diff options
Diffstat (limited to 'fs')
351 files changed, 16771 insertions, 9364 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index d384a8b..aa5ecf4 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -183,7 +183,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) else flock.length = fl->fl_end - fl->fl_start + 1; flock.proc_id = fl->fl_pid; - flock.client_id = utsname()->nodename; + flock.client_id = fid->clnt->name; if (IS_SETLKW(cmd)) flock.flags = P9_LOCK_FLAGS_BLOCK; @@ -260,7 +260,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) else glock.length = fl->fl_end - fl->fl_start + 1; glock.proc_id = fl->fl_pid; - glock.client_id = utsname()->nodename; + glock.client_id = fid->clnt->name; res = p9_client_getlock_dotl(fid, &glock); if (res < 0) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 25b018e..94de6d1 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -146,7 +146,7 @@ static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses, char type = 0, ext[32]; int major = -1, minor = -1; - strncpy(ext, stat->extension, sizeof(ext)); + strlcpy(ext, stat->extension, sizeof(ext)); sscanf(ext, "%c %u %u", &type, &major, &minor); switch (type) { case 'c': @@ -1186,7 +1186,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, * this even with .u extension. So check * for non NULL stat->extension */ - strncpy(ext, stat->extension, sizeof(ext)); + strlcpy(ext, stat->extension, sizeof(ext)); /* HARDLINKCOUNT %u */ sscanf(ext, "%13s %u", tag_name, &i_nlink); if (!strncmp(tag_name, "HARDLINKCOUNT", 13)) diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 5f95d1e..b9acada 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -50,7 +50,7 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } static int adfs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/affs/file.c b/fs/affs/file.c index af3261b..8669b6e 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -406,7 +406,7 @@ static void affs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); affs_truncate(inode); } } @@ -836,7 +836,7 @@ affs_truncate(struct inode *inode) struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata; - u32 size = inode->i_size; + loff_t size = inode->i_size; int res; res = mapping->a_ops->write_begin(NULL, mapping, size, 0, 0, &page, &fsdata); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 34494fb..646337d 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -685,16 +685,12 @@ not_found: spin_unlock(&dentry->d_lock); out_bad: - if (dentry->d_inode) { - /* don't unhash if we have submounts */ - if (have_submounts(dentry)) - goto out_skip; - } + /* don't unhash if we have submounts */ + if (check_submounts_and_drop(dentry) != 0) + goto out_skip; _debug("dropping dentry %s/%s", parent->d_name.name, dentry->d_name.name); - shrink_dcache_parent(dentry); - d_drop(dentry); dput(parent); key_put(key); @@ -755,10 +751,6 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) _enter("{%x:%u},{%s},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode); - ret = -ENAMETOOLONG; - if (dentry->d_name.len >= AFSNAMEMAX) - goto error; - key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); @@ -820,10 +812,6 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) _enter("{%x:%u},{%s}", dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name); - ret = -ENAMETOOLONG; - if (dentry->d_name.len >= AFSNAMEMAX) - goto error; - key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); @@ -940,10 +928,6 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, _enter("{%x:%u},{%s},%ho,", dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode); - ret = -ENAMETOOLONG; - if (dentry->d_name.len >= AFSNAMEMAX) - goto error; - key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); @@ -1009,10 +993,6 @@ static int afs_link(struct dentry *from, struct inode *dir, dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name); - ret = -ENAMETOOLONG; - if (dentry->d_name.len >= AFSNAMEMAX) - goto error; - key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); @@ -1057,10 +1037,6 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, content); - ret = -ENAMETOOLONG; - if (dentry->d_name.len >= AFSNAMEMAX) - goto error; - ret = -EINVAL; if (strlen(content) >= AFSPATHMAX) goto error; @@ -1131,10 +1107,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dvnode->fid.vid, new_dvnode->fid.vnode, new_dentry->d_name.name); - ret = -ENAMETOOLONG; - if (new_dentry->d_name.len >= AFSNAMEMAX) - goto error; - key = afs_request_key(orig_dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 743c7c2..0f00da3 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -183,13 +183,14 @@ static int autofs_dev_ioctl_protosubver(struct file *fp, return 0; } +/* Find the topmost mount satisfying test() */ static int find_autofs_mount(const char *pathname, struct path *res, int test(struct path *path, void *data), void *data) { struct path path; - int err = kern_path(pathname, 0, &path); + int err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0); if (err) return err; err = -ENOENT; @@ -197,10 +198,9 @@ static int find_autofs_mount(const char *pathname, if (path.dentry->d_sb->s_magic == AUTOFS_SUPER_MAGIC) { if (test(&path, data)) { path_get(&path); - if (!err) /* already found some */ - path_put(res); *res = path; err = 0; + break; } } if (!follow_up(&path)) @@ -486,12 +486,11 @@ static int autofs_dev_ioctl_askumount(struct file *fp, * mount if there is one or 0 if it isn't a mountpoint. * * If we aren't supplied with a file descriptor then we - * lookup the nameidata of the path and check if it is the - * root of a mount. If a type is given we are looking for - * a particular autofs mount and if we don't find a match - * we return fail. If the located nameidata path is the - * root of a mount we return 1 along with the super magic - * of the mount or 0 otherwise. + * lookup the path and check if it is the root of a mount. + * If a type is given we are looking for a particular autofs + * mount and if we don't find a match we return fail. If the + * located path is the root of a mount we return 1 along with + * the super magic of the mount or 0 otherwise. * * In both cases the the device number (as returned by * new_encode_dev()) is also returned. @@ -519,9 +518,11 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp, if (!fp || param->ioctlfd == -1) { if (autofs_type_any(type)) - err = kern_path(name, LOOKUP_FOLLOW, &path); + err = kern_path_mountpoint(AT_FDCWD, + name, &path, LOOKUP_FOLLOW); else - err = find_autofs_mount(name, &path, test_by_type, &type); + err = find_autofs_mount(name, &path, + test_by_type, &type); if (err) goto out; devid = new_encode_dev(path.dentry->d_sb->s_dev); diff --git a/fs/bfs/file.c b/fs/bfs/file.c index ad3ea14..ae28922 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -166,7 +166,7 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } static int bfs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 5e376bb..8defc6b 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -40,7 +40,7 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) int block, off; inode = iget_locked(sb, ino); - if (IS_ERR(inode)) + if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 8fb42916..6025084 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -716,13 +716,14 @@ int bioset_integrity_create(struct bio_set *bs, int pool_size) return 0; bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab); - - bs->bvec_integrity_pool = biovec_create_pool(bs, pool_size); - if (!bs->bvec_integrity_pool) + if (!bs->bio_integrity_pool) return -1; - if (!bs->bio_integrity_pool) + bs->bvec_integrity_pool = biovec_create_pool(bs, pool_size); + if (!bs->bvec_integrity_pool) { + mempool_destroy(bs->bio_integrity_pool); return -1; + } return 0; } @@ -1045,12 +1045,22 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs, int bio_uncopy_user(struct bio *bio) { struct bio_map_data *bmd = bio->bi_private; - int ret = 0; + struct bio_vec *bvec; + int ret = 0, i; - if (!bio_flagged(bio, BIO_NULL_MAPPED)) - ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, - bmd->nr_sgvecs, bio_data_dir(bio) == READ, - 0, bmd->is_our_pages); + if (!bio_flagged(bio, BIO_NULL_MAPPED)) { + /* + * if we're in a workqueue, the request is orphaned, so + * don't copy into a random user address space, just free. + */ + if (current->mm) + ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, + bmd->nr_sgvecs, bio_data_dir(bio) == READ, + 0, bmd->is_our_pages); + else if (bmd->is_our_pages) + bio_for_each_segment_all(bvec, bio, i) + __free_page(bvec->bv_page); + } bio_free_map_data(bmd); bio_put(bio); return ret; @@ -1946,7 +1956,7 @@ int bio_associate_current(struct bio *bio) /* associate blkcg if exists */ rcu_read_lock(); - css = task_subsys_state(current, blkio_subsys_id); + css = task_css(current, blkio_subsys_id); if (css && css_tryget(css)) bio->bi_css = css; rcu_read_unlock(); diff --git a/fs/block_dev.c b/fs/block_dev.c index c7bda5c..1173a4e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1519,7 +1519,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, blk_start_plug(&plug); ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); - if (ret > 0 || ret == -EIOCBQUEUED) { + if (ret > 0) { ssize_t err; err = generic_write_sync(file, pos, ret); diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 2b3b832..398cbd5 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -72,3 +72,12 @@ config BTRFS_DEBUG performance, or export extra information via sysfs. If unsure, say N. + +config BTRFS_ASSERT + bool "Btrfs assert support" + depends on BTRFS_FS + help + Enable run-time assertion checking. This will result in panics if + any of the assertions trip. This is meant for btrfs developers only. + + If unsure, say N. diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 3932224..a91a6a3 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -8,7 +8,10 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \ export.o tree-log.o free-space-cache.o zlib.o lzo.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ - reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o + reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ + uuid-tree.o btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o + +btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index eaf1333..0552a59 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -36,16 +36,23 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb, u64 extent_item_pos, struct extent_inode_elem **eie) { - u64 data_offset; - u64 data_len; + u64 offset = 0; struct extent_inode_elem *e; - data_offset = btrfs_file_extent_offset(eb, fi); - data_len = btrfs_file_extent_num_bytes(eb, fi); + if (!btrfs_file_extent_compression(eb, fi) && + !btrfs_file_extent_encryption(eb, fi) && + !btrfs_file_extent_other_encoding(eb, fi)) { + u64 data_offset; + u64 data_len; - if (extent_item_pos < data_offset || - extent_item_pos >= data_offset + data_len) - return 1; + data_offset = btrfs_file_extent_offset(eb, fi); + data_len = btrfs_file_extent_num_bytes(eb, fi); + + if (extent_item_pos < data_offset || + extent_item_pos >= data_offset + data_len) + return 1; + offset = extent_item_pos - data_offset; + } e = kmalloc(sizeof(*e), GFP_NOFS); if (!e) @@ -53,7 +60,7 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb, e->next = *eie; e->inum = key->objectid; - e->offset = key->offset + (extent_item_pos - data_offset); + e->offset = key->offset + offset; *eie = e; return 0; @@ -112,6 +119,26 @@ struct __prelim_ref { u64 wanted_disk_byte; }; +static struct kmem_cache *btrfs_prelim_ref_cache; + +int __init btrfs_prelim_ref_init(void) +{ + btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref", + sizeof(struct __prelim_ref), + 0, + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, + NULL); + if (!btrfs_prelim_ref_cache) + return -ENOMEM; + return 0; +} + +void btrfs_prelim_ref_exit(void) +{ + if (btrfs_prelim_ref_cache) + kmem_cache_destroy(btrfs_prelim_ref_cache); +} + /* * the rules for all callers of this function are: * - obtaining the parent is the goal @@ -153,12 +180,12 @@ struct __prelim_ref { static int __add_prelim_ref(struct list_head *head, u64 root_id, struct btrfs_key *key, int level, - u64 parent, u64 wanted_disk_byte, int count) + u64 parent, u64 wanted_disk_byte, int count, + gfp_t gfp_mask) { struct __prelim_ref *ref; - /* in case we're adding delayed refs, we're holding the refs spinlock */ - ref = kmalloc(sizeof(*ref), GFP_ATOMIC); + ref = kmem_cache_alloc(btrfs_prelim_ref_cache, gfp_mask); if (!ref) return -ENOMEM; @@ -189,7 +216,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb; struct btrfs_key key; struct btrfs_file_extent_item *fi; - struct extent_inode_elem *eie = NULL; + struct extent_inode_elem *eie = NULL, *old = NULL; u64 disk_byte; if (level != 0) { @@ -223,6 +250,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, if (disk_byte == wanted_disk_byte) { eie = NULL; + old = NULL; if (extent_item_pos) { ret = check_extent_in_eb(&key, eb, fi, *extent_item_pos, @@ -230,18 +258,20 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, if (ret < 0) break; } - if (!ret) { - ret = ulist_add(parents, eb->start, - (uintptr_t)eie, GFP_NOFS); - if (ret < 0) - break; - if (!extent_item_pos) { - ret = btrfs_next_old_leaf(root, path, - time_seq); - continue; - } + if (ret > 0) + goto next; + ret = ulist_add_merge(parents, eb->start, + (uintptr_t)eie, + (u64 *)&old, GFP_NOFS); + if (ret < 0) + break; + if (!ret && extent_item_pos) { + while (old->next) + old = old->next; + old->next = eie; } } +next: ret = btrfs_next_old_item(root, path, time_seq); } @@ -285,10 +315,9 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq); pr_debug("search slot in root %llu (level %d, ref count %d) returned " "%d for key (%llu %u %llu)\n", - (unsigned long long)ref->root_id, level, ref->count, ret, - (unsigned long long)ref->key_for_search.objectid, - ref->key_for_search.type, - (unsigned long long)ref->key_for_search.offset); + ref->root_id, level, ref->count, ret, + ref->key_for_search.objectid, ref->key_for_search.type, + ref->key_for_search.offset); if (ret < 0) goto out; @@ -355,11 +384,12 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, node = ulist_next(parents, &uiter); ref->parent = node ? node->val : 0; ref->inode_list = node ? - (struct extent_inode_elem *)(uintptr_t)node->aux : 0; + (struct extent_inode_elem *)(uintptr_t)node->aux : NULL; /* additional parents require new refs being added here */ while ((node = ulist_next(parents, &uiter))) { - new_ref = kmalloc(sizeof(*new_ref), GFP_NOFS); + new_ref = kmem_cache_alloc(btrfs_prelim_ref_cache, + GFP_NOFS); if (!new_ref) { ret = -ENOMEM; goto out; @@ -483,7 +513,7 @@ static void __merge_refs(struct list_head *head, int mode) ref1->count += ref2->count; list_del(&ref2->list); - kfree(ref2); + kmem_cache_free(btrfs_prelim_ref_cache, ref2); } } @@ -538,7 +568,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, ref = btrfs_delayed_node_to_tree_ref(node); ret = __add_prelim_ref(prefs, ref->root, &op_key, ref->level + 1, 0, node->bytenr, - node->ref_mod * sgn); + node->ref_mod * sgn, GFP_ATOMIC); break; } case BTRFS_SHARED_BLOCK_REF_KEY: { @@ -548,7 +578,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, ret = __add_prelim_ref(prefs, ref->root, NULL, ref->level + 1, ref->parent, node->bytenr, - node->ref_mod * sgn); + node->ref_mod * sgn, GFP_ATOMIC); break; } case BTRFS_EXTENT_DATA_REF_KEY: { @@ -560,7 +590,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, key.offset = ref->offset; ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0, node->bytenr, - node->ref_mod * sgn); + node->ref_mod * sgn, GFP_ATOMIC); break; } case BTRFS_SHARED_DATA_REF_KEY: { @@ -573,7 +603,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, key.offset = ref->offset; ret = __add_prelim_ref(prefs, ref->root, &key, 0, ref->parent, node->bytenr, - node->ref_mod * sgn); + node->ref_mod * sgn, GFP_ATOMIC); break; } default: @@ -647,7 +677,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, case BTRFS_SHARED_BLOCK_REF_KEY: ret = __add_prelim_ref(prefs, 0, NULL, *info_level + 1, offset, - bytenr, 1); + bytenr, 1, GFP_NOFS); break; case BTRFS_SHARED_DATA_REF_KEY: { struct btrfs_shared_data_ref *sdref; @@ -656,13 +686,13 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, sdref = (struct btrfs_shared_data_ref *)(iref + 1); count = btrfs_shared_data_ref_count(leaf, sdref); ret = __add_prelim_ref(prefs, 0, NULL, 0, offset, - bytenr, count); + bytenr, count, GFP_NOFS); break; } case BTRFS_TREE_BLOCK_REF_KEY: ret = __add_prelim_ref(prefs, offset, NULL, *info_level + 1, 0, - bytenr, 1); + bytenr, 1, GFP_NOFS); break; case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_extent_data_ref *dref; @@ -677,7 +707,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, key.offset = btrfs_extent_data_ref_offset(leaf, dref); root = btrfs_extent_data_ref_root(leaf, dref); ret = __add_prelim_ref(prefs, root, &key, 0, 0, - bytenr, count); + bytenr, count, GFP_NOFS); break; } default: @@ -728,7 +758,7 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, case BTRFS_SHARED_BLOCK_REF_KEY: ret = __add_prelim_ref(prefs, 0, NULL, info_level + 1, key.offset, - bytenr, 1); + bytenr, 1, GFP_NOFS); break; case BTRFS_SHARED_DATA_REF_KEY: { struct btrfs_shared_data_ref *sdref; @@ -738,13 +768,13 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, struct btrfs_shared_data_ref); count = btrfs_shared_data_ref_count(leaf, sdref); ret = __add_prelim_ref(prefs, 0, NULL, 0, key.offset, - bytenr, count); + bytenr, count, GFP_NOFS); break; } case BTRFS_TREE_BLOCK_REF_KEY: ret = __add_prelim_ref(prefs, key.offset, NULL, info_level + 1, 0, - bytenr, 1); + bytenr, 1, GFP_NOFS); break; case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_extent_data_ref *dref; @@ -760,7 +790,7 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, key.offset = btrfs_extent_data_ref_offset(leaf, dref); root = btrfs_extent_data_ref_root(leaf, dref); ret = __add_prelim_ref(prefs, root, &key, 0, 0, - bytenr, count); + bytenr, count, GFP_NOFS); break; } default: @@ -901,7 +931,6 @@ again: while (!list_empty(&prefs)) { ref = list_first_entry(&prefs, struct __prelim_ref, list); - list_del(&ref->list); WARN_ON(ref->count < 0); if (ref->count && ref->root_id && ref->parent == 0) { /* no parent == root of tree */ @@ -925,8 +954,10 @@ again: } ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie); - ref->inode_list = eie; free_extent_buffer(eb); + if (ret < 0) + goto out; + ref->inode_list = eie; } ret = ulist_add_merge(refs, ref->parent, (uintptr_t)ref->inode_list, @@ -944,7 +975,8 @@ again: eie->next = ref->inode_list; } } - kfree(ref); + list_del(&ref->list); + kmem_cache_free(btrfs_prelim_ref_cache, ref); } out: @@ -952,13 +984,13 @@ out: while (!list_empty(&prefs)) { ref = list_first_entry(&prefs, struct __prelim_ref, list); list_del(&ref->list); - kfree(ref); + kmem_cache_free(btrfs_prelim_ref_cache, ref); } while (!list_empty(&prefs_delayed)) { ref = list_first_entry(&prefs_delayed, struct __prelim_ref, list); list_del(&ref->list); - kfree(ref); + kmem_cache_free(btrfs_prelim_ref_cache, ref); } return ret; @@ -1316,8 +1348,7 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, found_key->type != BTRFS_METADATA_ITEM_KEY) || found_key->objectid > logical || found_key->objectid + size <= logical) { - pr_debug("logical %llu is not within any extent\n", - (unsigned long long)logical); + pr_debug("logical %llu is not within any extent\n", logical); return -ENOENT; } @@ -1330,11 +1361,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, pr_debug("logical %llu is at position %llu within the extent (%llu " "EXTENT_ITEM %llu) flags %#llx size %u\n", - (unsigned long long)logical, - (unsigned long long)(logical - found_key->objectid), - (unsigned long long)found_key->objectid, - (unsigned long long)found_key->offset, - (unsigned long long)flags, item_size); + logical, logical - found_key->objectid, found_key->objectid, + found_key->offset, flags, item_size); WARN_ON(!flags_ret); if (flags_ret) { @@ -1506,7 +1534,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, while (!ret && (root_node = ulist_next(roots, &root_uiter))) { pr_debug("root %llu references leaf %llu, data list " "%#llx\n", root_node->val, ref_node->val, - (long long)ref_node->aux); + ref_node->aux); ret = iterate_leaf_refs((struct extent_inode_elem *) (uintptr_t)ref_node->aux, root_node->val, @@ -1598,9 +1626,8 @@ static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root, name_len = btrfs_inode_ref_name_len(eb, iref); /* path must be released before calling iterate()! */ pr_debug("following ref at offset %u for inode %llu in " - "tree %llu\n", cur, - (unsigned long long)found_key.objectid, - (unsigned long long)fs_root->objectid); + "tree %llu\n", cur, found_key.objectid, + fs_root->objectid); ret = iterate(parent, name_len, (unsigned long)(iref + 1), eb, ctx); if (ret) diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 8f2e767..a910b27 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -72,4 +72,6 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid, struct btrfs_inode_extref **ret_extref, u64 *found_off); +int __init btrfs_prelim_ref_init(void); +void btrfs_prelim_ref_exit(void); #endif diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 08b286b..d0ae226 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -218,6 +218,27 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) return 0; } +struct btrfs_dio_private { + struct inode *inode; + u64 logical_offset; + u64 disk_bytenr; + u64 bytes; + void *private; + + /* number of bios pending for this dio */ + atomic_t pending_bios; + + /* IO errors */ + int errors; + + /* orig_bio is our btrfs_io_bio */ + struct bio *orig_bio; + + /* dio_bio came from fs/direct-io.c */ + struct bio *dio_bio; + u8 csum[0]; +}; + /* * Disable DIO read nolock optimization, so new dio readers will be forced * to grab i_mutex. It is used to avoid the endless truncate due to diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 1431a69..1c47be1 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -701,15 +701,13 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, next_bytenr = btrfs_super_root(selected_super); if (state->print_mask & BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION) - printk(KERN_INFO "root@%llu\n", - (unsigned long long)next_bytenr); + printk(KERN_INFO "root@%llu\n", next_bytenr); break; case 1: next_bytenr = btrfs_super_chunk_root(selected_super); if (state->print_mask & BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION) - printk(KERN_INFO "chunk@%llu\n", - (unsigned long long)next_bytenr); + printk(KERN_INFO "chunk@%llu\n", next_bytenr); break; case 2: next_bytenr = btrfs_super_log_root(selected_super); @@ -717,8 +715,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, continue; if (state->print_mask & BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION) - printk(KERN_INFO "log@%llu\n", - (unsigned long long)next_bytenr); + printk(KERN_INFO "log@%llu\n", next_bytenr); break; } @@ -727,7 +724,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, next_bytenr, state->metablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", - (unsigned long long)next_bytenr, num_copies); + next_bytenr, num_copies); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { struct btrfsic_block *next_block; @@ -742,8 +739,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, printk(KERN_INFO "btrfsic:" " btrfsic_map_block(root @%llu," " mirror %d) failed!\n", - (unsigned long long)next_bytenr, - mirror_num); + next_bytenr, mirror_num); kfree(selected_super); return -1; } @@ -767,7 +763,6 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, if (ret < (int)PAGE_CACHE_SIZE) { printk(KERN_INFO "btrfsic: read @logical %llu failed!\n", - (unsigned long long) tmp_next_block_ctx.start); btrfsic_release_block_ctx(&tmp_next_block_ctx); kfree(selected_super); @@ -813,7 +808,7 @@ static int btrfsic_process_superblock_dev_mirror( (bh->b_data + (dev_bytenr & 4095)); if (btrfs_super_bytenr(super_tmp) != dev_bytenr || - super_tmp->magic != cpu_to_le64(BTRFS_MAGIC) || + btrfs_super_magic(super_tmp) != BTRFS_MAGIC || memcmp(device->uuid, super_tmp->dev_item.uuid, BTRFS_UUID_SIZE) || btrfs_super_nodesize(super_tmp) != state->metablock_size || btrfs_super_leafsize(super_tmp) != state->metablock_size || @@ -847,10 +842,8 @@ static int btrfsic_process_superblock_dev_mirror( printk_in_rcu(KERN_INFO "New initial S-block (bdev %p, %s)" " @%llu (%s/%llu/%d)\n", superblock_bdev, - rcu_str_deref(device->name), - (unsigned long long)dev_bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, + rcu_str_deref(device->name), dev_bytenr, + dev_state->name, dev_bytenr, superblock_mirror_num); list_add(&superblock_tmp->all_blocks_node, &state->all_blocks_list); @@ -880,20 +873,20 @@ static int btrfsic_process_superblock_dev_mirror( tmp_disk_key.offset = 0; switch (pass) { case 0: - tmp_disk_key.objectid = - cpu_to_le64(BTRFS_ROOT_TREE_OBJECTID); + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_ROOT_TREE_OBJECTID); additional_string = "initial root "; next_bytenr = btrfs_super_root(super_tmp); break; case 1: - tmp_disk_key.objectid = - cpu_to_le64(BTRFS_CHUNK_TREE_OBJECTID); + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_CHUNK_TREE_OBJECTID); additional_string = "initial chunk "; next_bytenr = btrfs_super_chunk_root(super_tmp); break; case 2: - tmp_disk_key.objectid = - cpu_to_le64(BTRFS_TREE_LOG_OBJECTID); + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_TREE_LOG_OBJECTID); additional_string = "initial log "; next_bytenr = btrfs_super_log_root(super_tmp); if (0 == next_bytenr) @@ -906,7 +899,7 @@ static int btrfsic_process_superblock_dev_mirror( next_bytenr, state->metablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", - (unsigned long long)next_bytenr, num_copies); + next_bytenr, num_copies); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { struct btrfsic_block *next_block; struct btrfsic_block_data_ctx tmp_next_block_ctx; @@ -918,8 +911,7 @@ static int btrfsic_process_superblock_dev_mirror( mirror_num)) { printk(KERN_INFO "btrfsic: btrfsic_map_block(" "bytenr @%llu, mirror %d) failed!\n", - (unsigned long long)next_bytenr, - mirror_num); + next_bytenr, mirror_num); brelse(bh); return -1; } @@ -1003,19 +995,17 @@ continue_with_new_stack_frame: (struct btrfs_leaf *)sf->hdr; if (-1 == sf->i) { - sf->nr = le32_to_cpu(leafhdr->header.nritems); + sf->nr = btrfs_stack_header_nritems(&leafhdr->header); if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "leaf %llu items %d generation %llu" " owner %llu\n", - (unsigned long long) - sf->block_ctx->start, - sf->nr, - (unsigned long long) - le64_to_cpu(leafhdr->header.generation), - (unsigned long long) - le64_to_cpu(leafhdr->header.owner)); + sf->block_ctx->start, sf->nr, + btrfs_stack_header_generation( + &leafhdr->header), + btrfs_stack_header_owner( + &leafhdr->header)); } continue_with_current_leaf_stack_frame: @@ -1047,10 +1037,10 @@ leaf_item_out_of_bounce_error: &disk_item, disk_item_offset, sizeof(struct btrfs_item)); - item_offset = le32_to_cpu(disk_item.offset); - item_size = le32_to_cpu(disk_item.size); + item_offset = btrfs_stack_item_offset(&disk_item); + item_size = btrfs_stack_item_offset(&disk_item); disk_key = &disk_item.key; - type = disk_key->type; + type = btrfs_disk_key_type(disk_key); if (BTRFS_ROOT_ITEM_KEY == type) { struct btrfs_root_item root_item; @@ -1066,7 +1056,7 @@ leaf_item_out_of_bounce_error: sf->block_ctx, &root_item, root_item_offset, item_size); - next_bytenr = le64_to_cpu(root_item.bytenr); + next_bytenr = btrfs_root_bytenr(&root_item); sf->error = btrfsic_create_link_to_next_block( @@ -1081,8 +1071,8 @@ leaf_item_out_of_bounce_error: &sf->num_copies, &sf->mirror_num, disk_key, - le64_to_cpu(root_item. - generation)); + btrfs_root_generation( + &root_item)); if (sf->error) goto one_stack_frame_backwards; @@ -1130,18 +1120,17 @@ leaf_item_out_of_bounce_error: struct btrfs_node *const nodehdr = (struct btrfs_node *)sf->hdr; if (-1 == sf->i) { - sf->nr = le32_to_cpu(nodehdr->header.nritems); + sf->nr = btrfs_stack_header_nritems(&nodehdr->header); if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "node %llu level %d items %d" " generation %llu owner %llu\n", - (unsigned long long) sf->block_ctx->start, nodehdr->header.level, sf->nr, - (unsigned long long) - le64_to_cpu(nodehdr->header.generation), - (unsigned long long) - le64_to_cpu(nodehdr->header.owner)); + btrfs_stack_header_generation( + &nodehdr->header), + btrfs_stack_header_owner( + &nodehdr->header)); } continue_with_current_node_stack_frame: @@ -1168,7 +1157,7 @@ continue_with_current_node_stack_frame: btrfsic_read_from_block_data( sf->block_ctx, &key_ptr, key_ptr_offset, sizeof(struct btrfs_key_ptr)); - next_bytenr = le64_to_cpu(key_ptr.blockptr); + next_bytenr = btrfs_stack_key_blockptr(&key_ptr); sf->error = btrfsic_create_link_to_next_block( state, @@ -1182,7 +1171,7 @@ continue_with_current_node_stack_frame: &sf->num_copies, &sf->mirror_num, &key_ptr.key, - le64_to_cpu(key_ptr.generation)); + btrfs_stack_key_generation(&key_ptr)); if (sf->error) goto one_stack_frame_backwards; @@ -1247,8 +1236,7 @@ static void btrfsic_read_from_block_data( unsigned long i = (start_offset + offset) >> PAGE_CACHE_SHIFT; WARN_ON(offset + len > block_ctx->len); - offset_in_page = (start_offset + offset) & - ((unsigned long)PAGE_CACHE_SIZE - 1); + offset_in_page = (start_offset + offset) & (PAGE_CACHE_SIZE - 1); while (len > 0) { cur = min(len, ((size_t)PAGE_CACHE_SIZE - offset_in_page)); @@ -1290,7 +1278,7 @@ static int btrfsic_create_link_to_next_block( next_bytenr, state->metablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", - (unsigned long long)next_bytenr, *num_copiesp); + next_bytenr, *num_copiesp); *mirror_nump = 1; } @@ -1307,7 +1295,7 @@ static int btrfsic_create_link_to_next_block( if (ret) { printk(KERN_INFO "btrfsic: btrfsic_map_block(@%llu, mirror=%d) failed!\n", - (unsigned long long)next_bytenr, *mirror_nump); + next_bytenr, *mirror_nump); btrfsic_release_block_ctx(next_block_ctx); *next_blockp = NULL; return -1; @@ -1335,20 +1323,16 @@ static int btrfsic_create_link_to_next_block( "Referenced block @%llu (%s/%llu/%d)" " found in hash table, %c," " bytenr mismatch (!= stored %llu).\n", - (unsigned long long)next_bytenr, - next_block_ctx->dev->name, - (unsigned long long)next_block_ctx->dev_bytenr, - *mirror_nump, + next_bytenr, next_block_ctx->dev->name, + next_block_ctx->dev_bytenr, *mirror_nump, btrfsic_get_block_type(state, next_block), - (unsigned long long)next_block->logical_bytenr); + next_block->logical_bytenr); } else if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "Referenced block @%llu (%s/%llu/%d)" " found in hash table, %c.\n", - (unsigned long long)next_bytenr, - next_block_ctx->dev->name, - (unsigned long long)next_block_ctx->dev_bytenr, - *mirror_nump, + next_bytenr, next_block_ctx->dev->name, + next_block_ctx->dev_bytenr, *mirror_nump, btrfsic_get_block_type(state, next_block)); next_block->logical_bytenr = next_bytenr; @@ -1400,7 +1384,7 @@ static int btrfsic_create_link_to_next_block( if (ret < (int)next_block_ctx->len) { printk(KERN_INFO "btrfsic: read block @logical %llu failed!\n", - (unsigned long long)next_bytenr); + next_bytenr); btrfsic_release_block_ctx(next_block_ctx); *next_blockp = NULL; return -1; @@ -1444,12 +1428,12 @@ static int btrfsic_handle_extent_data( file_extent_item_offset, offsetof(struct btrfs_file_extent_item, disk_num_bytes)); if (BTRFS_FILE_EXTENT_REG != file_extent_item.type || - ((u64)0) == le64_to_cpu(file_extent_item.disk_bytenr)) { + btrfs_stack_file_extent_disk_bytenr(&file_extent_item) == 0) { if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE) printk(KERN_INFO "extent_data: type %u, disk_bytenr = %llu\n", file_extent_item.type, - (unsigned long long) - le64_to_cpu(file_extent_item.disk_bytenr)); + btrfs_stack_file_extent_disk_bytenr( + &file_extent_item)); return 0; } @@ -1463,20 +1447,19 @@ static int btrfsic_handle_extent_data( btrfsic_read_from_block_data(block_ctx, &file_extent_item, file_extent_item_offset, sizeof(struct btrfs_file_extent_item)); - next_bytenr = le64_to_cpu(file_extent_item.disk_bytenr) + - le64_to_cpu(file_extent_item.offset); - generation = le64_to_cpu(file_extent_item.generation); - num_bytes = le64_to_cpu(file_extent_item.num_bytes); - generation = le64_to_cpu(file_extent_item.generation); + next_bytenr = btrfs_stack_file_extent_disk_bytenr(&file_extent_item) + + btrfs_stack_file_extent_offset(&file_extent_item); + generation = btrfs_stack_file_extent_generation(&file_extent_item); + num_bytes = btrfs_stack_file_extent_num_bytes(&file_extent_item); + generation = btrfs_stack_file_extent_generation(&file_extent_item); if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE) printk(KERN_INFO "extent_data: type %u, disk_bytenr = %llu," " offset = %llu, num_bytes = %llu\n", file_extent_item.type, - (unsigned long long) - le64_to_cpu(file_extent_item.disk_bytenr), - (unsigned long long)le64_to_cpu(file_extent_item.offset), - (unsigned long long)num_bytes); + btrfs_stack_file_extent_disk_bytenr(&file_extent_item), + btrfs_stack_file_extent_offset(&file_extent_item), + num_bytes); while (num_bytes > 0) { u32 chunk_len; int num_copies; @@ -1492,7 +1475,7 @@ static int btrfsic_handle_extent_data( next_bytenr, state->datablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", - (unsigned long long)next_bytenr, num_copies); + next_bytenr, num_copies); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { struct btrfsic_block_data_ctx next_block_ctx; struct btrfsic_block *next_block; @@ -1504,8 +1487,7 @@ static int btrfsic_handle_extent_data( if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE) printk(KERN_INFO "\tdisk_bytenr = %llu, num_bytes %u\n", - (unsigned long long)next_bytenr, - chunk_len); + next_bytenr, chunk_len); ret = btrfsic_map_block(state, next_bytenr, chunk_len, &next_block_ctx, mirror_num); @@ -1513,8 +1495,7 @@ static int btrfsic_handle_extent_data( printk(KERN_INFO "btrfsic: btrfsic_map_block(@%llu," " mirror=%d) failed!\n", - (unsigned long long)next_bytenr, - mirror_num); + next_bytenr, mirror_num); return -1; } @@ -1543,12 +1524,10 @@ static int btrfsic_handle_extent_data( " found in hash table, D," " bytenr mismatch" " (!= stored %llu).\n", - (unsigned long long)next_bytenr, + next_bytenr, next_block_ctx.dev->name, - (unsigned long long) next_block_ctx.dev_bytenr, mirror_num, - (unsigned long long) next_block->logical_bytenr); } next_block->logical_bytenr = next_bytenr; @@ -1675,7 +1654,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, if (block_ctx->dev_bytenr & ((u64)PAGE_CACHE_SIZE - 1)) { printk(KERN_INFO "btrfsic: read_block() with unaligned bytenr %llu\n", - (unsigned long long)block_ctx->dev_bytenr); + block_ctx->dev_bytenr); return -1; } @@ -1772,10 +1751,8 @@ static void btrfsic_dump_database(struct btrfsic_state *state) printk(KERN_INFO "%c-block @%llu (%s/%llu/%d)\n", btrfsic_get_block_type(state, b_all), - (unsigned long long)b_all->logical_bytenr, - b_all->dev_state->name, - (unsigned long long)b_all->dev_bytenr, - b_all->mirror_num); + b_all->logical_bytenr, b_all->dev_state->name, + b_all->dev_bytenr, b_all->mirror_num); list_for_each(elem_ref_to, &b_all->ref_to_list) { const struct btrfsic_block_link *const l = @@ -1787,16 +1764,13 @@ static void btrfsic_dump_database(struct btrfsic_state *state) " refers %u* to" " %c @%llu (%s/%llu/%d)\n", btrfsic_get_block_type(state, b_all), - (unsigned long long)b_all->logical_bytenr, - b_all->dev_state->name, - (unsigned long long)b_all->dev_bytenr, - b_all->mirror_num, + b_all->logical_bytenr, b_all->dev_state->name, + b_all->dev_bytenr, b_all->mirror_num, l->ref_cnt, btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); } @@ -1810,16 +1784,12 @@ static void btrfsic_dump_database(struct btrfsic_state *state) " is ref %u* from" " %c @%llu (%s/%llu/%d)\n", btrfsic_get_block_type(state, b_all), - (unsigned long long)b_all->logical_bytenr, - b_all->dev_state->name, - (unsigned long long)b_all->dev_bytenr, - b_all->mirror_num, + b_all->logical_bytenr, b_all->dev_state->name, + b_all->dev_bytenr, b_all->mirror_num, l->ref_cnt, btrfsic_get_block_type(state, l->block_ref_from), - (unsigned long long) l->block_ref_from->logical_bytenr, l->block_ref_from->dev_state->name, - (unsigned long long) l->block_ref_from->dev_bytenr, l->block_ref_from->mirror_num); } @@ -1896,8 +1866,8 @@ again: struct list_head *tmp_ref_to; if (block->is_superblock) { - bytenr = le64_to_cpu(((struct btrfs_super_block *) - mapped_datav[0])->bytenr); + bytenr = btrfs_super_bytenr((struct btrfs_super_block *) + mapped_datav[0]); if (num_pages * PAGE_CACHE_SIZE < BTRFS_SUPER_INFO_SIZE) { printk(KERN_INFO @@ -1923,8 +1893,9 @@ again: return; } processed_len = state->metablock_size; - bytenr = le64_to_cpu(((struct btrfs_header *) - mapped_datav[0])->bytenr); + bytenr = btrfs_stack_header_bytenr( + (struct btrfs_header *) + mapped_datav[0]); btrfsic_cmp_log_and_dev_bytenr(state, bytenr, dev_state, dev_bytenr); @@ -1935,12 +1906,9 @@ again: " found in hash table, %c," " bytenr mismatch" " (!= stored %llu).\n", - (unsigned long long)bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, + bytenr, dev_state->name, dev_bytenr, block->mirror_num, btrfsic_get_block_type(state, block), - (unsigned long long) block->logical_bytenr); block->logical_bytenr = bytenr; } else if (state->print_mask & @@ -1948,9 +1916,7 @@ again: printk(KERN_INFO "Written block @%llu (%s/%llu/%d)" " found in hash table, %c.\n", - (unsigned long long)bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, + bytenr, dev_state->name, dev_bytenr, block->mirror_num, btrfsic_get_block_type(state, block)); } else { @@ -1966,9 +1932,7 @@ again: printk(KERN_INFO "Written block @%llu (%s/%llu/%d)" " found in hash table, %c.\n", - (unsigned long long)bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, + bytenr, dev_state->name, dev_bytenr, block->mirror_num, btrfsic_get_block_type(state, block)); } @@ -1985,21 +1949,14 @@ again: " new(gen=%llu)," " which is referenced by most recent superblock" " (superblockgen=%llu)!\n", - btrfsic_get_block_type(state, block), - (unsigned long long)bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, - block->mirror_num, - (unsigned long long)block->generation, - (unsigned long long) - le64_to_cpu(block->disk_key.objectid), + btrfsic_get_block_type(state, block), bytenr, + dev_state->name, dev_bytenr, block->mirror_num, + block->generation, + btrfs_disk_key_objectid(&block->disk_key), block->disk_key.type, - (unsigned long long) - le64_to_cpu(block->disk_key.offset), - (unsigned long long) - le64_to_cpu(((struct btrfs_header *) - mapped_datav[0])->generation), - (unsigned long long) + btrfs_disk_key_offset(&block->disk_key), + btrfs_stack_header_generation( + (struct btrfs_header *) mapped_datav[0]), state->max_superblock_generation); btrfsic_dump_tree(state); } @@ -2008,15 +1965,12 @@ again: printk(KERN_INFO "btrfs: attempt to overwrite %c-block" " @%llu (%s/%llu/%d), oldgen=%llu, newgen=%llu," " which is not yet iodone!\n", - btrfsic_get_block_type(state, block), - (unsigned long long)bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, - block->mirror_num, - (unsigned long long)block->generation, - (unsigned long long) - le64_to_cpu(((struct btrfs_header *) - mapped_datav[0])->generation)); + btrfsic_get_block_type(state, block), bytenr, + dev_state->name, dev_bytenr, block->mirror_num, + block->generation, + btrfs_stack_header_generation( + (struct btrfs_header *) + mapped_datav[0])); /* it would not be safe to go on */ btrfsic_dump_tree(state); goto continue_loop; @@ -2056,7 +2010,7 @@ again: if (ret) { printk(KERN_INFO "btrfsic: btrfsic_map_block(root @%llu)" - " failed!\n", (unsigned long long)bytenr); + " failed!\n", bytenr); goto continue_loop; } block_ctx.datav = mapped_datav; @@ -2140,7 +2094,7 @@ again: printk(KERN_INFO "btrfsic: btrfsic_process_metablock" "(root @%llu) failed!\n", - (unsigned long long)dev_bytenr); + dev_bytenr); } else { block->is_metadata = 0; block->mirror_num = 0; /* unknown */ @@ -2168,8 +2122,7 @@ again: if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "Written block (%s/%llu/?)" " !found in hash table, D.\n", - dev_state->name, - (unsigned long long)dev_bytenr); + dev_state->name, dev_bytenr); if (!state->include_extent_data) { /* ignore that written D block */ goto continue_loop; @@ -2184,17 +2137,16 @@ again: block_ctx.pagev = NULL; } else { processed_len = state->metablock_size; - bytenr = le64_to_cpu(((struct btrfs_header *) - mapped_datav[0])->bytenr); + bytenr = btrfs_stack_header_bytenr( + (struct btrfs_header *) + mapped_datav[0]); btrfsic_cmp_log_and_dev_bytenr(state, bytenr, dev_state, dev_bytenr); if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "Written block @%llu (%s/%llu/?)" " !found in hash table, M.\n", - (unsigned long long)bytenr, - dev_state->name, - (unsigned long long)dev_bytenr); + bytenr, dev_state->name, dev_bytenr); ret = btrfsic_map_block(state, bytenr, processed_len, &block_ctx, 0); @@ -2202,7 +2154,7 @@ again: printk(KERN_INFO "btrfsic: btrfsic_map_block(root @%llu)" " failed!\n", - (unsigned long long)dev_bytenr); + dev_bytenr); goto continue_loop; } } @@ -2267,10 +2219,8 @@ again: printk(KERN_INFO "New written %c-block @%llu (%s/%llu/%d)\n", is_metadata ? 'M' : 'D', - (unsigned long long)block->logical_bytenr, - block->dev_state->name, - (unsigned long long)block->dev_bytenr, - block->mirror_num); + block->logical_bytenr, block->dev_state->name, + block->dev_bytenr, block->mirror_num); list_add(&block->all_blocks_node, &state->all_blocks_list); btrfsic_block_hashtable_add(block, &state->block_hashtable); @@ -2281,7 +2231,7 @@ again: printk(KERN_INFO "btrfsic: process_metablock(root @%llu)" " failed!\n", - (unsigned long long)dev_bytenr); + dev_bytenr); } btrfsic_release_block_ctx(&block_ctx); } @@ -2319,10 +2269,8 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) "bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n", bio_error_status, btrfsic_get_block_type(dev_state->state, block), - (unsigned long long)block->logical_bytenr, - dev_state->name, - (unsigned long long)block->dev_bytenr, - block->mirror_num); + block->logical_bytenr, dev_state->name, + block->dev_bytenr, block->mirror_num); next_block = block->next_in_same_bio; block->iodone_w_error = iodone_w_error; if (block->submit_bio_bh_rw & REQ_FLUSH) { @@ -2332,7 +2280,6 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) printk(KERN_INFO "bio_end_io() new %s flush_gen=%llu\n", dev_state->name, - (unsigned long long) dev_state->last_flush_gen); } if (block->submit_bio_bh_rw & REQ_FUA) @@ -2358,10 +2305,8 @@ static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate) "bh_end_io(error=%d) for %c @%llu (%s/%llu/%d)\n", iodone_w_error, btrfsic_get_block_type(dev_state->state, block), - (unsigned long long)block->logical_bytenr, - block->dev_state->name, - (unsigned long long)block->dev_bytenr, - block->mirror_num); + block->logical_bytenr, block->dev_state->name, + block->dev_bytenr, block->mirror_num); block->iodone_w_error = iodone_w_error; if (block->submit_bio_bh_rw & REQ_FLUSH) { @@ -2370,8 +2315,7 @@ static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate) BTRFSIC_PRINT_MASK_END_IO_BIO_BH)) printk(KERN_INFO "bh_end_io() new %s flush_gen=%llu\n", - dev_state->name, - (unsigned long long)dev_state->last_flush_gen); + dev_state->name, dev_state->last_flush_gen); } if (block->submit_bio_bh_rw & REQ_FUA) block->flush_gen = 0; /* FUA completed means block is on disk */ @@ -2396,26 +2340,20 @@ static int btrfsic_process_written_superblock( printk(KERN_INFO "btrfsic: superblock @%llu (%s/%llu/%d)" " with old gen %llu <= %llu\n", - (unsigned long long)superblock->logical_bytenr, + superblock->logical_bytenr, superblock->dev_state->name, - (unsigned long long)superblock->dev_bytenr, - superblock->mirror_num, - (unsigned long long) + superblock->dev_bytenr, superblock->mirror_num, btrfs_super_generation(super_hdr), - (unsigned long long) state->max_superblock_generation); } else { if (state->print_mask & BTRFSIC_PRINT_MASK_SUPERBLOCK_WRITE) printk(KERN_INFO "btrfsic: got new superblock @%llu (%s/%llu/%d)" " with new gen %llu > %llu\n", - (unsigned long long)superblock->logical_bytenr, + superblock->logical_bytenr, superblock->dev_state->name, - (unsigned long long)superblock->dev_bytenr, - superblock->mirror_num, - (unsigned long long) + superblock->dev_bytenr, superblock->mirror_num, btrfs_super_generation(super_hdr), - (unsigned long long) state->max_superblock_generation); state->max_superblock_generation = @@ -2432,43 +2370,41 @@ static int btrfsic_process_written_superblock( int num_copies; int mirror_num; const char *additional_string = NULL; - struct btrfs_disk_key tmp_disk_key; + struct btrfs_disk_key tmp_disk_key = {0}; - tmp_disk_key.type = BTRFS_ROOT_ITEM_KEY; - tmp_disk_key.offset = 0; + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_ROOT_ITEM_KEY); + btrfs_set_disk_key_objectid(&tmp_disk_key, 0); switch (pass) { case 0: - tmp_disk_key.objectid = - cpu_to_le64(BTRFS_ROOT_TREE_OBJECTID); + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_ROOT_TREE_OBJECTID); additional_string = "root "; next_bytenr = btrfs_super_root(super_hdr); if (state->print_mask & BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION) - printk(KERN_INFO "root@%llu\n", - (unsigned long long)next_bytenr); + printk(KERN_INFO "root@%llu\n", next_bytenr); break; case 1: - tmp_disk_key.objectid = - cpu_to_le64(BTRFS_CHUNK_TREE_OBJECTID); + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_CHUNK_TREE_OBJECTID); additional_string = "chunk "; next_bytenr = btrfs_super_chunk_root(super_hdr); if (state->print_mask & BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION) - printk(KERN_INFO "chunk@%llu\n", - (unsigned long long)next_bytenr); + printk(KERN_INFO "chunk@%llu\n", next_bytenr); break; case 2: - tmp_disk_key.objectid = - cpu_to_le64(BTRFS_TREE_LOG_OBJECTID); + btrfs_set_disk_key_objectid(&tmp_disk_key, + BTRFS_TREE_LOG_OBJECTID); additional_string = "log "; next_bytenr = btrfs_super_log_root(super_hdr); if (0 == next_bytenr) continue; if (state->print_mask & BTRFSIC_PRINT_MASK_ROOT_CHUNK_LOG_TREE_LOCATION) - printk(KERN_INFO "log@%llu\n", - (unsigned long long)next_bytenr); + printk(KERN_INFO "log@%llu\n", next_bytenr); break; } @@ -2477,7 +2413,7 @@ static int btrfsic_process_written_superblock( next_bytenr, BTRFS_SUPER_INFO_SIZE); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", - (unsigned long long)next_bytenr, num_copies); + next_bytenr, num_copies); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { int was_created; @@ -2493,8 +2429,7 @@ static int btrfsic_process_written_superblock( printk(KERN_INFO "btrfsic: btrfsic_map_block(@%llu," " mirror=%d) failed!\n", - (unsigned long long)next_bytenr, - mirror_num); + next_bytenr, mirror_num); return -1; } @@ -2579,26 +2514,22 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state, " %u* refers to %c @%llu (%s/%llu/%d)\n", recursion_level, btrfsic_get_block_type(state, block), - (unsigned long long)block->logical_bytenr, - block->dev_state->name, - (unsigned long long)block->dev_bytenr, - block->mirror_num, + block->logical_bytenr, block->dev_state->name, + block->dev_bytenr, block->mirror_num, l->ref_cnt, btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); if (l->block_ref_to->never_written) { printk(KERN_INFO "btrfs: attempt to write superblock" " which references block %c @%llu (%s/%llu/%d)" " which is never written!\n", btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); ret = -1; } else if (!l->block_ref_to->is_iodone) { @@ -2606,10 +2537,9 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state, " which references block %c @%llu (%s/%llu/%d)" " which is not yet iodone!\n", btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); ret = -1; } else if (l->block_ref_to->iodone_w_error) { @@ -2617,10 +2547,9 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state, " which references block %c @%llu (%s/%llu/%d)" " which has write error!\n", btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); ret = -1; } else if (l->parent_generation != @@ -2634,13 +2563,12 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state, " with generation %llu !=" " parent generation %llu!\n", btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num, - (unsigned long long)l->block_ref_to->generation, - (unsigned long long)l->parent_generation); + l->block_ref_to->generation, + l->parent_generation); ret = -1; } else if (l->block_ref_to->flush_gen > l->block_ref_to->dev_state->last_flush_gen) { @@ -2650,13 +2578,10 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state, " (block flush_gen=%llu," " dev->flush_gen=%llu)!\n", btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long) l->block_ref_to->logical_bytenr, l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, - l->block_ref_to->mirror_num, - (unsigned long long)block->flush_gen, - (unsigned long long) + l->block_ref_to->dev_bytenr, + l->block_ref_to->mirror_num, block->flush_gen, l->block_ref_to->dev_state->last_flush_gen); ret = -1; } else if (-1 == btrfsic_check_all_ref_blocks(state, @@ -2701,16 +2626,12 @@ static int btrfsic_is_block_ref_by_superblock( " is ref %u* from %c @%llu (%s/%llu/%d)\n", recursion_level, btrfsic_get_block_type(state, block), - (unsigned long long)block->logical_bytenr, - block->dev_state->name, - (unsigned long long)block->dev_bytenr, - block->mirror_num, + block->logical_bytenr, block->dev_state->name, + block->dev_bytenr, block->mirror_num, l->ref_cnt, btrfsic_get_block_type(state, l->block_ref_from), - (unsigned long long) l->block_ref_from->logical_bytenr, l->block_ref_from->dev_state->name, - (unsigned long long) l->block_ref_from->dev_bytenr, l->block_ref_from->mirror_num); if (l->block_ref_from->is_superblock && @@ -2737,14 +2658,12 @@ static void btrfsic_print_add_link(const struct btrfsic_state *state, " to %c @%llu (%s/%llu/%d).\n", l->ref_cnt, btrfsic_get_block_type(state, l->block_ref_from), - (unsigned long long)l->block_ref_from->logical_bytenr, + l->block_ref_from->logical_bytenr, l->block_ref_from->dev_state->name, - (unsigned long long)l->block_ref_from->dev_bytenr, - l->block_ref_from->mirror_num, + l->block_ref_from->dev_bytenr, l->block_ref_from->mirror_num, btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long)l->block_ref_to->logical_bytenr, - l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->logical_bytenr, + l->block_ref_to->dev_state->name, l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); } @@ -2756,14 +2675,12 @@ static void btrfsic_print_rem_link(const struct btrfsic_state *state, " to %c @%llu (%s/%llu/%d).\n", l->ref_cnt, btrfsic_get_block_type(state, l->block_ref_from), - (unsigned long long)l->block_ref_from->logical_bytenr, + l->block_ref_from->logical_bytenr, l->block_ref_from->dev_state->name, - (unsigned long long)l->block_ref_from->dev_bytenr, - l->block_ref_from->mirror_num, + l->block_ref_from->dev_bytenr, l->block_ref_from->mirror_num, btrfsic_get_block_type(state, l->block_ref_to), - (unsigned long long)l->block_ref_to->logical_bytenr, - l->block_ref_to->dev_state->name, - (unsigned long long)l->block_ref_to->dev_bytenr, + l->block_ref_to->logical_bytenr, + l->block_ref_to->dev_state->name, l->block_ref_to->dev_bytenr, l->block_ref_to->mirror_num); } @@ -2807,10 +2724,8 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state, */ indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)", btrfsic_get_block_type(state, block), - (unsigned long long)block->logical_bytenr, - block->dev_state->name, - (unsigned long long)block->dev_bytenr, - block->mirror_num); + block->logical_bytenr, block->dev_state->name, + block->dev_bytenr, block->mirror_num); if (indent_level + indent_add > BTRFSIC_TREE_DUMP_MAX_INDENT_LEVEL) { printk("[...]\n"); return; @@ -2943,10 +2858,8 @@ static struct btrfsic_block *btrfsic_block_lookup_or_add( "New %s%c-block @%llu (%s/%llu/%d)\n", additional_string, btrfsic_get_block_type(state, block), - (unsigned long long)block->logical_bytenr, - dev_state->name, - (unsigned long long)block->dev_bytenr, - mirror_num); + block->logical_bytenr, dev_state->name, + block->dev_bytenr, mirror_num); list_add(&block->all_blocks_node, &state->all_blocks_list); btrfsic_block_hashtable_add(block, &state->block_hashtable); if (NULL != was_created) @@ -2980,7 +2893,7 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, printk(KERN_INFO "btrfsic:" " btrfsic_map_block(logical @%llu," " mirror %d) failed!\n", - (unsigned long long)bytenr, mirror_num); + bytenr, mirror_num); continue; } @@ -2997,8 +2910,7 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, printk(KERN_INFO "btrfs: attempt to write M-block which contains logical bytenr that doesn't map to dev+physical bytenr of submit_bio," " buffer->log_bytenr=%llu, submit_bio(bdev=%s," " phys_bytenr=%llu)!\n", - (unsigned long long)bytenr, dev_state->name, - (unsigned long long)dev_bytenr); + bytenr, dev_state->name, dev_bytenr); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { ret = btrfsic_map_block(state, bytenr, state->metablock_size, @@ -3008,10 +2920,8 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, printk(KERN_INFO "Read logical bytenr @%llu maps to" " (%s/%llu/%d)\n", - (unsigned long long)bytenr, - block_ctx.dev->name, - (unsigned long long)block_ctx.dev_bytenr, - mirror_num); + bytenr, block_ctx.dev->name, + block_ctx.dev_bytenr, mirror_num); } WARN_ON(1); } @@ -3048,12 +2958,10 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh) if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) printk(KERN_INFO - "submit_bh(rw=0x%x, blocknr=%lu (bytenr %llu)," - " size=%lu, data=%p, bdev=%p)\n", - rw, (unsigned long)bh->b_blocknr, - (unsigned long long)dev_bytenr, - (unsigned long)bh->b_size, bh->b_data, - bh->b_bdev); + "submit_bh(rw=0x%x, blocknr=%llu (bytenr %llu)," + " size=%zu, data=%p, bdev=%p)\n", + rw, (unsigned long long)bh->b_blocknr, + dev_bytenr, bh->b_size, bh->b_data, bh->b_bdev); btrfsic_process_written_block(dev_state, dev_bytenr, &bh->b_data, 1, NULL, NULL, bh, rw); @@ -3118,9 +3026,9 @@ void btrfsic_submit_bio(int rw, struct bio *bio) BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) printk(KERN_INFO "submit_bio(rw=0x%x, bi_vcnt=%u," - " bi_sector=%lu (bytenr %llu), bi_bdev=%p)\n", - rw, bio->bi_vcnt, (unsigned long)bio->bi_sector, - (unsigned long long)dev_bytenr, + " bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", + rw, bio->bi_vcnt, + (unsigned long long)bio->bi_sector, dev_bytenr, bio->bi_bdev); mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt, @@ -3213,19 +3121,19 @@ int btrfsic_mount(struct btrfs_root *root, if (root->nodesize & ((u64)PAGE_CACHE_SIZE - 1)) { printk(KERN_INFO "btrfsic: cannot handle nodesize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", - root->nodesize, (unsigned long)PAGE_CACHE_SIZE); + root->nodesize, PAGE_CACHE_SIZE); return -1; } if (root->leafsize & ((u64)PAGE_CACHE_SIZE - 1)) { printk(KERN_INFO "btrfsic: cannot handle leafsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", - root->leafsize, (unsigned long)PAGE_CACHE_SIZE); + root->leafsize, PAGE_CACHE_SIZE); return -1; } if (root->sectorsize & ((u64)PAGE_CACHE_SIZE - 1)) { printk(KERN_INFO "btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", - root->sectorsize, (unsigned long)PAGE_CACHE_SIZE); + root->sectorsize, PAGE_CACHE_SIZE); return -1; } state = kzalloc(sizeof(*state), GFP_NOFS); @@ -3369,10 +3277,8 @@ void btrfsic_unmount(struct btrfs_root *root, " @%llu (%s/%llu/%d) on umount which is" " not yet iodone!\n", btrfsic_get_block_type(state, b_all), - (unsigned long long)b_all->logical_bytenr, - b_all->dev_state->name, - (unsigned long long)b_all->dev_bytenr, - b_all->mirror_num); + b_all->logical_bytenr, b_all->dev_state->name, + b_all->dev_bytenr, b_all->mirror_num); } mutex_unlock(&btrfsic_mutex); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b189bd1..6aad98c 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -132,9 +132,8 @@ static int check_compressed_csum(struct inode *inode, printk(KERN_INFO "btrfs csum failed ino %llu " "extent %llu csum %u " "wanted %u mirror %d\n", - (unsigned long long)btrfs_ino(inode), - (unsigned long long)disk_start, - csum, *cb_sum, cb->mirror_num); + btrfs_ino(inode), disk_start, csum, *cb_sum, + cb->mirror_num); ret = -EIO; goto fail; } @@ -639,7 +638,11 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, faili = nr_pages - 1; cb->nr_pages = nr_pages; - add_ra_bio_pages(inode, em_start + em_len, cb); + /* In the parent-locked case, we only locked the range we are + * interested in. In all other cases, we can opportunistically + * cache decompressed data that goes beyond the requested range. */ + if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED)) + add_ra_bio_pages(inode, em_start + em_len, cb); /* include any pages we added in add_ra-bio_pages */ uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5bf4c39..6434672 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -274,8 +274,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, else btrfs_set_header_owner(cow, new_root_objectid); - write_extent_buffer(cow, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(cow), + write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(cow), BTRFS_FSID_SIZE); WARN_ON(btrfs_header_generation(buf) > trans->transid); @@ -484,8 +483,27 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) struct rb_node **new; struct rb_node *parent = NULL; struct tree_mod_elem *cur; + int ret = 0; + + BUG_ON(!tm); + + tree_mod_log_write_lock(fs_info); + if (list_empty(&fs_info->tree_mod_seq_list)) { + tree_mod_log_write_unlock(fs_info); + /* + * Ok we no longer care about logging modifications, free up tm + * and return 0. Any callers shouldn't be using tm after + * calling tree_mod_log_insert, but if they do we can just + * change this to return a special error code to let the callers + * do their own thing. + */ + kfree(tm); + return 0; + } - BUG_ON(!tm || !tm->seq); + spin_lock(&fs_info->tree_mod_seq_lock); + tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info); + spin_unlock(&fs_info->tree_mod_seq_lock); tm_root = &fs_info->tree_mod_log; new = &tm_root->rb_node; @@ -501,14 +519,17 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) else if (cur->seq > tm->seq) new = &((*new)->rb_right); else { + ret = -EEXIST; kfree(tm); - return -EEXIST; + goto out; } } rb_link_node(&tm->node, parent, new); rb_insert_color(&tm->node, tm_root); - return 0; +out: + tree_mod_log_write_unlock(fs_info); + return ret; } /* @@ -524,57 +545,19 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info, return 1; if (eb && btrfs_header_level(eb) == 0) return 1; - - tree_mod_log_write_lock(fs_info); - if (list_empty(&fs_info->tree_mod_seq_list)) { - /* - * someone emptied the list while we were waiting for the lock. - * we must not add to the list when no blocker exists. - */ - tree_mod_log_write_unlock(fs_info); - return 1; - } - return 0; } -/* - * This allocates memory and gets a tree modification sequence number. - * - * Returns <0 on error. - * Returns >0 (the added sequence number) on success. - */ -static inline int tree_mod_alloc(struct btrfs_fs_info *fs_info, gfp_t flags, - struct tree_mod_elem **tm_ret) -{ - struct tree_mod_elem *tm; - - /* - * once we switch from spin locks to something different, we should - * honor the flags parameter here. - */ - tm = *tm_ret = kzalloc(sizeof(*tm), GFP_ATOMIC); - if (!tm) - return -ENOMEM; - - spin_lock(&fs_info->tree_mod_seq_lock); - tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info); - spin_unlock(&fs_info->tree_mod_seq_lock); - - return tm->seq; -} - static inline int __tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, int slot, enum mod_log_op op, gfp_t flags) { - int ret; struct tree_mod_elem *tm; - ret = tree_mod_alloc(fs_info, flags, &tm); - if (ret < 0) - return ret; + tm = kzalloc(sizeof(*tm), flags); + if (!tm) + return -ENOMEM; tm->index = eb->start >> PAGE_CACHE_SHIFT; if (op != MOD_LOG_KEY_ADD) { @@ -589,34 +572,14 @@ __tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, } static noinline int -tree_mod_log_insert_key_mask(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int slot, - enum mod_log_op op, gfp_t flags) +tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int slot, + enum mod_log_op op, gfp_t flags) { - int ret; - if (tree_mod_dont_log(fs_info, eb)) return 0; - ret = __tree_mod_log_insert_key(fs_info, eb, slot, op, flags); - - tree_mod_log_write_unlock(fs_info); - return ret; -} - -static noinline int -tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, - int slot, enum mod_log_op op) -{ - return tree_mod_log_insert_key_mask(fs_info, eb, slot, op, GFP_NOFS); -} - -static noinline int -tree_mod_log_insert_key_locked(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int slot, - enum mod_log_op op) -{ - return __tree_mod_log_insert_key(fs_info, eb, slot, op, GFP_NOFS); + return __tree_mod_log_insert_key(fs_info, eb, slot, op, flags); } static noinline int @@ -637,14 +600,14 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, * buffer, i.e. dst_slot < src_slot. */ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) { - ret = tree_mod_log_insert_key_locked(fs_info, eb, i + dst_slot, - MOD_LOG_KEY_REMOVE_WHILE_MOVING); + ret = __tree_mod_log_insert_key(fs_info, eb, i + dst_slot, + MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS); BUG_ON(ret < 0); } - ret = tree_mod_alloc(fs_info, flags, &tm); - if (ret < 0) - goto out; + tm = kzalloc(sizeof(*tm), flags); + if (!tm) + return -ENOMEM; tm->index = eb->start >> PAGE_CACHE_SHIFT; tm->slot = src_slot; @@ -652,10 +615,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, tm->move.nr_items = nr_items; tm->op = MOD_LOG_MOVE_KEYS; - ret = __tree_mod_log_insert(fs_info, tm); -out: - tree_mod_log_write_unlock(fs_info); - return ret; + return __tree_mod_log_insert(fs_info, tm); } static inline void @@ -670,8 +630,8 @@ __tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) nritems = btrfs_header_nritems(eb); for (i = nritems - 1; i >= 0; i--) { - ret = tree_mod_log_insert_key_locked(fs_info, eb, i, - MOD_LOG_KEY_REMOVE_WHILE_FREEING); + ret = __tree_mod_log_insert_key(fs_info, eb, i, + MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS); BUG_ON(ret < 0); } } @@ -683,7 +643,6 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, int log_removal) { struct tree_mod_elem *tm; - int ret; if (tree_mod_dont_log(fs_info, NULL)) return 0; @@ -691,9 +650,9 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, if (log_removal) __tree_mod_log_free_eb(fs_info, old_root); - ret = tree_mod_alloc(fs_info, flags, &tm); - if (ret < 0) - goto out; + tm = kzalloc(sizeof(*tm), flags); + if (!tm) + return -ENOMEM; tm->index = new_root->start >> PAGE_CACHE_SHIFT; tm->old_root.logical = old_root->start; @@ -701,10 +660,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, tm->generation = btrfs_header_generation(old_root); tm->op = MOD_LOG_ROOT_REPLACE; - ret = __tree_mod_log_insert(fs_info, tm); -out: - tree_mod_log_write_unlock(fs_info); - return ret; + return __tree_mod_log_insert(fs_info, tm); } static struct tree_mod_elem * @@ -784,23 +740,20 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, if (tree_mod_dont_log(fs_info, NULL)) return; - if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0) { - tree_mod_log_write_unlock(fs_info); + if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0) return; - } for (i = 0; i < nr_items; i++) { - ret = tree_mod_log_insert_key_locked(fs_info, src, + ret = __tree_mod_log_insert_key(fs_info, src, i + src_offset, - MOD_LOG_KEY_REMOVE); + MOD_LOG_KEY_REMOVE, GFP_NOFS); BUG_ON(ret < 0); - ret = tree_mod_log_insert_key_locked(fs_info, dst, + ret = __tree_mod_log_insert_key(fs_info, dst, i + dst_offset, - MOD_LOG_KEY_ADD); + MOD_LOG_KEY_ADD, + GFP_NOFS); BUG_ON(ret < 0); } - - tree_mod_log_write_unlock(fs_info); } static inline void @@ -819,9 +772,9 @@ tree_mod_log_set_node_key(struct btrfs_fs_info *fs_info, { int ret; - ret = tree_mod_log_insert_key_mask(fs_info, eb, slot, - MOD_LOG_KEY_REPLACE, - atomic ? GFP_ATOMIC : GFP_NOFS); + ret = __tree_mod_log_insert_key(fs_info, eb, slot, + MOD_LOG_KEY_REPLACE, + atomic ? GFP_ATOMIC : GFP_NOFS); BUG_ON(ret < 0); } @@ -830,10 +783,7 @@ tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) { if (tree_mod_dont_log(fs_info, eb)) return; - __tree_mod_log_free_eb(fs_info, eb); - - tree_mod_log_write_unlock(fs_info); } static noinline void @@ -1046,8 +996,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, else btrfs_set_header_owner(cow, root->root_key.objectid); - write_extent_buffer(cow, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(cow), + write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(cow), BTRFS_FSID_SIZE); ret = update_ref_for_cow(trans, root, buf, cow, &last_ref); @@ -1083,7 +1032,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, WARN_ON(trans->transid != btrfs_header_generation(parent)); tree_mod_log_insert_key(root->fs_info, parent, parent_slot, - MOD_LOG_KEY_REPLACE); + MOD_LOG_KEY_REPLACE, GFP_NOFS); btrfs_set_node_blockptr(parent, parent_slot, cow->start); btrfs_set_node_ptr_generation(parent, parent_slot, @@ -1116,7 +1065,7 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, int looped = 0; if (!time_seq) - return 0; + return NULL; /* * the very last operation that's logged for a root is the replacement @@ -1127,7 +1076,7 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, tm = tree_mod_log_search_oldest(fs_info, root_logical, time_seq); if (!looped && !tm) - return 0; + return NULL; /* * if there are no tree operation for the oldest root, we simply * return it. this should only happen if that (old) root is at @@ -1240,8 +1189,8 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, * is freed (its refcount is decremented). */ static struct extent_buffer * -tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, - u64 time_seq) +tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, + struct extent_buffer *eb, u64 time_seq) { struct extent_buffer *eb_rewin; struct tree_mod_elem *tm; @@ -1256,11 +1205,18 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, if (!tm) return eb; + btrfs_set_path_blocking(path); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) { BUG_ON(tm->slot != 0); eb_rewin = alloc_dummy_extent_buffer(eb->start, fs_info->tree_root->nodesize); - BUG_ON(!eb_rewin); + if (!eb_rewin) { + btrfs_tree_read_unlock_blocking(eb); + free_extent_buffer(eb); + return NULL; + } btrfs_set_header_bytenr(eb_rewin, eb->start); btrfs_set_header_backref_rev(eb_rewin, btrfs_header_backref_rev(eb)); @@ -1268,11 +1224,15 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, btrfs_set_header_level(eb_rewin, btrfs_header_level(eb)); } else { eb_rewin = btrfs_clone_extent_buffer(eb); - BUG_ON(!eb_rewin); + if (!eb_rewin) { + btrfs_tree_read_unlock_blocking(eb); + free_extent_buffer(eb); + return NULL; + } } - extent_buffer_get(eb_rewin); - btrfs_tree_read_unlock(eb); + btrfs_clear_path_blocking(path, NULL, BTRFS_READ_LOCK); + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); extent_buffer_get(eb_rewin); @@ -1336,8 +1296,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) free_extent_buffer(eb_root); eb = alloc_dummy_extent_buffer(logical, root->nodesize); } else { + btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK); eb = btrfs_clone_extent_buffer(eb_root); - btrfs_tree_read_unlock(eb_root); + btrfs_tree_read_unlock_blocking(eb_root); free_extent_buffer(eb_root); } @@ -1420,14 +1381,12 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, if (trans->transaction != root->fs_info->running_transaction) WARN(1, KERN_CRIT "trans %llu running %llu\n", - (unsigned long long)trans->transid, - (unsigned long long) + trans->transid, root->fs_info->running_transaction->transid); if (trans->transid != root->fs_info->generation) WARN(1, KERN_CRIT "trans %llu running %llu\n", - (unsigned long long)trans->transid, - (unsigned long long)root->fs_info->generation); + trans->transid, root->fs_info->generation); if (!should_cow_block(trans, root, buf)) { *cow_ret = buf; @@ -2467,6 +2426,40 @@ done: return ret; } +static void key_search_validate(struct extent_buffer *b, + struct btrfs_key *key, + int level) +{ +#ifdef CONFIG_BTRFS_ASSERT + struct btrfs_disk_key disk_key; + + btrfs_cpu_key_to_disk(&disk_key, key); + + if (level == 0) + ASSERT(!memcmp_extent_buffer(b, &disk_key, + offsetof(struct btrfs_leaf, items[0].key), + sizeof(disk_key))); + else + ASSERT(!memcmp_extent_buffer(b, &disk_key, + offsetof(struct btrfs_node, ptrs[0].key), + sizeof(disk_key))); +#endif +} + +static int key_search(struct extent_buffer *b, struct btrfs_key *key, + int level, int *prev_cmp, int *slot) +{ + if (*prev_cmp != 0) { + *prev_cmp = bin_search(b, key, level, slot); + return *prev_cmp; + } + + key_search_validate(b, key, level); + *slot = 0; + + return 0; +} + /* * look for key in the tree. path is filled in with nodes along the way * if key is found, we return zero and you can find the item in the leaf @@ -2495,6 +2488,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root int write_lock_level = 0; u8 lowest_level = 0; int min_write_lock_level; + int prev_cmp; lowest_level = p->lowest_level; WARN_ON(lowest_level && ins_len > 0); @@ -2525,6 +2519,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root min_write_lock_level = write_lock_level; again: + prev_cmp = -1; /* * we try very hard to do read locks on the root */ @@ -2625,7 +2620,7 @@ cow_done: if (!cow) btrfs_unlock_up_safe(p, level + 1); - ret = bin_search(b, key, level, &slot); + ret = key_search(b, key, level, &prev_cmp, &slot); if (level != 0) { int dec = 0; @@ -2760,6 +2755,7 @@ int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, int level; int lowest_unlock = 1; u8 lowest_level = 0; + int prev_cmp; lowest_level = p->lowest_level; WARN_ON(p->nodes[0] != NULL); @@ -2770,6 +2766,7 @@ int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, } again: + prev_cmp = -1; b = get_old_root(root, time_seq); level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; @@ -2787,7 +2784,7 @@ again: */ btrfs_unlock_up_safe(p, level + 1); - ret = bin_search(b, key, level, &slot); + ret = key_search(b, key, level, &prev_cmp, &slot); if (level != 0) { int dec = 0; @@ -2821,7 +2818,11 @@ again: btrfs_clear_path_blocking(p, b, BTRFS_READ_LOCK); } - b = tree_mod_log_rewind(root->fs_info, b, time_seq); + b = tree_mod_log_rewind(root->fs_info, p, b, time_seq); + if (!b) { + ret = -ENOMEM; + goto done; + } p->locks[level] = BTRFS_READ_LOCK; p->nodes[level] = b; } else { @@ -3144,13 +3145,11 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(c, root->root_key.objectid); - write_extent_buffer(c, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(c), + write_extent_buffer(c, root->fs_info->fsid, btrfs_header_fsid(c), BTRFS_FSID_SIZE); write_extent_buffer(c, root->fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(c), - BTRFS_UUID_SIZE); + btrfs_header_chunk_tree_uuid(c), BTRFS_UUID_SIZE); btrfs_set_node_key(c, &lower_key, 0); btrfs_set_node_blockptr(c, 0, lower->start); @@ -3209,7 +3208,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, } if (level) { ret = tree_mod_log_insert_key(root->fs_info, lower, slot, - MOD_LOG_KEY_ADD); + MOD_LOG_KEY_ADD, GFP_NOFS); BUG_ON(ret < 0); } btrfs_set_node_key(lower, key, slot); @@ -3285,10 +3284,9 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(split, root->root_key.objectid); write_extent_buffer(split, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(split), - BTRFS_FSID_SIZE); + btrfs_header_fsid(split), BTRFS_FSID_SIZE); write_extent_buffer(split, root->fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(split), + btrfs_header_chunk_tree_uuid(split), BTRFS_UUID_SIZE); tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid); @@ -4041,11 +4039,10 @@ again: btrfs_set_header_owner(right, root->root_key.objectid); btrfs_set_header_level(right, 0); write_extent_buffer(right, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(right), - BTRFS_FSID_SIZE); + btrfs_header_fsid(right), BTRFS_FSID_SIZE); write_extent_buffer(right, root->fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(right), + btrfs_header_chunk_tree_uuid(right), BTRFS_UUID_SIZE); if (split == 0) { @@ -4643,7 +4640,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, (nritems - slot - 1)); } else if (level) { ret = tree_mod_log_insert_key(root->fs_info, parent, slot, - MOD_LOG_KEY_REMOVE); + MOD_LOG_KEY_REMOVE, GFP_NOFS); BUG_ON(ret < 0); } @@ -4815,7 +4812,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, * This may release the path, and so you may lose any locks held at the * time you call it. */ -int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) +static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; struct btrfs_disk_key found_key; @@ -5330,19 +5327,20 @@ int btrfs_compare_trees(struct btrfs_root *left_root, goto out; advance_right = ADVANCE; } else { + enum btrfs_compare_tree_result cmp; + WARN_ON(!extent_buffer_uptodate(left_path->nodes[0])); ret = tree_compare_item(left_root, left_path, right_path, tmp_buf); - if (ret) { - WARN_ON(!extent_buffer_uptodate(left_path->nodes[0])); - ret = changed_cb(left_root, right_root, - left_path, right_path, - &left_key, - BTRFS_COMPARE_TREE_CHANGED, - ctx); - if (ret < 0) - goto out; - } + if (ret) + cmp = BTRFS_COMPARE_TREE_CHANGED; + else + cmp = BTRFS_COMPARE_TREE_SAME; + ret = changed_cb(left_root, right_root, + left_path, right_path, + &left_key, cmp, ctx); + if (ret < 0) + goto out; advance_left = ADVANCE; advance_right = ADVANCE; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e795bf1..3c1da6f 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -23,6 +23,7 @@ #include <linux/highmem.h> #include <linux/fs.h> #include <linux/rwsem.h> +#include <linux/semaphore.h> #include <linux/completion.h> #include <linux/backing-dev.h> #include <linux/wait.h> @@ -91,6 +92,9 @@ struct btrfs_ordered_sum; /* holds quota configuration and tracking */ #define BTRFS_QUOTA_TREE_OBJECTID 8ULL +/* for storing items that use the BTRFS_UUID_KEY* types */ +#define BTRFS_UUID_TREE_OBJECTID 9ULL + /* for storing balance parameters in the root tree */ #define BTRFS_BALANCE_OBJECTID -4ULL @@ -142,7 +146,7 @@ struct btrfs_ordered_sum; #define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2 -#define BTRFS_DEV_REPLACE_DEVID 0 +#define BTRFS_DEV_REPLACE_DEVID 0ULL /* * the max metadata block size. This limit is somewhat artificial, @@ -478,9 +482,10 @@ struct btrfs_super_block { char label[BTRFS_LABEL_SIZE]; __le64 cache_generation; + __le64 uuid_tree_generation; /* future expansion */ - __le64 reserved[31]; + __le64 reserved[30]; u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; } __attribute__ ((__packed__)); @@ -1188,6 +1193,7 @@ enum btrfs_caching_type { BTRFS_CACHE_STARTED = 1, BTRFS_CACHE_FAST = 2, BTRFS_CACHE_FINISHED = 3, + BTRFS_CACHE_ERROR = 4, }; enum btrfs_disk_cache_state { @@ -1302,6 +1308,7 @@ struct btrfs_fs_info { struct btrfs_root *fs_root; struct btrfs_root *csum_root; struct btrfs_root *quota_root; + struct btrfs_root *uuid_root; /* the log root tree is a directory of all the other log roots */ struct btrfs_root *log_root_tree; @@ -1350,6 +1357,7 @@ struct btrfs_fs_info { u64 last_trans_log_full_commit; unsigned long mount_opt; unsigned long compress_type:4; + int commit_interval; /* * It is a suggestive number, the read side is safe even it gets a * wrong number because we will write out the data into a regular @@ -1411,6 +1419,13 @@ struct btrfs_fs_info { * before jumping into the main commit. */ struct mutex ordered_operations_mutex; + + /* + * Same as ordered_operations_mutex except this is for ordered extents + * and not the operations. + */ + struct mutex ordered_extent_flush_mutex; + struct rw_semaphore extent_commit_sem; struct rw_semaphore cleanup_work_sem; @@ -1641,6 +1656,9 @@ struct btrfs_fs_info { struct btrfs_dev_replace dev_replace; atomic_t mutually_exclusive_operation_running; + + struct semaphore uuid_tree_rescan_sem; + unsigned int update_uuid_tree_gen:1; }; /* @@ -1934,6 +1952,19 @@ struct btrfs_ioctl_defrag_range_args { #define BTRFS_DEV_REPLACE_KEY 250 /* + * Stores items that allow to quickly map UUIDs to something else. + * These items are part of the filesystem UUID tree. + * The key is built like this: + * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits). + */ +#if BTRFS_UUID_SIZE != 16 +#error "UUID items require BTRFS_UUID_SIZE == 16!" +#endif +#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */ +#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to + * received subvols */ + +/* * string items are for debugging. They just store a short string of * data in the FS */ @@ -1967,6 +1998,9 @@ struct btrfs_ioctl_defrag_range_args { #define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 20) #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21) #define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22) +#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23) + +#define BTRFS_DEFAULT_COMMIT_INTERVAL (30) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@ -2130,14 +2164,14 @@ BTRFS_SETGET_STACK_FUNCS(stack_device_bandwidth, struct btrfs_dev_item, BTRFS_SETGET_STACK_FUNCS(stack_device_generation, struct btrfs_dev_item, generation, 64); -static inline char *btrfs_device_uuid(struct btrfs_dev_item *d) +static inline unsigned long btrfs_device_uuid(struct btrfs_dev_item *d) { - return (char *)d + offsetof(struct btrfs_dev_item, uuid); + return (unsigned long)d + offsetof(struct btrfs_dev_item, uuid); } -static inline char *btrfs_device_fsid(struct btrfs_dev_item *d) +static inline unsigned long btrfs_device_fsid(struct btrfs_dev_item *d) { - return (char *)d + offsetof(struct btrfs_dev_item, fsid); + return (unsigned long)d + offsetof(struct btrfs_dev_item, fsid); } BTRFS_SETGET_FUNCS(chunk_length, struct btrfs_chunk, length, 64); @@ -2240,6 +2274,23 @@ BTRFS_SETGET_FUNCS(inode_gid, struct btrfs_inode_item, gid, 32); BTRFS_SETGET_FUNCS(inode_mode, struct btrfs_inode_item, mode, 32); BTRFS_SETGET_FUNCS(inode_rdev, struct btrfs_inode_item, rdev, 64); BTRFS_SETGET_FUNCS(inode_flags, struct btrfs_inode_item, flags, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item, + generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item, + sequence, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item, + transid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item, + nbytes, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item, + block_group, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32); +BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64); +BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64); static inline struct btrfs_timespec * btrfs_inode_atime(struct btrfs_inode_item *inode_item) @@ -2267,6 +2318,8 @@ btrfs_inode_ctime(struct btrfs_inode_item *inode_item) BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64); BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32); +BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64); +BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32); /* struct btrfs_dev_extent */ BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent, @@ -2277,10 +2330,10 @@ BTRFS_SETGET_FUNCS(dev_extent_chunk_offset, struct btrfs_dev_extent, chunk_offset, 64); BTRFS_SETGET_FUNCS(dev_extent_length, struct btrfs_dev_extent, length, 64); -static inline u8 *btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev) +static inline unsigned long btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev) { unsigned long ptr = offsetof(struct btrfs_dev_extent, chunk_tree_uuid); - return (u8 *)((unsigned long)dev + ptr); + return (unsigned long)dev + ptr; } BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 64); @@ -2348,6 +2401,10 @@ BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32); /* struct btrfs_node */ BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64); BTRFS_SETGET_FUNCS(key_generation, struct btrfs_key_ptr, generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_key_blockptr, struct btrfs_key_ptr, + blockptr, 64); +BTRFS_SETGET_STACK_FUNCS(stack_key_generation, struct btrfs_key_ptr, + generation, 64); static inline u64 btrfs_node_blockptr(struct extent_buffer *eb, int nr) { @@ -2404,6 +2461,8 @@ static inline void btrfs_set_node_key(struct extent_buffer *eb, /* struct btrfs_item */ BTRFS_SETGET_FUNCS(item_offset, struct btrfs_item, offset, 32); BTRFS_SETGET_FUNCS(item_size, struct btrfs_item, size, 32); +BTRFS_SETGET_STACK_FUNCS(stack_item_offset, struct btrfs_item, offset, 32); +BTRFS_SETGET_STACK_FUNCS(stack_item_size, struct btrfs_item, size, 32); static inline unsigned long btrfs_item_nr_offset(int nr) { @@ -2466,6 +2525,13 @@ BTRFS_SETGET_FUNCS(dir_data_len, struct btrfs_dir_item, data_len, 16); BTRFS_SETGET_FUNCS(dir_type, struct btrfs_dir_item, type, 8); BTRFS_SETGET_FUNCS(dir_name_len, struct btrfs_dir_item, name_len, 16); BTRFS_SETGET_FUNCS(dir_transid, struct btrfs_dir_item, transid, 64); +BTRFS_SETGET_STACK_FUNCS(stack_dir_type, struct btrfs_dir_item, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_dir_data_len, struct btrfs_dir_item, + data_len, 16); +BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item, + name_len, 16); +BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item, + transid, 64); static inline void btrfs_dir_item_key(struct extent_buffer *eb, struct btrfs_dir_item *item, @@ -2568,6 +2634,12 @@ BTRFS_SETGET_HEADER_FUNCS(header_owner, struct btrfs_header, owner, 64); BTRFS_SETGET_HEADER_FUNCS(header_nritems, struct btrfs_header, nritems, 32); BTRFS_SETGET_HEADER_FUNCS(header_flags, struct btrfs_header, flags, 64); BTRFS_SETGET_HEADER_FUNCS(header_level, struct btrfs_header, level, 8); +BTRFS_SETGET_STACK_FUNCS(stack_header_generation, struct btrfs_header, + generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_header_owner, struct btrfs_header, owner, 64); +BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header, + nritems, 32); +BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64); static inline int btrfs_header_flag(struct extent_buffer *eb, u64 flag) { @@ -2603,16 +2675,14 @@ static inline void btrfs_set_header_backref_rev(struct extent_buffer *eb, btrfs_set_header_flags(eb, flags); } -static inline u8 *btrfs_header_fsid(struct extent_buffer *eb) +static inline unsigned long btrfs_header_fsid(struct extent_buffer *eb) { - unsigned long ptr = offsetof(struct btrfs_header, fsid); - return (u8 *)ptr; + return offsetof(struct btrfs_header, fsid); } -static inline u8 *btrfs_header_chunk_tree_uuid(struct extent_buffer *eb) +static inline unsigned long btrfs_header_chunk_tree_uuid(struct extent_buffer *eb) { - unsigned long ptr = offsetof(struct btrfs_header, chunk_tree_uuid); - return (u8 *)ptr; + return offsetof(struct btrfs_header, chunk_tree_uuid); } static inline int btrfs_is_leaf(struct extent_buffer *eb) @@ -2830,6 +2900,9 @@ BTRFS_SETGET_STACK_FUNCS(super_csum_type, struct btrfs_super_block, csum_type, 16); BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block, cache_generation, 64); +BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64); +BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, + uuid_tree_generation, 64); static inline int btrfs_super_csum_size(struct btrfs_super_block *s) { @@ -2847,6 +2920,14 @@ static inline unsigned long btrfs_leaf_data(struct extent_buffer *l) /* struct btrfs_file_extent_item */ BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr, + struct btrfs_file_extent_item, disk_bytenr, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_offset, + struct btrfs_file_extent_item, offset, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation, + struct btrfs_file_extent_item, generation, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes, + struct btrfs_file_extent_item, num_bytes, 64); static inline unsigned long btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e) @@ -3107,11 +3188,9 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, u64 offset, struct btrfs_key *ins); -int btrfs_reserve_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 num_bytes, u64 min_alloc_size, - u64 empty_size, u64 hint_byte, - struct btrfs_key *ins, int is_data); +int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, + u64 min_alloc_size, u64 empty_size, u64 hint_byte, + struct btrfs_key *ins, int is_data); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3175,7 +3254,7 @@ void btrfs_orphan_release_metadata(struct inode *inode); int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int nitems, - u64 *qgroup_reserved); + u64 *qgroup_reserved, bool use_global_rsv); void btrfs_subvolume_release_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, u64 qgroup_reserved); @@ -3245,6 +3324,7 @@ enum btrfs_compare_tree_result { BTRFS_COMPARE_TREE_NEW, BTRFS_COMPARE_TREE_DELETED, BTRFS_COMPARE_TREE_CHANGED, + BTRFS_COMPARE_TREE_SAME, }; typedef int (*btrfs_changed_cb_t)(struct btrfs_root *left_root, struct btrfs_root *right_root, @@ -3380,6 +3460,7 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info) kfree(fs_info->dev_root); kfree(fs_info->csum_root); kfree(fs_info->quota_root); + kfree(fs_info->uuid_root); kfree(fs_info->super_copy); kfree(fs_info->super_for_commit); kfree(fs_info); @@ -3414,8 +3495,6 @@ int __must_check btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_key *key, struct btrfs_root_item *item); -void btrfs_read_root_item(struct extent_buffer *eb, int slot, - struct btrfs_root_item *item); int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key, struct btrfs_path *path, struct btrfs_root_item *root_item, struct btrfs_key *root_key); @@ -3426,6 +3505,17 @@ void btrfs_check_and_init_root_item(struct btrfs_root_item *item); void btrfs_update_root_times(struct btrfs_trans_handle *trans, struct btrfs_root *root); +/* uuid-tree.c */ +int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, + struct btrfs_root *uuid_root, u8 *uuid, u8 type, + u64 subid); +int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans, + struct btrfs_root *uuid_root, u8 *uuid, u8 type, + u64 subid); +int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info, + int (*check_func)(struct btrfs_fs_info *, u8 *, u8, + u64)); + /* dir-item.c */ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, const char *name, int name_len); @@ -3509,12 +3599,14 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, struct btrfs_inode_extref **extref_ret); /* file-item.c */ +struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 len); int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, struct bio *bio, u32 *dst); int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode, - struct bio *bio, u64 logical_offset); + struct btrfs_dio_private *dip, struct bio *bio, + u64 logical_offset); int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 objectid, u64 pos, @@ -3552,8 +3644,7 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work); struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page, size_t pg_offset, u64 start, u64 len, int create); -noinline int can_nocow_extent(struct btrfs_trans_handle *trans, - struct inode *inode, u64 offset, u64 *len, +noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, u64 *ram_bytes); @@ -3643,11 +3734,15 @@ extern const struct dentry_operations btrfs_dentry_operations; long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); void btrfs_update_iflags(struct inode *inode); void btrfs_inherit_iflags(struct inode *inode, struct inode *dir); +int btrfs_is_empty_uuid(u8 *uuid); int btrfs_defrag_file(struct inode *inode, struct file *file, struct btrfs_ioctl_defrag_range_args *range, u64 newer_than, unsigned long max_pages); void btrfs_get_block_group_info(struct list_head *groups_list, struct btrfs_ioctl_space_info *space); +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, + struct btrfs_ioctl_balance_args *bargs); + /* file.c */ int btrfs_auto_defrag_init(void); @@ -3720,6 +3815,22 @@ void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) #define btrfs_debug(fs_info, fmt, args...) \ btrfs_printk(fs_info, KERN_DEBUG fmt, ##args) +#ifdef CONFIG_BTRFS_ASSERT + +static inline void assfail(char *expr, char *file, int line) +{ + printk(KERN_ERR "BTRFS assertion failed: %s, file: %s, line: %d", + expr, file, line); + BUG(); +} + +#define ASSERT(expr) \ + (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__)) +#else +#define ASSERT(expr) ((void)0) +#endif + +#define btrfs_assert() __printf(5, 6) void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 3755109..cbd9523 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -21,6 +21,7 @@ #include "delayed-inode.h" #include "disk-io.h" #include "transaction.h" +#include "ctree.h" #define BTRFS_DELAYED_WRITEBACK 512 #define BTRFS_DELAYED_BACKGROUND 128 @@ -1453,10 +1454,10 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, dir_item = (struct btrfs_dir_item *)delayed_item->data; dir_item->location = *disk_key; - dir_item->transid = cpu_to_le64(trans->transid); - dir_item->data_len = 0; - dir_item->name_len = cpu_to_le16(name_len); - dir_item->type = type; + btrfs_set_stack_dir_transid(dir_item, trans->transid); + btrfs_set_stack_dir_data_len(dir_item, 0); + btrfs_set_stack_dir_name_len(dir_item, name_len); + btrfs_set_stack_dir_type(dir_item, type); memcpy((char *)(dir_item + 1), name, name_len); ret = btrfs_delayed_item_reserve_metadata(trans, root, delayed_item); @@ -1470,13 +1471,11 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, mutex_lock(&delayed_node->mutex); ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item); if (unlikely(ret)) { - printk(KERN_ERR "err add delayed dir index item(name: %s) into " - "the insertion tree of the delayed node" + printk(KERN_ERR "err add delayed dir index item(name: %.*s) " + "into the insertion tree of the delayed node" "(root id: %llu, inode id: %llu, errno: %d)\n", - name, - (unsigned long long)delayed_node->root->objectid, - (unsigned long long)delayed_node->inode_id, - ret); + name_len, name, delayed_node->root->objectid, + delayed_node->inode_id, ret); BUG(); } mutex_unlock(&delayed_node->mutex); @@ -1547,9 +1546,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, printk(KERN_ERR "err add delayed dir index item(index: %llu) " "into the deletion tree of the delayed node" "(root id: %llu, inode id: %llu, errno: %d)\n", - (unsigned long long)index, - (unsigned long long)node->root->objectid, - (unsigned long long)node->inode_id, + index, node->root->objectid, node->inode_id, ret); BUG(); } @@ -1699,7 +1696,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, di = (struct btrfs_dir_item *)curr->data; name = (char *)(di + 1); - name_len = le16_to_cpu(di->name_len); + name_len = btrfs_stack_dir_name_len(di); d_type = btrfs_filetype_table[di->type]; btrfs_disk_key_to_cpu(&location, &di->location); @@ -1716,27 +1713,6 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, return 0; } -BTRFS_SETGET_STACK_FUNCS(stack_inode_generation, struct btrfs_inode_item, - generation, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_sequence, struct btrfs_inode_item, - sequence, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_transid, struct btrfs_inode_item, - transid, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_size, struct btrfs_inode_item, size, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_nbytes, struct btrfs_inode_item, - nbytes, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_block_group, struct btrfs_inode_item, - block_group, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_nlink, struct btrfs_inode_item, nlink, 32); -BTRFS_SETGET_STACK_FUNCS(stack_inode_uid, struct btrfs_inode_item, uid, 32); -BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32); -BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32); -BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64); -BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64); - -BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64); -BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32); - static void fill_stack_inode_item(struct btrfs_trans_handle *trans, struct btrfs_inode_item *inode_item, struct inode *inode) diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index c219463..e4d467b 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -241,7 +241,7 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, return 0; } -static void inline drop_delayed_ref(struct btrfs_trans_handle *trans, +static inline void drop_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_node *ref) { @@ -600,7 +600,7 @@ static noinline void add_delayed_ref_head(struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&head_ref->cluster); mutex_init(&head_ref->mutex); - trace_btrfs_delayed_ref_head(ref, head_ref, action); + trace_add_delayed_ref_head(ref, head_ref, action); existing = tree_insert(&delayed_refs->root, &ref->rb_node); @@ -661,7 +661,7 @@ static noinline void add_delayed_tree_ref(struct btrfs_fs_info *fs_info, ref->type = BTRFS_TREE_BLOCK_REF_KEY; full_ref->level = level; - trace_btrfs_delayed_tree_ref(ref, full_ref, action); + trace_add_delayed_tree_ref(ref, full_ref, action); existing = tree_insert(&delayed_refs->root, &ref->rb_node); @@ -722,7 +722,7 @@ static noinline void add_delayed_data_ref(struct btrfs_fs_info *fs_info, full_ref->objectid = owner; full_ref->offset = offset; - trace_btrfs_delayed_data_ref(ref, full_ref, action); + trace_add_delayed_data_ref(ref, full_ref, action); existing = tree_insert(&delayed_refs->root, &ref->rb_node); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 4253ad5..a644353 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -148,13 +148,13 @@ no_valid_dev_replace_entry_found: !btrfs_test_opt(dev_root, DEGRADED)) { ret = -EIO; pr_warn("btrfs: cannot mount because device replace operation is ongoing and\n" "srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?\n", - (unsigned long long)src_devid); + src_devid); } if (!dev_replace->tgtdev && !btrfs_test_opt(dev_root, DEGRADED)) { ret = -EIO; pr_warn("btrfs: cannot mount because device replace operation is ongoing and\n" "tgtdev (devid %llu) is missing, need to run btrfs dev scan?\n", - (unsigned long long)BTRFS_DEV_REPLACE_DEVID); + BTRFS_DEV_REPLACE_DEVID); } if (dev_replace->tgtdev) { if (dev_replace->srcdev) { @@ -747,7 +747,7 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info) WARN_ON(atomic_xchg( &fs_info->mutually_exclusive_operation_running, 1)); task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl"); - return PTR_RET(task); + return PTR_ERR_OR_ZERO(task); } static int btrfs_dev_replace_kthread(void *data) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 6b092a1..4cbb00a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -31,6 +31,7 @@ #include <linux/migrate.h> #include <linux/ratelimit.h> #include <linux/uuid.h> +#include <linux/semaphore.h> #include <asm/unaligned.h> #include "compat.h" #include "ctree.h" @@ -302,9 +303,8 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, printk_ratelimited(KERN_INFO "btrfs: %s checksum verify " "failed on %llu wanted %X found %X " "level %d\n", - root->fs_info->sb->s_id, - (unsigned long long)buf->start, val, found, - btrfs_header_level(buf)); + root->fs_info->sb->s_id, buf->start, + val, found, btrfs_header_level(buf)); if (result != (char *)&inline_result) kfree(result); return 1; @@ -345,9 +345,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, } printk_ratelimited("parent transid verify failed on %llu wanted %llu " "found %llu\n", - (unsigned long long)eb->start, - (unsigned long long)parent_transid, - (unsigned long long)btrfs_header_generation(eb)); + eb->start, parent_transid, btrfs_header_generation(eb)); ret = 1; clear_extent_buffer_uptodate(eb); out: @@ -497,8 +495,7 @@ static int check_tree_block_fsid(struct btrfs_root *root, u8 fsid[BTRFS_UUID_SIZE]; int ret = 1; - read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb), - BTRFS_FSID_SIZE); + read_extent_buffer(eb, fsid, btrfs_header_fsid(eb), BTRFS_FSID_SIZE); while (fs_devices) { if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) { ret = 0; @@ -512,8 +509,7 @@ static int check_tree_block_fsid(struct btrfs_root *root, #define CORRUPT(reason, eb, root, slot) \ printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \ "root=%llu, slot=%d\n", reason, \ - (unsigned long long)btrfs_header_bytenr(eb), \ - (unsigned long long)root->objectid, slot) + btrfs_header_bytenr(eb), root->objectid, slot) static noinline int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf) @@ -576,8 +572,9 @@ static noinline int check_leaf(struct btrfs_root *root, return 0; } -static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state, int mirror) +static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, + u64 phy_offset, struct page *page, + u64 start, u64 end, int mirror) { struct extent_io_tree *tree; u64 found_start; @@ -612,14 +609,13 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, if (found_start != eb->start) { printk_ratelimited(KERN_INFO "btrfs bad tree block start " "%llu %llu\n", - (unsigned long long)found_start, - (unsigned long long)eb->start); + found_start, eb->start); ret = -EIO; goto err; } if (check_tree_block_fsid(root, eb)) { printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n", - (unsigned long long)eb->start); + eb->start); ret = -EIO; goto err; } @@ -1148,6 +1144,10 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, return NULL; ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid); + if (ret) { + free_extent_buffer(buf); + return NULL; + } return buf; } @@ -1291,11 +1291,10 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, btrfs_set_header_owner(leaf, objectid); root->node = leaf; - write_extent_buffer(leaf, fs_info->fsid, - (unsigned long)btrfs_header_fsid(leaf), + write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(leaf), BTRFS_FSID_SIZE); write_extent_buffer(leaf, fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(leaf), + btrfs_header_chunk_tree_uuid(leaf), BTRFS_UUID_SIZE); btrfs_mark_buffer_dirty(leaf); @@ -1379,8 +1378,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->node = leaf; write_extent_buffer(root->node, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(root->node), - BTRFS_FSID_SIZE); + btrfs_header_fsid(root->node), BTRFS_FSID_SIZE); btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); return root; @@ -1413,11 +1411,11 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, log_root->root_key.offset = root->root_key.objectid; inode_item = &log_root->root_item.inode; - inode_item->generation = cpu_to_le64(1); - inode_item->size = cpu_to_le64(3); - inode_item->nlink = cpu_to_le32(1); - inode_item->nbytes = cpu_to_le64(root->leafsize); - inode_item->mode = cpu_to_le32(S_IFDIR | 0755); + btrfs_set_stack_inode_generation(inode_item, 1); + btrfs_set_stack_inode_size(inode_item, 3); + btrfs_set_stack_inode_nlink(inode_item, 1); + btrfs_set_stack_inode_nbytes(inode_item, root->leafsize); + btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755); btrfs_set_root_node(&log_root->root_item, log_root->node); @@ -1428,8 +1426,8 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, return 0; } -struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, - struct btrfs_key *key) +static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, + struct btrfs_key *key) { struct btrfs_root *root; struct btrfs_fs_info *fs_info = tree_root->fs_info; @@ -1529,8 +1527,8 @@ fail: return ret; } -struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; @@ -1581,10 +1579,16 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID) return fs_info->quota_root ? fs_info->quota_root : ERR_PTR(-ENOENT); + if (location->objectid == BTRFS_UUID_TREE_OBJECTID) + return fs_info->uuid_root ? fs_info->uuid_root : + ERR_PTR(-ENOENT); again: root = btrfs_lookup_fs_root(fs_info, location->objectid); - if (root) + if (root) { + if (btrfs_root_refs(&root->root_item) == 0) + return ERR_PTR(-ENOENT); return root; + } root = btrfs_read_fs_root(fs_info->tree_root, location); if (IS_ERR(root)) @@ -1737,7 +1741,7 @@ static int transaction_kthread(void *arg) do { cannot_commit = false; - delay = HZ * 30; + delay = HZ * root->fs_info->commit_interval; mutex_lock(&root->fs_info->transaction_kthread_mutex); spin_lock(&root->fs_info->trans_lock); @@ -1749,7 +1753,8 @@ static int transaction_kthread(void *arg) now = get_seconds(); if (cur->state < TRANS_STATE_BLOCKED && - (now < cur->start_time || now - cur->start_time < 30)) { + (now < cur->start_time || + now - cur->start_time < root->fs_info->commit_interval)) { spin_unlock(&root->fs_info->trans_lock); delay = HZ * 5; goto sleep; @@ -2038,6 +2043,12 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) info->quota_root->node = NULL; info->quota_root->commit_root = NULL; } + if (info->uuid_root) { + free_extent_buffer(info->uuid_root->node); + free_extent_buffer(info->uuid_root->commit_root); + info->uuid_root->node = NULL; + info->uuid_root->commit_root = NULL; + } if (chunk_root) { free_extent_buffer(info->chunk_root->node); free_extent_buffer(info->chunk_root->commit_root); @@ -2098,11 +2109,14 @@ int open_ctree(struct super_block *sb, struct btrfs_root *chunk_root; struct btrfs_root *dev_root; struct btrfs_root *quota_root; + struct btrfs_root *uuid_root; struct btrfs_root *log_tree_root; int ret; int err = -EINVAL; int num_backups_tried = 0; int backup_index = 0; + bool create_uuid_tree; + bool check_uuid_tree; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); @@ -2189,6 +2203,7 @@ int open_ctree(struct super_block *sb, fs_info->defrag_inodes = RB_ROOT; fs_info->free_chunk_space = 0; fs_info->tree_mod_log = RB_ROOT; + fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; /* readahead state */ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); @@ -2270,6 +2285,7 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->ordered_operations_mutex); + mutex_init(&fs_info->ordered_extent_flush_mutex); mutex_init(&fs_info->tree_log_mutex); mutex_init(&fs_info->chunk_mutex); mutex_init(&fs_info->transaction_kthread_mutex); @@ -2278,6 +2294,7 @@ int open_ctree(struct super_block *sb, init_rwsem(&fs_info->extent_commit_sem); init_rwsem(&fs_info->cleanup_work_sem); init_rwsem(&fs_info->subvol_sem); + sema_init(&fs_info->uuid_tree_rescan_sem, 1); fs_info->dev_replace.lock_owner = 0; atomic_set(&fs_info->dev_replace.nesting_level, 0); mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); @@ -2383,7 +2400,7 @@ int open_ctree(struct super_block *sb, if (features) { printk(KERN_ERR "BTRFS: couldn't mount because of " "unsupported optional features (%Lx).\n", - (unsigned long long)features); + features); err = -EINVAL; goto fail_alloc; } @@ -2453,7 +2470,7 @@ int open_ctree(struct super_block *sb, if (!(sb->s_flags & MS_RDONLY) && features) { printk(KERN_ERR "BTRFS: couldn't mount RDWR because of " "unsupported option features (%Lx).\n", - (unsigned long long)features); + features); err = -EINVAL; goto fail_alloc; } @@ -2466,20 +2483,17 @@ int open_ctree(struct super_block *sb, &fs_info->generic_worker); btrfs_init_workers(&fs_info->delalloc_workers, "delalloc", - fs_info->thread_pool_size, - &fs_info->generic_worker); + fs_info->thread_pool_size, NULL); btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc", - fs_info->thread_pool_size, - &fs_info->generic_worker); + fs_info->thread_pool_size, NULL); btrfs_init_workers(&fs_info->submit_workers, "submit", min_t(u64, fs_devices->num_devices, - fs_info->thread_pool_size), - &fs_info->generic_worker); + fs_info->thread_pool_size), NULL); btrfs_init_workers(&fs_info->caching_workers, "cache", - 2, &fs_info->generic_worker); + fs_info->thread_pool_size, NULL); /* a higher idle thresh on the submit workers makes it much more * likely that bios will be send down in a sane order to the @@ -2575,7 +2589,7 @@ int open_ctree(struct super_block *sb, sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); - if (disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) { + if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) { printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id); goto fail_sb_buffer; } @@ -2615,8 +2629,7 @@ int open_ctree(struct super_block *sb, chunk_root->commit_root = btrfs_root_node(chunk_root); read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node), - BTRFS_UUID_SIZE); + btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE); ret = btrfs_read_chunk_tree(chunk_root); if (ret) { @@ -2696,6 +2709,22 @@ retry_root_backup: fs_info->quota_root = quota_root; } + location.objectid = BTRFS_UUID_TREE_OBJECTID; + uuid_root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(uuid_root)) { + ret = PTR_ERR(uuid_root); + if (ret != -ENOENT) + goto recovery_tree_root; + create_uuid_tree = true; + check_uuid_tree = false; + } else { + uuid_root->track_dirty = 1; + fs_info->uuid_root = uuid_root; + create_uuid_tree = false; + check_uuid_tree = + generation != btrfs_super_uuid_tree_generation(disk_super); + } + fs_info->generation = generation; fs_info->last_trans_committed = generation; @@ -2882,6 +2911,29 @@ retry_root_backup: btrfs_qgroup_rescan_resume(fs_info); + if (create_uuid_tree) { + pr_info("btrfs: creating UUID tree\n"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + pr_warn("btrfs: failed to create the UUID tree %d\n", + ret); + close_ctree(tree_root); + return ret; + } + } else if (check_uuid_tree || + btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) { + pr_info("btrfs: checking UUID tree\n"); + ret = btrfs_check_uuid_tree(fs_info); + if (ret) { + pr_warn("btrfs: failed to check the UUID tree %d\n", + ret); + close_ctree(tree_root); + return ret; + } + } else { + fs_info->update_uuid_tree_gen = 1; + } + return 0; fail_qgroup: @@ -2983,15 +3035,17 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) */ for (i = 0; i < 1; i++) { bytenr = btrfs_sb_offset(i); - if (bytenr + 4096 >= i_size_read(bdev->bd_inode)) + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + i_size_read(bdev->bd_inode)) break; - bh = __bread(bdev, bytenr / 4096, 4096); + bh = __bread(bdev, bytenr / 4096, + BTRFS_SUPER_INFO_SIZE); if (!bh) continue; super = (struct btrfs_super_block *)bh->b_data; if (btrfs_super_bytenr(super) != bytenr || - super->magic != cpu_to_le64(BTRFS_MAGIC)) { + btrfs_super_magic(super) != BTRFS_MAGIC) { brelse(bh); continue; } @@ -3311,7 +3365,6 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) int total_errors = 0; u64 flags; - max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; do_barriers = !btrfs_test_opt(root, NOBARRIER); backup_super_roots(root->fs_info); @@ -3320,6 +3373,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) mutex_lock(&root->fs_info->fs_devices->device_list_mutex); head = &root->fs_info->fs_devices->devices; + max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; if (do_barriers) { ret = barrier_all_devices(root->fs_info); @@ -3362,8 +3416,10 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) printk(KERN_ERR "btrfs: %d errors while writing supers\n", total_errors); - /* This shouldn't happen. FUA is masked off if unsupported */ - BUG(); + /* FUA is masked off if unsupported and can't be the reason */ + btrfs_error(root->fs_info, -EIO, + "%d errors while writing supers", total_errors); + return -EIO; } total_errors = 0; @@ -3421,6 +3477,8 @@ static void free_fs_root(struct btrfs_root *root) { iput(root->cache_inode); WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); + btrfs_free_block_rsv(root, root->orphan_block_rsv); + root->orphan_block_rsv = NULL; if (root->anon_dev) free_anon_bdev(root->anon_dev); free_extent_buffer(root->node); @@ -3510,6 +3568,11 @@ int close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + /* wait for the uuid_scan task to finish */ + down(&fs_info->uuid_tree_rescan_sem); + /* avoid complains from lockdep et al., set sem back to initial state */ + up(&fs_info->uuid_tree_rescan_sem); + /* pause restriper - we want to resume on mount */ btrfs_pause_balance(fs_info); @@ -3573,6 +3636,9 @@ int close_ctree(struct btrfs_root *root) btrfs_free_stripe_hash_table(fs_info); + btrfs_free_block_rsv(root, root->orphan_block_rsv); + root->orphan_block_rsv = NULL; + return 0; } @@ -3608,9 +3674,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) if (transid != root->fs_info->generation) WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, " "found %llu running %llu\n", - (unsigned long long)buf->start, - (unsigned long long)transid, - (unsigned long long)root->fs_info->generation); + buf->start, transid, root->fs_info->generation); was_dirty = set_extent_buffer_dirty(buf); if (!was_dirty) __percpu_counter_add(&root->fs_info->dirty_metadata_bytes, @@ -3744,8 +3808,8 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->ordered_root_lock); } -int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_root *root) +static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, + struct btrfs_root *root) { struct rb_node *node; struct btrfs_delayed_ref_root *delayed_refs; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0236de7..cfb3cf7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -113,7 +113,8 @@ static noinline int block_group_cache_done(struct btrfs_block_group_cache *cache) { smp_mb(); - return cache->cached == BTRFS_CACHE_FINISHED; + return cache->cached == BTRFS_CACHE_FINISHED || + cache->cached == BTRFS_CACHE_ERROR; } static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits) @@ -389,7 +390,7 @@ static noinline void caching_thread(struct btrfs_work *work) u64 total_found = 0; u64 last = 0; u32 nritems; - int ret = 0; + int ret = -ENOMEM; caching_ctl = container_of(work, struct btrfs_caching_control, work); block_group = caching_ctl->block_group; @@ -420,6 +421,7 @@ again: /* need to make sure the commit_root doesn't disappear */ down_read(&fs_info->extent_commit_sem); +next: ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) goto err; @@ -459,6 +461,16 @@ again: continue; } + if (key.objectid < last) { + key.objectid = last; + key.offset = 0; + key.type = BTRFS_EXTENT_ITEM_KEY; + + caching_ctl->progress = last; + btrfs_release_path(path); + goto next; + } + if (key.objectid < block_group->key.objectid) { path->slots[0]++; continue; @@ -506,6 +518,12 @@ err: mutex_unlock(&caching_ctl->mutex); out: + if (ret) { + spin_lock(&block_group->lock); + block_group->caching_ctl = NULL; + block_group->cached = BTRFS_CACHE_ERROR; + spin_unlock(&block_group->lock); + } wake_up(&caching_ctl->wait); put_caching_control(caching_ctl); @@ -771,10 +789,23 @@ again: goto out_free; if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) { - key.type = BTRFS_EXTENT_ITEM_KEY; - key.offset = root->leafsize; - btrfs_release_path(path); - goto again; + metadata = 0; + if (path->slots[0]) { + path->slots[0]--; + btrfs_item_key_to_cpu(path->nodes[0], &key, + path->slots[0]); + if (key.objectid == bytenr && + key.type == BTRFS_EXTENT_ITEM_KEY && + key.offset == root->leafsize) + ret = 0; + } + if (ret) { + key.objectid = bytenr; + key.type = BTRFS_EXTENT_ITEM_KEY; + key.offset = root->leafsize; + btrfs_release_path(path); + goto again; + } } if (ret == 0) { @@ -2011,6 +2042,8 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; ref = btrfs_delayed_node_to_data_ref(node); + trace_run_delayed_data_ref(node, ref, node->action); + if (node->type == BTRFS_SHARED_DATA_REF_KEY) parent = ref->parent; else @@ -2154,6 +2187,8 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, SKINNY_METADATA); ref = btrfs_delayed_node_to_tree_ref(node); + trace_run_delayed_tree_ref(node, ref, node->action); + if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) parent = ref->parent; else @@ -2212,6 +2247,8 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, */ BUG_ON(extent_op); head = btrfs_delayed_node_to_head(node); + trace_run_delayed_ref_head(node, head, node->action); + if (insert_reserved) { btrfs_pin_extent(root, node->bytenr, node->num_bytes, 1); @@ -2403,6 +2440,8 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, default: WARN_ON(1); } + } else { + list_del_init(&locked_ref->cluster); } spin_unlock(&delayed_refs->lock); @@ -2425,7 +2464,6 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, * list before we release it. */ if (btrfs_delayed_ref_is_head(ref)) { - list_del_init(&locked_ref->cluster); btrfs_delayed_ref_unlock(locked_ref); locked_ref = NULL; } @@ -3799,8 +3837,12 @@ again: if (force < space_info->force_alloc) force = space_info->force_alloc; if (space_info->full) { + if (should_alloc_chunk(extent_root, space_info, force)) + ret = -ENOSPC; + else + ret = 0; spin_unlock(&space_info->lock); - return 0; + return ret; } if (!should_alloc_chunk(extent_root, space_info, force)) { @@ -4320,6 +4362,9 @@ static struct btrfs_block_rsv *get_block_rsv( if (root == root->fs_info->csum_root && trans->adding_csums) block_rsv = trans->block_rsv; + if (root == root->fs_info->uuid_root) + block_rsv = trans->block_rsv; + if (!block_rsv) block_rsv = root->block_rsv; @@ -4729,10 +4774,12 @@ void btrfs_orphan_release_metadata(struct inode *inode) int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int items, - u64 *qgroup_reserved) + u64 *qgroup_reserved, + bool use_global_rsv) { u64 num_bytes; int ret; + struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv; if (root->fs_info->quota_enabled) { /* One for parent inode, two for dir entries */ @@ -4751,6 +4798,10 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, BTRFS_BLOCK_GROUP_METADATA); ret = btrfs_block_rsv_add(root, rsv, num_bytes, BTRFS_RESERVE_FLUSH_ALL); + + if (ret == -ENOSPC && use_global_rsv) + ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes); + if (ret) { if (*qgroup_reserved) btrfs_qgroup_free(root, *qgroup_reserved); @@ -5668,7 +5719,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (ret) { btrfs_err(info, "umm, got %d back from search, was looking for %llu", - ret, (unsigned long long)bytenr); + ret, bytenr); if (ret > 0) btrfs_print_leaf(extent_root, path->nodes[0]); @@ -5684,11 +5735,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, WARN_ON(1); btrfs_err(info, "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu", - (unsigned long long)bytenr, - (unsigned long long)parent, - (unsigned long long)root_objectid, - (unsigned long long)owner_objectid, - (unsigned long long)owner_offset); + bytenr, parent, root_objectid, owner_objectid, + owner_offset); } else { btrfs_abort_transaction(trans, extent_root, ret); goto out; @@ -5717,7 +5765,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, -1, 1); if (ret) { btrfs_err(info, "umm, got %d back from search, was looking for %llu", - ret, (unsigned long long)bytenr); + ret, bytenr); btrfs_print_leaf(extent_root, path->nodes[0]); } if (ret < 0) { @@ -5999,8 +6047,11 @@ static u64 stripe_align(struct btrfs_root *root, * for our min num_bytes. Another option is to have it go ahead * and look in the rbtree for a free extent of a given size, but this * is a good start. + * + * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using + * any of the information in this block group. */ -static noinline int +static noinline void wait_block_group_cache_progress(struct btrfs_block_group_cache *cache, u64 num_bytes) { @@ -6008,28 +6059,29 @@ wait_block_group_cache_progress(struct btrfs_block_group_cache *cache, caching_ctl = get_caching_control(cache); if (!caching_ctl) - return 0; + return; wait_event(caching_ctl->wait, block_group_cache_done(cache) || (cache->free_space_ctl->free_space >= num_bytes)); put_caching_control(caching_ctl); - return 0; } static noinline int wait_block_group_cache_done(struct btrfs_block_group_cache *cache) { struct btrfs_caching_control *caching_ctl; + int ret = 0; caching_ctl = get_caching_control(cache); if (!caching_ctl) - return 0; + return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0; wait_event(caching_ctl->wait, block_group_cache_done(cache)); - + if (cache->cached == BTRFS_CACHE_ERROR) + ret = -EIO; put_caching_control(caching_ctl); - return 0; + return ret; } int __get_raid_index(u64 flags) @@ -6070,8 +6122,7 @@ enum btrfs_loop_type { * ins->offset == number of blocks * Any available blocks before search_start are skipped. */ -static noinline int find_free_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *orig_root, +static noinline int find_free_extent(struct btrfs_root *orig_root, u64 num_bytes, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, u64 flags) @@ -6212,6 +6263,8 @@ have_block_group: ret = 0; } + if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) + goto loop; if (unlikely(block_group->ro)) goto loop; @@ -6292,10 +6345,10 @@ refill_cluster: block_group->full_stripe_len); /* allocate a cluster in this block group */ - ret = btrfs_find_space_cluster(trans, root, - block_group, last_ptr, - search_start, num_bytes, - aligned_cluster); + ret = btrfs_find_space_cluster(root, block_group, + last_ptr, search_start, + num_bytes, + aligned_cluster); if (ret == 0) { /* * now pull our allocation out of this @@ -6426,17 +6479,28 @@ loop: index = 0; loop++; if (loop == LOOP_ALLOC_CHUNK) { + struct btrfs_trans_handle *trans; + + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out; + } + ret = do_chunk_alloc(trans, root, flags, CHUNK_ALLOC_FORCE); /* * Do not bail out on ENOSPC since we * can do more things. */ - if (ret < 0 && ret != -ENOSPC) { + if (ret < 0 && ret != -ENOSPC) btrfs_abort_transaction(trans, root, ret); + else + ret = 0; + btrfs_end_transaction(trans, root); + if (ret) goto out; - } } if (loop == LOOP_NO_EMPTY_SIZE) { @@ -6463,19 +6527,15 @@ static void dump_space_info(struct btrfs_space_info *info, u64 bytes, spin_lock(&info->lock); printk(KERN_INFO "space_info %llu has %llu free, is %sfull\n", - (unsigned long long)info->flags, - (unsigned long long)(info->total_bytes - info->bytes_used - - info->bytes_pinned - info->bytes_reserved - - info->bytes_readonly), + info->flags, + info->total_bytes - info->bytes_used - info->bytes_pinned - + info->bytes_reserved - info->bytes_readonly, (info->full) ? "" : "not "); printk(KERN_INFO "space_info total=%llu, used=%llu, pinned=%llu, " "reserved=%llu, may_use=%llu, readonly=%llu\n", - (unsigned long long)info->total_bytes, - (unsigned long long)info->bytes_used, - (unsigned long long)info->bytes_pinned, - (unsigned long long)info->bytes_reserved, - (unsigned long long)info->bytes_may_use, - (unsigned long long)info->bytes_readonly); + info->total_bytes, info->bytes_used, info->bytes_pinned, + info->bytes_reserved, info->bytes_may_use, + info->bytes_readonly); spin_unlock(&info->lock); if (!dump_block_groups) @@ -6486,12 +6546,9 @@ again: list_for_each_entry(cache, &info->block_groups[index], list) { spin_lock(&cache->lock); printk(KERN_INFO "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s\n", - (unsigned long long)cache->key.objectid, - (unsigned long long)cache->key.offset, - (unsigned long long)btrfs_block_group_used(&cache->item), - (unsigned long long)cache->pinned, - (unsigned long long)cache->reserved, - cache->ro ? "[readonly]" : ""); + cache->key.objectid, cache->key.offset, + btrfs_block_group_used(&cache->item), cache->pinned, + cache->reserved, cache->ro ? "[readonly]" : ""); btrfs_dump_free_space(cache, bytes); spin_unlock(&cache->lock); } @@ -6500,8 +6557,7 @@ again: up_read(&info->groups_sem); } -int btrfs_reserve_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data) @@ -6513,8 +6569,8 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans, flags = btrfs_get_alloc_profile(root, is_data); again: WARN_ON(num_bytes < root->sectorsize); - ret = find_free_extent(trans, root, num_bytes, empty_size, - hint_byte, ins, flags); + ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, + flags); if (ret == -ENOSPC) { if (!final_tried) { @@ -6529,8 +6585,7 @@ again: sinfo = __find_space_info(root->fs_info, flags); btrfs_err(root->fs_info, "allocation failed flags %llu, wanted %llu", - (unsigned long long)flags, - (unsigned long long)num_bytes); + flags, num_bytes); if (sinfo) dump_space_info(sinfo, num_bytes, 1); } @@ -6550,7 +6605,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, cache = btrfs_lookup_block_group(root->fs_info, start); if (!cache) { btrfs_err(root->fs_info, "Unable to find block group for %llu", - (unsigned long long)start); + start); return -ENOSPC; } @@ -6646,8 +6701,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ret = update_block_group(root, ins->objectid, ins->offset, 1); if (ret) { /* -ENOENT, logic error */ btrfs_err(fs_info, "update block group failed for %llu %llu", - (unsigned long long)ins->objectid, - (unsigned long long)ins->offset); + ins->objectid, ins->offset); BUG(); } return ret; @@ -6719,8 +6773,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, ret = update_block_group(root, ins->objectid, root->leafsize, 1); if (ret) { /* -ENOENT, logic error */ btrfs_err(fs_info, "update block group failed for %llu %llu", - (unsigned long long)ins->objectid, - (unsigned long long)ins->offset); + ins->objectid, ins->offset); BUG(); } return ret; @@ -6902,7 +6955,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, if (IS_ERR(block_rsv)) return ERR_CAST(block_rsv); - ret = btrfs_reserve_extent(trans, root, blocksize, blocksize, + ret = btrfs_reserve_extent(root, blocksize, blocksize, empty_size, hint, &ins, 0); if (ret) { unuse_block_rsv(root->fs_info, block_rsv, blocksize); @@ -7173,6 +7226,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, next = btrfs_find_create_tree_block(root, bytenr, blocksize); if (!next) return -ENOMEM; + btrfs_set_buffer_lockdep_class(root->root_key.objectid, next, + level - 1); reada = 1; } btrfs_tree_lock(next); @@ -7466,6 +7521,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int err = 0; int ret; int level; + bool root_dropped = false; path = btrfs_alloc_path(); if (!path) { @@ -7523,6 +7579,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, while (1) { btrfs_tree_lock(path->nodes[level]); btrfs_set_lock_blocking(path->nodes[level]); + path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; ret = btrfs_lookup_extent_info(trans, root, path->nodes[level]->start, @@ -7538,6 +7595,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, break; btrfs_tree_unlock(path->nodes[level]); + path->locks[level] = 0; WARN_ON(wc->refs[level] != 1); level--; } @@ -7552,11 +7610,6 @@ int btrfs_drop_snapshot(struct btrfs_root *root, wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root); while (1) { - if (!for_reloc && btrfs_need_cleaner_sleep(root)) { - pr_debug("btrfs: drop snapshot early exit\n"); - err = -EAGAIN; - goto out_end_trans; - } ret = walk_down_tree(trans, root, path, wc); if (ret < 0) { @@ -7584,7 +7637,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } BUG_ON(wc->level == 0); - if (btrfs_should_end_transaction(trans, tree_root)) { + if (btrfs_should_end_transaction(trans, tree_root) || + (!for_reloc && btrfs_need_cleaner_sleep(root))) { ret = btrfs_update_root(trans, tree_root, &root->root_key, root_item); @@ -7595,6 +7649,12 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } btrfs_end_transaction_throttle(trans, tree_root); + if (!for_reloc && btrfs_need_cleaner_sleep(root)) { + pr_debug("btrfs: drop snapshot early exit\n"); + err = -EAGAIN; + goto out_free; + } + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -7639,12 +7699,22 @@ int btrfs_drop_snapshot(struct btrfs_root *root, free_extent_buffer(root->commit_root); btrfs_put_fs_root(root); } + root_dropped = true; out_end_trans: btrfs_end_transaction_throttle(trans, tree_root); out_free: kfree(wc); btrfs_free_path(path); out: + /* + * So if we need to stop dropping the snapshot for whatever reason we + * need to make sure to add it back to the dead root list so that we + * keep trying to do the work later. This also cleans up roots if we + * don't have it in the radix (like when we recover after a power fail + * or unmount) so we don't leak memory. + */ + if (!for_reloc && root_dropped == false) + btrfs_add_dead_root(root); if (err) btrfs_std_error(root->fs_info, err); return err; @@ -8177,7 +8247,8 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) * We haven't cached this block group, which means we could * possibly have excluded extents on this block group. */ - if (block_group->cached == BTRFS_CACHE_NO) + if (block_group->cached == BTRFS_CACHE_NO || + block_group->cached == BTRFS_CACHE_ERROR) free_excluded_extents(info->extent_root, block_group); btrfs_remove_free_space_cache(block_group); @@ -8394,9 +8465,13 @@ int btrfs_read_block_groups(struct btrfs_root *root) * avoid allocating from un-mirrored block group if there are * mirrored block groups. */ - list_for_each_entry(cache, &space_info->block_groups[3], list) + list_for_each_entry(cache, + &space_info->block_groups[BTRFS_RAID_RAID0], + list) set_block_group_ro(cache, 1); - list_for_each_entry(cache, &space_info->block_groups[4], list) + list_for_each_entry(cache, + &space_info->block_groups[BTRFS_RAID_SINGLE], + list) set_block_group_ro(cache, 1); } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 583d98b..09582b8 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -61,9 +61,8 @@ void btrfs_leak_debug_check(void) state = list_entry(states.next, struct extent_state, leak_list); printk(KERN_ERR "btrfs state leak: start %llu end %llu " "state %lu in tree %p refs %d\n", - (unsigned long long)state->start, - (unsigned long long)state->end, - state->state, state->tree, atomic_read(&state->refs)); + state->start, state->end, state->state, state->tree, + atomic_read(&state->refs)); list_del(&state->leak_list); kmem_cache_free(extent_state_cache, state); } @@ -71,8 +70,8 @@ void btrfs_leak_debug_check(void) while (!list_empty(&buffers)) { eb = list_entry(buffers.next, struct extent_buffer, leak_list); printk(KERN_ERR "btrfs buffer leak start %llu len %lu " - "refs %d\n", (unsigned long long)eb->start, - eb->len, atomic_read(&eb->refs)); + "refs %d\n", + eb->start, eb->len, atomic_read(&eb->refs)); list_del(&eb->leak_list); kmem_cache_free(extent_buffer_cache, eb); } @@ -88,11 +87,7 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller, if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { printk_ratelimited(KERN_DEBUG "btrfs: %s: ino %llu isize %llu odd range [%llu,%llu]\n", - caller, - (unsigned long long)btrfs_ino(inode), - (unsigned long long)isize, - (unsigned long long)start, - (unsigned long long)end); + caller, btrfs_ino(inode), isize, start, end); } } #else @@ -388,8 +383,7 @@ static int insert_state(struct extent_io_tree *tree, if (end < start) WARN(1, KERN_ERR "btrfs end < start %llu %llu\n", - (unsigned long long)end, - (unsigned long long)start); + end, start); state->start = start; state->end = end; @@ -400,9 +394,8 @@ static int insert_state(struct extent_io_tree *tree, struct extent_state *found; found = rb_entry(node, struct extent_state, rb_node); printk(KERN_ERR "btrfs found node %llu %llu on insert of " - "%llu %llu\n", (unsigned long long)found->start, - (unsigned long long)found->end, - (unsigned long long)start, (unsigned long long)end); + "%llu %llu\n", + found->start, found->end, start, end); return -EEXIST; } state->tree = tree; @@ -762,15 +755,6 @@ static void cache_state(struct extent_state *state, } } -static void uncache_state(struct extent_state **cached_ptr) -{ - if (cached_ptr && (*cached_ptr)) { - struct extent_state *state = *cached_ptr; - *cached_ptr = NULL; - free_extent_state(state); - } -} - /* * set some bits on a range in the tree. This may require allocations or * sleeping, so the gfp mask is used to indicate what is allowed. @@ -1687,31 +1671,21 @@ out_failed: return found; } -int extent_clear_unlock_delalloc(struct inode *inode, - struct extent_io_tree *tree, - u64 start, u64 end, struct page *locked_page, - unsigned long op) +int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, + struct page *locked_page, + unsigned long clear_bits, + unsigned long page_ops) { + struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; int ret; struct page *pages[16]; unsigned long index = start >> PAGE_CACHE_SHIFT; unsigned long end_index = end >> PAGE_CACHE_SHIFT; unsigned long nr_pages = end_index - index + 1; int i; - unsigned long clear_bits = 0; - - if (op & EXTENT_CLEAR_UNLOCK) - clear_bits |= EXTENT_LOCKED; - if (op & EXTENT_CLEAR_DIRTY) - clear_bits |= EXTENT_DIRTY; - - if (op & EXTENT_CLEAR_DELALLOC) - clear_bits |= EXTENT_DELALLOC; clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS); - if (!(op & (EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | EXTENT_END_WRITEBACK | - EXTENT_SET_PRIVATE2))) + if (page_ops == 0) return 0; while (nr_pages > 0) { @@ -1720,20 +1694,20 @@ int extent_clear_unlock_delalloc(struct inode *inode, nr_pages, ARRAY_SIZE(pages)), pages); for (i = 0; i < ret; i++) { - if (op & EXTENT_SET_PRIVATE2) + if (page_ops & PAGE_SET_PRIVATE2) SetPagePrivate2(pages[i]); if (pages[i] == locked_page) { page_cache_release(pages[i]); continue; } - if (op & EXTENT_CLEAR_DIRTY) + if (page_ops & PAGE_CLEAR_DIRTY) clear_page_dirty_for_io(pages[i]); - if (op & EXTENT_SET_WRITEBACK) + if (page_ops & PAGE_SET_WRITEBACK) set_page_writeback(pages[i]); - if (op & EXTENT_END_WRITEBACK) + if (page_ops & PAGE_END_WRITEBACK) end_page_writeback(pages[i]); - if (op & EXTENT_CLEAR_UNLOCK_PAGE) + if (page_ops & PAGE_UNLOCK) unlock_page(pages[i]); page_cache_release(pages[i]); } @@ -1810,7 +1784,7 @@ out: * set the private field for a given byte offset in the tree. If there isn't * an extent_state there already, this does nothing. */ -int set_state_private(struct extent_io_tree *tree, u64 start, u64 private) +static int set_state_private(struct extent_io_tree *tree, u64 start, u64 private) { struct rb_node *node; struct extent_state *state; @@ -1837,64 +1811,6 @@ out: return ret; } -void extent_cache_csums_dio(struct extent_io_tree *tree, u64 start, u32 csums[], - int count) -{ - struct rb_node *node; - struct extent_state *state; - - spin_lock(&tree->lock); - /* - * this search will find all the extents that end after - * our range starts. - */ - node = tree_search(tree, start); - BUG_ON(!node); - - state = rb_entry(node, struct extent_state, rb_node); - BUG_ON(state->start != start); - - while (count) { - state->private = *csums++; - count--; - state = next_state(state); - } - spin_unlock(&tree->lock); -} - -static inline u64 __btrfs_get_bio_offset(struct bio *bio, int bio_index) -{ - struct bio_vec *bvec = bio->bi_io_vec + bio_index; - - return page_offset(bvec->bv_page) + bvec->bv_offset; -} - -void extent_cache_csums(struct extent_io_tree *tree, struct bio *bio, int bio_index, - u32 csums[], int count) -{ - struct rb_node *node; - struct extent_state *state = NULL; - u64 start; - - spin_lock(&tree->lock); - do { - start = __btrfs_get_bio_offset(bio, bio_index); - if (state == NULL || state->start != start) { - node = tree_search(tree, start); - BUG_ON(!node); - - state = rb_entry(node, struct extent_state, rb_node); - BUG_ON(state->start != start); - } - state->private = *csums++; - count--; - bio_index++; - - state = next_state(state); - } while (count); - spin_unlock(&tree->lock); -} - int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private) { struct rb_node *node; @@ -2173,7 +2089,8 @@ static int clean_io_failure(u64 start, struct page *page) EXTENT_LOCKED); spin_unlock(&BTRFS_I(inode)->io_tree.lock); - if (state && state->start == failrec->start) { + if (state && state->start <= failrec->start && + state->end >= failrec->start + failrec->len - 1) { fs_info = BTRFS_I(inode)->root->fs_info; num_copies = btrfs_num_copies(fs_info, failrec->logical, failrec->len); @@ -2201,9 +2118,9 @@ out: * needed */ -static int bio_readpage_error(struct bio *failed_bio, struct page *page, - u64 start, u64 end, int failed_mirror, - struct extent_state *state) +static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, + struct page *page, u64 start, u64 end, + int failed_mirror) { struct io_failure_record *failrec = NULL; u64 private; @@ -2213,6 +2130,8 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page, struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; struct bio *bio; + struct btrfs_io_bio *btrfs_failed_bio; + struct btrfs_io_bio *btrfs_bio; int num_copies; int ret; int read_mode; @@ -2296,23 +2215,12 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page, * all the retry and error correction code that follows. no * matter what the error is, it is very likely to persist. */ - pr_debug("bio_readpage_error: cannot repair, num_copies == 1. " - "state=%p, num_copies=%d, next_mirror %d, " - "failed_mirror %d\n", state, num_copies, - failrec->this_mirror, failed_mirror); + pr_debug("bio_readpage_error: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d\n", + num_copies, failrec->this_mirror, failed_mirror); free_io_failure(inode, failrec, 0); return -EIO; } - if (!state) { - spin_lock(&tree->lock); - state = find_first_extent_bit_state(tree, failrec->start, - EXTENT_LOCKED); - if (state && state->start != failrec->start) - state = NULL; - spin_unlock(&tree->lock); - } - /* * there are two premises: * a) deliver good data to the caller @@ -2349,9 +2257,8 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page, read_mode = READ_SYNC; } - if (!state || failrec->this_mirror > num_copies) { - pr_debug("bio_readpage_error: (fail) state=%p, num_copies=%d, " - "next_mirror %d, failed_mirror %d\n", state, + if (failrec->this_mirror > num_copies) { + pr_debug("bio_readpage_error: (fail) num_copies=%d, next_mirror %d, failed_mirror %d\n", num_copies, failrec->this_mirror, failed_mirror); free_io_failure(inode, failrec, 0); return -EIO; @@ -2362,12 +2269,24 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page, free_io_failure(inode, failrec, 0); return -EIO; } - bio->bi_private = state; bio->bi_end_io = failed_bio->bi_end_io; bio->bi_sector = failrec->logical >> 9; bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev; bio->bi_size = 0; + btrfs_failed_bio = btrfs_io_bio(failed_bio); + if (btrfs_failed_bio->csum) { + struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + + btrfs_bio = btrfs_io_bio(bio); + btrfs_bio->csum = btrfs_bio->csum_inline; + phy_offset >>= inode->i_sb->s_blocksize_bits; + phy_offset *= csum_size; + memcpy(btrfs_bio->csum, btrfs_failed_bio->csum + phy_offset, + csum_size); + } + bio_add_page(bio, page, failrec->len, start - page_offset(page)); pr_debug("bio_readpage_error: submitting new read[%#x] to " @@ -2450,6 +2369,18 @@ static void end_bio_extent_writepage(struct bio *bio, int err) bio_put(bio); } +static void +endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len, + int uptodate) +{ + struct extent_state *cached = NULL; + u64 end = start + len - 1; + + if (uptodate && tree->track_uptodate) + set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC); + unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC); +} + /* * after a readpage IO is done, we need to: * clear the uptodate bits on error @@ -2466,9 +2397,14 @@ static void end_bio_extent_readpage(struct bio *bio, int err) int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1; struct bio_vec *bvec = bio->bi_io_vec; + struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct extent_io_tree *tree; + u64 offset = 0; u64 start; u64 end; + u64 len; + u64 extent_start = 0; + u64 extent_len = 0; int mirror; int ret; @@ -2477,9 +2413,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err) do { struct page *page = bvec->bv_page; - struct extent_state *cached = NULL; - struct extent_state *state; - struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct inode *inode = page->mapping->host; pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, " @@ -2500,37 +2433,32 @@ static void end_bio_extent_readpage(struct bio *bio, int err) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; + len = bvec->bv_len; if (++bvec <= bvec_end) prefetchw(&bvec->bv_page->flags); - spin_lock(&tree->lock); - state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED); - if (state && state->start == start) { - /* - * take a reference on the state, unlock will drop - * the ref - */ - cache_state(state, &cached); - } - spin_unlock(&tree->lock); - mirror = io_bio->mirror_num; - if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { - ret = tree->ops->readpage_end_io_hook(page, start, end, - state, mirror); + if (likely(uptodate && tree->ops && + tree->ops->readpage_end_io_hook)) { + ret = tree->ops->readpage_end_io_hook(io_bio, offset, + page, start, end, + mirror); if (ret) uptodate = 0; else clean_io_failure(start, page); } - if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) { + if (likely(uptodate)) + goto readpage_ok; + + if (tree->ops && tree->ops->readpage_io_failed_hook) { ret = tree->ops->readpage_io_failed_hook(page, mirror); if (!ret && !err && test_bit(BIO_UPTODATE, &bio->bi_flags)) uptodate = 1; - } else if (!uptodate) { + } else { /* * The generic bio_readpage_error handles errors the * following way: If possible, new read requests are @@ -2541,24 +2469,18 @@ static void end_bio_extent_readpage(struct bio *bio, int err) * can't handle the error it will return -EIO and we * remain responsible for that page. */ - ret = bio_readpage_error(bio, page, start, end, mirror, NULL); + ret = bio_readpage_error(bio, offset, page, start, end, + mirror); if (ret == 0) { uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); if (err) uptodate = 0; - uncache_state(&cached); continue; } } - - if (uptodate && tree->track_uptodate) { - set_extent_uptodate(tree, start, end, &cached, - GFP_ATOMIC); - } - unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC); - - if (uptodate) { +readpage_ok: + if (likely(uptodate)) { loff_t i_size = i_size_read(inode); pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; unsigned offset; @@ -2573,8 +2495,36 @@ static void end_bio_extent_readpage(struct bio *bio, int err) SetPageError(page); } unlock_page(page); + offset += len; + + if (unlikely(!uptodate)) { + if (extent_len) { + endio_readpage_release_extent(tree, + extent_start, + extent_len, 1); + extent_start = 0; + extent_len = 0; + } + endio_readpage_release_extent(tree, start, + end - start + 1, 0); + } else if (!extent_len) { + extent_start = start; + extent_len = end + 1 - start; + } else if (extent_start + extent_len == start) { + extent_len += end + 1 - start; + } else { + endio_readpage_release_extent(tree, extent_start, + extent_len, uptodate); + extent_start = start; + extent_len = end + 1 - start; + } } while (bvec <= bvec_end); + if (extent_len) + endio_readpage_release_extent(tree, extent_start, extent_len, + uptodate); + if (io_bio->end_io) + io_bio->end_io(io_bio, err); bio_put(bio); } @@ -2586,6 +2536,7 @@ struct bio * btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, gfp_t gfp_flags) { + struct btrfs_io_bio *btrfs_bio; struct bio *bio; bio = bio_alloc_bioset(gfp_flags, nr_vecs, btrfs_bioset); @@ -2601,6 +2552,10 @@ btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, bio->bi_size = 0; bio->bi_bdev = bdev; bio->bi_sector = first_sector; + btrfs_bio = btrfs_io_bio(bio); + btrfs_bio->csum = NULL; + btrfs_bio->csum_allocated = NULL; + btrfs_bio->end_io = NULL; } return bio; } @@ -2614,7 +2569,17 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) /* this also allocates from the btrfs_bioset */ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) { - return bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset); + struct btrfs_io_bio *btrfs_bio; + struct bio *bio; + + bio = bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset); + if (bio) { + btrfs_bio = btrfs_io_bio(bio); + btrfs_bio->csum = NULL; + btrfs_bio->csum_allocated = NULL; + btrfs_bio->end_io = NULL; + } + return bio; } @@ -2738,17 +2703,45 @@ void set_page_extent_mapped(struct page *page) } } +static struct extent_map * +__get_extent_map(struct inode *inode, struct page *page, size_t pg_offset, + u64 start, u64 len, get_extent_t *get_extent, + struct extent_map **em_cached) +{ + struct extent_map *em; + + if (em_cached && *em_cached) { + em = *em_cached; + if (em->in_tree && start >= em->start && + start < extent_map_end(em)) { + atomic_inc(&em->refs); + return em; + } + + free_extent_map(em); + *em_cached = NULL; + } + + em = get_extent(inode, page, pg_offset, start, len, 0); + if (em_cached && !IS_ERR_OR_NULL(em)) { + BUG_ON(*em_cached); + atomic_inc(&em->refs); + *em_cached = em; + } + return em; +} /* * basic readpage implementation. Locked extent state structs are inserted * into the tree that are removed when the IO is done (by the end_io * handlers) * XXX JDM: This needs looking at to ensure proper page locking */ -static int __extent_read_full_page(struct extent_io_tree *tree, - struct page *page, - get_extent_t *get_extent, - struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) +static int __do_readpage(struct extent_io_tree *tree, + struct page *page, + get_extent_t *get_extent, + struct extent_map **em_cached, + struct bio **bio, int mirror_num, + unsigned long *bio_flags, int rw) { struct inode *inode = page->mapping->host; u64 start = page_offset(page); @@ -2762,35 +2755,26 @@ static int __extent_read_full_page(struct extent_io_tree *tree, sector_t sector; struct extent_map *em; struct block_device *bdev; - struct btrfs_ordered_extent *ordered; int ret; int nr = 0; + int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED; size_t pg_offset = 0; size_t iosize; size_t disk_io_size; size_t blocksize = inode->i_sb->s_blocksize; - unsigned long this_bio_flag = 0; + unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED; set_page_extent_mapped(page); + end = page_end; if (!PageUptodate(page)) { if (cleancache_get_page(page) == 0) { BUG_ON(blocksize != PAGE_SIZE); + unlock_extent(tree, start, end); goto out; } } - end = page_end; - while (1) { - lock_extent(tree, start, end); - ordered = btrfs_lookup_ordered_extent(inode, start); - if (!ordered) - break; - unlock_extent(tree, start, end); - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); - } - if (page->index == last_byte >> PAGE_CACHE_SHIFT) { char *userpage; size_t zero_offset = last_byte & (PAGE_CACHE_SIZE - 1); @@ -2817,15 +2801,18 @@ static int __extent_read_full_page(struct extent_io_tree *tree, kunmap_atomic(userpage); set_extent_uptodate(tree, cur, cur + iosize - 1, &cached, GFP_NOFS); - unlock_extent_cached(tree, cur, cur + iosize - 1, - &cached, GFP_NOFS); + if (!parent_locked) + unlock_extent_cached(tree, cur, + cur + iosize - 1, + &cached, GFP_NOFS); break; } - em = get_extent(inode, page, pg_offset, cur, - end - cur + 1, 0); + em = __get_extent_map(inode, page, pg_offset, cur, + end - cur + 1, get_extent, em_cached); if (IS_ERR_OR_NULL(em)) { SetPageError(page); - unlock_extent(tree, cur, end); + if (!parent_locked) + unlock_extent(tree, cur, end); break; } extent_offset = cur - em->start; @@ -2833,7 +2820,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree, BUG_ON(end < cur); if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) { - this_bio_flag = EXTENT_BIO_COMPRESSED; + this_bio_flag |= EXTENT_BIO_COMPRESSED; extent_set_compress_type(&this_bio_flag, em->compress_type); } @@ -2877,7 +2864,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree, if (test_range_bit(tree, cur, cur_end, EXTENT_UPTODATE, 1, NULL)) { check_page_uptodate(tree, page); - unlock_extent(tree, cur, cur + iosize - 1); + if (!parent_locked) + unlock_extent(tree, cur, cur + iosize - 1); cur = cur + iosize; pg_offset += iosize; continue; @@ -2887,7 +2875,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree, */ if (block_start == EXTENT_MAP_INLINE) { SetPageError(page); - unlock_extent(tree, cur, cur + iosize - 1); + if (!parent_locked) + unlock_extent(tree, cur, cur + iosize - 1); cur = cur + iosize; pg_offset += iosize; continue; @@ -2905,7 +2894,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree, *bio_flags = this_bio_flag; } else { SetPageError(page); - unlock_extent(tree, cur, cur + iosize - 1); + if (!parent_locked) + unlock_extent(tree, cur, cur + iosize - 1); } cur = cur + iosize; pg_offset += iosize; @@ -2919,6 +2909,104 @@ out: return 0; } +static inline void __do_contiguous_readpages(struct extent_io_tree *tree, + struct page *pages[], int nr_pages, + u64 start, u64 end, + get_extent_t *get_extent, + struct extent_map **em_cached, + struct bio **bio, int mirror_num, + unsigned long *bio_flags, int rw) +{ + struct inode *inode; + struct btrfs_ordered_extent *ordered; + int index; + + inode = pages[0]->mapping->host; + while (1) { + lock_extent(tree, start, end); + ordered = btrfs_lookup_ordered_range(inode, start, + end - start + 1); + if (!ordered) + break; + unlock_extent(tree, start, end); + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } + + for (index = 0; index < nr_pages; index++) { + __do_readpage(tree, pages[index], get_extent, em_cached, bio, + mirror_num, bio_flags, rw); + page_cache_release(pages[index]); + } +} + +static void __extent_readpages(struct extent_io_tree *tree, + struct page *pages[], + int nr_pages, get_extent_t *get_extent, + struct extent_map **em_cached, + struct bio **bio, int mirror_num, + unsigned long *bio_flags, int rw) +{ + u64 start = 0; + u64 end = 0; + u64 page_start; + int index; + int first_index = 0; + + for (index = 0; index < nr_pages; index++) { + page_start = page_offset(pages[index]); + if (!end) { + start = page_start; + end = start + PAGE_CACHE_SIZE - 1; + first_index = index; + } else if (end + 1 == page_start) { + end += PAGE_CACHE_SIZE; + } else { + __do_contiguous_readpages(tree, &pages[first_index], + index - first_index, start, + end, get_extent, em_cached, + bio, mirror_num, bio_flags, + rw); + start = page_start; + end = start + PAGE_CACHE_SIZE - 1; + first_index = index; + } + } + + if (end) + __do_contiguous_readpages(tree, &pages[first_index], + index - first_index, start, + end, get_extent, em_cached, bio, + mirror_num, bio_flags, rw); +} + +static int __extent_read_full_page(struct extent_io_tree *tree, + struct page *page, + get_extent_t *get_extent, + struct bio **bio, int mirror_num, + unsigned long *bio_flags, int rw) +{ + struct inode *inode = page->mapping->host; + struct btrfs_ordered_extent *ordered; + u64 start = page_offset(page); + u64 end = start + PAGE_CACHE_SIZE - 1; + int ret; + + while (1) { + lock_extent(tree, start, end); + ordered = btrfs_lookup_ordered_extent(inode, start); + if (!ordered) + break; + unlock_extent(tree, start, end); + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } + + ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num, + bio_flags, rw); + return ret; +} + int extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, int mirror_num) { @@ -2933,6 +3021,20 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page, return ret; } +int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, + get_extent_t *get_extent, int mirror_num) +{ + struct bio *bio = NULL; + unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED; + int ret; + + ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num, + &bio_flags, READ); + if (bio) + ret = submit_one_bio(READ, bio, mirror_num, bio_flags); + return ret; +} + static noinline void update_nr_written(struct page *page, struct writeback_control *wbc, unsigned long nr_written) @@ -3189,8 +3291,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, if (!PageWriteback(page)) { printk(KERN_ERR "btrfs warning page %lu not " "writeback, cur %llu end %llu\n", - page->index, (unsigned long long)cur, - (unsigned long long)end); + page->index, cur, end); } ret = submit_extent_page(write_flags, tree, page, @@ -3769,7 +3870,7 @@ int extent_readpages(struct extent_io_tree *tree, unsigned long bio_flags = 0; struct page *pagepool[16]; struct page *page; - int i = 0; + struct extent_map *em_cached = NULL; int nr = 0; for (page_idx = 0; page_idx < nr_pages; page_idx++) { @@ -3786,18 +3887,16 @@ int extent_readpages(struct extent_io_tree *tree, pagepool[nr++] = page; if (nr < ARRAY_SIZE(pagepool)) continue; - for (i = 0; i < nr; i++) { - __extent_read_full_page(tree, pagepool[i], get_extent, - &bio, 0, &bio_flags, READ); - page_cache_release(pagepool[i]); - } + __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, + &bio, 0, &bio_flags, READ); nr = 0; } - for (i = 0; i < nr; i++) { - __extent_read_full_page(tree, pagepool[i], get_extent, - &bio, 0, &bio_flags, READ); - page_cache_release(pagepool[i]); - } + if (nr) + __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, + &bio, 0, &bio_flags, READ); + + if (em_cached) + free_extent_map(em_cached); BUG_ON(!list_empty(pages)); if (bio) @@ -4048,7 +4147,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } while (!end) { - u64 offset_in_extent; + u64 offset_in_extent = 0; /* break if the extent we found is outside the range */ if (em->start >= max || extent_map_end(em) < off) @@ -4064,9 +4163,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* * record the offset from the start of the extent - * for adjusting the disk offset below + * for adjusting the disk offset below. Only do this if the + * extent isn't compressed since our in ram offset may be past + * what we have actually allocated on disk. */ - offset_in_extent = em_start - em->start; + if (!