fs/open.c @@ -21,6 +21,7 @@ #include <linux/vfs.h> #include <asm/uaccess.h> #include <linux/fs.h> +#include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> @@ -933,31 +934,27 @@ EXPORT_SYMBOL(fd_install); asmlinkage long sys_open(const char __user * filename, int flags, int mode) { char * tmp; - int fd, error; + int fd; + + if (force_o_largefile()) + flags |= O_LARGEFILE; -#if BITS_PER_LONG != 32 - flags |= O_LARGEFILE; -#endif tmp = getname(filename); fd = PTR_ERR(tmp); if (!IS_ERR(tmp)) { fd = get_unused_fd(); if (fd >= 0) { struct file *f = filp_open(tmp, flags, mode); - error = PTR_ERR(f); - if (IS_ERR(f)) - goto out_error; - fd_install(fd, f); + if (IS_ERR(f)) { + put_unused_fd(fd); + fd = PTR_ERR(f); + } else { + fd_install(fd, f); + } } -out: putname(tmp); } return fd; - -out_error: - put_unused_fd(fd); - fd = error; - goto out; } EXPORT_SYMBOL_GPL(sys_open); @@ -980,23 +977,15 @@ asmlinkage long sys_creat(const char __user * pathname, int mode) */ int filp_close(struct file *filp, fl_owner_t id) { - int retval; - - /* Report and clear outstanding errors */ - retval = filp->f_error; - if (retval) - filp->f_error = 0; + int retval = 0; if (!file_count(filp)) { printk(KERN_ERR "VFS: Close: file count is 0\n"); - return retval; + return 0; } - if (filp->f_op && filp->f_op->flush) { - int err = filp->f_op->flush(filp); - if (!retval) - retval = err; - } + if (filp->f_op && filp->f_op->flush) + retval = filp->f_op->flush(filp); dnotify_flush(filp, id); locks_remove_posix(filp, id); diff --git a/fs/proc/base.c b/fs/proc/base.c index e31903aadd96..ace151fa4878 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -314,7 +314,7 @@ static int may_ptrace_attach(struct task_struct *task) (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) goto out; rmb(); - if (!task->mm->dumpable && !capable(CAP_SYS_PTRACE)) + if (task->mm->dumpable != 1 && !capable(CAP_SYS_PTRACE)) goto out; if (security_ptrace(current, task)) goto out; @@ -1113,7 +1113,9 @@ static int task_dumpable(struct task_struct *task) if (mm) dumpable = mm->dumpable; task_unlock(task); - return dumpable; + if(dumpable == 1) + return 1; + return 0; } diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 63a9fbf1ac51..94b570ad037d 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -451,7 +451,7 @@ static int devices_read_proc(char *page, char **start, off_t off, int count, int *eof, void *data) { int len = get_chrdev_list(page); - len += get_blkdev_list(page+len); + len += get_blkdev_list(page+len, len); return proc_calc_metrics(page, start, off, count, eof, len); } diff --git a/fs/quota.c b/fs/quota.c index 3f0333a51a23..f5d1cff55196 100644 --- a/fs/quota.c +++ b/fs/quota.c @@ -149,36 +149,6 @@ static int check_quotactl_valid(struct super_block *sb, int type, int cmd, qid_t return error; } -static struct super_block *get_super_to_sync(int type) -{ - struct list_head *head; - int cnt, dirty; - -restart: - spin_lock(&sb_lock); - list_for_each(head, &super_blocks) { - struct super_block *sb = list_entry(head, struct super_block, s_list); - - /* This test just improves performance so it needn't be reliable... */ - for (cnt = 0, dirty = 0; cnt < MAXQUOTAS; cnt++) - if ((type == cnt || type == -1) && sb_has_quota_enabled(sb, cnt) - && info_any_dirty(&sb_dqopt(sb)->info[cnt])) - dirty = 1; - if (!dirty) - continue; - sb->s_count++; - spin_unlock(&sb_lock); - down_read(&sb->s_umount); - if (!sb->s_root) { - drop_super(sb); - goto restart; - } - return sb; - } - spin_unlock(&sb_lock); - return