From eccbe858ce6412b96fc7cb32eb23a3592f64e5f6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Fabian=20Silva=20Delgado?= Date: Tue, 8 Mar 2016 21:17:20 -0300 Subject: Linux-libre 4.4.4-gnu --- fs/aufs/cpup.c | 4 ++- fs/aufs/f_op.c | 24 +++++++++++++++++ fs/btrfs/disk-io.c | 28 ++++++++++++++++++++ fs/btrfs/inode-map.c | 9 +------ fs/btrfs/inode-map.h | 1 + fs/btrfs/inode.c | 27 +++++++++++++++---- fs/btrfs/ioctl.c | 4 +++ fs/btrfs/send.c | 16 ++++++++++- fs/btrfs/super.c | 24 +++++++++++++++++ fs/btrfs/volumes.c | 1 + fs/dcache.c | 2 +- fs/direct-io.c | 2 +- fs/efivarfs/file.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++ fs/efivarfs/inode.c | 30 +++++++++++++-------- fs/efivarfs/internal.h | 3 ++- fs/efivarfs/super.c | 16 ++++++----- fs/exec.c | 2 +- fs/ext4/inode.c | 32 ++++++++++++++++++++-- fs/fcntl.c | 5 +++- fs/file_table.c | 8 +++--- fs/fs-writeback.c | 15 ++++++++--- fs/hostfs/hostfs_kern.c | 4 +-- fs/hpfs/namei.c | 31 +++------------------- fs/locks.c | 51 ++++++++++++++++++++--------------- fs/namei.c | 22 +++++++++++----- fs/namespace.c | 2 +- fs/nfs/nfs4proc.c | 4 +-- fs/notify/group.c | 6 ++--- fs/notify/mark.c | 8 +++--- fs/ocfs2/aops.c | 1 + fs/open.c | 4 +-- fs/read_write.c | 4 +-- fs/splice.c | 4 +-- fs/xattr.c | 2 +- 34 files changed, 343 insertions(+), 123 deletions(-) (limited to 'fs') diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c index d34a6d283..cadb3adb7 100644 --- a/fs/aufs/cpup.c +++ b/fs/aufs/cpup.c @@ -527,6 +527,8 @@ static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) /* forget_all_cached_acls(h_inode)); */ err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); AuTraceErr(err); + if (err == -EOPNOTSUPP) + err = 0; if (!err) err = vfsub_acl_chmod(h_inode, mode); @@ -605,7 +607,7 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, switch (mode & S_IFMT) { case S_IFREG: isreg = 1; - err = vfsub_create(h_dir, &h_path, mode | S_IWUSR, + err = vfsub_create(h_dir, &h_path, S_IRUSR | S_IWUSR, /*want_excl*/true); if (!err) err = au_do_cpup_regular(cpg, h_src_attr); diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c index 2baacd7a6..145dec870 100644 --- a/fs/aufs/f_op.c +++ b/fs/aufs/f_op.c @@ -688,6 +688,29 @@ out: return err; } +static int aufs_setfl(struct file *file, unsigned long arg) +{ + int err; + struct file *h_file; + struct super_block *sb; + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + arg |= vfsub_file_flags(file) & FASYNC; /* stop calling h_file->fasync */ + err = setfl(/*unused fd*/-1, h_file, arg); + fput(h_file); /* instead of au_read_post() */ + +out: + si_read_unlock(sb); + return err; +} + /* ---------------------------------------------------------------------- */ /* no one supports this operation, currently */ @@ -725,6 +748,7 @@ const struct file_operations aufs_file_fop = { /* .aio_fsync = aufs_aio_fsync_nondir, */ .fasync = aufs_fasync, /* .sendpage = aufs_sendpage, */ + .setfl = aufs_setfl, .splice_write = aufs_splice_write, .splice_read = aufs_splice_read, #if 0 diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0ddca6734..4958360a4 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1582,8 +1582,23 @@ int btrfs_init_fs_root(struct btrfs_root *root) ret = get_anon_bdev(&root->anon_dev); if (ret) goto free_writers; + + mutex_lock(&root->objectid_mutex); + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + if (ret) { + mutex_unlock(&root->objectid_mutex); + goto free_root_dev; + } + + ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&root->objectid_mutex); + return 0; +free_root_dev: + free_anon_bdev(root->anon_dev); free_writers: btrfs_free_subvolume_writers(root->subv_writers); fail: @@ -2667,6 +2682,7 @@ int open_ctree(struct super_block *sb, if (btrfs_check_super_csum(bh->b_data)) { printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); err = -EINVAL; + brelse(bh); goto fail_alloc; } @@ -2899,6 +2915,18 @@ retry_root_backup: tree_root->commit_root = btrfs_root_node(tree_root); btrfs_set_root_refs(&tree_root->root_item, 1); + mutex_lock(&tree_root->objectid_mutex); + ret = btrfs_find_highest_objectid(tree_root, + &tree_root->highest_objectid); + if (ret) { + mutex_unlock(&tree_root->objectid_mutex); + goto recovery_tree_root; + } + + ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&tree_root->objectid_mutex); + ret = btrfs_read_roots(fs_info, tree_root); if (ret) goto recovery_tree_root; diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 767a6056a..07573dc16 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -515,7 +515,7 @@ out: return ret; } -static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) { struct btrfs_path *path; int