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) + offset_in_extent = em_start - em->start; em_end = extent_map_end(em); em_len = em_end - em_start; emflags = em->flags; @@ -4133,6 +4235,76 @@ static void __free_extent_buffer(struct extent_buffer *eb) kmem_cache_free(extent_buffer_cache, eb); } +static int extent_buffer_under_io(struct extent_buffer *eb) +{ + return (atomic_read(&eb->io_pages) || + test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || + test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); +} + +/* + * Helper for releasing extent buffer page. + */ +static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, + unsigned long start_idx) +{ + unsigned long index; + unsigned long num_pages; + struct page *page; + int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags); + + BUG_ON(extent_buffer_under_io(eb)); + + num_pages = num_extent_pages(eb->start, eb->len); + index = start_idx + num_pages; + if (start_idx >= index) + return; + + do { + index--; + page = extent_buffer_page(eb, index); + if (page && mapped) { + spin_lock(&page->mapping->private_lock); + /* + * We do this since we'll remove the pages after we've + * removed the eb from the radix tree, so we could race + * and have this page now attached to the new eb. So + * only clear page_private if it's still connected to + * this eb. + */ + if (PagePrivate(page) && + page->private == (unsigned long)eb) { + BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + BUG_ON(PageDirty(page)); + BUG_ON(PageWriteback(page)); + /* + * We need to make sure we haven't be attached + * to a new eb. + */ + ClearPagePrivate(page); + set_page_private(page, 0); + /* One for the page private */ + page_cache_release(page); + } + spin_unlock(&page->mapping->private_lock); + + } + if (page) { + /* One for when we alloced the page */ + page_cache_release(page); + } + } while (index != start_idx); +} + +/* + * Helper for releasing the extent buffer. + */ +static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) +{ + btrfs_release_extent_buffer_page(eb, 0); + __free_extent_buffer(eb); +} + static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree, u64 start, unsigned long len, @@ -4181,13 +4353,16 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src) struct extent_buffer *new; unsigned long num_pages = num_extent_pages(src->start, src->len); - new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_ATOMIC); + new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_NOFS); if (new == NULL) return NULL; for (i = 0; i < num_pages; i++) { - p = alloc_page(GFP_ATOMIC); - BUG_ON(!p); + p = alloc_page(GFP_NOFS); + if (!p) { + btrfs_release_extent_buffer(new); + return NULL; + } attach_extent_buffer_page(new, p); WARN_ON(PageDirty(p)); SetPageUptodate(p); @@ -4207,12 +4382,12 @@ struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len) unsigned long num_pages = num_extent_pages(0, len); unsigned long i; - eb = __alloc_extent_buffer(NULL, start, len, GFP_ATOMIC); + eb = __alloc_extent_buffer(NULL, start, len, GFP_NOFS); if (!eb) return NULL; for (i = 0; i < num_pages; i++) { - eb->pages[i] = alloc_page(GFP_ATOMIC); + eb->pages[i] = alloc_page(GFP_NOFS); if (!eb->pages[i]) goto err; } @@ -4228,76 +4403,6 @@ err: return NULL; } -static int extent_buffer_under_io(struct extent_buffer *eb) -{ - return (atomic_read(&eb->io_pages) || - test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || - test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); -} - -/* - * Helper for releasing extent buffer page. - */ -static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, - unsigned long start_idx) -{ - unsigned long index; - unsigned long num_pages; - struct page *page; - int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags); - - BUG_ON(extent_buffer_under_io(eb)); - - num_pages = num_extent_pages(eb->start, eb->len); - index = start_idx + num_pages; - if (start_idx >= index) - return; - - do { - index--; - page = extent_buffer_page(eb, index); - if (page && mapped) { - spin_lock(&page->mapping->private_lock); - /* - * We do this since we'll remove the pages after we've - * removed the eb from the radix tree, so we could race - * and have this page now attached to the new eb. So - * only clear page_private if it's still connected to - * this eb. - */ - if (PagePrivate(page) && - page->private == (unsigned long)eb) { - BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); - BUG_ON(PageDirty(page)); - BUG_ON(PageWriteback(page)); - /* - * We need to make sure we haven't be attached - * to a new eb. - */ - ClearPagePrivate(page); - set_page_private(page, 0); - /* One for the page private */ - page_cache_release(page); - } - spin_unlock(&page->mapping->private_lock); - - } - if (page) { - /* One for when we alloced the page */ - page_cache_release(page); - } - } while (index != start_idx); -} - -/* - * Helper for releasing the extent buffer. - */ -static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) -{ - btrfs_release_extent_buffer_page(eb, 0); - __free_extent_buffer(eb); -} - static void check_buffer_tree_ref(struct extent_buffer *eb) { int refs; @@ -4768,7 +4873,7 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv, WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); while (len > 0) { page = extent_buffer_page(eb, i); @@ -4810,8 +4915,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, if (start + min_len > eb->len) { WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, " - "wanted %lu %lu\n", (unsigned long long)eb->start, - eb->len, start, min_len); + "wanted %lu %lu\n", + eb->start, eb->len, start, min_len); return -EINVAL; } @@ -4838,7 +4943,7 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv, WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); while (len > 0) { page = extent_buffer_page(eb, i); @@ -4872,7 +4977,7 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv, WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); while (len > 0) { page = extent_buffer_page(eb, i); @@ -4902,7 +5007,7 @@ void memset_extent_buffer(struct extent_buffer *eb, char c, WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = (start_offset + start) & ((unsigned long)PAGE_CACHE_SIZE - 1); + offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); while (len > 0) { page = extent_buffer_page(eb, i); @@ -4933,7 +5038,7 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src, WARN_ON(src->len != dst_len); offset = (start_offset + dst_offset) & - ((unsigned long)PAGE_CACHE_SIZE - 1); + (PAGE_CACHE_SIZE - 1); while (len > 0) { page = extent_buffer_page(dst, i); @@ -5019,9 +5124,9 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, while (len > 0) { dst_off_in_page = (start_offset + dst_offset) & - ((unsigned long)PAGE_CACHE_SIZE - 1); + (PAGE_CACHE_SIZE - 1); src_off_in_page = (start_offset + src_offset) & - ((unsigned long)PAGE_CACHE_SIZE - 1); + (PAGE_CACHE_SIZE - 1); dst_i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT; src_i = (start_offset + src_offset) >> PAGE_CACHE_SHIFT; @@ -5072,9 +5177,9 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, src_i = (start_offset + src_end) >> PAGE_CACHE_SHIFT; dst_off_in_page = (start_offset + dst_end) & - ((unsigned long)PAGE_CACHE_SIZE - 1); + (PAGE_CACHE_SIZE - 1); src_off_in_page = (start_offset + src_end) & - ((unsigned long)PAGE_CACHE_SIZE - 1); + (PAGE_CACHE_SIZE - 1); cur = min_t(unsigned long, len, src_off_in_page + 1); cur = min(cur, dst_off_in_page + 1); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 3b8c4e2..6dbc645 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -29,6 +29,7 @@ */ #define EXTENT_BIO_COMPRESSED 1 #define EXTENT_BIO_TREE_LOG 2 +#define EXTENT_BIO_PARENT_LOCKED 4 #define EXTENT_BIO_FLAG_SHIFT 16 /* these are bit numbers for test/set bit */ @@ -44,14 +45,11 @@ #define EXTENT_BUFFER_DUMMY 9 /* these are flags for extent_clear_unlock_delalloc */ -#define EXTENT_CLEAR_UNLOCK_PAGE 0x1 -#define EXTENT_CLEAR_UNLOCK 0x2 -#define EXTENT_CLEAR_DELALLOC 0x4 -#define EXTENT_CLEAR_DIRTY 0x8 -#define EXTENT_SET_WRITEBACK 0x10 -#define EXTENT_END_WRITEBACK 0x20 -#define EXTENT_SET_PRIVATE2 0x40 -#define EXTENT_CLEAR_ACCOUNTING 0x80 +#define PAGE_UNLOCK (1 << 0) +#define PAGE_CLEAR_DIRTY (1 << 1) +#define PAGE_SET_WRITEBACK (1 << 2) +#define PAGE_END_WRITEBACK (1 << 3) +#define PAGE_SET_PRIVATE2 (1 << 4) /* * page->private values. Every page that is controlled by the extent @@ -62,6 +60,7 @@ struct extent_state; struct btrfs_root; +struct btrfs_io_bio; typedef int (extent_submit_bio_hook_t)(struct inode *inode, int rw, struct bio *bio, int mirror_num, @@ -77,8 +76,9 @@ struct extent_io_ops { size_t size, struct bio *bio, unsigned long bio_flags); int (*readpage_io_failed_hook)(struct page *page, int failed_mirror); - int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end, - struct extent_state *state, int mirror); + int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset, + struct page *page, u64 start, u64 end, + int mirror); int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); void (*set_bit_hook)(struct inode *inode, struct extent_state *state, @@ -200,6 +200,8 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end, int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end); int extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, int mirror_num); +int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, + get_extent_t *get_extent, int mirror_num); int __init extent_io_init(void); void extent_io_exit(void); @@ -261,11 +263,6 @@ int extent_readpages(struct extent_io_tree *tree, get_extent_t get_extent); int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len, get_extent_t *get_extent); -int set_state_private(struct extent_io_tree *tree, u64 start, u64 private); -void extent_cache_csums_dio(struct extent_io_tree *tree, u64 start, u32 csums[], - int count); -void extent_cache_csums(struct extent_io_tree *tree, struct bio *bio, - int bvec_index, u32 csums[], int count); int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private); void set_page_extent_mapped(struct page *page); @@ -330,10 +327,10 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset, unsigned long *map_len); int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end); int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); -int extent_clear_unlock_delalloc(struct inode *inode, - struct extent_io_tree *tree, - u64 start, u64 end, struct page *locked_page, - unsigned long op); +int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, + struct page *locked_page, + unsigned long bits_to_clear, + unsigned long page_ops); struct bio * btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, gfp_t gfp_flags); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index a7bfc95..4f53159 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -23,6 +23,7 @@ #include "ctree.h" #include "disk-io.h" #include "transaction.h" +#include "volumes.h" #include "print-tree.h" #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \ @@ -152,28 +153,54 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, return ret; } +static void btrfs_io_bio_endio_readpage(struct btrfs_io_bio *bio, int err) +{ + kfree(bio->csum_allocated); +} + static int __btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, struct bio *bio, u64 logical_offset, u32 *dst, int dio) { - u32 sum[16]; - int len; struct bio_vec *bvec = bio->bi_io_vec; - int bio_index = 0; + struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio); + struct btrfs_csum_item *item = NULL; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct btrfs_path *path; + u8 *csum; u64 offset = 0; u64 item_start_offset = 0; u64 item_last_offset = 0; u64 disk_bytenr; u32 diff; - u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); + int nblocks; + int bio_index = 0; int count; - struct btrfs_path *path; - struct btrfs_csum_item *item = NULL; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); path = btrfs_alloc_path(); if (!path) return -ENOMEM; + + nblocks = bio->bi_size >> inode->i_sb->s_blocksize_bits; + if (!dst) { + if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) { + btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size, + GFP_NOFS); + if (!btrfs_bio->csum_allocated) { + btrfs_free_path(path); + return -ENOMEM; + } + btrfs_bio->csum = btrfs_bio->csum_allocated; + btrfs_bio->end_io = btrfs_io_bio_endio_readpage; + } else { + btrfs_bio->csum = btrfs_bio->csum_inline; + } + csum = btrfs_bio->csum; + } else { + csum = (u8 *)dst; + } + if (bio->bi_size > PAGE_CACHE_SIZE * 8) path->reada = 2; @@ -194,11 +221,10 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, if (dio) offset = logical_offset; while (bio_index < bio->bi_vcnt) { - len = min_t(int, ARRAY_SIZE(sum), bio->bi_vcnt - bio_index); if (!dio) offset = page_offset(bvec->bv_page) + bvec->bv_offset; - count = btrfs_find_ordered_sum(inode, offset, disk_bytenr, sum, - len); + count = btrfs_find_ordered_sum(inode, offset, disk_bytenr, + (u32 *)csum, nblocks); if (count) goto found; @@ -213,7 +239,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, path, disk_bytenr, 0); if (IS_ERR(item)) { count = 1; - sum[0] = 0; + memset(csum, 0, csum_size); if (BTRFS_I(inode)->root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) { set_extent_bits(io_tree, offset, @@ -222,9 +248,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, } else { printk(KERN_INFO "btrfs no csum found " "for inode %llu start %llu\n", - (unsigned long long) - btrfs_ino(inode), - (unsigned long long)offset); + btrfs_ino(inode), offset); } item = NULL; btrfs_release_path(path); @@ -249,23 +273,14 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, diff = disk_bytenr - item_start_offset; diff = diff / root->sectorsize; diff = diff * csum_size; - count = min_t(int, len, (item_last_offset - disk_bytenr) >> - inode->i_sb->s_blocksize_bits); - read_extent_buffer(path->nodes[0], sum, + count = min_t(int, nblocks, (item_last_offset - disk_bytenr) >> + inode->i_sb->s_blocksize_bits); + read_extent_buffer(path->nodes[0], csum, ((unsigned long)item) + diff, csum_size * count); found: - if (dst) { - memcpy(dst, sum, count * csum_size); - dst += count; - } else { - if (dio) - extent_cache_csums_dio(io_tree, offset, sum, - count); - else - extent_cache_csums(io_tree, bio, bio_index, sum, - count); - } + csum += count * csum_size; + nblocks -= count; while (count--) { disk_bytenr += bvec->bv_len; offset += bvec->bv_len; @@ -284,9 +299,19 @@ int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, } int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode, - struct bio *bio, u64 offset) + struct btrfs_dio_private *dip, struct bio *bio, + u64 offset) { - return __btrfs_lookup_bio_sums(root, inode, bio, offset, NULL, 1); + int len = (bio->bi_sector << 9) - dip->disk_bytenr; + u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); + int ret; + + len >>= inode->i_sb->s_blocksize_bits; + len *= csum_size; + + ret = __btrfs_lookup_bio_sums(root, inode, bio, offset, + (u32 *)(dip->csum + len), 1); + return ret; } int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a005fe2..bc5072b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -596,20 +596,29 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, if (no_splits) goto next; - if (em->block_start < EXTENT_MAP_LAST_BYTE && - em->start < start) { + if (em->start < start) { split->start = em->start; split->len = start - em->start; - split->orig_start = em->orig_start; - split->block_start = em->block_start; - if (compressed) - split->block_len = em->block_len; - else - split->block_len = split->len; - split->ram_bytes = em->ram_bytes; - split->orig_block_len = max(split->block_len, - em->orig_block_len); + if (em->block_start < EXTENT_MAP_LAST_BYTE) { + split->orig_start = em->orig_start; + split->block_start = em->block_start; + + if (compressed) + split->block_len = em->block_len; + else + split->block_len = split->len; + split->orig_block_len = max(split->block_len, + em->orig_block_len); + split->ram_bytes = em->ram_bytes; + } else { + split->orig_start = split->start; + split->block_len = 0; + split->block_start = em->block_start; + split->orig_block_len = 0; + split->ram_bytes = split->len; + } + split->generation = gen; split->bdev = em->bdev; split->flags = flags; @@ -620,8 +629,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split = split2; split2 = NULL; } - if (em->block_start < EXTENT_MAP_LAST_BYTE && - testend && em->start + em->len > start + len) { + if (testend && em->start + em->len > start + len) { u64 diff = start + len - em->start; split->start = start + len; @@ -630,18 +638,28 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split->flags = flags; split->compress_type = em->compress_type; split->generation = gen; - split->orig_block_len = max(em->block_len, + + if (em->block_start < EXTENT_MAP_LAST_BYTE) { + split->orig_block_len = max(em->block_len, em->orig_block_len); - split->ram_bytes = em->ram_bytes; - if (compressed) { - split->block_len = em->block_len; - split->block_start = em->block_start; - split->orig_start = em->orig_start; + split->ram_bytes = em->ram_bytes; + if (compressed) { + split->block_len = em->block_len; + split->block_start = em->block_start; + split->orig_start = em->orig_start; + } else { + split->block_len = split->len; + split->block_start = em->block_start + + diff; + split->orig_start = em->orig_start; + } } else { - split->block_len = split->len; - split->block_start = em->block_start + diff; - split->orig_start = em->orig_start; + split->ram_bytes = split->len; + split->orig_start = split->start; + split->block_len = 0; + split->block_start = em->block_start; + split->orig_block_len = 0; } ret = add_extent_mapping(em_tree, split, modified); @@ -1316,7 +1334,6 @@ fail: static noinline int check_can_nocow(struct inode *inode, loff_t pos, size_t *write_bytes) { - struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_ordered_extent *ordered; u64 lockstart, lockend; @@ -1338,16 +1355,8 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos, btrfs_put_ordered_extent(ordered); } - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend); - return PTR_ERR(trans); - } - num_bytes = lockend - lockstart + 1; - ret = can_nocow_extent(trans, inode, lockstart, &num_bytes, NULL, NULL, - NULL); - btrfs_end_transaction(trans, root); + ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL); if (ret <= 0) { ret = 0; } else { @@ -1709,7 +1718,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, */ BTRFS_I(inode)->last_trans = root->fs_info->generation + 1; BTRFS_I(inode)->last_sub_trans = root->log_transid; - if (num_written > 0 || num_written == -EIOCBQUEUED) { + if (num_written > 0) { err = generic_write_sync(file, pos, num_written); if (err < 0 && num_written > 0) num_written = err; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index b21a3cd..3f0ddfc 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -221,12 +221,10 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root, struct btrfs_path *path, struct inode *inode) { - loff_t oldsize; int ret = 0; - oldsize = i_size_read(inode); btrfs_i_size_write(inode, 0); - truncate_pagecache(inode, oldsize, 0); + truncate_pagecache(inode, 0); /* * We don't need an orphan item because truncating the free space cache @@ -308,7 +306,7 @@ static void io_ctl_unmap_page(struct io_ctl *io_ctl) static void io_ctl_map_page(struct io_ctl *io_ctl, int clear) { - BUG_ON(io_ctl->index >= io_ctl->num_pages); + ASSERT(io_ctl->index < io_ctl->num_pages); io_ctl->page = io_ctl->pages[io_ctl->index++]; io_ctl->cur = kmap(io_ctl->page); io_ctl->orig = io_ctl->cur; @@ -673,8 +671,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, btrfs_err(root->fs_info, "free space inode generation (%llu) " "did not match free space cache generation (%llu)", - (unsigned long long)BTRFS_I(inode)->generation, - (unsigned long long)generation); + BTRFS_I(inode)->generation, generation); return 0; } @@ -729,7 +726,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, goto free_cache; } } else { - BUG_ON(!num_bitmaps); + ASSERT(num_bitmaps); num_bitmaps--; e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); if (!e->bitmap) { @@ -1029,7 +1026,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, leaf = path->nodes[0]; if (ret > 0) { struct btrfs_key found_key; - BUG_ON(!path->slots[0]); + ASSERT(path->slots[0]); path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID || @@ -1117,7 +1114,7 @@ int btrfs_write_out_cache(struct btrfs_root *root, static inline unsigned long offset_to_bit(u64 bitmap_start, u32 unit, u64 offset) { - BUG_ON(offset < bitmap_start); + ASSERT(offset >= bitmap_start); offset -= bitmap_start; return (unsigned long)(div_u64(offset, unit)); } @@ -1272,7 +1269,7 @@ tree_search_offset(struct btrfs_free_space_ctl *ctl, if (n) { entry = rb_entry(n, struct btrfs_free_space, offset_index); - BUG_ON(entry->offset > offset); + ASSERT(entry->offset <= offset); } else { if (fuzzy) return entry; @@ -1336,7 +1333,7 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl, { int ret = 0; - BUG_ON(!info->bitmap && !info->bytes); + ASSERT(info->bytes || info->bitmap); ret = tree_insert_offset(&ctl->free_space_offset, info->offset, &info->offset_index, (info->bitmap != NULL)); if (ret) @@ -1359,7 +1356,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) max_bitmaps = max(max_bitmaps, 1); - BUG_ON(ctl->total_bitmaps > max_bitmaps); + ASSERT(ctl->total_bitmaps <= max_bitmaps); /* * The goal is to keep the total amount of memory used per 1gb of space @@ -1403,7 +1400,7 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, start = offset_to_bit(info->offset, ctl->unit, offset); count = bytes_to_bits(bytes, ctl->unit); - BUG_ON(start + count > BITS_PER_BITMAP); + ASSERT(start + count <= BITS_PER_BITMAP); bitmap_clear(info->bitmap, start, count); @@ -1426,7 +1423,7 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl, start = offset_to_bit(info->offset, ctl->unit, offset); count = bytes_to_bits(bytes, ctl->unit); - BUG_ON(start + count > BITS_PER_BITMAP); + ASSERT(start + count <= BITS_PER_BITMAP); bitmap_set(info->bitmap, start, count); @@ -1742,7 +1739,7 @@ no_cluster_bitmap: bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 1, 0); if (!bitmap_info) { - BUG_ON(added); + ASSERT(added == 0); goto new_bitmap; } @@ -1882,7 +1879,7 @@ out: if (ret) { printk(KERN_CRIT "btrfs: unable to add free space :%d\n", ret); - BUG_ON(ret == -EEXIST); + ASSERT(ret != -EEXIST); } return ret; @@ -1991,8 +1988,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, if (info->bytes >= bytes && !block_group->ro) count++; printk(KERN_CRIT "entry offset %llu, bytes %llu, bitmap %s\n", - (unsigned long long)info->offset, - (unsigned long long)info->bytes, + info->offset, info->bytes, (info->bitmap) ? "yes" : "no"); } printk(KERN_INFO "block group has cluster?: %s\n", @@ -2371,7 +2367,7 @@ again: rb_erase(&entry->offset_index, &ctl->free_space_offset); ret = tree_insert_offset(&cluster->root, entry->offset, &entry->offset_index, 1); - BUG_ON(ret); /* -EEXIST; Logic error */ + ASSERT(!ret); /* -EEXIST; Logic error */ trace_btrfs_setup_cluster(block_group, cluster, total_found * ctl->unit, 1); @@ -2464,7 +2460,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group, ret = tree_insert_offset(&cluster->root, entry->offset, &entry->offset_index, 0); total_size += entry->bytes; - BUG_ON(ret); /* -EEXIST; Logic error */ + ASSERT(!ret); /* -EEXIST; Logic error */ } while (node && entry != last); cluster->max_size = max_extent; @@ -2525,8 +2521,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group, * returns zero and sets up cluster if things worked out, otherwise * it returns -enospc */ -int btrfs_find_space_cluster(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +int btrfs_find_space_cluster(struct btrfs_root *root, struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size) @@ -2856,7 +2851,7 @@ u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root) ret = search_bitmap(ctl, entry, &offset, &count); /* Logic error; Should be empty if it can't find anything */ - BUG_ON(ret); + ASSERT(!ret); ino = offset; bitmap_clear_bits(ctl, entry, offset, 1); @@ -2973,33 +2968,68 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root, } #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -static struct btrfs_block_group_cache *init_test_block_group(void) +/* + * Use this if you need to make a bitmap or extent entry specifically, it + * doesn't do any of the merging that add_free_space does, this acts a lot like + * how the free space cache loading stuff works, so you can get really weird + * configurations. + */ +int test_add_free_space_entry(struct btrfs_block_group_cache *cache, + u64 offset, u64 bytes, bool bitmap) { - struct btrfs_block_group_cache *cache; + struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; + struct btrfs_free_space *info = NULL, *bitmap_info; + void *map = NULL; + u64 bytes_added; + int ret; - cache = kzalloc(sizeof(*cache), GFP_NOFS); - if (!cache) - return NULL; - cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl), - GFP_NOFS); - if (!cache->free_space_ctl) { - kfree(cache); - return NULL; +again: + if (!info) { + info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); + if (!info) + return -ENOMEM; } - cache->key.objectid = 0; - cache->key.offset = 1024 * 1024 * 1024; - cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; - cache->sectorsize = 4096; + if (!bitmap) { + spin_lock(&ctl->tree_lock); + info->offset = offset; + info->bytes = bytes; + ret = link_free_space(ctl, info); + spin_unlock(&ctl->tree_lock); + if (ret) + kmem_cache_free(btrfs_free_space_cachep, info); + return ret; + } + + if (!map) { + map = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); + if (!map) { + kmem_cache_free(btrfs_free_space_cachep, info); + return -ENOMEM; + } + } + + spin_lock(&ctl->tree_lock); + bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), + 1, 0); + if (!bitmap_info) { + info->bitmap = map; + map = NULL; + add_new_bitmap(ctl, info, offset); + bitmap_info = info; + } - spin_lock_init(&cache->lock); - INIT_LIST_HEAD(&cache->list); - INIT_LIST_HEAD(&cache->cluster_list); - INIT_LIST_HEAD(&cache->new_bg_list); + bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes); + bytes -= bytes_added; + offset += bytes_added; + spin_unlock(&ctl->tree_lock); - btrfs_init_free_space_ctl(cache); + if (bytes) + goto again; - return cache; + if (map) + kfree(map); + return 0; } /* @@ -3007,8 +3037,8 @@ static struct btrfs_block_group_cache *init_test_block_group(void) * just used to check the absence of space, so if there is free space in the * range at all we will return 1. */ -static int check_exists(struct btrfs_block_group_cache *cache, u64 offset, - u64 bytes) +int test_check_exists(struct btrfs_block_group_cache *cache, + u64 offset, u64 bytes) { struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; struct btrfs_free_space *info; @@ -3085,411 +3115,4 @@ out: spin_unlock(&ctl->tree_lock); return ret; } - -/* - * Use this if you need to make a bitmap or extent entry specifically, it - * doesn't do any of the merging that add_free_space does, this acts a lot like - * how the free space cache loading stuff works, so you can get really weird - * configurations. - */ -static int add_free_space_entry(struct btrfs_block_group_cache *cache, - u64 offset, u64 bytes, bool bitmap) -{ - struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; - struct btrfs_free_space *info = NULL, *bitmap_info; - void *map = NULL; - u64 bytes_added; - int ret; - -again: - if (!info) { - info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); - if (!info) - return -ENOMEM; - } - - if (!bitmap) { - spin_lock(&ctl->tree_lock); - info->offset = offset; - info->bytes = bytes; - ret = link_free_space(ctl, info); - spin_unlock(&ctl->tree_lock); - if (ret) - kmem_cache_free(btrfs_free_space_cachep, info); - return ret; - } - - if (!map) { - map = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); - if (!map) { - kmem_cache_free(btrfs_free_space_cachep, info); - return -ENOMEM; - } - } - - spin_lock(&ctl->tree_lock); - bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), - 1, 0); - if (!bitmap_info) { - info->bitmap = map; - map = NULL; - add_new_bitmap(ctl, info, offset); - bitmap_info = info; - } - - bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes); - bytes -= bytes_added; - offset += bytes_added; - spin_unlock(&ctl->tree_lock); - - if (bytes) - goto again; - - if (map) - kfree(map); - return 0; -} - -#define test_msg(fmt, ...) printk(KERN_INFO "btrfs: selftest: " fmt, ##__VA_ARGS__) - -/* - * This test just does basic sanity checking, making sure we can add an exten - * entry and remove space from either end and the middle, and make sure we can - * remove space that covers adjacent extent entries. - */ -static int test_extents(struct btrfs_block_group_cache *cache) -{ - int ret = 0; - - test_msg("Running extent only tests\n"); - - /* First just make sure we can remove an entire entry */ - ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024); - if (ret) { - test_msg("Error adding initial extents %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024); - if (ret) { - test_msg("Error removing extent %d\n", ret); - return ret; - } - - if (check_exists(cache, 0, 4 * 1024 * 1024)) { - test_msg("Full remove left some lingering space\n"); - return -1; - } - - /* Ok edge and middle cases now */ - ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024); - if (ret) { - test_msg("Error adding half extent %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 1 * 1024 * 1024); - if (ret) { - test_msg("Error removing tail end %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024); - if (ret) { - test_msg("Error removing front end %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 2 * 1024 * 1024, 4096); - if (ret) { - test_msg("Error removing middle piece %d\n", ret); - return ret; - } - - if (check_exists(cache, 0, 1 * 1024 * 1024)) { - test_msg("Still have space at the front\n"); - return -1; - } - - if (check_exists(cache, 2 * 1024 * 1024, 4096)) { - test_msg("Still have space in the middle\n"); - return -1; - } - - if (check_exists(cache, 3 * 1024 * 1024, 1 * 1024 * 1024)) { - test_msg("Still have space at the end\n"); - return -1; - } - - /* Cleanup */ - __btrfs_remove_free_space_cache(cache->free_space_ctl); - - return 0; -} - -static int test_bitmaps(struct btrfs_block_group_cache *cache) -{ - u64 next_bitmap_offset; - int ret; - - test_msg("Running bitmap only tests\n"); - - ret = add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't create a bitmap entry %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024); - if (ret) { - test_msg("Error removing bitmap full range %d\n", ret); - return ret; - } - - if (check_exists(cache, 0, 4 * 1024 * 1024)) { - test_msg("Left some space in bitmap\n"); - return -1; - } - - ret = add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't add to our bitmap entry %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 2 * 1024 * 1024); - if (ret) { - test_msg("Couldn't remove middle chunk %d\n", ret); - return ret; - } - - /* - * The first bitmap we have starts at offset 0 so the next one is just - * at the end of the first bitmap. - */ - next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096); - - /* Test a bit straddling two bitmaps */ - ret = add_free_space_entry(cache, next_bitmap_offset - - (2 * 1024 * 1024), 4 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't add space that straddles two bitmaps %d\n", - ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, next_bitmap_offset - - (1 * 1024 * 1024), 2 * 1024 * 1024); - if (ret) { - test_msg("Couldn't remove overlapping space %d\n", ret); - return ret; - } - - if (check_exists(cache, next_bitmap_offset - (1 * 1024 * 1024), - 2 * 1024 * 1024)) { - test_msg("Left some space when removing overlapping\n"); - return -1; - } - - __btrfs_remove_free_space_cache(cache->free_space_ctl); - - return 0; -} - -/* This is the high grade jackassery */ -static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache) -{ - u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096); - int ret; - - test_msg("Running bitmap and extent tests\n"); - - /* - * First let's do something simple, an extent at the same offset as the - * bitmap, but the free space completely in the extent and then - * completely in the bitmap. - */ - ret = add_free_space_entry(cache, 4 * 1024 * 1024, 1 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't create bitmap entry %d\n", ret); - return ret; - } - - ret = add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0); - if (ret) { - test_msg("Couldn't add extent entry %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024); - if (ret) { - test_msg("Couldn't remove extent entry %d\n", ret); - return ret; - } - - if (check_exists(cache, 0, 1 * 1024 * 1024)) { - test_msg("Left remnants after our remove\n"); - return -1; - } - - /* Now to add back the extent entry and remove from the bitmap */ - ret = add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0); - if (ret) { - test_msg("Couldn't re-add extent entry %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 4 * 1024 * 1024, 1 * 1024 * 1024); - if (ret) { - test_msg("Couldn't remove from bitmap %d\n", ret); - return ret; - } - - if (check_exists(cache, 4 * 1024 * 1024, 1 * 1024 * 1024)) { - test_msg("Left remnants in the bitmap\n"); - return -1; - } - - /* - * Ok so a little more evil, extent entry and bitmap at the same offset, - * removing an overlapping chunk. - */ - ret = add_free_space_entry(cache, 1 * 1024 * 1024, 4 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't add to a bitmap %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 512 * 1024, 3 * 1024 * 1024); - if (ret) { - test_msg("Couldn't remove overlapping space %d\n", ret); - return ret; - } - - if (check_exists(cache, 512 * 1024, 3 * 1024 * 1024)) { - test_msg("Left over peices after removing overlapping\n"); - return -1; - } - - __btrfs_remove_free_space_cache(cache->free_space_ctl); - - /* Now with the extent entry offset into the bitmap */ - ret = add_free_space_entry(cache, 4 * 1024 * 1024, 4 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't add space to the bitmap %d\n", ret); - return ret; - } - - ret = add_free_space_entry(cache, 2 * 1024 * 1024, 2 * 1024 * 1024, 0); - if (ret) { - test_msg("Couldn't add extent to the cache %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 4 * 1024 * 1024); - if (ret) { - test_msg("Problem removing overlapping space %d\n", ret); - return ret; - } - - if (check_exists(cache, 3 * 1024 * 1024, 4 * 1024 * 1024)) { - test_msg("Left something behind when removing space"); - return -1; - } - - /* - * This has blown up in the past, the extent entry starts before the - * bitmap entry, but we're trying to remove an offset that falls - * completely within the bitmap range and is in both the extent entry - * and the bitmap entry, looks like this - * - * [ extent ] - * [ bitmap ] - * [ del ] - */ - __btrfs_remove_free_space_cache(cache->free_space_ctl); - ret = add_free_space_entry(cache, bitmap_offset + 4 * 1024 * 1024, - 4 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't add bitmap %d\n", ret); - return ret; - } - - ret = add_free_space_entry(cache, bitmap_offset - 1 * 1024 * 1024, - 5 * 1024 * 1024, 0); - if (ret) { - test_msg("Couldn't add extent entry %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, bitmap_offset + 1 * 1024 * 1024, - 5 * 1024 * 1024); - if (ret) { - test_msg("Failed to free our space %d\n", ret); - return ret; - } - - if (check_exists(cache, bitmap_offset + 1 * 1024 * 1024, - 5 * 1024 * 1024)) { - test_msg("Left stuff over\n"); - return -1; - } - - __btrfs_remove_free_space_cache(cache->free_space_ctl); - - /* - * This blew up before, we have part of the free space in a bitmap and - * then the entirety of the rest of the space in an extent. This used - * to return -EAGAIN back from btrfs_remove_extent, make sure this - * doesn't happen. - */ - ret = add_free_space_entry(cache, 1 * 1024 * 1024, 2 * 1024 * 1024, 1); - if (ret) { - test_msg("Couldn't add bitmap entry %d\n", ret); - return ret; - } - - ret = add_free_space_entry(cache, 3 * 1024 * 1024, 1 * 1024 * 1024, 0); - if (ret) { - test_msg("Couldn't add extent entry %d\n", ret); - return ret; - } - - ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 3 * 1024 * 1024); - if (ret) { - test_msg("Error removing bitmap and extent overlapping %d\n", ret); - return ret; - } - - __btrfs_remove_free_space_cache(cache->free_space_ctl); - return 0; -} - -void btrfs_test_free_space_cache(void) -{ - struct btrfs_block_group_cache *cache; - - test_msg("Running btrfs free space cache tests\n"); - - cache = init_test_block_group(); - if (!cache) { - test_msg("Couldn't run the tests\n"); - return; - } - - if (test_extents(cache)) - goto out; - if (test_bitmaps(cache)) - goto out; - if (test_bitmaps_and_extents(cache)) - goto out; -out: - __btrfs_remove_free_space_cache(cache->free_space_ctl); - kfree(cache->free_space_ctl); - kfree(cache); - test_msg("Free space cache tests finished\n"); -} -#undef test_msg -#else /* !CONFIG_BTRFS_FS_RUN_SANITY_TESTS */ -void btrfs_test_free_space_cache(void) {} -#endif /* !CONFIG_BTRFS_FS_RUN_SANITY_TESTS */ +#endif /* CONFIG_BTRFS_FS_RUN_SANITY_TESTS */ diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 894116b7..c749041 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -98,8 +98,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, u64 bytes); -int btrfs_find_space_cluster(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +int btrfs_find_space_cluster(struct btrfs_root *root, struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size); @@ -113,6 +112,12 @@ int btrfs_return_cluster_to_free_space( int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen); -void btrfs_test_free_space_cache(void); +/* Support functions for runnint our sanity tests */ +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +int test_add_free_space_entry(struct btrfs_block_group_cache *cache, + u64 offset, u64 bytes, bool bitmap); +int test_check_exists(struct btrfs_block_group_cache *cache, + u64 offset, u64 bytes); +#endif #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6d1b93c..f338c56 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -230,12 +230,13 @@ fail: * does the checks required to make sure the data is small enough * to fit as an inline extent. */ -static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct inode *inode, u64 start, u64 end, - size_t compressed_size, int compress_type, - struct page **compressed_pages) +static noinline int cow_file_range_inline(struct btrfs_root *root, + struct inode *inode, u64 start, + u64 end, size_t compressed_size, + int compress_type, + struct page **compressed_pages) { + struct btrfs_trans_handle *trans; u64 isize = i_size_read(inode); u64 actual_end = min(end + 1, isize); u64 inline_len = actual_end - start; @@ -256,9 +257,16 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans, return 1; } + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) + return PTR_ERR(trans); + trans->block_rsv = &root->fs_info->delalloc_block_rsv; + ret = btrfs_drop_extents(trans, root, inode, start, aligned_end, 1); - if (ret) - return ret; + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out; + } if (isize > actual_end) inline_len = min_t(u64, isize, actual_end); @@ -267,15 +275,18 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans, compress_type, compressed_pages); if (ret && ret != -ENOSPC) { btrfs_abort_transaction(trans, root, ret); - return ret; + goto out; } else if (ret == -ENOSPC) { - return 1; + ret = 1; + goto out; } set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); btrfs_delalloc_release_metadata(inode, end + 1 - start); btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0); - return 0; +out: + btrfs_end_transaction(trans, root); + return ret; } struct async_extent { @@ -343,7 +354,6 @@ static noinline int compress_file_range(struct inode *inode, int *num_added) { struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_trans_handle *trans; u64 num_bytes; u64 blocksize = root->sectorsize; u64 actual_end; @@ -461,45 +471,36 @@ again: } cont: if (start == 0) { - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto cleanup_and_out; - } - trans->block_rsv = &root->fs_info->delalloc_block_rsv; - /* lets try to make an inline extent */ if (ret || total_in < (actual_end - start)) { /* we didn't compress the entire range, try * to make an uncompressed inline extent. */ - ret = cow_file_range_inline(trans, root, inode, - start, end, 0, 0, NULL); + ret = cow_file_range_inline(root, inode, start, end, + 0, 0, NULL); } else { /* try making a compressed inline extent */ - ret = cow_file_range_inline(trans, root, inode, - start, end, + ret = cow_file_range_inline(root, inode, start, end, total_compressed, compress_type, pages); } if (ret <= 0) { + unsigned long clear_flags = EXTENT_DELALLOC | + EXTENT_DEFRAG; + clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0; + /* * inline extent creation worked or returned error, * we don't need to create any more async work items. * Unlock and free up our temp pages. */ - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - start, end, NULL, - EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_DIRTY | - EXTENT_CLEAR_DELALLOC | - EXTENT_SET_WRITEBACK | EXTENT_END_WRITEBACK); - - btrfs_end_transaction(trans, root); + extent_clear_unlock_delalloc(inode, start, end, NULL, + clear_flags, PAGE_UNLOCK | + PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | + PAGE_END_WRITEBACK); goto free_pages_out; } - btrfs_end_transaction(trans, root); } if (will_compress) { @@ -590,20 +591,6 @@ free_pages_out: kfree(pages); goto out; - -cleanup_and_out: - extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - start, end, NULL, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_DIRTY | - EXTENT_CLEAR_DELALLOC | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); - if (!trans || IS_ERR(trans)) - btrfs_error(root->fs_info, ret, "Failed to join transaction"); - else - btrfs_abort_transaction(trans, root, ret); - goto free_pages_out; } /* @@ -617,7 +604,6 @@ static noinline int submit_compressed_extents(struct inode *inode, { struct async_extent *async_extent; u64 alloc_hint = 0; - struct btrfs_trans_handle *trans; struct btrfs_key ins; struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -678,20 +664,10 @@ retry: lock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - } else { - trans->block_rsv = &root->fs_info->delalloc_block_rsv; - ret = btrfs_reserve_extent(trans, root, + ret = btrfs_reserve_extent(root, async_extent->compressed_size, async_extent->compressed_size, 0, alloc_hint, &ins, 1); - if (ret && ret != -ENOSPC) - btrfs_abort_transaction(trans, root, ret); - btrfs_end_transaction(trans, root); - } - if (ret) { int i; @@ -770,16 +746,12 @@ retry: /* * clear dirty, set writeback and unlock the pages. */ - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - async_extent->start, + extent_clear_unlock_delalloc(inode, async_extent->start, async_extent->start + async_extent->ram_size - 1, - NULL, EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | EXTENT_SET_WRITEBACK); - + NULL, EXTENT_LOCKED | EXTENT_DELALLOC, + PAGE_UNLOCK | PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK); ret = btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, @@ -798,16 +770,13 @@ out: out_free_reserve: btrfs_free_reserved_extent(root, ins.objectid, ins.offset); out_free: - extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - async_extent->start, + extent_clear_unlock_delalloc(inode, async_extent->start, async_extent->start + async_extent->ram_size - 1, - NULL, EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); + NULL, EXTENT_LOCKED | EXTENT_DELALLOC | + EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, + PAGE_UNLOCK | PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); kfree(async_extent); goto again; } @@ -857,14 +826,13 @@ static u64 get_extent_allocation_hint(struct inode *inode, u64 start, * required to start IO on it. It may be clean and already done with * IO when we return. */ -static noinline int __cow_file_range(struct btrfs_trans_handle *trans, - struct inode *inode, - struct btrfs_root *root, - struct page *locked_page, - u64 start, u64 end, int *page_started, - unsigned long *nr_written, - int unlock) +static noinline int cow_file_range(struct inode *inode, + struct page *locked_page, + u64 start, u64 end, int *page_started, + unsigned long *nr_written, + int unlock) { + struct btrfs_root *root = BTRFS_I(inode)->root; u64 alloc_hint = 0; u64 num_bytes; unsigned long ram_size; @@ -885,29 +853,24 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans, /* if this is a small write inside eof, kick off defrag */ if (num_bytes < 64 * 1024 && (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) - btrfs_add_inode_defrag(trans, inode); + btrfs_add_inode_defrag(NULL, inode); if (start == 0) { /* lets try to make an inline extent */ - ret = cow_file_range_inline(trans, root, inode, - start, end, 0, 0, NULL); + ret = cow_file_range_inline(root, inode, start, end, 0, 0, + NULL); if (ret == 0) { - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - start, end, NULL, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); + extent_clear_unlock_delalloc(inode, start, end, NULL, + EXTENT_LOCKED | EXTENT_DELALLOC | + EXTENT_DEFRAG, PAGE_UNLOCK | + PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | + PAGE_END_WRITEBACK); *nr_written = *nr_written + (end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE; *page_started = 1; goto out; } else if (ret < 0) { - btrfs_abort_transaction(trans, root, ret); goto out_unlock; } } @@ -922,13 +885,11 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans, unsigned long op; cur_alloc_size = disk_num_bytes; - ret = btrfs_reserve_extent(trans, root, cur_alloc_size, + ret = btrfs_reserve_extent(root, cur_alloc_size, root->sectorsize, 0, alloc_hint, &ins, 1); - if (ret < 0) { - btrfs_abort_transaction(trans, root, ret); + if (ret < 0) goto out_unlock; - } em = alloc_extent_map(); if (!em) { @@ -974,10 +935,8 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans, BTRFS_DATA_RELOC_TREE_OBJECTID) { ret = btrfs_reloc_clone_csums(inode, start, cur_alloc_size); - if (ret) { - btrfs_abort_transaction(trans, root, ret); + if (ret) goto out_reserve; - } } if (disk_num_bytes < cur_alloc_size) @@ -990,13 +949,13 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans, * Do set the Private2 bit so we know this page was properly * setup for writepage */ - op = unlock ? EXTENT_CLEAR_UNLOCK_PAGE : 0; - op |= EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC | - EXTENT_SET_PRIVATE2; + op = unlock ? PAGE_UNLOCK : 0; + op |= PAGE_SET_PRIVATE2; - extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - start, start + ram_size - 1, - locked_page, op); + extent_clear_unlock_delalloc(inode, start, + start + ram_size - 1, locked_page, + EXTENT_LOCKED | EXTENT_DELALLOC, + op); disk_num_bytes -= cur_alloc_size; num_bytes -= cur_alloc_size; alloc_hint = ins.objectid + ins.offset; @@ -1008,52 +967,14 @@ out: out_reserve: btrfs_free_reserved_extent(root, ins.objectid, ins.offset); out_unlock: - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - start, end, locked_page, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); - + extent_clear_unlock_delalloc(inode, start, end, locked_page, + EXTENT_LOCKED | EXTENT_DO_ACCOUNTING | + EXTENT_DELALLOC | EXTENT_DEFRAG, + PAGE_UNLOCK | PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); goto out; } -static noinline int cow_file_range(struct inode *inode, - struct page *locked_page, - u64 start, u64 end, int *page_started, - unsigned long *nr_written, - int unlock) -{ - struct btrfs_trans_handle *trans; - struct btrfs_root *root = BTRFS_I(inode)->root; - int ret; - - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - start, end, locked_page, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); - return PTR_ERR(trans); - } - trans->block_rsv = &root->fs_info->delalloc_block_rsv; - - ret = __cow_file_range(trans, inode, root, locked_page, start, end, - page_started, nr_written, unlock); - - btrfs_end_transaction(trans, root); - - return ret; -} - /* * work queue call back to started compression on a file and pages */ @@ -1221,15 +1142,13 @@ static noinline int run_delalloc_nocow(struct inode *inode, path = btrfs_alloc_path(); if (!path) { - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - start, end, locked_page, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); + extent_clear_unlock_delalloc(inode, start, end, locked_page, + EXTENT_LOCKED | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | + EXTENT_DEFRAG, PAGE_UNLOCK | + PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | + PAGE_END_WRITEBACK); return -ENOMEM; } @@ -1241,15 +1160,13 @@ static noinline int run_delalloc_nocow(struct inode *inode, trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - start, end, locked_page, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); + extent_clear_unlock_delalloc(inode, start, end, locked_page, + EXTENT_LOCKED | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | + EXTENT_DEFRAG, PAGE_UNLOCK | + PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | + PAGE_END_WRITEBACK); btrfs_free_path(path); return PTR_ERR(trans); } @@ -1369,9 +1286,9 @@ out_check: btrfs_release_path(path); if (cow_start != (u64)-1) { - ret = __cow_file_range(trans, inode, root, locked_page, - cow_start, found_key.offset - 1, - page_started, nr_written, 1); + ret = cow_file_range(inode, locked_page, + cow_start, found_key.offset - 1, + page_started, nr_written, 1); if (ret) { btrfs_abort_transaction(trans, root, ret); goto error; @@ -1428,11 +1345,11 @@ out_check: } } - extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - cur_offset, cur_offset + num_bytes - 1, - locked_page, EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC | - EXTENT_SET_PRIVATE2); + extent_clear_unlock_delalloc(inode, cur_offset, + cur_offset + num_bytes - 1, + locked_page, EXTENT_LOCKED | + EXTENT_DELALLOC, PAGE_UNLOCK | + PAGE_SET_PRIVATE2); cur_offset = extent_end; if (cur_offset > end) break; @@ -1445,9 +1362,8 @@ out_check: } if (cow_start != (u64)-1) { - ret = __cow_file_range(trans, inode, root, locked_page, - cow_start, end, - page_started, nr_written, 1); + ret = cow_file_range(inode, locked_page, cow_start, end, + page_started, nr_written, 1); if (ret) { btrfs_abort_transaction(trans, root, ret); goto error; @@ -1460,16 +1376,13 @@ error: ret = err; if (ret && cur_offset < end) - extent_clear_unlock_delalloc(inode, - &BTRFS_I(inode)->io_tree, - cur_offset, end, locked_page, - EXTENT_CLEAR_UNLOCK_PAGE | - EXTENT_CLEAR_UNLOCK | - EXTENT_CLEAR_DELALLOC | - EXTENT_CLEAR_DIRTY | - EXTENT_SET_WRITEBACK | - EXTENT_END_WRITEBACK); - + extent_clear_unlock_delalloc(inode, cur_offset, end, + locked_page, EXTENT_LOCKED | + EXTENT_DELALLOC | EXTENT_DEFRAG | + EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | + PAGE_CLEAR_DIRTY | + PAGE_SET_WRITEBACK | + PAGE_END_WRITEBACK); btrfs_free_path(path); return ret; } @@ -2132,6 +2045,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id, WARN_ON(1); return ret; } + ret = 0; while (1) { cond_resched(); @@ -2166,16 +2080,21 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id, if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr) continue; - extent_offset = btrfs_file_extent_offset(leaf, extent); - if (key.offset - extent_offset != offset) + /* + * 'offset' refers to the exact key.offset, + * NOT the 'offset' field in btrfs_extent_data_ref, ie. + * (key.offset - extent_offset). + */ + if (key.offset != offset) continue; + extent_offset = btrfs_file_extent_offset(leaf, extent); num_bytes = btrfs_file_extent_num_bytes(leaf, extent); + if (extent_offset >= old->extent_offset + old->offset + old->len || extent_offset + num_bytes <= old->extent_offset + old->offset) continue; - break; } @@ -2187,7 +2106,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id, backref->root_id = root_id; backref->inum = inum; - backref->file_pos = offset + extent_offset; + backref->file_pos = offset; backref->num_bytes = num_bytes; backref->extent_offset = extent_offset; backref->generation = btrfs_file_extent_generation(leaf, extent); @@ -2210,7 +2129,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path, new->path = path; list_for_each_entry_safe(old, tmp, &new->head, list) { - ret = iterate_inodes_from_logical(old->bytenr, fs_info, + ret = iterate_inodes_from_logical(old->bytenr + + old->extent_offset, fs_info, path, record_one_backref, old); BUG_ON(ret < 0 && ret != -ENOENT); @@ -2230,16 +2150,18 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path, static int relink_is_mergable(struct extent_buffer *leaf, struct btrfs_file_extent_item *fi, - u64 disk_bytenr) + struct new_sa_defrag_extent *new) { - if (btrfs_file_extent_disk_bytenr(leaf, fi) != disk_bytenr) + if (btrfs_file_extent_disk_bytenr(leaf, fi) != new->bytenr) return 0; if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG) return 0; - if (btrfs_file_extent_compression(leaf, fi) || - btrfs_file_extent_encryption(leaf, fi) || + if (btrfs_file_extent_compression(leaf, fi) != new->compress_type) + return 0; + + if (btrfs_file_extent_encryption(leaf, fi) || btrfs_file_extent_other_encoding(leaf, fi)) return 0; @@ -2383,8 +2305,8 @@ again: struct btrfs_file_extent_item); extent_len = btrfs_file_extent_num_bytes(leaf, fi); - if (relink_is_mergable(leaf, fi, new->bytenr) && - extent_len + found_key.offset == start) { + if (extent_len + found_key.offset == start && + relink_is_mergable(leaf, fi, new)) { btrfs_set_file_extent_num_bytes(leaf, fi, extent_len + len); btrfs_mark_buffer_dirty(leaf); @@ -2640,8 +2562,10 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) struct extent_state *cached_state = NULL; struct new_sa_defrag_extent *new = NULL; int compress_type = 0; - int ret; + int ret = 0; + u64 logical_len = ordered_extent->len; bool nolock; + bool truncated = false; nolock = btrfs_is_free_space_inode(inode); @@ -2650,6 +2574,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } + if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { + truncated = true; + logical_len = ordered_extent->truncated_len; + /* Truncated the entire extent, don't bother adding */ + if (!logical_len) + goto out; + } + if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */ btrfs_ordered_update_i_size(inode, 0, ordered_extent); @@ -2705,15 +2637,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) ret = btrfs_mark_extent_written(trans, inode, ordered_extent->file_offset, ordered_extent->file_offset + - ordered_extent->len); + logical_len); } else { BUG_ON(root == root->fs_info->tree_root); ret = insert_reserved_file_extent(trans, inode, ordered_extent->file_offset, ordered_extent->start, ordered_extent->disk_len, - ordered_extent->len, - ordered_extent->len, + logical_len, logical_len, compress_type, 0, 0, BTRFS_FILE_EXTENT_REG); } @@ -2745,17 +2676,27 @@ out: if (trans) btrfs_end_transaction(trans, root); - if (ret) { - clear_extent_uptodate(io_tree, ordered_extent->file_offset, - ordered_extent->file_offset + - ordered_extent->len - 1, NULL, GFP_NOFS); + if (ret || truncated) { + u64 start, end; + + if (truncated) + start = ordered_extent->file_offset + logical_len; + else + start = ordered_extent->file_offset; + end = ordered_extent->file_offset + ordered_extent->len - 1; + clear_extent_uptodate(io_tree, start, end, NULL, GFP_NOFS); + + /* Drop the cache for the part of the extent we didn't write. */ + btrfs_drop_extent_cache(inode, start, end, 0); /* * If the ordered extent had an IOERR or something else went * wrong we need to return the space for this ordered extent - * back to the allocator. + * back to the allocator. We only free the extent in the + * truncated case if we didn't write out the extent at all. */ - if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) && + if ((ret || !logical_len) && + !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) && !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) btrfs_free_reserved_extent(root, ordered_extent->start, ordered_extent->disk_len); @@ -2819,16 +2760,16 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, * if there's a match, we allow the bio to finish. If not, the code in * extent_io.c will try to find good copies for us. */ -static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state, int mirror) +static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio, + u64 phy_offset, struct page *page, + u64 start, u64 end, int mirror) { size_t offset = start - page_offset(page); struct inode *inode = page->mapping->host; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; char *kaddr; - u64 private = ~(u32)0; - int ret; struct btrfs_root *root = BTRFS_I(inode)->root; + u32 csum_expected; u32 csum = ~(u32)0; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -2848,19 +2789,13 @@ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end, return 0; } - if (state && state->start == start) { - private = state->private; - ret = 0; - } else { - ret = get_state_private(io_tree, start, &private); - } - kaddr = kmap_atomic(page); - if (ret) - goto zeroit; + phy_offset >>= inode->i_sb->s_blocksize_bits; + csum_expected = *(((u32 *)io_bio->csum) + phy_offset); + kaddr = kmap_atomic(page); csum = btrfs_csum_data(kaddr + offset, csum, end - start + 1); btrfs_csum_final(csum, (char *)&csum); - if (csum != private) + if (csum != csum_expected) goto zeroit; kunmap_atomic(kaddr); @@ -2869,14 +2804,12 @@ good: zeroit: if (__ratelimit(&_rs)) - btrfs_info(root->fs_info, "csum failed ino %llu off %llu csum %u private %llu", - (unsigned long long)btrfs_ino(page->mapping->host), - (unsigned long long)start, csum, - (unsigned long long)private); + btrfs_info(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u", + btrfs_ino(page->mapping->host), start, csum, csum_expected); memset(kaddr + offset, 1, end - start + 1); flush_dcache_page(page); kunmap_atomic(kaddr); - if (private == 0) + if (csum_expected == 0) return 0; return -EIO; } @@ -2963,8 +2896,10 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, btrfs_root_refs(&root->root_item) > 0) { ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root, root->root_key.objectid); - BUG_ON(ret); - root->orphan_item_inserted = 0; + if (ret) + btrfs_abort_transaction(trans, root, ret); + else + root->orphan_item_inserted = 0; } if (block_rsv) { @@ -3033,11 +2968,18 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) /* insert an orphan item to track this unlinked/truncated file */ if (insert >= 1) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); - if (ret && ret != -EEXIST) { - clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags); - btrfs_abort_transaction(trans, root, ret); - return ret; + if (ret) { + if (reserve) { + clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, + &BTRFS_I(inode)->runtime_flags); + btrfs_orphan_release_metadata(inode); + } + if (ret != -EEXIST) { + clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags); + btrfs_abort_transaction(trans, root, ret); + return ret; + } } ret = 0; } @@ -3076,17 +3018,15 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, release_rsv = 1; spin_unlock(&root->orphan_lock); - if (trans && delete_item) { + if (trans && delete_item) ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); - BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */ - } if (release_rsv) { btrfs_orphan_release_metadata(inode); atomic_dec(&root->orphan_inodes); } - return 0; + return ret; } /* @@ -3166,7 +3106,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) found_key.type = BTRFS_INODE_ITEM_KEY; found_key.offset = 0; inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL); - ret = PTR_RET(inode); + ret = PTR_ERR_OR_ZERO(inode); if (ret && ret != -ESTALE) goto out; @@ -3216,8 +3156,9 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) found_key.objectid); ret = btrfs_del_orphan_item(trans, root, found_key.objectid); - BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */ btrfs_end_transaction(trans, root); + if (ret) + goto out; continue; } @@ -3649,8 +3590,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, if (ret) { btrfs_info(root->fs_info, "failed to delete reference to %.*s, inode %llu parent %llu", - name_len, name, - (unsigned long long)ino, (unsigned long long)dir_ino); + name_len, name, ino, dir_ino); btrfs_abort_transaction(trans, root, ret); goto err; } @@ -3921,6 +3861,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u64 extent_num_bytes = 0; u64 extent_offset = 0; u64 item_end = 0; + u64 last_size = (u64)-1; u32 found_type = (u8)-1; int found_extent; int del_item; @@ -4018,6 +3959,11 @@ search_again: if (found_type != BTRFS_EXTENT_DATA_KEY) goto delete; + if (del_item) + last_size = found_key.offset; + else + last_size = new_size; + if (extent_type != BTRFS_FILE_EXTENT_INLINE) { u64 num_dec; extent_start = btrfs_file_extent_disk_bytenr(leaf, fi); @@ -4129,6 +4075,8 @@ out: btrfs_abort_transaction(trans, root, ret); } error: + if (last_size != (u64)-1) + btrfs_ordered_update_i_size(inode, last_size, NULL); btrfs_free_path(path); return err; } @@ -4391,9 +4339,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) int mask = attr->ia_valid; int ret; - if (newsize == oldsize) - return 0; - /* * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a * special case where we need to update the times despite not having @@ -4404,7 +4349,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb); if (newsize > oldsize) { - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); ret = btrfs_cont_expand(inode, oldsize, newsize); if (ret) return ret; @@ -4460,8 +4405,26 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) btrfs_inode_resume_unlocked_dio(inode); ret = btrfs_truncate(inode); - if (ret && inode->i_nlink) - btrfs_orphan_del(NULL, inode); + if (ret && inode->i_nlink) { + int err; + + /* + * failed to truncate, disk_i_size is only adjusted down + * as we remove extents, so it should represent the true + * size of the inode, so reset the in memory size and + * delete our orphan entry. + */ + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + btrfs_orphan_del(NULL, inode); + return ret; + } + i_size_write(inode, BTRFS_I(inode)->disk_i_size); + err = btrfs_orphan_del(trans, inode); + if (err) + btrfs_abort_transaction(trans, root, err); + btrfs_end_transaction(trans, root); + } } return ret; @@ -4596,10 +4559,15 @@ void btrfs_evict_inode(struct inode *inode) btrfs_free_block_rsv(root, rsv); + /* + * Errors here aren't a big deal, it just means we leave orphan items + * in the tree. They will be cleaned up on the next mount. + */ if (ret == 0) { trans->block_rsv = root->orphan_block_rsv; - ret = btrfs_orphan_del(trans, inode); - BUG_ON(ret); + btrfs_orphan_del(trans, inode); + } else { + btrfs_orphan_del(NULL, inode); } trans->block_rsv = &root->fs_info->trans_block_rsv; @@ -5165,14 +5133,31 @@ next: } /* Reached end of directory/root. Bump pos past the last item. */ - if (key_type == BTRFS_DIR_INDEX_KEY) - /* - * 32-bit glibc will use getdents64, but then strtol - - * so the last number we can serve is this. - */ - ctx->pos = 0x7fffffff; - else - ctx->pos++; + ctx->pos++; + + /* + * Stop new entries from being returned after we return the last + * entry. + * + * New directory entries are assigned a strictly increasing + * offset. This means that new entries created during readdir + * are *guaranteed* to be seen in the future by that readdir. + * This has broken buggy programs which operate on names as + * they're returned by readdir. Until we re-use freed offsets + * we have this hack to stop new entries from being returned + * under the assumption that they'll never reach this huge + * offset. + * + * This is being careful not to overflow 32bit loff_t unless the + * last entry requires it because doing so has broken 32bit apps + * in the past. + */ + if (key_type == BTRFS_DIR_INDEX_KEY) { + if (ctx->pos >= INT_MAX) + ctx->pos = LLONG_MAX; + else + ctx->pos = INT_MAX; + } nopos: ret = 0; err: @@ -6139,10 +6124,7 @@ insert: btrfs_release_path(path); if (em->start > start || extent_map_end(em) <= start) { btrfs_err(root->fs_info, "bad extent! em: [%llu %llu] passed [%llu %llu]", - (unsigned long long)em->start, - (unsigned long long)em->len, - (unsigned long long)start, - (unsigned long long)len); + em->start, em->len, start, len); err = -EIO; goto out; } @@ -6340,39 +6322,32 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, u64 start, u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_trans_handle *trans; struct extent_map *em; struct btrfs_key ins; u64 alloc_hint; int ret; - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return ERR_CAST(trans); - - trans->block_rsv = &root->fs_info->delalloc_block_rsv; - alloc_hint = get_extent_allocation_hint(inode, start, len); - ret = btrfs_reserve_extent(trans, root, len, root->sectorsize, 0, + ret = btrfs_reserve_extent(root, len, root->sectorsize, 0, alloc_hint, &ins, 1); - if (ret) { - em = ERR_PTR(ret); - goto out; - } + if (ret) + return ERR_PTR(ret); em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, ins.offset, ins.offset, ins.offset, 0); - if (IS_ERR(em)) - goto out; + if (IS_ERR(em)) { + btrfs_free_reserved_extent(root, ins.objectid, ins.offset); + return em; + } ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, ins.offset, ins.offset, 0); if (ret) { btrfs_free_reserved_extent(root, ins.objectid, ins.offset); - em = ERR_PTR(ret); + free_extent_map(em); + return ERR_PTR(ret); } -out: - btrfs_end_transaction(trans, root); + return em; } @@ -6380,11 +6355,11 @@ out: * returns 1 when the nocow is safe, < 1 on error, 0 if the * block must be cow'd */ -noinline int can_nocow_extent(struct btrfs_trans_handle *trans, - struct inode *inode, u64 offset, u64 *len, +noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, u64 *ram_bytes) { + struct btrfs_trans_handle *trans; struct btrfs_path *path; int ret; struct extent_buffer *leaf; @@ -6402,7 +6377,7 @@ noinline int can_nocow_extent(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode), + ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode), offset, 0); if (ret < 0) goto out; @@ -6467,9 +6442,19 @@ noinline int can_nocow_extent(struct btrfs_trans_handle *trans, * look for other files referencing this extent, if we * find any we must cow */ - if (btrfs_cross_ref_exist(trans, root, btrfs_ino(inode), - key.offset - backref_offset, disk_bytenr)) + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + ret = 0; goto out; + } + + ret = btrfs_cross_ref_exist(trans, root, btrfs_ino(inode), + key.offset - backref_offset, disk_bytenr); + btrfs_end_transaction(trans, root); + if (ret) { + ret = 0; + goto out; + } /* * adjust disk_bytenr and num_bytes to cover just the bytes @@ -6611,7 +6596,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, u64 start = iblock << inode->i_blkbits; u64 lockstart, lockend; u64 len = bh_result->b_size; - struct btrfs_trans_handle *trans; int unlock_bits = EXTENT_LOCKED; int ret = 0; @@ -6693,16 +6677,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, len = min(len, em->len - (start - em->start)); block_start = em->block_start + (start - em->start); - /* - * we're not going to log anything, but we do need - * to make sure the current transaction stays open - * while we look for nocow cross refs - */ - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - goto must_cow; - - if (can_nocow_extent(trans, inode, start, &len, &orig_start, + if (can_nocow_extent(inode, start, &len, &orig_start, &orig_block_len, &ram_bytes) == 1) { if (type == BTRFS_ORDERED_PREALLOC) { free_extent_map(em); @@ -6711,24 +6686,20 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, block_start, len, orig_block_len, ram_bytes, type); - if (IS_ERR(em)) { - btrfs_end_transaction(trans, root); + if (IS_ERR(em)) goto unlock_err; - } } ret = btrfs_add_ordered_extent_dio(inode, start, block_start, len, len, type); - btrfs_end_transaction(trans, root); if (ret) { free_extent_map(em); goto unlock_err; } goto unlock; } - btrfs_end_transaction(trans, root); } -must_cow: + /* * this will cow the extent, reset the len in case we changed * it above @@ -6791,26 +6762,6 @@ unlock_err: return ret; } -struct btrfs_dio_private { - struct inode *inode; - u64 logical_offset; - u64 disk_bytenr; - u64 bytes; - void *private; - - /* number of bios pending for this dio */ - atomic_t pending_bios; - - /* IO errors */ - int errors; - - /* orig_bio is our btrfs_io_bio */ - struct bio *orig_bio; - - /* dio_bio came from fs/direct-io.c */ - struct bio *dio_bio; -}; - static void btrfs_endio_direct_read(struct bio *bio, int err) { struct btrfs_dio_private *dip = bio->bi_private; @@ -6819,6 +6770,8 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct inode *inode = dip->inode; struct btrfs_root *root = BTRFS_I(inode)->root; struct bio *dio_bio; + u32 *csums = (u32 *)dip->csum; + int index = 0; u64 start; start = dip->logical_offset; @@ -6827,12 +6780,8 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct page *page = bvec->bv_page; char *kaddr; u32 csum = ~(u32)0; - u64 private = ~(u32)0; unsigned long flags; - if (get_state_private(&BTRFS_I(inode)->io_tree, - start, &private)) - goto failed; local_irq_save(flags); kaddr = kmap_atomic(page); csum = btrfs_csum_data(kaddr + bvec->bv_offset, @@ -6842,18 +6791,17 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) local_irq_restore(flags); flush_dcache_page(bvec->bv_page); - if (csum != private) { -failed: - btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u private %u", - (unsigned long long)btrfs_ino(inode), - (unsigned long long)start, - csum, (unsigned)private); + if (csum != csums[index]) { + btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u", + btrfs_ino(inode), start, csum, + csums[index]); err = -EIO; } } start += bvec->bv_len; bvec++; + index++; } while (bvec <= bvec_end); unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, @@ -6934,7 +6882,7 @@ static void btrfs_end_dio_bio(struct bio *bio, int err) if (err) { printk(KERN_ERR "btrfs direct IO failed ino %llu rw %lu " "sector %#Lx len %u err no %d\n", - (unsigned long long)btrfs_ino(dip->inode), bio->bi_rw, + btrfs_ino(dip->inode), bio->bi_rw, (unsigned long long)bio->bi_sector, bio->bi_size, err); dip->errors = 1; @@ -6970,6 +6918,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, int rw, u64 file_offset, int skip_sum, int async_submit) { + struct btrfs_dio_private *dip = bio->bi_private; int write = rw & REQ_WRITE; struct btrfs_root *root = BTRFS_I(inode)->root; int ret; @@ -7004,7 +6953,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, if (ret) goto err; } else if (!skip_sum) { - ret = btrfs_lookup_bio_sums_dio(root, inode, bio, file_offset); + ret = btrfs_lookup_bio_sums_dio(root, inode, dip, bio, + file_offset); if (ret) goto err; } @@ -7039,6 +6989,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, bio_put(orig_bio); return -EIO; } + if (map_length >= orig_bio->bi_size) { bio = orig_bio; goto submit; @@ -7134,19 +7085,28 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio, struct btrfs_dio_private *dip; struct bio *io_bio; int skip_sum; + int sum_len; int write = rw & REQ_WRITE; int ret = 0; + u16 csum_size; skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS); - if (!io_bio) { ret = -ENOMEM; goto free_ordered; } - dip = kmalloc(sizeof(*dip), GFP_NOFS); + if (!skip_sum && !write) { + csum_size = btrfs_super_csum_size(root->fs_info->super_copy); + sum_len = dio_bio->bi_size >> inode->i_sb->s_blocksize_bits; + sum_len *= csum_size; + } else { + sum_len = 0; + } + + dip = kmalloc(sizeof(*dip) + sum_len, GFP_NOFS); if (!dip) { ret = -ENOMEM; goto free_io_bio; @@ -7421,10 +7381,23 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, * whoever cleared the private bit is responsible * for the finish_ordered_io */ - if (TestClearPagePrivate2(page) && - btrfs_dec_test_ordered_pending(inode, &ordered, page_start, - PAGE_CACHE_SIZE, 1)) { - btrfs_finish_ordered_io(ordered); + if (TestClearPagePrivate2(page)) { + struct btrfs_ordered_inode_tree *tree; + u64 new_len; + + tree = &BTRFS_I(inode)->ordered_tree; + + spin_lock_irq(&tree->lock); + set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags); + new_len = page_start - ordered->file_offset; + if (new_len < ordered->truncated_len) + ordered->truncated_len = new_len; + spin_unlock_irq(&tree->lock); + + if (btrfs_dec_test_ordered_pending(inode, &ordered, + page_start, + PAGE_CACHE_SIZE, 1)) + btrfs_finish_ordered_io(ordered); } btrfs_put_ordered_extent(ordered); cached_state = NULL; @@ -7590,7 +7563,6 @@ static int btrfs_truncate(struct inode *inode) u64 min_size = btrfs_calc_trunc_metadata_size(root, 1); btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1); - btrfs_ordered_update_i_size(inode, inode->i_size, NULL); /* * Yes ladies and gentelment, this is indeed ugly. The fact is we have @@ -7854,7 +7826,7 @@ void btrfs_destroy_inode(struct inode *inode) if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &BTRFS_I(inode)->runtime_flags)) { btrfs_info(root->fs_info, "inode %llu still on the orphan list", - (unsigned long long)btrfs_ino(inode)); + btrfs_ino(inode)); atomic_dec(&root->orphan_inodes); } @@ -7864,8 +7836,7 @@ void btrfs_destroy_inode(struct inode *inode) break; else { btrfs_err(root->fs_info, "found ordered extent %llu %llu on inode cleanup", - (unsigned long long)ordered->file_offset, - (unsigned long long)ordered->len); + ordered->file_offset, ordered->len); btrfs_remove_ordered_extent(inode, ordered); btrfs_put_ordered_extent(ordered); btrfs_put_ordered_extent(ordered); @@ -8139,10 +8110,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dentry->d_name.name, new_dentry->d_name.len); } - if (!ret && new_inode->i_nlink == 0) { + if (!ret && new_inode->i_nlink == 0) ret = btrfs_orphan_add(trans, new_dentry->d_inode); - BUG_ON(ret); - } if (ret) { btrfs_abort_transaction(trans, root, ret); goto out_fail; @@ -8503,8 +8472,8 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, cur_bytes = min(num_bytes, 256ULL * 1024 * 1024); cur_bytes = max(cur_bytes, min_size); - ret = btrfs_reserve_extent(trans, root, cur_bytes, - min_size, 0, *alloc_hint, &ins, 1); + ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, + *alloc_hint, &ins, 1); if (ret) { if (own_trans) btrfs_end_transaction(trans, root); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 238a055..1a5b946 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -43,6 +43,7 @@ #include <linux/blkdev.h> #include <linux/uuid.h> #include <linux/btrfs.h> +#include <linux/uaccess.h> #include "compat.h" #include "ctree.h" #include "disk-io.h" @@ -57,6 +58,9 @@ #include "send.h" #include "dev-replace.h" +static int btrfs_clone(struct inode *src, struct inode *inode, + u64 off, u64 olen, u64 olen_aligned, u64 destoff); + /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags) { @@ -363,6 +367,13 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) return 0; } +int btrfs_is_empty_uuid(u8 *uuid) +{ + static char empty_uuid[BTRFS_UUID_SIZE] = {0}; + + return !memcmp(uuid, empty_uuid, BTRFS_UUID_SIZE); +} + static noinline int create_subvol(struct inode *dir, struct dentry *dentry, char *name, int namelen, @@ -396,7 +407,7 @@ static noinline int create_subvol(struct inode *dir, * of create_snapshot(). */ ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, - 7, &qgroup_reserved); + 8, &qgroup_reserved, false); if (ret) return ret; @@ -425,26 +436,25 @@ static noinline int create_subvol(struct inode *dir, btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(leaf, objectid); - write_extent_buffer(leaf, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(leaf), + write_extent_buffer(leaf, root->fs_info->fsid, btrfs_header_fsid(leaf), BTRFS_FSID_SIZE); write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(leaf), + btrfs_header_chunk_tree_uuid(leaf), BTRFS_UUID_SIZE); btrfs_mark_buffer_dirty(leaf); memset(&root_item, 0, sizeof(root_item)); inode_item = &root_item.inode; - inode_item->generation = cpu_to_le64(1); - inode_item->size = cpu_to_le64(3); - inode_item->nlink = cpu_to_le32(1); - inode_item->nbytes = cpu_to_le64(root->leafsize); - inode_item->mode = cpu_to_le32(S_IFDIR | 0755); + btrfs_set_stack_inode_generation(inode_item, 1); + btrfs_set_stack_inode_size(inode_item, 3); + btrfs_set_stack_inode_nlink(inode_item, 1); + btrfs_set_stack_inode_nbytes(inode_item, root->leafsize); + btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755); - root_item.flags = 0; - root_item.byte_limit = 0; - inode_item->flags = cpu_to_le64(BTRFS_INODE_ROOT_ITEM_INIT); + btrfs_set_root_flags(&root_item, 0); + btrfs_set_root_limit(&root_item, 0); + btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT); btrfs_set_root_bytenr(&root_item, leaf->start); btrfs_set_root_generation(&root_item, trans->transid); @@ -457,8 +467,8 @@ static noinline int create_subvol(struct inode *dir, btrfs_root_generation(&root_item)); uuid_le_gen(&new_uuid); memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE); - root_item.otime.sec = cpu_to_le64(cur_time.tv_sec); - root_item.otime.nsec = cpu_to_le32(cur_time.tv_nsec); + btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec); + btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec); root_item.ctime = root_item.otime; btrfs_set_root_ctransid(&root_item, trans->transid); btrfs_set_root_otransid(&root_item, trans->transid); @@ -518,9 +528,14 @@ static noinline int create_subvol(struct inode *dir, ret = btrfs_add_root_ref(trans, root->fs_info->tree_root, objectid, root->root_key.objectid, btrfs_ino(dir), index, name, namelen); - BUG_ON(ret); + ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root, + root_item.uuid, BTRFS_UUID_KEY_SUBVOL, + objectid); + if (ret) + btrfs_abort_transaction(trans, root, ret); + fail: trans->block_rsv = NULL; trans->bytes_reserved = 0; @@ -573,10 +588,12 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, * 1 - root item * 2 - root ref/backref * 1 - root of snapshot + * 1 - UUID item */ ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, - &pending_snapshot->block_rsv, 7, - &pending_snapshot->qgroup_reserved); + &pending_snapshot->block_rsv, 8, + &pending_snapshot->qgroup_reserved, + false); if (ret) goto out; @@ -1267,9 +1284,6 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, cluster = max_cluster; } - if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) - BTRFS_I(inode)->force_compress = compress_type; - if (i + cluster > ra_index) { ra_index = max(i, ra_index); btrfs_force_ra(inode->i_mapping, ra, file, ra_index, @@ -1278,6 +1292,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, } mutex_lock(&inode->i_mutex); + if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) + BTRFS_I(inode)->force_compress = compress_type; ret = cluster_pages_for_defrag(inode, pages, i, cluster); if (ret < 0) { mutex_unlock(&inode->i_mutex); @@ -1334,10 +1350,6 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, atomic_read(&root->fs_info->async_delalloc_pages) == 0)); } atomic_dec(&root->fs_info->async_submit_draining); - - mutex_lock(&inode->i_mutex); - BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE; - mutex_unlock(&inode->i_mutex); } if (range->compress_type == BTRFS_COMPRESS_LZO) { @@ -1347,6 +1359,11 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, ret = defrag_count; out_ra: + if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) { + mutex_lock(&inode->i_mutex); + BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE; + mutex_unlock(&inode->i_mutex); + } if (!file) kfree(ra); kfree(pages); @@ -1377,9 +1394,8 @@ static noinline int btrfs_ioctl_resize(struct file *file, if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running, 1)) { - pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n"); mnt_drop_write_file(file); - return -EINVAL; + return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; } mutex_lock(&root->fs_info->volume_mutex); @@ -1403,14 +1419,13 @@ static noinline int btrfs_ioctl_resize(struct file *file, ret = -EINVAL; goto out_free; } - printk(KERN_INFO "btrfs: resizing devid %llu\n", - (unsigned long long)devid); + printk(KERN_INFO "btrfs: resizing devid %llu\n", devid); } device = btrfs_find_device(root->fs_info, devid, NULL, NULL); if (!device) { printk(KERN_INFO "btrfs: resizer unable to find device %llu\n", - (unsigned long long)devid); + devid); ret = -ENODEV; goto out_free; } @@ -1418,7 +1433,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, if (!device->writeable) { printk(KERN_INFO "btrfs: resizer unable to apply on " "readonly device %llu\n", - (unsigned long long)devid); + devid); ret = -EPERM; goto out_free; } @@ -1470,8 +1485,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, new_size *= root->sectorsize; printk_in_rcu(KERN_INFO "btrfs: new size for %s is %llu\n", - rcu_str_deref(device->name), - (unsigned long long)new_size); + rcu_str_deref(device->name), new_size); if (new_size > old_size) { trans = btrfs_start_transaction(root, 0); @@ -1721,13 +1735,28 @@ out: static noinline int may_destroy_subvol(struct btrfs_root *root) { struct btrfs_path *path; + struct btrfs_dir_item *di; struct btrfs_key key; + u64 dir_id; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; + /* Make sure this root isn't set as the default subvol */ + dir_id = btrfs_super_root_dir(root->fs_info->super_copy); + di = btrfs_lookup_dir_item(NULL, root->fs_info->tree_root, path, + dir_id, "default", 7, 0); + if (di && !IS_ERR(di)) { + btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); + if (key.objectid == root->root_key.objectid) { + ret = -ENOTEMPTY; + goto out; + } + btrfs_release_path(path); + } + key.objectid = root->root_key.objectid; key.type = BTRFS_ROOT_REF_KEY; key.offset = (u64)-1; @@ -1993,25 +2022,29 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; + else if (ret > 0) { + ret = btrfs_previous_item(root, path, dirid, + BTRFS_INODE_REF_KEY); + if (ret < 0) + goto out; + else if (ret > 0) { + ret = -ENOENT; + goto out; + } + } l = path->nodes[0]; slot = path->slots[0]; - if (ret > 0 && slot > 0) - slot--; btrfs_item_key_to_cpu(l, &key, slot); - if (ret > 0 && (key.objectid != dirid || - key.type != BTRFS_INODE_REF_KEY)) { - ret = -ENOENT; - goto out; - } - iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref); len = btrfs_inode_ref_name_len(l, iref); ptr -= len + 1; total_len += len + 1; - if (ptr < name) + if (ptr < name) { + ret = -ENAMETOOLONG; goto out; + } *(ptr + len) = '/'; read_extent_buffer(l, ptr,(unsigned long)(iref + 1), len); @@ -2024,8 +2057,6 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.offset = (u64)-1; dirid = key.objectid; } - if (ptr < name) - goto out; memmove(name, ptr, total_len); name[total_len]='\0'; ret = 0; @@ -2174,7 +2205,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, * ref/backref. */ err = btrfs_subvolume_reserve_metadata(root, &block_rsv, - 5, &qgroup_reserved); + 5, &qgroup_reserved, true); if (err) goto out_up_write; @@ -2213,6 +2244,27 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto out_end_trans; } } + + ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root, + dest->root_item.uuid, BTRFS_UUID_KEY_SUBVOL, + dest->root_key.objectid); + if (ret && ret != -ENOENT) { + btrfs_abort_transaction(trans, root, ret); + err = ret; + goto out_end_trans; + } + if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { + ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root, + dest->root_item.received_uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + dest->root_key.objectid); + if (ret && ret != -ENOENT) { + btrfs_abort_transaction(trans, root, ret); + err = ret; + goto out_end_trans; + } + } + out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; @@ -2326,8 +2378,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg) if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running, 1)) { - pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n"); - return -EINVAL; + return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; } mutex_lock(&root->fs_info->volume_mutex); @@ -2400,10 +2451,10 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg) if (!fi_args) return -ENOMEM; + mutex_lock(&fs_devices->device_list_mutex); fi_args->num_devices = fs_devices->num_devices; memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid)); - mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) { if (device->devid > fi_args->max_id) fi_args->max_id = device->devid; @@ -2424,7 +2475,6 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg) struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; int ret = 0; char *s_uuid = NULL; - char empty_uuid[BTRFS_UUID_SIZE] = {0}; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2433,7 +2483,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg) if (IS_ERR(di_args)) return PTR_ERR(di_args); - if (memcmp(empty_uuid, di_args->uuid, BTRFS_UUID_SIZE) != 0) + if (!btrfs_is_empty_uuid(di_args->uuid)) s_uuid = di_args->uuid; mutex_lock(&fs_devices->device_list_mutex); @@ -2469,150 +2519,336 @@ out: return ret; } -static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, - u64 off, u64 olen, u64 destoff) +static struct page *extent_same_get_page(struct inode *inode, u64 off) +{ + struct page *page; + pgoff_t index; + struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; + + index = off >> PAGE_CACHE_SHIFT; + + page = grab_cache_page(inode->i_mapping, index); + if (!page) + return NULL; + + if (!PageUptodate(page)) { + if (extent_read_full_page_nolock(tree, page, btrfs_get_extent, + 0)) + return NULL; + lock_page(page); + if (!PageUptodate(page)) { + unlock_page(page); + page_cache_release(page); + return NULL; + } + } + unlock_page(page); + + return page; +} + +static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) +{ + /* do any pending delalloc/csum calc on src, one way or + another, and lock file content */ + while (1) { + struct btrfs_ordered_extent *ordered; + lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); + ordered = btrfs_lookup_first_ordered_extent(inode, + off + len - 1); + if (!ordered && + !test_range_bit(&BTRFS_I(inode)->io_tree, off, + off + len - 1, EXTENT_DELALLOC, 0, NULL)) + break; + unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); + if (ordered) + btrfs_put_ordered_extent(ordered); + btrfs_wait_ordered_range(inode, off, len); + } +} + +static void btrfs_double_unlock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len) +{ + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); + unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); + + mutex_unlock(&inode1->i_mutex); + mutex_unlock(&inode2->i_mutex); +} + +static void btrfs_double_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len) +{ + if (inode1 < inode2) { + swap(inode1, inode2); + swap(loff1, loff2); + } + + mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT); + lock_extent_range(inode1, loff1, len); + if (inode1 != inode2) { + mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD); + lock_extent_range(inode2, loff2, len); + } +} + +static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, + u64 dst_loff, u64 len) +{ + int ret = 0; + struct page *src_page, *dst_page; + unsigned int cmp_len = PAGE_CACHE_SIZE; + void *addr, *dst_addr; + + while (len) { + if (len < PAGE_CACHE_SIZE) + cmp_len = len; + + src_page = extent_same_get_page(src, loff); + if (!src_page) + return -EINVAL; + dst_page = extent_same_get_page(dst, dst_loff); + if (!dst_page) { + page_cache_release(src_page); + return -EINVAL; + } + addr = kmap_atomic(src_page); + dst_addr = kmap_atomic(dst_page); + + flush_dcache_page(src_page); + flush_dcache_page(dst_page); + + if (memcmp(addr, dst_addr, cmp_len)) + ret = BTRFS_SAME_DATA_DIFFERS; + + kunmap_atomic(addr); + kunmap_atomic(dst_addr); + page_cache_release(src_page); + page_cache_release(dst_page); + + if (ret) + break; + + loff += cmp_len; + dst_loff += cmp_len; + len -= cmp_len; + } + + return ret; +} + +static int extent_same_check_offsets(struct inode *inode, u64 off, u64 len) +{ + u64 bs = BTRFS_I(inode)->root->fs_info->sb->s_blocksize; + + if (off + len > inode->i_size || off + len < off) + return -EINVAL; + /* Check that we are block aligned - btrfs_clone() requires this */ + if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs)) + return -EINVAL; + + return 0; +} + +static int btrfs_extent_same(struct inode *src, u64 loff, u64 len, + struct inode *dst, u64 dst_loff) { - struct inode *inode = file_inode(file); - struct btrfs_root *root = BTRFS_I(inode)->root; - struct fd src_file; - struct inode *src; - struct btrfs_trans_handle *trans; - struct btrfs_path *path; - struct extent_buffer *leaf; - char *buf; - struct btrfs_key key; - u32 nritems; - int slot; int ret; - u64 len = olen; - u64 bs = root->fs_info->sb->s_blocksize; - int same_inode = 0; /* - * TODO: - * - split compressed inline extents. annoying: we need to - * decompress into destination's address_space (the file offset - * may change, so source mapping won't do), then recompress (or - * otherwise reinsert) a subrange. - * - allow ranges within the same file to be cloned (provided - * they don't overlap)? + * btrfs_clone() can't handle extents in the same file + * yet. Once that works, we can drop this check and replace it + * with a check for the same inode, but overlapping extents. */ - - /* the destination must be opened for writing */ - if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) + if (src == dst) return -EINVAL; - if (btrfs_root_readonly(root)) - return -EROFS; + btrfs_double_lock(src, loff, dst, dst_loff, len); + + ret = extent_same_check_offsets(src, loff, len); + if (ret) + goto out_unlock; + + ret = extent_same_check_offsets(dst, dst_loff, len); + if (ret) + goto out_unlock; + + /* don't make the dst file partly checksummed */ + if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != + (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) { + ret = -EINVAL; + goto out_unlock; + } + + ret = btrfs_cmp_data(src, loff, dst, dst_loff, len); + if (ret == 0) + ret = btrfs_clone(src, dst, loff, len, len, dst_loff); + +out_unlock: + btrfs_double_unlock(src, loff, dst, dst_loff, len); + + return ret; +} + +#define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024) + +static long btrfs_ioctl_file_extent_same(struct file *file, + void __user *argp) +{ + struct btrfs_ioctl_same_args *args = argp; + struct btrfs_ioctl_same_args same; + struct btrfs_ioctl_same_extent_info info; + struct inode *src = file->f_dentry->d_inode; + struct file *dst_file = NULL; + struct inode *dst; + u64 off; + u64 len; + int i; + int ret; + u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; + bool is_admin = capable(CAP_SYS_ADMIN); + + if (!(file->f_mode & FMODE_READ)) + return -EINVAL; ret = mnt_want_write_file(file); if (ret) return ret; - src_file = fdget(srcfd); - if (!src_file.file) { - ret = -EBADF; - goto out_drop_write; + if (copy_from_user(&same, + (struct btrfs_ioctl_same_args __user *)argp, + sizeof(same))) { + ret = -EFAULT; + goto out; } - ret = -EXDEV; - if (src_file.file->f_path.mnt != file->f_path.mnt) - goto out_fput; + off = same.logical_offset; + len = same.length; - src = file_inode(src_file.file); + /* + * Limit the total length we will dedupe for each operation. + * This is intended to bound the total time spent in this + * ioctl to something sane. + */ + if (len > BTRFS_MAX_DEDUPE_LEN) + len = BTRFS_MAX_DEDUPE_LEN; - ret = -EINVAL; - if (src == inode) - same_inode = 1; + if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) { + /* + * Btrfs does not support blocksize < page_size. As a + * result, btrfs_cmp_data() won't correctly handle + * this situation without an update. + */ + ret = -EINVAL; + goto out; + } - /* the src must be open for reading */ - if (!(src_file.file->f_mode & FMODE_READ)) - goto out_fput; + ret = -EISDIR; + if (S_ISDIR(src->i_mode)) + goto out; - /* don't make the dst file partly checksummed */ - if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != - (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) - goto out_fput; + ret = -EACCES; + if (!S_ISREG(src->i_mode)) + goto out; - ret = -EISDIR; - if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode)) - goto out_fput; + ret = 0; + for (i = 0; i < same.dest_count; i++) { + if (copy_from_user(&info, &args->info[i], sizeof(info))) { + ret = -EFAULT; + goto out; + } - ret = -EXDEV; - if (src->i_sb != inode->i_sb) - goto out_fput; + info.bytes_deduped = 0; - ret = -ENOMEM; - buf = vmalloc(btrfs_level_size(root, 0)); - if (!buf) - goto out_fput; + dst_file = fget(info.fd); + if (!dst_file) { + info.status = -EBADF; + goto next; + } - path = btrfs_alloc_path(); - if (!path) { - vfree(buf); - goto out_fput; - } - path->reada = 2; + if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { + info.status = -EINVAL; + goto next; + } - if (!same_inode) { - if (inode < src) { - mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); + info.status = -EXDEV; + if (file->f_path.mnt != dst_file->f_path.mnt) + goto next; + + dst = dst_file->f_dentry->d_inode; + if (src->i_sb != dst->i_sb) + goto next; + + if (S_ISDIR(dst->i_mode)) { + info.status = -EISDIR; + goto next; } - } else { - mutex_lock(&src->i_mutex); - } - /* determine range to clone */ - ret = -EINVAL; - if (off + len > src->i_size || off + len < off) - goto out_unlock; - if (len == 0) - olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) - len = ALIGN(src->i_size, bs) - off; + if (!S_ISREG(dst->i_mode)) { + info.status = -EACCES; + goto next; + } - /* verify the end result is block aligned */ - if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || - !IS_ALIGNED(destoff, bs)) - goto out_unlock; + info.status = btrfs_extent_same(src, off, len, dst, + info.logical_offset); + if (info.status == 0) + info.bytes_deduped += len; - /* verify if ranges are overlapped within the same file */ - if (same_inode) { - if (destoff + len > off && destoff < off + len) - goto out_unlock; - } +next: + if (dst_file) + fput(dst_file); - if (destoff > inode->i_size) { - ret = btrfs_cont_expand(inode, inode->i_size, destoff); - if (ret) - goto out_unlock; + if (__put_user_unaligned(info.status, &args->info[i].status) || + __put_user_unaligned(info.bytes_deduped, + &args->info[i].bytes_deduped)) { + ret = -EFAULT; + goto out; + } } - /* truncate page cache pages from target inode range */ - truncate_inode_pages_range(&inode->i_data, destoff, - PAGE_CACHE_ALIGN(destoff + len) - 1); +out: + mnt_drop_write_file(file); + return ret; +} - /* do any pending delalloc/csum calc on src, one way or - another, and lock file content */ - while (1) { - struct btrfs_ordered_extent *ordered; - lock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1); - ordered = btrfs_lookup_first_ordered_extent(src, off + len - 1); - if (!ordered && - !test_range_bit(&BTRFS_I(src)->io_tree, off, off + len - 1, - EXTENT_DELALLOC, 0, NULL)) - break; - unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1); - if (ordered) - btrfs_put_ordered_extent(ordered); - btrfs_wait_ordered_range(src, off, len); +/** + * btrfs_clone() - clone a range from inode file to another + * + * @src: Inode to clone from + * @inode: Inode to clone to + * @off: Offset within source to start clone from + * @olen: Original length, passed by user, of range to clone + * @olen_aligned: Block-aligned value of olen, extent_same uses + * identical values here + * @destoff: Offset within @inode to start clone + */ +static int btrfs_clone(struct inode *src, struct inode *inode, + u64 off, u64 olen, u64 olen_aligned, u64 destoff) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_path *path = NULL; + struct extent_buffer *leaf; + struct btrfs_trans_handle *trans; + char *buf = NULL; + struct btrfs_key key; + u32 nritems; + int slot; + int ret; + u64 len = olen_aligned; + + ret = -ENOMEM; + buf = vmalloc(btrfs_level_size(root, 0)); + if (!buf) + return ret; + + path = btrfs_alloc_path(); + if (!path) { + vfree(buf); + return ret; } + path->reada = 2; /* clone data */ key.objectid = btrfs_ino(src); key.type = BTRFS_EXTENT_DATA_KEY; @@ -2858,15 +3094,132 @@ next: key.offset++; } ret = 0; + out: btrfs_release_path(path); + btrfs_free_path(path); + vfree(buf); + return ret; +} + +static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, + u64 off, u64 olen, u64 destoff) +{ + struct inode *inode = fdentry(file)->d_inode; + struct btrfs_root *root = BTRFS_I(inode)->root; + struct fd src_file; + struct inode *src; + int ret; + u64 len = olen; + u64 bs = root->fs_info->sb->s_blocksize; + int same_inode = 0; + + /* + * TODO: + * - split compressed inline extents. annoying: we need to + * decompress into destination's address_space (the file offset + * may change, so source mapping won't do), then recompress (or + * otherwise reinsert) a subrange. + * - allow ranges within the same file to be cloned (provided + * they don't overlap)? + */ + + /* the destination must be opened for writing */ + if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) + return -EINVAL; + + if (btrfs_root_readonly(root)) + return -EROFS; + + ret = mnt_want_write_file(file); + if (ret) + return ret; + + src_file = fdget(srcfd); + if (!src_file.file) { + ret = -EBADF; + goto out_drop_write; + } + + ret = -EXDEV; + if (src_file.file->f_path.mnt != file->f_path.mnt) + goto out_fput; + + src = file_inode(src_file.file); + + ret = -EINVAL; + if (src == inode) + same_inode = 1; + + /* the src must be open for reading */ + if (!(src_file.file->f_mode & FMODE_READ)) + goto out_fput; + + /* don't make the dst file partly checksummed */ + if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != + (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) + goto out_fput; + + ret = -EISDIR; + if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode)) + goto out_fput; + + ret = -EXDEV; + if (src->i_sb != inode->i_sb) + goto out_fput; + + if (!same_inode) { + if (inode < src) { + mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); + } + } else { + mutex_lock(&src->i_mutex); + } + + /* determine range to clone */ + ret = -EINVAL; + if (off + len > src->i_size || off + len < off) + goto out_unlock; + if (len == 0) + olen = len = src->i_size - off; + /* if we extend to eof, continue to block boundary */ + if (off + len == src->i_size) + len = ALIGN(src->i_size, bs) - off; + + /* verify the end result is block aligned */ + if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || + !IS_ALIGNED(destoff, bs)) + goto out_unlock; + + /* verify if ranges are overlapped within the same file */ + if (same_inode) { + if (destoff + len > off && destoff < off + len) + goto out_unlock; + } + + if (destoff > inode->i_size) { + ret = btrfs_cont_expand(inode, inode->i_size, destoff); + if (ret) + goto out_unlock; + } + + /* truncate page cache pages from target inode range */ + truncate_inode_pages_range(&inode->i_data, destoff, + PAGE_CACHE_ALIGN(destoff + len) - 1); + + lock_extent_range(src, off, len); + + ret = btrfs_clone(src, inode, off, olen, len, destoff); + unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1); out_unlock: mutex_unlock(&src->i_mutex); if (!same_inode) mutex_unlock(&inode->i_mutex); - vfree(buf); - btrfs_free_path(path); out_fput: fdput(src_file); out_drop_write: @@ -3312,11 +3665,13 @@ static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg) switch (p->cmd) { case BTRFS_IOCTL_DEV_REPLACE_CMD_START: + if (root->fs_info->sb->s_flags & MS_RDONLY) + return -EROFS; + if (atomic_xchg( &root->fs_info->mutually_exclusive_operation_running, 1)) { - pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n"); - ret = -EINPROGRESS; + ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; } else { ret = btrfs_dev_replace_start(root, p); atomic_set( @@ -3560,8 +3915,7 @@ again: } else { /* this is (1) */ mutex_unlock(&fs_info->balance_mutex); - pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n"); - ret = -EINVAL; + ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; goto out; } @@ -3967,6 +4321,7 @@ static long btrfs_ioctl_set_received_subvol(struct file *file, struct btrfs_trans_handle *trans; struct timespec ct = CURRENT_TIME; int ret = 0; + int received_uuid_changed; ret = mnt_want_write_file(file); if (ret < 0) @@ -3996,7 +4351,11 @@ static long btrfs_ioctl_set_received_subvol(struct file *file, goto out; } - trans = btrfs_start_transaction(root, 1); + /* + * 1 - root item + * 2 - uuid items (received uuid + subvol uuid) + */ + trans = btrfs_start_transaction(root, 3); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; @@ -4007,24 +4366,42 @@ static long btrfs_ioctl_set_received_subvol(struct file *file, sa->rtime.sec = ct.tv_sec; sa->rtime.nsec = ct.tv_nsec; + received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid, + BTRFS_UUID_SIZE); + if (received_uuid_changed && + !btrfs_is_empty_uuid(root_item->received_uuid)) + btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root, + root_item->received_uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + root->root_key.objectid); memcpy(root_item->received_uuid, sa->uuid, BTRFS_UUID_SIZE); btrfs_set_root_stransid(root_item, sa->stransid); btrfs_set_root_rtransid(root_item, sa->rtransid); - root_item->stime.sec = cpu_to_le64(sa->stime.sec); - root_item->stime.nsec = cpu_to_le32(sa->stime.nsec); - root_item->rtime.sec = cpu_to_le64(sa->rtime.sec); - root_item->rtime.nsec = cpu_to_le32(sa->rtime.nsec); + btrfs_set_stack_timespec_sec(&root_item->stime, sa->stime.sec); + btrfs_set_stack_timespec_nsec(&root_item->stime, sa->stime.nsec); + btrfs_set_stack_timespec_sec(&root_item->rtime, sa->rtime.sec); + btrfs_set_stack_timespec_nsec(&root_item->rtime, sa->rtime.nsec); ret = btrfs_update_root(trans, root->fs_info->tree_root, &root->root_key, &root->root_item); if (ret < 0) { btrfs_end_transaction(trans, root); - trans = NULL; goto out; - } else { - ret = btrfs_commit_transaction(trans, root); - if (ret < 0) + } + if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) { + ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root, + sa->uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + root->root_key.objectid); + if (ret < 0 && ret != -EEXIST) { + btrfs_abort_transaction(trans, root, ret); goto out; + } + } + ret = btrfs_commit_transaction(trans, root); + if (ret < 0) { + btrfs_abort_transaction(trans, root, ret); + goto out; } ret = copy_to_user(arg, sa, sizeof(*sa)); @@ -4041,18 +4418,22 @@ out: static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg) { struct btrfs_root *root = BTRFS_I(file_inode(file))->root; - const char *label = root->fs_info->super_copy->label; - size_t len = strnlen(label, BTRFS_LABEL_SIZE); + size_t len; int ret; + char label[BTRFS_LABEL_SIZE]; + + spin_lock(&root->fs_info->super_lock); + memcpy(label, root->fs_info->super_copy->label, BTRFS_LABEL_SIZE); + spin_unlock(&root->fs_info->super_lock); + + len = strnlen(label, BTRFS_LABEL_SIZE); if (len == BTRFS_LABEL_SIZE) { pr_warn("btrfs: label is too long, return the first %zu bytes\n", --len); } - mutex_lock(&root->fs_info->volume_mutex); ret = copy_to_user(arg, label, len); - mutex_unlock(&root->fs_info->volume_mutex); return ret ? -EFAULT : 0; } @@ -4081,18 +4462,18 @@ static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg) if (ret) return ret; - mutex_lock(&root->fs_info->volume_mutex); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_unlock; } + spin_lock(&root->fs_info->super_lock); strcpy(super_block->label, label); + spin_unlock(&root->fs_info->super_lock); ret = btrfs_end_transaction(trans, root); out_unlock: - mutex_unlock(&root->fs_info->volume_mutex); mnt_drop_write_file(file); return ret; } @@ -4207,6 +4588,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_get_fslabel(file, argp); case BTRFS_IOC_SET_FSLABEL: return btrfs_ioctl_set_fslabel(file, argp); + case BTRFS_IOC_FILE_EXTENT_SAME: + return btrfs_ioctl_file_extent_same(file, argp); } return -ENOTTY; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index f93151a..b6a6f07 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -207,8 +207,10 @@ static int lzo_compress_pages(struct list_head *ws, } /* we're making it bigger, give up */ - if (tot_in > 8192 && tot_in < tot_out) + if (tot_in > 8192 && tot_in < tot_out) { + ret = -1; goto out; + } /* we're all done */ if (tot_in >= len) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 8136982..966b413 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -67,7 +67,7 @@ static void ordered_data_tree_panic(struct inode *inode, int errno, { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); btrfs_panic(fs_info, errno, "Inconsistency in ordered tree at offset " - "%llu\n", (unsigned long long)offset); + "%llu\n", offset); } /* @@ -205,6 +205,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, entry->bytes_left = len; entry->inode = igrab(inode); entry->compress_type = compress_type; + entry->truncated_len = (u64)-1; if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) set_bit(type, &entry->flags); @@ -336,14 +337,12 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode, *file_offset = dec_end; if (dec_start > dec_end) { printk(KERN_CRIT "bad ordering dec_start %llu end %llu\n", - (unsigned long long)dec_start, - (unsigned long long)dec_end); + dec_start, dec_end); } to_dec = dec_end - dec_start; if (to_dec > entry->bytes_left) { printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n", - (unsigned long long)entry->bytes_left, - (unsigned long long)to_dec); + entry->bytes_left, to_dec); } entry->bytes_left -= to_dec; if (!uptodate) @@ -403,8 +402,7 @@ have_entry: if (io_size > entry->bytes_left) { printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n", - (unsigned long long)entry->bytes_left, - (unsigned long long)io_size); + entry->bytes_left, io_size); } entry->bytes_left -= io_size; if (!uptodate) @@ -671,7 +669,7 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans, INIT_LIST_HEAD(&splice); INIT_LIST_HEAD(&works); - mutex_lock(&root->fs_info->ordered_operations_mutex); + mutex_lock(&root->fs_info->ordered_extent_flush_mutex); spin_lock(&root->fs_info->ordered_root_lock); list_splice_init(&cur_trans->ordered_operations, &splice); while (!list_empty(&splice)) { @@ -718,7 +716,7 @@ out: list_del_init(&work->list); btrfs_wait_and_free_delalloc_work(work); } - mutex_unlock(&root->fs_info->ordered_operations_mutex); + mutex_unlock(&root->fs_info->ordered_extent_flush_mutex); return ret; } @@ -923,12 +921,16 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct btrfs_ordered_extent *test; int ret = 1; - if (ordered) + spin_lock_irq(&tree->lock); + if (ordered) { offset = entry_end(ordered); - else + if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags)) + offset = min(offset, + ordered->file_offset + + ordered->truncated_len); + } else { offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize); - - spin_lock_irq(&tree->lock); + } disk_i_size = BTRFS_I(inode)->disk_i_size; /* truncate file */ diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 68844d5..d9a5aa0 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -69,6 +69,7 @@ struct btrfs_ordered_sum { * the isize. */ #define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered ordered extent */ +#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */ struct btrfs_ordered_extent { /* logical offset in the file */ @@ -96,6 +97,12 @@ struct btrfs_ordered_extent { */ u64 outstanding_isize; + /* + * If we get truncated we need to adjust the file extent we enter for + * this ordered extent so that we do not expose stale data. + */ + u64 truncated_len; + /* flags (described above) */ unsigned long flags; diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index dc0024f..0088bed 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -26,14 +26,12 @@ static void print_chunk(struct extent_buffer *eb, struct btrfs_chunk *chunk) int i; printk(KERN_INFO "\t\tchunk length %llu owner %llu type %llu " "num_stripes %d\n", - (unsigned long long)btrfs_chunk_length(eb, chunk), - (unsigned long long)btrfs_chunk_owner(eb, chunk), - (unsigned long long)btrfs_chunk_type(eb, chunk), - num_stripes); + btrfs_chunk_length(eb, chunk), btrfs_chunk_owner(eb, chunk), + btrfs_chunk_type(eb, chunk), num_stripes); for (i = 0 ; i < num_stripes ; i++) { printk(KERN_INFO "\t\t\tstripe %d devid %llu offset %llu\n", i, - (unsigned long long)btrfs_stripe_devid_nr(eb, chunk, i), - (unsigned long long)btrfs_stripe_offset_nr(eb, chunk, i)); + btrfs_stripe_devid_nr(eb, chunk, i), + btrfs_stripe_offset_nr(eb, chunk, i)); } } static void print_dev_item(struct extent_buffer *eb, @@ -41,18 +39,18 @@ static void print_dev_item(struct extent_buffer *eb, { printk(KERN_INFO "\t\tdev item devid %llu " "total_bytes %llu bytes used %llu\n", - (unsigned long long)btrfs_device_id(eb, dev_item), - (unsigned long long)btrfs_device_total_bytes(eb, dev_item), - (unsigned long long)btrfs_device_bytes_used(eb, dev_item)); + btrfs_device_id(eb, dev_item), + btrfs_device_total_bytes(eb, dev_item), + btrfs_device_bytes_used(eb, dev_item)); } static void print_extent_data_ref(struct extent_buffer *eb, struct btrfs_extent_data_ref *ref) { printk(KERN_INFO "\t\textent data backref root %llu " "objectid %llu offset %llu count %u\n", - (unsigned long long)btrfs_extent_data_ref_root(eb, ref), - (unsigned long long)btrfs_extent_data_ref_objectid(eb, ref), - (unsigned long long)btrfs_extent_data_ref_offset(eb, ref), + btrfs_extent_data_ref_root(eb, ref), + btrfs_extent_data_ref_objectid(eb, ref), + btrfs_extent_data_ref_offset(eb, ref), btrfs_extent_data_ref_count(eb, ref)); } @@ -87,19 +85,17 @@ static void print_extent_item(struct extent_buffer *eb, int slot) flags = btrfs_extent_flags(eb, ei); printk(KERN_INFO "\t\textent refs %llu gen %llu flags %llu\n", - (unsigned long long)btrfs_extent_refs(eb, ei), - (unsigned long long)btrfs_extent_generation(eb, ei), - (unsigned long long)flags); + btrfs_extent_refs(eb, ei), btrfs_extent_generation(eb, ei), + flags); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { struct btrfs_tree_block_info *info; info = (struct btrfs_tree_block_info *)(ei + 1); btrfs_tree_block_key(eb, info, &key); - printk(KERN_INFO "\t\ttree block key (%llu %x %llu) " + printk(KERN_INFO "\t\ttree block key (%llu %u %llu) " "level %d\n", - (unsigned long long)btrfs_disk_key_objectid(&key), - key.type, - (unsigned long long)btrfs_disk_key_offset(&key), + btrfs_disk_key_objectid(&key), key.type, + btrfs_disk_key_offset(&key), btrfs_tree_block_level(eb, info)); iref = (struct btrfs_extent_inline_ref *)(info + 1); } else { @@ -115,11 +111,11 @@ static void print_extent_item(struct extent_buffer *eb, int slot) switch (type) { case BTRFS_TREE_BLOCK_REF_KEY: printk(KERN_INFO "\t\ttree block backref " - "root %llu\n", (unsigned long long)offset); + "root %llu\n", offset); break; case BTRFS_SHARED_BLOCK_REF_KEY: printk(KERN_INFO "\t\tshared block backref " - "parent %llu\n", (unsigned long long)offset); + "parent %llu\n", offset); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = (struct btrfs_extent_data_ref *)(&iref->offset); @@ -129,8 +125,7 @@ static void print_extent_item(struct extent_buffer *eb, int slot) sref = (struct btrfs_shared_data_ref *)(iref + 1); printk(KERN_INFO "\t\tshared data backref " "parent %llu count %u\n", - (unsigned long long)offset, - btrfs_shared_data_ref_count(eb, sref)); + offset, btrfs_shared_data_ref_count(eb, sref)); break; default: BUG(); @@ -148,13 +143,32 @@ static void print_extent_ref_v0(struct extent_buffer *eb, int slot) ref0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_ref_v0); printk("\t\textent back ref root %llu gen %llu " "owner %llu num_refs %lu\n", - (unsigned long long)btrfs_ref_root_v0(eb, ref0), - (unsigned long long)btrfs_ref_generation_v0(eb, ref0), - (unsigned long long)btrfs_ref_objectid_v0(eb, ref0), + btrfs_ref_root_v0(eb, ref0), + btrfs_ref_generation_v0(eb, ref0), + btrfs_ref_objectid_v0(eb, ref0), (unsigned long)btrfs_ref_count_v0(eb, ref0)); } #endif +static void print_uuid_item(struct extent_buffer *l, unsigned long offset, + u32 item_size) +{ + if (!IS_ALIGNED(item_size, sizeof(u64))) { + pr_warn("btrfs: uuid item with illegal size %lu!\n", + (unsigned long)item_size); + return; + } + while (item_size) { + __le64 subvol_id; + + read_extent_buffer(l, &subvol_id, offset, sizeof(subvol_id)); + printk(KERN_INFO "\t\tsubvol_id %llu\n", + (unsigned long long)le64_to_cpu(subvol_id)); + item_size -= sizeof(u64); + offset += sizeof(u64); + } +} + void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) { int i; @@ -177,39 +191,34 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) nr = btrfs_header_nritems(l); btrfs_info(root->fs_info, "leaf %llu total ptrs %d free space %d", - (unsigned long long)btrfs_header_bytenr(l), nr, - btrfs_leaf_free_space(root, l)); + btrfs_header_bytenr(l), nr, btrfs_leaf_free_space(root, l)); for (i = 0 ; i < nr ; i++) { item = btrfs_item_nr(l, i); btrfs_item_key_to_cpu(l, &key, i); type = btrfs_key_type(&key); - printk(KERN_INFO "\titem %d key (%llu %x %llu) itemoff %d " + printk(KERN_INFO "\titem %d key (%llu %u %llu) itemoff %d " "itemsize %d\n", - i, - (unsigned long long)key.objectid, type, - (unsigned long long)key.offset, + i, key.objectid, type, key.offset, btrfs_item_offset(l, item), btrfs_item_size(l, item)); switch (type) { case BTRFS_INODE_ITEM_KEY: ii = btrfs_item_ptr(l, i, struct btrfs_inode_item); printk(KERN_INFO "\t\tinode generation %llu size %llu " "mode %o\n", - (unsigned long long) btrfs_inode_generation(l, ii), - (unsigned long long)btrfs_inode_size(l, ii), + btrfs_inode_size(l, ii), btrfs_inode_mode(l, ii)); break; case BTRFS_DIR_ITEM_KEY: di = btrfs_item_ptr(l, i, struct btrfs_dir_item); btrfs_dir_item_key_to_cpu(l, di, &found_key); printk(KERN_INFO "\t\tdir oid %llu type %u\n", - (unsigned long long)found_key.objectid, + found_key.objectid, btrfs_dir_type(l, di)); break; case BTRFS_ROOT_ITEM_KEY: ri = btrfs_item_ptr(l, i, struct btrfs_root_item); printk(KERN_INFO "\t\troot data bytenr %llu refs %u\n", - (unsigned long long) btrfs_disk_root_bytenr(l, ri), btrfs_disk_root_refs(l, ri)); break; @@ -245,17 +254,12 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) } printk(KERN_INFO "\t\textent data disk bytenr %llu " "nr %llu\n", - (unsigned long long) btrfs_file_extent_disk_bytenr(l, fi), - (unsigned long long) btrfs_file_extent_disk_num_bytes(l, fi)); printk(KERN_INFO "\t\textent data offset %llu " "nr %llu ram %llu\n", - (unsigned long long) btrfs_file_extent_offset(l, fi), - (unsigned long long) btrfs_file_extent_num_bytes(l, fi), - (unsigned long long) btrfs_file_extent_ram_bytes(l, fi)); break; case BTRFS_EXTENT_REF_V0_KEY: @@ -269,7 +273,6 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) bi = btrfs_item_ptr(l, i, struct btrfs_block_group_item); printk(KERN_INFO "\t\tblock group used %llu\n", - (unsigned long long) btrfs_disk_block_group_used(l, bi)); break; case BTRFS_CHUNK_ITEM_KEY: @@ -286,13 +289,9 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) printk(KERN_INFO "\t\tdev extent chunk_tree %llu\n" "\t\tchunk objectid %llu chunk offset %llu " "length %llu\n", - (unsigned long long) btrfs_dev_extent_chunk_tree(l, dev_extent), - (unsigned long long) btrfs_dev_extent_chunk_objectid(l, dev_extent), - (unsigned long long) btrfs_dev_extent_chunk_offset(l, dev_extent), - (unsigned long long) btrfs_dev_extent_length(l, dev_extent)); break; case BTRFS_DEV_STATS_KEY: @@ -301,6 +300,11 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) case BTRFS_DEV_REPLACE_KEY: printk(KERN_INFO "\t\tdev replace\n"); break; + case BTRFS_UUID_KEY_SUBVOL: + case BTRFS_UUID_KEY_RECEIVED_SUBVOL: + print_uuid_item(l, btrfs_item_ptr_offset(l, i), + btrfs_item_size_nr(l, i)); + break; }; } } @@ -320,16 +324,13 @@ void btrfs_print_tree(struct btrfs_root *root, struct extent_buffer *c) return; } btrfs_info(root->fs_info, "node %llu level %d total ptrs %d free spc %u", - (unsigned long long)btrfs_header_bytenr(c), - level, nr, (u32)BTRFS_NODEPTRS_PER_BLOCK(root) - nr); + btrfs_header_bytenr(c), level, nr, + (u32)BTRFS_NODEPTRS_PER_BLOCK(root) - nr); for (i = 0; i < nr; i++) { btrfs_node_key_to_cpu(c, &key, i); printk(KERN_INFO "\tkey %d (%llu %u %llu) block %llu\n", - i, - (unsigned long long)key.objectid, - key.type, - (unsigned long long)key.offset, - (unsigned long long)btrfs_node_blockptr(c, i)); + i, key.objectid, key.type, key.offset, + btrfs_node_blockptr(c, i)); } for (i = 0; i < nr; i++) { struct extent_buffer *next = read_tree_block(root, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1280eff..4e6ef49 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -157,18 +157,11 @@ static struct btrfs_qgroup *add_qgroup_rb(struct btrfs_fs_info *fs_info, return qgroup; } -/* must be called with qgroup_lock held */ -static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid) +static void __del_qgroup_rb(struct btrfs_qgroup *qgroup) { - struct btrfs_qgroup *qgroup = find_qgroup_rb(fs_info, qgroupid); struct btrfs_qgroup_list *list; - if (!qgroup) - return -ENOENT; - - rb_erase(&qgroup->node, &fs_info->qgroup_tree); list_del(&qgroup->dirty); - while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, struct btrfs_qgroup_list, next_group); @@ -185,7 +178,18 @@ static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid) kfree(list); } kfree(qgroup); +} +/* must be called with qgroup_lock held */ +static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid) +{ + struct btrfs_qgroup *qgroup = find_qgroup_rb(fs_info, qgroupid); + + if (!qgroup) + return -ENOENT; + + rb_erase(&qgroup->node, &fs_info->qgroup_tree); + __del_qgroup_rb(qgroup); return 0; } @@ -394,8 +398,7 @@ next1: if (ret == -ENOENT) { printk(KERN_WARNING "btrfs: orphan qgroup relation 0x%llx->0x%llx\n", - (unsigned long long)found_key.objectid, - (unsigned long long)found_key.offset); + found_key.objectid, found_key.offset); ret = 0; /* ignore the error */ } if (ret) @@ -428,39 +431,28 @@ out: } /* - * This is only called from close_ctree() or open_ctree(), both in single- - * treaded paths. Clean up the in-memory structures. No locking needed. + * This is called from close_ctree() or open_ctree() or btrfs_quota_disable(), + * first two are in single-threaded paths.And for the third one, we have set + * quota_root to be null with qgroup_lock held before, so it is safe to clean + * up the in-memory structures without qgroup_lock held. */ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) { struct rb_node *n; struct btrfs_qgroup *qgroup; - struct btrfs_qgroup_list *list; while ((n = rb_first(&fs_info->qgroup_tree))) { qgroup = rb_entry(n, struct btrfs_qgroup, node); rb_erase(n, &fs_info->qgroup_tree); - - while (!list_empty(&qgroup->groups)) { - list = list_first_entry(&qgroup->groups, - struct btrfs_qgroup_list, - next_group); - list_del(&list->next_group); - list_del(&list->next_member); - kfree(list); - } - - while (!list_empty(&qgroup->members)) { - list = list_first_entry(&qgroup->members, - struct btrfs_qgroup_list, - next_member); - list_del(&list->next_group); - list_del(&list->next_member); - kfree(list); - } - kfree(qgroup); + __del_qgroup_rb(qgroup); } + /* + * we call btrfs_free_qgroup_config() when umounting + * filesystem and disabling quota, so we set qgroup_ulit + * to be null here to avoid double free. + */ ulist_free(fs_info->qgroup_ulist); + fs_info->qgroup_ulist = NULL; } static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, @@ -946,13 +938,9 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, fs_info->pending_quota_state = 0; quota_root = fs_info->quota_root; fs_info->quota_root = NULL; - btrfs_free_qgroup_config(fs_info); spin_unlock(&fs_info->qgroup_lock); - if (!quota_root) { - ret = -EINVAL; - goto out; - } + btrfs_free_qgroup_config(fs_info); ret = btrfs_clean_quota_tree(trans, quota_root); if (ret) @@ -1174,7 +1162,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, if (ret) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; printk(KERN_INFO "unable to update quota limit for %llu\n", - (unsigned long long)qgroupid); + qgroupid); } spin_lock(&fs_info->qgroup_lock); @@ -1884,10 +1872,9 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, path, 1, 0); pr_debug("current progress key (%llu %u %llu), search_slot ret %d\n", - (unsigned long long)fs_info->qgroup_rescan_progress.objectid, + fs_info->qgroup_rescan_progress.objectid, fs_info->qgroup_rescan_progress.type, - (unsigned long long)fs_info->qgroup_rescan_progress.offset, - ret); + fs_info->qgroup_rescan_progress.offset, ret); if (ret) { /* diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 0525e13..d0ecfbd 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1540,8 +1540,10 @@ static int full_stripe_write(struct btrfs_raid_bio *rbio) int ret; ret = alloc_rbio_parity_pages(rbio); - if (ret) + if (ret) { + __free_raid_bio(rbio); return ret; + } ret = lock_stripe_add(rbio); if (ret == 0) @@ -1687,11 +1689,8 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio, struct blk_plug_cb *cb; rbio = alloc_rbio(root, bbio, raid_map, stripe_len); - if (IS_ERR(rbio)) { - kfree(raid_map); - kfree(bbio); + if (IS_ERR(rbio)) return PTR_ERR(rbio); - } bio_list_add(&rbio->bio_list, bio); rbio->bio_list_bytes = bio->bi_size; @@ -2041,9 +2040,8 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, int ret; rbio = alloc_rbio(root, bbio, raid_map, stripe_len); - if (IS_ERR(rbio)) { + if (IS_ERR(rbio)) return PTR_ERR(rbio); - } rbio->read_rebuild = 1; bio_list_add(&rbio->bio_list, bio); @@ -2052,6 +2050,8 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio, rbio->faila = find_logical_bio_stripe(rbio, bio); if (rbio->faila == -1) { BUG(); + kfree(raid_map); + kfree(bbio); kfree(rbio); return -EIO; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 1209649..aacc212 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -335,7 +335,7 @@ static void backref_tree_panic(struct rb_node *rb_node, int errno, u64 bytenr) if (bnode->root) fs_info = bnode->root->fs_info; btrfs_panic(fs_info, errno, "Inconsistency in backref cache " - "found at offset %llu\n", (unsigned long long)bytenr); + "found at offset %llu\n", bytenr); } /* @@ -641,6 +641,11 @@ int find_inline_backref(struct extent_buffer *leaf, int slot, WARN_ON(item_size < sizeof(*ei) + sizeof(*bi)); return 1; } + if (key.type == BTRFS_METADATA_ITEM_KEY && + item_size <= sizeof(*ei)) { + WARN_ON(item_size < sizeof(*ei)); + return 1; + } if (key.type == BTRFS_EXTENT_ITEM_KEY) { bi = (struct btrfs_tree_block_info *)(ei + 1); @@ -691,6 +696,7 @@ struct backref_node *build_backref_tree(struct reloc_control *rc, int cowonly; int ret; int err = 0; + bool need_check = true; path1 = btrfs_alloc_path(); path2 = btrfs_alloc_path(); @@ -914,6 +920,7 @@ again: cur->bytenr); lower = cur; + need_check = true; for (; level < BTRFS_MAX_LEVEL; level++) { if (!path2->nodes[level]) { BUG_ON(btrfs_root_bytenr(&root->root_item) != @@ -957,14 +964,12 @@ again: /* * add the block to pending list if we - * need check its backrefs. only block - * at 'cur->level + 1' is added to the - * tail of pending list. this guarantees - * we check backrefs from lower level - * blocks to upper level blocks. + * need check its backrefs, we only do this once + * while walking up a tree as we will catch + * anything else later on. */ - if (!upper->checked && - level == cur->level + 1) { + if (!upper->checked && need_check) { + need_check = false; list_add_tail(&edge->list[UPPER], &list); } else @@ -2314,8 +2319,13 @@ again: BUG_ON(root->reloc_root != reloc_root); ret = merge_reloc_root(rc, root); - if (ret) + if (ret) { + __update_reloc_root(reloc_root, 1); + free_extent_buffer(reloc_root->node); + free_extent_buffer(reloc_root->commit_root); + kfree(reloc_root); goto out; + } } else { list_del_init(&reloc_root->root_list); } @@ -2344,9 +2354,6 @@ again: if (IS_ERR(root)) continue; - if (btrfs_root_refs(&root->root_item) == 0) - continue; - trans = btrfs_join_transaction(root); BUG_ON(IS_ERR(trans)); @@ -3628,7 +3635,7 @@ int add_data_references(struct reloc_control *rc, unsigned long ptr; unsigned long end; u32 blocksize = btrfs_level_size(rc->extent_root, 0); - int ret; + int ret = 0; int err = 0; eb = path->nodes[0]; @@ -3655,6 +3662,10 @@ int add_data_references(struct reloc_control *rc, } else { BUG(); } + if (ret) { + err = ret; + goto out; + } ptr += btrfs_extent_inline_ref_size(key.type); } WARN_ON(ptr > end); @@ -3700,6 +3711,7 @@ int add_data_references(struct reloc_control *rc, } path->slots[0]++; } +out: btrfs_release_path(path); if (err) free_block_list(blocks); @@ -4219,8 +4231,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) } printk(KERN_INFO "btrfs: relocating block group %llu flags %llu\n", - (unsigned long long)rc->block_group->key.objectid, - (unsigned long long)rc->block_group->flags); + rc->block_group->key.objectid, rc->block_group->flags); ret = btrfs_start_all_delalloc_inodes(fs_info, 0); if (ret < 0) { @@ -4242,7 +4253,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) break; printk(KERN_INFO "btrfs: found %llu extents\n", - (unsigned long long)rc->extents_found); + rc->extents_found); if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) { btrfs_wait_ordered_range(rc->data_inode, 0, (u64)-1); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index ffb1036..0b1f4ef 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -29,8 +29,8 @@ * generation numbers as then we know the root was once mounted with an older * kernel that was not aware of the root item structure change. */ -void btrfs_read_root_item(struct extent_buffer *eb, int slot, - struct btrfs_root_item *item) +static void btrfs_read_root_item(struct extent_buffer *eb, int slot, + struct btrfs_root_item *item) { uuid_le uuid; int len; @@ -155,8 +155,7 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root if (ret != 0) { btrfs_print_leaf(root, path->nodes[0]); printk(KERN_CRIT "unable to update root key %llu %u %llu\n", - (unsigned long long)key->objectid, key->type, - (unsigned long long)key->offset); + key->objectid, key->type, key->offset); BUG_ON(1); } @@ -490,13 +489,13 @@ again: */ void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item) { - u64 inode_flags = le64_to_cpu(root_item->inode.flags); + u64 inode_flags = btrfs_stack_inode_flags(&root_item->inode); if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) { inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT; - root_item->inode.flags = cpu_to_le64(inode_flags); - root_item->flags = 0; - root_item->byte_limit = 0; + btrfs_set_stack_inode_flags(&root_item->inode, inode_flags); + btrfs_set_root_flags(root_item, 0); + btrfs_set_root_limit(root_item, 0); } } @@ -507,8 +506,8 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans, struct timespec ct = CURRENT_TIME; spin_lock(&root->root_item_lock); - item->ctransid = cpu_to_le64(trans->transid); - item->ctime.sec = cpu_to_le64(ct.tv_sec); - item->ctime.nsec = cpu_to_le32(ct.tv_nsec); + btrfs_set_root_ctransid(item, trans->transid); + btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec); + btrfs_set_stack_timespec_nsec(&item->ctime, ct.tv_nsec); spin_unlock(&root->root_item_lock); } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 4ba2a69..0afcd45 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -754,8 +754,7 @@ out: num_uncorrectable_read_errors); printk_ratelimited_in_rcu(KERN_ERR "btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n", - (unsigned long long)fixup->logical, - rcu_str_deref(fixup->dev->name)); + fixup->logical, rcu_str_deref(fixup->dev->name)); } btrfs_free_path(path); @@ -1154,8 +1153,7 @@ corrected_error: spin_unlock(&sctx->stat_lock); printk_ratelimited_in_rcu(KERN_ERR "btrfs: fixed up error at logical %llu on dev %s\n", - (unsigned long long)logical, - rcu_str_deref(dev->name)); + logical, rcu_str_deref(dev->name)); } } else { did_not_correct_error: @@ -1164,8 +1162,7 @@ did_not_correct_error: spin_unlock(&sctx->stat_lock); printk_ratelimited_in_rcu(KERN_ERR "btrfs: unable to fixup (regular) error at logical %llu on dev %s\n", - (unsigned long long)logical, - rcu_str_deref(dev->name)); + logical, rcu_str_deref(dev->name)); } out: @@ -1345,12 +1342,12 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, mapped_buffer = kmap_atomic(sblock->pagev[0]->page); h = (struct btrfs_header *)mapped_buffer; - if (sblock->pagev[0]->logical != le64_to_cpu(h->bytenr) || + if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) || memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE) || memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, BTRFS_UUID_SIZE)) { sblock->header_error = 1; - } else if (generation != le64_to_cpu(h->generation)) { + } else if (generation != btrfs_stack_header_generation(h)) { sblock->header_error = 1; sblock->generation_error = 1; } @@ -1720,10 +1717,10 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) * b) the page is already kmapped */ - if (sblock->pagev[0]->logical != le64_to_cpu(h->bytenr)) + if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h)) ++fail; - if (sblock->pagev[0]->generation != le64_to_cpu(h->generation)) + if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) ++fail; if (memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE)) @@ -1786,10 +1783,10 @@ static int scrub_checksum_super(struct scrub_block *sblock) s = (struct btrfs_super_block *)mapped_buffer; memcpy(on_disk_csum, s->csum, sctx->csum_size); - if (sblock->pagev[0]->logical != le64_to_cpu(s->bytenr)) + if (sblock->pagev[0]->logical != btrfs_super_bytenr(s)) ++fail_cor; - if (sblock->pagev[0]->generation != le64_to_cpu(s->generation)) + if (sblock->pagev[0]->generation != btrfs_super_generation(s)) ++fail_gen; if (memcmp(s->fsid, fs_info->fsid, BTRFS_UUID_SIZE)) @@ -2455,8 +2452,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, printk(KERN_ERR "btrfs scrub: tree block %llu spanning " "stripes, ignored. logical=%llu\n", - (unsigned long long)key.objectid, - (unsigned long long)logical); + key.objectid, logical); goto next; } @@ -2495,7 +2491,7 @@ again: ret = scrub_extent(sctx, extent_logical, extent_len, extent_physical, extent_dev, flags, generation, extent_mirror_num, - extent_physical); + extent_logical - logical + physical); if (ret) goto out; @@ -2863,9 +2859,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (fs_info->chunk_root->sectorsize != PAGE_SIZE) { /* not supported for data w/o checksums */ printk(KERN_ERR - "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lld) fails\n", - fs_info->chunk_root->sectorsize, - (unsigned long long)PAGE_SIZE); + "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lu) fails\n", + fs_info->chunk_root->sectorsize, PAGE_SIZE); return -EINVAL; } @@ -3175,11 +3170,9 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) copy_nocow_pages_for_inode, nocow_ctx); if (ret != 0 && ret != -ENOENT) { - pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %llu, ret %d\n", - (unsigned long long)logical, - (unsigned long long)physical_for_dev_replace, - (unsigned long long)len, - (unsigned long long)mirror_num, ret); + pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n", + logical, physical_for_dev_replace, len, mirror_num, + ret); not_written = 1; goto out; } @@ -3224,11 +3217,6 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) return PTR_ERR(local_root); } - if (btrfs_root_refs(&local_root->root_item) == 0) { - srcu_read_unlock(&fs_info->subvol_srcu, srcu_index); - return -ENOENT; - } - key.type = BTRFS_INODE_ITEM_KEY; key.objectid = inum; key.offset = 0; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index d3f3b43..e46e0ed 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -26,6 +26,7 @@ #include <linux/radix-tree.h> #include <linux/crc32c.h> #include <linux/vmalloc.h> +#include <linux/string.h> #include "send.h" #include "backref.h" @@ -54,8 +55,8 @@ struct fs_path { char *buf; int buf_len; - int reversed:1; - int virtual_mem:1; + unsigned int reversed:1; + unsigned int virtual_mem:1; char inline_buf[]; }; char pad[PAGE_SIZE]; @@ -219,7 +220,7 @@ static int fs_path_ensure_buf(struct fs_path *p, int len) len = PAGE_ALIGN(len); if (p->buf == p->inline_buf) { - tmp_buf = kmalloc(len, GFP_NOFS); + tmp_buf = kmalloc(len, GFP_NOFS | __GFP_NOWARN); if (!tmp_buf) { tmp_buf = vmalloc(len); if (!tmp_buf) @@ -1668,6 +1669,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, u64 *who_ino, u64 *who_gen) { int ret = 0; + u64 gen; u64 other_inode = 0; u8 other_type = 0; @@ -1678,6 +1680,24 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, if (ret <= 0) goto out; + /* + * If we have a parent root we need to verify that the parent dir was + * not delted and then re-created, if it was then we have no overwrite + * and we can just unlink this entry. + */ + if (sctx->parent_root) { + ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL, + NULL, NULL, NULL); + if (ret < 0 && ret != -ENOENT) + goto out; + if (ret) { + ret = 0; + goto out; + } + if (gen != dir_gen) + goto out; + } + ret = lookup_dir_item_inode(sctx->parent_root, dir, name, name_len, &other_inode, &other_type); if (ret < 0 && ret != -ENOENT) @@ -2519,7 +2539,8 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir) di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); btrfs_dir_item_key_to_cpu(eb, di, &di_key); - if (di_key.objectid < sctx->send_progress) { + if (di_key.type != BTRFS_ROOT_ITEM_KEY && + di_key.objectid < sctx->send_progress) { ret = 1; goto out; } @@ -2581,7 +2602,6 @@ static int record_ref(struct list_head *head, u64 dir, u64 dir_gen, struct fs_path *path) { struct recorded_ref *ref; - char *tmp; ref = kmalloc(sizeof(*ref), GFP_NOFS); if (!ref) @@ -2591,25 +2611,35 @@ static int record_ref(struct list_head *head, u64 dir, ref->dir_gen = dir_gen; ref->full_path = path; - tmp = strrchr(ref->full_path->start, '/'); - if (!tmp) { - ref->name_len = ref->full_path->end - ref->full_path->start; - ref->name = ref->full_path->start; + ref->name = (char *)kbasename(ref->full_path->start); + ref->name_len = ref->full_path->end - ref->name; + ref->dir_path = ref->full_path->start; + if (ref->name == ref->full_path->start) ref->dir_path_len = 0; - ref->dir_path = ref->full_path->start; - } else { - tmp++; - ref->name_len = ref->full_path->end - tmp; - ref->name = tmp; - ref->dir_path = ref->full_path->start; + else ref->dir_path_len = ref->full_path->end - ref->full_path->start - 1 - ref->name_len; - } list_add_tail(&ref->list, head); return 0; } +static int dup_ref(struct recorded_ref *ref, struct list_head *list) +{ + struct recorded_ref *new; + + new = kmalloc(sizeof(*ref), GFP_NOFS); + if (!new) + return -ENOMEM; + + new->dir = ref->dir; + new->dir_gen = ref->dir_gen; + new->full_path = NULL; + INIT_LIST_HEAD(&new->list); + list_add_tail(&new->list, list); + return 0; +} + static void __free_recorded_refs(struct list_head *head) { struct recorded_ref *cur; @@ -2724,9 +2754,7 @@ static int process_recorded_refs(struct send_ctx *sctx) int ret = 0; struct recorded_ref *cur; struct recorded_ref *cur2; - struct ulist *check_dirs = NULL; - struct ulist_iterator uit; - struct ulist_node *un; + struct list_head check_dirs; struct fs_path *valid_path = NULL; u64 ow_inode = 0; u64 ow_gen; @@ -2740,6 +2768,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); * which is always '..' */ BUG_ON(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID); + INIT_LIST_HEAD(&check_dirs); valid_path = fs_path_alloc(); if (!valid_path) { @@ -2747,12 +2776,6 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); goto out; } - check_dirs = ulist_alloc(GFP_NOFS); - if (!check_dirs) { - ret = -ENOMEM; - goto out; - } - /* * First, check if the first ref of the current inode was overwritten * before. If yes, we know that the current inode was already orphanized @@ -2889,8 +2912,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); goto out; } } - ret = ulist_add(check_dirs, cur->dir, cur->dir_gen, - GFP_NOFS); + ret = dup_ref(cur, &check_dirs); if (ret < 0) goto out; } @@ -2918,8 +2940,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); } list_for_each_entry(cur, &sctx->deleted_refs, list) { - ret = ulist_add(check_dirs, cur->dir, cur->dir_gen, - GFP_NOFS); + ret = dup_ref(cur, &check_dirs); if (ret < 0) goto out; } @@ -2930,8 +2951,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); */ cur = list_entry(sctx->deleted_refs.next, struct recorded_ref, list); - ret = ulist_add(check_dirs, cur->dir, cur->dir_gen, - GFP_NOFS); + ret = dup_ref(cur, &check_dirs); if (ret < 0) goto out; } else if (!S_ISDIR(sctx->cur_inode_mode)) { @@ -2951,12 +2971,10 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); if (ret < 0) goto out; } - ret = ulist_add(check_dirs, cur->dir, cur->dir_gen, - GFP_NOFS); + ret = dup_ref(cur, &check_dirs); if (ret < 0) goto out; } - /* * If the inode is still orphan, unlink the orphan. This may * happen when a previous inode did overwrite the first ref @@ -2978,33 +2996,32 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); * deletion and if it's finally possible to perform the rmdir now. * We also update the inode stats of the parent dirs here. */ - ULIST_ITER_INIT(&uit); - while ((un = ulist_next(check_dirs, &uit))) { + list_for_each_entry(cur, &check_dirs, list) { /* * In case we had refs into dirs that were not processed yet, * we don't need to do the utime and rmdir logic for these dirs. * The dir will be processed later. */ - if (un->val > sctx->cur_ino) + if (cur->dir > sctx->cur_ino) continue; - ret = get_cur_inode_state(sctx, un->val, un->aux); + ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; if (ret == inode_state_did_create || ret == inode_state_no_change) { /* TODO delayed utimes */ - ret = send_utimes(sctx, un->val, un->aux); + ret = send_utimes(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; } else if (ret == inode_state_did_delete) { - ret = can_rmdir(sctx, un->val, sctx->cur_ino); + ret = can_rmdir(sctx, cur->dir, sctx->cur_ino); if (ret < 0) goto out; if (ret) { - ret = get_cur_path(sctx, un->val, un->aux, - valid_path); + ret = get_cur_path(sctx, cur->dir, + cur->dir_gen, valid_path); if (ret < 0) goto out; ret = send_rmdir(sctx, valid_path); @@ -3017,8 +3034,8 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); ret = 0; out: + __free_recorded_refs(&check_dirs); free_recorded_refs(sctx); - ulist_free(check_dirs); fs_path_free(valid_path); return ret; } @@ -3119,6 +3136,8 @@ out: struct find_ref_ctx { u64 dir; + u64 dir_gen; + struct btrfs_root *root; struct fs_path *name; int found_idx; }; @@ -3128,9 +3147,21 @@ static int __find_iref(int num, u64 dir, int index, void *ctx_) { struct find_ref_ctx *ctx = ctx_; + u64 dir_gen; + int ret; if (dir == ctx->dir && fs_path_len(name) == fs_path_len(ctx->name) && strncmp(name->start, ctx->name->start, fs_path_len(name)) == 0) { + /* + * To avoid doing extra lookups we'll only do this if everything + * else matches. + */ + ret = get_inode_info(ctx->root, dir, NULL, &dir_gen, NULL, + NULL, NULL, NULL); + if (ret) + return ret; + if (dir_gen != ctx->dir_gen) + return 0; ctx->found_idx = num; return 1; } @@ -3140,14 +3171,16 @@ static int __find_iref(int num, u64 dir, int index, static int find_iref(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *key, - u64 dir, struct fs_path *name) + u64 dir, u64 dir_gen, struct fs_path *name) { int ret; struct find_ref_ctx ctx; ctx.dir = dir; ctx.name = name; + ctx.dir_gen = dir_gen; ctx.found_idx = -1; + ctx.root = root; ret = iterate_inode_ref(root, path, key, 0, __find_iref, &ctx); if (ret < 0) @@ -3163,11 +3196,17 @@ static int __record_changed_new_ref(int num, u64 dir, int index, struct fs_path *name, void *ctx) { + u64 dir_gen; int ret; struct send_ctx *sctx = ctx; + ret = get_inode_info(sctx->send_root, dir, NULL, &dir_gen, NULL, + NULL, NULL, NULL); + if (ret) + return ret; + ret = find_iref(sctx->parent_root, sctx->right_path, - sctx->cmp_key, dir, name); + sctx->cmp_key, dir, dir_gen, name); if (ret == -ENOENT) ret = __record_new_ref(num, dir, index, name, sctx); else if (ret > 0) @@ -3180,11 +3219,17 @@ static int __record_changed_deleted_ref(int num, u64 dir, int index, struct fs_path *name, void *ctx) { + u64 dir_gen; int ret; struct send_ctx *sctx = ctx; + ret = get_inode_info(sctx->parent_root, dir, NULL, &dir_gen, NULL, + NULL, NULL, NULL); + if (ret) + return ret; + ret = find_iref(sctx->send_root, sctx->left_path, sctx->cmp_key, - dir, name); + dir, dir_gen, name); if (ret == -ENOENT) ret = __record_deleted_ref(num, dir, index, name, sctx); else if (ret > 0) @@ -3869,7 +3914,8 @@ static int is_extent_unchanged(struct send_ctx *sctx, btrfs_item_key_to_cpu(eb, &found_key, slot); if (found_key.objectid != key.objectid || found_key.type != key.type) { - ret = 0; + /* If we're a hole then just pretend nothing changed */ + ret = (left_disknr) ? 0 : 1; goto out; } @@ -3895,7 +3941,8 @@ static int is_extent_unchanged(struct send_ctx *sctx, * This may only happen on the first iteration. */ if (found_key.offset + right_len <= ekey->offset) { - ret = 0; + /* If we're a hole just pretend nothing changed */ + ret = (left_disknr) ? 0 : 1; goto out; } @@ -3960,8 +4007,8 @@ static int process_extent(struct send_ctx *sctx, struct btrfs_path *path, struct btrfs_key *key) { - int ret = 0; struct clone_root *found_clone = NULL; + int ret = 0; if (S_ISLNK(sctx->cur_inode_mode)) return 0; @@ -3974,6 +4021,32 @@ static int process_extent(struct send_ctx *sctx, ret = 0; goto out; } + } else { + struct btrfs_file_extent_item *ei; + u8 type; + + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + type = btrfs_file_extent_type(path->nodes[0], ei); + if (type == BTRFS_FILE_EXTENT_PREALLOC || + type == BTRFS_FILE_EXTENT_REG) { + /* + * The send spec does not have a prealloc command yet, + * so just leave a hole for prealloc'ed extents until + * we have enough commands queued up to justify rev'ing + * the send spec. + */ + if (type == BTRFS_FILE_EXTENT_PREALLOC) { + ret = 0; + goto out; + } + + /* Have a hole, just skip it. */ + if (btrfs_file_extent_disk_bytenr(path->nodes[0], ei) == 0) { + ret = 0; + goto out; + } + } } ret = find_extent_clone(sctx, path, key->objectid, key->offset, @@ -4361,6 +4434,64 @@ static int changed_extent(struct send_ctx *sctx, return ret; } +static int dir_changed(struct send_ctx *sctx, u64 dir) +{ + u64 orig_gen, new_gen; + int ret; + + ret = get_inode_info(sctx->send_root, dir, NULL, &new_gen, NULL, NULL, + NULL, NULL); + if (ret) + return ret; + + ret = get_inode_info(sctx->parent_root, dir, NULL, &orig_gen, NULL, + NULL, NULL, NULL); + if (ret) + return ret; + + return (orig_gen != new_gen) ? 1 : 0; +} + +static int compare_refs(struct send_ctx *sctx, struct btrfs_path *path, + struct btrfs_key *key) +{ + struct btrfs_inode_extref *extref; + struct extent_buffer *leaf; + u64 dirid = 0, last_dirid = 0; + unsigned long ptr; + u32 item_size; + u32 cur_offset = 0; + int ref_name_len; + int ret = 0; + + /* Easy case, just check this one dirid */ + if (key->type == BTRFS_INODE_REF_KEY) { + dirid = key->offset; + + ret = dir_changed(sctx, dirid); + goto out; + } + + leaf = path->nodes[0]; + item_size = btrfs_item_size_nr(leaf, path->slots[0]); + ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); + while (cur_offset < item_size) { + extref = (struct btrfs_inode_extref *)(ptr + + cur_offset); + dirid = btrfs_inode_extref_parent(leaf, extref); + ref_name_len = btrfs_inode_extref_name_len(leaf, extref); + cur_offset += ref_name_len + sizeof(*extref); + if (dirid == last_dirid) + continue; + ret = dir_changed(sctx, dirid); + if (ret) + break; + last_dirid = dirid; + } +out: + return ret; +} + /* * Updates compare related fields in sctx and simply forwards to the actual * changed_xxx functions. @@ -4376,6 +4507,19 @@ static int changed_cb(struct btrfs_root *left_root, int ret = 0; struct send_ctx *sctx = ctx; + if (result == BTRFS_COMPARE_TREE_SAME) { + if (key->type != BTRFS_INODE_REF_KEY && + key->type != BTRFS_INODE_EXTREF_KEY) + return 0; + ret = compare_refs(sctx, left_path, key); + if (!ret) + return 0; + if (ret < 0) + return ret; + result = BTRFS_COMPARE_TREE_CHANGED; + ret = 0; + } + sctx->left_path = left_path; sctx->right_path = right_path; sctx->cmp_key = key; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8eb6191..3aab10c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -56,6 +56,8 @@ #include "rcu-string.h" #include "dev-replace.h" #include "free-space-cache.h" +#include "backref.h" +#include "tests/btrfs-tests.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> @@ -320,14 +322,15 @@ enum { Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_skip_balance, Opt_check_integrity, Opt_check_integrity_including_extent_data, - Opt_check_integrity_print_mask, Opt_fatal_errors, + Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree, + Opt_commit_interval, Opt_err, }; static match_table_t tokens = { {Opt_degraded, "degraded"}, {Opt_subvol, "subvol=%s"}, - {Opt_subvolid, "subvolid=%d"}, + {Opt_subvolid, "subvolid=%s"}, {Opt_device, "device=%s"}, {Opt_nodatasum, "nodatasum"}, {Opt_nodatacow, "nodatacow"}, @@ -360,7 +363,9 @@ static match_table_t tokens = { {Opt_check_integrity, "check_int"}, {Opt_check_integrity_including_extent_data, "check_int_data"}, {Opt_check_integrity_print_mask, "check_int_print_mask=%d"}, + {Opt_rescan_uuid_tree, "rescan_uuid_tree"}, {Opt_fatal_errors, "fatal_errors=%s"}, + {Opt_commit_interval, "commit=%d"}, {Opt_err, NULL}, }; @@ -496,10 +501,15 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_opt(info->mount_opt, NOBARRIER); break; case Opt_thread_pool: - intarg = 0; - match_int(&args[0], &intarg); - if (intarg) + ret = match_int(&args[0], &intarg); + if (ret) { + goto out; + } else if (intarg > 0) { info->thread_pool_size = intarg; + } else { + ret = -EINVAL; + goto out; + } break; case Opt_max_inline: num = match_strdup(&args[0]); @@ -513,7 +523,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) root->sectorsize); } printk(KERN_INFO "btrfs: max_inline at %llu\n", - (unsigned long long)info->max_inline); + info->max_inline); + } else { + ret = -ENOMEM; + goto out; } break; case Opt_alloc_start: @@ -525,7 +538,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) kfree(num); printk(KERN_INFO "btrfs: allocations start at %llu\n", - (unsigned long long)info->alloc_start); + info->alloc_start); + } else { + ret = -ENOMEM; + goto out; } break; case Opt_noacl: @@ -540,12 +556,16 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT); break; case Opt_ratio: - intarg = 0; - match_int(&args[0], &intarg); - if (intarg) { + ret = match_int(&args[0], &intarg); + if (ret) { + goto out; + } else if (intarg >= 0) { info->metadata_ratio = intarg; printk(KERN_INFO "btrfs: metadata ratio %d\n", info->metadata_ratio); + } else { + ret = -EINVAL; + goto out; } break; case Opt_discard: @@ -554,6 +574,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_space_cache: btrfs_set_opt(info->mount_opt, SPACE_CACHE); break; + case Opt_rescan_uuid_tree: + btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE); + break; case Opt_no_space_cache: printk(KERN_INFO "btrfs: disabling disk space caching\n"); btrfs_clear_opt(info->mount_opt, SPACE_CACHE); @@ -596,13 +619,17 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); break; case Opt_check_integrity_print_mask: - intarg = 0; - match_int(&args[0], &intarg); - if (intarg) { + ret = match_int(&args[0], &intarg); + if (ret) { + goto out; + } else if (intarg >= 0) { info->check_integrity_print_mask = intarg; printk(KERN_INFO "btrfs:" " check_integrity_print_mask 0x%x\n", info->check_integrity_print_mask); + } else { + ret = -EINVAL; + goto out; } break; #else @@ -626,6 +653,29 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) goto out; } break; + case Opt_commit_interval: + intarg = 0; + ret = match_int(&args[0], &intarg); + if (ret < 0) { + printk(KERN_ERR + "btrfs: invalid commit interval\n"); + ret = -EINVAL; + goto out; + } + if (intarg > 0) { + if (intarg > 300) { + printk(KERN_WARNING + "btrfs: excessive commit interval %d\n", + intarg); + } + info->commit_interval = intarg; + } else { + printk(KERN_INFO + "btrfs: using default commit interval %ds\n", + BTRFS_DEFAULT_COMMIT_INTERVAL); + info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; + } + break; case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); @@ -654,8 +704,8 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, { substring_t args[MAX_OPT_ARGS]; char *device_name, *opts, *orig, *p; + char *num = NULL; int error = 0; - int intarg; if (!options) return 0; @@ -679,17 +729,23 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, case Opt_subvol: kfree(*subvol_name); *subvol_name = match_strdup(&args[0]); + if (!*subvol_name) { + error = -ENOMEM; + goto out; + } break; case Opt_subvolid: - intarg = 0; - error = match_int(&args[0], &intarg); - if (!error) { + num = match_strdup(&args[0]); + if (num) { + *subvol_objectid = memparse(num, NULL); + kfree(num); /* we want the original fs_tree */ - if (!intarg) + if (!*subvol_objectid) *subvol_objectid = BTRFS_FS_TREE_OBJECTID; - else - *subvol_objectid = intarg; + } else { + error = -EINVAL; + goto out; } break; case Opt_subvolrootid: @@ -892,11 +948,9 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) if (btrfs_test_opt(root, NOBARRIER)) seq_puts(seq, ",nobarrier"); if (info->max_inline != 8192 * 1024) - seq_printf(seq, ",max_inline=%llu", - (unsigned long long)info->max_inline); + seq_printf(seq, ",max_inline=%llu", info->max_inline); if (info->alloc_start != 0) - seq_printf(seq, ",alloc_start=%llu", - (unsigned long long)info->alloc_start); + seq_printf(seq, ",alloc_start=%llu", info->alloc_start); if (info->thread_pool_size != min_t(unsigned long, num_online_cpus() + 2, 8)) seq_printf(seq, ",thread_pool=%d", info->thread_pool_size); @@ -928,6 +982,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",space_cache"); else seq_puts(seq, ",nospace_cache"); + if (btrfs_test_opt(root, RESCAN_UUID_TREE)) + seq_puts(seq, ",rescan_uuid_tree"); if (btrfs_test_opt(root, CLEAR_CACHE)) seq_puts(seq, ",clear_cache"); if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED)) @@ -940,8 +996,24 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",inode_cache"); if (btrfs_test_opt(root, SKIP_BALANCE)) seq_puts(seq, ",skip_balance"); + if (btrfs_test_opt(root, RECOVERY)) + seq_puts(seq, ",recovery"); +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA)) + seq_puts(seq, ",check_int_data"); + else if (btrfs_test_opt(root, CHECK_INTEGRITY)) + seq_puts(seq, ",check_int"); + if (info->check_integrity_print_mask) + seq_printf(seq, ",check_int_print_mask=%d", + info->check_integrity_print_mask); +#endif + if (info->metadata_ratio) + seq_printf(seq, ",metadata_ratio=%d", + info->metadata_ratio); if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR)) seq_puts(seq, ",fatal_errors=panic"); + if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL) + seq_printf(seq, ",commit=%d", info->commit_interval); return 0; } @@ -1696,6 +1768,11 @@ static void btrfs_print_info(void) "\n"); } +static int btrfs_run_sanity_tests(void) +{ + return btrfs_test_free_space_cache(); +} + static int __init init_btrfs_fs(void) { int err; @@ -1734,23 +1811,32 @@ static int __init init_btrfs_fs(void) if (err) goto free_auto_defrag; - err = btrfs_interface_init(); + err = btrfs_prelim_ref_init(); if (err) - goto free_delayed_ref; + goto free_prelim_ref; - err = register_filesystem(&btrfs_fs_type); + err = btrfs_interface_init(); if (err) - goto unregister_ioctl; + goto free_delayed_ref; btrfs_init_lockdep(); btrfs_print_info(); - btrfs_test_free_space_cache(); + + err = btrfs_run_sanity_tests(); + if (err) + goto unregister_ioctl; + + err = register_filesystem(&btrfs_fs_type); + if (err) + goto unregister_ioctl; return 0; unregister_ioctl: btrfs_interface_exit(); +free_prelim_ref: + btrfs_prelim_ref_exit(); free_delayed_ref: btrfs_delayed_ref_exit(); free_auto_defrag: @@ -1777,6 +1863,7 @@ static void __exit exit_btrfs_fs(void) btrfs_delayed_ref_exit(); btrfs_auto_defrag_exit(); btrfs_delayed_inode_exit(); + btrfs_prelim_ref_exit(); ordered_data_exit(); extent_map_exit(); extent_io_exit(); diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h new file mode 100644 index 0000000..5808776 --- /dev/null +++ b/fs/btrfs/tests/btrfs-tests.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) 2013 Fusion IO. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#ifndef __BTRFS_TESTS +#define __BTRFS_TESTS + +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + +#define test_msg(fmt, ...) pr_info("btrfs: selftest: " fmt, ##__VA_ARGS__) + +int btrfs_test_free_space_cache(void); +#else +static inline int btrfs_test_free_space_cache(void) +{ + return 0; +} +#endif + +#endif diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c new file mode 100644 index 0000000..6fc8201 --- /dev/null +++ b/fs/btrfs/tests/free-space-tests.c @@ -0,0 +1,395 @@ +/* + * Copyright (C) 2013 Fusion IO. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#include <linux/slab.h> +#include "btrfs-tests.h" +#include "../ctree.h" +#include "../free-space-cache.h" + +#define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8) +static struct btrfs_block_group_cache *init_test_block_group(void) +{ + struct btrfs_block_group_cache *cache; + + cache = kzalloc(sizeof(*cache), GFP_NOFS); + if (!cache) + return NULL; + cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl), + GFP_NOFS); + if (!cache->free_space_ctl) { + kfree(cache); + return NULL; + } + + cache->key.objectid = 0; + cache->key.offset = 1024 * 1024 * 1024; + cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; + cache->sectorsize = 4096; + + spin_lock_init(&cache->lock); + INIT_LIST_HEAD(&cache->list); + INIT_LIST_HEAD(&cache->cluster_list); + INIT_LIST_HEAD(&cache->new_bg_list); + + btrfs_init_free_space_ctl(cache); + + return cache; +} + +/* + * This test just does basic sanity checking, making sure we can add an exten + * entry and remove space from either end and the middle, and make sure we can + * remove space that covers adjacent extent entries. + */ +static int test_extents(struct btrfs_block_group_cache *cache) +{ + int ret = 0; + + test_msg("Running extent only tests\n"); + + /* First just make sure we can remove an entire entry */ + ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024); + if (ret) { + test_msg("Error adding initial extents %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024); + if (ret) { + test_msg("Error removing extent %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 0, 4 * 1024 * 1024)) { + test_msg("Full remove left some lingering space\n"); + return -1; + } + + /* Ok edge and middle cases now */ + ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024); + if (ret) { + test_msg("Error adding half extent %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 1 * 1024 * 1024); + if (ret) { + test_msg("Error removing tail end %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024); + if (ret) { + test_msg("Error removing front end %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 2 * 1024 * 1024, 4096); + if (ret) { + test_msg("Error removing middle peice %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 0, 1 * 1024 * 1024)) { + test_msg("Still have space at the front\n"); + return -1; + } + + if (test_check_exists(cache, 2 * 1024 * 1024, 4096)) { + test_msg("Still have space in the middle\n"); + return -1; + } + + if (test_check_exists(cache, 3 * 1024 * 1024, 1 * 1024 * 1024)) { + test_msg("Still have space at the end\n"); + return -1; + } + + /* Cleanup */ + __btrfs_remove_free_space_cache(cache->free_space_ctl); + + return 0; +} + +static int test_bitmaps(struct btrfs_block_group_cache *cache) +{ + u64 next_bitmap_offset; + int ret; + + test_msg("Running bitmap only tests\n"); + + ret = test_add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't create a bitmap entry %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024); + if (ret) { + test_msg("Error removing bitmap full range %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 0, 4 * 1024 * 1024)) { + test_msg("Left some space in bitmap\n"); + return -1; + } + + ret = test_add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't add to our bitmap entry %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 2 * 1024 * 1024); + if (ret) { + test_msg("Couldn't remove middle chunk %d\n", ret); + return ret; + } + + /* + * The first bitmap we have starts at offset 0 so the next one is just + * at the end of the first bitmap. + */ + next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096); + + /* Test a bit straddling two bitmaps */ + ret = test_add_free_space_entry(cache, next_bitmap_offset - + (2 * 1024 * 1024), 4 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't add space that straddles two bitmaps %d\n", + ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, next_bitmap_offset - + (1 * 1024 * 1024), 2 * 1024 * 1024); + if (ret) { + test_msg("Couldn't remove overlapping space %d\n", ret); + return ret; + } + + if (test_check_exists(cache, next_bitmap_offset - (1 * 1024 * 1024), + 2 * 1024 * 1024)) { + test_msg("Left some space when removing overlapping\n"); + return -1; + } + + __btrfs_remove_free_space_cache(cache->free_space_ctl); + + return 0; +} + +/* This is the high grade jackassery */ +static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache) +{ + u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096); + int ret; + + test_msg("Running bitmap and extent tests\n"); + + /* + * First let's do something simple, an extent at the same offset as the + * bitmap, but the free space completely in the extent and then + * completely in the bitmap. + */ + ret = test_add_free_space_entry(cache, 4 * 1024 * 1024, 1 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't create bitmap entry %d\n", ret); + return ret; + } + + ret = test_add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0); + if (ret) { + test_msg("Couldn't add extent entry %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024); + if (ret) { + test_msg("Couldn't remove extent entry %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 0, 1 * 1024 * 1024)) { + test_msg("Left remnants after our remove\n"); + return -1; + } + + /* Now to add back the extent entry and remove from the bitmap */ + ret = test_add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0); + if (ret) { + test_msg("Couldn't re-add extent entry %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 4 * 1024 * 1024, 1 * 1024 * 1024); + if (ret) { + test_msg("Couldn't remove from bitmap %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 4 * 1024 * 1024, 1 * 1024 * 1024)) { + test_msg("Left remnants in the bitmap\n"); + return -1; + } + + /* + * Ok so a little more evil, extent entry and bitmap at the same offset, + * removing an overlapping chunk. + */ + ret = test_add_free_space_entry(cache, 1 * 1024 * 1024, 4 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't add to a bitmap %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 512 * 1024, 3 * 1024 * 1024); + if (ret) { + test_msg("Couldn't remove overlapping space %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 512 * 1024, 3 * 1024 * 1024)) { + test_msg("Left over peices after removing overlapping\n"); + return -1; + } + + __btrfs_remove_free_space_cache(cache->free_space_ctl); + + /* Now with the extent entry offset into the bitmap */ + ret = test_add_free_space_entry(cache, 4 * 1024 * 1024, 4 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't add space to the bitmap %d\n", ret); + return ret; + } + + ret = test_add_free_space_entry(cache, 2 * 1024 * 1024, 2 * 1024 * 1024, 0); + if (ret) { + test_msg("Couldn't add extent to the cache %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 4 * 1024 * 1024); + if (ret) { + test_msg("Problem removing overlapping space %d\n", ret); + return ret; + } + + if (test_check_exists(cache, 3 * 1024 * 1024, 4 * 1024 * 1024)) { + test_msg("Left something behind when removing space"); + return -1; + } + + /* + * This has blown up in the past, the extent entry starts before the + * bitmap entry, but we're trying to remove an offset that falls + * completely within the bitmap range and is in both the extent entry + * and the bitmap entry, looks like this + * + * [ extent ] + * [ bitmap ] + * [ del ] + */ + __btrfs_remove_free_space_cache(cache->free_space_ctl); + ret = test_add_free_space_entry(cache, bitmap_offset + 4 * 1024 * 1024, + 4 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't add bitmap %d\n", ret); + return ret; + } + + ret = test_add_free_space_entry(cache, bitmap_offset - 1 * 1024 * 1024, + 5 * 1024 * 1024, 0); + if (ret) { + test_msg("Couldn't add extent entry %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, bitmap_offset + 1 * 1024 * 1024, + 5 * 1024 * 1024); + if (ret) { + test_msg("Failed to free our space %d\n", ret); + return ret; + } + + if (test_check_exists(cache, bitmap_offset + 1 * 1024 * 1024, + 5 * 1024 * 1024)) { + test_msg("Left stuff over\n"); + return -1; + } + + __btrfs_remove_free_space_cache(cache->free_space_ctl); + + /* + * This blew up before, we have part of the free space in a bitmap and + * then the entirety of the rest of the space in an extent. This used + * to return -EAGAIN back from btrfs_remove_extent, make sure this + * doesn't happen. + */ + ret = test_add_free_space_entry(cache, 1 * 1024 * 1024, 2 * 1024 * 1024, 1); + if (ret) { + test_msg("Couldn't add bitmap entry %d\n", ret); + return ret; + } + + ret = test_add_free_space_entry(cache, 3 * 1024 * 1024, 1 * 1024 * 1024, 0); + if (ret) { + test_msg("Couldn't add extent entry %d\n", ret); + return ret; + } + + ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 3 * 1024 * 1024); + if (ret) { + test_msg("Error removing bitmap and extent overlapping %d\n", ret); + return ret; + } + + __btrfs_remove_free_space_cache(cache->free_space_ctl); + return 0; +} + +int btrfs_test_free_space_cache(void) +{ + struct btrfs_block_group_cache *cache; + int ret; + + test_msg("Running btrfs free space cache tests\n"); + + cache = init_test_block_group(); + if (!cache) { + test_msg("Couldn't run the tests\n"); + return 0; + } + + ret = test_extents(cache); + if (ret) + goto out; + ret = test_bitmaps(cache); + if (ret) + goto out; + ret = test_bitmaps_and_extents(cache); + if (ret) + goto out; +out: + __btrfs_remove_free_space_cache(cache->free_space_ctl); + kfree(cache->free_space_ctl); + kfree(cache); + test_msg("Free space cache tests finished\n"); + return ret; +} diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index d58cce7..cac4a3f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -837,7 +837,7 @@ int btrfs_wait_marked_extents(struct btrfs_root *root, * them in one of two extent_io trees. This is used to make sure all of * those extents are on disk for transaction or log commit */ -int btrfs_write_and_wait_marked_extents(struct btrfs_root *root, +static int btrfs_write_and_wait_marked_extents(struct btrfs_root *root, struct extent_io_tree *dirty_pages, int mark) { int ret; @@ -983,12 +983,12 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, * a dirty root struct and adds it into the list of dead roots that need to * be deleted */ -int btrfs_add_dead_root(struct btrfs_root *root) +void btrfs_add_dead_root(struct btrfs_root *root) { spin_lock(&root->fs_info->trans_lock); - list_add_tail(&root->root_list, &root->fs_info->dead_roots); + if (list_empty(&root->root_list)) + list_add_tail(&root->root_list, &root->fs_info->dead_roots); spin_unlock(&root->fs_info->trans_lock); - return 0; } /* @@ -1225,8 +1225,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, btrfs_set_root_stransid(new_root_item, 0); btrfs_set_root_rtransid(new_root_item, 0); } - new_root_item->otime.sec = cpu_to_le64(cur_time.tv_sec); - new_root_item->otime.nsec = cpu_to_le32(cur_time.tv_nsec); + btrfs_set_stack_timespec_sec(&new_root_item->otime, cur_time.tv_sec); + btrfs_set_stack_timespec_nsec(&new_root_item->otime, cur_time.tv_nsec); btrfs_set_root_otransid(new_root_item, trans->transid); old = btrfs_lock_root_node(root); @@ -1311,8 +1311,26 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, dentry->d_name.len * 2); parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode); - if (ret) + if (ret) { btrfs_abort_transaction(trans, root, ret); + goto fail; + } + ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, new_uuid.b, + BTRFS_UUID_KEY_SUBVOL, objectid); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto fail; + } + if (!btrfs_is_empty_uuid(new_root_item->received_uuid)) { + ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, + new_root_item->received_uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + objectid); + if (ret && ret != -EEXIST) { + btrfs_abort_transaction(trans, root, ret); + goto fail; + } + } fail: pending->error = ret; dir_item_existed: @@ -1362,6 +1380,8 @@ static void update_super_roots(struct btrfs_root *root) super->root_level = root_item->level; if (btrfs_test_opt(root, SPACE_CACHE)) super->cache_generation = root_item->generation; + if (root->fs_info->update_uuid_tree_gen) + super->uuid_tree_generation = root_item->generation; } int btrfs_transaction_in_commit(struct btrfs_fs_info *info) @@ -1925,11 +1945,10 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root) } root = list_first_entry(&fs_info->dead_roots, struct btrfs_root, root_list); - list_del(&root->root_list); + list_del_init(&root->root_list); spin_unlock(&fs_info->trans_lock); - pr_debug("btrfs: cleaner removing %llu\n", - (unsigned long long)root->objectid); + pr_debug("btrfs: cleaner removing %llu\n", root->objectid); btrfs_kill_all_delayed_nodes(root); @@ -1942,6 +1961,5 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root) * If we encounter a transaction abort during snapshot cleaning, we * don't want to crash here */ - BUG_ON(ret < 0 && ret != -EAGAIN && ret != -EROFS); - return 1; + return (ret < 0) ? 0 : 1; } diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 005b037..5c2af84 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -143,7 +143,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid); int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); -int btrfs_add_dead_root(struct btrfs_root *root); +void btrfs_add_dead_root(struct btrfs_root *root); int btrfs_defrag_root(struct btrfs_root *root); int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root); int btrfs_commit_transaction(struct btrfs_trans_handle *trans, @@ -160,8 +160,6 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans, void btrfs_throttle(struct btrfs_root *root); int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root); -int btrfs_write_and_wait_marked_extents(struct btrfs_root *root, - struct extent_io_tree *dirty_pages, int mark); int btrfs_write_marked_extents(struct btrfs_root *root, struct extent_io_tree *dirty_pages, int mark); int btrfs_wait_marked_extents(struct btrfs_root *root, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2c67914..0d9613c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -747,7 +747,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); if (ret) goto out; - btrfs_run_delayed_items(trans, root); + else + ret = btrfs_run_delayed_items(trans, root); out: kfree(name); iput(inode); @@ -923,7 +924,9 @@ again: kfree(victim_name); if (ret) return ret; - btrfs_run_delayed_items(trans, root); + ret = btrfs_run_delayed_items(trans, root); + if (ret) + return ret; *search_done = 1; goto again; } @@ -990,7 +993,9 @@ again: inode, victim_name, victim_name_len); - btrfs_run_delayed_items(trans, root); + if (!ret) + ret = btrfs_run_delayed_items( + trans, root); } iput(victim_parent); kfree(victim_name); @@ -1536,8 +1541,10 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, name_len = btrfs_dir_name_len(eb, di); name = kmalloc(name_len, GFP_NOFS); - if (!name) - return -ENOMEM; + if (!name) { + ret = -ENOMEM; + goto out; + } log_type = btrfs_dir_type(eb, di); read_extent_buffer(eb, name, (unsigned long)(di + 1), @@ -1810,7 +1817,7 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); if (!ret) - btrfs_run_delayed_items(trans, root); + ret = btrfs_run_delayed_items(trans, root); kfree(name); iput(inode); if (ret) @@ -3746,8 +3753,9 @@ next_slot: } log_extents: + btrfs_release_path(path); + btrfs_release_path(dst_path); if (fast_search) { - btrfs_release_path(dst_path); ret = btrfs_log_changed_extents(trans, root, inode, dst_path); if (ret) { err = ret; @@ -3764,8 +3772,6 @@ log_extents: } if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) { - btrfs_release_path(path); - btrfs_release_path(dst_path); ret = log_directory_changes(trans, root, inode, path, dst_path); if (ret) { err = ret; diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c new file mode 100644 index 0000000..dd0dea3 --- /dev/null +++ b/fs/btrfs/uuid-tree.c @@ -0,0 +1,358 @@ +/* + * Copyright (C) STRATO AG 2013. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ +#include <linux/uuid.h> +#include <asm/unaligned.h> +#include "ctree.h" +#include "transaction.h" +#include "disk-io.h" +#include "print-tree.h" + + +static void btrfs_uuid_to_key(u8 *uuid, u8 type, struct btrfs_key *key) +{ + key->type = type; + key->objectid = get_unaligned_le64(uuid); + key->offset = get_unaligned_le64(uuid + sizeof(u64)); +} + +/* return -ENOENT for !found, < 0 for errors, or 0 if an item was found */ +static int btrfs_uuid_tree_lookup(struct btrfs_root *uuid_root, u8 *uuid, + u8 type, u64 subid) +{ + int ret; + struct btrfs_path *path = NULL; + struct extent_buffer *eb; + int slot; + u32 item_size; + unsigned long offset; + struct btrfs_key key; + + if (WARN_ON_ONCE(!uuid_root)) { + ret = -ENOENT; + goto out; + } + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + btrfs_uuid_to_key(uuid, type, &key); + ret = btrfs_search_slot(NULL, uuid_root, &key, path, 0, 0); + if (ret < 0) { + goto out; + } else if (ret > 0) { + ret = -ENOENT; + goto out; + } + + eb = path->nodes[0]; + slot = path->slots[0]; + item_size = btrfs_item_size_nr(eb, slot); + offset = btrfs_item_ptr_offset(eb, slot); + ret = -ENOENT; + + if (!IS_ALIGNED(item_size, sizeof(u64))) { + pr_warn("btrfs: uuid item with illegal size %lu!\n", + (unsigned long)item_size); + goto out; + } + while (item_size) { + __le64 data; + + read_extent_buffer(eb, &data, offset, sizeof(data)); + if (le64_to_cpu(data) == subid) { + ret = 0; + break; + } + offset += sizeof(data); + item_size -= sizeof(data); + } + +out: + btrfs_free_path(path); + return ret; +} + +int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, + struct btrfs_root *uuid_root, u8 *uuid, u8 type, + u64 subid_cpu) +{ + int ret; + struct btrfs_path *path = NULL; + struct btrfs_key key; + struct extent_buffer *eb; + int slot; + unsigned long offset; + __le64 subid_le; + + ret = btrfs_uuid_tree_lookup(uuid_root, uuid, type, subid_cpu); + if (ret != -ENOENT) + return ret; + + if (WARN_ON_ONCE(!uuid_root)) { + ret = -EINVAL; + goto out; + } + + btrfs_uuid_to_key(uuid, type, &key); + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + ret = btrfs_insert_empty_item(trans, uuid_root, path, &key, + sizeof(subid_le)); + if (ret >= 0) { + /* Add an item for the type for the first time */ + eb = path->nodes[0]; + slot = path->slots[0]; + offset = btrfs_item_ptr_offset(eb, slot); + } else if (ret == -EEXIST) { + /* + * An item with that type already exists. + * Extend the item and store the new subid at the end. + */ + btrfs_extend_item(uuid_root, path, sizeof(subid_le)); + eb = path->nodes[0]; + slot = path->slots[0]; + offset = btrfs_item_ptr_offset(eb, slot); + offset += btrfs_item_size_nr(eb, slot) - sizeof(subid_le); + } else if (ret < 0) { + pr_warn("btrfs: insert uuid item failed %d (0x%016llx, 0x%016llx) type %u!\n", + ret, (unsigned long long)key.objectid, + (unsigned long long)key.offset, type); + goto out; + } + + ret = 0; + subid_le = cpu_to_le64(subid_cpu); + write_extent_buffer(eb, &subid_le, offset, sizeof(subid_le)); + btrfs_mark_buffer_dirty(eb); + +out: + btrfs_free_path(path); + return ret; +} + +int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans, + struct btrfs_root *uuid_root, u8 *uuid, u8 type, + u64 subid) +{ + int ret; + struct btrfs_path *path = NULL; + struct btrfs_key key; + struct extent_buffer *eb; + int slot; + unsigned long offset; + u32 item_size; + unsigned long move_dst; + unsigned long move_src; + unsigned long move_len; + + if (WARN_ON_ONCE(!uuid_root)) { + ret = -EINVAL; + goto out; + } + + btrfs_uuid_to_key(uuid, type, &key); + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + ret = btrfs_search_slot(trans, uuid_root, &key, path, -1, 1); + if (ret < 0) { + pr_warn("btrfs: error %d while searching for uuid item!\n", + ret); + goto out; + } + if (ret > 0) { + ret = -ENOENT; + goto out; + } + + eb = path->nodes[0]; + slot = path->slots[0]; + offset = btrfs_item_ptr_offset(eb, slot); + item_size = btrfs_item_size_nr(eb, slot); + if (!IS_ALIGNED(item_size, sizeof(u64))) { + pr_warn("btrfs: uuid item with illegal size %lu!\n", + (unsigned long)item_size); + ret = -ENOENT; + goto out; + } + while (item_size) { + __le64 read_subid; + + read_extent_buffer(eb, &read_subid, offset, sizeof(read_subid)); + if (le64_to_cpu(read_subid) == subid) + break; + offset += sizeof(read_subid); + item_size -= sizeof(read_subid); + } + + if (!item_size) { + ret = -ENOENT; + goto out; + } + + item_size = btrfs_item_size_nr(eb, slot); + if (item_size == sizeof(subid)) { + ret = btrfs_del_item(trans, uuid_root, path); + goto out; + } + + move_dst = offset; + move_src = offset + sizeof(subid); + move_len = item_size - (move_src - btrfs_item_ptr_offset(eb, slot)); + memmove_extent_buffer(eb, move_dst, move_src, move_len); + btrfs_truncate_item(uuid_root, path, item_size - sizeof(subid), 1); + +out: + btrfs_free_path(path); + return ret; +} + +static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type, + u64 subid) +{ + struct btrfs_trans_handle *trans; + int ret; + + /* 1 - for the uuid item */ + trans = btrfs_start_transaction(uuid_root, 1); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out; + } + + ret = btrfs_uuid_tree_rem(trans, uuid_root, uuid, type, subid); + btrfs_end_transaction(trans, uuid_root); + +out: + return ret; +} + +int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info, + int (*check_func)(struct btrfs_fs_info *, u8 *, u8, + u64)) +{ + struct btrfs_root *root = fs_info->uuid_root; + struct btrfs_key key; + struct btrfs_key max_key; + struct btrfs_path *path; + int ret = 0; + struct extent_buffer *leaf; + int slot; + u32 item_size; + unsigned long offset; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + key.objectid = 0; + key.type = 0; + key.offset = 0; + max_key.objectid = (u64)-1; + max_key.type = (u8)-1; + max_key.offset = (u64)-1; + +again_search_slot: + path->keep_locks = 1; + ret = btrfs_search_forward(root, &key, &max_key, path, 0); + if (ret) { + if (ret > 0) + ret = 0; + goto out; + } + + while (1) { + cond_resched(); + leaf = path->nodes[0]; + slot = path->slots[0]; + btrfs_item_key_to_cpu(leaf, &key, slot); + + if (key.type != BTRFS_UUID_KEY_SUBVOL && + key.type != BTRFS_UUID_KEY_RECEIVED_SUBVOL) + goto skip; + + offset = btrfs_item_ptr_offset(leaf, slot); + item_size = btrfs_item_size_nr(leaf, slot); + if (!IS_ALIGNED(item_size, sizeof(u64))) { + pr_warn("btrfs: uuid item with illegal size %lu!