diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-08-01 10:26:23 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-08-01 10:26:23 -0700 |
| commit | a0e881b7c189fa2bd76c024dbff91e79511c971d (patch) | |
| tree | 0c801918565b08921d21aceee5b326f64d998f5f /fs | |
| parent | eff0d13f3823f35d70228cd151d2a2c89288ff32 (diff) | |
| parent | dbc6e0222d79e78925fe20733844a796a4b72cf9 (diff) | |
| download | op-kernel-dev-a0e881b7c189fa2bd76c024dbff91e79511c971d.zip op-kernel-dev-a0e881b7c189fa2bd76c024dbff91e79511c971d.tar.gz | |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull second vfs pile from Al Viro:
"The stuff in there: fsfreeze deadlock fixes by Jan (essentially, the
deadlock reproduced by xfstests 068), symlink and hardlink restriction
patches, plus assorted cleanups and fixes.
Note that another fsfreeze deadlock (emergency thaw one) is *not*
dealt with - the series by Fernando conflicts a lot with Jan's, breaks
userland ABI (FIFREEZE semantics gets changed) and trades the deadlock
for massive vfsmount leak; this is going to be handled next cycle.
There probably will be another pull request, but that stuff won't be
in it."
Fix up trivial conflicts due to unrelated changes next to each other in
drivers/{staging/gdm72xx/usb_boot.c, usb/gadget/storage_common.c}
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (54 commits)
delousing target_core_file a bit
Documentation: Correct s_umount state for freeze_fs/unfreeze_fs
fs: Remove old freezing mechanism
ext2: Implement freezing
btrfs: Convert to new freezing mechanism
nilfs2: Convert to new freezing mechanism
ntfs: Convert to new freezing mechanism
fuse: Convert to new freezing mechanism
gfs2: Convert to new freezing mechanism
ocfs2: Convert to new freezing mechanism
xfs: Convert to new freezing code
ext4: Convert to new freezing mechanism
fs: Protect write paths by sb_start_write - sb_end_write
fs: Skip atime update on frozen filesystem
fs: Add freezing handling to mnt_want_write() / mnt_drop_write()
fs: Improve filesystem freezing handling
switch the protection of percpu_counter list to spinlock
nfsd: Push mnt_want_write() outside of i_mutex
btrfs: Push mnt_want_write() outside of i_mutex
fat: Push mnt_want_write() outside of i_mutex
...
Diffstat (limited to 'fs')
57 files changed, 937 insertions, 412 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index fc06fd2..dd6f7ee 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -610,6 +610,9 @@ v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n", page, (unsigned long)filp->private_data); + /* Update file times before taking page lock */ + file_update_time(filp); + v9inode = V9FS_I(inode); /* make sure the cache has finished storing the page */ v9fs_fscache_wait_on_page_write(inode, page); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index fadeba6..62e0caf 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1614,8 +1614,6 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; do { - vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE); - if (!(root->fs_info->sb->s_flags & MS_RDONLY) && mutex_trylock(&root->fs_info->cleaner_mutex)) { btrfs_run_delayed_iputs(root); @@ -1647,7 +1645,6 @@ static int transaction_kthread(void *arg) do { cannot_commit = false; delay = HZ * 30; - vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE); mutex_lock(&root->fs_info->transaction_kthread_mutex); spin_lock(&root->fs_info->trans_lock); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9aa01ec..5caf285 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1379,7 +1379,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, ssize_t err = 0; size_t count, ocount; - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + sb_start_write(inode->i_sb); mutex_lock(&inode->i_mutex); @@ -1469,6 +1469,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, num_written = err; } out: + sb_end_write(inode->i_sb); current->backing_dev_info = NULL; return num_written ? num_written : err; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 48bdfd2..83baec2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6629,6 +6629,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_start; u64 page_end; + sb_start_pagefault(inode->i_sb); ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); if (!ret) { ret = file_update_time(vma->vm_file); @@ -6718,12 +6719,15 @@ again: unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS); out_unlock: - if (!ret) + if (!ret) { + sb_end_pagefault(inode->i_sb); return VM_FAULT_LOCKED; + } unlock_page(page); out: btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); out_noreserve: + sb_end_pagefault(inode->i_sb); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 43f0012..bc2f6ff 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -195,6 +195,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (!inode_owner_or_capable(inode)) return -EACCES; + ret = mnt_want_write_file(file); + if (ret) + return ret; + mutex_lock(&inode->i_mutex); ip_oldflags = ip->flags; @@ -209,10 +213,6 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } } - ret = mnt_want_write_file(file); - if (ret) - goto out_unlock; - if (flags & FS_SYNC_FL) ip->flags |= BTRFS_INODE_SYNC; else @@ -275,9 +275,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) inode->i_flags = i_oldflags; } - mnt_drop_write_file(file); out_unlock: mutex_unlock(&inode->i_mutex); + mnt_drop_write_file(file); return ret; } @@ -664,6 +664,10 @@ static noinline int btrfs_mksubvol(struct path *parent, struct dentry *dentry; int error; + error = mnt_want_write(parent->mnt); + if (error) + return error; + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); dentry = lookup_one_len(name, parent->dentry, namelen); @@ -699,6 +703,7 @@ out_dput: dput(dentry); out_unlock: mutex_unlock(&dir->i_mutex); + mnt_drop_write(parent->mnt); return error; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 7ac7cdc..17be3de 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -335,6 +335,8 @@ again: if (!h) return ERR_PTR(-ENOMEM); + sb_start_intwrite(root->fs_info->sb); + if (may_wait_transaction(root, type)) wait_current_trans(root); @@ -345,6 +347,7 @@ again: } while (ret == -EBUSY); if (ret < 0) { + sb_end_intwrite(root->fs_info->sb); kmem_cache_free(btrfs_trans_handle_cachep, h); return ERR_PTR(ret); } @@ -548,6 +551,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_metadata(trans, root); trans->block_rsv = NULL; + sb_end_intwrite(root->fs_info->sb); + if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) && should_end_transaction(trans, root)) { trans->transaction->blocked = 1; @@ -1578,6 +1583,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, put_transaction(cur_trans); put_transaction(cur_trans); + sb_end_intwrite(root->fs_info->sb); + trace_btrfs_transaction_commit(root); btrfs_scrub_continue(root); diff --git a/fs/buffer.c b/fs/buffer.c index c7062c8..9f6d2e4 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2306,8 +2306,8 @@ EXPORT_SYMBOL(block_commit_write); * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * - * Direct callers of this function should call vfs_check_frozen() so that page - * fault does not busyloop until the fs is thawed. + * Direct callers of this function should protect against filesystem freezing + * using sb_start_write() - sb_end_write() functions. */ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) @@ -2318,6 +2318,12 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, loff_t size; int ret; + /* + * Update file times before taking page lock. We may end up failing the + * fault so this update may be superfluous but who really cares... + */ + file_update_time(vma->vm_file); + lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || @@ -2339,18 +2345,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, if (unlikely(ret < 0)) goto out_unlock; - /* - * Freezing in progress? We check after the page is marked dirty and - * with page lock held so if the test here fails, we are sure freezing - * code will wait during syncing until the page fault is done - at that - * point page will be dirty and unlocked so freezing code will write it - * and writeprotect it again. - */ set_page_dirty(page); - if (inode->i_sb->s_frozen != SB_UNFROZEN) { - ret = -EAGAIN; - goto out_unlock; - } wait_on_page_writeback(page); return 0; out_unlock: @@ -2365,12 +2360,9 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, int ret; struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb; - /* - * This check is racy but catches the common case. The check in - * __block_page_mkwrite() is reliable. - */ - vfs_check_frozen(sb, SB_FREEZE_WRITE); + sb_start_pagefault(sb); ret = __block_page_mkwrite(vma, vmf, get_block); + sb_end_pagefault(sb); return block_page_mkwrite_return(ret); } EXPORT_SYMBOL(block_page_mkwrite); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8b67304..452e71a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1184,6 +1184,9 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) loff_t size, len; int ret; + /* Update time before taking page lock */ + file_update_time(vma->vm_file); + size = i_size_read(inode); if (off + PAGE_CACHE_SIZE <= size) len = PAGE_CACHE_SIZE; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index ffa2be5..c3ca12c 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -318,21 +318,20 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry, struct vfsmount *lower_mnt; int rc = 0; - lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent)); - fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode); - BUG_ON(!lower_dentry->d_count); - dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL); - ecryptfs_set_dentry_private(dentry, dentry_info); if (!dentry_info) { printk(KERN_ERR "%s: Out of memory whilst attempting " "to allocate ecryptfs_dentry_info struct\n", __func__); dput(lower_dentry); - mntput(lower_mnt); - d_drop(dentry); return -ENOMEM; } + + lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent)); + fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode); + BUG_ON(!lower_dentry->d_count); + + ecryptfs_set_dentry_private(dentry, dentry_info); ecryptfs_set_dentry_lower(dentry, lower_dentry); ecryptfs_set_dentry_lower_mnt(dentry, lower_mnt); @@ -381,12 +380,6 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, struct dentry *lower_dir_dentry, *lower_dentry; int rc = 0; - if ((ecryptfs_dentry->d_name.len == 1 - && !strcmp(ecryptfs_dentry->d_name.name, ".")) - || (ecryptfs_dentry->d_name.len == 2 - && !strcmp(ecryptfs_dentry->d_name.name, ".."))) { - goto out_d_drop; - } lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent); mutex_lock(&lower_dir_dentry->d_inode->i_mutex); lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name, @@ -397,8 +390,8 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, rc = PTR_ERR(lower_dentry); ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " "[%d] on lower_dentry = [%s]\n", __func__, rc, - encrypted_and_encoded_name); - goto out_d_drop; + ecryptfs_dentry->d_name.name); + goto out; } if (lower_dentry->d_inode) goto interpose; @@ -415,7 +408,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt and encode " "filename; rc = [%d]\n", __func__, rc); - goto