diff options
Diffstat (limited to 'fs')
188 files changed, 5283 insertions, 3190 deletions
@@ -211,6 +211,7 @@ source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/exofs/Kconfig" source "fs/f2fs/Kconfig" +source "fs/efivarfs/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 0efd152..370b24c 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -65,6 +65,20 @@ config CORE_DUMP_DEFAULT_ELF_HEADERS This config option changes the default setting of coredump_filter seen at boot time. If unsure, say Y. +config BINFMT_SCRIPT + tristate "Kernel support for scripts starting with #!" + default y + help + Say Y here if you want to execute interpreted scripts starting with + #! followed by the path to an interpreter. + + You can build this support as a module; however, until that module + gets loaded, you cannot run scripts. Thus, if you want to load this + module from an initramfs, the portion of the initramfs before loading + this module must consist of compiled binaries only. + + Most systems will not boot if you say M or N here. If unsure, say Y. + config BINFMT_FLAT bool "Kernel support for flat binaries" depends on !MMU && (!FRV || BROKEN) diff --git a/fs/Makefile b/fs/Makefile index b691a96..4fe6df3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o super.o \ ioctl.o readdir.o select.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ - pnode.o drop_caches.o splice.o sync.o utimes.o \ + pnode.o splice.o sync.o utimes.o \ stack.o fs_struct.o statfs.o ifeq ($(CONFIG_BLOCK),y) @@ -34,10 +34,7 @@ obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o - -# binfmt_script is always there -obj-y += binfmt_script.o - +obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o @@ -49,6 +46,7 @@ obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o xattr_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_GENERIC_ACL) += generic_acl.o obj-$(CONFIG_COREDUMP) += coredump.o +obj-$(CONFIG_SYSCTL) += drop_caches.o obj-$(CONFIG_FHANDLE) += fhandle.o @@ -127,3 +125,4 @@ obj-$(CONFIG_F2FS_FS) += f2fs/ obj-y += exofs/ # Multiple modules obj-$(CONFIG_CEPH_FS) += ceph/ obj-$(CONFIG_PSTORE) += pstore/ +obj-$(CONFIG_EFIVAR_FS) += efivarfs/ @@ -1029,9 +1029,9 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent) spin_unlock(&info->ring_lock); out: - kunmap_atomic(ring); dprintk("leaving aio_read_evt: %d h%lu t%lu\n", ret, (unsigned long)ring->head, (unsigned long)ring->tail); + kunmap_atomic(ring); return ret; } @@ -1794,7 +1794,5 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, ret = read_events(ioctx, min_nr, nr, events, timeout); put_ioctx(ioctx); } - - asmlinkage_protect(5, ret, ctx_id, min_nr, nr, events, timeout); return ret; } diff --git a/fs/befs/btree.c b/fs/befs/btree.c index a66c9b1..74e397d 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -436,8 +436,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, goto error; } - if ((this_node = (befs_btree_node *) - kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) { + if ((this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) { befs_error(sb, "befs_btree_read() failed to allocate %u " "bytes of memory", sizeof (befs_btree_node)); goto error; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index b23253d..bce8769 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -62,7 +62,6 @@ static int aout_core_dump(struct coredump_params *cprm) fs = get_fs(); set_fs(KERNEL_DS); has_dumped = 1; - current->flags |= PF_DUMPCORE; strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm)); dump.u_ar0 = offsetof(struct user, regs); dump.signal = cprm->siginfo->si_signo; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 3939829..34a9771 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -803,7 +803,8 @@ static int load_elf_binary(struct linux_binprm *bprm) * follow the loader, and is not movable. */ #ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE /* Memory randomization might have been switched off - * in runtime via sysctl. + * in runtime via sysctl or explicit setting of + * personality flags. * If that is the case, retain the original non-zero * load_bias value in order to establish proper * non-randomized mappings. @@ -1137,6 +1138,7 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, goto whole; if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE)) goto whole; + return 0; } /* Do not dump I/O mapped devices or special mappings */ @@ -2090,8 +2092,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto cleanup; has_dumped = 1; - current->flags |= PF_DUMPCORE; - + fs = get_fs(); set_fs(KERNEL_DS); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 2711d99..9dac212 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1684,8 +1684,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) fill_elf_fdpic_header(elf, e_phnum); has_dumped = 1; - current->flags |= PF_DUMPCORE; - /* * Set up the notes in similar form to SVR4 core dumps made * with info from their /proc. diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 751df5e..1c740e1 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -23,6 +23,7 @@ #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/ctype.h> +#include <linux/string_helpers.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/namei.h> @@ -234,24 +235,6 @@ static char *scanarg(char *s, char del) return s; } -static int unquote(char *from) -{ - char c = 0, *s = from, *p = from; - - while ((c = *s++) != '\0') { - if (c == '\\' && *s == 'x') { - s++; - c = toupper(*s++); - *p = (c - (isdigit(c) ? '0' : 'A' - 10)) << 4; - c = toupper(*s++); - *p++ |= c - (isdigit(c) ? '0' : 'A' - 10); - continue; - } - *p++ = c; - } - return p - from; -} - static char * check_special_flags (char * sfs, Node * e) { char * p = sfs; @@ -354,8 +337,9 @@ static Node *create_entry(const char __user *buffer, size_t count) p[-1] = '\0'; if (!e->mask[0]) e->mask = NULL; - e->size = unquote(e->magic); - if (e->mask && unquote(e->mask) != e->size) + e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX); + if (e->mask && + string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto Einval; if (e->size + e->offset > BINPRM_BUF_SIZE) goto Einval; @@ -1428,8 +1428,6 @@ void bio_endio(struct bio *bio, int error) else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) error = -EIO; - trace_block_bio_complete(bio, error); - if (bio->bi_end_io) bio->bi_end_io(bio, error); } diff --git a/fs/block_dev.c b/fs/block_dev.c index aea605c..ce08de7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -551,6 +551,7 @@ struct block_device *bdgrab(struct block_device *bdev) ihold(bdev->bd_inode); return bdev; } +EXPORT_SYMBOL(bdgrab); long nr_blockdev_pages(void) { @@ -616,11 +617,9 @@ void bd_forget(struct inode *inode) struct block_device *bdev = NULL; spin_lock(&bdev_lock); - if (inode->i_bdev) { - if (!sb_is_blkdev_sb(inode->i_sb)) - bdev = inode->i_bdev; - __bd_forget(inode); - } + if (!sb_is_blkdev_sb(inode->i_sb)) + bdev = inode->i_bdev; + __bd_forget(inode); spin_unlock(&bdev_lock); if (bdev) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index ecd25a1..ca9d8f1 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -651,6 +651,8 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, if (tree_mod_dont_log(fs_info, NULL)) return 0; + __tree_mod_log_free_eb(fs_info, old_root); + ret = tree_mod_alloc(fs_info, flags, &tm); if (ret < 0) goto out; @@ -736,7 +738,7 @@ tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq) static noinline void tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, struct extent_buffer *src, unsigned long dst_offset, - unsigned long src_offset, int nr_items) + unsigned long src_offset, int nr_items, int log_removal) { int ret; int i; @@ -750,10 +752,12 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, } for (i = 0; i < nr_items; i++) { - ret = tree_mod_log_insert_key_locked(fs_info, src, - i + src_offset, - MOD_LOG_KEY_REMOVE); - BUG_ON(ret < 0); + if (log_removal) { + ret = tree_mod_log_insert_key_locked(fs_info, src, + i + src_offset, + MOD_LOG_KEY_REMOVE); + BUG_ON(ret < 0); + } ret = tree_mod_log_insert_key_locked(fs_info, dst, i + dst_offset, MOD_LOG_KEY_ADD); @@ -927,7 +931,6 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, buf, 1, 1); BUG_ON(ret); /* -ENOMEM */ } - tree_mod_log_free_eb(root->fs_info, buf); clean_tree_block(trans, root, buf); *last_ref = 1; } @@ -1046,6 +1049,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, btrfs_set_node_ptr_generation(parent, parent_slot, trans->transid); btrfs_mark_buffer_dirty(parent); + tree_mod_log_free_eb(root->fs_info, buf); btrfs_free_tree_block(trans, root, buf, parent_start, last_ref); } @@ -1750,7 +1754,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, goto enospc; } - tree_mod_log_free_eb(root->fs_info, root->node); tree_mod_log_set_root_pointer(root, child); rcu_assign_pointer(root->node, child); @@ -2995,7 +2998,7 @@ static int push_node_left(struct btrfs_trans_handle *trans, push_items = min(src_nritems - 8, push_items); tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0, - push_items); + push_items, 1); copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst_nritems), btrfs_node_key_ptr_offset(0), @@ -3066,7 +3069,7 @@ static int balance_node_right(struct btrfs_trans_handle *trans, sizeof(struct btrfs_key_ptr)); tree_mod_log_eb_copy(root->fs_info, dst, src, 0, - src_nritems - push_items, push_items); + src_nritems - push_items, push_items, 1); copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(src_nritems - push_items), @@ -3218,12 +3221,18 @@ static noinline int split_node(struct btrfs_trans_handle *trans, int mid; int ret; u32 