\n", + (unsigned long)item_size); + goto skip; + } + while (item_size) { + u8 uuid[BTRFS_UUID_SIZE]; + __le64 subid_le; + u64 subid_cpu; + + put_unaligned_le64(key.objectid, uuid); + put_unaligned_le64(key.offset, uuid + sizeof(u64)); + read_extent_buffer(leaf, &subid_le, offset, + sizeof(subid_le)); + subid_cpu = le64_to_cpu(subid_le); + ret = check_func(fs_info, uuid, key.type, subid_cpu); + if (ret < 0) + goto out; + if (ret > 0) { + btrfs_release_path(path); + ret = btrfs_uuid_iter_rem(root, uuid, key.type, + subid_cpu); + if (ret == 0) { + /* + * this might look inefficient, but the + * justification is that it is an + * exception that check_func returns 1, + * and that in the regular case only one + * entry per UUID exists. + */ + goto again_search_slot; + } + if (ret < 0 && ret != -ENOENT) + goto out; + } + item_size -= sizeof(subid_le); + offset += sizeof(subid_le); + } + +skip: + ret = btrfs_next_item(root, path); + if (ret == 0) + continue; + else if (ret > 0) + ret = 0; + break; + } + +out: + btrfs_free_path(path); + if (ret) + pr_warn("btrfs: btrfs_uuid_tree_iterate failed %d\n", ret); + return 0; +} diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 78b8717..0052ca8 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -26,6 +26,7 @@ #include <linux/ratelimit.h> #include <linux/kthread.h> #include <linux/raid/pq.h> +#include <linux/semaphore.h> #include <asm/div64.h> #include "compat.h" #include "ctree.h" @@ -62,6 +63,48 @@ static void unlock_chunks(struct btrfs_root *root) mutex_unlock(&root->fs_info->chunk_mutex); } +static struct btrfs_fs_devices *__alloc_fs_devices(void) +{ + struct btrfs_fs_devices *fs_devs; + + fs_devs = kzalloc(sizeof(*fs_devs), GFP_NOFS); + if (!fs_devs) + return ERR_PTR(-ENOMEM); + + mutex_init(&fs_devs->device_list_mutex); + + INIT_LIST_HEAD(&fs_devs->devices); + INIT_LIST_HEAD(&fs_devs->alloc_list); + INIT_LIST_HEAD(&fs_devs->list); + + return fs_devs; +} + +/** + * alloc_fs_devices - allocate struct btrfs_fs_devices + * @fsid: a pointer to UUID for this FS. If NULL a new UUID is + * generated. + * + * Return: a pointer to a new &struct btrfs_fs_devices on success; + * ERR_PTR() on error. Returned struct is not linked onto any lists and + * can be destroyed with kfree() right away. + */ +static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid) +{ + struct btrfs_fs_devices *fs_devs; + + fs_devs = __alloc_fs_devices(); + if (IS_ERR(fs_devs)) + return fs_devs; + + if (fsid) + memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE); + else + generate_random_uuid(fs_devs->fsid); + + return fs_devs; +} + static void free_fs_devices(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *device; @@ -101,6 +144,27 @@ void btrfs_cleanup_fs_uuids(void) } } +static struct btrfs_device *__alloc_device(void) +{ + struct btrfs_device *dev; + + dev = kzalloc(sizeof(*dev), GFP_NOFS); + if (!dev) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&dev->dev_list); + INIT_LIST_HEAD(&dev->dev_alloc_list); + + spin_lock_init(&dev->io_lock); + + spin_lock_init(&dev->reada_lock); + atomic_set(&dev->reada_in_flight, 0); + INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); + + return dev; +} + static noinline struct btrfs_device *__find_device(struct list_head *head, u64 devid, u8 *uuid) { @@ -395,16 +459,14 @@ static noinline int device_list_add(const char *path, fs_devices = find_fsid(disk_super->fsid); if (!fs_devices) { - fs_devices = kzalloc(sizeof(*fs_devices), GFP_NOFS); - if (!fs_devices) - return -ENOMEM; - INIT_LIST_HEAD(&fs_devices->devices); - INIT_LIST_HEAD(&fs_devices->alloc_list); + fs_devices = alloc_fs_devices(disk_super->fsid); + if (IS_ERR(fs_devices)) + return PTR_ERR(fs_devices); + list_add(&fs_devices->list, &fs_uuids); - memcpy(fs_devices->fsid, disk_super->fsid, BTRFS_FSID_SIZE); fs_devices->latest_devid = devid; fs_devices->latest_trans = found_transid; - mutex_init(&fs_devices->device_list_mutex); + device = NULL; } else { device = __find_device(&fs_devices->devices, devid, @@ -414,17 +476,12 @@ static noinline int device_list_add(const char *path, if (fs_devices->opened) return -EBUSY; - device = kzalloc(sizeof(*device), GFP_NOFS); - if (!device) { + device = btrfs_alloc_device(NULL, &devid, + disk_super->dev_item.uuid); + if (IS_ERR(device)) { /* we can safely leave the fs_devices entry around */ - return -ENOMEM; + return PTR_ERR(device); } - device->devid = devid; - device->dev_stats_valid = 0; - device->work.func = pending_bios_fn; - memcpy(device->uuid, disk_super->dev_item.uuid, - BTRFS_UUID_SIZE); - spin_lock_init(&device->io_lock); name = rcu_string_strdup(path, GFP_NOFS); if (!name) { @@ -432,22 +489,13 @@ static noinline int device_list_add(const char *path, return -ENOMEM; } rcu_assign_pointer(device->name, name); - INIT_LIST_HEAD(&device->dev_alloc_list); - - /* init readahead state */ - spin_lock_init(&device->reada_lock); - device->reada_curr_zone = NULL; - atomic_set(&device->reada_in_flight, 0); - device->reada_next = 0; - INIT_RADIX_TREE(&device->reada_zones, GFP_NOFS & ~__GFP_WAIT); - INIT_RADIX_TREE(&device->reada_extents, GFP_NOFS & ~__GFP_WAIT); mutex_lock(&fs_devices->device_list_mutex); list_add_rcu(&device->dev_list, &fs_devices->devices); + fs_devices->num_devices++; mutex_unlock(&fs_devices->device_list_mutex); device->fs_devices = fs_devices; - fs_devices->num_devices++; } else if (!device->name || strcmp(device->name->str, path)) { name = rcu_string_strdup(path, GFP_NOFS); if (!name) @@ -474,25 +522,21 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) struct btrfs_device *device; struct btrfs_device *orig_dev; - fs_devices = kzalloc(sizeof(*fs_devices), GFP_NOFS); - if (!fs_devices) - return ERR_PTR(-ENOMEM); + fs_devices = alloc_fs_devices(orig->fsid); + if (IS_ERR(fs_devices)) + return fs_devices; - INIT_LIST_HEAD(&fs_devices->devices); - INIT_LIST_HEAD(&fs_devices->alloc_list); - INIT_LIST_HEAD(&fs_devices->list); - mutex_init(&fs_devices->device_list_mutex); fs_devices->latest_devid = orig->latest_devid; fs_devices->latest_trans = orig->latest_trans; fs_devices->total_devices = orig->total_devices; - memcpy(fs_devices->fsid, orig->fsid, sizeof(fs_devices->fsid)); /* We have held the volume lock, it is safe to get the devices. */ list_for_each_entry(orig_dev, &orig->devices, dev_list) { struct rcu_string *name; - device = kzalloc(sizeof(*device), GFP_NOFS); - if (!device) + device = btrfs_alloc_device(NULL, &orig_dev->devid, + orig_dev->uuid); + if (IS_ERR(device)) goto error; /* @@ -506,13 +550,6 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) } rcu_assign_pointer(device->name, name); - device->devid = orig_dev->devid; - device->work.func = pending_bios_fn; - memcpy(device->uuid, orig_dev->uuid, sizeof(device->uuid)); - spin_lock_init(&device->io_lock); - INIT_LIST_HEAD(&device->dev_list); - INIT_LIST_HEAD(&device->dev_alloc_list); - list_add(&device->dev_list, &fs_devices->devices); device->fs_devices = fs_devices; fs_devices->num_devices++; @@ -636,23 +673,22 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) if (device->can_discard) fs_devices->num_can_discard--; + if (device->missing) + fs_devices->missing_devices--; - new_device = kmalloc(sizeof(*new_device), GFP_NOFS); - BUG_ON(!new_device); /* -ENOMEM */ - memcpy(new_device, device, sizeof(*new_device)); + new_device = btrfs_alloc_device(NULL, &device->devid, + device->uuid); + BUG_ON(IS_ERR(new_device)); /* -ENOMEM */ /* Safe because we are under uuid_mutex */ if (device->name) { name = rcu_string_strdup(device->name->str, GFP_NOFS); - BUG_ON(device->name && !name); /* -ENOMEM */ + BUG_ON(!name); /* -ENOMEM */ rcu_assign_pointer(new_device->name, name); } - new_device->bdev = NULL; - new_device->writeable = 0; - new_device->in_fs_metadata = 0; - new_device->can_discard = 0; - spin_lock_init(&new_device->io_lock); + list_replace_rcu(&device->dev_list, &new_device->dev_list); + new_device->fs_devices = device->fs_devices; call_rcu(&device->rcu, free_device); } @@ -865,7 +901,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, disk_super = p + (bytenr & ~PAGE_CACHE_MASK); if (btrfs_super_bytenr(disk_super) != bytenr || - disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) + btrfs_super_magic(disk_super) != BTRFS_MAGIC) goto error_unmap; devid = btrfs_stack_device_id(&disk_super->dev_item); @@ -880,8 +916,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, printk(KERN_INFO "device fsid %pU ", disk_super->fsid); } - printk(KERN_CONT "devid %llu transid %llu %s\n", - (unsigned long long)devid, (unsigned long long)transid, path); + printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path); ret = device_list_add(path, disk_super, devid, fs_devices_ret); if (!ret && fs_devices_ret) @@ -1278,8 +1313,7 @@ static int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans, btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset); write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid, - (unsigned long)btrfs_dev_extent_chunk_tree_uuid(extent), - BTRFS_UUID_SIZE); + btrfs_dev_extent_chunk_tree_uuid(extent), BTRFS_UUID_SIZE); btrfs_set_dev_extent_length(leaf, extent, num_bytes); btrfs_mark_buffer_dirty(leaf); @@ -1307,15 +1341,14 @@ static u64 find_next_chunk(struct btrfs_fs_info *fs_info) return ret; } -static noinline int find_next_devid(struct btrfs_root *root, u64 *objectid) +static noinline int find_next_devid(struct btrfs_fs_info *fs_info, + u64 *devid_ret) { int ret; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_path *path; - root = root->fs_info->chunk_root; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -1324,20 +1357,21 @@ static noinline int find_next_devid(struct btrfs_root *root, u64 *objectid) key.type = BTRFS_DEV_ITEM_KEY; key.offset = (u64)-1; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->chunk_root, &key, path, 0, 0); if (ret < 0) goto error; BUG_ON(ret == 0); /* Corruption */ - ret = btrfs_previous_item(root, path, BTRFS_DEV_ITEMS_OBJECTID, + ret = btrfs_previous_item(fs_info->chunk_root, path, + BTRFS_DEV_ITEMS_OBJECTID, BTRFS_DEV_ITEM_KEY); if (ret) { - *objectid = 1; + *devid_ret = 1; } else { btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); - *objectid = found_key.offset + 1; + *devid_ret = found_key.offset + 1; } ret = 0; error: @@ -1391,9 +1425,9 @@ static int btrfs_add_device(struct btrfs_trans_handle *trans, btrfs_set_device_bandwidth(leaf, dev_item, 0); btrfs_set_device_start_offset(leaf, dev_item, 0); - ptr = (unsigned long)btrfs_device_uuid(dev_item); + ptr = btrfs_device_uuid(dev_item); write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE); - ptr = (unsigned long)btrfs_device_fsid(dev_item); + ptr = btrfs_device_fsid(dev_item); write_extent_buffer(leaf, root->fs_info->fsid, ptr, BTRFS_UUID_SIZE); btrfs_mark_buffer_dirty(leaf); @@ -1562,7 +1596,9 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) clear_super = true; } + mutex_unlock(&uuid_mutex); ret = btrfs_shrink_device(device, 0); + mutex_lock(&uuid_mutex); if (ret) goto error_undo; @@ -1586,7 +1622,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) /* * the device list mutex makes sure that we don't change * the device list while someone else is writing out all - * the device supers. + * the device supers. Whoever is writing all supers, should + * lock the device list mutex before getting the number of + * devices in the super block (super_copy). Conversely, + * whoever updates the number of devices in the super block + * (super_copy) should hold the device list mutex. */ cur_devices = device->fs_devices; @@ -1610,10 +1650,10 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) device->fs_devices->open_devices--; call_rcu(&device->rcu, free_device); - mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1; btrfs_set_super_num_devices(root->fs_info->super_copy, num_devices); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (cur_devices->open_devices == 0) { struct btrfs_fs_devices *fs_devices; @@ -1793,9 +1833,9 @@ static int btrfs_prepare_sprout(struct btrfs_root *root) if (!fs_devices->seeding) return -EINVAL; - seed_devices = kzalloc(sizeof(*fs_devices), GFP_NOFS); - if (!seed_devices) - return -ENOMEM; + seed_devices = __alloc_fs_devices(); + if (IS_ERR(seed_devices)) + return PTR_ERR(seed_devices); old_devices = clone_fs_devices(fs_devices); if (IS_ERR(old_devices)) { @@ -1814,7 +1854,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root) mutex_lock(&root->fs_info->fs_devices->device_list_mutex); list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices, synchronize_rcu); - mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list); list_for_each_entry(device, &seed_devices->devices, dev_list) { @@ -1830,6 +1869,8 @@ static int btrfs_prepare_sprout(struct btrfs_root *root) generate_random_uuid(fs_devices->fsid); memcpy(root->fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE); memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); + super_flags = btrfs_super_flags(disk_super) & ~BTRFS_SUPER_FLAG_SEEDING; btrfs_set_super_flags(disk_super, super_flags); @@ -1889,11 +1930,9 @@ next_slot: dev_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_item); devid = btrfs_device_id(leaf, dev_item); - read_extent_buffer(leaf, dev_uuid, - (unsigned long)btrfs_device_uuid(dev_item), + read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item), BTRFS_UUID_SIZE); - read_extent_buffer(leaf, fs_uuid, - (unsigned long)btrfs_device_fsid(dev_item), + read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item), BTRFS_UUID_SIZE); device = btrfs_find_device(root->fs_info, devid, dev_uuid, fs_uuid); @@ -1956,10 +1995,10 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); - device = kzalloc(sizeof(*device), GFP_NOFS); - if (!device) { + device = btrfs_alloc_device(root->fs_info, NULL, NULL); + if (IS_ERR(device)) { /* we can safely leave the fs_devices entry around */ - ret = -ENOMEM; + ret = PTR_ERR(device); goto error; } @@ -1971,13 +2010,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) } rcu_assign_pointer(device->name, name); - ret = find_next_devid(root, &device->devid); - if (ret) { - rcu_string_free(device->name); - kfree(device); - goto error; - } - trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { rcu_string_free(device->name); @@ -1992,9 +2024,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) if (blk_queue_discard(q)) device->can_discard = 1; device->writeable = 1; - device->work.func = pending_bios_fn; - generate_random_uuid(device->uuid); - spin_lock_init(&device->io_lock); device->generation = trans->transid; device->io_width = root->sectorsize; device->io_align = root->sectorsize; @@ -2121,6 +2150,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path, struct btrfs_fs_info *fs_info = root->fs_info; struct list_head *devices; struct rcu_string *name; + u64 devid = BTRFS_DEV_REPLACE_DEVID; int ret = 0; *device_out = NULL; @@ -2142,9 +2172,9 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path, } } - device = kzalloc(sizeof(*device), GFP_NOFS); - if (!device) { - ret = -ENOMEM; + device = btrfs_alloc_device(NULL, &devid, NULL); + if (IS_ERR(device)) { + ret = PTR_ERR(device); goto error; } @@ -2161,10 +2191,6 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path, device->can_discard = 1; mutex_lock(&root->fs_info->fs_devices->device_list_mutex); device->writeable = 1; - device->work.func = pending_bios_fn; - generate_random_uuid(device->uuid); - device->devid = BTRFS_DEV_REPLACE_DEVID; - spin_lock_init(&device->io_lock); device->generation = 0; device->io_width = root->sectorsize; device->io_align = root->sectorsize; @@ -2971,10 +2997,6 @@ again: if (found_key.objectid != key.objectid) break; - /* chunk zero is special */ - if (found_key.offset == 0) - break; - chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); if (!counting) { @@ -3010,6 +3032,8 @@ again: spin_unlock(&fs_info->balance_lock); } loop: + if (found_key.offset == 0) + break; key.offset = found_key.offset - 1; } @@ -3074,9 +3098,6 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info) atomic_set(&fs_info->mutually_exclusive_operation_running, 0); } -void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, - struct btrfs_ioctl_balance_args *bargs); - /* * Should be called with both balance and volume mutexes held */ @@ -3139,7 +3160,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, (bctl->data.target & ~allowed))) { printk(KERN_ERR "btrfs: unable to start balance with target " "data profile %llu\n", - (unsigned long long)bctl->data.target); + bctl->data.target); ret = -EINVAL; goto out; } @@ -3148,7 +3169,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, (bctl->meta.target & ~allowed))) { printk(KERN_ERR "btrfs: unable to start balance with target " "metadata profile %llu\n", - (unsigned long long)bctl->meta.target); + bctl->meta.target); ret = -EINVAL; goto out; } @@ -3157,7 +3178,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, (bctl->sys.target & ~allowed))) { printk(KERN_ERR "btrfs: unable to start balance with target " "system profile %llu\n", - (unsigned long long)bctl->sys.target); + bctl->sys.target); ret = -EINVAL; goto out; } @@ -3302,7 +3323,7 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info) } tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance"); - return PTR_RET(tsk); + return PTR_ERR_OR_ZERO(tsk); } int btrfs_recover_balance(struct btrfs_fs_info *fs_info) @@ -3430,6 +3451,264 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) return 0; } +static int btrfs_uuid_scan_kthread(void *data) +{ + struct btrfs_fs_info *fs_info = data; + struct btrfs_root *root = fs_info->tree_root; + struct btrfs_key key; + struct btrfs_key max_key; + struct btrfs_path *path = NULL; + int ret = 0; + struct extent_buffer *eb; + int slot; + struct btrfs_root_item root_item; + u32 item_size; + struct btrfs_trans_handle *trans = NULL; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + key.objectid = 0; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = 0; + + max_key.objectid = (u64)-1; + max_key.type = BTRFS_ROOT_ITEM_KEY; + max_key.offset = (u64)-1; + + path->keep_locks = 1; + + while (1) { + ret = btrfs_search_forward(root, &key, &max_key, path, 0); + if (ret) { + if (ret > 0) + ret = 0; + break; + } + + if (key.type != BTRFS_ROOT_ITEM_KEY || + (key.objectid < BTRFS_FIRST_FREE_OBJECTID && + key.objectid != BTRFS_FS_TREE_OBJECTID) || + key.objectid > BTRFS_LAST_FREE_OBJECTID) + goto skip; + + eb = path->nodes[0]; + slot = path->slots[0]; + item_size = btrfs_item_size_nr(eb, slot); + if (item_size < sizeof(root_item)) + goto skip; + + read_extent_buffer(eb, &root_item, + btrfs_item_ptr_offset(eb, slot), + (int)sizeof(root_item)); + if (btrfs_root_refs(&root_item) == 0) + goto skip; + + if (!btrfs_is_empty_uuid(root_item.uuid) || + !btrfs_is_empty_uuid(root_item.received_uuid)) { + if (trans) + goto update_tree; + + btrfs_release_path(path); + /* + * 1 - subvol uuid item + * 1 - received_subvol uuid item + */ + trans = btrfs_start_transaction(fs_info->uuid_root, 2); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } + continue; + } else { + goto skip; + } +update_tree: + if (!btrfs_is_empty_uuid(root_item.uuid)) { + ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, + root_item.uuid, + BTRFS_UUID_KEY_SUBVOL, + key.objectid); + if (ret < 0) { + pr_warn("btrfs: uuid_tree_add failed %d\n", + ret); + break; + } + } + + if (!btrfs_is_empty_uuid(root_item.received_uuid)) { + ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, + root_item.received_uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + key.objectid); + if (ret < 0) { + pr_warn("btrfs: uuid_tree_add failed %d\n", + ret); + break; + } + } + +skip: + if (trans) { + ret = btrfs_end_transaction(trans, fs_info->uuid_root); + trans = NULL; + if (ret) + break; + } + + btrfs_release_path(path); + if (key.offset < (u64)-1) { + key.offset++; + } else if (key.type < BTRFS_ROOT_ITEM_KEY) { + key.offset = 0; + key.type = BTRFS_ROOT_ITEM_KEY; + } else if (key.objectid < (u64)-1) { + key.offset = 0; + key.type = BTRFS_ROOT_ITEM_KEY; + key.objectid++; + } else { + break; + } + cond_resched(); + } + +out: + btrfs_free_path(path); + if (trans && !IS_ERR(trans)) + btrfs_end_transaction(trans, fs_info->uuid_root); + if (ret) + pr_warn("btrfs: btrfs_uuid_scan_kthread failed %d\n", ret); + else + fs_info->update_uuid_tree_gen = 1; + up(&fs_info->uuid_tree_rescan_sem); + return 0; +} + +/* + * Callback for btrfs_uuid_tree_iterate(). + * returns: + * 0 check succeeded, the entry is not outdated. + * < 0 if an error occured. + * > 0 if the check failed, which means the caller shall remove the entry. + */ +static int btrfs_check_uuid_tree_entry(struct btrfs_fs_info *fs_info, + u8 *uuid, u8 type, u64 subid) +{ + struct btrfs_key key; + int ret = 0; + struct btrfs_root *subvol_root; + + if (type != BTRFS_UUID_KEY_SUBVOL && + type != BTRFS_UUID_KEY_RECEIVED_SUBVOL) + goto out; + + key.objectid = subid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + subvol_root = btrfs_read_fs_root_no_name(fs_info, &key); + if (IS_ERR(subvol_root)) { + ret = PTR_ERR(subvol_root); + if (ret == -ENOENT) + ret = 1; + goto out; + } + + switch (type) { + case BTRFS_UUID_KEY_SUBVOL: + if (memcmp(uuid, subvol_root->root_item.uuid, BTRFS_UUID_SIZE)) + ret = 1; + break; + case BTRFS_UUID_KEY_RECEIVED_SUBVOL: + if (memcmp(uuid, subvol_root->root_item.received_uuid, + BTRFS_UUID_SIZE)) + ret = 1; + break; + } + +out: + return ret; +} + +static int btrfs_uuid_rescan_kthread(void *data) +{ + struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)data; + int ret; + + /* + * 1st step is to iterate through the existing UUID tree and + * to delete all entries that contain outdated data. + * 2nd step is to add all missing entries to the UUID tree. + */ + ret = btrfs_uuid_tree_iterate(fs_info, btrfs_check_uuid_tree_entry); + if (ret < 0) { + pr_warn("btrfs: iterating uuid_tree failed %d\n", ret); + up(&fs_info->uuid_tree_rescan_sem); + return ret; + } + return btrfs_uuid_scan_kthread(data); +} + +int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info) +{ + struct btrfs_trans_handle *trans; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *uuid_root; + struct task_struct *task; + int ret; + + /* + * 1 - root node + * 1 - root item + */ + trans = btrfs_start_transaction(tree_root, 2); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + uuid_root = btrfs_create_tree(trans, fs_info, + BTRFS_UUID_TREE_OBJECTID); + if (IS_ERR(uuid_root)) { + btrfs_abort_transaction(trans, tree_root, + PTR_ERR(uuid_root)); + return PTR_ERR(uuid_root); + } + + fs_info->uuid_root = uuid_root; + + ret = btrfs_commit_transaction(trans, tree_root); + if (ret) + return ret; + + down(&fs_info->uuid_tree_rescan_sem); + task = kthread_run(btrfs_uuid_scan_kthread, fs_info, "btrfs-uuid"); + if (IS_ERR(task)) { + /* fs_info->update_uuid_tree_gen remains 0 in all error case */ + pr_warn("btrfs: failed to start uuid_scan task\n"); + up(&fs_info->uuid_tree_rescan_sem); + return PTR_ERR(task); + } + + return 0; +} + +int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) +{ + struct task_struct *task; + + down(&fs_info->uuid_tree_rescan_sem); + task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid"); + if (IS_ERR(task)) { + /* fs_info->update_uuid_tree_gen remains 0 in all error case */ + pr_warn("btrfs: failed to start uuid_rescan task\n"); + up(&fs_info->uuid_tree_rescan_sem); + return PTR_ERR(task); + } + + return 0; +} + /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. @@ -4194,13 +4473,13 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len) * and exit, so return 1 so the callers don't try to use other copies. */ if (!em) { - btrfs_emerg(fs_info, "No mapping for %Lu-%Lu\n", logical, + btrfs_crit(fs_info, "No mapping for %Lu-%Lu\n", logical, logical+len); return 1; } if (em->start > logical || em->start + em->len < logical) { - btrfs_emerg(fs_info, "Invalid mapping for %Lu-%Lu, got " + btrfs_crit(fs_info, "Invalid mapping for %Lu-%Lu, got " "%Lu-%Lu\n", logical, logical+len, em->start, em->start + em->len); return 1; @@ -4375,8 +4654,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, if (!em) { btrfs_crit(fs_info, "unable to find logical %llu len %llu", - (unsigned long long)logical, - (unsigned long long)*length); + logical, *length); return -EINVAL; } @@ -4671,6 +4949,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, } bbio = kzalloc(btrfs_bio_size(num_alloc_stripes), GFP_NOFS); if (!bbio) { + kfree(raid_map); ret = -ENOMEM; goto out; } @@ -5246,9 +5525,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, if (map_length < length) { btrfs_crit(root->fs_info, "mapping failed logical %llu bio len %llu len %llu", - (unsigned long long)logical, - (unsigned long long)length, - (unsigned long long)map_length); + logical, length, map_length); BUG(); } @@ -5314,23 +5591,72 @@ static struct btrfs_device *add_missing_dev(struct btrfs_root *root, struct btrfs_device *device; struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; - device = kzalloc(sizeof(*device), GFP_NOFS); - if (!device) + device = btrfs_alloc_device(NULL, &devid, dev_uuid); + if (IS_ERR(device)) return NULL; - list_add(&device->dev_list, - &fs_devices->devices); - device->devid = devid; - device->work.func = pending_bios_fn; + + list_add(&device->dev_list, &fs_devices->devices); device->fs_devices = fs_devices; - device->missing = 1; fs_devices->num_devices++; + + device->missing = 1; fs_devices->missing_devices++; - spin_lock_init(&device->io_lock); - INIT_LIST_HEAD(&device->dev_alloc_list); - memcpy(device->uuid, dev_uuid, BTRFS_UUID_SIZE); + return device; } +/** + * btrfs_alloc_device - allocate struct btrfs_device + * @fs_info: used only for generating a new devid, can be NULL if + * devid is provided (i.e. @devid != NULL). + * @devid: a pointer to devid for this device. If NULL a new devid + * is generated. + * @uuid: a pointer to UUID for this device. If NULL a new UUID + * is generated. + * + * Return: a pointer to a new &struct btrfs_device on success; ERR_PTR() + * on error. Returned struct is not linked onto any lists and can be + * destroyed with kfree() right away. + */ +struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, + const u64 *devid, + const u8 *uuid) +{ + struct btrfs_device *dev; + u64 tmp; + + if (!devid && !fs_info) { + WARN_ON(1); + return ERR_PTR(-EINVAL); + } + + dev = __alloc_device(); + if (IS_ERR(dev)) + return dev; + + if (devid) + tmp = *devid; + else { + int ret; + + ret = find_next_devid(fs_info, &tmp); + if (ret) { + kfree(dev); + return ERR_PTR(ret); + } + } + dev->devid = tmp; + + if (uuid) + memcpy(dev->uuid, uuid, BTRFS_UUID_SIZE); + else + generate_random_uuid(dev->uuid); + + dev->work.func = pending_bios_fn; + + return dev; +} + static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, struct extent_buffer *leaf, struct btrfs_chunk *chunk) @@ -5437,7 +5763,7 @@ static void fill_device_from_item(struct extent_buffer *leaf, WARN_ON(device->devid == BTRFS_DEV_REPLACE_DEVID); device->is_tgtdev_for_dev_replace = 0; - ptr = (unsigned long)btrfs_device_uuid(dev_item); + ptr = btrfs_device_uuid(dev_item); read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE); } @@ -5500,11 +5826,9 @@ static int read_one_dev(struct btrfs_root *root, u8 dev_uuid[BTRFS_UUID_SIZE]; devid = btrfs_device_id(leaf, dev_item); - read_extent_buffer(leaf, dev_uuid, - (unsigned long)btrfs_device_uuid(dev_item), + read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item), BTRFS_UUID_SIZE); - read_extent_buffer(leaf, fs_uuid, - (unsigned long)btrfs_device_fsid(dev_item), + read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item), BTRFS_UUID_SIZE); if (memcmp(fs_uuid, root->fs_info->fsid, BTRFS_UUID_SIZE)) { @@ -5519,8 +5843,7 @@ static int read_one_dev(struct btrfs_root *root, return -EIO; if (!device) { - btrfs_warn(root->fs_info, "devid %llu missing", - (unsigned long long)devid); + btrfs_warn(root->fs_info, "devid %llu missing", devid); device = add_missing_dev(root, devid, dev_uuid); if (!device) return -ENOMEM; @@ -5644,14 +5967,15 @@ int btrfs_read_chunk_tree(struct btrfs_root *root) mutex_lock(&uuid_mutex); lock_chunks(root); - /* first we search for all of the device items, and then we - * read in all of the chunk items. This way we can create chunk - * mappings that reference all of the devices that are afound + /* + * Read all device items, and then all the chunk items. All + * device items are found before any chunk item (their object id + * is smaller than the lowest possible object id for a chunk + * item - BTRFS_FIRST_CHUNK_TREE_OBJECTID). */ key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.offset = 0; key.type = 0; -again: ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto error; @@ -5667,17 +5991,13 @@ again: break; } btrfs_item_key_to_cpu(leaf, &found_key, slot); - if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) { - if (found_key.objectid != BTRFS_DEV_ITEMS_OBJECTID) - break; - if (found_key.type == BTRFS_DEV_ITEM_KEY) { - struct btrfs_dev_item *dev_item; - dev_item = btrfs_item_ptr(leaf, slot, + if (found_key.type == BTRFS_DEV_ITEM_KEY) { + struct btrfs_dev_item *dev_item; + dev_item = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); - ret = read_one_dev(root, leaf, dev_item); - if (ret) - goto error; - } + ret = read_one_dev(root, leaf, dev_item); + if (ret) + goto error; } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); @@ -5687,11 +6007,6 @@ again: } path->slots[0]++; } - if (key.objectid == BTRFS_DEV_ITEMS_OBJECTID) { - key.objectid = 0; - btrfs_release_path(path); - goto again; - } ret = 0; error: unlock_chunks(root); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 8670558..b72f540 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -152,6 +152,8 @@ struct btrfs_fs_devices { int rotating; }; +#define BTRFS_BIO_INLINE_CSUM_SIZE 64 + /* * we need the mirror number and stripe index to be passed around * the call chain while we are processing end_io (especially errors). @@ -161,9 +163,14 @@ struct btrfs_fs_devices { * we allocate are actually btrfs_io_bios. We'll cram as much of * struct btrfs_bio as we can into this over time. */ +typedef void (btrfs_io_bio_end_io_t) (struct btrfs_io_bio *bio, int err); struct btrfs_io_bio { unsigned long mirror_num; unsigned long stripe_index; + u8 *csum; + u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE]; + u8 *csum_allocated; + btrfs_io_bio_end_io_t *end_io; struct bio bio; }; @@ -298,6 +305,9 @@ void btrfs_close_extra_devices(struct btrfs_fs_info *fs_info, int btrfs_find_device_missing_or_by_path(struct btrfs_root *root, char *device_path, struct btrfs_device **device); +struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, + const u64 *devid, + const u8 *uuid); int btrfs_rm_device(struct btrfs_root *root, char *device_path); void btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); @@ -315,6 +325,8 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info); int btrfs_recover_balance(struct btrfs_fs_info *fs_info); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); +int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info); +int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index d4c1206..43eb559 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -378,6 +378,31 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache) } /* + * check if the backing cache is updated to FS-Cache + * - called by FS-Cache when evaluates if need to invalidate the cache + */ +static bool cachefiles_check_consistency(struct fscache_operation *op) +{ + struct cachefiles_object *object; + struct cachefiles_cache *cache; + const struct cred *saved_cred; + int ret; + + _enter("{OBJ%x}", op->object->debug_id); + + object = container_of(op->object, struct cachefiles_object, fscache); + cache = container_of(object->fscache.cache, + struct cachefiles_cache, cache); + + cachefiles_begin_secure(cache, &saved_cred); + ret = cachefiles_check_auxdata(object); + cachefiles_end_secure(cache, saved_cred); + + _leave(" = %d", ret); + return ret; +} + +/* * notification the attributes on an object have changed * - called with reads/writes excluded by FS-Cache */ @@ -522,4 +547,5 @@ const struct fscache_cache_ops cachefiles_cache_ops = { .write_page = cachefiles_write_page, .uncache_page = cachefiles_uncache_page, .dissociate_pages = cachefiles_dissociate_pages, + .check_consistency = cachefiles_check_consistency, }; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 4938251..5349473 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -235,6 +235,7 @@ extern int cachefiles_set_object_xattr(struct cachefiles_object *object, struct cachefiles_xattr *auxdata); extern int cachefiles_update_object_xattr(struct cachefiles_object *object, struct cachefiles_xattr *auxdata); +extern int cachefiles_check_auxdata(struct cachefiles_object *object); extern int cachefiles_check_object_xattr(struct cachefiles_object *object, struct cachefiles_xattr *auxdata); extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 2476e51..34c88b8 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -157,6 +157,42 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object, } /* + * check the consistency between the backing cache and the FS-Cache cookie + */ +int cachefiles_check_auxdata(struct cachefiles_object *object) +{ + struct cachefiles_xattr *auxbuf; + struct dentry *dentry = object->dentry; + unsigned int dlen; + int ret; + + ASSERT(dentry); + ASSERT(dentry->d_inode); + ASSERT(object->fscache.cookie->def->check_aux); + + auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL); + if (!auxbuf) + return -ENOMEM; + + auxbuf->len = vfs_getxattr(dentry, cachefiles_xattr_cache, + &auxbuf->type, 512 + 1); + if (auxbuf->len < 1) + return -ESTALE; + + if (auxbuf->type != object->fscache.cookie->def->type) + return -ESTALE; + + dlen = auxbuf->len - 1; + ret = fscache_check_aux(&object->fscache, &auxbuf->data, dlen); + + kfree(auxbuf); + if (ret != FSCACHE_CHECKAUX_OKAY) + return -ESTALE; + + return 0; +} + +/* * check the state xattr on a cache file * - return -ESTALE if the object should be deleted */ diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index 49bc782..ac9a2ef 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -16,3 +16,12 @@ config CEPH_FS If unsure, say N. +if CEPH_FS +config CEPH_FSCACHE + bool "Enable Ceph client caching support" + depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y + help + Choose Y here to enable persistent, read-only local + caching support for Ceph clients using FS-Cache + +endif diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile index bd35212..32e3010 100644 --- a/fs/ceph/Makefile +++ b/fs/ceph/Makefile @@ -9,3 +9,4 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \ mds_client.o mdsmap.o strings.o ceph_frag.o \ debugfs.o +ceph-$(CONFIG_CEPH_FSCACHE) += cache.o diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 5318a3b..6df8bd4 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -11,6 +11,7 @@ #include "super.h" #include "mds_client.h" +#include "cache.h" #include <linux/ceph/osd_client.h> /* @@ -70,15 +71,16 @@ static int ceph_set_page_dirty(struct page *page) struct address_space *mapping = page->mapping; struct inode *inode; struct ceph_inode_info *ci; - int undo = 0; struct ceph_snap_context *snapc; + int ret; if (unlikely(!mapping)) return !TestSetPageDirty(page); - if (TestSetPageDirty(page)) { + if (PageDirty(page)) { dout("%p set_page_dirty %p idx %lu -- already dirty\n", mapping->host, page, page->index); + BUG_ON(!PagePrivate(page)); return 0; } @@ -107,35 +109,19 @@ static int ceph_set_page_dirty(struct page *page) snapc, snapc->seq, snapc->num_snaps); spin_unlock(&ci->i_ceph_lock); - /* now adjust page */ - spin_lock_irq(&mapping->tree_lock); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(!PageUptodate(page)); - account_page_dirtied(page, page->mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - - /* - * Reference snap context in page->private. Also set - * PagePrivate so that we get invalidatepage callback. - */ - page->private = (unsigned long)snapc; - SetPagePrivate(page); - } else { - dout("ANON set_page_dirty %p (raced truncate?)\n", page); - undo = 1; - } - - spin_unlock_irq(&mapping->tree_lock); - - if (undo) - /* whoops, we failed to dirty the page */ - ceph_put_wrbuffer_cap_refs(ci, 1, snapc); + /* + * Reference snap context in page->private. Also set + * PagePrivate so that we get invalidatepage callback. + */ + BUG_ON(PagePrivate(page)); + page->private = (unsigned long)snapc; + SetPagePrivate(page); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + ret = __set_page_dirty_nobuffers(page); + WARN_ON(!PageLocked(page)); + WARN_ON(!page->mapping); - BUG_ON(!PageDirty(page)); - return 1; + return ret; } /* @@ -150,11 +136,19 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, struct ceph_inode_info *ci; struct ceph_snap_context *snapc = page_snap_context(page); - BUG_ON(!PageLocked(page)); - BUG_ON(!PagePrivate(page)); - BUG_ON(!page->mapping); - inode = page->mapping->host; + ci = ceph_inode(inode); + + if (offset != 0 || length != PAGE_CACHE_SIZE) { + dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n", + inode, page, page->index, offset, length); + return; + } + + ceph_invalidate_fscache_page(inode, page); + + if (!PagePrivate(page)) + return; /* * We can get non-dirty pages here due to races between @@ -164,31 +158,28 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, if (!PageDirty(page)) pr_err("%p invalidatepage %p page not dirty\n", inode, page); - if (offset == 0 && length == PAGE_CACHE_SIZE) - ClearPageChecked(page); + ClearPageChecked(page); - ci = ceph_inode(inode); - if (offset == 0 && length == PAGE_CACHE_SIZE) { - dout("%p invalidatepage %p idx %lu full dirty page\n", - inode, page, page->index); - ceph_put_wrbuffer_cap_refs(ci, 1, snapc); - ceph_put_snap_context(snapc); - page->private = 0; - ClearPagePrivate(page); - } else { - dout("%p invalidatepage %p idx %lu partial dirty page %u(%u)\n", - inode, page, page->index, offset, length); - } + dout("%p invalidatepage %p idx %lu full dirty page\n", + inode, page, page->index); + + ceph_put_wrbuffer_cap_refs(ci, 1, snapc); + ceph_put_snap_context(snapc); + page->private = 0; + ClearPagePrivate(page); } -/* just a sanity check */ static int ceph_releasepage(struct page *page, gfp_t g) { struct inode *inode = page->mapping ? page->mapping->host : NULL; dout("%p releasepage %p idx %lu\n", inode, page, page->index); WARN_ON(PageDirty(page)); - WARN_ON(PagePrivate(page)); - return 0; + + /* Can we release the page from the cache? */ + if (!ceph_release_fscache_page(page, g)) + return 0; + + return !PagePrivate(page); } /* @@ -198,11 +189,16 @@ static int readpage_nounlock(struct file *filp, struct page *page) { struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_osd_client *osdc = + struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; int err = 0; u64 len = PAGE_CACHE_SIZE; + err = ceph_readpage_from_fscache(inode, page); + + if (err == 0) + goto out; + dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, @@ -220,6 +216,9 @@ static int readpage_nounlock(struct file *filp, struct page *page) } SetPageUptodate(page); + if (err == 0) + ceph_readpage_to_fscache(inode, page); + out: return err < 0 ? err : 0; } @@ -262,6 +261,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) page->index); flush_dcache_page(page); SetPageUptodate(page); + ceph_readpage_to_fscache(inode, page); unlock_page(page); page_cache_release(page); bytes -= PAGE_CACHE_SIZE; @@ -331,11 +331,12 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) page = list_entry(page_list->prev, struct page, lru); BUG_ON(PageLocked(page)); list_del(&page->lru); - + dout("start_read %p adding %p idx %lu\n", inode, page, page->index); if (add_to_page_cache_lru(page, &inode->i_data, page->index, GFP_NOFS)) { + ceph_fscache_uncache_page(inode, page); page_cache_release(page); dout("start_read %p add_to_page_cache failed %p\n", inode, page); @@ -378,6 +379,12 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, int rc = 0; int max = 0; + rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list, + &nr_pages); + + if (rc == 0) + goto out; + if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE) max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_SHIFT; @@ -392,6 +399,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, BUG_ON(rc == 0); } out: + ceph_fscache_readpages_cancel(inode, page_list); + dout("readpages %p file %p ret %d\n", inode, file, rc); return rc; } @@ -497,6 +506,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); + ceph_readpage_to_fscache(inode, page); + set_page_writeback(page); err = ceph_osdc_writepages(osdc, ceph_vino(inode), &ci->i_layout, snapc, @@ -552,7 +563,6 @@ static void ceph_release_pages(struct page **pages, int num) pagevec_release(&pvec); } - /* * async writeback completion handler. * diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c new file mode 100644 index 0000000..6bfe65e --- /dev/null +++ b/fs/ceph/cache.c @@ -0,0 +1,398 @@ +/* + * Ceph cache definitions. + * + * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved. + * Written by Milosz Tanski (milosz@adfin.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to: + * Free Software Foundation + * 51 Franklin Street, Fifth Floor + * Boston, MA 02111-1301 USA + * + */ + +#include "super.h" +#include "cache.h" + +struct ceph_aux_inode { + struct timespec mtime; + loff_t size; +}; + +struct fscache_netfs ceph_cache_netfs = { + .name = "ceph", + .version = 0, +}; + +static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data, + void *buffer, uint16_t maxbuf) +{ + const struct ceph_fs_client* fsc = cookie_netfs_data; + uint16_t klen; + + klen = sizeof(fsc->client->fsid); + if (klen > maxbuf) + return 0; + + memcpy(buffer, &fsc->client->fsid, klen); + return klen; +} + +static const struct fscache_cookie_def ceph_fscache_fsid_object_def = { + .name = "CEPH.fsid", + .type = FSCACHE_COOKIE_TYPE_INDEX, + .get_key = ceph_fscache_session_get_key, +}; + +int ceph_fscache_register(void) +{ + return fscache_register_netfs(&ceph_cache_netfs); +} + +void ceph_fscache_unregister(void) +{ + fscache_unregister_netfs(&ceph_cache_netfs); +} + +int ceph_fscache_register_fs(struct ceph_fs_client* fsc) +{ + fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index, + &ceph_fscache_fsid_object_def, + fsc); + + if (fsc->fscache == NULL) { + pr_err("Unable to resgister fsid: %p fscache cookie", fsc); + return 0; + } + + fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1); + if (fsc->revalidate_wq == NULL) + return -ENOMEM; + + return 0; +} + +static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data, + void *buffer, uint16_t maxbuf) +{ + const struct ceph_inode_info* ci = cookie_netfs_data; + uint16_t klen; + + /* use ceph virtual inode (id + snaphot) */ + klen = sizeof(ci->i_vino); + if (klen > maxbuf) + return 0; + + memcpy(buffer, &ci->i_vino, klen); + return klen; +} + +static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data, + void *buffer, uint16_t bufmax) +{ + struct ceph_aux_inode aux; + const struct ceph_inode_info* ci = cookie_netfs_data; + const struct inode* inode = &ci->vfs_inode; + + memset(&aux, 0, sizeof(aux)); + aux.mtime = inode->i_mtime; + aux.size = inode->i_size; + + memcpy(buffer, &aux, sizeof(aux)); + + return sizeof(aux); +} + +static void ceph_fscache_inode_get_attr(const void *cookie_netfs_data, + uint64_t *size) +{ + const struct ceph_inode_info* ci = cookie_netfs_data; + const struct inode* inode = &ci->vfs_inode; + + *size = inode->i_size; +} + +static enum fscache_checkaux ceph_fscache_inode_check_aux( + void *cookie_netfs_data, const void *data, uint16_t dlen) +{ + struct ceph_aux_inode aux; + struct ceph_inode_info* ci = cookie_netfs_data; + struct inode* inode = &ci->vfs_inode; + + if (dlen != sizeof(aux)) + return FSCACHE_CHECKAUX_OBSOLETE; + + memset(&aux, 0, sizeof(aux)); + aux.mtime = inode->i_mtime; + aux.size = inode->i_size; + + if (memcmp(data, &aux, sizeof(aux)) != 0) + return FSCACHE_CHECKAUX_OBSOLETE; + + dout("ceph inode 0x%p cached okay", ci); + return FSCACHE_CHECKAUX_OKAY; +} + +static void ceph_fscache_inode_now_uncached(void* cookie_netfs_data) +{ + struct ceph_inode_info* ci = cookie_netfs_data; + struct pagevec pvec; + pgoff_t first; + int loop, nr_pages; + + pagevec_init(&pvec, 0); + first = 0; + + dout("ceph inode 0x%p now uncached", ci); + + while (1) { + nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first, + PAGEVEC_SIZE - pagevec_count(&pvec)); + + if (!nr_pages) + break; + + for (loop = 0; loop < nr_pages; loop++) + ClearPageFsCache(pvec.pages[loop]); + + first = pvec.pages[nr_pages - 1]->index + 1; + + pvec.nr = nr_pages; + pagevec_release(&pvec); + cond_resched(); + } +} + +static const struct fscache_cookie_def ceph_fscache_inode_object_def = { + .name = "CEPH.inode", + .type = FSCACHE_COOKIE_TYPE_DATAFILE, + .get_key = ceph_fscache_inode_get_key, + .get_attr = ceph_fscache_inode_get_attr, + .get_aux = ceph_fscache_inode_get_aux, + .check_aux = ceph_fscache_inode_check_aux, + .now_uncached = ceph_fscache_inode_now_uncached, +}; + +void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc, + struct ceph_inode_info* ci) +{ + struct inode* inode = &ci->vfs_inode; + + /* No caching for filesystem */ + if (fsc->fscache == NULL) + return; + + /* Only cache for regular files that are read only */ + if ((ci->vfs_inode.i_mode & S_IFREG) == 0) + return; + + /* Avoid multiple racing open requests */ + mutex_lock(&inode->i_mutex); + + if (ci->fscache) + goto done; + + ci->fscache = fscache_acquire_cookie(fsc->fscache, + &ceph_fscache_inode_object_def, + ci); +done: + mutex_unlock(&inode->i_mutex); + +} + +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +{ + struct fscache_cookie* cookie; + + if ((cookie = ci->fscache) == NULL) + return; + + ci->fscache = NULL; + + fscache_uncache_all_inode_pages(cookie, &ci->vfs_inode); + fscache_relinquish_cookie(cookie, 0); +} + +static void ceph_vfs_readpage_complete(struct page *page, void *data, int error) +{ + if (!error) + SetPageUptodate(page); +} + +static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error) +{ + if (!error) + SetPageUptodate(page); + + unlock_page(page); +} + +static inline int cache_valid(struct ceph_inode_info *ci) +{ + return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) && + (ci->i_fscache_gen == ci->i_rdcache_gen)); +} + + +/* Atempt to read from the fscache, + * + * This function is called from the readpage_nounlock context. DO NOT attempt to + * unlock the page here (or in the callback). + */ +int ceph_readpage_from_fscache(struct inode *inode, struct page *page) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + int ret; + + if (!cache_valid(ci)) + return -ENOBUFS; + + ret = fscache_read_or_alloc_page(ci->fscache, page, + ceph_vfs_readpage_complete, NULL, + GFP_KERNEL); + + switch (ret) { + case 0: /* Page found */ + dout("page read submitted\n"); + return 0; + case -ENOBUFS: /* Pages were not found, and can't be */ + case -ENODATA: /* Pages were not found */ + dout("page/inode not in cache\n"); + return ret; + default: + dout("%s: unknown error ret = %i\n", __func__, ret); + return ret; + } +} + +int ceph_readpages_from_fscache(struct inode *inode, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + int ret; + + if (!cache_valid(ci)) + return -ENOBUFS; + + ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages, + ceph_vfs_readpage_complete_unlock, + NULL, mapping_gfp_mask(mapping)); + + switch (ret) { + case 0: /* All pages found */ + dout("all-page read submitted\n"); + return 0; + case -ENOBUFS: /* Some pages were not found, and can't be */ + case -ENODATA: /* some pages were not found */ + dout("page/inode not in cache\n"); + return ret; + default: + dout("%s: unknown error ret = %i\n", __func__, ret); + return ret; + } +} + +void ceph_readpage_to_fscache(struct inode *inode, struct page *page) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + int ret; + + if (!PageFsCache(page)) + return; + + if (!cache_valid(ci)) + return; + + ret = fscache_write_page(ci->fscache, page, GFP_KERNEL); + if (ret) + fscache_uncache_page(ci->fscache, page); +} + +void ceph_invalidate_fscache_page(struct inode* inode, struct page *page) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + + fscache_wait_on_page_write(ci->fscache, page); + fscache_uncache_page(ci->fscache, page); +} + +void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) +{ + if (fsc->revalidate_wq) + destroy_workqueue(fsc->revalidate_wq); + + fscache_relinquish_cookie(fsc->fscache, 0); + fsc->fscache = NULL; +} + +static void ceph_revalidate_work(struct work_struct *work) +{ + int issued; + u32 orig_gen; + struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, + i_revalidate_work); + struct inode *inode = &ci->vfs_inode; + + spin_lock(&ci->i_ceph_lock); + issued = __ceph_caps_issued(ci, NULL); + orig_gen = ci->i_rdcache_gen; + spin_unlock(&ci->i_ceph_lock); + + if (!(issued & CEPH_CAP_FILE_CACHE)) { + dout("revalidate_work lost cache before validation %p\n", + inode); + goto out; + } + + if (!fscache_check_consistency(ci->fscache)) + fscache_invalidate(ci->fscache); + + spin_lock(&ci->i_ceph_lock); + /* Update the new valid generation (backwards sanity check too) */ + if (orig_gen > ci->i_fscache_gen) { + ci->i_fscache_gen = orig_gen; + } + spin_unlock(&ci->i_ceph_lock); + +out: + iput(&ci->vfs_inode); +} + +void ceph_queue_revalidate(struct inode *inode) +{ + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); + struct ceph_inode_info *ci = ceph_inode(inode); + + if (fsc->revalidate_wq == NULL || ci->fscache == NULL) + return; + + ihold(inode); + + if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq, + &ci->i_revalidate_work)) { + dout("ceph_queue_revalidate %p\n", inode); + } else { + dout("ceph_queue_revalidate %p failed\n)", inode); + iput(inode); + } +} + +void ceph_fscache_inode_init(struct ceph_inode_info *ci) +{ + ci->fscache = NULL; + /* The first load is verifed cookie open time */ + ci->i_fscache_gen = 1; + INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work); +} diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h new file mode 100644 index 0000000..ba94940 --- /dev/null +++ b/fs/ceph/cache.h @@ -0,0 +1,159 @@ +/* + * Ceph cache definitions. + * + * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved. + * Written by Milosz Tanski (milosz@adfin.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to: + * Free Software Foundation + * 51 Franklin Street, Fifth Floor + * Boston, MA 02111-1301 USA + * + */ + +#ifndef _CEPH_CACHE_H +#define _CEPH_CACHE_H + +#ifdef CONFIG_CEPH_FSCACHE + +extern struct fscache_netfs ceph_cache_netfs; + +int ceph_fscache_register(void); +void ceph_fscache_unregister(void); + +int ceph_fscache_register_fs(struct ceph_fs_client* fsc); +void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc); + +void ceph_fscache_inode_init(struct ceph_inode_info *ci); +void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc, + struct ceph_inode_info* ci); +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci); + +int ceph_readpage_from_fscache(struct inode *inode, struct page *page); +int ceph_readpages_from_fscache(struct inode *inode, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages); +void ceph_readpage_to_fscache(struct inode *inode, struct page *page); +void ceph_invalidate_fscache_page(struct inode* inode, struct page *page); +void ceph_queue_revalidate(struct inode *inode); + +static inline void ceph_fscache_invalidate(struct inode *inode) +{ + fscache_invalidate(ceph_inode(inode)->fscache); +} + +static inline void ceph_fscache_uncache_page(struct inode *inode, + struct page *page) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + return fscache_uncache_page(ci->fscache, page); +} + +static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp) +{ + struct inode* inode = page->mapping->host; + struct ceph_inode_info *ci = ceph_inode(inode); + return fscache_maybe_release_page(ci->fscache, page, gfp); +} + +static inline void ceph_fscache_readpages_cancel(struct inode *inode, + struct list_head *pages) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + return fscache_readpages_cancel(ci->fscache, pages); +} + +#else + +static inline int ceph_fscache_register(void) +{ + return 0; +} + +static inline void ceph_fscache_unregister(void) +{ +} + +static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc) +{ + return 0; +} + +static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) +{ +} + +static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) +{ +} + +static inline void ceph_fscache_register_inode_cookie(struct ceph_fs_client* parent_fsc, + struct ceph_inode_info* ci) +{ +} + +static inline void ceph_fscache_uncache_page(struct inode *inode, + struct page *pages) +{ +} + +static inline int ceph_readpage_from_fscache(struct inode* inode, + struct page *page) +{ + return -ENOBUFS; +} + +static inline int ceph_readpages_from_fscache(struct inode *inode, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages) +{ + return -ENOBUFS; +} + +static inline void ceph_readpage_to_fscache(struct inode *inode, + struct page *page) +{ +} + +static inline void ceph_fscache_invalidate(struct inode *inode) +{ +} + +static inline void ceph_invalidate_fscache_page(struct inode *inode, + struct page *page) +{ +} + +static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +{ +} + +static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp) +{ + return 1; +} + +static inline void ceph_fscache_readpages_cancel(struct inode *inode, + struct list_head *pages) +{ +} + +static inline void ceph_queue_revalidate(struct inode *inode) +{ +} + +#endif + +#endif diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 25442b4..13976c3 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -10,6 +10,7 @@ #include "super.h" #include "mds_client.h" +#include "cache.h" #include <linux/ceph/decode.h> #include <linux/ceph/messenger.h> @@ -479,8 +480,9 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, * i_rdcache_gen. */ if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) && - (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) + (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) { ci->i_rdcache_gen++; + } /* * if we are newly issued FILE_SHARED, mark dir not complete; we @@ -2072,19 +2074,17 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want, /* finish pending truncate */ while (ci->i_truncate_pending) { spin_unlock(&ci->i_ceph_lock); - if (!(need & CEPH_CAP_FILE_WR)) - mutex_lock(&inode->i_mutex); __ceph_do_pending_vmtruncate(inode); - if (!(need & CEPH_CAP_FILE_WR)) - mutex_unlock(&inode->i_mutex); spin_lock(&ci->i_ceph_lock); } - if (need & CEPH_CAP_FILE_WR) { + have = __ceph_caps_issued(ci, &implemented); + + if (have & need & CEPH_CAP_FILE_WR) { if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) { dout("get_cap_refs %p endoff %llu > maxsize %llu\n", inode, endoff, ci->i_max_size); - if (endoff > ci->i_wanted_max_size) { + if (endoff > ci->i_requested_max_size) { *check_max = 1; ret = 1; } @@ -2099,7 +2099,6 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want, goto out; } } - have = __ceph_caps_issued(ci, &implemented); if ((have & need) == need) { /* @@ -2141,14 +2140,17 @@ static void check_max_size(struct inode *inode, loff_t endoff) /* do we need to explicitly request a larger max_size? */ spin_lock(&ci->i_ceph_lock); - if ((endoff >= ci->i_max_size || - endoff > (inode->i_size << 1)) && - endoff > ci->i_wanted_max_size) { + if (endoff >= ci->i_max_size && endoff > ci->i_wanted_max_size) { dout("write %p at large endoff %llu, req max_size\n", inode, endoff); ci->i_wanted_max_size = endoff; - check = 1; } + /* duplicate ceph_check_caps()'s logic */ + if (ci->i_auth_cap && + (ci->i_auth_cap->issued & CEPH_CAP_FILE_WR) && + ci->i_wanted_max_size > ci->i_max_size && + ci->i_wanted_max_size > ci->i_requested_max_size) + check = 1; spin_unlock(&ci->i_ceph_lock); if (check) ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); @@ -2334,6 +2336,38 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, } /* + * Invalidate unlinked inode's aliases, so we can drop the inode ASAP. + */ +static void invalidate_aliases(struct inode *inode) +{ + struct dentry *dn, *prev = NULL; + + dout("invalidate_aliases inode %p\n", inode); + d_prune_aliases(inode); + /* + * For non-directory inode, d_find_alias() only returns + * connected dentry. After calling d_invalidate(), the + * dentry become disconnected. + * + * For directory inode, d_find_alias() can return + * disconnected dentry. But directory inode should have + * one alias at most. + */ + while ((dn = d_find_alias(inode))) { + if (dn == prev) { + dput(dn); + break; + } + d_invalidate(dn); + if (prev) + dput(prev); + prev = dn; + } + if (prev) + dput(prev); +} + +/* * Handle a cap GRANT message from the MDS. (Note that a GRANT may * actually be a revocation if it specifies a smaller cap set.) * @@ -2361,8 +2395,9 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, int check_caps = 0; int wake = 0; int writeback = 0; - int revoked_rdcache = 0; int queue_invalidate = 0; + int deleted_inode = 0; + int queue_revalidate = 0; dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n", inode, cap, mds, seq, ceph_cap_string(newcaps)); @@ -2377,9 +2412,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, if (((cap->issued & ~newcaps) & CEPH_CAP_FILE_CACHE) && (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 && !ci->i_wrbuffer_ref) { - if (try_nonblocking_invalidate(inode) == 0) { - revoked_rdcache = 1; - } else { + if (try_nonblocking_invalidate(inode)) { /* there were locked pages.. invalidate later in a separate thread. */ if (ci->i_rdcache_revoking != ci->i_rdcache_gen) { @@ -2387,6 +2420,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, ci->i_rdcache_revoking = ci->i_rdcache_gen; } } + + ceph_fscache_invalidate(inode); } /* side effects now are allowed */ @@ -2407,8 +2442,12 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, from_kgid(&init_user_ns, inode->i_gid)); } - if ((issued & CEPH_CAP_LINK_EXCL) == 0) + if ((issued & CEPH_CAP_LINK_EXCL) == 0) { set_nlink(inode, le32_to_cpu(grant->nlink)); + if (inode->i_nlink == 0 && + (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL))) + deleted_inode = 1; + } if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) { int len = le32_to_cpu(grant->xattr_len); @@ -2424,6 +2463,11 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, } } + /* Do we need to revalidate our fscache cookie. Don't bother on the + * first cache cap as we already validate at cookie creation time. */ + if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1) + queue_revalidate = 1; + /* size/ctime/mtime/atime? */ ceph_fill_file_size(inode, issued, le32_to_cpu(grant->truncate_seq), @@ -2508,6 +2552,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, BUG_ON(cap->issued & ~cap->implemented); spin_unlock(&ci->i_ceph_lock); + if (writeback) /* * queue inode for writeback: we can't actually call @@ -2517,6 +2562,10 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, ceph_queue_writeback(inode); if (queue_invalidate) ceph_queue_invalidate(inode); + if (deleted_inode) + invalidate_aliases(inode); + if (queue_revalidate) + ceph_queue_revalidate(inode); if (wake) wake_up_all(&ci->i_cap_wq); @@ -2673,8 +2722,10 @@ static void handle_cap_trunc(struct inode *inode, truncate_seq, truncate_size, size); spin_unlock(&ci->i_ceph_lock); - if (queue_trunc) + if (queue_trunc) { ceph_queue_vmtruncate(inode); + ceph_fscache_invalidate(inode); + } } /* diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index a40ceda..868b61d 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -793,6 +793,8 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, req->r_locked_dir = dir; req->r_dentry_drop = CEPH_CAP_FILE_SHARED; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; + /* release LINK_SHARED on source inode (mds will lock it) */ + req->r_old_inode_drop = CEPH_CAP_LINK_SHARED; err = ceph_mdsc_do_request(mdsc, dir, req); if (err) { d_drop(dentry); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 2ddf061..3de8982 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -8,9 +8,11 @@ #include <linux/namei.h> #include <linux/writeback.h> #include <linux/aio.h> +#include <linux/falloc.h> #include "super.h" #include "mds_client.h" +#include "cache.h" /* * Ceph file operations @@ -68,9 +70,23 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) { struct ceph_file_info *cf; int ret = 0; + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); + struct ceph_mds_client *mdsc = fsc->mdsc; switch (inode->i_mode & S_IFMT) { case S_IFREG: + /* First file open request creates the cookie, we want to keep + * this cookie around for the filetime of the inode as not to + * have to worry about fscache register / revoke / operation + * races. + * + * Also, if we know the operation is going to invalidate data + * (non readonly) just nuke the cache right away. + */ + ceph_fscache_register_inode_cookie(mdsc->fsc, ci); + if ((fmode & CEPH_FILE_MODE_WR)) + ceph_fscache_invalidate(inode); case S_IFDIR: dout("init_file %p %p 0%o (regular)\n", inode, file, inode->i_mode); @@ -181,6 +197,7 @@ int ceph_open(struct inode *inode, struct file *file) spin_unlock(&ci->i_ceph_lock); return ceph_init_file(inode, file, fmode); } + spin_unlock(&ci->i_ceph_lock); dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted)); @@ -191,6 +208,7 @@ int ceph_open(struct inode *inode, struct file *file) } req->r_inode = inode; ihold(inode); + req->r_num_caps = 1; if (flags & (O_CREAT|O_TRUNC)) parent_inode = ceph_get_dentry_parent_inode(file->f_dentry); @@ -313,9 +331,9 @@ static int striped_read(struct inode *inode, { struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); - u64 pos, this_len; + u64 pos, this_len, left; int io_align, page_align; - int left, pages_left; + int pages_left; int read; struct page **page_pos; int ret; @@ -346,47 +364,40 @@ more: ret = 0; hit_stripe = this_len < left; was_short = ret >= 0 && ret < this_len; - dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read, + dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read, ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : ""); - if (ret > 0) { - int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT; - - if (read < pos - off) { - dout(" zero gap %llu to %llu\n", off + read, pos); - ceph_zero_page_vector_range(page_align + read, - pos - off - read, pages); + if (ret >= 0) { + int didpages; + if (was_short && (pos + ret < inode->i_size)) { + u64 tmp = min(this_len - ret, + inode->i_size - pos - ret); + dout(" zero gap %llu to %llu\n", + pos + ret, pos + ret + tmp); + ceph_zero_page_vector_range(page_align + read + ret, + tmp, pages); + ret += tmp; } + + didpages = (page_align + ret) >> PAGE_CACHE_SHIFT; pos += ret; read = pos - off; left -= ret; page_pos += didpages; pages_left -= didpages; - /* hit stripe? */ - if (left && hit_stripe) + /* hit stripe and need continue*/ + if (left && hit_stripe && pos < inode->i_size) goto more; } - if (was_short) { + if (read > 0) { + ret = read; /* did we bounce off eof? */ if (pos + left > inode->i_size) *checkeof = 1; - - /* zero trailing bytes (inside i_size) */ - if (left > 0 && pos < inode->i_size) { - if (pos + left > inode->i_size) - left = inode->i_size - pos; - - dout("zero tail %d\n", left); - ceph_zero_page_vector_range(page_align + read, left, - pages); - read += left; - } } - if (ret >= 0) - ret = read; dout("striped_read returns %d\n", ret); return ret; } @@ -618,6 +629,8 @@ out: if (check_caps) ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL); + } else if (ret != -EOLDSNAPC && written > 0) { + ret = written; } return ret; } @@ -659,7 +672,6 @@ again: if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 || (iocb->ki_filp->f_flags & O_DIRECT) || - (inode->i_sb->s_flags & MS_SYNCHRONOUS) || (fi->flags & CEPH_F_SYNC)) /* hmm, this isn't really async... */ ret = ceph_sync_read(filp, base, len, ppos, &checkeof); @@ -711,13 +723,11 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, &ceph_sb_to_client(inode->i_sb)->client->osdc; ssize_t count, written = 0; int err, want, got; - bool hold_mutex; if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; mutex_lock(&inode->i_mutex); - hold_mutex = true; err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); if (err) @@ -763,18 +773,31 @@ retry_snap: if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 || (iocb->ki_filp->f_flags & O_DIRECT) || - (inode->i_sb->s_flags & MS_SYNCHRONOUS) || (fi->flags & CEPH_F_SYNC)) { mutex_unlock(&inode->i_mutex); written = ceph_sync_write(file, iov->iov_base, count, pos, &iocb->ki_pos); + if (written == -EOLDSNAPC) { + dout("aio_write %p %llx.%llx %llu~%u" + "got EOLDSNAPC, retrying\n", + inode, ceph_vinop(inode), + pos, (unsigned)iov->iov_len); + mutex_lock(&inode->i_mutex); + goto retry_snap; + } } else { + /* + * No need to acquire the i_truncate_mutex. Because + * the MDS revokes Fwb caps before sending truncate + * message to us. We can't get Fwb cap while there + * are pending vmtruncate. So write and vmtruncate + * can not run at the same time + */ written = generic_file_buffered_write(iocb, iov, nr_segs, pos, &iocb->ki_pos, count, 0); mutex_unlock(&inode->i_mutex); } - hold_mutex = false; if (written >= 0) { int dirty; @@ -798,18 +821,12 @@ retry_snap: written = err; } - if (written == -EOLDSNAPC) { - dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n", - inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len); - mutex_lock(&inode->i_mutex); - hold_mutex = true; - goto retry_snap; - } + goto out_unlocked; + out: - if (hold_mutex) - mutex_unlock(&inode->i_mutex); + mutex_unlock(&inode->i_mutex); +out_unlocked: current->backing_dev_info = NULL; - return written ? written : err; } @@ -822,7 +839,6 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence) int ret; mutex_lock(&inode->i_mutex); - __ceph_do_pending_vmtruncate(inode); if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) { ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE); @@ -871,6 +887,204 @@ out: return offset; } +static inline void ceph_zero_partial_page( + struct inode *inode, loff_t offset, unsigned size) +{ + struct page *page; + pgoff_t index = offset >> PAGE_CACHE_SHIFT; + + page = find_lock_page(inode->i_mapping, index); + if (page) { + wait_on_page_writeback(page); + zero_user(page, offset & (PAGE_CACHE_SIZE - 1), size); + unlock_page(page); + page_cache_release(page); + } +} + +static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset, + loff_t length) +{ + loff_t nearly = round_up(offset, PAGE_CACHE_SIZE); + if (offset < nearly) { + loff_t size = nearly - offset; + if (length < size) + size = length; + ceph_zero_partial_page(inode, offset, size); + offset += size; + length -= size; + } + if (length >= PAGE_CACHE_SIZE) { + loff_t size = round_down(length, PAGE_CACHE_SIZE); + truncate_pagecache_range(inode, offset, offset + size - 1); + offset += size; + length -= size; + } + if (length) + ceph_zero_partial_page(inode, offset, length); +} + +static int ceph_zero_partial_object(struct inode *inode, + loff_t offset, loff_t *length) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_osd_request *req; + int ret = 0; + loff_t zero = 0; + int op; + + if (!length) { + op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE; + length = &zero; + } else { + op = CEPH_OSD_OP_ZERO; + } + + req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, + ceph_vino(inode), + offset, length, + 1, op, + CEPH_OSD_FLAG_WRITE | + CEPH_OSD_FLAG_ONDISK, + NULL, 0, 0, false); + if (IS_ERR(req)) { + ret = PTR_ERR(req); + goto out; + } + + ceph_osdc_build_request(req, offset, NULL, ceph_vino(inode).snap, + &inode->i_mtime); + + ret = ceph_osdc_start_request(&fsc->client->osdc, req, false); + if (!ret) { + ret = ceph_osdc_wait_request(&fsc->client->osdc, req); + if (ret == -ENOENT) + ret = 0; + } + ceph_osdc_put_request(req); + +out: + return ret; +} + +static int ceph_zero_objects(struct inode *inode, loff_t offset, loff_t length) +{ + int ret = 0; + struct ceph_inode_info *ci = ceph_inode(inode); + s32 stripe_unit = ceph_file_layout_su(ci->i_layout); + s32 stripe_count = ceph_file_layout_stripe_count(ci->i_layout); + s32 object_size = ceph_file_layout_object_size(ci->i_layout); + u64 object_set_size = object_size * stripe_count; + u64 nearly, t; + + /* round offset up to next period boundary */ + nearly = offset + object_set_size - 1; + t = nearly; + nearly -= do_div(t, object_set_size); + + while (length && offset < nearly) { + loff_t size = length; + ret = ceph_zero_partial_object(inode, offset, &size); + if (ret < 0) + return ret; + offset += size; + length -= size; + } + while (length >= object_set_size) { + int i; + loff_t pos = offset; + for (i = 0; i < stripe_count; ++i) { + ret = ceph_zero_partial_object(inode, pos, NULL); + if (ret < 0) + return ret; + pos += stripe_unit; + } + offset += object_set_size; + length -= object_set_size; + } + while (length) { + loff_t size = length; + ret = ceph_zero_partial_object(inode, offset, &size); + if (ret < 0) + return ret; + offset += size; + length -= size; + } + return ret; +} + +static long ceph_fallocate(struct file *file, int mode, + loff_t offset, loff_t length) +{ + struct ceph_file_info *fi = file->private_data; + struct inode *inode = file->f_dentry->d_inode; + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_osd_client *osdc = + &ceph_inode_to_client(inode)->client->osdc; + int want, got = 0; + int dirty; + int ret = 0; + loff_t endoff = 0; + loff_t size; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + if (IS_SWAPFILE(inode)) + return -ETXTBSY; + + mutex_lock(&inode->i_mutex); + + if (ceph_snap(inode) != CEPH_NOSNAP) { + ret = -EROFS; + goto unlock; + } + + if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) && + !(mode & FALLOC_FL_PUNCH_HOLE)) { + ret = -ENOSPC; + goto unlock; + } + + size = i_size_read(inode); + if (!(mode & FALLOC_FL_KEEP_SIZE)) + endoff = offset + length; + + if (fi->fmode & CEPH_FILE_MODE_LAZY) + want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO; + else + want = CEPH_CAP_FILE_BUFFER; + + ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff); + if (ret < 0) + goto unlock; + + if (mode & FALLOC_FL_PUNCH_HOLE) { + if (offset < size) + ceph_zero_pagecache_range(inode, offset, length); + ret = ceph_zero_objects(inode, offset, length); + } else if (endoff > size) { + truncate_pagecache_range(inode, size, -1); + if (ceph_inode_set_size(inode, endoff)) + ceph_check_caps(ceph_inode(inode), + CHECK_CAPS_AUTHONLY, NULL); + } + + if (!ret) { + spin_lock(&ci->i_ceph_lock); + dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR); + spin_unlock(&ci->i_ceph_lock); + if (dirty) + __mark_inode_dirty(inode, dirty); + } + + ceph_put_cap_refs(ci, got); +unlock: + mutex_unlock(&inode->i_mutex); + return ret; +} + const struct file_operations ceph_file_fops = { .open = ceph_open, .release = ceph_release, @@ -887,5 +1101,6 @@ const struct file_operations ceph_file_fops = { .splice_write = generic_file_splice_write, .unlocked_ioctl = ceph_ioctl, .compat_ioctl = ceph_ioctl, + .fallocate = ceph_fallocate, }; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index f3a2abf..8549a48 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -12,6 +12,7 @@ #include "super.h" #include "mds_client.h" +#include "cache.h" #include <linux/ceph/decode.h> /* @@ -344,6 +345,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) for (i = 0; i < CEPH_FILE_MODE_NUM; i++) ci->i_nr_by_mode[i] = 0; + mutex_init(&ci->i_truncate_mutex); ci->i_truncate_seq = 0; ci->i_truncate_size = 0; ci->i_truncate_pending = 0; @@ -377,6 +379,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work); + ceph_fscache_inode_init(ci); + return &ci->vfs_inode; } @@ -396,6 +400,8 @@ void ceph_destroy_inode(struct inode *inode) dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode)); + ceph_fscache_unregister_inode_cookie(ci); + ceph_queue_caps_release(inode); /* @@ -430,7 +436,6 @@ void ceph_destroy_inode(struct inode *inode) call_rcu(&inode->i_rcu, ceph_i_callback); } - /* * Helpers to fill in size, ctime, mtime, and atime. We have to be * careful because either the client or MDS may have more up to date @@ -455,16 +460,20 @@ int ceph_fill_file_size(struct inode *inode, int issued, dout("truncate_seq %u -> %u\n", ci->i_truncate_seq, truncate_seq); ci->i_truncate_seq = truncate_seq; + + /* the MDS should have revoked these caps */ + WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL | + CEPH_CAP_FILE_RD | + CEPH_CAP_FILE_WR | + CEPH_CAP_FILE_LAZYIO)); /* * If we hold relevant caps, or in the case where we're * not the only client referencing this file and we * don't hold those caps, then we need to check whether * the file is either opened or mmaped */ - if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_RD| - CEPH_CAP_FILE_WR|CEPH_CAP_FILE_BUFFER| - CEPH_CAP_FILE_EXCL| - CEPH_CAP_FILE_LAZYIO)) || + if ((issued & (CEPH_CAP_FILE_CACHE| + CEPH_CAP_FILE_BUFFER)) || mapping_mapped(inode->i_mapping) || __ceph_caps_file_wanted(ci)) { ci->i_truncate_pending++; @@ -478,6 +487,10 @@ int ceph_fill_file_size(struct inode *inode, int issued, truncate_size); ci->i_truncate_size = truncate_size; } + + if (queue_trunc) + ceph_fscache_invalidate(inode); + return queue_trunc; } @@ -1066,7 +1079,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, * complete. */ ceph_set_dentry_offset(req->r_old_dentry); - dout("dn %p gets new offset %lld\n", req->r_old_dentry, + dout("dn %p gets new offset %lld\n", req->r_old_dentry, ceph_dentry(req->r_old_dentry)->offset); dn = req->r_old_dentry; /* use old_dentry */ @@ -1419,18 +1432,20 @@ static void ceph_invalidate_work(struct work_struct *work) u32 orig_gen; int check = 0; + mutex_lock(&ci->i_truncate_mutex); spin_lock(&ci->i_ceph_lock); dout("invalidate_pages %p gen %d revoking %d\n", inode, ci->i_rdcache_gen, ci->i_rdcache_revoking); if (ci->i_rdcache_revoking != ci->i_rdcache_gen) { /* nevermind! */ spin_unlock(&ci->i_ceph_lock); + mutex_unlock(&ci->i_truncate_mutex); goto out; } orig_gen = ci->i_rdcache_gen; spin_unlock(&ci->i_ceph_lock); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages(inode->i_mapping, 0); spin_lock(&ci->i_ceph_lock); if (orig_gen == ci->i_rdcache_gen && @@ -1445,6 +1460,7 @@ static void ceph_invalidate_work(struct work_struct *work) ci->i_rdcache_revoking); } spin_unlock(&ci->i_ceph_lock); + mutex_unlock(&ci->i_truncate_mutex); if (check) ceph_check_caps(ci, 0, NULL); @@ -1465,9 +1481,7 @@ static void ceph_vmtruncate_work(struct work_struct *work) struct inode *inode = &ci->vfs_inode; dout("vmtruncate_work %p\n", inode); - mutex_lock(&inode->i_mutex); __ceph_do_pending_vmtruncate(inode); - mutex_unlock(&inode->i_mutex); iput(inode); } @@ -1480,6 +1494,7 @@ void ceph_queue_vmtruncate(struct inode *inode) struct ceph_inode_info *ci = ceph_inode(inode); ihold(inode); + if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq, &ci->i_vmtruncate_work)) { dout("ceph_queue_vmtruncate %p\n", inode); @@ -1500,11 +1515,13 @@ void __ceph_do_pending_vmtruncate(struct inode *inode) u64 to; int wrbuffer_refs, finish = 0; + mutex_lock(&ci->i_truncate_mutex); retry: spin_lock(&ci->i_ceph_lock); if (ci->i_truncate_pending == 0) { dout("__do_pending_vmtruncate %p none pending\n", inode); spin_unlock(&ci->i_ceph_lock); + mutex_unlock(&ci->i_truncate_mutex); return; } @@ -1521,6 +1538,9 @@ retry: goto retry; } + /* there should be no reader or writer */ + WARN_ON_ONCE(ci->i_rd_ref || ci->i_wr_ref); + to = ci->i_truncate_size; wrbuffer_refs = ci->i_wrbuffer_ref; dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode, @@ -1538,13 +1558,14 @@ retry: if (!finish) goto retry; + mutex_unlock(&ci->i_truncate_mutex); + if (wrbuffer_refs == 0) ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); wake_up_all(&ci->i_cap_wq); } - /* * symlinks */ @@ -1586,8 +1607,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; - __ceph_do_pending_vmtruncate(inode); - err = inode_change_ok(inode, attr); if (err != 0) return err; @@ -1768,7 +1787,8 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) ceph_cap_string(dirtied), mask); ceph_mdsc_put_request(req); - __ceph_do_pending_vmtruncate(inode); + if (mask & CEPH_SETATTR_SIZE) + __ceph_do_pending_vmtruncate(inode); return err; out: spin_unlock(&ci->i_ceph_lock); diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index e0b4ef3..669622f 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -196,8 +196,10 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len, &dl.object_no, &dl.object_offset, &olen); - if (r < 0) + if (r < 0) { + up_read(&osdc->map_sem); return -EIO; + } dl.file_offset -= dl.object_offset; dl.object_size = ceph_file_layout_object_size(ci->i_layout); dl.block_size = ceph_file_layout_su(ci->i_layout); @@ -209,8 +211,12 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx", ceph_ino(inode), dl.object_no); - ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap, - ceph_file_layout_pg_pool(ci->i_layout)); + r = ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap, + ceph_file_layout_pg_pool(ci->i_layout)); + if (r < 0) { + up_read(&osdc->map_sem); + return r; + } dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid); if (dl.osd >= 0) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 187bf21..b7bda5d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -414,6 +414,9 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, { struct ceph_mds_session *s; + if (mds >= mdsc->mdsmap->m_max_mds) + return ERR_PTR(-EINVAL); + s = kzalloc(sizeof(*s), GFP_NOFS); if (!s) return ERR_PTR(-ENOMEM); @@ -1028,6 +1031,37 @@ static void remove_session_caps(struct ceph_mds_session *session) { dout("remove_session_caps on %p\n", session); iterate_session_caps(session, remove_session_caps_cb, NULL); + + spin_lock(&session->s_cap_lock); + if (session->s_nr_caps > 0) { + struct super_block *sb = session->s_mdsc->fsc->sb; + struct inode *inode; + struct ceph_cap *cap, *prev = NULL; + struct ceph_vino vino; + /* + * iterate_session_caps() skips inodes that are being + * deleted, we need to wait until deletions are complete. + * __wait_on_freeing_inode() is designed for the job, + * but it is not exported, so use lookup inode function + * to access it. + */ + while (!list_empty(&session->s_caps)) { + cap = list_entry(session->s_caps.next, + struct ceph_cap, session_caps); + if (cap == prev) + break; + prev = cap; + vino = cap->ci->i_vino; + spin_unlock(&session->s_cap_lock); + + inode = ceph_find_inode(sb, vino); + iput(inode); + + spin_lock(&session->s_cap_lock); + } + } + spin_unlock(&session->s_cap_lock); + BUG_ON(session->s_nr_caps > 0); BUG_ON(!list_empty(&session->s_cap_flushing)); cleanup_cap_releases(session); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 6627b26..6a0951e 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -17,6 +17,7 @@ #include "super.h" #include "mds_client.h" +#include "cache.h" #include <linux/ceph/ceph_features.h> #include <linux/ceph/decode.h> @@ -142,6 +143,8 @@ enum { Opt_nodcache, Opt_ino32, Opt_noino32, + Opt_fscache, + Opt_nofscache }; static match_table_t fsopt_tokens = { @@ -167,6 +170,8 @@ static match_table_t fsopt_tokens = { {Opt_nodcache, "nodcache"}, {Opt_ino32, "ino32"}, {Opt_noino32, "noino32"}, + {Opt_fscache, "fsc"}, + {Opt_nofscache, "nofsc"}, {-1, NULL} }; @@ -260,6 +265,12 @@ static int parse_fsopt_token(char *c, void *private) case Opt_noino32: fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; + case Opt_fscache: + fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; + break; + case Opt_nofscache: + fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; + break; default: BUG_ON(token); } @@ -422,6 +433,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",dcache"); else seq_puts(m, ",nodcache"); + if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) + seq_puts(m, ",fsc"); + else + seq_puts(m, ",nofsc"); if (fsopt->wsize) seq_printf(m, ",wsize=%d", fsopt->wsize); @@ -530,11 +545,18 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, if (!fsc->wb_pagevec_pool) goto fail_trunc_wq; + /* setup fscache */ + if ((fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) && + (ceph_fscache_register_fs(fsc) != 0)) + goto fail_fscache; + /* caps */ fsc->min_caps = fsopt->max_readdir; return fsc; +fail_fscache: + ceph_fscache_unregister_fs(fsc); fail_trunc_wq: destroy_workqueue(fsc->trunc_wq); fail_pg_inv_wq: @@ -554,6 +576,8 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) { dout("destroy_fs_client %p\n", fsc); + ceph_fscache_unregister_fs(fsc); + destroy_workqueue(fsc->wb_wq); destroy_workqueue(fsc->pg_inv_wq); destroy_workqueue(fsc->trunc_wq); @@ -588,6 +612,8 @@ static void ceph_inode_init_once(void *foo) static int __init init_caches(void) { + int error = -ENOMEM; + ceph_inode_cachep = kmem_cache_create("ceph_inode_info", sizeof(struct ceph_inode_info), __alignof__(struct ceph_inode_info), @@ -611,15 +637,17 @@ static int __init init_caches(void) if (ceph_file_cachep == NULL) goto bad_file; - return 0; + if ((error = ceph_fscache_register())) + goto bad_file; + return 0; bad_file: kmem_cache_destroy(ceph_dentry_cachep); bad_dentry: kmem_cache_destroy(ceph_cap_cachep); bad_cap: kmem_cache_destroy(ceph_inode_cachep); - return -ENOMEM; + return error; } static void destroy_caches(void) @@ -629,10 +657,13 @@ static void destroy_caches(void) * destroy cache. */ rcu_barrier(); + kmem_cache_destroy(ceph_inode_cachep); kmem_cache_destroy(ceph_cap_cachep); kmem_cache_destroy(ceph_dentry_cachep); kmem_cache_destroy(ceph_file_cachep); + + ceph_fscache_unregister(); } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index cbded57..6014b0a 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -16,6 +16,10 @@ #include <linux/ceph/libceph.h> +#ifdef CONFIG_CEPH_FSCACHE +#include <linux/fscache.h> +#endif + /* f_type in struct statfs */ #define CEPH_SUPER_MAGIC 0x00c36400 @@ -29,6 +33,7 @@ #define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */ #define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */ #define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */ +#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */ #define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES) @@ -90,6 +95,11 @@ struct ceph_fs_client { struct dentry *debugfs_bdi; struct dentry *debugfs_mdsc, *debugfs_mdsmap; #endif + +#ifdef CONFIG_CEPH_FSCACHE + struct fscache_cookie *fscache; + struct workqueue_struct *revalidate_wq; +#endif }; @@ -288,6 +298,7 @@ struct ceph_inode_info { int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */ + struct mutex i_truncate_mutex; u32 i_truncate_seq; /* last truncate to smaller size */ u64 i_truncate_size; /* and the size we last truncated down to */ int i_truncate_pending; /* still need to call vmtruncate */ @@ -319,6 +330,12 @@ struct ceph_inode_info { struct work_struct i_vmtruncate_work; +#ifdef CONFIG_CEPH_FSCACHE + struct fscache_cookie *fscache; + u32 i_fscache_gen; /* sequence, for delayed fscache validate */ + struct work_struct i_revalidate_work; +#endif + struct inode vfs_inode; /* at end */ }; diff --git a/fs/cifs/AUTHORS b/fs/cifs/AUTHORS deleted file mode 100644 index ea940b1..0000000 --- a/fs/cifs/AUTHORS +++ /dev/null @@ -1,55 +0,0 @@ -Original Author -=============== -Steve French (sfrench@samba.org) - -The author wishes to express his appreciation and thanks to: -Andrew Tridgell (Samba team) for his early suggestions about smb/cifs VFS -improvements. Thanks to IBM for allowing me time and test resources to pursue -this project, to Jim McDonough from IBM (and the Samba Team) for his help, to -the IBM Linux JFS team for explaining many esoteric Linux filesystem features. -Jeremy Allison of the Samba team has done invaluable work in adding the server -side of the original CIFS Unix extensions and reviewing and implementing -portions of the newer CIFS POSIX extensions into the Samba 3 file server. Thank -Dave Boutcher of IBM Rochester (author of the OS/400 smb/cifs filesystem client) -for proving years ago that very good smb/cifs clients could be done on Unix-like -operating systems. Volker Lendecke, Andrew Tridgell, Urban Widmark, John -Newbigin and others for their work on the Linux smbfs module. Thanks to -the other members of the Storage Network Industry Association CIFS Technical -Workgroup for their work specifying this highly complex protocol and finally -thanks to the Samba team for their technical advice and encouragement. - -Patch Contributors ------------------- -Zwane Mwaikambo -Andi Kleen -Amrut Joshi -Shobhit Dayal -Sergey Vlasov -Richard Hughes -Yury Umanets -Mark Hamzy (for some of the early cifs IPv6 work) -Domen Puncer -Jesper Juhl (in particular for lots of whitespace/formatting cleanup) -Vince Negri and Dave Stahl (for finding an important caching bug) -Adrian Bunk (kcalloc cleanups) -Miklos Szeredi -Kazeon team for various fixes especially for 2.4 version. -Asser Ferno (Change Notify support) -Shaggy (Dave Kleikamp) for innumerable small fs suggestions and some good cleanup -Gunter Kukkukk (testing and suggestions for support of old servers) -Igor Mammedov (DFS support) -Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code) - -Test case and Bug Report contributors -------------------------------------- -Thanks to those in the community who have submitted detailed bug reports -and debug of problems they have found: Jochen Dolze, David Blaine, -Rene Scharfe, Martin Josefsson, Alexander Wild, Anthony Liguori, -Lars Muller, Urban Widmark, Massimiliano Ferrero, Howard Owen, -Olaf Kirch, Kieron Briggs, Nick Millington and others. Also special -mention to the Stanford Checker (SWAT) which pointed out many minor -bugs in error paths. Valuable suggestions also have come from Al Viro -and Dave Miller. - -And thanks to the IBM LTC and Power test teams and SuSE testers for -finding multiple bugs during excellent stress test runs. diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES deleted file mode 100644 index bc0025c..0000000 --- a/fs/cifs/CHANGES +++ /dev/null @@ -1,1065 +0,0 @@ -Version 1.62 ------------- -Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened -to more strictly handle corrupt frames. - -Version 1.61 ------------- -Fix append problem to Samba servers (files opened with O_APPEND could -have duplicated data). Fix oops in cifs_lookup. Workaround problem -mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session. -Disable use of server inode numbers when server only -partially supports them (e.g. for one server querying inode numbers on -FindFirst fails but QPathInfo queries works). Fix oops with dfs in -cifs_put_smb_ses. Fix mmap to work on directio mounts (needed -for OpenOffice when on forcedirectio mount e.g.) - -Version 1.60 -------------- -Fix memory leak in reconnect. Fix oops in DFS mount error path. -Set s_maxbytes to smaller (the max that vfs can handle) so that -sendfile will now work over cifs mounts again. Add noforcegid -and noforceuid mount parameters. Fix small mem leak when using -ntlmv2. Fix 2nd mount to same server but with different port to -be allowed (rather than reusing the 1st port) - only when the -user explicitly overrides the port on the 2nd mount. - -Version 1.59 ------------- -Client uses server inode numbers (which are persistent) rather than -client generated ones by default (mount option "serverino" turned -on by default if server supports it). Add forceuid and forcegid -mount options (so that when negotiating unix extensions specifying -which uid mounted does not immediately force the server's reported -uids to be overridden). Add support for scope mount parm. Improve -hard link detection to use same inode for both. Do not set -read-only dos attribute on directories (for chmod) since Windows -explorer special cases this attribute bit for directories for -a different purpose. - -Version 1.58 ------------- -Guard against buffer overruns in various UCS-2 to UTF-8 string conversions -when the UTF-8 string is composed of unusually long (more than 4 byte) converted -characters. Add support for mounting root of a share which redirects immediately -to DFS target. Convert string conversion functions from Unicode to more -accurately mark string length before allocating memory (which may help the -rare cases where a UTF-8 string is much larger than the UCS2 string that -we converted from). Fix endianness of the vcnum field used during -session setup to distinguish multiple mounts to same server from different -userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental -flag to be set to 2, and mount must enable krb5 to turn on extended security). -Performance of file create to Samba improved (posix create on lookup -removes 1 of 2 network requests sent on file create) - -Version 1.57 ------------- -Improve support for multiple security contexts to the same server. We -used to use the same "vcnumber" for all connections which could cause -the server to treat subsequent connections, especially those that -are authenticated as guest, as reconnections, invalidating the earlier -user's smb session. This fix allows cifs to mount multiple times to the -same server with different userids without risking invalidating earlier -established security contexts. fsync now sends SMB Flush operation -to better ensure that we wait for server to write all of the data to -server disk (not just write it over the network). Add new mount -parameter to allow user to disable sending the (slow) SMB flush on -fsync if desired (fsync still flushes all cached write data to the server). -Posix file open support added (turned off after one attempt if server -fails to support it properly, as with Samba server versions prior to 3.3.2) -Fix "redzone overwritten" bug in cifs_put_tcon (CIFSTcon may allocate too -little memory for the "nativeFileSystem" field returned by the server -during mount). Endian convert inode numbers if necessary (makes it easier -to compare inode numbers on network files from big endian systems). - -Version 1.56 ------------- -Add "forcemandatorylock" mount option to allow user to use mandatory -rather than posix (advisory) byte range locks, even though server would -support posix byte range locks. Fix query of root inode when prefixpath -specified and user does not have access to query information about the -top of the share. Fix problem in 2.6.28 resolving DFS paths to -Samba servers (worked to Windows). Fix rmdir so that pending search -(readdir) requests do not get invalid results which include the now -removed directory. Fix oops in cifs_dfs_ref.c when prefixpath is not reachable -when using DFS. Add better file create support to servers which support -the CIFS POSIX protocol extensions (this adds support for new flags -on create, and improves semantics for write of locked ranges). - -Version 1.55 ------------- -Various fixes to make delete of open files behavior more predictable -(when delete of an open file fails we mark the file as "delete-on-close" -in a way that more servers accept, but only if we can first rename the -file to a temporary name). Add experimental support for more safely -handling fcntl(F_SETLEASE). Convert cifs to using blocking tcp -sends, and also let tcp autotune the socket send and receive buffers. -This reduces the number of EAGAIN errors returned by TCP/IP in -high stress workloads (and the number of retries on socket writes -when sending large SMBWriteX requests). Fix case in which a portion of -data can in some cases not get written to the file on the server before the -file is closed. Fix DFS parsing to properly handle path consumed field, -and to handle certain codepage conversions better. Fix mount and -umount race that can cause oops in mount or umount or reconnect. - -Version 1.54 ------------- -Fix premature write failure on congested networks (we would give up -on EAGAIN from the socket too quickly on large writes). -Cifs_mkdir and cifs_create now respect the setgid bit on parent dir. -Fix endian problems in acl (mode from/to cifs acl) on bigendian -architectures. Fix problems with preserving timestamps on copying open -files (e.g. "cp -a") to Windows servers. For mkdir and create honor setgid bit -on parent directory when server supports Unix Extensions but not POSIX -create. Update cifs.upcall version to handle new Kerberos sec flags -(this requires update of cifs.upcall program from Samba). Fix memory leak -on dns_upcall (resolving DFS referralls). Fix plain text password -authentication (requires setting SecurityFlags to 0x30030 to enable -lanman and plain text though). Fix writes to be at correct offset when -file is open with O_APPEND and file is on a directio (forcediretio) mount. -Fix bug in rewinding readdir directory searches. Add nodfs mount option. - -Version 1.53 ------------- -DFS support added (Microsoft Distributed File System client support needed -for referrals which enable a hierarchical name space among servers). -Disable temporary caching of mode bits to servers which do not support -storing of mode (e.g. Windows servers, when client mounts without cifsacl -mount option) and add new "dynperm" mount option to enable temporary caching -of mode (enable old behavior). Fix hang on mount caused when server crashes -tcp session during negotiate protocol. - -Version 1.52 ------------- -Fix oops on second mount to server when null auth is used. -Enable experimental Kerberos support. Return writebehind errors on flush -and sync so that events like out of disk space get reported properly on -cached files. Fix setxattr failure to certain Samba versions. Fix mount -of second share to disconnected server session (autoreconnect on this). -Add ability to modify cifs acls for handling chmod (when mounted with -cifsacl flag). Fix prefixpath path separator so we can handle mounts -with prefixpaths longer than one directory (one path component) when -mounted to Windows servers. Fix slow file open when cifsacl -enabled. Fix memory leak in FindNext when the SMB call returns -EBADF. - - -Version 1.51 ------------- -Fix memory leak in statfs when mounted to very old servers (e.g. -Windows 9x). Add new feature "POSIX open" which allows servers -which support the current POSIX Extensions to provide better semantics -(e.g. delete for open files opened with posix open). Take into -account umask on posix mkdir not just older style mkdir. Add -ability to mount to IPC$ share (which allows CIFS named pipes to be -opened, read and written as if they were files). When 1st tree -connect fails (e.g. due to signing negotiation failure) fix -leak that causes cifsd not to stop and rmmod to fail to cleanup -cifs_request_buffers pool. Fix problem with POSIX Open/Mkdir on -bigendian architectures. Fix possible memory corruption when -EAGAIN returned on kern_recvmsg. Return better error if server -requires packet signing but client has disabled it. When mounted -with cifsacl mount option - mode bits are approximated based -on the contents of the ACL of the file or directory. When cifs -mount helper is missing convert make sure that UNC name -has backslash (not forward slash) between ip address of server -and the share name. - -Version 1.50 ------------- -Fix NTLMv2 signing. NFS server mounted over cifs works (if cifs mount is -done with "serverino" mount option). Add support for POSIX Unlink -(helps with certain sharing violation cases when server such as -Samba supports newer POSIX CIFS Protocol Extensions). Add "nounix" -mount option to allow disabling the CIFS Unix Extensions for just -that mount. Fix hang on spinlock in find_writable_file (race when -reopening file after session crash). Byte range unlock request to -windows server could unlock more bytes (on server copy of file) -than intended if start of unlock request is well before start of -a previous byte range lock that we issued. - -Version 1.49 ------------- -IPv6 support. Enable ipv6 addresses to be passed on mount (put the ipv6 -address after the "ip=" mount option, at least until mount.cifs is fixed to -handle DNS host to ipv6 name translation). Accept override of uid or gid -on mount even when Unix Extensions are negotiated (it used to be ignored -when Unix Extensions were ignored). This allows users to override the -default uid and gid for files when they are certain that the uids or -gids on the server do not match those of the client. Make "sec=none" -mount override username (so that null user connection is attempted) -to match what documentation said. Support for very large reads, over 127K, -available to some newer servers (such as Samba 3.0.26 and later but -note that it also requires setting CIFSMaxBufSize at module install -time to a larger value which may hurt performance in some cases). -Make sign option force signing (or fail if server does not support it). - -Version 1.48 ------------- -Fix mtime bouncing around from local idea of last write times to remote time. -Fix hang (in i_size_read) when simultaneous size update of same remote file -on smp system corrupts sequence number. Do not reread unnecessarily partial page -(which we are about to overwrite anyway) when writing out file opened rw. -When DOS attribute of file on non-Unix server's file changes on the server side -from read-only back to read-write, reflect this change in default file mode -(we had been leaving a file's mode read-only until the inode were reloaded). -Allow setting of attribute back to ATTR_NORMAL (removing readonly dos attribute -when archive dos attribute not set and we are changing mode back to writeable -on server which does not support the Unix Extensions). Remove read only dos -attribute on chmod when adding any write permission (ie on any of -user/group/other (not all of user/group/other ie 0222) when -mounted to windows. Add support for POSIX MkDir (slight performance -enhancement and eliminates the network race between the mkdir and set -path info of the mode). - - -Version 1.47 ------------- -Fix oops in list_del during mount caused by unaligned string. -Fix file corruption which could occur on some large file -copies caused by writepages page i/o completion bug. -Seek to SEEK_END forces check for update of file size for non-cached -files. Allow file size to be updated on remote extend of locally open, -non-cached file. Fix reconnect to newer Samba servers (or other servers -which support the CIFS Unix/POSIX extensions) so that we again tell the -server the Unix/POSIX cifs capabilities which we support (SetFSInfo). -Add experimental support for new POSIX Open/Mkdir (which returns -stat information on the open, and allows setting the mode). - -Version 1.46 ------------- -Support deep tree mounts. Better support OS/2, Win9x (DOS) time stamps. -Allow null user to be specified on mount ("username="). Do not return -EINVAL on readdir when filldir fails due to overwritten blocksize -(fixes FC problem). Return error in rename 2nd attempt retry (ie report -if rename by handle also fails, after rename by path fails, we were -not reporting whether the retry worked or not). Fix NTLMv2 to -work to Windows servers (mount with option "sec=ntlmv2"). - -Version 1.45 ------------- -Do not time out lockw calls when using posix extensions. Do not -time out requests if server still responding reasonably fast -on requests on other threads. Improve POSIX locking emulation, -(lock cancel now works, and unlock of merged range works even -to Windows servers now). Fix oops on mount to lanman servers -(win9x, os/2 etc.) when null password. Do not send listxattr -(SMB to query all EAs) if nouser_xattr specified. Fix SE Linux -problem (instantiate inodes/dentries in right order for readdir). - -Version 1.44 ------------- -Rewritten sessionsetup support, including support for legacy SMB -session setup needed for OS/2 and older servers such as Windows 95 and 98. -Fix oops on ls to OS/2 servers. Add support for level 1 FindFirst -so we can do search (ls etc.) to OS/2. Do not send NTCreateX -or recent levels of FindFirst unless server says it supports NT SMBs -(instead use legacy equivalents from LANMAN dialect). Fix to allow -NTLMv2 authentication support (now can use stronger password hashing -on mount if corresponding /proc/fs/cifs/SecurityFlags is set (0x4004). -Allow override of global cifs security flags on mount via "sec=" option(s). - -Version 1.43 ------------- -POSIX locking to servers which support CIFS POSIX Extensions -(disabled by default controlled by proc/fs/cifs/Experimental). -Handle conversion of long share names (especially Asian languages) -to Unicode during mount. Fix memory leak in sess struct on reconnect. -Fix rare oops after acpi suspend. Fix O_TRUNC opens to overwrite on -cifs open which helps rare case when setpathinfo fails or server does -not support it. - -Version 1.42 ------------- -Fix slow oplock break when mounted to different servers at the same time and -the tids match and we try to find matching fid on wrong server. Fix read -looping when signing required by server (2.6.16 kernel only). Fix readdir -vs. rename race which could cause each to hang. Return . and .. even -if server does not. Allow searches to skip first three entries and -begin at any location. Fix oops in find_writeable_file. - -Version 1.41 ------------- -Fix NTLMv2 security (can be enabled in /proc/fs/cifs) so customers can -configure stronger authentication. Fix sfu symlinks so they can -be followed (not just recognized). Fix wraparound of bcc on -read responses when buffer size over 64K and also fix wrap of -max smb buffer size when CIFSMaxBufSize over 64K. Fix oops in -cifs_user_read and cifs_readpages (when EAGAIN on send of smb -on socket is returned over and over). Add POSIX (advisory) byte range -locking support (requires server with newest CIFS UNIX Extensions -to the protocol implemented). Slow down negprot slightly in port 139 -RFC1001 case to give session_init time on buggy servers. - -Version 1.40 ------------- -Use fsuid (fsgid) more consistently instead of uid (gid). Improve performance -of readpages by eliminating one extra memcpy. Allow update of file size -from remote server even if file is open for write as long as mount is -directio. Recognize share mode security and send NTLM encrypted password -on tree connect if share mode negotiated. - -Version 1.39 ------------- -Defer close of a file handle slightly if pending writes depend on that handle -(this reduces the EBADF bad file handle errors that can be logged under heavy -stress on writes). Modify cifs Kconfig options to expose CONFIG_CIFS_STATS2 -Fix SFU style symlinks and mknod needed for servers which do not support the -CIFS Unix Extensions. Fix setfacl/getfacl on bigendian. Timeout negative -dentries so files that the client sees as deleted but that later get created -on the server will be recognized. Add client side permission check on setattr. -Timeout stuck requests better (where server has never responded or sent corrupt -responses) - -Version 1.38 ------------- -Fix tcp socket retransmission timeouts (e.g. on ENOSPACE from the socket) -to be smaller at first (but increasing) so large write performance performance -over GigE is better. Do not hang thread on illegal byte range lock response -from Windows (Windows can send an RFC1001 size which does not match smb size) by -allowing an SMBs TCP length to be up to a few bytes longer than it should be. -wsize and rsize can now be larger than negotiated buffer size if server -supports large readx/writex, even when directio mount flag not specified. -Write size will in many cases now be 16K instead of 4K which greatly helps -file copy performance on lightly loaded networks. Fix oops in dnotify -when experimental config flag enabled. Make cifsFYI more granular. - -Version 1.37 ------------- -Fix readdir caching when unlink removes file in current search buffer, -and this is followed by a rewind search to just before the deleted entry. -Do not attempt to set ctime unless atime and/or mtime change requested -(most servers throw it away anyway). Fix length check of received smbs -to be more accurate. Fix big endian problem with mapchars mount option, -and with a field returned by statfs. - -Version 1.36 ------------- -Add support for mounting to older pre-CIFS servers such as Windows9x and ME. -For these older servers, add option for passing netbios name of server in -on mount (servernetbiosname). Add suspend support for power management, to -avoid cifsd thread preventing software suspend from working. -Add mount option for disabling the default behavior of sending byte range lock -requests to the server (necessary for certain applications which break with -mandatory lock behavior such as Evolution), and also mount option for -requesting case insensitive matching for path based requests (requesting -case sensitive is the default). - -Version 1.35 ------------- -Add writepage performance improvements. Fix path name conversions -for long filenames on mounts which were done with "mapchars" mount option -specified. Ensure multiplex ids do not collide. Fix case in which -rmmod can oops if done soon after last unmount. Fix truncated -search (readdir) output when resume filename was a long filename. -Fix filename conversion when mapchars mount option was specified and -filename was a long filename. - -Version 1.34 ------------- -Fix error mapping of the TOO_MANY_LINKS (hardlinks) case. -Do not oops if root user kills cifs oplock kernel thread or -kills the cifsd thread (NB: killing the cifs kernel threads is not -recommended, unmount and rmmod cifs will kill them when they are -no longer needed). Fix readdir to ASCII servers (ie older servers -which do not support Unicode) and also require asterisk. -Fix out of memory case in which data could be written one page -off in the page cache. - -Version 1.33 ------------- -Fix caching problem, in which readdir of directory containing a file -which was cached could cause the file's time stamp to be updated -without invalidating the readahead data (so we could get stale -file data on the client for that file even as the server copy changed). -Cleanup response processing so cifsd can not loop when abnormally -terminated. - - -Version 1.32 ------------- -Fix oops in ls when Transact2 FindFirst (or FindNext) returns more than one -transact response for an SMB request and search entry split across two frames. -Add support for lsattr (getting ext2/ext3/reiserfs attr flags from the server) -as new protocol extensions. Do not send Get/Set calls for POSIX ACLs -unless server explicitly claims to support them in CIFS Unix extensions -POSIX ACL capability bit. Fix packet signing when multiuser mounting with -different users from the same client to the same server. Fix oops in -cifs_close. Add mount option for remapping reserved characters in -filenames (also allow recognizing files with created by SFU which have any -of these seven reserved characters, except backslash, to be recognized). -Fix invalid transact2 message (we were sometimes trying to interpret -oplock breaks as SMB responses). Add ioctl for checking that the -current uid matches the uid of the mounter (needed by umount.cifs). -Reduce the number of large buffer allocations in cifs response processing -(significantly reduces memory pressure under heavy stress with multiple -processes accessing the same server at the same time). - -Version 1.31 ------------- -Fix updates of DOS attributes and time fields so that files on NT4 servers -do not get marked delete on close. Display sizes of cifs buffer pools in -cifs stats. Fix oops in unmount when cifsd thread being killed by -shutdown. Add generic readv/writev and aio support. Report inode numbers -consistently in readdir and lookup (when serverino mount option is -specified use the inode number that the server reports - for both lookup -and readdir, otherwise by default the locally generated inode number is used -for inodes created in either path since servers are not always able to -provide unique inode numbers when exporting multiple volumes from under one -sharename). - -Version 1.30 ------------- -Allow new nouser_xattr mount parm to disable xattr support for user namespace. -Do not flag user_xattr mount parm in dmesg. Retry failures setting file time -(mostly affects NT4 servers) by retry with handle based network operation. -Add new POSIX Query FS Info for returning statfs info more accurately. -Handle passwords with multiple commas in them. - -Version 1.29 ------------- -Fix default mode in sysfs of cifs module parms. Remove old readdir routine. -Fix capabilities flags for large readx so as to allow reads larger than 64K. - -Version 1.28 ------------- -Add module init parm for large SMB buffer size (to allow it to be changed -from its default of 16K) which is especially useful for large file copy -when mounting with the directio mount option. Fix oops after -returning from mount when experimental ExtendedSecurity enabled and -SpnegoNegotiated returning invalid error. Fix case to retry better when -peek returns from 1 to 3 bytes on socket which should have more data. -Fixed path based calls (such as cifs lookup) to handle path names -longer than 530 (now can handle PATH_MAX). Fix pass through authentication -from Samba server to DC (Samba required dummy LM password). - -Version 1.27 ------------- -Turn off DNOTIFY (directory change notification support) by default -(unless built with the experimental flag) to fix hang with KDE -file browser. Fix DNOTIFY flag mappings. Fix hang (in wait_event -waiting on an SMB response) in SendReceive when session dies but -reconnects quickly from another task. Add module init parms for -minimum number of large and small network buffers in the buffer pools, -and for the maximum number of simultaneous requests. - -Version 1.26 ------------- -Add setfacl support to allow setting of ACLs remotely to Samba 3.10 and later -and other POSIX CIFS compliant servers. Fix error mapping for getfacl -to EOPNOTSUPP when server does not support posix acls on the wire. Fix -improperly zeroed buffer in CIFS Unix extensions set times call. - -Version 1.25 ------------- -Fix internationalization problem in cifs readdir with filenames that map to -longer UTF-8 strings than the string on the wire was in Unicode. Add workaround -for readdir to netapp servers. Fix search rewind (seek into readdir to return -non-consecutive entries). Do not do readdir when server negotiates -buffer size to small to fit filename. Add support for reading POSIX ACLs from -the server (add also acl and noacl mount options). - -Version 1.24 ------------- -Optionally allow using server side inode numbers, rather than client generated -ones by specifying mount option "serverino" - this is required for some apps -to work which double check hardlinked files and have persistent inode numbers. - -Version 1.23 ------------- -Multiple bigendian fixes. On little endian systems (for reconnect after -network failure) fix tcp session reconnect code so we do not try first -to reconnect on reverse of port 445. Treat reparse points (NTFS junctions) -as directories rather than symlinks because we can do follow link on them. - -Version 1.22 ------------- -Add config option to enable XATTR (extended attribute) support, mapping -xattr names in the "user." namespace space to SMB/CIFS EAs. Lots of -minor fixes pointed out by the Stanford SWAT checker (mostly missing -or out of order NULL pointer checks in little used error paths). - -Version 1.21 ------------- -Add new mount parm to control whether mode check (generic_permission) is done -on the client. If Unix extensions are enabled and the uids on the client -and server do not match, client permission checks are meaningless on -server uids that do not exist on the client (this does not affect the -normal ACL check which occurs on the server). Fix default uid -on mknod to match create and mkdir. Add optional mount parm to allow -override of the default uid behavior (in which the server sets the uid -and gid of newly created files). Normally for network filesystem mounts -user want the server to set the uid/gid on newly created files (rather than -using uid of the client processes you would in a local filesystem). - -Version 1.20 ------------- -Make transaction counts more consistent. Merge /proc/fs/cifs/SimultaneousOps -info into /proc/fs/cifs/DebugData. Fix oops in rare oops in readdir -(in build_wildcard_path_from_dentry). Fix mknod to pass type field -(block/char/fifo) properly. Remove spurious mount warning log entry when -credentials passed as mount argument. Set major/minor device number in -inode for block and char devices when unix extensions enabled. - -Version 1.19 ------------- -Fix /proc/fs/cifs/Stats and DebugData display to handle larger -amounts of return data. Properly limit requests to MAX_REQ (50 -is the usual maximum active multiplex SMB/CIFS requests per server). -Do not kill cifsd (and thus hurt the other SMB session) when more than one -session to the same server (but with different userids) exists and one -of the two user's smb sessions is being removed while leaving the other. -Do not loop reconnecting in cifsd demultiplex thread when admin -kills the thread without going through unmount. - -Version 1.18 ------------- -Do not rename hardlinked files (since that should be a noop). Flush -cached write behind data when reopening a file after session abend, -except when already in write. Grab per socket sem during reconnect -to avoid oops in sendmsg if overlapping with reconnect. Do not -reset cached inode file size on readdir for files open for write on -client. - - -Version 1.17 ------------- -Update number of blocks in file so du command is happier (in Linux a fake -blocksize of 512 is required for calculating number of blocks in inode). -Fix prepare write of partial pages to read in data from server if possible. -Fix race on tcpStatus field between unmount and reconnection code, causing -cifsd process sometimes to hang around forever. Improve out of memory -checks in cifs_filldir - -Version 1.16 ------------- -Fix incorrect file size in file handle based setattr on big endian hardware. -Fix oops in build_path_from_dentry when out of memory. Add checks for invalid -and closing file structs in writepage/partialpagewrite. Add statistics -for each mounted share (new menuconfig option). Fix endianness problem in -volume information displayed in /proc/fs/cifs/DebugData (only affects -affects big endian architectures). Prevent renames while constructing -path names for open, mkdir and rmdir. - -Version 1.15 ------------- -Change to mempools for alloc smb request buffers and multiplex structs -to better handle low memory problems (and potential deadlocks). - -Version 1.14 ------------- -Fix incomplete listings of large directories on Samba servers when Unix -extensions enabled. Fix oops when smb_buffer can not be allocated. Fix -rename deadlock when writing out dirty pages at same time. - -Version 1.13 ------------- -Fix open of files in which O_CREATE can cause the mode to change in -some cases. Fix case in which retry of write overlaps file close. -Fix PPC64 build error. Reduce excessive stack usage in smb password -hashing. Fix overwrite of Linux user's view of file mode to Windows servers. - -Version 1.12 ------------- -Fixes for large file copy, signal handling, socket retry, buffer -allocation and low memory situations. - -Version 1.11 ------------- -Better port 139 support to Windows servers (RFC1001/RFC1002 Session_Initialize) -also now allowing support for specifying client netbiosname. NT4 support added. - -Version 1.10 ------------- -Fix reconnection (and certain failed mounts) to properly wake up the -blocked users thread so it does not seem hung (in some cases was blocked -until the cifs receive timeout expired). Fix spurious error logging -to kernel log when application with open network files killed. - -Version 1.09 ------------- -Fix /proc/fs module unload warning message (that could be logged -to the kernel log). Fix intermittent failure in connectathon -test7 (hardlink count not immediately refreshed in case in which -inode metadata can be incorrectly kept cached when time near zero) - -Version 1.08 ------------- -Allow file_mode and dir_mode (specified at mount time) to be enforced -locally (the server already enforced its own ACLs too) for servers -that do not report the correct mode (do not support the -CIFS Unix Extensions). - -Version 1.07 ------------- -Fix some small memory leaks in some unmount error paths. Fix major leak -of cache pages in readpages causing multiple read oriented stress -testcases (including fsx, and even large file copy) to fail over time. - -Version 1.06 ------------- -Send NTCreateX with ATTR_POSIX if Linux/Unix extensions negotiated with server. -This allows files that differ only in case and improves performance of file -creation and file open to such servers. Fix semaphore conflict which causes -slow delete of open file to Samba (which unfortunately can cause an oplock -break to self while vfs_unlink held i_sem) which can hang for 20 seconds. - -Version 1.05 ------------- -fixes to cifs_readpages for fsx test case - -Version 1.04 ------------- -Fix caching data integrity bug when extending file size especially when no -oplock on file. Fix spurious logging of valid already parsed mount options -that are parsed outside of the cifs vfs such as nosuid. - - -Version 1.03 ------------- -Connect to server when port number override not specified, and tcp port -unitialized. Reset search to restart at correct file when kernel routine -filldir returns error during large directory searches (readdir). - -Version 1.02 ------------- -Fix caching problem when files opened by multiple clients in which -page cache could contain stale data, and write through did -not occur often enough while file was still open when read ahead -(read oplock) not allowed. Treat "sep=" when first mount option -as an override of comma as the default separator between mount -options. - -Version 1.01 ------------- -Allow passwords longer than 16 bytes. Allow null password string. - -Version 1.00 ------------- -Gracefully clean up failed mounts when attempting to mount to servers such as -Windows 98 that terminate tcp sessions during protocol negotiation. Handle -embedded commas in mount parsing of passwords. - -Version 0.99 ------------- -Invalidate local inode cached pages on oplock break and when last file -instance is closed so that the client does not continue using stale local -copy rather than later modified server copy of file. Do not reconnect -when server drops the tcp session prematurely before negotiate -protocol response. Fix oops in reopen_file when dentry freed. Allow -the support for CIFS Unix Extensions to be disabled via proc interface. - -Version 0.98 ------------- -Fix hang in commit_write during reconnection of open files under heavy load. -Fix unload_nls oops in a mount failure path. Serialize writes to same socket -which also fixes any possible races when cifs signatures are enabled in SMBs -being sent out of signature sequence number order. - -Version 0.97 ------------- -Fix byte range locking bug (endian problem) causing bad offset and -length. - -Version 0.96 ------------- -Fix oops (in send_sig) caused by CIFS unmount code trying to -wake up the demultiplex thread after it had exited. Do not log -error on harmless oplock release of closed handle. - -Version 0.95 ------------- -Fix unsafe global variable usage and password hash failure on gcc 3.3.1 -Fix problem reconnecting secondary mounts to same server after session -failure. Fix invalid dentry - race in mkdir when directory gets created -by another client between the lookup and mkdir. - -Version 0.94 ------------- -Fix to list processing in reopen_files. Fix reconnection when server hung -but tcpip session still alive. Set proper timeout on socket read. - -Version 0.93 ------------- -Add missing mount options including iocharset. SMP fixes in write and open. -Fix errors in reconnecting after TCP session failure. Fix module unloading -of default nls codepage - -Version 0.92 ------------- -Active smb transactions should never go negative (fix double FreeXid). Fix -list processing in file routines. Check return code on kmalloc in open. -Fix spinlock usage for SMP. - -Version 0.91 ------------- -Fix oops in reopen_files when invalid dentry. drop dentry on server rename -and on revalidate errors. Fix cases where pid is now tgid. Fix return code -on create hard link when server does not support them. - -Version 0.90 ------------- -Fix scheduling while atomic error in getting inode info on newly created file. -Fix truncate of existing files opened with O_CREAT but not O_TRUNC set. - -Version 0.89 ------------- -Fix oops on write to dead tcp session. Remove error log write for case when file open -O_CREAT but not O_EXCL - -Version 0.88 ------------- -Fix non-POSIX behavior on rename of open file and delete of open file by taking -advantage of trans2 SetFileInfo rename facility if available on target server. -Retry on ENOSPC and EAGAIN socket errors. - -Version 0.87 ------------- -Fix oops on big endian readdir. Set blksize to be even power of two (2**blkbits) to fix -allocation size miscalculation. After oplock token lost do not read through -cache. - -Version 0.86 ------------- -Fix oops on empty file readahead. Fix for file size handling for locally cached files. - -Version 0.85 ------------- -Fix oops in mkdir when server fails to return inode info. Fix oops in reopen_files -during auto reconnection to server after server recovered from failure. - -Version 0.84 ------------- -Finish support for Linux 2.5 open/create changes, which removes the -redundant NTCreate/QPathInfo/close that was sent during file create. -Enable oplock by default. Enable packet signing by default (needed to -access many recent Windows servers) - -Version 0.83 ------------- -Fix oops when mounting to long server names caused by inverted parms to kmalloc. -Fix MultiuserMount (/proc/fs/cifs configuration setting) so that when enabled -we will choose a cifs user session (smb uid) that better matches the local -uid if a) the mount uid does not match the current uid and b) we have another -session to the same server (ip address) for a different mount which -matches the current local uid. - -Version 0.82 ------------- -Add support for mknod of block or character devices. Fix oplock -code (distributed caching) to properly send response to oplock -break from server. - -Version 0.81 ------------- -Finish up CIFS packet digital signing for the default -NTLM security case. This should help Windows 2003 -network interoperability since it is common for -packet signing to be required now. Fix statfs (stat -f) -which recently started returning errors due to -invalid value (-1 instead of 0) being set in the -struct kstatfs f_ffiles field. - -Version 0.80 ------------ -Fix oops on stopping oplock thread when removing cifs when -built as module. - -Version 0.79 ------------- -Fix mount options for ro (readonly), uid, gid and file and directory mode. - -Version 0.78 ------------- -Fix errors displayed on failed mounts to be more understandable. -Fixed various incorrect or misleading smb to posix error code mappings. - -Version 0.77 ------------- -Fix display of NTFS DFS junctions to display as symlinks. -They are the network equivalent. Fix oops in -cifs_partialpagewrite caused by missing spinlock protection -of openfile linked list. Allow writebehind caching errors to -be returned to the application at file close. - -Version 0.76 ------------- -Clean up options displayed in /proc/mounts by show_options to -be more consistent with other filesystems. - -Version 0.75 ------------- -Fix delete of readonly file to Windows servers. Reflect -presence or absence of read only dos attribute in mode -bits for servers that do not support CIFS Unix extensions. -Fix shortened results on readdir of large directories to -servers supporting CIFS Unix extensions (caused by -incorrect resume key). - -Version 0.74 ------------- -Fix truncate bug (set file size) that could cause hangs e.g. running fsx - -Version 0.73 ------------- -unload nls if mount fails. - -Version 0.72 ------------- -Add resume key support to search (readdir) code to workaround -Windows bug. Add /proc/fs/cifs/LookupCacheEnable which -allows disabling caching of attribute information for -lookups. - -Version 0.71 ------------- -Add more oplock handling (distributed caching code). Remove -dead code. Remove excessive stack space utilization from -symlink routines. - -Version 0.70 ------------- -Fix oops in get dfs referral (triggered when null path sent in to -mount). Add support for overriding rsize at mount time. - -Version 0.69 ------------- -Fix buffer overrun in readdir which caused intermittent kernel oopses. -Fix writepage code to release kmap on write data. Allow "-ip=" new -mount option to be passed in on parameter distinct from the first part -(server name portion of) the UNC name. Allow override of the -tcp port of the target server via new mount option "-port=" - -Version 0.68 ------------- -Fix search handle leak on rewind. Fix setuid and gid so that they are -reflected in the local inode immediately. Cleanup of whitespace -to make 2.4 and 2.5 versions more consistent. - - -Version 0.67 ------------- -Fix signal sending so that captive thread (cifsd) exits on umount -(which was causing the warning in kmem_cache_free of the request buffers -at rmmod time). This had broken as a sideeffect of the recent global -kernel change to daemonize. Fix memory leak in readdir code which -showed up in "ls -R" (and applications that did search rewinding). - -Version 0.66 ------------- -Reconnect tids and fids after session reconnection (still do not -reconnect byte range locks though). Fix problem caching -lookup information for directory inodes, improving performance, -especially in deep directory trees. Fix various build warnings. - -Version 0.65 ------------- -Finish fixes to commit write for caching/readahead consistency. fsx -now works to Samba servers. Fix oops caused when readahead -was interrupted by a signal. - -Version 0.64 ------------- -Fix data corruption (in partial page after truncate) that caused fsx to -fail to Windows servers. Cleaned up some extraneous error logging in -common error paths. Add generic sendfile support. - -Version 0.63 ------------- -Fix memory leak in AllocMidQEntry. -Finish reconnection logic, so connection with server can be dropped -(or server rebooted) and the cifs client will reconnect. - -Version 0.62 ------------- -Fix temporary socket leak when bad userid or password specified -(or other SMBSessSetup failure). Increase maximum buffer size to slightly -over 16K to allow negotiation of up to Samba and Windows server default read -sizes. Add support for readpages - -Version 0.61 ------------- -Fix oops when username not passed in on mount. Extensive fixes and improvements -to error logging (strip redundant newlines, change debug macros to ensure newline -passed in and to be more consistent). Fix writepage wrong file handle problem, -a readonly file handle could be incorrectly used to attempt to write out -file updates through the page cache to multiply open files. This could cause -the iozone benchmark to fail on the fwrite test. Fix bug mounting two different -shares to the same Windows server when using different usernames -(doing this to Samba servers worked but Windows was rejecting it) - now it is -possible to use different userids when connecting to the same server from a -Linux client. Fix oops when treeDisconnect called during unmount on -previously freed socket. - -Version 0.60 ------------- -Fix oops in readpages caused by not setting address space operations in inode in -rare code path. - -Version 0.59 ------------- -Includes support for deleting of open files and renaming over existing files (per POSIX -requirement). Add readlink support for Windows junction points (directory symlinks). - -Version 0.58 ------------- -Changed read and write to go through pagecache. Added additional address space operations. -Memory mapped operations now working. - -Version 0.57 ------------- -Added writepage code for additional memory mapping support. Fixed leak in xids causing -the simultaneous operations counter (/proc/fs/cifs/SimultaneousOps) to increase on -every stat call. Additional formatting cleanup. - -Version 0.56 ------------- -Fix bigendian bug in order of time conversion. Merge 2.5 to 2.4 version. Formatting cleanup. - -Version 0.55 ------------- -Fixes from Zwane Mwaikambo for adding missing return code checking in a few places. -Also included a modified version of his fix to protect global list manipulation of -the smb session and tree connection and mid related global variables. - -Version 0.54 ------------- -Fix problem with captive thread hanging around at unmount time. Adjust to 2.5.42-pre -changes to superblock layout. Remove wasteful allocation of smb buffers (now the send -buffer is reused for responses). Add more oplock handling. Additional minor cleanup. - -Version 0.53 ------------- -More stylistic updates to better match kernel style. Add additional statistics -for filesystem which can be viewed via /proc/fs/cifs. Add more pieces of NTLMv2 -and CIFS Packet Signing enablement. - -Version 0.52 ------------- -Replace call to sleep_on with safer wait_on_event. -Make stylistic changes to better match kernel style recommendations. -Remove most typedef usage (except for the PDUs themselves). - -Version 0.51 ------------- -Update mount so the -unc mount option is no longer required (the ip address can be specified -in a UNC style device name. Implementation of readpage/writepage started. - -Version 0.50 ------------- -Fix intermittent problem with incorrect smb header checking on badly -fragmented tcp responses - -Version 0.49 ------------- -Fixes to setting of allocation size and file size. - -Version 0.48 ------------- -Various 2.5.38 fixes. Now works on 2.5.38 - -Version 0.47 ------------- -Prepare for 2.5 kernel merge. Remove ifdefs. - -Version 0.46 ------------- -Socket buffer management fixes. Fix dual free. - -Version 0.45 ------------- -Various big endian fixes for hardlinks and symlinks and also for dfs. - -Version 0.44 ------------- -Various big endian fixes for servers with Unix extensions such as Samba - -Version 0.43 ------------- -Various FindNext fixes for incorrect filenames on large directory searches on big endian -clients. basic posix file i/o tests now work on big endian machines, not just le - -Version 0.42 ------------- -SessionSetup and NegotiateProtocol now work from Big Endian machines. -Various Big Endian fixes found during testing on the Linux on 390. Various fixes for compatibility with older -versions of 2.4 kernel (now builds and works again on kernels at least as early as 2.4.7). - -Version 0.41 ------------- -Various minor fixes for Connectathon Posix "basic" file i/o test suite. Directory caching fixed so hardlinked -files now return the correct number of links on fstat as they are repeatedly linked and unlinked. - -Version 0.40 ------------- -Implemented "Raw" (i.e. not encapsulated in SPNEGO) NTLMSSP (i.e. the Security Provider Interface used to negotiate -session advanced session authentication). Raw NTLMSSP is preferred by Windows 2000 Professional and Windows XP. -Began implementing support for SPNEGO encapsulation of NTLMSSP based session authentication blobs -(which is the mechanism preferred by Windows 2000 server in the absence of Kerberos). - -Version 0.38 ------------- -Introduced optional mount helper utility mount.cifs and made coreq changes to cifs vfs to enable -it. Fixed a few bugs in the DFS code (e.g. bcc two bytes too short and incorrect uid in PDU). - -Version 0.37 ------------- -Rewrote much of connection and mount/unmount logic to handle bugs with -multiple uses to same share, multiple users to same server etc. - -Version 0.36 ------------- -Fixed major problem with dentry corruption (missing call to dput) - -Version 0.35 ------------- -Rewrite of readdir code to fix bug. Various fixes for bigendian machines. -Begin adding oplock support. Multiusermount and oplockEnabled flags added to /proc/fs/cifs -although corresponding function not fully implemented in the vfs yet - -Version 0.34 ------------- -Fixed dentry caching bug, misc. cleanup - -Version 0.33 ------------- -Fixed 2.5 support to handle build and configure changes as well as misc. 2.5 changes. Now can build -on current 2.5 beta version (2.5.24) of the Linux kernel as well as on 2.4 Linux kernels. -Support for STATUS codes (newer 32 bit NT error codes) added. DFS support begun to be added. - -Version 0.32 ------------- -Unix extensions (symlink, readlink, hardlink, chmod and some chgrp and chown) implemented -and tested against Samba 2.2.5 - - -Version 0.31 ------------- -1) Fixed lockrange to be correct (it was one byte too short) - -2) Fixed GETLK (i.e. the fcntl call to test a range of bytes in a file to see if locked) to correctly -show range as locked when there is a conflict with an existing lock. - -3) default file perms are now 2767 (indicating support for mandatory locks) instead of 777 for directories -in most cases. Eventually will offer optional ability to query server for the correct perms. - -3) Fixed eventual trap when mounting twice to different shares on the same server when the first succeeded -but the second one was invalid and failed (the second one was incorrectly disconnecting the tcp and smb -session) - -4) Fixed error logging of valid mount options - -5) Removed logging of password field. - -6) Moved negotiate, treeDisconnect and uloggoffX (only tConx and SessSetup remain in connect.c) to cifssmb.c -and cleaned them up and made them more consistent with other cifs functions. - -7) Server support for Unix extensions is now fully detected and FindFirst is implemented both ways -(with or without Unix extensions) but FindNext and QueryPathInfo with the Unix extensions are not completed, -nor is the symlink support using the Unix extensions - -8) Started adding the readlink and follow_link code - -Version 0.3 ------------ -Initial drop - diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index aa0d68b..1964d21 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_CIFS) += cifs.o cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \ link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \ cifs_unicode.o nterr.o xattr.o cifsencrypt.o \ - readdir.o ioctl.o sess.o export.o smb1ops.o + readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o cifs-$(CONFIG_CIFS_ACL) += cifsacl.o diff --git a/fs/cifs/README b/fs/cifs/README deleted file mode 100644 index 2d5622f..0000000 --- a/fs/cifs/README +++ /dev/null @@ -1,753 +0,0 @@ -The CIFS VFS support for Linux supports many advanced network filesystem -features such as hierarchical dfs like namespace, hardlinks, locking and more. -It was designed to comply with the SNIA CIFS Technical Reference (which -supersedes the 1992 X/Open SMB Standard) as well as to perform best practice -practical interoperability with Windows 2000, Windows XP, Samba and equivalent -servers. This code was developed in participation with the Protocol Freedom -Information Foundation. - -Please see - http://protocolfreedom.org/ and - http://samba.org/samba/PFIF/ -for more details. - - -For questions or bug reports please contact: - sfrench@samba.org (sfrench@us.ibm.com) - -Build instructions: -================== -For Linux 2.4: -1) Get the kernel source (e.g.from http://www.kernel.org) -and download the cifs vfs source (see the project page -at http://us1.samba.org/samba/Linux_CIFS_client.html) -and change directory into the top of the kernel directory -then patch the kernel (e.g. "patch -p1 < cifs_24.patch") -to add the cifs vfs to your kernel configure options if -it has not already been added (e.g. current SuSE and UL -users do not need to apply the cifs_24.patch since the cifs vfs is -already in the kernel configure menu) and then -mkdir linux/fs/cifs and then copy the current cifs vfs files from -the cifs download to your kernel build directory e.g. - - cp <cifs_download_dir>/fs/cifs/* to <kernel_download_dir>/fs/cifs - -2) make menuconfig (or make xconfig) -3) select cifs from within the network filesystem choices -4) save and exit -5) make dep -6) make modules (or "make" if CIFS VFS not to be built as a module) - -For Linux 2.6: -1) Download the kernel (e.g. from http://www.kernel.org) -and change directory into the top of the kernel directory tree -(e.g. /usr/src/linux-2.5.73) -2) make menuconfig (or make xconfig) -3) select cifs from within the network filesystem choices -4) save and exit -5) make - - -Installation instructions: -========================= -If you have built the CIFS vfs as module (successfully) simply -type "make modules_install" (or if you prefer, manually copy the file to -the modules directory e.g. /lib/modules/2.4.10-4GB/kernel/fs/cifs/cifs.o). - -If you have built the CIFS vfs into the kernel itself, follow the instructions -for your distribution on how to install a new kernel (usually you -would simply type "make install"). - -If you do not have the utility mount.cifs (in the Samba 3.0 source tree and on -the CIFS VFS web site) copy it to the same directory in which mount.smbfs and -similar files reside (usually /sbin). Although the helper software is not -required, mount.cifs is recommended. Eventually the Samba 3.0 utility program -"net" may also be helpful since it may someday provide easier mount syntax for -users who are used to Windows e.g. - net use <mount point> <UNC name or cifs URL> -Note that running the Winbind pam/nss module (logon service) on all of your -Linux clients is useful in mapping Uids and Gids consistently across the -domain to the proper network user. The mount.cifs mount helper can be -trivially built from Samba 3.0 or later source e.g. by executing: - - gcc samba/source/client/mount.cifs.c -o mount.cifs - -If cifs is built as a module, then the size and number of network buffers -and maximum number of simultaneous requests to one server can be configured. -Changing these from their defaults is not recommended. By executing modinfo - modinfo kernel/fs/cifs/cifs.ko -on kernel/fs/cifs/cifs.ko the list of configuration changes that can be made -at module initialization time (by running insmod cifs.ko) can be seen. - -Allowing User Mounts -==================== -To permit users to mount and unmount over directories they own is possible -with the cifs vfs. A way to enable such mounting is to mark the mount.cifs -utility as suid (e.g. "chmod +s /sbin/mount.cifs). To enable users to -umount shares they mount requires -1) mount.cifs version 1.4 or later -2) an entry for the share in /etc/fstab indicating that a user may -unmount it e.g. -//server/usersharename /mnt/username cifs user 0 0 - -Note that when the mount.cifs utility is run suid (allowing user mounts), -in order to reduce risks, the "nosuid" mount flag is passed in on mount to -disallow execution of an suid program mounted on the remote target. -When mount is executed as root, nosuid is not passed in by default, -and execution of suid programs on the remote target would be enabled -by default. This can be changed, as with nfs and other filesystems, -by simply specifying "nosuid" among the mount options. For user mounts -though to be able to pass the suid flag to mount requires rebuilding -mount.cifs with the following flag: - - gcc samba/source/client/mount.cifs.c -DCIFS_ALLOW_USR_SUID -o mount.cifs - -There is a corresponding manual page for cifs mounting in the Samba 3.0 and -later source tree in docs/manpages/mount.cifs.8 - -Allowing User Unmounts -====================== -To permit users to ummount directories that they have user mounted (see above), -the utility umount.cifs may be used. It may be invoked directly, or if -umount.cifs is placed in /sbin, umount can invoke the cifs umount helper -(at least for most versions of the umount utility) for umount of cifs -mounts, unless umount is invoked with -i (which will avoid invoking a umount -helper). As with mount.cifs, to enable user unmounts umount.cifs must be marked -as suid (e.g. "chmod +s /sbin/umount.cifs") or equivalent (some distributions -allow adding entries to a file to the /etc/permissions file to achieve the -equivalent suid effect). For this utility to succeed the target path -must be a cifs mount, and the uid of the current user must match the uid -of the user who mounted the resource. - -Also note that the customary way of allowing user mounts and unmounts is -(instead of using mount.cifs and unmount.cifs as suid) to add a line -to the file /etc/fstab for each //server/share you wish to mount, but -this can become unwieldy when potential mount targets include many -or unpredictable UNC names. - -Samba Considerations -==================== -To get the maximum benefit from the CIFS VFS, we recommend using a server that -supports the SNIA CIFS Unix Extensions standard (e.g. Samba 2.2.5 or later or -Samba 3.0) but the CIFS vfs works fine with a wide variety of CIFS servers. -Note that uid, gid and file permissions will display default values if you do -not have a server that supports the Unix extensions for CIFS (such as Samba -2.2.5 or later). To enable the Unix CIFS Extensions in the Samba server, add -the line: - - unix extensions = yes - -to your smb.conf file on the server. Note that the following smb.conf settings -are also useful (on the Samba server) when the majority of clients are Unix or -Linux: - - case sensitive = yes - delete readonly = yes - ea support = yes - -Note that server ea support is required for supporting xattrs from the Linux -cifs client, and that EA support is present in later versions of Samba (e.g. -3.0.6 and later (also EA support works in all versions of Windows, at least to -shares on NTFS filesystems). Extended Attribute (xattr) support is an optional -feature of most Linux filesystems which may require enabling via -make menuconfig. Client support for extended attributes (user xattr) can be -disabled on a per-mount basis by specifying "nouser_xattr" on mount. - -The CIFS client can get and set POSIX ACLs (getfacl, setfacl) to Samba servers -version 3.10 and later. Setting POSIX ACLs requires enabling both XATTR and -then POSIX support in the CIFS configuration options when building the cifs -module. POSIX ACL support can be disabled on a per mount basic by specifying -"noacl" on mount. - -Some administrators may want to change Samba's smb.conf "map archive" and -"create mask" parameters from the default. Unless the create mask is changed -newly created files can end up with an unnecessarily restrictive default mode, -which may not be what you want, although if the CIFS Unix extensions are -enabled on the server and client, subsequent setattr calls (e.g. chmod) can -fix the mode. Note that creating special devices (mknod) remotely -may require specifying a mkdev function to Samba if you are not using -Samba 3.0.6 or later. For more information on these see the manual pages -("man smb.conf") on the Samba server system. Note that the cifs vfs, -unlike the smbfs vfs, does not read the smb.conf on the client system -(the few optional settings are passed in on mount via -o parameters instead). -Note that Samba 2.2.7 or later includes a fix that allows the CIFS VFS to delete -open files (required for strict POSIX compliance). Windows Servers already -supported this feature. Samba server does not allow symlinks that refer to files -outside of the share, so in Samba versions prior to 3.0.6, most symlinks to -files with absolute paths (ie beginning with slash) such as: - ln -s /mnt/foo bar -would be forbidden. Samba 3.0.6 server or later includes the ability to create -such symlinks safely by converting unsafe symlinks (ie symlinks to server -files that are outside of the share) to a samba specific format on the server -that is ignored by local server applications and non-cifs clients and that will -not be traversed by the Samba server). This is opaque to the Linux client -application using the cifs vfs. Absolute symlinks will work to Samba 3.0.5 or -later, but only for remote clients using the CIFS Unix extensions, and will -be invisbile to Windows clients and typically will not affect local -applications running on the same server as Samba. - -Use instructions: -================ -Once the CIFS VFS support is built into the kernel or installed as a module -(cifs.o), you can use mount syntax like the following to access Samba or Windows -servers: - - mount -t cifs //9.53.216.11/e$ /mnt -o user=myname,pass=mypassword - -Before -o the option -v may be specified to make the mount.cifs -mount helper display the mount steps more verbosely. -After -o the following commonly used cifs vfs specific options -are supported: - - user=<username> - pass=<password> - domain=<domain name> - -Other cifs mount options are described below. Use of TCP names (in addition to -ip addresses) is available if the mount helper (mount.cifs) is installed. If -you do not trust the server to which are mounted, or if you do not have -cifs signing enabled (and the physical network is insecure), consider use -of the standard mount options "noexec" and "nosuid" to reduce the risk of -running an altered binary on your local system (downloaded from a hostile server -or altered by a hostile router). - -Although mounting using format corresponding to the CIFS URL specification is -not possible in mount.cifs yet, it is possible to use an alternate format -for the server and sharename (which is somewhat similar to NFS style mount -syntax) instead of the more widely used UNC format (i.e. \\server\share): - mount -t cifs tcp_name_of_server:share_name /mnt -o user=myname,pass=mypasswd - -When using the mount helper mount.cifs, passwords may be specified via alternate -mechanisms, instead of specifying it after -o using the normal "pass=" syntax -on the command line: -1) By including it in a credential file. Specify credentials=filename as one -of the mount options. Credential files contain two lines - username=someuser - password=your_password -2) By specifying the password in the PASSWD environment variable (similarly -the user name can be taken from the USER environment variable). -3) By specifying the password in a file by name via PASSWD_FILE -4) By specifying the password in a file by file descriptor via PASSWD_FD - -If no password is provided, mount.cifs will prompt for password entry - -Restrictions -============ -Servers must support either "pure-TCP" (port 445 TCP/IP CIFS connections) or RFC -1001/1002 support for "Netbios-Over-TCP/IP." This is not likely to be a -problem as most servers support this. - -Valid filenames differ between Windows and Linux. Windows typically restricts -filenames which contain certain reserved characters (e.g.the character : -which is used to delimit the beginning of a stream name by Windows), while -Linux allows a slightly wider set of valid characters in filenames. Windows -servers can remap such characters when an explicit mapping is specified in -the Server's registry. Samba starting with version 3.10 will allow such -filenames (ie those which contain valid Linux characters, which normally -would be forbidden for Windows/CIFS semantics) as long as the server is -configured for Unix Extensions (and the client has not disabled -/proc/fs/cifs/LinuxExtensionsEnabled). - - -CIFS VFS Mount Options -====================== -A partial list of the supported mount options follows: - user The user name to use when trying to establish - the CIFS session. - password The user password. If the mount helper is - installed, the user will be prompted for password - if not supplied. - ip The ip address of the target server - unc The target server Universal Network Name (export) to - mount. - domain Set the SMB/CIFS workgroup name prepended to the - username during CIFS session establishment - forceuid Set the default uid for inodes to the uid - passed in on mount. For mounts to servers - which do support the CIFS Unix extensions, such as a - properly configured Samba server, the server provides - the uid, gid and mode so this parameter should not be - specified unless the server and clients uid and gid - numbering differ. If the server and client are in the - same domain (e.g. running winbind or nss_ldap) and - the server supports the Unix Extensions then the uid - and gid can be retrieved from the server (and uid - and gid would not have to be specifed on the mount. - For servers which do not support the CIFS Unix - extensions, the default uid (and gid) returned on lookup - of existing files will be the uid (gid) of the person - who executed the mount (root, except when mount.cifs - is configured setuid for user mounts) unless the "uid=" - (gid) mount option is specified. Also note that permission - checks (authorization checks) on accesses to a file occur - at the server, but there are cases in which an administrator - may want to restrict at the client as well. For those - servers which do not report a uid/gid owner - (such as Windows), permissions can also be checked at the - client, and a crude form of client side permission checking - can be enabled by specifying file_mode and dir_mode on - the client. (default) - forcegid (similar to above but for the groupid instead of uid) (default) - noforceuid Fill in file owner information (uid) by requesting it from - the server if possible. With this option, the value given in - the uid= option (on mount) will only be used if the server - can not support returning uids on inodes. - noforcegid (similar to above but for the group owner, gid, instead of uid) - uid Set the default uid for inodes, and indicate to the - cifs kernel driver which local user mounted. If the server - supports the unix extensions the default uid is - not used to fill in the owner fields of inodes (files) - unless the "forceuid" parameter is specified. - gid Set the default gid for inodes (similar to above). - file_mode If CIFS Unix extensions are not supported by the server - this overrides the default mode for file inodes. - fsc Enable local disk caching using FS-Cache (off by default). This - option could be useful to improve performance on a slow link, - heavily loaded server and/or network where reading from the - disk is faster than reading from the server (over the network). - This could also impact scalability positively as the - number of calls to the server are reduced. However, local - caching is not suitable for all workloads for e.g. read-once - type workloads. So, you need to consider carefully your - workload/scenario before using this option. Currently, local - disk caching is functional for CIFS files opened as read-only. - dir_mode If CIFS Unix extensions are not supported by the server - this overrides the default mode for directory inodes. - port attempt to contact the server on this tcp port, before - trying the usual ports (port 445, then 139). - iocharset Codepage used to convert local path names to and from - Unicode. Unicode is used by default for network path - names if the server supports it. If iocharset is - not specified then the nls_default specified - during the local client kernel build will be used. - If server does not support Unicode, this parameter is - unused. - rsize default read size (usually 16K). The client currently - can not use rsize larger than CIFSMaxBufSize. CIFSMaxBufSize - defaults to 16K and may be changed (from 8K to the maximum - kmalloc size allowed by your kernel) at module install time - for cifs.ko. Setting CIFSMaxBufSize to a very large value - will cause cifs to use more memory and may reduce performance - in some cases. To use rsize greater than 127K (the original - cifs protocol maximum) also requires that the server support - a new Unix Capability flag (for very large read) which some - newer servers (e.g. Samba 3.0.26 or later) do. rsize can be - set from a minimum of 2048 to a maximum of 130048 (127K or - CIFSMaxBufSize, whichever is smaller) - wsize default write size (default 57344) - maximum wsize currently allowed by CIFS is 57344 (fourteen - 4096 byte pages) - actimeo=n attribute cache timeout in seconds (default 1 second). - After this timeout, the cifs client requests fresh attribute - information from the server. This option allows to tune the - attribute cache timeout to suit the workload needs. Shorter - timeouts mean better the cache coherency, but increased number - of calls to the server. Longer timeouts mean reduced number - of calls to the server at the expense of less stricter cache - coherency checks (i.e. incorrect attribute cache for a short - period of time). - rw mount the network share read-write (note that the - server may still consider the share read-only) - ro mount network share read-only - version used to distinguish different versions of the - mount helper utility (not typically needed) - sep if first mount option (after the -o), overrides - the comma as the separator between the mount - parms. e.g. - -o user=myname,password=mypassword,domain=mydom - could be passed instead with period as the separator by - -o sep=.user=myname.password=mypassword.domain=mydom - this might be useful when comma is contained within username - or password or domain. This option is less important - when the cifs mount helper cifs.mount (version 1.1 or later) - is used. - nosuid Do not allow remote executables with the suid bit - program to be executed. This is only meaningful for mounts - to servers such as Samba which support the CIFS Unix Extensions. - If you do not trust the servers in your network (your mount - targets) it is recommended that you specify this option for - greater security. - exec Permit execution of binaries on the mount. - noexec Do not permit execution of binaries on the mount. - dev Recognize block devices on the remote mount. - nodev Do not recognize devices on the remote mount. - suid Allow remote files on this mountpoint with suid enabled to - be executed (default for mounts when executed as root, - nosuid is default for user mounts). - credentials Although ignored by the cifs kernel component, it is used by - the mount helper, mount.cifs. When mount.cifs is installed it - opens and reads the credential file specified in order - to obtain the userid and password arguments which are passed to - the cifs vfs. - guest Although ignored by the kernel component, the mount.cifs - mount helper will not prompt the user for a password - if guest is specified on the mount options. If no - password is specified a null password will be used. - perm Client does permission checks (vfs_permission check of uid - and gid of the file against the mode and desired operation), - Note that this is in addition to the normal ACL check on the - target machine done by the server software. - Client permission checking is enabled by default. - noperm Client does not do permission checks. This can expose - files on this mount to access by other users on the local - client system. It is typically only needed when the server - supports the CIFS Unix Extensions but the UIDs/GIDs on the - client and server system do not match closely enough to allow - access by the user doing the mount, but it may be useful with - non CIFS Unix Extension mounts for cases in which the default - mode is specified on the mount but is not to be enforced on the - client (e.g. perhaps when MultiUserMount is enabled) - Note that this does not affect the normal ACL check on the - target machine done by the server software (of the server - ACL against the user name provided at mount time). - serverino Use server's inode numbers instead of generating automatically - incrementing inode numbers on the client. Although this will - make it easier to spot hardlinked files (as they will have - the same inode numbers) and inode numbers may be persistent, - note that the server does not guarantee that the inode numbers - are unique if multiple server side mounts are exported under a - single share (since inode numbers on the servers might not - be unique if multiple filesystems are mounted under the same - shared higher level directory). Note that some older - (e.g. pre-Windows 2000) do not support returning UniqueIDs - or the CIFS Unix Extensions equivalent and for those - this mount option will have no effect. Exporting cifs mounts - under nfsd requires this mount option on the cifs mount. - This is now the default if server supports the - required network operation. - noserverino Client generates inode numbers (rather than using the actual one - from the server). These inode numbers will vary after - unmount or reboot which can confuse some applications, - but not all server filesystems support unique inode - numbers. - setuids If the CIFS Unix extensions are negotiated with the server - the client will attempt to set the effective uid and gid of - the local process on newly created files, directories, and - devices (create, mkdir, mknod). If the CIFS Unix Extensions - are not negotiated, for newly created files and directories - instead of using the default uid and gid specified on - the mount, cache the new file's uid and gid locally which means - that the uid for the file can change when the inode is - reloaded (or the user remounts the share). - nosetuids The client will not attempt to set the uid and gid on - on newly created files, directories, and devices (create, - mkdir, mknod) which will result in the server setting the - uid and gid to the default (usually the server uid of the - user who mounted the share). Letting the server (rather than - the client) set the uid and gid is the default. If the CIFS - Unix Extensions are not negotiated then the uid and gid for - new files will appear to be the uid (gid) of the mounter or the - uid (gid) parameter specified on the mount. - netbiosname When mounting to servers via port 139, specifies the RFC1001 - source name to use to represent the client netbios machine - name when doing the RFC1001 netbios session initialize. - direct Do not do inode data caching on files opened on this mount. - This precludes mmapping files on this mount. In some cases - with fast networks and little or no caching benefits on the - client (e.g. when the application is doing large sequential - reads bigger than page size without rereading the same data) - this can provide better performance than the default - behavior which caches reads (readahead) and writes - (writebehind) through the local Linux client pagecache - if oplock (caching token) is granted and held. Note that - direct allows write operations larger than page size - to be sent to the server. - strictcache Use for switching on strict cache mode. In this mode the - client read from the cache all the time it has Oplock Level II, - otherwise - read from the server. All written data are stored - in the cache, but if the client doesn't have Exclusive Oplock, - it writes the data to the server. - rwpidforward Forward pid of a process who opened a file to any read or write - operation on that file. This prevent applications like WINE - from failing on read and write if we use mandatory brlock style. - acl Allow setfacl and getfacl to manage posix ACLs if server - supports them. (default) - noacl Do not allow setfacl and getfacl calls on this mount - user_xattr Allow getting and setting user xattrs (those attributes whose - name begins with "user." or "os2.") as OS/2 EAs (extended - attributes) to the server. This allows support of the - setfattr and getfattr utilities. (default) - nouser_xattr Do not allow getfattr/setfattr to get/set/list xattrs - mapchars Translate six of the seven reserved characters (not backslash) - *?<>|: - to the remap range (above 0xF000), which also - allows the CIFS client to recognize files created with - such characters by Windows's POSIX emulation. This can - also be useful when mounting to most versions of Samba - (which also forbids creating and opening files - whose names contain any of these seven characters). - This has no effect if the server does not support - Unicode on the wire. - nomapchars Do not translate any of these seven characters (default). - nocase Request case insensitive path name matching (case - sensitive is the default if the server supports it). - (mount option "ignorecase" is identical to "nocase") - posixpaths If CIFS Unix extensions are supported, attempt to - negotiate posix path name support which allows certain - characters forbidden in typical CIFS filenames, without - requiring remapping. (default) - noposixpaths If CIFS Unix extensions are supported, do not request - posix path name support (this may cause servers to - reject creatingfile with certain reserved characters). - nounix Disable the CIFS Unix Extensions for this mount (tree - connection). This is rarely needed, but it may be useful - in order to turn off multiple settings all at once (ie - posix acls, posix locks, posix paths, symlink support - and retrieving uids/gids/mode from the server) or to - work around a bug in server which implement the Unix - Extensions. - nobrl Do not send byte range lock requests to the server. - This is necessary for certain applications that break - with cifs style mandatory byte range locks (and most - cifs servers do not yet support requesting advisory - byte range locks). - forcemandatorylock Even if the server supports posix (advisory) byte range - locking, send only mandatory lock requests. For some - (presumably rare) applications, originally coded for - DOS/Windows, which require Windows style mandatory byte range - locking, they may be able to take advantage of this option, - forcing the cifs client to only send mandatory locks - even if the cifs server would support posix advisory locks. - "forcemand" is accepted as a shorter form of this mount - option. - nostrictsync If this mount option is set, when an application does an - fsync call then the cifs client does not send an SMB Flush - to the server (to force the server to write all dirty data - for this file immediately to disk), although cifs still sends - all dirty (cached) file data to the server and waits for the - server to respond to the write. Since SMB Flush can be - very slow, and some servers may be reliable enough (to risk - delaying slightly flushing the data to disk on the server), - turning on this option may be useful to improve performance for - applications that fsync too much, at a small risk of server - crash. If this mount option is not set, by default cifs will - send an SMB flush request (and wait for a response) on every - fsync call. - nodfs Disable DFS (global name space support) even if the - server claims to support it. This can help work around - a problem with parsing of DFS paths with Samba server - versions 3.0.24 and 3.0.25. - remount remount the share (often used to change from ro to rw mounts - or vice versa) - cifsacl Report mode bits (e.g. on stat) based on the Windows ACL for - the file. (EXPERIMENTAL) - servern Specify the server 's netbios name (RFC1001 name) to use - when attempting to setup a session to the server. - This is needed for mounting to some older servers (such - as OS/2 or Windows 98 and Windows ME) since they do not - support a default server name. A server name can be up - to 15 characters long and is usually uppercased. - sfu When the CIFS Unix Extensions are not negotiated, attempt to - create device files and fifos in a format compatible with - Services for Unix (SFU). In addition retrieve bits 10-12 - of the mode via the SETFILEBITS extended attribute (as - SFU does). In the future the bottom 9 bits of the - mode also will be emulated using queries of the security - descriptor (ACL). - mfsymlinks Enable support for Minshall+French symlinks - (see http://wiki.samba.org/index.php/UNIX_Extensions#Minshall.2BFrench_symlinks) - This option is ignored when specified together with the - 'sfu' option. Minshall+French symlinks are used even if - the server supports the CIFS Unix Extensions. - sign Must use packet signing (helps avoid unwanted data modification - by intermediate systems in the route). Note that signing - does not work with lanman or plaintext authentication. - seal Must seal (encrypt) all data on this mounted share before - sending on the network. Requires support for Unix Extensions. - Note that this differs from the sign mount option in that it - causes encryption of data sent over this mounted share but other - shares mounted to the same server are unaffected. - locallease This option is rarely needed. Fcntl F_SETLEASE is - used by some applications such as Samba and NFSv4 server to - check to see whether a file is cacheable. CIFS has no way - to explicitly request a lease, but can check whether a file - is cacheable (oplocked). Unfortunately, even if a file - is not oplocked, it could still be cacheable (ie cifs client - could grant fcntl leases if no other local processes are using - the file) for cases for example such as when the server does not - support oplocks and the user is sure that the only updates to - the file will be from this client. Specifying this mount option - will allow the cifs client to check for leases (only) locally - for files which are not oplocked instead of denying leases - in that case. (EXPERIMENTAL) - sec Security mode. Allowed values are: - none attempt to connection as a null user (no name) - krb5 Use Kerberos version 5 authentication - krb5i Use Kerberos authentication and packet signing - ntlm Use NTLM password hashing (default) - ntlmi Use NTLM password hashing with signing (if - /proc/fs/cifs/PacketSigningEnabled on or if - server requires signing also can be the default) - ntlmv2 Use NTLMv2 password hashing - ntlmv2i Use NTLMv2 password hashing with packet signing - lanman (if configured in kernel config) use older - lanman hash -hard Retry file operations if server is not responding -soft Limit retries to unresponsive servers (usually only - one retry) before returning an error. (default) - -The mount.cifs mount helper also accepts a few mount options before -o -including: - - -S take password from stdin (equivalent to setting the environment - variable "PASSWD_FD=0" - -V print mount.cifs version - -? display simple usage information - -With most 2.6 kernel versions of modutils, the version of the cifs kernel -module can be displayed via modinfo. - -Misc /proc/fs/cifs Flags and Debug Info -======================================= -Informational pseudo-files: -DebugData Displays information about active CIFS sessions and - shares, features enabled as well as the cifs.ko - version. -Stats Lists summary resource usage information as well as per - share statistics, if CONFIG_CIFS_STATS in enabled - in the kernel configuration. - -Configuration pseudo-files: -PacketSigningEnabled If set to one, cifs packet signing is enabled - and will be used if the server requires - it. If set to two, cifs packet signing is - required even if the server considers packet - signing optional. (default 1) -SecurityFlags Flags which control security negotiation and - also packet signing. Authentication (may/must) - flags (e.g. for NTLM and/or NTLMv2) may be combined with - the signing flags. Specifying two different password - hashing mechanisms (as "must use") on the other hand - does not make much sense. Default flags are - 0x07007 - (NTLM, NTLMv2 and packet signing allowed). The maximum - allowable flags if you want to allow mounts to servers - using weaker password hashes is 0x37037 (lanman, - plaintext, ntlm, ntlmv2, signing allowed). Some - SecurityFlags require the corresponding menuconfig - options to be enabled (lanman and plaintext require - CONFIG_CIFS_WEAK_PW_HASH for example). Enabling - plaintext authentication currently requires also - enabling lanman authentication in the security flags - because the cifs module only supports sending - laintext passwords using the older lanman dialect - form of the session setup SMB. (e.g. for authentication - using plain text passwords, set the SecurityFlags - to 0x30030): - - may use packet signing 0x00001 - must use packet signing 0x01001 - may use NTLM (most common password hash) 0x00002 - must use NTLM 0x02002 - may use NTLMv2 0x00004 - must use NTLMv2 0x04004 - may use Kerberos security 0x00008 - must use Kerberos 0x08008 - may use lanman (weak) password hash 0x00010 - must use lanman password hash 0x10010 - may use plaintext passwords 0x00020 - must use plaintext passwords 0x20020 - (reserved for future packet encryption) 0x00040 - -cifsFYI If set to non-zero value, additional debug information - will be logged to the system error log. This field - contains three flags controlling different classes of - debugging entries. The maximum value it can be set - to is 7 which enables all debugging points (default 0). - Some debugging statements are not compiled into the - cifs kernel unless CONFIG_CIFS_DEBUG2 is enabled in the - kernel configuration. cifsFYI may be set to one or - nore of the following flags (7 sets them all): - - log cifs informational messages 0x01 - log return codes from cifs entry points 0x02 - log slow responses (ie which take longer than 1 second) - CONFIG_CIFS_STATS2 must be enabled in .config 0x04 - - -traceSMB If set to one, debug information is logged to the - system error log with the start of smb requests - and responses (default 0) -LookupCacheEnable If set to one, inode information is kept cached - for one second improving performance of lookups - (default 1) -OplockEnabled If set to one, safe distributed caching enabled. - (default 1) -LinuxExtensionsEnabled If set to one then the client will attempt to - use the CIFS "UNIX" extensions which are optional - protocol enhancements that allow CIFS servers - to return accurate UID/GID information as well - as support symbolic links. If you use servers - such as Samba that support the CIFS Unix - extensions but do not want to use symbolic link - support and want to map the uid and gid fields - to values supplied at mount (rather than the - actual values, then set this to zero. (default 1) - -These experimental features and tracing can be enabled by changing flags in -/proc/fs/cifs (after the cifs module has been installed or built into the -kernel, e.g. insmod cifs). To enable a feature set it to 1 e.g. to enable -tracing to the kernel message log type: - - echo 7 > /proc/fs/cifs/cifsFYI - -cifsFYI functions as a bit mask. Setting it to 1 enables additional kernel -logging of various informational messages. 2 enables logging of non-zero -SMB return codes while 4 enables logging of requests that take longer -than one second to complete (except for byte range lock requests). -Setting it to 4 requires defining CONFIG_CIFS_STATS2 manually in the -source code (typically by setting it in the beginning of cifsglob.h), -and setting it to seven enables all three. Finally, tracing -the start of smb requests and responses can be enabled via: - - echo 1 > /proc/fs/cifs/traceSMB - -Per share (per client mount) statistics are available in /proc/fs/cifs/Stats -if the kernel was configured with cifs statistics enabled. The statistics -represent the number of successful (ie non-zero return code from the server) -SMB responses to some of the more common commands (open, delete, mkdir etc.). -Also recorded is the total bytes read and bytes written to the server for -that share. Note that due to client caching effects this can be less than the -number of bytes read and written by the application running on the client. -The statistics for the number of total SMBs and oplock breaks are different in -that they represent all for that share, not just those for which the server -returned success. - -Also note that "cat /proc/fs/cifs/DebugData" will display information about -the active sessions and the shares that are mounted. - -Enabling Kerberos (extended security) works but requires version 1.2 or later -of the helper program cifs.upcall to be present and to be configured in the -/etc/request-key.conf file. The cifs.upcall helper program is from the Samba -project(http://www.samba.org). NTLM and NTLMv2 and LANMAN support do not -require this helper. Note that NTLMv2 security (which does not require the -cifs.upcall helper program), instead of using Kerberos, is sufficient for -some use cases. - -DFS support allows transparent redirection to shares in an MS-DFS name space. -In addition, DFS support for target shares which are specified as UNC -names which begin with host names (rather than IP addresses) requires -a user space helper (such as cifs.upcall) to be present in order to -translate host names to ip address, and the user space helper must also -be configured in the file /etc/request-key.conf. Samba, Windows servers and -many NAS appliances support DFS as a way of constructing a global name -space to ease network configuration and improve reliability. - -To use cifs Kerberos and DFS support, the Linux keyutils package should be -installed and something like the following lines should be added to the -/etc/request-key.conf file: - -create cifs.spnego * * /usr/local/sbin/cifs.upcall %k -create dns_resolver * * /usr/local/sbin/cifs.upcall %k - -CIFS kernel module parameters -============================= -These module parameters can be specified or modified either during the time of -module loading or during the runtime by using the interface - /proc/module/cifs/parameters/<param> - -i.e. echo "value" > /sys/module/cifs/parameters/<param> - -1. enable_oplocks - Enable or disable oplocks. Oplocks are enabled by default. - [Y/y/1]. To disable use any of [N/n/0]. - diff --git a/fs/cifs/TODO b/fs/cifs/TODO deleted file mode 100644 index 355abcdc..0000000 --- a/fs/cifs/TODO +++ /dev/null @@ -1,129 +0,0 @@ -Version 1.53 May 20, 2008 - -A Partial List of Missing Features -================================== - -Contributions are welcome. There are plenty of opportunities -for visible, important contributions to this module. Here -is a partial list of the known problems and missing features: - -a) Support for SecurityDescriptors(Windows/CIFS ACLs) for chmod/chgrp/chown -so that these operations can be supported to Windows servers - -b) Mapping POSIX ACLs (and eventually NFSv4 ACLs) to CIFS -SecurityDescriptors - -c) Better pam/winbind integration (e.g. to handle uid mapping -better) - -d) Cleanup now unneeded SessSetup code in -fs/cifs/connect.c and add back in NTLMSSP code if any servers -need it - -e) fix NTLMv2 signing when two mounts with different users to same -server. - -f) Directory entry caching relies on a 1 second timer, rather than -using FindNotify or equivalent. - (started) - -g) quota support (needs minor kernel change since quota calls -to make it to network filesystems or deviceless filesystems) - -h) investigate sync behavior (including syncpage) and check -for proper behavior of intr/nointr - -i) improve support for very old servers (OS/2 and Win9x for example) -Including support for changing the time remotely (utimes command). - -j) hook lower into the sockets api (as NFS/SunRPC does) to avoid the -extra copy in/out of the socket buffers in some cases. - -k) Better optimize open (and pathbased setfilesize) to reduce the -oplock breaks coming from windows srv. Piggyback identical file -opens on top of each other by incrementing reference count rather -than resending (helps reduce server resource utilization and avoid -spurious oplock breaks). - -l) Improve performance of readpages by sending more than one read -at a time when 8 pages or more are requested. In conjuntion -add support for async_cifs_readpages. - -m) Add support for storing symlink info to Windows servers -in the Extended Attribute format their SFU clients would recognize. - -n) Finish fcntl D_NOTIFY support so kde and gnome file list windows -will autorefresh (partially complete by Asser). Needs minor kernel -vfs change to support removing D_NOTIFY on a file. - -o) Add GUI tool to configure /proc/fs/cifs settings and for display of -the CIFS statistics (started) - -p) implement support for security and trusted categories of xattrs -(requires minor protocol extension) to enable better support for SELINUX - -q) Implement O_DIRECT flag on open (already supported on mount) - -r) Create UID mapping facility so server UIDs can be mapped on a per -mount or a per server basis to client UIDs or nobody if no mapping -exists. This is helpful when Unix extensions are negotiated to -allow better permission checking when UIDs differ on the server -and client. Add new protocol request to the CIFS protocol -standard for asking the server for the corresponding name of a -particular uid. - -s) Add support for CIFS Unix and also the newer POSIX extensions to the -server side for Samba 4. - -t) In support for OS/2 (LANMAN 1.2 and LANMAN2.1 based SMB servers) -need to add ability to set time to server (utimes command) - -u) DOS attrs - returned as pseudo-xattr in Samba format (check VFAT and NTFS for this too) - -v) mount check for unmatched uids - -w) Add support for new vfs entry point for fallocate - -x) Fix Samba 3 server to handle Linux kernel aio so dbench with lots of -processes can proceed better in parallel (on the server) - -y) Fix Samba 3 to handle reads/writes over 127K (and remove the cifs mount -restriction of wsize max being 127K) - -KNOWN BUGS (updated April 24, 2007) -==================================== -See http://bugzilla.samba.org - search on product "CifsVFS" for -current bug list. - -1) existing symbolic links (Windows reparse points) are recognized but -can not be created remotely. They are implemented for Samba and those that -support the CIFS Unix extensions, although earlier versions of Samba -overly restrict the pathnames. -2) follow_link and readdir code does not follow dfs junctions -but recognizes them -3) create of new files to FAT partitions on Windows servers can -succeed but still return access denied (appears to be Windows -server not cifs client problem) and has not been reproduced recently. -NTFS partitions do not have this problem. -4) Unix/POSIX capabilities are reset after reconnection, and affect -a few fields in the tree connection but we do do not know which -superblocks to apply these changes to. We should probably walk -the list of superblocks to set these. Also need to check the -flags on the second mount to the same share, and see if we -can do the same trick that NFS does to remount duplicate shares. - -Misc testing to do -================== -1) check out max path names and max path name components against various server -types. Try nested symlinks (8 deep). Return max path name in stat -f information - -2) Modify file portion of ltp so it can run against a mounted network -share and run it against cifs vfs in automated fashion. - -3) Additional performance testing and optimization using iozone and similar - -there are some easy changes that can be done to parallelize sequential writes, -and when signing is disabled to request larger read sizes (larger than -negotiated size) and send larger write sizes to modern servers. - -4) More exhaustively test against less common servers. More testing -against Windows 9x, Windows ME servers. - diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index fe8d627..d8eac3b 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -91,6 +91,8 @@ extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen, #endif /* CONFIG_CIFS_SMB2 */ #endif +wchar_t cifs_toupper(wchar_t in); + /* * UniStrcat: Concatenate the second string to the first * diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 45e57cc..fc6f4f3 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -43,17 +43,18 @@ cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server) server->secmech.md5 = crypto_alloc_shash("md5", 0, 0); if (IS_ERR(server->secmech.md5)) { cifs_dbg(VFS, "could not allocate crypto md5\n"); - return PTR_ERR(server->secmech.md5); + rc = PTR_ERR(server->secmech.md5); + server->secmech.md5 = NULL; + return rc; } size = sizeof(struct shash_desc) + crypto_shash_descsize(server->secmech.md5); server->secmech.sdescmd5 = kmalloc(size, GFP_KERNEL); if (!server->secmech.sdescmd5) { - rc = -ENOMEM; crypto_free_shash(server->secmech.md5); server->secmech.md5 = NULL; - return rc; + return -ENOMEM; } server->secmech.sdescmd5->shash.tfm = server->secmech.md5; server->secmech.sdescmd5->shash.flags = 0x0; @@ -421,7 +422,7 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) if (blobptr + attrsize > blobend) break; if (type == NTLMSSP_AV_NB_DOMAIN_NAME) { - if (!attrsize) + if (!attrsize || attrsize >= CIFS_MAX_DOMAINNAME_LEN) break; if (!ses->domainName) { ses->domainName = @@ -591,6 +592,7 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) static int crypto_hmacmd5_alloc(struct TCP_Server_Info *server) { + int rc; unsigned int size; /* check if already allocated */ @@ -600,7 +602,9 @@ static int crypto_hmacmd5_alloc(struct TCP_Server_Info *server) server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0); if (IS_ERR(server->secmech.hmacmd5)) { cifs_dbg(VFS, "could not allocate crypto hmacmd5\n"); - return PTR_ERR(server->secmech.hmacmd5); + rc = PTR_ERR(server->secmech.hmacmd5); + server->secmech.hmacmd5 = NULL; + return rc; } size = sizeof(struct shash_desc) + diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 4bdd547..a16b4e5 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -147,18 +147,17 @@ cifs_read_super(struct super_block *sb) goto out_no_root; } + if (cifs_sb_master_tcon(cifs_sb)->nocase) + sb->s_d_op = &cifs_ci_dentry_ops; + else + sb->s_d_op = &cifs_dentry_ops; + sb->s_root = d_make_root(inode); if (!sb->s_root) { rc = -ENOMEM; goto out_no_root; } - /* do that *after* d_make_root() - we want NULL ->d_op for root here */ - if (cifs_sb_master_tcon(cifs_sb)->nocase) - sb->s_d_op = &cifs_ci_dentry_ops; - else - sb->s_d_op = &cifs_dentry_ops; - #ifdef CONFIG_CIFS_NFSD_EXPORT if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { cifs_dbg(FYI, "export ops supported\n"); @@ -256,6 +255,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->server_eof = 0; cifs_inode->uniqueid = 0; cifs_inode->createtime = 0; + cifs_inode->epoch = 0; #ifdef CONFIG_CIFS_SMB2 get_random_bytes(cifs_inode->lease_key, SMB2_LEASE_KEY_SIZE); #endif @@ -358,6 +358,18 @@ cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb) seq_printf(s, "loose"); } +static void +cifs_show_nls(struct seq_file *s, struct nls_table *cur) +{ + struct nls_table *def; + + /* Display iocharset= option if it's not default charset */ + def = load_nls_default(); + if (def != cur) + seq_printf(s, ",iocharset=%s", cur->charset); + unload_nls(def); +} + /* * cifs_show_options() is for displaying mount options in /proc/mounts. * Not all settable options are displayed but most of the important @@ -419,6 +431,9 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",file_mode=0%ho,dir_mode=0%ho", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); + + cifs_show_nls(s, cifs_sb->local_nls); + if (tcon->seal) seq_printf(s, ",seal"); if (tcon->nocase) @@ -719,7 +734,7 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, written = generic_file_aio_write(iocb, iov, nr_segs, pos); - if (CIFS_I(inode)->clientCanCacheAll) + if (CIFS_CACHE_WRITE(CIFS_I(inode))) return written; rc = filemap_fdatawrite(inode->i_mapping); @@ -744,7 +759,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) * We need to be sure that all dirty pages are written and the * server has the newest file length. */ - if (!CIFS_I(inode)->clientCanCacheRead && inode->i_mapping && + if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping && inode->i_mapping->nrpages != 0) { rc = filemap_fdatawait(inode->i_mapping); if (rc) { @@ -768,8 +783,10 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) { - /* note that this is called by vfs setlease with i_lock held - to protect *lease from going away */ + /* + * Note that this is called by vfs setlease with i_lock held to + * protect *lease from going away. + */ struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; @@ -777,20 +794,19 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) return -EINVAL; /* check if file is oplocked */ - if (((arg == F_RDLCK) && - (CIFS_I(inode)->clientCanCacheRead)) || - ((arg == F_WRLCK) && - (CIFS_I(inode)->clientCanCacheAll))) + if (((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) || + ((arg == F_WRLCK) && CIFS_CACHE_WRITE(CIFS_I(inode)))) return generic_setlease(file, arg, lease); else if (tlink_tcon(cfile->tlink)->local_lease && - !CIFS_I(inode)->clientCanCacheRead) - /* If the server claims to support oplock on this - file, then we still need to check oplock even - if the local_lease mount option is set, but there - are servers which do not support oplock for which - this mount option may be useful if the user - knows that the file won't be changed on the server - by anyone else */ + !CIFS_CACHE_READ(CIFS_I(inode))) + /* + * If the server claims to support oplock on this file, then we + * still need to check oplock even if the local_lease mount + * option is set, but there are servers which do not support + * oplock for which this mount option may be useful if the user + * knows that the file won't be changed on the server by anyone + * else. + */ return generic_setlease(file, arg, lease); else return -EAGAIN; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 1fdc370..cfa14c8 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -28,6 +28,7 @@ #include "cifsacl.h" #include <crypto/internal/hash.h> #include <linux/scatterlist.h> +#include <uapi/linux/cifs/cifs_mount.h> #ifdef CONFIG_CIFS_SMB2 #include "smb2pdu.h" #endif @@ -41,11 +42,7 @@ #define MAX_SES_INFO 2 #define MAX_TCON_INFO 4 -#define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1) -#define MAX_SERVER_SIZE 15 -#define MAX_SHARE_SIZE 80 -#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */ -#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */ +#define MAX_TREE_SIZE (2 + CIFS_NI_MAXHOST + 1 + CIFS_MAX_SHARE_LEN + 1) #define CIFS_MIN_RCV_POOL 4 @@ -134,6 +131,7 @@ struct cifs_secmech { /* per smb session structure/fields */ struct ntlmssp_auth { + bool sesskey_per_smbsess; /* whether session key is per smb session */ __u32 client_flags; /* sent by client in type 1 ntlmsssp exchange */ __u32 server_flags; /* sent by server in type 2 ntlmssp exchange */ unsigned char ciphertext[CIFS_CPHTXT_SIZE]; /* sent to server */ @@ -307,6 +305,9 @@ struct smb_version_operations { int (*create_hardlink)(const unsigned int, struct cifs_tcon *, const char *, const char *, struct cifs_sb_info *); + /* query symlink target */ + int (*query_symlink)(const unsigned int, struct cifs_tcon *, + const char *, char **, struct cifs_sb_info *); /* open a file for non-posix mounts */ int (*open)(const unsigned int, struct cifs_open_parms *, __u32 *, FILE_ALL_INFO *); @@ -360,15 +361,24 @@ struct smb_version_operations { /* push brlocks from the cache to the server */ int (*push_mand_locks)(struct cifsFileInfo *); /* get lease key of the inode */ - void (*get_lease_key)(struct inode *, struct cifs_fid *fid); + void (*get_lease_key)(struct inode *, struct cifs_fid *); /* set lease key of the inode */ - void (*set_lease_key)(struct inode *, struct cifs_fid *fid); + void (*set_lease_key)(struct inode *, struct cifs_fid *); /* generate new lease key */ - void (*new_lease_key)(struct cifs_fid *fid); - /* The next two functions will need to be changed to per smb session */ - void (*generate_signingkey)(struct TCP_Server_Info *server); - int (*calc_signature)(struct smb_rqst *rqst, - struct TCP_Server_Info *server); + void (*new_lease_key)(struct cifs_fid *); + int (*generate_signingkey)(struct cifs_ses *); + int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *); + int (*query_mf_symlink)(const unsigned char *, char *, unsigned int *, + struct cifs_sb_info *, unsigned int); + /* if we can do cache read operations */ + bool (*is_read_op)(__u32); + /* set oplock level for the inode */ + void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int, + bool *); + /* create lease context buffer for CREATE request */ + char * (*create_lease_buf)(u8 *, u8); + /* parse lease context buffer and return oplock/epoch info */ + __u8 (*parse_lease_buf)(void *, unsigned int *); }; struct smb_version_values { @@ -386,9 +396,9 @@ struct smb_version_values { unsigned int cap_unix; unsigned int cap_nt_find; unsigned int cap_large_files; - unsigned int oplock_read; __u16 signing_enabled; __u16 signing_required; + size_t create_lease_size; }; #define HEADER_SIZE(server) (server->vals->header_size) @@ -544,7 +554,6 @@ struct TCP_Server_Info { int timeAdj; /* Adjust for difference in server time zone in sec */ __u64 CurrentMid; /* multiplex id - rotating counter */ char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlm, ntlmv2 etc */ - char smb3signingkey[SMB3_SIGN_KEY_SIZE]; /* for signing smb3 packets */ /* 16th byte of RFC1001 workstation name is always null */ char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; __u32 sequence_number; /* for signing, protected by srv_mutex */ @@ -727,6 +736,7 @@ struct cifs_ses { bool need_reconnect:1; /* connection reset, uid now invalid */ #ifdef CONFIG_CIFS_SMB2 __u16 session_flags; + char smb3signingkey[SMB3_SIGN_KEY_SIZE]; /* for signing smb3 packets */ #endif /* CONFIG_CIFS_SMB2 */ }; @@ -931,6 +941,8 @@ struct cifs_fid { __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */ #endif struct cifs_pending_open *pending_open; + unsigned int epoch; + bool purge_cache; }; struct cifs_fid_locks { @@ -1028,6 +1040,17 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); +#define CIFS_CACHE_READ_FLG 1 +#define CIFS_CACHE_HANDLE_FLG 2 +#define CIFS_CACHE_RH_FLG (CIFS_CACHE_READ_FLG | CIFS_CACHE_HANDLE_FLG) +#define CIFS_CACHE_WRITE_FLG 4 +#define CIFS_CACHE_RW_FLG (CIFS_CACHE_READ_FLG | CIFS_CACHE_WRITE_FLG) +#define CIFS_CACHE_RHW_FLG (CIFS_CACHE_RW_FLG | CIFS_CACHE_HANDLE_FLG) + +#define CIFS_CACHE_READ(cinode) (cinode->oplock & CIFS_CACHE_READ_FLG) +#define CIFS_CACHE_HANDLE(cinode) (cinode->oplock & CIFS_CACHE_HANDLE_FLG) +#define CIFS_CACHE_WRITE(cinode) (cinode->oplock & CIFS_CACHE_WRITE_FLG) + /* * One of these for each file inode */ @@ -1039,8 +1062,8 @@ struct cifsInodeInfo { /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; __u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */ - bool clientCanCacheRead; /* read oplock */ - bool clientCanCacheAll; /* read and writebehind oplock */ + unsigned int oplock; /* oplock/lease level we have */ + unsigned int epoch; /* used to track lease state changes */ bool delete_pending; /* DELETE_ON_CLOSE is set */ bool invalid_mapping; /* pagecache is invalid */ unsigned long time; /* jiffies of last update of inode */ @@ -1498,7 +1521,7 @@ extern mempool_t *cifs_mid_poolp; extern struct smb_version_operations smb1_operations; extern struct smb_version_values smb1_values; #define SMB20_VERSION_STRING "2.0" -/*extern struct smb_version_operations smb20_operations; */ /* not needed yet */ +extern struct smb_version_operations smb20_operations; extern struct smb_version_values smb20_values; #define SMB21_VERSION_STRING "2.1" extern struct smb_version_operations smb21_operations; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 11ca24a..948676d 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1495,11 +1495,12 @@ struct reparse_data { __u32 ReparseTag; __u16 ReparseDataLength; __u16 Reserved; - __u16 AltNameOffset; - __u16 AltNameLen; - __u16 TargetNameOffset; - __u16 TargetNameLen; - char LinkNamesBuf[1]; + __u16 SubstituteNameOffset; + __u16 SubstituteNameLength; + __u16 PrintNameOffset; + __u16 PrintNameLength; + __u32 Flags; + char PathBuffer[0]; } __attribute__((packed)); struct cifs_quota_data { diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f7e584d..b5ec2a2 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -357,13 +357,9 @@ extern int CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, char **syminfo, const struct nls_table *nls_codepage); -#ifdef CONFIG_CIFS_SYMLINK_EXPERIMENTAL -extern int CIFSSMBQueryReparseLinkInfo(const unsigned int xid, - struct cifs_tcon *tcon, - const unsigned char *searchName, - char *symlinkinfo, const int buflen, __u16 fid, - const struct nls_table *nls_codepage); -#endif /* temporarily unused until cifs_symlink fixed */ +extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, + __u16 fid, char **symlinkinfo, + const struct nls_table *nls_codepage); extern int CIFSSMBOpen(const unsigned int xid, struct cifs_tcon *tcon, const char *fileName, const int disposition, const int access_flags, const int omode, @@ -435,7 +431,7 @@ extern int setup_ntlm_response(struct cifs_ses *, const struct nls_table *); extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *); extern void cifs_crypto_shash_release(struct TCP_Server_Info *); extern int calc_seckey(struct cifs_ses *); -extern void generate_smb3signingkey(struct TCP_Server_Info *); +extern int generate_smb3signingkey(struct cifs_ses *); #ifdef CONFIG_CIFS_WEAK_PW_HASH extern int calc_lanman_hash(const char *password, const char *cryptkey, @@ -497,5 +493,7 @@ void cifs_writev_complete(struct work_struct *work); struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete); void cifs_writedata_release(struct kref *refcount); - +int open_query_close_cifs_symlink(const unsigned char *path, char *pbuf, + unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb, + unsigned int xid); #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a89c4cb..a3d74fe 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -3067,7 +3067,6 @@ querySymLinkRetry: return rc; } -#ifdef CONFIG_CIFS_SYMLINK_EXPERIMENTAL /* * Recent Windows versions now create symlinks more frequently * and they use the "reparse point" mechanism below. We can of course @@ -3079,18 +3078,22 @@ querySymLinkRetry: * it is not compiled in by default until callers fixed up and more tested. */ int -CIFSSMBQueryReparseLinkInfo(const unsigned int xid, struct cifs_tcon *tcon, - const unsigned char *searchName, - char *symlinkinfo, const int buflen, __u16 fid, - const struct nls_table *nls_codepage) +CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, + __u16 fid, char **symlinkinfo, + const struct nls_table *nls_codepage) { int rc = 0; int bytes_returned; struct smb_com_transaction_ioctl_req *pSMB; struct smb_com_transaction_ioctl_rsp *pSMBr; + bool is_unicode; + unsigned int sub_len; + char *sub_start; + struct reparse_data *reparse_buf; + __u32 data_offset, data_count; + char *end_of_smb; - cifs_dbg(FYI, "In Windows reparse style QueryLink for path %s\n", - searchName); + cifs_dbg(FYI, "In Windows reparse style QueryLink for fid %u\n", fid); rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB, (void **) &pSMBr); if (rc) @@ -3119,66 +3122,55 @@ CIFSSMBQueryReparseLinkInfo(const unsigned int xid, struct cifs_tcon *tcon, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { cifs_dbg(FYI, "Send error in QueryReparseLinkInfo = %d\n", rc); - } else { /* decode response */ - __u32 data_offset = le32_to_cpu(pSMBr->DataOffset); - __u32 data_count = le32_to_cpu(pSMBr->DataCount); - if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) { - /* BB also check enough total bytes returned */ - rc = -EIO; /* bad smb */ - goto qreparse_out; - } - if (data_count && (data_count < 2048)) { - char *end_of_smb = 2 /* sizeof byte count */ + - get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount; - - struct reparse_data *reparse_buf = - (struct reparse_data *) - ((char *)&pSMBr->hdr.Protocol - + data_offset); - if ((char *)reparse_buf >= end_of_smb) { - rc = -EIO; - goto qreparse_out; - } - if ((reparse_buf->LinkNamesBuf + - reparse_buf->TargetNameOffset + - reparse_buf->TargetNameLen) > end_of_smb) { - cifs_dbg(FYI, "reparse buf beyond SMB\n"); - rc = -EIO; - goto qreparse_out; - } + goto qreparse_out; + } - if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) { - cifs_from_ucs2(symlinkinfo, (__le16 *) - (reparse_buf->LinkNamesBuf + - reparse_buf->TargetNameOffset), - buflen, - reparse_buf->TargetNameLen, - nls_codepage, 0); - } else { /* ASCII names */ - strncpy(symlinkinfo, - reparse_buf->LinkNamesBuf + - reparse_buf->TargetNameOffset, - min_t(const int, buflen, - reparse_buf->TargetNameLen)); - } - } else { - rc = -EIO; - cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n"); - } - symlinkinfo[buflen] = 0; /* just in case so the caller - does not go off the end of the buffer */ - cifs_dbg(FYI, "readlink result - %s\n", symlinkinfo); + data_offset = le32_to_cpu(pSMBr->DataOffset); + data_count = le32_to_cpu(pSMBr->DataCount); + if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) { + /* BB also check enough total bytes returned */ + rc = -EIO; /* bad smb */ + goto qreparse_out; + } + if (!data_count || (data_count > 2048)) { + rc = -EIO; + cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n"); + goto qreparse_out; + } + end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount; + reparse_buf = (struct reparse_data *) + ((char *)&pSMBr->hdr.Protocol + data_offset); + if ((char *)reparse_buf >= end_of_smb) { + rc = -EIO; + goto qreparse_out; } + if ((reparse_buf->PathBuffer + reparse_buf->PrintNameOffset + + reparse_buf->PrintNameLength) > end_of_smb) { + cifs_dbg(FYI, "reparse buf beyond SMB\n"); + rc = -EIO; + goto qreparse_out; + } + sub_start = reparse_buf->SubstituteNameOffset + reparse_buf->PathBuffer; + sub_len = reparse_buf->SubstituteNameLength; + if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) + is_unicode = true; + else + is_unicode = false; + /* BB FIXME investigate remapping reserved chars here */ + *symlinkinfo = cifs_strndup_from_utf16(sub_start, sub_len, is_unicode, + nls_codepage); + if (!