ret; @@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) int ret; mutex_lock(&root->objectid_mutex); - if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) { - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); - if (ret) - goto out; - } - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { ret = -ENOSPC; goto out; diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h index ddb347bfe..c8e864b2d 100644 --- a/fs/btrfs/inode-map.h +++ b/fs/btrfs/inode-map.h @@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans); int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 54b5f0de6..52fc1b5e9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6493,7 +6493,7 @@ out_unlock_inode: static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; struct btrfs_root *root = BTRFS_I(dir)->root; struct inode *inode = d_inode(old_dentry); u64 index; @@ -6519,6 +6519,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, trans = btrfs_start_transaction(root, 5); if (IS_ERR(trans)) { err = PTR_ERR(trans); + trans = NULL; goto fail; } @@ -6552,9 +6553,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, btrfs_log_new_name(trans, inode, NULL, parent); } - btrfs_end_transaction(trans, root); btrfs_balance_delayed_items(root); fail: + if (trans) + btrfs_end_transaction(trans, root); if (drop_inode) { inode_dec_link_count(inode); iput(inode); @@ -8548,15 +8550,28 @@ int btrfs_readpage(struct file *file, struct page *page) static int btrfs_writepage(struct page *page, struct writeback_control *wbc) { struct extent_io_tree *tree; - + struct inode *inode = page->mapping->host; + int ret; if (current->flags & PF_MEMALLOC) { redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; } + + /* + * If we are under memory pressure we will call this directly from the + * VM, we need to make sure we have the inode referenced for the ordered + * extent. If not just return like we didn't do anything. + */ + if (!igrab(inode)) { + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; + } tree = &BTRFS_I(page->mapping->host)->io_tree; - return extent_write_full_page(tree, page, btrfs_get_extent, wbc); + ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc); + btrfs_add_delayed_iput(inode); + return ret; } static int btrfs_writepages(struct address_space *mapping, @@ -9650,9 +9665,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, /* * 2 items for inode item and ref * 2 items for dir items + * 1 item for updating parent inode item + * 1 item for the inline extent item * 1 item for xattr if selinux is on */ - trans = btrfs_start_transaction(root, 5); + trans = btrfs_start_transaction(root, 7); if (IS_ERR(trans)) return PTR_ERR(trans); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 08fd3f0f3..f07d01bc4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir, goto fail; } + mutex_lock(&new_root->objectid_mutex); + new_root->highest_objectid = new_dirid; + mutex_unlock(&new_root->objectid_mutex); + /* * insert the directory item */ diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 355a458cb..63a6152be 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1469,7 +1469,21 @@ static int read_symlink(struct btrfs_root *root, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; - BUG_ON(ret); + if (ret) { + /* + * An empty symlink inode. Can happen in rare error paths when + * creating a symlink (transaction committed before the inode + * eviction handler removed the symlink inode items and a crash + * happened in between or the subvol was snapshoted in between). + * Print an informative message to dmesg/syslog so that the user + * can delete the symlink. + */ + btrfs_err(root->fs_info, + "Found empty symlink inode %llu at root %llu", + ino, root->root_key.objectid); + ret = -EIO; + goto out; + } ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_file_extent_item); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 24154e422..fe609b81d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1956,6 +1956,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) * there are other factors that may change the result (like a new metadata * chunk). * + * If metadata is exhausted, f_bavail will be 0. + * * FIXME: not accurate for mixed block groups, total and free/used are ok, * available appears slightly larger. */ @@ -1967,11 +1969,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; + u64 total_free_meta = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)fs_info->fsid; unsigned factor = 1; struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; + u64 thresh = 0; /* * holding chunk_muext to avoid allocating new chunks, holding @@ -1997,6 +2001,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) } } } + if (found->flags & BTRFS_BLOCK_GROUP_METADATA) + total_free_meta += found->disk_total - found->disk_used; total_used += found->disk_used; } @@ -2019,6 +2025,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail += div_u64(total_free_data, factor); buf->f_bavail = buf->f_bavail >> bits; + /* + * We calculate the remaining metadata space minus global reserve. If + * this is (supposedly) smaller than zero, there's no space. But this + * does not hold in practice, the exhausted state happens where's still + * some positive delta. So we apply some guesswork and compare the + * delta to a 4M threshold. (Practically observed delta was ~2M.) + * + * We probably cannot calculate the exact threshold value because this + * depends on the internal reservations requested by various + * operations, so some operations that consume a few metadata will + * succeed even if the Avail is zero. But this is better than the other + * way around. + */ + thresh = 4 * 1024 * 1024; + + if (total_free_meta - thresh < block_rsv->size) + buf->f_bavail = 0; + buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_namelen = BTRFS_NAME_LEN; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9e084477d..9c62a6f97 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -232,6 +232,7 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); diff --git a/fs/dcache.c b/fs/dcache.c index f997345b8..ff9a6f397 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1272,7 +1272,7 @@ rename_retry: seq = 1; goto again; } -EXPORT_SYMBOL(d_walk); +EXPORT_SYMBOL_GPL(d_walk); /* * Search for at least 1 mount point in the dentry's subdirs. diff --git a/fs/direct-io.c b/fs/direct-io.c index 602e8441b..01171d8a6 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -472,8 +472,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) dio->io_error = -EIO; if (dio->is_async && dio->rw == READ && dio->should_dirty) { - bio_check_pages_dirty(bio); /* transfers ownership */ err = bio->bi_error; + bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 90001da9a..66842e55c 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internal.h" @@ -103,9 +104,78 @@ out_free: return size; } +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int i_flags; + unsigned int flags = 0; + + i_flags = inode->i_flags; + if (i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (copy_to_user(arg, &flags, sizeof(flags))) + return -EFAULT; + return 0; +} + +static int +efivarfs_ioc_setxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags; + unsigned int i_flags = 0; + int error; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (copy_from_user(&flags, arg, sizeof(flags))) + return -EFAULT; + + if (flags & ~FS_IMMUTABLE_FL) + return -EOPNOTSUPP; + + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + if (flags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + + + error = mnt_want_write_file(file); + if (error) + return error; + + mutex_lock(&inode->i_mutex); + inode_set_flags(inode, i_flags, S_IMMUTABLE); + mutex_unlock(&inode->i_mutex); + + mnt_drop_write_file(file); + + return 0; +} + +long +efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) +{ + void __user *arg = (void __user *)p; + + switch (cmd) { + case FS_IOC_GETFLAGS: + return efivarfs_ioc_getxflags(file, arg); + case FS_IOC_SETFLAGS: + return efivarfs_ioc_setxflags(file, arg); + } + + return -ENOTTY; +} + const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, .llseek = no_llseek, + .unlocked_ioctl = efivarfs_file_ioctl, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 3381b9da9..e2ab6d049 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -15,7 +15,8 @@ #include "internal.h" struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) + const struct inode *dir, int mode, + dev_t dev, bool is_removable) { struct inode *inode = new_inode(sb); @@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: inode->i_fop = &efivarfs_file_operations; @@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) static int efivarfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; + struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; + bool is_removable = false; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); - if (!inode) - return -ENOMEM; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) { - err = -ENOMEM; - goto out; - } + if (!var) + return -ENOMEM; /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; @@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (efivar_variable_is_removable(var->var.VendorGuid, + dentry->d_name.name, namelen)) + is_removable = true; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); + if (!inode) { + err = -ENOMEM; + goto out; + } + for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, out: if (err) { kfree(var); - iput(inode); + if (inode) + iput(inode); } return err; } diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b5ff16add..b4505188e 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev); + const struct inode *dir, int mode, dev_t dev, + bool is_removable); extern struct list_head efivarfs_list; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 86a212182..abb244b06 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, struct dentry *dentry, *root = sb->s_root; unsigned long size = 0; char *name; - int len, i; + int len; int err = -ENOMEM; + bool is_removable = false; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) @@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, memcpy(entry->var.VariableName, name16, name_size); memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); - len = ucs2_strlen(entry->var.VariableName); + len = ucs2_utf8size(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); if (!name) goto fail; - for (i = 0; i < len; i++) - name[i] = entry->var.VariableName[i] & 0xFF; + ucs2_as_utf8(name, entry->var.VariableName, len); + + if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + is_removable = true; name[len] = '-'; @@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, + is_removable); if (!inode) goto fail_name; @@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; - inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; inode->i_op = &efivarfs_dir_inode_operations; diff --git a/fs/exec.c b/fs/exec.c index 0aebe362d..203f822aa 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -106,7 +106,7 @@ bool path_noexec(const struct path *path) return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } -EXPORT_SYMBOL(path_noexec); +EXPORT_SYMBOL_GPL(path_noexec); #ifdef CONFIG_USELIB /* diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ea433a7f4..06bda0361 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -657,6 +657,34 @@ has_zeroout: return retval; } +/* + * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages + * we have to be careful as someone else may be manipulating b_state as well. + */ +static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) +{ + unsigned long old_state; + unsigned long new_state; + + flags &= EXT4_MAP_FLAGS; + + /* Dummy buffer_head? Set non-atomically. */ + if (!bh->b_page) { + bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; + return; + } + /* + * Someone else may be modifying b_state. Be careful! This is ugly but + * once we get rid of using bh as a container for mapping information + * to pass to / from get_block functions, this can go away. + */ + do { + old_state = READ_ONCE(bh->b_state); + new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; + } while (unlikely( + cmpxchg(&bh->b_state, old_state, new_state) != old_state)); +} + /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 @@ -693,7 +721,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ext4_io_end_t *io_end = ext4_inode_aio(inode); map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (IS_DAX(inode) && buffer_unwritten(bh)) { /* * dgc: I suspect unwritten conversion on ext4+DAX is @@ -1669,7 +1697,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked diff --git a/fs/fcntl.c b/fs/fcntl.c index ee85cd4e1..8abb9f814 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -29,7 +29,7 @@ #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) -static int setfl(int fd, struct file * filp, unsigned long arg) +int setfl(int fd, struct file * filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; @@ -59,6 +59,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg) if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); + if (!error && filp->f_op->setfl) + error = filp->f_op->setfl(filp, arg); if (error) return error; @@ -79,6 +81,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) out: return error; } +EXPORT_SYMBOL_GPL(setfl); static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) diff --git a/fs/file_table.c b/fs/file_table.c index 38e046adc..ae9f2676d 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -147,7 +147,7 @@ over: } return ERR_PTR(-ENFILE); } -EXPORT_SYMBOL(get_empty_filp); +EXPORT_SYMBOL_GPL(get_empty_filp); /** * alloc_file - allocate and initialize a 'struct file' @@ -259,7 +259,7 @@ void flush_delayed_fput(void) { delayed_fput(NULL); } -EXPORT_SYMBOL(flush_delayed_fput); +EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); @@ -302,7 +302,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); -EXPORT_SYMBOL(__fput_sync); +EXPORT_SYMBOL_GPL(__fput_sync); void