diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/btrfs/ctree.c | 2 | ||||
-rw-r--r-- | fs/btrfs/ctree.h | 5 | ||||
-rw-r--r-- | fs/btrfs/dir-item.c | 10 | ||||
-rw-r--r-- | fs/btrfs/xattr.c | 159 | ||||
-rw-r--r-- | fs/dcache.c | 16 | ||||
-rw-r--r-- | fs/exec.c | 76 | ||||
-rw-r--r-- | fs/file_table.c | 148 | ||||
-rw-r--r-- | fs/internal.h | 3 | ||||
-rw-r--r-- | fs/open.c | 2 | ||||
-rw-r--r-- | fs/pipe.c | 55 | ||||
-rw-r--r-- | fs/super.c | 23 |
11 files changed, 211 insertions, 288 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 7fb054ba1b60..82f14a1da542 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2769,7 +2769,7 @@ done: */ if (!p->leave_spinning) btrfs_set_path_blocking(p); - if (ret < 0) + if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d6dd49b51ba8..c19444e412be 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -586,6 +586,7 @@ struct btrfs_path { unsigned int skip_locking:1; unsigned int leave_spinning:1; unsigned int search_commit_root:1; + unsigned int skip_release_on_error:1; }; /* @@ -3406,6 +3407,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_root *root, struct extent_buffer *leaf, struct btrfs_dir_item *dir_item); +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, + int name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 79e594e341c7..6f61b9b1526f 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -21,10 +21,6 @@ #include "hash.h" #include "transaction.h" -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len); - /* * insert a name into a directory, doing overflow properly if there is a hash * collision. data_size indicates how big the item inserted should be. On @@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, * this walks through all the entries in a dir item and finds one * for a specific name. */ -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len) +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, int name_len) { struct btrfs_dir_item *dir_item; unsigned long name_ptr; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 05740b9789e4..9cf20d63cc99 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -27,6 +27,7 @@ #include "transaction.h" #include "xattr.h" #include "disk-io.h" +#include "locking.h" ssize_t __btrfs_getxattr(struct inode *inode, const char *name, @@ -89,7 +90,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct btrfs_dir_item *di; + struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; size_t name_len = strlen(name); @@ -101,84 +102,128 @@ static int do_setxattr(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; + path->skip_release_on_error = 1; + + if (!value) { + di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), + name, name_len, -1); + if (!di && (flags & XATTR_REPLACE)) + ret = -ENODATA; + else if (di) + ret = btrfs_delete_one_dir_name(trans, root, path, di); + goto out; + } + /* + * For a replace we can't just do the insert blindly. + * Do a lookup first (read-only btrfs_search_slot), and return if xattr + * doesn't exist. If it exists, fall down below to the insert/replace + * path - we can't race with a concurrent xattr delete, because the VFS + * locks the inode's i_mutex before calling setxattr or removexattr. + */ if (flags & XATTR_REPLACE) { - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name, - name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { + if(!mutex_is_locked(&inode->i_mutex)) { + pr_err("BTRFS: assertion failed: %s, file: %s, line: %d", + "mutex_is_locked(&inode->i_mutex)", __FILE__, + __LINE__); + BUG(); + } + di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), + name, name_len, 0); + if (!di) { ret = -ENODATA; goto out; } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; btrfs_release_path(path); + di = NULL; + } + ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), + name, name_len, value, size); + if (ret == -EOVERFLOW) { /* - * remove the attribute + * We have an existing item in a leaf, split_leaf couldn't + * expand it. That item might have or not a dir_item that + * matches our target xattr, so lets check. */ - if (!value) - goto out; - } else { - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), - name, name_len, 0); - if (IS_ERR(di)) { - ret = PTR_ERR(di); + ret = 0; + btrfs_assert_tree_locked(path->nodes[0]); + di = btrfs_match_dir_item_name(root, path, name, name_len); + if (!di && !