*symlinkinfo) + rc = -ENOMEM; qreparse_out: cifs_buf_release(pSMB); - /* Note: On -EAGAIN error only caller can retry on handle based calls - since file handle passed in no longer valid */ - + /* + * Note: On -EAGAIN error only caller can retry on handle based calls + * since file handle passed in no longer valid. + */ return rc; } -#endif /* CIFS_SYMLINK_EXPERIMENTAL */ /* BB temporarily unused */ #ifdef CONFIG_CIFS_POSIX diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index fa68813..a279ffc 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -379,6 +379,7 @@ cifs_reconnect(struct TCP_Server_Info *server) try_to_freeze(); /* we should try only the port we connected to before */ + mutex_lock(&server->srv_mutex); rc = generic_ip_connect(server); if (rc) { cifs_dbg(FYI, "reconnect error %d\n", rc); @@ -390,6 +391,7 @@ cifs_reconnect(struct TCP_Server_Info *server) server->tcpStatus = CifsNeedNegotiate; spin_unlock(&GlobalMid_Lock); } + mutex_unlock(&server->srv_mutex); } while (server->tcpStatus == CifsNeedReconnect); return rc; @@ -1114,7 +1116,7 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol) break; #ifdef CONFIG_CIFS_SMB2 case Smb_20: - vol->ops = &smb21_operations; /* currently identical with 2.1 */ + vol->ops = &smb20_operations; vol->vals = &smb20_values; break; case Smb_21: @@ -1575,8 +1577,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (string == NULL) goto out_nomem; - if (strnlen(string, MAX_USERNAME_SIZE) > - MAX_USERNAME_SIZE) { + if (strnlen(string, CIFS_MAX_USERNAME_LEN) > + CIFS_MAX_USERNAME_LEN) { printk(KERN_WARNING "CIFS: username too long\n"); goto cifs_parse_mount_err; } @@ -1675,7 +1677,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (string == NULL) goto out_nomem; - if (strnlen(string, 256) == 256) { + if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN) + == CIFS_MAX_DOMAINNAME_LEN) { printk(KERN_WARNING "CIFS: domain name too" " long\n"); goto cifs_parse_mount_err; @@ -2220,13 +2223,13 @@ static int match_session(struct cifs_ses *ses, struct smb_vol *vol) /* anything else takes username/password */ if (strncmp(ses->user_name, vol->username ? vol->username : "", - MAX_USERNAME_SIZE)) + CIFS_MAX_USERNAME_LEN)) return 0; if (strlen(vol->username) != 0 && ses->password != NULL && strncmp(ses->password, vol->password ? vol->password : "", - MAX_PASSWORD_SIZE)) + CIFS_MAX_PASSWORD_LEN)) return 0; } return 1; @@ -2276,8 +2279,8 @@ cifs_put_smb_ses(struct cifs_ses *ses) #ifdef CONFIG_KEYS -/* strlen("cifs:a:") + INET6_ADDRSTRLEN + 1 */ -#define CIFSCREDS_DESC_SIZE (7 + INET6_ADDRSTRLEN + 1) +/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */ +#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1) /* Populate username and pw fields from keyring if possible */ static int @@ -2351,7 +2354,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) } len = delim - payload; - if (len > MAX_USERNAME_SIZE || len <= 0) { + if (len > CIFS_MAX_USERNAME_LEN || len <= 0) { cifs_dbg(FYI, "Bad value from username search (len=%zd)\n", len); rc = -EINVAL; @@ -2368,7 +2371,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) cifs_dbg(FYI, "%s: username=%s\n", __func__, vol->username); len = key->datalen - (len + 1); - if (len > MAX_PASSWORD_SIZE || len <= 0) { + if (len > CIFS_MAX_PASSWORD_LEN || len <= 0) { cifs_dbg(FYI, "Bad len for password search (len=%zd)\n", len); rc = -EINVAL; kfree(vol->username); @@ -3825,33 +3828,8 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (server->ops->sess_setup) rc = server->ops->sess_setup(xid, ses, nls_info); - if (rc) { + if (rc) cifs_dbg(VFS, "Send error in SessSetup = %d\n", rc); - } else { - mutex_lock(&server->srv_mutex); - if (!server->session_estab) { - server->session_key.response = ses->auth_key.response; - server->session_key.len = ses->auth_key.len; - server->sequence_number = 0x2; - server->session_estab = true; - ses->auth_key.response = NULL; - if (server->ops->generate_signingkey) - server->ops->generate_signingkey(server); - } - mutex_unlock(&server->srv_mutex); - - cifs_dbg(FYI, "CIFS Session Established successfully\n"); - spin_lock(&GlobalMid_Lock); - ses->status = CifsGood; - ses->need_reconnect = false; - spin_unlock(&GlobalMid_Lock); - } - - kfree(ses->auth_key.response); - ses->auth_key.response = NULL; - ses->auth_key.len = 0; - kfree(ses->ntlmssp); - ses->ntlmssp = NULL; return rc; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index d62ce0d..d3e2eaa 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -32,6 +32,7 @@ #include "cifsproto.h" #include "cifs_debug.h" #include "cifs_fs_sb.h" +#include "cifs_unicode.h" static void renew_parental_timestamps(struct dentry *direntry) @@ -834,12 +835,17 @@ static int cifs_ci_hash(const struct dentry *dentry, struct qstr *q) { struct nls_table *codepage = CIFS_SB(dentry->d_sb)->local_nls; unsigned long hash; - int i; + wchar_t c; + int i, charlen; hash = init_name_hash(); - for (i = 0; i < q->len; i++) - hash = partial_name_hash(nls_tolower(codepage, q->name[i]), - hash); + for (i = 0; i < q->len; i += charlen) { + charlen = codepage->char2uni(&q->name[i], q->len - i, &c); + /* error out if we can't convert the character */ + if (unlikely(charlen < 0)) + return charlen; + hash = partial_name_hash(cifs_toupper(c), hash); + } q->hash = end_name_hash(hash); return 0; @@ -849,11 +855,47 @@ static int cifs_ci_compare(const struct dentry *parent, const struct dentry *den unsigned int len, const char *str, const struct qstr *name) { struct nls_table *codepage = CIFS_SB(parent->d_sb)->local_nls; + wchar_t c1, c2; + int i, l1, l2; - if ((name->len == len) && - (nls_strnicmp(codepage, name->name, str, len) == 0)) - return 0; - return 1; + /* + * We make the assumption here that uppercase characters in the local + * codepage are always the same length as their lowercase counterparts. + * + * If that's ever not the case, then this will fail to match it. + */ + if (name->len != len) + return 1; + + for (i = 0; i < len; i += l1) { + /* Convert characters in both strings to UTF-16. */ + l1 = codepage->char2uni(&str[i], len - i, &c1); + l2 = codepage->char2uni(&name->name[i], name->len - i, &c2); + + /* + * If we can't convert either character, just declare it to + * be 1 byte long and compare the original byte. + */ + if (unlikely(l1 < 0 && l2 < 0)) { + if (str[i] != name->name[i]) + return 1; + l1 = 1; + continue; + } + + /* + * Here, we again ass|u|me that upper/lowercase versions of + * a character are the same length in the local NLS. + */ + if (l1 != l2) + return 1; + + /* Now compare uppercase versions of these characters */ + if (cifs_toupper(c1) != cifs_toupper(c2)) + return 1; + } + + return 0; } const struct dentry_operations cifs_ci_dentry_ops = { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 1e57f36..d044b35 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -313,8 +313,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, * If the server returned a read oplock and we have mandatory brlocks, * set oplock level to None. */ - if (oplock == server->vals->oplock_read && - cifs_has_mand_locks(cinode)) { + if (server->ops->is_read_op(oplock) && cifs_has_mand_locks(cinode)) { cifs_dbg(FYI, "Reset oplock val from read to None due to mand locks\n"); oplock = 0; } @@ -324,6 +323,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, oplock = fid->pending_open->oplock; list_del(&fid->pending_open->olist); + fid->purge_cache = false; server->ops->set_fid(cfile, fid, oplock); list_add(&cfile->tlist, &tcon->openFileList); @@ -334,6 +334,9 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, list_add_tail(&cfile->flist, &cinode->openFileList); spin_unlock(&cifs_file_list_lock); + if (fid->purge_cache) + cifs_invalidate_mapping(inode); + file->private_data = cfile; return cfile; } @@ -647,6 +650,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) oflags, &oplock, &cfile->fid.netfid, xid); if (rc == 0) { cifs_dbg(FYI, "posix reopen succeeded\n"); + oparms.reconnect = true; goto reopen_success; } /* @@ -1523,12 +1527,12 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, * read won't conflict with non-overlapted locks due to * pagereading. */ - if (!CIFS_I(inode)->clientCanCacheAll && - CIFS_I(inode)->clientCanCacheRead) { + if (!CIFS_CACHE_WRITE(CIFS_I(inode)) && + CIFS_CACHE_READ(CIFS_I(inode))) { cifs_invalidate_mapping(inode); cifs_dbg(FYI, "Set no oplock for inode=%p due to mand locks\n", inode); - CIFS_I(inode)->clientCanCacheRead = false; + CIFS_I(inode)->oplock = 0; } rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length, @@ -2212,7 +2216,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, cifs_dbg(FYI, "Sync file - name: %s datasync: 0x%x\n", file->f_path.dentry->d_name.name, datasync); - if (!CIFS_I(inode)->clientCanCacheRead) { + if (!CIFS_CACHE_READ(CIFS_I(inode))) { rc = cifs_invalidate_mapping(inode); if (rc) { cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc); @@ -2552,7 +2556,7 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, mutex_unlock(&inode->i_mutex); } - if (rc > 0 || rc == -EIOCBQUEUED) { + if (rc > 0) { ssize_t err; err = generic_write_sync(file, pos, rc); @@ -2576,7 +2580,7 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); ssize_t written; - if (cinode->clientCanCacheAll) { + if (CIFS_CACHE_WRITE(cinode)) { if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) @@ -2590,7 +2594,7 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, * these pages but not on the region from pos to ppos+len-1. */ written = cifs_user_writev(iocb, iov, nr_segs, pos); - if (written > 0 && cinode->clientCanCacheRead) { + if (written > 0 && CIFS_CACHE_READ(cinode)) { /* * Windows 7 server can delay breaking level2 oplock if a write * request comes - break it on the client to prevent reading @@ -2599,7 +2603,7 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, cifs_invalidate_mapping(inode); cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n", inode); - cinode->clientCanCacheRead = false; + cinode->oplock = 0; } return written; } @@ -2956,7 +2960,7 @@ cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov, * on pages affected by this read but not on the region from pos to * pos+len-1. */ - if (!cinode->clientCanCacheRead) + if (!CIFS_CACHE_READ(cinode)) return cifs_user_readv(iocb, iov, nr_segs, pos); if (cap_unix(tcon->ses) && @@ -3092,7 +3096,7 @@ int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) xid = get_xid(); - if (!CIFS_I(inode)->clientCanCacheRead) { + if (!CIFS_CACHE_READ(CIFS_I(inode))) { rc = cifs_invalidate_mapping(inode); if (rc) return rc; @@ -3525,7 +3529,7 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping, * is, when the page lies beyond the EOF, or straddles the EOF * and the write will cover all of the existing data. */ - if (CIFS_I(mapping->host)->clientCanCacheRead) { + if (CIFS_CACHE_READ(CIFS_I(mapping->host))) { i_size = i_size_read(mapping->host); if (page_start >= i_size || (offset == 0 && (pos + len) >= i_size)) { @@ -3608,20 +3612,20 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; - if (!cinode->clientCanCacheAll && cinode->clientCanCacheRead && + if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) && cifs_has_mand_locks(cinode)) { cifs_dbg(FYI, "Reset oplock to None for inode=%p due to mand locks\n", inode); - cinode->clientCanCacheRead = false; + cinode->oplock = 0; } if (inode && S_ISREG(inode->i_mode)) { - if (cinode->clientCanCacheRead) + if (CIFS_CACHE_READ(cinode)) break_lease(inode, O_RDONLY); else break_lease(inode, O_WRONLY); rc = filemap_fdatawrite(inode->i_mapping); - if (cinode->clientCanCacheRead == 0) { + if (!CIFS_CACHE_READ(cinode)) { rc = filemap_fdatawait(inode->i_mapping); mapping_set_error(inode->i_mapping, rc); cifs_invalidate_mapping(inode); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 449b6cf..f9ff9c1 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -101,7 +101,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) } /* don't bother with revalidation if we have an oplock */ - if (cifs_i->clientCanCacheRead) { + if (CIFS_CACHE_READ(cifs_i)) { cifs_dbg(FYI, "%s: inode %llu is oplocked\n", __func__, cifs_i->uniqueid); return; @@ -549,6 +549,10 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, * when Unix extensions are disabled - fake it. */ fattr->cf_nlink = 2; + } else if (fattr->cf_cifsattrs & ATTR_REPARSE) { + fattr->cf_mode = S_IFLNK; + fattr->cf_dtype = DT_LNK; + fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks); } else { fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode; fattr->cf_dtype = DT_REG; @@ -646,7 +650,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, cifs_dbg(FYI, "Getting info on %s\n", full_path); if ((data == NULL) && (*inode != NULL)) { - if (CIFS_I(*inode)->clientCanCacheRead) { + if (CIFS_CACHE_READ(CIFS_I(*inode))) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); goto cgii_exit; } @@ -1657,7 +1661,7 @@ cifs_inode_needs_reval(struct inode *inode) struct cifsInodeInfo *cifs_i = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - if (cifs_i->clientCanCacheRead) + if (CIFS_CACHE_READ(cifs_i)) return false; if (!lookupCacheEnabled) @@ -1800,7 +1804,7 @@ int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry, * We need to be sure that all dirty pages are written and the server * has actual ctime, mtime and file length. */ - if (!CIFS_I(inode)->clientCanCacheRead && inode->i_mapping && + if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping && inode->i_mapping->nrpages != 0) { rc = filemap_fdatawait(inode->i_mapping); if (rc) { @@ -1852,14 +1856,11 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from) static void cifs_setsize(struct inode *inode, loff_t offset) { - loff_t oldsize; - spin_lock(&inode->i_lock); - oldsize = inode->i_size; i_size_write(inode, offset); spin_unlock(&inode->i_lock); - truncate_pagecache(inode, oldsize, offset); + truncate_pagecache(inode, offset); } static int diff --git a/fs/cifs/link.c b/fs/cifs/link.c index b83c3f5..7e36ceb 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -305,67 +305,89 @@ CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr) } int -CIFSCheckMFSymlink(struct cifs_fattr *fattr, - const unsigned char *path, - struct cifs_sb_info *cifs_sb, unsigned int xid) +open_query_close_cifs_symlink(const unsigned char *path, char *pbuf, + unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb, + unsigned int xid) { int rc; int oplock = 0; __u16 netfid = 0; struct tcon_link *tlink; - struct cifs_tcon *pTcon; + struct cifs_tcon *ptcon; struct cifs_io_parms io_parms; - u8 *buf; - char *pbuf; - unsigned int bytes_read = 0; int buf_type = CIFS_NO_BUFFER; - unsigned int link_len = 0; FILE_ALL_INFO file_info; - if (!CIFSCouldBeMFSymlink(fattr)) - /* it's not a symlink */ - return 0; - tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); - pTcon = tlink_tcon(tlink); + ptcon = tlink_tcon(tlink); - rc = CIFSSMBOpen(xid, pTcon, path, FILE_OPEN, GENERIC_READ, + rc = CIFSSMBOpen(xid, ptcon, path, FILE_OPEN, GENERIC_READ, CREATE_NOT_DIR, &netfid, &oplock, &file_info, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc != 0) - goto out; + if (rc != 0) { + cifs_put_tlink(tlink); + return rc; + } if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { - CIFSSMBClose(xid, pTcon, netfid); + CIFSSMBClose(xid, ptcon, netfid); + cifs_put_tlink(tlink); /* it's not a symlink */ - goto out; + return rc; } - buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - goto out; - } - pbuf = buf; io_parms.netfid = netfid; io_parms.pid = current->tgid; - io_parms.tcon = pTcon; + io_parms.tcon = ptcon; io_parms.offset = 0; io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE; - rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type); - CIFSSMBClose(xid, pTcon, netfid); - if (rc != 0) { - kfree(buf); + rc = CIFSSMBRead(xid, &io_parms, pbytes_read, &pbuf, &buf_type); + CIFSSMBClose(xid, ptcon, netfid); + cifs_put_tlink(tlink); + return rc; +} + + +int +CIFSCheckMFSymlink(struct cifs_fattr *fattr, + const unsigned char *path, + struct cifs_sb_info *cifs_sb, unsigned int xid) +{ + int rc = 0; + u8 *buf = NULL; + unsigned int link_len = 0; + unsigned int bytes_read = 0; + struct cifs_tcon *ptcon; + + if (!CIFSCouldBeMFSymlink(fattr)) + /* it's not a symlink */ + return 0; + + buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); + if (!buf) { + rc = -ENOMEM; goto out; } + ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb)); + if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink)) + rc = ptcon->ses->server->ops->query_mf_symlink(path, buf, + &bytes_read, cifs_sb, xid); + else + goto out; + + if (rc != 0) + goto out; + + if (bytes_read == 0) /* not a symlink */ + goto out; + rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, NULL); - kfree(buf); if (rc == -EINVAL) { /* it's not a symlink */ rc = 0; @@ -381,7 +403,7 @@ CIFSCheckMFSymlink(struct cifs_fattr *fattr, fattr->cf_mode |= S_IFLNK | S_IRWXU | S_IRWXG | S_IRWXO; fattr->cf_dtype = DT_LNK; out: - cifs_put_tlink(tlink); + kfree(buf); return rc; } @@ -487,6 +509,7 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd) struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = NULL; struct cifs_tcon *tcon; + struct TCP_Server_Info *server; xid = get_xid(); @@ -497,25 +520,7 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd) goto out; } tcon = tlink_tcon(tlink); - - /* - * For now, we just handle symlinks with unix extensions enabled. - * Eventually we should handle NTFS reparse points, and MacOS - * symlink support. For instance... - * - * rc = CIFSSMBQueryReparseLinkInfo(...) - * - * For now, just return -EACCES when the server doesn't support posix - * extensions. Note that we still allow querying symlinks when posix - * extensions are manually disabled. We could disable these as well - * but there doesn't seem to be any harm in allowing the client to - * read them. - */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) && - !cap_unix(tcon->ses)) { - rc = -EACCES; - goto out; - } + server = tcon->ses->server; full_path = build_path_from_dentry(direntry); if (!full_path) @@ -537,6 +542,9 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd) if ((rc != 0) && cap_unix(tcon->ses)) rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, &target_path, cifs_sb->local_nls); + else if (rc != 0 && server->ops->query_symlink) + rc = server->ops->query_symlink(xid, tcon, full_path, + &target_path, cifs_sb); kfree(full_path); out: diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index f7d4b22..138a011 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -105,6 +105,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) } kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); + kfree(buf_to_free->auth_key.response); kfree(buf_to_free); } @@ -545,19 +546,15 @@ void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock) oplock &= 0xF; if (oplock == OPLOCK_EXCLUSIVE) { - cinode->clientCanCacheAll = true; - cinode->clientCanCacheRead = true; + cinode->oplock = CIFS_CACHE_WRITE_FLG | CIFS_CACHE_READ_FLG; cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n", &cinode->vfs_inode); } else if (oplock == OPLOCK_READ) { - cinode->clientCanCacheAll = false; - cinode->clientCanCacheRead = true; + cinode->oplock = CIFS_CACHE_READ_FLG; cifs_dbg(FYI, "Level II Oplock granted on inode %p\n", &cinode->vfs_inode); - } else { - cinode->clientCanCacheAll = false; - cinode->clientCanCacheRead = false; - } + } else + cinode->oplock = 0; } bool diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index ab87784..42ef03b 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -111,6 +111,14 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, return; } + /* + * If we know that the inode will need to be revalidated immediately, + * then don't create a new dentry for it. We'll end up doing an on + * the wire call either way and this spares us an invalidation. + */ + if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL) + return; + dentry = d_alloc(parent, name); if (!dentry) return; @@ -164,6 +172,9 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) if (cifs_dfs_is_possible(cifs_sb) && (fattr->cf_cifsattrs & ATTR_REPARSE)) fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; + } else if (fattr->cf_cifsattrs & ATTR_REPARSE) { + fattr->cf_mode = S_IFLNK; + fattr->cf_dtype = DT_LNK; } else { fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode; fattr->cf_dtype = DT_REG; diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 79358e3..5f99b7f 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -197,7 +197,7 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses, bytes_ret = 0; } else bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->domainName, - 256, nls_cp); + CIFS_MAX_DOMAINNAME_LEN, nls_cp); bcc_ptr += 2 * bytes_ret; bcc_ptr += 2; /* account for null terminator */ @@ -226,7 +226,7 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses, *(bcc_ptr+1) = 0; } else { bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->user_name, - MAX_USERNAME_SIZE, nls_cp); + CIFS_MAX_USERNAME_LEN, nls_cp); } bcc_ptr += 2 * bytes_ret; bcc_ptr += 2; /* account for null termination */ @@ -246,8 +246,8 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses, /* BB what about null user mounts - check that we do this BB */ /* copy user */ if (ses->user_name != NULL) { - strncpy(bcc_ptr, ses->user_name, MAX_USERNAME_SIZE); - bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE); + strncpy(bcc_ptr, ses->user_name, CIFS_MAX_USERNAME_LEN); + bcc_ptr += strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); } /* else null user mount */ *bcc_ptr = 0; @@ -255,8 +255,8 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses, /* copy domain */ if (ses->domainName != NULL) { - strncpy(bcc_ptr, ses->domainName, 256); - bcc_ptr += strnlen(ses->domainName, 256); + strncpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN); + bcc_ptr += strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); } /* else we will send a null domain name so the server will default to its own domain */ *bcc_ptr = 0; @@ -428,7 +428,8 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC; if (ses->server->sign) { flags |= NTLMSSP_NEGOTIATE_SIGN; - if (!ses->server->session_estab) + if (!ses->server->session_estab || + ses->ntlmssp->sesskey_per_smbsess) flags |= NTLMSSP_NEGOTIATE_KEY_XCH; } @@ -466,7 +467,8 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC; if (ses->server->sign) { flags |= NTLMSSP_NEGOTIATE_SIGN; - if (!ses->server->session_estab) + if (!ses->server->session_estab || + ses->ntlmssp->sesskey_per_smbsess) flags |= NTLMSSP_NEGOTIATE_KEY_XCH; } @@ -501,7 +503,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, } else { int len; len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName, - MAX_USERNAME_SIZE, nls_cp); + CIFS_MAX_USERNAME_LEN, nls_cp); len *= 2; /* unicode is 2 bytes each */ sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->DomainName.Length = cpu_to_le16(len); @@ -517,7 +519,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, } else { int len; len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name, - MAX_USERNAME_SIZE, nls_cp); + CIFS_MAX_USERNAME_LEN, nls_cp); len *= 2; /* unicode is 2 bytes each */ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->UserName.Length = cpu_to_le16(len); @@ -629,7 +631,8 @@ CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses, type = select_sectype(ses->server, ses->sectype); cifs_dbg(FYI, "sess setup type %d\n", type); if (type == Unspecified) { - cifs_dbg(VFS, "Unable to select appropriate authentication method!"); + cifs_dbg(VFS, + "Unable to select appropriate authentication method!"); return -EINVAL; } @@ -640,6 +643,8 @@ CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses, ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL); if (!ses->ntlmssp) return -ENOMEM; + ses->ntlmssp->sesskey_per_smbsess = false; + } ssetup_ntlmssp_authenticate: @@ -815,8 +820,9 @@ ssetup_ntlmssp_authenticate: ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, GFP_KERNEL); if (!ses->auth_key.response) { - cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory", - msg->sesskey_len); + cifs_dbg(VFS, + "Kerberos can't allocate (%u bytes) memory", + msg->sesskey_len); rc = -ENOMEM; goto ssetup_exit; } @@ -1005,5 +1011,37 @@ ssetup_exit: if ((phase == NtLmChallenge) && (rc == 0)) goto ssetup_ntlmssp_authenticate; + if (!rc) { + mutex_lock(&ses->server->srv_mutex); + if (!ses->server->session_estab) { + if (ses->server->sign) { + ses->server->session_key.response = + kmemdup(ses->auth_key.response, + ses->auth_key.len, GFP_KERNEL); + if (!ses->server->session_key.response) { + rc = -ENOMEM; + mutex_unlock(&ses->server->srv_mutex); + goto keycp_exit; + } + ses->server->session_key.len = + ses->auth_key.len; + } + ses->server->sequence_number = 0x2; + ses->server->session_estab = true; + } + mutex_unlock(&ses->server->srv_mutex); + + cifs_dbg(FYI, "CIFS session established successfully\n"); + spin_lock(&GlobalMid_Lock); + ses->status = CifsGood; + ses->need_reconnect = false; + spin_unlock(&GlobalMid_Lock); + } + +keycp_exit: + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + kfree(ses->ntlmssp); + return rc; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 6457690..8233b17 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -700,7 +700,7 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); cfile->fid.netfid = fid->netfid; cifs_set_oplock_level(cinode, oplock); - cinode->can_cache_brlcks = cinode->clientCanCacheAll; + cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } static void @@ -837,7 +837,7 @@ cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, { return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, false, - cinode->clientCanCacheRead ? 1 : 0); + CIFS_CACHE_READ(cinode) ? 1 : 0); } static int @@ -881,6 +881,43 @@ cifs_mand_lock(const unsigned int xid, struct cifsFileInfo *cfile, __u64 offset, (__u8)type, wait, 0); } +static int +cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, + const char *full_path, char **target_path, + struct cifs_sb_info *cifs_sb) +{ + int rc; + int oplock = 0; + __u16 netfid; + + cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); + + rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN, + FILE_READ_ATTRIBUTES, OPEN_REPARSE_POINT, &netfid, + &oplock, NULL, cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + if (rc) + return rc; + + rc = CIFSSMBQuerySymLink(xid, tcon, netfid, target_path, + cifs_sb->local_nls); + if (rc) { + CIFSSMBClose(xid, tcon, netfid); + return rc; + } + + convert_delimiter(*target_path, '/'); + CIFSSMBClose(xid, tcon, netfid); + cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + return rc; +} + +static bool +cifs_is_read_op(__u32 oplock) +{ + return oplock == OPLOCK_READ; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -927,6 +964,7 @@ struct smb_version_operations smb1_operations = { .rename_pending_delete = cifs_rename_pending_delete, .rename = CIFSSMBRename, .create_hardlink = CIFSCreateHardLink, + .query_symlink = cifs_query_symlink, .open = cifs_open_file, .set_fid = cifs_set_fid, .close = cifs_close_file, @@ -944,6 +982,8 @@ struct smb_version_operations smb1_operations = { .mand_lock = cifs_mand_lock, .mand_unlock_range = cifs_unlock_range, .push_mand_locks = cifs_push_mandatory_locks, + .query_mf_symlink = open_query_close_cifs_symlink, + .is_read_op = cifs_is_read_op, }; struct smb_version_values smb1_values = { @@ -959,7 +999,6 @@ struct smb_version_values smb1_values = { .cap_unix = CAP_UNIX, .cap_nt_find = CAP_NT_SMBS | CAP_NT_FIND, .cap_large_files = CAP_LARGE_FILES, - .oplock_read = OPLOCK_READ, .signing_enabled = SECMODE_SIGN_ENABLED, .signing_required = SECMODE_SIGN_REQUIRED, }; diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 04a81a4..3f17b45 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -34,29 +34,6 @@ #include "fscache.h" #include "smb2proto.h" -void -smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock) -{ - oplock &= 0xFF; - if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) - return; - if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE || - oplock == SMB2_OPLOCK_LEVEL_BATCH) { - cinode->clientCanCacheAll = true; - cinode->clientCanCacheRead = true; - cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n", - &cinode->vfs_inode); - } else if (oplock == SMB2_OPLOCK_LEVEL_II) { - cinode->clientCanCacheAll = false; - cinode->clientCanCacheRead = true; - cifs_dbg(FYI, "Level II Oplock granted on inode %p\n", - &cinode->vfs_inode); - } else { - cinode->clientCanCacheAll = false; - cinode->clientCanCacheRead = false; - } -} - int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, FILE_ALL_INFO *buf) @@ -86,7 +63,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE); - rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data); + rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL); if (rc) goto out; diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index c6ec163..78ff88c 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -60,7 +60,7 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); if (rc) { kfree(utf16_path); return rc; @@ -136,7 +136,8 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, return -ENOMEM; rc = smb2_open_op_close(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, 0, smb2_data, + FILE_READ_ATTRIBUTES, FILE_OPEN, + OPEN_REPARSE_POINT, smb2_data, SMB2_OP_QUERY_INFO); if (rc) goto out; @@ -191,8 +192,8 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, - CREATE_DELETE_ON_CLOSE, NULL, - SMB2_OP_DELETE); + CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, + NULL, SMB2_OP_DELETE); } static int diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index b0c4334..fb39662 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -171,6 +171,10 @@ smb2_check_message(char *buf, unsigned int length) if (4 + len != clc_len) { cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n", clc_len, 4 + len, mid); + /* create failed on symlink */ + if (command == SMB2_CREATE_HE && + hdr->Status == STATUS_STOPPED_ON_SYMLINK) + return 0; /* Windows 7 server returns 24 bytes more */ if (clc_len + 20 == len && command == SMB2_OPLOCK_BREAK_HE) return 0; @@ -376,23 +380,15 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb) __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode) { - if (cinode->clientCanCacheAll) - return SMB2_LEASE_WRITE_CACHING | SMB2_LEASE_READ_CACHING; - else if (cinode->clientCanCacheRead) - return SMB2_LEASE_READ_CACHING; - return 0; -} - -__u8 smb2_map_lease_to_oplock(__le32 lease_state) -{ - if (lease_state & SMB2_LEASE_WRITE_CACHING) { - if (lease_state & SMB2_LEASE_HANDLE_CACHING) - return SMB2_OPLOCK_LEVEL_BATCH; - else - return SMB2_OPLOCK_LEVEL_EXCLUSIVE; - } else if (lease_state & SMB2_LEASE_READ_CACHING) - return SMB2_OPLOCK_LEVEL_II; - return 0; + __le32 lease = 0; + + if (CIFS_CACHE_WRITE(cinode)) + lease |= SMB2_LEASE_WRITE_CACHING; + if (CIFS_CACHE_HANDLE(cinode)) + lease |= SMB2_LEASE_HANDLE_CACHING; + if (CIFS_CACHE_READ(cinode)) + lease |= SMB2_LEASE_READ_CACHING; + return lease; } struct smb2_lease_break_work { @@ -417,96 +413,109 @@ cifs_ses_oplock_break(struct work_struct *work) } static bool -smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) +smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, + struct smb2_lease_break_work *lw) { - struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer; - struct list_head *tmp, *tmp1, *tmp2; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - struct cifsInodeInfo *cinode; + bool found; + __u8 lease_state; + struct list_head *tmp; struct cifsFileInfo *cfile; + struct TCP_Server_Info *server = tcon->ses->server; struct cifs_pending_open *open; - struct smb2_lease_break_work *lw; - bool found; + struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); - lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); - if (!lw) - return false; + lease_state = le32_to_cpu(rsp->NewLeaseState); - INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); - lw->lease_state = rsp->NewLeaseState; + list_for_each(tmp, &tcon->openFileList) { + cfile = list_entry(tmp, struct cifsFileInfo, tlist); + cinode = CIFS_I(cfile->dentry->d_inode); - cifs_dbg(FYI, "Checking for lease break\n"); + if (memcmp(cinode->lease_key, rsp->LeaseKey, + SMB2_LEASE_KEY_SIZE)) + continue; - /* look up tcon based on tid & uid */ - spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + cifs_dbg(FYI, "found in the open list\n"); + cifs_dbg(FYI, "lease key match, lease break 0x%d\n", + le32_to_cpu(rsp->NewLeaseState)); - spin_lock(&cifs_file_list_lock); - list_for_each(tmp1, &ses->tcon_list) { - tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); + server->ops->set_oplock_level(cinode, lease_state, 0, NULL); - cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks); - list_for_each(tmp2, &tcon->openFileList) { - cfile = list_entry(tmp2, struct cifsFileInfo, - tlist); - cinode = CIFS_I(cfile->dentry->d_inode); + if (ack_req) + cfile->oplock_break_cancelled = false; + else + cfile->oplock_break_cancelled = true; - if (memcmp(cinode->lease_key, rsp->LeaseKey, - SMB2_LEASE_KEY_SIZE)) - continue; + queue_work(cifsiod_wq, &cfile->oplock_break); + kfree(lw); + return true; + } - cifs_dbg(FYI, "found in the open list\n"); - cifs_dbg(FYI, "lease key match, lease break 0x%d\n", - le32_to_cpu(rsp->NewLeaseState)); + found = false; + list_for_each_entry(open, &tcon->pending_opens, olist) { + if (memcmp(open->lease_key, rsp->LeaseKey, + SMB2_LEASE_KEY_SIZE)) + continue; + + if (!found && ack_req) { + found = true; + memcpy(lw->lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + lw->tlink = cifs_get_tlink(open->tlink); + queue_work(cifsiod_wq, &lw->lease_break); + } - smb2_set_oplock_level(cinode, - smb2_map_lease_to_oplock(rsp->NewLeaseState)); + cifs_dbg(FYI, "found in the pending open list\n"); + cifs_dbg(FYI, "lease key match, lease break 0x%d\n", + le32_to_cpu(rsp->NewLeaseState)); - if (ack_req) - cfile->oplock_break_cancelled = false; - else - cfile->oplock_break_cancelled = true; + open->oplock = lease_state; + } + return found; +} - queue_work(cifsiod_wq, &cfile->oplock_break); +static bool +smb2_is_valid_lease_break(char *buffer) +{ + struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer; + struct list_head *tmp, *tmp1, *tmp2; + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + struct smb2_lease_break_work *lw; - spin_unlock(&cifs_file_list_lock); - spin_unlock(&cifs_tcp_ses_lock); - return true; - } + lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); + if (!lw) + return false; - found = false; - list_for_each_entry(open, &tcon->pending_opens, olist) { - if (memcmp(open->lease_key, rsp->LeaseKey, - SMB2_LEASE_KEY_SIZE)) - continue; + INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); + lw->lease_state = rsp->NewLeaseState; - if (!found && ack_req) { - found = true; - memcpy(lw->lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - lw->tlink = cifs_get_tlink(open->tlink); - queue_work(cifsiod_wq, - &lw->lease_break); - } + cifs_dbg(FYI, "Checking for lease break\n"); - cifs_dbg(FYI, "found in the pending open list\n"); - cifs_dbg(FYI, "lease key match, lease break 0x%d\n", - le32_to_cpu(rsp->NewLeaseState)); + /* look up tcon based on tid & uid */ + spin_lock(&cifs_tcp_ses_lock); + list_for_each(tmp, &cifs_tcp_ses_list) { + server = list_entry(tmp, struct TCP_Server_Info, tcp_ses_list); - open->oplock = - smb2_map_lease_to_oplock(rsp->NewLeaseState); - } - if (found) { - spin_unlock(&cifs_file_list_lock); - spin_unlock(&cifs_tcp_ses_lock); - return true; + list_for_each(tmp1, &server->smb_ses_list) { + ses = list_entry(tmp1, struct cifs_ses, smb_ses_list); + + spin_lock(&cifs_file_list_lock); + list_for_each(tmp2, &ses->tcon_list) { + tcon = list_entry(tmp2, struct cifs_tcon, + tcon_list); + cifs_stats_inc( + &tcon->stats.cifs_stats.num_oplock_brks); + if (smb2_tcon_has_lease(tcon, rsp, lw)) { + spin_unlock(&cifs_file_list_lock); + spin_unlock(&cifs_tcp_ses_lock); + return true; + } } + spin_unlock(&cifs_file_list_lock); } - spin_unlock(&cifs_file_list_lock); } spin_unlock(&cifs_tcp_ses_lock); kfree(lw); @@ -532,7 +541,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) if (rsp->StructureSize != smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) { if (le16_to_cpu(rsp->StructureSize) == 44) - return smb2_is_valid_lease_break(buffer, server); + return smb2_is_valid_lease_break(buffer); else return false; } @@ -560,14 +569,15 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) cifs_dbg(FYI, "file id match, oplock break\n"); cinode = CIFS_I(cfile->dentry->d_inode); - if (!cinode->clientCanCacheAll && + if (!CIFS_CACHE_WRITE(cinode) && rsp->OplockLevel == SMB2_OPLOCK_LEVEL_NONE) cfile->oplock_break_cancelled = true; else cfile->oplock_break_cancelled = false; - smb2_set_oplock_level(cinode, - rsp->OplockLevel ? SMB2_OPLOCK_LEVEL_II : 0); + server->ops->set_oplock_level(cinode, + rsp->OplockLevel ? SMB2_OPLOCK_LEVEL_II : 0, + 0, NULL); queue_work(cifsiod_wq, &cfile->oplock_break); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f259e6c..861b332 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -24,6 +24,7 @@ #include "smb2proto.h" #include "cifsproto.h" #include "cifs_debug.h" +#include "cifs_unicode.h" #include "smb2status.h" #include "smb2glob.h" @@ -229,7 +230,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); if (rc) { kfree(utf16_path); return rc; @@ -376,10 +377,13 @@ static void smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) { struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); + struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; + cfile->fid.persistent_fid = fid->persistent_fid; cfile->fid.volatile_fid = fid->volatile_fid; - smb2_set_oplock_level(cinode, oplock); - cinode->can_cache_brlcks = cinode->clientCanCacheAll; + server->ops->set_oplock_level(cinode, oplock, fid->epoch, + &fid->purge_cache); + cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } static void @@ -463,7 +467,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); kfree(utf16_path); if (rc) { cifs_dbg(VFS, "open dir failed\n"); @@ -530,7 +534,7 @@ smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, return SMB2_oplock_break(0, tcon, fid->persistent_fid, fid->volatile_fid, - cinode->clientCanCacheRead ? 1 : 0); + CIFS_CACHE_READ(cinode) ? 1 : 0); } static int @@ -550,7 +554,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL); + rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL); if (rc) return rc; buf->f_type = SMB2_MAGIC_NUMBER; @@ -596,7 +600,245 @@ smb2_new_lease_key(struct cifs_fid *fid) get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE); } -struct smb_version_operations smb21_operations = { +static int +smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, + const char *full_path, char **target_path, + struct cifs_sb_info *cifs_sb) +{ + int rc; + __le16 *utf16_path; + __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_open_parms oparms; + struct cifs_fid fid; + struct smb2_err_rsp *err_buf = NULL; + struct smb2_symlink_err_rsp *symlink; + unsigned int sub_len, sub_offset; + + cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); + + utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb); + if (!utf16_path) + return -ENOMEM; + + oparms.tcon = tcon; + oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.disposition = FILE_OPEN; + oparms.create_options = 0; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_buf); + + if (!rc || !err_buf) { + kfree(utf16_path); + return -ENOENT; + } + /* open must fail on symlink - reset rc */ + rc = 0; + symlink = (struct smb2_symlink_err_rsp *)err_buf->ErrorData; + sub_len = le16_to_cpu(symlink->SubstituteNameLength); + sub_offset = le16_to_cpu(symlink->SubstituteNameOffset); + *target_path = cifs_strndup_from_utf16( + (char *)symlink->PathBuffer + sub_offset, + sub_len, true, cifs_sb->local_nls); + if (!(*target_path)) { + kfree(utf16_path); + return -ENOMEM; + } + convert_delimiter(*target_path, '/'); + cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + kfree(utf16_path); + return rc; +} + +static void +smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) +{ + oplock &= 0xFF; + if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) + return; + if (oplock == SMB2_OPLOCK_LEVEL_BATCH) { + cinode->oplock = CIFS_CACHE_RHW_FLG; + cifs_dbg(FYI, "Batch Oplock granted on inode %p\n", + &cinode->vfs_inode); + } else if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { + cinode->oplock = CIFS_CACHE_RW_FLG; + cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n", + &cinode->vfs_inode); + } else if (oplock == SMB2_OPLOCK_LEVEL_II) { + cinode->oplock = CIFS_CACHE_READ_FLG; + cifs_dbg(FYI, "Level II Oplock granted on inode %p\n", + &cinode->vfs_inode); + } else + cinode->oplock = 0; +} + +static void +smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) +{ + char message[5] = {0}; + + oplock &= 0xFF; + if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) + return; + + cinode->oplock = 0; + if (oplock & SMB2_LEASE_READ_CACHING_HE) { + cinode->oplock |= CIFS_CACHE_READ_FLG; + strcat(message, "R"); + } + if (oplock & SMB2_LEASE_HANDLE_CACHING_HE) { + cinode->oplock |= CIFS_CACHE_HANDLE_FLG; + strcat(message, "H"); + } + if (oplock & SMB2_LEASE_WRITE_CACHING_HE) { + cinode->oplock |= CIFS_CACHE_WRITE_FLG; + strcat(message, "W"); + } + if (!cinode->oplock) + strcat(message, "None"); + cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, + &cinode->vfs_inode); +} + +static void +smb3_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) +{ + unsigned int old_oplock = cinode->oplock; + + smb21_set_oplock_level(cinode, oplock, epoch, purge_cache); + + if (purge_cache) { + *purge_cache = false; + if (old_oplock == CIFS_CACHE_READ_FLG) { + if (cinode->oplock == CIFS_CACHE_READ_FLG && + (epoch - cinode->epoch > 0)) + *purge_cache = true; + else if (cinode->oplock == CIFS_CACHE_RH_FLG && + (epoch - cinode->epoch > 1)) + *purge_cache = true; + else if (cinode->oplock == CIFS_CACHE_RHW_FLG && + (epoch - cinode->epoch > 1)) + *purge_cache = true; + else if (cinode->oplock == 0 && + (epoch - cinode->epoch > 0)) + *purge_cache = true; + } else if (old_oplock == CIFS_CACHE_RH_FLG) { + if (cinode->oplock == CIFS_CACHE_RH_FLG && + (epoch - cinode->epoch > 0)) + *purge_cache = true; + else if (cinode->oplock == CIFS_CACHE_RHW_FLG && + (epoch - cinode->epoch > 1)) + *purge_cache = true; + } + cinode->epoch = epoch; + } +} + +static bool +smb2_is_read_op(__u32 oplock) +{ + return oplock == SMB2_OPLOCK_LEVEL_II; +} + +static bool +smb21_is_read_op(__u32 oplock) +{ + return (oplock & SMB2_LEASE_READ_CACHING_HE) && + !(oplock & SMB2_LEASE_WRITE_CACHING_HE); +} + +static __le32 +map_oplock_to_lease(u8 oplock) +{ + if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) + return SMB2_LEASE_WRITE_CACHING | SMB2_LEASE_READ_CACHING; + else if (oplock == SMB2_OPLOCK_LEVEL_II) + return SMB2_LEASE_READ_CACHING; + else if (oplock == SMB2_OPLOCK_LEVEL_BATCH) + return SMB2_LEASE_HANDLE_CACHING | SMB2_LEASE_READ_CACHING | + SMB2_LEASE_WRITE_CACHING; + return 0; +} + +static char * +smb2_create_lease_buf(u8 *lease_key, u8 oplock) +{ + struct create_lease *buf; + + buf = kzalloc(sizeof(struct create_lease), GFP_KERNEL); + if (!buf) + return NULL; + + buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key)); + buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8))); + buf->lcontext.LeaseState = map_oplock_to_lease(oplock); + + buf->ccontext.DataOffset = cpu_to_le16(offsetof + (struct create_lease, lcontext)); + buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context)); + buf->ccontext.NameOffset = cpu_to_le16(offsetof + (struct create_lease, Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + buf->Name[0] = 'R'; + buf->Name[1] = 'q'; + buf->Name[2] = 'L'; + buf->Name[3] = 's'; + return (char *)buf; +} + +static char * +smb3_create_lease_buf(u8 *lease_key, u8 oplock) +{ + struct create_lease_v2 *buf; + + buf = kzalloc(sizeof(struct create_lease_v2), GFP_KERNEL); + if (!buf) + return NULL; + + buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key)); + buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8))); + buf->lcontext.LeaseState = map_oplock_to_lease(oplock); + + buf->ccontext.DataOffset = cpu_to_le16(offsetof + (struct create_lease_v2, lcontext)); + buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2)); + buf->ccontext.NameOffset = cpu_to_le16(offsetof + (struct create_lease_v2, Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + buf->Name[0] = 'R'; + buf->Name[1] = 'q'; + buf->Name[2] = 'L'; + buf->Name[3] = 's'; + return (char *)buf; +} + +static __u8 +smb2_parse_lease_buf(void *buf, unsigned int *epoch) +{ + struct create_lease *lc = (struct create_lease *)buf; + + *epoch = 0; /* not used */ + if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) + return SMB2_OPLOCK_LEVEL_NOCHANGE; + return le32_to_cpu(lc->lcontext.LeaseState); +} + +static __u8 +smb3_parse_lease_buf(void *buf, unsigned int *epoch) +{ + struct create_lease_v2 *lc = (struct create_lease_v2 *)buf; + + *epoch = le16_to_cpu(lc->lcontext.Epoch); + if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) + return SMB2_OPLOCK_LEVEL_NOCHANGE; + return le32_to_cpu(lc->lcontext.LeaseState); +} + +struct smb_version_operations smb20_operations = { .compare_fids = smb2_compare_fids, .setup_request = smb2_setup_request, .setup_async_request = smb2_setup_async_request, @@ -638,6 +880,7 @@ struct smb_version_operations smb21_operations = { .unlink = smb2_unlink, .rename = smb2_rename_path, .create_hardlink = smb2_create_hardlink, + .query_symlink = smb2_query_symlink, .open = smb2_open_file, .set_fid = smb2_set_fid, .close = smb2_close_file, @@ -660,8 +903,82 @@ struct smb_version_operations smb21_operations = { .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, .calc_signature = smb2_calc_signature, + .is_read_op = smb2_is_read_op, + .set_oplock_level = smb2_set_oplock_level, + .create_lease_buf = smb2_create_lease_buf, + .parse_lease_buf = smb2_parse_lease_buf, }; +struct smb_version_operations smb21_operations = { + .compare_fids = smb2_compare_fids, + .setup_request = smb2_setup_request, + .setup_async_request = smb2_setup_async_request, + .check_receive = smb2_check_receive, + .add_credits = smb2_add_credits, + .set_credits = smb2_set_credits, + .get_credits_field = smb2_get_credits_field, + .get_credits = smb2_get_credits, + .get_next_mid = smb2_get_next_mid, + .read_data_offset = smb2_read_data_offset, + .read_data_length = smb2_read_data_length, + .map_error = map_smb2_to_linux_error, + .find_mid = smb2_find_mid, + .check_message = smb2_check_message, + .dump_detail = smb2_dump_detail, + .clear_stats = smb2_clear_stats, + .print_stats = smb2_print_stats, + .is_oplock_break = smb2_is_valid_oplock_break, + .need_neg = smb2_need_neg, + .negotiate = smb2_negotiate, + .negotiate_wsize = smb2_negotiate_wsize, + .negotiate_rsize = smb2_negotiate_rsize, + .sess_setup = SMB2_sess_setup, + .logoff = SMB2_logoff, + .tree_connect = SMB2_tcon, + .tree_disconnect = SMB2_tdis, + .is_path_accessible = smb2_is_path_accessible, + .can_echo = smb2_can_echo, + .echo = SMB2_echo, + .query_path_info = smb2_query_path_info, + .get_srv_inum = smb2_get_srv_inum, + .query_file_info = smb2_query_file_info, + .set_path_size = smb2_set_path_size, + .set_file_size = smb2_set_file_size, + .set_file_info = smb2_set_file_info, + .mkdir = smb2_mkdir, + .mkdir_setinfo = smb2_mkdir_setinfo, + .rmdir = smb2_rmdir, + .unlink = smb2_unlink, + .rename = smb2_rename_path, + .create_hardlink = smb2_create_hardlink, + .query_symlink = smb2_query_symlink, + .open = smb2_open_file, + .set_fid = smb2_set_fid, + .close = smb2_close_file, + .flush = smb2_flush_file, + .async_readv = smb2_async_readv, + .async_writev = smb2_async_writev, + .sync_read = smb2_sync_read, + .sync_write = smb2_sync_write, + .query_dir_first = smb2_query_dir_first, + .query_dir_next = smb2_query_dir_next, + .close_dir = smb2_close_dir, + .calc_smb_size = smb2_calc_size, + .is_status_pending = smb2_is_status_pending, + .oplock_response = smb2_oplock_response, + .queryfs = smb2_queryfs, + .mand_lock = smb2_mand_lock, + .mand_unlock_range = smb2_unlock_range, + .push_mand_locks = smb2_push_mandatory_locks, + .get_lease_key = smb2_get_lease_key, + .set_lease_key = smb2_set_lease_key, + .new_lease_key = smb2_new_lease_key, + .calc_signature = smb2_calc_signature, + .is_read_op = smb21_is_read_op, + .set_oplock_level = smb21_set_oplock_level, + .create_lease_buf = smb2_create_lease_buf, + .parse_lease_buf = smb2_parse_lease_buf, +}; struct smb_version_operations smb30_operations = { .compare_fids = smb2_compare_fids, @@ -706,6 +1023,7 @@ struct smb_version_operations smb30_operations = { .unlink = smb2_unlink, .rename = smb2_rename_path, .create_hardlink = smb2_create_hardlink, + .query_symlink = smb2_query_symlink, .open = smb2_open_file, .set_fid = smb2_set_fid, .close = smb2_close_file, @@ -729,6 +1047,10 @@ struct smb_version_operations smb30_operations = { .new_lease_key = smb2_new_lease_key, .generate_signingkey = generate_smb3signingkey, .calc_signature = smb3_calc_signature, + .is_read_op = smb21_is_read_op, + .set_oplock_level = smb3_set_oplock_level, + .create_lease_buf = smb3_create_lease_buf, + .parse_lease_buf = smb3_parse_lease_buf, }; struct smb_version_values smb20_values = { @@ -746,9 +1068,9 @@ struct smb_version_values smb20_values = { .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, .cap_large_files = SMB2_LARGE_FILES, - .oplock_read = SMB2_OPLOCK_LEVEL_II, .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED, .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED, + .create_lease_size = sizeof(struct create_lease), }; struct smb_version_values smb21_values = { @@ -766,9 +1088,9 @@ struct smb_version_values smb21_values = { .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, .cap_large_files = SMB2_LARGE_FILES, - .oplock_read = SMB2_OPLOCK_LEVEL_II, .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED, .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED, + .create_lease_size = sizeof(struct create_lease), }; struct smb_version_values smb30_values = { @@ -786,9 +1108,9 @@ struct smb_version_values smb30_values = { .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, .cap_large_files = SMB2_LARGE_FILES, - .oplock_read = SMB2_OPLOCK_LEVEL_II, .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED, .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED, + .create_lease_size = sizeof(struct create_lease_v2), }; struct smb_version_values smb302_values = { @@ -806,7 +1128,7 @@ struct smb_version_values smb302_values = { .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, .cap_large_files = SMB2_LARGE_FILES, - .oplock_read = SMB2_OPLOCK_LEVEL_II, .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED, .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED, + .create_lease_size = sizeof(struct create_lease_v2), }; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index abc9c28..eba0efd 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -478,12 +478,20 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, } /* + * If we are here due to reconnect, free per-smb session key + * in case signing was required. + */ + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + + /* * If memory allocation is successful, caller of this function * frees it. */ ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL); if (!ses->ntlmssp) return -ENOMEM; + ses->ntlmssp->sesskey_per_smbsess = true; /* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */ ses->sectype = RawNTLMSSP; @@ -628,6 +636,40 @@ ssetup_exit: /* if ntlmssp, and negotiate succeeded, proceed to authenticate phase */ if ((phase == NtLmChallenge) && (rc == 0)) goto ssetup_ntlmssp_authenticate; + + if (!rc) { + mutex_lock(&server->srv_mutex); + if (server->sign && server->ops->generate_signingkey) { + rc = server->ops->generate_signingkey(ses); + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + if (rc) { + cifs_dbg(FYI, + "SMB3 session key generation failed\n"); + mutex_unlock(&server->srv_mutex); + goto keygen_exit; + } + } + if (!server->session_estab) { + server->sequence_number = 0x2; + server->session_estab = true; + } + mutex_unlock(&server->srv_mutex); + + cifs_dbg(FYI, "SMB2/3 session established successfully\n"); + spin_lock(&GlobalMid_Lock); + ses->status = CifsGood; + ses->need_reconnect = false; + spin_unlock(&GlobalMid_Lock); + } + +keygen_exit: + if (!server->sign) { + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + } + kfree(ses->ntlmssp); + return rc; } @@ -813,39 +855,6 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) return rc; } -static struct create_lease * -create_lease_buf(u8 *lease_key, u8 oplock) -{ - struct create_lease *buf; - - buf = kzalloc(sizeof(struct create_lease), GFP_KERNEL); - if (!buf) - return NULL; - - buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key)); - buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8))); - if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) - buf->lcontext.LeaseState = SMB2_LEASE_WRITE_CACHING | - SMB2_LEASE_READ_CACHING; - else if (oplock == SMB2_OPLOCK_LEVEL_II) - buf->lcontext.LeaseState = SMB2_LEASE_READ_CACHING; - else if (oplock == SMB2_OPLOCK_LEVEL_BATCH) - buf->lcontext.LeaseState = SMB2_LEASE_HANDLE_CACHING | - SMB2_LEASE_READ_CACHING | - SMB2_LEASE_WRITE_CACHING; - - buf->ccontext.DataOffset = cpu_to_le16(offsetof - (struct create_lease, lcontext)); - buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context)); - buf->ccontext.NameOffset = cpu_to_le16(offsetof - (struct create_lease, Name)); - buf->ccontext.NameLength = cpu_to_le16(4); - buf->Name[0] = 'R'; - buf->Name[1] = 'q'; - buf->Name[2] = 'L'; - buf->Name[3] = 's'; - return buf; -} static struct create_durable * create_durable_buf(void) @@ -894,55 +903,49 @@ create_reconnect_durable_buf(struct cifs_fid *fid) } static __u8 -parse_lease_state(struct smb2_create_rsp *rsp) +parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, + unsigned int *epoch) { char *data_offset; - struct create_lease *lc; - bool found = false; + struct create_context *cc; unsigned int next = 0; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); - lc = (struct create_lease *)data_offset; + cc = (struct create_context *)data_offset; do { - lc = (struct create_lease *)((char *)lc + next); - name = le16_to_cpu(lc->ccontext.NameOffset) + (char *)lc; - if (le16_to_cpu(lc->ccontext.NameLength) != 4 || + cc = (struct create_context *)((char *)cc + next); + name = le16_to_cpu(cc->NameOffset) + (char *)cc; + if (le16_to_cpu(cc->NameLength) != 4 || strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(lc->ccontext.Next); + next = le32_to_cpu(cc->Next); continue; } - if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) - return SMB2_OPLOCK_LEVEL_NOCHANGE; - found = true; - break; + return server->ops->parse_lease_buf(cc, epoch); } while (next != 0); - if (!found) - return 0; - - return smb2_map_lease_to_oplock(lc->lcontext.LeaseState); + return 0; } static int -add_lease_context(struct kvec *iov, unsigned int *num_iovec, __u8 *oplock) +add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, + unsigned int *num_iovec, __u8 *oplock) { struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; - iov[num].iov_base = create_lease_buf(oplock+1, *oplock); + iov[num].iov_base = server->ops->create_lease_buf(oplock+1, *oplock); if (iov[num].iov_base == NULL) return -ENOMEM; - iov[num].iov_len = sizeof(struct create_lease); + iov[num].iov_len = server->vals->create_lease_size; req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_LEASE; if (!req->CreateContextsOffset) req->CreateContextsOffset = cpu_to_le32( sizeof(struct smb2_create_req) - 4 + iov[num - 1].iov_len); - req->CreateContextsLength = cpu_to_le32( - le32_to_cpu(req->CreateContextsLength) + - sizeof(struct create_lease)); - inc_rfc1001_len(&req->hdr, sizeof(struct create_lease)); + le32_add_cpu(&req->CreateContextsLength, + server->vals->create_lease_size); + inc_rfc1001_len(&req->hdr, server->vals->create_lease_size); *num_iovec = num + 1; return 0; } @@ -967,9 +970,7 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec, req->CreateContextsOffset = cpu_to_le32(sizeof(struct smb2_create_req) - 4 + iov[1].iov_len); - req->CreateContextsLength = - cpu_to_le32(le32_to_cpu(req->CreateContextsLength) + - sizeof(struct create_durable)); + le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable)); inc_rfc1001_len(&req->hdr, sizeof(struct create_durable)); *num_iovec = num + 1; return 0; @@ -977,7 +978,8 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec, int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, - __u8 *oplock, struct smb2_file_all_info *buf) + __u8 *oplock, struct smb2_file_all_info *buf, + struct smb2_err_rsp **err_buf) { struct smb2_create_req *req; struct smb2_create_rsp *rsp; @@ -1048,11 +1050,11 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (!server->oplocks) *oplock = SMB2_OPLOCK_LEVEL_NONE; - if (!(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) || + if (!(server->capabilities & SMB2_GLOBAL_CAP_LEASING) || *oplock == SMB2_OPLOCK_LEVEL_NONE) req->RequestedOplockLevel = *oplock; else { - rc = add_lease_context(iov, &num_iovecs, oplock); + rc = add_lease_context(server, iov, &num_iovecs, oplock); if (rc) { cifs_small_buf_release(req); kfree(copy_path); @@ -1062,11 +1064,11 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) { /* need to set Next field of lease context if we request it */ - if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) { + if (server->capabilities & SMB2_GLOBAL_CAP_LEASING) { struct create_context *ccontext = (struct create_context *)iov[num_iovecs-1].iov_base; ccontext->Next = - cpu_to_le32(sizeof(struct create_lease)); + cpu_to_le32(server->vals->create_lease_size); } rc = add_durable_context(iov, &num_iovecs, oparms); if (rc) { @@ -1082,6 +1084,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (rc != 0) { cifs_stats_fail_inc(tcon, SMB2_CREATE_HE); + if (err_buf) + *err_buf = kmemdup(rsp, get_rfc1002_length(rsp) + 4, + GFP_KERNEL); goto creat_exit; } @@ -1098,7 +1103,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - *oplock = parse_lease_state(rsp); + *oplock = parse_lease_state(server, rsp, &oparms->fid->epoch); else *oplock = rsp->OplockLevel; creat_exit: diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 36b0d37..b83d011 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -150,6 +150,20 @@ struct smb2_err_rsp { __u8 ErrorData[1]; /* variable length */ } __packed; +struct smb2_symlink_err_rsp { + __le32 SymLinkLength; + __le32 SymLinkErrorTag; + __le32 ReparseTag; + __le16 ReparseDataLength; + __le16 UnparsedPathLength; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __le32 Flags; + __u8 PathBuffer[0]; +} __packed; + #define SMB2_CLIENT_GUID_SIZE 16 extern __u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE]; @@ -462,6 +476,10 @@ struct create_context { __u8 Buffer[0]; } __packed; +#define SMB2_LEASE_READ_CACHING_HE 0x01 +#define SMB2_LEASE_HANDLE_CACHING_HE 0x02 +#define SMB2_LEASE_WRITE_CACHING_HE 0x04 + #define SMB2_LEASE_NONE __constant_cpu_to_le32(0x00) #define SMB2_LEASE_READ_CACHING __constant_cpu_to_le32(0x01) #define SMB2_LEASE_HANDLE_CACHING __constant_cpu_to_le32(0x02) @@ -479,12 +497,31 @@ struct lease_context { __le64 LeaseDuration; } __packed; +struct lease_context_v2 { + __le64 LeaseKeyLow; + __le64 LeaseKeyHigh; + __le32 LeaseState; + __le32 LeaseFlags; + __le64 LeaseDuration; + __le64 ParentLeaseKeyLow; + __le64 ParentLeaseKeyHigh; + __le16 Epoch; + __le16 Reserved; +} __packed; + struct create_lease { struct create_context ccontext; __u8 Name[8]; struct lease_context lcontext; } __packed; +struct create_lease_v2 { + struct create_context ccontext; + __u8 Name[8]; + struct lease_context_v2 lcontext; + __u8 Pad[4]; +} __packed; + struct create_durable { struct create_context ccontext; __u8 Name[8]; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 1a5ecbe..e3fb480 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -53,7 +53,6 @@ extern int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server); extern void smb2_echo_request(struct work_struct *work); extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode); -extern __u8 smb2_map_lease_to_oplock(__le32 lease_state); extern bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv); @@ -87,7 +86,6 @@ extern int smb2_create_hardlink(const unsigned int xid, struct cifs_tcon *tcon, extern int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, FILE_ALL_INFO *buf); -extern void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock); extern int smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile); @@ -106,7 +104,8 @@ extern int SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, extern int SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon); extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, __u8 *oplock, - struct smb2_file_all_info *buf); + struct smb2_file_all_info *buf, + struct smb2_err_rsp **err_buf); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 301b191..340abca 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -42,6 +42,7 @@ static int smb2_crypto_shash_allocate(struct TCP_Server_Info *server) { + int rc; unsigned int size; if (server->secmech.sdeschmacsha256 != NULL) @@ -50,7 +51,9 @@ smb2_crypto_shash_allocate(struct TCP_Server_Info *server) server->secmech.hmacsha256 = crypto_alloc_shash("hmac(sha256)", 0, 0); if (IS_ERR(server->secmech.hmacsha256)) { cifs_dbg(VFS, "could not allocate crypto hmacsha256\n"); - return PTR_ERR(server->secmech.hmacsha256); + rc = PTR_ERR(server->secmech.hmacsha256); + server->secmech.hmacsha256 = NULL; + return rc; } size = sizeof(struct shash_desc) + @@ -87,7 +90,9 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server) server->secmech.sdeschmacsha256 = NULL; crypto_free_shash(server->secmech.hmacsha256); server->secmech.hmacsha256 = NULL; - return PTR_ERR(server->secmech.cmacaes); + rc = PTR_ERR(server->secmech.cmacaes); + server->secmech.cmacaes = NULL; + return rc; } size = sizeof(struct shash_desc) + @@ -109,6 +114,23 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server) return 0; } +static struct cifs_ses * +smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server) +{ + struct cifs_ses *ses; + + spin_lock(&cifs_tcp_ses_lock); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (ses->Suid != smb2hdr->SessionId) + continue; + spin_unlock(&cifs_tcp_ses_lock); + return ses; + } + spin_unlock(&cifs_tcp_ses_lock); + + return NULL; +} + int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) @@ -119,6 +141,13 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base; + struct cifs_ses *ses; + + ses = smb2_find_smb_ses(smb2_pdu, server); + if (!ses) { + cifs_dbg(VFS, "%s: Could not find session\n", __func__); + return 0; + } memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE); memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE); @@ -130,7 +159,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) } rc = crypto_shash_setkey(server->secmech.hmacsha256, - server->session_key.response, SMB2_NTLMV2_SESSKEY_SIZE); + ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { cifs_dbg(VFS, "%s: Could not update with response\n", __func__); return rc; @@ -193,8 +222,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } -void -generate_smb3signingkey(struct TCP_Server_Info *server) +int +generate_smb3signingkey(struct cifs_ses *ses) { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; @@ -204,90 +233,99 @@ generate_smb3signingkey(struct TCP_Server_Info *server) unsigned char *hashptr = prfhash; memset(prfhash, 0x0, SMB2_HMACSHA256_SIZE); - memset(server->smb3signingkey, 0x0, SMB3_SIGNKEY_SIZE); + memset(ses->smb3signingkey, 0x0, SMB3_SIGNKEY_SIZE); - rc = smb3_crypto_shash_allocate(server); + rc = smb3_crypto_shash_allocate(ses->server); if (rc) { cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_setkey(server->secmech.hmacsha256, - server->session_key.response, SMB2_NTLMV2_SESSKEY_SIZE); + rc = crypto_shash_setkey(ses->server->secmech.hmacsha256, + ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { cifs_dbg(VFS, "%s: Could not set with session key\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash); + rc = crypto_shash_init(&ses->server->secmech.sdeschmacsha256->shash); if (rc) { cifs_dbg(VFS, "%s: Could not init sign hmac\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash, i, 4); if (rc) { cifs_dbg(VFS, "%s: Could not update with n\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash, "SMB2AESCMAC", 12); if (rc) { cifs_dbg(VFS, "%s: Could not update with label\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash, &zero, 1); if (rc) { cifs_dbg(VFS, "%s: Could not update with zero\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash, "SmbSign", 8); if (rc) { cifs_dbg(VFS, "%s: Could not update with context\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash, L, 4); if (rc) { cifs_dbg(VFS, "%s: Could not update with L\n", __func__); goto smb3signkey_ret; } - rc = crypto_shash_final(&server->secmech.sdeschmacsha256->shash, + rc = crypto_shash_final(&ses->server->secmech.sdeschmacsha256->shash, hashptr); if (rc) { cifs_dbg(VFS, "%s: Could not generate sha256 hash\n", __func__); goto smb3signkey_ret; } - memcpy(server->smb3signingkey, hashptr, SMB3_SIGNKEY_SIZE); + memcpy(ses->smb3signingkey, hashptr, SMB3_SIGNKEY_SIZE); smb3signkey_ret: - return; + return rc; } int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { - int i, rc; + int i; + int rc = 0; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base; + struct cifs_ses *ses; + + ses = smb2_find_smb_ses(smb2_pdu, server); + if (!ses) { + cifs_dbg(VFS, "%s: Could not find session\n", __func__); + return 0; + } memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE); memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE); rc = crypto_shash_setkey(server->secmech.cmacaes, - server->smb3signingkey, SMB2_CMACAES_SIZE); + ses->smb3signingkey, SMB2_CMACAES_SIZE); + if (rc) { cifs_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__); return rc; @@ -384,6 +422,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)rqst->rq_iov[0].iov_base; if ((smb2_pdu->Command == SMB2_NEGOTIATE) || + (smb2_pdu->Command == SMB2_SESSION_SETUP) || (smb2_pdu->Command == SMB2_OPLOCK_BREAK) || (!server->session_estab)) return 0; diff --git a/fs/cifs/winucase.c b/fs/cifs/winucase.c new file mode 100644 index 0000000..1506d4f --- /dev/null +++ b/fs/cifs/winucase.c @@ -0,0 +1,663 @@ +/* + * fs/cifs/winucase.c + * + * Copyright (c) Jeffrey Layton <jlayton@redhat.com>, 2013 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * The const tables in this file were converted from the following info + * provided by Microsoft: + * + * 3.1.5.3 Mapping UTF-16 Strings to Upper Case: + * + * http://msdn.microsoft.com/en-us/library/hh877830.aspx + * http://www.microsoft.com/en-us/download/details.aspx?displaylang=en&id=10921 + * + * In particular, the table in "Windows 8 Upper Case Mapping Table.txt" was + * post-processed using the winucase_convert.pl script. + */ + +#include <linux/nls.h> + +wchar_t cifs_toupper(wchar_t in); /* quiet sparse */ + +static const wchar_t t2_00[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, + 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, + 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, + 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x0000, + 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x0178, +}; + +static const wchar_t t2_01[256] = { + 0x0000, 0x0100, 0x0000, 0x0102, 0x0000, 0x0104, 0x0000, 0x0106, + 0x0000, 0x0108, 0x0000, 0x010a, 0x0000, 0x010c, 0x0000, 0x010e, + 0x0000, 0x0110, 0x0000, 0x0112, 0x0000, 0x0114, 0x0000, 0x0116, + 0x0000, 0x0118, 0x0000, 0x011a, 0x0000, 0x011c, 0x0000, 0x011e, + 0x0000, 0x0120, 0x0000, 0x0122, 0x0000, 0x0124, 0x0000, 0x0126, + 0x0000, 0x0128, 0x0000, 0x012a, 0x0000, 0x012c, 0x0000, 0x012e, + 0x0000, 0x0000, 0x0000, 0x0132, 0x0000, 0x0134, 0x0000, 0x0136, + 0x0000, 0x0000, 0x0139, 0x0000, 0x013b, 0x0000, 0x013d, 0x0000, + 0x013f, 0x0000, 0x0141, 0x0000, 0x0143, 0x0000, 0x0145, 0x0000, + 0x0147, 0x0000, 0x0000, 0x014a, 0x0000, 0x014c, 0x0000, 0x014e, + 0x0000, 0x0150, 0x0000, 0x0152, 0x0000, 0x0154, 0x0000, 0x0156, + 0x0000, 0x0158, 0x0000, 0x015a, 0x0000, 0x015c, 0x0000, 0x015e, + 0x0000, 0x0160, 0x0000, 0x0162, 0x0000, 0x0164, 0x0000, 0x0166, + 0x0000, 0x0168, 0x0000, 0x016a, 0x0000, 0x016c, 0x0000, 0x016e, + 0x0000, 0x0170, 0x0000, 0x0172, 0x0000, 0x0174, 0x0000, 0x0176, + 0x0000, 0x0000, 0x0179, 0x0000, 0x017b, 0x0000, 0x017d, 0x0000, + 0x0243, 0x0000, 0x0000, 0x0182, 0x0000, 0x0184, 0x0000, 0x0000, + 0x0187, 0x0000, 0x0000, 0x0000, 0x018b, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0191, 0x0000, 0x0000, 0x01f6, 0x0000, 0x0000, + 0x0000, 0x0198, 0x023d, 0x0000, 0x0000, 0x0000, 0x0220, 0x0000, + 0x0000, 0x01a0, 0x0000, 0x01a2, 0x0000, 0x01a4, 0x0000, 0x0000, + 0x01a7, 0x0000, 0x0000, 0x0000, 0x0000, 0x01ac, 0x0000, 0x0000, + 0x01af, 0x0000, 0x0000, 0x0000, 0x01b3, 0x0000, 0x01b5, 0x0000, + 0x0000, 0x01b8, 0x0000, 0x0000, 0x0000, 0x01bc, 0x0000, 0x01f7, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x01c4, 0x0000, + 0x0000, 0x01c7, 0x0000, 0x0000, 0x01ca, 0x0000, 0x01cd, 0x0000, + 0x01cf, 0x0000, 0x01d1, 0x0000, 0x01d3, 0x0000, 0x01d5, 0x0000, + 0x01d7, 0x0000, 0x01d9, 0x0000, 0x01db, 0x018e, 0x0000, 0x01de, + 0x0000, 0x01e0, 0x0000, 0x01e2, 0x0000, 0x01e4, 0x0000, 0x01e6, + 0x0000, 0x01e8, 0x0000, 0x01ea, 0x0000, 0x01ec, 0x0000, 0x01ee, + 0x0000, 0x0000, 0x0000, 0x01f1, 0x0000, 0x01f4, 0x0000, 0x0000, + 0x0000, 0x01f8, 0x0000, 0x01fa, 0x0000, 0x01fc, 0x0000, 0x01fe, +}; + +static const wchar_t t2_02[256] = { + 0x0000, 0x0200, 0x0000, 0x0202, 0x0000, 0x0204, 0x0000, 0x0206, + 0x0000, 0x0208, 0x0000, 0x020a, 0x0000, 0x020c, 0x0000, 0x020e, + 0x0000, 0x0210, 0x0000, 0x0212, 0x0000, 0x0214, 0x0000, 0x0216, + 0x0000, 0x0218, 0x0000, 0x021a, 0x0000, 0x021c, 0x0000, 0x021e, + 0x0000, 0x0000, 0x0000, 0x0222, 0x0000, 0x0224, 0x0000, 0x0226, + 0x0000, 0x0228, 0x0000, 0x022a, 0x0000, 0x022c, 0x0000, 0x022e, + 0x0000, 0x0230, 0x0000, 0x0232, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x023b, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0241, 0x0000, 0x0000, 0x0000, 0x0000, 0x0246, + 0x0000, 0x0248, 0x0000, 0x024a, 0x0000, 0x024c, 0x0000, 0x024e, + 0x2c6f, 0x2c6d, 0x0000, 0x0181, 0x0186, 0x0000, 0x0189, 0x018a, + 0x0000, 0x018f, 0x0000, 0x0190, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0193, 0x0000, 0x0000, 0x0194, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0197, 0x0196, 0x0000, 0x2c62, 0x0000, 0x0000, 0x0000, 0x019c, + 0x0000, 0x2c6e, 0x019d, 0x0000, 0x0000, 0x019f, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2c64, 0x0000, 0x0000, + 0x01a6, 0x0000, 0x0000, 0x01a9, 0x0000, 0x0000, 0x0000, 0x0000, + 0x01ae, 0x0244, 0x01b1, 0x01b2, 0x0245, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x01b7, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_03[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0370, 0x0000, 0x0372, 0x0000, 0x0000, 0x0000, 0x0376, + 0x0000, 0x0000, 0x0000, 0x03fd, 0x03fe, 0x03ff, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0386, 0x0388, 0x0389, 0x038a, + 0x0000, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397, + 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f, + 0x03a0, 0x03a1, 0x0000, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7, + 0x03a8, 0x03a9, 0x03aa, 0x03ab, 0x038c, 0x038e, 0x038f, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x03cf, + 0x0000, 0x03d8, 0x0000, 0x03da, 0x0000, 0x03dc, 0x0000, 0x03de, + 0x0000, 0x03e0, 0x0000, 0x03e2, 0x0000, 0x03e4, 0x0000, 0x03e6, + 0x0000, 0x03e8, 0x0000, 0x03ea, 0x0000, 0x03ec, 0x0000, 0x03ee, + 0x0000, 0x0000, 0x03f9, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x03f7, 0x0000, 0x0000, 0x03fa, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_04[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, + 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f, + 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, + 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f, + 0x0400, 0x0401, 0x0402, 0x0403, 0x0404, 0x0405, 0x0406, 0x0407, + 0x0408, 0x0409, 0x040a, 0x040b, 0x040c, 0x040d, 0x040e, 0x040f, + 0x0000, 0x0460, 0x0000, 0x0462, 0x0000, 0x0464, 0x0000, 0x0466, + 0x0000, 0x0468, 0x0000, 0x046a, 0x0000, 0x046c, 0x0000, 0x046e, + 0x0000, 0x0470, 0x0000, 0x0472, 0x0000, 0x0474, 0x0000, 0x0476, + 0x0000, 0x0478, 0x0000, 0x047a, 0x0000, 0x047c, 0x0000, 0x047e, + 0x0000, 0x0480, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x048a, 0x0000, 0x048c, 0x0000, 0x048e, + 0x0000, 0x0490, 0x0000, 0x0492, 0x0000, 0x0494, 0x0000, 0x0496, + 0x0000, 0x0498, 0x0000, 0x049a, 0x0000, 0x049c, 0x0000, 0x049e, + 0x0000, 0x04a0, 0x0000, 0x04a2, 0x0000, 0x04a4, 0x0000, 0x04a6, + 0x0000, 0x04a8, 0x0000, 0x04aa, 0x0000, 0x04ac, 0x0000, 0x04ae, + 0x0000, 0x04b0, 0x0000, 0x04b2, 0x0000, 0x04b4, 0x0000, 0x04b6, + 0x0000, 0x04b8, 0x0000, 0x04ba, 0x0000, 0x04bc, 0x0000, 0x04be, + 0x0000, 0x0000, 0x04c1, 0x0000, 0x04c3, 0x0000, 0x04c5, 0x0000, + 0x04c7, 0x0000, 0x04c9, 0x0000, 0x04cb, 0x0000, 0x04cd, 0x04c0, + 0x0000, 0x04d0, 0x0000, 0x04d2, 0x0000, 0x04d4, 0x0000, 0x04d6, + 0x0000, 0x04d8, 0x0000, 0x04da, 0x0000, 0x04dc, 0x0000, 0x04de, + 0x0000, 0x04e0, 0x0000, 0x04e2, 0x0000, 0x04e4, 0x0000, 0x04e6, + 0x0000, 0x04e8, 0x0000, 0x04ea, 0x0000, 0x04ec, 0x0000, 0x04ee, + 0x0000, 0x04f0, 0x0000, 0x04f2, 0x0000, 0x04f4, 0x0000, 0x04f6, + 0x0000, 0x04f8, 0x0000, 0x04fa, 0x0000, 0x04fc, 0x0000, 0x04fe, +}; + +static const wchar_t t2_05[256] = { + 0x0000, 0x0500, 0x0000, 0x0502, 0x0000, 0x0504, 0x0000, 0x0506, + 0x0000, 0x0508, 0x0000, 0x050a, 0x0000, 0x050c, 0x0000, 0x050e, + 0x0000, 0x0510, 0x0000, 0x0512, 0x0000, 0x0514, 0x0000, 0x0516, + 0x0000, 0x0518, 0x0000, 0x051a, 0x0000, 0x051c, 0x0000, 0x051e, + 0x0000, 0x0520, 0x0000, 0x0522, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0531, 0x0532, 0x0533, 0x0534, 0x0535, 0x0536, 0x0537, + 0x0538, 0x0539, 0x053a, 0x053b, 0x053c, 0x053d, 0x053e, 0x053f, + 0x0540, 0x0541, 0x0542, 0x0543, 0x0544, 0x0545, 0x0546, 0x0547, + 0x0548, 0x0549, 0x054a, 0x054b, 0x054c, 0x054d, 0x054e, 0x054f, + 0x0550, 0x0551, 0x0552, 0x0553, 0x0554, 0x0555, 0x0556, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_1d[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0xa77d, 0x0000, 0x0000, 0x0000, 0x2c63, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_1e[256] = { + 0x0000, 0x1e00, 0x0000, 0x1e02, 0x0000, 0x1e04, 0x0000, 0x1e06, + 0x0000, 0x1e08, 0x0000, 0x1e0a, 0x0000, 0x1e0c, 0x0000, 0x1e0e, + 0x0000, 0x1e10, 0x0000, 0x1e12, 0x0000, 0x1e14, 0x0000, 0x1e16, + 0x0000, 0x1e18, 0x0000, 0x1e1a, 0x0000, 0x1e1c, 0x0000, 0x1e1e, + 0x0000, 0x1e20, 0x0000, 0x1e22, 0x0000, 0x1e24, 0x0000, 0x1e26, + 0x0000, 0x1e28, 0x0000, 0x1e2a, 0x0000, 0x1e2c, 0x0000, 0x1e2e, + 0x0000, 0x1e30, 0x0000, 0x1e32, 0x0000, 0x1e34, 0x0000, 0x1e36, + 0x0000, 0x1e38, 0x0000, 0x1e3a, 0x0000, 0x1e3c, 0x0000, 0x1e3e, + 0x0000, 0x1e40, 0x0000, 0x1e42, 0x0000, 0x1e44, 0x0000, 0x1e46, + 0x0000, 0x1e48, 0x0000, 0x1e4a, 0x0000, 0x1e4c, 0x0000, 0x1e4e, + 0x0000, 0x1e50, 0x0000, 0x1e52, 0x0000, 0x1e54, 0x0000, 0x1e56, + 0x0000, 0x1e58, 0x0000, 0x1e5a, 0x0000, 0x1e5c, 0x0000, 0x1e5e, + 0x0000, 0x1e60, 0x0000, 0x1e62, 0x0000, 0x1e64, 0x0000, 0x1e66, + 0x0000, 0x1e68, 0x0000, 0x1e6a, 0x0000, 0x1e6c, 0x0000, 0x1e6e, + 0x0000, 0x1e70, 0x0000, 0x1e72, 0x0000, 0x1e74, 0x0000, 0x1e76, + 0x0000, 0x1e78, 0x0000, 0x1e7a, 0x0000, 0x1e7c, 0x0000, 0x1e7e, + 0x0000, 0x1e80, 0x0000, 0x1e82, 0x0000, 0x1e84, 0x0000, 0x1e86, + 0x0000, 0x1e88, 0x0000, 0x1e8a, 0x0000, 0x1e8c, 0x0000, 0x1e8e, + 0x0000, 0x1e90, 0x0000, 0x1e92, 0x0000, 0x1e94, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x1ea0, 0x0000, 0x1ea2, 0x0000, 0x1ea4, 0x0000, 0x1ea6, + 0x0000, 0x1ea8, 0x0000, 0x1eaa, 0x0000, 0x1eac, 0x0000, 0x1eae, + 0x0000, 0x1eb0, 0x0000, 0x1eb2, 0x0000, 0x1eb4, 0x0000, 0x1eb6, + 0x0000, 0x1eb8, 0x0000, 0x1eba, 0x0000, 0x1ebc, 0x0000, 0x1ebe, + 0x0000, 0x1ec0, 0x0000, 0x1ec2, 0x0000, 0x1ec4, 0x0000, 0x1ec6, + 0x0000, 0x1ec8, 0x0000, 0x1eca, 0x0000, 0x1ecc, 0x0000, 0x1ece, + 0x0000, 0x1ed0, 0x0000, 0x1ed2, 0x0000, 0x1ed4, 0x0000, 0x1ed6, + 0x0000, 0x1ed8, 0x0000, 0x1eda, 0x0000, 0x1edc, 0x0000, 0x1ede, + 0x0000, 0x1ee0, 0x0000, 0x1ee2, 0x0000, 0x1ee4, 0x0000, 0x1ee6, + 0x0000, 0x1ee8, 0x0000, 0x1eea, 0x0000, 0x1eec, 0x0000, 0x1eee, + 0x0000, 0x1ef0, 0x0000, 0x1ef2, 0x0000, 0x1ef4, 0x0000, 0x1ef6, + 0x0000, 0x1ef8, 0x0000, 0x1efa, 0x0000, 0x1efc, 0x0000, 0x1efe, +}; + +static const wchar_t t2_1f[256] = { + 0x1f08, 0x1f09, 0x1f0a, 0x1f0b, 0x1f0c, 0x1f0d, 0x1f0e, 0x1f0f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1f18, 0x1f19, 0x1f1a, 0x1f1b, 0x1f1c, 0x1f1d, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1f28, 0x1f29, 0x1f2a, 0x1f2b, 0x1f2c, 0x1f2d, 0x1f2e, 0x1f2f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1f38, 0x1f39, 0x1f3a, 0x1f3b, 0x1f3c, 0x1f3d, 0x1f3e, 0x1f3f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1f48, 0x1f49, 0x1f4a, 0x1f4b, 0x1f4c, 0x1f4d, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x1f59, 0x0000, 0x1f5b, 0x0000, 0x1f5d, 0x0000, 0x1f5f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1f68, 0x1f69, 0x1f6a, 0x1f6b, 0x1f6c, 0x1f6d, 0x1f6e, 0x1f6f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1fba, 0x1fbb, 0x1fc8, 0x1fc9, 0x1fca, 0x1fcb, 0x1fda, 0x1fdb, + 0x1ff8, 0x1ff9, 0x1fea, 0x1feb, 0x1ffa, 0x1ffb, 0x0000, 0x0000, + 0x1f88, 0x1f89, 0x1f8a, 0x1f8b, 0x1f8c, 0x1f8d, 0x1f8e, 0x1f8f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1f98, 0x1f99, 0x1f9a, 0x1f9b, 0x1f9c, 0x1f9d, 0x1f9e, 0x1f9f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1fa8, 0x1fa9, 0x1faa, 0x1fab, 0x1fac, 0x1fad, 0x1fae, 0x1faf, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1fb8, 0x1fb9, 0x0000, 0x1fbc, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x1fcc, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1fd8, 0x1fd9, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x1fe8, 0x1fe9, 0x0000, 0x0000, 0x0000, 0x1fec, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x1ffc, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_21[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2132, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x2160, 0x2161, 0x2162, 0x2163, 0x2164, 0x2165, 0x2166, 0x2167, + 0x2168, 0x2169, 0x216a, 0x216b, 0x216c, 0x216d, 0x216e, 0x216f, + 0x0000, 0x0000, 0x0000, 0x0000, 0x2183, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_24[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x24b6, 0x24b7, 0x24b8, 0x24b9, 0x24ba, 0x24bb, 0x24bc, 0x24bd, + 0x24be, 0x24bf, 0x24c0, 0x24c1, 0x24c2, 0x24c3, 0x24c4, 0x24c5, + 0x24c6, 0x24c7, 0x24c8, 0x24c9, 0x24ca, 0x24cb, 0x24cc, 0x24cd, + 0x24ce, 0x24cf, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_2c[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x2c00, 0x2c01, 0x2c02, 0x2c03, 0x2c04, 0x2c05, 0x2c06, 0x2c07, + 0x2c08, 0x2c09, 0x2c0a, 0x2c0b, 0x2c0c, 0x2c0d, 0x2c0e, 0x2c0f, + 0x2c10, 0x2c11, 0x2c12, 0x2c13, 0x2c14, 0x2c15, 0x2c16, 0x2c17, + 0x2c18, 0x2c19, 0x2c1a, 0x2c1b, 0x2c1c, 0x2c1d, 0x2c1e, 0x2c1f, + 0x2c20, 0x2c21, 0x2c22, 0x2c23, 0x2c24, 0x2c25, 0x2c26, 0x2c27, + 0x2c28, 0x2c29, 0x2c2a, 0x2c2b, 0x2c2c, 0x2c2d, 0x2c2e, 0x0000, + 0x0000, 0x2c60, 0x0000, 0x0000, 0x0000, 0x023a, 0x023e, 0x0000, + 0x2c67, 0x0000, 0x2c69, 0x0000, 0x2c6b, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x2c72, 0x0000, 0x0000, 0x2c75, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x2c80, 0x0000, 0x2c82, 0x0000, 0x2c84, 0x0000, 0x2c86, + 0x0000, 0x2c88, 0x0000, 0x2c8a, 0x0000, 0x2c8c, 0x0000, 0x2c8e, + 0x0000, 0x2c90, 0x0000, 0x2c92, 0x0000, 0x2c94, 0x0000, 0x2c96, + 0x0000, 0x2c98, 0x0000, 0x2c9a, 0x0000, 0x2c9c, 0x0000, 0x2c9e, + 0x0000, 0x2ca0, 0x0000, 0x2ca2, 0x0000, 0x2ca4, 0x0000, 0x2ca6, + 0x0000, 0x2ca8, 0x0000, 0x2caa, 0x0000, 0x2cac, 0x0000, 0x2cae, + 0x0000, 0x2cb0, 0x0000, 0x2cb2, 0x0000, 0x2cb4, 0x0000, 0x2cb6, + 0x0000, 0x2cb8, 0x0000, 0x2cba, 0x0000, 0x2cbc, 0x0000, 0x2cbe, + 0x0000, 0x2cc0, 0x0000, 0x2cc2, 0x0000, 0x2cc4, 0x0000, 0x2cc6, + 0x0000, 0x2cc8, 0x0000, 0x2cca, 0x0000, 0x2ccc, 0x0000, 0x2cce, + 0x0000, 0x2cd0, 0x0000, 0x2cd2, 0x0000, 0x2cd4, 0x0000, 0x2cd6, + 0x0000, 0x2cd8, 0x0000, 0x2cda, 0x0000, 0x2cdc, 0x0000, 0x2cde, + 0x0000, 0x2ce0, 0x0000, 0x2ce2, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_2d[256] = { + 0x10a0, 0x10a1, 0x10a2, 0x10a3, 0x10a4, 0x10a5, 0x10a6, 0x10a7, + 0x10a8, 0x10a9, 0x10aa, 0x10ab, 0x10ac, 0x10ad, 0x10ae, 0x10af, + 0x10b0, 0x10b1, 0x10b2, 0x10b3, 0x10b4, 0x10b5, 0x10b6, 0x10b7, + 0x10b8, 0x10b9, 0x10ba, 0x10bb, 0x10bc, 0x10bd, 0x10be, 0x10bf, + 0x10c0, 0x10c1, 0x10c2, 0x10c3, 0x10c4, 0x10c5, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_a6[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0xa640, 0x0000, 0xa642, 0x0000, 0xa644, 0x0000, 0xa646, + 0x0000, 0xa648, 0x0000, 0xa64a, 0x0000, 0xa64c, 0x0000, 0xa64e, + 0x0000, 0xa650, 0x0000, 0xa652, 0x0000, 0xa654, 0x0000, 0xa656, + 0x0000, 0xa658, 0x0000, 0xa65a, 0x0000, 0xa65c, 0x0000, 0xa65e, + 0x0000, 0x0000, 0x0000, 0xa662, 0x0000, 0xa664, 0x0000, 0xa666, + 0x0000, 0xa668, 0x0000, 0xa66a, 0x0000, 0xa66c, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0xa680, 0x0000, 0xa682, 0x0000, 0xa684, 0x0000, 0xa686, + 0x0000, 0xa688, 0x0000, 0xa68a, 0x0000, 0xa68c, 0x0000, 0xa68e, + 0x0000, 0xa690, 0x0000, 0xa692, 0x0000, 0xa694, 0x0000, 0xa696, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_a7[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0xa722, 0x0000, 0xa724, 0x0000, 0xa726, + 0x0000, 0xa728, 0x0000, 0xa72a, 0x0000, 0xa72c, 0x0000, 0xa72e, + 0x0000, 0x0000, 0x0000, 0xa732, 0x0000, 0xa734, 0x0000, 0xa736, + 0x0000, 0xa738, 0x0000, 0xa73a, 0x0000, 0xa73c, 0x0000, 0xa73e, + 0x0000, 0xa740, 0x0000, 0xa742, 0x0000, 0xa744, 0x0000, 0xa746, + 0x0000, 0xa748, 0x0000, 0xa74a, 0x0000, 0xa74c, 0x0000, 0xa74e, + 0x0000, 0xa750, 0x0000, 0xa752, 0x0000, 0xa754, 0x0000, 0xa756, + 0x0000, 0xa758, 0x0000, 0xa75a, 0x0000, 0xa75c, 0x0000, 0xa75e, + 0x0000, 0xa760, 0x0000, 0xa762, 0x0000, 0xa764, 0x0000, 0xa766, + 0x0000, 0xa768, 0x0000, 0xa76a, 0x0000, 0xa76c, 0x0000, 0xa76e, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0xa779, 0x0000, 0xa77b, 0x0000, 0x0000, 0xa77e, + 0x0000, 0xa780, 0x0000, 0xa782, 0x0000, 0xa784, 0x0000, 0xa786, + 0x0000, 0x0000, 0x0000, 0x0000, 0xa78b, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t t2_ff[256] = { + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0xff21, 0xff22, 0xff23, 0xff24, 0xff25, 0xff26, 0xff27, + 0xff28, 0xff29, 0xff2a, 0xff2b, 0xff2c, 0xff2d, 0xff2e, 0xff2f, + 0xff30, 0xff31, 0xff32, 0xff33, 0xff34, 0xff35, 0xff36, 0xff37, + 0xff38, 0xff39, 0xff3a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, +}; + +static const wchar_t *const toplevel[256] = { + t2_00, t2_01, t2_02, t2_03, t2_04, t2_05, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, t2_1d, t2_1e, t2_1f, + NULL, t2_21, NULL, NULL, t2_24, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, t2_2c, t2_2d, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, t2_a6, t2_a7, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, t2_ff, +}; + +/** + * cifs_toupper - convert a wchar_t from lower to uppercase + * @in: character to convert from lower to uppercase + * + * This function consults the static tables above to convert a wchar_t from + * lower to uppercase. In the event that there is no mapping, the original + * "in" character is returned. + */ +wchar_t +cifs_toupper(wchar_t in) +{ + unsigned char idx; + const wchar_t *tbl; + wchar_t out; + + /* grab upper byte */ + idx = (in & 0xff00) >> 8; + + /* find pointer to 2nd layer table */ + tbl = toplevel[idx]; + if (!tbl) + return in; + + /* grab lower byte */ + idx = in & 0xff; + + /* look up character in table */ + out = tbl[idx]; + if (out) + return out; + + return in; +} diff --git a/fs/coredump.c b/fs/coredump.c index 72f816d..9bdeca1 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -190,6 +190,11 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) err = cn_printf(cn, "%d", task_tgid_vnr(current)); break; + /* global pid */ + case 'P': + err = cn_printf(cn, "%d", + task_tgid_nr(current)); + break; /* uid */ case 'u': err = cn_printf(cn, "%d", cred->uid); diff --git a/fs/dcache.c b/fs/dcache.c index 87bdb53..1bd4614 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -37,6 +37,7 @@ #include <linux/rculist_bl.h> #include <linux/prefetch.h> #include <linux/ratelimit.h> +#include <linux/list_lru.h> #include "internal.h" #include "mount.h" @@ -48,7 +49,7 @@ * - the dcache hash table * s_anon bl list spinlock protects: * - the s_anon list (see __d_drop) - * dcache_lru_lock protects: + * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags @@ -63,7 +64,7 @@ * Ordering: * dentry->d_inode->i_lock * dentry->d_lock - * dcache_lru_lock + * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_anon lock * @@ -81,13 +82,41 @@ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; +/** + * read_seqbegin_or_lock - begin a sequence number check or locking block + * @lock: sequence lock + * @seq : sequence number to be checked + * + * First try it once optimistically without taking the lock. If that fails, + * take the lock. The sequence number is also used as a marker for deciding + * whether to be a reader (even) or writer (odd). + * N.B. seq must be initialized to an even number to begin with. + */ +static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) +{ + if (!(*seq & 1)) /* Even */ + *seq = read_seqbegin(lock); + else /* Odd */ + read_seqlock_excl(lock); +} + +static inline int need_seqretry(seqlock_t *lock, int seq) +{ + return !(seq & 1) && read_seqretry(lock, seq); +} + +static inline void done_seqretry(seqlock_t *lock, int seq) +{ + if (seq & 1) + read_sequnlock_excl(lock); +} + /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try @@ -117,23 +146,47 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; -static DEFINE_PER_CPU(unsigned int, nr_dentry); +static DEFINE_PER_CPU(long, nr_dentry); +static DEFINE_PER_CPU(long, nr_dentry_unused); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -static int get_nr_dentry(void) + +/* + * Here we resort to our own counters instead of using generic per-cpu counters + * for consistency with what the vfs inode code does. We are expected to harvest + * better code and performance by having our own specialized counters. + * + * Please note that the loop is done over all possible CPUs, not over all online + * CPUs. The reason for this is that we don't want to play games with CPUs going + * on and off. If one of them goes off, we will just keep their counters. + * + * glommer: See cffbc8a for details, and if you ever intend to change this, + * please update all vfs counters to match. + */ +static long get_nr_dentry(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } +static long get_nr_dentry_unused(void) +{ + int i; + long sum = 0; + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry_unused, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); - return proc_dointvec(table, write, buffer, lenp, ppos); + dentry_stat.nr_unused = get_nr_dentry_unused(); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -229,7 +282,7 @@ static void __d_free(struct rcu_head *head) */ static void d_free(struct dentry *dentry) { - BUG_ON(dentry->d_count); + BUG_ON((int)dentry->d_lockref.count > 0); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); @@ -304,50 +357,35 @@ static void dentry_unlink_inode(struct dentry * dentry) } /* - * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held. + * dentry_lru_(add|del)_list) must be called with d_lock held. */ static void dentry_lru_add(struct dentry *dentry) { - if (list_empty(&dentry->d_lru)) { - spin_lock(&dcache_lru_lock); - list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); - dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; - spin_unlock(&dcache_lru_lock); + if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) { + if (list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)) + this_cpu_inc(nr_dentry_unused); + dentry->d_flags |= DCACHE_LRU_LIST; } } -static void __dentry_lru_del(struct dentry *dentry) -{ - list_del_init(&dentry->d_lru); - dentry->d_flags &= ~DCACHE_SHRINK_LIST; - dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; -} - /* * Remove a dentry with references from the LRU. + * + * If we are on the shrink list, then we can get to try_prune_one_dentry() and + * lose our last reference through the parent walk. In this case, we need to + * remove ourselves from the shrink list, not the LRU. */ static void dentry_lru_del(struct dentry *dentry) { - if (!list_empty(&dentry->d_lru)) { - spin_lock(&dcache_lru_lock); - __dentry_lru_del(dentry); - spin_unlock(&dcache_lru_lock); + if (dentry->d_flags & DCACHE_SHRINK_LIST) { + list_del_init(&dentry->d_lru); + dentry->d_flags &= ~DCACHE_SHRINK_LIST; + return; } -} -static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list) -{ - spin_lock(&dcache_lru_lock); - if (list_empty(&dentry->d_lru)) { - list_add_tail(&dentry->d_lru, list); - dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; - } else { - list_move_tail(&dentry->d_lru, list); - } - spin_unlock(&dcache_lru_lock); + if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)) + this_cpu_dec(nr_dentry_unused); + dentry->d_flags &= ~DCACHE_LRU_LIST; } /** @@ -443,7 +481,8 @@ EXPORT_SYMBOL(d_drop); * If ref is non-zero, then decrement the refcount too. * Returns dentry requiring refcount drop, or NULL if we're done. */ -static inline struct dentry *dentry_kill(struct dentry *dentry, int ref) +static inline struct dentry * +dentry_kill(struct dentry *dentry, int unlock_on_failure) __releases(dentry->d_lock) { struct inode *inode; @@ -452,8 +491,10 @@ static inline struct dentry *dentry_kill(struct dentry *dentry, int ref) inode = dentry->d_inode; if (inode && !spin_trylock(&inode->i_lock)) { relock: - spin_unlock(&dentry->d_lock); - cpu_relax(); + if (unlock_on_failure) { + spin_unlock(&dentry->d_lock); + cpu_relax(); + } return dentry; /* try again with same dentry */ } if (IS_ROOT(dentry)) @@ -466,13 +507,16 @@ relock: goto relock; } - if (ref) - dentry->d_count--; + /* + * The dentry is now unrecoverably dead to the world. + */ + lockref_mark_dead(&dentry->d_lockref); + /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ - if (dentry->d_flags & DCACHE_OP_PRUNE) + if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry)) dentry->d_op->d_prune(dentry); dentry_lru_del(dentry); @@ -509,33 +553,26 @@ relock: */ void dput(struct dentry *dentry) { - if (!dentry) + if (unlikely(!dentry)) return; repeat: - if (dentry->d_count == 1) - might_sleep(); - spin_lock(&dentry->d_lock); - BUG_ON(!dentry->d_count); - if (dentry->d_count > 1) { - dentry->d_count--; - spin_unlock(&dentry->d_lock); + if (lockref_put_or_lock(&dentry->d_lockref)) return; - } - if (dentry->d_flags & DCACHE_OP_DELETE) { + /* Unreachable? Get rid of it */ + if (unlikely(d_unhashed(dentry))) + goto kill_it; + + if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) goto kill_it; } - /* Unreachable? Get rid of it */ - if (d_unhashed(dentry)) - goto kill_it; - dentry->d_flags |= DCACHE_REFERENCED; dentry_lru_add(dentry); - dentry->d_count--; + dentry->d_lockref.count--; spin_unlock(&dentry->d_lock); return; @@ -590,7 +627,7 @@ int d_invalidate(struct dentry * dentry) * We also need to leave mountpoints alone, * directory or not. */ - if (dentry->d_count > 1 && dentry->d_inode) { + if (dentry->d_lockref.count > 1 && dentry->d_inode) { if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) { spin_unlock(&dentry->d_lock); return -EBUSY; @@ -606,20 +643,33 @@ EXPORT_SYMBOL(d_invalidate); /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) { - dentry->d_count++; + dentry->d_lockref.count++; } static inline void __dget(struct dentry *dentry) { - spin_lock(&dentry->d_lock); - __dget_dlock(dentry); - spin_unlock(&dentry->d_lock); + lockref_get(&dentry->d_lockref); } struct dentry *dget_parent(struct dentry *dentry) { + int gotref; struct dentry *ret; + /* + * Do optimistic parent lookup without any + * locking. + */ + rcu_read_lock(); + ret = ACCESS_ONCE(dentry->d_parent); + gotref = lockref_get_not_zero(&ret->d_lockref); + rcu_read_unlock(); + if (likely(gotref)) { + if (likely(ret == ACCESS_ONCE(dentry->d_parent))) + return ret; + dput(ret); + } + repeat: /* * Don't need rcu_dereference because we re-check it was correct under @@ -634,8 +684,8 @@ repeat: goto repeat; } rcu_read_unlock(); - BUG_ON(!ret->d_count); - ret->d_count++; + BUG_ON(!ret->d_lockref.count); + ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } @@ -718,7 +768,15 @@ restart: spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); - if (!dentry->d_count) { + if (!dentry->d_lockref.count) { + /* + * inform the fs via d_prune that this dentry + * is about to be unhashed and destroyed. + */ + if ((dentry->d_flags & DCACHE_OP_PRUNE) && + !d_unhashed(dentry)) + dentry->d_op->d_prune(dentry); + __dget_dlock(dentry); __d_drop(dentry); spin_unlock(&dentry->d_lock); @@ -739,7 +797,7 @@ EXPORT_SYMBOL(d_prune_aliases); * * This may fail if locks cannot be acquired no problem, just try again. */ -static void try_prune_one_dentry(struct dentry *dentry) +static struct dentry * try_prune_one_dentry(struct dentry *dentry) __releases(dentry->d_lock) { struct dentry *parent; @@ -756,21 +814,18 @@ static void try_prune_one_dentry(struct dentry *dentry) * fragmentation. */ if (!parent) - return; + return NULL; if (parent == dentry) - return; + return dentry; /* Prune ancestors. */ dentry = parent; while (dentry) { - spin_lock(&dentry->d_lock); - if (dentry->d_count > 1) { - dentry->d_count--; - spin_unlock(&dentry->d_lock); - return; - } + if (lockref_put_or_lock(&dentry->d_lockref)) + return NULL; dentry = dentry_kill(dentry, 1); } + return NULL; } static void shrink_dentry_list(struct list_head *list) @@ -789,76 +844,143 @@ static void shrink_dentry_list(struct list_head *list) } /* + * The dispose list is isolated and dentries are not accounted + * to the LRU here, so we can simply remove it from the list + * here regardless of whether it is referenced or not. + */ + list_del_init(&dentry->d_lru); + dentry->d_flags &= ~DCACHE_SHRINK_LIST; + + /* * We found an inuse dentry which was not removed from - * the LRU because of laziness during lookup. Do not free - * it - just keep it off the LRU list. + * the LRU because of laziness during lookup. Do not free it. */ - if (dentry->d_count) { - dentry_lru_del(dentry); + if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); continue; } - rcu_read_unlock(); - try_prune_one_dentry(dentry); + dentry = try_prune_one_dentry(dentry); rcu_read_lock(); + if (dentry) { + dentry->d_flags |= DCACHE_SHRINK_LIST; + list_add(&dentry->d_lru, list); + spin_unlock(&dentry->d_lock); + } } rcu_read_unlock(); } +static enum lru_status +dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg) +{ + struct list_head *freeable = arg; + struct dentry *dentry = container_of(item, struct dentry, d_lru); + + + /* + * we are inverting the lru lock/dentry->d_lock here, + * so use a trylock. If we fail to get the lock, just skip + * it + */ + if (!spin_trylock(&dentry->d_lock)) + return LRU_SKIP; + + /* + * Referenced dentries are still in use. If they have active + * counts, just remove them from the LRU. Otherwise give them + * another pass through the LRU. + */ + if (dentry->d_lockref.count) { + list_del_init(&dentry->d_lru); + spin_unlock(&dentry->d_lock); + return LRU_REMOVED; + } + + if (dentry->d_flags & DCACHE_REFERENCED) { + dentry->d_flags &= ~DCACHE_REFERENCED; + spin_unlock(&dentry->d_lock); + + /* + * The list move itself will be made by the common LRU code. At + * this point, we've dropped the dentry->d_lock but keep the + * lru lock. This is safe to do, since every list movement is + * protected by the lru lock even if both locks are held. + * + * This is guaranteed by the fact that all LRU management + * functions are intermediated by the LRU API calls like + * list_lru_add and list_lru_del. List movement in this file + * only ever occur through this functions or through callbacks + * like this one, that are called from the LRU API. + * + * The only exceptions to this are functions like + * shrink_dentry_list, and code that first checks for the + * DCACHE_SHRINK_LIST flag. Those are guaranteed to be + * operating only with stack provided lists after they are + * properly isolated from the main list. It is thus, always a + * local access. + */ + return LRU_ROTATE; + } + + dentry->d_flags |= DCACHE_SHRINK_LIST; + list_move_tail(&dentry->d_lru, freeable); + this_cpu_dec(nr_dentry_unused); + spin_unlock(&dentry->d_lock); + + return LRU_REMOVED; +} + /** * prune_dcache_sb - shrink the dcache * @sb: superblock - * @count: number of entries to try to free + * @nr_to_scan : number of entries to try to free + * @nid: which node to scan for freeable entities * - * Attempt to shrink the superblock dcache LRU by @count entries. This is + * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is * done when we need more memory an called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ -void prune_dcache_sb(struct super_block *sb, int count) +long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid) { - struct dentry *dentry; - LIST_HEAD(referenced); - LIST_HEAD(tmp); + LIST_HEAD(dispose); + long freed; -relock: - spin_lock(&dcache_lru_lock); - while (!list_empty(&sb->s_dentry_lru)) { - dentry = list_entry(sb->s_dentry_lru.prev, - struct dentry, d_lru); - BUG_ON(dentry->d_sb != sb); - - if (!spin_trylock(&dentry->d_lock)) { - spin_unlock(&dcache_lru_lock); - cpu_relax(); - goto relock; - } + freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate, + &dispose, &nr_to_scan); + shrink_dentry_list(&dispose); + return freed; +} - if (dentry->d_flags & DCACHE_REFERENCED) { - dentry->d_flags &= ~DCACHE_REFERENCED; - list_move(&dentry->d_lru, &referenced); - spin_unlock(&dentry->d_lock); - } else { - list_move_tail(&dentry->d_lru, &tmp); - dentry->d_flags |= DCACHE_SHRINK_LIST; - spin_unlock(&dentry->d_lock); - if (!--count) - break; - } - cond_resched_lock(&dcache_lru_lock); - } - if (!list_empty(&referenced)) - list_splice(&referenced, &sb->s_dentry_lru); - spin_unlock(&dcache_lru_lock); +static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, + spinlock_t *lru_lock, void *arg) +{ + struct list_head *freeable = arg; + struct dentry *dentry = container_of(item, struct dentry, d_lru); + + /* + * we are inverting the lru lock/dentry->d_lock here, + * so use a trylock. If we fail to get the lock, just skip + * it + */ + if (!spin_trylock(&dentry->d_lock)) + return LRU_SKIP; + + dentry->d_flags |= DCACHE_SHRINK_LIST; + list_move_tail(&dentry->d_lru, freeable); + this_cpu_dec(nr_dentry_unused); + spin_unlock(&dentry->d_lock); - shrink_dentry_list(&tmp); + return LRU_REMOVED; } + /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock @@ -868,16 +990,17 @@ relock: */ void shrink_dcache_sb(struct super_block *sb) { - LIST_HEAD(tmp); + long freed; - spin_lock(&dcache_lru_lock); - while (!list_empty(&sb->s_dentry_lru)) { - list_splice_init(&sb->s_dentry_lru, &tmp); - spin_unlock(&dcache_lru_lock); - shrink_dentry_list(&tmp); - spin_lock(&dcache_lru_lock); - } - spin_unlock(&dcache_lru_lock); + do { + LIST_HEAD(dispose); + + freed = list_lru_walk(&sb->s_dentry_lru, + dentry_lru_isolate_shrink, &dispose, UINT_MAX); + + this_cpu_sub(nr_dentry_unused, freed); + shrink_dentry_list(&dispose); + } while (freed > 0); } EXPORT_SYMBOL(shrink_dcache_sb); @@ -907,13 +1030,14 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) * inform the fs that this dentry is about to be * unhashed and destroyed. */ - if (dentry->d_flags & DCACHE_OP_PRUNE) + if ((dentry->d_flags & DCACHE_OP_PRUNE) && + !d_unhashed(dentry)) dentry->d_op->d_prune(dentry); dentry_lru_del(dentry); __d_shrink(dentry); - if (dentry->d_count != 0) { + if (dentry->d_lockref.count != 0) { printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%s}" " still in use (%d)" @@ -922,7 +1046,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry->d_name.name, - dentry->d_count, + dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); BUG(); @@ -933,7 +1057,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) list_del(&dentry->d_u.d_child); } else { parent = dentry->d_parent; - parent->d_count--; + parent->d_lockref.count--; list_del(&dentry->d_u.d_child); } @@ -981,7 +1105,7 @@ void shrink_dcache_for_umount(struct super_block *sb) dentry = sb->s_root; sb->s_root = NULL; - dentry->d_count--; + dentry->d_lockref.count--; shrink_dcache_for_umount_subtree(dentry); while (!hlist_bl_empty(&sb->s_anon)) { @@ -996,7 +1120,7 @@ void shrink_dcache_for_umount(struct super_block *sb) * the parenthood after dropping the lock and check * that the sequence number still matches. */ -static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq) +static struct dentry *try_to_ascend(struct dentry *old, unsigned seq) { struct dentry *new = old->d_parent; @@ -1010,7 +1134,7 @@ static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq */ if (new != old->d_parent || (old->d_flags & DCACHE_DENTRY_KILLED) || - (!locked && read_seqretry(&rename_lock, seq))) { + need_seqretry(&rename_lock, seq)) { spin_unlock(&new->d_lock); new = NULL; } @@ -1018,34 +1142,55 @@ static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq return new; } +/** + * enum d_walk_ret - action to talke during tree walk + * @D_WALK_CONTINUE: contrinue walk + * @D_WALK_QUIT: quit walk + * @D_WALK_NORETRY: quit when retry is needed + * @D_WALK_SKIP: skip this dentry and its children + */ +enum d_walk_ret { + D_WALK_CONTINUE, + D_WALK_QUIT, + D_WALK_NORETRY, + D_WALK_SKIP, +}; -/* - * Search for at least 1 mount point in the dentry's subdirs. - * We descend to the next level whenever the d_subdirs - * list is non-empty and continue searching. - */ - /** - * have_submounts - check for mounts over a dentry - * @parent: dentry to check. + * d_walk - walk the dentry tree + * @parent: start of walk + * @data: data passed to @enter() and @finish() + * @enter: callback when first entering the dentry + * @finish: callback when successfully finished the walk * - * Return true if the parent or its subdirectories contain - * a mount point + * The @enter() and @finish() callbacks are called with d_lock held. */ -int have_submounts(struct dentry *parent) +static void d_walk(struct dentry *parent, void *data, + enum d_walk_ret (*enter)(void *, struct dentry *), + void (*finish)(void *)) { struct dentry *this_parent; struct list_head *next; - unsigned seq; - int locked = 0; + unsigned seq = 0; + enum d_walk_ret ret; + bool retry = true; - seq = read_seqbegin(&rename_lock); again: + read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; - - if (d_mountpoint(parent)) - goto positive; spin_lock(&this_parent->d_lock); + + ret = enter(data, this_parent); + switch (ret) { + case D_WALK_CONTINUE: + break; + case D_WALK_QUIT: + case D_WALK_SKIP: + goto out_unlock; + case D_WALK_NORETRY: + retry = false; + break; + } repeat: next = this_parent->d_subdirs.next; resume: @@ -1055,12 +1200,22 @@ resume: next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - /* Have we found a mount point ? */ - if (d_mountpoint(dentry)) { + + ret = enter(data, dentry); + switch (ret) { + case D_WALK_CONTINUE: + break; + case D_WALK_QUIT: spin_unlock(&dentry->d_lock); - spin_unlock(&this_parent->d_lock); - goto positive; + goto out_unlock; + case D_WALK_NORETRY: + retry = false; + break; + case D_WALK_SKIP: + spin_unlock(&dentry->d_lock); + continue; } + if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); @@ -1075,35 +1230,99 @@ resume: */ if (this_parent != parent) { struct dentry *child = this_parent; - this_parent = try_to_ascend(this_parent, locked, seq); + this_parent = try_to_ascend(this_parent, seq); if (!this_parent) goto rename_retry; next = child->d_u.d_child.next; goto resume; } - spin_unlock(&this_parent->d_lock); - if (!locked && read_seqretry(&rename_lock, seq)) + if (need_seqretry(&rename_lock, seq)) { + spin_unlock(&this_parent->d_lock); goto rename_retry; - if (locked) - write_sequnlock(&rename_lock); - return 0; /* No mount points found in tree */ -positive: - if (!locked && read_seqretry(&rename_lock, seq)) - goto rename_retry; - if (locked) - write_sequnlock(&rename_lock); - return 1; + } + if (finish) + finish(data); + +out_unlock: + spin_unlock(&this_parent->d_lock); + done_seqretry(&rename_lock, seq); + return; rename_retry: - if (locked) - goto again; - locked = 1; - write_seqlock(&rename_lock); + if (!retry) + return; + seq = 1; goto again; } + +/* + * Search for at least 1 mount point in the dentry's subdirs. + * We descend to the next level whenever the d_subdirs + * list is non-empty and continue searching. + */ + +/** + * have_submounts - check for mounts over a dentry + * @parent: dentry to check. + * + * Return true if the parent or its subdirectories contain + * a mount point + */ + +static enum d_walk_ret check_mount(void *data, struct dentry *dentry) +{ + int *ret = data; + if (d_mountpoint(dentry)) { + *ret = 1; + return D_WALK_QUIT; + } + return D_WALK_CONTINUE; +} + +int have_submounts(struct dentry *parent) +{ + int ret = 0; + + d_walk(parent, &ret, check_mount, NULL); + + return ret; +} EXPORT_SYMBOL(have_submounts); /* + * Called by mount code to set a mountpoint and check if the mountpoint is + * reachable (e.g. NFS can unhash a directory dentry and then the complete + * subtree can become unreachable). + * + * Only one of check_submounts_and_drop() and d_set_mounted() must succeed. For + * this reason take rename_lock and d_lock on dentry and ancestors. + */ +int d_set_mounted(struct dentry *dentry) +{ + struct dentry *p; + int ret = -ENOENT; + write_seqlock(&rename_lock); + for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { + /* Need exclusion wrt. check_submounts_and_drop() */ + spin_lock(&p->d_lock); + if (unlikely(d_unhashed(p))) { + spin_unlock(&p->d_lock); + goto out; + } + spin_unlock(&p->d_lock); + } + spin_lock(&dentry->d_lock); + if (!d_unlinked(dentry)) { + dentry->d_flags |= DCACHE_MOUNTED; + ret = 0; + } + spin_unlock(&dentry->d_lock); +out: + write_sequnlock(&rename_lock); + return ret; +} + +/* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level @@ -1117,93 +1336,47 @@ EXPORT_SYMBOL(have_submounts); * drop the lock and return early due to latency * constraints. */ -static int select_parent(struct dentry *parent, struct list_head *dispose) -{ - struct dentry *this_parent; - struct list_head *next; - unsigned seq; - int found = 0; - int locked = 0; - seq = read_seqbegin(&rename_lock); -again: - this_parent = parent; - spin_lock(&this_parent->d_lock); -repeat: - next = this_parent->d_subdirs.next; -resume: - while (next != &this_parent->d_subdirs) { - struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); - next = tmp->next; +struct select_data { + struct dentry *start; + struct list_head dispose; + int found; +}; - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); +static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) +{ + struct select_data *data = _data; + enum d_walk_ret ret = D_WALK_CONTINUE; - /* - * move only zero ref count dentries to the dispose list. - * - * Those which are presently on the shrink list, being processed - * by shrink_dentry_list(), shouldn't be moved. Otherwise the - * loop in shrink_dcache_parent() might not make any progress - * and loop forever. - */ - if (dentry->d_count) { - dentry_lru_del(dentry); - } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { - dentry_lru_move_list(dentry, dispose); - dentry->d_flags |= DCACHE_SHRINK_LIST; - found++; - } - /* - * We can return to the caller if we have found some (this - * ensures forward progress). We'll be coming back to find - * the rest. - */ - if (found && need_resched()) { - spin_unlock(&dentry->d_lock); - goto out; - } + if (data->start == dentry) + goto out; - /* - * Descend a level if the d_subdirs list is non-empty. - */ - if (!list_empty(&dentry->d_subdirs)) { - spin_unlock(&this_parent->d_lock); - spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); - this_parent = dentry; - spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); - goto repeat; - } - - spin_unlock(&dentry->d_lock); - } /* - * All done at this level ... ascend and resume the search. + * move only zero ref count dentries to the dispose list. + * + * Those which are presently on the shrink list, being processed + * by shrink_dentry_list(), shouldn't be moved. Otherwise the + * loop in shrink_dcache_parent() might not make any progress + * and loop forever. */ - if (this_parent != parent) { - struct dentry *child = this_parent; - this_parent = try_to_ascend(this_parent, locked, seq); - if (!this_parent) - goto rename_retry; - next = child->d_u.d_child.next; - goto resume; + if (dentry->d_lockref.count) { + dentry_lru_del(dentry); + } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { + dentry_lru_del(dentry); + list_add_tail(&dentry->d_lru, &data->dispose); + dentry->d_flags |= DCACHE_SHRINK_LIST; + data->found++; + ret = D_WALK_NORETRY; } + /* + * We can return to the caller if we have found some (this + * ensures forward progress). We'll be coming back to find + * the rest. + */ + if (data->found && need_resched()) + ret = D_WALK_QUIT; out: - spin_unlock(&this_parent->d_lock); - if (!locked && read_seqretry(&rename_lock, seq)) - goto rename_retry; - if (locked) - write_sequnlock(&rename_lock); - return found; - -rename_retry: - if (found) - return found; - if (locked) - goto again; - locked = 1; - write_seqlock(&rename_lock); - goto again; + return ret; } /** @@ -1212,18 +1385,90 @@ rename_retry: * * Prune the dcache to remove unused children of the parent dentry. */ -void shrink_dcache_parent(struct dentry * parent) +void shrink_dcache_parent(struct dentry *parent) { - LIST_HEAD(dispose); - int found; + for (;;) { + struct select_data data; - while ((found = select_parent(parent, &dispose)) != 0) { - shrink_dentry_list(&dispose); + INIT_LIST_HEAD(&data.dispose); + data.start = parent; + data.found = 0; + + d_walk(parent, &data, select_collect, NULL); + if (!data.found) + break; + + shrink_dentry_list(&data.dispose); cond_resched(); } } EXPORT_SYMBOL(shrink_dcache_parent); +static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry) +{ + struct select_data *data = _data; + + if (d_mountpoint(dentry)) { + data->found = -EBUSY; + return D_WALK_QUIT; + } + + return select_collect(_data, dentry); +} + +static void check_and_drop(void *_data) +{ + struct select_data *data = _data; + + if (d_mountpoint(data->start)) + data->found = -EBUSY; + if (!data->found) + __d_drop(data->start); +} + +/** + * check_submounts_and_drop - prune dcache, check for submounts and drop + * + * All done as a single atomic operation relative to has_unlinked_ancestor(). + * Returns 0 if successfully unhashed @parent. If there were submounts then + * return -EBUSY. + * + * @dentry: dentry to prune and drop + */ +int check_submounts_and_drop(struct dentry *dentry) +{ + int ret = 0; + + /* Negative dentries can be dropped without further checks */ + if (!dentry->d_inode) { + d_drop(dentry); + goto out; + } + + for (;;) { + struct select_data data; + + INIT_LIST_HEAD(&data.dispose); + data.start = dentry; + data.found = 0; + + d_walk(dentry, &data, check_and_collect, check_and_drop); + ret = data.found; + + if (!list_empty(&data.dispose)) + shrink_dentry_list(&data.dispose); + + if (ret <= 0) + break; + + cond_resched(); + } + +out: + return ret; +} +EXPORT_SYMBOL(check_submounts_and_drop); + /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to @@ -1269,7 +1514,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) smp_wmb(); dentry->d_name.name = dname; - dentry->d_count = 1; + dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_init(&dentry->d_seq); @@ -1782,7 +2027,7 @@ static noinline enum slow_d_compare slow_dentry_cmp( * without taking d_lock and checking d_seq sequence count against @seq * returned here. * - * A refcount may be taken on the found dentry with the __d_rcu_to_refcount + * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of @@ -1970,7 +2215,7 @@ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) goto next; } - dentry->d_count++; + dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; @@ -2069,7 +2314,7 @@ again: spin_lock(&dentry->d_lock); inode = dentry->d_inode; isdir = S_ISDIR(inode->i_mode); - if (dentry->d_count == 1) { + if (dentry->d_lockref.count == 1) { if (!spin_trylock(&inode->i_lock)) { spin_unlock(&dentry->d_lock); cpu_relax(); @@ -2506,9 +2751,39 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) return 0; } +/** + * prepend_name - prepend a pathname in front of current buffer pointer + * @buffer: buffer pointer + * @buflen: allocated length of the buffer + * @name: name string and length qstr structure + * + * With RCU path tracing, it may race with d_move(). Use ACCESS_ONCE() to + * make sure that either the old or the new name pointer and length are + * fetched. However, there may be mismatch between length and pointer. + * The length cannot be trusted, we need to copy it byte-by-byte until + * the length is reached or a null byte is found. It also prepends "/" at + * the beginning of the name. The sequence number check at the caller will + * retry it again when a d_move() does happen. So any garbage in the buffer + * due to mismatched pointer and length will be discarded. + */ static int prepend_name(char **buffer, int *buflen, struct qstr *name) { - return prepend(buffer, buflen, name->name, name->len); + const char *dname = ACCESS_ONCE(name->name); + u32 dlen = ACCESS_ONCE(name->len); + char *p; + + if (*buflen < dlen + 1) + return -ENAMETOOLONG; + *buflen -= dlen + 1; + p = *buffer -= dlen + 1; + *p++ = '/'; + while (dlen--) { + char c = *dname++; + if (!c) + break; + *p++ = c; + } + return 0; } /** @@ -2518,7 +2793,15 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) * @buffer: pointer to the end of the buffer * @buflen: pointer to buffer length * - * Caller holds the rename_lock. + * The function will first try to write out the pathname without taking any + * lock other than the RCU read lock to make sure that dentries won't go away. + * It only checks the sequence number of the global rename_lock as any change + * in the dentry's d_seq will be preceded by changes in the rename_lock + * sequence number. If the sequence number had been changed, it will restart + * the whole pathname back-tracing sequence again by taking the rename_lock. + * In this case, there is no need to take the RCU read lock as the recursive + * parent pointer references will keep the dentry chain alive as long as no + * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, @@ -2527,54 +2810,66 @@ static int prepend_path(const struct path *path, struct dentry *dentry = path->dentry; struct vfsmount *vfsmnt = path->mnt; struct mount *mnt = real_mount(vfsmnt); - bool slash = false; int error = 0; + unsigned seq = 0; + char *bptr; + int blen; + rcu_read_lock(); +restart: + bptr = *buffer; + blen = *buflen; + read_seqbegin_or_lock(&rename_lock, &seq); while (dentry != root->dentry || vfsmnt != root->mnt) { struct dentry * parent; if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { /* Global root? */ - if (!mnt_has_parent(mnt)) - goto global_root; - dentry = mnt->mnt_mountpoint; - mnt = mnt->mnt_parent; - vfsmnt = &mnt->mnt; - continue; + if (mnt_has_parent(mnt)) { + dentry = mnt->mnt_mountpoint; + mnt = mnt->mnt_parent; + vfsmnt = &mnt->mnt; + continue; + } + /* + * Filesystems needing to implement special "root names" + * should do so with ->d_dname() + */ + if (IS_ROOT(dentry) && + (dentry->d_name.len != 1 || + dentry->d_name.name[0] != '/')) { + WARN(1, "Root dentry has weird name <%.*s>\n", + (int) dentry->d_name.len, + dentry->d_name.name); + } + if (!error) + error = is_mounted(vfsmnt) ? 1 : 2; + break; } parent = dentry->d_parent; prefetch(parent); - spin_lock(&dentry->d_lock); - error = prepend_name(buffer, buflen, &dentry->d_name); - spin_unlock(&dentry->d_lock); - if (!error) - error = prepend(buffer, buflen, "/", 1); + error = prepend_name(&bptr, &blen, &dentry->d_name); if (error) break; - slash = true; dentry = parent; } + if (!(seq & 1)) + rcu_read_unlock(); + if (need_seqretry(&rename_lock, seq)) { + seq = 1; + goto restart; + } + done_seqretry(&rename_lock, seq); - if (!error && !slash) - error = prepend(buffer, buflen, "/", 1); - - return error; - -global_root: - /* - * Filesystems needing to implement special "root names" - * should do so with ->d_dname() - */ - if (IS_ROOT(dentry) && - (dentry->d_name.len != 1 || dentry->d_name.name[0] != '/')) { - WARN(1, "Root dentry has weird name <%.*s>\n", - (int) dentry->d_name.len, dentry->d_name.name); - } - if (!slash) - error = prepend(buffer, buflen, "/", 1); - if (!error) - error = is_mounted(vfsmnt) ? 1 : 2; + if (error >= 0 && bptr == *buffer) { + if (--blen < 0) + error = -ENAMETOOLONG; + else + *--bptr = '/'; + } + *buffer = bptr; + *buflen = blen; return error; } @@ -2603,9 +2898,7 @@ char *__d_path(const struct path *path, prepend(&res, &buflen, "\0", 1); br_read_lock(&vfsmount_lock); - write_seqlock(&rename_lock); error = prepend_path(path, root, &res, &buflen); - write_sequnlock(&rename_lock); br_read_unlock(&vfsmount_lock); if (error < 0) @@ -2624,9 +2917,7 @@ char *d_absolute_path(const struct path *path, prepend(&res, &buflen, "\0", 1); br_read_lock(&vfsmount_lock); - write_seqlock(&rename_lock); error = prepend_path(path, &root, &res, &buflen); - write_sequnlock(&rename_lock); br_read_unlock(&vfsmount_lock); if (error > 1) @@ -2658,6 +2949,16 @@ static int prepend_unreachable(char **buffer, int *buflen) return prepend(buffer, buflen, "(unreachable)", 13); } +static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) +{ + unsigned seq; + + do { + seq = read_seqcount_begin(&fs->seq); + *root = fs->root; + } while (read_seqcount_retry(&fs->seq, seq)); +} + /** * d_path - return the path of a dentry * @path: path to report @@ -2690,15 +2991,15 @@ char *d_path(const struct path *path, char *buf, int buflen) if (path->dentry->d_op && path->dentry->d_op->d_dname) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); - get_fs_root(current->fs, &root); + rcu_read_lock(); + get_fs_root_rcu(current->fs, &root); br_read_lock(&vfsmount_lock); - write_seqlock(&rename_lock); error = path_with_deleted(path, &root, &res, &buflen); - write_sequnlock(&rename_lock); br_read_unlock(&vfsmount_lock); + rcu_read_unlock(); + if (error < 0) res = ERR_PTR(error); - path_put(&root); return res; } EXPORT_SYMBOL(d_path); @@ -2724,35 +3025,58 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen, return memcpy(buffer, temp, sz); } +char *simple_dname(struct dentry *dentry, char *buffer, int buflen) +{ + char *end = buffer + buflen; + /* these dentries are never renamed, so d_lock is not needed */ + if (prepend(&end, &buflen, " (deleted)", 11) || + prepend(&end, &buflen, dentry->d_name.name, dentry->d_name.len) || + prepend(&end, &buflen, "/", 1)) + end = ERR_PTR(-ENAMETOOLONG); + return end; +} + /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(struct dentry *dentry, char *buf, int buflen) { - char *end = buf + buflen; - char *retval; + char *end, *retval; + int len, seq = 0; + int error = 0; - prepend(&end, &buflen, "\0", 1); + rcu_read_lock(); +restart: + end = buf + buflen; + len = buflen; + prepend(&end, &len, "\0", 1); if (buflen < 1) goto Elong; /* Get '/' right */ retval = end-1; *retval = '/'; - + read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { struct dentry *parent = dentry->d_parent; int error; prefetch(parent); - spin_lock(&dentry->d_lock); - error = prepend_name(&end, &buflen, &dentry->d_name); - spin_unlock(&dentry->d_lock); - if (error != 0 || prepend(&end, &buflen, "/", 1) != 0) - goto Elong; + error = prepend_name(&end, &len, &dentry->d_name); + if (error) + break; retval = end; dentry = parent; } + if (!(seq & 1)) + rcu_read_unlock(); + if (need_seqretry(&rename_lock, seq)) { + seq = 1; + goto restart; + } + done_seqretry(&rename_lock, seq); + if (error) + goto Elong; return retval; Elong: return ERR_PTR(-ENAMETOOLONG); @@ -2760,13 +3084,7 @@ Elong: char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen) { - char *retval; - - write_seqlock(&rename_lock); - retval = __dentry_path(dentry, buf, buflen); - write_sequnlock(&rename_lock); - - return retval; + return __dentry_path(dentry, buf, buflen); } EXPORT_SYMBOL(dentry_path_raw); @@ -2775,7 +3093,6 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen) char *p = NULL; char *retval; - write_seqlock(&rename_lock); if (d_unlinked(dentry)) { p = buf + buflen; if (prepend(&p, &buflen, "//deleted", 10) != 0) @@ -2783,7 +3100,6 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen) buflen++; } retval = __dentry_path(dentry, buf, buflen); - write_sequnlock(&rename_lock); if (!IS_ERR(retval) && p) *p = '/'; /* restore '/' overriden with '\0' */ return retval; @@ -2791,6 +3107,18 @@ Elong: return ERR_PTR(-ENAMETOOLONG); } +static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, + struct path *pwd) +{ + unsigned seq; + + do { + seq = read_seqcount_begin(&fs->seq); + *root = fs->root; + *pwd = fs->pwd; + } while (read_seqcount_retry(&fs->seq, seq)); +} + /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just @@ -2813,25 +3141,25 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; - char *page = (char *) __get_free_page(GFP_USER); + char *page = __getname(); if (!page) return -ENOMEM; - get_fs_root_and_pwd(current->fs, &root, &pwd); + rcu_read_lock(); + get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); error = -ENOENT; br_read_lock(&vfsmount_lock); - write_seqlock(&rename_lock); if (!d_unlinked(pwd.dentry)) { unsigned long len; - char *cwd = page + PAGE_SIZE; - int buflen = PAGE_SIZE; + char *cwd = page + PATH_MAX; + int buflen = PATH_MAX; prepend(&cwd, &buflen, "\0", 1); error = prepend_path(&pwd, &root, &cwd, &buflen); - write_sequnlock(&rename_lock); br_read_unlock(&vfsmount_lock); + rcu_read_unlock(); if (error < 0) goto out; @@ -2844,21 +3172,19 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) } error = -ERANGE; - len = PAGE_SIZE + page - cwd; + len = PATH_MAX + page - cwd; if (len <= size) { error = len; if (copy_to_user(buf, cwd, len)) error = -EFAULT; } } else { - write_sequnlock(&rename_lock); br_read_unlock(&vfsmount_lock); + rcu_read_unlock(); } out: - path_put(&pwd); - path_put(&root); - free_page((unsigned long) page); + __putname(page); return error; } @@ -2904,68 +3230,24 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) return result; } -void d_genocide(struct dentry *root) +static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { - struct dentry *this_parent; - struct list_head *next; - unsigned seq; - int locked = 0; + struct dentry *root = data; + if (dentry != root) { + if (d_unhashed(dentry) || !dentry->d_inode) + return D_WALK_SKIP; - seq = read_seqbegin(&rename_lock); -again: - this_parent = root; - spin_lock(&this_parent->d_lock); -repeat: - next = this_parent->d_subdirs.next; -resume: - while (next != &this_parent->d_subdirs) { - struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); - next = tmp->next; - - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - if (d_unhashed(dentry) || !dentry->d_inode) { - spin_unlock(&dentry->d_lock); - continue; - } - if (!list_empty(&dentry->d_subdirs)) { - spin_unlock(&this_parent->d_lock); - spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); - this_parent = dentry; - spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); - goto repeat; - } if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; - dentry->d_count--; - } - spin_unlock(&dentry->d_lock); - } - if (this_parent != root) { - struct dentry *child = this_parent; - if (!(this_parent->d_flags & DCACHE_GENOCIDE)) { - this_parent->d_flags |= DCACHE_GENOCIDE; - this_parent->d_count--; + dentry->d_lockref.count--; } - this_parent = try_to_ascend(this_parent, locked, seq); - if (!this_parent) - goto rename_retry; - next = child->d_u.d_child.next; - goto resume; } - spin_unlock(&this_parent->d_lock); - if (!locked && read_seqretry(&rename_lock, seq)) - goto rename_retry; - if (locked) - write_sequnlock(&rename_lock); - return; + return D_WALK_CONTINUE; +} -rename_retry: - if (locked) - goto again; - locked = 1; - write_seqlock(&rename_lock); - goto again; +void d_genocide(struct dentry *parent) +{ + d_walk(parent, parent, d_genocide_kill, NULL); } void d_tmpfile(struct dentry *dentry, struct inode *inode) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 4888cb3..c7c83ff 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -533,8 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove); */ void debugfs_remove_recursive(struct dentry *dentry) { - struct dentry *child; - struct dentry *parent; + struct dentry *child, *next, *parent; if (IS_ERR_OR_NULL(dentry)) return; @@ -544,61 +543,37 @@ void debugfs_remove_recursive(struct dentry *dentry) return; parent = dentry; + down: mutex_lock(&parent->d_inode->i_mutex); + list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { + if (!debugfs_positive(child)) + continue; - while (1) { - /* - * When all dentries under "parent" has been removed, - * walk up the tree until we reach our starting point. - */ - if (list_empty(&parent->d_subdirs)) { - mutex_unlock(&parent->d_inode->i_mutex); - if (parent == dentry) - break; - parent = parent->d_parent; - mutex_lock(&parent->d_inode->i_mutex); - } - child = list_entry(parent->d_subdirs.next, struct dentry, - d_u.d_child); - next_sibling: - - /* - * If "child" isn't empty, walk down the tree and - * remove all its descendants first. - */ + /* perhaps simple_empty(child) makes more sense */ if (!list_empty(&child->d_subdirs)) { mutex_unlock(&parent->d_inode->i_mutex); parent = child; - mutex_lock(&parent->d_inode->i_mutex); - continue; + goto down; } - __debugfs_remove(child, parent); - if (parent->d_subdirs.next == &child->d_u.d_child) { - /* - * Try the next sibling. - */ - if (child->d_u.d_child.next != &parent->d_subdirs) { - child = list_entry(child->d_u.d_child.next, - struct dentry, - d_u.d_child); - goto next_sibling; - } - - /* - * Avoid infinite loop if we fail to remove - * one dentry. - */ - mutex_unlock(&parent->d_inode->i_mutex); - break; - } - simple_release_fs(&debugfs_mount, &debugfs_mount_count); + up: + if (!__debugfs_remove(child, parent)) + simple_release_fs(&debugfs_mount, &debugfs_mount_count); } - parent = dentry->d_parent; + mutex_unlock(&parent->d_inode->i_mutex); + child = parent; + parent = parent->d_parent; mutex_lock(&parent->d_inode->i_mutex); - __debugfs_remove(dentry, parent); + + if (child != dentry) { + next = list_entry(child->d_u.d_child.next, struct dentry, + d_u.d_child); + goto up; + } + + if (!__debugfs_remove(child, parent)) + simple_release_fs(&debugfs_mount, &debugfs_mount_count); mutex_unlock(&parent->d_inode->i_mutex); - simple_release_fs(&debugfs_mount, &debugfs_mount_count); } EXPORT_SYMBOL_GPL(debugfs_remove_recursive); diff --git a/fs/direct-io.c b/fs/direct-io.c index 7ab90f5..0e04142 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -127,6 +127,7 @@ struct dio { spinlock_t bio_lock; /* protects BIO fields below */ int page_errors; /* errno from get_user_pages() */ int is_async; /* is IO async ? */ + bool defer_completion; /* defer AIO completion to workqueue? */ int io_error; /* IO error in completion path */ unsigned long refcount; /* direct_io_worker() and bios */ struct bio *bio_list; /* singly linked via bi_private */ @@ -141,7 +142,10 @@ struct dio { * allocation time. Don't add new fields after pages[] unless you * wish that they not be zeroed. */ - struct page *pages[DIO_PAGES]; /* page buffer */ + union { + struct page *pages[DIO_PAGES]; /* page buffer */ + struct work_struct complete_work;/* deferred AIO completion */ + }; } ____cacheline_aligned_in_smp; static struct kmem_cache *dio_cache __read_mostly; @@ -221,16 +225,16 @@ static inline struct page *dio_get_page(struct dio *dio, * dio_complete() - called when all DIO BIO I/O has been completed * @offset: the byte offset in the file of the completed operation * - * This releases locks as dictated by the locking type, lets interested parties - * know that a DIO operation has completed, and calculates the resulting return - * code for the operation. + * This drops i_dio_count, lets interested parties know that a DIO operation + * has completed, and calculates the resulting return code for the operation. * * It lets the filesystem know if it registered an interest earlier via * get_block. Pass the private field of the map buffer_head so that * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, + bool is_async) { ssize_t transferred = 0; @@ -258,19 +262,36 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is if (ret == 0) ret = transferred; - if (dio->end_io && dio->result) { - dio->end_io(dio->iocb, offset, transferred, - dio->private, ret, is_async); - } else { - inode_dio_done(dio->inode); - if (is_async) - aio_complete(dio->iocb, ret, 0); + if (dio->end_io && dio->result) + dio->end_io(dio->iocb, offset, transferred, dio->private); + + inode_dio_done(dio->inode); + if (is_async) { + if (dio->rw & WRITE) { + int err; + + err = generic_write_sync(dio->iocb->ki_filp, offset, + transferred); + if (err < 0 && ret > 0) + ret = err; + } + + aio_complete(dio->iocb, ret, 0); } + kmem_cache_free(dio_cache, dio); return ret; } +static void dio_aio_complete_work(struct work_struct *work) +{ + struct dio *dio = container_of(work, struct dio, complete_work); + + dio_complete(dio, dio->iocb->ki_pos, 0, true); +} + static int dio_bio_complete(struct dio *dio, struct bio *bio); + /* * Asynchronous IO callback. */ @@ -290,8 +311,13 @@ static void dio_bio_end_aio(struct bio *bio, int error) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - dio_complete(dio, dio->iocb->ki_pos, 0, true); - kmem_cache_free(dio_cache, dio); + if (dio->result && dio->defer_completion) { + INIT_WORK(&dio->complete_work, dio_aio_complete_work); + queue_work(dio->inode->i_sb->s_dio_done_wq, + &dio->complete_work); + } else { + dio_complete(dio, dio->iocb->ki_pos, 0, true); + } } } @@ -511,6 +537,42 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio) } /* + * Create workqueue for deferred direct IO completions. We allocate the + * workqueue when it's first needed. This avoids creating workqueue for + * filesystems that don't need it and also allows us to create the workqueue + * late enough so the we can include s_id in the name of the workqueue. + */ +static int sb_init_dio_done_wq(struct super_block *sb) +{ + struct workqueue_struct *old; + struct workqueue_struct *wq = alloc_workqueue("dio/%s", + WQ_MEM_RECLAIM, 0, + sb->s_id); + if (!wq) + return -ENOMEM; + /* + * This has to be atomic as more DIOs can race to create the workqueue + */ + old = cmpxchg(&sb->s_dio_done_wq, NULL, wq); + /* Someone created workqueue before us? Free ours... */ + if (old) + destroy_workqueue(wq); + return 0; +} + +static int dio_set_defer_completion(struct dio *dio) +{ + struct super_block *sb = dio->inode->i_sb; + + if (dio->defer_completion) + return 0; + dio->defer_completion = true; + if (!sb->s_dio_done_wq) + return sb_init_dio_done_wq(sb); + return 0; +} + +/* * Call into the fs to map some more disk blocks. We record the current number * of available blocks at sdio->blocks_available. These are in units of the * fs blocksize, (1 << inode->i_blkbits). @@ -581,6 +643,9 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, /* Store for completion */ dio->private = map_bh->b_private; + + if (ret == 0 && buffer_defer_completion(map_bh)) + ret = dio_set_defer_completion(dio); } return ret; } @@ -1129,11 +1194,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, } /* - * Will be decremented at I/O completion time. - */ - atomic_inc(&inode->i_dio_count); - - /* * For file extending writes updating i_size before data * writeouts complete can expose uninitialized blocks. So * even for AIO, we need to wait for i/o to complete before @@ -1141,11 +1201,33 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, */ dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) && (end > i_size_read(inode))); - - retval = 0; - dio->inode = inode; dio->rw = rw; + + /* + * For AIO O_(D)SYNC writes we need to defer completions to a workqueue + * so that we can call ->fsync. + */ + if (dio->is_async && (rw & WRITE) && + ((iocb->ki_filp->f_flags & O_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host))) { + retval = dio_set_defer_completion(dio); + if (retval) { + /* + * We grab i_mutex only for reads so we don't have + * to release it here + */ + kmem_cache_free(dio_cache, dio); + goto out; + } + } + + /* + * Will be decremented at I/O completion time. + */ + atomic_inc(&inode->i_dio_count); + + retval = 0; sdio.blkbits = blkbits; sdio.blkfactor = i_blkbits - blkbits; sdio.block_in_file = offset >> blkbits; @@ -1269,7 +1351,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, if (drop_refcount(dio) == 0) { retval = dio_complete(dio, offset, retval, false); - kmem_cache_free(dio_cache, dio); } else BUG_ON(retval != -EIOCBQUEUED); diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 27a6ba9..0e90f0c 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -267,10 +267,7 @@ void dlm_callback_work(struct work_struct *work) int dlm_callback_start(struct dlm_ls *ls) { ls->ls_callback_wq = alloc_workqueue("dlm_callback", - WQ_UNBOUND | - WQ_MEM_RECLAIM | - WQ_NON_REENTRANT, - 0); + WQ_UNBOUND | WQ_MEM_RECLAIM, 0); if (!ls->ls_callback_wq) { log_print("can't start dlm_callback workqueue"); return -ENOMEM; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 911649a..142e2165 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -493,7 +493,6 @@ static ssize_t device_write(struct file *file, const char __user *buf, { struct dlm_user_proc *proc = file->private_data; struct dlm_write_request *kbuf; - sigset_t tmpsig, allsigs; int error; #ifdef CONFIG_COMPAT @@ -557,9 +556,6 @@ static ssize_t device_write(struct file *file, const char __user *buf, goto out_free; } - sigfillset(&allsigs); - sigprocmask(SIG_BLOCK, &allsigs, &tmpsig); - error = -EINVAL; switch (kbuf->cmd) @@ -567,7 +563,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, case DLM_USER_LOCK: if (!proc) { log_print("no locking on control device"); - goto out_sig; + goto out_free; } error = device_user_lock(proc, &kbuf->i.lock); break; @@ -575,7 +571,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, case DLM_USER_UNLOCK: if (!proc) { log_print("no locking on control device"); - goto out_sig; + goto out_free; } error = device_user_unlock(proc, &kbuf->i.lock); break; @@ -583,7 +579,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, case DLM_USER_DEADLOCK: if (!proc) { log_print("no locking on control device"); - goto out_sig; + goto out_free; } error = device_user_deadlock(proc, &kbuf->i.lock); break; @@ -591,7 +587,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, case DLM_USER_CREATE_LOCKSPACE: if (proc) { log_print("create/remove only on control device"); - goto out_sig; + goto out_free; } error = device_create_lockspace(&kbuf->i.lspace); break; @@ -599,7 +595,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, case DLM_USER_REMOVE_LOCKSPACE: if (proc) { log_print("create/remove only on control device"); - goto out_sig; + goto out_free; } error = device_remove_lockspace(&kbuf->i.lspace); break; @@ -607,7 +603,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, case DLM_USER_PURGE: if (!proc) { log_print("no locking on control device"); - goto out_sig; + goto out_free; } error = device_user_purge(proc, &kbuf->i.purge); break; @@ -617,8 +613,6 @@ static ssize_t device_write(struct file *file, const char __user *buf, kbuf->cmd); } - out_sig: - sigprocmask(SIG_SETMASK, &tmpsig, NULL); out_free: kfree(kbuf); return error; @@ -659,15 +653,11 @@ static int device_close(struct inode *inode, struct file *file) { struct dlm_user_proc *proc = file->private_data; struct dlm_ls *ls; - sigset_t tmpsig, allsigs; ls = dlm_find_lockspace_local(proc->lockspace); if (!ls) return -ENOENT; - sigfillset(&allsigs); - sigprocmask(SIG_BLOCK, &allsigs, &tmpsig); - set_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags); dlm_clear_proc_locks(ls, proc); @@ -685,9 +675,6 @@ static int device_close(struct inode *inode, struct file *file) /* FIXME: AUTOFREE: if this ls is no longer used do device_remove_lockspace() */ - sigprocmask(SIG_SETMASK, &tmpsig, NULL); - recalc_sigpending(); - return 0; } diff --git a/fs/drop_caches.c b/fs/drop_caches.c index c00e055..9fd702f 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -44,6 +44,7 @@ static void drop_slab(void) .gfp_mask = GFP_KERNEL, }; + nodes_setall(shrink.nodes_to_scan); do { nr_objects = shrink_slab(&shrink, 1000, 1000); } while (nr_objects > 10); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index d107576..c88e355 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -609,39 +609,35 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) char *full_alg_name; int rc = -EINVAL; - if (!crypt_stat->cipher) { - ecryptfs_printk(KERN_ERR, "No cipher specified\n"); - goto out; - } ecryptfs_printk(KERN_DEBUG, "Initializing cipher [%s]; strlen = [%d]; " "key_size_bits = [%zd]\n", crypt_stat->cipher, (int)strlen(crypt_stat->cipher), crypt_stat->key_size << 3); + mutex_lock(&crypt_stat->cs_tfm_mutex); if (crypt_stat->tfm) { rc = 0; - goto out; + goto out_unlock; } - mutex_lock(&crypt_stat->cs_tfm_mutex); rc = ecryptfs_crypto_api_algify_cipher_name(&full_alg_name, crypt_stat->cipher, "cbc"); if (rc) goto out_unlock; crypt_stat->tfm = crypto_alloc_ablkcipher(full_alg_name, 0, 0); - kfree(full_alg_name); if (IS_ERR(crypt_stat->tfm)) { rc = PTR_ERR(crypt_stat->tfm); crypt_stat->tfm = NULL; ecryptfs_printk(KERN_ERR, "cryptfs: init_crypt_ctx(): " "Error initializing cipher [%s]\n", - crypt_stat->cipher); - goto out_unlock; + full_alg_name); + goto out_free; } crypto_ablkcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY); rc = 0; +out_free: + kfree(full_alg_name); out_unlock: mutex_unlock(&crypt_stat->cs_tfm_mutex); -out: return rc; } diff --git a/fs/efs/inode.c b/fs/efs/inode.c index f3913eb..d15ccf2 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -57,7 +57,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) struct inode *inode; inode = iget_locked(super, ino); - if (IS_ERR(inode)) + if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9ad17b15..473e09d 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -740,6 +740,7 @@ static void ep_free(struct eventpoll *ep) epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); + cond_resched(); } /* @@ -754,6 +755,7 @@ static void ep_free(struct eventpoll *ep) while ((rbp = rb_first(&ep->rbr)) != NULL) { epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); + cond_resched(); } mutex_unlock(&ep->mtx); @@ -1792,7 +1794,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, { int error; int did_lock_epmutex = 0; - struct file *file, *tfile; + struct fd f, tf; struct eventpoll *ep; struct epitem *epi; struct epoll_event epds; @@ -1802,20 +1804,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, copy_from_user(&epds, event, sizeof(struct epoll_event))) goto error_return; - /* Get the "struct file *" for the eventpoll file */ error = -EBADF; - file = fget(epfd); - if (!file) + f = fdget(epfd); + if (!f.file) goto error_return; /* Get the "struct file *" for the target file */ - tfile = fget(fd); - if (!tfile) + tf = fdget(fd); + if (!tf.file) goto error_fput; /* The target file descriptor must support poll */ error = -EPERM; - if (!tfile->f_op || !tfile->f_op->poll) + if (!tf.file->f_op || !tf.file->f_op->poll) goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ @@ -1828,14 +1829,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * adding an epoll file descriptor inside itself. */ error = -EINVAL; - if (file == tfile || !is_file_epoll(file)) + if (f.file == tf.file || !is_file_epoll(f.file)) goto error_tgt_fput; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ - ep = file->private_data; + ep = f.file->private_data; /* * When we insert an epoll file descriptor, inside another epoll file @@ -1854,14 +1855,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, did_lock_epmutex = 1; } if (op == EPOLL_CTL_ADD) { - if (is_file_epoll(tfile)) { + if (is_file_epoll(tf.file)) { error = -ELOOP; - if (ep_loop_check(ep, tfile) != 0) { + if (ep_loop_check(ep, tf.file) != 0) { clear_tfile_check_list(); goto error_tgt_fput; } } else - list_add(&tfile->f_tfile_llink, &tfile_check_list); + list_add(&tf.file->f_tfile_llink, &tfile_check_list); } mutex_lock_nested(&ep->mtx, 0); @@ -1871,14 +1872,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ - epi = ep_find(ep, tfile, fd); + epi = ep_find(ep, tf.file, fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds.events |= POLLERR | POLLHUP; - error = ep_insert(ep, &epds, tfile, fd); + error = ep_insert(ep, &epds, tf.file, fd); } else error = -EEXIST; clear_tfile_check_list(); @@ -1903,9 +1904,9 @@ error_tgt_fput: if (did_lock_epmutex) mutex_unlock(&epmutex); - fput(tfile); + fdput(tf); error_fput: - fput(file); + fdput(f); error_return: return error; @@ -74,6 +74,8 @@ static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { BUG_ON(!fmt); + if (WARN_ON(!fmt->load_binary)) + return; write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); @@ -266,7 +268,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; - vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; + vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); INIT_LIST_HEAD(&vma->anon_vma_chain); @@ -608,7 +610,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) return -ENOMEM; lru_add_drain(); - tlb_gather_mmu(&tlb, mm, 0); + tlb_gather_mmu(&tlb, mm, old_start, old_end); if (new_end > old_start) { /* * when the old and new regions overlap clear from new_end. @@ -625,7 +627,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) free_pgd_range(&tlb, old_start, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } - tlb_finish_mmu(&tlb, new_end, old_end); + tlb_finish_mmu(&tlb, old_start, old_end); /* * Shrink the vma to just the new range. Always succeeds. @@ -1365,18 +1367,18 @@ out: } EXPORT_SYMBOL(remove_arg_zero); +#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ int search_binary_handler(struct linux_binprm *bprm) { - unsigned int depth = bprm->recursion_depth; - int try,retval; + bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; - pid_t old_pid, old_vpid; + int retval; /* This allows 4 levels of binfmt rewrites before failing hard. */ - if (depth > 5) + if (bprm->recursion_depth > 5) return -ELOOP; retval = security_bprm_check(bprm); @@ -1387,71 +1389,67 @@ int search_binary_handler(struct linux_binprm *bprm) if (retval) return retval; + retval = -ENOENT; + retry: + read_lock(&binfmt_lock); + list_for_each_entry(fmt, &formats, lh) { + if (!try_module_get(fmt->module)) + continue; + read_unlock(&binfmt_lock); + bprm->recursion_depth++; + retval = fmt->load_binary(bprm); + bprm->recursion_depth--; + if (retval >= 0 || retval != -ENOEXEC || + bprm->mm == NULL || bprm->file == NULL) { + put_binfmt(fmt); + return retval; + } + read_lock(&binfmt_lock); + put_binfmt(fmt); + } + read_unlock(&binfmt_lock); + + if (need_retry && retval == -ENOEXEC) { + if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && + printable(bprm->buf[2]) && printable(bprm->buf[3])) + return retval; + if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) + return retval; + need_retry = false; + goto retry; + } + + return retval; +} +EXPORT_SYMBOL(search_binary_handler); + +static int exec_binprm(struct linux_binprm *bprm) +{ + pid_t old_pid, old_vpid; + int ret; + /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; rcu_read_lock(); old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); - retval = -ENOENT; - for (try=0; try<2; try++) { - read_lock(&binfmt_lock); - list_for_each_entry(fmt, &formats, lh) { - int (*fn)(struct linux_binprm *) = fmt->load_binary; - if (!fn) - continue; - if (!try_module_get(fmt->module)) - continue; - read_unlock(&binfmt_lock); - bprm->recursion_depth = depth + 1; - retval = fn(bprm); - bprm->recursion_depth = depth; - if (retval >= 0) { - if (depth == 0) { - trace_sched_process_exec(current, old_pid, bprm); - ptrace_event(PTRACE_EVENT_EXEC, old_vpid); - } - put_binfmt(fmt); - allow_write_access(bprm->file); - if (bprm->file) - fput(bprm->file); - bprm->file = NULL; - current->did_exec = 1; - proc_exec_connector(current); - return retval; - } - read_lock(&binfmt_lock); - put_binfmt(fmt); - if (retval != -ENOEXEC || bprm->mm == NULL) - break; - if (!bprm->file) { - read_unlock(&binfmt_lock); - return retval; - } + ret = search_binary_handler(bprm); + if (ret >= 0) { + trace_sched_process_exec(current, old_pid, bprm); + ptrace_event(PTRACE_EVENT_EXEC, old_vpid); + current->did_exec = 1; + proc_exec_connector(current); + + if (bprm->file) { + allow_write_access(bprm->file); + fput(bprm->file); + bprm->file = NULL; /* to catch use-after-free */ } - read_unlock(&binfmt_lock); -#ifdef CONFIG_MODULES - if (retval != -ENOEXEC || bprm->mm == NULL) { - break; - } else { -#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) - if (printable(bprm->buf[0]) && - printable(bprm->buf[1]) && - printable(bprm->buf[2]) && - printable(bprm->buf[3])) - break; /* -ENOEXEC */ - if (try) - break; /* -ENOEXEC */ - request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2])); - } -#else - break; -#endif } - return retval; -} -EXPORT_SYMBOL(search_binary_handler); + return ret; +} /* * sys_execve() executes a new program. @@ -1541,7 +1539,7 @@ static int do_execve_common(const char *filename, if (retval < 0) goto out; - retval = search_binary_handler(bprm); + retval = exec_binprm(bprm); if (retval < 0) goto out; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 2ec8eb1..a52a5d2 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -861,7 +861,7 @@ static int exofs_writepage(struct page *page, struct writeback_control *wbc) static void _write_failed(struct inode *inode, loff_t to) { if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } int exofs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 293bc2e..a235f00 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -231,7 +231,7 @@ static int filldir_one(void * __buf, const char * name, int len, int result = 0; buf->sequence++; - if (buf->ino == ino) { + if (buf->ino == ino && len <= NAME_MAX) { memcpy(buf->name, name, len); buf->name[len] = '\0'; buf->found = 1; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 0a87bb1..c260de6 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -58,7 +58,7 @@ static void ext2_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); ext2_truncate_blocks(inode, inode->i_size); } } diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index f522425..bafdd48 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -41,7 +41,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype) /** * Check if the given dir-inode refers to an htree-indexed directory - * (or a directory which chould potentially get coverted to use htree + * (or a directory which could potentially get converted to use htree * indexing). * * Return 1 if it is a dx dir, 0 if not diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 998ea11..1194b1f 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1780,11 +1780,11 @@ retry: inode->i_op = &ext3_file_inode_operations; inode->i_fop = &ext3_file_operations; ext3_set_aops(inode); + d_tmpfile(dentry, inode); err = ext3_orphan_add(handle, inode); if (err) goto err_drop_inode; mark_inode_dirty(inode); - d_tmpfile(dentry, inode); unlock_new_inode(inode); } ext3_journal_stop(handle); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index c47f147..c50c761 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -27,6 +27,7 @@ #include <linux/seq_file.h> #include <linux/log2.h> #include <linux/cleancache.h> +#include <linux/namei.h> #include <asm/uaccess.h> @@ -819,6 +820,7 @@ enum { Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev, + Opt_journal_path, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, @@ -860,6 +862,7 @@ static const match_table_t tokens = { {Opt_journal_update, "journal=update"}, {Opt_journal_inum, "journal=%u"}, {Opt_journal_dev, "journal_dev=%u"}, + {Opt_journal_path, "journal_path=%s"}, {Opt_abort, "abort"}, {Opt_data_journal, "data=journal"}, {Opt_data_ordered, "data=ordered"}, @@ -975,6 +978,11 @@ static int parse_options (char *options, struct super_block *sb, int option; kuid_t uid; kgid_t gid; + char *journal_path; + struct inode *journal_inode; + struct path path; + int error; + #ifdef CONFIG_QUOTA int qfmt; #endif @@ -1129,6 +1137,41 @@ static int parse_options (char *options, struct super_block *sb, return 0; *journal_devnum = option; break; + case Opt_journal_path: + if (is_remount) { + ext3_msg(sb, KERN_ERR, "error: cannot specify " + "journal on remount"); + return 0; + } + + journal_path = match_strdup(&args[0]); + if (!journal_path) { + ext3_msg(sb, KERN_ERR, "error: could not dup " + "journal device string"); + return 0; + } + + error = kern_path(journal_path, LOOKUP_FOLLOW, &path); + if (error) { + ext3_msg(sb, KERN_ERR, "error: could not find " + "journal device path: error %d", error); + kfree(journal_path); + return 0; + } + + journal_inode = path.dentry->d_inode; + if (!S_ISBLK(journal_inode->i_mode)) { + ext3_msg(sb, KERN_ERR, "error: journal path %s " + "is not a block device", journal_path); + path_put(&path); + kfree(journal_path); + return 0; + } + + *journal_devnum = new_encode_dev(journal_inode->i_rdev); + path_put(&path); + kfree(journal_path); + break; case Opt_noload: set_opt (sbi->s_mount_opt, NOLOAD); break; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 5833939..dc5d572 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -38,8 +38,8 @@ ext4_group_t ext4_get_group_number(struct super_block *sb, ext4_group_t group; if (test_opt2(sb, STD_GROUP_SIZE)) - group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + - block) >> + group = (block - + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >> (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3); else ext4_get_group_no_and_offset(sb, block, &group, NULL); @@ -184,6 +184,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; int flex_bg = 0; + struct ext4_group_info *grp; J_ASSERT_BH(bh, buffer_locked(bh)); @@ -191,11 +192,9 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); - ext4_free_group_clusters_set(sb, gdp, 0); - ext4_free_inodes_set(sb, gdp, 0); - ext4_itable_unused_set(sb, gdp, 0); - memset(bh->b_data, 0xff, sb->s_blocksize); - ext4_block_bitmap_csum_set(sb, block_group, gdp, bh); + grp = ext4_get_group_info(sb, block_group); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return; } memset(bh->b_data, 0, sb->s_blocksize); @@ -305,7 +304,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, */ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, - unsigned int block_group, + ext4_group_t block_group, struct buffer_head *bh) { ext4_grpblk_t offset; @@ -352,10 +351,11 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, void ext4_validate_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, - unsigned int block_group, + ext4_group_t block_group, struct buffer_head *bh) { ext4_fsblk_t blk; + struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); if (buffer_verified(bh)) return; @@ -366,12 +366,14 @@ void ext4_validate_block_bitmap(struct super_block *sb, ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: block %llu: invalid block bitmap", block_group, blk); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); return; } if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, desc, bh))) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); return; } set_buffer_verified(bh); @@ -445,7 +447,10 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) return bh; verify: ext4_validate_block_bitmap(sb, desc, block_group, bh); - return bh; + if (buffer_verified(bh)) + return bh; + put_bh(bh); + return NULL; } /* Returns 0 on success, 1 on error */ @@ -469,7 +474,8 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, clear_buffer_new(bh); /* Panic or remount fs read-only if block bitmap is invalid */ ext4_validate_block_bitmap(sb, desc, block_group, bh); - return 0; + /* ...but check for error just in case errors=continue. */ + return !buffer_verified(bh); } struct buffer_head * diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 3c7d288..680bb33 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -33,7 +33,7 @@ static int ext4_dx_readdir(struct file *, struct dir_context *); /** * Check if the given dir-inode refers to an htree-indexed directory - * (or a directory which chould potentially get coverted to use htree + * (or a directory which could potentially get converted to use htree * indexing). * * Return 1 if it is a dx dir, 0 if not diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b577e45..af815ea 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -180,7 +180,6 @@ struct ext4_map_blocks { * Flags for ext4_io_end->flags */ #define EXT4_IO_END_UNWRITTEN 0x0001 -#define EXT4_IO_END_DIRECT 0x0002 /* * For converting uninitialized extents on a work queue. 'handle' is used for @@ -196,8 +195,6 @@ typedef struct ext4_io_end { unsigned int flag; /* unwritten or not */ loff_t offset; /* offset in the file */ ssize_t size; /* size of the extent */ - struct kiocb *iocb; /* iocb struct for AIO */ - int result; /* error value for AIO */ atomic_t count; /* reference counter */ } ext4_io_end_t; @@ -561,6 +558,18 @@ enum { #define EXT4_GET_BLOCKS_NO_PUT_HOLE 0x0200 /* + * The bit position of these flags must not overlap with any of the + * EXT4_GET_BLOCKS_*. They are used by ext4_ext_find_extent(), + * read_extent_tree_block(), ext4_split_extent_at(), + * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf(). + * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be + * caching the extents when reading from the extent tree while a + * truncate or punch hole operation is in progress. + */ +#define EXT4_EX_NOCACHE 0x0400 +#define EXT4_EX_FORCE_CACHE 0x0800 + +/* * Flags used by ext4_free_blocks */ #define EXT4_FREE_BLOCKS_METADATA 0x0001 @@ -569,6 +578,7 @@ enum { #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020 +#define EXT4_FREE_BLOCKS_RESERVE 0x0040 /* * ioctl commands @@ -590,6 +600,7 @@ enum { #define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent) #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) #define EXT4_IOC_SWAP_BOOT _IO('f', 17) +#define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18) #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -900,11 +911,9 @@ struct ext4_inode_info { * Completed IOs that need unwritten extents handling and don't have * transaction reserved */ - struct list_head i_unrsv_conversion_list; atomic_t i_ioend_count; /* Number of outstanding io_end structs */ atomic_t i_unwritten; /* Nr. of inflight conversions pending */ struct work_struct i_rsv_conversion_work; - struct work_struct i_unrsv_conversion_work; spinlock_t i_block_reservation_lock; @@ -1276,8 +1285,6 @@ struct ext4_sb_info { struct flex_groups *s_flex_groups; ext4_group_t s_flex_groups_allocated; - /* workqueue for unreserved extent convertions (dio) */ - struct workqueue_struct *unrsv_conversion_wq; /* workqueue for reserved extent conversions (buffered io) */ struct workqueue_struct *rsv_conversion_wq; @@ -1340,9 +1347,6 @@ static inline void ext4_set_io_unwritten_flag(struct inode *inode, struct ext4_io_end *io_end) { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - /* Writeback has to have coversion transaction reserved */ - WARN_ON(EXT4_SB(inode->i_sb)->s_journal && !io_end->handle && - !