out_d_drop; + goto out; } mutex_lock(&lower_dir_dentry->d_inode->i_mutex); lower_dentry = lookup_one_len(encrypted_and_encoded_name, @@ -427,14 +420,11 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " "[%d] on lower_dentry = [%s]\n", __func__, rc, encrypted_and_encoded_name); - goto out_d_drop; + goto out; } interpose: rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry, ecryptfs_dir_inode); - goto out; -out_d_drop: - d_drop(ecryptfs_dentry); out: kfree(encrypted_and_encoded_name); return ERR_PTR(rc); @@ -2069,25 +2069,18 @@ static void wait_for_dump_helpers(struct file *file) */ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) { - struct file *rp, *wp; + struct file *files[2]; struct fdtable *fdt; struct coredump_params *cp = (struct coredump_params *)info->data; struct files_struct *cf = current->files; + int err = create_pipe_files(files, 0); + if (err) + return err; - wp = create_write_pipe(0); - if (IS_ERR(wp)) - return PTR_ERR(wp); - - rp = create_read_pipe(wp, 0); - if (IS_ERR(rp)) { - free_write_pipe(wp); - return PTR_ERR(rp); - } - - cp->file = wp; + cp->file = files[1]; sys_close(0); - fd_install(0, rp); + fd_install(0, files[0]); spin_lock(&cf->file_lock); fdt = files_fdtable(cf); __set_open_fd(0, fdt); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 264d315..6363ac6 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -79,6 +79,7 @@ void ext2_evict_inode(struct inode * inode) truncate_inode_pages(&inode->i_data, 0); if (want_delete) { + sb_start_intwrite(inode->i_sb); /* set dtime */ EXT2_I(inode)->i_dtime = get_seconds(); mark_inode_dirty(inode); @@ -98,8 +99,10 @@ void ext2_evict_inode(struct inode * inode) if (unlikely(rsv)) kfree(rsv); - if (want_delete) + if (want_delete) { ext2_free_inode(inode); + sb_end_intwrite(inode->i_sb); + } } typedef struct { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 9f311d2..af74d9e 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -42,6 +42,8 @@ static void ext2_sync_super(struct super_block *sb, static int ext2_remount (struct super_block * sb, int * flags, char * data); static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf); static int ext2_sync_fs(struct super_block *sb, int wait); +static int ext2_freeze(struct super_block *sb); +static int ext2_unfreeze(struct super_block *sb); void ext2_error(struct super_block *sb, const char *function, const char *fmt, ...) @@ -305,6 +307,8 @@ static const struct super_operations ext2_sops = { .evict_inode = ext2_evict_inode, .put_super = ext2_put_super, .sync_fs = ext2_sync_fs, + .freeze_fs = ext2_freeze, + .unfreeze_fs = ext2_unfreeze, .statfs = ext2_statfs, .remount_fs = ext2_remount, .show_options = ext2_show_options, @@ -1200,6 +1204,35 @@ static int ext2_sync_fs(struct super_block *sb, int wait) return 0; } +static int ext2_freeze(struct super_block *sb) +{ + struct ext2_sb_info *sbi = EXT2_SB(sb); + + /* + * Open but unlinked files present? Keep EXT2_VALID_FS flag cleared + * because we have unattached inodes and thus filesystem is not fully + * consistent. + */ + if (atomic_long_read(&sb->s_remove_count)) { + ext2_sync_fs(sb, 1); + return 0; + } + /* Set EXT2_FS_VALID flag */ + spin_lock(&sbi->s_lock); + sbi->s_es->s_state = cpu_to_le16(sbi->s_mount_state); + spin_unlock(&sbi->s_lock); + ext2_sync_super(sb, sbi->s_es, 1); + + return 0; +} + +static int ext2_unfreeze(struct super_block *sb) +{ + /* Just write sb to clear EXT2_VALID_FS flag */ + ext2_write_super(sb); + + return 0; +} void ext2_write_super(struct super_block *sb) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 89b59cb..6324f74e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -233,6 +233,11 @@ void ext4_evict_inode(struct inode *inode) if (is_bad_inode(inode)) goto no_delete; + /* + * Protect us against freezing - iput() caller didn't have to have any + * protection against it + */ + sb_start_intwrite(inode->i_sb); handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); @@ -242,6 +247,7 @@ void ext4_evict_inode(struct inode *inode) * cleaned up. */ ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); goto no_delete; } @@ -273,6 +279,7 @@ void ext4_evict_inode(struct inode *inode) stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); goto no_delete; } } @@ -301,6 +308,7 @@ void ext4_evict_inode(struct inode *inode) else ext4_free_inode(handle, inode); ext4_journal_stop(handle); + sb_end_intwrite(inode->i_sb); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ @@ -4779,11 +4787,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) get_block_t *get_block; int retries = 0; - /* - * This check is racy but catches the common case. We rely on - * __block_page_mkwrite() to do a reliable check. - */ - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + sb_start_pagefault(inode->i_sb); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -4851,5 +4855,6 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + sb_end_pagefault(inode->i_sb); return ret; } diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index f99a131..fe7c63f 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -44,6 +44,11 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) { struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); + /* + * We protect against freezing so that we don't create dirty buffers + * on frozen filesystem. + */ + sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); mark_buffer_dirty(bh); lock_buffer(bh); @@ -51,6 +56,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) get_bh(bh); submit_bh(WRITE_SYNC, bh); wait_on_buffer(bh); + sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) return 1; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2d51cd9..d76ec82 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -331,33 +331,17 @@ static void ext4_put_nojournal(handle_t *handle) * journal_end calls result in the superblock being marked dirty, so * that sync() will call the filesystem's write_super callback if * appropriate. - * - * To avoid j_barrier hold in userspace when a user calls freeze(), - * ext4 prevents a new handle from being started by s_frozen, which - * is in an upper layer. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { journal_t *journal; - handle_t *handle; trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); + WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; - handle = ext4_journal_current_handle(); - - /* - * If a handle has been started, it should be allowed to - * finish, otherwise deadlock could happen between freeze - * and others(e.g. truncate) due to the restart of the - * journal handle if the filesystem is forzen and active - * handles are not stopped. - */ - if (!handle) - vfs_check_frozen(sb, SB_FREEZE_TRANS); - if (!journal) return ext4_get_nojournal(); /* @@ -2747,6 +2731,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr) sb = elr->lr_super; ngroups = EXT4_SB(sb)->s_groups_count; + sb_start_write(sb); for (group = elr->lr_next_group; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { @@ -2773,6 +2758,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr) elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } + sb_end_write(sb); return ret; } @@ -4460,10 +4446,8 @@ int ext4_force_commit(struct super_block *sb) return 0; journal = EXT4_SB(sb)->s_journal; - if (journal) { - vfs_check_frozen(sb, SB_FREEZE_TRANS); + if (journal) ret = ext4_journal_force_commit(journal); - } return ret; } @@ -4493,9 +4477,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait) * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean - * state independently, because ext4 prevents a new handle from being started - * by @sb->s_frozen, which stays in an upper layer. It thus needs help from - * the upper layer. + * state independently. It relies on upper layer to stop all data & metadata + * modifications. */ static int ext4_freeze(struct super_block *sb) { @@ -4522,7 +4505,7 @@ static int ext4_freeze(struct super_block *sb) EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); error = ext4_commit_super(sb, 1); out: - /* we rely on s_frozen to stop further updates */ + /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return error; } diff --git a/fs/fat/file.c b/fs/fat/file.c index a71fe37..e007b8b 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -43,10 +43,10 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) if (err) goto out; - mutex_lock(&inode->i_mutex); err = mnt_want_write_file(file); if (err) - goto out_unlock_inode; + goto out; + mutex_lock(&inode->i_mutex); /* * ATTR_VOLUME and ATTR_DIR cannot be changed; this also @@ -73,14 +73,14 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) /* The root directory has no attributes */ if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) { err = -EINVAL; - goto out_drop_write; + goto out_unlock_inode; } if (sbi->options.sys_immutable && ((attr | oldattr) & ATTR_SYS) && !capable(CAP_LINUX_IMMUTABLE)) { err = -EPERM; - goto out_drop_write; + goto out_unlock_inode; } /* @@ -90,12 +90,12 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) */ err = security_inode_setattr(file->f_path.dentry, &ia); if (err) - goto out_drop_write; + goto out_unlock_inode; /* This MUST be done before doing anything irreversible... */ err = fat_setattr(file->f_path.dentry, &ia); if (err) - goto out_drop_write; + goto out_unlock_inode; fsnotify_change(file->f_path.dentry, ia.ia_valid); if (sbi->options.sys_immutable) { @@ -107,10 +107,9 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) fat_save_attrs(inode, attr); mark_inode_dirty(inode); -out_drop_write: - mnt_drop_write_file(file); out_unlock_inode: mutex_unlock(&inode->i_mutex); + mnt_drop_write_file(file); out: return err; } diff --git a/fs/file_table.c b/fs/file_table.c index b3fc4d6..701985e 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -43,7 +43,7 @@ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; -static inline void file_free_rcu(struct rcu_head *head) +static void file_free_rcu(struct rcu_head *head) { struct file *f = container_of(head, struct file, f_u.fu_rcuhead); @@ -217,7 +217,7 @@ static void drop_file_write_access(struct file *file) return; if (file_check_writeable(file) != 0) return; - mnt_drop_write(mnt); + __mnt_drop_write(mnt); file_release_write(file); } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index b321a68..93d8d6c 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -944,9 +944,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, return err; count = ocount; - + sb_start_write(inode->i_sb); mutex_lock(&inode->i_mutex); - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; @@ -1004,6 +1003,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, out: current->backing_dev_info = NULL; mutex_unlock(&inode->i_mutex); + sb_end_write(inode->i_sb); return written ? written : err; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 9aa6af1..d1d791e 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -373,11 +373,10 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) loff_t size; int ret; - /* Wait if fs is frozen. This is racy so we check again later on - * and retry if the fs has been frozen after the page lock has - * been acquired - */ - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + sb_start_pagefault(inode->i_sb); + + /* Update file times before taking page lock */ + file_update_time(vma->vm_file); ret = gfs2_rs_alloc(ip); if (ret) @@ -462,14 +461,9 @@ out: gfs2_holder_uninit(&gh); if (ret == 0) { set_page_dirty(page); - /* This check must be post dropping of transaction lock */ - if (inode->i_sb->s_frozen == SB_UNFROZEN) { - wait_on_page_writeback(page); - } else { - ret = -EAGAIN; - unlock_page(page); - } + wait_on_page_writeback(page); } + sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index ad3e2fb..adbd278 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -50,6 +50,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, if (revokes) tr->tr_reserved += gfs2_struct2blk(sdp, revokes, sizeof(u64)); + sb_start_intwrite(sdp->sd_vfs); gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh); error = gfs2_glock_nq(&tr->tr_t_gh); @@ -68,6 +69,7 @@ fail_gunlock: gfs2_glock_dq(&tr->tr_t_gh); fail_holder_uninit: + sb_end_intwrite(sdp->sd_vfs); gfs2_holder_uninit(&tr->tr_t_gh); kfree(tr); @@ -116,6 +118,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) gfs2_holder_uninit(&tr->tr_t_gh); kfree(tr); } + sb_end_intwrite(sdp->sd_vfs); return; } @@ -136,6 +139,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS) gfs2_log_flush(sdp, NULL); + sb_end_intwrite(sdp->sd_vfs); } /** @@ -1542,9 +1542,11 @@ void touch_atime(struct path *path) if (timespec_equal(&inode->i_atime, &now)) return; - if (mnt_want_write(mnt)) + if (!sb_start_write_trylock(inode->i_sb)) return; + if (__mnt_want_write(mnt)) + goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for @@ -1555,7 +1557,9 @@ void touch_atime(struct path *path) * of the fs read only, e.g. subvolumes in Btrfs. */ update_time(inode, &now, S_ATIME); - mnt_drop_write(mnt); + __mnt_drop_write(mnt); +skip_update: + sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); @@ -1662,11 +1666,11 @@ int file_update_time(struct file *file) return 0; /* Finally allowed to write? Takes lock. */ - if (mnt_want_write_file(file)) + if (__mnt_want_write_file(file)) return 0; ret = update_time(inode, &now, sync_it); - mnt_drop_write_file(file); + __mnt_drop_write_file(file); return ret; } diff --git a/fs/internal.h b/fs/internal.h index a6fd56c..371bcc4 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -61,6 +61,10 @@ extern void __init mnt_init(void); extern struct lglock vfsmount_lock; +extern int __mnt_want_write(struct vfsmount *); +extern int __mnt_want_write_file(struct file *); +extern void __mnt_drop_write(struct vfsmount *); +extern void __mnt_drop_write_file(struct file *); /* * fs_struct.c diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 8392cb8..05d2912 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -156,12 +156,16 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl) struct nlm_rqst *call; int status; - nlm_get_host(host); call = nlm_alloc_call(host); if (call == NULL) return -ENOMEM; nlmclnt_locks_init_private(fl, host); + if (!fl->fl_u.nfs_fl.owner) { + /* lockowner allocation has failed */ + nlmclnt_release_call(call); + return -ENOMEM; + } /* Set up the argument struct */ nlmclnt_setlockargs(call, fl); @@ -185,9 +189,6 @@ EXPORT_SYMBOL_GPL(nlmclnt_proc); /* * Allocate an NLM RPC call struct - * - * Note: the caller must hold a reference to host. In case of failure, - * this reference will be released. */ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host) { @@ -199,7 +200,7 @@ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host) atomic_set(&call->a_count, 1); locks_init_lock(&call->a_args.lock.fl); locks_init_lock(&call->a_res.lock.fl); - call->a_host = host; + call->a_host = nlm_get_host(host); return call; } if (signalled()) @@ -207,7 +208,6 @@ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host) printk("nlm_alloc_call: failed, waiting for memory\n"); schedule_timeout_interruptible(5*HZ); } - nlmclnt_release_host(host); return NULL; } @@ -750,7 +750,7 @@ static int nlmclnt_cancel(struct nlm_host *host, int block, struct file_lock *fl dprintk("lockd: blocking lock attempt was interrupted by a signal.\n" " Attempting to cancel lock.\n"); - req = nlm_alloc_call(nlm_get_host(host)); + req = nlm_alloc_call(host); if (!req) return -ENOMEM; req->a_flags = RPC_TASK_ASYNC; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 4a43d25..b147d1a 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -257,6 +257,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_system_err; call = nlm_alloc_call(host); + nlmsvc_release_host(host); if (call == NULL) return rpc_system_err; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index afe4488..fb1a2be 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -219,7 +219,6 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host, struct nlm_block *block; struct nlm_rqst *call = NULL; - nlm_get_host(host); call = nlm_alloc_call(host); if (call == NULL) return NULL; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index de8f2ca..3009a36 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -297,6 +297,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_system_err; call = nlm_alloc_call(host); + nlmsvc_release_host(host); if (call == NULL) return rpc_system_err; @@ -650,6 +650,121 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki path_put(link); } +int sysctl_protected_symlinks __read_mostly = 1; +int sysctl_protected_hardlinks __read_mostly = 1; + +/** + * may_follow_link - Check symlink following for unsafe situations + * @link: The path of the symlink + * + * In the case of the sysctl_protected_symlinks sysctl being enabled, + * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is + * in a sticky world-writable directory. This is to protect privileged + * processes from failing races against path names that may change out + * from under them by way of other users creating malicious symlinks. + * It will permit symlinks to be followed only when outside a sticky + * world-writable directory, or when the uid of the symlink and follower + * match, or when the directory owner matches the symlink's owner. + * + * Returns 0 if following the symlink is allowed, -ve on error. + */ +static inline int may_follow_link(struct path *link, struct nameidata *nd) +{ + const struct inode *inode; + const struct inode *parent; + + if (!sysctl_protected_symlinks) + return 0; + + /* Allowed if owner and follower match. */ + inode = link->dentry->d_inode; + if (current_cred()->fsuid == inode->i_uid) + return 0; + + /* Allowed if parent directory not sticky and world-writable. */ + parent = nd->path.dentry->d_inode; + if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) + return 0; + + /* Allowed if parent directory and link owner match. */ + if (parent->i_uid == inode->i_uid) + return 0; + + path_put_conditional(link, nd); + path_put(&nd->path); + audit_log_link_denied("follow_link", link); + return -EACCES; +} + +/** + * safe_hardlink_source - Check for safe hardlink conditions + * @inode: the source inode to hardlink from + * + * Return false if at least one of the following conditions: + * - inode is not a regular file + * - inode is setuid + * - inode is setgid and group-exec + * - access failure for read and write + * + * Otherwise returns true. + */ +static bool safe_hardlink_source(struct inode *inode) +{ + umode_t mode = inode->i_mode; + + /* Special files should not get pinned to the filesystem. */ + if (!S_ISREG(mode)) + return false; + + /* Setuid files should not get pinned to the filesystem. */ + if (mode & S_ISUID) + return false; + + /* Executable setgid files should not get pinned to the filesystem. */ + if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) + return false; + + /* Hardlinking to unreadable or unwritable sources is dangerous. */ + if (inode_permission(inode, MAY_READ | MAY_WRITE)) + return false; + + return true; +} + +/** + * may_linkat - Check permissions for creating a hardlink + * @link: the source to hardlink from + * + * Block hardlink when all of: + * - sysctl_protected_hardlinks enabled + * - fsuid does not match inode + * - hardlink source is unsafe (see safe_hardlink_source() above) + * - not CAP_FOWNER + * + * Returns 0 if successful, -ve on error. + */ +static int may_linkat(struct path *link) +{ + const struct cred *cred; + struct inode *inode; + + if (!sysctl_protected_hardlinks) + return 0; + + cred = current_cred(); + inode = link->dentry->d_inode; + + /* Source inode owner (or CAP_FOWNER) can hardlink all they like, + * otherwise, it must be a safe source. + */ + if (cred->fsuid == inode->i_uid || safe_hardlink_source(inode) || + capable(CAP_FOWNER)) + return 0; + + audit_log_link_denied("linkat", link); + return -EPERM; +} + static __always_inline int follow_link(struct path *link, struct nameidata *nd, void **p) { @@ -1818,6 +1933,9 @@ static int path_lookupat(int dfd, const char *name, while (err > 0) { void *cookie; struct path link = path; + err = may_follow_link(&link, nd); + if (unlikely(err)) + break; nd->flags |= LOOKUP_PARENT; err = follow_link(&link, nd, &cookie); if (err) @@ -2277,7 +2395,7 @@ static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode) static int atomic_open(struct nameidata *nd, struct dentry *dentry, struct path *path, struct file *file, const struct open_flags *op, - bool *want_write, bool need_lookup, + bool got_write, bool need_lookup, int *opened) { struct inode *dir = nd->path.dentry->d_inode; @@ -2300,7 +2418,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) mode &= ~current_umask(); - if (open_flag & O_EXCL) { + if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT)) { open_flag &= ~O_TRUNC; *opened |= FILE_CREATED; } @@ -2314,12 +2432,9 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ - if ((open_flag & (O_CREAT | O_TRUNC)) || - (open_flag & O_ACCMODE) != O_RDONLY) { - error = mnt_want_write(nd->path.mnt); - if (!error) { - *want_write = true; - } else if (!(open_flag & O_CREAT)) { + if (((open_flag & (O_CREAT | O_TRUNC)) || + (open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) { + if (!