(flags & XATTR_REPLACE)) { + ret = -ENOSPC; goto out; } - if (!di && !value) - goto out; - btrfs_release_path(path); + } else if (ret == -EEXIST) { + ret = 0; + di = btrfs_match_dir_item_name(root, path, name, name_len); + if(!di) { /* logic error */ + pr_err("BTRFS: assertion failed: %s, file: %s, line: %d", + "di", __FILE__, __LINE__); + BUG(); + } + } else if (ret) { + goto out; } -again: - ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), - name, name_len, value, size); - /* - * If we're setting an xattr to a new value but the new value is say - * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting - * back from split_leaf. This is because it thinks we'll be extending - * the existing item size, but we're asking for enough space to add the - * item itself. So if we get EOVERFLOW just set ret to EEXIST and let - * the rest of the function figure it out. - */ - if (ret == -EOVERFLOW) + if (di && (flags & XATTR_CREATE)) { ret = -EEXIST; + goto out; + } - if (ret == -EEXIST) { - if (flags & XATTR_CREATE) - goto out; + if (di) { /* - * We can't use the path we already have since we won't have the - * proper locking for a delete, so release the path and - * re-lookup to delete the thing. + * We're doing a replace, and it must be atomic, that is, at + * any point in time we have either the old or the new xattr + * value in the tree. We don't want readers (getxattr and + * listxattrs) to miss a value, this is specially important + * for ACLs. */ - btrfs_release_path(path); - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), - name, name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { - /* Shouldn't happen but just in case... */ - btrfs_release_path(path); - goto again; + const int slot = path->slots[0]; + struct extent_buffer *leaf = path->nodes[0]; + const u16 old_data_len = btrfs_dir_data_len(leaf, di); + const u32 item_size = btrfs_item_size_nr(leaf, slot); + const u32 data_size = sizeof(*di) + name_len + size; + struct btrfs_item *item; + unsigned long data_ptr; + char *ptr; + + if (size > old_data_len) { + if (btrfs_leaf_free_space(root, leaf) < + (size - old_data_len)) { + ret = -ENOSPC; + goto out; + } } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; + if (old_data_len + name_len + sizeof(*di) == item_size) { + /* No other xattrs packed in the same leaf item. */ + if (size > old_data_len) + btrfs_extend_item(root, path, + size - old_data_len); + else if (size < old_data_len) + btrfs_truncate_item(root, path, data_size, 1); + } else { + /* There are other xattrs packed in the same item. */ + ret = btrfs_delete_one_dir_name(trans, root, path, di); + if (ret) + goto out; + btrfs_extend_item(root, path, data_size); + } + item = btrfs_item_nr(NULL, slot); + ptr = btrfs_item_ptr(leaf, slot, char); + ptr += btrfs_item_size(leaf, item) - data_size; + di = (struct btrfs_dir_item *)ptr; + btrfs_set_dir_data_len(leaf, di, size); + data_ptr = ((unsigned long)(di + 1)) + name_len; + write_extent_buffer(leaf, value, data_ptr, size); + btrfs_mark_buffer_dirty(leaf); + } else { /* - * We have a value to set, so go back and try to insert it now. + * Insert, and we had space for the xattr, so path->slots[0] is + * where our xattr dir_item is and btrfs_insert_xattr_item() + * filled it. */ - if (value) { - btrfs_release_path(path); - goto again; - } } out: btrfs_free_path(path); diff --git a/fs/dcache.c b/fs/dcache.c index e2800926ae05..38c4a302fab4 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1053,13 +1053,13 @@ ascend: /* might go back up the wrong parent if we have had a rename. */ if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; - next = child->d_child.next; - while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + /* go into the first sibling still alive */ + do { + next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); - next = next->next; - } + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } @@ -2977,13 +2977,13 @@ ascend: /* might go back up the wrong parent if we have had a rename. */ if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; - next = child->d_child.next; - while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + /* go into the first sibling still alive */ + do { + next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); - next = next->next; - } + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } diff --git a/fs/exec.c b/fs/exec.c index dd6aa61c8548..acbd7ac2deda 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1265,6 +1265,53 @@ static int check_unsafe_exec(struct linux_binprm *bprm) return res; } +static void bprm_fill_uid(struct linux_binprm *bprm) +{ + struct inode *inode; + unsigned int mode; + kuid_t uid; + kgid_t gid; + + /* clear any previous set[ug]id data from a previous binary */ + bprm->cred->euid = current_euid(); + bprm->cred->egid = current_egid(); + + if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) + return; + + if (current->no_new_privs) + return; + + inode = file_inode(bprm->file); + mode = ACCESS_ONCE(inode->i_mode); + if (!