(io_end->flag & EXT4_IO_END_DIRECT)); io_end->flag |= EXT4_IO_END_UNWRITTEN; atomic_inc(&EXT4_I(inode)->i_unwritten); } @@ -1375,6 +1379,7 @@ enum { nolocking */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ EXT4_STATE_ORDERED_MODE, /* data=ordered mode */ + EXT4_STATE_EXT_PRECACHED, /* extents have been precached */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1915,7 +1920,7 @@ extern ext4_group_t ext4_get_group_number(struct super_block *sb, extern void ext4_validate_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, - unsigned int block_group, + ext4_group_t block_group, struct buffer_head *bh); extern unsigned int ext4_block_group(struct super_block *sb, ext4_fsblk_t blocknr); @@ -2086,6 +2091,7 @@ extern int ext4_sync_inode(handle_t *, struct inode *); extern void ext4_dirty_inode(struct inode *, int); extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); +extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern void ext4_truncate(struct inode *); extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); @@ -2416,16 +2422,32 @@ do { \ #define EXT4_FREECLUSTERS_WATERMARK 0 #endif +/* Update i_disksize. Requires i_mutex to avoid races with truncate */ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) { - /* - * XXX: replace with spinlock if seen contended -bzzz - */ + WARN_ON_ONCE(S_ISREG(inode->i_mode) && + !mutex_is_locked(&inode->i_mutex)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) EXT4_I(inode)->i_disksize = newsize; up_write(&EXT4_I(inode)->i_data_sem); - return ; +} + +/* + * Update i_disksize after writeback has been started. Races with truncate + * are avoided by checking i_size under i_data_sem. + */ +static inline void ext4_wb_update_i_disksize(struct inode *inode, loff_t newsize) +{ + loff_t i_size; + + down_write(&EXT4_I(inode)->i_data_sem); + i_size = i_size_read(inode); + if (newsize > i_size) + newsize = i_size; + if (newsize > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = newsize; + up_write(&EXT4_I(inode)->i_data_sem); } struct ext4_group_info { @@ -2448,9 +2470,15 @@ struct ext4_group_info { #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 +#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2 +#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \ + (test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \ + (test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_WAS_TRIMMED(grp) \ (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) @@ -2654,6 +2682,12 @@ extern int ext4_check_blockref(const char *, unsigned int, struct ext4_ext_path; struct ext4_extent; +/* + * Maximum number of logical blocks in a file; ext4_extent's ee_block is + * __le32. + */ +#define EXT_MAX_BLOCKS 0xffffffff + extern int ext4_ext_tree_init(handle_t *handle, struct inode *); extern int ext4_ext_writepage_trans_blocks(struct inode *, int); extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents); @@ -2683,7 +2717,8 @@ extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int); extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, - struct ext4_ext_path *); + struct ext4_ext_path *, + int flags); extern void ext4_ext_drop_refs(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); extern int ext4_find_delalloc_range(struct inode *inode, @@ -2692,7 +2727,7 @@ extern int ext4_find_delalloc_range(struct inode *inode, extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); - +extern int ext4_ext_precache(struct inode *inode); /* move_extent.c */ extern void ext4_double_down_write_data_sem(struct inode *first, @@ -2715,7 +2750,6 @@ extern void ext4_put_io_end_defer(ext4_io_end_t *io_end); extern void ext4_io_submit_init(struct ext4_io_submit *io, struct writeback_control *wbc); extern void ext4_end_io_rsv_work(struct work_struct *work); -extern void ext4_end_io_unrsv_work(struct work_struct *work); extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 51bc821..5074fe2 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -134,12 +134,6 @@ struct ext4_ext_path { */ /* - * Maximum number of logical blocks in a file; ext4_extent's ee_block is - * __le32. - */ -#define EXT_MAX_BLOCKS 0xffffffff - -/* * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an * initialized extent. This is 2^15 and not (2^16 - 1), since we use the * MSB of ee_len field in the extent datastructure to signify if this diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 72a3600..17ac112 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -255,10 +255,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, set_buffer_prio(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); - if (err) { - /* Errors can only happen if there is a bug */ - handle->h_err = err; - __ext4_journal_stop(where, line, handle); + /* Errors can only happen if there is a bug */ + if (WARN_ON_ONCE(err)) { + ext4_journal_abort_handle(where, line, __func__, bh, + handle, err); } } else { if (inode) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 2877258..81cfefa 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -197,7 +197,7 @@ static inline void ext4_journal_callback_add(handle_t *handle, * ext4_journal_callback_del: delete a registered callback * @handle: active journal transaction handle on which callback was registered * @jce: registered journal callback entry to unregister - * Return true if object was sucessfully removed + * Return true if object was successfully removed */ static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7097b0f..54d52af 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -407,7 +407,7 @@ static int ext4_valid_extent_entries(struct inode *inode, static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, - int depth) + int depth, ext4_fsblk_t pblk) { const char *error_msg; int max = 0; @@ -447,42 +447,149 @@ static int __ext4_ext_check(const char *function, unsigned int line, corrupted: ext4_error_inode(inode, function, line, 0, - "bad header/extent: %s - magic %x, " - "entries %u, max %u(%u), depth %u(%u)", - error_msg, le16_to_cpu(eh->eh_magic), - le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), - max, le16_to_cpu(eh->eh_depth), depth); - + "pblk %llu bad header/extent: %s - magic %x, " + "entries %u, max %u(%u), depth %u(%u)", + (unsigned long long) pblk, error_msg, + le16_to_cpu(eh->eh_magic), + le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), + max, le16_to_cpu(eh->eh_depth), depth); return -EIO; } -#define ext4_ext_check(inode, eh, depth) \ - __ext4_ext_check(__func__, __LINE__, inode, eh, depth) +#define ext4_ext_check(inode, eh, depth, pblk) \ + __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk)) int ext4_ext_check_inode(struct inode *inode) { - return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode)); + return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } -static int __ext4_ext_check_block(const char *function, unsigned int line, - struct inode *inode, - struct ext4_extent_header *eh, - int depth, - struct buffer_head *bh) +static struct buffer_head * +__read_extent_tree_block(const char *function, unsigned int line, + struct inode *inode, ext4_fsblk_t pblk, int depth, + int flags) { - int ret; + struct buffer_head *bh; + int err; - if (buffer_verified(bh)) - return 0; - ret = ext4_ext_check(inode, eh, depth); - if (ret) - return ret; + bh = sb_getblk(inode->i_sb, pblk); + if (unlikely(!bh)) + return ERR_PTR(-ENOMEM); + + if (!bh_uptodate_or_lock(bh)) { + trace_ext4_ext_load_extent(inode, pblk, _RET_IP_); + err = bh_submit_read(bh); + if (err < 0) + goto errout; + } + if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) + return bh; + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; set_buffer_verified(bh); - return ret; + /* + * If this is a leaf block, cache all of its entries + */ + if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { + struct ext4_extent_header *eh = ext_block_hdr(bh); + struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); + ext4_lblk_t prev = 0; + int i; + + for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { + unsigned int status = EXTENT_STATUS_WRITTEN; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); + int len = ext4_ext_get_actual_len(ex); + + if (prev && (prev != lblk)) + ext4_es_cache_extent(inode, prev, + lblk - prev, ~0, + EXTENT_STATUS_HOLE); + + if (ext4_ext_is_uninitialized(ex)) + status = EXTENT_STATUS_UNWRITTEN; + ext4_es_cache_extent(inode, lblk, len, + ext4_ext_pblock(ex), status); + prev = lblk + len; + } + } + return bh; +errout: + put_bh(bh); + return ERR_PTR(err); + } -#define ext4_ext_check_block(inode, eh, depth, bh) \ - __ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh) +#define read_extent_tree_block(inode, pblk, depth, flags) \ + __read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \ + (depth), (flags)) + +/* + * This function is called to cache a file's extent information in the + * extent status tree + */ +int ext4_ext_precache(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_ext_path *path = NULL; + struct buffer_head *bh; + int i = 0, depth, ret = 0; + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + return 0; /* not an extent-mapped inode */ + + down_read(&ei->i_data_sem); + depth = ext_depth(inode); + + path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), + GFP_NOFS); + if (path == NULL) { + up_read(&ei->i_data_sem); + return -ENOMEM; + } + + /* Don't cache anything if there are no external extent blocks */ + if (depth == 0) + goto out; + path[0].p_hdr = ext_inode_hdr(inode); + ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); + if (ret) + goto out; + path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr); + while (i >= 0) { + /* + * If this is a leaf block or we've reached the end of + * the index block, go up + */ + if ((i == depth) || + path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) { + brelse(path[i].p_bh); + path[i].p_bh = NULL; + i--; + continue; + } + bh = read_extent_tree_block(inode, + ext4_idx_pblock(path[i].p_idx++), + depth - i - 1, + EXT4_EX_FORCE_CACHE); + if (IS_ERR(bh)) { + ret = PTR_ERR(bh); + break; + } + i++; + path[i].p_bh = bh; + path[i].p_hdr = ext_block_hdr(bh); + path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr); + } + ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); +out: + up_read(&ei->i_data_sem); + ext4_ext_drop_refs(path); + kfree(path); + return ret; +} #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) @@ -716,7 +823,7 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode) struct ext4_ext_path * ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, - struct ext4_ext_path *path) + struct ext4_ext_path *path, int flags) { struct ext4_extent_header *eh; struct buffer_head *bh; @@ -748,20 +855,13 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, path[ppos].p_depth = i; path[ppos].p_ext = NULL; - bh = sb_getblk(inode->i_sb, path[ppos].p_block); - if (unlikely(!bh)) { - ret = -ENOMEM; + bh = read_extent_tree_block(inode, path[ppos].p_block, --i, + flags); + if (IS_ERR(bh)) { + ret = PTR_ERR(bh); goto err; } - if (!bh_uptodate_or_lock(bh)) { - trace_ext4_ext_load_extent(inode, block, - path[ppos].p_block); - ret = bh_submit_read(bh); - if (ret < 0) { - put_bh(bh); - goto err; - } - } + eh = ext_block_hdr(bh); ppos++; if (unlikely(ppos > depth)) { @@ -773,11 +873,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, } path[ppos].p_bh = bh; path[ppos].p_hdr = eh; - i--; - - ret = ext4_ext_check_block(inode, eh, i, bh); - if (ret < 0) - goto err; } path[ppos].p_depth = i; @@ -1198,7 +1293,8 @@ out: * if no free index is found, then it requests in-depth growing. */ static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, - unsigned int flags, + unsigned int mb_flags, + unsigned int gb_flags, struct ext4_ext_path *path, struct ext4_extent *newext) { @@ -1220,7 +1316,7 @@ repeat: if (EXT_HAS_FREE_INDEX(curp)) { /* if we found index with free entry, then use that * entry: create all needed subtree and add new leaf */ - err = ext4_ext_split(handle, inode, flags, path, newext, i); + err = ext4_ext_split(handle, inode, mb_flags, path, newext, i); if (err) goto out; @@ -1228,12 +1324,12 @@ repeat: ext4_ext_drop_refs(path); path = ext4_ext_find_extent(inode, (ext4_lblk_t)le32_to_cpu(newext->ee_block), - path); + path, gb_flags); if (IS_ERR(path)) err = PTR_ERR(path); } else { /* tree is full, time to grow in depth */ - err = ext4_ext_grow_indepth(handle, inode, flags, newext); + err = ext4_ext_grow_indepth(handle, inode, mb_flags, newext); if (err) goto out; @@ -1241,7 +1337,7 @@ repeat: ext4_ext_drop_refs(path); path = ext4_ext_find_extent(inode, (ext4_lblk_t)le32_to_cpu(newext->ee_block), - path); + path, gb_flags); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; @@ -1412,29 +1508,21 @@ got_index: ix++; block = ext4_idx_pblock(ix); while (++depth < path->p_depth) { - bh = sb_bread(inode->i_sb, block); - if (bh == NULL) - return -EIO; - eh = ext_block_hdr(bh); /* subtract from p_depth to get proper eh_depth */ - if (ext4_ext_check_block(inode, eh, - path->p_depth - depth, bh)) { - put_bh(bh); - return -EIO; - } + bh = read_extent_tree_block(inode, block, + path->p_depth - depth, 0); + if (IS_ERR(bh)) + return PTR_ERR(bh); + eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); block = ext4_idx_pblock(ix); put_bh(bh); } - bh = sb_bread(inode->i_sb, block); - if (bh == NULL) - return -EIO; + bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0); + if (IS_ERR(bh)) + return PTR_ERR(bh); eh = ext_block_hdr(bh); - if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) { - put_bh(bh); - return -EIO; - } ex = EXT_FIRST_EXTENT(eh); found_extent: *logical = le32_to_cpu(ex->ee_block); @@ -1705,7 +1793,8 @@ static void ext4_ext_try_to_merge_up(handle_t *handle, brelse(path[1].p_bh); ext4_free_blocks(handle, inode, NULL, blk, 1, - EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); + EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET | + EXT4_FREE_BLOCKS_RESERVE); } /* @@ -1793,7 +1882,7 @@ out: */ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, - struct ext4_extent *newext, int flag) + struct ext4_extent *newext, int gb_flags) { struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; @@ -1802,7 +1891,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, int depth, len, err; ext4_lblk_t next; unsigned uninitialized = 0; - int flags = 0; + int mb_flags = 0; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); @@ -1817,7 +1906,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, } /* try to insert block into found extent and return */ - if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) { + if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) { /* * Try to see whether we should rather test the extent on @@ -1920,7 +2009,7 @@ prepend: if (next != EXT_MAX_BLOCKS) { ext_debug("next leaf block - %u\n", next); BUG_ON(npath != NULL); - npath = ext4_ext_find_extent(inode, next, NULL); + npath = ext4_ext_find_extent(inode, next, NULL, 0); if (IS_ERR(npath)) return PTR_ERR(npath); BUG_ON(npath->p_depth != path->p_depth); @@ -1939,9 +2028,10 @@ prepend: * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ - if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL) - flags = EXT4_MB_USE_RESERVED; - err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext); + if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) + mb_flags = EXT4_MB_USE_RESERVED; + err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, + path, newext); if (err) goto cleanup; depth = ext_depth(inode); @@ -2007,7 +2097,7 @@ has_space: merge: /* try to merge extents */ - if (!(flag & EXT4_GET_BLOCKS_PRE_IO)) + if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, nearex); @@ -2050,7 +2140,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode, path = NULL; } - path = ext4_ext_find_extent(inode, block, path); + path = ext4_ext_find_extent(inode, block, path, 0); if (IS_ERR(path)) { up_read(&EXT4_I(inode)->i_data_sem); err = PTR_ERR(path); @@ -2195,8 +2285,8 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { int depth = ext_depth(inode); - unsigned long len; - ext4_lblk_t lblock; + unsigned long len = 0; + ext4_lblk_t lblock = 0; struct ext4_extent *ex; ex = path[depth].p_ext; @@ -2233,7 +2323,6 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, ext4_es_insert_extent(inode, lblock, len, ~0, EXTENT_STATUS_HOLE); } else { - lblock = len = 0; BUG(); } @@ -2712,7 +2801,7 @@ again: ext4_lblk_t ee_block; /* find extent for this block */ - path = ext4_ext_find_extent(inode, end, NULL); + path = ext4_ext_find_extent(inode, end, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); @@ -2754,6 +2843,7 @@ again: */ err = ext4_split_extent_at(handle, inode, path, end + 1, split_flag, + EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_METADATA_NOFAIL); @@ -2782,7 +2872,7 @@ again: path[0].p_hdr = ext_inode_hdr(inode); i = 0; - if (ext4_ext_check(inode, path[0].p_hdr, depth)) { + if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) { err = -EIO; goto out; } @@ -2829,21 +2919,21 @@ again: ext_debug("move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); - bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx)); - if (!bh) { + bh = read_extent_tree_block(inode, + ext4_idx_pblock(path[i].p_idx), depth - i - 1, + EXT4_EX_NOCACHE); + if (IS_ERR(bh)) { /* should we reset i_size? */ - err = -EIO; + err = PTR_ERR(bh); break; } + /* Yield here to deal with large extent trees. + * Should be a no-op if we did IO above. */ + cond_resched(); if (WARN_ON(i + 1 > depth)) { err = -EIO; break; } - if (ext4_ext_check_block(inode, ext_block_hdr(bh), - depth - i - 1, bh)) { - err = -EIO; - break; - } path[i + 1].p_bh = bh; /* save actual number of indexes since this @@ -2958,6 +3048,23 @@ void ext4_ext_release(struct super_block *sb) #endif } +static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) +{ + ext4_lblk_t ee_block; + ext4_fsblk_t ee_pblock; + unsigned int ee_len; + + ee_block = le32_to_cpu(ex->ee_block); + ee_len = ext4_ext_get_actual_len(ex); + ee_pblock = ext4_ext_pblock(ex); + + if (ee_len == 0) + return 0; + + return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, + EXTENT_STATUS_WRITTEN); +} + /* FIXME!! we need to try to merge to left or right after zero-out */ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { @@ -3110,7 +3217,7 @@ static int ext4_split_extent_at(handle_t *handle, goto fix_extent_len; /* update extent status tree */ - err = ext4_es_zeroout(inode, &zero_ex); + err = ext4_zeroout_es(inode, &zero_ex); goto out; } else if (err) @@ -3130,7 +3237,7 @@ fix_extent_len: * ext4_split_extents() splits an extent and mark extent which is covered * by @map as split_flags indicates * - * It may result in splitting the extent into multiple extents (upto three) + * It may result in splitting the extent into multiple extents (up to three) * There are three possibilities: * a> There is no split required * b> Splits in two extents: Split is happening at either end of the extent @@ -3178,7 +3285,7 @@ static int ext4_split_extent(handle_t *handle, * result in split of original leaf or extent zeroout. */ ext4_ext_drop_refs(path); - path = ext4_ext_find_extent(inode, map->m_lblk, path); + path = ext4_ext_find_extent(inode, map->m_lblk, path, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); @@ -3461,7 +3568,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, out: /* If we have gotten a failure, don't zero out status tree */ if (!err) - err = ext4_es_zeroout(inode, &zero_ex); + err = ext4_zeroout_es(inode, &zero_ex); return err ? err : allocated; } @@ -3562,7 +3669,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, if (err < 0) goto out; ext4_ext_drop_refs(path); - path = ext4_ext_find_extent(inode, map->m_lblk, path); + path = ext4_ext_find_extent(inode, map->m_lblk, path, 0); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; @@ -4049,7 +4156,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ - path = ext4_ext_find_extent(inode, map->m_lblk, NULL); + path = ext4_ext_find_extent(inode, map->m_lblk, NULL, 0); if (IS_ERR(path)) { err = PTR_ERR(path); path = NULL; @@ -4261,8 +4368,8 @@ got_allocated_blocks: /* not a good idea to call discard here directly, * but otherwise we'd need to call it every free() */ ext4_discard_preallocations(inode); - ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex), - ext4_ext_get_actual_len(&newex), fb_flags); + ext4_free_blocks(handle, inode, NULL, newblock, + EXT4_C2B(sbi, allocated_clusters), fb_flags); goto out2; } @@ -4382,8 +4489,9 @@ out2: } out3: - trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); - + trace_ext4_ext_map_blocks_exit(inode, flags, map, + err ? err : allocated); + ext4_es_lru_add(inode); return err ? err : allocated; } @@ -4405,9 +4513,20 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); +retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); + if (err == -ENOMEM) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + if (err) { + ext4_std_error(inode->i_sb, err); + return; + } err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); + ext4_std_error(inode->i_sb, err); } static void ext4_falloc_update_inode(struct inode *inode, @@ -4729,6 +4848,12 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return error; } + if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { + error = ext4_ext_precache(inode); + if (error) + return error; + } + /* fallback to generic here if not in extents fmt */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return generic_block_fiemap(inode, fieinfo, start, len, @@ -4756,6 +4881,6 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, error = ext4_fill_fiemap_extents(inode, start_blk, len_blks, fieinfo); } - + ext4_es_lru_add(inode); return error; } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index ee018d5..3981ff7 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -13,7 +13,6 @@ #include <linux/list_sort.h> #include "ext4.h" #include "extents_status.h" -#include "ext4_extents.h" #include <trace/events/ext4.h> @@ -148,6 +147,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end); static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei, int nr_to_scan); +static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, + struct ext4_inode_info *locked_ei); int __init ext4_init_es(void) { @@ -261,7 +262,7 @@ void ext4_es_find_delayed_extent_range(struct inode *inode, if (tree->cache_es) { es1 = tree->cache_es; if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u) %llu %llx\n", + es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; @@ -407,6 +408,8 @@ ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) } #ifdef ES_AGGRESSIVE_TEST +#include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ + static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { @@ -417,7 +420,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, unsigned short ee_len; int depth, ee_status, es_status; - path = ext4_ext_find_extent(inode, es->es_lblk, NULL); + path = ext4_ext_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; @@ -439,7 +442,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { - pr_warn("ES insert assertation failed for " + pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add an delayed/hole extent " @@ -458,7 +461,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, @@ -468,7 +471,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, } if (ee_status ^ es_status) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, @@ -481,7 +484,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add an written/unwritten extent " "[%d/%d/%llu/%llx]\n", inode->i_ino, @@ -519,7 +522,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode, * We want to add a delayed/hole extent but this * block has been allocated. */ - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%llx]\n", inode->i_ino, es->es_lblk, es->es_len, @@ -527,13 +530,13 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode, return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { - pr_warn("ES insert assertation failed for " + pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { - pr_warn("ES insert assertation failed for " + pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, @@ -549,7 +552,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode, } } else if (retval == 0) { if (ext4_es_is_written(es)) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "an written extent [%d/%d/%llu/%llx]\n", inode->i_ino, es->es_lblk, es->es_len, @@ -632,22 +635,20 @@ out: } /* - * ext4_es_insert_extent() adds a space to a extent status tree. - * - * ext4_es_insert_extent is called by ext4_da_write_begin and - * ext4_es_remove_extent. + * ext4_es_insert_extent() adds information to an inode's extent + * status tree. * * Return 0 on success, error code on failure. */ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, - unsigned long long status) + unsigned int status) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err = 0; - es_debug("add [%u/%u) %llu %llx to extent status tree of inode %lu\n", + es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); if (!len) @@ -667,7 +668,13 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, err = __es_remove_extent(inode, lblk, end); if (err != 0) goto error; +retry: err = __es_insert_extent(inode, &newes); + if (err == -ENOMEM && __ext4_es_shrink(EXT4_SB(inode->i_sb), 1, + EXT4_I(inode))) + goto retry; + if (err == -ENOMEM && !ext4_es_is_delayed(&newes)) + err = 0; error: write_unlock(&EXT4_I(inode)->i_es_lock); @@ -678,6 +685,38 @@ error: } /* + * ext4_es_cache_extent() inserts information into the extent status + * tree if and only if there isn't information about the range in + * question already. + */ +void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, ext4_fsblk_t pblk, + unsigned int status) +{ + struct extent_status *es; + struct extent_status newes; + ext4_lblk_t end = lblk + len - 1; + + newes.es_lblk = lblk; + newes.es_len = len; + ext4_es_store_pblock(&newes, pblk); + ext4_es_store_status(&newes, status); + trace_ext4_es_cache_extent(inode, &newes); + + if (!len) + return; + + BUG_ON(end < lblk); + + write_lock(&EXT4_I(inode)->i_es_lock); + + es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk); + if (!es || es->es_lblk > end) + __es_insert_extent(inode, &newes); + write_unlock(&EXT4_I(inode)->i_es_lock); +} + +/* * ext4_es_lookup_extent() looks up an extent in extent status tree. * * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks. @@ -746,8 +785,10 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; - int err = 0; + int err; +retry: + err = 0; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; @@ -782,6 +823,10 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, if (err) { es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; + if ((err == -ENOMEM) && + __ext4_es_shrink(EXT4_SB(inode->i_sb), 1, + EXT4_I(inode))) + goto retry; goto out; } } else { @@ -859,23 +904,6 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, return err; } -int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex) -{ - ext4_lblk_t ee_block; - ext4_fsblk_t ee_pblock; - unsigned int ee_len; - - ee_block = le32_to_cpu(ex->ee_block); - ee_len = ext4_ext_get_actual_len(ex); - ee_pblock = ext4_ext_pblock(ex); - - if (ee_len == 0) - return 0; - - return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, - EXTENT_STATUS_WRITTEN); -} - static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a, struct list_head *b) { @@ -883,6 +911,12 @@ static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a, eia = list_entry(a, struct ext4_inode_info, i_es_lru); eib = list_entry(b, struct ext4_inode_info, i_es_lru); + if (ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) && + !ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED)) + return 1; + if (!ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) && + ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED)) + return -1; if (eia->i_touch_when == eib->i_touch_when) return 0; if (time_after(eia->i_touch_when, eib->i_touch_when)) @@ -891,35 +925,21 @@ static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a, return -1; } -static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) +static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, + struct ext4_inode_info *locked_ei) { - struct ext4_sb_info *sbi = container_of(shrink, - struct ext4_sb_info, s_es_shrinker); struct ext4_inode_info *ei; struct list_head *cur, *tmp; - LIST_HEAD(skiped); - int nr_to_scan = sc->nr_to_scan; - int ret, nr_shrunk = 0; - - ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); - trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret); - - if (!nr_to_scan) - return ret; + LIST_HEAD(skipped); + int nr_shrunk = 0; + int retried = 0, skip_precached = 1, nr_skipped = 0; spin_lock(&sbi->s_es_lru_lock); - /* - * If the inode that is at the head of LRU list is newer than - * last_sorted time, that means that we need to sort this list. - */ - ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info, i_es_lru); - if (sbi->s_es_last_sorted < ei->i_touch_when) { - list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp); - sbi->s_es_last_sorted = jiffies; - } - +retry: list_for_each_safe(cur, tmp, &sbi->s_es_lru) { + int shrunk; + /* * If we have already reclaimed all extents from extent * status tree, just stop the loop immediately. @@ -929,34 +949,96 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) ei = list_entry(cur, struct ext4_inode_info, i_es_lru); - /* Skip the inode that is newer than the last_sorted time */ - if (sbi->s_es_last_sorted < ei->i_touch_when) { - list_move_tail(cur, &skiped); + /* + * Skip the inode that is newer than the last_sorted + * time. Normally we try hard to avoid shrinking + * precached inodes, but we will as a last resort. + */ + if ((sbi->s_es_last_sorted < ei->i_touch_when) || + (skip_precached && ext4_test_inode_state(&ei->vfs_inode, + EXT4_STATE_EXT_PRECACHED))) { + nr_skipped++; + list_move_tail(cur, &skipped); continue; } - if (ei->i_es_lru_nr == 0) + if (ei->i_es_lru_nr == 0 || ei == locked_ei) continue; write_lock(&ei->i_es_lock); - ret = __es_try_to_reclaim_extents(ei, nr_to_scan); + shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan); if (ei->i_es_lru_nr == 0) list_del_init(&ei->i_es_lru); write_unlock(&ei->i_es_lock); - nr_shrunk += ret; - nr_to_scan -= ret; + nr_shrunk += shrunk; + nr_to_scan -= shrunk; if (nr_to_scan == 0) break; } /* Move the newer inodes into the tail of the LRU list. */ - list_splice_tail(&skiped, &sbi->s_es_lru); + list_splice_tail(&skipped, &sbi->s_es_lru); + INIT_LIST_HEAD(&skipped); + + /* + * If we skipped any inodes, and we weren't able to make any + * forward progress, sort the list and try again. + */ + if ((nr_shrunk == 0) && nr_skipped && !retried) { + retried++; + list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp); + sbi->s_es_last_sorted = jiffies; + ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info, + i_es_lru); + /* + * If there are no non-precached inodes left on the + * list, start releasing precached extents. + */ + if (ext4_test_inode_state(&ei->vfs_inode, + EXT4_STATE_EXT_PRECACHED)) + skip_precached = 0; + goto retry; + } + spin_unlock(&sbi->s_es_lru_lock); + if (locked_ei && nr_shrunk == 0) + nr_shrunk = __es_try_to_reclaim_extents(locked_ei, nr_to_scan); + + return nr_shrunk; +} + +static unsigned long ext4_es_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long nr; + struct ext4_sb_info *sbi; + + sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); + nr = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); + trace_ext4_es_shrink_enter(sbi->s_sb, sc->nr_to_scan, nr); + return nr; +} + +static unsigned long ext4_es_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct ext4_sb_info *sbi = container_of(shrink, + struct ext4_sb_info, s_es_shrinker); + int nr_to_scan = sc->nr_to_scan; + int ret, nr_shrunk; + ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); + trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret); + + if (!nr_to_scan) + return ret; + + nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL); + trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret); - return ret; + return nr_shrunk; } void ext4_es_register_shrinker(struct ext4_sb_info *sbi) @@ -964,7 +1046,8 @@ void ext4_es_register_shrinker(struct ext4_sb_info *sbi) INIT_LIST_HEAD(&sbi->s_es_lru); spin_lock_init(&sbi->s_es_lru_lock); sbi->s_es_last_sorted = 0; - sbi->s_es_shrinker.shrink = ext4_es_shrink; + sbi->s_es_shrinker.scan_objects = ext4_es_scan; + sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; register_shrinker(&sbi->s_es_shrinker); } @@ -1008,11 +1091,17 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei, struct ext4_es_tree *tree = &ei->i_es_tree; struct rb_node *node; struct extent_status *es; - int nr_shrunk = 0; + unsigned long nr_shrunk = 0; + static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); if (ei->i_es_lru_nr == 0) return 0; + if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) && + __ratelimit(&_rs)) + ext4_warning(inode->i_sb, "forced shrink of precached extents"); + node = rb_first(&tree->root); while (node != NULL) { es = rb_entry(node, struct extent_status, rb_node); diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index e936730..167f4ab8 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -29,16 +29,26 @@ /* * These flags live in the high bits of extent_status.es_pblk */ -#define EXTENT_STATUS_WRITTEN (1ULL << 63) -#define EXTENT_STATUS_UNWRITTEN (1ULL << 62) -#define EXTENT_STATUS_DELAYED (1ULL << 61) -#define EXTENT_STATUS_HOLE (1ULL << 60) +#define ES_SHIFT 60 + +#define EXTENT_STATUS_WRITTEN (1 << 3) +#define EXTENT_STATUS_UNWRITTEN (1 << 2) +#define EXTENT_STATUS_DELAYED (1 << 1) +#define EXTENT_STATUS_HOLE (1 << 0) #define EXTENT_STATUS_FLAGS (EXTENT_STATUS_WRITTEN | \ EXTENT_STATUS_UNWRITTEN | \ EXTENT_STATUS_DELAYED | \ EXTENT_STATUS_HOLE) +#define ES_WRITTEN (1ULL << 63) +#define ES_UNWRITTEN (1ULL << 62) +#define ES_DELAYED (1ULL << 61) +#define ES_HOLE (1ULL << 60) + +#define ES_MASK (ES_WRITTEN | ES_UNWRITTEN | \ + ES_DELAYED | ES_HOLE) + struct ext4_sb_info; struct ext4_extent; @@ -60,7 +70,10 @@ extern void ext4_es_init_tree(struct ext4_es_tree *tree); extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, - unsigned long long status); + unsigned int status); +extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, ext4_fsblk_t pblk, + unsigned int status); extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); extern void ext4_es_find_delayed_extent_range(struct inode *inode, @@ -68,36 +81,35 @@ extern void ext4_es_find_delayed_extent_range(struct inode *inode, struct extent_status *es); extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es); -extern int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex); static inline int ext4_es_is_written(struct extent_status *es) { - return (es->es_pblk & EXTENT_STATUS_WRITTEN) != 0; + return (es->es_pblk & ES_WRITTEN) != 0; } static inline int ext4_es_is_unwritten(struct extent_status *es) { - return (es->es_pblk & EXTENT_STATUS_UNWRITTEN) != 0; + return (es->es_pblk & ES_UNWRITTEN) != 0; } static inline int ext4_es_is_delayed(struct extent_status *es) { - return (es->es_pblk & EXTENT_STATUS_DELAYED) != 0; + return (es->es_pblk & ES_DELAYED) != 0; } static inline int ext4_es_is_hole(struct extent_status *es) { - return (es->es_pblk & EXTENT_STATUS_HOLE) != 0; + return (es->es_pblk & ES_HOLE) != 0; } -static inline ext4_fsblk_t ext4_es_status(struct extent_status *es) +static inline unsigned int ext4_es_status(struct extent_status *es) { - return (es->es_pblk & EXTENT_STATUS_FLAGS); + return es->es_pblk >> ES_SHIFT; } static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es) { - return (es->es_pblk & ~EXTENT_STATUS_FLAGS); + return es->es_pblk & ~ES_MASK; } static inline void ext4_es_store_pblock(struct extent_status *es, @@ -105,19 +117,16 @@ static inline void ext4_es_store_pblock(struct extent_status *es, { ext4_fsblk_t block; - block = (pb & ~EXTENT_STATUS_FLAGS) | - (es->es_pblk & EXTENT_STATUS_FLAGS); + block = (pb & ~ES_MASK) | (es->es_pblk & ES_MASK); es->es_pblk = block; } static inline void ext4_es_store_status(struct extent_status *es, - unsigned long long status) + unsigned int status) { - ext4_fsblk_t block; - - block = (status & EXTENT_STATUS_FLAGS) | - (es->es_pblk & ~EXTENT_STATUS_FLAGS); - es->es_pblk = block; + es->es_pblk = (((ext4_fsblk_t) + (status & EXTENT_STATUS_FLAGS) << ES_SHIFT) | + (es->es_pblk & ~ES_MASK)); } extern void ext4_es_register_shrinker(struct ext4_sb_info *sbi); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6f4cc56..3da2194 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -149,7 +149,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); - if (ret > 0 || ret == -EIOCBQUEUED) { + if (ret > 0) { ssize_t err; err = generic_write_sync(file, pos, ret); @@ -219,7 +219,6 @@ static int ext4_file_open(struct inode * inode, struct file * filp) { struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct ext4_inode_info *ei = EXT4_I(inode); struct vfsmount *mnt = filp->f_path.mnt; struct path path; char buf[64], *cp; @@ -259,22 +258,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp) * Set up the jbd2_inode if we are opening the inode for * writing and the journal is present */ - if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) { - struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL); - - spin_lock(&inode->i_lock); - if (!ei->jinode) { - if (!jinode) { - spin_unlock(&inode->i_lock); - return -ENOMEM; - } - ei->jinode = jinode; - jbd2_journal_init_jbd_inode(ei->jinode, inode); - jinode = NULL; - } - spin_unlock(&inode->i_lock); - if (unlikely(jinode != NULL)) - jbd2_free_inode(jinode); + if (filp->f_mode & FMODE_WRITE) { + int ret = ext4_inode_attach_jinode(inode); + if (ret < 0) + return ret; } return dquot_file_open(inode, filp); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f03598c..137193f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -70,18 +70,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { + struct ext4_group_info *grp; J_ASSERT_BH(bh, buffer_locked(bh)); /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); - ext4_free_group_clusters_set(sb, gdp, 0); - ext4_free_inodes_set(sb, gdp, 0); - ext4_itable_unused_set(sb, gdp, 0); - memset(bh->b_data, 0xff, sb->s_blocksize); - ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh, - EXT4_INODES_PER_GROUP(sb) / 8); + grp = ext4_get_group_info(sb, block_group); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return 0; } @@ -117,6 +115,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) struct ext4_group_desc *desc; struct buffer_head *bh = NULL; ext4_fsblk_t bitmap_blk; + struct ext4_group_info *grp; desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) @@ -185,6 +184,8 @@ verify: put_bh(bh); ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " "inode_bitmap = %llu", block_group, bitmap_blk); + grp = ext4_get_group_info(sb, block_group); + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return NULL; } ext4_unlock_group(sb, block_group); @@ -221,6 +222,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) struct ext4_super_block *es; struct ext4_sb_info *sbi; int fatal = 0, err, count, cleared; + struct ext4_group_info *grp; if (!sb) { printk(KERN_ERR "EXT4-fs: %s:%d: inode on " @@ -266,7 +268,9 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); - if (!bitmap_bh) + /* Don't bother if the inode bitmap is corrupt. */ + grp = ext4_get_group_info(sb, block_group); + if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) || !bitmap_bh) goto error_return; BUFFER_TRACE(bitmap_bh, "get_write_access"); @@ -315,8 +319,10 @@ out: err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!fatal) fatal = err; - } else + } else { ext4_error(sb, "bit already cleared for inode %lu", ino); + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); + } error_return: brelse(bitmap_bh); @@ -625,6 +631,51 @@ static int find_group_other(struct super_block *sb, struct inode *parent, } /* + * In no journal mode, if an inode has recently been deleted, we want + * to avoid reusing it until we're reasonably sure the inode table + * block has been written back to disk. (Yes, these values are + * somewhat arbitrary...) + */ +#define RECENTCY_MIN 5 +#define RECENTCY_DIRTY 30 + +static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) +{ + struct ext4_group_desc *gdp; + struct ext4_inode *raw_inode; + struct buffer_head *bh; + unsigned long dtime, now; + int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; + int offset, ret = 0, recentcy = RECENTCY_MIN; + + gdp = ext4_get_group_desc(sb, group, NULL); + if (unlikely(!gdp)) + return 0; + + bh = sb_getblk(sb, ext4_inode_table(sb, gdp) + + (ino / inodes_per_block)); + if (unlikely(!bh) || !buffer_uptodate(bh)) + /* + * If the block is not in the buffer cache, then it + * must have been written out. + */ + goto out; + + offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb); + raw_inode = (struct ext4_inode *) (bh->b_data + offset); + dtime = le32_to_cpu(raw_inode->i_dtime); + now = get_seconds(); + if (buffer_dirty(bh)) + recentcy += RECENTCY_DIRTY; + + if (dtime && (dtime < now) && (now < dtime + recentcy)) + ret = 1; +out: + brelse(bh); + return ret; +} + +/* * There are two policies for allocating an inode. If the new inode is * a directory, then a forward search is made for a block group with both * free space and a low directory-to-inode ratio; if that fails, then of @@ -652,6 +703,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, struct inode *ret; ext4_group_t i; ext4_group_t flex_group; + struct ext4_group_info *grp; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) @@ -725,25 +777,39 @@ got_group: continue; } + grp = ext4_get_group_info(sb, group); + /* Skip groups with already-known suspicious inode tables */ + if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + if (++group == ngroups) + group = 0; + continue; + } + brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); - if (!inode_bitmap_bh) - goto out; + /* Skip groups with suspicious inode tables */ + if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || !inode_bitmap_bh) { + if (++group == ngroups) + group = 0; + continue; + } repeat_in_this_group: ino = ext4_find_next_zero_bit((unsigned long *) inode_bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino); - if (ino >= EXT4_INODES_PER_GROUP(sb)) { - if (++group == ngroups) - group = 0; - continue; - } + if (ino >= EXT4_INODES_PER_GROUP(sb)) + goto next_group; if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) { ext4_error(sb, "reserved inode found cleared - " "inode=%lu", ino + 1); continue; } + if ((EXT4_SB(sb)->s_journal == NULL) && + recently_deleted(sb, group, ino)) { + ino++; + goto next_inode; + } if (!handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(dir->i_sb, line_no, @@ -767,8 +833,12 @@ repeat_in_this_group: ino++; /* the inode bitmap is zero-based */ if (!ret2) goto got; /* we grabbed the inode! */ +next_inode: if (ino < EXT4_INODES_PER_GROUP(sb)) goto repeat_in_this_group; +next_group: + if (++group == ngroups) + group = 0; } err = -ENOSPC; goto out; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 87b30cd..594009f 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -23,7 +23,6 @@ #include <linux/aio.h> #include "ext4_jbd2.h" #include "truncate.h" -#include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */ #include <trace/events/ext4.h> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0188e65..0d424d7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -465,7 +465,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { - printk("ES cache assertation failed for inode: %lu " + printk("ES cache assertion failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, @@ -514,10 +514,9 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, "logical block %lu\n", inode->i_ino, flags, map->m_len, (unsigned long) map->m_lblk); - ext4_es_lru_add(inode); - /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { + ext4_es_lru_add(inode); if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; @@ -554,16 +553,15 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, } if (retval > 0) { int ret; - unsigned long long status; + unsigned int status; -#ifdef ES_AGGRESSIVE_TEST - if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " - "retval %d != map->m_len %d " - "in %s (lookup)\n", inode->i_ino, retval, - map->m_len, __func__); + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); } -#endif status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; @@ -655,16 +653,15 @@ found: if (retval > 0) { int ret; - unsigned long long status; + unsigned int status; -#ifdef ES_AGGRESSIVE_TEST - if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " - "retval %d != map->m_len %d " - "in %s (allocation)\n", inode->i_ino, retval, - map->m_len, __func__); + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); } -#endif /* * If the extent has been zeroed out, we don't need to update @@ -730,8 +727,12 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ret = ext4_map_blocks(handle, inode, &map, flags); if (ret > 0) { + 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; + if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) + set_buffer_defer_completion(bh); bh->b_size = inode->i_sb->s_blocksize * map.m_len; ret = 0; } @@ -972,7 +973,8 @@ retry_journal: ext4_journal_stop(handle); goto retry_grab; } - wait_on_page_writeback(page); + /* In case writeback began while the page was unlocked */ + wait_for_stable_page(page); if (ext4_should_dioread_nolock(inode)) ret = __block_write_begin(page, pos, len, ext4_get_block_write); @@ -1529,11 +1531,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, "logical block %lu\n", inode->i_ino, map->m_len, (unsigned long) map->m_lblk); - ext4_es_lru_add(inode); - /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, &es)) { - + ext4_es_lru_add(inode); if (ext4_es_is_hole(&es)) { retval = 0; down_read((&EXT4_I(inode)->i_data_sem)); @@ -1638,16 +1638,15 @@ add_delayed: set_buffer_delay(bh); } else if (retval > 0) { int ret; - unsigned long long status; + unsigned int status; -#ifdef ES_AGGRESSIVE_TEST - if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " - "retval %d != map->m_len %d " - "in %s (lookup)\n", inode->i_ino, retval, - map->m_len, __func__); + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); } -#endif status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; @@ -1896,12 +1895,32 @@ static int ext4_writepage(struct page *page, return ret; } +static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) +{ + int len; + loff_t size = i_size_read(mpd->inode); + int err; + + BUG_ON(page->index != mpd->first_page); + if (page->index == size >> PAGE_CACHE_SHIFT) + len = size & ~PAGE_CACHE_MASK; + else + len = PAGE_CACHE_SIZE; + clear_page_dirty_for_io(page); + err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc); + if (!err) + mpd->wbc->nr_to_write--; + mpd->first_page++; + + return err; +} + #define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay)) /* * mballoc gives us at most this number of blocks... * XXX: That seems to be only a limitation of ext4_mb_normalize_request(). - * The rest of mballoc seems to handle chunks upto full group size. + * The rest of mballoc seems to handle chunks up to full group size. */ #define MAX_WRITEPAGES_EXTENT_LEN 2048 @@ -1910,82 +1929,94 @@ static int ext4_writepage(struct page *page, * * @mpd - extent of blocks * @lblk - logical number of the block in the file - * @b_state - b_state of the buffer head added + * @bh - buffer head we want to add to the extent * - * the function is used to collect contig. blocks in same state + * The function is used to collect contig. blocks in the same state. If the + * buffer doesn't require mapping for writeback and we haven't started the + * extent of buffers to map yet, the function returns 'true' immediately - the + * caller can write the buffer right away. Otherwise the function returns true + * if the block has been added to the extent, false if the block couldn't be + * added. */ -static int mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, - unsigned long b_state) +static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, + struct buffer_head *bh) { struct ext4_map_blocks *map = &mpd->map; - /* Don't go larger than mballoc is willing to allocate */ - if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) - return 0; + /* Buffer that doesn't need mapping for writeback? */ + if (!buffer_dirty(bh) || !buffer_mapped(bh) || + (!buffer_delay(bh) && !buffer_unwritten(bh))) { + /* So far no extent to map => we write the buffer right away */ + if (map->m_len == 0) + return true; + return false; + } /* First block in the extent? */ if (map->m_len == 0) { map->m_lblk = lblk; map->m_len = 1; - map->m_flags = b_state & BH_FLAGS; - return 1; + map->m_flags = bh->b_state & BH_FLAGS; + return true; } + /* Don't go larger than mballoc is willing to allocate */ + if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) + return false; + /* Can we merge the block to our big extent? */ if (lblk == map->m_lblk + map->m_len && - (b_state & BH_FLAGS) == map->m_flags) { + (bh->b_state & BH_FLAGS) == map->m_flags) { map->m_len++; - return 1; + return true; } - return 0; + return false; } -static bool add_page_bufs_to_extent(struct mpage_da_data *mpd, - struct buffer_head *head, - struct buffer_head *bh, - ext4_lblk_t lblk) +/* + * mpage_process_page_bufs - submit page buffers for IO or add them to extent + * + * @mpd - extent of blocks for mapping + * @head - the first buffer in the page + * @bh - buffer we should start processing from + * @lblk - logical number of the block in the file corresponding to @bh + * + * Walk through page buffers from @bh upto @head (exclusive) and either submit + * the page for IO if all buffers in this page were mapped and there's no + * accumulated extent of buffers to map or add buffers in the page to the + * extent of buffers to map. The function returns 1 if the caller can continue + * by processing the next page, 0 if it should stop adding buffers to the + * extent to map because we cannot extend it anymore. It can also return value + * < 0 in case of error during IO submission. + */ +static int mpage_process_page_bufs(struct mpage_da_data *mpd, + struct buffer_head *head, + struct buffer_head *bh, + ext4_lblk_t lblk) { struct inode *inode = mpd->inode; + int err; ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) >> inode->i_blkbits; do { BUG_ON(buffer_locked(bh)); - if (!buffer_dirty(bh) || !buffer_mapped(bh) || - (!buffer_delay(bh) && !buffer_unwritten(bh)) || - lblk >= blocks) { + if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) { /* Found extent to map? */ if (mpd->map.m_len) - return false; - if (lblk >= blocks) - return true; - continue; + return 0; + /* Everything mapped so far and we hit EOF */ + break; } - if (!mpage_add_bh_to_extent(mpd, lblk, bh->b_state)) - return false; } while (lblk++, (bh = bh->b_this_page) != head); - return true; -} - -static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) -{ - int len; - loff_t size = i_size_read(mpd->inode); - int err; - - BUG_ON(page->index != mpd->first_page); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - clear_page_dirty_for_io(page); - err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc); - if (!err) - mpd->wbc->nr_to_write--; - mpd->first_page++; - - return err; + /* So far everything mapped? Submit the page for IO. */ + if (mpd->map.m_len == 0) { + err = mpage_submit_page(mpd, head->b_page); + if (err < 0) + return err; + } + return lblk < blocks; } /* @@ -2009,8 +2040,6 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) struct inode *inode = mpd->inode; struct buffer_head *head, *bh; int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits; - ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) - >> inode->i_blkbits; pgoff_t start, end; ext4_lblk_t lblk; sector_t pblock; @@ -2032,7 +2061,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) if (page->index > end) break; - /* Upto 'end' pages must be contiguous */ + /* Up to 'end' pages must be contiguous */ BUG_ON(page->index != start); bh = head = page_buffers(page); do { @@ -2045,18 +2074,26 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) */ mpd->map.m_len = 0; mpd->map.m_flags = 0; - add_page_bufs_to_extent(mpd, head, bh, - lblk); + /* + * FIXME: If dioread_nolock supports + * blocksize < pagesize, we need to make + * sure we add size mapped so far to + * io_end->size as the following call + * can submit the page for IO. + */ + err = mpage_process_page_bufs(mpd, head, + bh, lblk); pagevec_release(&pvec); - return 0; + if (err > 0) + err = 0; + return err; } if (buffer_delay(bh)) { clear_buffer_delay(bh); bh->b_blocknr = pblock++; } clear_buffer_unwritten(bh); - } while (++lblk < blocks && - (bh = bh->b_this_page) != head); + } while (lblk++, (bh = bh->b_this_page) != head); /* * FIXME: This is going to break if dioread_nolock @@ -2163,7 +2200,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, mpd->io_submit.io_end->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; - while (map->m_len) { + do { err = mpage_map_one_extent(handle, mpd); if (err < 0) { struct super_block *sb = inode->i_sb; @@ -2201,16 +2238,14 @@ static int mpage_map_and_submit_extent(handle_t *handle, err = mpage_map_and_submit_buffers(mpd); if (err < 0) return err; - } + } while (map->m_len); /* Update on-disk size after IO is submitted */ disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); if (disksize > EXT4_I(inode)->i_disksize) { int err2; - ext4_update_i_disksize(inode, disksize); + ext4_wb_update_i_disksize(inode, disksize); err2 = ext4_mark_inode_dirty(handle, inode); if (err2) ext4_error(inode->i_sb, @@ -2225,7 +2260,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, /* * Calculate the total number of credits to reserve for one writepages * iteration. This is called from ext4_writepages(). We map an extent of - * upto MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping + * up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN + * bpp - 1 blocks in bpp different extents. */ @@ -2325,14 +2360,10 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) lblk = ((ext4_lblk_t)page->index) << (PAGE_CACHE_SHIFT - blkbits); head = page_buffers(page); - if (!add_page_bufs_to_extent(mpd, head, head, lblk)) + err = mpage_process_page_bufs(mpd, head, head, lblk); + if (err <= 0) goto out; - /* So far everything mapped? Submit the page for IO. */ - if (mpd->map.m_len == 0) { - err = mpage_submit_page(mpd, page); - if (err < 0) - goto out; - } + err = 0; /* * Accumulated enough dirty pages? This doesn't apply @@ -2416,7 +2447,7 @@ static int ext4_writepages(struct address_space *mapping, if (ext4_should_dioread_nolock(inode)) { /* - * We may need to convert upto one extent per block in + * We may need to convert up to one extent per block in * the page and we may dirty the inode. */ rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits); @@ -2652,7 +2683,7 @@ retry_journal: goto retry_grab; } /* In case writeback began while the page was unlocked */ - wait_on_page_writeback(page); + wait_for_stable_page(page); ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep); if (ret < 0) { @@ -2997,19 +3028,13 @@ static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, } static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, - ssize_t size, void *private, int ret, - bool is_async) + ssize_t size, void *private) { - struct inode *inode = file_inode(iocb->ki_filp); ext4_io_end_t *io_end = iocb->private; /* if not async direct IO just return */ - if (!io_end) { - inode_dio_done(inode); - if (is_async) - aio_complete(iocb, ret, 0); + if (!io_end) return; - } ext_debug("ext4_end_io_dio(): io_end 0x%p " "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", @@ -3019,11 +3044,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, iocb->private = NULL; io_end->offset = offset; io_end->size = size; - if (is_async) { - io_end->iocb = iocb; - io_end->result = ret; - } - ext4_put_io_end_defer(io_end); + ext4_put_io_end(io_end); } /* @@ -3108,7 +3129,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, ret = -ENOMEM; goto retake_lock; } - io_end->flag |= EXT4_IO_END_DIRECT; /* * Grab reference for DIO. Will be dropped in ext4_end_io_dio() */ @@ -3153,13 +3173,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) { WARN_ON(iocb->private != io_end); WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN); - WARN_ON(io_end->iocb); - /* - * Generic code already did inode_dio_done() so we - * have to clear EXT4_IO_END_DIRECT to not do it for - * the second time. - */ - io_end->flag = 0; ext4_put_io_end(io_end); iocb->private = NULL; } @@ -3539,6 +3552,18 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + if (offset & (sb->s_blocksize - 1) || + (offset + length) & (sb->s_blocksize - 1)) { + /* + * Attach jinode to inode for jbd2 if we do any zeroing of + * partial block + */ + ret = ext4_inode_attach_jinode(inode); + if (ret < 0) + goto out_mutex; + + } + first_block_offset = round_up(offset, sb->s_blocksize); last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; @@ -3607,6 +3632,31 @@ out_mutex: return ret; } +int ext4_inode_attach_jinode(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct jbd2_inode *jinode; + + if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal) + return 0; + + jinode = jbd2_alloc_inode(GFP_KERNEL); + spin_lock(&inode->i_lock); + if (!ei->jinode) { + if (!jinode) { + spin_unlock(&inode->i_lock); + return -ENOMEM; + } + ei->jinode = jinode; + jbd2_journal_init_jbd_inode(ei->jinode, inode); + jinode = NULL; + } + spin_unlock(&inode->i_lock); + if (unlikely(jinode != NULL)) + jbd2_free_inode(jinode); + return 0; +} + /* * ext4_truncate() * @@ -3667,6 +3717,12 @@ void ext4_truncate(struct inode *inode) return; } + /* If we zero-out tail of the page, we have to create jinode for jbd2 */ + if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { + if (ext4_inode_attach_jinode(inode) < 0) + return; + } + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); else @@ -4529,7 +4585,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ext4_journal_stop(handle); } - if (attr->ia_valid & ATTR_SIZE) { + if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) { + handle_t *handle; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -4537,73 +4594,69 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_size > sbi->s_bitmap_maxbytes) return -EFBIG; } - } - - if (S_ISREG(inode->i_mode) && - attr->ia_valid & ATTR_SIZE && - (attr->ia_size < inode->i_size)) { - handle_t *handle; - - handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); - if (IS_ERR(handle)) { - error = PTR_ERR(handle); - goto err_out; - } - if (ext4_handle_valid(handle)) { - error = ext4_orphan_add(handle, inode); - orphan = 1; - } - EXT4_I(inode)->i_disksize = attr->ia_size; - rc = ext4_mark_inode_dirty(handle, inode); - if (!error) - error = rc; - ext4_journal_stop(handle); - - if (ext4_should_order_data(inode)) { - error = ext4_begin_ordered_truncate(inode, + if (S_ISREG(inode->i_mode) && + (attr->ia_size < inode->i_size)) { + if (ext4_should_order_data(inode)) { + error = ext4_begin_ordered_truncate(inode, attr->ia_size); - if (error) { - /* Do as much error cleanup as possible */ - handle = ext4_journal_start(inode, - EXT4_HT_INODE, 3); - if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); + if (error) goto err_out; - } - ext4_orphan_del(handle, inode); - orphan = 0; - ext4_journal_stop(handle); + } + handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); goto err_out; } - } - } - - if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size != inode->i_size) { - loff_t oldsize = inode->i_size; - - i_size_write(inode, attr->ia_size); - /* - * Blocks are going to be removed from the inode. Wait - * for dio in flight. Temporarily disable - * dioread_nolock to prevent livelock. - */ - if (orphan) { - if (!ext4_should_journal_data(inode)) { - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - ext4_inode_resume_unlocked_dio(inode); - } else - ext4_wait_for_tail_page_commit(inode); + if (ext4_handle_valid(handle)) { + error = ext4_orphan_add(handle, inode); + orphan = 1; } + down_write(&EXT4_I(inode)->i_data_sem); + EXT4_I(inode)->i_disksize = attr->ia_size; + rc = ext4_mark_inode_dirty(handle, inode); + if (!error) + error = rc; /* - * Truncate pagecache after we've waited for commit - * in data=journal mode to make pages freeable. + * We have to update i_size under i_data_sem together + * with i_disksize to avoid races with writeback code + * running ext4_wb_update_i_disksize(). */ - truncate_pagecache(inode, oldsize, inode->i_size); + if (!error) + i_size_write(inode, attr->ia_size); + up_write(&EXT4_I(inode)->i_data_sem); + ext4_journal_stop(handle); + if (error) { + ext4_orphan_del(NULL, inode); + goto err_out; + } + } else + i_size_write(inode, attr->ia_size); + + /* + * Blocks are going to be removed from the inode. Wait + * for dio in flight. Temporarily disable + * dioread_nolock to prevent livelock. + */ + if (orphan) { + if (!ext4_should_journal_data(inode)) { + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ext4_inode_resume_unlocked_dio(inode); + } else + ext4_wait_for_tail_page_commit(inode); } - ext4_truncate(inode); + /* + * Truncate pagecache after we've waited for commit + * in data=journal mode to make pages freeable. + */ + truncate_pagecache(inode, inode->i_size); } + /* + * We want to call ext4_truncate() even if attr->ia_size == + * inode->i_size for cases like truncation of fallocated space + */ + if (attr->ia_valid & ATTR_SIZE) + ext4_truncate(inode); if (!rc) { setattr_copy(inode, attr); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 9491ac0..a569d33 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -17,7 +17,6 @@ #include <asm/uaccess.h> #include "ext4_jbd2.h" #include "ext4.h" -#include "ext4_extents.h" #define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1) @@ -77,8 +76,10 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags)); memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize)); - memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree)); - memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr)); + ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS); + ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS); + ext4_es_lru_del(inode1); + ext4_es_lru_del(inode2); isize = i_size_read(inode1); i_size_write(inode1, i_size_read(inode2)); @@ -622,6 +623,8 @@ resizefs_out: return 0; } + case EXT4_IOC_PRECACHE_EXTENTS: + return ext4_ext_precache(inode); default: return -ENOTTY; @@ -686,6 +689,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_MOVE_EXT: case FITRIM: case EXT4_IOC_RESIZE_FS: + case EXT4_IOC_PRECACHE_EXTENTS: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a9ff5e5..a41e3ba 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -751,13 +751,15 @@ void ext4_mb_generate_buddy(struct super_block *sb, if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, - "%u clusters in bitmap, %u in gd", + "%u clusters in bitmap, %u in gd; " + "block bitmap corrupt.", free, grp->bb_free); /* - * If we intent to continue, we consider group descritor + * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); } mb_set_largest_free_order(sb, grp); @@ -1398,6 +1400,10 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); + /* Don't bother if the block group is corrupt. */ + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + return; + mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); @@ -1423,7 +1429,11 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, inode ? inode->i_ino : 0, blocknr, "freeing already freed block " - "(bit %u)", block); + "(bit %u); block bitmap corrupt.", + block); + /* Mark the block group as corrupt. */ + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, + &e4b->bd_info->bb_state); mb_regenerate_buddy(e4b); goto done; } @@ -1790,6 +1800,11 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { + ext4_mb_unload_buddy(e4b); + return 0; + } + ext4_lock_group(ac->ac_sb, group); max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); @@ -1987,6 +2002,9 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, if (cr <= 2 && free < ac->ac_g_ex.fe_len) return 0; + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + return 0; + /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { int ret = ext4_mb_init_group(ac->ac_sb, group); @@ -4585,6 +4603,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *gd_bh; ext4_group_t block_group; struct ext4_sb_info *sbi; + struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; @@ -4673,6 +4692,10 @@ do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT( + ext4_get_group_info(sb, block_group)))) + return; + /* * Check to see if we are freeing blocks across a group * boundary. @@ -4740,11 +4763,16 @@ do_more: * blocks being freed are metadata. these blocks shouldn't * be used until this transaction is committed */ + retry: new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS); if (!new_entry) { - ext4_mb_unload_buddy(&e4b); - err = -ENOMEM; - goto error_return; + /* + * We use a retry loop because + * ext4_free_blocks() is not allowed to fail. + */ + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; } new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; @@ -4779,7 +4807,6 @@ do_more: ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); - percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); @@ -4787,10 +4814,23 @@ do_more: &sbi->s_flex_groups[flex_group].free_clusters); } - ext4_mb_unload_buddy(&e4b); - - if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) + if (flags & EXT4_FREE_BLOCKS_RESERVE && ei->i_reserved_data_blocks) { + percpu_counter_add(&sbi->s_dirtyclusters_counter, + count_clusters); + spin_lock(&ei->i_block_reservation_lock); + if (flags & EXT4_FREE_BLOCKS_METADATA) + ei->i_reserved_meta_blocks += count_clusters; + else + ei->i_reserved_data_blocks += count_clusters; + spin_unlock(&ei->i_block_reservation_lock); + if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) + dquot_reclaim_block(inode, + EXT4_C2B(sbi, count_clusters)); + } else if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); + percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); + + ext4_mb_unload_buddy(&e4b); /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 49e8bdf..2ae73a8 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -39,7 +39,7 @@ static int finish_range(handle_t *handle, struct inode *inode, newext.ee_block = cpu_to_le32(lb->first_block); newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1); ext4_ext_store_pblock(&newext, lb->first_pblock); - path = ext4_ext_find_extent(inode, lb->first_block, NULL); + path = ext4_ext_find_extent(inode, lb->first_block, NULL, 0); if (IS_ERR(path)) { retval = PTR_ERR(path); @@ -494,7 +494,7 @@ int ext4_ext_migrate(struct inode *inode) * superblock modification. * * For the tmp_inode we already have committed the - * trascation that created the inode. Later as and + * transaction that created the inode. Later as and * when we add extents we extent the journal */ /* diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index e86dddb..7fa4d85 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -37,7 +37,7 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, int ret = 0; struct ext4_ext_path *path; - path = ext4_ext_find_extent(inode, lblock, *orig_path); + path = ext4_ext_find_extent(inode, lblock, *orig_path, EXT4_EX_NOCACHE); if (IS_ERR(path)) ret = PTR_ERR(path); else if (path[ext_depth(inode)].p_ext == NULL) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 234b834..1bec5a5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2316,11 +2316,11 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); + d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); if (err) goto err_drop_inode; mark_inode_dirty(inode); - d_tmpfile(dentry, inode); unlock_new_inode(inode); } if (handle) @@ -3005,15 +3005,19 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, /* * Anybody can rename anything with this: the permission checks are left to the * higher-level routines. + * + * n.b. old_{dentry,inode) refers to the source dentry/inode + * while new_{dentry,inode) refers to the destination dentry/inode + * This comes from rename(const char *oldpath, const char *newpath) */ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { - handle_t *handle; + handle_t *handle = NULL; struct inode *old_inode, *new_inode; struct buffer_head *old_bh, *new_bh, *dir_bh; struct ext4_dir_entry_2 *old_de, *new_de; - int retval, force_da_alloc = 0; + int retval; int inlined = 0, new_inlined = 0; struct ext4_dir_entry_2 *parent_de; @@ -3026,14 +3030,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, * in separate transaction */ if (new_dentry->d_inode) dquot_initialize(new_dentry->d_inode); - handle = ext4_journal_start(old_dir, EXT4_HT_DIR, - (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - - if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) - ext4_handle_sync(handle); old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de, NULL); /* @@ -3056,6 +3052,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, new_bh = NULL; } } + if (new_inode && !test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC)) + ext4_alloc_da_blocks(old_inode); + + handle = ext4_journal_start(old_dir, EXT4_HT_DIR, + (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) + ext4_handle_sync(handle); + if (S_ISDIR(old_inode->i_mode)) { if (new_inode) { retval = -ENOTEMPTY; @@ -3186,8 +3194,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, ext4_mark_inode_dirty(handle, new_inode); if (!new_inode->i_nlink) ext4_orphan_add(handle, new_inode); - if (!test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC)) - force_da_alloc = 1; } retval = 0; @@ -3195,9 +3201,8 @@ end_rename: brelse(dir_bh); brelse(old_bh); brelse(new_bh); - ext4_journal_stop(handle); - if (retval == 0 && force_da_alloc) - ext4_alloc_da_blocks(old_inode); + if (handle) + ext4_journal_stop(handle); return retval; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 48786cd..d7d0c7b 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -25,6 +25,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/ratelimit.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -55,7 +56,7 @@ void ext4_exit_pageio(void) static void buffer_io_error(struct buffer_head *bh) { char b[BDEVNAME_SIZE]; - printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", + printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); } @@ -122,10 +123,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end) ext4_finish_bio(bio); bio_put(bio); } - if (io_end->flag & EXT4_IO_END_DIRECT) - inode_dio_done(io_end->inode); - if (io_end->iocb) - aio_complete(io_end->iocb, io_end->result, 0); kmem_cache_free(io_end_cachep, io_end); } @@ -203,19 +200,14 @@ static void ext4_add_complete_io(ext4_io_end_t *io_end) struct workqueue_struct *wq; unsigned long flags; - BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN)); + /* Only reserved conversions from writeback should enter here */ + WARN_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN)); + WARN_ON(!io_end->handle); spin_lock_irqsave(&ei->i_completed_io_lock, flags); - if (io_end->handle) { - wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq; - if (list_empty(&ei->i_rsv_conversion_list)) - queue_work(wq, &ei->i_rsv_conversion_work); - list_add_tail(&io_end->list, &ei->i_rsv_conversion_list); - } else { - wq = EXT4_SB(io_end->inode->i_sb)->unrsv_conversion_wq; - if (list_empty(&ei->i_unrsv_conversion_list)) - queue_work(wq, &ei->i_unrsv_conversion_work); - list_add_tail(&io_end->list, &ei->i_unrsv_conversion_list); - } + wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq; + if (list_empty(&ei->i_rsv_conversion_list)) + queue_work(wq, &ei->i_rsv_conversion_work); + list_add_tail(&io_end->list, &ei->i_rsv_conversion_list); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); } @@ -255,13 +247,6 @@ void ext4_end_io_rsv_work(struct work_struct *work) ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list); } -void ext4_end_io_unrsv_work(struct work_struct *work) -{ - struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info, - i_unrsv_conversion_work); - ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_unrsv_conversion_list); -} - ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) { ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags); @@ -308,6 +293,7 @@ ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) return io_end; } +/* BIO completion function for page writeback */ static void ext4_end_bio(struct bio *bio, int error) { ext4_io_end_t *io_end = bio->bi_private; @@ -318,18 +304,6 @@ static void ext4_end_bio(struct bio *bio, int error) if (test_bit(BIO_UPTODATE, &bio->bi_flags)) error = 0; - if (io_end->flag & EXT4_IO_END_UNWRITTEN) { - /* - * Link bio into list hanging from io_end. We have to do it - * atomically as bio completions can be racing against each - * other. - */ - bio->bi_private = xchg(&io_end->bio, bio); - } else { - ext4_finish_bio(bio); - bio_put(bio); - } - if (error) { struct inode *inode = io_end->inode; @@ -341,7 +315,24 @@ static void ext4_end_bio(struct bio *bio, int error) (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); } - ext4_put_io_end_defer(io_end); + + if (io_end->flag & EXT4_IO_END_UNWRITTEN) { + /* + * Link bio into list hanging from io_end. We have to do it + * atomically as bio completions can be racing against each + * other. + */ + bio->bi_private = xchg(&io_end->bio, bio); + ext4_put_io_end_defer(io_end); + } else { + /* + * Drop io_end reference early. Inode can get freed once + * we finish the bio. + */ + ext4_put_io_end_defer(io_end); + ext4_finish_bio(bio); + bio_put(bio); + } } void ext4_io_submit(struct ext4_io_submit *io) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 85b3dd6..2c2e6cb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -162,7 +162,7 @@ void *ext4_kvmalloc(size_t size, gfp_t flags) { void *ret; - ret = kmalloc(size, flags); + ret = kmalloc(size, flags | __GFP_NOWARN); if (!ret) ret = __vmalloc(size, flags, PAGE_KERNEL); return ret; @@ -172,7 +172,7 @@ void *ext4_kvzalloc(size_t size, gfp_t flags) { void *ret; - ret = kzalloc(size, flags); + ret = kzalloc(size, flags | __GFP_NOWARN); if (!ret) ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); return ret; @@ -762,9 +762,7 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - flush_workqueue(sbi->unrsv_conversion_wq); flush_workqueue(sbi->rsv_conversion_wq); - destroy_workqueue(sbi->unrsv_conversion_wq); destroy_workqueue(sbi->rsv_conversion_wq); if (sbi->s_journal) { @@ -875,14 +873,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); - INIT_LIST_HEAD(&ei->i_unrsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); - INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work); return &ei->vfs_inode; } @@ -1134,8 +1130,8 @@ enum { Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, - Opt_commit, Opt_min_batch_time, Opt_max_batch_time, - Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, + Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, + Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, @@ -1179,6 +1175,7 @@ static const match_table_t tokens = { {Opt_min_batch_time, "min_batch_time=%u"}, {Opt_max_batch_time, "max_batch_time=%u"}, {Opt_journal_dev, "journal_dev=%u"}, + {Opt_journal_path, "journal_path=%s"}, {Opt_journal_checksum, "journal_checksum"}, {Opt_journal_async_commit, "journal_async_commit"}, {Opt_abort, "abort"}, @@ -1338,6 +1335,7 @@ static int clear_qf_name(struct super_block *sb, int qtype) #define MOPT_NO_EXT2 0x0100 #define MOPT_NO_EXT3 0x0200 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) +#define MOPT_STRING 0x0400 static const struct mount_opts { int token; @@ -1359,7 +1357,7 @@ static const struct mount_opts { {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, - MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT}, + MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | @@ -1387,6 +1385,7 @@ static const struct mount_opts { {Opt_resuid, 0, MOPT_GTE0}, {Opt_resgid, 0, MOPT_GTE0}, {Opt_journal_dev, 0, MOPT_GTE0}, + {Opt_journal_path, 0, MOPT_STRING}, {Opt_journal_ioprio, 0, MOPT_GTE0}, {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, @@ -1480,7 +1479,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; } - if (args->from && match_int(args, &arg)) + if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg)) return -1; if (args->from && (m->flags & MOPT_GTE0) && (arg < 0)) return -1; @@ -1544,6 +1543,44 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; } *journal_devnum = arg; + } else if (token == Opt_journal_path) { + char *journal_path; + struct inode *journal_inode; + struct path path; + int error; + + if (is_remount) { + ext4_msg(sb, KERN_ERR, + "Cannot specify journal on remount"); + return -1; + } + journal_path = match_strdup(&args[0]); + if (!journal_path) { + ext4_msg(sb, KERN_ERR, "error: could not dup " + "journal device string"); + return -1; + } + + error = kern_path(journal_path, LOOKUP_FOLLOW, &path); + if (error) { + ext4_msg(sb, KERN_ERR, "error: could not find " + "journal device path: error %d", error); + kfree(journal_path); + return -1; + } + + journal_inode = path.dentry->d_inode; + if (!S_ISBLK(journal_inode->i_mode)) { + ext4_msg(sb, KERN_ERR, "error: journal path %s " + "is not a block device", journal_path); + path_put(&path); + kfree(journal_path); + return -1; + } + + *journal_devnum = new_encode_dev(journal_inode->i_rdev); + path_put(&path); + kfree(journal_path); } else if (token == Opt_journal_ioprio) { if (arg > 7) { ext4_msg(sb, KERN_ERR, "Invalid journal IO priority" @@ -1702,12 +1739,6 @@ static inline void ext4_show_quota_options(struct seq_file *seq, if (sbi->s_qf_names[GRPQUOTA]) seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]); - - if (test_opt(sb, USRQUOTA)) - seq_puts(seq, ",usrquota"); - - if (test_opt(sb, GRPQUOTA)) - seq_puts(seq, ",grpquota"); #endif } @@ -3489,7 +3520,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (test_opt(sb, DIOREAD_NOLOCK)) { ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and delalloc"); + "both data=journal and dioread_nolock"); goto failed_mount; } if (test_opt(sb, DELALLOC)) @@ -3624,10 +3655,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); - /* Do we have standard group size of blocksize * 8 blocks ? */ - if (sbi->s_blocks_per_group == blocksize << 3) - set_opt2(sb, STD_GROUP_SIZE); - for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; @@ -3697,6 +3724,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + /* Do we have standard group size of clustersize * 8 blocks ? */ + if (sbi->s_blocks_per_group == clustersize << 3) + set_opt2(sb, STD_GROUP_SIZE); + /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. @@ -3960,14 +3991,6 @@ no_journal: goto failed_mount4; } - EXT4_SB(sb)->unrsv_conversion_wq = - alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); - if (!EXT4_SB(sb)->unrsv_conversion_wq) { - printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); - ret = -ENOMEM; - goto failed_mount4; - } - /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. @@ -4121,8 +4144,6 @@ failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); - if (EXT4_SB(sb)->unrsv_conversion_wq) - destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); failed_mount_wq: if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -4570,7 +4591,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); - flush_workqueue(sbi->unrsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots @@ -4606,7 +4626,6 @@ static int ext4_sync_fs_nojournal(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq); - flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); dquot_writeback_dquots(sb, -1); if (wait && test_opt(sb, BARRIER)) ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL); @@ -4733,6 +4752,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + if (test_opt2(sb, EXPLICIT_DELALLOC)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and delalloc"); + err = -EINVAL; + goto restore_opts; + } + if (test_opt(sb, DIOREAD_NOLOCK)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dioread_nolock"); + err = -EINVAL; + goto restore_opts; + } + } + if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ext4_abort(sb, "Abort forced by user"); @@ -5487,6 +5521,7 @@ static void __exit ext4_exit_fs(void) kset_unregister(ext4_kset); ext4_exit_system_zone(); ext4_exit_pageio(); + ext4_exit_es(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 66a6b85..bb31220 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -182,7 +182,7 @@ const struct address_space_operations f2fs_meta_aops = { .set_page_dirty = f2fs_set_meta_page_dirty, }; -int check_orphan_space(struct f2fs_sb_info *sbi) +int acquire_orphan_inode(struct f2fs_sb_info *sbi) { unsigned int max_orphans; int err = 0; @@ -197,10 +197,19 @@ int check_orphan_space(struct f2fs_sb_info *sbi) mutex_lock(&sbi->orphan_inode_mutex); if (sbi->n_orphans >= max_orphans) err = -ENOSPC; + else + sbi->n_orphans++; mutex_unlock(&sbi->orphan_inode_mutex); return err; } +void release_orphan_inode(struct f2fs_sb_info *sbi) +{ + mutex_lock(&sbi->orphan_inode_mutex); + sbi->n_orphans--; + mutex_unlock(&sbi->orphan_inode_mutex); +} + void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { struct list_head *head, *this; @@ -229,21 +238,18 @@ retry: list_add(&new->list, this->prev); else list_add_tail(&new->list, head); - - sbi->n_orphans++; out: mutex_unlock(&sbi->orphan_inode_mutex); } void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { - struct list_head *this, *next, *head; + struct list_head *head; struct orphan_inode_entry *orphan; mutex_lock(&sbi->orphan_inode_mutex); head = &sbi->orphan_inode_list; - list_for_each_safe(this, next, head) { - orphan = list_entry(this, struct orphan_inode_entry, list); + list_for_each_entry(orphan, head, list) { if (orphan->ino == ino) { list_del(&orphan->list); kmem_cache_free(orphan_entry_slab, orphan); @@ -373,7 +379,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, if (!f2fs_crc_valid(crc, cp_block, crc_offset)) goto invalid_cp1; - pre_version = le64_to_cpu(cp_block->checkpoint_ver); + pre_version = cur_cp_version(cp_block); /* Read the 2nd cp block in this CP pack */ cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; @@ -388,7 +394,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, if (!f2fs_crc_valid(crc, cp_block, crc_offset)) goto invalid_cp2; - cur_version = le64_to_cpu(cp_block->checkpoint_ver); + cur_version = cur_cp_version(cp_block); if (cur_version == pre_version) { *version = cur_version; @@ -793,7 +799,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount) * Increase the version number so that * SIT entries and seg summaries are written at correct place */ - ckpt_ver = le64_to_cpu(ckpt->checkpoint_ver); + ckpt_ver = cur_cp_version(ckpt); ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); /* write cached NAT/SIT entries to NAT/SIT area */ diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 035f9a3..941f9b9 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -37,9 +37,9 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr) struct page *node_page = dn->node_page; unsigned int ofs_in_node = dn->ofs_in_node; - wait_on_page_writeback(node_page); + f2fs_wait_on_page_writeback(node_page, NODE, false); - rn = (struct f2fs_node *)page_address(node_page); + rn = F2FS_NODE(node_page); /* Get physical address of data block */ addr_array = blkaddr_in_node(rn); @@ -117,7 +117,8 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn) block_t start_blkaddr, end_blkaddr; BUG_ON(blk_addr == NEW_ADDR); - fofs = start_bidx_of_node(ofs_of_node(dn->node_page)) + dn->ofs_in_node; + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + dn->ofs_in_node; /* Update the page address in the parent node */ __set_data_blkaddr(dn, blk_addr); @@ -176,7 +177,6 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn) end_update: write_unlock(&fi->ext.ext_lock); sync_inode_page(dn); - return; } struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) @@ -260,8 +260,17 @@ repeat: if (PageUptodate(page)) return page; - BUG_ON(dn.data_blkaddr == NEW_ADDR); - BUG_ON(dn.data_blkaddr == NULL_ADDR); + /* + * A new dentry page is allocated but not able to be written, since its + * new inode page couldn't be allocated due to -ENOSPC. + * In such the case, its blkaddr can be remained as NEW_ADDR. + * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. + */ + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + return page; + } err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC); if (err) @@ -365,7 +374,6 @@ static void read_end_io(struct bio *bio, int err) } unlock_page(page); } while (bvec >= bio->bi_io_vec); - kfree(bio->bi_private); bio_put(bio); } @@ -391,7 +399,6 @@ int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page, bio->bi_end_io = read_end_io; if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { - kfree(bio->bi_private); bio_put(bio); up_read(&sbi->bio_sem); f2fs_put_page(page, 1); @@ -442,7 +449,7 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock, unsigned int end_offset; end_offset = IS_INODE(dn.node_page) ? - ADDRS_PER_INODE : + ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK; clear_buffer_new(bh_result); @@ -636,9 +643,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, int err = 0; int ilock; - /* for nobh_write_end */ - *fsdata = NULL; - f2fs_balance_fs(sbi); repeat: page = grab_cache_page_write_begin(mapping, index, flags); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 0d6c6aa..a84b0a8 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -29,7 +29,7 @@ static DEFINE_MUTEX(f2fs_stat_mutex); static void update_general_status(struct f2fs_sb_info *sbi) { - struct f2fs_stat_info *si = sbi->stat_info; + struct f2fs_stat_info *si = F2FS_STAT(sbi); int i; /* valid check of the segment numbers */ @@ -83,7 +83,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) */ static void update_sit_info(struct f2fs_sb_info *sbi) { - struct f2fs_stat_info *si = sbi->stat_info; + struct f2fs_stat_info *si = F2FS_STAT(sbi); unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist; struct sit_info *sit_i = SIT_I(sbi); unsigned int segno, vblocks; @@ -118,7 +118,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi) */ static void update_mem_info(struct f2fs_sb_info *sbi) { - struct f2fs_stat_info *si = sbi->stat_info; + struct f2fs_stat_info *si = F2FS_STAT(sbi); unsigned npages; if (si->base_mem) @@ -253,21 +253,21 @@ static int stat_show(struct seq_file *s, void *v) si->nats, NM_WOUT_THRESHOLD); seq_printf(s, " - SITs: %5d\n - free_nids: %5d\n", si->sits, si->fnids); - seq_printf(s, "\nDistribution of User Blocks:"); - seq_printf(s, " [ valid | invalid | free ]\n"); - seq_printf(s, " ["); + seq_puts(s, "\nDistribution of User Blocks:"); + seq_puts(s, " [ valid | invalid | free ]\n"); + seq_puts(s, " ["); for (j = 0; j < si->util_valid; j++) - seq_printf(s, "-"); - seq_printf(s, "|"); + seq_putc(s, '-'); + seq_putc(s, '|'); for (j = 0; j < si->util_invalid; j++) - seq_printf(s, "-"); - seq_printf(s, "|"); + seq_putc(s, '-'); + seq_putc(s, '|'); for (j = 0; j < si->util_free; j++) - seq_printf(s, "-"); - seq_printf(s, "]\n\n"); + seq_putc(s, '-'); + seq_puts(s, "]\n\n"); seq_printf(s, "SSR: %u blocks in %u segments\n", si->block_count[SSR], si->segment_count[SSR]); seq_printf(s, "LFS: %u blocks in %u segments\n", @@ -305,11 +305,10 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_stat_info *si; - sbi->stat_info = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL); - if (!sbi->stat_info) + si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL); + if (!si) return -ENOMEM; - si = sbi->stat_info; si->all_area_segs = le32_to_cpu(raw_super->segment_count); si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit); si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat); @@ -319,6 +318,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) si->main_area_zones = si->main_area_sections / le32_to_cpu(raw_super->secs_per_zone); si->sbi = sbi; + sbi->stat_info = si; mutex_lock(&f2fs_stat_mutex); list_add_tail(&si->stat_list, &f2fs_stat_list); @@ -329,13 +329,13 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { - struct f2fs_stat_info *si = sbi->stat_info; + struct f2fs_stat_info *si = F2FS_STAT(sbi); mutex_lock(&f2fs_stat_mutex); list_del(&si->stat_list); mutex_unlock(&f2fs_stat_mutex); - kfree(sbi->stat_info); + kfree(si); } void __init f2fs_create_root_stats(void) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 62f0d59..384c6da 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -270,12 +270,27 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) struct f2fs_node *rn; /* copy name info. to this inode page */ - rn = (struct f2fs_node *)page_address(ipage); + rn = F2FS_NODE(ipage); rn->i.i_namelen = cpu_to_le32(name->len); memcpy(rn->i.i_name, name->name, name->len); set_page_dirty(ipage); } +int update_dent_inode(struct inode *inode, const struct qstr *name) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) + return PTR_ERR(page); + + init_dent_inode(name, page); + f2fs_put_page(page, 1); + + return 0; +} + static int make_empty_dir(struct inode *inode, struct inode *parent, struct page *page) { @@ -557,6 +572,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, if (inode->i_nlink == 0) add_orphan_inode(sbi, inode->i_ino); + else + release_orphan_inode(sbi); } if (bit_pos == NR_DENTRY_IN_BLOCK) { diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 467d42d..608f0df 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/crc32.h> #include <linux/magic.h> +#include <linux/kobject.h> /* * For mount options @@ -28,6 +29,7 @@ #define F2FS_MOUNT_XATTR_USER 0x00000010 #define F2FS_MOUNT_POSIX_ACL 0x00000020 #define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040 +#define F2FS_MOUNT_INLINE_XATTR 0x00000080 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -134,11 +136,13 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i) /* * For INODE and NODE manager */ -#define XATTR_NODE_OFFSET (-1) /* - * store xattrs to one node block per - * file keeping -1 as its node offset to - * distinguish from index node blocks. - */ +/* + * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 + * as its node offset to distinguish from index node blocks. + * But some bits are used to mark the node block. + */ +#define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \ + >> OFFSET_BIT_SHIFT) enum { ALLOC_NODE, /* allocate a new node page if needed */ LOOKUP_NODE, /* look up a node without readahead */ @@ -178,6 +182,7 @@ struct f2fs_inode_info { f2fs_hash_t chash; /* hash value of given file name */ unsigned int clevel; /* maximum level of given file name */ nid_t i_xattr_nid; /* node id that contains xattrs */ + unsigned long long xattr_ver; /* cp version of xattr modification */ struct extent_info ext; /* in-memory extent cache entry */ }; @@ -296,15 +301,6 @@ struct f2fs_sm_info { }; /* - * For directory operation - */ -#define NODE_DIR1_BLOCK (ADDRS_PER_INODE + 1) -#define NODE_DIR2_BLOCK (ADDRS_PER_INODE + 2) -#define NODE_IND1_BLOCK (ADDRS_PER_INODE + 3) -#define NODE_IND2_BLOCK (ADDRS_PER_INODE + 4) -#define NODE_DIND_BLOCK (ADDRS_PER_INODE + 5) - -/* * For superblock */ /* @@ -350,6 +346,7 @@ enum page_type { struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ + struct proc_dir_entry *s_proc; /* proc entry */ struct buffer_head *raw_super_buf; /* buffer head of raw sb */ struct f2fs_super_block *raw_super; /* raw super block pointer */ int s_dirty; /* dirty flag for checkpoint */ @@ -429,6 +426,10 @@ struct f2fs_sb_info { #endif unsigned int last_victim[2]; /* last victim segment # */ spinlock_t stat_lock; /* lock for stat operations */ + + /* For sysfs suppport */ + struct kobject s_kobj; + struct completion s_kobj_unregister; }; /* @@ -454,6 +455,11 @@ static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi) return (struct f2fs_checkpoint *)(sbi->ckpt); } +static inline struct f2fs_node *F2FS_NODE(struct page *page) +{ + return (struct f2fs_node *)page_address(page); +} + static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi) { return (struct f2fs_nm_info *)(sbi->nm_info); @@ -489,6 +495,11 @@ static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi) sbi->s_dirty = 0; } +static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) +{ + return le64_to_cpu(cp->checkpoint_ver); +} + static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) { unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); @@ -677,7 +688,7 @@ static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi) { block_t start_addr; struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); - unsigned long long ckpt_version = le64_to_cpu(ckpt->checkpoint_ver); + unsigned long long ckpt_version = cur_cp_version(ckpt); start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); @@ -812,7 +823,7 @@ static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name, static inline bool IS_INODE(struct page *page) { - struct f2fs_node *p = (struct f2fs_node *)page_address(page); + struct f2fs_node *p = F2FS_NODE(page); return RAW_IS_INODE(p); } @@ -826,7 +837,7 @@ static inline block_t datablock_addr(struct page *node_page, { struct f2fs_node *raw_node; __le32 *addr_array; - raw_node = (struct f2fs_node *)page_address(node_page); + raw_node = F2FS_NODE(node_page); addr_array = blkaddr_in_node(raw_node); return le32_to_cpu(addr_array[offset]); } @@ -873,6 +884,7 @@ enum { FI_NO_ALLOC, /* should not allocate any blocks */ FI_UPDATE_DIR, /* should update inode block for consistency */ FI_DELAY_IPUT, /* used for the recovery */ + FI_INLINE_XATTR, /* used for inline xattr */ }; static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) @@ -905,6 +917,45 @@ static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag) return 0; } +static inline void get_inline_info(struct f2fs_inode_info *fi, + struct f2fs_inode *ri) +{ + if (ri->i_inline & F2FS_INLINE_XATTR) + set_inode_flag(fi, FI_INLINE_XATTR); +} + +static inline void set_raw_inline(struct f2fs_inode_info *fi, + struct f2fs_inode *ri) +{ + ri->i_inline = 0; + + if (is_inode_flag_set(fi, FI_INLINE_XATTR)) + ri->i_inline |= F2FS_INLINE_XATTR; +} + +static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi) +{ + if (is_inode_flag_set(fi, FI_INLINE_XATTR)) + return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS; + return DEF_ADDRS_PER_INODE; +} + +static inline void *inline_xattr_addr(struct page *page) +{ + struct f2fs_inode *ri; + ri = (struct f2fs_inode *)page_address(page); + return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE - + F2FS_INLINE_XATTR_ADDRS]); +} + +static inline int inline_xattr_size(struct inode *inode) +{ + if (is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR)) + return F2FS_INLINE_XATTR_ADDRS << 2; + else + return 0; +} + static inline int f2fs_readonly(struct super_block *sb) { return sb->s_flags & MS_RDONLY; @@ -947,6 +998,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); ino_t f2fs_inode_by_name(struct inode *, struct qstr *); void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, struct page *, struct inode *); +int update_dent_inode(struct inode *, const struct qstr *); int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *); void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *); int f2fs_make_empty(struct inode *, struct inode *); @@ -980,6 +1032,7 @@ int is_checkpointed_node(struct f2fs_sb_info *, nid_t); void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); int truncate_inode_blocks(struct inode *, pgoff_t); +int truncate_xattr_node(struct inode *, struct page *); int remove_inode_page(struct inode *); struct page *new_inode_page(struct inode *, const struct qstr *); struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *); @@ -1012,7 +1065,8 @@ int npages_for_summary_flush(struct f2fs_sb_info *); void allocate_new_segments(struct f2fs_sb_info *); struct page *get_sum_page(struct f2fs_sb_info *, unsigned int); struct bio *f2fs_bio_alloc(struct block_device *, int); -void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync); +void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool); +void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool); void write_meta_page(struct f2fs_sb_info *, struct page *); void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int, block_t, block_t *); @@ -1037,7 +1091,8 @@ void destroy_segment_manager(struct f2fs_sb_info *); struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); -int check_orphan_space(struct f2fs_sb_info *); +int acquire_orphan_inode(struct f2fs_sb_info *); +void release_orphan_inode(struct f2fs_sb_info *); void add_orphan_inode(struct f2fs_sb_info *, nid_t); void remove_orphan_inode(struct f2fs_sb_info *, nid_t); int recover_orphan_inodes(struct f2fs_sb_info *); @@ -1068,7 +1123,7 @@ int do_write_data_page(struct page *); */ int start_gc_thread(struct f2fs_sb_info *); void stop_gc_thread(struct f2fs_sb_info *); -block_t start_bidx_of_node(unsigned int); +block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *); int f2fs_gc(struct f2fs_sb_info *); void build_gc_manager(struct f2fs_sb_info *); int __init create_gc_caches(void); @@ -1112,11 +1167,16 @@ struct f2fs_stat_info { unsigned base_mem, cache_mem; }; +static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) +{ + return (struct f2fs_stat_info*)sbi->stat_info; +} + #define stat_inc_call_count(si) ((si)->call_count++) #define stat_inc_seg_count(sbi, type) \ do { \ - struct f2fs_stat_info *si = sbi->stat_info; \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ (si)->tot_segs++; \ if (type == SUM_TYPE_DATA) \ si->data_segs++; \ @@ -1129,14 +1189,14 @@ struct f2fs_stat_info { #define stat_inc_data_blk_count(sbi, blks) \ do { \ - struct f2fs_stat_info *si = sbi->stat_info; \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ stat_inc_tot_blk_count(si, blks); \ si->data_blks += (blks); \ } while (0) #define stat_inc_node_blk_count(sbi, blks) \ do { \ - struct f2fs_stat_info *si = sbi->stat_info; \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ stat_inc_tot_blk_count(si, blks); \ si->node_blks += (blks); \ } while (0) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d2d2b7d..02c9069 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -112,11 +112,13 @@ static int get_parent_ino(struct inode *inode, nid_t *pino) if (!dentry) return 0; - inode = igrab(dentry->d_parent->d_inode); - dput(dentry); + if (update_dent_inode(inode, &dentry->d_name)) { + dput(dentry); + return 0; + } - *pino = inode->i_ino; - iput(inode); + *pino = parent_ino(dentry); + dput(dentry); return 1; } @@ -147,9 +149,10 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) mutex_lock(&inode->i_mutex); - if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) - goto out; - + /* + * Both of fdatasync() and fsync() are able to be recovered from + * sudden-power-off. + */ if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) need_cp = true; else if (file_wrong_pino(inode)) @@ -158,10 +161,14 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) need_cp = true; else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) need_cp = true; + else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi))) + need_cp = true; if (need_cp) { nid_t pino; + F2FS_I(inode)->xattr_ver = 0; + /* all the dirty node pages should be flushed for POR */ ret = f2fs_sync_fs(inode->i_sb, 1); if (file_wrong_pino(inode) && inode->i_nlink == 1 && @@ -205,7 +212,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) struct f2fs_node *raw_node; __le32 *addr; - raw_node = page_address(dn->node_page); + raw_node = F2FS_NODE(dn->node_page); addr = blkaddr_in_node(raw_node) + ofs; for ( ; count > 0; count--, addr++, dn->ofs_in_node++) { @@ -283,7 +290,7 @@ static int truncate_blocks(struct inode *inode, u64 from) } if (IS_INODE(dn.node_page)) - count = ADDRS_PER_INODE; + count = ADDRS_PER_INODE(F2FS_I(inode)); else count = ADDRS_PER_BLOCK; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 35f9b1a..2f157e8 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -29,10 +29,11 @@ static struct kmem_cache *winode_slab; static int gc_thread_func(void *data) { struct f2fs_sb_info *sbi = data; + struct f2fs_gc_kthread *gc_th = sbi->gc_thread; wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; long wait_ms; - wait_ms = GC_THREAD_MIN_SLEEP_TIME; + wait_ms = gc_th->min_sleep_time; do { if (try_to_freeze()) @@ -45,7 +46,7 @@ static int gc_thread_func(void *data) break; if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) { - wait_ms = GC_THREAD_MAX_SLEEP_TIME; + wait_ms = increase_sleep_time(gc_th, wait_ms); continue; } @@ -66,15 +67,15 @@ static int gc_thread_func(void *data) continue; if (!is_idle(sbi)) { - wait_ms = increase_sleep_time(wait_ms); + wait_ms = increase_sleep_time(gc_th, wait_ms); mutex_unlock(&sbi->gc_mutex); continue; } if (has_enough_invalid_blocks(sbi)) - wait_ms = decrease_sleep_time(wait_ms); + wait_ms = decrease_sleep_time(gc_th, wait_ms); else - wait_ms = increase_sleep_time(wait_ms); + wait_ms = increase_sleep_time(gc_th, wait_ms); #ifdef CONFIG_F2FS_STAT_FS sbi->bg_gc++; @@ -82,7 +83,7 @@ static int gc_thread_func(void *data) /* if return value is not zero, no victim was selected */ if (f2fs_gc(sbi)) - wait_ms = GC_THREAD_NOGC_SLEEP_TIME; + wait_ms = gc_th->no_gc_sleep_time; } while (!kthread_should_stop()); return 0; } @@ -101,6 +102,12 @@ int start_gc_thread(struct f2fs_sb_info *sbi) goto out; } + gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME; + gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME; + gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME; + + gc_th->gc_idle = 0; + sbi->gc_thread = gc_th; init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head); sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi, @@ -125,9 +132,17 @@ void stop_gc_thread(struct f2fs_sb_info *sbi) sbi->gc_thread = NULL; } -static int select_gc_type(int gc_type) +static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type) { - return (gc_type == BG_GC) ? GC_CB : GC_GREEDY; + int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY; + + if (gc_th && gc_th->gc_idle) { + if (gc_th->gc_idle == 1) + gc_mode = GC_CB; + else if (gc_th->gc_idle == 2) + gc_mode = GC_GREEDY; + } + return gc_mode; } static void select_policy(struct f2fs_sb_info *sbi, int gc_type, @@ -138,12 +153,18 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, if (p->alloc_mode == SSR) { p->gc_mode = GC_GREEDY; p->dirty_segmap = dirty_i->dirty_segmap[type]; + p->max_search = dirty_i->nr_dirty[type]; p->ofs_unit = 1; } else { - p->gc_mode = select_gc_type(gc_type); + p->gc_mode = select_gc_type(sbi->gc_thread, gc_type); p->dirty_segmap = dirty_i->dirty_segmap[DIRTY]; + p->max_search = dirty_i->nr_dirty[DIRTY]; p->ofs_unit = sbi->segs_per_sec; } + + if (p->max_search > MAX_VICTIM_SEARCH) + p->max_search = MAX_VICTIM_SEARCH; + p->offset = sbi->last_victim[p->gc_mode]; } @@ -290,7 +311,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (cost == max_cost) continue; - if (nsearched++ >= MAX_VICTIM_SEARCH) { + if (nsearched++ >= p.max_search) { sbi->last_victim[p.gc_mode] = segno; break; } @@ -407,8 +428,7 @@ next_step: /* set page dirty and write it */ if (gc_type == FG_GC) { - f2fs_submit_bio(sbi, NODE, true); - wait_on_page_writeback(node_page); + f2fs_wait_on_page_writeback(node_page, NODE, true); set_page_dirty(node_page); } else { if (!PageWriteback(node_page)) @@ -447,7 +467,7 @@ next_step: * as indirect or double indirect node blocks, are given, it must be a caller's * bug. */ -block_t start_bidx_of_node(unsigned int node_ofs) +block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi) { unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4; unsigned int bidx; @@ -464,7 +484,7 @@ block_t start_bidx_of_node(unsigned int node_ofs) int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); bidx = node_ofs - 5 - dec; } - return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE; + return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi); } static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, @@ -508,10 +528,7 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type) } else { struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); - if (PageWriteback(page)) { - f2fs_submit_bio(sbi, DATA, true); - wait_on_page_writeback(page); - } + f2fs_wait_on_page_writeback(page, DATA, true); if (clear_page_dirty_for_io(page) && S_ISDIR(inode->i_mode)) { @@ -575,7 +592,6 @@ next_step: continue; } - start_bidx = start_bidx_of_node(nofs); ofs_in_node = le16_to_cpu(entry->ofs_in_node); if (phase == 2) { @@ -583,6 +599,8 @@ next_step: if (IS_ERR(inode)) continue; + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + data_page = find_data_page(inode, start_bidx + ofs_in_node, false); if (IS_ERR(data_page)) @@ -593,6 +611,8 @@ next_step: } else { inode = find_gc_inode(dni.ino, ilist); if (inode) { + start_bidx = start_bidx_of_node(nofs, + F2FS_I(inode)); data_page = get_lock_data_page(inode, start_bidx + ofs_in_node); if (IS_ERR(data_page)) diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index 2c6a6bd..507056d 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -13,18 +13,26 @@ * whether IO subsystem is idle * or not */ -#define GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */ -#define GC_THREAD_MAX_SLEEP_TIME 60000 -#define GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */ +#define DEF_GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */ +#define DEF_GC_THREAD_MAX_SLEEP_TIME 60000 +#define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */ #define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */ #define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */ /* Search max. number of dirty segments to select a victim segment */ -#define MAX_VICTIM_SEARCH 20 +#define MAX_VICTIM_SEARCH 4096 /* covers 8GB */ struct f2fs_gc_kthread { struct task_struct *f2fs_gc_task; wait_queue_head_t gc_wait_queue_head; + + /* for gc sleep time */ + unsigned int min_sleep_time; + unsigned int max_sleep_time; + unsigned int no_gc_sleep_time; + + /* for changing gc mode */ + unsigned int gc_idle; }; struct inode_entry { @@ -56,25 +64,25 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi) return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100; } -static inline long increase_sleep_time(long wait) +static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait) { - if (wait == GC_THREAD_NOGC_SLEEP_TIME) + if (wait == gc_th->no_gc_sleep_time) return wait; - wait += GC_THREAD_MIN_SLEEP_TIME; - if (wait > GC_THREAD_MAX_SLEEP_TIME) - wait = GC_THREAD_MAX_SLEEP_TIME; + wait += gc_th->min_sleep_time; + if (wait > gc_th->max_sleep_time) + wait = gc_th->max_sleep_time; return wait; } -static inline long decrease_sleep_time(long wait) +static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait) { - if (wait == GC_THREAD_NOGC_SLEEP_TIME) - wait = GC_THREAD_MAX_SLEEP_TIME; + if (wait == gc_th->no_gc_sleep_time) + wait = gc_th->max_sleep_time; - wait -= GC_THREAD_MIN_SLEEP_TIME; - if (wait <= GC_THREAD_MIN_SLEEP_TIME) - wait = GC_THREAD_MIN_SLEEP_TIME; + wait -= gc_th->min_sleep_time; + if (wait <= gc_th->min_sleep_time) + wait = gc_th->min_sleep_time; return wait; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 2b2d45d1..9339cd2 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -56,7 +56,7 @@ static int do_read_inode(struct inode *inode) if (IS_ERR(node_page)) return PTR_ERR(node_page); - rn = page_address(node_page); + rn = F2FS_NODE(node_page); ri = &(rn->i); inode->i_mode = le16_to_cpu(ri->i_mode); @@ -85,6 +85,7 @@ static int do_read_inode(struct inode *inode) fi->i_advise = ri->i_advise; fi->i_pino = le32_to_cpu(ri->i_pino); get_extent_info(&fi->ext, ri->i_ext); + get_inline_info(fi, ri); f2fs_put_page(node_page, 1); return 0; } @@ -151,9 +152,9 @@ void update_inode(struct inode *inode, struct page *node_page) struct f2fs_node *rn; struct f2fs_inode *ri; - wait_on_page_writeback(node_page); + f2fs_wait_on_page_writeback(node_page, NODE, false); - rn = page_address(node_page); + rn = F2FS_NODE(node_page); ri = &(rn->i); ri->i_mode = cpu_to_le16(inode->i_mode); @@ -164,6 +165,7 @@ void update_inode(struct inode *inode, struct page *node_page) ri->i_size = cpu_to_le64(i_size_read(inode)); ri->i_blocks = cpu_to_le64(inode->i_blocks); set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext); + set_raw_inline(F2FS_I(inode), ri); ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec); ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); @@ -221,9 +223,6 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE)) return 0; - if (wbc) - f2fs_balance_fs(sbi); - /* * We need to lock here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. @@ -231,6 +230,10 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) ilock = mutex_lock_op(sbi); ret = update_inode_page(inode); mutex_unlock_op(sbi, ilock); + + if (wbc) + f2fs_balance_fs(sbi); + return ret; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 64c0716..2a5359c 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -83,21 +83,11 @@ static int is_multimedia_file(const unsigned char *s, const char *sub) { size_t slen = strlen(s); size_t sublen = strlen(sub); - int ret; if (sublen > slen) return 0; - ret = memcmp(s + slen - sublen, sub, sublen); - if (ret) { /* compare upper case */ - int i; - char upper_sub[8]; - for (i = 0; i < sublen && i < sizeof(upper_sub); i++) - upper_sub[i] = toupper(sub[i]); - return !memcmp(s + slen - sublen, upper_sub, sublen); - } - - return !ret; + return !strncasecmp(s + slen - sublen, sub, sublen); } /* @@ -239,7 +229,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) if (!de) goto fail; - err = check_orphan_space(sbi); + err = acquire_orphan_inode(sbi); if (err) { kunmap(page); f2fs_put_page(page, 0); @@ -393,7 +383,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *old_inode = old_dentry->d_inode; struct inode *new_inode = new_dentry->d_inode; struct page *old_dir_page; - struct page *old_page; + struct page *old_page, *new_page; struct f2fs_dir_entry *old_dir_entry = NULL; struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; @@ -415,7 +405,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, ilock = mutex_lock_op(sbi); if (new_inode) { - struct page *new_page; err = -ENOTEMPTY; if (old_dir_entry && !f2fs_empty_dir(new_inode)) @@ -427,14 +416,28 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (!new_entry) goto out_dir; + err = acquire_orphan_inode(sbi); + if (err) + goto put_out_dir; + + if (update_dent_inode(old_inode, &new_dentry->d_name)) { + release_orphan_inode(sbi); + goto put_out_dir; + } + f2fs_set_link(new_dir, new_entry, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME; if (old_dir_entry) drop_nlink(new_inode); drop_nlink(new_inode); + if (!new_inode->i_nlink) add_orphan_inode(sbi, new_inode->i_ino); + else + release_orphan_inode(sbi); + + update_inode_page(old_inode); update_inode_page(new_inode); } else { err = f2fs_add_link(new_dentry, old_inode); @@ -467,6 +470,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, mutex_unlock_op(sbi, ilock); return 0; +put_out_dir: + f2fs_put_page(new_page, 1); out_dir: if (old_dir_entry) { kunmap(old_dir_page); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b418aee..51ef278 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -315,9 +315,10 @@ cache: * The maximum depth is four. * Offset[0] will have raw inode offset. */ -static int get_node_path(long block, int offset[4], unsigned int noffset[4]) +static int get_node_path(struct f2fs_inode_info *fi, long block, + int offset[4], unsigned int noffset[4]) { - const long direct_index = ADDRS_PER_INODE; + const long direct_index = ADDRS_PER_INODE(fi); const long direct_blks = ADDRS_PER_BLOCK; const long dptrs_per_blk = NIDS_PER_BLOCK; const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; @@ -405,7 +406,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) int level, i; int err = 0; - level = get_node_path(index, offset, noffset); + level = get_node_path(F2FS_I(dn->inode), index, offset, noffset); nids[0] = dn->inode->i_ino; npage[0] = dn->inode_page; @@ -565,7 +566,7 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, return PTR_ERR(page); } - rn = (struct f2fs_node *)page_address(page); + rn = F2FS_NODE(page); if (depth < 3) { for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) { child_nid = le32_to_cpu(rn->in.nid[i]); @@ -687,7 +688,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) trace_f2fs_truncate_inode_blocks_enter(inode, from); - level = get_node_path(from, offset, noffset); + level = get_node_path(F2FS_I(inode), from, offset, noffset); restart: page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { @@ -698,7 +699,7 @@ restart: set_new_dnode(&dn, inode, page, NULL, 0); unlock_page(page); - rn = page_address(page); + rn = F2FS_NODE(page); switch (level) { case 0: case 1: @@ -771,6 +772,33 @@ fail: return err > 0 ? 0 : err; } +int truncate_xattr_node(struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + nid_t nid = F2FS_I(inode)->i_xattr_nid; + struct dnode_of_data dn; + struct page *npage; + + if (!nid) + return 0; + + npage = get_node_page(sbi, nid); + if (IS_ERR(npage)) + return PTR_ERR(npage); + + F2FS_I(inode)->i_xattr_nid = 0; + + /* need to do checkpoint during fsync */ + F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); + + set_new_dnode(&dn, inode, page, npage, nid); + + if (page) + dn.inode_page_locked = 1; + truncate_node(&dn); + return 0; +} + /* * Caller should grab and release a mutex by calling mutex_lock_op() and * mutex_unlock_op(). @@ -781,22 +809,16 @@ int remove_inode_page(struct inode *inode) struct page *page; nid_t ino = inode->i_ino; struct dnode_of_data dn; + int err; page = get_node_page(sbi, ino); if (IS_ERR(page)) return PTR_ERR(page); - if (F2FS_I(inode)->i_xattr_nid) { - nid_t nid = F2FS_I(inode)->i_xattr_nid; - struct page *npage = get_node_page(sbi, nid); - - if (IS_ERR(npage)) - return PTR_ERR(npage); - - F2FS_I(inode)->i_xattr_nid = 0; - set_new_dnode(&dn, inode, page, npage, nid); - dn.inode_page_locked = 1; - truncate_node(&dn); + err = truncate_xattr_node(inode, page); + if (err) { + f2fs_put_page(page, 1); + return err; } /* 0 is possible, after f2fs_new_inode() is failed */ @@ -833,29 +855,32 @@ struct page *new_node_page(struct dnode_of_data *dn, if (!page) return ERR_PTR(-ENOMEM); - get_node_info(sbi, dn->nid, &old_ni); + if (!inc_valid_node_count(sbi, dn->inode, 1)) { + err = -ENOSPC; + goto fail; + } - SetPageUptodate(page); - fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); + get_node_info(sbi, dn->nid, &old_ni); /* Reinitialize old_ni with new node page */ BUG_ON(old_ni.blk_addr != NULL_ADDR); new_ni = old_ni; new_ni.ino = dn->inode->i_ino; - - if (!inc_valid_node_count(sbi, dn->inode, 1)) { - err = -ENOSPC; - goto fail; - } set_node_addr(sbi, &new_ni, NEW_ADDR); + + fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); set_cold_node(dn->inode, page); + SetPageUptodate(page); + set_page_dirty(page); + + if (ofs == XATTR_NODE_OFFSET) + F2FS_I(dn->inode)->i_xattr_nid = dn->nid; dn->node_page = page; if (ipage) update_inode(dn->inode, ipage); else sync_inode_page(dn); - set_page_dirty(page); if (ofs == 0) inc_valid_inode_count(sbi); @@ -916,7 +941,6 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) f2fs_put_page(apage, 0); else if (err == LOCKED_PAGE) f2fs_put_page(apage, 1); - return; } struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) @@ -1167,9 +1191,9 @@ static int f2fs_write_node_page(struct page *page, /* * It is very important to gather dirty pages and write at once, so that we can * submit a big bio without interfering other data writes. - * Be default, 512 pages (2MB), a segment size, is quite reasonable. + * Be default, 512 pages (2MB) * 3 node types, is more reasonable. */ -#define COLLECT_DIRTY_NODES 512 +#define COLLECT_DIRTY_NODES 1536 static int f2fs_write_node_pages(struct address_space *mapping, struct writeback_control *wbc) { @@ -1187,9 +1211,10 @@ static int f2fs_write_node_pages(struct address_space *mapping, return 0; /* if mounting is failed, skip writing node pages */ - wbc->nr_to_write = max_hw_blocks(sbi); + wbc->nr_to_write = 3 * max_hw_blocks(sbi); sync_node_pages(sbi, 0, wbc); - wbc->nr_to_write = nr_to_write - (max_hw_blocks(sbi) - wbc->nr_to_write); + wbc->nr_to_write = nr_to_write - (3 * max_hw_blocks(sbi) - + wbc->nr_to_write); return 0; } @@ -1444,6 +1469,9 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; + if (!nid) + return; + spin_lock(&nm_i->free_nid_list_lock); i = __lookup_free_nid_list(nid, &nm_i->free_nid_list); BUG_ON(!i || i->state != NID_ALLOC); @@ -1484,8 +1512,8 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); - src = (struct f2fs_node *)page_address(page); - dst = (struct f2fs_node *)page_address(ipage); + src = F2FS_NODE(page); + dst = F2FS_NODE(ipage); memcpy(dst, src, (unsigned long)&src->i.i_ext - (unsigned long)&src->i); dst->i.i_size = 0; @@ -1515,8 +1543,8 @@ int restore_node_summary(struct f2fs_sb_info *sbi, /* alloc temporal page for read node */ page = alloc_page(GFP_NOFS | __GFP_ZERO); - if (IS_ERR(page)) - return PTR_ERR(page); + if (!page) + return -ENOMEM; lock_page(page); /* scan the node segment */ @@ -1535,7 +1563,7 @@ int restore_node_summary(struct f2fs_sb_info *sbi, goto out; lock_page(page); - rn = (struct f2fs_node *)page_address(page); + rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; sum_entry->version = 0; sum_entry->ofs_in_node = 0; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index c65fb4f..3496bb3 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -155,8 +155,7 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid) static inline void fill_node_footer(struct page *page, nid_t nid, nid_t ino, unsigned int ofs, bool reset) { - void *kaddr = page_address(page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(page); if (reset) memset(rn, 0, sizeof(*rn)); rn->footer.nid = cpu_to_le32(nid); @@ -166,10 +165,8 @@ static inline void fill_node_footer(struct page *page, nid_t nid, static inline void copy_node_footer(struct page *dst, struct page *src) { - void *src_addr = page_address(src); - void *dst_addr = page_address(dst); - struct f2fs_node *src_rn = (struct f2fs_node *)src_addr; - struct f2fs_node *dst_rn = (struct f2fs_node *)dst_addr; + struct f2fs_node *src_rn = F2FS_NODE(src); + struct f2fs_node *dst_rn = F2FS_NODE(dst); memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer)); } @@ -177,45 +174,40 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr) { struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); - void *kaddr = page_address(page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(page); + rn->footer.cp_ver = ckpt->checkpoint_ver; rn->footer.next_blkaddr = cpu_to_le32(blkaddr); } static inline nid_t ino_of_node(struct page *node_page) { - void *kaddr = page_address(node_page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(node_page); return le32_to_cpu(rn->footer.ino); } static inline nid_t nid_of_node(struct page *node_page) { - void *kaddr = page_address(node_page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(node_page); return le32_to_cpu(rn->footer.nid); } static inline unsigned int ofs_of_node(struct page *node_page) { - void *kaddr = page_address(node_page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(node_page); unsigned flag = le32_to_cpu(rn->footer.flag); return flag >> OFFSET_BIT_SHIFT; } static inline unsigned long long cpver_of_node(struct page *node_page) { - void *kaddr = page_address(node_page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(node_page); return le64_to_cpu(rn->footer.cp_ver); } static inline block_t next_blkaddr_of_node(struct page *node_page) { - void *kaddr = page_address(node_page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(node_page); return le32_to_cpu(rn->footer.next_blkaddr); } @@ -237,6 +229,10 @@ static inline block_t next_blkaddr_of_node(struct page *node_page) static inline bool IS_DNODE(struct page *node_page) { unsigned int ofs = ofs_of_node(node_page); + + if (ofs == XATTR_NODE_OFFSET) + return false; + if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK || ofs == 5 + 2 * NIDS_PER_BLOCK) return false; @@ -250,7 +246,7 @@ static inline bool IS_DNODE(struct page *node_page) static inline void set_nid(struct page *p, int off, nid_t nid, bool i) { - struct f2fs_node *rn = (struct f2fs_node *)page_address(p); + struct f2fs_node *rn = F2FS_NODE(p); wait_on_page_writeback(p); @@ -263,7 +259,8 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i) static inline nid_t get_nid(struct page *p, int off, bool i) { - struct f2fs_node *rn = (struct f2fs_node *)page_address(p); + struct f2fs_node *rn = F2FS_NODE(p); + if (i) return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]); return le32_to_cpu(rn->in.nid[off]); @@ -314,8 +311,7 @@ static inline void clear_cold_data(struct page *page) static inline int is_node(struct page *page, int type) { - void *kaddr = page_address(page); - struct f2fs_node *rn = (struct f2fs_node *)kaddr; + struct f2fs_node *rn = F2FS_NODE(page); return le32_to_cpu(rn->footer.flag) & (1 << type); } @@ -325,7 +321,7 @@ static inline int is_node(struct page *page, int type) static inline void set_cold_node(struct inode *inode, struct page *page) { - struct f2fs_node *rn = (struct f2fs_node *)page_address(page); + struct f2fs_node *rn = F2FS_NODE(page); unsigned int flag = le32_to_cpu(rn->footer.flag); if (S_ISDIR(inode->i_mode)) @@ -337,7 +333,7 @@ static inline void set_cold_node(struct inode *inode, struct page *page) static inline void set_mark(struct page *page, int mark, int type) { - struct f2fs_node *rn = (struct f2fs_node *)page_address(page); + struct f2fs_node *rn = F2FS_NODE(page); unsigned int flag = le32_to_cpu(rn->footer.flag); if (mark) flag |= (0x1 << type); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index d56d951..51ef5ee 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -40,8 +40,7 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head, static int recover_dentry(struct page *ipage, struct inode *inode) { - void *kaddr = page_address(ipage); - struct f2fs_node *raw_node = (struct f2fs_node *)kaddr; + struct f2fs_node *raw_node = F2FS_NODE(ipage); struct f2fs_inode *raw_inode = &(raw_node->i); nid_t pino = le32_to_cpu(raw_inode->i_pino); struct f2fs_dir_entry *de; @@ -93,8 +92,7 @@ out: static int recover_inode(struct inode *inode, struct page *node_page) { - void *kaddr = page_address(node_page); - struct f2fs_node *raw_node = (struct f2fs_node *)kaddr; + struct f2fs_node *raw_node = F2FS_NODE(node_page); struct f2fs_inode *raw_inode = &(raw_node->i); if (!IS_INODE(node_page)) @@ -119,7 +117,7 @@ static int recover_inode(struct inode *inode, struct page *node_page) static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) { - unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver); + unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); struct curseg_info *curseg; struct page *page; block_t blkaddr; @@ -131,8 +129,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) /* read node page */ page = alloc_page(GFP_F2FS_ZERO); - if (IS_ERR(page)) - return PTR_ERR(page); + if (!page) + return -ENOMEM; lock_page(page); while (1) { @@ -215,6 +213,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, void *kaddr; struct inode *inode; struct page *node_page; + unsigned int offset; block_t bidx; int i; @@ -259,8 +258,8 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, node_page = get_node_page(sbi, nid); if (IS_ERR(node_page)) return PTR_ERR(node_page); - bidx = start_bidx_of_node(ofs_of_node(node_page)) + - le16_to_cpu(sum.ofs_in_node); + + offset = ofs_of_node(node_page); ino = ino_of_node(node_page); f2fs_put_page(node_page, 1); @@ -269,6 +268,9 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, if (IS_ERR(inode)) return PTR_ERR(inode); + bidx = start_bidx_of_node(offset, F2FS_I(inode)) + + le16_to_cpu(sum.ofs_in_node); + truncate_hole(inode, bidx, bidx + 1); iput(inode); return 0; @@ -277,6 +279,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page, block_t blkaddr) { + struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int start, end; struct dnode_of_data dn; struct f2fs_summary sum; @@ -284,9 +287,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, int err = 0, recovered = 0; int ilock; - start = start_bidx_of_node(ofs_of_node(page)); + start = start_bidx_of_node(ofs_of_node(page), fi); if (IS_INODE(page)) - end = start + ADDRS_PER_INODE; + end = start + ADDRS_PER_INODE(fi); else end = start + ADDRS_PER_BLOCK; @@ -357,7 +360,7 @@ err: static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head, int type) { - unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver); + unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); struct curseg_info *curseg; struct page *page; int err = 0; @@ -369,7 +372,7 @@ static int recover_data(struct f2fs_sb_info *sbi, /* read node page */ page = alloc_page(GFP_NOFS | __GFP_ZERO); - if (IS_ERR(page)) + if (!page) return -ENOMEM; lock_page(page); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a86d125..09af9c7 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -117,7 +117,6 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) } mutex_unlock(&dirty_i->seglist_lock); - return; } /* @@ -261,7 +260,6 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type, void *addr = curseg->sum_blk; addr += curseg->next_blkoff * sizeof(struct f2fs_summary); memcpy(addr, sum, sizeof(struct f2fs_summary)); - return; } /* @@ -542,12 +540,9 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, { struct curseg_info *curseg = CURSEG_I(sbi, type); - if (force) { + if (force) new_curseg(sbi, type, true); - goto out; - } - - if (type == CURSEG_WARM_NODE) + else if (type == CURSEG_WARM_NODE) new_curseg(sbi, type, false); else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) new_curseg(sbi, type, false); @@ -555,11 +550,9 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, change_curseg(sbi, type, true); else new_curseg(sbi, type, false); -out: #ifdef CONFIG_F2FS_STAT_FS sbi->segment_count[curseg->alloc_type]++; #endif - return; } void allocate_new_segments(struct f2fs_sb_info *sbi) @@ -611,18 +604,12 @@ static void f2fs_end_io_write(struct bio *bio, int err) struct bio *f2fs_bio_alloc(struct block_device *bdev, int npages) { struct bio *bio; - struct bio_private *priv; -retry: - priv = kmalloc(sizeof(struct bio_private), GFP_NOFS); - if (!priv) { - cond_resched(); - goto retry; - } /* No failure on bio allocation */ bio = bio_alloc(GFP_NOIO, npages); bio->bi_bdev = bdev; - bio->bi_private = priv; + bio->bi_private = NULL; + return bio; } @@ -681,8 +668,17 @@ static void submit_write_page(struct f2fs_sb_info *sbi, struct page *page, do_submit_bio(sbi, type, false); alloc_new: if (sbi->bio[type] == NULL) { + struct bio_private *priv; +retry: + priv = kmalloc(sizeof(struct bio_private), GFP_NOFS); + if (!priv) { + cond_resched(); + goto retry; + } + sbi->bio[type] = f2fs_bio_alloc(bdev, max_hw_blocks(sbi)); sbi->bio[type]->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); + sbi->bio[type]->bi_private = priv; /* * The end_io will be assigned at the sumbission phase. * Until then, let bio_add_page() merge consecutive IOs as much @@ -702,6 +698,16 @@ alloc_new: trace_f2fs_submit_write_page(page, blk_addr, type); } +void f2fs_wait_on_page_writeback(struct page *page, + enum page_type type, bool sync) +{ + struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + if (PageWriteback(page)) { + f2fs_submit_bio(sbi, type, sync); + wait_on_page_writeback(page); + } +} + static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -1179,7 +1185,6 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); - return; } int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type, diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 062424a..bdd10ea 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -142,6 +142,7 @@ struct victim_sel_policy { int alloc_mode; /* LFS or SSR */ int gc_mode; /* GC_CB or GC_GREEDY */ unsigned long *dirty_segmap; /* dirty segment bitmap */ + unsigned int max_search; /* maximum # of segments to search */ unsigned int offset; /* last scanned bitmap offset */ unsigned int ofs_unit; /* bitmap search unit */ unsigned int min_cost; /* minimum cost */ @@ -453,7 +454,8 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi) static inline bool need_SSR(struct f2fs_sb_info *sbi) { - return (free_sections(sbi) < overprovision_sections(sbi)); + return ((prefree_segments(sbi) / sbi->segs_per_sec) + + free_sections(sbi) < overprovision_sections(sbi)); } static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed) @@ -470,7 +472,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed) static inline int utilization(struct f2fs_sb_info *sbi) { - return div_u64(valid_user_blocks(sbi) * 100, sbi->user_block_count); + return div_u64((u64)valid_user_blocks(sbi) * 100, sbi->user_block_count); } /* diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 75c7dc3..13d0a0f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -18,20 +18,25 @@ #include <linux/parser.h> #include <linux/mount.h> #include <linux/seq_file.h> +#include <linux/proc_fs.h> #include <linux/random.h> #include <linux/exportfs.h> #include <linux/blkdev.h> #include <linux/f2fs_fs.h> +#include <linux/sysfs.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" +#include "gc.h" #define CREATE_TRACE_POINTS #include <trace/events/f2fs.h> +static struct proc_dir_entry *f2fs_proc_root; static struct kmem_cache *f2fs_inode_cachep; +static struct kset *f2fs_kset; enum { Opt_gc_background, @@ -42,6 +47,7 @@ enum { Opt_noacl, Opt_active_logs, Opt_disable_ext_identify, + Opt_inline_xattr, Opt_err, }; @@ -54,9 +60,117 @@ static match_table_t f2fs_tokens = { {Opt_noacl, "noacl"}, {Opt_active_logs, "active_logs=%u"}, {Opt_disable_ext_identify, "disable_ext_identify"}, + {Opt_inline_xattr, "inline_xattr"}, {Opt_err, NULL}, }; +/* Sysfs support for f2fs */ +struct f2fs_attr { + struct attribute attr; + ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *); + ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *, + const char *, size_t); + int offset; +}; + +static ssize_t f2fs_sbi_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + struct f2fs_gc_kthread *gc_kth = sbi->gc_thread; + unsigned int *ui; + + if (!gc_kth) + return -EINVAL; + + ui = (unsigned int *)(((char *)gc_kth) + a->offset); + + return snprintf(buf, PAGE_SIZE, "%u\n", *ui); +} + +static ssize_t f2fs_sbi_store(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, + const char *buf, size_t count) +{ + struct f2fs_gc_kthread *gc_kth = sbi->gc_thread; + unsigned long t; + unsigned int *ui; + ssize_t ret; + + if (!gc_kth) + return -EINVAL; + + ui = (unsigned int *)(((char *)gc_kth) + a->offset); + + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret < 0) + return ret; + *ui = t; + return count; +} + +static ssize_t f2fs_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->show ? a->show(a, sbi, buf) : 0; +} + +static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->store ? a->store(a, sbi, buf, len) : 0; +} + +static void f2fs_sb_release(struct kobject *kobj) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + complete(&sbi->s_kobj_unregister); +} + +#define F2FS_ATTR_OFFSET(_name, _mode, _show, _store, _elname) \ +static struct f2fs_attr f2fs_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .show = _show, \ + .store = _store, \ + .offset = offsetof(struct f2fs_gc_kthread, _elname), \ +} + +#define F2FS_RW_ATTR(name, elname) \ + F2FS_ATTR_OFFSET(name, 0644, f2fs_sbi_show, f2fs_sbi_store, elname) + +F2FS_RW_ATTR(gc_min_sleep_time, min_sleep_time); +F2FS_RW_ATTR(gc_max_sleep_time, max_sleep_time); +F2FS_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time); +F2FS_RW_ATTR(gc_idle, gc_idle); + +#define ATTR_LIST(name) (&f2fs_attr_##name.attr) +static struct attribute *f2fs_attrs[] = { + ATTR_LIST(gc_min_sleep_time), + ATTR_LIST(gc_max_sleep_time), + ATTR_LIST(gc_no_gc_sleep_time), + ATTR_LIST(gc_idle), + NULL, +}; + +static const struct sysfs_ops f2fs_attr_ops = { + .show = f2fs_attr_show, + .store = f2fs_attr_store, +}; + +static struct kobj_type f2fs_ktype = { + .default_attrs = f2fs_attrs, + .sysfs_ops = &f2fs_attr_ops, + .release = f2fs_sb_release, +}; + void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) { struct va_format vaf; @@ -126,11 +240,18 @@ static int parse_options(struct super_block *sb, char *options) case Opt_nouser_xattr: clear_opt(sbi, XATTR_USER); break; + case Opt_inline_xattr: + set_opt(sbi, INLINE_XATTR); + break; #else case Opt_nouser_xattr: f2fs_msg(sb, KERN_INFO, "nouser_xattr options not supported"); break; + case Opt_inline_xattr: + f2fs_msg(sb, KERN_INFO, + "inline_xattr options not supported"); + break; #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL case Opt_noacl: @@ -180,6 +301,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) set_inode_flag(fi, FI_NEW_INODE); + if (test_opt(F2FS_SB(sb), INLINE_XATTR)) + set_inode_flag(fi, FI_INLINE_XATTR); + return &fi->vfs_inode; } @@ -205,7 +329,6 @@ static int f2fs_drop_inode(struct inode *inode) static void f2fs_dirty_inode(struct inode *inode, int flags) { set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE); - return; } static void f2fs_i_callback(struct rcu_head *head) @@ -223,6 +346,12 @@ static void f2fs_put_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); + if (sbi->s_proc) { + remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry(sb->s_id, f2fs_proc_root); + } + kobject_del(&sbi->s_kobj); + f2fs_destroy_stats(sbi); stop_gc_thread(sbi); @@ -236,6 +365,8 @@ static void f2fs_put_super(struct super_block *sb) destroy_segment_manager(sbi); kfree(sbi->ckpt); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); sb->s_fs_info = NULL; brelse(sbi->raw_super_buf); @@ -325,6 +456,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",user_xattr"); else seq_puts(seq, ",nouser_xattr"); + if (test_opt(sbi, INLINE_XATTR)) + seq_puts(seq, ",inline_xattr"); #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL if (test_opt(sbi, POSIX_ACL)) @@ -340,6 +473,36 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) return 0; } +static int segment_info_seq_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + unsigned int total_segs = le32_to_cpu(sbi->raw_super->segment_count_main); + int i; + + for (i = 0; i < total_segs; i++) { + seq_printf(seq, "%u", get_valid_blocks(sbi, i, 1)); + if (i != 0 && (i % 10) == 0) + seq_puts(seq, "\n"); + else + seq_puts(seq, " "); + } + return 0; +} + +static int segment_info_open_fs(struct inode *inode, struct file *file) +{ + return single_open(file, segment_info_seq_show, PDE_DATA(inode)); +} + +static const struct file_operations f2fs_seq_segment_info_fops = { + .owner = THIS_MODULE, + .open = segment_info_open_fs, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -455,7 +618,7 @@ static const struct export_operations f2fs_export_ops = { static loff_t max_file_size(unsigned bits) { - loff_t result = ADDRS_PER_INODE; + loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS); loff_t leaf_count = ADDRS_PER_BLOCK; /* two direct node blocks */ @@ -766,6 +929,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) if (err) goto fail; + if (f2fs_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); + + if (sbi->s_proc) + proc_create_data("segment_info", S_IRUGO, sbi->s_proc, + &f2fs_seq_segment_info_fops, sb); + if (test_opt(sbi, DISCARD)) { struct request_queue *q = bdev_get_queue(sb->s_bdev); if (!blk_queue_discard(q)) @@ -774,6 +944,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) "the device does not support discard"); } + sbi->s_kobj.kset = f2fs_kset; + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL, + "%s", sb->s_id); + if (err) + goto fail; + return 0; fail: stop_gc_thread(sbi); @@ -841,29 +1018,49 @@ static int __init init_f2fs_fs(void) goto fail; err = create_node_manager_caches(); if (err) - goto fail; + goto free_inodecache; err = create_gc_caches(); if (err) - goto fail; + goto free_node_manager_caches; err = create_checkpoint_caches(); if (err) - goto fail; + goto free_gc_caches; + f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj); + if (!f2fs_kset) { + err = -ENOMEM; + goto free_checkpoint_caches; + } err = register_filesystem(&f2fs_fs_type); if (err) - goto fail; + goto free_kset; f2fs_create_root_stats(); + f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); + return 0; + +free_kset: + kset_unregister(f2fs_kset); +free_checkpoint_caches: + destroy_checkpoint_caches(); +free_gc_caches: + destroy_gc_caches(); +free_node_manager_caches: + destroy_node_manager_caches(); +free_inodecache: + destroy_inodecache(); fail: return err; } static void __exit exit_f2fs_fs(void) { + remove_proc_entry("fs/f2fs", NULL); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); destroy_checkpoint_caches(); destroy_gc_caches(); destroy_node_manager_caches(); destroy_inodecache(); + kset_unregister(f2fs_kset); } module_init(init_f2fs_fs) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 3ab07ec..1ac8a5f 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -246,40 +246,170 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int name_index) return handler; } +static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index, + size_t name_len, const char *name) +{ + struct f2fs_xattr_entry *entry; + + list_for_each_xattr(entry, base_addr) { + if (entry->e_name_index != name_index) + continue; + if (entry->e_name_len != name_len) + continue; + if (!memcmp(entry->e_name, name, name_len)) + break; + } + return entry; +} + +static void *read_all_xattrs(struct inode *inode, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_xattr_header *header; + size_t size = PAGE_SIZE, inline_size = 0; + void *txattr_addr; + + inline_size = inline_xattr_size(inode); + + txattr_addr = kzalloc(inline_size + size, GFP_KERNEL); + if (!txattr_addr) + return NULL; + + /* read from inline xattr */ + if (inline_size) { + struct page *page = NULL; + void *inline_addr; + + if (ipage) { + inline_addr = inline_xattr_addr(ipage); + } else { + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) + goto fail; + inline_addr = inline_xattr_addr(page); + } + memcpy(txattr_addr, inline_addr, inline_size); + f2fs_put_page(page, 1); + } + + /* read from xattr node block */ + if (F2FS_I(inode)->i_xattr_nid) { + struct page *xpage; + void *xattr_addr; + + /* The inode already has an extended attribute block. */ + xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); + if (IS_ERR(xpage)) + goto fail; + + xattr_addr = page_address(xpage); + memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE); + f2fs_put_page(xpage, 1); + } + + header = XATTR_HDR(txattr_addr); + + /* never been allocated xattrs */ + if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) { + header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC); + header->h_refcount = cpu_to_le32(1); + } + return txattr_addr; +fail: + kzfree(txattr_addr); + return NULL; +} + +static inline int write_all_xattrs(struct inode *inode, __u32 hsize, + void *txattr_addr, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + size_t inline_size = 0; + void *xattr_addr; + struct page *xpage; + nid_t new_nid = 0; + int err; + + inline_size = inline_xattr_size(inode); + + if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid) + if (!alloc_nid(sbi, &new_nid)) + return -ENOSPC; + + /* write to inline xattr */ + if (inline_size) { + struct page *page = NULL; + void *inline_addr; + + if (ipage) { + inline_addr = inline_xattr_addr(ipage); + } else { + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) { + alloc_nid_failed(sbi, new_nid); + return PTR_ERR(page); + } + inline_addr = inline_xattr_addr(page); + } + memcpy(inline_addr, txattr_addr, inline_size); + f2fs_put_page(page, 1); + + /* no need to use xattr node block */ + if (hsize <= inline_size) { + err = truncate_xattr_node(inode, ipage); + alloc_nid_failed(sbi, new_nid); + return err; + } + } + + /* write to xattr node block */ + if (F2FS_I(inode)->i_xattr_nid) { + xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); + if (IS_ERR(xpage)) { + alloc_nid_failed(sbi, new_nid); + return PTR_ERR(xpage); + } + BUG_ON(new_nid); + } else { + struct dnode_of_data dn; + set_new_dnode(&dn, inode, NULL, NULL, new_nid); + xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage); + if (IS_ERR(xpage)) { + alloc_nid_failed(sbi, new_nid); + return PTR_ERR(xpage); + } + alloc_nid_done(sbi, new_nid); + } + + xattr_addr = page_address(xpage); + memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE - + sizeof(struct node_footer)); + set_page_dirty(xpage); + f2fs_put_page(xpage, 1); + + /* need to checkpoint during fsync */ + F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); + return 0; +} + int f2fs_getxattr(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { - struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); - struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_xattr_entry *entry; - struct page *page; void *base_addr; - int error = 0, found = 0; + int error = 0; size_t value_len, name_len; if (name == NULL) return -EINVAL; name_len = strlen(name); - if (!fi->i_xattr_nid) - return -ENODATA; + base_addr = read_all_xattrs(inode, NULL); + if (!base_addr) + return -ENOMEM; - page = get_node_page(sbi, fi->i_xattr_nid); - if (IS_ERR(page)) - return PTR_ERR(page); - base_addr = page_address(page); - - list_for_each_xattr(entry, base_addr) { - if (entry->e_name_index != name_index) - continue; - if (entry->e_name_len != name_len) - continue; - if (!memcmp(entry->e_name, name, name_len)) { - found = 1; - break; - } - } - if (!found) { + entry = __find_xattr(base_addr, name_index, name_len, name); + if (IS_XATTR_LAST_ENTRY(entry)) { error = -ENODATA; goto cleanup; } @@ -298,28 +428,21 @@ int f2fs_getxattr(struct inode *inode, int name_index, const char *name, error = value_len; cleanup: - f2fs_put_page(page, 1); + kzfree(base_addr); return error; } ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = dentry->d_inode; - struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); - struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_xattr_entry *entry; - struct page *page; void *base_addr; int error = 0; size_t rest = buffer_size; - if (!fi->i_xattr_nid) - return 0; - - page = get_node_page(sbi, fi->i_xattr_nid); - if (IS_ERR(page)) - return PTR_ERR(page); - base_addr = page_address(page); + base_addr = read_all_xattrs(inode, NULL); + if (!base_addr) + return -ENOMEM; list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = @@ -342,7 +465,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) } error = buffer_size - rest; cleanup: - f2fs_put_page(page, 1); + kzfree(base_addr); return error; } @@ -351,14 +474,13 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name, { struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); struct f2fs_inode_info *fi = F2FS_I(inode); - struct f2fs_xattr_header *header = NULL; struct f2fs_xattr_entry *here, *last; - struct page *page; void *base_addr; - int error, found, free, newsize; + int found, newsize; size_t name_len; - char *pval; int ilock; + __u32 new_hsize; + int error = -ENOMEM; if (name == NULL) return -EINVAL; @@ -368,67 +490,21 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name, name_len = strlen(name); - if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN) + if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode)) return -ERANGE; f2fs_balance_fs(sbi); ilock = mutex_lock_op(sbi); - if (!fi->i_xattr_nid) { - /* Allocate new attribute block */ - struct dnode_of_data dn; - - if (!alloc_nid(sbi, &fi->i_xattr_nid)) { - error = -ENOSPC; - goto exit; - } - set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid); - mark_inode_dirty(inode); - - page = new_node_page(&dn, XATTR_NODE_OFFSET, ipage); - if (IS_ERR(page)) { - alloc_nid_failed(sbi, fi->i_xattr_nid); - fi->i_xattr_nid = 0; - error = PTR_ERR(page); - goto exit; - } - - alloc_nid_done(sbi, fi->i_xattr_nid); - base_addr = page_address(page); - header = XATTR_HDR(base_addr); - header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC); - header->h_refcount = cpu_to_le32(1); - } else { - /* The inode already has an extended attribute block. */ - page = get_node_page(sbi, fi->i_xattr_nid); - if (IS_ERR(page)) { - error = PTR_ERR(page); - goto exit; - } - - base_addr = page_address(page); - header = XATTR_HDR(base_addr); - } - - if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) { - error = -EIO; - goto cleanup; - } + base_addr = read_all_xattrs(inode, ipage); + if (!base_addr) + goto exit; /* find entry with wanted name. */ - found = 0; - list_for_each_xattr(here, base_addr) { - if (here->e_name_index != name_index) - continue; - if (here->e_name_len != name_len) - continue; - if (!memcmp(here->e_name, name, name_len)) { - found = 1; - break; - } - } + here = __find_xattr(base_addr, name_index, name_len, name); + found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1; last = here; while (!IS_XATTR_LAST_ENTRY(last)) @@ -439,22 +515,25 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name, /* 1. Check space */ if (value) { - /* If value is NULL, it is remove operation. + int free; + /* + * If value is NULL, it is remove operation. * In case of update operation, we caculate free. */ - free = MIN_OFFSET - ((char *)last - (char *)header); + free = MIN_OFFSET(inode) - ((char *)last - (char *)base_addr); if (found) free = free - ENTRY_SIZE(here); if (free < newsize) { error = -ENOSPC; - goto cleanup; + goto exit; } } /* 2. Remove old entry */ if (found) { - /* If entry is found, remove old entry. + /* + * If entry is found, remove old entry. * If not found, remove operation is not needed. */ struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here); @@ -465,10 +544,15 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name, memset(last, 0, oldsize); } + new_hsize = (char *)last - (char *)base_addr; + /* 3. Write new entry */ if (value) { - /* Before we come here, old entry is removed. - * We just write new entry. */ + char *pval; + /* + * Before we come here, old entry is removed. + * We just write new entry. + */ memset(last, 0, newsize); last->e_name_index = name_index; last->e_name_len = name_len; @@ -476,26 +560,25 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name, pval = last->e_name + name_len; memcpy(pval, value, value_len); last->e_value_size = cpu_to_le16(value_len); + new_hsize += newsize; } - set_page_dirty(page); - f2fs_put_page(page, 1); + error = write_all_xattrs(inode, new_hsize, base_addr, ipage); + if (error) + goto exit; if (is_inode_flag_set(fi, FI_ACL_MODE)) { inode->i_mode = fi->i_acl_mode; inode->i_ctime = CURRENT_TIME; clear_inode_flag(fi, FI_ACL_MODE); } + if (ipage) update_inode(inode, ipage); else update_inode_page(inode); - mutex_unlock_op(sbi, ilock); - - return 0; -cleanup: - f2fs_put_page(page, 1); exit: mutex_unlock_op(sbi, ilock); + kzfree(base_addr); return error; } diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 3c0817b..02a08fb 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -51,7 +51,7 @@ struct f2fs_xattr_entry { #define XATTR_HDR(ptr) ((struct f2fs_xattr_header *)(ptr)) #define XATTR_ENTRY(ptr) ((struct f2fs_xattr_entry *)(ptr)) -#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr)+1)) +#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr) + 1)) #define XATTR_ROUND (3) #define XATTR_ALIGN(size) ((size + XATTR_ROUND) & ~XATTR_ROUND) @@ -69,17 +69,16 @@ struct f2fs_xattr_entry { !IS_XATTR_LAST_ENTRY(entry);\ entry = XATTR_NEXT_ENTRY(entry)) +#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE - \ + sizeof(struct node_footer) - sizeof(__u32)) -#define MIN_OFFSET XATTR_ALIGN(PAGE_SIZE - \ - sizeof(struct node_footer) - \ - sizeof(__u32)) - -#define MAX_VALUE_LEN (MIN_OFFSET - sizeof(struct f2fs_xattr_header) - \ - sizeof(struct f2fs_xattr_entry)) +#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \ + sizeof(struct f2fs_xattr_header) - \ + sizeof(struct f2fs_xattr_entry)) /* * On-disk structure of f2fs_xattr - * We use only 1 block for xattr. + * We use inline xattrs space + 1 block for xattr. * * +--------------------+ * | f2fs_xattr_header | diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 11b51bb..0062da2 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -147,7 +147,7 @@ static void fat_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); fat_truncate_blocks(inode, inode->i_size); } } @@ -730,14 +730,14 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( + BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | O_APPEND | /* O_NONBLOCK | */ __O_SYNC | O_DSYNC | FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - __FMODE_EXEC | O_PATH + __FMODE_EXEC | O_PATH | __O_TMPFILE )); fasync_cache = kmem_cache_create("fasync_cache", diff --git a/fs/file_table.c b/fs/file_table.c index b44e4c5..abdd15a 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -311,8 +311,7 @@ void fput(struct file *file) return; /* * After this task has run exit_task_work(), - * task_work_add() will fail. free_ipc_ns()-> - * shm_destroy() can do this. Fall through to delayed + * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } @@ -385,6 +384,10 @@ static inline void __file_sb_list_add(struct file *file, struct super_block *sb) */ void file_sb_list_add(struct file *file, struct super_block *sb) { + if (likely(!(file->f_mode & FMODE_WRITE))) + return; + if (!S_ISREG(file_inode(file)->i_mode)) + return; lg_local_lock(&files_lglock); __file_sb_list_add(file, sb); lg_local_unlock(&files_lglock); @@ -450,8 +453,6 @@ void mark_files_ro(struct super_block *sb) lg_global_lock(&files_lglock); do_file_list_for_each_entry(sb, f) { - if (!S_ISREG(file_inode(f)->i_mode)) - continue; if (!file_count(f)) continue; if (!(f->f_mode & FMODE_WRITE)) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 68851ff..30f6f27 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -723,7 +723,7 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, return wrote; } -long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, +static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { @@ -1049,10 +1049,8 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) { struct backing_dev_info *bdi; - if (!nr_pages) { - nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); - } + if (!nr_pages) + nr_pages = get_nr_dirty_pages(); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { @@ -1173,6 +1171,8 @@ void __mark_inode_dirty(struct inode *inode, int flags) bool wakeup_bdi = false; bdi = inode_to_bdi(inode); + spin_unlock(&inode->i_lock); + spin_lock(&bdi->wb.list_lock); if (bdi_cap_writeback_dirty(bdi)) { WARN(!test_bit(BDI_registered, &bdi->state), "bdi-%s not registered\n", bdi->name); @@ -1187,8 +1187,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) wakeup_bdi = true; } - spin_unlock(&inode->i_lock); - spin_lock(&bdi->wb.list_lock); inode->dirtied_when = jiffies; list_move(&inode->i_wb_list, &bdi->wb.b_dirty); spin_unlock(&bdi->wb.list_lock); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 0e91a3c..318e843 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -558,3 +558,74 @@ void __fscache_cookie_put(struct fscache_cookie *cookie) _leave(""); } + +/* + * check the consistency between the netfs inode and the backing cache + * + * NOTE: it only serves no-index type + */ +int __fscache_check_consistency(struct fscache_cookie *cookie) +{ + struct fscache_operation *op; + struct fscache_object *object; + int ret; + + _enter("%p,", cookie); + + ASSERTCMP(cookie->def->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE); + + if (fscache_wait_for_deferred_lookup(cookie) < 0) + return -ERESTARTSYS; + + if (hlist_empty(&cookie->backing_objects)) + return 0; + + op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY); + if (!op) + return -ENOMEM; + + fscache_operation_init(op, NULL, NULL); + op->flags = FSCACHE_OP_MYTHREAD | + (1 << FSCACHE_OP_WAITING); + + spin_lock(&cookie->lock); + + if (hlist_empty(&cookie->backing_objects)) + goto inconsistent; + object = hlist_entry(cookie->backing_objects.first, + struct fscache_object, cookie_link); + if (test_bit(FSCACHE_IOERROR, &object->cache->flags)) + goto inconsistent; + + op->debug_id = atomic_inc_return(&fscache_op_debug_id); + + atomic_inc(&cookie->n_active); + if (fscache_submit_op(object, op) < 0) + goto submit_failed; + + /* the work queue now carries its own ref on the object */ + spin_unlock(&cookie->lock); + + ret = fscache_wait_for_operation_activation(object, op, + NULL, NULL, NULL); + if (ret == 0) { + /* ask the cache to honour the operation */ + ret = object->cache->ops->check_consistency(op); + fscache_op_complete(op, false); + } else if (ret == -ENOBUFS) { + ret = 0; + } + + fscache_put_operation(op); + _leave(" = %d", ret); + return ret; + +submit_failed: + atomic_dec(&cookie->n_active); +inconsistent: + spin_unlock(&cookie->lock); + kfree(op); + _leave(" = -ESTALE"); + return -ESTALE; +} +EXPORT_SYMBOL(__fscache_check_consistency); diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 12d505b..4226f66 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -130,6 +130,12 @@ extern void fscache_operation_gc(struct work_struct *); /* * page.c */ +extern int fscache_wait_for_deferred_lookup(struct fscache_cookie *); +extern int fscache_wait_for_operation_activation(struct fscache_object *, + struct fscache_operation *, + atomic_t *, + atomic_t *, + void (*)(struct fscache_operation *)); extern void fscache_invalidate_writes(struct fscache_cookie *); /* diff --git a/fs/fscache/page.c b/fs/fscache/page.c index d479ab3..73899c1 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -278,7 +278,7 @@ static struct fscache_retrieval *fscache_alloc_retrieval( /* * wait for a deferred lookup to complete */ -static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) +int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) { unsigned long jif; @@ -322,42 +322,46 @@ static void fscache_do_cancel_retrieval(struct fscache_operation *_op) /* * wait for an object to become active (or dead) */ -static int fscache_wait_for_retrieval_activation(struct fscache_object *object, - struct fscache_retrieval *op, - atomic_t *stat_op_waits, - atomic_t *stat_object_dead) +int fscache_wait_for_operation_activation(struct fscache_object *object, + struct fscache_operation *op, + atomic_t *stat_op_waits, + atomic_t *stat_object_dead, + void (*do_cancel)(struct fscache_operation *)) { int ret; - if (!test_bit(FSCACHE_OP_WAITING, &op->op.flags)) + if (!test_bit(FSCACHE_OP_WAITING, &op->flags)) goto check_if_dead; _debug(">>> WT"); - fscache_stat(stat_op_waits); - if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, + if (stat_op_waits) + fscache_stat(stat_op_waits); + if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING, fscache_wait_bit_interruptible, TASK_INTERRUPTIBLE) != 0) { - ret = fscache_cancel_op(&op->op, fscache_do_cancel_retrieval); + ret = fscache_cancel_op(op, do_cancel); if (ret == 0) return -ERESTARTSYS; /* it's been removed from the pending queue by another party, * so we should get to run shortly */ - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, + wait_on_bit(&op->flags, FSCACHE_OP_WAITING, fscache_wait_bit, TASK_UNINTERRUPTIBLE); } _debug("<<< GO"); check_if_dead: - if (op->op.state == FSCACHE_OP_ST_CANCELLED) { - fscache_stat(stat_object_dead); + if (op->state == FSCACHE_OP_ST_CANCELLED) { + if (stat_object_dead) + fscache_stat(stat_object_dead); _leave(" = -ENOBUFS [cancelled]"); return -ENOBUFS; } if (unlikely(fscache_object_is_dead(object))) { - pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->op.state); - fscache_cancel_op(&op->op, fscache_do_cancel_retrieval); - fscache_stat(stat_object_dead); + pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->state); + fscache_cancel_op(op, do_cancel); + if (stat_object_dead) + fscache_stat(stat_object_dead); return -ENOBUFS; } return 0; @@ -432,10 +436,11 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, /* we wait for the operation to become active, and then process it * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_retrieval_activation( - object, op, + ret = fscache_wait_for_operation_activation( + object, &op->op, __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); + __fscache_stat(&fscache_n_retrievals_object_dead), + fscache_do_cancel_retrieval); if (ret < 0) goto error; @@ -557,10 +562,11 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, /* we wait for the operation to become active, and then process it * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_retrieval_activation( - object, op, + ret = fscache_wait_for_operation_activation( + object, &op->op, __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); + __fscache_stat(&fscache_n_retrievals_object_dead), + fscache_do_cancel_retrieval); if (ret < 0) goto error; @@ -658,10 +664,11 @@ int __fscache_alloc_page(struct fscache_cookie *cookie, fscache_stat(&fscache_n_alloc_ops); - ret = fscache_wait_for_retrieval_activation( - object, op, + ret = fscache_wait_for_operation_activation( + object, &op->op, __fscache_stat(&fscache_n_alloc_op_waits), - __fscache_stat(&fscache_n_allocs_object_dead)); + __fscache_stat(&fscache_n_allocs_object_dead), + fscache_do_cancel_retrieval); if (ret < 0) goto error; @@ -694,6 +701,22 @@ nobufs: EXPORT_SYMBOL(__fscache_alloc_page); /* + * Unmark pages allocate in the readahead code path (via: + * fscache_readpages_or_alloc) after delegating to the base filesystem + */ +void __fscache_readpages_cancel(struct fscache_cookie *cookie, + struct list_head *pages) +{ + struct page *page; + + list_for_each_entry(page, pages, lru) { + if (PageFsCache(page)) + __fscache_uncache_page(cookie, page); + } +} +EXPORT_SYMBOL(__fscache_readpages_cancel); + +/* * release a write op reference */ static void fscache_release_write_op(struct fscache_operation *_op) @@ -890,7 +913,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, (1 << FSCACHE_OP_WAITING) | (1 << FSCACHE_OP_UNUSE_COOKIE); - ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM); + ret = radix_tree_maybe_preload(gfp & ~__GFP_HIGHMEM); if (ret < 0) goto nomem_free; diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index aef34b1..adbfd66 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -568,6 +568,7 @@ static ssize_t cuse_class_waiting_show(struct device *dev, return sprintf(buf, "%d\n", atomic_read(&cc->fc.num_waiting)); } +static DEVICE_ATTR(waiting, S_IFREG | 0400, cuse_class_waiting_show, NULL); static ssize_t cuse_class_abort_store(struct device *dev, struct device_attribute *attr, @@ -578,12 +579,14 @@ static ssize_t cuse_class_abort_store(struct device *dev, fuse_abort_conn(&cc->fc); return count; } +static DEVICE_ATTR(abort, S_IFREG | 0200, NULL, cuse_class_abort_store); -static struct device_attribute cuse_class_dev_attrs[] = { - __ATTR(waiting, S_IFREG | 0400, cuse_class_waiting_show, NULL), - __ATTR(abort, S_IFREG | 0200, NULL, cuse_class_abort_store), - { } +static struct attribute *cuse_class_dev_attrs[] = { + &dev_attr_waiting.attr, + &dev_attr_abort.attr, + NULL, }; +ATTRIBUTE_GROUPS(cuse_class_dev); static struct miscdevice cuse_miscdev = { .minor = MISC_DYNAMIC_MINOR, @@ -609,7 +612,7 @@ static int __init cuse_init(void) if (IS_ERR(cuse_class)) return PTR_ERR(cuse_class); - cuse_class->dev_attrs = cuse_class_dev_attrs; + cuse_class->dev_groups = cuse_class_dev_groups; rc = misc_register(&cuse_miscdev); if (rc) { diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 1d55f94..ef74ad5 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1765,11 +1765,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, /* Look up request on processing list by unique ID */ static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique) { - struct list_head *entry; + struct fuse_req *req; - list_for_each(entry, &fc->processing) { - struct fuse_req *req; - req = list_entry(entry, struct fuse_req, list); + list_for_each_entry(req, &fc->processing, list) { if (req->in.h.unique == unique || req->intr_unique == unique) return req; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 0eda527..62b43b5 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -182,10 +182,11 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) struct inode *inode; struct dentry *parent; struct fuse_conn *fc; + int ret; inode = ACCESS_ONCE(entry->d_inode); if (inode && is_bad_inode(inode)) - return 0; + goto invalid; else if (fuse_dentry_time(entry) < get_jiffies_64()) { int err; struct fuse_entry_out outarg; @@ -195,20 +196,23 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) /* For negative dentries, always do a fresh lookup */ if (!inode) - return 0; + goto invalid; + ret = -ECHILD; if (flags & LOOKUP_RCU) - return -ECHILD; + goto out; fc = get_fuse_conn(inode); req = fuse_get_req_nopages(fc); + ret = PTR_ERR(req); if (IS_ERR(req)) - return 0; + goto out; forget = fuse_alloc_forget(); if (!forget) { fuse_put_request(fc, req); - return 0; + ret = -ENOMEM; + goto out; } attr_version = fuse_get_attr_version(fc); @@ -227,7 +231,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) struct fuse_inode *fi = get_fuse_inode(inode); if (outarg.nodeid != get_node_id(inode)) { fuse_queue_forget(fc, forget, outarg.nodeid, 1); - return 0; + goto invalid; } spin_lock(&fc->lock); fi->nlookup++; @@ -235,7 +239,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) } kfree(forget); if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) - return 0; + goto invalid; fuse_change_attributes(inode, &outarg.attr, entry_attr_timeout(&outarg), @@ -249,7 +253,15 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) dput(parent); } } - return 1; + ret = 1; +out: + return ret; + +invalid: + ret = 0; + if (check_submounts_and_drop(entry) != 0) + ret = 1; + goto out; } static int invalid_nodeid(u64 nodeid) @@ -267,26 +279,6 @@ int fuse_valid_type(int m) S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m); } -/* - * Add a directory inode to a dentry, ensuring that no other dentry - * refers to this inode. Called with fc->inst_mutex. - */ -static struct dentry *fuse_d_add_directory(struct dentry *entry, - struct inode *inode) -{ - struct dentry *alias = d_find_alias(inode); - if (alias && !(alias->d_flags & DCACHE_DISCONNECTED)) { - /* This tries to shrink the subtree below alias */ - fuse_invalidate_entry(alias); - dput(alias); - if (!hlist_empty(&inode->i_dentry)) - return ERR_PTR(-EBUSY); - } else { - dput(alias); - } - return d_splice_alias(inode, entry); -} - int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name, struct fuse_entry_out *outarg, struct inode **inode) { @@ -345,6 +337,24 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name, return err; } +static struct dentry *fuse_materialise_dentry(struct dentry *dentry, + struct inode *inode) +{ + struct dentry *newent; + + if (inode && S_ISDIR(inode->i_mode)) { + struct fuse_conn *fc = get_fuse_conn(inode); + + mutex_lock(&fc->inst_mutex); + newent = d_materialise_unique(dentry, inode); + mutex_unlock(&fc->inst_mutex); + } else { + newent = d_materialise_unique(dentry, inode); + } + + return newent; +} + static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, unsigned int flags) { @@ -352,7 +362,6 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, struct fuse_entry_out outarg; struct inode *inode; struct dentry *newent; - struct fuse_conn *fc = get_fuse_conn(dir); bool outarg_valid = true; err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name, @@ -368,16 +377,10 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, if (inode && get_node_id(inode) == FUSE_ROOT_ID) goto out_iput; - if (inode && S_ISDIR(inode->i_mode)) { - mutex_lock(&fc->inst_mutex); - newent = fuse_d_add_directory(entry, inode); - mutex_unlock(&fc->inst_mutex); - err = PTR_ERR(newent); - if (IS_ERR(newent)) - goto out_iput; - } else { - newent = d_splice_alias(inode, entry); - } + newent = fuse_materialise_dentry(entry, inode); + err = PTR_ERR(newent); + if (IS_ERR(newent)) + goto out_err; entry = newent ? newent : entry; if (outarg_valid) @@ -1174,6 +1177,8 @@ static int parse_dirfile(char *buf, size_t nbytes, struct file *file, return -EIO; if (reclen > nbytes) break; + if (memchr(dirent->name, '/', dirent->namelen) != NULL) + return -EIO; if (!dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, dirent->type)) @@ -1223,30 +1228,46 @@ static int fuse_direntplus_link(struct file *file, if (name.name[1] == '.' && name.len == 2) return 0; } + + if (invalid_nodeid(o->nodeid)) + return -EIO; + if (!fuse_valid_type(o->attr.mode)) + return -EIO; + fc = get_fuse_conn(dir); name.hash = full_name_hash(name.name, name.len); dentry = d_lookup(parent, &name); - if (dentry && dentry->d_inode) { + if (dentry) { inode = dentry->d_inode; - if (get_node_id(inode) == o->nodeid) { + if (!inode) { + d_drop(dentry); + } else if (get_node_id(inode) != o->nodeid || + ((o->attr.mode ^ inode->i_mode) & S_IFMT)) { + err = d_invalidate(dentry); + if (err) + goto out; + } else if (is_bad_inode(inode)) { + err = -EIO; + goto out; + } else { struct fuse_inode *fi; fi = get_fuse_inode(inode); spin_lock(&fc->lock); fi->nlookup++; spin_unlock(&fc->lock); + fuse_change_attributes(inode, &o->attr, + entry_attr_timeout(o), + attr_version); + /* * The other branch to 'found' comes via fuse_iget() * which bumps nlookup inside */ goto found; } - err = d_invalidate(dentry); - if (err) - goto out; dput(dentry); - dentry = NULL; } dentry = d_alloc(parent, &name); @@ -1259,25 +1280,22 @@ static int fuse_direntplus_link(struct file *file, if (!inode) goto out; - alias = d_materialise_unique(dentry, inode); + alias = fuse_materialise_dentry(dentry, inode); err = PTR_ERR(alias); if (IS_ERR(alias)) goto out; + if (alias) { dput(dentry); dentry = alias; } found: - fuse_change_attributes(inode, &o->attr, entry_attr_timeout(o), - attr_version); - fuse_change_entry_timeout(dentry, o); err = 0; out: - if (dentry) - dput(dentry); + dput(dentry); return err; } @@ -1299,6 +1317,8 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, return -EIO; if (reclen > nbytes) break; + if (memchr(dirent->name, '/', dirent->namelen) != NULL) + return -EIO; if (!over) { /* We fill entries into dstbuf only as much as @@ -1569,6 +1589,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct file *file) { struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_req *req; struct fuse_setattr_in inarg; struct fuse_attr_out outarg; @@ -1596,8 +1617,10 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, if (IS_ERR(req)) return PTR_ERR(req); - if (is_truncate) + if (is_truncate) { fuse_set_nowrite(inode); + set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); + } memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); @@ -1655,16 +1678,18 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock. */ if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { - truncate_pagecache(inode, oldsize, outarg.attr.size); + truncate_pagecache(inode, outarg.attr.size); invalidate_inode_pages2(inode->i_mapping); } + clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); return 0; error: if (is_truncate) fuse_release_nowrite(inode); + clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); return err; } @@ -1728,6 +1753,8 @@ static int fuse_setxattr(struct dentry *entry, const char *name, fc->no_setxattr = 1; err = -EOPNOTSUPP; } + if (!err) + fuse_invalidate_attr(inode); return err; } @@ -1857,6 +1884,8 @@ static int fuse_removexattr(struct dentry *entry, const char *name) fc->no_removexattr = 1; err = -EOPNOTSUPP; } + if (!err) + fuse_invalidate_attr(inode); return err; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5c121fe..d409dea 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -629,7 +629,8 @@ static void fuse_read_update_size(struct inode *inode, loff_t size, struct fuse_inode *fi = get_fuse_inode(inode); spin_lock(&fc->lock); - if (attr_ver == fi->attr_version && size < inode->i_size) { + if (attr_ver == fi->attr_version && size < inode->i_size && + !test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { fi->attr_version = ++fc->attr_version; i_size_write(inode, size); } @@ -1032,12 +1033,16 @@ static ssize_t fuse_perform_write(struct file *file, { struct inode *inode = mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); int err = 0; ssize_t res = 0; if (is_bad_inode(inode)) return -EIO; + if (inode->i_size < pos + iov_iter_count(ii)) + set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); + do { struct fuse_req *req; ssize_t count; @@ -1073,6 +1078,7 @@ static ssize_t fuse_perform_write(struct file *file, if (res > 0) fuse_write_update_size(inode, pos); + clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); fuse_invalidate_attr(inode); return res > 0 ? res : err; @@ -1529,7 +1535,6 @@ static int fuse_writepage_locked(struct page *page) inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK); inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP); - end_page_writeback(page); spin_lock(&fc->lock); list_add(&req->writepages_entry, &fi->writepages); @@ -1537,6 +1542,8 @@ static int fuse_writepage_locked(struct page *page) fuse_flush_writepages(inode); spin_unlock(&fc->lock); + end_page_writeback(page); + return 0; err_free: diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index fde7249..5ced199 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -115,6 +115,8 @@ struct fuse_inode { enum { /** Advise readdirplus */ FUSE_I_ADVISE_RDPLUS, + /** An operation changing file size is in progress */ + FUSE_I_SIZE_UNSTABLE, }; struct fuse_conn; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 0b57859..a8ce6da 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -201,7 +201,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, struct timespec old_mtime; spin_lock(&fc->lock); - if (attr_version != 0 && fi->attr_version > attr_version) { + if ((attr_version != 0 && fi->attr_version > attr_version) || + test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { spin_unlock(&fc->lock); return; } @@ -217,7 +218,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, bool inval = false; if (oldsize != attr->size) { - truncate_pagecache(inode, oldsize, attr->size); + truncate_pagecache(inode, attr->size); inval = true; } else if (fc->auto_inval_data) { struct timespec new_mtime = { @@ -929,7 +930,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) fc->bdi.name = "fuse"; fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; /* fuse does it's own writeback accounting */ - fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB; + fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT; err = bdi_init(&fc->bdi); if (err) diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index ee48ad3..1f7d805 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -122,14 +122,13 @@ out: } /** - * gfs2_writeback_writepage - Write page for writeback mappings + * gfs2_writepage - Write page for writeback mappings * @page: The page * @wbc: The writeback control * */ -static int gfs2_writeback_writepage(struct page *page, - struct writeback_control *wbc) +static int gfs2_writepage(struct page *page, struct writeback_control *wbc) { int ret; @@ -141,32 +140,6 @@ static int gfs2_writeback_writepage(struct page *page, } /** - * gfs2_ordered_writepage - Write page for ordered data files - * @page: The page to write - * @wbc: The writeback control - * - */ - -static int gfs2_ordered_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - struct gfs2_inode *ip = GFS2_I(inode); - int ret; - - ret = gfs2_writepage_common(page, wbc); - if (ret <= 0) - return ret; - - if (!page_has_buffers(page)) { - create_empty_buffers(page, inode->i_sb->s_blocksize, - (1 << BH_Dirty)|(1 << BH_Uptodate)); - } - gfs2_page_add_databufs(ip, page, 0, inode->i_sb->s_blocksize-1); - return block_write_full_page(page, gfs2_get_block_noalloc, wbc); -} - -/** * __gfs2_jdata_writepage - The core of jdata writepage * @page: The page to write * @wbc: The writeback control @@ -842,6 +815,8 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, unsigned int from = pos & (PAGE_CACHE_SIZE - 1); unsigned int to = from + len; int ret; + struct gfs2_trans *tr = current->journal_info; + BUG_ON(!tr); BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL); @@ -852,8 +827,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, goto failed; } - gfs2_trans_add_meta(ip->i_gl, dibh); - if (gfs2_is_stuffed(ip)) return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page); @@ -861,6 +834,11 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, gfs2_page_add_databufs(ip, page, from, to); ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + if (tr->tr_num_buf_new) + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + else + gfs2_trans_add_meta(ip->i_gl, dibh); + if (inode == sdp->sd_rindex) { adjust_fs_space(inode); @@ -1107,7 +1085,7 @@ cannot_release: } static const struct address_space_operations gfs2_writeback_aops = { - .writepage = gfs2_writeback_writepage, + .writepage = gfs2_writepage, .writepages = gfs2_writepages, .readpage = gfs2_readpage, .readpages = gfs2_readpages, @@ -1123,7 +1101,7 @@ static const struct address_space_operations gfs2_writeback_aops = { }; static const struct address_space_operations gfs2_ordered_aops = { - .writepage = gfs2_ordered_writepage, + .writepage = gfs2_writepage, .writepages = gfs2_writepages, .readpage = gfs2_readpage, .readpages = gfs2_readpages, diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 5e2f56f..62a65fc 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1016,7 +1016,7 @@ static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize chunk = oldsize - newsize; if (chunk > max_chunk) chunk = max_chunk; - truncate_pagecache(inode, oldsize, oldsize - chunk); + truncate_pagecache(inode, oldsize - chunk); oldsize -= chunk; gfs2_trans_end(sdp); error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES); @@ -1067,7 +1067,7 @@ static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize) if (journaled) error = gfs2_journaled_truncate(inode, oldsize, newsize); else - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); if (error) { brelse(dibh); diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index f2448ab..d3a5d4e 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -93,12 +93,9 @@ invalid_gunlock: if (!had_lock) gfs2_glock_dq_uninit(&d_gh); invalid: - if (inode && S_ISDIR(inode->i_mode)) { - if (have_submounts(dentry)) - goto valid; - shrink_dcache_parent(dentry); - } - d_drop(dentry); + if (check_submounts_and_drop(dentry) != 0) + goto valid; + dput(parent); return 0; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 0cb4c155..2e5fc26 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1859,7 +1859,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, memset(&rlist, 0, sizeof(struct gfs2_rgrp_list)); - ht = kzalloc(size, GFP_NOFS); + ht = kzalloc(size, GFP_NOFS | __GFP_NOWARN); if (ht == NULL) ht = vzalloc(size); if (!ht) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 72c3866..0621b46 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -650,7 +650,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC); + int sync_state = inode->i_state & I_DIRTY; struct gfs2_inode *ip = GFS2_I(inode); int ret = 0, ret1 = 0; @@ -660,6 +660,8 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, return ret1; } + if (!gfs2_is_jdata(ip)) + sync_state &= ~I_DIRTY_PAGES; if (datasync) sync_state &= ~I_DIRTY_SYNC; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9435384..c2f41b4 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1411,7 +1411,6 @@ __acquires(&lru_lock) if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags)); - smp_mb__after_clear_bit(); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put_nolock(gl); spin_unlock(&gl->gl_spin); @@ -1428,21 +1427,22 @@ __acquires(&lru_lock) * gfs2_dispose_glock_lru() above. */ -static void gfs2_scan_glock_lru(int nr) +static long gfs2_scan_glock_lru(int nr) { struct gfs2_glock *gl; LIST_HEAD(skipped); LIST_HEAD(dispose); + long freed = 0; spin_lock(&lru_lock); - while(nr && !list_empty(&lru_list)) { + while ((nr-- >= 0) && !list_empty(&lru_list)) { gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru); /* Test for being demotable */ if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); - nr--; + freed++; continue; } @@ -1452,23 +1452,28 @@ static void gfs2_scan_glock_lru(int nr) if (!list_empty(&dispose)) gfs2_dispose_glock_lru(&dispose); spin_unlock(&lru_lock); + + return freed; } -static int gfs2_shrink_glock_memory(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long gfs2_glock_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) { - if (sc->nr_to_scan) { - if (!