put_filp(struct file *file) { @@ -311,7 +311,7 @@ void put_filp(struct file *file) file_free(file); } } -EXPORT_SYMBOL(put_filp); +EXPORT_SYMBOL_GPL(put_filp); void __init files_init(void) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 023f6a1f2..e5232bbcb 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -317,6 +317,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; + struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -423,6 +424,7 @@ skip_switch: wb_put(new_wb); iput(inode); + deactivate_super(sb); kfree(isw); } @@ -469,11 +471,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); + if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) { - spin_unlock(&inode->i_lock); - goto out_free; - } + inode_to_wb(inode) == isw->new_wb) + goto out_unlock; + + if (!atomic_inc_not_zero(&inode->i_sb->s_active)) + goto out_unlock; + inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); @@ -489,6 +494,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; +out_unlock: + spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2ac99db37..5a7b3229b 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -730,15 +730,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, init_special_inode(inode, mode, dev); err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); - if (!err) + if (err) goto out_free; err = read_name(inode, name); __putname(name); if (err) goto out_put; - if (err) - goto out_put; d_instantiate(dentry, inode); return 0; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index ae4d5a1fa..bffb908ac 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -375,12 +375,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -400,33 +399,9 @@ again: hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; diff --git a/fs/locks.c b/fs/locks.c index 0d2b3267e..6333263b7 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2182,7 +2182,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2224,19 +2223,22 @@ again: * Attempt to detect a close/fcntl race and recover by * releasing the lock that was just acquired. */ - /* - * we need that spin_lock here - it prevents reordering between - * update of i_flctx->flc_posix and check for it done in close(). - * rcu_read_lock() wouldn't do. - */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; @@ -2322,7 +2324,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2364,14 +2365,22 @@ again: * Attempt to detect a close/fcntl race and recover by * releasing the lock that was just acquired. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; diff --git a/fs/namei.c b/fs/namei.c index 0c3974cd3..d8ee4da93 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1711,6 +1711,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link, return 0; if (!follow) return 0; + /* make sure that d_is_symlink above matches inode */ + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&link->dentry->d_seq, seq)) + return -ECHILD; + } return pick_link(nd, link, inode, seq); } @@ -1742,11 +1747,11 @@ static int walk_component(struct nameidata *nd, int flags) if (err < 0) return err; - inode = d_backing_inode(path.dentry); seq = 0; /* we are already out of RCU mode */ err = -ENOENT; if (d_is_negative(path.dentry)) goto out_path_put; + inode = d_backing_inode(path.dentry); } if (flags & WALK_PUT) @@ -3130,12 +3135,12 @@ retry_lookup: return error; BUG_ON(nd->flags & LOOKUP_RCU); - inode = d_backing_inode(path.dentry); seq = 0; /* out of RCU mode, so the value doesn't matter */ if (unlikely(d_is_negative(path.dentry))) { path_to_nameidata(&path, nd); return -ENOENT; } + inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) put_link(nd); @@ -3144,11 +3149,6 @@ finish_lookup: if (unlikely(error)) return error; - if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) { - path_to_nameidata(&path, nd); - return -ELOOP; - } - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { path_to_nameidata(&path, nd); } else { @@ -3167,6 +3167,10 @@ finish_open: return error; } audit_inode(nd->name, nd->path.dentry, 0); + if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { + error = -ELOOP; + goto out; + } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; @@ -3210,6 +3214,10 @@ opened: goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); diff --git a/fs/namespace.c b/fs/namespace.c index ec560d8f4..fc5002819 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1804,7 +1804,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, } return 0; } -EXPORT_SYMBOL(iterate_mounts); +EXPORT_SYMBOL_GPL(iterate_mounts); static void cleanup_group_ids(struct mount *mnt, struct mount *end) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f496ed721..98a441573 