NULL; -} - static void quota_sync_sb(struct super_block *sb, int type) { int cnt; @@ -219,17 +189,35 @@ static void quota_sync_sb(struct super_block *sb, int type) void sync_dquots(struct super_block *sb, int type) { + int cnt, dirty; + if (sb) { if (sb->s_qcop->quota_sync) quota_sync_sb(sb, type); + return; } - else { - while ((sb = get_super_to_sync(type)) != NULL) { - if (sb->s_qcop->quota_sync) - quota_sync_sb(sb, type); - drop_super(sb); - } + + spin_lock(&sb_lock); +restart: + list_for_each_entry(sb, &super_blocks, s_list) { + /* This test just improves performance so it needn't be reliable... */ + for (cnt = 0, dirty = 0; cnt < MAXQUOTAS; cnt++) + if ((type == cnt || type == -1) && sb_has_quota_enabled(sb, cnt) + && info_any_dirty(&sb_dqopt(sb)->info[cnt])) + dirty = 1; + if (!dirty) + continue; + sb->s_count++; + spin_unlock(&sb_lock); + down_read(&sb->s_umount); + if (sb->s_root && sb->s_qcop->quota_sync) + quota_sync_sb(sb, type); + up_read(&sb->s_umount); + spin_lock(&sb_lock); + if (__put_super_and_need_restart(sb)) + goto restart; } + spin_unlock(&sb_lock); } /* Copy parameters and call proper function */ diff --git a/fs/read_write.c b/fs/read_write.c index c4c2bee373ed..9292f5fa4d62 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -203,6 +203,16 @@ Einval: return -EINVAL; } +static void wait_on_retry_sync_kiocb(struct kiocb *iocb) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + if (!kiocbIsKicked(iocb)) + schedule(); + else + kiocbClearKicked(iocb); + __set_current_state(TASK_RUNNING); +} + ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; @@ -210,7 +220,10 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos); + while (-EIOCBRETRY == + (ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos))) + wait_on_retry_sync_kiocb(&kiocb); + if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -258,7 +271,10 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; - ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos); + while (-EIOCBRETRY == + (ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos))) + wait_on_retry_sync_kiocb(&kiocb); + if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index b35b87744983..aae0779ed5b4 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1932,27 +1932,12 @@ static int reiserfs_write_info(struct super_block *sb, int type) } /* - * Turn on quotas during mount time - we need to find - * the quota file and such... + * Turn on quotas during mount time - we need to find the quota file and such... */ static int reiserfs_quota_on_mount(struct super_block *sb, int type) { - int err; - struct dentry *dentry; - struct qstr name = { .name = REISERFS_SB(sb)->s_qf_names[type], - .hash = 0, - .len = strlen(REISERFS_SB(sb)->s_qf_names[type])}; - - dentry = lookup_hash(&name, sb->s_root); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - err = vfs_quota_on_mount(type, REISERFS_SB(sb)->s_jquota_fmt, dentry); - /* Now invalidate and put the dentry - quota got its own reference - * to inode and dentry has at least wrong hash so we had better - * throw it away */ - d_invalidate(dentry); - dput(dentry); - return err; + return vfs_quota_on_mount(sb, REISERFS_SB(sb)->s_qf_names[type], + REISERFS_SB(sb)->s_jquota_fmt, type); } /* diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index e302071903a1..c312881c5f53 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -4,7 +4,7 @@ #include <linux/errno.h> #include <linux/pagemap.h> #include <linux/xattr.h> -#include <linux/xattr_acl.h> +#include <linux/posix_acl_xattr.h> #include <linux/reiserfs_xattr.h> #include <linux/reiserfs_acl.h> #include <asm/uaccess.h> @@ -192,11 +192,11 @@ reiserfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = XATTR_NAME_ACL_ACCESS; + name = POSIX_ACL_XATTR_ACCESS; p_acl = &reiserfs_i->i_acl_access; break; case ACL_TYPE_DEFAULT: - name = XATTR_NAME_ACL_DEFAULT; + name = POSIX_ACL_XATTR_DEFAULT; p_acl = &reiserfs_i->i_acl_default; break; default: @@ -260,7 +260,7 @@ reiserfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) switch (type) { case ACL_TYPE_ACCESS: - name = XATTR_NAME_ACL_ACCESS; + name = POSIX_ACL_XATTR_ACCESS; p_acl = &reiserfs_i->i_acl_access; if (acl) { mode_t mode = inode->i_mode; @@ -275,7 +275,7 @@ reiserfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) } break; case ACL_TYPE_DEFAULT: - name = XATTR_NAME_ACL_DEFAULT; + name = POSIX_ACL_XATTR_DEFAULT; p_acl = &reiserfs_i->i_acl_default; if (!S_ISDIR (inode->i_mode)) return acl ? -EACCES : 0; @@ -468,7 +468,7 @@ static int posix_acl_access_get(struct inode *inode, const char *name, void *buffer, size_t size) { - if (strlen(name) != sizeof(XATTR_NAME_ACL_ACCESS)-1) + if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS)-1) return -EINVAL; return xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size); } @@ -477,7 +477,7 @@ static int posix_acl_access_set(struct inode *inode, const char *name, const void *value, size_t size, int flags) { - if (strlen(name) != sizeof(XATTR_NAME_ACL_ACCESS)-1) + if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS)-1) return -EINVAL; return xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size); } @@ -487,7 +487,7 @@ posix_acl_access_del (struct inode *inode, const char *name) { struct reiserfs_inode_info *reiserfs_i = REISERFS_I(inode); struct posix_acl **acl = &reiserfs_i->i_acl_access; - if (strlen(name) != sizeof(XATTR_NAME_ACL_ACCESS)-1) + if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS)-1) return -EINVAL; if (!IS_ERR (*acl) && *acl) { posix_acl_release (*acl); @@ -510,7 +510,7 @@ posix_acl_access_list (struct inode *inode, const char *name, int namelen, char } struct reiserfs_xattr_handler posix_acl_access_handler = { - .prefix = XATTR_NAME_ACL_ACCESS, + .prefix = POSIX_ACL_XATTR_ACCESS, .get = posix_acl_access_get, .set = posix_acl_access_set, .del = posix_acl_access_del, @@ -521,7 +521,7 @@ static int posix_acl_default_get (struct inode *inode, const char *name, void *buffer, size_t size) { - if (strlen(name) != sizeof(XATTR_NAME_ACL_DEFAULT)-1) + if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT)-1) return -EINVAL; return xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size); } @@ -530,7 +530,7 @@ static int posix_acl_default_set(struct inode *inode, const char *name, const void *value, size_t size, int flags) { - if (strlen(name) != sizeof(XATTR_NAME_ACL_DEFAULT)-1) + if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT)-1) return -EINVAL; return xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size); } @@ -540,7 +540,7 @@ posix_acl_default_del (struct inode *inode, const char *name) { struct reiserfs_inode_info *reiserfs_i = REISERFS_I(inode); struct posix_acl **acl = &reiserfs_i->i_acl_default; - if (strlen(name) != sizeof(XATTR_NAME_ACL_DEFAULT)-1) + if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT)-1) return -EINVAL; if (!IS_ERR (*acl) && *acl) { posix_acl_release (*acl); @@ -563,7 +563,7 @@ posix_acl_default_list (struct inode *inode, const char *name, int namelen, char } struct reiserfs_xattr_handler