(sc->gfp_mask & __GFP_FS)) - return -1; - gfs2_scan_glock_lru(sc->nr_to_scan); - } + if (!(sc->gfp_mask & __GFP_FS)) + return SHRINK_STOP; + return gfs2_scan_glock_lru(sc->nr_to_scan); +} - return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure; +static unsigned long gfs2_glock_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_read(&lru_count)); } static struct shrinker glock_shrinker = { - .shrink = gfs2_shrink_glock_memory, .seeks = DEFAULT_SEEKS, + .count_objects = gfs2_glock_shrink_count, + .scan_objects = gfs2_glock_shrink_scan, }; /** @@ -1488,7 +1493,7 @@ static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp, rcu_read_lock(); hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) { - if ((gl->gl_sbd == sdp) && atomic_read(&gl->gl_ref)) + if ((gl->gl_sbd == sdp) && atomic_inc_not_zero(&gl->gl_ref)) examiner(gl); } rcu_read_unlock(); @@ -1508,18 +1513,17 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) * thaw_glock - thaw out a glock which has an unprocessed reply waiting * @gl: The glock to thaw * - * N.B. When we freeze a glock, we leave a ref to the glock outstanding, - * so this has to result in the ref count being dropped by one. */ static void thaw_glock(struct gfs2_glock *gl) { if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) - return; + goto out; set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - gfs2_glock_hold(gl); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) + if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) { +out: gfs2_glock_put(gl); + } } /** @@ -1536,7 +1540,6 @@ static void clear_glock(struct gfs2_glock *gl) if (gl->gl_state != LM_ST_UNLOCKED) handle_callback(gl, LM_ST_UNLOCKED, 0, false); spin_unlock(&gl->gl_spin); - gfs2_glock_hold(gl); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); } @@ -1838,14 +1841,14 @@ int __init gfs2_glock_init(void) glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_FREEZABLE, 0); - if (IS_ERR(glock_workqueue)) - return PTR_ERR(glock_workqueue); + if (!glock_workqueue) + return -ENOMEM; gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", WQ_MEM_RECLAIM | WQ_FREEZABLE, 0); - if (IS_ERR(gfs2_delete_workqueue)) { + if (!gfs2_delete_workqueue) { destroy_workqueue(glock_workqueue); - return PTR_ERR(gfs2_delete_workqueue); + return -ENOMEM; } register_shrinker(&glock_shrinker); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 5f2e522..e2e0a90 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -47,7 +47,8 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) * None of the buffers should be dirty, locked, or pinned. */ -static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) +static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync, + unsigned int nr_revokes) { struct gfs2_sbd *sdp = gl->gl_sbd; struct list_head *head = &gl->gl_ail_list; @@ -57,7 +58,9 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) gfs2_log_lock(sdp); spin_lock(&sdp->sd_ail_lock); - list_for_each_entry_safe(bd, tmp, head, bd_ail_gl_list) { + list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) { + if (nr_revokes == 0) + break; bh = bd->bd_bh; if (bh->b_state & b_state) { if (fsync) @@ -65,6 +68,7 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) gfs2_ail_error(gl, bh); } gfs2_trans_add_revoke(sdp, bd); + nr_revokes--; } GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count)); spin_unlock(&sdp->sd_ail_lock); @@ -91,7 +95,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) WARN_ON_ONCE(current->journal_info); current->journal_info = &tr; - __gfs2_ail_flush(gl, 0); + __gfs2_ail_flush(gl, 0, tr.tr_revokes); gfs2_trans_end(sdp); gfs2_log_flush(sdp, NULL); @@ -101,15 +105,19 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) { struct gfs2_sbd *sdp = gl->gl_sbd; unsigned int revokes = atomic_read(&gl->gl_ail_count); + unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64); int ret; if (!revokes) return; - ret = gfs2_trans_begin(sdp, 0, revokes); + while (revokes > max_revokes) + max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64); + + ret = gfs2_trans_begin(sdp, 0, max_revokes); if (ret) return; - __gfs2_ail_flush(gl, fsync); + __gfs2_ail_flush(gl, fsync, max_revokes); gfs2_trans_end(sdp); gfs2_log_flush(sdp, NULL); } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index bbb2715..64915ee 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -594,7 +594,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, } gfs2_glock_dq_uninit(ghs); if (IS_ERR(d)) - return PTR_RET(d); + return PTR_ERR(d); return error; } else if (error != -ENOENT) { goto fail_gunlock; @@ -1750,6 +1750,10 @@ static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name, struct gfs2_holder gh; int ret; + /* For selinux during lookup */ + if (gfs2_glock_is_locked_by_me(ip->i_gl)) + return generic_getxattr(dentry, name, data, size); + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); ret = gfs2_glock_nq(&gh); if (ret == 0) { diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 17c5b5d..010b9fb 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -579,6 +579,24 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, return error; } +/** + * gfs2_meta_sync - Sync all buffers associated with a glock + * @gl: The glock + * + */ + +static void gfs2_meta_sync(struct gfs2_glock *gl) +{ + struct address_space *mapping = gfs2_glock2aspace(gl); + int error; + + filemap_fdatawrite(mapping); + error = filemap_fdatawait(mapping); + + if (error) + gfs2_io_error(gl->gl_sbd); +} + static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) { struct gfs2_inode *ip = GFS2_I(jd->jd_inode); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index e04d0e0..351586e 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -32,7 +32,8 @@ struct workqueue_struct *gfs2_control_wq; static struct shrinker qd_shrinker = { - .shrink = gfs2_shrink_qd_memory, + .count_objects = gfs2_qd_shrink_count, + .scan_objects = gfs2_qd_shrink_scan, .seeks = DEFAULT_SEEKS, }; @@ -155,7 +156,7 @@ static int __init init_gfs2_fs(void) goto fail_wq; gfs2_control_wq = alloc_workqueue("gfs2_control", - WQ_NON_REENTRANT | WQ_UNBOUND | WQ_FREEZABLE, 0); + WQ_UNBOUND | WQ_FREEZABLE, 0); if (!gfs2_control_wq) goto fail_recovery; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 0da3906..9324150 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -98,24 +98,6 @@ const struct address_space_operations gfs2_meta_aops = { }; /** - * gfs2_meta_sync - Sync all buffers associated with a glock - * @gl: The glock - * - */ - -void gfs2_meta_sync(struct gfs2_glock *gl) -{ - struct address_space *mapping = gfs2_glock2aspace(gl); - int error; - - filemap_fdatawrite(mapping); - error = filemap_fdatawait(mapping); - - if (error) - gfs2_io_error(gl->gl_sbd); -} - -/** * gfs2_getbuf - Get a buffer with a given address space * @gl: the glock * @blkno: the block number (filesystem scope) diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 0d4c843..4823b93 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -48,21 +48,17 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) return inode->i_sb->s_fs_info; } -void gfs2_meta_sync(struct gfs2_glock *gl); - -struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno); -int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, - int flags, struct buffer_head **bhp); -int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh); -struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create); - -void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, - int meta); - -void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen); - -int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, - struct buffer_head **bhp); +extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno); +extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, + struct buffer_head **bhp); +extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh); +extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, + int create); +extern void gfs2_remove_from_journal(struct buffer_head *bh, + struct gfs2_trans *tr, int meta); +extern void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, + struct buffer_head **bhp); static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip, struct buffer_head **bhp) diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 0262c19..19ff5e8 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -646,6 +646,48 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) return error; } +/** + * check_journal_clean - Make sure a journal is clean for a spectator mount + * @sdp: The GFS2 superblock + * @jd: The journal descriptor + * + * Returns: 0 if the journal is clean or locked, else an error + */ +static int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd) +{ + int error; + struct gfs2_holder j_gh; + struct gfs2_log_header_host head; + struct gfs2_inode *ip; + + ip = GFS2_I(jd->jd_inode); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_NOEXP | + GL_EXACT | GL_NOCACHE, &j_gh); + if (error) { + fs_err(sdp, "Error locking journal for spectator mount.\n"); + return -EPERM; + } + error = gfs2_jdesc_check(jd); + if (error) { + fs_err(sdp, "Error checking journal for spectator mount.\n"); + goto out_unlock; + } + error = gfs2_find_jhead(jd, &head); + if (error) { + fs_err(sdp, "Error parsing journal for spectator mount.\n"); + goto out_unlock; + } + if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) { + error = -EPERM; + fs_err(sdp, "jid=%u: Journal is dirty, so the first mounter " + "must not be a spectator.\n", jd->jd_jid); + } + +out_unlock: + gfs2_glock_dq_uninit(&j_gh); + return error; +} + static int init_journal(struct gfs2_sbd *sdp, int undo) { struct inode *master = sdp->sd_master_dir->d_inode; @@ -732,8 +774,15 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) if (sdp->sd_lockstruct.ls_first) { unsigned int x; for (x = 0; x < sdp->sd_journals; x++) { - error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x), - true); + struct gfs2_jdesc *jd = gfs2_jdesc_find(sdp, x); + + if (sdp->sd_args.ar_spectator) { + error = check_journal_clean(sdp, jd); + if (error) + goto fail_jinode_gh; + continue; + } + error = gfs2_recover_journal(jd, true); if (error) { fs_err(sdp, "error recovering journal %u: %d\n", x, error); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 3768c2f..db44135 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -75,17 +75,16 @@ static LIST_HEAD(qd_lru_list); static atomic_t qd_lru_count = ATOMIC_INIT(0); static DEFINE_SPINLOCK(qd_lru_lock); -int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc) +unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct gfs2_quota_data *qd; struct gfs2_sbd *sdp; int nr_to_scan = sc->nr_to_scan; - - if (nr_to_scan == 0) - goto out; + long freed = 0; if (!(sc->gfp_mask & __GFP_FS)) - return -1; + return SHRINK_STOP; spin_lock(&qd_lru_lock); while (nr_to_scan && !list_empty(&qd_lru_list)) { @@ -110,11 +109,16 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc) kmem_cache_free(gfs2_quotad_cachep, qd); spin_lock(&qd_lru_lock); nr_to_scan--; + freed++; } spin_unlock(&qd_lru_lock); + return freed; +} -out: - return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100; +unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_read(&qd_lru_count)); } static u64 qd2index(struct gfs2_quota_data *qd) diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 4f5e6e4..0f64d9d 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -53,8 +53,10 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) return ret; } -extern int gfs2_shrink_qd_memory(struct shrinker *shrink, - struct shrink_control *sc); +extern unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, + struct shrink_control *sc); +extern unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc); extern const struct quotactl_ops gfs2_quotactl_ops; #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index f9299d8..380ab31 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -41,7 +41,7 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); hfs_file_truncate(inode); } } diff --git a/fs/hfsplus/Kconfig b/fs/hfsplus/Kconfig index a633718..24bc20f 100644 --- a/fs/hfsplus/Kconfig +++ b/fs/hfsplus/Kconfig @@ -11,3 +11,21 @@ config HFSPLUS_FS MacOS 8. It includes all Mac specific filesystem data such as data forks and creator codes, but it also has several UNIX style features such as file ownership and permissions. + +config HFSPLUS_FS_POSIX_ACL + bool "HFS+ POSIX Access Control Lists" + depends on HFSPLUS_FS + select FS_POSIX_ACL + help + POSIX Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the POSIX ACLs for + Linux website <http://acl.bestbits.at/>. + + It needs to understand that POSIX ACLs are treated only under + Linux. POSIX ACLs doesn't mean something under Mac OS X. + Mac OS X beginning with version 10.4 ("Tiger") support NFSv4 ACLs, + which are part of the NFSv4 standard. + + If you don't know what Access Control Lists are, say N diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile index 09d278b..683fca2 100644 --- a/fs/hfsplus/Makefile +++ b/fs/hfsplus/Makefile @@ -7,3 +7,5 @@ obj-$(CONFIG_HFSPLUS_FS) += hfsplus.o hfsplus-objs := super.o options.o inode.o ioctl.o extents.o catalog.o dir.o btree.o \ bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o \ attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o + +hfsplus-$(CONFIG_HFSPLUS_FS_POSIX_ACL) += posix_acl.o diff --git a/fs/hfsplus/acl.h b/fs/hfsplus/acl.h new file mode 100644 index 0000000..07c0d49 --- /dev/null +++ b/fs/hfsplus/acl.h @@ -0,0 +1,30 @@ +/* + * linux/fs/hfsplus/acl.h + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for Posix Access Control Lists (ACLs) support. + */ + +#include <linux/posix_acl_xattr.h> + +#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL + +/* posix_acl.c */ +struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type); +extern int hfsplus_posix_acl_chmod(struct inode *); +extern int hfsplus_init_posix_acl(struct inode *, struct inode *); + +#else /* CONFIG_HFSPLUS_FS_POSIX_ACL */ +#define hfsplus_get_posix_acl NULL + +static inline int hfsplus_posix_acl_chmod(struct inode *inode) +{ + return 0; +} + +static inline int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) +{ + return 0; +} +#endif /* CONFIG_HFSPLUS_FS_POSIX_ACL */ diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index d8ce4bd..4a4fea0 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -16,6 +16,7 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" #include "xattr.h" +#include "acl.h" static inline void hfsplus_instantiate(struct dentry *dentry, struct inode *inode, u32 cnid) @@ -529,6 +530,9 @@ const struct inode_operations hfsplus_dir_inode_operations = { .getxattr = generic_getxattr, .listxattr = hfsplus_listxattr, .removexattr = hfsplus_removexattr, +#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL + .get_acl = hfsplus_get_posix_acl, +#endif }; const struct file_operations hfsplus_dir_operations = { diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index ede7931..2b9cd016 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -30,6 +30,7 @@ #define DBG_EXTENT 0x00000020 #define DBG_BITMAP 0x00000040 #define DBG_ATTR_MOD 0x00000080 +#define DBG_ACL_MOD 0x00000100 #if 0 #define DBG_MASK (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD) diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index f833d35..37213d0 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -19,6 +19,7 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" #include "xattr.h" +#include "acl.h" static int hfsplus_readpage(struct file *file, struct page *page) { @@ -35,7 +36,7 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); hfsplus_file_truncate(inode); } } @@ -316,6 +317,13 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) setattr_copy(inode, attr); mark_inode_dirty(inode); + + if (attr->ia_valid & ATTR_MODE) { + error = hfsplus_posix_acl_chmod(inode); + if (unlikely(error)) + return error; + } + return 0; } @@ -383,6 +391,9 @@ static const struct inode_operations hfsplus_file_inode_operations = { .getxattr = generic_getxattr, .listxattr = hfsplus_listxattr, .removexattr = hfsplus_removexattr, +#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL + .get_acl = hfsplus_get_posix_acl, +#endif }; static const struct file_operations hfsplus_file_operations = { diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c new file mode 100644 index 0000000..b609cc1 --- /dev/null +++ b/fs/hfsplus/posix_acl.c @@ -0,0 +1,274 @@ +/* + * linux/fs/hfsplus/posix_acl.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for Posix Access Control Lists (ACLs) support. + */ + +#include "hfsplus_fs.h" +#include "xattr.h" +#include "acl.h" + +struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) +{ + struct posix_acl *acl; + char *xattr_name; + char *value = NULL; + ssize_t size; + + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + + switch (type) { + case ACL_TYPE_ACCESS: + xattr_name = POSIX_ACL_XATTR_ACCESS; + break; + case ACL_TYPE_DEFAULT: + xattr_name = POSIX_ACL_XATTR_DEFAULT; + break; + default: + return ERR_PTR(-EINVAL); + } + + size = __hfsplus_getxattr(inode, xattr_name, NULL, 0); + + if (size > 0) { + value = (char *)hfsplus_alloc_attr_entry(); + if (unlikely(!value)) + return ERR_PTR(-ENOMEM); + size = __hfsplus_getxattr(inode, xattr_name, value, size); + } + + if (size > 0) + acl = posix_acl_from_xattr(&init_user_ns, value, size); + else if (size == -ENODATA) + acl = NULL; + else + acl = ERR_PTR(size); + + hfsplus_destroy_attr_entry((hfsplus_attr_entry *)value); + + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); + + return acl; +} + +static int hfsplus_set_posix_acl(struct inode *inode, + int type, + struct posix_acl *acl) +{ + int err; + char *xattr_name; + size_t size = 0; + char *value = NULL; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + switch (type) { + case ACL_TYPE_ACCESS: + xattr_name = POSIX_ACL_XATTR_ACCESS; + if (acl) { + err = posix_acl_equiv_mode(acl, &inode->i_mode); + if (err < 0) + return err; + } + err = 0; + break; + + case ACL_TYPE_DEFAULT: + xattr_name = POSIX_ACL_XATTR_DEFAULT; + if (!S_ISDIR(inode->i_mode)) + return acl ? -EACCES : 0; + break; + + default: + return -EINVAL; + } + + if (acl) { + size = posix_acl_xattr_size(acl->a_count); + if (unlikely(size > HFSPLUS_MAX_INLINE_DATA_SIZE)) + return -ENOMEM; + value = (char *)hfsplus_alloc_attr_entry(); + if (unlikely(!value)) + return -ENOMEM; + err = posix_acl_to_xattr(&init_user_ns, acl, value, size); + if (unlikely(err < 0)) + goto end_set_acl; + } + + err = __hfsplus_setxattr(inode, xattr_name, value, size, 0); + +end_set_acl: + hfsplus_destroy_attr_entry((hfsplus_attr_entry *)value); + + if (!err) + set_cached_acl(inode, type, acl); + + return err; +} + +int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) +{ + int err = 0; + struct posix_acl *acl = NULL; + + hfs_dbg(ACL_MOD, + "[%s]: ino %lu, dir->ino %lu\n", + __func__, inode->i_ino, dir->i_ino); + + if (S_ISLNK(inode->i_mode)) + return 0; + + acl = hfsplus_get_posix_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(acl)) + return PTR_ERR(acl); + + if (acl) { + if (S_ISDIR(inode->i_mode)) { + err = hfsplus_set_posix_acl(inode, + ACL_TYPE_DEFAULT, + acl); + if (unlikely(err)) + goto init_acl_cleanup; + } + + err = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode); + if (unlikely(err < 0)) + return err; + + if (err > 0) + err = hfsplus_set_posix_acl(inode, + ACL_TYPE_ACCESS, + acl); + } else + inode->i_mode &= ~current_umask(); + +init_acl_cleanup: + posix_acl_release(acl); + return err; +} + +int hfsplus_posix_acl_chmod(struct inode *inode) +{ + int err; + struct posix_acl *acl; + + hfs_dbg(ACL_MOD, "[%s]: ino %lu\n", __func__, inode->i_ino); + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + acl = hfsplus_get_posix_acl(inode, ACL_TYPE_ACCESS); + if (IS_ERR(acl) || !acl) + return PTR_ERR(acl); + + err = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); + if (unlikely(err)) + return err; + + err = hfsplus_set_posix_acl(inode, ACL_TYPE_ACCESS, acl); + posix_acl_release(acl); + return err; +} + +static int hfsplus_xattr_get_posix_acl(struct dentry *dentry, + const char *name, + void *buffer, + size_t size, + int type) +{ + int err = 0; + struct posix_acl *acl; + + hfs_dbg(ACL_MOD, + "[%s]: ino %lu, buffer %p, size %zu, type %#x\n", + __func__, dentry->d_inode->i_ino, buffer, size, type); + + if (strcmp(name, "") != 0) + return -EINVAL; + + acl = hfsplus_get_posix_acl(dentry->d_inode, type); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl == NULL) + return -ENODATA; + + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); + posix_acl_release(acl); + + return err; +} + +static int hfsplus_xattr_set_posix_acl(struct dentry *dentry, + const char *name, + const void *value, + size_t size, + int flags, + int type) +{ + int err = 0; + struct inode *inode = dentry->d_inode; + struct posix_acl *acl = NULL; + + hfs_dbg(ACL_MOD, + "[%s]: ino %lu, value %p, size %zu, flags %#x, type %#x\n", + __func__, inode->i_ino, value, size, flags, type); + + if (strcmp(name, "") != 0) + return -EINVAL; + + if (!inode_owner_or_capable(inode)) + return -EPERM; + + if (value) { + acl = posix_acl_from_xattr(&init_user_ns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + else if (acl) { + err = posix_acl_valid(acl); + if (err) + goto end_xattr_set_acl; + } + } + + err = hfsplus_set_posix_acl(inode, type, acl); + +end_xattr_set_acl: + posix_acl_release(acl); + return err; +} + +static size_t hfsplus_xattr_list_posix_acl(struct dentry *dentry, + char *list, + size_t list_size, + const char *name, + size_t name_len, + int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_acl_access_handler = { + .prefix = POSIX_ACL_XATTR_ACCESS, + .flags = ACL_TYPE_ACCESS, + .list = hfsplus_xattr_list_posix_acl, + .get = hfsplus_xattr_get_posix_acl, + .set = hfsplus_xattr_set_posix_acl, +}; + +const struct xattr_handler hfsplus_xattr_acl_default_handler = { + .prefix = POSIX_ACL_XATTR_DEFAULT, + .flags = ACL_TYPE_DEFAULT, + .list = hfsplus_xattr_list_posix_acl, + .get = hfsplus_xattr_get_posix_acl, + .set = hfsplus_xattr_set_posix_acl, +}; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index f6634615..bd8471f 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -8,11 +8,16 @@ #include "hfsplus_fs.h" #include "xattr.h" +#include "acl.h" const struct xattr_handler *hfsplus_xattr_handlers[] = { &hfsplus_xattr_osx_handler, &hfsplus_xattr_user_handler, &hfsplus_xattr_trusted_handler, +#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL + &hfsplus_xattr_acl_access_handler, + &hfsplus_xattr_acl_default_handler, +#endif &hfsplus_xattr_security_handler, NULL }; @@ -46,11 +51,58 @@ static inline int is_known_namespace(const char *name) return true; } +static int can_set_system_xattr(struct inode *inode, const char *name, + const void *value, size_t size) +{ +#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL + struct posix_acl *acl; + int err; + + if (!inode_owner_or_capable(inode)) + return -EPERM; + + /* + * POSIX_ACL_XATTR_ACCESS is tied to i_mode + */ + if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0) { + acl = posix_acl_from_xattr(&init_user_ns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl) { + err = posix_acl_equiv_mode(acl, &inode->i_mode); + posix_acl_release(acl); + if (err < 0) + return err; + mark_inode_dirty(inode); + } + /* + * We're changing the ACL. Get rid of the cached one + */ + forget_cached_acl(inode, ACL_TYPE_ACCESS); + + return 0; + } else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0) { + acl = posix_acl_from_xattr(&init_user_ns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + posix_acl_release(acl); + + /* + * We're changing the default ACL. Get rid of the cached one + */ + forget_cached_acl(inode, ACL_TYPE_DEFAULT); + + return 0; + } +#endif /* CONFIG_HFSPLUS_FS_POSIX_ACL */ + return -EOPNOTSUPP; +} + static int can_set_xattr(struct inode *inode, const char *name, const void *value, size_t value_len) { if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return -EOPNOTSUPP; /* TODO: implement ACL support */ + return can_set_system_xattr(inode, name, value, value_len); if (!strncmp(name, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN)) { /* @@ -253,11 +305,10 @@ static int copy_name(char *buffer, const char *xattr_name, int name_len) return len; } -static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry, +static ssize_t hfsplus_getxattr_finder_info(struct inode *inode, void *value, size_t size) { ssize_t res = 0; - struct inode *inode = dentry->d_inode; struct hfs_find_data fd; u16 entry_type; u16 folder_rec_len = sizeof(struct DInfo) + sizeof(struct DXInfo); @@ -304,10 +355,9 @@ end_getxattr_finder_info: return res; } -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, +ssize_t __hfsplus_getxattr(struct inode *inode, const char *name, void *value, size_t size) { - struct inode *inode = dentry->d_inode; struct hfs_find_data fd; hfsplus_attr_entry *entry; __be32 xattr_record_type; @@ -333,7 +383,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, } if (!strcmp_xattr_finder_info(name)) - return hfsplus_getxattr_finder_info(dentry, value, size); + return hfsplus_getxattr_finder_info(inode, value, size); if (!HFSPLUS_SB(inode->i_sb)->attr_tree) return -EOPNOTSUPP; diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h index 847b695..841b569 100644 --- a/fs/hfsplus/xattr.h +++ b/fs/hfsplus/xattr.h @@ -14,8 +14,8 @@ extern const struct xattr_handler hfsplus_xattr_osx_handler; extern const struct xattr_handler hfsplus_xattr_user_handler; extern const struct xattr_handler hfsplus_xattr_trusted_handler; -/*extern const struct xattr_handler hfsplus_xattr_acl_access_handler;*/ -/*extern const struct xattr_handler hfsplus_xattr_acl_default_handler;*/ +extern const struct xattr_handler hfsplus_xattr_acl_access_handler; +extern const struct xattr_handler hfsplus_xattr_acl_default_handler; extern const struct xattr_handler hfsplus_xattr_security_handler; extern const struct xattr_handler *hfsplus_xattr_handlers[]; @@ -29,9 +29,17 @@ static inline int hfsplus_setxattr(struct dentry *dentry, const char *name, return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags); } -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, +ssize_t __hfsplus_getxattr(struct inode *inode, const char *name, void *value, size_t size); +static inline ssize_t hfsplus_getxattr(struct dentry *dentry, + const char *name, + void *value, + size_t size) +{ + return __hfsplus_getxattr(dentry->d_inode, name, value, size); +} + ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); int hfsplus_removexattr(struct dentry *dentry, const char *name); @@ -39,22 +47,7 @@ int hfsplus_removexattr(struct dentry *dentry, const char *name); int hfsplus_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr); -static inline int hfsplus_init_acl(struct inode *inode, struct inode *dir) -{ - /*TODO: implement*/ - return 0; -} - -static inline int hfsplus_init_inode_security(struct inode *inode, - struct inode *dir, - const struct qstr *qstr) -{ - int err; - - err = hfsplus_init_acl(inode, dir); - if (!err) - err = hfsplus_init_security(inode, dir, qstr); - return err; -} +int hfsplus_init_inode_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr); #endif diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c index 83b842f..0072276 100644 --- a/fs/hfsplus/xattr_security.c +++ b/fs/hfsplus/xattr_security.c @@ -9,6 +9,7 @@ #include <linux/security.h> #include "hfsplus_fs.h" #include "xattr.h" +#include "acl.h" static int hfsplus_security_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size, int type) @@ -96,6 +97,18 @@ int hfsplus_init_security(struct inode *inode, struct inode *dir, &hfsplus_initxattrs, NULL); } +int hfsplus_init_inode_security(struct inode *inode, + struct inode *dir, + const struct qstr *qstr) +{ + int err; + + err = hfsplus_init_posix_acl(inode, dir); + if (!err) + err = hfsplus_init_security(inode, dir, qstr); + return err; +} + const struct xattr_handler hfsplus_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .list = hfsplus_security_listxattr, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index cddb052..2543728 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -361,6 +361,13 @@ retry: return 0; } +static int hostfs_file_release(struct inode *inode, struct file *file) +{ + filemap_write_and_wait(inode->i_mapping); + + return 0; +} + int hostfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; @@ -386,7 +393,7 @@ static const struct file_operations hostfs_file_fops = { .write = do_sync_write, .mmap = generic_file_mmap, .open = hostfs_file_open, - .release = NULL, + .release = hostfs_file_release, .fsync = hostfs_fsync, }; diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 4e9dabc..67c1a61 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -138,7 +138,7 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to) hpfs_lock(inode->i_sb); if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); hpfs_truncate(inode); } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a3f868a..d19b30a 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -463,6 +463,14 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, return inode; } +/* + * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never + * be taken from reclaim -- unlike regular filesystems. This needs an + * annotation because huge_pmd_share() does an allocation under + * i_mmap_mutex. + */ +struct lock_class_key hugetlbfs_i_mmap_mutex_key; + static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev) @@ -474,6 +482,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct hugetlbfs_inode_info *info; inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); + lockdep_set_class(&inode->i_mapping->i_mmap_mutex, + &hugetlbfs_i_mmap_mutex_key); inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -916,14 +926,8 @@ static int get_hstate_idx(int page_size_log) return h - hstates; } -static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen) -{ - return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)", - dentry->d_name.name); -} - static struct dentry_operations anon_ops = { - .d_dname = hugetlb_dname + .d_dname = simple_dname }; /* @@ -17,6 +17,7 @@ #include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> +#include <linux/list_lru.h> #include "internal.h" /* @@ -24,7 +25,7 @@ * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget() - * inode->i_sb->s_inode_lru_lock protects: + * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode_sb_list_lock protects: * sb->s_inodes, inode->i_sb_list @@ -37,7 +38,7 @@ * * inode_sb_list_lock * inode->i_lock - * inode->i_sb->s_inode_lru_lock + * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock @@ -70,33 +71,33 @@ EXPORT_SYMBOL(empty_aops); */ struct inodes_stat_t inodes_stat; -static DEFINE_PER_CPU(unsigned int, nr_inodes); -static DEFINE_PER_CPU(unsigned int, nr_unused); +static DEFINE_PER_CPU(unsigned long, nr_inodes); +static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __read_mostly; -static int get_nr_inodes(void) +static long get_nr_inodes(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } -static inline int get_nr_inodes_unused(void) +static inline long get_nr_inodes_unused(void) { int i; - int sum = 0; + long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } -int get_nr_dirty_inodes(void) +long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ - int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } @@ -109,7 +110,7 @@ int proc_nr_inodes(ctl_table *table, int write, { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -401,13 +402,8 @@ EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_lru_lock); - if (list_empty(&inode->i_lru)) { - list_add(&inode->i_lru, &inode->i_sb->s_inode_lru); - inode->i_sb->s_nr_inodes_unused++; + if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); - } - spin_unlock(&inode->i_sb->s_inode_lru_lock); } /* @@ -425,13 +421,9 @@ void inode_add_lru(struct inode *inode) static void inode_lru_list_del(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_lru_lock); - if (!list_empty(&inode->i_lru)) { - list_del_init(&inode->i_lru); - inode->i_sb->s_nr_inodes_unused--; + + if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); - } - spin_unlock(&inode->i_sb->s_inode_lru_lock); } /** @@ -675,24 +667,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) return busy; } -static int can_unuse(struct inode *inode) -{ - if (inode->i_state & ~I_REFERENCED) - return 0; - if (inode_has_buffers(inode)) - return 0; - if (atomic_read(&inode->i_count)) - return 0; - if (inode->i_data.nrpages) - return 0; - return 1; -} - /* - * Walk the superblock inode LRU for freeable inodes and attempt to free them. - * This is called from the superblock shrinker function with a number of inodes - * to trim from the LRU. Inodes to be freed are moved to a temporary list and - * then are freed outside inode_lock by dispose_list(). + * Isolate the inode from the LRU in preparation for freeing it. * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. If the inode has metadata buffers attached to @@ -706,89 +682,82 @@ static int can_unuse(struct inode *inode) * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ -void prune_icache_sb(struct super_block *sb, int nr_to_scan) +static enum lru_status +inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg) { - LIST_HEAD(freeable); - int nr_scanned; - unsigned long reap = 0; + struct list_head *freeable = arg; + struct inode *inode = container_of(item, struct inode, i_lru); - spin_lock(&sb->s_inode_lru_lock); - for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) { - struct inode *inode; + /* + * we are inverting the lru lock/inode->i_lock here, so use a trylock. + * If we fail to get the lock, just skip it. + */ + if (!spin_trylock(&inode->i_lock)) + return LRU_SKIP; - if (list_empty(&sb->s_inode_lru)) - break; + /* + * Referenced or dirty inodes are still in use. Give them another pass + * through the LRU as we canot reclaim them now. + */ + if (atomic_read(&inode->i_count) || + (inode->i_state & ~I_REFERENCED)) { + list_del_init(&inode->i_lru); + spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; + } - inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru); + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { + inode->i_state &= ~I_REFERENCED; + spin_unlock(&inode->i_lock); + return LRU_ROTATE; + } - /* - * we are inverting the sb->s_inode_lru_lock/inode->i_lock here, - * so use a trylock. If we fail to get the lock, just move the - * inode to the back of the list so we don't spin on it. - */ - if (!spin_trylock(&inode->i_lock)) { - list_move(&inode->i_lru, &sb->s_inode_lru); - continue; + if (inode_has_buffers(inode) || inode->i_data.nrpages) { + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(lru_lock); + if (remove_inode_buffers(inode)) { + unsigned long reap; + reap = invalidate_mapping_pages(&inode->i_data, 0, -1); + if (current_is_kswapd()) + __count_vm_events(KSWAPD_INODESTEAL, reap); + else + __count_vm_events(PGINODESTEAL, reap); + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += reap; } + iput(inode); + spin_lock(lru_lock); + return LRU_RETRY; + } - /* - * Referenced or dirty inodes are still in use. Give them - * another pass through the LRU as we canot reclaim them now. - */ - if (atomic_read(&inode->i_count) || - (inode->i_state & ~I_REFERENCED)) { - list_del_init(&inode->i_lru); - spin_unlock(&inode->i_lock); - sb->s_nr_inodes_unused--; - this_cpu_dec(nr_unused); - continue; - } + WARN_ON(inode->i_state & I_NEW); + inode->i_state |= I_FREEING; + list_move(&inode->i_lru, freeable); + spin_unlock(&inode->i_lock); - /* recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { - inode->i_state &= ~I_REFERENCED; - list_move(&inode->i_lru, &sb->s_inode_lru); - spin_unlock(&inode->i_lock); - continue; - } - if (inode_has_buffers(inode) || inode->i_data.nrpages) { - __iget(inode); - spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_lru_lock); - if (remove_inode_buffers(inode)) - reap += invalidate_mapping_pages(&inode->i_data, - 0, -1); - iput(inode); - spin_lock(&sb->s_inode_lru_lock); - - if (inode != list_entry(sb->s_inode_lru.next, - struct inode, i_lru)) - continue; /* wrong inode or list_empty */ - /* avoid lock inversions with trylock */ - if (!spin_trylock(&inode->i_lock)) - continue; - if (!can_unuse(inode)) { - spin_unlock(&inode->i_lock); - continue; - } - } - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; - spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; +} - list_move(&inode->i_lru, &freeable); - sb->s_nr_inodes_unused--; - this_cpu_dec(nr_unused); - } - if (current_is_kswapd()) - __count_vm_events(KSWAPD_INODESTEAL, reap); - else - __count_vm_events(PGINODESTEAL, reap); - spin_unlock(&sb->s_inode_lru_lock); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += reap; +/* + * Walk the superblock inode LRU for freeable inodes and attempt to free them. + * This is called from the superblock shrinker function with a number of inodes + * to trim from the LRU. Inodes to be freed are moved to a temporary list and + * then are freed outside inode_lock by dispose_list(). + */ +long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid) +{ + LIST_HEAD(freeable); + long freed; + freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate, + &freeable, &nr_to_scan); dispose_list(&freeable); + return freed; } static void __wait_on_freeing_inode(struct inode *inode); @@ -1525,7 +1494,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags) * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ -void touch_atime(struct path *path) +void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = path->dentry->d_inode; diff --git a/fs/internal.h b/fs/internal.h index 7c5f01c..513e0d8 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -45,6 +45,9 @@ extern void __init chrdev_init(void); * namei.c */ extern int __inode_permission(struct inode *, int); +extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); +extern int vfs_path_lookup(struct dentry *, struct vfsmount *, + const char *, unsigned int, struct path *); /* * namespace.c @@ -111,6 +114,8 @@ extern int open_check_o_direct(struct file *f); * inode.c */ extern spinlock_t inode_sb_list_lock; +extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid); extern void inode_add_lru(struct inode *inode); /* @@ -118,7 +123,7 @@ extern void inode_add_lru(struct inode *inode); */ extern void inode_wb_list_del(struct inode *inode); -extern int get_nr_dirty_inodes(void); +extern long get_nr_dirty_inodes(void); extern void evict_inodes(struct super_block *); extern int invalidate_inodes(struct super_block *, bool); @@ -126,6 +131,9 @@ extern int invalidate_inodes(struct super_block *, bool); * dcache.c */ extern struct dentry *__d_alloc(struct super_block *, const struct qstr *); +extern int d_set_mounted(struct dentry *dentry); +extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid); /* * read_write.c diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index c348d6d..e5d408a 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -117,8 +117,8 @@ static void destroy_inodecache(void) static int isofs_remount(struct super_block *sb, int *flags, char *data) { - /* we probably want a lot more here */ - *flags |= MS_RDONLY; + if (!(*flags & MS_RDONLY)) + return -EROFS; return 0; } @@ -763,15 +763,6 @@ root_found: */ s->s_maxbytes = 0x80000000000LL; - /* - * The CDROM is read-only, has no nodes (devices) on it, and since - * all of the files appear to be owned by root, we really do not want - * to allow suid. (suid or devices will not show up unless we have - * Rock Ridge extensions) - */ - - s->s_flags |= MS_RDONLY /* | MS_NODEV | MS_NOSUID */; - /* Set this for reference. Its not currently used except on write which we don't have .. */ @@ -1530,6 +1521,9 @@ struct inode *isofs_iget(struct super_block *sb, static struct dentry *isofs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { + /* We don't support read-write mounts */ + if (!(flags & MS_RDONLY)) + return ERR_PTR(-EACCES); return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super); } diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 11bb11f..bb217dc 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -340,13 +340,13 @@ void journal_commit_transaction(journal_t *journal) J_ASSERT(journal->j_committing_transaction == NULL); commit_transaction = journal->j_running_transaction; - J_ASSERT(commit_transaction->t_state == T_RUNNING); trace_jbd_start_commit(journal, commit_transaction); jbd_debug(1, "JBD: starting commit of transaction %d\n", commit_transaction->t_tid); spin_lock(&journal->j_state_lock); + J_ASSERT(commit_transaction->t_state == T_RUNNING); commit_transaction->t_state = T_LOCKED; trace_jbd_commit_locking(journal, commit_transaction); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 6510d63..2d04f9a 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -90,6 +90,24 @@ static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); static const char *journal_dev_name(journal_t *journal, char *buffer); +#ifdef CONFIG_JBD_DEBUG +void __jbd_debug(int level, const char *file, const char *func, + unsigned int line, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + if (level > journal_enable_debug) + return; + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf); + va_end(args); +} +EXPORT_SYMBOL(__jbd_debug); +#endif + /* * Helper function used to manage commit timeouts */ diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 559bec1..cf2fc05 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -343,14 +343,14 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, struct page *page = bh->b_page; __u8 *addr; __u32 csum32; + __be32 seq; if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return; - sequence = cpu_to_be32(sequence); + seq = cpu_to_be32(sequence); addr = kmap_atomic(page); - csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence, - sizeof(sequence)); + csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(j, csum32, addr + offset_in_page(bh->b_data), bh->b_size); kunmap_atomic(addr); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 02c7ad9..5203264 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -130,9 +130,10 @@ int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; } -static __u32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) +static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) { - __u32 csum, old_csum; + __u32 csum; + __be32 old_csum; old_csum = sb->s_checksum; sb->s_checksum = 0; diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index d4851464..3929c50 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -178,7 +178,8 @@ static int jbd2_descr_block_csum_verify(journal_t *j, void *buf) { struct jbd2_journal_block_tail *tail; - __u32 provided, calculated; + __be32 provided; + __u32 calculated; if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return 1; @@ -190,8 +191,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j, calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); tail->t_checksum = provided; - provided = be32_to_cpu(provided); - return provided == calculated; + return provided == cpu_to_be32(calculated); } /* @@ -381,7 +381,8 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh, static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) { struct commit_header *h; - __u32 provided, calculated; + __be32 provided; + __u32 calculated; if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return 1; @@ -392,21 +393,20 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); h->h_chksum[0] = provided; - provided = be32_to_cpu(provided); - return provided == calculated; + return provided == cpu_to_be32(calculated); } static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, void *buf, __u32 sequence) { __u32 csum32; + __be32 seq; if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return 1; - sequence = cpu_to_be32(sequence); - csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence, - sizeof(sequence)); + seq = cpu_to_be32(sequence); + csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize); return tag->t_checksum == cpu_to_be16(csum32); @@ -808,7 +808,8 @@ static int jbd2_revoke_block_csum_verify(journal_t *j, void *buf) { struct jbd2_journal_revoke_tail *tail; - __u32 provided, calculated; + __be32 provided; + __u32 calculated; if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return 1; @@ -820,8 +821,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j, calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); tail->r_checksum = provided; - provided = be32_to_cpu(provided); - return provided == calculated; + return provided == cpu_to_be32(calculated); } /* Scan a revoke record, marking all blocks mentioned as revoked. */ diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 730f24e..f4aab71 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -306,7 +306,7 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); jfs_truncate(inode); } } diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 8743ba9..984c2bb 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -3047,6 +3047,14 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) dir_index = (u32) ctx->pos; + /* + * NFSv4 reserves cookies 1 and 2 for . and .. so the value + * we return to the vfs is one greater than the one we use + * internally. + */ + if (dir_index) + dir_index--; + if (dir_index > 1) { struct dir_table_slot dirtab_slot; @@ -3086,7 +3094,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) if (p->header.flag & BT_INTERNAL) { jfs_err("jfs_readdir: bad index table"); DT_PUTPAGE(mp); - ctx->pos = -1; + ctx->pos = DIREND; return 0; } } else { @@ -3094,14 +3102,14 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) /* * self "." */ - ctx->pos = 0; + ctx->pos = 1; if (!dir_emit(ctx, ".", 1, ip->i_ino, DT_DIR)) return 0; } /* * parent ".." */ - ctx->pos = 1; + ctx->pos = 2; if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR)) return 0; @@ -3122,22 +3130,23 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) /* * Legacy filesystem - OS/2 & Linux JFS < 0.3.6 * - * pn = index = 0: First entry "." - * pn = 0; index = 1: Second entry ".." + * pn = 0; index = 1: First entry "." + * pn = 0; index = 2: Second entry ".." * pn > 0: Real entries, pn=1 -> leftmost page * pn = index = -1: No more entries */ dtpos = ctx->pos; - if (dtpos == 0) { + if (dtpos < 2) { /* build "." entry */ + ctx->pos = 1; if (!dir_emit(ctx, ".", 1, ip->i_ino, DT_DIR)) return 0; - dtoffset->index = 1; + dtoffset->index = 2; ctx->pos = dtpos; } if (dtoffset->pn == 0) { - if (dtoffset->index == 1) { + if (dtoffset->index == 2) { /* build ".." entry */ if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR)) return 0; @@ -3228,6 +3237,12 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) } jfs_dirent->position = unique_pos++; } + /* + * We add 1 to the index because we may + * use a value of 2 internally, and NFSv4 + * doesn't like that. + */ + jfs_dirent->position++; } else { jfs_dirent->position = dtpos; len = min(d_namleft, DTLHDRDATALEN_LEGACY); diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 01bfe766..41e491b 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -64,12 +64,17 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init) nlm_init->protocol, nlm_version, nlm_init->hostname, nlm_init->noresvport, nlm_init->net); - if (host == NULL) { - lockd_down(nlm_init->net); - return ERR_PTR(-ENOLCK); - } + if (host == NULL) + goto out_nohost; + if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL) + goto out_nobind; return host; +out_nobind: + nlmclnt_release_host(host); +out_nohost: + lockd_down(nlm_init->net); + return ERR_PTR(-ENOLCK); } EXPORT_SYMBOL_GPL(nlmclnt_init); diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 9760ecb..acd3947 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -125,14 +125,15 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl) { struct nlm_args *argp = &req->a_args; struct nlm_lock *lock = &argp->lock; + char *nodename = req->a_host->h_rpcclnt->cl_nodename; nlmclnt_next_cookie(&argp->cookie); memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh)); - lock->caller = utsname()->nodename; + lock->caller = nodename; lock->oh.data = req->a_owner; lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s", (unsigned int)fl->fl_u.nfs_fl.owner->pid, - utsname()->nodename); + nodename); lock->svid = fl->fl_u.nfs_fl.owner->pid; lock->fl.fl_start = fl->fl_start; lock->fl.fl_end = fl->fl_end; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 067778b..e066a39 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -951,6 +951,7 @@ nlmsvc_retry_blocked(void) unsigned long timeout = MAX_SCHEDULE_TIMEOUT; struct nlm_block *block; + spin_lock(&nlm_blocked_lock); while (!list_empty(&nlm_blocked) && !kthread_should_stop()) { block = list_entry(nlm_blocked.next, struct nlm_block, b_list); @@ -960,6 +961,7 @@ nlmsvc_retry_blocked(void) timeout = block->b_when - jiffies; break; } + spin_unlock(&nlm_blocked_lock); dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n", block, block->b_when); @@ -969,7 +971,9 @@ nlmsvc_retry_blocked(void) retry_deferred_block(block); } else nlmsvc_grant_blocked(block); + spin_lock(&nlm_blocked_lock); } + spin_unlock(&nlm_blocked_lock); return timeout; } diff --git a/fs/mbcache.c b/fs/mbcache.c index 8c32ef3..e519e45 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -86,18 +86,6 @@ static LIST_HEAD(mb_cache_list); static LIST_HEAD(mb_cache_lru_list); static DEFINE_SPINLOCK(mb_cache_spinlock); -/* - * What the mbcache registers as to get shrunk dynamically. - */ - -static int mb_cache_shrink_fn(struct shrinker *shrink, - struct shrink_control *sc); - -static struct shrinker mb_cache_shrinker = { - .shrink = mb_cache_shrink_fn, - .seeks = DEFAULT_SEEKS, -}; - static inline int __mb_cache_entry_is_hashed(struct mb_cache_entry *ce) { @@ -151,7 +139,7 @@ forget: /* - * mb_cache_shrink_fn() memory pressure callback + * mb_cache_shrink_scan() memory pressure callback * * This function is called by the kernel memory management when memory * gets low. @@ -159,17 +147,16 @@ forget: * @shrink: (ignored) * @sc: shrink_control passed from reclaim * - * Returns the number of objects which are present in the cache. + * Returns the number of objects freed. */ -static int -mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +mb_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(free_list); - struct mb_cache *cache; struct mb_cache_entry *entry, *tmp; - int count = 0; int nr_to_scan = sc->nr_to_scan; gfp_t gfp_mask = sc->gfp_mask; + unsigned long freed = 0; mb_debug("trying to free %d entries", nr_to_scan); spin_lock(&mb_cache_spinlock); @@ -179,19 +166,37 @@ mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc) struct mb_cache_entry, e_lru_list); list_move_tail(&ce->e_lru_list, &free_list); __mb_cache_entry_unhash(ce); + freed++; + } + spin_unlock(&mb_cache_spinlock); + list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) { + __mb_cache_entry_forget(entry, gfp_mask); } + return freed; +} + +static unsigned long +mb_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct mb_cache *cache; + unsigned long count = 0; + + spin_lock(&mb_cache_spinlock); list_for_each_entry(cache, &mb_cache_list, c_cache_list) { mb_debug("cache %s (%d)", cache->c_name, atomic_read(&cache->c_entry_count)); count += atomic_read(&cache->c_entry_count); } spin_unlock(&mb_cache_spinlock); - list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) { - __mb_cache_entry_forget(entry, gfp_mask); - } - return (count / 100) * sysctl_vfs_cache_pressure; + + return vfs_pressure_ratio(count); } +static struct shrinker mb_cache_shrinker = { + .count_objects = mb_cache_shrink_count, + .scan_objects = mb_cache_shrink_scan, + .seeks = DEFAULT_SEEKS, +}; /* * mb_cache_create() create a new cache diff --git a/fs/minix/inode.c b/fs/minix/inode.c index df12249..0332109 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -400,7 +400,7 @@ static void minix_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); minix_truncate(inode); } } @@ -508,56 +508,78 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) { struct fs_struct *fs = current->fs; struct dentry *parent = nd->path.dentry; - int want_root = 0; BUG_ON(!(nd->flags & LOOKUP_RCU)); - if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) { - want_root = 1; - spin_lock(&fs->lock); - if (nd->root.mnt != fs->root.mnt || - nd->root.dentry != fs->root.dentry) - goto err_root; - } - spin_lock(&parent->d_lock); + + /* + * Get a reference to the parent first: we're + * going to make "path_put(nd->path)" valid in + * non-RCU context for "terminate_walk()". + * + * If this doesn't work, return immediately with + * RCU walking still active (and then we will do + * the RCU walk cleanup in terminate_walk()). + */ + if (!lockref_get_not_dead(&parent->d_lockref)) + return -ECHILD; + + /* + * After the mntget(), we terminate_walk() will do + * the right thing for non-RCU mode, and all our + * subsequent exit cases should unlock_rcu_walk() + * before returning. + */ + mntget(nd->path.mnt); + nd->flags &= ~LOOKUP_RCU; + + /* + * For a negative lookup, the lookup sequence point is the parents + * sequence point, and it only needs to revalidate the parent dentry. + * + * For a positive lookup, we need to move both the parent and the + * dentry from the RCU domain to be properly refcounted. And the + * sequence number in the dentry validates *both* dentry counters, + * since we checked the sequence number of the parent after we got + * the child sequence number. So we know the parent must still + * be valid if the child sequence number is still valid. + */ if (!dentry) { - if (!__d_rcu_to_refcount(parent, nd->seq)) - goto err_parent; + if (read_seqcount_retry(&parent->d_seq, nd->seq)) + goto out; BUG_ON(nd->inode != parent->d_inode); } else { - if (dentry->d_parent != parent) - goto err_parent; - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - if (!__d_rcu_to_refcount(dentry, nd->seq)) - goto err_child; - /* - * If the sequence check on the child dentry passed, then - * the child has not been removed from its parent. This - * means the parent dentry must be valid and able to take - * a reference at this point. - */ - BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent); - BUG_ON(!parent->d_count); - parent->d_count++; - spin_unlock(&dentry->d_lock); + if (!lockref_get_not_dead(&dentry->d_lockref)) + goto out; + if (read_seqcount_retry(&dentry->d_seq, nd->seq)) + goto drop_dentry; } - spin_unlock(&parent->d_lock); - if (want_root) { + + /* + * Sequence counts matched. Now make sure that the root is + * still valid and get it if required. + */ + if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) { + spin_lock(&fs->lock); + if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry) + goto unlock_and_drop_dentry; path_get(&nd->root); spin_unlock(&fs->lock); } - mntget(nd->path.mnt); unlock_rcu_walk(); - nd->flags &= ~LOOKUP_RCU; return 0; -err_child: - spin_unlock(&dentry->d_lock); -err_parent: - spin_unlock(&parent->d_lock); -err_root: - if (want_root) - spin_unlock(&fs->lock); +unlock_and_drop_dentry: + spin_unlock(&fs->lock); +drop_dentry: + unlock_rcu_walk(); + dput(dentry); + goto drop_root_mnt; +out: + unlock_rcu_walk(); +drop_root_mnt: + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; return -ECHILD; } @@ -585,14 +607,16 @@ static int complete_walk(struct nameidata *nd) nd->flags &= ~LOOKUP_RCU; if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - spin_lock(&dentry->d_lock); - if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) { - spin_unlock(&dentry->d_lock); + + if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) { unlock_rcu_walk(); return -ECHILD; } - BUG_ON(nd->inode != dentry->d_inode); - spin_unlock(&dentry->d_lock); + if (read_seqcount_retry(&dentry->d_seq, nd->seq)) { + unlock_rcu_walk(); + dput(dentry); + return -ECHILD; + } mntget(nd->path.mnt); unlock_rcu_walk(); } @@ -636,29 +660,6 @@ static __always_inline void set_root_rcu(struct nameidata *nd) } } -static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link) -{ - int ret; - - if (IS_ERR(link)) - goto fail; - - if (*link == '/') { - set_root(nd); - path_put(&nd->path); - nd->path = nd->root; - path_get(&nd->root); - nd->flags |= LOOKUP_JUMPED; - } - nd->inode = nd->path.dentry->d_inode; - - ret = link_path_walk(link, nd); - return ret; -fail: - path_put(&nd->path); - return PTR_ERR(link); -} - static void path_put_conditional(struct path *path, struct nameidata *nd) { dput(path->dentry); @@ -850,7 +851,20 @@ follow_link(struct path *link, struct nameidata *nd, void **p) error = 0; s = nd_get_link(nd); if (s) { - error = __vfs_follow_link(nd, s); + if (unlikely(IS_ERR(s))) { + path_put(&nd->path); + put_link(nd, link, *p); + return PTR_ERR(s); + } + if (*s == '/') { + set_root(nd); + path_put(&nd->path); + nd->path = nd->root; + path_get(&nd->root); + nd->flags |= LOOKUP_JUMPED; + } + nd->inode = nd->path.dentry->d_inode; + error = link_path_walk(s, nd); if (unlikely(error)) put_link(nd, link, *p); } @@ -2184,6 +2198,197 @@ user_path_parent(int dfd, const char __user *path, struct nameidata *nd, return s; } +/** + * mountpoint_last - look up last component for umount + * @nd: pathwalk nameidata - currently pointing at parent directory of "last" + * @path: pointer to container for result + * + * This is a special lookup_last function just for umount. In this case, we + * need to resolve the path without doing any revalidation. + * + * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since + * mountpoints are always pinned in the dcache, their ancestors are too. Thus, + * in almost all cases, this lookup will be served out of the dcache. The only + * cases where it won't are if nd->last refers to a symlink or the path is + * bogus and it doesn't exist. + * + * Returns: + * -error: if there was an error during lookup. This includes -ENOENT if the + * lookup found a negative dentry. The nd->path reference will also be + * put in this case. + * + * 0: if we successfully resolved nd->path and found it to not to be a + * symlink that needs to be followed. "path" will also be populated. + * The nd->path reference will also be put. + * + * 1: if we successfully resolved nd->last and found it to be a symlink + * that needs to be followed. "path" will be populated with the path + * to the link, and nd->path will *not* be put. + */ +static int +mountpoint_last(struct nameidata *nd, struct path *path) +{ + int error = 0; + struct dentry *dentry; + struct dentry *dir = nd->path.dentry; + + /* If we're in rcuwalk, drop out of it to handle last component */ + if (nd->flags & LOOKUP_RCU) { + if (unlazy_walk(nd, NULL)) { + error = -ECHILD; + goto out; + } + } + + nd->flags &= ~LOOKUP_PARENT; + + if (unlikely(nd->last_type != LAST_NORM)) { + error = handle_dots(nd, nd->last_type); + if (error) + goto out; + dentry = dget(nd->path.dentry); + goto done; + } + + mutex_lock(&dir->d_inode->i_mutex); + dentry = d_lookup(dir, &nd->last); + if (!dentry) { + /* + * No cached dentry. Mounted dentries are pinned in the cache, + * so that means that this dentry is probably a symlink or the + * path doesn't actually point to a mounted dentry. + */ + dentry = d_alloc(dir, &nd->last); + if (!dentry) { + error = -ENOMEM; + mutex_unlock(&dir->d_inode->i_mutex); + goto out; + } + dentry = lookup_real(dir->d_inode, dentry, nd->flags); + error = PTR_ERR(dentry); + if (IS_ERR(dentry)) { + mutex_unlock(&dir->d_inode->i_mutex); + goto out; + } + } + mutex_unlock(&dir->d_inode->i_mutex); + +done: + if (!dentry->d_inode) { + error = -ENOENT; + dput(dentry); + goto out; + } + path->dentry = dentry; + path->mnt = mntget(nd->path.mnt); + if (should_follow_link(dentry->d_inode, nd->flags & LOOKUP_FOLLOW)) + return 1; + follow_mount(path); + error = 0; +out: + terminate_walk(nd); + return error; +} + +/** + * path_mountpoint - look up a path to be umounted + * @dfd: directory file descriptor to start walk from + * @name: full pathname to walk + * @flags: lookup flags + * + * Look up the given name, but don't attempt to revalidate the last component. + * Returns 0 and "path" will be valid on success; Retuns error otherwise. + */ +static int +path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags) +{ + struct file *base = NULL; + struct nameidata nd; + int err; + + err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base); + if (unlikely(err)) + return err; + + current->total_link_count = 0; + err = link_path_walk(name, &nd); + if (err) + goto out; + + err = mountpoint_last(&nd, path); + 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) + break; + err = mountpoint_last(&nd, path); + put_link(&nd, &link, cookie); + } +out: + if (base) + fput(base); + + if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT)) + path_put(&nd.root); + + return err; +} + +static int +filename_mountpoint(int dfd, struct filename *s, struct path *path, + unsigned int flags) +{ + int error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU); + if (unlikely(error == -ECHILD)) + error = path_mountpoint(dfd, s->name, path, flags); + if (unlikely(error == -ESTALE)) + error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL); + if (likely(!error)) + audit_inode(s, path->dentry, 0); + return error; +} + +/** + * user_path_mountpoint_at - lookup a path from userland in order to umount it + * @dfd: directory file descriptor + * @name: pathname from userland + * @flags: lookup flags + * @path: pointer to container to hold result + * + * A umount is a special case for path walking. We're not actually interested + * in the inode in this situation, and ESTALE errors can be a problem. We + * simply want track down the dentry and vfsmount attached at the mountpoint + * and avoid revalidating the last component. + * + * Returns 0 and populates "path" on success. + */ +int +user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags, + struct path *path) +{ + struct filename *s = getname(name); + int error; + if (IS_ERR(s)) + return PTR_ERR(s); + error = filename_mountpoint(dfd, s, path, flags); + putname(s); + return error; +} + +int +kern_path_mountpoint(int dfd, const char *name, struct path *path, + unsigned int flags) +{ + struct filename s = {.name = name}; + return filename_mountpoint(dfd, &s, path, flags); +} +EXPORT_SYMBOL(kern_path_mountpoint); + /* * It's inline, so penalty for filesystems that don't use sticky bit is * minimal. @@ -3327,7 +3532,7 @@ void dentry_unhash(struct dentry *dentry) { shrink_dcache_parent(dentry); spin_lock(&dentry->d_lock); - if (dentry->d_count == 1) + if (dentry->d_lockref.count == 1) __d_drop(dentry); spin_unlock(&dentry->d_lock); } @@ -4024,11 +4229,6 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) return res; } -int vfs_follow_link(struct nameidata *nd, const char *link) -{ - return __vfs_follow_link(nd, link); -} - /* get the link contents into pagecache */ static char *page_getlink(struct dentry * dentry, struct page **ppage) { @@ -4140,7 +4340,6 @@ EXPORT_SYMBOL(vfs_path_lookup); EXPORT_SYMBOL(inode_permission); EXPORT_SYMBOL(unlock_rename); EXPORT_SYMBOL(vfs_create); -EXPORT_SYMBOL(vfs_follow_link); EXPORT_SYMBOL(vfs_link); EXPORT_SYMBOL(vfs_mkdir); EXPORT_SYMBOL(vfs_mknod); diff --git a/fs/namespace.c b/fs/namespace.c index 7b1ca9b..da5c494 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -17,7 +17,7 @@ #include <linux/security.h> #include <linux/idr.h> #include <linux/acct.h> /* acct_auto_close_mnt */ -#include <linux/ramfs.h> /* init_rootfs */ +#include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/uaccess.h> @@ -611,6 +611,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry) { struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry); struct mountpoint *mp; + int ret; list_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { @@ -626,14 +627,12 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry) if (!mp) return ERR_PTR(-ENOMEM); - spin_lock(&dentry->d_lock); - if (d_unlinked(dentry)) { - spin_unlock(&dentry->d_lock); + ret = d_set_mounted(dentry); + if (ret) { kfree(mp); - return ERR_PTR(-ENOENT); + return ERR_PTR(ret); } - dentry->d_flags |= DCACHE_MOUNTED; - spin_unlock(&dentry->d_lock); + mp->m_dentry = dentry; mp->m_count = 1; list_add(&mp->m_hash, chain); @@ -831,6 +830,10 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY)) mnt->mnt.mnt_flags |= MNT_LOCK_READONLY; + /* Don't allow unprivileged users to reveal what is under a mount */ + if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire)) + mnt->mnt.mnt_flags |= MNT_LOCKED; + atomic_inc(&sb->s_active); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); @@ -1318,7 +1321,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; - retval = user_path_at(AT_FDCWD, name, lookup_flags, &path); + retval = user_path_mountpoint_at(AT_FDCWD, name, lookup_flags, &path); if (retval) goto out; mnt = real_mount(path.mnt); @@ -1327,6 +1330,8 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto dput_and_out; retval = do_umount(mnt, flags); dput_and_out: @@ -1349,14 +1354,11 @@ SYSCALL_DEFINE1(oldumount, char __user *, name) #endif -static bool mnt_ns_loop(struct path *path) +static bool is_mnt_ns_file(struct dentry *dentry) { - /* Could bind mounting the mount namespace inode cause a - * mount namespace loop? - */ - struct inode *inode = path->dentry->d_inode; + /* Is this a proxy for a mount namespace? */ + struct inode *inode = dentry->d_inode; struct proc_ns *ei; - struct mnt_namespace *mnt_ns; if (!proc_ns_inode(inode)) return false; @@ -1365,7 +1367,19 @@ static bool mnt_ns_loop(struct path *path) if (ei->ns_ops != &mntns_operations) return false; - mnt_ns = ei->ns; + return true; +} + +static bool mnt_ns_loop(struct dentry *dentry) +{ + /* Could bind mounting the mount namespace inode cause a + * mount namespace loop? + */ + struct mnt_namespace *mnt_ns; + if (!is_mnt_ns_file(dentry)) + return false; + + mnt_ns = get_proc_ns(dentry->d_inode)->ns; return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } @@ -1374,13 +1388,17 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, { struct mount *res, *p, *q, *r, *parent; - if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt)) + if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) + return ERR_PTR(-EINVAL); + + if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; + q->mnt.mnt_flags &= ~MNT_LOCKED; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; @@ -1390,7 +1408,13 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { - if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(s)) { + if (!(flag & CL_COPY_UNBINDABLE) && + IS_MNT_UNBINDABLE(s)) { + s = skip_mnt_tree(s); + continue; + } + if (!(flag & CL_COPY_MNT_NS_FILE) && + is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } @@ -1429,7 +1453,7 @@ struct vfsmount *collect_mounts(struct path *path) CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) - return NULL; + return ERR_CAST(tree); return &tree->mnt; } @@ -1696,6 +1720,19 @@ static int do_change_type(struct path *path, int flag) return err; } +static bool has_locked_children(struct mount *mnt, struct dentry *dentry) +{ + struct mount *child; + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (!is_subdir(child->mnt_mountpoint, dentry)) + continue; + + if (child->mnt.mnt_flags & MNT_LOCKED) + return true; + } + return false; +} + /* * do loopback mount. */ @@ -1713,7 +1750,7 @@ static int do_loopback(struct path *path, const char *old_name, return err; err = -EINVAL; - if (mnt_ns_loop(&old_path)) + if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); @@ -1731,8 +1768,11 @@ static int do_loopback(struct path *path, const char *old_name, if (!check_mnt(parent) || !check_mnt(old)) goto out2; + if (!recurse && has_locked_children(old, old_path.dentry)) + goto out2; + if (recurse) - mnt = copy_tree(old, old_path.dentry, 0); + mnt = copy_tree(old, old_path.dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path.dentry, 0); @@ -1741,6 +1781,8 @@ static int do_loopback(struct path *path, const char *old_name, goto out2; } + mnt->mnt.mnt_flags &= ~MNT_LOCKED; + err = graft_tree(mnt, parent, mp); if (err) { br_write_lock(&vfsmount_lock); @@ -1853,6 +1895,9 @@ static int do_move_mount(struct path *path, const char *old_name) if (!check_mnt(p) || !check_mnt(old)) goto out1; + if (old->mnt.mnt_flags & MNT_LOCKED) + goto out1; + err = -EINVAL; if (old_path.dentry != old_path.mnt->mnt_root) goto out1; @@ -2389,7 +2434,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, namespace_lock(); /* First pass: copy the tree topology */ - copy_flags = CL_COPY_ALL | CL_EXPIRE; + copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != mnt_ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED; new = copy_tree(old, old->mnt.mnt_root, copy_flags); @@ -2424,6 +2469,10 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, } p = next_mnt(p, old); q = next_mnt(q, new); + if (!q) + break; + while (p->mnt.mnt_root != q->mnt.mnt_root) + p = next_mnt(p, old); } namespace_unlock(); @@ -2630,6 +2679,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; + if (new_mnt->mnt.mnt_flags & MNT_LOCKED) + goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; @@ -2653,6 +2704,10 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, br_write_lock(&vfsmount_lock); detach_mnt(new_mnt, &parent_path); detach_mnt(root_mnt, &root_parent); + if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { + new_mnt->mnt.mnt_flags |= MNT_LOCKED; + root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; + } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ @@ -2811,25 +2866,38 @@ bool current_chrooted(void) return chrooted; } -void update_mnt_policy(struct user_namespace *userns) +bool fs_fully_visible(struct file_system_type *type) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; + bool visible = false; - down_read(&namespace_sem); + if (unlikely(!ns)) + return false; + + namespace_lock(); list_for_each_entry(mnt, &ns->list, mnt_list) { - switch (mnt->mnt.mnt_sb->s_magic) { - case SYSFS_MAGIC: - userns->may_mount_sysfs = true; - break; - case PROC_SUPER_MAGIC: - userns->may_mount_proc = true; - break; + struct mount *child; + if (mnt->mnt.mnt_sb->s_type != type) + continue; + + /* This mount is not fully visible if there are any child mounts + * that cover anything except for empty directories. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + struct inode *inode = child->mnt_mountpoint->d_inode; + if (!S_ISDIR(inode->i_mode)) + goto next; + if (inode->i_nlink != 2) + goto next; } - if (userns->may_mount_sysfs && userns->may_mount_proc) - break; + visible = true; + goto found; + next: ; } - up_read(&namespace_sem); +found: + namespace_unlock(); + return visible; } static void *mntns_get(struct task_struct *task) @@ -2860,8 +2928,8 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns) struct path root; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || - !nsown_capable(CAP_SYS_CHROOT) || - !nsown_capable(CAP_SYS_ADMIN)) + !ns_capable(current_user_ns(), CAP_SYS_CHROOT) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; if (fs->users != 1) diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index e0bb048..03192a6 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -4,9 +4,10 @@ obj-$(CONFIG_NFS_FS) += nfs.o +CFLAGS_nfstrace.o += -I$(src) nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ direct.o pagelist.o read.o symlink.o unlink.o \ - write.o namespace.o mount_clnt.o + write.o namespace.o mount_clnt.o nfstrace.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o @@ -19,12 +20,14 @@ nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o obj-$(CONFIG_NFS_V4) += nfsv4.o +CFLAGS_nfs4trace.o += -I$(src) nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \ - nfs4namespace.o nfs4getroot.o nfs4client.o dns_resolve.o + nfs4namespace.o nfs4getroot.o nfs4client.o nfs4session.o \ + dns_resolve.o nfs4trace.o nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o -nfsv4-$(CONFIG_NFS_V4_1) += nfs4session.o pnfs.o pnfs_dev.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index e6ebc4c..ae2e87b 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -15,6 +15,7 @@ #include "internal.h" #include "pnfs.h" #include "nfs4session.h" +#include "nfs4trace.h" #ifdef NFS_DEBUG #define NFSDBG_FACILITY NFSDBG_CALLBACK @@ -93,6 +94,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, default: res = htonl(NFS4ERR_RESOURCE); } + trace_nfs4_recall_delegation(inode, -ntohl(res)); iput(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res)); @@ -301,14 +303,14 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args) { struct nfs4_slot *slot; - dprintk("%s enter. slotid %d seqid %d\n", + dprintk("%s enter. slotid %u seqid %u\n", __func__, args->csa_slotid, args->csa_sequenceid); if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS) return htonl(NFS4ERR_BADSLOT); slot = tbl->slots + args->csa_slotid; - dprintk("%s slot table seqid: %d\n", __func__, slot->seq_nr); + dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr); /* Normal */ if (likely(args->csa_sequenceid == slot->seq_nr + 1)) { @@ -318,7 +320,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args) /* Replay */ if (args->csa_sequenceid == slot->seq_nr) { - dprintk("%s seqid %d is a replay\n", + dprintk("%s seqid %u is a replay\n", __func__, args->csa_sequenceid); /* Signal process_op to set this error on next op */ if (args->csa_cachethis == 0) @@ -462,6 +464,7 @@ out: } else res->csr_status = status; + trace_nfs4_cb_sequence(args, res, status); dprintk("%s: exit with status = %d res->csr_status %d\n", __func__, ntohl(status), ntohl(res->csr_status)); return status; @@ -518,7 +521,7 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy, if (!cps->clp) /* set in cb_sequence */ goto out; - dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target highest slotid %d\n", + dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target highest slotid %u\n", rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR), args->crsa_target_highest_slotid); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 340b1ef..2dceee4 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -501,8 +501,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); new->cl_flags = cl_init->init_flags; - return rpc_ops->init_client(new, timeparms, ip_addr, - authflavour); + return rpc_ops->init_client(new, timeparms, ip_addr); } spin_unlock(&nn->nfs_client_lock); @@ -694,13 +693,12 @@ EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient); * @clp: nfs_client to initialise * @timeparms: timeout parameters for underlying RPC transport * @ip_addr: IP presentation address (not used) - * @authflavor: authentication flavor for underlying RPC transport * * Returns pointer to an NFS client, or an ERR_PTR value. */ struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour) + const char *ip_addr) { int error; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7ec4814..ef792f2 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -20,6 +20,7 @@ #include "nfs4_fs.h" #include "delegation.h" #include "internal.h" +#include "nfs4trace.h" static void nfs_free_delegation(struct nfs_delegation *delegation) { @@ -160,6 +161,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, spin_unlock(&delegation->lock); put_rpccred(oldcred); rcu_read_unlock(); + trace_nfs4_reclaim_delegation(inode, res->delegation_type); } else { /* We appear to have raced with a delegation return. */ spin_unlock(&delegation->lock); @@ -344,6 +346,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct spin_lock(&inode->i_lock); nfsi->cache_validity |= NFS_INO_REVAL_FORCED; spin_unlock(&inode->i_lock); + trace_nfs4_set_delegation(inode, res->delegation_type); out: spin_unlock(&clp->cl_lock); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e474ca2b..de434f3 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -43,6 +43,8 @@ #include "internal.h" #include "fscache.h" +#include "nfstrace.h" + /* #define NFS_DEBUG_VERBOSE 1 */ static int nfs_opendir(struct inode *, struct file *); @@ -1100,7 +1102,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) if (IS_ERR(label)) goto out_error; + trace_nfs_lookup_revalidate_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); if (error) goto out_bad; if (nfs_compare_fh(NFS_FH(inode), fhandle)) @@ -1135,14 +1139,13 @@ out_zap_parent: if (inode && S_ISDIR(inode->i_mode)) { /* Purge readdir caches. */ nfs_zap_caches(inode); - /* If we have submounts, don't unhash ! */ - if (have_submounts(dentry)) - goto out_valid; if (dentry->d_flags & DCACHE_DISCONNECTED) goto out_valid; - shrink_dcache_parent(dentry); } - d_drop(dentry); + /* If we have submounts, don't unhash ! */ + if (check_submounts_and_drop(dentry) != 0) + goto out_valid; + dput(parent); dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n", __func__, dentry->d_parent->d_name.name, @@ -1313,6 +1316,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ + trace_nfs_lookup_enter(dir, dentry, flags); nfs_block_sillyrename(parent); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); if (error == -ENOENT) @@ -1339,6 +1343,7 @@ no_entry: nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_unblock_sillyrename: nfs_unblock_sillyrename(parent); + trace_nfs_lookup_exit(dir, dentry, flags, error); nfs4_label_free(label); out: nfs_free_fattr(fattr); @@ -1393,7 +1398,6 @@ static int nfs_finish_open(struct nfs_open_context *ctx, nfs_file_set_open_context(file, ctx); out: - put_nfs_open_context(ctx); return err; } @@ -1405,6 +1409,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct dentry *res; struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; + unsigned int lookup_flags = 0; int err; /* Expect a negative dentry */ @@ -1413,6 +1418,10 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); + err = nfs_check_flags(open_flags); + if (err) + return err; + /* NFS only supports OPEN on regular files */ if ((open_flags & O_DIRECTORY)) { if (!d_unhashed(dentry)) { @@ -1423,6 +1432,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, */ return -ENOENT; } + lookup_flags = LOOKUP_OPEN|LOOKUP_DIRECTORY; goto no_open; } @@ -1443,12 +1453,14 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, if (IS_ERR(ctx)) goto out; + trace_nfs_atomic_open_enter(dir, ctx, open_flags); nfs_block_sillyrename(dentry->d_parent); inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); nfs_unblock_sillyrename(dentry->d_parent); if (IS_ERR(inode)) { - put_nfs_open_context(ctx); err = PTR_ERR(inode); + trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); + put_nfs_open_context(ctx); switch (err) { case -ENOENT: d_drop(dentry); @@ -1469,11 +1481,13 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, } err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened); + trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); + put_nfs_open_context(ctx); out: return err; no_open: - res = nfs_lookup(dir, dentry, 0); + res = nfs_lookup(dir, dentry, lookup_flags); err = PTR_ERR(res); if (IS_ERR(res)) goto out; @@ -1597,7 +1611,9 @@ int nfs_create(struct inode *dir, struct dentry *dentry, attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; + trace_nfs_create_enter(dir, dentry, open_flags); error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); + trace_nfs_create_exit(dir, dentry, open_flags, error); if (error != 0) goto out_err; return 0; @@ -1625,7 +1641,9 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; + trace_nfs_mknod_enter(dir, dentry); status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev); + trace_nfs_mknod_exit(dir, dentry, status); if (status != 0) goto out_err; return 0; @@ -1649,7 +1667,9 @@ int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) attr.ia_valid = ATTR_MODE; attr.ia_mode = mode | S_IFDIR; + trace_nfs_mkdir_enter(dir, dentry); error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr); + trace_nfs_mkdir_exit(dir, dentry, error); if (error != 0) goto out_err; return 0; @@ -1672,12 +1692,21 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) dfprintk(VFS, "NFS: rmdir(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); - error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); - /* Ensure the VFS deletes this inode */ - if (error == 0 && dentry->d_inode != NULL) - clear_nlink(dentry->d_inode); - else if (error == -ENOENT) - nfs_dentry_handle_enoent(dentry); + trace_nfs_rmdir_enter(dir, dentry); + if (dentry->d_inode) { + nfs_wait_on_sillyrename(dentry); + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + /* Ensure the VFS deletes this inode */ + switch (error) { + case 0: + clear_nlink(dentry->d_inode); + break; + case -ENOENT: + nfs_dentry_handle_enoent(dentry); + } + } else + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + trace_nfs_rmdir_exit(dir, dentry, error); return error; } @@ -1705,6 +1734,7 @@ static int nfs_safe_remove(struct dentry *dentry) goto out; } + trace_nfs_remove_enter(dir, dentry); if (inode != NULL) { NFS_PROTO(inode)->return_delegation(inode); error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); @@ -1714,6 +1744,7 @@ static int nfs_safe_remove(struct dentry *dentry) error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); if (error == -ENOENT) nfs_dentry_handle_enoent(dentry); + trace_nfs_remove_exit(dir, dentry, error); out: return error; } @@ -1731,13 +1762,14 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); + trace_nfs_unlink_enter(dir, dentry); spin_lock(&dentry->d_lock); if (d_count(dentry) > 1) { spin_unlock(&dentry->d_lock); /* Start asynchronous writeout of the inode */ write_inode_now(dentry->d_inode, 0); error = nfs_sillyrename(dir, dentry); - return error; + goto out; } if (!d_unhashed(dentry)) { __d_drop(dentry); @@ -1749,6 +1781,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); } else if (need_rehash) d_rehash(dentry); +out: + trace_nfs_unlink_exit(dir, dentry, error); return error; } EXPORT_SYMBOL_GPL(nfs_unlink); @@ -1795,7 +1829,9 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen); kunmap_atomic(kaddr); + trace_nfs_symlink_enter(dir, dentry); error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr); + trace_nfs_symlink_exit(dir, dentry, error); if (error != 0) { dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s) error %d\n", dir->i_sb->s_id, dir->i_ino, @@ -1830,6 +1866,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) old_dentry->d_parent->d_name.name, old_dentry->d_name.name, dentry->d_parent->d_name.name, dentry->d_name.name); + trace_nfs_link_enter(inode, dir, dentry); NFS_PROTO(inode)->return_delegation(inode); d_drop(dentry); @@ -1838,6 +1875,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) ihold(inode); d_add(dentry, inode); } + trace_nfs_link_exit(inode, dir, dentry, error); return error; } EXPORT_SYMBOL_GPL(nfs_link); @@ -1879,6 +1917,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dentry->d_parent->d_name.name, new_dentry->d_name.name, d_count(new_dentry)); + trace_nfs_rename_enter(old_dir, old_dentry, new_dir, new_dentry); /* * For non-directories, check whether the target is busy and if so, * make a copy of the dentry and then do a silly-rename. If the @@ -1925,6 +1964,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, out: if (rehash) d_rehash(rehash); + trace_nfs_rename_exit(old_dir, old_dentry, + new_dir, new_dentry, error); if (!error) { if (new_inode != NULL) nfs_drop_nlink(new_inode); @@ -1965,17 +2006,18 @@ static void nfs_access_free_list(struct list_head *head) } } -int nfs_access_cache_shrinker(struct shrinker *shrink, - struct shrink_control *sc) +unsigned long +nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(head); struct nfs_inode *nfsi, *next; struct nfs_access_entry *cache; int nr_to_scan = sc->nr_to_scan; gfp_t gfp_mask = sc->gfp_mask; + long freed = 0; if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) - return (nr_to_scan == 0) ? 0 : -1; + return SHRINK_STOP; spin_lock(&nfs_access_lru_lock); list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) { @@ -1991,6 +2033,7 @@ int nfs_access_cache_shrinker(struct shrinker *shrink, struct nfs_access_entry, lru); list_move(&cache->lru, &head); rb_erase(&cache->rb_node, &nfsi->access_cache); + freed++; if (!list_empty(&nfsi->access_cache_entry_lru)) list_move_tail(&nfsi->access_cache_inode_lru, &nfs_access_lru_list); @@ -2005,7 +2048,13 @@ remove_lru_entry: } spin_unlock(&nfs_access_lru_lock); nfs_access_free_list(&head); - return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure; + return freed; +} + +unsigned long +nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc) +{ + return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries)); } static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head) @@ -2174,9 +2223,11 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) struct nfs_access_entry cache; int status; + trace_nfs_access_enter(inode); + status = nfs_access_get_cached(inode, cred, &cache); if (status == 0) - goto out; + goto out_cached; /* Be clever: ask server to check for all possible rights */ cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ; @@ -2189,13 +2240,15 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) if (!S_ISDIR(inode->i_mode)) set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } - return status; + goto out; } nfs_access_add_cache(inode, &cache); +out_cached: + if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) + status = -EACCES; out: - if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) - return 0; - return -EACCES; + trace_nfs_access_exit(inode, status); + return status; } static int nfs_open_permission_mask(int openflags) @@ -2241,11 +2294,6 @@ int nfs_permission(struct inode *inode, int mask) case S_IFLNK: goto out; case S_IFREG: - /* NFSv4 has atomic_open... */ - if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN) - && (mask & MAY_OPEN) - && !(mask & MAY_EXEC)) - goto out; break; case S_IFDIR: /* diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 94e94bd..1e6bfdb 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -37,6 +37,8 @@ #include "iostat.h" #include "fscache.h" +#include "nfstrace.h" + #define NFSDBG_FACILITY NFSDBG_FILE static const struct vm_operations_struct nfs_file_vm_ops; @@ -294,6 +296,8 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) int ret; struct inode *inode = file_inode(file); + trace_nfs_fsync_enter(inode); + do { ret = filemap_write_and_wait_range(inode->i_mapping, start, end); if (ret != 0) @@ -310,6 +314,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) end = LLONG_MAX; } while (ret == -EAGAIN); + trace_nfs_fsync_exit(inode, ret); return ret; } @@ -406,6 +411,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { unsigned offset = pos & (PAGE_CACHE_SIZE - 1); + struct nfs_open_context *ctx = nfs_file_open_context(file); int status; dfprintk(PAGECACHE, "NFS: write_end(%s/%s(%ld), %u@%lld)\n", @@ -441,6 +447,13 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, if (status < 0) return status; NFS_I(mapping->host)->write_io += copied; + + if (nfs_ctx_key_to_expire(ctx)) { + status = nfs_wb_all(mapping->host); + if (status < 0) + return status; + } + return copied; } @@ -637,7 +650,8 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode) if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC)) return 1; ctx = nfs_file_open_context(filp); - if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) + if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) || + nfs_ctx_key_to_expire(ctx)) return 1; return 0; } @@ -651,6 +665,10 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, ssize_t result; size_t count = iov_length(iov, nr_segs); + result = nfs_key_timeout_notify(iocb->ki_filp, inode); + if (result) + return result; + if (iocb->ki_filp->f_flags & O_DIRECT) return nfs_file_direct_write(iocb, iov, nr_segs, pos, true); diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index c2c4163..567983d2 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -49,6 +49,7 @@ #include "internal.h" #include "netns.h" +#include "nfs4trace.h" #define NFS_UINT_MAXLEN 11 @@ -63,6 +64,7 @@ struct idmap_legacy_upcalldata { }; struct idmap { + struct rpc_pipe_dir_object idmap_pdo; struct rpc_pipe *idmap_pipe; struct idmap_legacy_upcalldata *idmap_upcall_data; struct mutex idmap_mutex; @@ -310,7 +312,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, if (ret < 0) goto out_up; - payload = rcu_dereference(rkey->payload.data); + payload = rcu_dereference(rkey->payload.rcudata); if (IS_ERR_OR_NULL(payload)) { ret = PTR_ERR(payload); goto out_up; @@ -401,16 +403,23 @@ static struct key_type key_type_id_resolver_legacy = { .request_key = nfs_idmap_legacy_upcall, }; -static void __nfs_idmap_unregister(struct rpc_pipe *pipe) +static void nfs_idmap_pipe_destroy(struct dentry *dir, + struct rpc_pipe_dir_object *pdo) { - if (pipe->dentry) + struct idmap *idmap = pdo->pdo_data; + struct rpc_pipe *pipe = idmap->idmap_pipe; + + if (pipe->dentry) { rpc_unlink(pipe->dentry); + pipe->dentry = NULL; + } } -static int __nfs_idmap_register(struct dentry *dir, - struct idmap *idmap, - struct rpc_pipe *pipe) +static int nfs_idmap_pipe_create(struct dentry *dir, + struct rpc_pipe_dir_object *pdo) { + struct idmap *idmap = pdo->pdo_data; + struct rpc_pipe *pipe = idmap->idmap_pipe; struct dentry *dentry; dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe); @@ -420,36 +429,10 @@ static int __nfs_idmap_register(struct dentry *dir, return 0; } -static void nfs_idmap_unregister(struct nfs_client *clp, - struct rpc_pipe *pipe) -{ - struct net *net = clp->cl_net; - struct super_block *pipefs_sb; - - pipefs_sb = rpc_get_sb_net(net); - if (pipefs_sb) { - __nfs_idmap_unregister(pipe); - rpc_put_sb_net(net); - } -} - -static int nfs_idmap_register(struct nfs_client *clp, - struct idmap *idmap, - struct rpc_pipe *pipe) -{ - struct net *net = clp->cl_net; - struct super_block *pipefs_sb; - int err = 0; - - pipefs_sb = rpc_get_sb_net(net); - if (pipefs_sb) { - if (clp->cl_rpcclient->cl_dentry) - err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry, - idmap, pipe); - rpc_put_sb_net(net); - } - return err; -} +static const struct rpc_pipe_dir_object_ops nfs_idmap_pipe_dir_object_ops = { + .create = nfs_idmap_pipe_create, + .destroy = nfs_idmap_pipe_destroy, +}; int nfs_idmap_new(struct nfs_client *clp) @@ -462,23 +445,31 @@ nfs_idmap_new(struct nfs_client *clp) if (idmap == NULL) return -ENOMEM; + rpc_init_pipe_dir_object(&idmap->idmap_pdo, + &nfs_idmap_pipe_dir_object_ops, + idmap); + pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0); if (IS_ERR(pipe)) { error = PTR_ERR(pipe); - kfree(idmap); - return error; - } - error = nfs_idmap_register(clp, idmap, pipe); - if (error) { - rpc_destroy_pipe_data(pipe); - kfree(idmap); - return error; + goto err; } idmap->idmap_pipe = pipe; mutex_init(&idmap->idmap_mutex); + error = rpc_add_pipe_dir_object(clp->cl_net, + &clp->cl_rpcclient->cl_pipedir_objects, + &idmap->idmap_pdo); + if (error) + goto err_destroy_pipe; + clp->cl_idmap = idmap; return 0; +err_destroy_pipe: + rpc_destroy_pipe_data(idmap->idmap_pipe); +err: + kfree(idmap); + return error; } void @@ -488,130 +479,26 @@ nfs_idmap_delete(struct nfs_client *clp) if (!idmap) return; - nfs_idmap_unregister(clp, idmap->idmap_pipe); - rpc_destroy_pipe_data(idmap->idmap_pipe); clp->cl_idmap = NULL; + rpc_remove_pipe_dir_object(clp->cl_net, + &clp->cl_rpcclient->cl_pipedir_objects, + &idmap->idmap_pdo); + rpc_destroy_pipe_data(idmap->idmap_pipe); kfree(idmap); } -static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event, - struct super_block *sb) -{ - int err = 0; - - switch (event) { - case RPC_PIPEFS_MOUNT: - err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry, - clp->cl_idmap, - clp->cl_idmap->idmap_pipe); - break; - case RPC_PIPEFS_UMOUNT: - if (clp->cl_idmap->idmap_pipe) { - struct dentry *parent; - - parent = clp->cl_idmap->idmap_pipe->dentry->d_parent; - __nfs_idmap_unregister(clp->cl_idmap->idmap_pipe); - /* - * Note: This is a dirty hack. SUNRPC hook has been - * called already but simple_rmdir() call for the - * directory returned with error because of idmap pipe - * inside. Thus now we have to remove this directory - * here. - */ - if (rpc_rmdir(parent)) - printk(KERN_ERR "NFS: %s: failed to remove " - "clnt dir!\n", __func__); - } - break; - default: - printk(KERN_ERR "NFS: %s: unknown event: %ld\n", __func__, - event); - return -ENOTSUPP; - } - return err; -} - -static struct nfs_client *nfs_get_client_for_event(struct net *net, int event) -{ - struct nfs_net *nn = net_generic(net, nfs_net_id); - struct dentry *cl_dentry; - struct nfs_client *clp; - int err; - -restart: - spin_lock(&nn->nfs_client_lock); - list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { - /* Wait for initialisation to finish */ - if (clp->cl_cons_state == NFS_CS_INITING) { - atomic_inc(&clp->cl_count); - spin_unlock(&nn->nfs_client_lock); - err = nfs_wait_client_init_complete(clp); - nfs_put_client(clp); - if (err) - return NULL; - goto restart; - } - /* Skip nfs_clients that failed to initialise */ - if (clp->cl_cons_state < 0) - continue; - smp_rmb(); - if (clp->rpc_ops != &nfs_v4_clientops) - continue; - cl_dentry = clp->cl_idmap->idmap_pipe->dentry; - if (((event == RPC_PIPEFS_MOUNT) && cl_dentry) || - ((event == RPC_PIPEFS_UMOUNT) && !cl_dentry)) - continue; - atomic_inc(&clp->cl_count); - spin_unlock(&nn->nfs_client_lock); - return clp; - } - spin_unlock(&nn->nfs_client_lock); - return NULL; -} - -static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, - void *ptr) -{ - struct super_block *sb = ptr; - struct nfs_client *clp; - int error = 0; - - if (!try_module_get(THIS_MODULE)) - return 0; - - while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) { - error = __rpc_pipefs_event(clp, event, sb); - nfs_put_client(clp); - if (error) - break; - } - module_put(THIS_MODULE); - return error; -} - -#define PIPEFS_NFS_PRIO 1 - -static struct notifier_block nfs_idmap_block = { - .notifier_call = rpc_pipefs_event, - .priority = SUNRPC_PIPEFS_NFS_PRIO, -}; - int nfs_idmap_init(void) { int ret; ret = nfs_idmap_init_keyring(); if (ret != 0) goto out; - ret = rpc_pipefs_notifier_register(&nfs_idmap_block); - if (ret != 0) - nfs_idmap_quit_keyring(); out: return ret; } void nfs_idmap_quit(void) { - rpc_pipefs_notifier_unregister(&nfs_idmap_block); nfs_idmap_quit_keyring(); } @@ -849,6 +736,7 @@ int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_ if (!uid_valid(*uid)) ret = -ERANGE; } + trace_nfs4_map_name_to_uid(name, namelen, id, ret); return ret; } @@ -865,6 +753,7 @@ int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size if (!gid_valid(*gid)) ret = -ERANGE; } + trace_nfs4_map_group_to_gid(name, namelen, id, ret); return ret; } @@ -879,6 +768,7 @@ int nfs_map_uid_to_name(const struct nfs_server *server, kuid_t uid, char *buf, ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap); if (ret < 0) ret = nfs_map_numeric_to_string(id, buf, buflen); + trace_nfs4_map_uid_to_name(buf, ret, id, ret); return ret; } int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, size_t buflen) @@ -892,5 +782,6 @@ int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap); if (ret < 0) ret = nfs_map_numeric_to_string(id, buf, buflen); + trace_nfs4_map_gid_to_group(buf, ret, id, ret); return ret; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index af6e806..eda8879 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -38,7 +38,6 @@ #include <linux/slab.h> #include <linux/compat.h> #include <linux/freezer.h> -#include <linux/crc32.h> #include <asm/uaccess.h> @@ -52,6 +51,8 @@ #include "nfs.h" #include "netns.h" +#include "nfstrace.h" + #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_64_BIT_INODE_NUMBERS_ENABLED 1 @@ -463,7 +464,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st unlock_new_inode(inode); } else nfs_refresh_inode(inode, fattr); - nfs_setsecurity(inode, fattr, label); dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (long long)NFS_FILEID(inode), @@ -504,6 +504,8 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0) return 0; + trace_nfs_setattr_enter(inode); + /* Write all dirty data */ if (S_ISREG(inode->i_mode)) { nfs_inode_dio_wait(inode); @@ -523,6 +525,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) error = nfs_refresh_inode(inode, fattr); nfs_free_fattr(fattr); out: + trace_nfs_setattr_exit(inode, error); return error; } EXPORT_SYMBOL_GPL(nfs_setattr); @@ -538,7 +541,6 @@ EXPORT_SYMBOL_GPL(nfs_setattr); */ static int nfs_vmtruncate(struct inode * inode, loff_t offset) { - loff_t oldsize; int err; err = inode_newsize_ok(inode, offset); @@ -546,11 +548,10 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset) goto out; spin_lock(&inode->i_lock); - oldsize = inode->i_size; i_size_write(inode, offset); spin_unlock(&inode->i_lock); - truncate_pagecache(inode, oldsize, offset); + truncate_pagecache(inode, offset); out: return err; } @@ -592,6 +593,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; int err; + trace_nfs_getattr_enter(inode); /* Flush out writes to the server in order to update c/mtime. */ if (S_ISREG(inode->i_mode)) { nfs_inode_dio_wait(inode); @@ -622,6 +624,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); } out: + trace_nfs_getattr_exit(inode, err); return err; } EXPORT_SYMBOL_GPL(nfs_getattr); @@ -876,6 +879,8 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n", inode->i_sb->s_id, (long long)NFS_FILEID(inode)); + trace_nfs_revalidate_inode_enter(inode); + if (is_bad_inode(inode)) goto out; if (NFS_STALE(inode)) @@ -926,6 +931,7 @@ err_out: nfs4_label_free(label); out: nfs_free_fattr(fattr); + trace_nfs_revalidate_inode_exit(inode, status); return status; } @@ -963,9 +969,15 @@ EXPORT_SYMBOL_GPL(nfs_revalidate_inode); static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { struct nfs_inode *nfsi = NFS_I(inode); - + int ret; + if (mapping->nrpages != 0) { - int ret = invalidate_inode_pages2(mapping); + if (S_ISREG(inode->i_mode)) { + ret = nfs_sync_mapping(mapping); + if (ret < 0) + return ret; + } + ret = invalidate_inode_pages2(mapping); if (ret < 0) return ret; } @@ -976,6 +988,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map spin_unlock(&inode->i_lock); nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); nfs_fscache_wait_on_invalidate(inode); + dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n", inode->i_sb->s_id, (long long)NFS_FILEID(inode)); return 0; @@ -1009,8 +1022,12 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) if (ret < 0) goto out; } - if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) { + trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); + trace_nfs_invalidate_mapping_exit(inode, ret); + } + out: return ret; } @@ -1190,7 +1207,7 @@ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) { /* wireshark uses 32-bit AUTODIN crc and does a bitwise * not on the result */ - return ~crc32(0xFFFFFFFF, &fh->data[0], fh->size); + return nfs_fhandle_hash(fh); } /* @@ -1269,9 +1286,17 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { + int ret; + + trace_nfs_refresh_inode_enter(inode); + if (nfs_inode_attrs_need_update(inode, fattr)) - return nfs_update_inode(inode, fattr); - return nfs_check_inode_attributes(inode, fattr); + ret = nfs_update_inode(inode, fattr); + else + ret = nfs_check_inode_attributes(inode, fattr); + + trace_nfs_refresh_inode_exit(inode, ret); + return ret; } /** diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3c8373f..38da8c2 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -5,6 +5,7 @@ #include "nfs4_fs.h" #include <linux/mount.h> #include <linux/security.h> +#include <linux/crc32.h> #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) @@ -185,6 +186,8 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); +extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, + struct inode *); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); @@ -267,11 +270,13 @@ extern struct rpc_procinfo nfs4_procedures[]; void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour); + const char *ip_addr); /* dir.c */ -extern int nfs_access_cache_shrinker(struct shrinker *shrink, - struct shrink_control *sc); +extern unsigned long nfs_access_cache_count(struct shrinker *shrink, + struct shrink_control *sc); +extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, + struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); int nfs_create(struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct inode *, struct dentry *, umode_t); @@ -355,7 +360,7 @@ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, const char *); -extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); +extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif struct nfs_pgio_completion_ops; @@ -430,6 +435,8 @@ void nfs_request_remove_commit_list(struct nfs_page *req, void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct inode *inode, struct nfs_direct_req *dreq); +int nfs_key_timeout_notify(struct file *filp, struct inode *inode); +bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, @@ -451,8 +458,7 @@ extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); extern void __nfs4_read_done_cb(struct nfs_read_data *); extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, - rpc_authflavor_t authflavour); + const char *ip_addr); extern int nfs40_walk_client_list(struct nfs_client *clp, struct nfs_client **result, struct rpc_cred *cred); @@ -575,3 +581,22 @@ u64 nfs_timespec_to_change_attr(const struct timespec *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } + +#ifdef CONFIG_CRC32 +/** + * nfs_fhandle_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); +} +#else +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return 0; +} +#endif diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index f5c84c3..90cb10d 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -336,8 +336,8 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, data->arg.create.createmode = NFS3_CREATE_UNCHECKED; if (flags & O_EXCL) { data->arg.create.createmode = NFS3_CREATE_EXCLUSIVE; - data->arg.create.verifier[0] = jiffies; - data->arg.create.verifier[1] = current->pid; + data->arg.create.verifier[0] = cpu_to_be32(jiffies); + data->arg.create.verifier[1] = cpu_to_be32(current->pid); } sattr->ia_mode &= ~current_umask(); @@ -826,9 +826,10 @@ static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ]; } -static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) +static int nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { rpc_call_start(task); + return 0; } static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data) @@ -847,9 +848,10 @@ static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_messag msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE]; } -static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) +static int nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { rpc_call_start(task); + return 0; } static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ee81e35..28842ab 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -38,17 +38,15 @@ struct nfs4_minor_version_ops { u32 minor_version; unsigned init_caps; - int (*call_sync)(struct rpc_clnt *clnt, - struct nfs_server *server, - struct rpc_message *msg, - struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res); + int (*init_client)(struct nfs_client *); + void (*shutdown_client)(struct nfs_client *); bool (*match_stateid)(const nfs4_stateid *, const nfs4_stateid *); int (*find_root_sec)(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); int (*free_lock_state)(struct nfs_server *, struct nfs4_lock_state *); + const struct rpc_call_ops *call_sync_ops; const struct nfs4_state_recovery_ops *reboot_recovery_ops; const struct nfs4_state_recovery_ops *nograce_recovery_ops; const struct nfs4_state_maintenance_ops *state_renewal_ops; @@ -135,6 +133,7 @@ struct nfs4_lock_state { struct list_head ls_locks; /* Other lock stateids */ struct nfs4_state * ls_state; /* Pointer to open state */ #define NFS_LOCK_INITIALIZED 0 +#define NFS_LOCK_LOST 1 unsigned long ls_flags; struct nfs_seqid_counter ls_seqid; nfs4_stateid ls_stateid; @@ -193,7 +192,6 @@ struct nfs4_state_recovery_ops { int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *); int (*recover_lock)(struct nfs4_state *, struct file_lock *); int (*establish_clid)(struct nfs_client *, struct rpc_cred *); - struct rpc_cred * (*get_clid_cred)(struct nfs_client *); int (*reclaim_complete)(struct nfs_client *, struct rpc_cred *); int (*detect_trunking)(struct nfs_client *, struct nfs_client **, struct rpc_cred *); @@ -223,7 +221,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); -extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); +extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool); extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); extern int nfs4_destroy_clientid(struct nfs_client *clp); @@ -248,9 +246,6 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser return server->nfs_client->cl_session; } -extern int nfs4_setup_sequence(const struct nfs_server *server, - struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, - struct rpc_task *task); extern int nfs41_setup_sequence(struct nfs4_session *session, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, struct rpc_task *task); @@ -273,18 +268,63 @@ is_ds_client(struct nfs_client *clp) { return clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_DS; } -#else /* CONFIG_NFS_v4_1 */ -static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server) + +static inline bool +_nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, + struct rpc_clnt **clntp, struct rpc_message *msg) { - return NULL; + struct rpc_cred *newcred = NULL; + rpc_authflavor_t flavor; + + if (test_bit(sp4_mode, &clp->cl_sp4_flags)) { + spin_lock(&clp->cl_lock); + if (clp->cl_machine_cred != NULL) + /* don't call get_rpccred on the machine cred - + * a reference will be held for life of clp */ + newcred = clp->cl_machine_cred; + spin_unlock(&clp->cl_lock); + msg->rpc_cred = newcred; + + flavor = clp->cl_rpcclient->cl_auth->au_flavor; + WARN_ON_ONCE(flavor != RPC_AUTH_GSS_KRB5I && + flavor != RPC_AUTH_GSS_KRB5P); + *clntp = clp->cl_rpcclient; + + return true; + } + return false; } -static inline int nfs4_setup_sequence(const struct nfs_server *server, - struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, - struct rpc_task *task) +/* + * Function responsible for determining if an rpc_message should use the + * machine cred under SP4_MACH_CRED and if so switching the credential and + * authflavor (using the nfs_client's rpc_clnt which will be krb5i/p). + * Should be called before rpc_call_sync/rpc_call_async. + */ +static inline void +nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, + struct rpc_clnt **clntp, struct rpc_message *msg) { - rpc_call_start(task); - return 0; + _nfs4_state_protect(clp, sp4_mode, clntp, msg); +} + +/* + * Special wrapper to nfs4_state_protect for write. + * If WRITE can use machine cred but COMMIT cannot, make sure all writes + * that use machine cred use NFS_FILE_SYNC. + */ +static inline void +nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp, + struct rpc_message *msg, struct nfs_write_data *wdata) +{ + if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) && + !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags)) + wdata->args.stable = NFS_FILE_SYNC; +} +#else /* CONFIG_NFS_v4_1 */ +static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server) +{ + return NULL; } static inline bool @@ -298,6 +338,18 @@ is_ds_client(struct nfs_client *clp) { return false; } + +static inline void +nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags, + struct rpc_clnt **clntp, struct rpc_message *msg) +{ +} + +static inline void +nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp, + struct rpc_message *msg, struct nfs_write_data *wdata) +{ +} #endif /* CONFIG_NFS_V4_1 */ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[]; @@ -308,6 +360,10 @@ extern const u32 nfs4_pathconf_bitmap[3]; extern const u32 nfs4_fsinfo_bitmap[3]; extern const u32 nfs4_fs_locations_bitmap[3]; +void nfs40_shutdown_client(struct nfs_client *); +void nfs41_shutdown_client(struct nfs_client *); +int nfs40_init_client(struct nfs_client *); +int nfs41_init_client(struct nfs_client *); void nfs4_free_client(struct nfs_client *); struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *); @@ -319,7 +375,7 @@ extern void nfs4_kill_renewd(struct nfs_client *); extern void nfs4_renew_state(struct work_struct *); /* nfs4state.c */ -struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp); +struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp); struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp); struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp); int nfs4_discover_server_trunking(struct nfs_client *clp, @@ -327,7 +383,6 @@ int nfs4_discover_server_trunking(struct nfs_client *clp, int nfs40_discover_server_trunking(struct nfs_client *clp, struct nfs_client **, struct rpc_cred *); #if defined(CONFIG_NFS_V4_1) -struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp); int nfs41_discover_server_trunking(struct nfs_client *clp, struct nfs_client **, struct rpc_cred *); extern void nfs4_schedule_session_recovery(struct nfs4_session *, int); @@ -382,6 +437,7 @@ struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct extern bool nfs4_disable_idmapping; extern unsigned short max_session_slots; extern unsigned short send_implementation_id; +extern bool recover_lost_locks; #define NFS4_CLIENT_ID_UNIQ_LEN (64) extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN]; @@ -429,6 +485,8 @@ static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state) #define nfs4_close_state(a, b) do { } while (0) #define nfs4_close_sync(a, b) do { } while (0) +#define nfs4_state_protect(a, b, c, d) do { } while (0) +#define nfs4_state_protect_write(a, b, c, d) do { } while (0) #endif /* CONFIG_NFS_V4 */ #endif /* __LINUX_FS_NFS_NFS4_FS.H */ diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 90dce91..a860ab5 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -41,19 +41,138 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) } #ifdef CONFIG_NFS_V4_1 -static void nfs4_shutdown_session(struct nfs_client *clp) +/** + * Per auth flavor data server rpc clients + */ +struct nfs4_ds_server { + struct list_head list; /* ds_clp->cl_ds_clients */ + struct rpc_clnt *rpc_clnt; +}; + +/** + * Common lookup case for DS I/O + */ +static struct nfs4_ds_server * +nfs4_find_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor) +{ + struct nfs4_ds_server *dss; + + rcu_read_lock(); + list_for_each_entry_rcu(dss, &ds_clp->cl_ds_clients, list) { + if (dss->rpc_clnt->cl_auth->au_flavor != flavor) + continue; + goto out; + } + dss = NULL; +out: + rcu_read_unlock(); + return dss; +} + +static struct nfs4_ds_server * +nfs4_add_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor, + struct nfs4_ds_server *new) +{ + struct nfs4_ds_server *dss; + + spin_lock(&ds_clp->cl_lock); + list_for_each_entry(dss, &ds_clp->cl_ds_clients, list) { + if (dss->rpc_clnt->cl_auth->au_flavor != flavor) + continue; + goto out; + } + if (new) + list_add_rcu(&new->list, &ds_clp->cl_ds_clients); + dss = new; +out: + spin_unlock(&ds_clp->cl_lock); /* need some lock to protect list */ + return dss; +} + +static struct nfs4_ds_server * +nfs4_alloc_ds_server(struct nfs_client *ds_clp, rpc_authflavor_t flavor) +{ + struct nfs4_ds_server *dss; + + dss = kmalloc(sizeof(*dss), GFP_NOFS); + if (dss == NULL) + return ERR_PTR(-ENOMEM); + + dss->rpc_clnt = rpc_clone_client_set_auth(ds_clp->cl_rpcclient, flavor); + if (IS_ERR(dss->rpc_clnt)) { + int err = PTR_ERR(dss->rpc_clnt); + kfree (dss); + return ERR_PTR(err); + } + INIT_LIST_HEAD(&dss->list); + + return dss; +} + +static void +nfs4_free_ds_server(struct nfs4_ds_server *dss) +{ + rpc_release_client(dss->rpc_clnt); + kfree(dss); +} + +/** +* Find or create a DS rpc client with th MDS server rpc client auth flavor +* in the nfs_client cl_ds_clients list. +*/ +struct rpc_clnt * +nfs4_find_or_create_ds_client(struct nfs_client *ds_clp, struct inode *inode) +{ + struct nfs4_ds_server *dss, *new; + rpc_authflavor_t flavor = NFS_SERVER(inode)->client->cl_auth->au_flavor; + + dss = nfs4_find_ds_client(ds_clp, flavor); + if (dss != NULL) + goto out; + new = nfs4_alloc_ds_server(ds_clp, flavor); + if (IS_ERR(new)) + return ERR_CAST(new); + dss = nfs4_add_ds_client(ds_clp, flavor, new); + if (dss != new) + nfs4_free_ds_server(new); +out: + return dss->rpc_clnt; +} +EXPORT_SYMBOL_GPL(nfs4_find_or_create_ds_client); + +static void +nfs4_shutdown_ds_clients(struct nfs_client *clp) +{ + struct nfs4_ds_server *dss; + LIST_HEAD(shutdown_list); + + while (!list_empty(&clp->cl_ds_clients)) { + dss = list_entry(clp->cl_ds_clients.next, + struct nfs4_ds_server, list); + list_del(&dss->list); + rpc_shutdown_client(dss->rpc_clnt); + kfree (dss); + } +} + +void nfs41_shutdown_client(struct nfs_client *clp) { if (nfs4_has_session(clp)) { + nfs4_shutdown_ds_clients(clp); nfs4_destroy_session(clp->cl_session); nfs4_destroy_clientid(clp); } } -#else /* CONFIG_NFS_V4_1 */ -static void nfs4_shutdown_session(struct nfs_client *clp) +#endif /* CONFIG_NFS_V4_1 */ + +void nfs40_shutdown_client(struct nfs_client *clp) { + if (clp->cl_slot_tbl) { + nfs4_release_slot_table(clp->cl_slot_tbl); + kfree(clp->cl_slot_tbl); + } } -#endif /* CONFIG_NFS_V4_1 */ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) { @@ -73,6 +192,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) spin_lock_init(&clp->cl_lock); INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); + INIT_LIST_HEAD(&clp->cl_ds_clients); rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_minorversion = cl_init->minorversion; @@ -97,7 +217,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) { if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state)) nfs4_kill_renewd(clp); - nfs4_shutdown_session(clp); + clp->cl_mvops->shutdown_client(clp); nfs4_destroy_callback(clp); if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state)) nfs_idmap_delete(clp); @@ -144,34 +264,77 @@ static int nfs4_init_callback(struct nfs_client *clp) return 0; } +/** + * nfs40_init_client - nfs_client initialization tasks for NFSv4.0 + * @clp - nfs_client to initialize + * + * Returns zero on success, or a negative errno if some error occurred. + */ +int nfs40_init_client(struct nfs_client *clp) +{ + struct nfs4_slot_table *tbl; + int ret; + + tbl = kzalloc(sizeof(*tbl), GFP_NOFS); + if (tbl == NULL) + return -ENOMEM; + + ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, + "NFSv4.0 transport Slot table"); + if (ret) { + kfree(tbl); + return ret; + } + + clp->cl_slot_tbl = tbl; + return 0; +} + +#if defined(CONFIG_NFS_V4_1) + +/** + * nfs41_init_client - nfs_client initialization tasks for NFSv4.1+ + * @clp - nfs_client to initialize + * + * Returns zero on success, or a negative errno if some error occurred. + */ +int nfs41_init_client(struct nfs_client *clp) +{ + struct nfs4_session *session = NULL; + + /* + * Create the session and mark it expired. + * When a SEQUENCE operation encounters the expired session + * it will do session recovery to initialize it. + */ + session = nfs4_alloc_session(clp); + if (!session) + return -ENOMEM; + + clp->cl_session = session; + + /* + * The create session reply races with the server back + * channel probe. Mark the client NFS_CS_SESSION_INITING + * so that the client back channel can find the + * nfs_client struct + */ + nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING); + return 0; +} + +#endif /* CONFIG_NFS_V4_1 */ + /* * Initialize the minor version specific parts of an NFS4 client record */ static int nfs4_init_client_minor_version(struct nfs_client *clp) { -#if defined(CONFIG_NFS_V4_1) - if (clp->cl_mvops->minor_version) { - struct nfs4_session *session = NULL; - /* - * Create the session and mark it expired. - * When a SEQUENCE operation encounters the expired session - * it will do session recovery to initialize it. - */ - session = nfs4_alloc_session(clp); - if (!session) - return -ENOMEM; - - clp->cl_session = session; - /* - * The create session reply races with the server back - * channel probe. Mark the client NFS_CS_SESSION_INITING - * so that the client back channel can find the - * nfs_client struct - */ - nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING); - } -#endif /* CONFIG_NFS_V4_1 */ + int ret; + ret = clp->cl_mvops->init_client(clp); + if (ret) + return ret; return nfs4_init_callback(clp); } @@ -187,8 +350,7 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) */ struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, - rpc_authflavor_t authflavour) + const char *ip_addr) { char buf[INET6_ADDRSTRLEN + 1]; struct nfs_client *old; @@ -723,7 +885,7 @@ static void nfs4_session_set_rwsize(struct nfs_server *server) } static int nfs4_server_common_setup(struct nfs_server *server, - struct nfs_fh *mntfh) + struct nfs_fh *mntfh, bool auth_probe) { struct nfs_fattr *fattr; int error; @@ -755,7 +917,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, /* Probe the root fh to retrieve its FSID and filehandle */ - error = nfs4_get_rootfh(server, mntfh); + error = nfs4_get_rootfh(server, mntfh, auth_probe); if (error < 0) goto out; @@ -787,6 +949,7 @@ out: static int nfs4_init_server(struct nfs_server *server, const struct nfs_parsed_mount_data *data) { + rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; struct rpc_timeout timeparms; int error; @@ -799,13 +962,16 @@ static int nfs4_init_server(struct nfs_server *server, server->flags = data->flags; server->options = data->options; + if (data->auth_flavor_len >= 1) + pseudoflavor = data->auth_flavors[0]; + /* Get a client record */ error = nfs4_set_client(server, data->nfs_server.hostname, (const struct sockaddr *)&data->nfs_server.address, data->nfs_server.addrlen, data->client_address, - data->auth_flavors[0], + pseudoflavor, data->nfs_server.protocol, &timeparms, data->minorversion, @@ -825,7 +991,7 @@ static int nfs4_init_server(struct nfs_server *server, server->port = data->nfs_server.port; - error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]); + error = nfs_init_server_rpcclient(server, &timeparms, pseudoflavor); error: /* Done */ @@ -843,6 +1009,7 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, struct nfs_subversion *nfs_mod) { struct nfs_server *server; + bool auth_probe; int error; dprintk("--> nfs4_create_server()\n"); @@ -851,12 +1018,14 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, if (!server) return ERR_PTR(-ENOMEM); + auth_probe = mount_info->parsed->auth_flavor_len < 1; + /* set up the general RPC client */ error = nfs4_init_server(server, mount_info->parsed); if (error < 0) goto error; - error = nfs4_server_common_setup(server, mount_info->mntfh); + error = nfs4_server_common_setup(server, mount_info->mntfh, auth_probe); if (error < 0) goto error; @@ -909,7 +1078,8 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, if (error < 0) goto error; - error = nfs4_server_common_setup(server, mntfh); + error = nfs4_server_common_setup(server, mntfh, + !(parent_server->flags & NFS_MOUNT_SECFLAVOUR)); if (error < 0) goto error; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 17ed87e..b86464b 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -39,6 +39,7 @@ #include "internal.h" #include "delegation.h" #include "nfs4filelayout.h" +#include "nfs4trace.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD @@ -247,6 +248,7 @@ static int filelayout_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr = data->header; int err; + trace_nfs4_pnfs_read(data, task->tk_status); err = filelayout_async_handle_error(task, data->args.context->state, data->ds_clp, hdr->lseg); @@ -363,6 +365,7 @@ static int filelayout_write_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr = data->header; int err; + trace_nfs4_pnfs_write(data, task->tk_status); err = filelayout_async_handle_error(task, data->args.context->state, data->ds_clp, hdr->lseg); @@ -395,6 +398,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task, { int err; + trace_nfs4_pnfs_commit_ds(data, task->tk_status); err = filelayout_async_handle_error(task, NULL, data->ds_clp, data->lseg); @@ -524,6 +528,7 @@ filelayout_read_pagelist(struct nfs_read_data *data) struct nfs_pgio_header *hdr = data->header; struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; loff_t offset = data->args.offset; u32 j, idx; struct nfs_fh *fh; @@ -538,6 +543,11 @@ filelayout_read_pagelist(struct nfs_read_data *data) ds = nfs4_fl_prepare_ds(lseg, idx); if (!ds) return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + dprintk("%s USE DS: %s cl_count %d\n", __func__, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); @@ -552,7 +562,7 @@ filelayout_read_pagelist(struct nfs_read_data *data) data->mds_offset = offset; /* Perform an asynchronous read to ds */ - nfs_initiate_read(ds->ds_clp->cl_rpcclient, data, + nfs_initiate_read(ds_clnt, data, &filelayout_read_call_ops, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; } @@ -564,6 +574,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) struct nfs_pgio_header *hdr = data->header; struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; loff_t offset = data->args.offset; u32 j, idx; struct nfs_fh *fh; @@ -574,6 +585,11 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) ds = nfs4_fl_prepare_ds(lseg, idx); if (!ds) return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n", __func__, hdr->inode->i_ino, sync, (size_t) data->args.count, offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); @@ -591,7 +607,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) data->args.offset = filelayout_get_dserver_offset(lseg, offset); /* Perform an asynchronous write */ - nfs_initiate_write(ds->ds_clp->cl_rpcclient, data, + nfs_initiate_write(ds_clnt, data, &filelayout_write_call_ops, sync, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; @@ -1101,16 +1117,19 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) { struct pnfs_layout_segment *lseg = data->lseg; struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; u32 idx; struct nfs_fh *fh; idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); ds = nfs4_fl_prepare_ds(lseg, idx); - if (!ds) { - prepare_to_resend_writes(data); - filelayout_commit_release(data); - return -EAGAIN; - } + if (!ds) + goto out_err; + + ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, data->inode); + if (IS_ERR(ds_clnt)) + goto out_err; + dprintk("%s ino %lu, how %d cl_count %d\n", __func__, data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count)); data->commit_done_cb = filelayout_commit_done_cb; @@ -1119,9 +1138,13 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); if (fh) data->args.fh = fh; - return nfs_initiate_commit(ds->ds_clp->cl_rpcclient, data, + return nfs_initiate_commit(ds_clnt, data, &filelayout_commit_call_ops, how, RPC_TASK_SOFTCONN); +out_err: + prepare_to_resend_writes(data); + filelayout_commit_release(data); + return -EAGAIN; } static int diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c index 549462e..c0b3a16 100644 --- a/fs/nfs/nfs4getroot.c +++ b/fs/nfs/nfs4getroot.c @@ -9,7 +9,7 @@ #define NFSDBG_FACILITY NFSDBG_CLIENT -int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh) +int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_probe) { struct nfs_fsinfo fsinfo; int ret = -ENOMEM; @@ -21,7 +21,7 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh) goto out; /* Start by getting the root filehandle from the server */ - ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo); + ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo, auth_probe); if (ret < 0) { dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret); goto out; diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index cdb0b41..2288cd3 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -11,6 +11,7 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/sunrpc/clnt.h> @@ -369,21 +370,33 @@ out: struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr) { + rpc_authflavor_t flavor = server->client->cl_auth->au_flavor; struct dentry *parent = dget_parent(dentry); + struct inode *dir = parent->d_inode; + struct qstr *name = &dentry->d_name; struct rpc_clnt *client; struct vfsmount *mnt; /* Look it up again to get its attributes and sec flavor */ - client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr); + client = nfs4_proc_lookup_mountpoint(dir, name, fh, fattr); dput(parent); if (IS_ERR(client)) return ERR_CAST(client); - if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { mnt = nfs_do_refmount(client, dentry); - else - mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor); + goto out; + } + if (client->cl_auth->au_flavor != flavor) + flavor = client->cl_auth->au_flavor; + else if (!(server->flags & NFS_MOUNT_SECFLAVOUR)) { + rpc_authflavor_t new = nfs4_negotiate_security(dir, name); + if ((int)new >= 0) + flavor = new; + } + mnt = nfs_do_submount(dentry, fh, fattr, flavor); +out: rpc_shutdown_client(client); return mnt; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cf11799..989bb9d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -66,6 +66,8 @@ #include "nfs4session.h" #include "fscache.h" +#include "nfs4trace.h" + #define NFSDBG_FACILITY NFSDBG_PROC #define NFS4_POLL_RETRY_MIN (HZ/10) @@ -150,6 +152,7 @@ static int nfs4_map_errors(int err) case -NFS4ERR_RECALLCONFLICT: return -EREMOTEIO; case -NFS4ERR_WRONGSEC: + case -NFS4ERR_WRONG_CRED: return -EPERM; case -NFS4ERR_BADOWNER: case -NFS4ERR_BADNAME: @@ -433,6 +436,20 @@ wait_on_recovery: return ret; } +/* + * Return 'true' if 'clp' is using an rpc_client that is integrity protected + * or 'false' otherwise. + */ +static bool _nfs4_is_integrity_protected(struct nfs_client *clp) +{ + rpc_authflavor_t flavor = clp->cl_rpcclient->cl_auth->au_flavor; + + if (flavor == RPC_AUTH_GSS_KRB5I || + flavor == RPC_AUTH_GSS_KRB5P) + return true; + + return false; +} static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp) { @@ -447,6 +464,88 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp do_renew_lease(server->nfs_client, timestamp); } +struct nfs4_call_sync_data { + const struct nfs_server *seq_server; + struct nfs4_sequence_args *seq_args; + struct nfs4_sequence_res *seq_res; +}; + +static void nfs4_init_sequence(struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, int cache_reply) +{ + args->sa_slot = NULL; + args->sa_cache_this = cache_reply; + args->sa_privileged = 0; + + res->sr_slot = NULL; +} + +static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args) +{ + args->sa_privileged = 1; +} + +static int nfs40_setup_sequence(const struct nfs_server *server, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + struct nfs4_slot_table *tbl = server->nfs_client->cl_slot_tbl; + struct nfs4_slot *slot; + + /* slot already allocated? */ + if (res->sr_slot != NULL) + goto out_start; + + spin_lock(&tbl->slot_tbl_lock); + if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged) + goto out_sleep; + + slot = nfs4_alloc_slot(tbl); + if (IS_ERR(slot)) { + if (slot == ERR_PTR(-ENOMEM)) + task->tk_timeout = HZ >> 2; + goto out_sleep; + } + spin_unlock(&tbl->slot_tbl_lock); + + args->sa_slot = slot; + res->sr_slot = slot; + +out_start: + rpc_call_start(task); + return 0; + +out_sleep: + if (args->sa_privileged) + rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task, + NULL, RPC_PRIORITY_PRIVILEGED); + else + rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL); + spin_unlock(&tbl->slot_tbl_lock); + return -EAGAIN; +} + +static int nfs40_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res) +{ + struct nfs4_slot *slot = res->sr_slot; + struct nfs4_slot_table *tbl; + + if (!RPC_WAS_SENT(task)) + goto out; + + tbl = slot->table; + spin_lock(&tbl->slot_tbl_lock); + if (!nfs41_wake_and_assign_slot(tbl, slot)) + nfs4_free_slot(tbl, slot); + spin_unlock(&tbl->slot_tbl_lock); + + res->sr_slot = NULL; +out: + return 1; +} + #if defined(CONFIG_NFS_V4_1) static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) @@ -506,6 +605,7 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res * interrupted = true; } + trace_nfs4_sequence_done(session, res); /* Check the SEQUENCE operation status */ switch (res->sr_status) { case 0: @@ -591,25 +691,11 @@ static int nfs4_sequence_done(struct rpc_task *task, { if (res->sr_slot == NULL) return 1; + if (!res->sr_slot->table->session) + return nfs40_sequence_done(task, res); return nfs41_sequence_done(task, res); } -static void nfs41_init_sequence(struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res, int cache_reply) -{ - args->sa_slot = NULL; - args->sa_cache_this = 0; - args->sa_privileged = 0; - if (cache_reply) - args->sa_cache_this = 1; - res->sr_slot = NULL; -} - -static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args) -{ - args->sa_privileged = 1; -} - int nfs41_setup_sequence(struct nfs4_session *session, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, @@ -647,7 +733,7 @@ int nfs41_setup_sequence(struct nfs4_session *session, args->sa_slot = slot; - dprintk("<-- %s slotid=%d seqid=%d\n", __func__, + dprintk("<-- %s slotid=%u seqid=%u\n", __func__, slot->slot_nr, slot->seq_nr); res->sr_slot = slot; @@ -658,6 +744,7 @@ int nfs41_setup_sequence(struct nfs4_session *session, * set to 1 if an rpc level failure occurs. */ res->sr_status = 1; + trace_nfs4_setup_sequence(session, args); out_success: rpc_call_start(task); return 0; @@ -673,38 +760,30 @@ out_sleep: } EXPORT_SYMBOL_GPL(nfs41_setup_sequence); -int nfs4_setup_sequence(const struct nfs_server *server, - struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res, - struct rpc_task *task) +static int nfs4_setup_sequence(const struct nfs_server *server, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) { struct nfs4_session *session = nfs4_get_session(server); int ret = 0; - if (session == NULL) { - rpc_call_start(task); - goto out; - } + if (!session) + return nfs40_setup_sequence(server, args, res, task); - dprintk("--> %s clp %p session %p sr_slot %d\n", + dprintk("--> %s clp %p session %p sr_slot %u\n", __func__, session->clp, session, res->sr_slot ? - res->sr_slot->slot_nr : -1); + res->sr_slot->slot_nr : NFS4_NO_SLOT); ret = nfs41_setup_sequence(session, args, res, task); -out: + dprintk("<-- %s status=%d\n", __func__, ret); return ret; } -struct nfs41_call_sync_data { - const struct nfs_server *seq_server; - struct nfs4_sequence_args *seq_args; - struct nfs4_sequence_res *seq_res; -}; - static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata) { - struct nfs41_call_sync_data *data = calldata; + struct nfs4_call_sync_data *data = calldata; struct nfs4_session *session = nfs4_get_session(data->seq_server); dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server); @@ -714,7 +793,7 @@ static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata) static void nfs41_call_sync_done(struct rpc_task *task, void *calldata) { - struct nfs41_call_sync_data *data = calldata; + struct nfs4_call_sync_data *data = calldata; nfs41_sequence_done(task, data->seq_res); } @@ -724,6 +803,42 @@ static const struct rpc_call_ops nfs41_call_sync_ops = { .rpc_call_done = nfs41_call_sync_done, }; +#else /* !CONFIG_NFS_V4_1 */ + +static int nfs4_setup_sequence(const struct nfs_server *server, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + return nfs40_setup_sequence(server, args, res, task); +} + +static int nfs4_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res) +{ + return nfs40_sequence_done(task, res); +} + +#endif /* !CONFIG_NFS_V4_1 */ + +static void nfs40_call_sync_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_setup_sequence(data->seq_server, + data->seq_args, data->seq_res, task); +} + +static void nfs40_call_sync_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_sequence_done(task, data->seq_res); +} + +static const struct rpc_call_ops nfs40_call_sync_ops = { + .rpc_call_prepare = nfs40_call_sync_prepare, + .rpc_call_done = nfs40_call_sync_done, +}; + static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, struct nfs_server *server, struct rpc_message *msg, @@ -732,7 +847,8 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, { int ret; struct rpc_task *task; - struct nfs41_call_sync_data data = { + struct nfs_client *clp = server->nfs_client; + struct nfs4_call_sync_data data = { .seq_server = server, .seq_args = args, .seq_res = res, @@ -740,7 +856,7 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, struct rpc_task_setup task_setup = { .rpc_client = clnt, .rpc_message = msg, - .callback_ops = &nfs41_call_sync_ops, + .callback_ops = clp->cl_mvops->call_sync_ops, .callback_data = &data }; @@ -754,35 +870,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, return ret; } -#else -static -void nfs41_init_sequence(struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res, int cache_reply) -{ -} - -static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args) -{ -} - - -static int nfs4_sequence_done(struct rpc_task *task, - struct nfs4_sequence_res *res) -{ - return 1; -} -#endif /* CONFIG_NFS_V4_1 */ - -static -int _nfs4_call_sync(struct rpc_clnt *clnt, - struct nfs_server *server, - struct rpc_message *msg, - struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res) -{ - return rpc_call_sync(clnt, msg, 0); -} - static int nfs4_call_sync(struct rpc_clnt *clnt, struct nfs_server *server, @@ -791,9 +878,8 @@ int nfs4_call_sync(struct rpc_clnt *clnt, struct nfs4_sequence_res *res, int cache_reply) { - nfs41_init_sequence(args, res, cache_reply); - return server->nfs_client->cl_mvops->call_sync(clnt, server, msg, - args, res); + nfs4_init_sequence(args, res, cache_reply); + return nfs4_call_sync_sequence(clnt, server, msg, args, res); } static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) @@ -933,7 +1019,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.fh = NFS_FH(dentry->d_inode); } if (attrs != NULL && attrs->ia_valid != 0) { - __be32 verf[2]; + __u32 verf[2]; p->o_arg.u.attrs = &p->attrs; memcpy(&p->attrs, attrs, sizeof(p->attrs)); @@ -1103,7 +1189,7 @@ static int update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stat goto no_delegation; spin_lock(&deleg_cur->lock); - if (nfsi->delegation != deleg_cur || + if (rcu_dereference(nfsi->delegation) != deleg_cur || test_bit(NFS_DELEGATION_RETURNING, &deleg_cur->flags) || (deleg_cur->type & fmode) != fmode) goto no_delegation_unlock; @@ -1440,6 +1526,7 @@ static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state int err; do { err = _nfs4_do_open_reclaim(ctx, state); + trace_nfs4_open_reclaim(ctx, 0, err); if (nfs4_clear_cap_atomic_open_v1(server, err, &exception)) continue; if (err != -NFS4ERR_DELAY) @@ -1524,10 +1611,20 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state return nfs4_handle_delegation_recall_error(server, state, stateid, err); } +static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_opendata *data = calldata; + + nfs40_setup_sequence(data->o_arg.server, &data->o_arg.seq_args, + &data->o_res.seq_res, task); +} + static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; + nfs40_sequence_done(task, &data->o_res.seq_res); + data->rpc_status = task->tk_status; if (data->rpc_status == 0) { nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid); @@ -1556,6 +1653,7 @@ out_free: } static const struct rpc_call_ops nfs4_open_confirm_ops = { + .rpc_call_prepare = nfs4_open_confirm_prepare, .rpc_call_done = nfs4_open_confirm_done, .rpc_release = nfs4_open_confirm_release, }; @@ -1583,6 +1681,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) }; int status; + nfs4_init_sequence(&data->o_arg.seq_args, &data->o_res.seq_res, 1); kref_get(&data->kref); data->rpc_done = 0; data->rpc_status = 0; @@ -1742,7 +1841,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover) }; int status; - nfs41_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1); + nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1); kref_get(&data->kref); data->rpc_done = 0; data->rpc_status = 0; @@ -1895,6 +1994,7 @@ static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state do { err = _nfs4_open_expired(ctx, state); + trace_nfs4_open_expired(ctx, 0, err); if (nfs4_clear_cap_atomic_open_v1(server, err, &exception)) continue; switch (err) { @@ -1944,6 +2044,7 @@ static void nfs41_clear_delegation_stateid(struct nfs4_state *state) cred = get_rpccred(delegation->cred); rcu_read_unlock(); status = nfs41_test_stateid(server, stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); } else rcu_read_unlock(); @@ -1986,6 +2087,7 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) return -NFS4ERR_BAD_STATEID; status = nfs41_test_stateid(server, stateid, cred); + trace_nfs4_test_open_stateid(state, NULL, status); if (status != NFS_OK) { /* Free the stateid unless the server explicitly * informs us the stateid is unrecognized. */ @@ -2197,6 +2299,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, do { status = _nfs4_do_open(dir, ctx, flags, sattr, label); res = ctx->state; + trace_nfs4_open_file(ctx, flags, status); if (status == 0) break; /* NOTE: BAD_SEQID means the server and client disagree about the @@ -2310,6 +2413,7 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, int err; do { err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel); + trace_nfs4_setattr(inode, err); switch (err) { case -NFS4ERR_OPENMODE: if (!(sattr->ia_valid & ATTR_SIZE)) { @@ -2387,6 +2491,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data) dprintk("%s: begin!\n", __func__); if (!nfs4_sequence_done(task, &calldata->res.seq_res)) return; + trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status); /* hmm. we are done with the inode, and in the process of freeing * the state_owner. we keep this around to process errors */ @@ -2511,10 +2616,13 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) }; int status = -ENOMEM; + nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP, + &task_setup_data.rpc_client, &msg); + calldata = kzalloc(sizeof(*calldata), gfp_mask); if (calldata == NULL) goto out; - nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 1); + nfs4_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 1); calldata->inode = state->inode; calldata->state = state; calldata->arg.fh = NFS_FH(state->inode); @@ -2690,6 +2798,7 @@ static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, int err; do { err = _nfs4_lookup_root(server, fhandle, info); + trace_nfs4_lookup_root(server, fhandle, info->fattr, err); switch (err) { case 0: case -NFS4ERR_WRONGSEC: @@ -2705,10 +2814,13 @@ out: static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info, rpc_authflavor_t flavor) { + struct rpc_auth_create_args auth_args = { + .pseudoflavor = flavor, + }; struct rpc_auth *auth; int ret; - auth = rpcauth_create(flavor, server->client); + auth = rpcauth_create(&auth_args, server->client); if (IS_ERR(auth)) { ret = -EACCES; goto out; @@ -2772,18 +2884,27 @@ static int nfs4_do_find_root_sec(struct nfs_server *server, * @server: initialized nfs_server handle * @fhandle: we fill in the pseudo-fs root file handle * @info: we fill in an FSINFO struct + * @auth_probe: probe the auth flavours * * Returns zero on success, or a negative errno. */ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fsinfo *info) + struct nfs_fsinfo *info, + bool auth_probe) { int status; - status = nfs4_lookup_root(server, fhandle, info); - if ((status == -NFS4ERR_WRONGSEC) && - !(server->flags & NFS_MOUNT_SECFLAVOUR)) + switch (auth_probe) { + case false: + status = nfs4_lookup_root(server, fhandle, info); + if (status != -NFS4ERR_WRONGSEC) + break; + /* Did user force a 'sec=' mount option? */ + if (server->flags & NFS_MOUNT_SECFLAVOUR) + break; + default: status = nfs4_do_find_root_sec(server, fhandle, info); + } if (status == 0) status = nfs4_server_capabilities(server, fhandle); @@ -2899,8 +3020,9 @@ static int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(server, - _nfs4_proc_getattr(server, fhandle, fattr, label), + err = _nfs4_proc_getattr(server, fhandle, fattr, label); + trace_nfs4_getattr(server, fhandle, fattr, err); + err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); return err; @@ -2940,10 +3062,10 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, /* Deal with open(O_TRUNC) */ if (sattr->ia_valid & ATTR_OPEN) - sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN); + sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME); /* Optimization: if the end result is no change, don't RPC */ - if ((sattr->ia_valid & ~(ATTR_FILE)) == 0) + if ((sattr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0) return 0; /* Search for an existing open(O_WRITE) file */ @@ -3020,6 +3142,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, int err; do { err = _nfs4_proc_lookup(client, dir, name, fhandle, fattr, label); + trace_nfs4_lookup(dir, name, err); switch (err) { case -NFS4ERR_BADNAME: err = -ENOENT; @@ -3031,7 +3154,9 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, err = -EPERM; if (client != *clnt) goto out; - + /* No security negotiation if the user specified 'sec=' */ + if (NFS_SERVER(dir)->flags & NFS_MOUNT_SECFLAVOUR) + goto out; client = nfs4_create_sec_client(client, dir, name); if (IS_ERR(client)) return PTR_ERR(client); @@ -3071,15 +3196,13 @@ struct rpc_clnt * nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { + struct rpc_clnt *client = NFS_CLIENT(dir); int status; - struct rpc_clnt *client = rpc_clone_client(NFS_CLIENT(dir)); status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, NULL); - if (status < 0) { - rpc_shutdown_client(client); + if (status < 0) return ERR_PTR(status); - } - return client; + return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; } static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) @@ -3136,8 +3259,9 @@ static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(inode), - _nfs4_proc_access(inode, entry), + err = _nfs4_proc_access(inode, entry); + trace_nfs4_access(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); return err; @@ -3190,8 +3314,9 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page, struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(inode), - _nfs4_proc_readlink(inode, page, pgbase, pglen), + err = _nfs4_proc_readlink(inode, page, pgbase, pglen); + trace_nfs4_readlink(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); return err; @@ -3255,8 +3380,9 @@ static int nfs4_proc_remove(struct inode *dir, struct qstr *name) struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_remove(dir, name), + err = _nfs4_proc_remove(dir, name); + trace_nfs4_remove(dir, name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); return err; @@ -3270,7 +3396,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) res->server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; - nfs41_init_sequence(&args->seq_args, &res->seq_res, 1); + nfs4_init_sequence(&args->seq_args, &res->seq_res, 1); nfs_fattr_init(res->dir_attr); } @@ -3285,7 +3411,8 @@ static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlin static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) { - struct nfs_removeres *res = task->tk_msg.rpc_resp; + struct nfs_unlinkdata *data = task->tk_calldata; + struct nfs_removeres *res = &data->res; if (!nfs4_sequence_done(task, &res->seq_res)) return 0; @@ -3303,7 +3430,7 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir) msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME]; res->server = server; - nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1); + nfs4_init_sequence(&arg->seq_args, &res->seq_res, 1); } static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data) @@ -3317,7 +3444,8 @@ static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renam static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, struct inode *new_dir) { - struct nfs_renameres *res = task->tk_msg.rpc_resp; + struct nfs_renamedata *data = task->tk_calldata; + struct nfs_renameres *res = &data->res; if (!nfs4_sequence_done(task, &res->seq_res)) return 0; @@ -3363,9 +3491,10 @@ static int nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(old_dir), - _nfs4_proc_rename(old_dir, old_name, - new_dir, new_name), + err = _nfs4_proc_rename(old_dir, old_name, + new_dir, new_name); + trace_nfs4_rename(old_dir, old_name, new_dir, new_name, err); + err = nfs4_handle_exception(NFS_SERVER(old_dir), err, &exception); } while (exception.retry); return err; @@ -3527,9 +3656,9 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry, label = nfs4_label_init_security(dir, dentry, sattr, &l); do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_symlink(dir, dentry, page, - len, sattr, label), + err = _nfs4_proc_symlink(dir, dentry, page, len, sattr, label); + trace_nfs4_symlink(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); @@ -3566,8 +3695,9 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, sattr->ia_mode &= ~current_umask(); do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_mkdir(dir, dentry, sattr, label), + err = _nfs4_proc_mkdir(dir, dentry, sattr, label); + trace_nfs4_mkdir(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); nfs4_label_release_security(label); @@ -3620,9 +3750,10 @@ static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(dentry->d_inode), - _nfs4_proc_readdir(dentry, cred, cookie, - pages, count, plus), + err = _nfs4_proc_readdir(dentry, cred, cookie, + pages, count, plus); + trace_nfs4_readdir(dentry->d_inode, err); + err = nfs4_handle_exception(NFS_SERVER(dentry->d_inode), err, &exception); } while (exception.retry); return err; @@ -3674,8 +3805,9 @@ static int nfs4_proc_mknod(struct inode *dir, struct dentry *dentry, sattr->ia_mode &= ~current_umask(); do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_mknod(dir, dentry, sattr, label, rdev), + err = _nfs4_proc_mknod(dir, dentry, sattr, label, rdev); + trace_nfs4_mknod(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); @@ -3743,6 +3875,7 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str do { err = _nfs4_do_fsinfo(server, fhandle, fsinfo); + trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err); if (err == 0) { struct nfs_client *clp = server->nfs_client; @@ -3861,6 +3994,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { struct nfs_server *server = NFS_SERVER(data->header->inode); + trace_nfs4_read(data, task->tk_status); if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); return -EAGAIN; @@ -3904,24 +4038,29 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message data->timestamp = jiffies; data->read_done_cb = nfs4_read_done_cb; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; - nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); } -static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) +static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) - return; - nfs4_set_rw_stateid(&data->args.stateid, data->args.context, - data->args.lock_context, FMODE_READ); + return 0; + if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context, + data->args.lock_context, FMODE_READ) == -EIO) + return -EIO; + if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags))) + return -EIO; + return 0; } static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { struct inode *inode = data->header->inode; + trace_nfs4_write(data, task->tk_status); if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); return -EAGAIN; @@ -3987,18 +4126,22 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag data->timestamp = jiffies; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; - nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); } -static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) +static int nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) - return; - nfs4_set_rw_stateid(&data->args.stateid, data->args.context, - data->args.lock_context, FMODE_WRITE); + return 0; + if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context, + data->args.lock_context, FMODE_WRITE) == -EIO) + return -EIO; + if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags))) + return -EIO; + return 0; } static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) @@ -4013,6 +4156,7 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *da { struct inode *inode = data->inode; + trace_nfs4_commit(data, task->tk_status); if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) { rpc_restart_call_prepare(task); return -EAGAIN; @@ -4035,7 +4179,7 @@ static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_mess data->commit_done_cb = nfs4_commit_done_cb; data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; - nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); } struct nfs4_renewdata { @@ -4064,6 +4208,7 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata) struct nfs_client *clp = data->client; unsigned long timestamp = data->timestamp; + trace_nfs4_renew_async(clp, task->tk_status); if (task->tk_status < 0) { /* Unless we're shutting down, schedule state recovery! */ if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0) @@ -4321,6 +4466,7 @@ static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bufl ssize_t ret; do { ret = __nfs4_get_acl_uncached(inode, buf, buflen); + trace_nfs4_get_acl(inode, ret); if (ret >= 0) break; ret = nfs4_handle_exception(NFS_SERVER(inode), ret, &exception); @@ -4400,8 +4546,9 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(inode), - __nfs4_proc_set_acl(inode, buf, buflen), + err = __nfs4_proc_set_acl(inode, buf, buflen); + trace_nfs4_set_acl(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); return err; @@ -4454,8 +4601,9 @@ static int nfs4_get_security_label(struct inode *inode, void *buf, return -EOPNOTSUPP; do { - err = nfs4_handle_exception(NFS_SERVER(inode), - _nfs4_get_security_label(inode, buf, buflen), + err = _nfs4_get_security_label(inode, buf, buflen); + trace_nfs4_get_security_label(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); return err; @@ -4507,9 +4655,10 @@ static int nfs4_do_set_security_label(struct inode *inode, int err; do { - err = nfs4_handle_exception(NFS_SERVER(inode), - _nfs4_do_set_security_label(inode, ilabel, - fattr, olabel), + err = _nfs4_do_set_security_label(inode, ilabel, + fattr, olabel); + trace_nfs4_set_security_label(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); return err; @@ -4632,11 +4781,11 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, /* An impossible timestamp guarantees this value * will never match a generated boot time. */ verf[0] = 0; - verf[1] = (__be32)(NSEC_PER_SEC + 1); + verf[1] = cpu_to_be32(NSEC_PER_SEC + 1); } else { struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); - verf[0] = (__be32)nn->boot_time.tv_sec; - verf[1] = (__be32)nn->boot_time.tv_nsec; + verf[0] = cpu_to_be32(nn->boot_time.tv_sec); + verf[1] = cpu_to_be32(nn->boot_time.tv_nsec); } memcpy(bootverf->data, verf, sizeof(bootverf->data)); } @@ -4662,10 +4811,14 @@ static unsigned int nfs4_init_uniform_client_string(const struct nfs_client *clp, char *buf, size_t len) { - char *nodename = clp->cl_rpcclient->cl_nodename; + const char *nodename = clp->cl_rpcclient->cl_nodename; if (nfs4_client_id_uniquifier[0] != '\0') - nodename = nfs4_client_id_uniquifier; + return scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", + clp->rpc_ops->version, + clp->cl_minorversion, + nfs4_client_id_uniquifier, + nodename); return scnprintf(buf, len, "Linux NFSv%u.%u %s", clp->rpc_ops->version, clp->cl_minorversion, nodename); @@ -4726,6 +4879,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, clp->cl_rpcclient->cl_auth->au_ops->au_name, setclientid.sc_name_len, setclientid.sc_name); status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_setclientid(clp, status); dprintk("NFS reply setclientid: %d\n", status); return status; } @@ -4753,6 +4907,7 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, clp->cl_rpcclient->cl_auth->au_ops->au_name, clp->cl_clientid); status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_setclientid_confirm(clp, status); dprintk("NFS reply setclientid_confirm: %d\n", status); return status; } @@ -4774,6 +4929,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) if (!nfs4_sequence_done(task, &data->res.seq_res)) return; + trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status); switch (task->tk_status) { case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: @@ -4795,7 +4951,6 @@ static void nfs4_delegreturn_release(void *calldata) kfree(calldata); } -#if defined(CONFIG_NFS_V4_1) static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) { struct nfs4_delegreturndata *d_data; @@ -4807,12 +4962,9 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) &d_data->res.seq_res, task); } -#endif /* CONFIG_NFS_V4_1 */ static const struct rpc_call_ops nfs4_delegreturn_ops = { -#if defined(CONFIG_NFS_V4_1) .rpc_call_prepare = nfs4_delegreturn_prepare, -#endif /* CONFIG_NFS_V4_1 */ .rpc_call_done = nfs4_delegreturn_done, .rpc_release = nfs4_delegreturn_release, }; @@ -4837,7 +4989,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co data = kzalloc(sizeof(*data), GFP_NOFS); if (data == NULL) return -ENOMEM; - nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; data->args.bitmask = server->cache_consistency_bitmask; @@ -4877,6 +5029,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4 int err; do { err = _nfs4_proc_delegreturn(inode, cred, stateid, issync); + trace_nfs4_delegreturn(inode, err); switch (err) { case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: @@ -4951,8 +5104,9 @@ static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock * int err; do { - err = nfs4_handle_exception(NFS_SERVER(state->inode), - _nfs4_proc_getlk(state, cmd, request), + err = _nfs4_proc_getlk(state, cmd, request); + trace_nfs4_get_lock(request, state, cmd, err); + err = nfs4_handle_exception(NFS_SERVER(state->inode), err, &exception); } while (exception.retry); return err; @@ -5089,6 +5243,9 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl, .flags = RPC_TASK_ASYNC, }; + nfs4_state_protect(NFS_SERVER(lsp->ls_state->inode)->nfs_client, + NFS_SP4_MACH_CRED_CLEANUP, &task_setup_data.rpc_client, &msg); + /* Ensure this is an unlock - when canceling a lock, the * canceled lock is passed in, and it won't be an unlock. */ @@ -5100,7 +5257,7 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl, return ERR_PTR(-ENOMEM); } - nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1); + nfs4_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1); msg.rpc_argp = &data->arg; msg.rpc_resp = &data->res; task_setup_data.callback_data = data; @@ -5150,6 +5307,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock * rpc_put_task(task); out: request->fl_flags = fl_flags; + trace_nfs4_unlock(request, state, F_SETLK, status); return status; } @@ -5335,7 +5493,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f return -ENOMEM; if (IS_SETLKW(cmd)) data->arg.block = 1; - nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1); + nfs4_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1); msg.rpc_argp = &data->arg; msg.rpc_resp = &data->res; task_setup_data.callback_data = data; @@ -5373,6 +5531,7 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM); + trace_nfs4_lock_reclaim(request, state, F_SETLK, err); if (err != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, err, &exception); @@ -5391,10 +5550,15 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request err = nfs4_set_lock_state(state, request); if (err != 0) return err; + if (!recover_lost_locks) { + set_bit(NFS_LOCK_LOST, &request->fl_u.nfs4_fl.owner->ls_flags); + return 0; + } do { if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED); + trace_nfs4_lock_expired(request, state, F_SETLK, err); switch (err) { default: goto out; @@ -5430,6 +5594,7 @@ static int nfs41_check_expired_locks(struct nfs4_state *state) status = nfs41_test_stateid(server, &lsp->ls_stateid, cred); + trace_nfs4_test_lock_stateid(state, lsp, status); if (status != NFS_OK) { /* Free the stateid unless the server * informs us the stateid is unrecognized. */ @@ -5517,6 +5682,7 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock * do { err = _nfs4_proc_setlk(state, cmd, request); + trace_nfs4_set_lock(request, state, cmd, err); if (err == -NFS4ERR_DENIED) err = -EAGAIN; err = nfs4_handle_exception(NFS_SERVER(state->inode), @@ -5599,8 +5765,23 @@ struct nfs_release_lockowner_data { struct nfs4_lock_state *lsp; struct nfs_server *server; struct nfs_release_lockowner_args args; + struct nfs4_sequence_args seq_args; + struct nfs4_sequence_res seq_res; }; +static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_release_lockowner_data *data = calldata; + nfs40_setup_sequence(data->server, + &data->seq_args, &data->seq_res, task); +} + +static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) +{ + struct nfs_release_lockowner_data *data = calldata; + nfs40_sequence_done(task, &data->seq_res); +} + static void nfs4_release_lockowner_release(void *calldata) { struct nfs_release_lockowner_data *data = calldata; @@ -5609,6 +5790,8 @@ static void nfs4_release_lockowner_release(void *calldata) } static const struct rpc_call_ops nfs4_release_lockowner_ops = { + .rpc_call_prepare = nfs4_release_lockowner_prepare, + .rpc_call_done = nfs4_release_lockowner_done, .rpc_release = nfs4_release_lockowner_release, }; @@ -5621,14 +5804,17 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st if (server->nfs_client->cl_mvops->minor_version != 0) return -EINVAL; + data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) return -ENOMEM; + nfs4_init_sequence(&data->seq_args, &data->seq_res, 0); data->lsp = lsp; data->server = server; data->args.lock_owner.clientid = server->nfs_client->cl_clientid; data->args.lock_owner.id = lsp->ls_seqid.owner_id; data->args.lock_owner.s_dev = server->s_dev; + msg.rpc_argp = &data->args; rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data); return 0; @@ -5783,14 +5969,23 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_fs_locations(client, dir, name, fs_locations, page), + err = _nfs4_proc_fs_locations(client, dir, name, + fs_locations, page); + trace_nfs4_get_fs_locations(dir, name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); return err; } -static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors) +/** + * If 'use_integrity' is true and the state managment nfs_client + * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient + * and the machine credential as per RFC3530bis and RFC5661 Security + * Considerations sections. Otherwise, just use the user cred with the + * filesystem's rpc_client. + */ +static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors, bool use_integrity) { int status; struct nfs4_secinfo_arg args = { @@ -5805,10 +6000,27 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct .rpc_argp = &args, .rpc_resp = &res, }; + struct rpc_clnt *clnt = NFS_SERVER(dir)->client; + struct rpc_cred *cred = NULL; + + if (use_integrity) { + clnt = NFS_SERVER(dir)->nfs_client->cl_rpcclient; + cred = nfs4_get_clid_cred(NFS_SERVER(dir)->nfs_client); + msg.rpc_cred = cred; + } dprintk("NFS call secinfo %s\n", name->name); - status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); + + nfs4_state_protect(NFS_SERVER(dir)->nfs_client, + NFS_SP4_MACH_CRED_SECINFO, &clnt, &msg); + + status = nfs4_call_sync(clnt, NFS_SERVER(dir), &msg, &args.seq_args, + &res.seq_res, 0); dprintk("NFS reply secinfo: %d\n", status); + + if (cred) + put_rpccred(cred); + return status; } @@ -5818,8 +6030,23 @@ int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_secinfo(dir, name, flavors), + err = -NFS4ERR_WRONGSEC; + + /* try to use integrity protection with machine cred */ + if (_nfs4_is_integrity_protected(NFS_SERVER(dir)->nfs_client)) + err = _nfs4_proc_secinfo(dir, name, flavors, true); + + /* + * if unable to use integrity protection, or SECINFO with + * integrity protection returns NFS4ERR_WRONGSEC (which is + * disallowed by spec, but exists in deployed servers) use + * the current filesystem's rpc_client and the user cred. + */ + if (err == -NFS4ERR_WRONGSEC) + err = _nfs4_proc_secinfo(dir, name, flavors, false); + + trace_nfs4_secinfo(dir, name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); return err; @@ -5883,6 +6110,7 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred } status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_bind_conn_to_session(clp, status); if (status == 0) { if (memcmp(res.session->sess_id.data, clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { @@ -5911,16 +6139,126 @@ out: } /* - * nfs4_proc_exchange_id() + * Minimum set of SP4_MACH_CRED operations from RFC 5661 in the enforce map + * and operations we'd like to see to enable certain features in the allow map + */ +static const struct nfs41_state_protection nfs4_sp4_mach_cred_request = { + .how = SP4_MACH_CRED, + .enforce.u.words = { + [1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) | + 1 << (OP_EXCHANGE_ID - 32) | + 1 << (OP_CREATE_SESSION - 32) | + 1 << (OP_DESTROY_SESSION - 32) | + 1 << (OP_DESTROY_CLIENTID - 32) + }, + .allow.u.words = { + [0] = 1 << (OP_CLOSE) | + 1 << (OP_LOCKU) | + 1 << (OP_COMMIT), + [1] = 1 << (OP_SECINFO - 32) | + 1 << (OP_SECINFO_NO_NAME - 32) | + 1 << (OP_TEST_STATEID - 32) | + 1 << (OP_FREE_STATEID - 32) | + 1 << (OP_WRITE - 32) + } +}; + +/* + * Select the state protection mode for client `clp' given the server results + * from exchange_id in `sp'. * - * Returns zero, a negative errno, or a negative NFS4ERR status code. + * Returns 0 on success, negative errno otherwise. + */ +static int nfs4_sp4_select_mode(struct nfs_client *clp, + struct nfs41_state_protection *sp) +{ + static const u32 supported_enforce[NFS4_OP_MAP_NUM_WORDS] = { + [1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) | + 1 << (OP_EXCHANGE_ID - 32) | + 1 << (OP_CREATE_SESSION - 32) | + 1 << (OP_DESTROY_SESSION - 32) | + 1 << (OP_DESTROY_CLIENTID - 32) + }; + unsigned int i; + + if (sp->how == SP4_MACH_CRED) { + /* Print state protect result */ + dfprintk(MOUNT, "Server SP4_MACH_CRED support:\n"); + for (i = 0; i <= LAST_NFS4_OP; i++) { + if (test_bit(i, sp->enforce.u.longs)) + dfprintk(MOUNT, " enforce op %d\n", i); + if (test_bit(i, sp->allow.u.longs)) + dfprintk(MOUNT, " allow op %d\n", i); + } + + /* make sure nothing is on enforce list that isn't supported */ + for (i = 0; i < NFS4_OP_MAP_NUM_WORDS; i++) { + if (sp->enforce.u.words[i] & ~supported_enforce[i]) { + dfprintk(MOUNT, "sp4_mach_cred: disabled\n"); + return -EINVAL; + } + } + + /* + * Minimal mode - state operations are allowed to use machine + * credential. Note this already happens by default, so the + * client doesn't have to do anything more than the negotiation. + * + * NOTE: we don't care if EXCHANGE_ID is in the list - + * we're already using the machine cred for exchange_id + * and will never use a different cred. + */ + if (test_bit(OP_BIND_CONN_TO_SESSION, sp->enforce.u.longs) && + test_bit(OP_CREATE_SESSION, sp->enforce.u.longs) && + test_bit(OP_DESTROY_SESSION, sp->enforce.u.longs) && + test_bit(OP_DESTROY_CLIENTID, sp->enforce.u.longs)) { + dfprintk(MOUNT, "sp4_mach_cred:\n"); + dfprintk(MOUNT, " minimal mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_MINIMAL, &clp->cl_sp4_flags); + } else { + dfprintk(MOUNT, "sp4_mach_cred: disabled\n"); + return -EINVAL; + } + + if (test_bit(OP_CLOSE, sp->allow.u.longs) && + test_bit(OP_LOCKU, sp->allow.u.longs)) { + dfprintk(MOUNT, " cleanup mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags); + } + + if (test_bit(OP_SECINFO, sp->allow.u.longs) && + test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) { + dfprintk(MOUNT, " secinfo mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_SECINFO, &clp->cl_sp4_flags); + } + + if (test_bit(OP_TEST_STATEID, sp->allow.u.longs) && + test_bit(OP_FREE_STATEID, sp->allow.u.longs)) { + dfprintk(MOUNT, " stateid mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_STATEID, &clp->cl_sp4_flags); + } + + if (test_bit(OP_WRITE, sp->allow.u.longs)) { + dfprintk(MOUNT, " write mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_WRITE, &clp->cl_sp4_flags); + } + + if (test_bit(OP_COMMIT, sp->allow.u.longs)) { + dfprintk(MOUNT, " commit mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags); + } + } + + return 0; +} + +/* + * _nfs4_proc_exchange_id() * - * Since the clientid has expired, all compounds using sessions - * associated with the stale clientid will be returning - * NFS4ERR_BADSESSION in the sequence operation, and will therefore - * be in some phase of session reset. + * Wrapper for EXCHANGE_ID operation. */ -int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) +static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, + u32 sp4_how) { nfs4_verifier verifier; struct nfs41_exchange_id_args args = { @@ -5967,10 +6305,30 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) goto out_server_scope; } + switch (sp4_how) { + case SP4_NONE: + args.state_protect.how = SP4_NONE; + break; + + case SP4_MACH_CRED: + args.state_protect = nfs4_sp4_mach_cred_request; + break; + + default: + /* unsupported! */ + WARN_ON_ONCE(1); + status = -EINVAL; + goto out_server_scope; + } + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_exchange_id(clp, status); if (status == 0) status = nfs4_check_cl_exchange_flags(res.flags); + if (status == 0) + status = nfs4_sp4_select_mode(clp, &res.state_protect); + if (status == 0) { clp->cl_clientid = res.clientid; clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R); @@ -6017,6 +6375,35 @@ out: return status; } +/* + * nfs4_proc_exchange_id() + * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + * + * Since the clientid has expired, all compounds using sessions + * associated with the stale clientid will be returning + * NFS4ERR_BADSESSION in the sequence operation, and will therefore + * be in some phase of session reset. + * + * Will attempt to negotiate SP4_MACH_CRED if krb5i / krb5p auth is used. + */ +int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) +{ + rpc_authflavor_t authflavor = clp->cl_rpcclient->cl_auth->au_flavor; + int status; + + /* try SP4_MACH_CRED if krb5i/p */ + if (authflavor == RPC_AUTH_GSS_KRB5I || + authflavor == RPC_AUTH_GSS_KRB5P) { + status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED); + if (!status) + return 0; + } + + /* try SP4_NONE */ + return _nfs4_proc_exchange_id(clp, cred, SP4_NONE); +} + static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, struct rpc_cred *cred) { @@ -6028,6 +6415,7 @@ static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, int status; status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_destroy_clientid(clp, status); if (status) dprintk("NFS: Got error %d from the server %s on " "DESTROY_CLIENTID.", status, clp->cl_hostname); @@ -6065,7 +6453,7 @@ int nfs4_destroy_clientid(struct nfs_client *clp) goto out; if (clp->cl_preserve_clid) goto out; - cred = nfs4_get_exchange_id_cred(clp); + cred = nfs4_get_clid_cred(clp); ret = nfs4_proc_destroy_clientid(clp, cred); if (cred) put_rpccred(cred); @@ -6157,7 +6545,7 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo) }; int status; - nfs41_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0); + nfs4_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0); nfs4_set_sequence_privileged(&args.la_seq_args); dprintk("--> %s\n", __func__); task = rpc_run_task(&task_setup); @@ -6291,6 +6679,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp, args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN); status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_create_session(clp, status); if (!status) { /* Verify the session's negotiated channel_attrs values */ @@ -6354,6 +6743,7 @@ int nfs4_proc_destroy_session(struct nfs4_session *session, return status; status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + trace_nfs4_destroy_session(session->clp, status); if (status) dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " @@ -6403,6 +6793,7 @@ static void nfs41_sequence_call_done(struct rpc_task *task, void *data) if (!nfs41_sequence_done(task, task->tk_msg.rpc_resp)) return; + trace_nfs4_sequence(clp, task->tk_status); if (task->tk_status < 0) { dprintk("%s ERROR %d\n", __func__, task->tk_status); if (atomic_read(&clp->cl_count) == 1) @@ -6460,7 +6851,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, nfs_put_client(clp); return ERR_PTR(-ENOMEM); } - nfs41_init_sequence(&calldata->args, &calldata->res, 0); + nfs4_init_sequence(&calldata->args, &calldata->res, 0); if (is_privileged) nfs4_set_sequence_privileged(&calldata->args); msg.rpc_argp = &calldata->args; @@ -6555,6 +6946,7 @@ static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data) if (!nfs41_sequence_done(task, res)) return; + trace_nfs4_reclaim_complete(clp, task->tk_status); if (nfs41_reclaim_complete_handle_errors(task, clp) == -EAGAIN) { rpc_restart_call_prepare(task); return; @@ -6602,7 +6994,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp, calldata->clp = clp; calldata->arg.one_fs = 0; - nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0); + nfs4_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0); nfs4_set_sequence_privileged(&calldata->arg.seq_args); msg.rpc_argp = &calldata->arg; msg.rpc_resp = &calldata->res; @@ -6793,7 +7185,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->res.layoutp = &lgp->args.layout; lgp->res.seq_res.sr_slot = NULL; - nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); + nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ pnfs_get_layout_hdr(NFS_I(inode)->layout); @@ -6804,6 +7196,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) status = nfs4_wait_for_completion_rpc_task(task); if (status == 0) status = task->tk_status; + trace_nfs4_layoutget(lgp->args.ctx, + &lgp->args.range, + &lgp->res.range, + status); /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ if (status == 0 && lgp->res.layoutp->len) lseg = pnfs_layout_process(lgp); @@ -6876,7 +7272,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) .rpc_cred = lrp->cred, }; struct rpc_task_setup task_setup_data = { - .rpc_client = lrp->clp->cl_rpcclient, + .rpc_client = NFS_SERVER(lrp->args.inode)->client, .rpc_message = &msg, .callback_ops = &nfs4_layoutreturn_call_ops, .callback_data = lrp, @@ -6884,11 +7280,12 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) int status; dprintk("--> %s\n", __func__); - nfs41_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1); + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); status = task->tk_status; + trace_nfs4_layoutreturn(lrp->args.inode, status); dprintk("<-- %s status=%d\n", __func__, status); rpc_put_task(task); return status; @@ -7065,7 +7462,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) data->args.lastbytewritten, data->args.inode->i_ino); - nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -7075,15 +7472,21 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) if (status != 0) goto out; status = task->tk_status; + trace_nfs4_layoutcommit(data->args.inode, status); out: dprintk("%s: status %d\n", __func__, status); rpc_put_task(task); return status; } +/** + * Use the state managment nfs_client cl_rpcclient, which uses krb5i (if + * possible) as per RFC3530bis and RFC5661 Security Considerations sections + */ static int _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors) + struct nfs_fsinfo *info, + struct nfs4_secinfo_flavors *flavors, bool use_integrity) { struct nfs41_secinfo_no_name_args args = { .style = SECINFO_STYLE_CURRENT_FH, @@ -7096,7 +7499,25 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_argp = &args, .rpc_resp = &res, }; - return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + struct rpc_clnt *clnt = server->client; + struct rpc_cred *cred = NULL; + int status; + + if (use_integrity) { + clnt = server->nfs_client->cl_rpcclient; + cred = nfs4_get_clid_cred(server->nfs_client); + msg.rpc_cred = cred; + } + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("<-- %s status=%d\n", __func__, status); + + if (cred) + put_rpccred(cred); + + return status; } static int @@ -7106,7 +7527,24 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs4_exception exception = { }; int err; do { - err = _nfs41_proc_secinfo_no_name(server, fhandle, info, flavors); + /* first try using integrity protection */ + err = -NFS4ERR_WRONGSEC; + + /* try to use integrity protection with machine cred */ + if (_nfs4_is_integrity_protected(server->nfs_client)) + err = _nfs41_proc_secinfo_no_name(server, fhandle, info, + flavors, true); + + /* + * if unable to use integrity protection, or SECINFO with + * integrity protection returns NFS4ERR_WRONGSEC (which is + * disallowed by spec, but exists in deployed servers) use + * the current filesystem's rpc_client and the user cred. + */ + if (err == -NFS4ERR_WRONGSEC) + err = _nfs41_proc_secinfo_no_name(server, fhandle, info, + flavors, false); + switch (err) { case 0: case -NFS4ERR_WRONGSEC: @@ -7176,11 +7614,15 @@ static int _nfs41_test_stateid(struct nfs_server *server, .rpc_resp = &res, .rpc_cred = cred, }; + struct rpc_clnt *rpc_client = server->client; + + nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID, + &rpc_client, &msg); dprintk("NFS call test_stateid %p\n", stateid); - nfs41_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); nfs4_set_sequence_privileged(&args.seq_args); - status = nfs4_call_sync_sequence(server->client, server, &msg, + status = nfs4_call_sync_sequence(rpc_client, server, &msg, &args.seq_args, &res.seq_res); if (status != NFS_OK) { dprintk("NFS reply test_stateid: failed, %d\n", status); @@ -7249,7 +7691,7 @@ static void nfs41_free_stateid_release(void *calldata) kfree(calldata); } -const struct rpc_call_ops nfs41_free_stateid_ops = { +static const struct rpc_call_ops nfs41_free_stateid_ops = { .rpc_call_prepare = nfs41_free_stateid_prepare, .rpc_call_done = nfs41_free_stateid_done, .rpc_release = nfs41_free_stateid_release, @@ -7272,6 +7714,9 @@ static struct rpc_task *_nfs41_free_stateid(struct nfs_server *server, }; struct nfs_free_stateid_data *data; + nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID, + &task_setup.rpc_client, &msg); + dprintk("NFS call free_stateid %p\n", stateid); data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) @@ -7283,7 +7728,7 @@ static struct rpc_task *_nfs41_free_stateid(struct nfs_server *server, msg.rpc_argp = &data->args; msg.rpc_resp = &data->res; - nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); if (privileged) nfs4_set_sequence_privileged(&data->args.seq_args); @@ -7359,7 +7804,6 @@ static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = { .recover_open = nfs4_open_reclaim, .recover_lock = nfs4_lock_reclaim, .establish_clid = nfs4_init_clientid, - .get_clid_cred = nfs4_get_setclientid_cred, .detect_trunking = nfs40_discover_server_trunking, }; @@ -7370,7 +7814,6 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { .recover_open = nfs4_open_reclaim, .recover_lock = nfs4_lock_reclaim, .establish_clid = nfs41_init_clientid, - .get_clid_cred = nfs4_get_exchange_id_cred, .reclaim_complete = nfs41_proc_reclaim_complete, .detect_trunking = nfs41_discover_server_trunking, }; @@ -7382,7 +7825,6 @@ static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { .recover_open = nfs4_open_expired, .recover_lock = nfs4_lock_expired, .establish_clid = nfs4_init_clientid, - .get_clid_cred = nfs4_get_setclientid_cred, }; #if defined(CONFIG_NFS_V4_1) @@ -7392,7 +7834,6 @@ static const struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = { .recover_open = nfs41_open_expired, .recover_lock = nfs41_lock_expired, .establish_clid = nfs41_init_clientid, - .get_clid_cred = nfs4_get_exchange_id_cred, }; #endif /* CONFIG_NFS_V4_1 */ @@ -7416,10 +7857,12 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { | NFS_CAP_ATOMIC_OPEN | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK, - .call_sync = _nfs4_call_sync, + .init_client = nfs40_init_client, + .shutdown_client = nfs40_shutdown_client, .match_stateid = nfs4_match_stateid, .find_root_sec = nfs4_find_root_sec, .free_lock_state = nfs4_release_lockowner, + .call_sync_ops = &nfs40_call_sync_ops, .reboot_recovery_ops = &nfs40_reboot_recovery_ops, .nograce_recovery_ops = &nfs40_nograce_recovery_ops, .state_renewal_ops = &nfs40_state_renewal_ops, @@ -7434,10 +7877,12 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1, - .call_sync = nfs4_call_sync_sequence, + .init_client = nfs41_init_client, + .