c_nritems; + int tree_mod_log_removal = 1; c = path->nodes[level]; WARN_ON(btrfs_header_generation(c) != trans->transid); if (c == root->node) { /* trying to split the root, lets make a new one */ ret = insert_new_root(trans, root, path, level + 1); + /* + * removal of root nodes has been logged by + * tree_mod_log_set_root_pointer due to locking + */ + tree_mod_log_removal = 0; if (ret) return ret; } else { @@ -3261,7 +3270,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, (unsigned long)btrfs_header_chunk_tree_uuid(split), BTRFS_UUID_SIZE); - tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid); + tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid, + tree_mod_log_removal); copy_extent_buffer(split, c, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(mid), diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7d84651..6d19a0a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1291,6 +1291,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, 0, objectid, NULL, 0, 0, 0); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); + leaf = NULL; goto fail; } @@ -1334,11 +1335,16 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, btrfs_tree_unlock(leaf); + return root; + fail: - if (ret) - return ERR_PTR(ret); + if (leaf) { + btrfs_tree_unlock(leaf); + free_extent_buffer(leaf); + } + kfree(root); - return root; + return ERR_PTR(ret); } static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, @@ -3253,7 +3259,7 @@ void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); - if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { btrfs_free_log(NULL, root); btrfs_free_log_root_tree(NULL, fs_info); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9ac2eca..3d55123 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -257,7 +257,8 @@ static int exclude_super_stripes(struct btrfs_root *root, cache->bytes_super += stripe_len; ret = add_excluded_extent(root, cache->key.objectid, stripe_len); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { @@ -265,13 +266,17 @@ static int exclude_super_stripes(struct btrfs_root *root, ret = btrfs_rmap_block(&root->fs_info->mapping_tree, cache->key.objectid, bytenr, 0, &logical, &nr, &stripe_len); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; while (nr--) { cache->bytes_super += stripe_len; ret = add_excluded_extent(root, logical[nr], stripe_len); - BUG_ON(ret); /* -ENOMEM */ + if (ret) { + kfree(logical); + return ret; + } } kfree(logical); @@ -4438,7 +4443,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) spin_lock(&sinfo->lock); spin_lock(&block_rsv->lock); - block_rsv->size = num_bytes; + block_rsv->size = min_t(u64, num_bytes, 512 * 1024 * 1024); num_bytes = sinfo->bytes_used + sinfo->bytes_pinned + sinfo->bytes_reserved + sinfo->bytes_readonly + @@ -4793,14 +4798,49 @@ out_fail: * If the inodes csum_bytes is the same as the original * csum_bytes then we know we haven't raced with any free()ers * so we can just reduce our inodes csum bytes and carry on. - * Otherwise we have to do the normal free thing to account for - * the case that the free side didn't free up its reserve - * because of this outstanding reservation. */ - if (BTRFS_I(inode)->csum_bytes == csum_bytes) + if (BTRFS_I(inode)->csum_bytes == csum_bytes) { calc_csum_metadata_size(inode, num_bytes, 0); - else - to_free = calc_csum_metadata_size(inode, num_bytes, 0); + } else { + u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes; + u64 bytes; + + /* + * This is tricky, but first we need to figure out how much we + * free'd from any free-ers that occured during this + * reservation, so we reset ->csum_bytes to the csum_bytes + * before we dropped our lock, and then call the free for the + * number of bytes that were freed while we were trying our + * reservation. + */ + bytes = csum_bytes - BTRFS_I(inode)->csum_bytes; + BTRFS_I(inode)->csum_bytes = csum_bytes; + to_free = calc_csum_metadata_size(inode, bytes, 0); + + + /* + * Now we need to see how much we would have freed had we not + * been making this reservation and our ->csum_bytes were not + * artificially inflated. + */ + BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes; + bytes = csum_bytes - orig_csum_bytes; + bytes = calc_csum_metadata_size(inode, bytes, 0); + + /* + * Now reset ->csum_bytes to what it should be. If bytes is + * more than to_free then we would have free'd more space had we + * not had an artificially high ->csum_bytes, so we need to free + * the remainder. If bytes is the same or less then we don't + * need to do anything, the other free-ers did the correct + * thing. + */ + BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes; + if (bytes > to_free) + to_free = bytes - to_free; + else + to_free = 0; + } spin_unlock(&BTRFS_I(inode)->lock); if (dropped) to_free += btrfs_calc_trans_metadata_size(root, dropped); @@ -7947,7 +7987,17 @@ int btrfs_read_block_groups(struct btrfs_root *root) * info has super bytes accounted for, otherwise we'll think * we have more space than we actually do. */ - exclude_super_stripes(root, cache); + ret = exclude_super_stripes(root, cache); + if (ret) { + /* + * We may have excluded something, so call this just in + * case. + */ + free_excluded_extents(root, cache); + kfree(cache->free_space_ctl); + kfree(cache); + goto error; + } /* * check for two cases, either we are full, and therefore @@ -8089,7 +8139,17 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; - exclude_super_stripes(root, cache); + ret = exclude_super_stripes(root, cache); + if (ret) { + /* + * We may have excluded something, so call this just in + * case. + */ + free_excluded_extents(root, cache); + kfree(cache->free_space_ctl); + kfree(cache); + return ret; + } add_new_free_space(cache, root->fs_info, chunk_offset, chunk_offset + size); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f173c5a..cdee391 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1257,6 +1257,39 @@ int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end) GFP_NOFS); } +int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end) +{ + unsigned long index = start >> PAGE_CACHE_SHIFT; + unsigned long end_index = end >> PAGE_CACHE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + BUG_ON(!page); /* Pages should be in the extent_io_tree */ + clear_page_dirty_for_io(page); + page_cache_release(page); + index++; + } + return 0; +} + +int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) +{ + unsigned long index = start >> PAGE_CACHE_SHIFT; + unsigned long end_index = end >> PAGE_CACHE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + BUG_ON(!page); /* Pages should be in the extent_io_tree */ + account_page_redirty(page); + __set_page_dirty_nobuffers(page); + page_cache_release(page); + index++; + } + return 0; +} + /* * helper function to set both pages and extents in the tree writeback */ diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 6068a19..258c921 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -325,6 +325,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset, unsigned long *map_len); int extent_range_uptodate(struct extent_io_tree *tree, u64 start, u64 end); +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, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index ec16020..c4628a2 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -118,9 +118,11 @@ struct btrfs_csum_item *btrfs_lookup_csum(struct btrfs_trans_handle *trans, csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]); csums_in_item /= csum_size; - if (csum_offset >= csums_in_item) { + if (csum_offset == csums_in_item) { ret = -EFBIG; goto fail; + } else if (csum_offset > csums_in_item) { + goto fail; } } item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item); @@ -728,7 +730,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, return -ENOMEM; sector_sum = sums->sums; - trans->adding_csums = 1; again: next_offset = (u64)-1; found_next = 0; @@ -899,7 +900,6 @@ next_sector: goto again; } out: - trans->adding_csums = 0; btrfs_free_path(path); return ret; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 254aeb7..bb8b7a0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2139,6 +2139,7 @@ static long btrfs_fallocate(struct file *file, int mode, { struct inode *inode = file_inode(file); struct extent_state *cached_state = NULL; + struct btrfs_root *root = BTRFS_I(inode)->root; u64 cur_offset; u64 last_byte; u64 alloc_start; @@ -2166,6 +2167,11 @@ static long btrfs_fallocate(struct file *file, int mode, ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start); if (ret) return ret; + if (root->fs_info->quota_enabled) { + ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start); + if (ret) + goto out_reserve_fail; + } /* * wait for ordered IO before we have any locks. We'll loop again @@ -2269,6 +2275,9 @@ static long btrfs_fallocate(struct file *file, int mode, &cached_state, GFP_NOFS); out: mutex_unlock(&inode->i_mutex); + if (root->fs_info->quota_enabled) + btrfs_qgroup_free(root, alloc_end - alloc_start); +out_reserve_fail: /* Let go of our reservation. */ btrfs_free_reserved_data_space(inode, alloc_end - alloc_start); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ca1b767..09c58a3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -353,6 +353,7 @@ static noinline int compress_file_range(struct inode *inode, int i; int will_compress; int compress_type = root->fs_info->compress_type; + int redirty = 0; /* if this is a small write inside eof, kick off a defrag */ if ((end - start + 1) < 16 * 1024 && @@ -415,6 +416,17 @@ again: if (BTRFS_I(inode)->force_compress) compress_type = BTRFS_I(inode)->force_compress; + /* + * we need to call clear_page_dirty_for_io on each + * page in the range. Otherwise applications with the file + * mmap'd can wander in and change the page contents while + * we are compressing them. + * + * If the compression fails for any reason, we set the pages + * dirty again later on. + */ + extent_range_clear_dirty_for_io(inode, start, end); + redirty = 1; ret = btrfs_compress_pages(compress_type, inode->i_mapping, start, total_compressed, pages, @@ -554,6 +566,8 @@ cleanup_and_bail_uncompressed: __set_page_dirty_nobuffers(locked_page); /* unlocked later on in the async handlers */ } + if (redirty) + extent_range_redirty_for_io(inode, start, end); add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0, BTRFS_COMPRESS_NONE); *num_added += 1; @@ -1743,8 +1757,10 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum *sum; list_for_each_entry(sum, list, list) { + trans->adding_csums = 1; btrfs_csum_file_blocks(trans, BTRFS_I(inode)->root->fs_info->csum_root, sum); + trans->adding_csums = 0; } return 0; } @@ -3679,11 +3695,9 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir, * 1 for the dir item * 1 for the dir index * 1 for the inode ref - * 1 for the inode ref in the tree log - * 2 for the dir entries in the log * 1 for the inode */ - trans = btrfs_start_transaction(root, 8); + trans = btrfs_start_transaction(root, 5); if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC) return trans; @@ -8127,7 +8141,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, * inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items * should cover the worst case number of items we'll modify. */ - trans = btrfs_start_transaction(root, 20); + trans = btrfs_start_transaction(root, 11); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_notrans; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index dc08d77..005c45d 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -557,6 +557,7 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) INIT_LIST_HEAD(&splice); INIT_LIST_HEAD(&works); + mutex_lock(&root->fs_info->ordered_operations_mutex); spin_lock(&root->fs_info->ordered_extent_lock); list_splice_init(&root->fs_info->ordered_extents, &splice); while (!list_empty(&splice)) { @@ -600,6 +601,7 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) cond_resched(); } + mutex_unlock(&root->fs_info->ordered_operations_mutex); } /* diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5471e47..b44124d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1153,7 +1153,7 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans, ret = btrfs_find_all_roots(trans, fs_info, node->bytenr, sgn > 0 ? node->seq - 1 : node->seq, &roots); if (ret < 0) - goto out; + return ret; spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -1275,7 +1275,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans, ret = 0; unlock: spin_unlock(&fs_info->qgroup_lock); -out: ulist_free(roots); ulist_free(tmp); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 53c3501..85e072b 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -542,7 +542,6 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) eb = path->nodes[0]; ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); item_size = btrfs_item_size_nr(eb, path->slots[0]); - btrfs_release_path(path); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { do { @@ -558,7 +557,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) ret < 0 ? -1 : ref_level, ret < 0 ? -1 : ref_root); } while (ret != 1); + btrfs_release_path(path); } else { + btrfs_release_path(path); swarn.path = path; swarn.dev = dev; iterate_extent_inodes(fs_info, found_key.objectid, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index f7a8b86..c85e7c6 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3945,12 +3945,10 @@ static int is_extent_unchanged(struct send_ctx *sctx, found_key.type != key.type) { key.offset += right_len; break; - } else { - if (found_key.offset != key.offset + right_len) { - /* Should really not happen */ - ret = -EIO; - goto out; - } + } + if (found_key.offset != key.offset + right_len) { + ret = 0; + goto out; } key = found_key; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 451fad9..ef96381 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -317,6 +317,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, unsigned long src_ptr; unsigned long dst_ptr; int overwrite_root = 0; + bool inode_item = key->type == BTRFS_INODE_ITEM_KEY; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) overwrite_root = 1; @@ -326,6 +327,9 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, /* look for the key in the destination tree */ ret = btrfs_search_slot(NULL, root, key, path, 0, 0); + if (ret < 0) + return ret; + if (ret == 0) { char *src_copy; char *dst_copy; @@ -367,6 +371,30 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, return 0; } + /* + * We need to load the old nbytes into the inode so when we + * replay the extents we've logged we get the right nbytes. + */ + if (inode_item) { + struct btrfs_inode_item *item; + u64 nbytes; + + item = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_inode_item); + nbytes = btrfs_inode_nbytes(path->nodes[0], item); + item = btrfs_item_ptr(eb, slot, + struct btrfs_inode_item); + btrfs_set_inode_nbytes(eb, item, nbytes); + } + } else if (inode_item) { + struct btrfs_inode_item *item; + + /* + * New inode, set nbytes to 0 so that the nbytes comes out + * properly when we replay the extents. + */ + item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); + btrfs_set_inode_nbytes(eb, item, 0); } insert: btrfs_release_path(path); @@ -486,7 +514,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, int found_type; u64 extent_end; u64 start = key->offset; - u64 saved_nbytes; + u64 nbytes = 0; struct btrfs_file_extent_item *item; struct inode *inode = NULL; unsigned long size; @@ -496,10 +524,19 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, found_type = btrfs_file_extent_type(eb, item); if (found_type == BTRFS_FILE_EXTENT_REG || - found_type == BTRFS_FILE_EXTENT_PREALLOC) - extent_end = start + btrfs_file_extent_num_bytes(eb, item); - else if (found_type == BTRFS_FILE_EXTENT_INLINE) { + found_type == BTRFS_FILE_EXTENT_PREALLOC) { + nbytes = btrfs_file_extent_num_bytes(eb, item); + extent_end = start + nbytes; + + /* + * We don't add to the inodes nbytes if we are prealloc or a + * hole. + */ + if (btrfs_file_extent_disk_bytenr(eb, item) == 0) + nbytes = 0; + } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { size = btrfs_file_extent_inline_len(eb, item); + nbytes = btrfs_file_extent_ram_bytes(eb, item); extent_end = ALIGN(start + size, root->sectorsize); } else { ret = 0; @@ -548,7 +585,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - saved_nbytes = inode_get_bytes(inode); /* drop any overlapping extents */ ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1); BUG_ON(ret); @@ -635,7 +671,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, BUG_ON(ret); } - inode_set_bytes(inode, saved_nbytes); + inode_add_bytes(inode, nbytes); ret = btrfs_update_inode(trans, root, inode); out: if (inode) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5989a92..2854c82 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4935,7 +4935,18 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, em = lookup_extent_mapping(em_tree, chunk_start, 1); read_unlock(&em_tree->lock); - BUG_ON(!em || em->start != chunk_start); + if (!em) { + printk(KERN_ERR "btrfs: couldn't find em for chunk %Lu\n", + chunk_start); + return -EIO; + } + + if (em->start != chunk_start) { + printk(KERN_ERR "btrfs: bad chunk start, em=%Lu, wanted=%Lu\n", + em->start, chunk_start); + free_extent_map(em); + return -EIO; + } map = (struct map_lookup *)em->bdev; length = em->len; diff --git a/fs/buffer.c b/fs/buffer.c index b4dcb34..bc1fe14 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -865,8 +865,6 @@ try_again: /* Link the buffer to its page */ set_bh_page(bh, page, offset); - - init_buffer(bh, NULL, NULL); } return head; /* @@ -2949,7 +2947,7 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh) } } -int submit_bh(int rw, struct buffer_head * bh) +int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) { struct bio *bio; int ret = 0; @@ -2984,10 +2982,16 @@ int submit_bh(int rw, struct buffer_head * bh) bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; + bio->bi_flags |= bio_flags; /* Take care of bh's that straddle the end of the device */ guard_bh_eod(rw, bio, bh); + if (buffer_meta(bh)) + rw |= REQ_META; + if (buffer_prio(bh)) + rw |= REQ_PRIO; + bio_get(bio); submit_bio(rw, bio); @@ -2997,6 +3001,12 @@ int submit_bh(int rw, struct buffer_head * bh) bio_put(bio); return ret; } +EXPORT_SYMBOL_GPL(_submit_bh); + +int submit_bh(int rw, struct buffer_head *bh) +{ + return _submit_bh(rw, bh, 0); +} EXPORT_SYMBOL(submit_bh); /** diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 991c63c..21b3a29 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1575,14 +1575,24 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } break; case Opt_blank_pass: - vol->password = NULL; - break; - case Opt_pass: /* passwords have to be handled differently * to allow the character used for deliminator * to be passed within them */ + /* + * Check if this is a case where the password + * starts with a delimiter + */ + tmp_end = strchr(data, '='); + tmp_end++; + if (!(tmp_end < end && tmp_end[1] == delim)) { + /* No it is not. Set the password to NULL */ + vol->password = NULL; + break; + } + /* Yes it is. Drop down to Opt_pass below.