(open_flag & O_CREAT)) { /* * No O_CREATE -> atomicity not a requirement -> fall * back to lookup + open @@ -2327,11 +2442,11 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, goto no_open; } else if (open_flag & (O_EXCL | O_TRUNC)) { /* Fall back and fail with the right error */ - create_error = error; + create_error = -EROFS; goto no_open; } else { /* No side effects, safe to clear O_CREAT */ - create_error = error; + create_error = -EROFS; open_flag &= ~O_CREAT; } } @@ -2438,7 +2553,7 @@ looked_up: static int lookup_open(struct nameidata *nd, struct path *path, struct file *file, const struct open_flags *op, - bool *want_write, int *opened) + bool got_write, int *opened) { struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; @@ -2456,7 +2571,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, goto out_no_open; if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) { - return atomic_open(nd, dentry, path, file, op, want_write, + return atomic_open(nd, dentry, path, file, op, got_write, need_lookup, opened); } @@ -2480,10 +2595,10 @@ static int lookup_open(struct nameidata *nd, struct path *path, * a permanent write count is taken through * the 'struct file' in finish_open(). */ - error = mnt_want_write(nd->path.mnt); - if (error) + if (!got_write) { + error = -EROFS; goto out_dput; - *want_write = true; + } *opened |= FILE_CREATED; error = security_path_mknod(&nd->path, dentry, mode, 0); if (error) @@ -2513,7 +2628,7 @@ static int do_last(struct nameidata *nd, struct path *path, struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool will_truncate = (open_flag & O_TRUNC) != 0; - bool want_write = false; + bool got_write = false; int acc_mode = op->acc_mode; struct inode *inode; bool symlink_ok = false; @@ -2582,8 +2697,18 @@ static int do_last(struct nameidata *nd, struct path *path, } retry_lookup: + if (op->open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { + error = mnt_want_write(nd->path.mnt); + if (!error) + got_write = true; + /* + * do _not_ fail yet - we might not need that or fail with + * a different error; let lookup_open() decide; we'll be + * dropping this one anyway. + */ + } mutex_lock(&dir->d_inode->i_mutex); - error = lookup_open(nd, path, file, op, &want_write, opened); + error = lookup_open(nd, path, file, op, got_write, opened); mutex_unlock(&dir->d_inode->i_mutex); if (error <= 0) { @@ -2608,22 +2733,23 @@ retry_lookup: } /* - * It already exists. + * create/update audit record if it already exists. */ - audit_inode(pathname, path->dentry); + if (path->dentry->d_inode) + audit_inode(pathname, path->dentry); /* * If atomic_open() acquired write access it is dropped now due to * possible mount and symlink following (this might be optimized away if * necessary...) */ - if (want_write) { + if (got_write) { mnt_drop_write(nd->path.mnt); - want_write = false; + got_write = false; } error = -EEXIST; - if (open_flag & O_EXCL) + if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT)) goto exit_dput; error = follow_managed(path, nd->flags); @@ -2684,7 +2810,7 @@ finish_open: error = mnt_want_write(nd->path.mnt); if (error) goto out; - want_write = true; + got_write = true; } finish_open_created: error = may_open(&nd->path, acc_mode, open_flag); @@ -2711,7 +2837,7 @@ opened: goto exit_fput; } out: - if (want_write) + if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); terminate_walk(nd); @@ -2735,9 +2861,9 @@ stale_open: nd->inode = dir->d_inode; save_parent.mnt = NULL; save_parent.dentry = NULL; - if (want_write) { + if (got_write) { mnt_drop_write(nd->path.mnt); - want_write = false; + got_write = false; } retried = true; goto retry_lookup; @@ -2777,6 +2903,9 @@ static struct file *path_openat(int dfd, const char *pathname, error = -ELOOP; break; } + error = may_follow_link(&link, nd); + if (unlikely(error)) + break; nd->flags |= LOOKUP_PARENT; nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); error = follow_link(&link, nd, &cookie); @@ -2846,6 +2975,7 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path { struct dentry *dentry = ERR_PTR(-EEXIST); struct nameidata nd; + int err2; int error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd); if (error) return ERR_PTR(error); @@ -2859,16 +2989,19 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path nd.flags &= ~LOOKUP_PARENT; nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL; + /* don't fail immediately if it's r/o, at least try to report other errors */ + err2 = mnt_want_write(nd.path.mnt); /* * Do the final lookup. */ mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); if (IS_ERR(dentry)) - goto fail; + goto unlock; + error = -EEXIST; if (dentry->d_inode) - goto eexist; + goto fail; /* * Special case - lookup gave negative, but... we had foo/bar/ * From the vfs_mknod() POV we just have a negative dentry - @@ -2876,23 +3009,37 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path * been asking for (non-existent) directory. -ENOENT for you. */ if (unlikely(!is_dir && nd.last.name[nd.last.len])) { - dput(dentry); - dentry = ERR_PTR(-ENOENT); + error = -ENOENT; + goto fail; + } + if (unlikely(err2)) { + error = err2; goto fail; } *path = nd.path; return dentry; -eexist: - dput(dentry); - dentry = ERR_PTR(-EEXIST); fail: + dput(dentry); + dentry = ERR_PTR(error); +unlock: mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + if (!err2) + mnt_drop_write(nd.path.mnt); out: path_put(&nd.path); return dentry; } EXPORT_SYMBOL(kern_path_create); +void done_path_create(struct path *path, struct dentry *dentry) +{ + dput(dentry); + mutex_unlock(&path->dentry->d_inode->i_mutex); + mnt_drop_write(path->mnt); + path_put(path); +} +EXPORT_SYMBOL(done_path_create); + struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir) { char *tmp = getname(pathname); @@ -2956,8 +3103,9 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, struct path path; int error; - if (S_ISDIR(mode)) - return -EPERM; + error = may_mknod(mode); + if (error) + return error; dentry = user_path_create(dfd, filename, &path, 0); if (IS_ERR(dentry)) @@ -2965,15 +3113,9 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, if (!IS_POSIXACL(path.dentry->d_inode)) mode &= ~current_umask(); - error = may_mknod(mode); - if (error) - goto out_dput; - error = mnt_want_write(path.mnt); - if (error) - goto out_dput; error = security_path_mknod(&path, dentry, mode, dev); if (error) - goto out_drop_write; + goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(path.dentry->d_inode,dentry,mode,true); @@ -2986,13 +3128,8 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); break; } -out_drop_write: - mnt_drop_write(path.mnt); -out_dput: - dput(dentry); - mutex_unlock(&path.dentry->d_inode->i_mutex); - path_put(&path); - +out: + done_path_create(&path, dentry); return error; } @@ -3038,19 +3175,10 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) if (!IS_POSIXACL(path.dentry->d_inode)) mode &= ~current_umask(); - error = mnt_want_write(path.mnt); - if (error) - goto out_dput; error = security_path_mkdir(&path, dentry, mode); - if (error) - goto out_drop_write; - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); -out_drop_write: - mnt_drop_write(path.mnt); -out_dput: - dput(dentry); - mutex_unlock(&path.dentry->d_inode->i_mutex); - path_put(&path); + if (!error) + error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + done_path_create(&path, dentry); return error; } @@ -3144,6 +3272,9 @@ static long do_rmdir(int dfd, const char __user *pathname) } nd.flags &= ~LOOKUP_PARENT; + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit1; mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); @@ -3154,19 +3285,15 @@ static long do_rmdir(int dfd, const char __user *pathname) error = -ENOENT; goto exit3; } - error = mnt_want_write(nd.path.mnt); - if (error) - goto exit3; error = security_path_rmdir(&nd.path, dentry); if (error) - goto exit4; + goto exit3; error = vfs_rmdir(nd.path.dentry->d_inode, dentry); -exit4: - mnt_drop_write(nd.path.mnt); exit3: dput(dentry); exit2: mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + mnt_drop_write(nd.path.mnt); exit1: path_put(&nd.path); putname(name); @@ -3233,6 +3360,9 @@ static long do_unlinkat(int dfd, const char __user *pathname) goto exit1; nd.flags &= ~LOOKUP_PARENT; + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit1; mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); @@ -3245,21 +3375,17 @@ static long do_unlinkat(int dfd, const char __user *pathname) if (!inode) goto slashes; ihold(inode); - error = mnt_want_write(nd.path.mnt); - if (error) - goto exit2; error = security_path_unlink(&nd.path, dentry); if (error) - goto exit3; + goto exit2; error = vfs_unlink(nd.path.dentry->d_inode, dentry); -exit3: - mnt_drop_write(nd.path.mnt); - exit2: +exit2: dput(dentry); } mutex_unlock(&nd.path.dentry->d_inode->i_mutex); if (inode) iput(inode); /* truncate the inode here */ + mnt_drop_write(nd.path.mnt); exit1: path_put(&nd.path); putname(name); @@ -3324,19 +3450,10 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, if (IS_ERR(dentry)) goto out_putname; - error = mnt_want_write(path.mnt); - if (error) - goto out_dput; error = security_path_symlink(&path, dentry, from); - if (error) - goto out_drop_write; - error = vfs_symlink(path.dentry->d_inode, dentry, from); -out_drop_write: - mnt_drop_write(path.mnt); -out_dput: - dput(dentry); - mutex_unlock(&path.dentry->d_inode->i_mutex); - path_put(&path); + if (!error) + error = vfs_symlink(path.dentry->d_inode, dentry, from); + done_path_create(&path, dentry); out_putname: putname(from); return error; @@ -3436,19 +3553,15 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - error = mnt_want_write(new_path.mnt); - if (error) + error = may_linkat(&old_path); + if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) - goto out_drop_write; + goto out_dput; error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry); -out_drop_write: - mnt_drop_write(new_path.mnt); out_dput: - dput(new_dentry); - mutex_unlock(&new_path.dentry->d_inode->i_mutex); - path_put(&new_path); + done_path_create(&new_path, new_dentry); out: path_put(&old_path); @@ -3644,6 +3757,10 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, if (newnd.last_type != LAST_NORM) goto exit2; + error = mnt_want_write(oldnd.path.mnt); + if (error) + goto exit2; + oldnd.flags &= ~LOOKUP_PARENT; newnd.flags &= ~LOOKUP_PARENT; newnd.flags |= LOOKUP_RENAME_TARGET; @@ -3679,23 +3796,19 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, if (new_dentry == trap) goto exit5; - error = mnt_want_write(oldnd.path.mnt); - if (error) - goto exit5; error = security_path_rename(&oldnd.path, old_dentry, &newnd.path, new_dentry); if (error) - goto exit6; + goto exit5; error = vfs_rename(old_dir->d_inode, old_dentry, new_dir->d_inode, new_dentry); -exit6: - mnt_drop_write(oldnd.path.mnt); exit5: dput(new_dentry); exit4: dput(old_dentry); exit3: unlock_rename(new_dir, old_dir); + mnt_drop_write(oldnd.path.mnt); exit2: path_put(&newnd.path); putname(to); diff --git a/fs/namespace.c b/fs/namespace.c index c53d338..4d31f73 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -283,24 +283,22 @@ static int mnt_is_readonly(struct vfsmount *mnt) } /* - * Most r/o checks on a fs are for operations that take - * discrete amounts of time, like a write() or unlink(). - * We must keep track of when those operations start - * (for permission checks) and when they end, so that - * we can determine when writes are able to occur to - * a filesystem. + * Most r/o & frozen checks on a fs are for operations that take discrete + * amounts of time, like a write() or unlink(). We must keep track of when + * those operations start (for permission checks) and when they end, so that we + * can determine when writes are able to occur to a filesystem. */ /** - * mnt_want_write - get write access to a mount + * __mnt_want_write - get write access to a mount without freeze protection * @m: the mount on which to take a write * - * This tells the low-level filesystem that a write is - * about to be performed to it, and makes sure that - * writes are allowed before returning success. When - * the write operation is finished, mnt_drop_write() - * must be called. This is effectively a refcount. + * This tells