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, .find_root_sec = nfs41_find_root_sec, .free_lock_state = nfs41_free_lock_state, + .call_sync_ops = &nfs41_call_sync_ops, .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, .state_renewal_ops = &nfs41_state_renewal_ops, @@ -7453,10 +7898,12 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1, - .call_sync = nfs4_call_sync_sequence, + .init_client = nfs41_init_client, + .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, .find_root_sec = nfs41_find_root_sec, .free_lock_state = nfs41_free_lock_state, + .call_sync_ops = &nfs41_call_sync_ops, .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, .state_renewal_ops = &nfs41_state_renewal_ops, @@ -7473,7 +7920,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { #endif }; -const struct inode_operations nfs4_dir_inode_operations = { +static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, .atomic_open = nfs_atomic_open, diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index 36e21cb..cf883c7 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -23,6 +23,14 @@ #define NFSDBG_FACILITY NFSDBG_STATE +static void nfs4_init_slot_table(struct nfs4_slot_table *tbl, const char *queue) +{ + tbl->highest_used_slotid = NFS4_NO_SLOT; + spin_lock_init(&tbl->slot_tbl_lock); + rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue); + init_completion(&tbl->complete); +} + /* * nfs4_shrink_slot_table - free retired slots from the slot table */ @@ -44,6 +52,17 @@ static void nfs4_shrink_slot_table(struct nfs4_slot_table *tbl, u32 newsize) } } +/** + * nfs4_slot_tbl_drain_complete - wake waiters when drain is complete + * @tbl - controlling slot table + * + */ +void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl) +{ + if (nfs4_slot_tbl_draining(tbl)) + complete(&tbl->complete); +} + /* * nfs4_free_slot - free a slot and efficiently update slot table. * @@ -76,7 +95,7 @@ void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot) nfs4_slot_tbl_drain_complete(tbl); } } - dprintk("%s: slotid %u highest_used_slotid %d\n", __func__, + dprintk("%s: slotid %u highest_used_slotid %u\n", __func__, slotid, tbl->highest_used_slotid); } @@ -146,9 +165,9 @@ struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl) ret->generation = tbl->generation; out: - dprintk("<-- %s used_slots=%04lx highest_used=%d slotid=%d \n", + dprintk("<-- %s used_slots=%04lx highest_used=%u slotid=%u\n", __func__, tbl->used_slots[0], tbl->highest_used_slotid, - !IS_ERR(ret) ? ret->slot_nr : -1); + !IS_ERR(ret) ? ret->slot_nr : NFS4_NO_SLOT); return ret; } @@ -191,7 +210,7 @@ static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, { int ret; - dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__, + dprintk("--> %s: max_reqs=%u, tbl->max_slots %u\n", __func__, max_reqs, tbl->max_slots); if (max_reqs > NFS4_MAX_SLOT_TABLE) @@ -205,18 +224,36 @@ static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, nfs4_reset_slot_table(tbl, max_reqs - 1, ivalue); spin_unlock(&tbl->slot_tbl_lock); - dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__, + dprintk("%s: tbl=%p slots=%p max_slots=%u\n", __func__, tbl, tbl->slots, tbl->max_slots); out: dprintk("<-- %s: return %d\n", __func__, ret); return ret; } -/* Destroy the slot table */ -static void nfs4_destroy_slot_tables(struct nfs4_session *session) +/** + * nfs4_release_slot_table - release resources attached to a slot table + * @tbl: slot table to shut down + * + */ +void nfs4_release_slot_table(struct nfs4_slot_table *tbl) +{ + nfs4_shrink_slot_table(tbl, 0); +} + +/** + * nfs4_setup_slot_table - prepare a stand-alone slot table for use + * @tbl: slot table to set up + * @max_reqs: maximum number of requests allowed + * @queue: name to give RPC wait queue + * + * Returns zero on success, or a negative errno. + */ +int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, unsigned int max_reqs, + const char *queue) { - nfs4_shrink_slot_table(&session->fc_slot_table, 0); - nfs4_shrink_slot_table(&session->bc_slot_table, 0); + nfs4_init_slot_table(tbl, queue); + return nfs4_realloc_slot_table(tbl, max_reqs, 0); } static bool nfs41_assign_slot(struct rpc_task *task, void *pslot) @@ -273,6 +310,8 @@ void nfs41_wake_slot_table(struct nfs4_slot_table *tbl) } } +#if defined(CONFIG_NFS_V4_1) + static void nfs41_set_max_slotid_locked(struct nfs4_slot_table *tbl, u32 target_highest_slotid) { @@ -383,6 +422,12 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, spin_unlock(&tbl->slot_tbl_lock); } +static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) +{ + nfs4_release_slot_table(&session->fc_slot_table); + nfs4_release_slot_table(&session->bc_slot_table); +} + /* * Initialize or reset the forechannel and backchannel tables */ @@ -405,31 +450,20 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses) if (status && tbl->slots == NULL) /* Fore and back channel share a connection so get * both slot tables or neither */ - nfs4_destroy_slot_tables(ses); + nfs4_destroy_session_slot_tables(ses); return status; } struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp) { struct nfs4_session *session; - struct nfs4_slot_table *tbl; session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS); if (!session) return NULL; - tbl = &session->fc_slot_table; - tbl->highest_used_slotid = NFS4_NO_SLOT; - spin_lock_init(&tbl->slot_tbl_lock); - rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table"); - init_completion(&tbl->complete); - - tbl = &session->bc_slot_table; - tbl->highest_used_slotid = NFS4_NO_SLOT; - spin_lock_init(&tbl->slot_tbl_lock); - rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table"); - init_completion(&tbl->complete); - + nfs4_init_slot_table(&session->fc_slot_table, "ForeChannel Slot table"); + nfs4_init_slot_table(&session->bc_slot_table, "BackChannel Slot table"); session->session_state = 1<<NFS4_SESSION_INITING; session->clp = clp; @@ -441,7 +475,7 @@ void nfs4_destroy_session(struct nfs4_session *session) struct rpc_xprt *xprt; struct rpc_cred *cred; - cred = nfs4_get_exchange_id_cred(session->clp); + cred = nfs4_get_clid_cred(session->clp); nfs4_proc_destroy_session(session, cred); if (cred) put_rpccred(cred); @@ -452,7 +486,7 @@ void nfs4_destroy_session(struct nfs4_session *session) dprintk("%s Destroy backchannel for xprt %p\n", __func__, xprt); xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS); - nfs4_destroy_slot_tables(session); + nfs4_destroy_session_slot_tables(session); kfree(session); } @@ -513,4 +547,4 @@ int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time) } EXPORT_SYMBOL_GPL(nfs4_init_ds_session); - +#endif /* defined(CONFIG_NFS_V4_1) */ diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 3a153d8..2323061 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -8,7 +8,7 @@ #define __LINUX_FS_NFS_NFS4SESSION_H /* maximum number of slots to use */ -#define NFS4_DEF_SLOT_TABLE_SIZE (16U) +#define NFS4_DEF_SLOT_TABLE_SIZE (64U) #define NFS4_MAX_SLOT_TABLE (1024U) #define NFS4_NO_SLOT ((u32)-1) @@ -72,10 +72,22 @@ enum nfs4_session_state { NFS4_SESSION_INITING, }; -#if defined(CONFIG_NFS_V4_1) +extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, + unsigned int max_reqs, const char *queue); +extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl); extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); +extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); +bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl, + struct nfs4_slot *slot); +void nfs41_wake_slot_table(struct nfs4_slot_table *tbl); + +static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl) +{ + return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); +} +#if defined(CONFIG_NFS_V4_1) extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl, u32 target_highest_slotid); extern void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, @@ -89,17 +101,6 @@ extern void nfs4_destroy_session(struct nfs4_session *session); extern int nfs4_init_session(struct nfs_client *clp); extern int nfs4_init_ds_session(struct nfs_client *, unsigned long); -extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); - -static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl) -{ - return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); -} - -bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl, - struct nfs4_slot *slot); -void nfs41_wake_slot_table(struct nfs4_slot_table *tbl); - /* * Determine if sessions are in use. */ @@ -117,6 +118,16 @@ static inline int nfs4_has_persistent_session(const struct nfs_client *clp) return 0; } +#ifdef CONFIG_CRC32 +/* + * nfs_session_id_hash - calculate the crc32 hash for the session id + * @session - pointer to session + */ +#define nfs_session_id_hash(sess_id) \ + (~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data))) +#else +#define nfs_session_id_hash(session) (0) +#endif #else /* defined(CONFIG_NFS_V4_1) */ static inline int nfs4_init_session(struct nfs_client *clp) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e22862f..cc14cbb 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -154,6 +154,19 @@ struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp) return cred; } +static void nfs4_root_machine_cred(struct nfs_client *clp) +{ + struct rpc_cred *cred, *new; + + new = rpc_lookup_machine_cred(NULL); + spin_lock(&clp->cl_lock); + cred = clp->cl_machine_cred; + clp->cl_machine_cred = new; + spin_unlock(&clp->cl_lock); + if (cred != NULL) + put_rpccred(cred); +} + static struct rpc_cred * nfs4_get_renew_cred_server_locked(struct nfs_server *server) { @@ -202,32 +215,6 @@ out: return cred; } -#if defined(CONFIG_NFS_V4_1) - -static int nfs41_setup_state_renewal(struct nfs_client *clp) -{ - int status; - struct nfs_fsinfo fsinfo; - - if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { - nfs4_schedule_state_renewal(clp); - return 0; - } - - status = nfs4_proc_get_lease_time(clp, &fsinfo); - if (status == 0) { - /* Update lease time and schedule renewal */ - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo.lease_time * HZ; - clp->cl_last_renewal = jiffies; - spin_unlock(&clp->cl_lock); - - nfs4_schedule_state_renewal(clp); - } - - return status; -} - static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl) { if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) { @@ -241,20 +228,18 @@ static void nfs4_end_drain_session(struct nfs_client *clp) { struct nfs4_session *ses = clp->cl_session; + if (clp->cl_slot_tbl) { + nfs4_end_drain_slot_table(clp->cl_slot_tbl); + return; + } + if (ses != NULL) { nfs4_end_drain_slot_table(&ses->bc_slot_table); nfs4_end_drain_slot_table(&ses->fc_slot_table); } } -/* - * Signal state manager thread if session fore channel is drained - */ -void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl) -{ - if (nfs4_slot_tbl_draining(tbl)) - complete(&tbl->complete); -} +#if defined(CONFIG_NFS_V4_1) static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl) { @@ -274,6 +259,9 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) struct nfs4_session *ses = clp->cl_session; int ret = 0; + if (clp->cl_slot_tbl) + return nfs4_drain_slot_tbl(clp->cl_slot_tbl); + /* back channel */ ret = nfs4_drain_slot_tbl(&ses->bc_slot_table); if (ret) @@ -282,6 +270,30 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) return nfs4_drain_slot_tbl(&ses->fc_slot_table); } +static int nfs41_setup_state_renewal(struct nfs_client *clp) +{ + int status; + struct nfs_fsinfo fsinfo; + + if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { + nfs4_schedule_state_renewal(clp); + return 0; + } + + status = nfs4_proc_get_lease_time(clp, &fsinfo); + if (status == 0) { + /* Update lease time and schedule renewal */ + spin_lock(&clp->cl_lock); + clp->cl_lease_time = fsinfo.lease_time * HZ; + clp->cl_last_renewal = jiffies; + spin_unlock(&clp->cl_lock); + + nfs4_schedule_state_renewal(clp); + } + + return status; +} + static void nfs41_finish_session_reset(struct nfs_client *clp) { clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); @@ -339,62 +351,21 @@ int nfs41_discover_server_trunking(struct nfs_client *clp, return nfs41_walk_client_list(clp, result, cred); } -struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp) -{ - struct rpc_cred *cred; - - spin_lock(&clp->cl_lock); - cred = nfs4_get_machine_cred_locked(clp); - spin_unlock(&clp->cl_lock); - return cred; -} - #endif /* CONFIG_NFS_V4_1 */ -static struct rpc_cred * -nfs4_get_setclientid_cred_server(struct nfs_server *server) -{ - struct nfs_client *clp = server->nfs_client; - struct rpc_cred *cred = NULL; - struct nfs4_state_owner *sp; - struct rb_node *pos; - - spin_lock(&clp->cl_lock); - pos = rb_first(&server->state_owners); - if (pos != NULL) { - sp = rb_entry(pos, struct nfs4_state_owner, so_server_node); - cred = get_rpccred(sp->so_cred); - } - spin_unlock(&clp->cl_lock); - return cred; -} - /** - * nfs4_get_setclientid_cred - Acquire credential for a setclientid operation + * nfs4_get_clid_cred - Acquire credential for a setclientid operation * @clp: client state handle * * Returns an rpc_cred with reference count bumped, or NULL. */ -struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp) +struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp) { - struct nfs_server *server; struct rpc_cred *cred; spin_lock(&clp->cl_lock); cred = nfs4_get_machine_cred_locked(clp); spin_unlock(&clp->cl_lock); - if (cred != NULL) - goto out; - - rcu_read_lock(); - list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - cred = nfs4_get_setclientid_cred_server(server); - if (cred != NULL) - break; - } - rcu_read_unlock(); - -out: return cred; } @@ -998,7 +969,9 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst, fl_pid = lockowner->l_pid; spin_lock(&state->state_lock); lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE); - if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) { + if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags)) + ret = -EIO; + else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) { nfs4_stateid_copy(dst, &lsp->ls_stateid); ret = 0; smp_rmb(); @@ -1038,11 +1011,17 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state, fmode_t fmode, const struct nfs_lockowner *lockowner) { - int ret = 0; + int ret = nfs4_copy_lock_stateid(dst, state, lockowner); + if (ret == -EIO) + /* A lost lock - don't even consider delegations */ + goto out; if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) goto out; - ret = nfs4_copy_lock_stateid(dst, state, lockowner); if (ret != -ENOENT) + /* nfs4_copy_delegation_stateid() didn't over-write + * dst, so it still has the lock stateid which we now + * choose to use. + */ goto out; ret = nfs4_copy_open_stateid(dst, state); out: @@ -1443,14 +1422,16 @@ restart: if (status >= 0) { status = nfs4_reclaim_locks(state, ops); if (status >= 0) { - spin_lock(&state->state_lock); - list_for_each_entry(lock, &state->lock_states, ls_locks) { - if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags)) - pr_warn_ratelimited("NFS: " - "%s: Lock reclaim " - "failed!\n", __func__); + if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) { + spin_lock(&state->state_lock); + list_for_each_entry(lock, &state->lock_states, ls_locks) { + if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags)) + pr_warn_ratelimited("NFS: " + "%s: Lock reclaim " + "failed!\n", __func__); + } + spin_unlock(&state->state_lock); } - spin_unlock(&state->state_lock); nfs4_put_open_state(state); spin_lock(&sp->so_lock); goto restart; @@ -1618,7 +1599,7 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) if (!nfs4_state_clear_reclaim_reboot(clp)) return; ops = clp->cl_mvops->reboot_recovery_ops; - cred = ops->get_clid_cred(clp); + cred = nfs4_get_clid_cred(clp); nfs4_reclaim_complete(clp, ops, cred); put_rpccred(cred); } @@ -1732,7 +1713,7 @@ static int nfs4_check_lease(struct nfs_client *clp) cred = ops->get_state_renewal_cred_locked(clp); spin_unlock(&clp->cl_lock); if (cred == NULL) { - cred = nfs4_get_setclientid_cred(clp); + cred = nfs4_get_clid_cred(clp); status = -ENOKEY; if (cred == NULL) goto out; @@ -1804,7 +1785,7 @@ static int nfs4_establish_lease(struct nfs_client *clp) clp->cl_mvops->reboot_recovery_ops; int status; - cred = ops->get_clid_cred(clp); + cred = nfs4_get_clid_cred(clp); if (cred == NULL) return -ENOENT; status = ops->establish_clid(clp, cred); @@ -1878,7 +1859,7 @@ int nfs4_discover_server_trunking(struct nfs_client *clp, mutex_lock(&nfs_clid_init_mutex); again: status = -ENOENT; - cred = ops->get_clid_cred(clp); + cred = nfs4_get_clid_cred(clp); if (cred == NULL) goto out_unlock; @@ -1896,7 +1877,11 @@ again: __func__, status); goto again; case -EACCES: - if (i++) + if (i++ == 0) { + nfs4_root_machine_cred(clp); + goto again; + } + if (i > 2) break; case -NFS4ERR_CLID_INUSE: case -NFS4ERR_WRONGSEC: @@ -2052,7 +2037,7 @@ static int nfs4_reset_session(struct nfs_client *clp) if (!nfs4_has_session(clp)) return 0; nfs4_begin_drain_session(clp); - cred = nfs4_get_exchange_id_cred(clp); + cred = nfs4_get_clid_cred(clp); status = nfs4_proc_destroy_session(clp->cl_session, cred); switch (status) { case 0: @@ -2095,7 +2080,7 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp) if (!nfs4_has_session(clp)) return 0; nfs4_begin_drain_session(clp); - cred = nfs4_get_exchange_id_cred(clp); + cred = nfs4_get_clid_cred(clp); ret = nfs4_proc_bind_conn_to_session(clp, cred); if (cred) put_rpccred(cred); @@ -2116,7 +2101,6 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp) } #else /* CONFIG_NFS_V4_1 */ static int nfs4_reset_session(struct nfs_client *clp) { return 0; } -static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; } static int nfs4_bind_conn_to_session(struct nfs_client *clp) { diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 5dbe2d2..e26acdd 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -253,8 +253,6 @@ struct dentry *nfs4_try_mount(int flags, const char *dev_name, dfprintk(MOUNT, "--> nfs4_try_mount()\n"); - if (data->auth_flavors[0] == RPC_AUTH_MAXFLAVOR) - data->auth_flavors[0] = RPC_AUTH_UNIX; export_path = data->nfs_server.export_path; data->nfs_server.export_path = "/"; root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c new file mode 100644 index 0000000..d774335 --- /dev/null +++ b/fs/nfs/nfs4trace.c @@ -0,0 +1,17 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" +#include "internal.h" +#include "nfs4session.h" +#include "callback.h" + +#define CREATE_TRACE_POINTS +#include "nfs4trace.h" + +#ifdef CONFIG_NFS_V4_1 +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_read); +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_write); +EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_commit_ds); +#endif diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h new file mode 100644 index 0000000..849cf14 --- /dev/null +++ b/fs/nfs/nfs4trace.h @@ -0,0 +1,1148 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfs4 + +#if !defined(_TRACE_NFS4_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NFS4_H + +#include <linux/tracepoint.h> + +#define show_nfsv4_errors(error) \ + __print_symbolic(error, \ + { NFS4_OK, "OK" }, \ + /* Mapped by nfs4_stat_to_errno() */ \ + { -EPERM, "EPERM" }, \ + { -ENOENT, "ENOENT" }, \ + { -EIO, "EIO" }, \ + { -ENXIO, "ENXIO" }, \ + { -EACCES, "EACCES" }, \ + { -EEXIST, "EEXIST" }, \ + { -EXDEV, "EXDEV" }, \ + { -ENOTDIR, "ENOTDIR" }, \ + { -EISDIR, "EISDIR" }, \ + { -EFBIG, "EFBIG" }, \ + { -ENOSPC, "ENOSPC" }, \ + { -EROFS, "EROFS" }, \ + { -EMLINK, "EMLINK" }, \ + { -ENAMETOOLONG, "ENAMETOOLONG" }, \ + { -ENOTEMPTY, "ENOTEMPTY" }, \ + { -EDQUOT, "EDQUOT" }, \ + { -ESTALE, "ESTALE" }, \ + { -EBADHANDLE, "EBADHANDLE" }, \ + { -EBADCOOKIE, "EBADCOOKIE" }, \ + { -ENOTSUPP, "ENOTSUPP" }, \ + { -ETOOSMALL, "ETOOSMALL" }, \ + { -EREMOTEIO, "EREMOTEIO" }, \ + { -EBADTYPE, "EBADTYPE" }, \ + { -EAGAIN, "EAGAIN" }, \ + { -ELOOP, "ELOOP" }, \ + { -EOPNOTSUPP, "EOPNOTSUPP" }, \ + { -EDEADLK, "EDEADLK" }, \ + /* RPC errors */ \ + { -ENOMEM, "ENOMEM" }, \ + { -EKEYEXPIRED, "EKEYEXPIRED" }, \ + { -ETIMEDOUT, "ETIMEDOUT" }, \ + { -ERESTARTSYS, "ERESTARTSYS" }, \ + { -ECONNREFUSED, "ECONNREFUSED" }, \ + { -ECONNRESET, "ECONNRESET" }, \ + { -ENETUNREACH, "ENETUNREACH" }, \ + { -EHOSTUNREACH, "EHOSTUNREACH" }, \ + { -EHOSTDOWN, "EHOSTDOWN" }, \ + { -EPIPE, "EPIPE" }, \ + { -EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { -EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + /* NFSv4 native errors */ \ + { -NFS4ERR_ACCESS, "ACCESS" }, \ + { -NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { -NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { -NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { -NFS4ERR_BADCHAR, "BADCHAR" }, \ + { -NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { -NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { -NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { -NFS4ERR_BADLABEL, "BADLABEL" }, \ + { -NFS4ERR_BADNAME, "BADNAME" }, \ + { -NFS4ERR_BADOWNER, "BADOWNER" }, \ + { -NFS4ERR_BADSESSION, "BADSESSION" }, \ + { -NFS4ERR_BADSLOT, "BADSLOT" }, \ + { -NFS4ERR_BADTYPE, "BADTYPE" }, \ + { -NFS4ERR_BADXDR, "BADXDR" }, \ + { -NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { -NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { -NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { -NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { -NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { -NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { -NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { -NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { -NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { -NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { -NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ + "CONN_NOT_BOUND_TO_SESSION" }, \ + { -NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { -NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { -NFS4ERR_DELAY, "DELAY" }, \ + { -NFS4ERR_DELEG_ALREADY_WANTED, \ + "DELEG_ALREADY_WANTED" }, \ + { -NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { -NFS4ERR_DENIED, "DENIED" }, \ + { -NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { -NFS4ERR_DQUOT, "DQUOT" }, \ + { -NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { -NFS4ERR_EXIST, "EXIST" }, \ + { -NFS4ERR_EXPIRED, "EXPIRED" }, \ + { -NFS4ERR_FBIG, "FBIG" }, \ + { -NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { -NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { -NFS4ERR_GRACE, "GRACE" }, \ + { -NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { -NFS4ERR_INVAL, "INVAL" }, \ + { -NFS4ERR_IO, "IO" }, \ + { -NFS4ERR_ISDIR, "ISDIR" }, \ + { -NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { -NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { -NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { -NFS4ERR_LOCKED, "LOCKED" }, \ + { -NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { -NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { -NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { -NFS4ERR_MLINK, "MLINK" }, \ + { -NFS4ERR_MOVED, "MOVED" }, \ + { -NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { -NFS4ERR_NOENT, "NOENT" }, \ + { -NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { -NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { -NFS4ERR_NOSPC, "NOSPC" }, \ + { -NFS4ERR_NOTDIR, "NOTDIR" }, \ + { -NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { -NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { -NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { -NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { -NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { -NFS4ERR_NXIO, "NXIO" }, \ + { -NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { -NFS4ERR_OPENMODE, "OPENMODE" }, \ + { -NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { -NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { -NFS4ERR_PERM, "PERM" }, \ + { -NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { -NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { -NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { -NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { -NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { -NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { -NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { -NFS4ERR_REP_TOO_BIG_TO_CACHE, \ + "REP_TOO_BIG_TO_CACHE" }, \ + { -NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { -NFS4ERR_RESOURCE, "RESOURCE" }, \ + { -NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { -NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { -NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { -NFS4ERR_ROFS, "ROFS" }, \ + { -NFS4ERR_SAME, "SAME" }, \ + { -NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { -NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { -NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { -NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { -NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { -NFS4ERR_STALE, "STALE" }, \ + { -NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { -NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { -NFS4ERR_SYMLINK, "SYMLINK" }, \ + { -NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { -NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { -NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { -NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { -NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { -NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { -NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { -NFS4ERR_XDEV, "XDEV" }) + +#define show_open_flags(flags) \ + __print_flags(flags, "|", \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_DIRECT, "O_DIRECT" }) + +#define show_fmode_flags(mode) \ + __print_flags(mode, "|", \ + { ((__force unsigned long)FMODE_READ), "READ" }, \ + { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ + { ((__force unsigned long)FMODE_EXEC), "EXEC" }) + +#define show_nfs_fattr_flags(valid) \ + __print_flags((unsigned long)valid, "|", \ + { NFS_ATTR_FATTR_TYPE, "TYPE" }, \ + { NFS_ATTR_FATTR_MODE, "MODE" }, \ + { NFS_ATTR_FATTR_NLINK, "NLINK" }, \ + { NFS_ATTR_FATTR_OWNER, "OWNER" }, \ + { NFS_ATTR_FATTR_GROUP, "GROUP" }, \ + { NFS_ATTR_FATTR_RDEV, "RDEV" }, \ + { NFS_ATTR_FATTR_SIZE, "SIZE" }, \ + { NFS_ATTR_FATTR_FSID, "FSID" }, \ + { NFS_ATTR_FATTR_FILEID, "FILEID" }, \ + { NFS_ATTR_FATTR_ATIME, "ATIME" }, \ + { NFS_ATTR_FATTR_MTIME, "MTIME" }, \ + { NFS_ATTR_FATTR_CTIME, "CTIME" }, \ + { NFS_ATTR_FATTR_CHANGE, "CHANGE" }, \ + { NFS_ATTR_FATTR_OWNER_NAME, "OWNER_NAME" }, \ + { NFS_ATTR_FATTR_GROUP_NAME, "GROUP_NAME" }) + +DECLARE_EVENT_CLASS(nfs4_clientid_event, + TP_PROTO( + const struct nfs_client *clp, + int error + ), + + TP_ARGS(clp, error), + + TP_STRUCT__entry( + __string(dstaddr, + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR)) + __field(int, error) + ), + + TP_fast_assign( + __entry->error = error; + __assign_str(dstaddr, + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR)); + ), + + TP_printk( + "error=%d (%s) dstaddr=%s", + __entry->error, + show_nfsv4_errors(__entry->error), + __get_str(dstaddr) + ) +); +#define DEFINE_NFS4_CLIENTID_EVENT(name) \ + DEFINE_EVENT(nfs4_clientid_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp, \ + int error \ + ), \ + TP_ARGS(clp, error)) +DEFINE_NFS4_CLIENTID_EVENT(nfs4_setclientid); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_setclientid_confirm); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_renew); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_renew_async); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_CLIENTID_EVENT(nfs4_exchange_id); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_create_session); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_destroy_session); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_destroy_clientid); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence); +DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete); + +TRACE_EVENT(nfs4_setup_sequence, + TP_PROTO( + const struct nfs4_session *session, + const struct nfs4_sequence_args *args + ), + TP_ARGS(session, args), + + TP_STRUCT__entry( + __field(unsigned int, session) + __field(unsigned int, slot_nr) + __field(unsigned int, seq_nr) + __field(unsigned int, highest_used_slotid) + ), + + TP_fast_assign( + const struct nfs4_slot *sa_slot = args->sa_slot; + __entry->session = nfs_session_id_hash(&session->sess_id); + __entry->slot_nr = sa_slot->slot_nr; + __entry->seq_nr = sa_slot->seq_nr; + __entry->highest_used_slotid = + sa_slot->table->highest_used_slotid; + ), + TP_printk( + "session=0x%08x slot_nr=%u seq_nr=%u " + "highest_used_slotid=%u", + __entry->session, + __entry->slot_nr, + __entry->seq_nr, + __entry->highest_used_slotid + ) +); + +#define show_nfs4_sequence_status_flags(status) \ + __print_flags((unsigned long)status, "|", \ + { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, \ + "CB_GSS_CONTEXTS_EXPIRING" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, \ + "CB_GSS_CONTEXTS_EXPIRED" }, \ + { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, \ + "EXPIRED_ALL_STATE_REVOKED" }, \ + { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, \ + "EXPIRED_SOME_STATE_REVOKED" }, \ + { SEQ4_STATUS_ADMIN_STATE_REVOKED, \ + "ADMIN_STATE_REVOKED" }, \ + { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, \ + "RECALLABLE_STATE_REVOKED" }, \ + { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ + { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, \ + "RESTART_RECLAIM_NEEDED" }, \ + { SEQ4_STATUS_CB_PATH_DOWN_SESSION, \ + "CB_PATH_DOWN_SESSION" }, \ + { SEQ4_STATUS_BACKCHANNEL_FAULT, \ + "BACKCHANNEL_FAULT" }) + +TRACE_EVENT(nfs4_sequence_done, + TP_PROTO( + const struct nfs4_session *session, + const struct nfs4_sequence_res *res + ), + TP_ARGS(session, res), + + TP_STRUCT__entry( + __field(unsigned int, session) + __field(unsigned int, slot_nr) + __field(unsigned int, seq_nr) + __field(unsigned int, highest_slotid) + __field(unsigned int, target_highest_slotid) + __field(unsigned int, status_flags) + __field(int, error) + ), + + TP_fast_assign( + const struct nfs4_slot *sr_slot = res->sr_slot; + __entry->session = nfs_session_id_hash(&session->sess_id); + __entry->slot_nr = sr_slot->slot_nr; + __entry->seq_nr = sr_slot->seq_nr; + __entry->highest_slotid = res->sr_highest_slotid; + __entry->target_highest_slotid = + res->sr_target_highest_slotid; + __entry->error = res->sr_status; + ), + TP_printk( + "error=%d (%s) session=0x%08x slot_nr=%u seq_nr=%u " + "highest_slotid=%u target_highest_slotid=%u " + "status_flags=%u (%s)", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->session, + __entry->slot_nr, + __entry->seq_nr, + __entry->highest_slotid, + __entry->target_highest_slotid, + __entry->status_flags, + show_nfs4_sequence_status_flags(__entry->status_flags) + ) +); + +struct cb_sequenceargs; +struct cb_sequenceres; + +TRACE_EVENT(nfs4_cb_sequence, + TP_PROTO( + const struct cb_sequenceargs *args, + const struct cb_sequenceres *res, + __be32 status + ), + TP_ARGS(args, res, status), + + TP_STRUCT__entry( + __field(unsigned int, session) + __field(unsigned int, slot_nr) + __field(unsigned int, seq_nr) + __field(unsigned int, highest_slotid) + __field(unsigned int, cachethis) + __field(int, error) + ), + + TP_fast_assign( + __entry->session = nfs_session_id_hash(&args->csa_sessionid); + __entry->slot_nr = args->csa_slotid; + __entry->seq_nr = args->csa_sequenceid; + __entry->highest_slotid = args->csa_highestslotid; + __entry->cachethis = args->csa_cachethis; + __entry->error = -be32_to_cpu(status); + ), + + TP_printk( + "error=%d (%s) session=0x%08x slot_nr=%u seq_nr=%u " + "highest_slotid=%u", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->session, + __entry->slot_nr, + __entry->seq_nr, + __entry->highest_slotid + ) +); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_open_event, + TP_PROTO( + const struct nfs_open_context *ctx, + int flags, + int error + ), + + TP_ARGS(ctx, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(unsigned int, fmode) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, dir) + __string(name, ctx->dentry->d_name.name) + ), + + TP_fast_assign( + const struct nfs4_state *state = ctx->state; + const struct inode *inode = NULL; + + __entry->error = error; + __entry->flags = flags; + __entry->fmode = (__force unsigned int)ctx->mode; + __entry->dev = ctx->dentry->d_sb->s_dev; + if (!IS_ERR(state)) + inode = state->inode; + if (inode != NULL) { + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + } else { + __entry->fileid = 0; + __entry->fhandle = 0; + } + __entry->dir = NFS_FILEID(ctx->dentry->d_parent->d_inode); + __assign_str(name, ctx->dentry->d_name.name); + ), + + TP_printk( + "error=%d (%s) flags=%d (%s) fmode=%s " + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "name=%02x:%02x:%llu/%s", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->flags, + show_open_flags(__entry->flags), + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS4_OPEN_EVENT(name) \ + DEFINE_EVENT(nfs4_open_event, name, \ + TP_PROTO( \ + const struct nfs_open_context *ctx, \ + int flags, \ + int error \ + ), \ + TP_ARGS(ctx, flags, error)) +DEFINE_NFS4_OPEN_EVENT(nfs4_open_reclaim); +DEFINE_NFS4_OPEN_EVENT(nfs4_open_expired); +DEFINE_NFS4_OPEN_EVENT(nfs4_open_file); + +TRACE_EVENT(nfs4_close, + TP_PROTO( + const struct nfs4_state *state, + const struct nfs_closeargs *args, + const struct nfs_closeres *res, + int error + ), + + TP_ARGS(state, args, res, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, fmode) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fmode = (__force unsigned int)state->state; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fmode=%s fileid=%02x:%02x:%llu " + "fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + __entry->fmode ? show_fmode_flags(__entry->fmode) : + "closed", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define show_lock_cmd(type) \ + __print_symbolic((int)type, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }) +#define show_lock_type(type) \ + __print_symbolic((int)type, \ + { F_RDLCK, "RDLCK" }, \ + { F_WRLCK, "WRLCK" }, \ + { F_UNLCK, "UNLCK" }) + +DECLARE_EVENT_CLASS(nfs4_lock_event, + TP_PROTO( + const struct file_lock *request, + const struct nfs4_state *state, + int cmd, + int error + ), + + TP_ARGS(request, state, cmd, error), + + TP_STRUCT__entry( + __field(int, error) + __field(int, cmd) + __field(char, type) + __field(loff_t, start) + __field(loff_t, end) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->error = error; + __entry->cmd = cmd; + __entry->type = request->fl_type; + __entry->start = request->fl_start; + __entry->end = request->fl_end; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + ), + + TP_printk( + "error=%d (%s) cmd=%s:%s range=%lld:%lld " + "fileid=%02x:%02x:%llu fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + show_lock_cmd(__entry->cmd), + show_lock_type(__entry->type), + (long long)__entry->start, + (long long)__entry->end, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define DEFINE_NFS4_LOCK_EVENT(name) \ + DEFINE_EVENT(nfs4_lock_event, name, \ + TP_PROTO( \ + const struct file_lock *request, \ + const struct nfs4_state *state, \ + int cmd, \ + int error \ + ), \ + TP_ARGS(request, state, cmd, error)) +DEFINE_NFS4_LOCK_EVENT(nfs4_get_lock); +DEFINE_NFS4_LOCK_EVENT(nfs4_set_lock); +DEFINE_NFS4_LOCK_EVENT(nfs4_lock_reclaim); +DEFINE_NFS4_LOCK_EVENT(nfs4_lock_expired); +DEFINE_NFS4_LOCK_EVENT(nfs4_unlock); + +DECLARE_EVENT_CLASS(nfs4_set_delegation_event, + TP_PROTO( + const struct inode *inode, + fmode_t fmode + ), + + TP_ARGS(inode, fmode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, fmode) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fmode = (__force unsigned int)fmode; + ), + + TP_printk( + "fmode=%s fileid=%02x:%02x:%llu fhandle=0x%08x", + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); +#define DEFINE_NFS4_SET_DELEGATION_EVENT(name) \ + DEFINE_EVENT(nfs4_set_delegation_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + fmode_t fmode \ + ), \ + TP_ARGS(inode, fmode)) +DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_set_delegation); +DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_reclaim_delegation); + +TRACE_EVENT(nfs4_delegreturn_exit, + TP_PROTO( + const struct nfs4_delegreturnargs *args, + const struct nfs4_delegreturnres *res, + int error + ), + + TP_ARGS(args, res, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = res->server->s_dev; + __entry->fhandle = nfs_fhandle_hash(args->fhandle); + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) dev=%02x:%02x fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->fhandle + ) +); + +#ifdef CONFIG_NFS_V4_1 +DECLARE_EVENT_CLASS(nfs4_test_stateid_event, + TP_PROTO( + const struct nfs4_state *state, + const struct nfs4_lock_state *lsp, + int error + ), + + TP_ARGS(state, lsp, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->error = error; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define DEFINE_NFS4_TEST_STATEID_EVENT(name) \ + DEFINE_EVENT(nfs4_test_stateid_event, name, \ + TP_PROTO( \ + const struct nfs4_state *state, \ + const struct nfs4_lock_state *lsp, \ + int error \ + ), \ + TP_ARGS(state, lsp, error)) +DEFINE_NFS4_TEST_STATEID_EVENT(nfs4_test_delegation_stateid); +DEFINE_NFS4_TEST_STATEID_EVENT(nfs4_test_open_stateid); +DEFINE_NFS4_TEST_STATEID_EVENT(nfs4_test_lock_stateid); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_lookup_event, + TP_PROTO( + const struct inode *dir, + const struct qstr *name, + int error + ), + + TP_ARGS(dir, name, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, dir) + __string(name, name->name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __assign_str(name, name->name); + ), + + TP_printk( + "error=%d (%s) name=%02x:%02x:%llu/%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS4_LOOKUP_EVENT(name) \ + DEFINE_EVENT(nfs4_lookup_event, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct qstr *name, \ + int error \ + ), \ + TP_ARGS(dir, name, error)) + +DEFINE_NFS4_LOOKUP_EVENT(nfs4_lookup); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_symlink); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_mkdir); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_mknod); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_remove); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_get_fs_locations); +DEFINE_NFS4_LOOKUP_EVENT(nfs4_secinfo); + +TRACE_EVENT(nfs4_rename, + TP_PROTO( + const struct inode *olddir, + const struct qstr *oldname, + const struct inode *newdir, + const struct qstr *newname, + int error + ), + + TP_ARGS(olddir, oldname, newdir, newname, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, olddir) + __string(oldname, oldname->name) + __field(u64, newdir) + __string(newname, newname->name) + ), + + TP_fast_assign( + __entry->dev = olddir->i_sb->s_dev; + __entry->olddir = NFS_FILEID(olddir); + __entry->newdir = NFS_FILEID(newdir); + __entry->error = error; + __assign_str(oldname, oldname->name); + __assign_str(newname, newname->name); + ), + + TP_printk( + "error=%d (%s) oldname=%02x:%02x:%llu/%s " + "newname=%02x:%02x:%llu/%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->olddir, + __get_str(oldname), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->newdir, + __get_str(newname) + ) +); + +DECLARE_EVENT_CLASS(nfs4_inode_event, + TP_PROTO( + const struct inode *inode, + int error + ), + + TP_ARGS(inode, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle + ) +); + +#define DEFINE_NFS4_INODE_EVENT(name) \ + DEFINE_EVENT(nfs4_inode_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + int error \ + ), \ + TP_ARGS(inode, error)) + +DEFINE_NFS4_INODE_EVENT(nfs4_setattr); +DEFINE_NFS4_INODE_EVENT(nfs4_access); +DEFINE_NFS4_INODE_EVENT(nfs4_readlink); +DEFINE_NFS4_INODE_EVENT(nfs4_readdir); +DEFINE_NFS4_INODE_EVENT(nfs4_get_acl); +DEFINE_NFS4_INODE_EVENT(nfs4_set_acl); +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +DEFINE_NFS4_INODE_EVENT(nfs4_get_security_label); +DEFINE_NFS4_INODE_EVENT(nfs4_set_security_label); +#endif /* CONFIG_NFS_V4_SECURITY_LABEL */ +DEFINE_NFS4_INODE_EVENT(nfs4_recall_delegation); +DEFINE_NFS4_INODE_EVENT(nfs4_delegreturn); + +DECLARE_EVENT_CLASS(nfs4_getattr_event, + TP_PROTO( + const struct nfs_server *server, + const struct nfs_fh *fhandle, + const struct nfs_fattr *fattr, + int error + ), + + TP_ARGS(server, fhandle, fattr, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, valid) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = server->s_dev; + __entry->valid = fattr->valid; + __entry->fhandle = nfs_fhandle_hash(fhandle); + __entry->fileid = (fattr->valid & NFS_ATTR_FATTR_FILEID) ? fattr->fileid : 0; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "valid=%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_nfs_fattr_flags(__entry->valid) + ) +); + +#define DEFINE_NFS4_GETATTR_EVENT(name) \ + DEFINE_EVENT(nfs4_getattr_event, name, \ + TP_PROTO( \ + const struct nfs_server *server, \ + const struct nfs_fh *fhandle, \ + const struct nfs_fattr *fattr, \ + int error \ + ), \ + TP_ARGS(server, fhandle, fattr, error)) +DEFINE_NFS4_GETATTR_EVENT(nfs4_getattr); +DEFINE_NFS4_GETATTR_EVENT(nfs4_lookup_root); +DEFINE_NFS4_GETATTR_EVENT(nfs4_fsinfo); + +DECLARE_EVENT_CLASS(nfs4_idmap_event, + TP_PROTO( + const char *name, + int len, + u32 id, + int error + ), + + TP_ARGS(name, len, id, error), + + TP_STRUCT__entry( + __field(int, error) + __field(u32, id) + __dynamic_array(char, name, len > 0 ? len + 1 : 1) + ), + + TP_fast_assign( + if (len < 0) + len = 0; + __entry->error = error < 0 ? error : 0; + __entry->id = id; + memcpy(__get_dynamic_array(name), name, len); + ((char *)__get_dynamic_array(name))[len] = 0; + ), + + TP_printk( + "error=%d id=%u name=%s", + __entry->error, + __entry->id, + __get_str(name) + ) +); +#define DEFINE_NFS4_IDMAP_EVENT(name) \ + DEFINE_EVENT(nfs4_idmap_event, name, \ + TP_PROTO( \ + const char *name, \ + int len, \ + u32 id, \ + int error \ + ), \ + TP_ARGS(name, len, id, error)) +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_name_to_uid); +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_group_to_gid); +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_uid_to_name); +DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group); + +DECLARE_EVENT_CLASS(nfs4_read_event, + TP_PROTO( + const struct nfs_read_data *data, + int error + ), + + TP_ARGS(data, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(size_t, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = data->header->inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->offset = data->args.offset; + __entry->count = data->args.count; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, + __entry->count + ) +); +#define DEFINE_NFS4_READ_EVENT(name) \ + DEFINE_EVENT(nfs4_read_event, name, \ + TP_PROTO( \ + const struct nfs_read_data *data, \ + int error \ + ), \ + TP_ARGS(data, error)) +DEFINE_NFS4_READ_EVENT(nfs4_read); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_write_event, + TP_PROTO( + const struct nfs_write_data *data, + int error + ), + + TP_ARGS(data, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(size_t, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = data->header->inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->offset = data->args.offset; + __entry->count = data->args.count; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, + __entry->count + ) +); + +#define DEFINE_NFS4_WRITE_EVENT(name) \ + DEFINE_EVENT(nfs4_write_event, name, \ + TP_PROTO( \ + const struct nfs_write_data *data, \ + int error \ + ), \ + TP_ARGS(data, error)) +DEFINE_NFS4_WRITE_EVENT(nfs4_write); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_WRITE_EVENT(nfs4_pnfs_write); +#endif /* CONFIG_NFS_V4_1 */ + +DECLARE_EVENT_CLASS(nfs4_commit_event, + TP_PROTO( + const struct nfs_commit_data *data, + int error + ), + + TP_ARGS(data, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(size_t, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = data->inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->offset = data->args.offset; + __entry->count = data->args.count; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, + __entry->count + ) +); +#define DEFINE_NFS4_COMMIT_EVENT(name) \ + DEFINE_EVENT(nfs4_commit_event, name, \ + TP_PROTO( \ + const struct nfs_commit_data *data, \ + int error \ + ), \ + TP_ARGS(data, error)) +DEFINE_NFS4_COMMIT_EVENT(nfs4_commit); +#ifdef CONFIG_NFS_V4_1 +DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds); + +#define show_pnfs_iomode(iomode) \ + __print_symbolic(iomode, \ + { IOMODE_READ, "READ" }, \ + { IOMODE_RW, "RW" }, \ + { IOMODE_ANY, "ANY" }) + +TRACE_EVENT(nfs4_layoutget, + TP_PROTO( + const struct nfs_open_context *ctx, + const struct pnfs_layout_range *args, + const struct pnfs_layout_range *res, + int error + ), + + TP_ARGS(ctx, args, res, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u32, iomode) + __field(u64, offset) + __field(u64, count) + __field(int, error) + ), + + TP_fast_assign( + const struct inode *inode = ctx->dentry->d_inode; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->iomode = args->iomode; + __entry->offset = args->offset; + __entry->count = args->length; + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "iomode=%s offset=%llu count=%llu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_pnfs_iomode(__entry->iomode), + (unsigned long long)__entry->offset, + (unsigned long long)__entry->count + ) +); + +DEFINE_NFS4_INODE_EVENT(nfs4_layoutcommit); +DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn); + +#endif /* CONFIG_NFS_V4_1 */ + +#endif /* _TRACE_NFS4_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE nfs4trace +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0abfb846..79210d2 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -294,7 +294,9 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_EXCHANGE_ID_LEN) + \ 1 /* flags */ + \ 1 /* spa_how */ + \ - 0 /* SP4_NONE (for now) */ + \ + /* max is SP4_MACH_CRED (for now) */ + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ 1 /* implementation id array of size 1 */ + \ 1 /* nii_domain */ + \ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \ @@ -306,7 +308,9 @@ static int nfs4_stat_to_errno(int); 1 /* eir_sequenceid */ + \ 1 /* eir_flags */ + \ 1 /* spr_how */ + \ - 0 /* SP4_NONE (for now) */ + \ + /* max is SP4_MACH_CRED (for now) */ + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ + 1 + NFS4_OP_MAP_NUM_WORDS + \ 2 /* eir_server_owner.so_minor_id */ + \ /* eir_server_owner.so_major_id<> */ \ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \ @@ -410,7 +414,7 @@ static int nfs4_stat_to_errno(int); #define decode_test_stateid_maxsz (op_decode_hdr_maxsz + 2 + 1) #define encode_free_stateid_maxsz (op_encode_hdr_maxsz + 1 + \ XDR_QUADLEN(NFS4_STATEID_SIZE)) -#define decode_free_stateid_maxsz (op_decode_hdr_maxsz + 1) +#define decode_free_stateid_maxsz (op_decode_hdr_maxsz) #else /* CONFIG_NFS_V4_1 */ #define encode_sequence_maxsz 0 #define decode_sequence_maxsz 0 @@ -997,11 +1001,10 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, int owner_namelen = 0; int owner_grouplen = 0; __be32 *p; - __be32 *q; - int len; - uint32_t bmval0 = 0; - uint32_t bmval1 = 0; - uint32_t bmval2 = 0; + unsigned i; + uint32_t len = 0; + uint32_t bmval_len; + uint32_t bmval[3] = { 0 }; /* * We reserve enough space to write the entire attribute buffer at once. @@ -1010,13 +1013,14 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, * = 40 bytes, plus any contribution from variable-length fields * such as owner/group. */ - len = 20; - - /* Sigh */ - if (iap->ia_valid & ATTR_SIZE) + if (iap->ia_valid & ATTR_SIZE) { + bmval[0] |= FATTR4_WORD0_SIZE; len += 8; - if (iap->ia_valid & ATTR_MODE) + } + if (iap->ia_valid & ATTR_MODE) { + bmval[1] |= FATTR4_WORD1_MODE; len += 4; + } if (iap->ia_valid & ATTR_UID) { owner_namelen = nfs_map_uid_to_name(server, iap->ia_uid, owner_name, IDMAP_NAMESZ); if (owner_namelen < 0) { @@ -1027,6 +1031,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, owner_namelen = sizeof("nobody") - 1; /* goto out; */ } + bmval[1] |= FATTR4_WORD1_OWNER; len += 4 + (XDR_QUADLEN(owner_namelen) << 2); } if (iap->ia_valid & ATTR_GID) { @@ -1038,86 +1043,73 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, owner_grouplen = sizeof("nobody") - 1; /* goto out; */ } + bmval[1] |= FATTR4_WORD1_OWNER_GROUP; len += 4 + (XDR_QUADLEN(owner_grouplen) << 2); } - if (label) - len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2); - if (iap->ia_valid & ATTR_ATIME_SET) + if (iap->ia_valid & ATTR_ATIME_SET) { + bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET; len += 16; - else if (iap->ia_valid & ATTR_ATIME) + } else if (iap->ia_valid & ATTR_ATIME) { + bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET; len += 4; - if (iap->ia_valid & ATTR_MTIME_SET) + } + if (iap->ia_valid & ATTR_MTIME_SET) { + bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET; len += 16; - else if (iap->ia_valid & ATTR_MTIME) + } else if (iap->ia_valid & ATTR_MTIME) { + bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET; len += 4; - p = reserve_space(xdr, len); + } + if (label) { + len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2); + bmval[2] |= FATTR4_WORD2_SECURITY_LABEL; + } - /* - * We write the bitmap length now, but leave the bitmap and the attribute - * buffer length to be backfilled at the end of this routine. - */ - *p++ = cpu_to_be32(3); - q = p; - p += 4; + if (bmval[2] != 0) + bmval_len = 3; + else if (bmval[1] != 0) + bmval_len = 2; + else + bmval_len = 1; - if (iap->ia_valid & ATTR_SIZE) { - bmval0 |= FATTR4_WORD0_SIZE; + p = reserve_space(xdr, 4 + (bmval_len << 2) + 4 + len); + + *p++ = cpu_to_be32(bmval_len); + for (i = 0; i < bmval_len; i++) + *p++ = cpu_to_be32(bmval[i]); + *p++ = cpu_to_be32(len); + + if (bmval[0] & FATTR4_WORD0_SIZE) p = xdr_encode_hyper(p, iap->ia_size); - } - if (iap->ia_valid & ATTR_MODE) { - bmval1 |= FATTR4_WORD1_MODE; + if (bmval[1] & FATTR4_WORD1_MODE) *p++ = cpu_to_be32(iap->ia_mode & S_IALLUGO); - } - if (iap->ia_valid & ATTR_UID) { - bmval1 |= FATTR4_WORD1_OWNER; + if (bmval[1] & FATTR4_WORD1_OWNER) p = xdr_encode_opaque(p, owner_name, owner_namelen); - } - if (iap->ia_valid & ATTR_GID) { - bmval1 |= FATTR4_WORD1_OWNER_GROUP; + if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) p = xdr_encode_opaque(p, owner_group, owner_grouplen); + if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { + if (iap->ia_valid & ATTR_ATIME_SET) { + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + p = xdr_encode_hyper(p, (s64)iap->ia_atime.tv_sec); + *p++ = cpu_to_be32(iap->ia_atime.tv_nsec); + } else + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } - if (iap->ia_valid & ATTR_ATIME_SET) { - bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; - *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); - p = xdr_encode_hyper(p, (s64)iap->ia_atime.tv_sec); - *p++ = cpu_to_be32(iap->ia_atime.tv_nsec); - } - else if (iap->ia_valid & ATTR_ATIME) { - bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; - *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); - } - if (iap->ia_valid & ATTR_MTIME_SET) { - bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; - *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); - p = xdr_encode_hyper(p, (s64)iap->ia_mtime.tv_sec); - *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); - } - else if (iap->ia_valid & ATTR_MTIME) { - bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; - *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); + if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { + if (iap->ia_valid & ATTR_MTIME_SET) { + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + p = xdr_encode_hyper(p, (s64)iap->ia_mtime.tv_sec); + *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); + } else + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } - if (label) { - bmval2 |= FATTR4_WORD2_SECURITY_LABEL; + if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { *p++ = cpu_to_be32(label->lfs); *p++ = cpu_to_be32(label->pi); *p++ = cpu_to_be32(label->len); p = xdr_encode_opaque_fixed(p, label->label, label->len); } - /* - * Now we backfill the bitmap and the attribute buffer length. - */ - if (len != ((char *)p - (char *)q) + 4) { - printk(KERN_ERR "NFS: Attr length error, %u != %Zu\n", - len, ((char *)p - (char *)q) + 4); - BUG(); - } - len = (char *)p - (char *)q - 16; - *q++ = htonl(bmval0); - *q++ = htonl(bmval1); - *q++ = htonl(bmval2); - *q = htonl(len); - /* out: */ } @@ -1738,6 +1730,14 @@ static void encode_bind_conn_to_session(struct xdr_stream *xdr, *p = 0; /* use_conn_in_rdma_mode = False */ } +static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +{ + unsigned int i; + encode_uint32(xdr, NFS4_OP_MAP_NUM_WORDS); + for (i = 0; i < NFS4_OP_MAP_NUM_WORDS; i++) + encode_uint32(xdr, op_map->u.words[i]); +} + static void encode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) @@ -1751,9 +1751,20 @@ static void encode_exchange_id(struct xdr_stream *xdr, encode_string(xdr, args->id_len, args->id); - p = reserve_space(xdr, 12); - *p++ = cpu_to_be32(args->flags); - *p++ = cpu_to_be32(0); /* zero length state_protect4_a */ + encode_uint32(xdr, args->flags); + encode_uint32(xdr, args->state_protect.how); + + switch (args->state_protect.how) { + case SP4_NONE: + break; + case SP4_MACH_CRED: + encode_op_map(xdr, &args->state_protect.enforce); + encode_op_map(xdr, &args->state_protect.allow); + break; + default: + WARN_ON_ONCE(1); + break; + } if (send_implementation_id && sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) > 1 && @@ -1764,7 +1775,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, utsname()->version, utsname()->machine); if (len > 0) { - *p = cpu_to_be32(1); /* implementation id array length=1 */ + encode_uint32(xdr, 1); /* implementation id array length=1 */ encode_string(xdr, sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) - 1, @@ -1775,7 +1786,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, p = xdr_encode_hyper(p, 0); *p = cpu_to_be32(0); } else - *p = cpu_to_be32(0); /* implementation id array length=0 */ + encode_uint32(xdr, 0); /* implementation id array length=0 */ } static void encode_create_session(struct xdr_stream *xdr, @@ -1828,7 +1839,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ - *p++ = (__be32)nn->boot_time.tv_nsec; /* stamp */ + *p++ = cpu_to_be32(nn->boot_time.tv_nsec); /* stamp */ p = xdr_encode_opaque(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ @@ -1870,11 +1881,10 @@ static void encode_sequence(struct xdr_stream *xdr, struct nfs4_slot *slot = args->sa_slot; __be32 *p; - if (slot == NULL) - return; - tp = slot->table; session = tp->session; + if (!session) + return; encode_op_hdr(xdr, OP_SEQUENCE, decode_sequence_maxsz, hdr); @@ -2055,9 +2065,9 @@ static void encode_free_stateid(struct xdr_stream *xdr, static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args) { #if defined(CONFIG_NFS_V4_1) - - if (args->sa_slot) - return args->sa_slot->table->session->clp->cl_mvops->minor_version; + struct nfs4_session *session = args->sa_slot->table->session; + if (session) + return session->clp->cl_mvops->minor_version; #endif /* CONFIG_NFS_V4_1 */ return 0; } @@ -4642,7 +4652,7 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, static int decode_first_pnfs_layout_type(struct xdr_stream *xdr, uint32_t *layouttype) { - uint32_t *p; + __be32 *p; int num; p = xdr_inline_decode(xdr, 4); @@ -5387,6 +5397,23 @@ static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_re return decode_secinfo_common(xdr, res); } +static int decode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +{ + __be32 *p; + uint32_t bitmap_words; + unsigned int i; + + p = xdr_inline_decode(xdr, 4); + bitmap_words = be32_to_cpup(p++); + if (bitmap_words > NFS4_OP_MAP_NUM_WORDS) + return -EIO; + p = xdr_inline_decode(xdr, 4 * bitmap_words); + for (i = 0; i < bitmap_words; i++) + op_map->u.words[i] = be32_to_cpup(p++); + + return 0; +} + static int decode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_res *res) { @@ -5410,10 +5437,22 @@ static int decode_exchange_id(struct xdr_stream *xdr, res->seqid = be32_to_cpup(p++); res->flags = be32_to_cpup(p++); - /* We ask for SP4_NONE */ - dummy = be32_to_cpup(p); - if (dummy != SP4_NONE) + res->state_protect.how = be32_to_cpup(p); + switch (res->state_protect.how) { + case SP4_NONE: + break; + case SP4_MACH_CRED: + status = decode_op_map(xdr, &res->state_protect.enforce); + if (status) + return status; + status = decode_op_map(xdr, &res->state_protect.allow); + if (status) + return status; + break; + default: + WARN_ON_ONCE(1); return -EIO; + } /* server_owner4.so_minor_id */ p = xdr_inline_decode(xdr, 8); @@ -5607,6 +5646,8 @@ static int decode_sequence(struct xdr_stream *xdr, if (res->sr_slot == NULL) return 0; + if (!res->sr_slot->table->session) + return 0; status = decode_op_hdr(xdr, OP_SEQUENCE); if (!status) @@ -5925,21 +5966,8 @@ out: static int decode_free_stateid(struct xdr_stream *xdr, struct nfs41_free_stateid_res *res) { - __be32 *p; - int status; - - status = decode_op_hdr(xdr, OP_FREE_STATEID); - if (status) - return status; - - p = xdr_inline_decode(xdr, 4); - if (unlikely(!p)) - goto out_overflow; - res->status = be32_to_cpup(p++); + res->status = decode_op_hdr(xdr, OP_FREE_STATEID); return res->status; -out_overflow: - print_overflow_msg(__func__, xdr); - return -EIO; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfstrace.c b/fs/nfs/nfstrace.c new file mode 100644 index 0000000..4eb0aea --- /dev/null +++ b/fs/nfs/nfstrace.c @@ -0,0 +1,9 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/nfs_fs.h> +#include <linux/namei.h> +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include "nfstrace.h" diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h new file mode 100644 index 0000000..89fe741 --- /dev/null +++ b/fs/nfs/nfstrace.h @@ -0,0 +1,729 @@ +/* + * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfs + +#if !defined(_TRACE_NFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NFS_H + +#include <linux/tracepoint.h> + +#define nfs_show_file_type(ftype) \ + __print_symbolic(ftype, \ + { DT_UNKNOWN, "UNKNOWN" }, \ + { DT_FIFO, "FIFO" }, \ + { DT_CHR, "CHR" }, \ + { DT_DIR, "DIR" }, \ + { DT_BLK, "BLK" }, \ + { DT_REG, "REG" }, \ + { DT_LNK, "LNK" }, \ + { DT_SOCK, "SOCK" }, \ + { DT_WHT, "WHT" }) + +#define nfs_show_cache_validity(v) \ + __print_flags(v, "|", \ + { NFS_INO_INVALID_ATTR, "INVALID_ATTR" }, \ + { NFS_INO_INVALID_DATA, "INVALID_DATA" }, \ + { NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \ + { NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \ + { NFS_INO_INVALID_ACL, "INVALID_ACL" }, \ + { NFS_INO_REVAL_PAGECACHE, "REVAL_PAGECACHE" }, \ + { NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \ + { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }) + +#define nfs_show_nfsi_flags(v) \ + __print_flags(v, "|", \ + { 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \ + { 1 << NFS_INO_STALE, "STALE" }, \ + { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \ + { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \ + { 1 << NFS_INO_COMMIT, "COMMIT" }, \ + { 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \ + { 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" }) + +DECLARE_EVENT_CLASS(nfs_inode_event, + TP_PROTO( + const struct inode *inode + ), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode->i_version; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu ", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (unsigned long long)__entry->version + ) +); + +DECLARE_EVENT_CLASS(nfs_inode_event_done, + TP_PROTO( + const struct inode *inode, + int error + ), + + TP_ARGS(inode, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(unsigned char, type) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, size) + __field(unsigned long, nfsi_flags) + __field(unsigned long, cache_validity) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->error = error; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->type = nfs_umode_to_dtype(inode->i_mode); + __entry->version = inode->i_version; + __entry->size = i_size_read(inode); + __entry->nfsi_flags = nfsi->flags; + __entry->cache_validity = nfsi->cache_validity; + ), + + TP_printk( + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "type=%u (%s) version=%llu size=%lld " + "cache_validity=%lu (%s) nfs_flags=%ld (%s)", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->type, + nfs_show_file_type(__entry->type), + (unsigned long long)__entry->version, + (long long)__entry->size, + __entry->cache_validity, + nfs_show_cache_validity(__entry->cache_validity), + __entry->nfsi_flags, + nfs_show_nfsi_flags(__entry->nfsi_flags) + ) +); + +#define DEFINE_NFS_INODE_EVENT(name) \ + DEFINE_EVENT(nfs_inode_event, name, \ + TP_PROTO( \ + const struct inode *inode \ + ), \ + TP_ARGS(inode)) +#define DEFINE_NFS_INODE_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_inode_event_done, name, \ + TP_PROTO( \ + const struct inode *inode, \ + int error \ + ), \ + TP_ARGS(inode, error)) +DEFINE_NFS_INODE_EVENT(nfs_refresh_inode_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_refresh_inode_exit); +DEFINE_NFS_INODE_EVENT(nfs_revalidate_inode_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_revalidate_inode_exit); +DEFINE_NFS_INODE_EVENT(nfs_invalidate_mapping_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_invalidate_mapping_exit); +DEFINE_NFS_INODE_EVENT(nfs_getattr_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_getattr_exit); +DEFINE_NFS_INODE_EVENT(nfs_setattr_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_setattr_exit); +DEFINE_NFS_INODE_EVENT(nfs_writeback_page_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_page_exit); +DEFINE_NFS_INODE_EVENT(nfs_writeback_inode_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); +DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); +DEFINE_NFS_INODE_EVENT(nfs_access_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_access_exit); + +#define show_lookup_flags(flags) \ + __print_flags((unsigned long)flags, "|", \ + { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ + { LOOKUP_DIRECTORY, "DIRECTORY" }, \ + { LOOKUP_OPEN, "OPEN" }, \ + { LOOKUP_CREATE, "CREATE" }, \ + { LOOKUP_EXCL, "EXCL" }) + +DECLARE_EVENT_CLASS(nfs_lookup_event, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags + ), + + TP_ARGS(dir, dentry, flags), + + TP_STRUCT__entry( + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->flags, + show_lookup_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_LOOKUP_EVENT(name) \ + DEFINE_EVENT(nfs_lookup_event, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry, \ + unsigned int flags \ + ), \ + TP_ARGS(dir, dentry, flags)) + +DECLARE_EVENT_CLASS(nfs_lookup_event_done, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags, + int error + ), + + TP_ARGS(dir, dentry, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->error, + __entry->flags, + show_lookup_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_LOOKUP_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_lookup_event_done, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry, \ + unsigned int flags, \ + int error \ + ), \ + TP_ARGS(dir, dentry, flags, error)) + +DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter); +DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); +DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); +DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); + +#define show_open_flags(flags) \ + __print_flags((unsigned long)flags, "|", \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_APPEND, "O_APPEND" }, \ + { O_DSYNC, "O_DSYNC" }, \ + { O_DIRECT, "O_DIRECT" }, \ + { O_DIRECTORY, "O_DIRECTORY" }) + +#define show_fmode_flags(mode) \ + __print_flags(mode, "|", \ + { ((__force unsigned long)FMODE_READ), "READ" }, \ + { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ + { ((__force unsigned long)FMODE_EXEC), "EXEC" }) + +TRACE_EVENT(nfs_atomic_open_enter, + TP_PROTO( + const struct inode *dir, + const struct nfs_open_context *ctx, + unsigned int flags + ), + + TP_ARGS(dir, ctx, flags), + + TP_STRUCT__entry( + __field(unsigned int, flags) + __field(unsigned int, fmode) + __field(dev_t, dev) + __field(u64, dir) + __string(name, ctx->dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __entry->fmode = (__force unsigned int)ctx->mode; + __assign_str(name, ctx->dentry->d_name.name); + ), + + TP_printk( + "flags=%u (%s) fmode=%s name=%02x:%02x:%llu/%s", + __entry->flags, + show_open_flags(__entry->flags), + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_atomic_open_exit, + TP_PROTO( + const struct inode *dir, + const struct nfs_open_context *ctx, + unsigned int flags, + int error + ), + + TP_ARGS(dir, ctx, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(unsigned int, fmode) + __field(dev_t, dev) + __field(u64, dir) + __string(name, ctx->dentry->d_name.name) + ), + + TP_fast_assign( + __entry->error = error; + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __entry->fmode = (__force unsigned int)ctx->mode; + __assign_str(name, ctx->dentry->d_name.name); + ), + + TP_printk( + "error=%d flags=%u (%s) fmode=%s " + "name=%02x:%02x:%llu/%s", + __entry->error, + __entry->flags, + show_open_flags(__entry->flags), + show_fmode_flags(__entry->fmode), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_create_enter, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags + ), + + TP_ARGS(dir, dentry, flags), + + TP_STRUCT__entry( + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->flags, + show_open_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_create_exit, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + unsigned int flags, + int error + ), + + TP_ARGS(dir, dentry, flags, error), + + TP_STRUCT__entry( + __field(int, error) + __field(unsigned int, flags) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->error = error; + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->flags = flags; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d flags=%u (%s) name=%02x:%02x:%llu/%s", + __entry->error, + __entry->flags, + show_open_flags(__entry->flags), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +DECLARE_EVENT_CLASS(nfs_directory_event, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry + ), + + TP_ARGS(dir, dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "name=%02x:%02x:%llu/%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_DIRECTORY_EVENT(name) \ + DEFINE_EVENT(nfs_directory_event, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry \ + ), \ + TP_ARGS(dir, dentry)) + +DECLARE_EVENT_CLASS(nfs_directory_event_done, + TP_PROTO( + const struct inode *dir, + const struct dentry *dentry, + int error + ), + + TP_ARGS(dir, dentry, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +#define DEFINE_NFS_DIRECTORY_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_directory_event_done, name, \ + TP_PROTO( \ + const struct inode *dir, \ + const struct dentry *dentry, \ + int error \ + ), \ + TP_ARGS(dir, dentry, error)) + +DEFINE_NFS_DIRECTORY_EVENT(nfs_mknod_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mknod_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_mkdir_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mkdir_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_rmdir_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_rmdir_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_remove_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_remove_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_unlink_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_unlink_exit); +DEFINE_NFS_DIRECTORY_EVENT(nfs_symlink_enter); +DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_symlink_exit); + +TRACE_EVENT(nfs_link_enter, + TP_PROTO( + const struct inode *inode, + const struct inode *dir, + const struct dentry *dentry + ), + + TP_ARGS(inode, dir, dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->dir = NFS_FILEID(dir); + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->fileid, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +TRACE_EVENT(nfs_link_exit, + TP_PROTO( + const struct inode *inode, + const struct inode *dir, + const struct dentry *dentry, + int error + ), + + TP_ARGS(inode, dir, dentry, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u64, fileid) + __field(u64, dir) + __string(name, dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + __assign_str(name, dentry->d_name.name); + ), + + TP_printk( + "error=%d fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->fileid, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); + +DECLARE_EVENT_CLASS(nfs_rename_event, + TP_PROTO( + const struct inode *old_dir, + const struct dentry *old_dentry, + const struct inode *new_dir, + const struct dentry *new_dentry + ), + + TP_ARGS(old_dir, old_dentry, new_dir, new_dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, old_dir) + __field(u64, new_dir) + __string(old_name, old_dentry->d_name.name) + __string(new_name, new_dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = old_dir->i_sb->s_dev; + __entry->old_dir = NFS_FILEID(old_dir); + __entry->new_dir = NFS_FILEID(new_dir); + __assign_str(old_name, old_dentry->d_name.name); + __assign_str(new_name, new_dentry->d_name.name); + ), + + TP_printk( + "old_name=%02x:%02x:%llu/%s new_name=%02x:%02x:%llu/%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->old_dir, + __get_str(old_name), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->new_dir, + __get_str(new_name) + ) +); +#define DEFINE_NFS_RENAME_EVENT(name) \ + DEFINE_EVENT(nfs_rename_event, name, \ + TP_PROTO( \ + const struct inode *old_dir, \ + const struct dentry *old_dentry, \ + const struct inode *new_dir, \ + const struct dentry *new_dentry \ + ), \ + TP_ARGS(old_dir, old_dentry, new_dir, new_dentry)) + +DECLARE_EVENT_CLASS(nfs_rename_event_done, + TP_PROTO( + const struct inode *old_dir, + const struct dentry *old_dentry, + const struct inode *new_dir, + const struct dentry *new_dentry, + int error + ), + + TP_ARGS(old_dir, old_dentry, new_dir, new_dentry, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, old_dir) + __string(old_name, old_dentry->d_name.name) + __field(u64, new_dir) + __string(new_name, new_dentry->d_name.name) + ), + + TP_fast_assign( + __entry->dev = old_dir->i_sb->s_dev; + __entry->old_dir = NFS_FILEID(old_dir); + __entry->new_dir = NFS_FILEID(new_dir); + __entry->error = error; + __assign_str(old_name, old_dentry->d_name.name); + __assign_str(new_name, new_dentry->d_name.name); + ), + + TP_printk( + "error=%d old_name=%02x:%02x:%llu/%s " + "new_name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->old_dir, + __get_str(old_name), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->new_dir, + __get_str(new_name) + ) +); +#define DEFINE_NFS_RENAME_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_rename_event_done, name, \ + TP_PROTO( \ + const struct inode *old_dir, \ + const struct dentry *old_dentry, \ + const struct inode *new_dir, \ + const struct dentry *new_dentry, \ + int error \ + ), \ + TP_ARGS(old_dir, old_dentry, new_dir, \ + new_dentry, error)) + +DEFINE_NFS_RENAME_EVENT(nfs_rename_enter); +DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit); + +DEFINE_NFS_RENAME_EVENT_DONE(nfs_sillyrename_rename); + +TRACE_EVENT(nfs_sillyrename_unlink, + TP_PROTO( + const struct nfs_unlinkdata *data, + int error + ), + + TP_ARGS(data, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, error) + __field(u64, dir) + __dynamic_array(char, name, data->args.name.len + 1) + ), + + TP_fast_assign( + struct inode *dir = data->dir; + size_t len = data->args.name.len; + __entry->dev = dir->i_sb->s_dev; + __entry->dir = NFS_FILEID(dir); + __entry->error = error; + memcpy(__get_dynamic_array(name), + data->args.name.name, len); + ((char *)__get_dynamic_array(name))[len] = 0; + ), + + TP_printk( + "error=%d name=%02x:%02x:%llu/%s", + __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->dir, + __get_str(name) + ) +); +#endif /* _TRACE_NFS_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE nfstrace +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 29cfb7a..2ffebf2 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -328,6 +328,19 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, } EXPORT_SYMBOL_GPL(nfs_pageio_init); +static bool nfs_match_open_context(const struct nfs_open_context *ctx1, + const struct nfs_open_context *ctx2) +{ + return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; +} + +static bool nfs_match_lock_context(const struct nfs_lock_context *l1, + const struct nfs_lock_context *l2) +{ + return l1->lockowner.l_owner == l2->lockowner.l_owner + && l1->lockowner.l_pid == l2->lockowner.l_pid; +} + /** * nfs_can_coalesce_requests - test two requests for compatibility * @prev: pointer to nfs_page @@ -343,13 +356,10 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, struct nfs_page *req, struct nfs_pageio_descriptor *pgio) { - if (req->wb_context->cred != prev->wb_context->cred) - return false; - if (req->wb_lock_context->lockowner.l_owner != prev->wb_lock_context->lockowner.l_owner) - return false; - if (req->wb_lock_context->lockowner.l_pid != prev->wb_lock_context->lockowner.l_pid) + if (!nfs_match_open_context(req->wb_context, prev->wb_context)) return false; - if (req->wb_context->state != prev->wb_context->state) + if (req->wb_context->dentry->d_inode->i_flock != NULL && + !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return false; if (req->wb_pgbase != 0) return false; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 3a3a79d..d75d938 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -33,6 +33,7 @@ #include "internal.h" #include "pnfs.h" #include "iostat.h" +#include "nfs4trace.h" #define NFSDBG_FACILITY NFSDBG_PNFS #define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ) @@ -1526,6 +1527,7 @@ void pnfs_ld_write_done(struct nfs_write_data *data) { struct nfs_pgio_header *hdr = data->header; + trace_nfs4_pnfs_write(data, hdr->pnfs_error); if (!hdr->pnfs_error) { pnfs_set_layoutcommit(data); hdr->mds_ops->rpc_call_done(&data->task, data); @@ -1680,6 +1682,7 @@ void pnfs_ld_read_done(struct nfs_read_data *data) { struct nfs_pgio_header *hdr = data->header; + trace_nfs4_pnfs_read(data, hdr->pnfs_error); if (likely(!hdr->pnfs_error)) { __nfs4_read_done_cb(data); hdr->mds_ops->rpc_call_done(&data->task, data); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index c041c41..a8f57c7 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -623,9 +623,10 @@ static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message * msg->rpc_proc = &nfs_procedures[NFSPROC_READ]; } -static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) +static int nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { rpc_call_start(task); + return 0; } static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data) @@ -644,9 +645,10 @@ static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE]; } -static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) +static int nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { rpc_call_start(task); + return 0; } static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 70a26c6..31db5c3 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -513,9 +513,10 @@ static void nfs_readpage_release_common(void *calldata) void nfs_read_prepare(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); - if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags))) - rpc_exit(task, -EIO); + int err; + err = NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); + if (err) + rpc_exit(task, err); } static const struct rpc_call_ops nfs_read_common_ops = { diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 71fdc0d..a03b9c6 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -360,7 +360,8 @@ static void unregister_nfs4_fs(void) #endif static struct shrinker acl_shrinker = { - .shrink = nfs_access_cache_shrinker, + .count_objects = nfs_access_cache_count, + .scan_objects = nfs_access_cache_scan, .seeks = DEFAULT_SEEKS, }; @@ -923,7 +924,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) data->nfs_server.port = NFS_UNSPEC_PORT; data->nfs_server.protocol = XPRT_TRANSPORT_TCP; data->auth_flavors[0] = RPC_AUTH_MAXFLAVOR; - data->auth_flavor_len = 1; + data->auth_flavor_len = 0; data->minorversion = 0; data->need_mount = true; data->net = current->nsproxy->net_ns; @@ -1018,6 +1019,13 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) } } +static void nfs_set_auth_parsed_mount_data(struct nfs_parsed_mount_data *data, + rpc_authflavor_t pseudoflavor) +{ + data->auth_flavors[0] = pseudoflavor; + data->auth_flavor_len = 1; +} + /* * Parse the value of the 'sec=' option. */ @@ -1025,49 +1033,50 @@ static int nfs_parse_security_flavors(char *value, struct nfs_parsed_mount_data *mnt) { substring_t args[MAX_OPT_ARGS]; + rpc_authflavor_t pseudoflavor; dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value); switch (match_token(value, nfs_secflavor_tokens, args)) { case Opt_sec_none: - mnt->auth_flavors[0] = RPC_AUTH_NULL; + pseudoflavor = RPC_AUTH_NULL; break; case Opt_sec_sys: - mnt->auth_flavors[0] = RPC_AUTH_UNIX; + pseudoflavor = RPC_AUTH_UNIX; break; case Opt_sec_krb5: - mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5; + pseudoflavor = RPC_AUTH_GSS_KRB5; break; case Opt_sec_krb5i: - mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I; + pseudoflavor = RPC_AUTH_GSS_KRB5I; break; case Opt_sec_krb5p: - mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P; + pseudoflavor = RPC_AUTH_GSS_KRB5P; break; case Opt_sec_lkey: - mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY; + pseudoflavor = RPC_AUTH_GSS_LKEY; break; case Opt_sec_lkeyi: - mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI; + pseudoflavor = RPC_AUTH_GSS_LKEYI; break; case Opt_sec_lkeyp: - mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP; + pseudoflavor = RPC_AUTH_GSS_LKEYP; break; case Opt_sec_spkm: - mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM; + pseudoflavor = RPC_AUTH_GSS_SPKM; break; case Opt_sec_spkmi: - mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI; + pseudoflavor = RPC_AUTH_GSS_SPKMI; break; case Opt_sec_spkmp: - mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP; + pseudoflavor = RPC_AUTH_GSS_SPKMP; break; default: return 0; } mnt->flags |= NFS_MOUNT_SECFLAVOUR; - mnt->auth_flavor_len = 1; + nfs_set_auth_parsed_mount_data(mnt, pseudoflavor); return 1; } @@ -1729,7 +1738,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf * Was a sec= authflavor specified in the options? First, verify * whether the server supports it, and then just try to use it if so. */ - if (args->auth_flavors[0] != RPC_AUTH_MAXFLAVOR) { + if (args->auth_flavor_len > 0) { status = nfs_verify_authflavor(args, authlist, authlist_len); dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]); if (status) @@ -1760,7 +1769,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Fallthrough */ } dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor); - args->auth_flavors[0] = flavor; + nfs_set_auth_parsed_mount_data(args, flavor); server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); if (!IS_ERR(server)) return server; @@ -1776,7 +1785,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Last chance! Try AUTH_UNIX */ dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX); - args->auth_flavors[0] = RPC_AUTH_UNIX; + nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); } @@ -1893,6 +1902,7 @@ static int nfs23_validate_mount_data(void *options, { struct nfs_mount_data *data = (struct nfs_mount_data *)options; struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; if (data == NULL) goto out_no_data; @@ -1908,6 +1918,8 @@ static int nfs23_validate_mount_data(void *options, goto out_no_v3; data->root.size = NFS2_FHSIZE; memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); + /* Turn off security negotiation */ + extra_flags |= NFS_MOUNT_SECFLAVOUR; case 4: if (data->flags & NFS_MOUNT_SECFLAVOUR) goto out_no_sec; @@ -1935,7 +1947,7 @@ static int nfs23_validate_mount_data(void *options, * can deal with. */ args->flags = data->flags & NFS_MOUNT_FLAGMASK; - args->flags |= NFS_MOUNT_LEGACY_INTERFACE; + args->flags |= extra_flags; args->rsize = data->rsize; args->wsize = data->wsize; args->timeo = data->timeo; @@ -1959,9 +1971,10 @@ static int nfs23_validate_mount_data(void *options, args->namlen = data->namlen; args->bsize = data->bsize; - args->auth_flavors[0] = RPC_AUTH_UNIX; if (data->flags & NFS_MOUNT_SECFLAVOUR) - args->auth_flavors[0] = data->pseudoflavor; + nfs_set_auth_parsed_mount_data(args, data->pseudoflavor); + else + nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); if (!args->nfs_server.hostname) goto out_nomem; @@ -2084,6 +2097,8 @@ static int nfs_validate_text_mount_data(void *options, max_namelen = NFS4_MAXNAMLEN; max_pathlen = NFS4_MAXPATHLEN; nfs_validate_transport_protocol(args); + if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; nfs4_validate_mount_flags(args); #else goto out_v4_not_compiled; @@ -2106,6 +2121,10 @@ static int nfs_validate_text_mount_data(void *options, out_v4_not_compiled: dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); return -EPROTONOSUPPORT; +#else +out_invalid_transport_udp: + dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n"); + return -EINVAL; #endif /* !CONFIG_NFS_V4 */ out_no_address: @@ -2170,7 +2189,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->rsize = nfss->rsize; data->wsize = nfss->wsize; data->retrans = nfss->client->cl_timeout->to_retries; - data->auth_flavors[0] = nfss->client->cl_auth->au_flavor; + nfs_set_auth_parsed_mount_data(data, nfss->client->cl_auth->au_flavor); data->acregmin = nfss->acregmin / HZ; data->acregmax = nfss->acregmax / HZ; data->acdirmin = nfss->acdirmin / HZ; @@ -2277,6 +2296,18 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) nfs_initialise_sb(sb); } +#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \ + | NFS_MOUNT_SECURE \ + | NFS_MOUNT_TCP \ + | NFS_MOUNT_VER3 \ + | NFS_MOUNT_KERBEROS \ + | NFS_MOUNT_NONLM \ + | NFS_MOUNT_BROKEN_SUID \ + | NFS_MOUNT_STRICTLOCK \ + | NFS_MOUNT_UNSHARED \ + | NFS_MOUNT_NORESVPORT \ + | NFS_MOUNT_LEGACY_INTERFACE) + static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags) { const struct nfs_server *a = s->s_fs_info; @@ -2287,7 +2318,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->nfs_client != b->nfs_client) goto Ebusy; - if (a->flags != b->flags) + if ((a->flags ^ b->flags) & NFS_MOUNT_CMP_FLAGMASK) goto Ebusy; if (a->wsize != b->wsize) goto Ebusy; @@ -2301,7 +2332,8 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->acdirmax != b->acdirmax) goto Ebusy; - if (clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) + if (b->flags & NFS_MOUNT_SECFLAVOUR && + clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) goto Ebusy; return 1; Ebusy: @@ -2478,6 +2510,10 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, if (server->flags & NFS_MOUNT_NOAC) sb_mntdata.mntflags |= MS_SYNCHRONOUS; + if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL) + if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata); if (IS_ERR(s)) { @@ -2669,15 +2705,17 @@ static int nfs4_validate_mount_data(void *options, goto out_no_address; args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); - args->auth_flavors[0] = RPC_AUTH_UNIX; if (data->auth_flavourlen) { + rpc_authflavor_t pseudoflavor; if (data->auth_flavourlen > 1) goto out_inval_auth; - if (copy_from_user(&args->auth_flavors[0], + if (copy_from_user(&pseudoflavor, data->auth_flavours, - sizeof(args->auth_flavors[0]))) + sizeof(pseudoflavor))) return -EFAULT; - } + nfs_set_auth_parsed_mount_data(args, pseudoflavor); + } else + nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); if (IS_ERR(c)) @@ -2711,6 +2749,8 @@ static int nfs4_validate_mount_data(void *options, args->acdirmax = data->acdirmax; args->nfs_server.protocol = data->proto; nfs_validate_transport_protocol(args); + if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; break; default: @@ -2731,6 +2771,10 @@ out_inval_auth: out_no_address: dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n"); return -EINVAL; + +out_invalid_transport_udp: + dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n"); + return -EINVAL; } /* @@ -2746,6 +2790,7 @@ bool nfs4_disable_idmapping = true; unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE; unsigned short send_implementation_id = 1; char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = ""; +bool recover_lost_locks = false; EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport); EXPORT_SYMBOL_GPL(nfs_callback_tcpport); @@ -2754,6 +2799,7 @@ EXPORT_SYMBOL_GPL(nfs4_disable_idmapping); EXPORT_SYMBOL_GPL(max_session_slots); EXPORT_SYMBOL_GPL(send_implementation_id); EXPORT_SYMBOL_GPL(nfs4_client_id_uniquifier); +EXPORT_SYMBOL_GPL(recover_lost_locks); #define NFS_CALLBACK_MAXPORTNR (65535U) @@ -2791,4 +2837,10 @@ MODULE_PARM_DESC(send_implementation_id, "Send implementation ID with NFSv4.1 exchange_id"); MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string"); +module_param(recover_lost_locks, bool, 0644); +MODULE_PARM_DESC(recover_lost_locks, + "If the server reports that a lock might be lost, " + "try to recover it risking data corruption."); + + #endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 60395ad..bb939ed 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -20,6 +20,8 @@ #include "iostat.h" #include "delegation.h" +#include "nfstrace.h" + /** * nfs_free_unlinkdata - release data from a sillydelete operation. * @data: pointer to unlink structure. @@ -77,6 +79,7 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) struct nfs_unlinkdata *data = calldata; struct inode *dir = data->dir; + trace_nfs_sillyrename_unlink(data, task->tk_status); if (!NFS_PROTO(dir)->unlink_done(task, dir)) rpc_restart_call_prepare(task); } @@ -204,6 +207,13 @@ out_free: return ret; } +void nfs_wait_on_sillyrename(struct dentry *dentry) +{ + struct nfs_inode *nfsi = NFS_I(dentry->d_inode); + + wait_event(nfsi->waitqueue, atomic_read(&nfsi->silly_count) <= 1); +} + void nfs_block_sillyrename(struct dentry *dentry) { struct nfs_inode *nfsi = NFS_I(dentry->d_inode); @@ -336,6 +346,8 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata) struct inode *new_dir = data->new_dir; struct dentry *old_dentry = data->old_dentry; + trace_nfs_sillyrename_rename(old_dir, old_dentry, + new_dir, data->new_dentry, task->tk_status); if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) { rpc_restart_call_prepare(task); return; @@ -444,6 +456,14 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, return rpc_run_task(&task_setup_data); } +#define SILLYNAME_PREFIX ".nfs" +#define SILLYNAME_PREFIX_LEN ((unsigned)sizeof(SILLYNAME_PREFIX) - 1) +#define SILLYNAME_FILEID_LEN ((unsigned)sizeof(u64) << 1) +#define SILLYNAME_COUNTER_LEN ((unsigned)sizeof(unsigned int) << 1) +#define SILLYNAME_LEN (SILLYNAME_PREFIX_LEN + \ + SILLYNAME_FILEID_LEN + \ + SILLYNAME_COUNTER_LEN) + /** * nfs_sillyrename - Perform a silly-rename of a dentry * @dir: inode of directory that contains dentry @@ -469,10 +489,8 @@ int nfs_sillyrename(struct inode *dir, struct dentry *dentry) { static unsigned int sillycounter; - const int fileidsize = sizeof(NFS_FILEID(dentry->d_inode))*2; - const int countersize = sizeof(sillycounter)*2; - const int slen = sizeof(".nfs")+fileidsize+countersize-1; - char silly[slen+1]; + unsigned char silly[SILLYNAME_LEN + 1]; + unsigned long long fileid; struct dentry *sdentry; struct rpc_task *task; int error = -EIO; @@ -489,20 +507,20 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) if (dentry->d_flags & DCACHE_NFSFS_RENAMED) goto out; - sprintf(silly, ".nfs%*.*Lx", - fileidsize, fileidsize, - (unsigned long long)NFS_FILEID(dentry->d_inode)); + fileid = NFS_FILEID(dentry->d_inode); /* Return delegation in anticipation of the rename */ NFS_PROTO(dentry->d_inode)->return_delegation(dentry->d_inode); sdentry = NULL; do { - char *suffix = silly + slen - countersize; - + int slen; dput(sdentry); sillycounter++; - sprintf(suffix, "%*.*x", countersize, countersize, sillycounter); + slen = scnprintf(silly, sizeof(silly), + SILLYNAME_PREFIX "%0*llx%0*x", + SILLYNAME_FILEID_LEN, fileid, + SILLYNAME_COUNTER_LEN, sillycounter); dfprintk(VFS, "NFS: trying to rename %s to %s\n", dentry->d_name.name, silly); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f1bdb72..ac1dc33 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -31,6 +31,8 @@ #include "fscache.h" #include "pnfs.h" +#include "nfstrace.h" + #define NFSDBG_FACILITY NFSDBG_PAGECACHE #define MIN_POOL_WRITE (32) @@ -861,7 +863,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) return 0; l_ctx = req->wb_lock_context; do_flush = req->wb_page != page || req->wb_context != ctx; - if (l_ctx) { + if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) { do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; } @@ -874,6 +876,33 @@ int nfs_flush_incompatible(struct file *file, struct page *page) } /* + * Avoid buffered writes when a open context credential's key would + * expire soon. + * + * Returns -EACCES if the key will expire within RPC_KEY_EXPIRE_FAIL. + * + * Return 0 and set a credential flag which triggers the inode to flush + * and performs NFS_FILE_SYNC writes if the key will expired within + * RPC_KEY_EXPIRE_TIMEO. + */ +int +nfs_key_timeout_notify(struct file *filp, struct inode *inode) +{ + struct nfs_open_context *ctx = nfs_file_open_context(filp); + struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; + + return rpcauth_key_timeout_notify(auth, ctx->cred); +} + +/* + * Test if the open context credential key is marked to expire soon. + */ +bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx) +{ + return rpcauth_cred_key_to_expire(ctx->cred); +} + +/* * If the page cache is marked as unsafe or invalid, then we can't rely on * the PageUptodate() flag. In this case, we will need to turn off * write optimisations that depend on the page contents being correct. @@ -993,6 +1022,9 @@ int nfs_initiate_write(struct rpc_clnt *clnt, data->args.count, (unsigned long long)data->args.offset); + nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client, + &task_setup_data.rpc_client, &msg, data); + task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) { ret = PTR_ERR(task); @@ -1265,9 +1297,10 @@ EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); void nfs_write_prepare(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; - NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data); - if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags))) - rpc_exit(task, -EIO); + int err; + err = NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data); + if (err) + rpc_exit(task, err); } void nfs_commit_prepare(struct rpc_task *task, void *calldata) @@ -1458,6 +1491,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid); + nfs4_state_protect(NFS_SERVER(data->inode)->nfs_client, + NFS_SP4_MACH_CRED_COMMIT, &task_setup_data.rpc_client, &msg); + task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -1732,8 +1768,14 @@ int nfs_wb_all(struct inode *inode) .range_start = 0, .range_end = LLONG_MAX, }; + int ret; - return sync_inode(inode, &wbc); + trace_nfs_writeback_inode_enter(inode); + + ret = sync_inode(inode, &wbc); + + trace_nfs_writeback_inode_exit(inode, ret); + return ret; } EXPORT_SYMBOL_GPL(nfs_wb_all); @@ -1781,6 +1823,8 @@ int nfs_wb_page(struct inode *inode, struct page *page) }; int ret; + trace_nfs_writeback_page_enter(inode); + for (;;) { wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { @@ -1789,14 +1833,15 @@ int nfs_wb_page(struct inode *inode, struct page *page) goto out_error; continue; } + ret = 0; if (!PagePrivate(page)) break; ret = nfs_commit_inode(inode, FLUSH_SYNC); if (ret < 0) goto out_error; } - return 0; out_error: + trace_nfs_writeback_page_exit(inode, ret); return ret; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a7cee86..419572f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1293,7 +1293,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, * According to RFC3010, this takes precedence over all other errors. */ status = nfserr_minor_vers_mismatch; - if (args->minorversion > nfsd_supported_minorversion) + if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0) goto out; status = nfs41_check_op_ordering(args); @@ -1524,7 +1524,7 @@ static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\ - 1 + 1 + 0 + /* eir_flags, spr_how, SP4_NONE (for now) */\ + 1 + 1 + 2 + /* eir_flags, spr_how, spo_must_enforce & _allow */\ 2 + /*eir_server_owner.so_minor_id */\ /* eir_server_owner.so_major_id<> */\ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 +\ diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 105a3b0..e0a65a9 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -173,8 +173,6 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) int status; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname); - if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) return; if (!nn->rec_file) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 280acef..0874998 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -368,11 +368,8 @@ static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh) { struct nfs4_delegation *dp; - struct nfs4_file *fp = stp->st_file; dprintk("NFSD alloc_init_deleg\n"); - if (fp->fi_had_conflict) - return NULL; if (num_delegations > max_delegations) return NULL; dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); @@ -389,8 +386,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv INIT_LIST_HEAD(&dp->dl_perfile); INIT_LIST_HEAD(&dp->dl_perclnt); INIT_LIST_HEAD(&dp->dl_recall_lru); - get_nfs4_file(fp); - dp->dl_file = fp; + dp->dl_file = NULL; dp->dl_type = NFS4_OPEN_DELEGATE_READ; fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle); dp->dl_time = 0; @@ -1264,6 +1260,8 @@ static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp) struct svc_cred *cr = &rqstp->rq_cred; u32 service; + if (!cr->cr_gss_mech) + return false; service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor); return service == RPC_GSS_SVC_INTEGRITY || service == RPC_GSS_SVC_PRIVACY; @@ -3033,7 +3031,7 @@ static int nfs4_setlease(struct nfs4_delegation *dp) if (status) { list_del_init(&dp->dl_perclnt); locks_free_lock(fl); - return -ENOMEM; + return status; } fp->fi_lease = fl; fp->fi_deleg_file = get_file(fl->fl_file); @@ -3042,22 +3040,35 @@ static int nfs4_setlease(struct nfs4_delegation *dp) return 0; } -static int nfs4_set_delegation(struct nfs4_delegation *dp) +static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp) { - struct nfs4_file *fp = dp->dl_file; + int status; - if (!fp->fi_lease) - return nfs4_setlease(dp); + if (fp->fi_had_conflict) + return -EAGAIN; + get_nfs4_file(fp); + dp->dl_file = fp; + if (!fp->fi_lease) { + status = nfs4_setlease(dp); + if (status) + goto out_free; + return 0; + } spin_lock(&recall_lock); if (fp->fi_had_conflict) { spin_unlock(&recall_lock); - return -EAGAIN; + status = -EAGAIN; + goto out_free; } atomic_inc(&fp->fi_delegees); list_add(&dp->dl_perfile, &fp->fi_delegations); spin_unlock(&recall_lock); list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); return 0; +out_free: + put_nfs4_file(fp); + dp->dl_file = fp; + return status; } static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) @@ -3132,7 +3143,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh, dp = alloc_init_deleg(oo->oo_owner.so_client, stp, fh); if (dp == NULL) goto out_no_deleg; - status = nfs4_set_delegation(dp); + status = nfs4_set_delegation(dp, stp->st_file); if (status) goto out_free; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 0c0f3ea9..d9454fe 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1816,10 +1816,7 @@ static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location, static __be32 nfsd4_encode_path(const struct path *root, const struct path *path, __be32 **pp, int *buflen) { - struct path cur = { - .mnt = path->mnt, - .dentry = path->dentry, - }; + struct path cur = *path; __be32 *p = *pp; struct dentry **components = NULL; unsigned int ncomponents = 0; @@ -1859,14 +1856,19 @@ static __be32 nfsd4_encode_path(const struct path *root, while (ncomponents) { struct dentry *dentry = components[ncomponents - 1]; - unsigned int len = dentry->d_name.len; + unsigned int len; + spin_lock(&dentry->d_lock); + len = dentry->d_name.len; *buflen -= 4 + (XDR_QUADLEN(len) << 2); - if (*buflen < 0) + if (*buflen < 0) { + spin_unlock(&dentry->d_lock); goto out_free; + } WRITE32(len); WRITEMEM(dentry->d_name.name, len); dprintk("/%s", dentry->d_name.name); + spin_unlock(&dentry->d_lock); dput(dentry); ncomponents--; } @@ -3360,7 +3362,8 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, 8 /* eir_clientid */ + 4 /* eir_sequenceid */ + 4 /* eir_flags */ + - 4 /* spr_how (SP4_NONE) */ + + 4 /* spr_how */ + + 8 /* spo_must_enforce, spo_must_allow */ + 8 /* so_minor_id */ + 4 /* so_major_id.len */ + (XDR_QUADLEN(major_id_sz) * 4) + @@ -3372,8 +3375,6 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, WRITE32(exid->seqid); WRITE32(exid->flags); - /* state_protect4_r. Currently only support SP4_NONE */ - BUG_ON(exid->spa_how != SP4_NONE); WRITE32(exid->spa_how); switch (exid->spa_how) { case SP4_NONE: diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index e76244e..9186c7c 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -59,11 +59,14 @@ static unsigned int longest_chain_cachesize; static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); static void cache_cleaner_func(struct work_struct *unused); -static int nfsd_reply_cache_shrink(struct shrinker *shrink, - struct shrink_control *sc); +static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, + struct shrink_control *sc); static struct shrinker nfsd_reply_cache_shrinker = { - .shrink = nfsd_reply_cache_shrink, + .scan_objects = nfsd_reply_cache_scan, + .count_objects = nfsd_reply_cache_count, .seeks = 1, }; @@ -232,16 +235,18 @@ nfsd_cache_entry_expired(struct svc_cacherep *rp) * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. */ -static void +static long prune_cache_entries(void) { struct svc_cacherep *rp, *tmp; + long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { if (!nfsd_cache_entry_expired(rp) && num_drc_entries <= max_drc_entries) break; nfsd_reply_cache_free_locked(rp); + freed++; } /* @@ -254,6 +259,7 @@ prune_cache_entries(void) cancel_delayed_work(&cache_cleaner); else mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE); + return freed; } static void @@ -264,20 +270,28 @@ cache_cleaner_func(struct work_struct *unused) spin_unlock(&cache_lock); } -static int -nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - unsigned int num; + unsigned long num; spin_lock(&cache_lock); - if (sc->nr_to_scan) - prune_cache_entries(); num = num_drc_entries; spin_unlock(&cache_lock); return num; } +static unsigned long +nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned long freed; + + spin_lock(&cache_lock); + freed = prune_cache_entries(); + spin_unlock(&cache_lock); + return freed; +} /* * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes */ diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 2bbd94e..30f34ab 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -53,7 +53,6 @@ struct readdir_cd { extern struct svc_program nfsd_program; extern struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; -extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; extern unsigned long nfsd_drc_max_mem; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 6b9f48c..760c85a 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -116,7 +116,10 @@ struct svc_program nfsd_program = { }; -u32 nfsd_supported_minorversion = 1; +static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = { + [0] = 1, + [1] = 1, +}; int nfsd_vers(int vers, enum vers_op change) { @@ -151,15 +154,13 @@ int nfsd_minorversion(u32 minorversion, enum vers_op change) return -1; switch(change) { case NFSD_SET: - nfsd_supported_minorversion = minorversion; + nfsd_supported_minorversions[minorversion] = true; break; case NFSD_CLEAR: - if (minorversion == 0) - return -1; - nfsd_supported_minorversion = minorversion - 1; + nfsd_supported_minorversions[minorversion] = false; break; case NFSD_TEST: - return minorversion <= nfsd_supported_minorversion; + return nfsd_supported_minorversions[minorversion]; case NFSD_AVAIL: return minorversion <= NFSD_SUPPORTED_MINOR_VERSION; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 8ff6a00..c827acb 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -830,9 +830,10 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, flags = O_WRONLY|O_LARGEFILE; } *filp = dentry_open(&path, flags, current_cred()); - if (IS_ERR(*filp)) + if (IS_ERR(*filp)) { host_err = PTR_ERR(*filp); - else { + *filp = NULL; + } else { host_err = ima_file_check(*filp, may_flags); if (may_flags & NFSD_MAY_64BIT_COOKIE) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index b1a5277..7e350c5 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -254,7 +254,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); nilfs_truncate(inode); } } diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index dc9a913..2d8be51 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -345,8 +345,7 @@ static void nilfs_end_bio_write(struct bio *bio, int err) if (err == -EOPNOTSUPP) { set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - bio_put(bio); - /* to be detected by submit_seg_bio() */ + /* to be detected by nilfs_segbuf_submit_bio() */ } if (!uptodate) @@ -377,12 +376,12 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf, bio->bi_private = segbuf; bio_get(bio); submit_bio(mode, bio); + segbuf->sb_nbio++; if (bio_flagged(bio, BIO_EOPNOTSUPP)) { bio_put(bio); err = -EOPNOTSUPP; goto failed; } - segbuf->sb_nbio++; bio_put(bio); wi->bio = NULL; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index af3ba04..7ac2a12 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -994,23 +994,16 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, return ret; } -static int nilfs_tree_was_touched(struct dentry *root_dentry) -{ - return d_count(root_dentry) > 1; -} - /** - * nilfs_try_to_shrink_tree() - try to shrink dentries of a checkpoint + * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint * @root_dentry: root dentry of the tree to be shrunk * * This function returns true if the tree was in-use. */ -static int nilfs_try_to_shrink_tree(struct dentry *root_dentry) +static bool nilfs_tree_is_busy(struct dentry *root_dentry) { - if (have_submounts(root_dentry)) - return true; shrink_dcache_parent(root_dentry); - return nilfs_tree_was_touched(root_dentry); + return d_count(root_dentry) > 1; } int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno) @@ -1034,8 +1027,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno) if (inode) { dentry = d_find_alias(inode); if (dentry) { - if (nilfs_tree_was_touched(dentry)) - ret = nilfs_try_to_shrink_tree(dentry); + ret = nilfs_tree_is_busy(dentry); dput(dentry); } iput(inode); @@ -1331,11 +1323,8 @@ nilfs_mount(struct file_system_type *fs_type, int flags, s->s_flags |= MS_ACTIVE; } else if (!sd.cno) { - int busy = false; - - if (nilfs_tree_was_touched(s->s_root)) { - busy = nilfs_try_to_shrink_tree(s->s_root); - if (busy && (flags ^ s->s_flags) & MS_RDONLY) { + if (nilfs_tree_is_busy(s->s_root)) { + if ((flags ^ s->s_flags) & MS_RDONLY) { printk(KERN_ERR "NILFS: the device already " "has a %s mount.\n", (s->s_flags & MS_RDONLY) ? @@ -1343,8 +1332,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, err = -EBUSY; goto failed_super; } - } - if (!busy) { + } else { /* * Try remount to setup mount states if the current * tree is not mounted and only snapshots use this sb. diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index c5670b8..ea4ba9d 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1768,7 +1768,7 @@ static void ntfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); ntfs_truncate_vfs(inode); } } diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 8a40457..b4f788e 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -51,10 +51,6 @@ static struct posix_acl *ocfs2_acl_from_xattr(const void *value, size_t size) return ERR_PTR(-EINVAL); count = size / sizeof(struct posix_acl_entry); - if (count < 0) - return ERR_PTR(-EINVAL); - if (count == 0) - return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 79736a2..f37d3c0 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -565,9 +565,7 @@ bail: static void ocfs2_dio_end_io(struct kiocb *iocb, loff_t offset, ssize_t bytes, - void *private, - int ret, - bool is_async) + void *private) { struct inode *inode = file_inode(iocb->ki_filp); int level; @@ -592,10 +590,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); - - inode_dio_done(inode); - if (is_async) - aio_complete(iocb, ret, 0); } /* @@ -1757,7 +1751,7 @@ try_again: goto out; } else if (ret == 1) { clusters_need = wc->w_clen; - ret = ocfs2_refcount_cow(inode, filp, di_bh, + ret = ocfs2_refcount_cow(inode, di_bh, wc->w_cpos, wc->w_clen, UINT_MAX); if (ret) { mlog_errno(ret); @@ -2050,7 +2044,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping, out_write_size: pos += copied; - if (pos > inode->i_size) { + if (pos > i_size_read(inode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 5c1c864..363f0dc 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -628,11 +628,9 @@ static void o2hb_fire_callbacks(struct o2hb_callback *hbcall, struct o2nm_node *node, int idx) { - struct list_head *iter; struct o2hb_callback_func *f; - list_for_each(iter, &hbcall->list) { - f = list_entry(iter, struct o2hb_callback_func, hc_item); + list_for_each_entry(f, &hbcall->list, hc_item) { mlog(ML_HEARTBEAT, "calling funcs %p\n", f); (f->hc_func)(node, idx, f->hc_data); } @@ -641,16 +639,9 @@ static void o2hb_fire_callbacks(struct o2hb_callback *hbcall, /* Will run the list in order until we process the passed event */ static void o2hb_run_event_list(struct o2hb_node_event *queued_event) { - int empty; struct o2hb_callback *hbcall; struct o2hb_node_event *event; - spin_lock(&o2hb_live_lock); - empty = list_empty(&queued_event->hn_item); - spin_unlock(&o2hb_live_lock); - if (empty) - return; - /* Holding callback sem assures we don't alter the callback * lists when doing this, and serializes ourselves with other * processes wanting callbacks. */ @@ -709,6 +700,7 @@ static void o2hb_shutdown_slot(struct o2hb_disk_slot *slot) struct o2hb_node_event event = { .hn_item = LIST_HEAD_INIT(event.hn_item), }; struct o2nm_node *node; + int queued = 0; node = o2nm_get_node_by_num(slot->ds_node_num); if (!node) @@ -726,11 +718,13 @@ static void o2hb_shutdown_slot(struct o2hb_disk_slot *slot) o2hb_queue_node_event(&event, O2HB_NODE_DOWN_CB, node, slot->ds_node_num); + queued = 1; } } spin_unlock(&o2hb_live_lock); - o2hb_run_event_list(&event); + if (queued) + o2hb_run_event_list(&event); o2nm_node_put(node); } @@ -790,6 +784,7 @@ static int o2hb_check_slot(struct o2hb_region *reg, unsigned int dead_ms = o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS; unsigned int slot_dead_ms; int tmp; + int queued = 0; memcpy(hb_block, slot->ds_raw_block, reg->hr_block_bytes); @@ -883,6 +878,7 @@ fire_callbacks: slot->ds_node_num); changed = 1; + queued = 1; } list_add_tail(&slot->ds_live_item, @@ -934,6 +930,7 @@ fire_callbacks: node, slot->ds_node_num); changed = 1; + queued = 1; } /* We don't clear this because the node is still @@ -949,7 +946,8 @@ fire_callbacks: out: spin_unlock(&o2hb_live_lock); - o2hb_run_event_list(&event); + if (queued) + o2hb_run_event_list(&event); if (node) o2nm_node_put(node); @@ -2516,8 +2514,7 @@ unlock: int o2hb_register_callback(const char *region_uuid, struct o2hb_callback_func *hc) { - struct o2hb_callback_func *tmp; - struct list_head *iter; + struct o2hb_callback_func *f; struct o2hb_callback *hbcall; int ret; @@ -2540,10 +2537,9 @@ int o2hb_register_callback(const char *region_uuid, down_write(&o2hb_callback_sem); - list_for_each(iter, &hbcall->list) { - tmp = list_entry(iter, struct o2hb_callback_func, hc_item); - if (hc->hc_priority < tmp->hc_priority) { - list_add_tail(&hc->hc_item, iter); + list_for_each_entry(f, &hbcall->list, hc_item) { + if (hc->hc_priority < f->hc_priority) { + list_add_tail(&hc->hc_item, &f->hc_item); break; } } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index d644dc6..2cd2406 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -543,8 +543,9 @@ static void o2net_set_nn_state(struct o2net_node *nn, } if (was_valid && !valid) { - printk(KERN_NOTICE "o2net: No longer connected to " - SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc)); + if (old_sc) + printk(KERN_NOTICE "o2net: No longer connected to " + SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc)); o2net_complete_nodes_nsw(nn); } @@ -765,32 +766,32 @@ static struct o2net_msg_handler * o2net_handler_tree_lookup(u32 msg_type, u32 key, struct rb_node ***ret_p, struct rb_node **ret_parent) { - struct rb_node **p = &o2net_handler_tree.rb_node; - struct rb_node *parent = NULL; + struct rb_node **p = &o2net_handler_tree.rb_node; + struct rb_node *parent = NULL; struct o2net_msg_handler *nmh, *ret = NULL; int cmp; - while (*p) { - parent = *p; - nmh = rb_entry(parent, struct o2net_msg_handler, nh_node); + while (*p) { + parent = *p; + nmh = rb_entry(parent, struct o2net_msg_handler, nh_node); cmp = o2net_handler_cmp(nmh, msg_type, key); - if (cmp < 0) - p = &(*p)->rb_left; - else if (cmp > 0) - p = &(*p)->rb_right; - else { + if (cmp < 0) + p = &(*p)->rb_left; + else if (cmp > 0) + p = &(*p)->rb_right; + else { ret = nmh; - break; + break; } - } + } - if (ret_p != NULL) - *ret_p = p; - if (ret_parent != NULL) - *ret_parent = parent; + if (ret_p != NULL) + *ret_p = p; + if (ret_parent != NULL) + *ret_parent = parent; - return ret; + return ret; } static void o2net_handler_kref_release(struct kref *kref) @@ -1695,13 +1696,12 @@ static void o2net_start_connect(struct work_struct *work) ret = 0; out: - if (ret) { + if (ret && sc) { printk(KERN_NOTICE "o2net: Connect attempt to " SC_NODEF_FMT " failed with errno %d\n", SC_NODEF_ARGS(sc), ret); /* 0 err so that another will be queued and attempted * from set_nn_state */ - if (sc) - o2net_ensure_shutdown(nn, sc, 0); + o2net_ensure_shutdown(nn, sc, 0); } if (sc) sc_put(sc); @@ -1873,12 +1873,16 @@ static int o2net_accept_one(struct socket *sock) if (o2nm_this_node() >= node->nd_num) { local_node = o2nm_get_node_by_num(o2nm_this_node()); - printk(KERN_NOTICE "o2net: Unexpected connect attempt seen " - "at node '%s' (%u, %pI4:%d) from node '%s' (%u, " - "%pI4:%d)\n", local_node->nd_name, local_node->nd_num, - &(local_node->nd_ipv4_address), - ntohs(local_node->nd_ipv4_port), node->nd_name, - node->nd_num, &sin.sin_addr.s_addr, ntohs(sin.sin_port)); + if (local_node) + printk(KERN_NOTICE "o2net: Unexpected connect attempt " + "seen at node '%s' (%u, %pI4:%d) from " + "node '%s' (%u, %pI4:%d)\n", + local_node->nd_name, local_node->nd_num, + &(local_node->nd_ipv4_address), + ntohs(local_node->nd_ipv4_port), + node->nd_name, + node->nd_num, &sin.sin_addr.s_addr, + ntohs(sin.sin_port)); ret = -EINVAL; goto out; } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index eb760d8..30544ce 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2153,11 +2153,9 @@ int ocfs2_empty_dir(struct inode *inode) { int ret; struct ocfs2_empty_dir_priv priv = { - .ctx.actor = ocfs2_empty_dir_filldir + .ctx.actor = ocfs2_empty_dir_filldir, }; - memset(&priv, 0, sizeof(priv)); - if (ocfs2_dir_indexed(inode)) { ret = ocfs2_empty_dir_dx(inode, &priv); if (ret) diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index fbec0be..b46278f 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -292,7 +292,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data, struct dlm_lock *lock = NULL; struct dlm_proxy_ast *past = (struct dlm_proxy_ast *) msg->buf; char *name; - struct list_head *iter, *head=NULL; + struct list_head *head = NULL; __be64 cookie; u32 flags; u8 node; @@ -373,8 +373,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data, /* try convert queue for both ast/bast */ head = &res->converting; lock = NULL; - list_for_each(iter, head) { - lock = list_entry (iter, struct dlm_lock, list); + list_for_each_entry(lock, head, list) { if (lock->ml.cookie == cookie) goto do_ast; } @@ -385,8 +384,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data, else head = &res->granted; - list_for_each(iter, head) { - lock = list_entry (iter, struct dlm_lock, list); + list_for_each_entry(lock, head, list) { if (lock->ml.cookie == cookie) goto do_ast; } diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index de854cc..e051776 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -1079,11 +1079,9 @@ static inline int dlm_lock_compatible(int existing, int request) static inline int dlm_lock_on_list(struct list_head *head, struct dlm_lock *lock) { - struct list_head *iter; struct dlm_lock *tmplock; - list_for_each(iter, head) { - tmplock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(tmplock, head, list) { if (tmplock == lock) return 1; } diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index 29a886d..e36d63f 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -123,7 +123,6 @@ static enum dlm_status __dlmconvert_master(struct dlm_ctxt *dlm, int *kick_thread) { enum dlm_status status = DLM_NORMAL; - struct list_head *iter; struct dlm_lock *tmplock=NULL; assert_spin_locked(&res->spinlock); @@ -185,16 +184,14 @@ static enum dlm_status __dlmconvert_master(struct dlm_ctxt *dlm, /* upconvert from here on */ status = DLM_NORMAL; - list_for_each(iter, &res->granted) { - tmplock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(tmplock, &res->granted, list) { if (tmplock == lock) continue; if (!dlm_lock_compatible(tmplock->ml.type, type)) goto switch_queues; } - list_for_each(iter, &res->converting) { - tmplock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(tmplock, &res->converting, list) { if (!dlm_lock_compatible(tmplock->ml.type, type)) goto switch_queues; /* existing conversion requests take precedence */ @@ -424,8 +421,8 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data, struct dlm_ctxt *dlm = data; struct dlm_convert_lock *cnv = (struct dlm_convert_lock *)msg->buf; struct dlm_lock_resource *res = NULL; - struct list_head *iter; struct dlm_lock *lock = NULL; + struct dlm_lock *tmp_lock; struct dlm_lockstatus *lksb; enum dlm_status status = DLM_NORMAL; u32 flags; @@ -471,14 +468,13 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data, dlm_error(status); goto leave; } - list_for_each(iter, &res->granted) { - lock = list_entry(iter, struct dlm_lock, list); - if (lock->ml.cookie == cnv->cookie && - lock->ml.node == cnv->node_idx) { + list_for_each_entry(tmp_lock, &res->granted, list) { + if (tmp_lock->ml.cookie == cnv->cookie && + tmp_lock->ml.node == cnv->node_idx) { + lock = tmp_lock; dlm_lock_get(lock); break; } - lock = NULL; } spin_unlock(&res->spinlock); if (!lock) { diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index 0e28e24..e33cd7a 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -96,7 +96,6 @@ static void __dlm_print_lock(struct dlm_lock *lock) void __dlm_print_one_lock_resource(struct dlm_lock_resource *res) { - struct list_head *iter2; struct dlm_lock *lock; char buf[DLM_LOCKID_NAME_MAX]; @@ -118,18 +117,15 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res) res->inflight_locks, atomic_read(&res->asts_reserved)); dlm_print_lockres_refmap(res); printk(" granted queue:\n"); - list_for_each(iter2, &res->granted) { - lock = list_entry(iter2, struct dlm_lock, list); + list_for_each_entry(lock, &res->granted, list) { __dlm_print_lock(lock); } printk(" converting queue:\n"); - list_for_each(iter2, &res->converting) { - lock = list_entry(iter2, struct dlm_lock, list); + list_for_each_entry(lock, &res->converting, list) { __dlm_print_lock(lock); } printk(" blocked queue:\n"); - list_for_each(iter2, &res->blocked) { - lock = list_entry(iter2, struct dlm_lock, list); + list_for_each_entry(lock, &res->blocked, list) { __dlm_print_lock(lock); } } @@ -446,7 +442,6 @@ static int debug_mle_print(struct dlm_ctxt *dlm, char *buf, int len) { struct dlm_master_list_entry *mle; struct hlist_head *bucket; - struct hlist_node *list; int i, out = 0; unsigned long total = 0, longest = 0, bucket_count = 0; @@ -456,9 +451,7 @@ static int debug_mle_print(struct dlm_ctxt *dlm, char *buf, int len) spin_lock(&dlm->master_lock); for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_master_hash(dlm, i); - hlist_for_each(list, bucket) { - mle = hlist_entry(list, struct dlm_master_list_entry, - master_hash_node); + hlist_for_each_entry(mle, bucket, master_hash_node) { ++total; ++bucket_count; if (len - out < 200) diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index dbb17c0..8b3382a 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -193,7 +193,7 @@ struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm, unsigned int hash) { struct hlist_head *bucket; - struct hlist_node *list; + struct dlm_lock_resource *res; mlog(0, "%.*s\n", len, name); @@ -201,9 +201,7 @@ struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm, bucket = dlm_lockres_hash(dlm, hash); - hlist_for_each(list, bucket) { - struct dlm_lock_resource *res = hlist_entry(list, - struct dlm_lock_resource, hash_node); + hlist_for_each_entry(res, bucket, hash_node) { if (res->lockname.name[0] != name[0]) continue; if (unlikely(res->lockname.len != len)) @@ -262,22 +260,19 @@ struct dlm_lock_resource * dlm_lookup_lockres(struct dlm_ctxt *dlm, static struct dlm_ctxt * __dlm_lookup_domain_full(const char *domain, int len) { - struct dlm_ctxt *tmp = NULL; - struct list_head *iter; + struct dlm_ctxt *tmp; assert_spin_locked(&dlm_domain_lock); /* tmp->name here is always NULL terminated, * but domain may not be! */ - list_for_each(iter, &dlm_domains) { - tmp = list_entry (iter, struct dlm_ctxt, list); + list_for_each_entry(tmp, &dlm_domains, list) { if (strlen(tmp->name) == len && memcmp(tmp->name, domain, len)==0) - break; - tmp = NULL; + return tmp; } - return tmp; + return NULL; } /* For null terminated domain strings ONLY */ @@ -366,25 +361,22 @@ static void __dlm_get(struct dlm_ctxt *dlm) * you shouldn't trust your pointer. */ struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm) { - struct list_head *iter; - struct dlm_ctxt *target = NULL; + struct dlm_ctxt *target; + struct dlm_ctxt *ret = NULL; spin_lock(&dlm_domain_lock); - list_for_each(iter, &dlm_domains) { - target = list_entry (iter, struct dlm_ctxt, list); - + list_for_each_entry(target, &dlm_domains, list) { if (target == dlm) { __dlm_get(target); + ret = target; break; } - - target = NULL; } spin_unlock(&dlm_domain_lock); - return target; + return ret; } int dlm_domain_fully_joined(struct dlm_ctxt *dlm) @@ -2296,13 +2288,10 @@ static DECLARE_RWSEM(dlm_callback_sem); void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm, int node_num) { - struct list_head *iter; struct dlm_eviction_cb *cb; down_read(&dlm_callback_sem); - list_for_each(iter, &dlm->dlm_eviction_callbacks) { - cb = list_entry(iter, struct dlm_eviction_cb, ec_item); - + list_for_each_entry(cb, &dlm->dlm_eviction_callbacks, ec_item) { cb->ec_func(node_num, cb->ec_data); } up_read(&dlm_callback_sem); diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 47e67c2..5d32f75 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -91,19 +91,14 @@ void dlm_destroy_lock_cache(void) static int dlm_can_grant_new_lock(struct dlm_lock_resource *res, struct dlm_lock *lock) { - struct list_head *iter; struct dlm_lock *tmplock; - list_for_each(iter, &res->granted) { - tmplock = list_entry(iter, struct dlm_lock, list); - + list_for_each_entry(tmplock, &res->granted, list) { if (!dlm_lock_compatible(tmplock->ml.type, lock->ml.type)) return 0; } - list_for_each(iter, &res->converting) { - tmplock = list_entry(iter, struct dlm_lock, list); - + list_for_each_entry(tmplock, &res->converting, list) { if (!dlm_lock_compatible(tmplock->ml.type, lock->ml.type)) return 0; if (!dlm_lock_compatible(tmplock->ml.convert_type, diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 33ecbe0..cf0f103 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -342,16 +342,13 @@ static int dlm_find_mle(struct dlm_ctxt *dlm, { struct dlm_master_list_entry *tmpmle; struct hlist_head *bucket; - struct hlist_node *list; unsigned int hash; assert_spin_locked(&dlm->master_lock); hash = dlm_lockid_hash(name, namelen); bucket = dlm_master_hash(dlm, hash); - hlist_for_each(list, bucket) { - tmpmle = hlist_entry(list, struct dlm_master_list_entry, - master_hash_node); + hlist_for_each_entry(tmpmle, bucket, master_hash_node) { if (!dlm_mle_equal(dlm, tmpmle, name, namelen)) continue; dlm_get_mle(tmpmle); @@ -3183,7 +3180,7 @@ void dlm_clean_master_list(struct dlm_ctxt *dlm, u8 dead_node) struct dlm_master_list_entry *mle; struct dlm_lock_resource *res; struct hlist_head *bucket; - struct hlist_node *list; + struct hlist_node *tmp; unsigned int i; mlog(0, "dlm=%s, dead node=%u\n", dlm->name, dead_node); @@ -3194,10 +3191,7 @@ top: spin_lock(&dlm->master_lock); for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_master_hash(dlm, i); - hlist_for_each(list, bucket) { - mle = hlist_entry(list, struct dlm_master_list_entry, - master_hash_node); - + hlist_for_each_entry_safe(mle, tmp, bucket, master_hash_node) { BUG_ON(mle->type != DLM_MLE_BLOCK && mle->type != DLM_MLE_MASTER && mle->type != DLM_MLE_MIGRATION); @@ -3378,7 +3372,7 @@ void dlm_force_free_mles(struct dlm_ctxt *dlm) int i; struct hlist_head *bucket; struct dlm_master_list_entry *mle; - struct hlist_node *tmp, *list; + struct hlist_node *tmp; /* * We notified all other nodes that we are exiting the domain and @@ -3394,9 +3388,7 @@ void dlm_force_free_mles(struct dlm_ctxt *dlm) for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_master_hash(dlm, i); - hlist_for_each_safe(list, tmp, bucket) { - mle = hlist_entry(list, struct dlm_master_list_entry, - master_hash_node); + hlist_for_each_entry_safe(mle, tmp, bucket, master_hash_node) { if (mle->type != DLM_MLE_BLOCK) { mlog(ML_ERROR, "bad mle: %p\n", mle); dlm_print_one_mle(mle); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 773bd32..0b5adca 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -787,6 +787,7 @@ static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from, { struct dlm_lock_request lr; int ret; + int status; mlog(0, "\n"); @@ -800,13 +801,15 @@ static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from, // send message ret = o2net_send_message(DLM_LOCK_REQUEST_MSG, dlm->key, - &lr, sizeof(lr), request_from, NULL); + &lr, sizeof(lr), request_from, &status); /* negative status is handled by caller */ if (ret < 0) mlog(ML_ERROR, "%s: Error %d send LOCK_REQUEST to node %u " "to recover dead node %u\n", dlm->name, ret, request_from, dead_node); + else + ret = status; // return from here, then // sleep until all received or error return ret; @@ -2328,6 +2331,14 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) } else if (res->owner == dlm->node_num) { dlm_free_dead_locks(dlm, res, dead_node); __dlm_lockres_calc_usage(dlm, res); + } else if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { + if (test_bit(dead_node, res->refmap)) { + mlog(0, "%s:%.*s: dead node %u had a ref, but had " + "no locks and had not purged before dying\n", + dlm->name, res->lockname.len, + res->lockname.name, dead_node); + dlm_lockres_clear_refmap_bit(dlm, res, dead_node); + } } spin_unlock(&res->spinlock); } diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index e73c833..9db869d 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -286,8 +286,6 @@ static void dlm_shuffle_lists(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { struct dlm_lock *lock, *target; - struct list_head *iter; - struct list_head *head; int can_grant = 1; /* @@ -314,9 +312,7 @@ converting: dlm->name, res->lockname.len, res->lockname.name); BUG(); } - head = &res->granted; - list_for_each(iter, head) { - lock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(lock, &res->granted, list) { if (lock==target) continue; if (!dlm_lock_compatible(lock->ml.type, @@ -333,9 +329,8 @@ converting: target->ml.convert_type; } } - head = &res->converting; - list_for_each(iter, head) { - lock = list_entry(iter, struct dlm_lock, list); + + list_for_each_entry(lock, &res->converting, list) { if (lock==target) continue; if (!dlm_lock_compatible(lock->ml.type, @@ -384,9 +379,7 @@ blocked: goto leave; target = list_entry(res->blocked.next, struct dlm_lock, list); - head = &res->granted; - list_for_each(iter, head) { - lock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(lock, &res->granted, list) { if (lock==target) continue; if (!dlm_lock_compatible(lock->ml.type, target->ml.type)) { @@ -400,9 +393,7 @@ blocked: } } - head = &res->converting; - list_for_each(iter, head) { - lock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(lock, &res->converting, list) { if (lock==target) continue; if (!dlm_lock_compatible(lock->ml.type, target->ml.type)) { diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 850aa7e..5698b52 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -388,7 +388,6 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data, struct dlm_ctxt *dlm = data; struct dlm_unlock_lock *unlock = (struct dlm_unlock_lock *)msg->buf; struct dlm_lock_resource *res = NULL; - struct list_head *iter; struct dlm_lock *lock = NULL; enum dlm_status status = DLM_NORMAL; int found = 0, i; @@ -458,8 +457,7 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data, } for (i=0; i<3; i++) { - list_for_each(iter, queue) { - lock = list_entry(iter, struct dlm_lock, list); + list_for_each_entry(lock, queue, list) { if (lock->ml.cookie == unlock->cookie && lock->ml.node == unlock->node_idx) { dlm_lock_get(lock); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 12bafb7..efa2b3d 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -401,11 +401,8 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); umode_t mode = S_IFDIR | 0755; - struct dlmfs_inode_private *ip; if (inode) { - ip = DLMFS_I(inode); - inode->i_ino = get_next_ino(); inode_init_owner(inode, NULL, mode); inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 2487116..767370b 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -781,7 +781,6 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, cpos = map_start >> osb->s_clustersize_bits; mapping_end = ocfs2_clusters_for_bytes(inode->i_sb, map_start + map_len); - mapping_end -= cpos; is_last = 0; while (cpos < mapping_end && !is_last) { u32 fe_flags; @@ -852,20 +851,20 @@ int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence) down_read(&OCFS2_I(inode)->ip_alloc_sem); - if (*offset >= inode->i_size) { + if (*offset >= i_size_read(inode)) { ret = -ENXIO; goto out_unlock; } if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { if (whence == SEEK_HOLE) - *offset = inode->i_size; + *offset = i_size_read(inode); goto out_unlock; } clen = 0; cpos = *offset >> cs_bits; - cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size); + cend = ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)); while (cpos < cend && !is_last) { ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size, @@ -904,8 +903,8 @@ int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence) extlen = clen; extlen <<= cs_bits; - if ((extoff + extlen) > inode->i_size) - extlen = inode->i_size - extoff; + if ((extoff + extlen) > i_size_read(inode)) + extlen = i_size_read(inode) - extoff; extoff += extlen; if (extoff > *offset) *offset = extoff; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 41000f2..4f8197c 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -370,7 +370,7 @@ static int ocfs2_cow_file_pos(struct inode *inode, if (!(ext_flags & OCFS2_EXT_REFCOUNTED)) goto out; - return ocfs2_refcount_cow(inode, NULL, fe_bh, cpos, 1, cpos+1); + return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1); out: return status; @@ -671,11 +671,7 @@ restarted_transaction: } else { BUG_ON(why != RESTART_TRANS); - /* TODO: This can be more intelligent. */ - credits = ocfs2_calc_extend_credits(osb->sb, - &fe->id2.i_list, - clusters_to_add); - status = ocfs2_extend_trans(handle, credits); + status = ocfs2_allocate_extend_trans(handle, 1); if (status < 0) { /* handle still has to be committed at * this point. */ @@ -899,7 +895,7 @@ static int ocfs2_zero_extend_get_range(struct inode *inode, zero_clusters = last_cpos - zero_cpos; if (needs_cow) { - rc = ocfs2_refcount_cow(inode, NULL, di_bh, zero_cpos, + rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos, zero_clusters, UINT_MAX); if (rc) { mlog_errno(rc); @@ -1800,6 +1796,7 @@ static int ocfs2_remove_inode_range(struct inode *inode, ocfs2_truncate_cluster_pages(inode, byte_start, byte_len); out: + ocfs2_free_path(path); ocfs2_schedule_truncate_log_flush(osb, 1); ocfs2_run_deallocs(osb, &dealloc); @@ -2078,7 +2075,7 @@ static int ocfs2_prepare_inode_for_refcount(struct inode *inode, *meta_level = 1; - ret = ocfs2_refcount_cow(inode, file, di_bh, cpos, clusters, UINT_MAX); + ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); if (ret) mlog_errno(ret); out: diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 0c60ef2..fa32ce9 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -303,7 +303,7 @@ int ocfs2_info_handle_journal_size(struct inode *inode, if (o2info_from_user(oij, req)) goto bail; - oij.ij_journal_size = osb->journal->j_inode->i_size; + oij.ij_journal_size = i_size_read(osb->journal->j_inode); o2info_set_request_filled(&oij.ij_req); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 242170d..44fc3e5 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -455,6 +455,41 @@ bail: return status; } +/* + * If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA. + * If that fails, restart the transaction & regain write access for the + * buffer head which is used for metadata modifications. + * Taken from Ext4: extend_or_restart_transaction() + */ +int ocfs2_allocate_extend_trans(handle_t *handle, int thresh) +{ + int status, old_nblks; + + BUG_ON(!handle); + + old_nblks = handle->h_buffer_credits; + trace_ocfs2_allocate_extend_trans(old_nblks, thresh); + + if (old_nblks < thresh) + return 0; + + status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA); + if (status < 0) { + mlog_errno(status); + goto bail; + } + + if (status > 0) { + status = jbd2_journal_restart(handle, OCFS2_MAX_TRANS_DATA); + if (status < 0) + mlog_errno(status); + } + +bail: + return status; +} + + struct ocfs2_triggers { struct jbd2_buffer_trigger_type ot_triggers; int ot_offset; @@ -801,14 +836,14 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty) inode_lock = 1; di = (struct ocfs2_dinode *)bh->b_data; - if (inode->i_size < OCFS2_MIN_JOURNAL_SIZE) { + if (i_size_read(inode) < OCFS2_MIN_JOURNAL_SIZE) { mlog(ML_ERROR, "Journal file size (%lld) is too small!\n", - inode->i_size); + i_size_read(inode)); status = -EINVAL; goto done; } - trace_ocfs2_journal_init(inode->i_size, + trace_ocfs2_journal_init(i_size_read(inode), (unsigned long long)inode->i_blocks, OCFS2_I(inode)->ip_clusters); @@ -1096,7 +1131,7 @@ static int ocfs2_force_read_journal(struct inode *inode) memset(bhs, 0, sizeof(struct buffer_head *) * CONCURRENT_JOURNAL_FILL); - num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, inode->i_size); + num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); v_blkno = 0; while (v_blkno < num_blocks) { status = ocfs2_extent_map_get_blocks(inode, v_blkno, diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 96f9ac2..0b479ba 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -258,6 +258,17 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int ocfs2_commit_trans(struct ocfs2_super *osb, handle_t *handle); int ocfs2_extend_trans(handle_t *handle, int nblocks); +int ocfs2_allocate_extend_trans(handle_t *handle, + int thresh); + +/* + * Define an arbitrary limit for the amount of data we will anticipate + * writing to any given transaction. For unbounded transactions such as + * fallocate(2) we can write more than this, but we always + * start off at the maximum transaction size and grow the transaction + * optimistically as we go. + */ +#define OCFS2_MAX_TRANS_DATA 64U /* * Create access is for when we get a newly created buffer and we're @@ -537,7 +548,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb, extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth); return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks + - ocfs2_quota_trans_credits(sb) + bits_wanted; + ocfs2_quota_trans_credits(sb); } static inline int ocfs2_calc_symlink_credits(struct super_block *sb) diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index aebeacd..cd5496b 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -1082,7 +1082,7 @@ static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb, } retry_enospc: - (*ac)->ac_bits_wanted = osb->local_alloc_default_bits; + (*ac)->ac_bits_wanted = osb->local_alloc_bits; status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac); if (status == -ENOSPC) { if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_ENOSPC) == @@ -1154,7 +1154,7 @@ retry_enospc: OCFS2_LA_DISABLED) goto bail; - ac->ac_bits_wanted = osb->local_alloc_default_bits; + ac->ac_bits_wanted = osb->local_alloc_bits; status = ocfs2_claim_clusters(handle, ac, osb->local_alloc_bits, &cluster_off, diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index f1fc172..3d3f3c8 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -69,7 +69,7 @@ static int __ocfs2_move_extent(handle_t *handle, u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci); u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos); - ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos, + ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos, p_cpos, new_p_cpos, len); if (ret) { mlog_errno(ret); @@ -152,6 +152,7 @@ static int __ocfs2_move_extent(handle_t *handle, } out: + ocfs2_free_path(path); return ret; } @@ -845,7 +846,7 @@ static int __ocfs2_move_extents_range(struct buffer_head *di_bh, struct ocfs2_move_extents *range = context->range; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - if ((inode->i_size == 0) || (range->me_len == 0)) + if ((i_size_read(inode) == 0) || (range->me_len == 0)) return 0; if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 3b481f4..1b60c62 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -2579,6 +2579,8 @@ DEFINE_OCFS2_INT_INT_EVENT(ocfs2_extend_trans); DEFINE_OCFS2_INT_EVENT(ocfs2_extend_trans_restart); +DEFINE_OCFS2_INT_INT_EVENT(ocfs2_allocate_extend_trans); + DEFINE_OCFS2_ULL_ULL_UINT_UINT_EVENT(ocfs2_journal_access); DEFINE_OCFS2_ULL_EVENT(ocfs2_journal_dirty); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 332a281..aaa5061 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -234,7 +234,7 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type, len = sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE - offset; } - if (gqinode->i_size < off + len) { + if (i_size_read(gqinode) < off + len) { loff_t rounded_end = ocfs2_align_bytes_to_blocks(sb, off + len); @@ -778,8 +778,8 @@ static int ocfs2_acquire_dquot(struct dquot *dquot) */ WARN_ON(journal_current_handle()); status = ocfs2_extend_no_holes(gqinode, NULL, - gqinode->i_size + (need_alloc << sb->s_blocksize_bits), - gqinode->i_size); + i_size_read(gqinode) + (need_alloc << sb->s_blocksize_bits), + i_size_read(gqinode)); if (status < 0) goto out_dq; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 27fe7ee..2e4344b 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -982,14 +982,14 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( /* We are protected by dqio_sem so no locking needed */ status = ocfs2_extend_no_holes(lqinode, NULL, - lqinode->i_size + 2 * sb->s_blocksize, - lqinode->i_size); + i_size_read(lqinode) + 2 * sb->s_blocksize, + i_size_read(lqinode)); if (status < 0) { mlog_errno(status); goto out; } status = ocfs2_simple_size_update(lqinode, oinfo->dqi_lqi_bh, - lqinode->i_size + 2 * sb->s_blocksize); + i_size_read(lqinode) + 2 * sb->s_blocksize); if (status < 0) { mlog_errno(status); goto out; @@ -1125,14 +1125,14 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file( /* We are protected by dqio_sem so no locking needed */ status = ocfs2_extend_no_holes(lqinode, NULL, - lqinode->i_size + sb->s_blocksize, - lqinode->i_size); + i_size_read(lqinode) + sb->s_blocksize, + i_size_read(lqinode)); if (status < 0) { mlog_errno(status); goto out; } status = ocfs2_simple_size_update(lqinode, oinfo->dqi_lqi_bh, - lqinode->i_size + sb->s_blocksize); + i_size_read(lqinode) + sb->s_blocksize); if (status < 0) { mlog_errno(status); goto out; diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 998b17e..bf4dfc1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -49,7 +49,6 @@ struct ocfs2_cow_context { struct inode *inode; - struct file *file; u32 cow_start; u32 cow_len; struct ocfs2_extent_tree data_et; @@ -66,7 +65,7 @@ struct ocfs2_cow_context { u32 *num_clusters, unsigned int *extent_flags); int (*cow_duplicate_clusters)(handle_t *handle, - struct file *file, + struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len); }; @@ -2922,14 +2921,12 @@ static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh) } int ocfs2_duplicate_clusters_by_page(handle_t *handle, - struct file *file, + struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len) { int ret = 0, partial; - struct inode *inode = file_inode(file); - struct ocfs2_caching_info *ci = INODE_CACHE(inode); - struct super_block *sb = ocfs2_metadata_cache_get_super(ci); + struct super_block *sb = inode->i_sb; u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster); struct page *page; pgoff_t page_index; @@ -2965,6 +2962,11 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, to = map_end & (PAGE_CACHE_SIZE - 1); page = find_or_create_page(mapping, page_index, GFP_NOFS); + if (!page) { + ret = -ENOMEM; + mlog_errno(ret); + break; + } /* * In case PAGE_CACHE_SIZE <= CLUSTER_SIZE, This page @@ -2973,13 +2975,6 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize) BUG_ON(PageDirty(page)); - if (PageReadahead(page)) { - page_cache_async_readahead(mapping, - &file->f_ra, file, - page, page_index, - readahead_pages); - } - if (!PageUptodate(page)) { ret = block_read_full_page(page, ocfs2_get_block); if (ret) { @@ -2999,7 +2994,8 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, } } - ocfs2_map_and_dirty_page(inode, handle, from, to, + ocfs2_map_and_dirty_page(inode, + handle, from, to, page, 0, &new_block); mark_page_accessed(page); unlock: @@ -3015,12 +3011,11 @@ unlock: } int ocfs2_duplicate_clusters_by_jbd(handle_t *handle, - struct file *file, + struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len) { int ret = 0; - struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct ocfs2_caching_info *ci = INODE_CACHE(inode); int i, blocks = ocfs2_clusters_to_blocks(sb, new_len); @@ -3145,7 +3140,7 @@ static int ocfs2_replace_clusters(handle_t *handle, /*If the old clusters is unwritten, no need to duplicate. */ if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) { - ret = context->cow_duplicate_clusters(handle, context->file, + ret = context->cow_duplicate_clusters(handle, context->inode, cpos, old, new, len); if (ret) { mlog_errno(ret); @@ -3423,35 +3418,12 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context) return ret; } -static void ocfs2_readahead_for_cow(struct inode *inode, - struct file *file, - u32 start, u32 len) -{ - struct address_space *mapping; - pgoff_t index; - unsigned long num_pages; - int cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits; - - if (!file) - return; - - mapping = file->f_mapping; - num_pages = (len << cs_bits) >> PAGE_CACHE_SHIFT; - if (!num_pages) - num_pages = 1; - - index = ((loff_t)start << cs_bits) >> PAGE_CACHE_SHIFT; - page_cache_sync_readahead(mapping, &file->f_ra, file, - index, num_pages); -} - /* * Starting at cpos, try to CoW write_len clusters. Don't CoW * past max_cpos. This will stop when it runs into a hole or an * unrefcounted extent. */ static int ocfs2_refcount_cow_hunk(struct inode *inode, - struct file *file, struct buffer_head *di_bh, u32 cpos, u32 write_len, u32 max_cpos) { @@ -3480,8 +3452,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode, BUG_ON(cow_len == 0); - ocfs2_readahead_for_cow(inode, file, cow_start, cow_len); - context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS); if (!context) { ret = -ENOMEM; @@ -3503,7 +3473,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode, context->ref_root_bh = ref_root_bh; context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page; context->get_clusters = ocfs2_di_get_clusters; - context->file = file; ocfs2_init_dinode_extent_tree(&context->data_et, INODE_CACHE(inode), di_bh); @@ -3532,7 +3501,6 @@ out: * clusters between cpos and cpos+write_len are safe to modify. */ int ocfs2_refcount_cow(struct inode *inode, - struct file *file, struct buffer_head *di_bh, u32 cpos, u32 write_len, u32 max_cpos) { @@ -3552,7 +3520,7 @@ int ocfs2_refcount_cow(struct inode *inode, num_clusters = write_len; if (ext_flags & OCFS2_EXT_REFCOUNTED) { - ret = ocfs2_refcount_cow_hunk(inode, file, di_bh, cpos, + ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos, num_clusters, max_cpos); if (ret) { mlog_errno(ret); @@ -3886,7 +3854,10 @@ static int ocfs2_attach_refcount_tree(struct inode *inode, while (cpos < clusters) { ret = ocfs2_get_clusters(inode, cpos, &p_cluster, &num_clusters, &ext_flags); - + if (ret) { + mlog_errno(ret); + goto unlock; + } if (p_cluster && !(ext_flags & OCFS2_EXT_REFCOUNTED)) { ret = ocfs2_add_refcount_flag(inode, &di_et, &ref_tree->rf_ci, @@ -4057,7 +4028,10 @@ static int ocfs2_duplicate_extent_list(struct inode *s_inode, while (cpos < clusters) { ret = ocfs2_get_clusters(s_inode, cpos, &p_cluster, &num_clusters, &ext_flags); - + if (ret) { + mlog_errno(ret); + goto out; + } if (p_cluster) { ret = ocfs2_add_refcounted_extent(t_inode, &et, ref_ci, ref_root_bh, diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index 7754608..6422bbc 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -53,7 +53,7 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode, int *credits, int *ref_blocks); int ocfs2_refcount_cow(struct inode *inode, - struct file *filep, struct buffer_head *di_bh, + struct buffer_head *di_bh, u32 cpos, u32 write_len, u32 max_cpos); typedef int (ocfs2_post_refcount_func)(struct inode *inode, @@ -85,11 +85,11 @@ int ocfs2_refcount_cow_xattr(struct inode *inode, u32 cpos, u32 write_len, struct ocfs2_post_refcount *post); int ocfs2_duplicate_clusters_by_page(handle_t *handle, - struct file *file, + struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len); int ocfs2_duplicate_clusters_by_jbd(handle_t *handle, - struct file *file, + struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len); int ocfs2_cow_sync_writeback(struct super_block *sb, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 854d809..121da2d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1022,7 +1022,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode = NULL; struct ocfs2_super *osb = NULL; struct buffer_head *bh = NULL; - char nodestr[8]; + char nodestr[12]; struct ocfs2_blockcheck_stats stats; trace_ocfs2_fill_super(sb, data, silent); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 317ef0a..6ce0686 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3505,7 +3505,7 @@ int ocfs2_xattr_set(struct inode *inode, int ret, credits, ref_meta = 0, ref_credits = 0; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct inode *tl_inode = osb->osb_tl_inode; - struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, }; + struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, NULL, }; struct ocfs2_refcount_tree *ref_tree = NULL; struct ocfs2_xattr_info xi = { @@ -3609,13 +3609,14 @@ int ocfs2_xattr_set(struct inode *inode, if (IS_ERR(ctxt.handle)) { ret = PTR_ERR(ctxt.handle); mlog_errno(ret); - goto cleanup; + goto out_free_ac; } ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt); ocfs2_commit_trans(osb, ctxt.handle); +out_free_ac: if (ctxt.data_ac) ocfs2_free_alloc_context(ctxt.data_ac); if (ctxt.meta_ac) @@ -5881,6 +5882,10 @@ static int ocfs2_xattr_value_attach_refcount(struct inode *inode, while (cpos < clusters) { ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster, &num_clusters, el, &ext_flags); + if (ret) { + mlog_errno(ret); + break; + } cpos += num_clusters; if ((ext_flags & OCFS2_EXT_REFCOUNTED)) @@ -6797,7 +6802,7 @@ out: if (ret) { if (*meta_ac) { ocfs2_free_alloc_context(*meta_ac); - meta_ac = NULL; + *meta_ac = NULL; } } diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index e5c7f15..19f134e 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -32,7 +32,7 @@ enum ocfs2_xattr_type { struct ocfs2_security_xattr_info { int enable; - char *name; + const char *name; void *value; size_t value_len; }; diff --git a/fs/omfs/file.c b/fs/omfs/file.c index e0d9b3e..54d57d6 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -311,7 +311,7 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); omfs_truncate(inode); } } @@ -443,7 +443,7 @@ retry: goto dput_and_out; error = -EPERM; - if (!nsown_capable(CAP_SYS_CHROOT)) + if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (error) @@ -485,14 +485,13 @@ out_unlock: SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { - struct file * file; + struct fd f = fdget(fd); int err = -EBADF; - file = fget(fd); - if (file) { - audit_inode(NULL, file->f_path.dentry, 0); - err = chmod_common(&file->f_path, mode); - fput(file); + if (f.file) { + audit_inode(NULL, f.file->f_path.dentry, 0); + err = chmod_common(&f.file->f_path, mode); + fdput(f); } return err; } @@ -823,7 +822,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o int lookup_flags = 0; int acc_mode; - if (flags & O_CREAT) + if (flags & (O_CREAT | __O_TMPFILE)) op->mode = (mode & S_IALLUGO) | S_IFREG; else op->mode = 0; @@ -844,6 +843,8 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; acc_mode = MAY_OPEN | ACC_MODE(flags); + if (!(acc_mode & MAY_WRITE)) + return -EINVAL; } else if (flags & O_PATH) { /* * If we have O_PATH in the open flag. Then we @@ -19,11 +19,14 @@ #define CL_EXPIRE 0x01 #define CL_SLAVE 0x02 -#define CL_COPY_ALL 0x04 +#define CL_COPY_UNBINDABLE 0x04 #define CL_MAKE_SHARED 0x08 #define CL_PRIVATE 0x10 #define CL_SHARED_TO_SLAVE 0x20 #define CL_UNPRIVILEGED 0x40 +#define CL_COPY_MNT_NS_FILE 0x80 + +#define CL_COPY_ALL (CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE) static inline void set_mnt_shared(struct mount *mnt) { diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 75f2890..985ea88 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -230,8 +230,6 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, if (!dir_emit_dots(file, ctx)) goto out; - if (!dir_emit_dots(file, ctx)) - goto out; files = get_files_struct(p); if (!files) goto out; @@ -288,7 +286,7 @@ int proc_fd_permission(struct inode *inode, int mask) int rv = generic_permission(inode, mask); if (rv == 0) return 0; - if (task_pid(current) == proc_pid(inode)) + if (task_tgid(current) == proc_pid(inode)) rv = 0; return rv; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 94441a4..737e156 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -271,7 +271,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file, de = next; } while (de); spin_unlock(&proc_subdir_lock); - return 0; + return 1; } int proc_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 073aea60..9f8ef9b 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -285,6 +285,20 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) return rv; } +static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + int rv = -EIO; + unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + if (use_pde(pde)) { + get_unmapped_area = pde->proc_fops->get_unmapped_area; + if (get_unmapped_area) + rv = get_unmapped_area(file, orig_addr, len, pgoff, flags); + unuse_pde(pde); + } + return rv; +} + static int proc_reg_open(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); @@ -356,6 +370,7 @@ static const struct file_operations proc_reg_file_ops = { .compat_ioctl = proc_reg_compat_ioctl, #endif .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; @@ -368,6 +383,7 @@ static const struct file_operations proc_reg_file_ops_no_compat = { .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 5aa847a..59d85d6 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -132,13 +132,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freeswap), K(global_page_state(NR_FILE_DIRTY)), K(global_page_state(NR_WRITEBACK)), -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - K(global_page_state(NR_ANON_PAGES) - + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * - HPAGE_PMD_NR), -#else K(global_page_state(NR_ANON_PAGES)), -#endif K(global_page_state(NR_FILE_MAPPED)), K(global_page_state(NR_SHMEM)), K(global_page_state(NR_SLAB_RECLAIMABLE) + diff --git a/fs/proc/root.c b/fs/proc/root.c index 229e366..87dbcbe 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -110,7 +110,11 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, ns = task_active_pid_ns(current); options = data; - if (!current_user_ns()->may_mount_proc) + if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) + return ERR_PTR(-EPERM); + + /* Does the mounter have privilege over the pid namespace? */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); } @@ -205,7 +209,9 @@ static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentr static int proc_root_readdir(struct file *file, struct dir_context *ctx) { if (ctx->pos < FIRST_PROCESS_ENTRY) { - proc_readdir(file, ctx); + int error = proc_readdir(file, ctx); + if (unlikely(error <= 0)) + return error; ctx->pos = FIRST_PROCESS_ENTRY; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index dbf61f6..7366e9d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -730,8 +730,19 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, * of how soft-dirty works. */ pte_t ptent = *pte; - ptent = pte_wrprotect(ptent); - ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + + if (pte_present(ptent)) { + ptent = pte_wrprotect(ptent); + ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + } else if (is_swap_pte(ptent)) { + ptent = pte_swp_clear_soft_dirty(ptent); + } else if (pte_file(ptent)) { + ptent = pte_file_clear_soft_dirty(ptent); + } + + if (vma->vm_flags & VM_SOFTDIRTY) + vma->vm_flags &= ~VM_SOFTDIRTY; + set_pte_at(vma->vm_mm, addr, pte, ptent); #endif } @@ -752,14 +763,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = *pte; - if (!pte_present(ptent)) - continue; if (cp->type == CLEAR_REFS_SOFT_DIRTY) { clear_soft_dirty(vma, addr, pte); continue; } + if (!pte_present(ptent)) + continue; + page = vm_normal_page(vma, addr, ptent); if (!page) continue; @@ -859,7 +871,7 @@ typedef struct { } pagemap_entry_t; struct pagemapread { - int pos, len; + int pos, len; /* units: PM_ENTRY_BYTES, not bytes */ pagemap_entry_t *buffer; bool v2; }; @@ -867,7 +879,7 @@ struct pagemapread { #define PAGEMAP_WALK_SIZE (PMD_SIZE) #define PAGEMAP_WALK_MASK (PMD_MASK) -#define PM_ENTRY_BYTES sizeof(u64) +#define PM_ENTRY_BYTES sizeof(pagemap_entry_t) #define PM_STATUS_BITS 3 #define PM_STATUS_OFFSET (64 - PM_STATUS_BITS) #define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET) @@ -930,21 +942,25 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, flags = PM_PRESENT; page = vm_normal_page(vma, addr, pte); } else if (is_swap_pte(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - + swp_entry_t entry; + if (pte_swp_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; + entry = pte_to_swp_entry(pte); frame = swp_type(entry) | (swp_offset(entry) << MAX_SWAPFILES_SHIFT); flags = PM_SWAP; if (is_migration_entry(entry)) page = migration_entry_to_page(entry); } else { - *pme = make_pme(PM_NOT_PRESENT(pm->v2)); + if (vma->vm_flags & VM_SOFTDIRTY) + flags2 |= __PM_SOFT_DIRTY; + *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2)); return; } if (page && !PageAnon(page)) flags |= PM_FILE; - if (pte_soft_dirty(pte)) + if ((vma->vm_flags & VM_SOFTDIRTY) || pte_soft_dirty(pte)) flags2 |= __PM_SOFT_DIRTY; *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags); @@ -963,7 +979,7 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *p *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset) | PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT); else - *pme = make_pme(PM_NOT_PRESENT(pm->v2)); + *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2)); } #else static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, @@ -986,7 +1002,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (vma && pmd_trans_huge_lock(pmd, vma) == 1) { int pmd_flags2; - pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0); + if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd)) + pmd_flags2 = __PM_SOFT_DIRTY; + else + pmd_flags2 = 0; + for (; addr != end; addr += PAGE_SIZE) { unsigned long offset; @@ -1004,12 +1024,17 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (pmd_trans_unstable(pmd)) return 0; for (; addr != end; addr += PAGE_SIZE) { + int flags2; /* check to see if we've left 'vma' behind * and need a new, higher one */ if (vma && (addr >= vma->vm_end)) { vma = find_vma(walk->mm, addr); - pme = make_pme(PM_NOT_PRESENT(pm->v2)); + if (vma && (vma->vm_flags & VM_SOFTDIRTY)) + flags2 = __PM_SOFT_DIRTY; + else + flags2 = 0; + pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2)); } /* check that 'vma' actually covers this address, @@ -1033,13 +1058,15 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, #ifdef CONFIG_HUGETLB_PAGE static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, - pte_t pte, int offset) + pte_t pte, int offset, int flags2) { if (pte_present(pte)) - *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) - | PM_STATUS2(pm->v2, 0) | PM_PRESENT); + *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) | + PM_STATUS2(pm->v2, flags2) | + PM_PRESENT); else - *pme = make_pme(PM_NOT_PRESENT(pm->v2)); + *pme = make_pme(PM_NOT_PRESENT(pm->v2) | + PM_STATUS2(pm->v2, flags2)); } /* This function walks within one hugetlb entry in the single call */ @@ -1048,12 +1075,22 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, struct mm_walk *walk) { struct pagemapread *pm = walk->private; + struct vm_area_struct *vma; int err = 0; + int flags2; pagemap_entry_t pme; + vma = find_vma(walk->mm, addr); + WARN_ON_ONCE(!vma); + + if (vma && (vma->vm_flags & VM_SOFTDIRTY)) + flags2 = __PM_SOFT_DIRTY; + else + flags2 = 0; + for (; addr != end; addr += PAGE_SIZE) { int offset = (addr & ~hmask) >> PAGE_SHIFT; - huge_pte_to_pagemap_entry(&pme, pm, *pte, offset); + huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2); err = add_to_pagemap(addr, &pme, pm); if (err) return err; @@ -1116,8 +1153,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, goto out_task; pm.v2 = soft_dirty_cleared; - pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); - pm.buffer = kmalloc(pm.len, GFP_TEMPORARY); + pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); + pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY); ret = -ENOMEM; if (!pm.buffer) goto out_task; @@ -1365,8 +1402,10 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) walk.mm = mm; pol = get_vma_policy(task, vma, vma->vm_start); - mpol_to_str(buffer, sizeof(buffer), pol); + n = mpol_to_str(buffer, sizeof(buffer), pol); mpol_cond_put(pol); + if (n < 0) + return n; seq_printf(m, "%08lx %s", vma->vm_start, buffer); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 2850317..9100d69 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -21,6 +21,7 @@ #include <linux/crash_dump.h> #include <linux/list.h> #include <linux/vmalloc.h> +#include <linux/pagemap.h> #include <asm/uaccess.h> #include <asm/io.h> #include "internal.h" @@ -123,11 +124,65 @@ static ssize_t read_from_oldmem(char *buf, size_t count, return read; } +/* + * Architectures may override this function to allocate ELF header in 2nd kernel + */ +int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) +{ + return 0; +} + +/* + * Architectures may override this function to free header + */ +void __weak elfcorehdr_free(unsigned long long addr) +{} + +/* + * Architectures may override this function to read from ELF header + */ +ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + return read_from_oldmem(buf, count, ppos, 0); +} + +/* + * Architectures may override this function to read from notes sections + */ +ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) +{ + return read_from_oldmem(buf, count, ppos, 0); +} + +/* + * Architectures may override this function to map oldmem + */ +int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Copy to either kernel or user space + */ +static int copy_to(void *target, void *src, size_t size, int userbuf) +{ + if (userbuf) { + if (copy_to_user((char __user *) target, src, size)) + return -EFAULT; + } else { + memcpy(target, src, size); + } + return 0; +} + /* Read from the ELF header and then the crash dump. On error, negative value is * returned otherwise number of bytes read are returned. */ -static ssize_t read_vmcore(struct file *file, char __user *buffer, - size_t buflen, loff_t *fpos) +static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, + int userbuf) { ssize_t acc = 0, tmp; size_t tsz; @@ -144,7 +199,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, /* Read ELF core header */ if (*fpos < elfcorebuf_sz) { tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen); - if (copy_to_user(buffer, elfcorebuf + *fpos, tsz)) + if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf)) return -EFAULT; buflen -= tsz; *fpos += tsz; @@ -162,7 +217,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen); kaddr = elfnotes_buf + *fpos - elfcorebuf_sz; - if (copy_to_user(buffer, kaddr, tsz)) + if (copy_to(buffer, kaddr, tsz, userbuf)) return -EFAULT; buflen -= tsz; *fpos += tsz; @@ -178,7 +233,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, if (*fpos < m->offset + m->size) { tsz = min_t(size_t, m->offset + m->size - *fpos, buflen); start = m->paddr + *fpos - m->offset; - tmp = read_from_oldmem(buffer, tsz, &start, 1); + tmp = read_from_oldmem(buffer, tsz, &start, userbuf); if (tmp < 0) return tmp; buflen -= tsz; @@ -195,6 +250,55 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, return acc; } +static ssize_t read_vmcore(struct file *file, char __user *buffer, + size_t buflen, loff_t *fpos) +{ + return __read_vmcore((__force char *) buffer, buflen, fpos, 1); +} + +/* + * The vmcore fault handler uses the page cache and fills data using the + * standard __vmcore_read() function. + * + * On s390 the fault handler is used for memory regions that can't be mapped + * directly with remap_pfn_range(). + */ +static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ +#ifdef CONFIG_S390 + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t index = vmf->pgoff; + struct page *page; + loff_t offset; + char *buf; + int rc; + + page = find_or_create_page(mapping, index, GFP_KERNEL); + if (!page) + return VM_FAULT_OOM; + if (!PageUptodate(page)) { + offset = (loff_t) index << PAGE_CACHE_SHIFT; + buf = __va((page_to_pfn(page) << PAGE_SHIFT)); + rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0); + if (rc < 0) { + unlock_page(page); + page_cache_release(page); + return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS; + } + SetPageUptodate(page); + } + unlock_page(page); + vmf->page = page; + return 0; +#else + return VM_FAULT_SIGBUS; +#endif +} + +static const struct vm_operations_struct vmcore_mmap_ops = { + .fault = mmap_vmcore_fault, +}; + /** * alloc_elfnotes_buf - allocate buffer for ELF note segment in * vmalloc memory @@ -241,6 +345,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); vma->vm_flags |= VM_MIXEDMAP; + vma->vm_ops = &vmcore_mmap_ops; len = 0; @@ -282,9 +387,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) tsz = min_t(size_t, m->offset + m->size - start, size); paddr = m->paddr + start - m->offset; - if (remap_pfn_range(vma, vma->vm_start + len, - paddr >> PAGE_SHIFT, tsz, - vma->vm_page_prot)) + if (remap_oldmem_pfn_range(vma, vma->vm_start + len, + paddr >> PAGE_SHIFT, tsz, + vma->vm_page_prot)) goto fail; size -= tsz; start += tsz; @@ -357,7 +462,7 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr) notes_section = kmalloc(max_sz, GFP_KERNEL); if (!notes_section) return -ENOMEM; - rc = read_from_oldmem(notes_section, max_sz, &offset, 0); + rc = elfcorehdr_read_notes(notes_section, max_sz, &offset); if (rc < 0) { kfree(notes_section); return rc; @@ -444,7 +549,8 @@ static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf) if (phdr_ptr->p_type != PT_NOTE) continue; offset = phdr_ptr->p_offset; - rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0); + rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz, + &offset); if (rc < 0) return rc; notes_buf += phdr_ptr->p_memsz; @@ -536,7 +642,7 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr) notes_section = kmalloc(max_sz, GFP_KERNEL); if (!notes_section) return -ENOMEM; - rc = read_from_oldmem(notes_section, max_sz, &offset, 0); + rc = elfcorehdr_read_notes(notes_section, max_sz, &offset); if (rc < 0) { kfree(notes_section); return rc; @@ -623,7 +729,8 @@ static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf) if (phdr_ptr->p_type != PT_NOTE) continue; offset = phdr_ptr->p_offset; - rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0); + rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz, + &offset); if (rc < 0) return rc; notes_buf += phdr_ptr->p_memsz; @@ -810,7 +917,7 @@ static int __init parse_crash_elf64_headers(void) addr = elfcorehdr_addr; /* Read Elf header */ - rc = read_from_oldmem((char*)&ehdr, sizeof(Elf64_Ehdr), &addr, 0); + rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr); if (rc < 0) return rc; @@ -837,7 +944,7 @@ static int __init parse_crash_elf64_headers(void) if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0); + rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr); if (rc < 0) goto fail; @@ -866,7 +973,7 @@ static int __init parse_crash_elf32_headers(void) addr = elfcorehdr_addr; /* Read Elf header */ - rc = read_from_oldmem((char*)&ehdr, sizeof(Elf32_Ehdr), &addr, 0); + rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr); if (rc < 0) return rc; @@ -892,7 +999,7 @@ static int __init parse_crash_elf32_headers(void) if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0); + rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr); if (rc < 0) goto fail; @@ -919,7 +1026,7 @@ static int __init parse_crash_elf_headers(void) int rc=0; addr = elfcorehdr_addr; - rc = read_from_oldmem(e_ident, EI_NIDENT, &addr, 0); + rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr); if (rc < 0) return rc; if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) { @@ -952,7 +1059,14 @@ static int __init vmcore_init(void) { int rc = 0; - /* If elfcorehdr= has been passed in cmdline, then capture the dump.