*/ + case Opt_pass: /* Obtain the value string */ value = strchr(data, '='); value++; diff --git a/fs/compat.c b/fs/compat.c index 5058345..d0560c9 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -44,7 +44,6 @@ #include <linux/signal.h> #include <linux/poll.h> #include <linux/mm.h> -#include <linux/eventpoll.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/pagemap.h> @@ -1069,26 +1068,6 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, } #endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */ -asmlinkage long -compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32, - unsigned int nr_segs, unsigned int flags) -{ - unsigned i; - struct iovec __user *iov; - if (nr_segs > UIO_MAXIOV) - return -EINVAL; - iov = compat_alloc_user_space(nr_segs * sizeof(struct iovec)); - for (i = 0; i < nr_segs; i++) { - struct compat_iovec v; - if (get_user(v.iov_base, &iov32[i].iov_base) || - get_user(v.iov_len, &iov32[i].iov_len) || - put_user(compat_ptr(v.iov_base), &iov[i].iov_base) || - put_user(v.iov_len, &iov[i].iov_len)) - return -EFAULT; - } - return sys_vmsplice(fd, iov, nr_segs, flags); -} - /* * Exactly like fs/open.c:sys_open(), except that it doesn't set the * O_LARGEFILE flag. @@ -1474,84 +1453,6 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, return ret; } -#ifdef CONFIG_EPOLL - -asmlinkage long compat_sys_epoll_pwait(int epfd, - struct compat_epoll_event __user *events, - int maxevents, int timeout, - const compat_sigset_t __user *sigmask, - compat_size_t sigsetsize) -{ - long err; - compat_sigset_t csigmask; - sigset_t ksigmask, sigsaved; - - /* - * If the caller wants a certain signal mask to be set during the wait, - * we apply it here. - */ - if (sigmask) { - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - if (copy_from_user(&csigmask, sigmask, sizeof(csigmask))) - return -EFAULT; - sigset_from_compat(&ksigmask, &csigmask); - sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); - sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); - } - - err = sys_epoll_wait(epfd, events, maxevents, timeout); - - /* - * If we changed the signal mask, we need to restore the original one. - * In case we've got a signal while waiting, we do not restore the - * signal mask yet, and we allow do_signal() to deliver the signal on - * the way back to userspace, before the signal mask is restored. - */ - if (sigmask) { - if (err == -EINTR) { - memcpy(¤t->saved_sigmask, &sigsaved, - sizeof(sigsaved)); - set_restore_sigmask(); - } else - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - } - - return err; -} - -#endif /* CONFIG_EPOLL */ - -#ifdef CONFIG_SIGNALFD - -asmlinkage long compat_sys_signalfd4(int ufd, - const compat_sigset_t __user *sigmask, - compat_size_t sigsetsize, int flags) -{ - compat_sigset_t ss32; - sigset_t tmp; - sigset_t __user *ksigmask; - - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - if (copy_from_user(&ss32, sigmask, sizeof(ss32))) - return -EFAULT; - sigset_from_compat(&tmp, &ss32); - ksigmask = compat_alloc_user_space(sizeof(sigset_t)); - if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t))) - return -EFAULT; - - return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); -} - -asmlinkage long compat_sys_signalfd(int ufd, - const compat_sigset_t __user *sigmask, - compat_size_t sigsetsize) -{ - return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0); -} -#endif /* CONFIG_SIGNALFD */ - #ifdef CONFIG_FHANDLE /* * Exactly like fs/open.c:sys_open_by_handle_at(), except that it @@ -1563,25 +1464,3 @@ COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, return do_handle_open(mountdirfd, handle, flags); } #endif - -#ifdef __ARCH_WANT_COMPAT_SYS_SENDFILE -asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, - compat_off_t __user *offset, compat_size_t count) -{ - loff_t pos; - off_t off; - ssize_t ret; - - if (offset) { - if (unlikely(get_user(off, offset))) - return -EFAULT; - pos = off; - ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); - if (unlikely(put_user(pos, offset))) - return -EFAULT; - return ret; - } - - return do_sendfile(out_fd, in_fd, NULL, count, 0); -} -#endif /* __ARCH_WANT_COMPAT_SYS_SENDFILE */ diff --git a/fs/coredump.c b/fs/coredump.c index a987f3d..a9abe31 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -263,7 +263,6 @@ static int zap_process(struct task_struct *start, int exit_code) struct task_struct *t; int nr = 0; - start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; @@ -280,8 +279,8 @@ static int zap_process(struct task_struct *start, int exit_code) return nr; } -static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, - struct core_state *core_state, int exit_code) +static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, + struct core_state *core_state, int exit_code) { struct task_struct *g, *p; unsigned long flags; @@ -291,11 +290,16 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; nr = zap_process(tsk, exit_code); + tsk->signal->group_exit_task = tsk; + /* ignore all signals except SIGKILL, see prepare_signal() */ + tsk->signal->flags = SIGNAL_GROUP_COREDUMP; + clear_tsk_thread_flag(tsk, TIF_SIGPENDING); } spin_unlock_irq(&tsk->sighand->siglock); if (unlikely(nr < 0)) return nr; + tsk->flags = PF_DUMPCORE; if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* @@ -340,6 +344,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (unlikely(p->mm == mm)) { lock_task_sighand(p, &flags); nr += zap_process(p, exit_code); + p->signal->flags = SIGNAL_GROUP_EXIT; unlock_task_sighand(p, &flags); } break; @@ -386,11 +391,18 @@ static int coredump_wait(int exit_code, struct core_state *core_state) return core_waiters; } -static void coredump_finish(struct mm_struct *mm) +static void coredump_finish(struct mm_struct *mm, bool core_dumped) { struct core_thread *curr, *next; struct task_struct *task; + spin_lock_irq(¤t->sighand->siglock); + if (core_dumped && !__fatal_signal_pending(current)) + current->signal->group_exit_code |= 0x80; + current->signal->group_exit_task = NULL; + current->signal->flags = SIGNAL_GROUP_EXIT; + spin_unlock_irq(¤t->sighand->siglock); + next = mm->core_state->dumper.next; while ((curr = next) != NULL) { next = curr->next; @@ -407,6 +419,17 @@ static void coredump_finish(struct mm_struct *mm) mm->core_state = NULL; } +static bool dump_interrupted(void) +{ + /* + * SIGKILL or freezing() interrupt the coredumping. Perhaps we + * can do try_to_freeze() and check __fatal_signal_pending(), + * but then we need to teach dump_write() to restart and clear + * TIF_SIGPENDING. + */ + return signal_pending(current); +} + static void wait_for_dump_helpers(struct file *file) { struct pipe_inode_info *pipe = file->private_data; @@ -414,17 +437,20 @@ static void wait_for_dump_helpers(struct file *file) pipe_lock(pipe); pipe->readers++; pipe->writers--; + wake_up_interruptible_sync(&pipe->wait); + kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); + pipe_unlock(pipe); - while ((pipe->readers > 1) && (!signal_pending(current))) { - wake_up_interruptible_sync(&pipe->wait); - kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); - pipe_wait(pipe); - } + /* + * We actually want wait_event_freezable() but then we need + * to clear TIF_SIGPENDING and improve dump_interrupted(). + */ + wait_event_interruptible(pipe->wait, pipe->readers == 1); + pipe_lock(pipe); pipe->readers--; pipe->writers++; pipe_unlock(pipe); - } /* @@ -469,6 +495,7 @@ void do_coredump(siginfo_t *siginfo) int ispipe; struct files_struct *displaced; bool need_nonrelative = false; + bool core_dumped = false; static atomic_t core_dump_count = ATOMIC_INIT(0); struct coredump_params cprm = { .siginfo = siginfo, @@ -512,17 +539,12 @@ void do_coredump(siginfo_t *siginfo) old_cred = override_creds(cred); - /* - * Clear any false indication of pending signals that might - * be seen by the filesystem code called to write the core file. - */ - clear_thread_flag(TIF_SIGPENDING); - ispipe = format_corename(&cn, &cprm); - if (ispipe) { + if (ispipe) { int dump_count; char **helper_argv; + struct subprocess_info *sub_info; if (ispipe < 0) { printk(KERN_WARNING "format_corename failed\n"); @@ -569,15 +591,20 @@ void do_coredump(siginfo_t *siginfo) goto fail_dropcount; } - retval = call_usermodehelper_fns(helper_argv[0], helper_argv, - NULL, UMH_WAIT_EXEC, umh_pipe_setup, - NULL, &cprm); + retval = -ENOMEM; + sub_info = call_usermodehelper_setup(helper_argv[0], + helper_argv, NULL, GFP_KERNEL, + umh_pipe_setup, NULL, &cprm); + if (sub_info) + retval = call_usermodehelper_exec(sub_info, + UMH_WAIT_EXEC); + argv_free(helper_argv); if (retval) { - printk(KERN_INFO "Core dump to %s pipe failed\n", + printk(KERN_INFO "Core dump to %s pipe failed\n", cn.corename); goto close_fail; - } + } } else { struct inode *inode; @@ -628,9 +655,7 @@ void do_coredump(siginfo_t *siginfo) if (displaced) put_files_struct(displaced); file_start_write(cprm.file); - retval = binfmt->core_dump(&cprm); - if (retval) - current->signal->group_exit_code |= 0x80; + core_dumped = !dump_interrupted() && binfmt->core_dump(&cprm); file_end_write(cprm.file); if (ispipe && core_pipe_limit) @@ -644,7 +669,7 @@ fail_dropcount: fail_unlock: kfree(cn.corename); fail_corename: - coredump_finish(mm); + coredump_finish(mm, core_dumped); revert_creds(old_cred); fail_creds: put_cred(cred); @@ -659,7 +684,9 @@ fail: */ int dump_write(struct file *file, const void *addr, int nr) { - return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr; + return !dump_interrupted() && + access_ok(VERIFY_READ, addr, nr) && + file->f_op->write(file, addr, nr, &file->f_pos) == nr; } EXPORT_SYMBOL(dump_write); @@ -668,7 +695,8 @@ int dump_seek(struct file *file, loff_t off) int ret = 1; if (file->f_op->llseek && file->f_op->llseek != no_llseek) { - if (file->f_op->llseek(file, off, SEEK_CUR) < 0) + if (dump_interrupted() || + file->f_op->llseek(file, off, SEEK_CUR) < 0) return 0; } else { char *buf = (char *)get_zeroed_page(GFP_KERNEL); diff --git a/fs/dcache.c b/fs/dcache.c index e8bc342..e689268 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1230,8 +1230,10 @@ void shrink_dcache_parent(struct dentry * parent) LIST_HEAD(dispose); int found; - while ((found = select_parent(parent, &dispose)) != 0) + while ((found = select_parent(parent, &dispose)) != 0) { shrink_dentry_list(&dispose); + cond_resched(); + } } EXPORT_SYMBOL(shrink_dcache_parent); diff --git a/fs/dcookies.c b/fs/dcookies.c index 17c7799..ab5954b 100644 --- a/fs/dcookies.c +++ b/fs/dcookies.c @@ -25,6 +25,7 @@ #include <linux/dcookies.h> #include <linux/mutex.h> #include <linux/path.h> +#include <linux/compat.h> #include <asm/uaccess.h> /* The dcookies are allocated from a kmem_cache and @@ -145,7 +146,7 @@ out: /* And here is where the userspace process can look up the cookie value * to retrieve the path. */ -SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len) +SYSCALL_DEFINE3(lookup_dcookie, u64, cookie64, char __user *, buf, size_t, len) { unsigned long cookie = (unsigned long)cookie64; int err = -EINVAL; @@ -201,12 +202,16 @@ out: mutex_unlock(&dcookie_mutex); return err; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_lookup_dcookie(u64 cookie64, long buf, long len) + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, size_t, len) { - return SYSC_lookup_dcookie(cookie64, (char __user *) buf, (size_t) len); +#ifdef __BIG_ENDIAN + return sys_lookup_dcookie(((u64)w0 << 32) | w1, buf, len); +#else + return sys_lookup_dcookie(((u64)w1 << 32) | w0, buf, len); +#endif } -SYSCALL_ALIAS(sys_lookup_dcookie, SyS_lookup_dcookie); #endif static int dcookie_init(void) diff --git a/fs/direct-io.c b/fs/direct-io.c index f853263..cfb816d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -672,12 +672,6 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio, if (sdio->final_block_in_bio != sdio->cur_page_block || cur_offset != bio_next_offset) dio_bio_submit(dio, sdio); - /* - * Submit now if the underlying fs is about to perform a - * metadata read - */ - else if (sdio->boundary) - dio_bio_submit(dio, sdio); } if (sdio->bio == NULL) { @@ -737,16 +731,6 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits) == blocknr) { sdio->cur_page_len += len; - - /* - * If sdio->boundary then we want to schedule the IO now to - * avoid metadata seeks. - */ - if (sdio->boundary) { - ret = dio_send_cur_page(dio, sdio, map_bh); - page_cache_release(sdio->cur_page); - sdio->cur_page = NULL; - } goto out; } @@ -758,7 +742,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, page_cache_release(sdio->cur_page); sdio->cur_page = NULL; if (ret) - goto out; + return ret; } page_cache_get(page); /* It is in dio */ @@ -768,6 +752,16 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, sdio->cur_page_block = blocknr; sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits; out: + /* + * If sdio->boundary then we want to schedule the IO now to + * avoid metadata seeks. + */ + if (sdio->boundary) { + ret = dio_send_cur_page(dio, sdio, map_bh); + dio_bio_submit(dio, sdio); + page_cache_release(sdio->cur_page); + sdio->cur_page = NULL; + } return ret; } @@ -969,7 +963,8 @@ do_holes: this_chunk_bytes = this_chunk_blocks << blkbits; BUG_ON(this_chunk_bytes == 0); - sdio->boundary = buffer_boundary(map_bh); + if (this_chunk_blocks == sdio->blocks_available) + sdio->boundary = buffer_boundary(map_bh); ret = submit_page_section(dio, sdio, page, offset_in_page, this_chunk_bytes, diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 4f5ad24..d0ccd2f 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -52,8 +52,8 @@ #include <linux/mutex.h> #include <linux/sctp.h> #include <linux/slab.h> +#include <linux/sctp.h> #include <net/sctp/sctp.h> -#include <net/sctp/user.h> #include <net/ipv6.h> #include "dlm_internal.h" diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 01fd5c1..f704458 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -247,6 +247,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct dlm_ls *ls; struct plock_op *op; int rv; + unsigned char fl_flags = fl->fl_flags; ls = dlm_find_lockspace_local(lockspace); if (!ls) @@ -258,9 +259,18 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, goto out; } - if (posix_lock_file_wait(file, fl) < 0) - log_error(ls, "dlm_posix_unlock: vfs unlock error %llx", - (unsigned long long)number); + /* cause the vfs unlock to return ENOENT if lock is not found */ + fl->fl_flags |= FL_EXISTS; + + rv = posix_lock_file_wait(file, fl); + if (rv == -ENOENT) { + rv = 0; + goto out_free; + } + if (rv < 0) { + log_error(ls, "dlm_posix_unlock: vfs unlock error %d %llx", + rv, (unsigned long long)number); + } op->info.optype = DLM_PLOCK_OP_UNLOCK; op->info.pid = fl->fl_pid; @@ -296,9 +306,11 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, if (rv == -ENOENT) rv = 0; +out_free: kfree(op); out: dlm_put_lockspace(ls); + fl->fl_flags = fl_flags; return rv; } EXPORT_SYMBOL_GPL(dlm_posix_unlock); diff --git a/fs/efivarfs/Kconfig b/fs/efivarfs/Kconfig new file mode 100644 index 0000000..367bbb1 --- /dev/null +++ b/fs/efivarfs/Kconfig @@ -0,0 +1,12 @@ +config EFIVAR_FS + tristate "EFI Variable filesystem" + depends on EFI + help + efivarfs is a replacement filesystem for the old EFI + variable support via sysfs, as it doesn't suffer from the + same 1024-byte variable size limit. + + To compile this file system support as a module, choose M + here. The module will be called efivarfs. + + If unsure, say N. diff --git a/fs/efivarfs/Makefile b/fs/efivarfs/Makefile new file mode 100644 index 0000000..955d478 --- /dev/null +++ b/fs/efivarfs/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the efivarfs filesystem +# + +obj-$(CONFIG_EFIVAR_FS) += efivarfs.o + +efivarfs-objs := inode.o file.o super.o diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c new file mode 100644 index 0000000..bfb5315 --- /dev/null +++ b/fs/efivarfs/file.c @@ -0,0 +1,106 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.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. + */ + +#include <linux/efi.h> +#include <linux/fs.h> +#include <linux/slab.h> + +#include "internal.h" + +static ssize_t efivarfs_file_write(struct file *file, + const char __user *userbuf, size_t count, loff_t *ppos) +{ + struct efivar_entry *var = file->private_data; + void *data; + u32 attributes; + struct inode *inode = file->f_mapping->host; + unsigned long datasize = count - sizeof(attributes); + ssize_t bytes = 0; + bool set = false; + + if (count < sizeof(attributes)) + return -EINVAL; + + if (copy_from_user(&attributes, userbuf, sizeof(attributes))) + return -EFAULT; + + if (attributes & ~(EFI_VARIABLE_MASK)) + return -EINVAL; + + data = kmalloc(datasize, GFP_KERNEL); + if (!data) + return -ENOMEM; + + if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) { + bytes = -EFAULT; + goto out; + } + + bytes = efivar_entry_set_get_size(var, attributes, &datasize, + data, &set); + if (!set && bytes) + goto out; + + if (bytes == -ENOENT) { + drop_nlink(inode); + d_delete(file->f_dentry); + dput(file->f_dentry); + } else { + mutex_lock(&inode->i_mutex); + i_size_write(inode, datasize + sizeof(attributes)); + mutex_unlock(&inode->i_mutex); + } + + bytes = count; + +out: + kfree(data); + + return bytes; +} + +static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct efivar_entry *var = file->private_data; + unsigned long datasize = 0; + u32 attributes; + void *data; + ssize_t size = 0; + int err; + + err = efivar_entry_size(var, &datasize); + if (err) + return err; + + data = kmalloc(datasize + sizeof(attributes), GFP_KERNEL); + + if (!data) + return -ENOMEM; + + size = efivar_entry_get(var, &attributes, &datasize, + data + sizeof(attributes)); + if (size) + goto out_free; + + memcpy(data, &attributes, sizeof(attributes)); + size = simple_read_from_buffer(userbuf, count, ppos, + data, datasize + sizeof(attributes)); +out_free: + kfree(data); + + return size; +} + +const struct file_operations efivarfs_file_operations = { + .open = simple_open, + .read = efivarfs_file_read, + .write = efivarfs_file_write, + .llseek = no_llseek, +}; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c new file mode 100644 index 0000000..7e787fb --- /dev/null +++ b/fs/efivarfs/inode.c @@ -0,0 +1,174 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.