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2461,9 +2461,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); diff --git a/fs/notify/group.c b/fs/notify/group.c index 06ca6bc4a..53e45b61d 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -73,7 +73,7 @@ void fsnotify_get_group(struct fsnotify_group *group) { atomic_inc(&group->refcnt); } -EXPORT_SYMBOL(fsnotify_get_group); +EXPORT_SYMBOL_GPL(fsnotify_get_group); /* * Drop a reference to a group. Free it if it's through. @@ -83,7 +83,7 @@ void fsnotify_put_group(struct fsnotify_group *group) if (atomic_dec_and_test(&group->refcnt)) fsnotify_final_destroy_group(group); } -EXPORT_SYMBOL(fsnotify_put_group); +EXPORT_SYMBOL_GPL(fsnotify_put_group); /* * Create a new fsnotify_group and hold a reference for the group returned. @@ -112,7 +112,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) return group; } -EXPORT_SYMBOL(fsnotify_alloc_group); +EXPORT_SYMBOL_GPL(fsnotify_alloc_group); int fsnotify_fasync(int fd, struct file *file, int on) { diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 325b5c686..8175f3cd4 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -109,7 +109,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) mark->free_mark(mark); } } -EXPORT_SYMBOL(fsnotify_put_mark); +EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* Calculate mask of events for a list of marks */ u32 fsnotify_recalc_mask(struct hlist_head *head) @@ -209,7 +209,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark, mutex_unlock(&group->mark_mutex); fsnotify_free_mark(mark); } -EXPORT_SYMBOL(fsnotify_destroy_mark); +EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock) { @@ -394,7 +394,7 @@ err: return ret; } -EXPORT_SYMBOL(fsnotify_add_mark); +EXPORT_SYMBOL_GPL(fsnotify_add_mark); int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, struct vfsmount *mnt, int allow_dups) @@ -495,7 +495,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } -EXPORT_SYMBOL(fsnotify_init_mark); +EXPORT_SYMBOL_GPL(fsnotify_init_mark); static int fsnotify_mark_destroy(void *ignored) { diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 7f604727f..e6795c7c7 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -956,6 +956,7 @@ clean_orphan: tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, update_isize, end); if (tmp_ret < 0) { + ocfs2_inode_unlock(inode, 1); ret = tmp_ret; mlog_errno(ret); brelse(di_bh); diff --git a/fs/open.c b/fs/open.c index adc58f69f..32dfe4f2a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -67,7 +67,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, mutex_unlock(&dentry->d_inode->i_mutex); return ret; } -EXPORT_SYMBOL(do_truncate); +EXPORT_SYMBOL_GPL(do_truncate); long vfs_truncate(struct path *path, loff_t length) { @@ -682,7 +682,7 @@ int open_check_o_direct(struct file *f) } return 0; } -EXPORT_SYMBOL(open_check_o_direct); +EXPORT_SYMBOL_GPL(open_check_o_direct); static int do_dentry_open(struct file *f, struct inode *inode, diff --git a/fs/read_write.c b/fs/read_write.c index 8ace6ec15..0a2893354 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -504,7 +504,7 @@ vfs_readf_t vfs_readf(struct file *file) return new_sync_read; return ERR_PTR(-ENOSYS); } -EXPORT_SYMBOL(vfs_readf); +EXPORT_SYMBOL_GPL(vfs_readf); vfs_writef_t vfs_writef(struct file *file) { @@ -516,7 +516,7 @@ vfs_writef_t vfs_writef(struct file *file) return new_sync_write; return ERR_PTR(-ENOSYS); } -EXPORT_SYMBOL(vfs_writef); +EXPORT_SYMBOL_GPL(vfs_writef); ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) { diff --git a/fs/splice.c b/fs/splice.c index c37c311f2..b0ade1fd4 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1123,7 +1123,7 @@ long do_splice_from(struct pipe_inode_info *pipe, struct file *out, return splice_write(pipe, out, ppos, len, flags); } -EXPORT_SYMBOL(do_splice_from); +EXPORT_SYMBOL_GPL(do_splice_from); /* * Attempt to initiate a splice from a file to a pipe. @@ -1150,7 +1150,7 @@ long do_splice_to(struct file *in, loff_t *ppos, return splice_read(in, ppos, pipe, len, flags); } -EXPORT_SYMBOL(do_splice_to); +EXPORT_SYMBOL_GPL(do_splice_to); /** * splice_direct_to_actor - splices data directly between two non-pipes diff --git a/fs/xattr.c b/fs/xattr.c index 44c457a6d..0c317c4fd 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -207,7 +207,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, *xattr_value = value; return error; } -EXPORT_SYMBOL(vfs_getxattr_alloc); +EXPORT_SYMBOL_GPL(vfs_getxattr_alloc); /* Compare an extended attribute value with the given value */ int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, -- cgit v1.2.3