the low-level filesystem that a write is about to be performed to + * it, and makes sure that writes are allowed (mnt it read-write) before + * returning success. This operation does not protect against filesystem being + * frozen. When the write operation is finished, __mnt_drop_write() must be + * called. This is effectively a refcount. */ -int mnt_want_write(struct vfsmount *m) +int __mnt_want_write(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; @@ -326,6 +324,27 @@ int mnt_want_write(struct vfsmount *m) ret = -EROFS; } preempt_enable(); + + return ret; +} + +/** + * mnt_want_write - get write access to a mount + * @m: the mount on which to take a write + * + * This tells the low-level filesystem that a write is about to be performed to + * it, and makes sure that writes are allowed (mount is read-write, filesystem + * is not frozen) before returning success. When the write operation is + * finished, mnt_drop_write() must be called. This is effectively a refcount. + */ +int mnt_want_write(struct vfsmount *m) +{ + int ret; + + sb_start_write(m->mnt_sb); + ret = __mnt_want_write(m); + if (ret) + sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); @@ -355,38 +374,76 @@ int mnt_clone_write(struct vfsmount *mnt) EXPORT_SYMBOL_GPL(mnt_clone_write); /** - * mnt_want_write_file - get write access to a file's mount + * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like mnt_want_write, but it takes a file and can + * This is like __mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ -int mnt_want_write_file(struct file *file) +int __mnt_want_write_file(struct file *file) { struct inode *inode = file->f_dentry->d_inode; + if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode)) - return mnt_want_write(file->f_path.mnt); + return __mnt_want_write(file->f_path.mnt); else return mnt_clone_write(file->f_path.mnt); } + +/** + * mnt_want_write_file - get write access to a file's mount + * @file: the file who's mount on which to take a write + * + * This is like mnt_want_write, but it takes a file and can + * do some optimisations if the file is open for write already + */ +int mnt_want_write_file(struct file *file) +{ + int ret; + + sb_start_write(file->f_path.mnt->mnt_sb); + ret = __mnt_want_write_file(file); + if (ret) + sb_end_write(file->f_path.mnt->mnt_sb); + return ret; +} EXPORT_SYMBOL_GPL(mnt_want_write_file); /** - * mnt_drop_write - give up write access to a mount + * __mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with - * mnt_want_write() call above. + * __mnt_want_write() call above. */ -void mnt_drop_write(struct vfsmount *mnt) +void __mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } + +/** + * mnt_drop_write - give up write access to a mount + * @mnt: the mount on which to give up write access + * + * Tells the low-level filesystem that we are done performing writes to it and + * also allows filesystem to be frozen again. Must be matched with + * mnt_want_write() call above. + */ +void mnt_drop_write(struct vfsmount *mnt) +{ + __mnt_drop_write(mnt); + sb_end_write(mnt->mnt_sb); +} EXPORT_SYMBOL_GPL(mnt_drop_write); +void __mnt_drop_write_file(struct file *file) +{ + __mnt_drop_write(file->f_path.mnt); +} + void mnt_drop_write_file(struct file *file) { mnt_drop_write(file->f_path.mnt); diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 5ff0b7b..43295d4 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -154,6 +154,10 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) if (status < 0) return; + status = mnt_want_write_file(rec_file); + if (status) + return; + dir = rec_file->f_path.dentry; /* lock the parent */ mutex_lock(&dir->d_inode->i_mutex); @@ -173,11 +177,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * as well be forgiving and just succeed silently. */ goto out_put; - status = mnt_want_write_file(rec_file); - if (status) - goto out_put; status = vfs_mkdir(dir->d_inode, dentry, S_IRWXU); - mnt_drop_write_file(rec_file); out_put: dput(dentry); out_unlock: @@ -189,6 +189,7 @@ out_unlock: " (err %d); please check that %s exists" " and is writeable", status, user_recovery_dirname); + mnt_drop_write_file(rec_file); nfs4_reset_creds(original_cred); } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index cc79300..032af38 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -635,6 +635,7 @@ fh_put(struct svc_fh *fhp) fhp->fh_post_saved = 0; #endif } + fh_drop_write(fhp); if (exp) { exp_put(exp); fhp->fh_export = NULL; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index e15dc45..aad6d45 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -196,6 +196,7 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, struct dentry *dchild; int type, mode; __be32 nfserr; + int hosterr; dev_t rdev = 0, wanted = new_decode_dev(attr->ia_size); dprintk("nfsd: CREATE %s %.*s\n", @@ -214,6 +215,12 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, nfserr = nfserr_exist; if (isdotent(argp->name, argp->len)) goto done; + hosterr = fh_want_write(dirfhp); + if (hosterr) { + nfserr = nfserrno(hosterr); + goto done; + } + fh_lock_nested(dirfhp, I_MUTEX_PARENT); dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len); if (IS_ERR(dchild)) { @@ -330,7 +337,7 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, out_unlock: /* We don't really need to unlock, as fh_put does it. */ fh_unlock(dirfhp); - + fh_drop_write(dirfhp); done: fh_put(dirfhp); return nfsd_return_dirop(nfserr, resp); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 702f64e..a9269f1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1284,6 +1284,10 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, * If it has, the parent directory should already be locked. */ if (!resfhp->fh_dentry) { + host_err = fh_want_write(fhp); + if (host_err) + goto out_nfserr; + /* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */ fh_lock_nested(fhp, I_MUTEX_PARENT); dchild = lookup_one_len(fname, dentry, flen); @@ -1327,14 +1331,11 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; } - host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; - /* * Get the dir op function pointer. */ err = 0; + host_err = 0; switch (type) { case S_IFREG: host_err = vfs_create(dirp, dchild, iap->ia_mode, true); @@ -1351,10 +1352,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev); break; } - if (host_err < 0) { - fh_drop_write(fhp); + if (host_err < 0) goto out_nfserr; - } err = nfsd_create_setattr(rqstp, resfhp, iap); @@ -1366,7 +1365,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, err2 = nfserrno(commit_metadata(fhp)); if (err2) err = err2; - fh_drop_write(fhp); /* * Update the file handle to get the new inode info. */ @@ -1425,6 +1423,11 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfserr_notdir; if (!dirp->i_op->lookup) goto out; + + host_err = fh_want_write(fhp); + if (host_err) + goto out_nfserr; + fh_lock_nested(fhp, I_MUTEX_PARENT); /* @@ -1457,9 +1460,6 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, v_atime = verifier[1]&0x7fffffff; } - host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; if (dchild->d_inode) { err = 0; @@ -1530,7 +1530,6 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!err) err = nfserrno(commit_metadata(fhp)); - fh_drop_write(fhp); /* * Update the filehandle to get the new inode info. */ @@ -1541,6 +1540,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, fh_unlock(fhp); if (dchild && !IS_ERR(dchild)) dput(dchild); + fh_drop_write(fhp); return err; out_nfserr: @@ -1621,6 +1621,11 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; + + host_err = fh_want_write(fhp); + if (host_err) + goto out_nfserr; + fh_lock(fhp); dentry = fhp->fh_dentry; dnew = lookup_one_len(fname, dentry, flen); @@ -1628,10 +1633,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dnew)) goto out_nfserr; - host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; - if (unlikely(path[plen] != 0)) { char *path_alloced = kmalloc(plen+1, GFP_KERNEL); if (path_alloced == NULL) @@ -1691,6 +1692,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (isdotent(name, len)) goto out; + host_err = fh_want_write(tfhp); + if (host_err) { + err = nfserrno(host_err); + goto out; + } + fh_lock_nested(ffhp, I_MUTEX_PARENT); ddir = ffhp->fh_dentry; dirp = ddir->d_inode; @@ -1702,18 +1709,13 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, dold = tfhp->fh_dentry; - host_err = fh_want_write(tfhp); - if (host_err) { - err = nfserrno(host_err); - goto out_dput; - } err = nfserr_noent; if (!dold->d_inode) - goto out_drop_write; + goto out_dput; host_err = nfsd_break_lease(dold->d_inode); if (host_err) { err = nfserrno(host_err); - goto out_drop_write; + goto out_dput; } host_err = vfs_link(dold, dirp, dnew); if (!host_err) { @@ -1726,12 +1728,11 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, else err = nfserrno(host_err); } -out_drop_write: - fh_drop_write(tfhp); out_dput: dput(dnew); out_unlock: fh_unlock(ffhp); + fh_drop_write(tfhp); out: return err; @@ -1774,6 +1775,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + host_err = fh_want_write(ffhp); + if (host_err) { + err = nfserrno(host_err); + goto out; + } + /* cannot use fh_lock as we need deadlock protective ordering * so do it by hand */ trap = lock_rename(tdentry, fdentry); @@ -1804,17 +1811,14 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, host_err = -EXDEV; if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) goto out_dput_new; - host_err = fh_want_write(ffhp); - if (host_err) - goto out_dput_new; host_err = nfsd_break_lease(odentry->d_inode); if (host_err) - goto out_drop_write; + goto out_dput_new; if (ndentry->d_inode) { host_err = nfsd_break_lease(ndentry->d_inode); if (host_err) - goto out_drop_write; + goto out_dput_new; } host_err = vfs_rename(fdir, odentry, tdir, ndentry); if (!host_err) { @@ -1822,8 +1826,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!host_err) host_err = commit_metadata(ffhp); } -out_drop_write: - fh_drop_write(ffhp); out_dput_new: dput(ndentry); out_dput_old: @@ -1839,6 +1841,7 @@ out_drop_write: fill_post_wcc(tfhp); unlock_rename(tdentry, fdentry); ffhp->fh_locked = tfhp->fh_locked = 0; + fh_drop_write(ffhp); out: return err; @@ -1864,6 +1867,10 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (err) goto out; + host_err = fh_want_write(fhp); + if (host_err) + goto out_nfserr; + fh_lock_nested(fhp, I_MUTEX_PARENT); dentry = fhp->fh_dentry; dirp = dentry->d_inode; @@ -1882,21 +1889,15 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (!type) type = rdentry->d_inode->i_mode & S_IFMT; - host_err = fh_want_write(fhp); - if (host_err) - goto out_put; - host_err = nfsd_break_lease(rdentry->d_inode); if (host_err) - goto out_drop_write; + goto out_put; if (type != S_IFDIR) host_err = vfs_unlink(dirp, rdentry); else host_err = vfs_rmdir(dirp, rdentry); if (!host_err) host_err = commit_metadata(fhp); -out_drop_write: - fh_drop_write(fhp); out_put: dput(rdentry); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index ec0611b..359594c 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -110,12 +110,19 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); static inline int fh_want_write(struct svc_fh *fh) { - return