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. + */ + +#include <linux/efi.h> +#include <linux/fs.h> +#include <linux/ctype.h> +#include <linux/slab.h> + +#include "internal.h" + +struct inode *efivarfs_get_inode(struct super_block *sb, + const struct inode *dir, int mode, dev_t dev) +{ + struct inode *inode = new_inode(sb); + + if (inode) { + inode->i_ino = get_next_ino(); + inode->i_mode = mode; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + switch (mode & S_IFMT) { + case S_IFREG: + inode->i_fop = &efivarfs_file_operations; + break; + case S_IFDIR: + inode->i_op = &efivarfs_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + inc_nlink(inode); + break; + } + } + return inode; +} + +/* + * Return true if 'str' is a valid efivarfs filename of the form, + * + * VariableName-12345678-1234-1234-1234-1234567891bc + */ +bool efivarfs_valid_name(const char *str, int len) +{ + static const char dashes[EFI_VARIABLE_GUID_LEN] = { + [8] = 1, [13] = 1, [18] = 1, [23] = 1 + }; + const char *s = str + len - EFI_VARIABLE_GUID_LEN; + int i; + + /* + * We need a GUID, plus at least one letter for the variable name, + * plus the '-' separator + */ + if (len < EFI_VARIABLE_GUID_LEN + 2) + return false; + + /* GUID must be preceded by a '-' */ + if (*(s - 1) != '-') + return false; + + /* + * Validate that 's' is of the correct format, e.g. + * + * 12345678-1234-1234-1234-123456789abc + */ + for (i = 0; i < EFI_VARIABLE_GUID_LEN; i++) { + if (dashes[i]) { + if (*s++ != '-') + return false; + } else { + if (!isxdigit(*s++)) + return false; + } + } + + return true; +} + +static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) +{ + guid->b[0] = hex_to_bin(str[6]) << 4 | hex_to_bin(str[7]); + guid->b[1] = hex_to_bin(str[4]) << 4 | hex_to_bin(str[5]); + guid->b[2] = hex_to_bin(str[2]) << 4 | hex_to_bin(str[3]); + guid->b[3] = hex_to_bin(str[0]) << 4 | hex_to_bin(str[1]); + guid->b[4] = hex_to_bin(str[11]) << 4 | hex_to_bin(str[12]); + guid->b[5] = hex_to_bin(str[9]) << 4 | hex_to_bin(str[10]); + guid->b[6] = hex_to_bin(str[16]) << 4 | hex_to_bin(str[17]); + guid->b[7] = hex_to_bin(str[14]) << 4 | hex_to_bin(str[15]); + guid->b[8] = hex_to_bin(str[19]) << 4 | hex_to_bin(str[20]); + guid->b[9] = hex_to_bin(str[21]) << 4 | hex_to_bin(str[22]); + guid->b[10] = hex_to_bin(str[24]) << 4 | hex_to_bin(str[25]); + guid->b[11] = hex_to_bin(str[26]) << 4 | hex_to_bin(str[27]); + guid->b[12] = hex_to_bin(str[28]) << 4 | hex_to_bin(str[29]); + guid->b[13] = hex_to_bin(str[30]) << 4 | hex_to_bin(str[31]); + guid->b[14] = hex_to_bin(str[32]) << 4 | hex_to_bin(str[33]); + guid->b[15] = hex_to_bin(str[34]) << 4 | hex_to_bin(str[35]); +} + +static int efivarfs_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool excl) +{ + struct inode *inode; + struct efivar_entry *var; + int namelen, i = 0, err = 0; + + if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) + return -EINVAL; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); + if (!inode) + return -ENOMEM; + + var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); + if (!var) { + err = -ENOMEM; + goto out; + } + + /* length of the variable name itself: remove GUID and separator */ + namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; + + efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, + &var->var.VendorGuid); + + for (i = 0; i < namelen; i++) + var->var.VariableName[i] = dentry->d_name.name[i]; + + var->var.VariableName[i] = '\0'; + + inode->i_private = var; + + efivar_entry_add(var, &efivarfs_list); + d_instantiate(dentry, inode); + dget(dentry); +out: + if (err) { + kfree(var); + iput(inode); + } + return err; +} + +static int efivarfs_unlink(struct inode *dir, struct dentry *dentry) +{ + struct efivar_entry *var = dentry->d_inode->i_private; + + if (efivar_entry_delete(var)) + return -EINVAL; + + drop_nlink(dentry->d_inode); + dput(dentry); + return 0; +}; + +/* + * Handle negative dentry. + */ +static struct dentry *efivarfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + if (dentry->d_name.len > NAME_MAX) + return ERR_PTR(-ENAMETOOLONG); + d_add(dentry, NULL); + return NULL; +} + +const struct inode_operations efivarfs_dir_inode_operations = { + .lookup = efivarfs_lookup, + .unlink = efivarfs_unlink, + .create = efivarfs_create, +}; diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h new file mode 100644 index 0000000..b5ff16a --- /dev/null +++ b/fs/efivarfs/internal.h @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.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. + */ +#ifndef EFIVAR_FS_INTERNAL_H +#define EFIVAR_FS_INTERNAL_H + +#include <linux/list.h> + +extern const struct file_operations efivarfs_file_operations; +extern const struct inode_operations efivarfs_dir_inode_operations; +extern bool efivarfs_valid_name(const char *str, int len); +extern struct inode *efivarfs_get_inode(struct super_block *sb, + const struct inode *dir, int mode, dev_t dev); + +extern struct list_head efivarfs_list; + +#endif /* EFIVAR_FS_INTERNAL_H */ diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c new file mode 100644 index 0000000..141aee3 --- /dev/null +++ b/fs/efivarfs/super.c @@ -0,0 +1,270 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.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. + */ + +#include <linux/ctype.h> +#include <linux/efi.h> +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/pagemap.h> +#include <linux/ucs2_string.h> +#include <linux/slab.h> +#include <linux/magic.h> + +#include "internal.h" + +LIST_HEAD(efivarfs_list); + +static void efivarfs_evict_inode(struct inode *inode) +{ + clear_inode(inode); +} + +static const struct super_operations efivarfs_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .evict_inode = efivarfs_evict_inode, + .show_options = generic_show_options, +}; + +static struct super_block *efivarfs_sb; + +/* + * Compare two efivarfs file names. + * + * An efivarfs filename is composed of two parts, + * + * 1. A case-sensitive variable name + * 2. A case-insensitive GUID + * + * So we need to perform a case-sensitive match on part 1 and a + * case-insensitive match on part 2. + */ +static int efivarfs_d_compare(const struct dentry *parent, const struct inode *pinode, + const struct dentry *dentry, const struct inode *inode, + unsigned int len, const char *str, + const struct qstr *name) +{ + int guid = len - EFI_VARIABLE_GUID_LEN; + + if (name->len != len) + return 1; + + /* Case-sensitive compare for the variable name */ + if (memcmp(str, name->name, guid)) + return 1; + + /* Case-insensitive compare for the GUID */ + return strncasecmp(name->name + guid, str + guid, EFI_VARIABLE_GUID_LEN); +} + +static int efivarfs_d_hash(const struct dentry *dentry, + const struct inode *inode, struct qstr *qstr) +{ + unsigned long hash = init_name_hash(); + const unsigned char *s = qstr->name; + unsigned int len = qstr->len; + + if (!efivarfs_valid_name(s, len)) + return -EINVAL; + + while (len-- > EFI_VARIABLE_GUID_LEN) + hash = partial_name_hash(*s++, hash); + + /* GUID is case-insensitive. */ + while (len--) + hash = partial_name_hash(tolower(*s++), hash); + + qstr->hash = end_name_hash(hash); + return 0; +} + +/* + * Retaining negative dentries for an in-memory filesystem just wastes + * memory and lookup time: arrange for them to be deleted immediately. + */ +static int efivarfs_delete_dentry(const struct dentry *dentry) +{ + return 1; +} + +static struct dentry_operations efivarfs_d_ops = { + .d_compare = efivarfs_d_compare, + .d_hash = efivarfs_d_hash, + .d_delete = efivarfs_delete_dentry, +}; + +static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name) +{ + struct dentry *d; + struct qstr q; + int err; + + q.name = name; + q.len = strlen(name); + + err = efivarfs_d_hash(NULL, NULL, &q); + if (err) + return ERR_PTR(err); + + d = d_alloc(parent, &q); + if (d) + return d; + + return ERR_PTR(-ENOMEM); +} + +static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, + unsigned long name_size, void *data) +{ + struct super_block *sb = (struct super_block *)data; + struct efivar_entry *entry; + struct inode *inode = NULL; + struct dentry *dentry, *root = sb->s_root; + unsigned long size = 0; + char *name; + int len, i; + int err = -ENOMEM; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return err; + + memcpy(entry->var.VariableName, name16, name_size); + memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); + + len = ucs2_strlen(entry->var.VariableName); + + /* name, plus '-', plus GUID, plus NUL*/ + name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); + if (!name) + goto fail; + + for (i = 0; i < len; i++) + name[i] = entry->var.VariableName[i] & 0xFF; + + name[len] = '-'; + + efi_guid_unparse(&entry->var.VendorGuid, name + len + 1); + + name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; + + inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0); + if (!inode) + goto fail_name; + + dentry = efivarfs_alloc_dentry(root, name); + if (IS_ERR(dentry)) { + err = PTR_ERR(dentry); + goto fail_inode; + } + + /* copied by the above to local storage in the dentry. */ + kfree(name); + + efivar_entry_size(entry, &size); + efivar_entry_add(entry, &efivarfs_list); + + mutex_lock(&inode->i_mutex); + inode->i_private = entry; + i_size_write(inode, size + sizeof(entry->var.Attributes)); + mutex_unlock(&inode->i_mutex); + d_add(dentry, inode); + + return 0; + +fail_inode: + iput(inode); +fail_name: + kfree(name); +fail: + kfree(entry); + return err; +} + +static int efivarfs_destroy(struct efivar_entry *entry, void *data) +{ + efivar_entry_remove(entry); + kfree(entry); + return 0; +} + +static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) +{ + struct inode *inode = NULL; + struct dentry *root; + int err; + + efivarfs_sb = sb; + + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_magic = EFIVARFS_MAGIC; + sb->s_op = &efivarfs_ops; + sb->s_d_op = &efivarfs_d_ops; + sb->s_time_gran = 1; + + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + if (!inode) + return -ENOMEM; + inode->i_op = &efivarfs_dir_inode_operations; + + root = d_make_root(inode); + sb->s_root = root; + if (!root) + return -ENOMEM; + + INIT_LIST_HEAD(&efivarfs_list); + + err = efivar_init(efivarfs_callback, (void *)sb, false, + true, &efivarfs_list); + if (err) + __efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL); + + return err; +} + +static struct dentry *efivarfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return mount_single(fs_type, flags, data, efivarfs_fill_super); +} + +static void efivarfs_kill_sb(struct