posix_acl_default_handler = { - .prefix = XATTR_NAME_ACL_DEFAULT, + .prefix = POSIX_ACL_XATTR_DEFAULT, .get = posix_acl_default_get, .set = posix_acl_default_set, .del = posix_acl_default_del, diff --git a/fs/super.c b/fs/super.c index 573bcc81bb82..25bc1ec6bc5d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -341,20 +341,22 @@ static inline void write_super(struct super_block *sb) */ void sync_supers(void) { - struct super_block * sb; -restart: + struct super_block *sb; + spin_lock(&sb_lock); - sb = sb_entry(super_blocks.next); - while (sb != sb_entry(&super_blocks)) +restart: + list_for_each_entry(sb, &super_blocks, s_list) { if (sb->s_dirt) { sb->s_count++; spin_unlock(&sb_lock); down_read(&sb->s_umount); write_super(sb); - drop_super(sb); - goto restart; - } else - sb = sb_entry(sb->s_list.next); + up_read(&sb->s_umount); + spin_lock(&sb_lock); + if (__put_super_and_need_restart(sb)) + goto restart; + } + } spin_unlock(&sb_lock); } @@ -381,20 +383,16 @@ void sync_filesystems(int wait) down(&mutex); /* Could be down_interruptible */ spin_lock(&sb_lock); - for (sb = sb_entry(super_blocks.next); sb != sb_entry(&super_blocks); - sb = sb_entry(sb->s_list.next)) { + list_for_each_entry(sb, &super_blocks, s_list) { if (!sb->s_op->sync_fs) continue; if (sb->s_flags & MS_RDONLY) continue; sb->s_need_sync_fs = 1; } - spin_unlock(&sb_lock); restart: - spin_lock(&sb_lock); - for (sb = sb_entry(super_blocks.next); sb != sb_entry(&super_blocks); - sb = sb_entry(sb->s_list.next)) { + list_for_each_entry(sb, &super_blocks, s_list) { if (!sb->s_need_sync_fs) continue; sb->s_need_sync_fs = 0; @@ -405,8 +403,11 @@ restart: down_read(&sb->s_umount); if (sb->s_root && (wait || sb->s_dirt)) sb->s_op->sync_fs(sb, wait); - drop_super(sb); - goto restart; + up_read(&sb->s_umount); + /* restart only when sb is no longer on the list */ + spin_lock(&sb_lock); + if (__put_super_and_need_restart(sb)) + goto restart; } spin_unlock(&sb_lock); up(&mutex); @@ -422,21 +423,25 @@ restart: struct super_block * get_super(struct block_device *bdev) { - struct list_head *p; + struct super_block *sb; + if (!bdev) return NULL; -rescan: + spin_lock(&sb_lock); - list_for_each(p, &super_blocks) { - struct super_block *s = sb_entry(p); - if (s->s_bdev == bdev) { - s->s_count++; +rescan: + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_bdev == bdev) { + sb->s_count++; spin_unlock(&sb_lock); - down_read(&s->s_umount); - if (s->s_root) - return s; - drop_super(s); - goto rescan; + down_read(&sb->s_umount); + if (sb->s_root) + return sb; + up_read(&sb->s_umount); + /* restart only when sb is no longer on the list */ + spin_lock(&sb_lock); + if (__put_super_and_need_restart(sb)) + goto rescan; } } spin_unlock(&sb_lock); @@ -447,20 +452,22 @@ EXPORT_SYMBOL(get_super); struct super_block * user_get_super(dev_t dev) { - struct list_head *p; + struct super_block *sb; -rescan: spin_lock(&sb_lock); - list_for_each(p, &super_blocks) { - struct super_block *s = sb_entry(p); - if (s->s_dev == dev) { - s->s_count++; +rescan: + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_dev == dev) { + sb->s_count++; spin_unlock(&sb_lock); - down_read(&s->s_umount); - if (s->s_root) - return s; - drop_super(s); - goto rescan; + down_read(&sb->s_umount); + if (sb->s_root) + return sb; + up_read(&sb->s_umount); + /* restart only when sb is no longer on the list */ + spin_lock(&sb_lock); + if (__put_super_and_need_restart(sb)) + goto rescan; } } spin_unlock(&sb_lock); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 