(mode & (S_ISUID|S_ISGID))) + return; + + /* Be careful if suid/sgid is set */ + mutex_lock(&inode->i_mutex); + + /* reload atomically mode/uid/gid now that lock held */ + mode = inode->i_mode; + uid = inode->i_uid; + gid = inode->i_gid; + mutex_unlock(&inode->i_mutex); + + /* We ignore suid/sgid if there are no mappings for them in the ns */ + if (!kuid_has_mapping(bprm->cred->user_ns, uid) || + !kgid_has_mapping(bprm->cred->user_ns, gid)) + return; + + if (mode & S_ISUID) { + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->euid = uid; + } + + if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->egid = gid; + } +} + /* * Fill the binprm structure from the inode. * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes @@ -1273,39 +1320,12 @@ static int check_unsafe_exec(struct linux_binprm *bprm) */ int prepare_binprm(struct linux_binprm *bprm) { - umode_t mode; - struct inode * inode = file_inode(bprm->file); int retval; - mode = inode->i_mode; if (bprm->file->f_op == NULL) return -EACCES; - /* clear any previous set[ug]id data from a previous binary */ - bprm->cred->euid = current_euid(); - bprm->cred->egid = current_egid(); - - if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && - !current->no_new_privs && - kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) && - kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) { - /* Set-uid? */ - if (mode & S_ISUID) { - bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->euid = inode->i_uid; - } - - /* Set-gid? */ - /* - * If setgid is set but no group execute bit then this - * is a candidate for mandatory locking, not a setgid - * executable. - */ - if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { - bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->egid = inode->i_gid; - } - } + bprm_fill_uid(bprm); /* fill in binprm security blob */ retval = security_bprm_set_creds(bprm); diff --git a/fs/file_table.c b/fs/file_table.c index 54a34be444f9..28f02a7cbba1 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -36,8 +36,6 @@ struct files_stat_struct files_stat = { .max_files = NR_FILE }; -DEFINE_STATIC_LGLOCK(files_lglock); - /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __read_mostly; @@ -134,7 +132,6 @@ struct file *get_empty_filp(void) return ERR_PTR(error); } - INIT_LIST_HEAD(&f->f_u.fu_list); atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); @@ -265,18 +262,15 @@ static void __fput(struct file *file) mntput(mnt); } -static DEFINE_SPINLOCK(delayed_fput_lock); -static LIST_HEAD(delayed_fput_list); +static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { - LIST_HEAD(head); - spin_lock_irq(&delayed_fput_lock); - list_splice_init(&delayed_fput_list, &head); - spin_unlock_irq(&delayed_fput_lock); - while (!list_empty(&head)) { - struct file *f = list_first_entry(&head, struct file, f_u.fu_list); - list_del_init(&f->f_u.fu_list); - __fput(f); + struct llist_node *node = llist_del_all(&delayed_fput_list); + struct llist_node *next; + + for (; node; node = next) { + next = llist_next(node); + __fput(llist_entry(node, struct file, f_u.fu_llist)); } } @@ -306,18 +300,15 @@ void fput(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; - unsigned long flags; - file_sb_list_del(file); if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_u.fu_rcuhead, ____fput); if (!task_work_add(task, &file->f_u.fu_rcuhead, true)) return; } - spin_lock_irqsave(&delayed_fput_lock, flags); - list_add(&file->f_u.fu_list, &delayed_fput_list); - schedule_work(&delayed_fput_work); - spin_unlock_irqrestore(&delayed_fput_lock, flags); + + if (llist_add(&file->f_u.fu_llist, &delayed_fput_list)) + schedule_work(&delayed_fput_work); } } @@ -333,7 +324,6 @@ void __fput_sync(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; - file_sb_list_del(file); BUG_ON(!