super_block *sb) +{ + kill_litter_super(sb); + efivarfs_sb = NULL; + + /* Remove all entries and destroy */ + __efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL); +} + +static struct file_system_type efivarfs_type = { + .name = "efivarfs", + .mount = efivarfs_mount, + .kill_sb = efivarfs_kill_sb, +}; + +static __init int efivarfs_init(void) +{ + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + + if (!efivars_kobject()) + return 0; + + return register_filesystem(&efivarfs_type); +} + +MODULE_AUTHOR("Matthew Garrett, Jeremy Kerr"); +MODULE_DESCRIPTION("EFI Variable Filesystem"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_FS("efivarfs"); + +module_init(efivarfs_init); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9fec183..deecc72 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -40,6 +40,7 @@ #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/compat.h> /* * LOCKING: @@ -104,7 +105,7 @@ struct epoll_filefd { struct file *file; int fd; -}; +} __packed; /* * Structure used to track possible nested calls, for too deep recursions @@ -128,6 +129,8 @@ struct nested_calls { /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. + * Avoid increasing the size of this struct, there can be many thousands + * of these on a server and we do not want this to take another cache line. */ struct epitem { /* RB tree node used to link this structure to the eventpoll RB tree */ @@ -158,7 +161,7 @@ struct epitem { struct list_head fllink; /* wakeup_source used when EPOLLWAKEUP is set */ - struct wakeup_source *ws; + struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; @@ -536,6 +539,38 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) } } +/* call only when ep->mtx is held */ +static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) +{ + return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); +} + +/* call only when ep->mtx is held */ +static inline void ep_pm_stay_awake(struct epitem *epi) +{ + struct wakeup_source *ws = ep_wakeup_source(epi); + + if (ws) + __pm_stay_awake(ws); +} + +static inline bool ep_has_wakeup_source(struct epitem *epi) +{ + return rcu_access_pointer(epi->ws) ? true : false; +} + +/* call when ep->mtx cannot be held (ep_poll_callback) */ +static inline void ep_pm_stay_awake_rcu(struct epitem *epi) +{ + struct wakeup_source *ws; + + rcu_read_lock(); + ws = rcu_dereference(epi->ws); + if (ws) + __pm_stay_awake(ws); + rcu_read_unlock(); +} + /** * ep_scan_ready_list - Scans the ready list in a way that makes possible for * the scan code, to call f_op->poll(). Also allows for @@ -599,7 +634,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, */ if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); } } /* @@ -668,7 +703,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) list_del_init(&epi->rdllink); spin_unlock_irqrestore(&ep->lock, flags); - wakeup_source_unregister(epi->ws); + wakeup_source_unregister(ep_wakeup_source(epi)); /* At this point it is safe to free the eventpoll item */ kmem_cache_free(epi_cache, epi); @@ -711,11 +746,15 @@ static void ep_free(struct eventpoll *ep) * point we are sure no poll callbacks will be lingering around, and also by * holding "epmutex" we can be sure that no file cleanup code will hit * us during this operation. So we can avoid the lock on "ep->lock". + * We do not need to lock ep->mtx, either, we only do it to prevent + * a lockdep warning. */ + mutex_lock(&ep->mtx); while ((rbp = rb_first(&ep->rbr)) != NULL) { epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); } + mutex_unlock(&ep->mtx); mutex_unlock(&epmutex); mutex_destroy(&ep->mtx); @@ -734,6 +773,13 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file) return 0; } +static inline unsigned int ep_item_poll(struct epitem *epi, poll_table *pt) +{ + pt->_key = epi->event.events; + + return epi->ffd.file->f_op->poll(epi->ffd.file, pt) & epi->event.events; +} + static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv) { @@ -741,10 +787,9 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, poll_table pt; init_poll_funcptr(&pt, NULL); + list_for_each_entry_safe(epi, tmp, head, rdllink) { - pt._key = epi->event.events; - if (epi->ffd.file->f_op->poll(epi->ffd.file, &pt) & - epi->event.events) + if (ep_item_poll(epi, &pt)) return POLLIN | POLLRDNORM; else { /* @@ -752,7 +797,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ - __pm_relax(epi->ws); + __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } @@ -984,7 +1029,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k /* If this file is already in the ready list we exit soon */ if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake_rcu(epi); } /* @@ -1146,6 +1191,7 @@ static int reverse_path_check(void) static int ep_create_wakeup_source(struct epitem *epi) { const char *name; + struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register("eventpoll"); @@ -1154,17 +1200,29 @@ static int ep_create_wakeup_source(struct epitem *epi) } name = epi->ffd.file->f_path.dentry->d_name.name; - epi->ws = wakeup_source_register(name); - if (!epi->ws) + ws = wakeup_source_register(name); + + if (!ws) return -ENOMEM; + rcu_assign_pointer(epi->ws, ws); return 0; } -static void ep_destroy_wakeup_source(struct epitem *epi) +/* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ +static noinline void ep_destroy_wakeup_source(struct epitem *epi) { - wakeup_source_unregister(epi->ws); - epi->ws = NULL; + struct wakeup_source *ws = ep_wakeup_source(epi); + + RCU_INIT_POINTER(epi->ws, NULL); + + /* + * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is + * used internally by wakeup_source_remove, too (called by + * wakeup_source_unregister), so we cannot use call_rcu + */ + synchronize_rcu(); + wakeup_source_unregister(ws); } /* @@ -1199,13 +1257,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, if (error) goto error_create_wakeup_source; } else { - epi->ws = NULL; + RCU_INIT_POINTER(epi->ws, NULL); } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); - epq.pt._key = event->events; /* * Attach the item to the poll hooks and get current event bits. @@ -1214,7 +1271,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, * this operation completes, the poll callback can start hitting * the new item. */ - revents = tfile->f_op->poll(tfile, &epq.pt); + revents = ep_item_poll(epi, &epq.pt); /* * We have to check if something went wrong during the poll wait queue @@ -1247,7 +1304,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* If the file is already "ready" we drop it inside the ready list */ if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1288,7 +1345,7 @@ error_unregister: list_del_init(&epi->rdllink); spin_unlock_irqrestore(&ep->lock, flags); - wakeup_source_unregister(epi->ws); + wakeup_source_unregister(ep_wakeup_source(epi)); error_create_wakeup_source: kmem_cache_free(epi_cache, epi); @@ -1314,12 +1371,11 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ - pt._key = event->events; epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { - if (!epi->ws) + if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); - } else if (epi->ws) { + } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } @@ -1347,7 +1403,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. */ - revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt); + revents = ep_item_poll(epi, &pt); /* * If the item is "hot" and it is not registered inside the ready @@ -1357,7 +1413,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even spin_lock_irq(&ep->lock); if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1383,6 +1439,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, unsigned int revents; struct epitem *epi; struct epoll_event __user *uevent; + struct wakeup_source *ws; poll_table pt; init_poll_funcptr(&pt, NULL); @@ -1405,14 +1462,16 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ - if (epi->ws && epi->ws->active) - __pm_stay_awake(ep->ws); - __pm_relax(epi->ws); + ws = ep_wakeup_source(epi); + if (ws) { + if (ws->active) + __pm_stay_awake(ep->ws); + __pm_relax(ws); + } + list_del_init(&epi->rdllink); - pt._key = epi->event.events; - revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt) & - epi->event.events; + revents = ep_item_poll(epi, &pt); /* * If the event mask intersect the caller-requested one, @@ -1424,7 +1483,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, if (__put_user(revents, &uevent->events) || __put_user(epi->event.data, &uevent->data)) { list_add(&epi->rdllink, head); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); return eventcnt ? eventcnt : -EFAULT; } eventcnt++; @@ -1444,7 +1503,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); } } } @@ -1940,6 +1999,52 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, return error; } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, + struct epoll_event __user *, events, + int, maxevents, int, timeout, + const compat_sigset_t __user *, sigmask, + compat_size_t, sigsetsize) +{ + long err; + compat_sigset_t csigmask; + sigset_t ksigmask, sigsaved; + + /* + * If the caller wants a certain signal mask to be set during the wait, + * we apply it here. + */ + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&csigmask, sigmask, sizeof(csigmask))) + return -EFAULT; + sigset_from_compat(&ksigmask, &csigmask); + sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + err = sys_epoll_wait(epfd, events, maxevents, timeout); + + /* + * If we changed the signal mask, we need to restore the original one. + * In case we've got a signal while waiting, we do not restore the + * signal mask yet, and we allow