mnt_want_write(fh->fh_export->ex_path.mnt); + int ret = mnt_want_write(fh->fh_export->ex_path.mnt); + + if (!ret) + fh->fh_want_write = 1; + return ret; } static inline void fh_drop_write(struct svc_fh *fh) { - mnt_drop_write(fh->fh_export->ex_path.mnt); + if (fh->fh_want_write) { + fh->fh_want_write = 0; + mnt_drop_write(fh->fh_export->ex_path.mnt); + } } #endif /* LINUX_NFSD_VFS_H */ diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 62cebc8..a4d56ac 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -69,16 +69,18 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) struct page *page = vmf->page; struct inode *inode = vma->vm_file->f_dentry->d_inode; struct nilfs_transaction_info ti; - int ret; + int ret = 0; if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info))) return VM_FAULT_SIGBUS; /* -ENOSPC */ + sb_start_pagefault(inode->i_sb); lock_page(page); if (page->mapping != inode->i_mapping || page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) { unlock_page(page); - return VM_FAULT_NOPAGE; /* make the VM retry the fault */ + ret = -EFAULT; /* make the VM retry the fault */ + goto out; } /* @@ -112,19 +114,21 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) ret = nilfs_transaction_begin(inode->i_sb, &ti, 1); /* never returns -ENOMEM, but may return -ENOSPC */ if (unlikely(ret)) - return VM_FAULT_SIGBUS; + goto out; - ret = block_page_mkwrite(vma, vmf, nilfs_get_block); - if (ret != VM_FAULT_LOCKED) { + ret = __block_page_mkwrite(vma, vmf, nilfs_get_block); + if (ret) { nilfs_transaction_abort(inode->i_sb); - return ret; + goto out; } nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits)); nilfs_transaction_commit(inode->i_sb); mapped: wait_on_page_writeback(page); - return VM_FAULT_LOCKED; + out: + sb_end_pagefault(inode->i_sb); + return block_page_mkwrite_return(ret); } static const struct vm_operations_struct nilfs_file_vm_ops = { diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 0b6387c..fdb1807 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -660,8 +660,6 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, goto out_free; } - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); - ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]); if (ret < 0) printk(KERN_ERR "NILFS: GC failed during preparation: " diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 88e11fb..a5752a58 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -189,7 +189,7 @@ int nilfs_transaction_begin(struct super_block *sb, if (ret > 0) return 0; - vfs_check_frozen(sb, SB_FREEZE_WRITE); + sb_start_intwrite(sb); nilfs = sb->s_fs_info; down_read(&nilfs->ns_segctor_sem); @@ -205,6 +205,7 @@ int nilfs_transaction_begin(struct super_block *sb, current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC) kmem_cache_free(nilfs_transaction_cachep, ti); + sb_end_intwrite(sb); return ret; } @@ -246,6 +247,7 @@ int nilfs_transaction_commit(struct super_block *sb) err = nilfs_construct_segment(sb); if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC) kmem_cache_free(nilfs_transaction_cachep, ti); + sb_end_intwrite(sb); return err; } @@ -264,6 +266,7 @@ void nilfs_transaction_abort(struct super_block *sb) current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC) kmem_cache_free(nilfs_transaction_cachep, ti); + sb_end_intwrite(sb); } void nilfs_relax_pressure_in_lock(struct super_block *sb) diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 7389d2d..1ecf464 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2084,7 +2084,6 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, if (err) return err; pos = *ppos; - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); /* We can write back this queue in page reclaim. */ current->backing_dev_info = mapping->backing_dev_info; written = 0; @@ -2119,6 +2118,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, BUG_ON(iocb->ki_pos != pos); + sb_start_write(inode->i_sb); mutex_lock(&inode->i_mutex); ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); @@ -2127,6 +2127,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err < 0) ret = err; } + sb_end_write(inode->i_sb); return ret; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 7602783..46a1f6d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1971,6 +1971,7 @@ int ocfs2_change_file_space(struct file *file, unsigned int cmd, { struct inode *inode = file->f_path.dentry->d_inode; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + int ret; if ((cmd == OCFS2_IOC_RESVSP || cmd == OCFS2_IOC_RESVSP64) && !ocfs2_writes_unwritten_extents(osb)) @@ -1985,7 +1986,12 @@ int ocfs2_change_file_space(struct file *file, unsigned int cmd, if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - return __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0); + ret = mnt_want_write_file(file); + if (ret) + return ret; + ret = __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0); + mnt_drop_write_file(file); + return ret; } static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, @@ -2261,7 +2267,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, if (iocb->ki_left == 0) return 0; - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + sb_start_write(inode->i_sb); appending = file->f_flags & O_APPEND ? 1 : 0; direct_io = file->f_flags & O_DIRECT ? 1 : 0; @@ -2436,6 +2442,7 @@ out_sems: ocfs2_iocb_clear_sem_locked(iocb); mutex_unlock(&inode->i_mutex); + sb_end_write(inode->i_sb); if (written) ret = written; diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index d96f7f8..f20edcb 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -928,7 +928,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (get_user(new_clusters, (int __user *)arg)) return -EFAULT; - return ocfs2_group_extend(inode, new_clusters); + status = mnt_want_write_file(filp); + if (status) + return status; + status = ocfs2_group_extend(inode, new_clusters); + mnt_drop_write_file(filp); + return status; case OCFS2_IOC_GROUP_ADD: case OCFS2_IOC_GROUP_ADD64: if (!capable(CAP_SYS_RESOURCE)) @@ -937,7 +942,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (copy_from_user(&input, (int __user *) arg, sizeof(input))) return -EFAULT; - return ocfs2_group_add(inode, &input); + status = mnt_want_write_file(filp); + if (status) + return status; + status = ocfs2_group_add(inode, &input); + mnt_drop_write_file(filp); + return status; case OCFS2_IOC_REFLINK: if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 0a42ae9..2dd36af 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -355,11 +355,14 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs) if (journal_current_handle()) return jbd2_journal_start(journal, max_buffs); + sb_start_intwrite(osb->sb); + down_read(&osb->journal->j_trans_barrier); handle = jbd2_journal_start(journal, max_buffs); if (IS_ERR(handle)) { up_read(&osb->journal->j_trans_barrier); + sb_end_intwrite(osb->sb); mlog_errno(PTR_ERR(handle)); @@ -388,8 +391,10 @@ int ocfs2_commit_trans(struct ocfs2_super *osb, if (ret < 0) mlog_errno(ret); - if (!nested) + if (!nested) { up_read(&journal->j_trans_barrier); + sb_end_intwrite(osb->sb); + } return ret; } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 9cd4108..d150372 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -136,6 +136,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) sigset_t oldset; int ret; + sb_start_pagefault(inode->i_sb); ocfs2_block_signals(&oldset); /* @@ -165,6 +166,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) out: ocfs2_unblock_signals(&oldset); + sb_end_pagefault(inode->i_sb); return ret; } diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 9f32d7c..30a0550 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4466,20 +4466,11 @@ int ocfs2_reflink_ioctl(struct inode *inode, goto out_dput; } - error = mnt_want_write(new_path.mnt); - if (error) { - mlog_errno(error); - goto out_dput; - } - error = ocfs2_vfs_reflink(old_path.dentry, new_path.dentry->d_inode, new_dentry, preserve); - mnt_drop_write(new_path.mnt); out_dput: - dput(new_dentry); - mutex_unlock(&new_path.dentry->d_inode->i_mutex); - path_put(&new_path); + done_path_create(&new_path, new_dentry); out: path_put(&old_path); @@ -164,11 +164,13 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) if (IS_APPEND(inode)) goto out_putf; + sb_start_write(inode->i_sb); error = locks_verify_truncate(inode, file, length); if (!error) error = security_path_truncate(&file->f_path); if (!error) error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file); + sb_end_write(inode->i_sb); out_putf: fput(file); out: @@ -266,7 +268,10 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (!file->f_op->fallocate) return -EOPNOTSUPP; - return file->f_op->fallocate(file, mode, offset, len); + sb_start_write(inode->i_sb); + ret = file->f_op->fallocate(file, mode, offset, len); + sb_end_write(inode->i_sb); + return ret; } SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) @@ -620,7 +625,7 @@ static inline int __get_file_write_access(struct inode *inode, /* * Balanced in __fput() */ - error = mnt_want_write(mnt); + error = __mnt_want_write(mnt); if (error) put_write_access(inode); } @@ -654,6 +659,7 @@ static int do_dentry_open(struct file *f, if (unlikely(f->f_flags & O_PATH)) f->f_mode = FMODE_PATH; + path_get(&f->f_path); inode = f->f_path.dentry->d_inode; if (f->f_mode & FMODE_WRITE) { error = __get_file_write_access(inode, f->f_path.mnt); @@ -739,9 +745,7 @@ int finish_open(struct file *file, struct dentry *dentry, int error; BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ - mntget(file->f_path.mnt); - file->f_path.dentry = dget(dentry); - + file->f_path.dentry = dentry; error = do_dentry_open(file, open, current_cred()); if (!error) *opened |= FILE_OPENED; @@ -784,7 +788,6 @@ struct file *dentry_open(const struct path *path, int flags, f->f_flags = flags; f->f_path = *path; - path_get(&f->f_path); error = do_dentry_open(f, NULL, cred); if (!error) { error = open_check_o_direct(f); @@ -1016,18 +1016,16 @@ fail_inode: return NULL; } -struct file *create_write_pipe(int flags) +int create_pipe_files(struct file **res, int flags) { int err; - struct inode *inode; + struct inode *inode = get_pipe_inode(); struct file *f; struct path path; - struct qstr name = { .name = "" }; + static struct qstr name = { .name = "" }; - err = -ENFILE; - inode = get_pipe_inode(); if (!inode) - goto err; + return -ENFILE; err = -ENOMEM; path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name); @@ -1041,62 +1039,43 @@ struct file *create_write_pipe(int flags) f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops); if (!f) goto err_dentry; - f->f_mapping = inode->i_mapping; f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)); - f->f_version = 0; - return f; + res[0] = alloc_file(&path, FMODE_READ, &read_pipefifo_fops); + if (!res[0]) + goto err_file; + + path_get(&path); + res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK); + res[1] = f; + return 0; - err_dentry: +err_file: + put_filp(f); +err_dentry: free_pipe_info(inode); path_put(&path); - return ERR_PTR(err); + return err; - err_inode: +err_inode: free_pipe_info(inode); iput(inode); - err: - return ERR_PTR(err); -} - -void free_write_pipe(struct