*/ + /* Allow architectures to allocate ELF header in 2nd kernel */ + rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size); + if (rc) + return rc; + /* + * If elfcorehdr= has been passed in cmdline or created in 2nd kernel, + * then capture the dump. + */ if (!(is_vmcore_usable())) return rc; rc = parse_crash_elf_headers(); @@ -960,6 +1074,8 @@ static int __init vmcore_init(void) pr_warn("Kdump: vmcore not initialized\n"); return rc; } + elfcorehdr_free(elfcorehdr_addr); + elfcorehdr_addr = ELFCORE_ADDR_ERR; proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations); if (proc_vmcore) diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index ca71db6..983d951 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -1,6 +1,8 @@ config PSTORE bool "Persistent store support" default n + select ZLIB_DEFLATE + select ZLIB_INFLATE help This option enables generic access to platform level persistent storage via "pstore" filesystem that can diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 71bf5f4..1282384 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -275,8 +275,8 @@ int pstore_is_mounted(void) * Set the mtime & ctime to the date that this record was originally stored. */ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, - char *data, size_t size, struct timespec time, - struct pstore_info *psi) + char *data, bool compressed, size_t size, + struct timespec time, struct pstore_info *psi) { struct dentry *root = pstore_sb->s_root; struct dentry *dentry; @@ -315,7 +315,8 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, switch (type) { case PSTORE_TYPE_DMESG: - sprintf(name, "dmesg-%s-%lld", psname, id); + sprintf(name, "dmesg-%s-%lld%s", psname, id, + compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: sprintf(name, "console-%s", psname); @@ -345,9 +346,8 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, mutex_lock(&root->d_inode->i_mutex); - rc = -ENOSPC; dentry = d_alloc_name(root, name); - if (IS_ERR(dentry)) + if (!dentry) goto fail_lockedalloc; memcpy(private->data, data, size); diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 937d820..3b3d305 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -50,8 +50,9 @@ extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); extern void pstore_get_records(int); extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id, - int count, char *data, size_t size, - struct timespec time, struct pstore_info *psi); + int count, char *data, bool compressed, + size_t size, struct timespec time, + struct pstore_info *psi); extern int pstore_is_mounted(void); #endif diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 422962a..4ffb7ab 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -26,6 +26,7 @@ #include <linux/console.h> #include <linux/module.h> #include <linux/pstore.h> +#include <linux/zlib.h> #include <linux/string.h> #include <linux/timer.h> #include <linux/slab.h> @@ -65,6 +66,15 @@ struct pstore_info *psinfo; static char *backend; +/* Compression parameters */ +#define COMPR_LEVEL 6 +#define WINDOW_BITS 12 +#define MEM_LEVEL 4 +static struct z_stream_s stream; + +static char *big_oops_buf; +static size_t big_oops_buf_sz; + /* How much of the console log to snapshot */ static unsigned long kmsg_bytes = 10240; @@ -117,6 +127,121 @@ bool pstore_cannot_block_path(enum kmsg_dump_reason reason) } EXPORT_SYMBOL_GPL(pstore_cannot_block_path); +/* Derived from logfs_compress() */ +static int pstore_compress(const void *in, void *out, size_t inlen, + size_t outlen) +{ + int err, ret; + + ret = -EIO; + err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS, + MEM_LEVEL, Z_DEFAULT_STRATEGY); + if (err != Z_OK) + goto error; + + stream.next_in = in; + stream.avail_in = inlen; + stream.total_in = 0; + stream.next_out = out; + stream.avail_out = outlen; + stream.total_out = 0; + + err = zlib_deflate(&stream, Z_FINISH); + if (err != Z_STREAM_END) + goto error; + + err = zlib_deflateEnd(&stream); + if (err != Z_OK) + goto error; + + if (stream.total_out >= stream.total_in) + goto error; + + ret = stream.total_out; +error: + return ret; +} + +/* Derived from logfs_uncompress */ +static int pstore_decompress(void *in, void *out, size_t inlen, size_t outlen) +{ + int err, ret; + + ret = -EIO; + err = zlib_inflateInit(&stream); + if (err != Z_OK) + goto error; + + stream.next_in = in; + stream.avail_in = inlen; + stream.total_in = 0; + stream.next_out = out; + stream.avail_out = outlen; + stream.total_out = 0; + + err = zlib_inflate(&stream, Z_FINISH); + if (err != Z_STREAM_END) + goto error; + + err = zlib_inflateEnd(&stream); + if (err != Z_OK) + goto error; + + ret = stream.total_out; +error: + return ret; +} + +static void allocate_buf_for_compression(void) +{ + size_t size; + + big_oops_buf_sz = (psinfo->bufsize * 100) / 45; + big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); + if (big_oops_buf) { + size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL), + zlib_inflate_workspacesize()); + stream.workspace = kmalloc(size, GFP_KERNEL); + if (!stream.workspace) { + pr_err("pstore: No memory for compression workspace; " + "skipping compression\n"); + kfree(big_oops_buf); + big_oops_buf = NULL; + } + } else { + pr_err("No memory for uncompressed data; " + "skipping compression\n"); + stream.workspace = NULL; + } + +} + +/* + * Called when compression fails, since the printk buffer + * would be fetched for compression calling it again when + * compression fails would have moved the iterator of + * printk buffer which results in fetching old contents. + * Copy the recent messages from big_oops_buf to psinfo->buf + */ +static size_t copy_kmsg_to_buffer(int hsize, size_t len) +{ + size_t total_len; + size_t diff; + + total_len = hsize + len; + + if (total_len > psinfo->bufsize) { + diff = total_len - psinfo->bufsize + hsize; + memcpy(psinfo->buf, big_oops_buf, hsize); + memcpy(psinfo->buf + hsize, big_oops_buf + diff, + psinfo->bufsize - hsize); + total_len = psinfo->bufsize; + } else + memcpy(psinfo->buf, big_oops_buf, total_len); + + return total_len; +} + /* * callback from kmsg_dump. (s2,l2) has the most recently * written bytes, older bytes are in (s1,l1). Save as much @@ -148,22 +273,56 @@ static void pstore_dump(struct kmsg_dumper *dumper, char *dst; unsigned long size; int hsize; + int zipped_len = -1; size_t len; + bool compressed; + size_t total_len; - dst = psinfo->buf; - hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); - size = psinfo->bufsize - hsize; - dst += hsize; + if (big_oops_buf) { + dst = big_oops_buf; + hsize = sprintf(dst, "%s#%d Part%d\n", why, + oopscount, part); + size = big_oops_buf_sz - hsize; - if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len)) - break; + if (!kmsg_dump_get_buffer(dumper, true, dst + hsize, + size, &len)) + break; + + zipped_len = pstore_compress(dst, psinfo->buf, + hsize + len, psinfo->bufsize); + + if (zipped_len > 0) { + compressed = true; + total_len = zipped_len; + } else { + pr_err("pstore: compression failed for Part %d" + " returned %d\n", part, zipped_len); + pr_err("pstore: Capture uncompressed" + " oops/panic report of Part %d\n", part); + compressed = false; + total_len = copy_kmsg_to_buffer(hsize, len); + } + } else { + dst = psinfo->buf; + hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, + part); + size = psinfo->bufsize - hsize; + dst += hsize; + + if (!kmsg_dump_get_buffer(dumper, true, dst, + size, &len)) + break; + + compressed = false; + total_len = hsize + len; + } ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - oopscount, hsize, hsize + len, psinfo); + oopscount, compressed, total_len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - total += hsize + len; + total += total_len; part++; } if (pstore_cannot_block_path(reason)) { @@ -221,10 +380,10 @@ static void pstore_register_console(void) {} static int pstore_write_compat(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { - return psi->write_buf(type, reason, id, part, psinfo->buf, hsize, + return psi->write_buf(type, reason, id, part, psinfo->buf, compressed, size, psi); } @@ -261,6 +420,8 @@ int pstore_register(struct pstore_info *psi) return -EINVAL; } + allocate_buf_for_compression(); + if (pstore_is_mounted()) pstore_get_records(0); @@ -297,6 +458,8 @@ void pstore_get_records(int quiet) enum pstore_type_id type; struct timespec time; int failed = 0, rc; + bool compressed; + int unzipped_len = -1; if (!psi) return; @@ -305,11 +468,32 @@ void pstore_get_records(int quiet) if (psi->open && psi->open(psi)) goto out; - while ((size = psi->read(&id, &type, &count, &time, &buf, psi)) > 0) { + while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed, + psi)) > 0) { + if (compressed && (type == PSTORE_TYPE_DMESG)) { + if (big_oops_buf) + unzipped_len = pstore_decompress(buf, + big_oops_buf, size, + big_oops_buf_sz); + + if (unzipped_len > 0) { + buf = big_oops_buf; + size = unzipped_len; + compressed = false; + } else { + pr_err("pstore: decompression failed;" + "returned %d\n", unzipped_len); + compressed = true; + } + } rc = pstore_mkfile(type, psi->name, id, count, buf, - (size_t)size, time, psi); - kfree(buf); - buf = NULL; + compressed, (size_t)size, time, psi); + if (unzipped_len < 0) { + /* Free buffer other than big oops */ + kfree(buf); + buf = NULL; + } else + unzipped_len = -1; if (rc && (rc != -EEXIST || !quiet)) failed++; } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index a6119f9..fa8cef2 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -131,9 +131,31 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, return prz; } +static void ramoops_read_kmsg_hdr(char *buffer, struct timespec *time, + bool *compressed) +{ + char data_type; + + if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n", + &time->tv_sec, &time->tv_nsec, &data_type) == 3) { + if (data_type == 'C') + *compressed = true; + else + *compressed = false; + } else if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu\n", + &time->tv_sec, &time->tv_nsec) == 2) { + *compressed = false; + } else { + time->tv_sec = 0; + time->tv_nsec = 0; + *compressed = false; + } +} + static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, - char **buf, struct pstore_info *psi) + char **buf, bool *compressed, + struct pstore_info *psi) { ssize_t size; ssize_t ecc_notice_size; @@ -152,10 +174,6 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (!prz) return 0; - /* TODO(kees): Bogus time for the moment. */ - time->tv_sec = 0; - time->tv_nsec = 0; - size = persistent_ram_old_size(prz); /* ECC correction notice */ @@ -166,12 +184,14 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, return -ENOMEM; memcpy(*buf, persistent_ram_old(prz), size); + ramoops_read_kmsg_hdr(*buf, time, compressed); persistent_ram_ecc_string(prz, *buf + size, ecc_notice_size + 1); return size + ecc_notice_size; } -static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) +static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz, + bool compressed) { char *hdr; struct timespec timestamp; @@ -182,8 +202,9 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) timestamp.tv_sec = 0; timestamp.tv_nsec = 0; } - hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n", - (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000)); + hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n", + (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000), + compressed ? 'C' : 'D'); WARN_ON_ONCE(!hdr); len = hdr ? strlen(hdr) : 0; persistent_ram_write(prz, hdr, len); @@ -196,7 +217,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, const char *buf, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { struct ramoops_context *cxt = psi->data; @@ -242,7 +263,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, prz = cxt->przs[cxt->dump_write_cnt]; - hlen = ramoops_write_kmsg_hdr(prz); + hlen = ramoops_write_kmsg_hdr(prz, compressed); if (size + hlen > prz->buffer_size) size = prz->buffer_size - hlen; persistent_ram_write(prz, buf, size); @@ -400,11 +421,11 @@ static int ramoops_probe(struct platform_device *pdev) goto fail_out; } - if (!is_power_of_2(pdata->record_size)) + if (pdata->record_size && !is_power_of_2(pdata->record_size)) pdata->record_size = rounddown_pow_of_two(pdata->record_size); - if (!is_power_of_2(pdata->console_size)) + if (pdata->console_size && !is_power_of_2(pdata->console_size)) pdata->console_size = rounddown_pow_of_two(pdata->console_size); - if (!is_power_of_2(pdata->ftrace_size)) + if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); cxt->dump_read_cnt = 0; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index fbad622..831d49a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -687,45 +687,37 @@ int dquot_quota_sync(struct super_block *sb, int type) } EXPORT_SYMBOL(dquot_quota_sync); -/* Free unused dquots from cache */ -static void prune_dqcache(int count) +static unsigned long +dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct list_head *head; struct dquot *dquot; + unsigned long freed = 0; head = free_dquots.prev; - while (head != &free_dquots && count) { + while (head != &free_dquots && sc->nr_to_scan) { dquot = list_entry(head, struct dquot, dq_free); remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); - count--; + sc->nr_to_scan--; + freed++; head = free_dquots.prev; } + return freed; } -/* - * This is called from kswapd when we think we need some - * more memory - */ -static int shrink_dqcache_memory(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long +dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { - int nr = sc->nr_to_scan; - - if (nr) { - spin_lock(&dq_list_lock); - prune_dqcache(nr); - spin_unlock(&dq_list_lock); - } - return ((unsigned) - percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS]) - /100) * sysctl_vfs_cache_pressure; + return vfs_pressure_ratio( + percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])); } static struct shrinker dqcache_shrinker = { - .shrink = shrink_dqcache_memory, + .count_objects = dqcache_shrink_count, + .scan_objects = dqcache_shrink_scan, .seeks = DEFAULT_SEEKS, }; @@ -1094,6 +1086,14 @@ static void dquot_claim_reserved_space(struct dquot *dquot, qsize_t number) dquot->dq_dqb.dqb_rsvspace -= number; } +static void dquot_reclaim_reserved_space(struct dquot *dquot, qsize_t number) +{ + if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) + number = dquot->dq_dqb.dqb_curspace; + dquot->dq_dqb.dqb_rsvspace += number; + dquot->dq_dqb.dqb_curspace -= number; +} + static inline void dquot_free_reserved_space(struct dquot *dquot, qsize_t number) { @@ -1528,6 +1528,15 @@ void inode_claim_rsv_space(struct inode *inode, qsize_t number) } EXPORT_SYMBOL(inode_claim_rsv_space); +void inode_reclaim_rsv_space(struct inode *inode, qsize_t number) +{ + spin_lock(&inode->i_lock); + *inode_reserved_space(inode) += number; + __inode_sub_bytes(inode, number); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL(inode_reclaim_rsv_space); + void inode_sub_rsv_space(struct inode *inode, qsize_t number) { spin_lock(&inode->i_lock); @@ -1702,6 +1711,35 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) EXPORT_SYMBOL(dquot_claim_space_nodirty); /* + * Convert allocated space back to in-memory reserved quotas + */ +void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) +{ + int cnt; + + if (!dquot_active(inode)) { + inode_reclaim_rsv_space(inode, number); + return; + } + + down_read(&sb_dqopt(inode->i_sb)->dqptr_sem); + spin_lock(&dq_data_lock); + /* Claim reserved quotas to allocated quotas */ + for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + if (inode->i_dquot[cnt]) + dquot_reclaim_reserved_space(inode->i_dquot[cnt], + number); + } + /* Update inode bytes */ + inode_reclaim_rsv_space(inode, number); + spin_unlock(&dq_data_lock); + mark_all_dquot_dirty(inode->i_dquot); + up_read(&sb_dqopt(inode->i_sb)->dqptr_sem); + return; +} +EXPORT_SYMBOL(dquot_reclaim_space_nodirty); + +/* * This operation can block, but only after everything is updated */ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index c24f1e1..39d1465 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -244,12 +244,6 @@ struct dentry *ramfs_mount(struct file_system_type *fs_type, return mount_nodev(fs_type, flags, data, ramfs_fill_super); } -static struct dentry *rootfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super); -} - static void ramfs_kill_sb(struct super_block *sb) { kfree(sb->s_fs_info); @@ -262,29 +256,23 @@ static struct file_system_type ramfs_fs_type = { .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; -static struct file_system_type rootfs_fs_type = { - .name = "rootfs", - .mount = rootfs_mount, - .kill_sb = kill_litter_super, -}; -static int __init init_ramfs_fs(void) -{ - return register_filesystem(&ramfs_fs_type); -} -module_init(init_ramfs_fs) - -int __init init_rootfs(void) +int __init init_ramfs_fs(void) { + static unsigned long once; int err; + if (test_and_set_bit(0, &once)) + return 0; + err = bdi_init(&ramfs_backing_dev_info); if (err) return err; - err = register_filesystem(&rootfs_fs_type); + err = register_filesystem(&ramfs_fs_type); if (err) bdi_destroy(&ramfs_backing_dev_info); return err; } +module_init(init_ramfs_fs) diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index a98b774..dc9a682 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -423,8 +423,11 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, set_sb_free_blocks(rs, sb_free_blocks(rs) + 1); journal_mark_dirty(th, s, sbh); - if (for_unformatted) + if (for_unformatted) { + int depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(inode, 1); + reiserfs_write_lock_nested(s, depth); + } } void reiserfs_free_block(struct reiserfs_transaction_handle *th, @@ -1128,6 +1131,7 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start b_blocknr_t finish = SB_BLOCK_COUNT(s) - 1; int passno = 0; int nr_allocated = 0; + int depth; determine_prealloc_size(hint); if (!hint->formatted_node) { @@ -1137,10 +1141,13 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start "reiserquota: allocating %d blocks id=%u", amount_needed, hint->inode->i_uid); #endif + depth = reiserfs_write_unlock_nested(s); quota_ret = dquot_alloc_block_nodirty(hint->inode, amount_needed); - if (quota_ret) /* Quota exceeded? */ + if (quota_ret) { /* Quota exceeded? */ + reiserfs_write_lock_nested(s, depth); return QUOTA_EXCEEDED; + } if (hint->preallocate && hint->prealloc_size) { #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, @@ -1153,6 +1160,7 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start hint->preallocate = hint->prealloc_size = 0; } /* for unformatted nodes, force large allocations */ + reiserfs_write_lock_nested(s, depth); } do { @@ -1181,9 +1189,11 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start hint->inode->i_uid); #endif /* Free not allocated blocks */ + depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(hint->inode, amount_needed + hint->prealloc_size - nr_allocated); + reiserfs_write_lock_nested(s, depth); } while (nr_allocated--) reiserfs_free_block(hint->th, hint->inode, @@ -1214,10 +1224,13 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start REISERFS_I(hint->inode)->i_prealloc_count, hint->inode->i_uid); #endif + + depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(hint->inode, amount_needed + hint->prealloc_size - nr_allocated - REISERFS_I(hint->inode)-> i_prealloc_count); + reiserfs_write_lock_nested(s, depth); } return CARRY_ON; @@ -1340,10 +1353,11 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, "reading failed", __func__, block); else { if (buffer_locked(bh)) { + int depth; PROC_INFO_INC(sb, scan_bitmap.wait); - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(sb); __wait_on_buffer(bh); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(sb, depth); } BUG_ON(!buffer_uptodate(bh)); BUG_ON(atomic_read(&bh->b_count) == 0); diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 03e4ca5..1fd2051 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -71,6 +71,7 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx) char small_buf[32]; /* avoid kmalloc if we can */ struct reiserfs_dir_entry de; int ret = 0; + int depth; reiserfs_write_lock(inode->i_sb); @@ -181,17 +182,17 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx) * Since filldir might sleep, we can release * the write lock here for other waiters */ - reiserfs_write_unlock(inode->i_sb); + depth = reiserfs_write_unlock_nested(inode->i_sb); if (!dir_emit (ctx, local_buf, d_reclen, d_ino, DT_UNKNOWN)) { - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); if (local_buf != small_buf) { kfree(local_buf); } goto end; } - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); if (local_buf != small_buf) { kfree(local_buf); } diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c index 430e065..dc4d415 100644 --- a/fs/reiserfs/fix_node.c +++ b/fs/reiserfs/fix_node.c @@ -1022,9 +1022,9 @@ static int get_far_parent(struct tree_balance *tb, if (buffer_locked(*pcom_father)) { /* Release the write lock while the buffer is busy */ - reiserfs_write_unlock(tb->tb_sb); + int depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(*pcom_father); - reiserfs_write_lock(tb->tb_sb); + reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) { brelse(*pcom_father); return REPEAT_SEARCH; @@ -1929,9 +1929,9 @@ static int get_direct_parent(struct tree_balance *tb, int h) return REPEAT_SEARCH; if (buffer_locked(bh)) { - reiserfs_write_unlock(tb->tb_sb); + int depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(bh); - reiserfs_write_lock(tb->tb_sb); + reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; } @@ -1952,6 +1952,7 @@ static int get_neighbors(struct tree_balance *tb, int h) unsigned long son_number; struct super_block *sb = tb->tb_sb; struct buffer_head *bh; + int depth; PROC_INFO_INC(sb, get_neighbors[h]); @@ -1969,9 +1970,9 @@ static int get_neighbors(struct tree_balance *tb, int h) tb->FL[h]) ? tb->lkey[h] : B_NR_ITEMS(tb-> FL[h]); son_number = B_N_CHILD_NUM(tb->FL[h], child_position); - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(tb->tb_sb); bh = sb_bread(sb, son_number); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(tb->tb_sb, depth); if (!bh) return IO_ERROR; if (FILESYSTEM_CHANGED_TB(tb)) { @@ -2009,9 +2010,9 @@ static int get_neighbors(struct tree_balance *tb, int h) child_position = (bh == tb->FR[h]) ? tb->rkey[h] + 1 : 0; son_number = B_N_CHILD_NUM(tb->FR[h], child_position); - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(tb->tb_sb); bh = sb_bread(sb, son_number); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(tb->tb_sb, depth); if (!bh) return IO_ERROR; if (FILESYSTEM_CHANGED_TB(tb)) { @@ -2272,6 +2273,7 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb) } if (locked) { + int depth; #ifdef CONFIG_REISERFS_CHECK repeat_counter++; if ((repeat_counter % 10000) == 0) { @@ -2286,9 +2288,9 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb) REPEAT_SEARCH : CARRY_ON; } #endif - reiserfs_write_unlock(tb->tb_sb); + depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(locked); - reiserfs_write_lock(tb->tb_sb); + reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; } @@ -2359,9 +2361,9 @@ int fix_nodes(int op_mode, struct tree_balance *tb, /* if it possible in indirect_to_direct conversion */ if (buffer_locked(tbS0)) { - reiserfs_write_unlock(tb->tb_sb); + int depth = reiserfs_write_unlock_nested(tb->tb_sb); __wait_on_buffer(tbS0); - reiserfs_write_lock(tb->tb_sb); + reiserfs_write_lock_nested(tb->tb_sb, depth); if (FILESYSTEM_CHANGED_TB(tb)) return REPEAT_SEARCH; } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 0048cc1..ad62bdb 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -30,7 +30,6 @@ void reiserfs_evict_inode(struct inode *inode) JOURNAL_PER_BALANCE_CNT * 2 + 2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb); struct reiserfs_transaction_handle th; - int depth; int err; if (!inode->i_nlink && !is_bad_inode(inode)) @@ -40,12 +39,13 @@ void reiserfs_evict_inode(struct inode *inode) if (inode->i_nlink) goto no_delete; - depth = reiserfs_write_lock_once(inode->i_sb); - /* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */ if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) { /* also handles bad_inode case */ + reiserfs_delete_xattrs(inode); + reiserfs_write_lock(inode->i_sb); + if (journal_begin(&th, inode->i_sb, jbegin_count)) goto out; reiserfs_update_inode_transaction(inode); @@ -57,8 +57,11 @@ void reiserfs_evict_inode(struct inode *inode) /* Do quota update inside a transaction for journaled quotas. We must do that * after delete_object so that quota updates go into the same transaction as * stat data deletion */ - if (!err) + if (!err) { + int depth = reiserfs_write_unlock_nested(inode->i_sb); dquot_free_inode(inode); + reiserfs_write_lock_nested(inode->i_sb, depth); + } if (journal_end(&th, inode->i_sb, jbegin_count)) goto out; @@ -72,12 +75,12 @@ void reiserfs_evict_inode(struct inode *inode) /* all items of file are deleted, so we can remove "save" link */ remove_save_link(inode, 0 /* not truncate */ ); /* we can't do anything * about an error here */ +out: + reiserfs_write_unlock(inode->i_sb); } else { /* no object items are in the tree */ ; } - out: - reiserfs_write_unlock_once(inode->i_sb, depth); clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */ dquot_drop(inode); inode->i_blocks = 0; @@ -610,7 +613,6 @@ int reiserfs_get_block(struct inode *inode, sector_t block, __le32 *item; int done; int fs_gen; - int lock_depth; struct reiserfs_transaction_handle *th = NULL; /* space reserved in transaction batch: . 3 balancings in direct->indirect conversion @@ -626,11 +628,11 @@ int reiserfs_get_block(struct inode *inode, sector_t block, loff_t new_offset = (((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1; - lock_depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); version = get_inode_item_key_version(inode); if (!file_capable(inode, block)) { - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); return -EFBIG; } @@ -642,7 +644,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block, /* find number of block-th logical block of the file */ ret = _get_block_create_0(inode, block, bh_result, create | GET_BLOCK_READ_DIRECT); - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); return ret; } /* @@ -760,7 +762,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block, if (!dangle && th) retval = reiserfs_end_persistent_transaction(th); - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); /* the item was found, so new blocks were not added to the file ** there is no need to make sure the inode is updated with this @@ -1011,11 +1013,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block, * long time. reschedule if needed and also release the write * lock for others. */ - if (need_resched()) { - reiserfs_write_unlock_once(inode->i_sb, lock_depth); - schedule(); - lock_depth = reiserfs_write_lock_once(inode->i_sb); - } + reiserfs_cond_resched(inode->i_sb); retval = search_for_position_by_key(inode->i_sb, &key, &path); if (retval == IO_ERROR) { @@ -1050,7 +1048,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block, retval = err; } - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); reiserfs_check_path(&path); return retval; } @@ -1509,14 +1507,15 @@ struct inode *reiserfs_iget(struct super_block *s, const struct cpu_key *key) { struct inode *inode; struct reiserfs_iget_args args; + int depth; args.objectid = key->on_disk_key.k_objectid; args.dirid = key->on_disk_key.k_dir_id; - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(s); inode = iget5_locked(s, key->on_disk_key.k_objectid, reiserfs_find_actor, reiserfs_init_locked_inode, (void *)(&args)); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); if (!inode) return ERR_PTR(-ENOMEM); @@ -1772,7 +1771,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_security_handle *security) { - struct super_block *sb; + struct super_block *sb = dir->i_sb; struct reiserfs_iget_args args; INITIALIZE_PATH(path_to_key); struct cpu_key key; @@ -1780,12 +1779,13 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, struct stat_data sd; int retval; int err; + int depth; BUG_ON(!th->t_trans_id); - reiserfs_write_unlock(inode->i_sb); + depth = reiserfs_write_unlock_nested(sb); err = dquot_alloc_inode(inode); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(sb, depth); if (err) goto out_end_trans; if (!dir->i_nlink) { @@ -1793,8 +1793,6 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, goto out_bad_inode; } - sb = dir->i_sb; - /* item head of new item */ ih.ih_key.k_dir_id = reiserfs_choose_packing(dir); ih.ih_key.k_objectid = cpu_to_le32(reiserfs_get_unused_objectid(th)); @@ -1812,10 +1810,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE); args.dirid = le32_to_cpu(ih.ih_key.k_dir_id); - reiserfs_write_unlock(inode->i_sb); + depth = reiserfs_write_unlock_nested(inode->i_sb); err = insert_inode_locked4(inode, args.objectid, reiserfs_find_actor, &args); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); if (err) { err = -EINVAL; goto out_bad_inode; @@ -1941,7 +1939,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, } if (reiserfs_posixacl(inode->i_sb)) { + reiserfs_write_unlock(inode->i_sb); retval = reiserfs_inherit_default_acl(th, dir, dentry, inode); + reiserfs_write_lock(inode->i_sb); if (retval) { err = retval; reiserfs_check_path(&path_to_key); @@ -1956,7 +1956,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, inode->i_flags |= S_PRIVATE; if (security->name) { + reiserfs_write_unlock(inode->i_sb); retval = reiserfs_security_write(th, inode, security); + reiserfs_write_lock(inode->i_sb); if (retval) { err = retval; reiserfs_check_path(&path_to_key); @@ -1982,14 +1984,16 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, INODE_PKEY(inode)->k_objectid = 0; /* Quota change must be inside a transaction for journaling */ + depth = reiserfs_write_unlock_nested(inode->i_sb); dquot_free_inode(inode); + reiserfs_write_lock_nested(inode->i_sb, depth); out_end_trans: journal_end(th, th->t_super, th->t_blocks_allocated); - reiserfs_write_unlock(inode->i_sb); /* Drop can be outside and it needs more credits so it's better to have it outside */ + depth = reiserfs_write_unlock_nested(inode->i_sb); dquot_drop(inode); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); inode->i_flags |= S_NOQUOTA; make_bad_inode(inode); @@ -2103,9 +2107,8 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps) int error; struct buffer_head *bh = NULL; int err2; - int lock_depth; - lock_depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); if (inode->i_size > 0) { error = grab_tail_page(inode, &page, &bh); @@ -2174,7 +2177,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps) page_cache_release(page); } - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); return 0; out: @@ -2183,7 +2186,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps) page_cache_release(page); } - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); return error; } @@ -2648,10 +2651,11 @@ int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len) struct inode *inode = page->mapping->host; int ret; int old_ref = 0; + int depth; - reiserfs_write_unlock(inode->i_sb); + depth = reiserfs_write_unlock_nested(inode->i_sb); reiserfs_wait_on_write_block(inode->i_sb); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); fix_tail_page_for_writing(page); if (reiserfs_transaction_running(inode->i_sb)) { @@ -2708,7 +2712,6 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, int update_sd = 0; struct reiserfs_transaction_handle *th; unsigned start; - int lock_depth = 0; bool locked = false; if ((unsigned long)fsdata & AOP_FLAG_CONT_EXPAND) @@ -2737,7 +2740,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, */ if (pos + copied > inode->i_size) { struct reiserfs_transaction_handle myth; - lock_depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); locked = true; /* If the file have grown beyond the border where it can have a tail, unmark it as needing a tail @@ -2768,7 +2771,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, } if (th) { if (!locked) { - lock_depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); locked = true; } if (!update_sd) @@ -2780,7 +2783,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, out: if (locked) - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); unlock_page(page); page_cache_release(page); @@ -2790,7 +2793,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping, return ret == 0 ? copied : ret; journal_error: - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); locked = false; if (th) { if (!update_sd) @@ -2808,10 +2811,11 @@ int reiserfs_commit_write(struct file *f, struct page *page, int ret = 0; int update_sd = 0; struct reiserfs_transaction_handle *th = NULL; + int depth; - reiserfs_write_unlock(inode->i_sb); + depth = reiserfs_write_unlock_nested(inode->i_sb); reiserfs_wait_on_write_block(inode->i_sb); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); if (reiserfs_transaction_running(inode->i_sb)) { th = current->journal_info; @@ -3110,7 +3114,6 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; unsigned int ia_valid; - int depth; int error; error = inode_change_ok(inode, attr); @@ -3122,13 +3125,14 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) if (is_quota_modification(inode, attr)) dquot_initialize(inode); - depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); if (attr->ia_valid & ATTR_SIZE) { /* version 2 items will be caught by the s_maxbytes check ** done for us in vmtruncate */ if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5 && attr->ia_size > MAX_NON_LFS) { + reiserfs_write_unlock(inode->i_sb); error = -EFBIG; goto out; } @@ -3150,8 +3154,10 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) if (err) error = err; } - if (error) + if (error) { + reiserfs_write_unlock(inode->i_sb); goto out; + } /* * file size is changed, ctime and mtime are * to be updated @@ -3159,6 +3165,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_valid |= (ATTR_MTIME | ATTR_CTIME); } } + reiserfs_write_unlock(inode->i_sb); if ((((attr->ia_valid & ATTR_UID) && (from_kuid(&init_user_ns, attr->ia_uid) & ~0xffff)) || ((attr->ia_valid & ATTR_GID) && (from_kgid(&init_user_ns, attr->ia_gid) & ~0xffff))) && @@ -3183,14 +3190,16 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) return error; /* (user+group)*(old+new) structure - we count quota info and , inode write (sb, inode) */ + reiserfs_write_lock(inode->i_sb); error = journal_begin(&th, inode->i_sb, jbegin_count); + reiserfs_write_unlock(inode->i_sb); if (error) goto out; - reiserfs_write_unlock_once(inode->i_sb, depth); error = dquot_transfer(inode, attr); - depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); if (error) { journal_end(&th, inode->i_sb, jbegin_count); + reiserfs_write_unlock(inode->i_sb); goto out; } @@ -3202,17 +3211,11 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) inode->i_gid = attr->ia_gid; mark_inode_dirty(inode); error = journal_end(&th, inode->i_sb, jbegin_count); + reiserfs_write_unlock(inode->i_sb); if (error) goto out; } - /* - * Relax the lock here, as it might truncate the - * inode pages and wait for inode pages locks. - * To release such page lock, the owner needs the - * reiserfs lock - */ - reiserfs_write_unlock_once(inode->i_sb, depth); if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size != i_size_read(inode)) { error = inode_newsize_ok(inode, attr->ia_size); @@ -3226,16 +3229,13 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) setattr_copy(inode, attr); mark_inode_dirty(inode); } - depth = reiserfs_write_lock_once(inode->i_sb); if (!error && reiserfs_posixacl(inode->i_sb)) { if (attr->ia_valid & ATTR_MODE) error = reiserfs_acl_chmod(inode); } - out: - reiserfs_write_unlock_once(inode->i_sb, depth); - +out: return error; } diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 15cb5fe..946ccbf 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -167,7 +167,6 @@ int reiserfs_commit_write(struct file *f, struct page *page, int reiserfs_unpack(struct inode *inode, struct file *filp) { int retval = 0; - int depth; int index; struct page *page; struct address_space *mapping; @@ -183,11 +182,11 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) return 0; } - depth = reiserfs_write_lock_once(inode->i_sb); - /* we need to make sure nobody is changing the file size beneath us */ reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb); + reiserfs_write_lock(inode->i_sb); + write_from = inode->i_size & (blocksize - 1); /* if we are on a block boundary, we are already unpacked. */ if (write_from == 0) { @@ -221,6 +220,6 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) out: mutex_unlock(&inode->i_mutex); - reiserfs_write_unlock_once(inode->i_sb, depth); + reiserfs_write_unlock(inode->i_sb); return retval; } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 742fdd4..73feacc4 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -947,9 +947,11 @@ static int reiserfs_async_progress_wait(struct super_block *s) struct reiserfs_journal *j = SB_JOURNAL(s); if (atomic_read(&j->j_async_throttle)) { - reiserfs_write_unlock(s); + int depth; + + depth = reiserfs_write_unlock_nested(s); congestion_wait(BLK_RW_ASYNC, HZ / 10); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } return 0; @@ -972,6 +974,7 @@ static int flush_commit_list(struct super_block *s, struct reiserfs_journal *journal = SB_JOURNAL(s); int retval = 0; int write_len; + int depth; reiserfs_check_lock_depth(s, "flush_commit_list"); @@ -1018,12 +1021,12 @@ static int flush_commit_list(struct super_block *s, * We might sleep in numerous places inside * write_ordered_buffers. Relax the write lock. */ - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(s); ret = write_ordered_buffers(&journal->j_dirty_buffers_lock, journal, jl, &jl->j_bh_list); if (ret < 0 && retval == 0) retval = ret; - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } BUG_ON(!list_empty(&jl->j_bh_list)); /* @@ -1043,9 +1046,9 @@ static int flush_commit_list(struct super_block *s, tbh = journal_find_get_block(s, bn); if (tbh) { if (buffer_dirty(tbh)) { - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(s); ll_rw_block(WRITE, 1, &tbh); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } put_bh(tbh) ; } @@ -1057,17 +1060,17 @@ static int flush_commit_list(struct super_block *s, (jl->j_start + i) % SB_ONDISK_JOURNAL_SIZE(s); tbh = journal_find_get_block(s, bn); - reiserfs_write_unlock(s); - wait_on_buffer(tbh); - reiserfs_write_lock(s); + depth = reiserfs_write_unlock_nested(s); + __wait_on_buffer(tbh); + reiserfs_write_lock_nested(s, depth); // since we're using ll_rw_blk above, it might have skipped over // a locked buffer. Double check here // /* redundant, sync_dirty_buffer() checks */ if (buffer_dirty(tbh)) { - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(s); sync_dirty_buffer(tbh); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } if (unlikely(!buffer_uptodate(tbh))) { #ifdef CONFIG_REISERFS_CHECK @@ -1091,12 +1094,12 @@ static int flush_commit_list(struct super_block *s, if (buffer_dirty(jl->j_commit_bh)) BUG(); mark_buffer_dirty(jl->j_commit_bh) ; - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(s); if (reiserfs_barrier_flush(s)) __sync_dirty_buffer(jl->j_commit_bh, WRITE_FLUSH_FUA); else sync_dirty_buffer(jl->j_commit_bh); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } /* If there was a write error in the journal - we can't commit this @@ -1228,15 +1231,16 @@ static int _update_journal_header_block(struct super_block *sb, { struct reiserfs_journal_header *jh; struct reiserfs_journal *journal = SB_JOURNAL(sb); + int depth; if (reiserfs_is_journal_aborted(journal)) return -EIO; if (trans_id >= journal->j_last_flush_trans_id) { if (buffer_locked((journal->j_header_bh))) { - reiserfs_write_unlock(sb); - wait_on_buffer((journal->j_header_bh)); - reiserfs_write_lock(sb); + depth = reiserfs_write_unlock_nested(sb); + __wait_on_buffer(journal->j_header_bh); + reiserfs_write_lock_nested(sb, depth); if (unlikely(!buffer_uptodate(journal->j_header_bh))) { #ifdef CONFIG_REISERFS_CHECK reiserfs_warning(sb, "journal-699", @@ -1254,14 +1258,14 @@ static int _update_journal_header_block(struct super_block *sb, jh->j_mount_id = cpu_to_le32(journal->j_mount_id); set_buffer_dirty(journal->j_header_bh); - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(sb); if (reiserfs_barrier_flush(sb)) __sync_dirty_buffer(journal->j_header_bh, WRITE_FLUSH_FUA); else sync_dirty_buffer(journal->j_header_bh); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(sb, depth); if (!buffer_uptodate(journal->j_header_bh)) { reiserfs_warning(sb, "journal-837", "IO error during journal replay"); @@ -1341,6 +1345,7 @@ static int flush_journal_list(struct super_block *s, unsigned long j_len_saved = jl->j_len; struct reiserfs_journal *journal = SB_JOURNAL(s); int err = 0; + int depth; BUG_ON(j_len_saved <= 0); @@ -1495,9 +1500,9 @@ static int flush_journal_list(struct super_block *s, "cn->bh is NULL"); } - reiserfs_write_unlock(s); - wait_on_buffer(cn->bh); - reiserfs_write_lock(s); + depth = reiserfs_write_unlock_nested(s); + __wait_on_buffer(cn->bh); + reiserfs_write_lock_nested(s, depth); if (!cn->bh) { reiserfs_panic(s, "journal-1012", @@ -1974,6 +1979,7 @@ static int journal_compare_desc_commit(struct super_block *sb, /* returns 0 if it did not find a description block ** returns -1 if it found a corrupt commit block ** returns 1 if both desc and commit were valid +** NOTE: only called during fs mount */ static int journal_transaction_is_valid(struct super_block *sb, struct buffer_head *d_bh, @@ -2073,8 +2079,9 @@ static void brelse_array(struct buffer_head **heads, int num) /* ** given the start, and values for the oldest acceptable transactions, -** this either reads in a replays a transaction, or returns because the transaction -** is invalid, or too old. +** this either reads in a replays a transaction, or returns because the +** transaction is invalid, or too old. +** NOTE: only called during fs mount */ static int journal_read_transaction(struct super_block *sb, unsigned long cur_dblock, @@ -2208,10 +2215,7 @@ static int journal_read_transaction(struct super_block *sb, ll_rw_block(READ, get_desc_trans_len(desc), log_blocks); for (i = 0; i < get_desc_trans_len(desc); i++) { - reiserfs_write_unlock(sb); wait_on_buffer(log_blocks[i]); - reiserfs_write_lock(sb); - if (!buffer_uptodate(log_blocks[i])) { reiserfs_warning(sb, "journal-1212", "REPLAY FAILURE fsck required! " @@ -2318,12 +2322,13 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, /* ** read and replay the log -** on a clean unmount, the journal header's next unflushed pointer will be to an invalid -** transaction. This tests that before finding all the transactions in the log, which makes normal mount times fast. -** -** After a crash, this starts with the next unflushed transaction, and replays until it finds one too old, or invalid. -** +** on a clean unmount, the journal header's next unflushed pointer will +** be to an invalid transaction. This tests that before finding all the +** transactions in the log, which makes normal mount times fast. +** After a crash, this starts with the next unflushed transaction, and +** replays until it finds one too old, or invalid. ** On exit, it sets things up so the first transaction will work correctly. +** NOTE: only called during fs mount */ static int journal_read(struct super_block *sb) { @@ -2501,14 +2506,18 @@ static int journal_read(struct super_block *sb) "replayed %d transactions in %lu seconds\n", replay_count, get_seconds() - start); } + /* needed to satisfy the locking in _update_journal_header_block */ + reiserfs_write_lock(sb); if (!bdev_read_only(sb->s_bdev) && _update_journal_header_block(sb, journal->j_start, journal->j_last_flush_trans_id)) { + reiserfs_write_unlock(sb); /* replay failed, caller must call free_journal_ram and abort ** the mount */ return -1; } + reiserfs_write_unlock(sb); return 0; } @@ -2828,13 +2837,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name, goto free_and_return; } - /* - * Journal_read needs to be inspected in order to push down - * the lock further inside (or even remove it). - */ - reiserfs_write_lock(sb); ret = journal_read(sb); - reiserfs_write_unlock(sb); if (ret < 0) { reiserfs_warning(sb, "reiserfs-2006", "Replay Failure, unable to mount"); @@ -2923,9 +2926,9 @@ static void queue_log_writer(struct super_block *s) add_wait_queue(&journal->j_join_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); if (test_bit(J_WRITERS_QUEUED, &journal->j_state)) { - reiserfs_write_unlock(s); + int depth = reiserfs_write_unlock_nested(s); schedule(); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } __set_current_state(TASK_RUNNING); remove_wait_queue(&journal->j_join_wait, &wait); @@ -2943,9 +2946,12 @@ static void let_transaction_grow(struct super_block *sb, unsigned int trans_id) struct reiserfs_journal *journal = SB_JOURNAL(sb); unsigned long bcount = journal->j_bcount; while (1) { - reiserfs_write_unlock(sb); + int depth; + + depth = reiserfs_write_unlock_nested(sb); schedule_timeout_uninterruptible(1); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(sb, depth); + journal->j_current_jl->j_state |= LIST_COMMIT_PENDING; while ((atomic_read(&journal->j_wcount) > 0 || atomic_read(&journal->j_jlock)) && @@ -2976,6 +2982,7 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th, struct reiserfs_transaction_handle myth; int sched_count = 0; int retval; + int depth; reiserfs_check_lock_depth(sb, "journal_begin"); BUG_ON(nblocks > journal->j_trans_max); @@ -2996,9 +3003,9 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th, if (test_bit(J_WRITERS_BLOCKED, &journal->j_state)) { unlock_journal(sb); - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(sb); reiserfs_wait_on_write_block(sb); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(sb, depth); PROC_INFO_INC(sb, journal.journal_relock_writers); goto relock; } @@ -3821,6 +3828,7 @@ void reiserfs_restore_prepared_buffer(struct super_block *sb, if (test_clear_buffer_journal_restore_dirty(bh) && buffer_journal_dirty(bh)) { struct reiserfs_journal_cnode *cn; + reiserfs_write_lock(sb); cn = get_journal_hash_dev(sb, journal->j_list_hash_table, bh->b_blocknr); @@ -3828,6 +3836,7 @@ void reiserfs_restore_prepared_buffer(struct super_block *sb, set_buffer_journal_test(bh); mark_buffer_dirty(bh); } + reiserfs_write_unlock(sb); } clear_buffer_journal_prepared(bh); } @@ -3911,6 +3920,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, unsigned long jindex; unsigned int commit_trans_id; int trans_half; + int depth; BUG_ON(th->t_refcount > 1); BUG_ON(!th->t_trans_id); @@ -4116,9 +4126,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, next = cn->next; free_cnode(sb, cn); cn = next; - reiserfs_write_unlock(sb); - cond_resched(); - reiserfs_write_lock(sb); + reiserfs_cond_resched(sb); } /* we are done with both the c_bh and d_bh, but @@ -4165,10 +4173,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, * is lost. */ if (!list_empty(&jl->j_tail_bh_list)) { - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(sb); write_ordered_buffers(&journal->j_dirty_buffers_lock, journal, jl, &jl->j_tail_bh_list); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(sb, depth); } BUG_ON(!list_empty(&jl->j_tail_bh_list)); mutex_unlock(&jl->j_commit_mutex); diff --git a/fs/reiserfs/lock.c b/fs/reiserfs/lock.c index d735bc8..045b83ef 100644 --- a/fs/reiserfs/lock.c +++ b/fs/reiserfs/lock.c @@ -48,30 +48,35 @@ void reiserfs_write_unlock(struct super_block *s) } } -/* - * If we already own the lock, just exit and don't increase the depth. - * Useful when we don't want to lock more than once. - * - * We always return the lock_depth we had before calling - * this function. - */ -int reiserfs_write_lock_once(struct super_block *s) +int __must_check reiserfs_write_unlock_nested(struct super_block *s) { struct reiserfs_sb_info *sb_i = REISERFS_SB(s); + int depth; - if (sb_i->lock_owner != current) { - mutex_lock(&sb_i->lock); - sb_i->lock_owner = current; - return sb_i->lock_depth++; - } + /* this can happen when the lock isn't always held */ + if (sb_i->lock_owner != current) + return -1; + + depth = sb_i->lock_depth; + + sb_i->lock_depth = -1; + sb_i->lock_owner = NULL; + mutex_unlock(&sb_i->lock); - return sb_i->lock_depth; + return depth; } -void reiserfs_write_unlock_once(struct super_block *s, int lock_depth) +void reiserfs_write_lock_nested(struct super_block *s, int depth) { - if (lock_depth == -1) - reiserfs_write_unlock(s); + struct reiserfs_sb_info *sb_i = REISERFS_SB(s); + + /* this can happen when the lock isn't always held */ + if (depth == -1) + return; + + mutex_lock(&sb_i->lock); + sb_i->lock_owner = current; + sb_i->lock_depth = depth; } /* @@ -82,9 +87,7 @@ void reiserfs_check_lock_depth(struct super_block *sb, char *caller) { struct reiserfs_sb_info *sb_i = REISERFS_SB(sb); - if (sb_i->lock_depth < 0) - reiserfs_panic(sb, "%s called without kernel lock held %d", - caller); + WARN_ON(sb_i->lock_depth < 0); } #ifdef CONFIG_REISERFS_CHECK diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 8567fb8..dc5236f 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -325,7 +325,6 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int retval; - int lock_depth; struct inode *inode = NULL; struct reiserfs_dir_entry de; INITIALIZE_PATH(path_to_entry); @@ -333,12 +332,7 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, if (REISERFS_MAX_NAME(dir->i_sb->s_blocksize) < dentry->d_name.len) return ERR_PTR(-ENAMETOOLONG); - /* - * Might be called with or without the write lock, must be careful - * to not recursively hold it in case we want to release the lock - * before rescheduling. - */ - lock_depth = reiserfs_write_lock_once(dir->i_sb); + reiserfs_write_lock(dir->i_sb); de.de_gen_number_bit_string = NULL; retval = @@ -349,7 +343,7 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, inode = reiserfs_iget(dir->i_sb, (struct cpu_key *)&(de.de_dir_id)); if (!inode || IS_ERR(inode)) { - reiserfs_write_unlock_once(dir->i_sb, lock_depth); + reiserfs_write_unlock(dir->i_sb); return ERR_PTR(-EACCES); } @@ -358,7 +352,7 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, if (IS_PRIVATE(dir)) inode->i_flags |= S_PRIVATE; } - reiserfs_write_unlock_once(dir->i_sb, lock_depth); + reiserfs_write_unlock(dir->i_sb); if (retval == IO_ERROR) { return ERR_PTR(-EIO); } @@ -727,7 +721,6 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode struct inode *inode; struct reiserfs_transaction_handle th; struct reiserfs_security_handle security; - int lock_depth; /* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */ int jbegin_count = JOURNAL_PER_BALANCE_CNT * 3 + @@ -753,7 +746,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode return retval; } jbegin_count += retval; - lock_depth = reiserfs_write_lock_once(dir->i_sb); + reiserfs_write_lock(dir->i_sb); retval = journal_begin(&th, dir->i_sb, jbegin_count); if (retval) { @@ -804,7 +797,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: - reiserfs_write_unlock_once(dir->i_sb, lock_depth); + reiserfs_write_unlock(dir->i_sb); return retval; } @@ -920,7 +913,6 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) struct reiserfs_transaction_handle th; int jbegin_count; unsigned long savelink; - int depth; dquot_initialize(dir); @@ -934,7 +926,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) JOURNAL_PER_BALANCE_CNT * 2 + 2 + 4 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb); - depth = reiserfs_write_lock_once(dir->i_sb); + reiserfs_write_lock(dir->i_sb); retval = journal_begin(&th, dir->i_sb, jbegin_count); if (retval) goto out_unlink; @@ -995,7 +987,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) retval = journal_end(&th, dir->i_sb, jbegin_count); reiserfs_check_path(&path); - reiserfs_write_unlock_once(dir->i_sb, depth); + reiserfs_write_unlock(dir->i_sb); return retval; end_unlink: @@ -1005,7 +997,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) if (err) retval = err; out_unlink: - reiserfs_write_unlock_once(dir->i_sb, depth); + reiserfs_write_unlock(dir->i_sb); return retval; } diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index c0b1112..54944d5 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -358,12 +358,13 @@ void __reiserfs_panic(struct super_block *sb, const char *id, dump_stack(); #endif if (sb) - panic(KERN_WARNING "REISERFS panic (device %s): %s%s%s: %s\n", + printk(KERN_WARNING "REISERFS panic (device %s): %s%s%s: %s\n", sb->s_id, id ? id : "", id ? " " : "", function, error_buf); else - panic(KERN_WARNING "REISERFS panic: %s%s%s: %s\n", + printk(KERN_WARNING "REISERFS panic: %s%s%s: %s\n", id ? id : "", id ? " " : "", function, error_buf); + BUG(); } void __reiserfs_error(struct super_block *sb, const char *id, diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 33532f7..a958444 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -19,12 +19,13 @@ /* * LOCKING: * - * We rely on new Alexander Viro's super-block locking. + * These guys are evicted from procfs as the very first step in ->kill_sb(). * */ -static int show_version(struct seq_file *m, struct super_block *sb) +static int show_version(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; char *format; if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) { @@ -66,8 +67,9 @@ static int show_version(struct seq_file *m, struct super_block *sb) #define DJP( x ) le32_to_cpu( jp -> x ) #define JF( x ) ( r -> s_journal -> x ) -static int show_super(struct seq_file *m, struct super_block *sb) +static int show_super(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; struct reiserfs_sb_info *r = REISERFS_SB(sb); seq_printf(m, "state: \t%s\n" @@ -128,8 +130,9 @@ static int show_super(struct seq_file *m, struct super_block *sb) return 0; } -static int show_per_level(struct seq_file *m, struct super_block *sb) +static int show_per_level(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; struct reiserfs_sb_info *r = REISERFS_SB(sb); int level; @@ -186,8 +189,9 @@ static int show_per_level(struct seq_file *m, struct super_block *sb) return 0; } -static int show_bitmap(struct seq_file *m, struct super_block *sb) +static int show_bitmap(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; struct reiserfs_sb_info *r = REISERFS_SB(sb); seq_printf(m, "free_block: %lu\n" @@ -218,8 +222,9 @@ static int show_bitmap(struct seq_file *m, struct super_block *sb) return 0; } -static int show_on_disk_super(struct seq_file *m, struct super_block *sb) +static int show_on_disk_super(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; struct reiserfs_sb_info *sb_info = REISERFS_SB(sb); struct reiserfs_super_block *rs = sb_info->s_rs; int hash_code = DFL(s_hash_function_code); @@ -261,8 +266,9 @@ static int show_on_disk_super(struct seq_file *m, struct super_block *sb) return 0; } -static int show_oidmap(struct seq_file *m, struct super_block *sb) +static int show_oidmap(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; struct reiserfs_sb_info *sb_info = REISERFS_SB(sb); struct reiserfs_super_block *rs = sb_info->s_rs; unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize); @@ -291,8 +297,9 @@ static int show_oidmap(struct seq_file *m, struct super_block *sb) return 0; } -static int show_journal(struct seq_file *m, struct super_block *sb) +static int show_journal(struct seq_file *m, void *unused) { + struct super_block *sb = m->private; struct reiserfs_sb_info *r = REISERFS_SB(sb); struct reiserfs_super_block *rs = r->s_rs; struct journal_params *jp = &rs->s_v1.s_journal; @@ -383,92 +390,24 @@ static int show_journal(struct seq_file *m, struct super_block *sb) return 0; } -/* iterator */ -static int test_sb(struct super_block *sb, void *data) -{ - return data == sb; -} - -static int set_sb(struct super_block *sb, void *data) -{ - return -ENOENT; -} - -struct reiserfs_seq_private { - struct super_block *sb; - int (*show) (struct seq_file *, struct super_block *); -}; - -static void *r_start(struct seq_file *m, loff_t * pos) -{ - struct reiserfs_seq_private *priv = m->private; - loff_t l = *pos; - - if (l) - return NULL; - - if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, priv->sb))) - return NULL; - - up_write(&priv->sb->s_umount); - return priv->sb; -} - -static void *r_next(struct seq_file *m, void *v, loff_t * pos) -{ - ++*pos; - if (v) - deactivate_super(v); - return NULL; -} - -static void r_stop(struct seq_file *m, void *v) -{ - if (v) - deactivate_super(v); -} - -static int r_show(struct seq_file *m, void *v) -{ - struct reiserfs_seq_private *priv = m->private; - return priv->show(m, v); -} - -static const struct seq_operations r_ops = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = r_show, -}; - static int r_open(struct inode *inode, struct file *file) { - struct reiserfs_seq_private *priv; - int ret = seq_open_private(file, &r_ops, - sizeof(struct reiserfs_seq_private)); - - if (!ret) { - struct seq_file *m = file->private_data; - priv = m->private; - priv->sb = proc_get_parent_data(inode); - priv->show = PDE_DATA(inode); - } - return ret; + return single_open(file, PDE_DATA(inode), + proc_get_parent_data(inode)); } static const struct file_operations r_file_operations = { .open = r_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, - .owner = THIS_MODULE, + .release = single_release, }; static struct proc_dir_entry *proc_info_root = NULL; static const char proc_info_root_name[] = "fs/reiserfs"; static void add_file(struct super_block *sb, char *name, - int (*func) (struct seq_file *, struct super_block *)) + int (*func) (struct seq_file *, void *)) { proc_create_data(name, 0, REISERFS_SB(sb)->procdir, &r_file_operations, func); diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 3df5ce6..f8adaee 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -630,8 +630,8 @@ static inline int __reiserfs_is_journal_aborted(struct reiserfs_journal */ void reiserfs_write_lock(struct super_block *s); void reiserfs_write_unlock(struct super_block *s); -int reiserfs_write_lock_once(struct super_block *s); -void reiserfs_write_unlock_once(struct super_block *s, int lock_depth); +int __must_check reiserfs_write_unlock_nested(struct super_block *s); +void reiserfs_write_lock_nested(struct super_block *s, int depth); #ifdef CONFIG_REISERFS_CHECK void reiserfs_lock_check_recursive(struct super_block *s); @@ -667,31 +667,33 @@ static inline void reiserfs_lock_check_recursive(struct super_block *s) { } * - The inode mutex */ static inline void reiserfs_mutex_lock_safe(struct mutex *m, - struct super_block *s) + struct super_block *s) { - reiserfs_lock_check_recursive(s); - reiserfs_write_unlock(s); + int depth; + + depth = reiserfs_write_unlock_nested(s); mutex_lock(m); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } static inline void reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass, - struct super_block *s) + struct super_block *s) { - reiserfs_lock_check_recursive(s); - reiserfs_write_unlock(s); + int depth; + + depth = reiserfs_write_unlock_nested(s); mutex_lock_nested(m, subclass); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } static inline void reiserfs_down_read_safe(struct rw_semaphore *sem, struct super_block *s) { - reiserfs_lock_check_recursive(s); - reiserfs_write_unlock(s); - down_read(sem); - reiserfs_write_lock(s); + int depth; + depth = reiserfs_write_unlock_nested(s); + down_read(sem); + reiserfs_write_lock_nested(s, depth); } /* @@ -701,9 +703,11 @@ reiserfs_down_read_safe(struct rw_semaphore *sem, struct super_block *s) static inline void reiserfs_cond_resched(struct super_block *s) { if (need_resched()) { - reiserfs_write_unlock(s); + int depth; + + depth = reiserfs_write_unlock_nested(s); schedule(); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); } } diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c index 3ce02cf..a4ef5cd 100644 --- a/fs/reiserfs/resize.c +++ b/fs/reiserfs/resize.c @@ -34,6 +34,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) unsigned long int block_count, free_blocks; int i; int copy_size; + int depth; sb = SB_DISK_SUPER_BLOCK(s); @@ -43,7 +44,9 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) } /* check the device size */ + depth = reiserfs_write_unlock_nested(s); bh = sb_bread(s, block_count_new - 1); + reiserfs_write_lock_nested(s, depth); if (!bh) { printk("reiserfs_resize: can\'t read last block\n"); return -EINVAL; @@ -125,9 +128,12 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) * transaction begins, and the new bitmaps don't matter if the * transaction fails. */ for (i = bmap_nr; i < bmap_nr_new; i++) { + int depth; /* don't use read_bitmap_block since it will cache * the uninitialized bitmap */ + depth = reiserfs_write_unlock_nested(s); bh = sb_bread(s, i * s->s_blocksize * 8); + reiserfs_write_lock_nested(s, depth); if (!bh) { vfree(bitmap); return -EIO; @@ -138,9 +144,9 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) set_buffer_uptodate(bh); mark_buffer_dirty(bh); - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(s); sync_dirty_buffer(bh); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(s, depth); // update bitmap_info stuff bitmap[i].free_count = sb_blocksize(sb) * 8 - 1; brelse(bh); diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 2f40a4c..b14706a 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -524,14 +524,14 @@ static int is_tree_node(struct buffer_head *bh, int level) * the caller (search_by_key) will perform other schedule-unsafe * operations just after calling this function. * - * @return true if we have unlocked + * @return depth of lock to be restored after read completes */ -static bool search_by_key_reada(struct super_block *s, +static int search_by_key_reada(struct super_block *s, struct buffer_head **bh, b_blocknr_t *b, int num) { int i, j; - bool unlocked = false; + int depth = -1; for (i = 0; i < num; i++) { bh[i] = sb_getblk(s, b[i]); @@ -549,15 +549,13 @@ static bool search_by_key_reada(struct super_block *s, * you have to make sure the prepared bit isn't set on this buffer */ if (!buffer_uptodate(bh[j])) { - if (!unlocked) { - reiserfs_write_unlock(s); - unlocked = true; - } + if (depth == -1) + depth = reiserfs_write_unlock_nested(s); ll_rw_block(READA, 1, bh + j); } brelse(bh[j]); } - return unlocked; + return depth; } /************************************************************************** @@ -645,26 +643,26 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key, /* Key to s have a pointer to it. */ if ((bh = last_element->pe_buffer = sb_getblk(sb, block_number))) { - bool unlocked = false; - if (!buffer_uptodate(bh) && reada_count > 1) - /* may unlock the write lock */ - unlocked = search_by_key_reada(sb, reada_bh, - reada_blocks, reada_count); /* - * If we haven't already unlocked the write lock, - * then we need to do that here before reading - * the current block + * We'll need to drop the lock if we encounter any + * buffers that need to be read. If all of them are + * already up to date, we don't need to drop the lock. */ - if (!buffer_uptodate(bh) && !unlocked) { - reiserfs_write_unlock(sb); - unlocked = true; - } + int depth = -1; + + if (!buffer_uptodate(bh) && reada_count > 1) + depth = search_by_key_reada(sb, reada_bh, + reada_blocks, reada_count); + + if (!buffer_uptodate(bh) && depth == -1) + depth = reiserfs_write_unlock_nested(sb); + ll_rw_block(READ, 1, &bh); wait_on_buffer(bh); - if (unlocked) - reiserfs_write_lock(sb); + if (depth != -1) + reiserfs_write_lock_nested(sb, depth); if (!buffer_uptodate(bh)) goto io_error; } else { @@ -1059,9 +1057,7 @@ static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, st reiserfs_free_block(th, inode, block, 1); } - reiserfs_write_unlock(sb); - cond_resched(); - reiserfs_write_lock(sb); + reiserfs_cond_resched(sb); if (item_moved (&s_ih, path)) { need_re_search = 1; @@ -1190,6 +1186,7 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th, struct item_head *q_ih; int quota_cut_bytes; int ret_value, del_size, removed; + int depth; #ifdef CONFIG_REISERFS_CHECK char mode; @@ -1299,7 +1296,9 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th, "reiserquota delete_item(): freeing %u, id=%u type=%c", quota_cut_bytes, inode->i_uid, head2type(&s_ih)); #endif + depth = reiserfs_write_unlock_nested(inode->i_sb); dquot_free_space_nodirty(inode, quota_cut_bytes); + reiserfs_write_lock_nested(inode->i_sb, depth); /* Return deleted body length */ return ret_value; @@ -1325,6 +1324,7 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th, void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_key *key) { + struct super_block *sb = th->t_super; struct tree_balance tb; INITIALIZE_PATH(path); int item_len = 0; @@ -1377,14 +1377,17 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th, if (retval == CARRY_ON) { do_balance(&tb, NULL, NULL, M_DELETE); if (inode) { /* Should we count quota for item? (we don't count quotas for save-links) */ + int depth; #ifdef REISERQUOTA_DEBUG reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE, "reiserquota delete_solid_item(): freeing %u id=%u type=%c", quota_cut_bytes, inode->i_uid, key2type(key)); #endif + depth = reiserfs_write_unlock_nested(sb); dquot_free_space_nodirty(inode, quota_cut_bytes); + reiserfs_write_lock_nested(sb, depth); } break; } @@ -1561,6 +1564,7 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th, int retval2 = -1; int quota_cut_bytes; loff_t tail_pos = 0; + int depth; BUG_ON(!th->t_trans_id); @@ -1733,7 +1737,9 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th, "reiserquota cut_from_item(): freeing %u id=%u type=%c", quota_cut_bytes, inode->i_uid, '?'); #endif + depth = reiserfs_write_unlock_nested(sb); dquot_free_space_nodirty(inode, quota_cut_bytes); + reiserfs_write_lock_nested(sb, depth); return ret_value; } @@ -1953,9 +1959,11 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree const char *body, /* Pointer to the bytes to paste. */ int pasted_size) { /* Size of pasted bytes. */ + struct super_block *sb = inode->i_sb; struct tree_balance s_paste_balance; int retval; int fs_gen; + int depth; BUG_ON(!th->t_trans_id); @@ -1968,9 +1976,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree key2type(&(key->on_disk_key))); #endif - reiserfs_write_unlock(inode->i_sb); + depth = reiserfs_write_unlock_nested(sb); retval = dquot_alloc_space_nodirty(inode, pasted_size); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(sb, depth); if (retval) { pathrelse(search_path); return retval; @@ -2027,7 +2035,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree pasted_size, inode->i_uid, key2type(&(key->on_disk_key))); #endif + depth = reiserfs_write_unlock_nested(sb); dquot_free_space_nodirty(inode, pasted_size); + reiserfs_write_lock_nested(sb, depth); return retval; } @@ -2050,6 +2060,7 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th, BUG_ON(!th->t_trans_id); if (inode) { /* Do we count quotas for item? */ + int depth; fs_gen = get_generation(inode->i_sb); quota_bytes = ih_item_len(ih); @@ -2063,11 +2074,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th, "reiserquota insert_item(): allocating %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif - reiserfs_write_unlock(inode->i_sb); /* We can't dirty inode here. It would be immediately written but * appropriate stat item isn't inserted yet... */ + depth = reiserfs_write_unlock_nested(inode->i_sb); retval = dquot_alloc_space_nodirty(inode, quota_bytes); - reiserfs_write_lock(inode->i_sb); + reiserfs_write_lock_nested(inode->i_sb, depth); if (retval) { pathrelse(path); return retval; @@ -2118,7 +2129,10 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th, "reiserquota insert_item(): freeing %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif - if (inode) + if (inode) { + int depth = reiserfs_write_unlock_nested(inode->i_sb); dquot_free_space_nodirty(inode, quota_bytes); + reiserfs_write_lock_nested(inode->i_sb, depth); + } return retval; } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index f8a23c3..3ead145 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -243,6 +243,7 @@ static int finish_unfinished(struct super_block *s) done = 0; REISERFS_SB(s)->s_is_unlinked_ok = 1; while (!retval) { + int depth; retval = search_item(s, &max_cpu_key, &path); if (retval != ITEM_NOT_FOUND) { reiserfs_error(s, "vs-2140", @@ -298,9 +299,9 @@ static int finish_unfinished(struct super_block *s) retval = remove_save_link_only(s, &save_link_key, 0); continue; } - reiserfs_write_unlock(s); + depth = reiserfs_write_unlock_nested(inode->i_sb); dquot_initialize(inode); - reiserfs_write_lock(s); + reiserfs_write_lock_nested(inode->i_sb, depth); if (truncate && S_ISDIR(inode->i_mode)) { /* We got a truncate request for a dir which is impossible. @@ -356,10 +357,12 @@ static int finish_unfinished(struct super_block *s) #ifdef CONFIG_QUOTA /* Turn quotas off */ + reiserfs_write_unlock(s); for (i = 0; i < MAXQUOTAS; i++) { if (sb_dqopt(s)->files[i] && quota_enabled[i]) dquot_quota_off(s, i); } + reiserfs_write_lock(s); if (ms_active_set) /* Restore the flag back */ s->s_flags &= ~MS_ACTIVE; @@ -499,6 +502,7 @@ int remove_save_link(struct inode *inode, int truncate) static void reiserfs_kill_sb(struct super_block *s) { if (REISERFS_SB(s)) { + reiserfs_proc_info_done(s); /* * Force any pending inode evictions to occur now. Any * inodes to be removed that have extended attributes @@ -554,8 +558,6 @@ static void reiserfs_put_super(struct super_block *s) REISERFS_SB(s)->reserved_blocks); } - reiserfs_proc_info_done(s); - reiserfs_write_unlock(s); mutex_destroy(&REISERFS_SB(s)->lock); kfree(s->s_fs_info); @@ -624,7 +626,6 @@ static void reiserfs_dirty_inode(struct inode *inode, int flags) struct reiserfs_transaction_handle th; int err = 0; - int lock_depth; if (inode->i_sb->s_flags & MS_RDONLY) { reiserfs_warning(inode->i_sb, "clm-6006", @@ -632,7 +633,7 @@ static void reiserfs_dirty_inode(struct inode *inode, int flags) inode->i_ino); return; } - lock_depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); /* this is really only used for atime updates, so they don't have ** to be included in O_SYNC or fsync @@ -645,7 +646,7 @@ static void reiserfs_dirty_inode(struct inode *inode, int flags) journal_end(&th, inode->i_sb, 1); out: - reiserfs_write_unlock_once(inode->i_sb, lock_depth); + reiserfs_write_unlock(inode->i_sb); } static int reiserfs_show_options(struct seq_file *seq, struct dentry *root) @@ -1335,7 +1336,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) kfree(qf_names[i]); #endif err = -EINVAL; - goto out_unlock; + goto out_err_unlock; } #ifdef CONFIG_QUOTA handle_quota_files(s, qf_names, &qfmt); @@ -1379,35 +1380,32 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (blocks) { err = reiserfs_resize(s, blocks); if (err != 0) - goto out_unlock; + goto out_err_unlock; } if (*mount_flags & MS_RDONLY) { + reiserfs_write_unlock(s); reiserfs_xattr_init(s, *mount_flags); /* remount read-only */ if (s->s_flags & MS_RDONLY) /* it is read-only already */ - goto out_ok; + goto out_ok_unlocked; - /* - * Drop write lock. Quota will retake it when needed and lock - * ordering requires calling dquot_suspend() without it. - */ - reiserfs_write_unlock(s); err = dquot_suspend(s, -1); if (err < 0) goto out_err; - reiserfs_write_lock(s); /* try to remount file system with read-only permissions */ if (sb_umount_state(rs) == REISERFS_VALID_FS || REISERFS_SB(s)->s_mount_state != REISERFS_VALID_FS) { - goto out_ok; + goto out_ok_unlocked; } + reiserfs_write_lock(s); + err = journal_begin(&th, s, 10); if (err) - goto out_unlock; + goto out_err_unlock; /* Mounting a rw partition read-only. */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1416,13 +1414,14 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) } else { /* remount read-write */ if (!(s->s_flags & MS_RDONLY)) { + reiserfs_write_unlock(s); reiserfs_xattr_init(s, *mount_flags); - goto out_ok; /* We are read-write already */ + goto out_ok_unlocked; /* We are read-write already */ } if (reiserfs_is_journal_aborted(journal)) { err = journal->j_errno; - goto out_unlock; + goto out_err_unlock; } handle_data_mode(s, mount_options); @@ -1431,7 +1430,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) s->s_flags &= ~MS_RDONLY; /* now it is safe to call journal_begin */ err = journal_begin(&th, s, 10); if (err) - goto out_unlock; + goto out_err_unlock; /* Mount a partition which is read-only, read-write */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1448,26 +1447,22 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) SB_JOURNAL(s)->j_must_wait = 1; err = journal_end(&th, s, 10); if (err) - goto out_unlock; + goto out_err_unlock; + reiserfs_write_unlock(s); if (!(*mount_flags & MS_RDONLY)) { - /* - * Drop write lock. Quota will retake it when needed and lock - * ordering requires calling dquot_resume() without it. - */ - reiserfs_write_unlock(s); dquot_resume(s, -1); reiserfs_write_lock(s); finish_unfinished(s); + reiserfs_write_unlock(s); reiserfs_xattr_init(s, *mount_flags); } -out_ok: +out_ok_unlocked: replace_mount_options(s, new_opts); - reiserfs_write_unlock(s); return 0; -out_unlock: +out_err_unlock: reiserfs_write_unlock(s); out_err: kfree(new_opts); @@ -2014,12 +2009,14 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) goto error; } + reiserfs_write_unlock(s); if ((errval = reiserfs_lookup_privroot(s)) || (errval = reiserfs_xattr_init(s, s->s_flags))) { dput(s->s_root); s->s_root = NULL; - goto error; + goto error_unlocked; } + reiserfs_write_lock(s); /* look for files which were to be removed in previous session */ finish_unfinished(s); @@ -2028,12 +2025,14 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) reiserfs_info(s, "using 3.5.x disk format\n"); } + reiserfs_write_unlock(s); if ((errval = reiserfs_lookup_privroot(s)) || (errval = reiserfs_xattr_init(s, s->s_flags))) { dput(s->s_root); s->s_root = NULL; - goto error; + goto error_unlocked; } + reiserfs_write_lock(s); } // mark hash in super block: it could be unset. overwrite should be ok set_sb_hash_function_code(rs, function2code(sbi->s_hash_function)); @@ -2101,6 +2100,7 @@ static int reiserfs_write_dquot(struct dquot *dquot) { struct reiserfs_transaction_handle th; int ret, err; + int depth; reiserfs_write_lock(dquot->dq_sb); ret = @@ -2108,9 +2108,9 @@ static int reiserfs_write_dquot(struct dquot *dquot) REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (ret) goto out; - reiserfs_write_unlock(dquot->dq_sb); + depth = reiserfs_write_unlock_nested(dquot->dq_sb); ret = dquot_commit(dquot); - reiserfs_write_lock(dquot->dq_sb); + reiserfs_write_lock_nested(dquot->dq_sb, depth); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); @@ -2125,6 +2125,7 @@ static int reiserfs_acquire_dquot(struct dquot *dquot) { struct reiserfs_transaction_handle th; int ret, err; + int depth; reiserfs_write_lock(dquot->dq_sb); ret = @@ -2132,9 +2133,9 @@ static int reiserfs_acquire_dquot(struct dquot *dquot) REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (ret) goto out; - reiserfs_write_unlock(dquot->dq_sb); + depth = reiserfs_write_unlock_nested(dquot->dq_sb); ret = dquot_acquire(dquot); - reiserfs_write_lock(dquot->dq_sb); + reiserfs_write_lock_nested(dquot->dq_sb, depth); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); @@ -2187,15 +2188,16 @@ static int reiserfs_write_info(struct super_block *sb, int type) { struct reiserfs_transaction_handle th; int ret, err; + int depth; /* Data block + inode block */ reiserfs_write_lock(sb); ret = journal_begin(&th, sb, 2); if (ret) goto out; - reiserfs_write_unlock(sb); + depth = reiserfs_write_unlock_nested(sb); ret = dquot_commit_info(sb, type); - reiserfs_write_lock(sb); + reiserfs_write_lock_nested(sb, depth); err = journal_end(&th, sb, 2); if (!ret && err) ret = err; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index c69cdd7..8a9e2dc 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -81,8 +81,7 @@ static int xattr_unlink(struct inode *dir, struct dentry *dentry) int error; BUG_ON(!mutex_is_locked(&dir->i_mutex)); - reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex, - I_MUTEX_CHILD, dir->i_sb); + mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD); error = dir->i_op->unlink(dir, dentry); mutex_unlock(&dentry->d_inode->i_mutex); @@ -96,8 +95,7 @@ static int xattr_rmdir(struct inode *dir, struct dentry *dentry) int error; BUG_ON(!mutex_is_locked(&dir->i_mutex)); - reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex, - I_MUTEX_CHILD, dir->i_sb); + mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD); error = dir->i_op->rmdir(dir, dentry); if (!error) dentry->d_inode->i_flags |= S_DEAD; @@ -232,22 +230,17 @@ static int reiserfs_for_each_xattr(struct inode *inode, if (IS_PRIVATE(inode) || get_inode_sd_version(inode) == STAT_DATA_V1) return 0; - reiserfs_write_unlock(inode->i_sb); dir = open_xa_dir(inode, XATTR_REPLACE); if (IS_ERR(dir)) { err = PTR_ERR(dir); - reiserfs_write_lock(inode->i_sb); goto out; } else if (!dir->d_inode) { err = 0; - reiserfs_write_lock(inode->i_sb); goto out_dir; } mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_XATTR); - reiserfs_write_lock(inode->i_sb); - buf.xadir = dir; while (1) { err = reiserfs_readdir_inode(dir->d_inode, &buf.ctx); @@ -281,14 +274,17 @@ static int reiserfs_for_each_xattr(struct inode *inode, int blocks = JOURNAL_PER_BALANCE_CNT * 2 + 2 + 4 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb); struct reiserfs_transaction_handle th; + reiserfs_write_lock(inode->i_sb); err = journal_begin(&th, inode->i_sb, blocks); + reiserfs_write_unlock(inode->i_sb); if (!err) { int jerror; - reiserfs_mutex_lock_nested_safe( - &dir->d_parent->d_inode->i_mutex, - I_MUTEX_XATTR, inode->i_sb); + mutex_lock_nested(&dir->d_parent->d_inode->i_mutex, + I_MUTEX_XATTR); err = action(dir, data); + reiserfs_write_lock(inode->i_sb); jerror = journal_end(&th, inode->i_sb, blocks); + reiserfs_write_unlock(inode->i_sb); mutex_unlock(&dir->d_parent->d_inode->i_mutex); err = jerror ?: err; } @@ -455,9 +451,7 @@ static int lookup_and_delete_xattr(struct inode *inode, const char *name) } if (dentry->d_inode) { - reiserfs_write_lock(inode->i_sb); err = xattr_unlink(xadir->d_inode, dentry); - reiserfs_write_unlock(inode->i_sb); update_ctime(inode); } @@ -491,24 +485,17 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, if (get_inode_sd_version(inode) == STAT_DATA_V1) return -EOPNOTSUPP; - reiserfs_write_unlock(inode->i_sb); - if (!buffer) { err = lookup_and_delete_xattr(inode, name); - reiserfs_write_lock(inode->i_sb); return err; } dentry = xattr_lookup(inode, name, flags); - if (IS_ERR(dentry)) { - reiserfs_write_lock(inode->i_sb); + if (IS_ERR(dentry)) return PTR_ERR(dentry); - } down_write(&REISERFS_I(inode)->i_xattr_sem); - reiserfs_write_lock(inode->i_sb); - xahash = xattr_hash(buffer, buffer_size); while (buffer_pos < buffer_size || buffer_pos == 0) { size_t chunk; @@ -538,6 +525,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, rxh->h_hash = cpu_to_le32(xahash); } + reiserfs_write_lock(inode->i_sb); err = __reiserfs_write_begin(page, page_offset, chunk + skip); if (!err) { if (buffer) @@ -546,6 +534,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, page_offset + chunk + skip); } + reiserfs_write_unlock(inode->i_sb); unlock_page(page); reiserfs_put_page(page); buffer_pos += chunk; @@ -563,10 +552,8 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, .ia_valid = ATTR_SIZE | ATTR_CTIME, }; - reiserfs_write_unlock(inode->i_sb); mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR); inode_dio_wait(dentry->d_inode); - reiserfs_write_lock(inode->i_sb); err = reiserfs_setattr(dentry, &newattrs); mutex_unlock(&dentry->d_inode->i_mutex); @@ -592,18 +579,19 @@ int reiserfs_xattr_set(struct inode *inode, const char *name, reiserfs_write_lock(inode->i_sb); error = journal_begin(&th, inode->i_sb, jbegin_count); + reiserfs_write_unlock(inode->i_sb); if (error) { - reiserfs_write_unlock(inode->i_sb); return error; } error = reiserfs_xattr_set_handle(&th, inode, name, buffer, buffer_size, flags); + reiserfs_write_lock(inode->i_sb); error2 = journal_end(&th, inode->i_sb, jbegin_count); + reiserfs_write_unlock(inode->i_sb); if (error == 0) error = error2; - reiserfs_write_unlock(inode->i_sb); return error; } @@ -968,7 +956,7 @@ int reiserfs_lookup_privroot(struct super_block *s) int err = 0; /* If we don't have the privroot located yet - go find it */ - reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s); + mutex_lock(&s->s_root->d_inode->i_mutex); dentry = lookup_one_len(PRIVROOT_NAME, s->s_root, strlen(PRIVROOT_NAME)); if (!IS_ERR(dentry)) { @@ -996,14 +984,14 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags) goto error; if (!privroot->d_inode && !(mount_flags & MS_RDONLY)) { - reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s); + mutex_lock(&s->s_root->d_inode->i_mutex); err = create_privroot(REISERFS_SB(s)->priv_root); mutex_unlock(&s->s_root->d_inode->i_mutex); } if (privroot->d_inode) { s->s_xattr = reiserfs_xattr_handlers; - reiserfs_mutex_lock_safe(&privroot->d_inode->i_mutex, s); + mutex_lock(&privroot->d_inode->i_mutex); if (!REISERFS_SB(s)->xattr_root) { struct dentry *dentry; dentry = lookup_one_len(XAROOT_NAME, privroot, diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 6c8767f..06c04f7 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -49,13 +49,15 @@ posix_acl_set(struct dentry *dentry, const char *name, const void *value, reiserfs_write_lock(inode->i_sb); error = journal_begin(&th, inode->i_sb, jcreate_blocks); + reiserfs_write_unlock(inode->i_sb); if (error == 0) { error = reiserfs_set_acl(&th, inode, type, acl); + reiserfs_write_lock(inode->i_sb); error2 = journal_end(&th, inode->i_sb, jcreate_blocks); + reiserfs_write_unlock(inode->i_sb); if (error2) error = error2; } - reiserfs_write_unlock(inode->i_sb); release_and_out: posix_acl_release(acl); @@ -435,12 +437,14 @@ int reiserfs_cache_default_acl(struct inode *inode) return nblocks; } +/* + * Called under i_mutex + */ int reiserfs_acl_chmod(struct inode *inode) { struct reiserfs_transaction_handle th; struct posix_acl *acl; size_t size; - int depth; int error; if (IS_PRIVATE(inode)) @@ -454,9 +458,7 @@ int reiserfs_acl_chmod(struct inode *inode) return 0; } - reiserfs_write_unlock(inode->i_sb); acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS); - reiserfs_write_lock(inode->i_sb); if (!acl) return 0; if (IS_ERR(acl)) @@ -466,16 +468,18 @@ int reiserfs_acl_chmod(struct inode *inode) return error; size = reiserfs_xattr_nblocks(inode, reiserfs_acl_size(acl->a_count)); - depth = reiserfs_write_lock_once(inode->i_sb); + reiserfs_write_lock(inode->i_sb); error = journal_begin(&th, inode->i_sb, size * 2); + reiserfs_write_unlock(inode->i_sb); if (!error) { int error2; error = reiserfs_set_acl(&th, inode, ACL_TYPE_ACCESS, acl); + reiserfs_write_lock(inode->i_sb); error2 = journal_end(&th, inode->i_sb, size * 2); + reiserfs_write_unlock(inode->i_sb); if (error2) error = error2; } - reiserfs_write_unlock_once(inode->i_sb, depth); posix_acl_release(acl); return error; } diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index fb50652..41d108e 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -167,17 +167,14 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, /* * Block is uncompressed. */ - int i, in, pg_offset = 0; - - for (i = 0; i < b; i++) { - wait_on_buffer(bh[i]); - if (!buffer_uptodate(bh[i])) - goto block_release; - } + int in, pg_offset = 0; for (bytes = length; k < b; k++) { in = min(bytes, msblk->devblksize - offset); bytes -= in; + wait_on_buffer(bh[k]); + if (!buffer_uptodate(bh[k])) + goto block_release; while (in) { if (pg_offset == PAGE_CACHE_SIZE) { page++; diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c index f7f527b..d8c2d74 100644 --- a/fs/squashfs/dir.c +++ b/fs/squashfs/dir.c @@ -54,6 +54,7 @@ static int get_dir_index_using_offset(struct super_block *sb, { struct squashfs_sb_info *msblk = sb->s_fs_info; int err, i, index, length = 0; + unsigned int size; struct squashfs_dir_index dir_index; TRACE("Entered get_dir_index_using_offset, i_count %d, f_pos %lld\n", @@ -81,8 +82,14 @@ static int get_dir_index_using_offset(struct super_block *sb, */ break; + size = le32_to_cpu(dir_index.size) + 1; + + /* size should never be larger than SQUASHFS_NAME_LEN */ + if (size > SQUASHFS_NAME_LEN) + break; + err = squashfs_read_metadata(sb, NULL, &index_start, - &index_offset, le32_to_cpu(dir_index.size) + 1); + &index_offset, size); if (err < 0) break; @@ -105,9 +112,8 @@ static int squashfs_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; u64 block = squashfs_i(inode)->start + msblk->directory_table; - int offset = squashfs_i(inode)->offset, length, dir_count, size, - type, err; - unsigned int inode_number; + int offset = squashfs_i(inode)->offset, length, err; + unsigned int inode_number, dir_count, size, type; struct squashfs_dir_header dirh; struct squashfs_dir_entry *dire; @@ -200,6 +206,9 @@ static int squashfs_readdir(struct file *file, struct dir_context *ctx) ((short) le16_to_cpu(dire->inode_number)); type = le16_to_cpu(dire->type); + if (type > SQUASHFS_MAX_DIR_TYPE) + goto failed_read; + if (!dir_emit(ctx, dire->name, size, inode_number, squashfs_filetype_table[type])) diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c index 7834a51..67cad77 100644 --- a/fs/squashfs/namei.c +++ b/fs/squashfs/namei.c @@ -79,7 +79,8 @@ static int get_dir_index_using_name(struct super_block *sb, int len) { struct squashfs_sb_info *msblk = sb->s_fs_info; - int i, size, length = 0, err; + int i, length = 0, err; + unsigned int size; struct squashfs_dir_index *index; char *str; @@ -103,6 +104,8 @@ static int get_dir_index_using_name(struct super_block *sb, size = le32_to_cpu(index->size) + 1; + if (size > SQUASHFS_NAME_LEN) + break; err = squashfs_read_metadata(sb, index->name, &index_start, &index_offset, size); @@ -144,7 +147,8 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry, struct squashfs_dir_entry *dire; u64 block = squashfs_i(dir)->start + msblk->directory_table; int offset = squashfs_i(dir)->offset; - int err, length, dir_count, size; + int err, length; + unsigned int dir_count, size; TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 9e2349d..4b2beda 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -87,7 +87,7 @@ #define SQUASHFS_COMP_OPTS(flags) SQUASHFS_BIT(flags, \ SQUASHFS_COMP_OPT) -/* Max number of types and file types */ +/* Inode types including extended types */ #define SQUASHFS_DIR_TYPE 1 #define SQUASHFS_REG_TYPE 2 #define SQUASHFS_SYMLINK_TYPE 3 @@ -103,6 +103,9 @@ #define SQUASHFS_LFIFO_TYPE 13 #define SQUASHFS_LSOCKET_TYPE 14 +/* Max type value stored in directory entry */ +#define SQUASHFS_MAX_DIR_TYPE 7 + /* Xattr types */ #define SQUASHFS_XATTR_USER 0 #define SQUASHFS_XATTR_TRUSTED 1 @@ -447,9 +447,8 @@ void inode_add_bytes(struct inode *inode, loff_t bytes) EXPORT_SYMBOL(inode_add_bytes); -void inode_sub_bytes(struct inode *inode, loff_t bytes) +void __inode_sub_bytes(struct inode *inode, loff_t bytes) { - spin_lock(&inode->i_lock); inode->i_blocks -= bytes >> 9; bytes &= 511; if (inode->i_bytes < bytes) { @@ -457,6 +456,14 @@ void inode_sub_bytes(struct inode *inode, loff_t bytes) inode->i_bytes += 512; } inode->i_bytes -= bytes; +} + +EXPORT_SYMBOL(__inode_sub_bytes); + +void inode_sub_bytes(struct inode *inode, loff_t bytes) +{ + spin_lock(&inode->i_lock); + __inode_sub_bytes(inode, bytes); spin_unlock(&inode->i_lock); } @@ -53,11 +53,15 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = { * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we * take a passive reference to the superblock to avoid this from occurring. */ -static int prune_super(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long super_cache_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct super_block *sb; - int fs_objects = 0; - int total_objects; + long fs_objects = 0; + long total_objects; + long freed = 0; + long dentries; + long inodes; sb = container_of(shrink, struct super_block, s_shrink); @@ -65,46 +69,62 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc) * Deadlock avoidance. We may hold various FS locks, and we don't want * to recurse into the FS that called us in clear_inode() and friends.. */ - if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS)) - return -1; + if (!(sc->gfp_mask & __GFP_FS)) + return SHRINK_STOP; if (!grab_super_passive(sb)) - return -1; + return SHRINK_STOP; - if (sb->s_op && sb->s_op->nr_cached_objects) - fs_objects = sb->s_op->nr_cached_objects(sb); - - total_objects = sb->s_nr_dentry_unused + - sb->s_nr_inodes_unused + fs_objects + 1; - - if (sc->nr_to_scan) { - int dentries; - int inodes; - - /* proportion the scan between the caches */ - dentries = (sc->nr_to_scan * sb->s_nr_dentry_unused) / - total_objects; - inodes = (sc->nr_to_scan * sb->s_nr_inodes_unused) / - total_objects; - if (fs_objects) - fs_objects = (sc->nr_to_scan * fs_objects) / - total_objects; - /* - * prune the dcache first as the icache is pinned by it, then - * prune the icache, followed by the filesystem specific caches - */ - prune_dcache_sb(sb, dentries); - prune_icache_sb(sb, inodes); + if (sb->s_op->nr_cached_objects) + fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid); - if (fs_objects && sb->s_op->free_cached_objects) { - sb->s_op->free_cached_objects(sb, fs_objects); - fs_objects = sb->s_op->nr_cached_objects(sb); - } - total_objects = sb->s_nr_dentry_unused + - sb->s_nr_inodes_unused + fs_objects; + inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid); + dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid); + total_objects = dentries + inodes + fs_objects + 1; + + /* proportion the scan between the caches */ + dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); + inodes = mult_frac(sc->nr_to_scan, inodes, total_objects); + + /* + * prune the dcache first as the icache is pinned by it, then + * prune the icache, followed by the filesystem specific caches + */ + freed = prune_dcache_sb(sb, dentries, sc->nid); + freed += prune_icache_sb(sb, inodes, sc->nid); + + if (fs_objects) { + fs_objects = mult_frac(sc->nr_to_scan, fs_objects, + total_objects); + freed += sb->s_op->free_cached_objects(sb, fs_objects, + sc->nid); } - total_objects = (total_objects / 100) * sysctl_vfs_cache_pressure; + drop_super(sb); + return freed; +} + +static unsigned long super_cache_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct super_block *sb; + long total_objects = 0; + + sb = container_of(shrink, struct super_block, s_shrink); + + if (!grab_super_passive(sb)) + return 0; + + if (sb->s_op && sb->s_op->nr_cached_objects) + total_objects = sb->s_op->nr_cached_objects(sb, + sc->nid); + + total_objects += list_lru_count_node(&sb->s_dentry_lru, + sc->nid); + total_objects += list_lru_count_node(&sb->s_inode_lru, + sc->nid); + + total_objects = vfs_pressure_ratio(total_objects); drop_super(sb); return total_objects; } @@ -152,15 +172,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) static const struct super_operations default_op; 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; - } + if (security_sb_alloc(s)) + goto out_free_sb; + #ifdef CONFIG_SMP s->s_files = alloc_percpu(struct list_head); if (!s->s_files) @@ -181,9 +195,12 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); INIT_LIST_HEAD(&s->s_inodes); - INIT_LIST_HEAD(&s->s_dentry_lru); - INIT_LIST_HEAD(&s->s_inode_lru); - spin_lock_init(&s->s_inode_lru_lock); + + if (list_lru_init(&s->s_dentry_lru)) + goto err_out; + if (list_lru_init(&s->s_inode_lru)) + goto err_out_dentry_lru; + INIT_LIST_HEAD(&s->s_mounts); init_rwsem(&s->s_umount); lockdep_set_class(&s->s_umount, &type->s_umount_key); @@ -216,11 +233,16 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) s->cleancache_poolid = -1; s->s_shrink.seeks = DEFAULT_SEEKS; - s->s_shrink.shrink = prune_super; + s->s_shrink.scan_objects = super_cache_scan; + s->s_shrink.count_objects = super_cache_count; s->s_shrink.batch = 1024; + s->s_shrink.flags = SHRINKER_NUMA_AWARE; } out: return s; + +err_out_dentry_lru: + list_lru_destroy(&s->s_dentry_lru); err_out: security_sb_free(s); #ifdef CONFIG_SMP @@ -228,6 +250,7 @@ err_out: free_percpu(s->s_files); #endif destroy_sb_writers(s); +out_free_sb: kfree(s); s = NULL; goto out; @@ -300,6 +323,9 @@ void deactivate_locked_super(struct super_block *s) /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + list_lru_destroy(&s->s_dentry_lru); + list_lru_destroy(&s->s_inode_lru); + put_filesystem(fs); put_super(s); } else { @@ -336,19 +362,19 @@ EXPORT_SYMBOL(deactivate_super); * and want to turn it into a full-blown active reference. grab_super() * is called with sb_lock held and drops it. Returns 1 in case of * success, 0 if we had failed (superblock contents was already dead or - * dying when grab_super() had been called). + * dying when grab_super() had been called). Note that this is only + * called for superblocks not in rundown mode (== ones still on ->fs_supers + * of their type), so increment of ->s_count is OK here. */ static int grab_super(struct super_block *s) __releases(sb_lock) { - if (atomic_inc_not_zero(&s->s_active)) { - spin_unlock(&sb_lock); - return 1; - } - /* it's going away */ s->s_count++; spin_unlock(&sb_lock); - /* wait for it to die */ down_write(&s->s_umount); + if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) { + put_super(s); + return 1; + } up_write(&s->s_umount); put_super(s); return 0; @@ -414,6 +440,11 @@ void generic_shutdown_super(struct super_block *sb) evict_inodes(sb); + if (sb->s_dio_done_wq) { + destroy_workqueue(sb->s_dio_done_wq); + sb->s_dio_done_wq = NULL; + } + if (sop->put_super) sop->put_super(sb); @@ -463,11 +494,6 @@ retry: destroy_super(s); s = NULL; } - down_write(&old->s_umount); - if (unlikely(!(old->s_flags & MS_BORN))) { - deactivate_locked_super(old); - goto retry; - } return old; } } @@ -660,10 +686,10 @@ restart: if (hlist_unhashed(&sb->s_instances)) continue; if (sb->s_bdev == bdev) { - if (grab_super(sb)) /* drops sb_lock */ - return sb; - else + if (!grab_super(sb)) goto restart; + up_write(&sb->s_umount); + return sb; } } spin_unlock(&sb_lock); diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 15c68f9..c590cab 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -22,8 +22,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/mm.h> - -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "sysfs.h" @@ -391,7 +390,7 @@ out_unlock: return rc; } -static int open(struct inode * inode, struct file * file) +static int open(struct inode *inode, struct file *file) { struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; @@ -435,7 +434,7 @@ static int open(struct inode * inode, struct file * file) return error; } -static int release(struct inode * inode, struct file * file) +static int release(struct inode *inode, struct file *file) { struct bin_buffer *bb = file->private_data; @@ -481,7 +480,6 @@ void unmap_bin_file(struct sysfs_dirent *attr_sd) * @kobj: object. * @attr: attribute descriptor. */ - int sysfs_create_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { @@ -489,19 +487,16 @@ int sysfs_create_bin_file(struct kobject *kobj, return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR); } - +EXPORT_SYMBOL_GPL(sysfs_create_bin_file); /** * sysfs_remove_bin_file - remove binary file for object. * @kobj: object. * @attr: attribute descriptor. */ - void sysfs_remove_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { sysfs_hash_and_remove(kobj->sd, NULL, attr->attr.name); } - -EXPORT_SYMBOL_GPL(sysfs_create_bin_file); EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index e068e74..4d83ced 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -46,7 +46,7 @@ static unsigned int sysfs_name_hash(const void *ns, const char *name) unsigned int len = strlen(name); while (len--) hash = partial_name_hash(*name++, hash); - hash = ( end_name_hash(hash) ^ hash_ptr( (void *)ns, 31 ) ); + hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31)); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ if (hash < 1) @@ -258,7 +258,7 @@ static void sysfs_free_ino(unsigned int ino) spin_unlock(&sysfs_ino_lock); } -void release_sysfs_dirent(struct sysfs_dirent * sd) +void release_sysfs_dirent(struct sysfs_dirent *sd) { struct sysfs_dirent *parent_sd; @@ -297,7 +297,6 @@ static int sysfs_dentry_delete(const struct dentry *dentry) static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags) { struct sysfs_dirent *sd; - int is_dir; int type; if (flags & LOOKUP_RCU) @@ -341,18 +340,15 @@ out_bad: * is performed at its new name the dentry will be readded * to the dcache hashes. */ - is_dir = (sysfs_type(sd) == SYSFS_DIR); mutex_unlock(&sysfs_mutex); - if (is_dir) { - /* If we have submounts we must allow the vfs caches - * to lie about the state of the filesystem to prevent - * leaks and other nasty things. - */ - if (have_submounts(dentry)) - goto out_valid; - shrink_dcache_parent(dentry); - } - d_drop(dentry); + + /* If we have submounts we must allow the vfs caches + * to lie about the state of the filesystem to prevent + * leaks and other nasty things. + */ + if (check_submounts_and_drop(dentry) != 0) + goto out_valid; + return 0; } @@ -451,7 +447,7 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) if (!!sysfs_ns_type(acxt->parent_sd) != !!sd->s_ns) { WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n", - sysfs_ns_type(acxt->parent_sd)? "required": "invalid", + sysfs_ns_type(acxt->parent_sd) ? "required" : "invalid", acxt->parent_sd->s_name, sd->s_name); return -EINVAL; } @@ -619,7 +615,7 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, if (!!sysfs_ns_type(parent_sd) != !!ns) { WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n", - sysfs_ns_type(parent_sd)? "required": "invalid", + sysfs_ns_type(parent_sd) ? "required" : "invalid", parent_sd->s_name, name); return NULL; } @@ -674,7 +670,7 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd, enum kobj_ns_type type, const void *ns, const char *name, struct sysfs_dirent **p_sd) { - umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; + umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; struct sysfs_addrm_cxt acxt; struct sysfs_dirent *sd; int rc; @@ -735,9 +731,9 @@ static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj) /** * sysfs_create_dir - create a directory for an object. - * @kobj: object we're creating directory for. + * @kobj: object we're creating directory for. */ -int sysfs_create_dir(struct kobject * kobj) +int sysfs_create_dir(struct kobject *kobj) { enum kobj_ns_type type; struct sysfs_dirent *parent_sd, *sd; @@ -764,8 +760,8 @@ int sysfs_create_dir(struct kobject * kobj) return error; } -static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, - unsigned int flags) +static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) { struct dentry *ret = NULL; struct dentry *parent = dentry->d_parent; @@ -857,7 +853,7 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd) * what used to be sysfs_rmdir() below, instead of calling separately. */ -void sysfs_remove_dir(struct kobject * kobj) +void sysfs_remove_dir(struct kobject *kobj) { struct sysfs_dirent *sd = kobj->sd; @@ -896,7 +892,9 @@ int sysfs_rename(struct sysfs_dirent *sd, sd->s_name = new_name; } - /* Move to the appropriate place in the appropriate directories rbtree. */ + /* + * Move to the appropriate place in the appropriate directories rbtree. + */ sysfs_unlink_sibling(sd); sysfs_get(new_parent_sd); sysfs_put(sd->s_parent); @@ -988,20 +986,21 @@ static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns, struct sysfs_dirent *parent_sd, ino_t ino, struct sysfs_dirent *pos) { pos = sysfs_dir_pos(ns, parent_sd, ino, pos); - if (pos) do { - struct rb_node *node = rb_next(&pos->s_rb); - if (!node) - pos = NULL; - else - pos = to_sysfs_dirent(node); - } while (pos && pos->s_ns != ns); + if (pos) + do { + struct rb_node *node = rb_next(&pos->s_rb); + if (!node) + pos = NULL; + else + pos = to_sysfs_dirent(node); + } while (pos && pos->s_ns != ns); return pos; } static int sysfs_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; - struct sysfs_dirent * parent_sd = dentry->d_fsdata; + struct sysfs_dirent *parent_sd = dentry->d_fsdata; struct sysfs_dirent *pos = file->private_data; enum kobj_ns_type type; const void *ns; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index d2bb7ed..15ef5eb 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -20,7 +20,7 @@ #include <linux/list.h> #include <linux/mutex.h> #include <linux/limits.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "sysfs.h" @@ -45,8 +45,8 @@ struct sysfs_open_dirent { struct sysfs_buffer { size_t count; loff_t pos; - char * page; - const struct sysfs_ops * ops; + char *page; + const struct sysfs_ops *ops; struct mutex mutex; int needs_read_fill; int event; @@ -59,16 +59,16 @@ struct sysfs_buffer { * @buffer: data buffer for file. * * Allocate @buffer->page, if it hasn't been already, then call the - * kobject's show() method to fill the buffer with this attribute's - * data. + * kobject's show() method to fill the buffer with this attribute's + * data. * This is called only once, on the file's first read unless an error * is returned. */ -static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer) +static int fill_read_buffer(struct dentry *dentry, struct sysfs_buffer *buffer) { struct sysfs_dirent *attr_sd = dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - const struct sysfs_ops * ops = buffer->ops; + const struct sysfs_ops *ops = buffer->ops; int ret = 0; ssize_t count; @@ -106,7 +106,7 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer } /** - * sysfs_read_file - read an attribute. + * sysfs_read_file - read an attribute. * @file: file pointer. * @buf: buffer to fill. * @count: number of bytes to read. @@ -127,12 +127,12 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer static ssize_t sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct sysfs_buffer * buffer = file->private_data; + struct sysfs_buffer *buffer = file->private_data; ssize_t retval = 0; mutex_lock(&buffer->mutex); if (buffer->needs_read_fill || *ppos == 0) { - retval = fill_read_buffer(file->f_path.dentry,buffer); + retval = fill_read_buffer(file->f_path.dentry, buffer); if (retval) goto out; } @@ -154,9 +154,8 @@ out: * Allocate @buffer->page if it hasn't been already, then * copy the user-supplied buffer into it. */ - -static int -fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t count) +static int fill_write_buffer(struct sysfs_buffer *buffer, + const char __user *buf, size_t count) { int error; @@ -167,7 +166,7 @@ fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t if (count >= PAGE_SIZE) count = PAGE_SIZE - 1; - error = copy_from_user(buffer->page,buf,count); + error = copy_from_user(buffer->page, buf, count); buffer->needs_read_fill = 1; /* if buf is assumed to contain a string, terminate it by \0, so e.g. sscanf() can scan the string easily */ @@ -183,16 +182,15 @@ fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t * @count: number of bytes * * Get the correct pointers for the kobject and the attribute we're - * dealing with, then call the store() method for the attribute, + * dealing with, then call the store() method for the attribute, * passing the buffer that we acquired in fill_write_buffer(). */ - -static int -flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t count) +static int flush_write_buffer(struct dentry *dentry, + struct sysfs_buffer *buffer, size_t count) { struct sysfs_dirent *attr_sd = dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - const struct sysfs_ops * ops = buffer->ops; + const struct sysfs_ops *ops = buffer->ops; int rc; /* need attr_sd for attr and ops, its parent for kobj */ @@ -219,15 +217,14 @@ flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t * then push it to the kobject in flush_write_buffer(). * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come - * on the first write. + * on the first write. * Hint: if you're writing a value, first read the file, modify only the - * the value you're changing, then write entire buffer back. + * the value you're changing, then write entire buffer back. */ - -static ssize_t -sysfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +static ssize_t sysfs_write_file(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) { - struct sysfs_buffer * buffer = file->private_data; + struct sysfs_buffer *buffer = file->private_data; ssize_t len; mutex_lock(&buffer->mutex); @@ -339,13 +336,14 @@ static int sysfs_open_file(struct inode *inode, struct file *file) if (kobj->ktype && kobj->ktype->sysfs_ops) ops = kobj->ktype->sysfs_ops; else { - WARN(1, KERN_ERR "missing sysfs attribute operations for " - "kobject: %s\n", kobject_name(kobj)); + WARN(1, KERN_ERR + "missing sysfs attribute operations for kobject: %s\n", + kobject_name(kobj)); goto err_out; } /* File needs write support. - * The inode's perms must say it's ok, + * The inode's perms must say it's ok, * and we must have a store method. */ if (file->f_mode & FMODE_WRITE) { @@ -420,7 +418,7 @@ static int sysfs_release(struct inode *inode, struct file *filp) */ static unsigned int sysfs_poll(struct file *filp, poll_table *wait) { - struct sysfs_buffer * buffer = filp->private_data; + struct sysfs_buffer *buffer = filp->private_data; struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata; struct sysfs_open_dirent *od = attr_sd->s_attr.open; @@ -518,8 +516,9 @@ static int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr, ns = ops->namespace(kobj, attr); out: if (err) { - WARN(1, KERN_ERR "missing sysfs namespace attribute operation for " - "kobject: %s\n", kobject_name(kobj)); + WARN(1, KERN_ERR + "missing sysfs namespace attribute operation for kobject: %s\n", + kobject_name(kobj)); } *pns = ns; return err; @@ -566,17 +565,17 @@ int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr, /** * sysfs_create_file - create an attribute file for an object. - * @kobj: object we're creating for. + * @kobj: object we're creating for. * @attr: attribute descriptor. */ - -int sysfs_create_file(struct kobject * kobj, const struct attribute * attr) +int sysfs_create_file(struct kobject *kobj, const struct attribute *attr) { BUG_ON(!kobj || !kobj->sd || !attr); return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR); } +EXPORT_SYMBOL_GPL(sysfs_create_file); int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr) { @@ -590,6 +589,7 @@ int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr) sysfs_remove_file(kobj, ptr[i]); return err; } +EXPORT_SYMBOL_GPL(sysfs_create_files); /** * sysfs_add_file_to_group - add an attribute file to a pre-existing group. @@ -654,7 +654,6 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, } EXPORT_SYMBOL_GPL(sysfs_chmod_file); - /** * sysfs_remove_file - remove an object attribute. * @kobj: object we're acting for. @@ -662,8 +661,7 @@ EXPORT_SYMBOL_GPL(sysfs_chmod_file); * * Hash the attribute name and kill the victim. */ - -void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr) +void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr) { const void *ns; @@ -672,13 +670,15 @@ void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr) sysfs_hash_and_remove(kobj->sd, ns, attr->name); } +EXPORT_SYMBOL_GPL(sysfs_remove_file); -void sysfs_remove_files(struct kobject * kobj, const struct attribute **ptr) +void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr) { int i; for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } +EXPORT_SYMBOL_GPL(sysfs_remove_files); /** * sysfs_remove_file_from_group - remove an attribute file from a group. @@ -793,9 +793,3 @@ int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), return 0; } EXPORT_SYMBOL_GPL(sysfs_schedule_callback); - - -EXPORT_SYMBOL_GPL(sysfs_create_file); -EXPORT_SYMBOL_GPL(sysfs_remove_file); -EXPORT_SYMBOL_GPL(sysfs_remove_files); -EXPORT_SYMBOL_GPL(sysfs_create_files); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index aec3d5c..5f92cd2 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -3,8 +3,10 @@ * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab + * Copyright (c) 2013 Greg Kroah-Hartman + * Copyright (c) 2013 The Linux Foundation * - * This file is released undert the GPL v2. + * This file is released undert the GPL v2. * */ @@ -19,39 +21,65 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, const struct attribute_group *grp) { - struct attribute *const* attr; - int i; + struct attribute *const *attr; + struct bin_attribute *const *bin_attr; - for (i = 0, attr = grp->attrs; *attr; i++, attr++) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); + if (grp->attrs) + for (attr = grp->attrs; *attr; attr++) + sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); + if (grp->bin_attrs) + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) + sysfs_remove_bin_file(kobj, *bin_attr); } static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, const struct attribute_group *grp, int update) { - struct attribute *const* attr; + struct attribute *const *attr; + struct bin_attribute *const *bin_attr; int error = 0, i; - for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { - umode_t mode = 0; + if (grp->attrs) { + for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { + umode_t mode = 0; + + /* + * In update mode, we're changing the permissions or + * visibility. Do this by first removing then + * re-adding (if required) the file. + */ + if (update) + sysfs_hash_and_remove(dir_sd, NULL, + (*attr)->name); + if (grp->is_visible) { + mode = grp->is_visible(kobj, *attr, i); + if (!mode) + continue; + } + error = sysfs_add_file_mode(dir_sd, *attr, + SYSFS_KOBJ_ATTR, + (*attr)->mode | mode); + if (unlikely(error)) + break; + } + if (error) { + remove_files(dir_sd, kobj, grp); + goto exit; + } + } - /* in update mode, we're changing the permissions or - * visibility. Do this by first removing then - * re-adding (if required) the file */ - if (update) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); - if (grp->is_visible) { - mode = grp->is_visible(kobj, *attr, i); - if (!mode) - continue; + if (grp->bin_attrs) { + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + if (update) + sysfs_remove_bin_file(kobj, *bin_attr); + error = sysfs_create_bin_file(kobj, *bin_attr); + if (error) + break; } - error = sysfs_add_file_mode(dir_sd, *attr, SYSFS_KOBJ_ATTR, - (*attr)->mode | mode); - if (unlikely(error)) - break; + if (error) + remove_files(dir_sd, kobj, grp); } - if (error) - remove_files(dir_sd, kobj, grp); +exit: return error; } @@ -67,8 +95,8 @@ static int internal_create_group(struct kobject *kobj, int update, /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; - if (!grp->attrs) { - WARN(1, "sysfs: attrs not set by subsystem for group: %s/%s\n", + if (!grp->attrs && !grp->bin_attrs) { + WARN(1, "sysfs: (bin_)attrs not set by subsystem for group: %s/%s\n", kobj->name, grp->name ? "" : grp->name); return -EINVAL; } @@ -103,6 +131,41 @@ int sysfs_create_group(struct kobject *kobj, { return internal_create_group(kobj, 0, grp); } +EXPORT_SYMBOL_GPL(sysfs_create_group); + +/** + * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups + * @kobj: The kobject to create the group on + * @groups: The attribute groups to create, NULL terminated + * + * This function creates a bunch of attribute groups. If an error occurs when + * creating a group, all previously created groups will be removed, unwinding + * everything back to the original state when this function was called. + * It will explicitly warn and error if any of the attribute files being + * created already exist. + * + * Returns 0 on success or error code from sysfs_create_group on error. + */ +int sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = sysfs_create_group(kobj, groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(kobj, groups[i]); + break; + } + } + return error; +} +EXPORT_SYMBOL_GPL(sysfs_create_groups); /** * sysfs_update_group - given a directory kobject, update an attribute group @@ -126,11 +189,18 @@ int sysfs_update_group(struct kobject *kobj, { return internal_create_group(kobj, 1, grp); } +EXPORT_SYMBOL_GPL(sysfs_update_group); - - -void sysfs_remove_group(struct kobject * kobj, - const struct attribute_group * grp) +/** + * sysfs_remove_group: remove a group from a kobject + * @kobj: kobject to remove the group from + * @grp: group to remove + * + * This function removes a group of attributes from a kobject. The attributes + * previously have to have been created for this group, otherwise it will fail. + */ +void sysfs_remove_group(struct kobject *kobj, + const struct attribute_group *grp) { struct sysfs_dirent *dir_sd = kobj->sd; struct sysfs_dirent *sd; @@ -138,8 +208,9 @@ void sysfs_remove_group(struct kobject * kobj, if (grp->name) { sd = sysfs_get_dirent(dir_sd, NULL, grp->name); if (!sd) { - WARN(!sd, KERN_WARNING "sysfs group %p not found for " - "kobject '%s'\n", grp, kobject_name(kobj)); + WARN(!sd, KERN_WARNING + "sysfs group %p not found for kobject '%s'\n", + grp, kobject_name(kobj)); return; } } else @@ -151,6 +222,27 @@ void sysfs_remove_group(struct kobject * kobj, sysfs_put(sd); } +EXPORT_SYMBOL_GPL(sysfs_remove_group); + +/** + * sysfs_remove_groups - remove a list of groups + * + * @kobj: The kobject for the groups to be removed from + * @groups: NULL terminated list of groups to be removed + * + * If groups is not NULL, remove the specified groups from the kobject. + */ +void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + int i; + + if (!groups) + return; + for (i = 0; groups[i]; i++) + sysfs_remove_group(kobj, groups[i]); +} +EXPORT_SYMBOL_GPL(sysfs_remove_groups); /** * sysfs_merge_group - merge files into a pre-existing attribute group. @@ -247,7 +339,3 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); - -EXPORT_SYMBOL_GPL(sysfs_create_group); -EXPORT_SYMBOL_GPL(sysfs_update_group); -EXPORT_SYMBOL_GPL(sysfs_remove_group); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index 3e2837a..963f910 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -10,7 +10,7 @@ * Please see Documentation/filesystems/sysfs.txt for more information. */ -#undef DEBUG +#undef DEBUG #include <linux/pagemap.h> #include <linux/namei.h> @@ -36,7 +36,7 @@ static struct backing_dev_info sysfs_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; -static const struct inode_operations sysfs_inode_operations ={ +static const struct inode_operations sysfs_inode_operations = { .permission = sysfs_permission, .setattr = sysfs_setattr, .getattr = sysfs_getattr, @@ -67,7 +67,7 @@ static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd) return attrs; } -int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr * iattr) +int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr) { struct sysfs_inode_attrs *sd_attrs; struct iattr *iattrs; @@ -128,7 +128,8 @@ out: return error; } -static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, u32 *secdata_len) +static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, + u32 *secdata_len) { struct sysfs_inode_attrs *iattrs; void *old_secdata; @@ -186,13 +187,13 @@ out: return error; } -static inline void set_default_inode_attr(struct inode * inode, umode_t mode) +static inline void set_default_inode_attr(struct inode *inode, umode_t mode) { inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } -static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) +static inline void set_inode_attr(struct inode *inode, struct iattr *iattr) { inode->i_uid = iattr->ia_uid; inode->i_gid = iattr->ia_gid; @@ -220,7 +221,8 @@ static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode) set_nlink(inode, sd->s_dir.subdirs + 2); } -int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) { struct sysfs_dirent *sd = dentry->d_fsdata; struct inode *inode = dentry->d_inode; @@ -285,7 +287,7 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode) * RETURNS: * Pointer to allocated inode on success, NULL on failure. */ -struct inode * sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd) +struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd) { struct inode *inode; @@ -312,7 +314,8 @@ void sysfs_evict_inode(struct inode *inode) sysfs_put(sd); } -int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const char *name) +int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, + const char *name) { struct sysfs_addrm_cxt acxt; struct sysfs_dirent *sd; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index afd8327..834ec2c 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -64,7 +64,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) /* instantiate and link root dentry */ root = d_make_root(inode); if (!root) { - pr_debug("%s: could not get root dentry!\n",__func__); + pr_debug("%s: could not get root dentry!\n", __func__); return -ENOMEM; } root->d_fsdata = &sysfs_root; @@ -112,8 +112,15 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, struct super_block *sb; int error; - if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs) - return ERR_PTR(-EPERM); + if (!(flags & MS_KERNMOUNT)) { + if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) + return ERR_PTR(-EPERM); + + for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) { + if (!kobj_ns_current_may_mount(type)) + return ERR_PTR(-EPERM); + } + } info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 8c940df..2dd4507 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -125,6 +125,7 @@ int sysfs_create_link(struct kobject *kobj, struct kobject *target, { return sysfs_do_create_link(kobj, target, name, 1); } +EXPORT_SYMBOL_GPL(sysfs_create_link); /** * sysfs_create_link_nowarn - create symlink between two objects. @@ -166,8 +167,7 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, * @kobj: object we're acting for. * @name: name of the symlink to remove. */ - -void sysfs_remove_link(struct kobject * kobj, const char * name) +void sysfs_remove_link(struct kobject *kobj, const char *name) { struct sysfs_dirent *parent_sd = NULL; @@ -178,6 +178,7 @@ void sysfs_remove_link(struct kobject * kobj, const char * name) sysfs_hash_and_remove(parent_sd, NULL, name); } +EXPORT_SYMBOL_GPL(sysfs_remove_link); /** * sysfs_rename_link - rename symlink in object's directory. @@ -223,6 +224,7 @@ out: sysfs_put(sd); return result; } +EXPORT_SYMBOL_GPL(sysfs_rename_link); static int sysfs_get_target_path(struct sysfs_dirent *parent_sd, struct sysfs_dirent *target_sd, char *path) @@ -276,7 +278,7 @@ static int sysfs_get_target_path(struct sysfs_dirent *parent_sd, return 0; } -static int sysfs_getlink(struct dentry *dentry, char * path) +static int sysfs_getlink(struct dentry *dentry, char *path) { struct sysfs_dirent *sd = dentry->d_fsdata; struct sysfs_dirent *parent_sd = sd->s_parent; @@ -295,7 +297,7 @@ static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd) int error = -ENOMEM; unsigned long page = get_zeroed_page(GFP_KERNEL); if (page) { - error = sysfs_getlink(dentry, (char *) page); + error = sysfs_getlink(dentry, (char *) page); if (error < 0) free_page((unsigned long)page); } @@ -303,7 +305,8 @@ static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd) return NULL; } -static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) +static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd, + void *cookie) { char *page = nd_get_link(nd); if (!IS_ERR(page)) @@ -319,8 +322,3 @@ const struct inode_operations sysfs_symlink_inode_operations = { .getattr = sysfs_getattr, .permission = sysfs_permission, }; - - -EXPORT_SYMBOL_GPL(sysfs_create_link); -EXPORT_SYMBOL_GPL(sysfs_remove_link); -EXPORT_SYMBOL_GPL(sysfs_rename_link); diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index d1e4043..b6deca3 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -78,7 +78,7 @@ struct sysfs_dirent { }; unsigned short s_flags; - umode_t s_mode; + umode_t s_mode; unsigned int s_ino; struct sysfs_inode_attrs *s_iattr; }; @@ -123,9 +123,9 @@ do { \ key = &attr->skey; \ \ lockdep_init_map(&sd->dep_map, "s_active", key, 0); \ -} while(0) +} while (0) #else -#define sysfs_dirent_init_lockdep(sd) do {} while(0) +#define sysfs_dirent_init_lockdep(sd) do {} while (0) #endif /* @@ -186,8 +186,8 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name, struct sysfs_dirent **p_sd); void sysfs_remove_subdir(struct sysfs_dirent *sd); -int sysfs_rename(struct sysfs_dirent *sd, - struct sysfs_dirent *new_parent_sd, const void *ns, const char *new_name); +int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd, + const void *ns, const char *new_name); static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd) { @@ -214,10 +214,12 @@ void sysfs_evict_inode(struct inode *inode); int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr); int sysfs_permission(struct inode *inode, int mask); int sysfs_setattr(struct dentry *dentry, struct iattr *iattr); -int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); +int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat); int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags); -int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const char *name); + size_t size, int flags); +int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, + const char *name); int sysfs_inode_init(void); /* diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index c1a591a..66bc316 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -469,7 +469,7 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) { - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); sysv_truncate(inode); } } diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index 9e1d056..f35135e 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -277,18 +277,25 @@ static int kick_a_thread(void) return 0; } -int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc) +unsigned long ubifs_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) { - int nr = sc->nr_to_scan; - int freed, contention = 0; long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); - if (nr == 0) - /* - * Due to the way UBIFS updates the clean znode counter it may - * temporarily be negative. - */ - return clean_zn_cnt >= 0 ? clean_zn_cnt : 1; + /* + * Due to the way UBIFS updates the clean znode counter it may + * temporarily be negative. + */ + return clean_zn_cnt >= 0 ? clean_zn_cnt : 1; +} + +unsigned long ubifs_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long nr = sc->nr_to_scan; + int contention = 0; + unsigned long freed; + long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); if (!clean_zn_cnt) { /* @@ -316,10 +323,10 @@ int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc) if (!freed && contention) { dbg_tnc("freed nothing, but contention"); - return -1; + return SHRINK_STOP; } out: - dbg_tnc("%d znodes were freed, requested %d", freed, nr); + dbg_tnc("%lu znodes were freed, requested %lu", freed, nr); return freed; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 879b997..3e4aa72 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -49,7 +49,8 @@ struct kmem_cache *ubifs_inode_slab; /* UBIFS TNC shrinker description */ static struct shrinker ubifs_shrinker_info = { - .shrink = ubifs_shrinker, + .scan_objects = ubifs_shrink_scan, + .count_objects = ubifs_shrink_count, .seeks = DEFAULT_SEEKS, }; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index b2babce..e8c8cfe 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1624,7 +1624,10 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot); int ubifs_tnc_end_commit(struct ubifs_info *c); /* shrinker.c */ -int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc); +unsigned long ubifs_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc); +unsigned long ubifs_shrink_count(struct shrinker *shrink, + struct shrink_control *sc); /* commit.c */ int ubifs_bg_thread(void *info); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index b6d15d3..062b792 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -172,7 +172,7 @@ static void udf_write_failed(struct address_space *mapping, loff_t to) loff_t isize = inode->i_size; if (to > isize) { - truncate_pagecache(inode, to, isize); + truncate_pagecache(inode, isize); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); diff --git a/fs/udf/super.c b/fs/udf/super.c index 9ac4057..839a2ba 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -630,6 +630,12 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) struct udf_sb_info *sbi = UDF_SB(sb); int error = 0; + if (sbi->s_lvid_bh) { + int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev); + if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY)) + return -EACCES; + } + uopt.flags = sbi->s_flags; uopt.uid = sbi->s_uid; uopt.gid = sbi->s_gid; @@ -649,12 +655,6 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) sbi->s_dmode = uopt.dmode; write_unlock(&sbi->s_cred_lock); - if (sbi->s_lvid_bh) { - int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev); - if (write_rev > UDF_MAX_WRITE_VERSION) - *flags |= MS_RDONLY; - } - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) goto out_unlock; @@ -843,27 +843,38 @@ static int udf_find_fileset(struct super_block *sb, return 1; } +/* + * Load primary Volume Descriptor Sequence + * + * Return <0 on error, 0 on success. -EAGAIN is special meaning next sequence + * should be tried. + */ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) { struct primaryVolDesc *pvoldesc; struct ustr *instr, *outstr; struct buffer_head *bh; uint16_t ident; - int ret = 1; + int ret = -ENOMEM; instr = kmalloc(sizeof(struct ustr), GFP_NOFS); if (!instr) - return 1; + return -ENOMEM; outstr = kmalloc(sizeof(struct ustr), GFP_NOFS); if (!outstr) goto out1; bh = udf_read_tagged(sb, block, block, &ident); - if (!bh) + if (!bh) { + ret = -EAGAIN; goto out2; + } - BUG_ON(ident != TAG_IDENT_PVD); + if (ident != TAG_IDENT_PVD) { + ret = -EIO; + goto out_bh; + } pvoldesc = (struct primaryVolDesc *)bh->b_data; @@ -889,8 +900,9 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) if (udf_CS0toUTF8(outstr, instr)) udf_debug("volSetIdent[] = '%s'\n", outstr->u_name); - brelse(bh); ret = 0; +out_bh: + brelse(bh); out2: kfree(outstr); out1: @@ -947,7 +959,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition) if (mdata->s_mirror_fe == NULL) { udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n"); - goto error_exit; + return -EIO; } } @@ -964,23 +976,18 @@ static int udf_load_metadata_files(struct super_block *sb, int partition) addr.logicalBlockNum, addr.partitionReferenceNum); mdata->s_bitmap_fe = udf_iget(sb, &addr); - if (mdata->s_bitmap_fe == NULL) { if (sb->s_flags & MS_RDONLY) udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n"); else { udf_err(sb, "bitmap inode efe not found and attempted read-write mount\n"); - goto error_exit; + return -EIO; } } } udf_debug("udf_load_metadata_files Ok\n"); - return 0; - -error_exit: - return 1; } static void udf_load_fileset(struct super_block *sb, struct buffer_head *bh, @@ -1069,7 +1076,7 @@ static int udf_fill_partdesc_info(struct super_block *sb, if (!map->s_uspace.s_table) { udf_debug("cannot load unallocSpaceTable (part %d)\n", p_index); - return 1; + return -EIO; } map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_TABLE; udf_debug("unallocSpaceTable (part %d) @ %ld\n", @@ -1079,7 +1086,7 @@ static int udf_fill_partdesc_info(struct super_block *sb, if (phd->unallocSpaceBitmap.extLength) { struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index); if (!bitmap) - return 1; + return -ENOMEM; map->s_uspace.s_bitmap = bitmap; bitmap->s_extPosition = le32_to_cpu( phd->unallocSpaceBitmap.extPosition); @@ -1102,7 +1109,7 @@ static int udf_fill_partdesc_info(struct super_block *sb, if (!map->s_fspace.s_table) { udf_debug("cannot load freedSpaceTable (part %d)\n", p_index); - return 1; + return -EIO; } map->s_partition_flags |= UDF_PART_FLAG_FREED_TABLE; @@ -1113,7 +1120,7 @@ static int udf_fill_partdesc_info(struct super_block *sb, if (phd->freedSpaceBitmap.extLength) { struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index); if (!bitmap) - return 1; + return -ENOMEM; map->s_fspace.s_bitmap = bitmap; bitmap->s_extPosition = le32_to_cpu( phd->freedSpaceBitmap.extPosition); @@ -1165,7 +1172,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) udf_find_vat_block(sb, p_index, type1_index, blocks - 1); } if (!sbi->s_vat_inode) - return 1; + return -EIO; if (map->s_partition_type == UDF_VIRTUAL_MAP15) { map->s_type_specific.s_virtual.s_start_offset = 0; @@ -1177,7 +1184,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) pos = udf_block_map(sbi->s_vat_inode, 0); bh = sb_bread(sb, pos); if (!bh) - return 1; + return -EIO; vat20 = (struct virtualAllocationTable20 *)bh->b_data; } else { vat20 = (struct virtualAllocationTable20 *) @@ -1195,6 +1202,12 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) return 0; } +/* + * Load partition descriptor block + * + * Returns <0 on error, 0 on success, -EAGAIN is special - try next descriptor + * sequence. + */ static int udf_load_partdesc(struct super_block *sb, sector_t block) { struct buffer_head *bh; @@ -1204,13 +1217,15 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block) int i, type1_idx; uint16_t partitionNumber; uint16_t ident; - int ret = 0; + int ret; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) - return 1; - if (ident != TAG_IDENT_PD) + return -EAGAIN; + if (ident != TAG_IDENT_PD) { + ret = 0; goto out_bh; + } p = (struct partitionDesc *)bh->b_data; partitionNumber = le16_to_cpu(p->partitionNumber); @@ -1229,10 +1244,13 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block) if (i >= sbi->s_partitions) { udf_debug("Partition (%d) not found in partition map\n", partitionNumber); + ret = 0; goto out_bh; } ret = udf_fill_partdesc_info(sb, p, i); + if (ret < 0) + goto out_bh; /* * Now rescan for VIRTUAL or METADATA partitions when SPARABLE and @@ -1249,32 +1267,37 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block) break; } - if (i >= sbi->s_partitions) + if (i >= sbi->s_partitions) { + ret = 0; goto out_bh; + } ret = udf_fill_partdesc_info(sb, p, i); - if (ret) + if (ret < 0) goto out_bh; if (map->s_partition_type == UDF_METADATA_MAP25) { ret = udf_load_metadata_files(sb, i); - if (ret) { + if (ret < 0) { udf_err(sb, "error loading MetaData partition map %d\n", i); goto out_bh; } } else { - ret = udf_load_vat(sb, i, type1_idx); - if (ret) - goto out_bh; /* - * Mark filesystem read-only if we have a partition with - * virtual map since we don't handle writing to it (we - * overwrite blocks instead of relocating them). + * If we have a partition with virtual map, we don't handle + * writing to it (we overwrite blocks instead of relocating + * them). */ - sb->s_flags |= MS_RDONLY; - pr_notice("Filesystem marked read-only because writing to pseudooverwrite partition is not implemented\n"); + if (!(sb->s_flags & MS_RDONLY)) { + ret = -EACCES; + goto out_bh; + } + ret = udf_load_vat(sb, i, type1_idx); + if (ret < 0) + goto out_bh; } + ret = 0; out_bh: /* In case loading failed, we handle cleanup in udf_fill_super */ brelse(bh); @@ -1340,11 +1363,11 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, uint16_t ident; struct buffer_head *bh; unsigned int table_len; - int ret = 0; + int ret; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) - return 1; + return -EAGAIN; BUG_ON(ident != TAG_IDENT_LVD); lvd = (struct logicalVolDesc *)bh->b_data; table_len = le32_to_cpu(lvd->mapTableLength); @@ -1352,7 +1375,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, udf_err(sb, "error loading logical volume descriptor: " "Partition table too long (%u > %lu)\n", table_len, sb->s_blocksize - sizeof(*lvd)); - ret = 1; + ret = -EIO; goto out_bh; } @@ -1396,11 +1419,10 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, } else if (!strncmp(upm2->partIdent.ident, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { - if (udf_load_sparable_map(sb, map, - (struct sparablePartitionMap *)gpm) < 0) { - ret = 1; + ret = udf_load_sparable_map(sb, map, + (struct sparablePartitionMap *)gpm); + if (ret < 0) goto out_bh; - } } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { @@ -1465,7 +1487,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, } if (lvd->integritySeqExt.extLength) udf_load_logicalvolint(sb, leea_to_cpu(lvd->integritySeqExt)); - + ret = 0; out_bh: brelse(bh); return ret; @@ -1503,22 +1525,18 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ } /* - * udf_process_sequence - * - * PURPOSE - * Process a main/reserve volume descriptor sequence. - * - * PRE-CONDITIONS - * sb Pointer to _locked_ superblock. - * block First block of first extent of the sequence. - * lastblock Lastblock of first extent of the sequence. + * Process a main/reserve volume descriptor sequence. + * @block First block of first extent of the sequence. + * @lastblock Lastblock of first extent of the sequence. + * @fileset There we store extent containing root fileset * - * HISTORY - * July 1, 1997 - Andrew E. Mileski - * Written, tested, and released. + * Returns <0 on error, 0 on success. -EAGAIN is special - try next descriptor + * sequence */ -static noinline int udf_process_sequence(struct super_block *sb, long block, - long lastblock, struct kernel_lb_addr *fileset) +static noinline int udf_process_sequence( + struct super_block *sb, + sector_t block, sector_t lastblock, + struct kernel_lb_addr *fileset) { struct buffer_head *bh = NULL; struct udf_vds_record vds[VDS_POS_LENGTH]; @@ -1529,6 +1547,7 @@ static noinline int udf_process_sequence(struct super_block *sb, long block, uint32_t vdsn; uint16_t ident; long next_s = 0, next_e = 0; + int ret; memset(vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH); @@ -1543,7 +1562,7 @@ static noinline int udf_process_sequence(struct super_block *sb, long block, udf_err(sb, "Block %llu of volume descriptor sequence is corrupted or we could not read it\n", (unsigned long long)block); - return 1; + return -EAGAIN; } /* Process each descriptor (ISO 13346 3/8.3-8.4) */ @@ -1616,14 +1635,19 @@ static noinline int udf_process_sequence(struct super_block *sb, long block, */ if (!vds[VDS_POS_PRIMARY_VOL_DESC].block) { udf_err(sb, "Primary Volume Descriptor not found!\n"); - return 1; + return -EAGAIN; + } + ret = udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block); + if (ret < 0) + return ret; + + if (vds[VDS_POS_LOGICAL_VOL_DESC].block) { + ret = udf_load_logicalvol(sb, + vds[VDS_POS_LOGICAL_VOL_DESC].block, + fileset); + if (ret < 0) + return ret; } - if (udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block)) - return 1; - - if (vds[VDS_POS_LOGICAL_VOL_DESC].block && udf_load_logicalvol(sb, - vds[VDS_POS_LOGICAL_VOL_DESC].block, fileset)) - return 1; if (vds[VDS_POS_PARTITION_DESC].block) { /* @@ -1632,19 +1656,27 @@ static noinline int udf_process_sequence(struct super_block *sb, long block, */ for (block = vds[VDS_POS_PARTITION_DESC].block; block < vds[VDS_POS_TERMINATING_DESC].block; - block++) - if (udf_load_partdesc(sb, block)) - return 1; + block++) { + ret = udf_load_partdesc(sb, block); + if (ret < 0) + return ret; + } } return 0; } +/* + * Load Volume Descriptor Sequence described by anchor in bh + * + * Returns <0 on error, 0 on success + */ static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh, struct kernel_lb_addr *fileset) { struct anchorVolDescPtr *anchor; - long main_s, main_e, reserve_s, reserve_e; + sector_t main_s, main_e, reserve_s, reserve_e; + int ret; anchor = (struct anchorVolDescPtr *)bh->b_data; @@ -1662,18 +1694,26 @@ static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh, /* Process the main & reserve sequences */ /* responsible for finding the PartitionDesc(s) */ - if (!udf_process_sequence(sb, main_s, main_e, fileset)) - return 1; - udf_sb_free_partitions(sb); - if (!udf_process_sequence(sb, reserve_s, reserve_e, fileset)) - return 1; + ret = udf_process_sequence(sb, main_s, main_e, fileset); + if (ret != -EAGAIN) + return ret; udf_sb_free_partitions(sb); - return 0; + ret = udf_process_sequence(sb, reserve_s, reserve_e, fileset); + if (ret < 0) { + udf_sb_free_partitions(sb); + /* No sequence was OK, return -EIO */ + if (ret == -EAGAIN) + ret = -EIO; + } + return ret; } /* * Check whether there is an anchor block in the given block and * load Volume Descriptor Sequence if so. + * + * Returns <0 on error, 0 on success, -EAGAIN is special - try next anchor + * block */ static int udf_check_anchor_block(struct super_block *sb, sector_t block, struct kernel_lb_addr *fileset) @@ -1685,33 +1725,40 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block, if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) && udf_fixed_to_variable(block) >= sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) - return 0; + return -EAGAIN; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) - return 0; + return -EAGAIN; if (ident != TAG_IDENT_AVDP) { brelse(bh); - return 0; + return -EAGAIN; } ret = udf_load_sequence(sb, bh, fileset); brelse(bh); return ret; } -/* Search for an anchor volume descriptor pointer */ -static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock, - struct kernel_lb_addr *fileset) +/* + * Search for an anchor volume descriptor pointer. + * + * Returns < 0 on error, 0 on success. -EAGAIN is special - try next set + * of anchors. + */ +static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock, + struct kernel_lb_addr *fileset) { sector_t last[6]; int i; struct udf_sb_info *sbi = UDF_SB(sb); int last_count = 0; + int ret; /* First try user provided anchor */ if (sbi->s_anchor) { - if (udf_check_anchor_block(sb, sbi->s_anchor, fileset)) - return lastblock; + ret = udf_check_anchor_block(sb, sbi->s_anchor, fileset); + if (ret != -EAGAIN) + return ret; } /* * according to spec, anchor is in either: @@ -1720,39 +1767,46 @@ static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock, * lastblock * however, if the disc isn't closed, it could be 512. */ - if (udf_check_anchor_block(sb, sbi->s_session + 256, fileset)) - return lastblock; + ret = udf_check_anchor_block(sb, sbi->s_session + 256, fileset); + if (ret != -EAGAIN) + return ret; /* * The trouble is which block is the last one. Drives often misreport * this so we try various possibilities. */ - last[last_count++] = lastblock; - if (lastblock >= 1) - last[last_count++] = lastblock - 1; - last[last_count++] = lastblock + 1; - if (lastblock >= 2) - last[last_count++] = lastblock - 2; - if (lastblock >= 150) - last[last_count++] = lastblock - 150; - if (lastblock >= 152) - last[last_count++] = lastblock - 152; + last[last_count++] = *lastblock; + if (*lastblock >= 1) + last[last_count++] = *lastblock - 1; + last[last_count++] = *lastblock + 1; + if (*lastblock >= 2) + last[last_count++] = *lastblock - 2; + if (*lastblock >= 150) + last[last_count++] = *lastblock - 150; + if (*lastblock >= 152) + last[last_count++] = *lastblock - 152; for (i = 0; i < last_count; i++) { if (last[i] >= sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) continue; - if (udf_check_anchor_block(sb, last[i], fileset)) - return last[i]; + ret = udf_check_anchor_block(sb, last[i], fileset); + if (ret != -EAGAIN) { + if (!ret) + *lastblock = last[i]; + return ret; + } if (last[i] < 256) continue; - if (udf_check_anchor_block(sb, last[i] - 256, fileset)) - return last[i]; + ret = udf_check_anchor_block(sb, last[i] - 256, fileset); + if (ret != -EAGAIN) { + if (!ret) + *lastblock = last[i]; + return ret; + } } /* Finally try block 512 in case media is open */ - if (udf_check_anchor_block(sb, sbi->s_session + 512, fileset)) - return last[0]; - return 0; + return udf_check_anchor_block(sb, sbi->s_session + 512, fileset); } /* @@ -1760,54 +1814,59 @@ static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock, * area specified by it. The function expects sbi->s_lastblock to be the last * block on the media. * - * Return 1 if ok, 0 if not found. - * + * Return <0 on error, 0 if anchor found. -EAGAIN is special meaning anchor + * was not found. */ static int udf_find_anchor(struct super_block *sb, struct kernel_lb_addr *fileset) { - sector_t lastblock; struct udf_sb_info *sbi = UDF_SB(sb); + sector_t lastblock = sbi->s_last_block; + int ret; - lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset); - if (lastblock) + ret = udf_scan_anchors(sb, &lastblock, fileset); + if (ret != -EAGAIN) goto out; /* No anchor found? Try VARCONV conversion of block numbers */ UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); + lastblock = udf_variable_to_fixed(sbi->s_last_block); /* Firstly, we try to not convert number of the last block */ - lastblock = udf_scan_anchors(sb, - udf_variable_to_fixed(sbi->s_last_block), - fileset); - if (lastblock) + ret = udf_scan_anchors(sb, &lastblock, fileset); + if (ret != -EAGAIN) goto out; + lastblock = sbi->s_last_block; /* Secondly, we try with converted number of the last block */ - lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset); - if (!lastblock) { + ret = udf_scan_anchors(sb, &lastblock, fileset); + if (ret < 0) { /* VARCONV didn't help. Clear it. */ UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV); - return 0; } out: - sbi->s_last_block = lastblock; - return 1; + if (ret == 0) + sbi->s_last_block = lastblock; + return ret; } /* * Check Volume Structure Descriptor, find Anchor block and load Volume - * Descriptor Sequence + * Descriptor Sequence. + * + * Returns < 0 on error, 0 on success. -EAGAIN is special meaning anchor + * block was not found. */ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, int silent, struct kernel_lb_addr *fileset) { struct udf_sb_info *sbi = UDF_SB(sb); loff_t nsr_off; + int ret; if (!sb_set_blocksize(sb, uopt->blocksize)) { if (!silent) udf_warn(sb, "Bad block size\n"); - return 0; + return -EINVAL; } sbi->s_last_block = uopt->lastblock; if (!uopt->novrs) { @@ -1828,12 +1887,13 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, /* Look for anchor block and load Volume Descriptor Sequence */ sbi->s_anchor = uopt->anchor; - if (!udf_find_anchor(sb, fileset)) { - if (!silent) + ret = udf_find_anchor(sb, fileset); + if (ret < 0) { + if (!silent && ret == -EAGAIN) udf_warn(sb, "No anchor found\n"); - return 0; + return ret; } - return 1; + return 0; } static void udf_open_lvid(struct super_block *sb) @@ -1939,7 +1999,7 @@ u64 lvid_get_unique_id(struct super_block *sb) static int udf_fill_super(struct super_block *sb, void *options, int silent) { - int ret; + int ret = -EINVAL; struct inode *inode = NULL; struct udf_options uopt; struct kernel_lb_addr rootdir, fileset; @@ -2011,7 +2071,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) } else { uopt.blocksize = bdev_logical_block_size(sb->s_bdev); ret = udf_load_vrs(sb, &uopt, silent, &fileset); - if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) { + if (ret == -EAGAIN && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) { if (!silent) pr_notice("Rescanning with blocksize %d\n", UDF_DEFAULT_BLOCKSIZE); @@ -2021,8 +2081,11 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) ret = udf_load_vrs(sb, &uopt, silent, &fileset); } } - if (!ret) { - udf_warn(sb, "No partition found (1)\n"); + if (ret < 0) { + if (ret == -EAGAIN) { + udf_warn(sb, "No partition found (1)\n"); + ret = -EINVAL; + } goto error_out; } @@ -2040,9 +2103,13 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) udf_err(sb, "minUDFReadRev=%x (max is %x)\n", le16_to_cpu(lvidiu->minUDFReadRev), UDF_MAX_READ_VERSION); + ret = -EINVAL; + goto error_out; + } else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION && + !(sb->s_flags & MS_RDONLY)) { + ret = -EACCES; goto error_out; - } else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION) - sb->s_flags |= MS_RDONLY; + } sbi->s_udfrev = minUDFWriteRev; @@ -2054,17 +2121,20 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (!sbi->s_partitions) { udf_warn(sb, "No partition found (2)\n"); + ret = -EINVAL; goto error_out; } if (sbi->s_partmaps[sbi->s_partition].s_partition_flags & - UDF_PART_FLAG_READ_ONLY) { - pr_notice("Partition marked readonly; forcing readonly mount\n"); - sb->s_flags |= MS_RDONLY; + UDF_PART_FLAG_READ_ONLY && + !(sb->s_flags & MS_RDONLY)) { + ret = -EACCES; + goto error_out; } if (udf_find_fileset(sb, &fileset, &rootdir)) { udf_warn(sb, "No fileset found\n"); + ret = -EINVAL; goto error_out; } @@ -2086,6 +2156,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (!inode) { udf_err(sb, "Error in udf_iget, block=%d, partition=%d\n", rootdir.logicalBlockNum, rootdir.partitionReferenceNum); + ret = -EIO; goto error_out; } @@ -2093,6 +2164,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) sb->s_root = d_make_root(inode); if (!sb->s_root) { udf_err(sb, "Couldn't allocate root dentry\n"); + ret = -ENOMEM; goto error_out; } sb->s_maxbytes = MAX_LFS_FILESIZE; @@ -2113,7 +2185,7 @@ error_out: kfree(sbi); sb->s_fs_info = NULL; - return -EINVAL; + return ret; } void _udf_err(struct super_block *sb, const char *function, diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index ff24e44..c8ca960 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -531,7 +531,7 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to) struct inode *inode = mapping->host; if (to > inode->i_size) - truncate_pagecache(inode, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); } static int ufs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2f9fb42..e51e581 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -86,14 +86,6 @@ xfs_destroy_ioend( bh->b_end_io(bh, !ioend->io_error); } - if (ioend->io_iocb) { - inode_dio_done(ioend->io_inode); - if (ioend->io_isasync) { - aio_complete(ioend->io_iocb, ioend->io_error ? - ioend->io_error : ioend->io_result, 0); - } - } - mempool_free(ioend, xfs_ioend_pool); } @@ -281,7 +273,6 @@ xfs_alloc_ioend( * all the I/O from calling the completion routine too early. */ atomic_set(&ioend->io_remaining, 1); - ioend->io_isasync = 0; ioend->io_isdirect = 0; ioend->io_error = 0; ioend->io_list = NULL; @@ -291,8 +282,6 @@ xfs_alloc_ioend( ioend->io_buffer_tail = NULL; ioend->io_offset = 0; ioend->io_size = 0; - ioend->io_iocb = NULL; - ioend->io_result = 0; ioend->io_append_trans = NULL; INIT_WORK(&ioend->io_work, xfs_end_io); @@ -1292,8 +1281,10 @@ __xfs_get_blocks( if (create || !ISUNWRITTEN(&imap)) xfs_map_buffer(inode, bh_result, &imap, offset); if (create && ISUNWRITTEN(&imap)) { - if (direct) + if (direct) { bh_result->b_private = inode; + set_buffer_defer_completion(bh_result); + } set_buffer_unwritten(bh_result); } } @@ -1390,9 +1381,7 @@ xfs_end_io_direct_write( struct kiocb *iocb, loff_t offset, ssize_t size, - void *private, - int ret, - bool is_async) + void *private) { struct xfs_ioend *ioend = iocb->private; @@ -1414,17 +1403,10 @@ xfs_end_io_direct_write( ioend->io_offset = offset; ioend->io_size = size; - ioend->io_iocb = iocb; - ioend->io_result = ret; if (private && size > 0) ioend->io_type = XFS_IO_UNWRITTEN; - if (is_async) { - ioend->io_isasync = 1; - xfs_finish_ioend(ioend); - } else { - xfs_finish_ioend_sync(ioend); - } + xfs_finish_ioend_sync(ioend); } STATIC ssize_t @@ -1600,7 +1582,7 @@ xfs_vm_write_begin( unlock_page(page); if (pos + len > i_size_read(inode)) - truncate_pagecache(inode, pos + len, i_size_read(inode)); + truncate_pagecache(inode, i_size_read(inode)); page_cache_release(page); page = NULL; @@ -1636,7 +1618,7 @@ xfs_vm_write_end( loff_t to = pos + len; if (to > isize) { - truncate_pagecache(inode, to, isize); + truncate_pagecache(inode, isize); xfs_vm_kill_delalloc_range(inode, isize, to); } } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index c325abb..f94dd45 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -45,7 +45,6 @@ typedef struct xfs_ioend { unsigned int io_type; /* delalloc / unwritten */ int io_error; /* I/O error code */ atomic_t io_remaining; /* hold count */ - unsigned int io_isasync : 1; /* needs aio_complete */ unsigned int io_isdirect : 1;/* direct I/O */ struct inode *io_inode; /* file being written to */ struct buffer_head *io_buffer_head;/* buffer linked list head */ @@ -54,8 +53,6 @@ typedef struct xfs_ioend { xfs_off_t io_offset; /* offset in the file */ struct work_struct io_work; /* xfsdatad work queue */ struct xfs_trans *io_append_trans;/* xact. for size update */ - struct kiocb *io_iocb; - int io_result; } xfs_ioend_t; extern const struct address_space_operations xfs_address_space_operations; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c06823f..2634700 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -81,54 +81,6 @@ xfs_buf_vmap_len( } /* - * xfs_buf_lru_add - add a buffer to the LRU. - * - * The LRU takes a new reference to the buffer so that it will only be freed - * once the shrinker takes the buffer off the LRU. - */ -STATIC void -xfs_buf_lru_add( - struct xfs_buf *bp) -{ - struct xfs_buftarg *btp = bp->b_target; - - spin_lock(&btp->bt_lru_lock); - if (list_empty(&bp->b_lru)) { - atomic_inc(&bp->b_hold); - list_add_tail(&bp->b_lru, &btp->bt_lru); - btp->bt_lru_nr++; - bp->b_lru_flags &= ~_XBF_LRU_DISPOSE; - } - spin_unlock(&btp->bt_lru_lock); -} - -/* - * xfs_buf_lru_del - remove a buffer from the LRU - * - * The unlocked check is safe here because it only occurs when there are not - * b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there - * to optimise the shrinker removing the buffer from the LRU and calling - * xfs_buf_free(). i.e. it removes an unnecessary round trip on the - * bt_lru_lock. - */ -STATIC void -xfs_buf_lru_del( - struct xfs_buf *bp) -{ - struct xfs_buftarg *btp = bp->b_target; - - if (list_empty(&bp->b_lru)) - return; - - spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru)) { - list_del_init(&bp->b_lru); - btp->bt_lru_nr--; - } - spin_unlock(&btp->bt_lru_lock); -} - -/* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer * reference count falls to zero. If the buffer is already on the LRU, we need @@ -151,20 +103,14 @@ xfs_buf_stale( */ bp->b_flags &= ~_XBF_DELWRI_Q; - atomic_set(&(bp)->b_lru_ref, 0); - if (!list_empty(&bp->b_lru)) { - struct xfs_buftarg *btp = bp->b_target; + spin_lock(&bp->b_lock); + atomic_set(&bp->b_lru_ref, 0); + if (!(bp->b_state & XFS_BSTATE_DISPOSE) && + (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru))) + atomic_dec(&bp->b_hold); - spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru) && - !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) { - list_del_init(&bp->b_lru); - btp->bt_lru_nr--; - atomic_dec(&bp->b_hold); - } - spin_unlock(&btp->bt_lru_lock); - } ASSERT(atomic_read(&bp->b_hold) >= 1); + spin_unlock(&bp->b_lock); } static int @@ -228,6 +174,7 @@ _xfs_buf_alloc( INIT_LIST_HEAD(&bp->b_list); RB_CLEAR_NODE(&bp->b_rbnode); sema_init(&bp->b_sema, 0); /* held, no waiters */ + spin_lock_init(&bp->b_lock); XB_SET_OWNER(bp); bp->b_target = target; bp->b_flags = flags; @@ -917,12 +864,33 @@ xfs_buf_rele( ASSERT(atomic_read(&bp->b_hold) > 0); if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) { - if (!(bp->b_flags & XBF_STALE) && - atomic_read(&bp->b_lru_ref)) { - xfs_buf_lru_add(bp); + spin_lock(&bp->b_lock); + if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { + /* + * If the buffer is added to the LRU take a new + * reference to the buffer for the LRU and clear the + * (now stale) dispose list state flag + */ + if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) { + bp->b_state &= ~XFS_BSTATE_DISPOSE; + atomic_inc(&bp->b_hold); + } + spin_unlock(&bp->b_lock); spin_unlock(&pag->pag_buf_lock); } else { - xfs_buf_lru_del(bp); + /* + * most of the time buffers will already be removed from + * the LRU, so optimise that case by checking for the + * XFS_BSTATE_DISPOSE flag indicating the last list the + * buffer was on was the disposal list + */ + if (!(bp->b_state & XFS_BSTATE_DISPOSE)) { + list_lru_del(&bp->b_target->bt_lru, &bp->b_lru); + } else { + ASSERT(list_empty(&bp->b_lru)); + } + spin_unlock(&bp->b_lock); + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); rb_erase(&bp->b_rbnode, &pag->pag_buf_tree); spin_unlock(&pag->pag_buf_lock); @@ -1502,83 +1470,121 @@ xfs_buf_iomove( * returned. These buffers will have an elevated hold count, so wait on those * while freeing all the buffers only held by the LRU. */ +static enum lru_status +xfs_buftarg_wait_rele( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) + +{ + struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); + struct list_head *dispose = arg; + + if (atomic_read(&bp->b_hold) > 1) { + /* need to wait, so skip it this pass */ + trace_xfs_buf_wait_buftarg(bp, _RET_IP_); + return LRU_SKIP; + } + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + + /* + * clear the LRU reference count so the buffer doesn't get + * ignored in xfs_buf_rele(). + */ + atomic_set(&bp->b_lru_ref, 0); + bp->b_state |= XFS_BSTATE_DISPOSE; + list_move(item, dispose); + spin_unlock(&bp->b_lock); + return LRU_REMOVED; +} + void xfs_wait_buftarg( struct xfs_buftarg *btp) { - struct xfs_buf *bp; + LIST_HEAD(dispose); + int loop = 0; -restart: - spin_lock(&btp->bt_lru_lock); - while (!list_empty(&btp->bt_lru)) { - bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); - if (atomic_read(&bp->b_hold) > 1) { - trace_xfs_buf_wait_buftarg(bp, _RET_IP_); - list_move_tail(&bp->b_lru, &btp->bt_lru); - spin_unlock(&btp->bt_lru_lock); - delay(100); - goto restart; + /* loop until there is nothing left on the lru list. */ + while (list_lru_count(&btp->bt_lru)) { + list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, + &dispose, LONG_MAX); + + while (!list_empty(&dispose)) { + struct xfs_buf *bp; + bp = list_first_entry(&dispose, struct xfs_buf, b_lru); + list_del_init(&bp->b_lru); + xfs_buf_rele(bp); } - /* - * clear the LRU reference count so the buffer doesn't get - * ignored in xfs_buf_rele(). - */ - atomic_set(&bp->b_lru_ref, 0); - spin_unlock(&btp->bt_lru_lock); - xfs_buf_rele(bp); - spin_lock(&btp->bt_lru_lock); + if (loop++ != 0) + delay(100); } - spin_unlock(&btp->bt_lru_lock); } -int -xfs_buftarg_shrink( +static enum lru_status +xfs_buftarg_isolate( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); + struct list_head *dispose = arg; + + /* + * we are inverting the lru lock/bp->b_lock here, so use a trylock. + * If we fail to get the lock, just skip it. + */ + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + /* + * Decrement the b_lru_ref count unless the value is already + * zero. If the value is already zero, we need to reclaim the + * buffer, otherwise it gets another trip through the LRU. + */ + if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { + spin_unlock(&bp->b_lock); + return LRU_ROTATE; + } + + bp->b_state |= XFS_BSTATE_DISPOSE; + list_move(item, dispose); + spin_unlock(&bp->b_lock); + return LRU_REMOVED; +} + +static unsigned long +xfs_buftarg_shrink_scan( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_buftarg *btp = container_of(shrink, struct xfs_buftarg, bt_shrinker); - struct xfs_buf *bp; - int nr_to_scan = sc->nr_to_scan; LIST_HEAD(dispose); + unsigned long freed; + unsigned long nr_to_scan = sc->nr_to_scan; - if (!nr_to_scan) - return btp->bt_lru_nr; - - spin_lock(&btp->bt_lru_lock); - while (!list_empty(&btp->bt_lru)) { - if (nr_to_scan-- <= 0) - break; - - bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); - - /* - * Decrement the b_lru_ref count unless the value is already - * zero. If the value is already zero, we need to reclaim the - * buffer, otherwise it gets another trip through the LRU. - */ - if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { - list_move_tail(&bp->b_lru, &btp->bt_lru); - continue; - } - - /* - * remove the buffer from the LRU now to avoid needing another - * lock round trip inside xfs_buf_rele(). - */ - list_move(&bp->b_lru, &dispose); - btp->bt_lru_nr--; - bp->b_lru_flags |= _XBF_LRU_DISPOSE; - } - spin_unlock(&btp->bt_lru_lock); + freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate, + &dispose, &nr_to_scan); while (!list_empty(&dispose)) { + struct xfs_buf *bp; bp = list_first_entry(&dispose, struct xfs_buf, b_lru); list_del_init(&bp->b_lru); xfs_buf_rele(bp); } - return btp->bt_lru_nr; + return freed; +} + +static unsigned long +xfs_buftarg_shrink_count( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_buftarg *btp = container_of(shrink, + struct xfs_buftarg, bt_shrinker); + return list_lru_count_node(&btp->bt_lru, sc->nid); } void @@ -1587,6 +1593,7 @@ xfs_free_buftarg( struct xfs_buftarg *btp) { unregister_shrinker(&btp->bt_shrinker); + list_lru_destroy(&btp->bt_lru); if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_blkdev_issue_flush(btp); @@ -1660,12 +1667,16 @@ xfs_alloc_buftarg( if (!btp->bt_bdi) goto error; - INIT_LIST_HEAD(&btp->bt_lru); - spin_lock_init(&btp->bt_lru_lock); if (xfs_setsize_buftarg_early(btp, bdev)) goto error; - btp->bt_shrinker.shrink = xfs_buftarg_shrink; + + if (list_lru_init(&btp->bt_lru)) + goto error; + + btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count; + btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; + btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; register_shrinker(&btp->bt_shrinker); return btp; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 433a12e..e656833 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -25,6 +25,7 @@ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/uio.h> +#include <linux/list_lru.h> /* * Base types @@ -59,7 +60,6 @@ typedef enum { #define _XBF_KMEM (1 << 21)/* backed by heap memory */ #define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ #define _XBF_COMPOUND (1 << 23)/* compound buffer */ -#define _XBF_LRU_DISPOSE (1 << 24)/* buffer being discarded */ typedef unsigned int xfs_buf_flags_t; @@ -78,8 +78,12 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_COMPOUND, "COMPOUND" }, \ - { _XBF_LRU_DISPOSE, "LRU_DISPOSE" } + { _XBF_COMPOUND, "COMPOUND" } + +/* + * Internal state flags. + */ +#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */ typedef struct xfs_buftarg { dev_t bt_dev; @@ -92,9 +96,7 @@ typedef struct xfs_buftarg { /* LRU control structures */ struct shrinker bt_shrinker; - struct list_head bt_lru; - spinlock_t bt_lru_lock; - unsigned int bt_lru_nr; + struct list_lru bt_lru; } xfs_buftarg_t; struct xfs_buf; @@ -137,7 +139,8 @@ typedef struct xfs_buf { * bt_lru_lock and not by b_sema */ struct list_head b_lru; /* lru list */ - xfs_buf_flags_t b_lru_flags; /* internal lru status flags */ + spinlock_t b_lock; /* internal state lock */ + unsigned int b_state; /* internal state flags */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 251c666..71520e6 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -940,13 +940,8 @@ xfs_qm_dqput_final( trace_xfs_dqput_free(dqp); - mutex_lock(&qi->qi_lru_lock); - if (list_empty(&dqp->q_lru)) { - list_add_tail(&dqp->q_lru, &qi->qi_lru_list); - qi->qi_lru_count++; + if (list_lru_add(&qi->qi_lru, &dqp->q_lru)) XFS_STATS_INC(xs_qm_dquot_unused); - } - mutex_unlock(&qi->qi_lru_lock); /* * If we just added a udquot to the freelist, then we want to release diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 7942432..193206b 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1167,7 +1167,7 @@ xfs_reclaim_inodes( * them to be cleaned, which we hope will not be very long due to the * background walker having already kicked the IO off on those dirty inodes. */ -void +long xfs_reclaim_inodes_nr( struct xfs_mount *mp, int nr_to_scan) @@ -1176,7 +1176,7 @@ xfs_reclaim_inodes_nr( xfs_reclaim_work_queue(mp); xfs_ail_push_all(mp->m_ail); - xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan); + return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan); } /* diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 458e6bc..9ed68bb 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -50,7 +50,7 @@ void xfs_reclaim_worker(struct work_struct *work); int xfs_reclaim_inodes(struct xfs_mount *mp, int mode); int xfs_reclaim_inodes_count(struct xfs_mount *mp); -void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); +long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6218a0a..3e6c2e6 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -51,8 +51,9 @@ */ STATIC int xfs_qm_init_quotainos(xfs_mount_t *); STATIC int xfs_qm_init_quotainfo(xfs_mount_t *); -STATIC int xfs_qm_shake(struct shrinker *, struct shrink_control *); + +STATIC void xfs_qm_dqfree_one(struct xfs_dquot *dqp); /* * We use the batch lookup interface to iterate over the dquots as it * currently is the only interface into the radix tree code that allows @@ -203,12 +204,9 @@ xfs_qm_dqpurge( * We move dquots to the freelist as soon as their reference count * hits zero, so it really should be on the freelist here. */ - mutex_lock(&qi->qi_lru_lock); ASSERT(!list_empty(&dqp->q_lru)); - list_del_init(&dqp->q_lru); - qi->qi_lru_count--; + list_lru_del(&qi->qi_lru, &dqp->q_lru); XFS_STATS_DEC(xs_qm_dquot_unused); - mutex_unlock(&qi->qi_lru_lock); xfs_qm_dqdestroy(dqp); @@ -680,6 +678,143 @@ xfs_qm_calc_dquots_per_chunk( return ndquots; } +struct xfs_qm_isolate { + struct list_head buffers; + struct list_head dispose; +}; + +static enum lru_status +xfs_qm_dquot_isolate( + struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct xfs_dquot *dqp = container_of(item, + struct xfs_dquot, q_lru); + struct xfs_qm_isolate *isol = arg; + + if (!xfs_dqlock_nowait(dqp)) + goto out_miss_busy; + + /* + * This dquot has acquired a reference in the meantime remove it from + * the freelist and try again. + */ + if (dqp->q_nrefs) { + xfs_dqunlock(dqp); + XFS_STATS_INC(xs_qm_dqwants); + + trace_xfs_dqreclaim_want(dqp); + list_del_init(&dqp->q_lru); + XFS_STATS_DEC(xs_qm_dquot_unused); + return LRU_REMOVED; + } + + /* + * If the dquot is dirty, flush it. If it's already being flushed, just + * skip it so there is time for the IO to complete before we try to + * reclaim it again on the next LRU pass. + */ + if (!xfs_dqflock_nowait(dqp)) { + xfs_dqunlock(dqp); + goto out_miss_busy; + } + + if (XFS_DQ_IS_DIRTY(dqp)) { + struct xfs_buf *bp = NULL; + int error; + + trace_xfs_dqreclaim_dirty(dqp); + + /* we have to drop the LRU lock to flush the dquot */ + spin_unlock(lru_lock); + + error = xfs_qm_dqflush(dqp, &bp); + if (error) { + xfs_warn(dqp->q_mount, "%s: dquot %p flush failed", + __func__, dqp); + goto out_unlock_dirty; + } + + xfs_buf_delwri_queue(bp, &isol->buffers); + xfs_buf_relse(bp); + goto out_unlock_dirty; + } + xfs_dqfunlock(dqp); + + /* + * Prevent lookups now that we are past the point of no return. + */ + dqp->dq_flags |= XFS_DQ_FREEING; + xfs_dqunlock(dqp); + + ASSERT(dqp->q_nrefs == 0); + list_move_tail(&dqp->q_lru, &isol->dispose); + XFS_STATS_DEC(xs_qm_dquot_unused); + trace_xfs_dqreclaim_done(dqp); + XFS_STATS_INC(xs_qm_dqreclaims); + return LRU_REMOVED; + +out_miss_busy: + trace_xfs_dqreclaim_busy(dqp); + XFS_STATS_INC(xs_qm_dqreclaim_misses); + return LRU_SKIP; + +out_unlock_dirty: + trace_xfs_dqreclaim_busy(dqp); + XFS_STATS_INC(xs_qm_dqreclaim_misses); + xfs_dqunlock(dqp); + spin_lock(lru_lock); + return LRU_RETRY; +} + +static unsigned long +xfs_qm_shrink_scan( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_quotainfo *qi = container_of(shrink, + struct xfs_quotainfo, qi_shrinker); + struct xfs_qm_isolate isol; + unsigned long freed; + int error; + unsigned long nr_to_scan = sc->nr_to_scan; + + if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + return 0; + + INIT_LIST_HEAD(&isol.buffers); + INIT_LIST_HEAD(&isol.dispose); + + freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol, + &nr_to_scan); + + error = xfs_buf_delwri_submit(&isol.buffers); + if (error) + xfs_warn(NULL, "%s: dquot reclaim failed", __func__); + + while (!list_empty(&isol.dispose)) { + struct xfs_dquot *dqp; + + dqp = list_first_entry(&isol.dispose, struct xfs_dquot, q_lru); + list_del_init(&dqp->q_lru); + xfs_qm_dqfree_one(dqp); + } + + return freed; +} + +static unsigned long +xfs_qm_shrink_count( + struct shrinker *shrink, + struct shrink_control *sc) +{ + struct xfs_quotainfo *qi = container_of(shrink, + struct xfs_quotainfo, qi_shrinker); + + return list_lru_count_node(&qi->qi_lru, sc->nid); +} + /* * This initializes all the quota information that's kept in the * mount structure @@ -696,11 +831,18 @@ xfs_qm_init_quotainfo( qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP); + if ((error = list_lru_init(&qinf->qi_lru))) { + kmem_free(qinf); + mp->m_quotainfo = NULL; + return error; + } + /* * See if quotainodes are setup, and if not, allocate them, * and change the superblock accordingly. */ if ((error = xfs_qm_init_quotainos(mp))) { + list_lru_destroy(&qinf->qi_lru); kmem_free(qinf); mp->m_quotainfo = NULL; return error; @@ -711,10 +853,6 @@ xfs_qm_init_quotainfo( INIT_RADIX_TREE(&qinf->qi_pquota_tree, GFP_NOFS); mutex_init(&qinf->qi_tree_lock); - INIT_LIST_HEAD(&qinf->qi_lru_list); - qinf->qi_lru_count = 0; - mutex_init(&qinf->qi_lru_lock); - /* mutex used to serialize quotaoffs */ mutex_init(&qinf->qi_quotaofflock); @@ -779,8 +917,10 @@ xfs_qm_init_quotainfo( qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT; } - qinf->qi_shrinker.shrink = xfs_qm_shake; + qinf->qi_shrinker.count_objects = xfs_qm_shrink_count; + qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan; qinf->qi_shrinker.seeks = DEFAULT_SEEKS; + qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; register_shrinker(&qinf->qi_shrinker); return 0; } @@ -801,6 +941,7 @@ xfs_qm_destroy_quotainfo( ASSERT(qi != NULL); unregister_shrinker(&qi->qi_shrinker); + list_lru_destroy(&qi->qi_lru); if (qi->qi_uquotaip) { IRELE(qi->qi_uquotaip); @@ -1599,132 +1740,6 @@ xfs_qm_dqfree_one( xfs_qm_dqdestroy(dqp); } -STATIC void -xfs_qm_dqreclaim_one( - struct xfs_dquot *dqp, - struct list_head *buffer_list, - struct list_head *dispose_list) -{ - struct xfs_mount *mp = dqp->q_mount; - struct xfs_quotainfo *qi = mp->m_quotainfo; - int error; - - if (!xfs_dqlock_nowait(dqp)) - goto out_move_tail; - - /* - * This dquot has acquired a reference in the meantime remove it from - * the freelist and try again. - */ - if (dqp->q_nrefs) { - xfs_dqunlock(dqp); - - trace_xfs_dqreclaim_want(dqp); - XFS_STATS_INC(xs_qm_dqwants); - - list_del_init(&dqp->q_lru); - qi->qi_lru_count--; - XFS_STATS_DEC(xs_qm_dquot_unused); - return; - } - - /* - * Try to grab the flush lock. If this dquot is in the process of - * getting flushed to disk, we don't want to reclaim it. - */ - if (!xfs_dqflock_nowait(dqp)) - goto out_unlock_move_tail; - - if (XFS_DQ_IS_DIRTY(dqp)) { - struct xfs_buf *bp = NULL; - - trace_xfs_dqreclaim_dirty(dqp); - - error = xfs_qm_dqflush(dqp, &bp); - if (error) { - xfs_warn(mp, "%s: dquot %p flush failed", - __func__, dqp); - goto out_unlock_move_tail; - } - - xfs_buf_delwri_queue(bp, buffer_list); - xfs_buf_relse(bp); - /* - * Give the dquot another try on the freelist, as the - * flushing will take some time. - */ - goto out_unlock_move_tail; - } - xfs_dqfunlock(dqp); - - /* - * Prevent lookups now that we are past the point of no return. - */ - dqp->dq_flags |= XFS_DQ_FREEING; - xfs_dqunlock(dqp); - - ASSERT(dqp->q_nrefs == 0); - list_move_tail(&dqp->q_lru, dispose_list); - qi->qi_lru_count--; - XFS_STATS_DEC(xs_qm_dquot_unused); - - trace_xfs_dqreclaim_done(dqp); - XFS_STATS_INC(xs_qm_dqreclaims); - return; - - /* - * Move the dquot to the tail of the list so that we don't spin on it. - */ -out_unlock_move_tail: - xfs_dqunlock(dqp); -out_move_tail: - list_move_tail(&dqp->q_lru, &qi->qi_lru_list); - trace_xfs_dqreclaim_busy(dqp); - XFS_STATS_INC(xs_qm_dqreclaim_misses); -} - -STATIC int -xfs_qm_shake( - struct shrinker *shrink, - struct shrink_control *sc) -{ - struct xfs_quotainfo *qi = - container_of(shrink, struct xfs_quotainfo, qi_shrinker); - int nr_to_scan = sc->nr_to_scan; - LIST_HEAD (buffer_list); - LIST_HEAD (dispose_list); - struct xfs_dquot *dqp; - int error; - - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) - return 0; - if (!nr_to_scan) - goto out; - - mutex_lock(&qi->qi_lru_lock); - while (!list_empty(&qi->qi_lru_list)) { - if (nr_to_scan-- <= 0) - break; - dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot, - q_lru); - xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list); - } - mutex_unlock(&qi->qi_lru_lock); - - error = xfs_buf_delwri_submit(&buffer_list); - if (error) - xfs_warn(NULL, "%s: dquot reclaim failed", __func__); - - while (!list_empty(&dispose_list)) { - dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru); - list_del_init(&dqp->q_lru); - xfs_qm_dqfree_one(dqp); - } - -out: - return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure; -} - /* * Start a transaction and write the incore superblock changes to * disk. flags parameter indicates which fields have changed. diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 670cd44..2b602df 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -49,9 +49,7 @@ typedef struct xfs_quotainfo { struct xfs_inode *qi_uquotaip; /* user quota inode */ struct xfs_inode *qi_gquotaip; /* group quota inode */ struct xfs_inode *qi_pquotaip; /* project quota inode */ - struct list_head qi_lru_list; - struct mutex qi_lru_lock; - int qi_lru_count; + struct list_lru qi_lru; int qi_dquots; time_t qi_btimelimit; /* limit for blks timer */ time_t qi_itimelimit; /* limit for inodes timer */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 979a77d..15188cc 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1535,19 +1535,21 @@ xfs_fs_mount( return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super); } -static int +static long xfs_fs_nr_cached_objects( - struct super_block *sb) + struct super_block *sb, + int nid) { return xfs_reclaim_inodes_count(XFS_M(sb)); } -static void +static long xfs_fs_free_cached_objects( struct super_block *sb, - int nr_to_scan) + long nr_to_scan, + int nid) { - xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan); + return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan); } static const struct super_operations xfs_super_operations = { |