37d7a6875d86..59734ba1ee60 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -8,6 +8,7 @@ #include <linux/mount.h> #include <linux/module.h> #include <linux/kobject.h> +#include <linux/namei.h> #include "sysfs.h" DECLARE_RWSEM(sysfs_rename_sem); @@ -99,7 +100,7 @@ static int create_dir(struct kobject * k, struct dentry * p, umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; down(&p->d_inode->i_sem); - *d = sysfs_get_dentry(p,n); + *d = lookup_one_len(n, p, strlen(n)); if (!IS_ERR(*d)) { error = sysfs_make_dirent(p->d_fsdata, *d, k, mode, SYSFS_DIR); if (!error) { @@ -315,7 +316,7 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name) down(&parent->d_inode->i_sem); - new_dentry = sysfs_get_dentry(parent, new_name); + new_dentry = lookup_one_len(new_name, parent, strlen(new_name)); if (!IS_ERR(new_dentry)) { if (!new_dentry->d_inode) { error = kobject_set_name(kobj, "%s", new_name); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 849aac115460..e9cfa39f4099 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/dnotify.h> #include <linux/kobject.h> +#include <linux/namei.h> #include <asm/uaccess.h> #include <asm/semaphore.h> @@ -400,7 +401,7 @@ int sysfs_update_file(struct kobject * kobj, const struct attribute * attr) int res = -ENOENT; down(&dir->d_inode->i_sem); - victim = sysfs_get_dentry(dir, attr->name); + victim = lookup_one_len(attr->name, dir, strlen(attr->name)); if (!IS_ERR(victim)) { /* make sure dentry is really there */ if (victim->d_inode && @@ -443,7 +444,7 @@ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode) int res = -ENOENT; down(&dir->d_inode->i_sem); - victim = sysfs_get_dentry(dir, attr->name); + victim = lookup_one_len(attr->name, dir, strlen(attr->name)); if (!IS_ERR(victim)) { if (victim->d_inode && (victim->d_parent->d_inode == dir->d_inode)) { diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index f11ac5ea7021..122145b0895c 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -11,6 +11,7 @@ #include <linux/kobject.h> #include <linux/module.h> #include <linux/dcache.h> +#include <linux/namei.h> #include <linux/err.h> #include "sysfs.h" @@ -68,7 +69,8 @@ void sysfs_remove_group(struct kobject * kobj, struct dentry * dir; if (grp->name) - dir = sysfs_get_dentry(kobj->dentry,grp->name); + dir = lookup_one_len(grp->name, kobj->dentry, + strlen(grp->name)); else dir = dget(kobj->dentry); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index 565cac1d4200..8de13bafaa76 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -166,16 +166,6 @@ int sysfs_create(struct dentry * dentry, int mode, int (*init)(struct inode *)) return error; } -struct dentry * sysfs_get_dentry(struct dentry * parent, const char * name) -{ - struct qstr qstr; - - qstr.name = name; - qstr.len = strlen(name); - qstr.hash = full_name_hash(name,qstr.len); - return lookup_hash(&qstr,parent); -} - /* * Get the name for corresponding element represented by the given sysfs_dirent */ diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 29da6f5f07c8..3f8953e0e5d0 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -7,7 +7,6 @@ extern int sysfs_create(struct dentry *, int mode, int (*init)(struct inode *)); extern int sysfs_make_dirent(struct sysfs_dirent *, struct dentry *, void *, umode_t, int); -extern struct dentry * sysfs_get_dentry(struct dentry *, const char *); extern int sysfs_add_file(struct dentry *, const struct attribute *, int); extern void sysfs_hash_and_remove(struct dentry * dir, const char * name); |