file *f) -{ - free_pipe_info(f->f_dentry->d_inode); - path_put(&f->f_path); - put_filp(f); -} - -struct file *create_read_pipe(struct file *wrf, int flags) -{ - /* Grab pipe from the writer */ - struct file *f = alloc_file(&wrf->f_path, FMODE_READ, - &read_pipefifo_fops); - if (!f) - return ERR_PTR(-ENFILE); - - path_get(&wrf->f_path); - f->f_flags = O_RDONLY | (flags & O_NONBLOCK); - - return f; + return err; } int do_pipe_flags(int *fd, int flags) { - struct file *fw, *fr; + struct file *files[2]; int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT)) return -EINVAL; - fw = create_write_pipe(flags); - if (IS_ERR(fw)) - return PTR_ERR(fw); - fr = create_read_pipe(fw, flags); - error = PTR_ERR(fr); - if (IS_ERR(fr)) - goto err_write_pipe; + error = create_pipe_files(files, flags); + if (error) + return error; error = get_unused_fd_flags(flags); if (error < 0) @@ -1109,8 +1088,8 @@ int do_pipe_flags(int *fd, int flags) fdw = error; audit_fd_pair(fdr, fdw); - fd_install(fdr, fr); - fd_install(fdw, fw); + fd_install(fdr, files[0]); + fd_install(fdw, files[1]); fd[0] = fdr; fd[1] = fdw; @@ -1119,10 +1098,8 @@ int do_pipe_flags(int *fd, int flags) err_fdr: put_unused_fd(fdr); err_read_pipe: - path_put(&fr->f_path); - put_filp(fr); - err_write_pipe: - free_write_pipe(fw); + fput(files[0]); + fput(files[1]); return error; } diff --git a/fs/splice.c b/fs/splice.c index 7bf08fa..41514dd 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -996,6 +996,8 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, }; ssize_t ret; + sb_start_write(inode->i_sb); + pipe_lock(pipe); splice_from_pipe_begin(&sd); @@ -1034,6 +1036,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, *ppos += ret; balance_dirty_pages_ratelimited_nr(mapping, nr_pages); } + sb_end_write(inode->i_sb); return ret; } @@ -33,12 +33,19 @@ #include <linux/rculist_bl.h> #include <linux/cleancache.h> #include <linux/fsnotify.h> +#include <linux/lockdep.h> #include "internal.h" LIST_HEAD(super_blocks); DEFINE_SPINLOCK(sb_lock); +static char *sb_writers_name[SB_FREEZE_LEVELS] = { + "sb_writers", + "sb_pagefaults", + "sb_internal", +}; + /* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. @@ -102,6 +109,35 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc) return total_objects; } +static int init_sb_writers(struct super_block *s, struct file_system_type *type) +{ + int err; + int i; + + for (i = 0; i < SB_FREEZE_LEVELS; i++) { + err = percpu_counter_init(&s->s_writers.counter[i], 0); + if (err < 0) + goto err_out; + lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i], + &type->s_writers_key[i], 0); + } + init_waitqueue_head(&s->s_writers.wait); + init_waitqueue_head(&s->s_writers.wait_unfrozen); + return 0; +err_out: + while (--i >= 0) + percpu_counter_destroy(&s->s_writers.counter[i]); + return err; +} + +static void destroy_sb_writers(struct super_block *s) +{ + int i; + + for (i = 0; i < SB_FREEZE_LEVELS; i++) + percpu_counter_destroy(&s->s_writers.counter[i]); +} + /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to @@ -117,18 +153,19 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) if (s) { if (security_sb_alloc(s)) { + /* + * We cannot call security_sb_free() without + * security_sb_alloc() succeeding. So bail out manually + */ kfree(s); s = NULL; goto out; } #ifdef CONFIG_SMP s->s_files = alloc_percpu(struct list_head); - if (!s->s_files) { - security_sb_free(s); - kfree(s); - s = NULL; - goto out; - } else { + if (!s->s_files) + goto err_out; + else { int i; for_each_possible_cpu(i) @@ -137,6 +174,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) #else INIT_LIST_HEAD(&s->s_files); #endif + if (init_sb_writers(s, type)) + goto err_out; s->s_flags = flags; s->s_bdi = &default_backing_dev_info; INIT_HLIST_NODE(&s->s_instances); @@ -178,7 +217,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) mutex_init(&s->s_dquot.dqio_mutex); mutex_init(&s->s_dquot.dqonoff_mutex); init_rwsem(&s->s_dquot.dqptr_sem); - init_waitqueue_head(&s->s_wait_unfrozen); s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; @@ -190,6 +228,16 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) } 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; + goto out; } /** @@ -203,6 +251,7 @@ 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)); kfree(s->s_subtype); @@ -651,10 +700,11 @@ struct super_block *get_super_thawed(struct block_device *bdev) { while (1) { struct super_block *s = get_super(bdev); - if (!s || s->s_frozen == SB_UNFROZEN) + if (!s || s->s_writers.frozen == SB_UNFROZEN) return s; up_read(&s->s_umount); - vfs_check_frozen(s, SB_FREEZE_WRITE); + wait_event(s->s_writers.wait_unfrozen, + s->s_writers.frozen == SB_UNFROZEN); put_super(s); } } @@ -732,7 +782,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) int retval; int remount_ro; - if (sb->s_frozen != SB_UNFROZEN) + if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; #ifdef CONFIG_BLOCK @@ -1163,6 +1213,120 @@ out: return ERR_PTR(error); } +/* + * This is an internal function, please use sb_end_{write,pagefault,intwrite} + * instead. + */ +void __sb_end_write(struct super_block *sb, int level) +{ + percpu_counter_dec(&sb->s_writers.counter[level-1]); + /* + * Make sure s_writers are updated before we wake up waiters in + * freeze_super(). + */ + smp_mb(); + if (waitqueue_active(&sb->s_writers.wait)) + wake_up(&sb->s_writers.wait); + rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_); +} +EXPORT_SYMBOL(__sb_end_write); + +#ifdef CONFIG_LOCKDEP +/* + * We want lockdep to tell us about possible deadlocks with freezing but + * it's it bit tricky to properly instrument it. Getting a freeze protection + * works as getting a read lock but there are subtle problems. XFS for example + * gets freeze protection on internal level twice in some cases, which is OK + * only because we already hold a freeze protection also on higher level. Due + * to these cases we have to tell lockdep we are doing trylock when we + * already hold a freeze protection for a higher freeze level. + */ +static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock, + unsigned long ip) +{ + int i; + + if (!trylock) { + for (i = 0; i < level - 1; i++) + if (lock_is_held(&sb->s_writers.lock_map[i])) { + trylock = true; + break; + } + } + rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip); +} +#endif + +/* + * This is an internal function, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +int __sb_start_write(struct super_block *sb, int level, bool wait) +{ +retry: + if (unlikely(sb->s_writers.frozen >= level)) { + if (!wait) + return 0; + wait_event(sb->s_writers.wait_unfrozen, + sb->s_writers.frozen < level); + } + +#ifdef CONFIG_LOCKDEP + acquire_freeze_lock(sb, level, !wait, _RET_IP_); +#endif + percpu_counter_inc(&sb->s_writers.counter[level-1]); + /* + * Make sure counter is updated before we check for frozen. + * freeze_super() first sets frozen and then checks the counter. + */ + smp_mb(); + if (unlikely(sb->s_writers.frozen >= level)) { + __sb_end_write(sb, level); + goto retry; + } + return 1; +} +EXPORT_SYMBOL(__sb_start_write); + +/** + * sb_wait_write - wait until all writers to given file system finish + * @sb: the super for which we wait + * @level: type of writers we wait for (normal vs page fault) + * + * This function waits until there are no writers of given type to given file + * system. Caller of this function should make sure there can be no new writers + * of type @level before calling this function. Otherwise this function can + * livelock. + */ +static void sb_wait_write(struct super_block *sb, int level) +{ + s64 writers; + + /* + * We just cycle-through lockdep here so that it does not complain + * about returning with lock to userspace + */ + rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_); + rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_); + + do { + DEFINE_WAIT(wait); + + /* + * We use a barrier in prepare_to_wait() to separate setting + * of frozen and checking of the counter + */ + prepare_to_wait(&sb->s_writers.wait, &wait, + TASK_UNINTERRUPTIBLE); + + writers = percpu_counter_sum(&sb->s_writers.counter[level-1]); + if (writers) + schedule(); + + finish_wait(&sb->s_writers.wait, &wait); + } while (writers); +} + /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock @@ -1170,6 +1334,31 @@ out: * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs will return * -EBUSY. + * + * During this function, sb->s_writers.frozen goes through these values: + * + * SB_UNFROZEN: File system is normal, all writes progress as usual. + * + * SB_FREEZE_WRITE: The file system is in the process of being frozen. New + * writes should be blocked, though page faults are still allowed. We wait for + * all writes to complete and then proceed to the next stage. + * + * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked + * but internal fs threads can still modify the filesystem (although they + * should not dirty new pages or inodes), writeback can run etc. After waiting + * for all running page faults we sync the filesystem which will clean all + * dirty pages and inodes (no new dirty pages or inodes can be created when + * sync is running). + * + * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs + * modification are blocked (e.g. XFS preallocation truncation on inode + * reclaim). This is usually implemented by blocking new transactions for + * filesystems that have them and need this additional guard. After all + * internal writers are finished we call ->freeze_fs() to finish filesystem + * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is + * mostly auxiliary for filesystems to verify they do not modify frozen fs. + * + * sb->s_writers.frozen is protected by sb->s_umount. */ int freeze_super(struct super_block *sb) { @@ -1177,7 +1366,7 @@ int freeze_super(struct super_block *sb) atomic_inc(&sb->s_active); down_write(&sb->s_umount); - if (sb->s_frozen) { + if (sb->s_writers.frozen != SB_UNFROZEN) { deactivate_locked_super(sb); return -EBUSY; } @@ -1188,33 +1377,53 @@ int freeze_super(struct super_block *sb) } if (sb->s_flags & MS_RDONLY) { - sb->s_frozen = SB_FREEZE_TRANS; - smp_wmb(); + /* Nothing to do really... */ + sb->s_writers.frozen = SB_FREEZE_COMPLETE; up_write(&sb->s_umount); return 0; } - sb->s_frozen = SB_FREEZE_WRITE; + /* From now on, no new normal writers can start */ + sb->s_writers.frozen = SB_FREEZE_WRITE; + smp_wmb(); + + /* Release s_umount to preserve sb_start_write -> s_umount ordering */ + up_write(&sb->s_umount); + + sb_wait_write(sb, SB_FREEZE_WRITE); + + /* Now we go and block page faults... */ + down_write(&sb->s_umount); + sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; smp_wmb(); + sb_wait_write(sb, SB_FREEZE_PAGEFAULT); + + /* All writers are done so after syncing there won't be dirty data */ sync_filesystem(sb); - sb->s_frozen = SB_FREEZE_TRANS; + /* Now wait for internal filesystem counter */ + sb->s_writers.frozen = SB_FREEZE_FS; smp_wmb(); + sb_wait_write(sb, SB_FREEZE_FS); - sync_blockdev(sb->s_bdev); if (sb->s_op->freeze_fs) { ret = sb->s_op->freeze_fs(sb); if (ret) { printk(KERN_ERR "VFS:Filesystem freeze failed\n"); - sb->s_frozen = SB_UNFROZEN; + sb->s_writers.frozen = SB_UNFROZEN; smp_wmb(); - wake_up(&sb->s_wait_unfrozen); + wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; } } + /* + * This is just for debugging purposes so that fs can warn if it + * sees write activity when frozen is set to SB_FREEZE_COMPLETE. + */ + sb->s_writers.frozen = SB_FREEZE_COMPLETE; up_write(&sb->s_umount); return 0; } @@ -1231,7 +1440,7 @@ int thaw_super(struct super_block *sb) int error; down_write(&sb->s_umount); - if (sb->s_frozen == SB_UNFROZEN) { + if (sb->s_writers.frozen == SB_UNFROZEN) { up_write(&sb->s_umount); return -EINVAL; } @@ -1244,16 +1453,15 @@ int thaw_super(struct super_block *sb) if (error) { printk(KERN_ERR "VFS:Filesystem thaw failed\n"); - sb->s_frozen = SB_FREEZE_TRANS; up_write(&sb->s_umount); return error; } } out: - sb->s_frozen = SB_UNFROZEN; + sb->s_writers.frozen = SB_UNFROZEN; smp_wmb(); - wake_up(&sb->s_wait_unfrozen); + wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return 0; diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index a475983..614b2b5 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -228,6 +228,8 @@ static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) ret = 0; if (bb->vm_ops->page_mkwrite) ret = bb->vm_ops->page_mkwrite(vma, vmf); + else + file_update_time(file); sysfs_put_active(attr_sd); return ret; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 15052ff..e562dd4 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -124,6 +124,12 @@ xfs_setfilesize_trans_alloc( ioend->io_append_trans = tp; /* + * We will pass freeze protection with a transaction. So tell lockdep + * we released it. + */ + rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], + 1, _THIS_IP_); + /* * We hand off the transaction to the completion thread now, so * clear the flag here. */ @@ -199,6 +205,15 @@ xfs_end_io( struct xfs_inode *ip = XFS_I(ioend->io_inode); int error = 0; + if (ioend->io_append_trans) { + /* + * We've got freeze protection passed with the transaction. + * Tell lockdep about it. + */ + rwsem_acquire_read( + &ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], + 0, 1, _THIS_IP_); + } if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { ioend->io_error = -EIO; goto done; @@ -1425,6 +1440,9 @@ out_trans_cancel: if (ioend->io_append_trans) { current_set_flags_nested(&ioend->io_append_trans->t_pflags, PF_FSTRANS); + rwsem_acquire_read( + &inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], + 0, 1, _THIS_IP_); xfs_trans_cancel(ioend->io_append_trans, 0); } out_destroy_ioend: diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index c4559c6..56afcdb 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -770,10 +770,12 @@ xfs_file_aio_write( if (ocount == 0) return 0; - xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE); + sb_start_write(inode->i_sb); - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) - return -EIO; + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { + ret = -EIO; + goto out; + } if (unlikely(file->f_flags & O_DIRECT)) ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount); @@ -792,6 +794,8 @@ xfs_file_aio_write( ret = err; } +out: + sb_end_write(inode->i_sb); return ret; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1f1535d..0e0232c 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -364,9 +364,15 @@ xfs_fssetdm_by_handle( if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(parfilp); + if (error) + return error; + dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq); - if (IS_ERR(dentry)) + if (IS_ERR(dentry)) { + mnt_drop_write_file(parfilp); return PTR_ERR(dentry); + } if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) { error = -XFS_ERROR(EPERM); @@ -382,6 +388,7 @@ xfs_fssetdm_by_handle( fsd.fsd_dmstate); out: + mnt_drop_write_file(parfilp); dput(dentry); return error; } @@ -634,7 +641,11 @@ xfs_ioc_space( if (ioflags & IO_INVIS) attr_flags |= XFS_ATTR_DMI; + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags); + mnt_drop_write_file(filp); return -error; } @@ -1163,6 +1174,7 @@ xfs_ioc_fssetxattr( { struct fsxattr fa; unsigned int mask; + int error; if (copy_from_user(&fa, arg, sizeof(fa))) return -EFAULT; @@ -1171,7 +1183,12 @@ xfs_ioc_fssetxattr( if (filp->f_flags & (O_NDELAY|O_NONBLOCK)) mask |= FSX_NONBLOCK; - return -xfs_ioctl_setattr(ip, &fa, mask); + error = mnt_want_write_file(filp); + if (error) + return error; + error = xfs_ioctl_setattr(ip, &fa, mask); + mnt_drop_write_file(filp); + return -error; } STATIC int @@ -1196,6 +1213,7 @@ xfs_ioc_setxflags( struct fsxattr fa; unsigned int flags; unsigned int mask; + int error; if (copy_from_user(&flags, arg, sizeof(flags))) return -EFAULT; @@ -1210,7 +1228,12 @@ xfs_ioc_setxflags( mask |= FSX_NONBLOCK; fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip)); - return -xfs_ioctl_setattr(ip, &fa, mask); + error = mnt_want_write_file(filp); + if (error) + return error; + error = xfs_ioctl_setattr(ip, &fa, mask); + mnt_drop_write_file(filp); + return -error; } STATIC int @@ -1385,8 +1408,13 @@ xfs_file_ioctl( if (copy_from_user(&dmi, arg, sizeof(dmi))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; + error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask, dmi.fsd_dmstate); + mnt_drop_write_file(filp); return -error; } @@ -1434,7 +1462,11 @@ xfs_file_ioctl( if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_swapext(&sxp); + mnt_drop_write_file(filp); return -error; } @@ -1463,9 +1495,14 @@ xfs_file_ioctl( if (copy_from_user(&inout, arg, sizeof(inout))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; + /* input parameter is passed in resblks field of structure */ in = inout.resblks; error = xfs_reserve_blocks(mp, &in, &inout); + mnt_drop_write_file(filp); if (error) return -error; @@ -1496,7 +1533,11 @@ xfs_file_ioctl( if (copy_from_user(&in, arg, sizeof(in))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_growfs_data(mp, &in); + mnt_drop_write_file(filp); return -error; } @@ -1506,7 +1547,11 @@ xfs_file_ioctl( if (copy_from_user(&in, arg, sizeof(in))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_growfs_log(mp, &in); + mnt_drop_write_file(filp); return -error; } @@ -1516,7 +1561,11 @@ xfs_file_ioctl( if (copy_from_user(&in, arg, sizeof(in))) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_growfs_rt(mp, &in); + mnt_drop_write_file(filp); return -error; } diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index c4f2da0..1244274a 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -600,7 +600,11 @@ xfs_file_compat_ioctl( if (xfs_compat_growfs_data_copyin(&in, arg)) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_growfs_data(mp, &in); + mnt_drop_write_file(filp); return -error; } case XFS_IOC_FSGROWFSRT_32: { @@ -608,7 +612,11 @@ xfs_file_compat_ioctl( if (xfs_compat_growfs_rt_copyin(&in, arg)) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_growfs_rt(mp, &in); + mnt_drop_write_file(filp); return -error; } #endif @@ -627,7 +635,11 @@ xfs_file_compat_ioctl( offsetof(struct xfs_swapext, sx_stat)) || xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat)) return -XFS_ERROR(EFAULT); + error = mnt_want_write_file(filp); + if (error) + return error; error = xfs_swapext(&sxp); + mnt_drop_write_file(filp); return -error; } case XFS_IOC_FSBULKSTAT_32: diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 915edf6..973dff6 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -680,9 +680,9 @@ xfs_iomap_write_unwritten( * the same inode that we complete here and might deadlock * on the iolock. */ - xfs_wait_for_freeze(mp, SB_FREEZE_TRANS); + sb_start_intwrite(mp->m_super); tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS); - tp->t_flags |= XFS_TRANS_RESERVE; + tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT; error = xfs_trans_reserve(tp, resblks, XFS_WRITE_LOG_RES(mp), 0, XFS_TRANS_PERM_LOG_RES, diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 711ca51..29c2f83 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1551,7 +1551,7 @@ xfs_unmountfs( int xfs_fs_writable(xfs_mount_t *mp) { - return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) || + return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) || (mp->m_flags & XFS_MOUNT_RDONLY)); } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 8724336..05a05a7 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -311,9 +311,6 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname, #define SHUTDOWN_REMOTE_REQ 0x0010 /* shutdown came from remote cell */ #define SHUTDOWN_DEVICE_REQ 0x0020 /* failed all paths to the device */ -#define xfs_test_for_freeze(mp) ((mp)->m_super->s_frozen) -#define xfs_wait_for_freeze(mp,l) vfs_check_frozen((mp)->m_super, (l)) - /* * Flags for xfs_mountfs */ diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index 97304f1..9654817 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -403,7 +403,7 @@ xfs_sync_worker( if (!(mp->m_super->s_flags & MS_ACTIVE) && !(mp->m_flags & XFS_MOUNT_RDONLY)) { /* dgc: errors ignored here */ - if (mp->m_super->s_frozen == SB_UNFROZEN && + if (mp->m_super->s_writers.frozen == SB_UNFROZEN && xfs_log_need_covered(mp)) error = xfs_fs_log_dummy(mp); else diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index fdf3245..06ed520 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -576,8 +576,12 @@ xfs_trans_alloc( xfs_mount_t *mp, uint type) { - xfs_wait_for_freeze(mp, SB_FREEZE_TRANS); - return _xfs_trans_alloc(mp, type, KM_SLEEP); + xfs_trans_t *tp; + + sb_start_intwrite(mp->m_super); + tp = _xfs_trans_alloc(mp, type, KM_SLEEP); + tp->t_flags |= XFS_TRANS_FREEZE_PROT; + return tp; } xfs_trans_t * @@ -588,6 +592,7 @@ _xfs_trans_alloc( { xfs_trans_t *tp; + WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); atomic_inc(&mp->m_active_trans); tp = kmem_zone_zalloc(xfs_trans_zone, memflags); @@ -611,6 +616,8 @@ xfs_trans_free( xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false); atomic_dec(&tp->t_mountp->m_active_trans); + if (tp->t_flags & XFS_TRANS_FREEZE_PROT) + sb_end_intwrite(tp->t_mountp->m_super); xfs_trans_free_dqinfo(tp); kmem_zone_free(xfs_trans_zone, tp); } @@ -643,7 +650,11 @@ xfs_trans_dup( ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(tp->t_ticket != NULL); - ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE); + ntp->t_flags = XFS_TRANS_PERM_LOG_RES | + (tp->t_flags & XFS_TRANS_RESERVE) | + (tp->t_flags & XFS_TRANS_FREEZE_PROT); + /* We gave our writer reference to the new transaction */ + tp->t_flags &= ~XFS_TRANS_FREEZE_PROT; ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket); ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used; tp->t_blk_res = tp->t_blk_res_used; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index bc2afd5..db05654 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -179,6 +179,8 @@ struct xfs_log_item_desc { #define XFS_TRANS_SYNC 0x08 /* make commit synchronous */ #define XFS_TRANS_DQ_DIRTY 0x10 /* at least one dquot in trx dirty */ #define XFS_TRANS_RESERVE 0x20 /* OK to use reserved data blocks */ +#define XFS_TRANS_FREEZE_PROT 0x40 /* Transaction has elevated writer + count in superblock */ /* * Values for call flags parameter. |