(task->flags & PF_KTHREAD)); __fput(file); } @@ -345,127 +335,10 @@ void put_filp(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { security_file_free(file); - file_sb_list_del(file); file_free(file); } } -static inline int file_list_cpu(struct file *file) -{ -#ifdef CONFIG_SMP - return file->f_sb_list_cpu; -#else - return smp_processor_id(); -#endif -} - -/* helper for file_sb_list_add to reduce ifdefs */ -static inline void __file_sb_list_add(struct file *file, struct super_block *sb) -{ - struct list_head *list; -#ifdef CONFIG_SMP - int cpu; - cpu = smp_processor_id(); - file->f_sb_list_cpu = cpu; - list = per_cpu_ptr(sb->s_files, cpu); -#else - list = &sb->s_files; -#endif - list_add(&file->f_u.fu_list, list); -} - -/** - * file_sb_list_add - add a file to the sb's file list - * @file: file to add - * @sb: sb to add it to - * - * Use this function to associate a file with the superblock of the inode it - * refers to. - */ -void file_sb_list_add(struct file *file, struct super_block *sb) -{ - lg_local_lock(&files_lglock); - __file_sb_list_add(file, sb); - lg_local_unlock(&files_lglock); -} - -/** - * file_sb_list_del - remove a file from the sb's file list - * @file: file to remove - * @sb: sb to remove it from - * - * Use this function to remove a file from its superblock. - */ -void file_sb_list_del(struct file *file) -{ - if (!list_empty(&file->f_u.fu_list)) { - lg_local_lock_cpu(&files_lglock, file_list_cpu(file)); - list_del_init(&file->f_u.fu_list); - lg_local_unlock_cpu(&files_lglock, file_list_cpu(file)); - } -} - -#ifdef CONFIG_SMP - -/* - * These macros iterate all files on all CPUs for a given superblock. - * files_lglock must be held globally. - */ -#define do_file_list_for_each_entry(__sb, __file) \ -{ \ - int i; \ - for_each_possible_cpu(i) { \ - struct list_head *list; \ - list = per_cpu_ptr((__sb)->s_files, i); \ - list_for_each_entry((__file), list, f_u.fu_list) - -#define while_file_list_for_each_entry \ - } \ -} - -#else - -#define do_file_list_for_each_entry(__sb, __file) \ -{ \ - struct list_head *list; \ - list = &(sb)->s_files; \ - list_for_each_entry((__file), list, f_u.fu_list) - -#define while_file_list_for_each_entry \ -} - -#endif - -/** - * mark_files_ro - mark all files read-only - * @sb: superblock in question - * - * All files are marked read-only. We don't care about pending - * delete files so this should be used in 'force' mode only. - */ -void mark_files_ro(struct super_block *sb) -{ - struct file *f; - - lg_global_lock(&files_lglock); - do_file_list_for_each_entry(sb, f) { - if (!S_ISREG(file_inode(f)->i_mode)) - continue; - if (!file_count(f)) - continue; - if (!(f->f_mode & FMODE_WRITE)) - continue; - spin_lock(&f->f_lock); - f->f_mode &= ~FMODE_WRITE; - spin_unlock(&f->f_lock); - if (file_check_writeable(f) != 0) - continue; - __mnt_drop_write(f->f_path.mnt); - file_release_write(f); - } while_file_list_for_each_entry; - lg_global_unlock(&files_lglock); -} - void __init files_init(unsigned long mempages) { unsigned long n; @@ -481,6 +354,5 @@ void __init files_init(unsigned long mempages) n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); - lg_lock_init(&files_lglock, "files_lglock"); percpu_counter_init(&nr_files, 0); } diff --git a/fs/internal.h b/fs/internal.h index 68121584ae37..2ffa65a36ca0 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -74,9 +74,6 @@ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ -extern void file_sb_list_add(struct file *f, struct super_block *sb); -extern void file_sb_list_del(struct file *f); -extern void mark_files_ro(struct super_block *); extern struct file *get_empty_filp(void); /* diff --git a/fs/open.c b/fs/open.c index 86092bde31f4..5f129683b7d7 100644 --- a/fs/open.c +++ b/fs/open.c @@ -674,7 +674,6 @@ static int do_dentry_open(struct file *f, } f->f_mapping = inode->i_mapping; - file_sb_list_add(f, inode->i_sb); if (unlikely(f->f_mode & FMODE_PATH)) { f->f_op = &empty_fops; @@ -709,7 +708,6 @@ static int do_dentry_open(struct file *f, cleanup_all: fops_put(f->f_op); - file_sb_list_del(f); if (f->f_mode & FMODE_WRITE) { if (!special_file(inode->i_mode)) { /* diff --git a/fs/pipe.c b/fs/pipe.c index 0e0752ef2715..3e7ab278bb0c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -117,25 +117,27 @@ void pipe_wait(struct pipe_inode_info *pipe) } static int -pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len, - int atomic) +pipe_iov_copy_from_user(void *addr, int *offset, struct iovec *iov, + size_t *remaining, int atomic) { unsigned long copy; - while (len > 0) { + while (*remaining > 0) { while (!iov->iov_len) iov++; - copy = min_t(unsigned long, len, iov->iov_len); + copy = min_t(unsigned long, *remaining, iov->iov_len); if (atomic) { - if (__copy_from_user_inatomic(to, iov->iov_base, copy)) + if (__copy_from_user_inatomic(addr + *offset, + iov->iov_base, copy)) return -EFAULT; } else { - if (copy_from_user(to, iov->iov_base, copy)) + if (copy_from_user(addr + *offset, + iov->iov_base, copy)) return -EFAULT; } - to += copy; - len -= copy; + *offset += copy; + *remaining -= copy; iov->iov_base += copy; iov->iov_len -= copy; } @@ -143,25 +145,27 @@ pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len, } static int -pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len, - int atomic) +pipe_iov_copy_to_user(struct iovec *iov, void *addr, int *offset, + size_t *remaining, int atomic) { unsigned long copy; - while (len > 0) { + while (*remaining > 0) { while (!iov->iov_len) iov++; - copy = min_t(unsigned long, len, iov->iov_len); + copy = min_t(unsigned long, *remaining, iov->iov_len); if (atomic) { - if (__copy_to_user_inatomic(iov->iov_base, from, copy)) + if (__copy_to_user_inatomic(iov->iov_base, + addr + *offset, copy)) return -EFAULT; } else { - if (copy_to_user(iov->iov_base, from, copy)) + if (copy_to_user(iov->iov_base, + addr + *offset, copy)) return -EFAULT; } - from += copy; - len -= copy; + *offset += copy; + *remaining -= copy; iov->iov_base += copy; iov->iov_len -= copy; } @@ -395,7 +399,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, struct pipe_buffer *buf = pipe->bufs + curbuf; const struct pipe_buf_operations *ops = buf->ops; void *addr; - size_t chars = buf->len; + size_t chars = buf->len, remaining; int error, atomic; if (chars > total_len) @@ -409,9 +413,11 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, } atomic = !iov_fault_in_pages_write(iov, chars); + remaining = chars; redo: addr = ops->map(pipe, buf, atomic); - error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic); + error = pipe_iov_copy_to_user(iov, addr, &buf->offset, + &remaining, atomic); ops->unmap(pipe, buf, addr); if (unlikely(error)) { /* @@ -426,7 +432,6 @@ redo: break; } ret += chars; - buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ @@ -531,6 +536,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, if (ops->can_merge && offset + chars <= PAGE_SIZE) { int error, atomic = 1; void *addr; + size_t remaining = chars; error = ops->confirm(pipe, buf); if (error) @@ -539,8 +545,8 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, iov_fault_in_pages_read(iov, chars); redo1: addr = ops->map(pipe, buf, atomic); - error = pipe_iov_copy_from_user(offset + addr, iov, - chars, atomic); + error = pipe_iov_copy_from_user(addr, &offset, iov, + &remaining, atomic); ops->unmap(pipe, buf, addr); ret = error; do_wakeup = 1; @@ -575,6 +581,8 @@ redo1: struct page *page = pipe->tmp_page; char *src; int error, atomic = 1; + int offset = 0; + size_t remaining; if (!page) { page = alloc_page(GFP_HIGHUSER); @@ -595,14 +603,15 @@ redo1: chars = total_len; iov_fault_in_pages_read(iov, chars); + remaining = chars; redo2: if (atomic) src = kmap_atomic(page); else src = kmap(page); - error = pipe_iov_copy_from_user(src, iov, chars, - atomic); + error = pipe_iov_copy_from_user(src, &offset, iov, + &remaining, atomic); if (atomic) kunmap_atomic(src); else diff --git a/fs/super.c b/fs/super.c index e028b508db25..97280e76179c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -163,19 +163,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) s = NULL; goto out; } -#ifdef CONFIG_SMP - s->s_files = alloc_percpu(struct list_head); - if (!s->s_files) - goto err_out; - else { - int i; - - for_each_possible_cpu(i) - INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i)); - } -#else - INIT_LIST_HEAD(&s->s_files); -#endif if (init_sb_writers(s, type)) goto err_out; s->s_flags = flags; @@ -225,10 +212,6 @@ out: return s; err_out: security_sb_free(s); -#ifdef CONFIG_SMP - if (s->s_files) - free_percpu(s->s_files); -#endif destroy_sb_writers(s); kfree(s); s = NULL; @@ -243,9 +226,6 @@ err_out: */ static inline void destroy_super(struct super_block *s) { -#ifdef CONFIG_SMP - free_percpu(s->s_files); -#endif destroy_sb_writers(s); security_sb_free(s); WARN_ON(!list_empty(&s->s_mounts)); @@ -727,7 +707,8 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) make sure there are no rw files opened */ if (remount_ro) { if (force) { - mark_files_ro(sb); + sb->s_readonly_remount = 1; + smp_wmb(); } else { retval = sb_prepare_remount_readonly(sb); if (retval) |