do_signal() to deliver the signal on + * the way back to userspace, before the signal mask is restored. + */ + if (sigmask) { + if (err == -EINTR) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } else + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + } + + return err; +} +#endif + static int __init eventpoll_init(void) { struct sysinfo si; @@ -1964,6 +2069,12 @@ static int __init eventpoll_init(void) /* Initialize the structure used to perform file's f_op->poll() calls */ ep_nested_calls_init(&poll_readywalk_ncalls); + /* + * We can have many thousands of epitems, so prevent this from + * using an extra cache line on 64-bit (and smaller) CPUs + */ + BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); + /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -613,7 +613,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * when the old and new regions overlap clear from new_end. */ free_pgd_range(&tlb, new_end, old_end, new_end, - vma->vm_next ? vma->vm_next->vm_start : 0); + vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } else { /* * otherwise, clean from old_start; this is done to not touch @@ -622,7 +622,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * for the others its just a little faster. */ free_pgd_range(&tlb, old_start, old_end, new_end, - vma->vm_next ? vma->vm_next->vm_start : 0); + vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } tlb_finish_mmu(&tlb, new_end, old_end); @@ -907,11 +907,13 @@ static int de_thread(struct task_struct *tsk) sig->notify_count = -1; /* for exit_notify() */ for (;;) { + threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); + threadgroup_change_end(tsk); schedule(); if (unlikely(__fatal_signal_pending(tsk))) goto killed; @@ -969,6 +971,7 @@ static int de_thread(struct task_struct *tsk) if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); + threadgroup_change_end(tsk); release_task(leader); } @@ -1036,17 +1039,7 @@ EXPORT_SYMBOL_GPL(get_task_comm); void set_task_comm(struct task_struct *tsk, char *buf) { task_lock(tsk); - trace_task_rename(tsk, buf); - - /* - * Threads may access current->comm without holding - * the task lock, so write the string carefully. - * Readers without a lock may see incomplete new - * names but are safe from non-terminating string reads. - */ - memset(tsk->comm, 0, TASK_COMM_LEN); - wmb(); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index fb5120a..3dc48cc 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2067,7 +2067,6 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal": test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered": "writeback"); - sb->s_flags |= MS_SNAP_STABLE; return 0; diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 9873587..efea5d5 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -71,4 +71,5 @@ config EXT4_DEBUG Enables run-time debugging support for the ext4 filesystem. If you select Y here, then you will be able to turn on debugging - with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug" + with a command such as: + echo 1 > /sys/module/ext4/parameters/mballoc_debug diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 92e68b3..d0f13ea 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -30,6 +30,23 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb, */ /* + * Calculate block group number for a given block number + */ +ext4_group_t ext4_get_group_number(struct super_block *sb, + ext4_fsblk_t block) +{ + 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) >> + (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3); + else + ext4_get_group_no_and_offset(sb, block, &group, NULL); + return group; +} + +/* * Calculate the block group number and offset into the block/cluster * allocation bitmap, given a block number */ @@ -49,14 +66,18 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, } -static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, - ext4_group_t block_group) +/* + * Check whether the 'block' lives within the 'block_group'. Returns 1 if so + * and 0 otherwise. + */ +static inline int ext4_block_in_group(struct super_block *sb, + ext4_fsblk_t block, + ext4_group_t block_group) { ext4_group_t actual_group; - ext4_get_group_no_and_offset(sb, block, &actual_group, NULL); - if (actual_group == block_group) - return 1; - return 0; + + actual_group = ext4_get_group_number(sb, block); + return (actual_group == block_group) ? 1 : 0; } /* Return the number of clusters used for file system metadata; this @@ -420,7 +441,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) trace_ext4_read_block_bitmap_load(sb, block_group); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(READ, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); return bh; verify: ext4_validate_block_bitmap(sb, desc, block_group, bh); @@ -478,20 +499,22 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) static int ext4_has_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { - s64 free_clusters, dirty_clusters, root_clusters; + s64 free_clusters, dirty_clusters, rsv, resv_clusters; struct percpu_counter *fcc = &sbi->s_freeclusters_counter; struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter; free_clusters = percpu_counter_read_positive(fcc); dirty_clusters = percpu_counter_read_positive(dcc); + resv_clusters = atomic64_read(&sbi->s_resv_clusters); /* * r_blocks_count should always be multiple of the cluster ratio so * we are safe to do a plane bit shift only. */ - root_clusters = ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits; + rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) + + resv_clusters; - if (free_clusters - (nclusters + root_clusters + dirty_clusters) < + if (free_clusters - (nclusters + rsv + dirty_clusters) < EXT4_FREECLUSTERS_WATERMARK) { free_clusters = percpu_counter_sum_positive(fcc); dirty_clusters = percpu_counter_sum_positive(dcc); @@ -499,15 +522,21 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, /* Check whether we have space after accounting for current * dirty clusters & root reserved clusters. */ - if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters)) + if (free_clusters >= (rsv + nclusters + dirty_clusters)) return 1; /* Hm, nope. Are (enough) root reserved clusters available? */ if (uid_eq(sbi->s_resuid, current_fsuid()) || (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || - (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + if (free_clusters >= (nclusters + dirty_clusters + + resv_clusters)) + return 1; + } + /* No free blocks. Let's see if we can dip into reserved pool */ + if (flags & EXT4_MB_USE_RESERVED) { if (free_clusters >= (nclusters + dirty_clusters)) return 1; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index d8cd1f0..f8d56e4 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -46,7 +46,8 @@ static int is_dx_dir(struct inode *inode) if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_COMPAT_DIR_INDEX) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || - ((inode->i_size >> sb->s_blocksize_bits) == 1))) + ((inode->i_size >> sb->s_blocksize_bits) == 1) || + ext4_has_inline_data(inode))) return 1; return 0; @@ -115,14 +116,6 @@ static int ext4_readdir(struct file *filp, int ret = 0; int dir_has_error = 0; - if (ext4_has_inline_data(inode)) { - int has_inline_data = 1; - ret = ext4_read_inline_dir(filp, dirent, filldir, - &has_inline_data); - if (has_inline_data) - return ret; - } - if (is_dx_dir(inode)) { err = ext4_dx_readdir(filp, dirent, filldir); if (err != ERR_BAD_DX_DIR) { @@ -136,6 +129,15 @@ static int ext4_readdir(struct file *filp, ext4_clear_inode_flag(file_inode(filp), EXT4_INODE_INDEX); } + + if (ext4_has_inline_data(inode)) { + int has_inline_data = 1; + ret = ext4_read_inline_dir(filp, dirent, filldir, + &has_inline_data); + if (has_inline_data) + return ret; + } + stored = 0; offset = filp->f_pos & (sb->s_blocksize - 1); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3b83cd6..0aabb34 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -121,6 +121,8 @@ typedef unsigned int ext4_group_t; #define EXT4_MB_STREAM_ALLOC 0x0800 /* Use reserved root blocks if needed */ #define EXT4_MB_USE_ROOT_BLOCKS 0x1000 +/* Use blocks from reserved pool */ +#define EXT4_MB_USE_RESERVED 0x2000 struct ext4_allocation_request { /* target inode for block we're allocating */ @@ -196,19 +198,8 @@ struct mpage_da_data { #define EXT4_IO_END_ERROR 0x0002 #define EXT4_IO_END_DIRECT 0x0004 -struct ext4_io_page { - struct page *p_page; - atomic_t p_count; -}; - -#define MAX_IO_PAGES 128 - /* * For converting uninitialized extents on a work queue. - * - * 'page' is only used from the writepage() path; 'pages' is only used for - * buffered writes; they are used to keep page references until conversion - * takes place. For AIO/DIO, neither field is filled in. */ typedef struct ext4_io_end { struct list_head list; /* per-file finished IO list */ @@ -218,15 +209,13 @@ typedef struct ext4_io_end { ssize_t size; /* size of the extent */ struct kiocb *iocb; /* iocb struct for AIO */ int result; /* error value for AIO */ - int num_io_pages; /* for writepages() */ - struct ext4_io_page *pages[MAX_IO_PAGES]; /* for writepages() */ + atomic_t count; /* reference counter */ } ext4_io_end_t; struct ext4_io_submit { int io_op; struct bio *io_bio; ext4_io_end_t *io_end; - struct ext4_io_page *io_page; sector_t io_next_block; }; @@ -403,7 +392,7 @@ struct flex_groups { #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */ +#define EXT4_FL_USER_MODIFIABLE 0x004380FF /* User modifiable flags */ /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ @@ -557,9 +546,8 @@ enum { #define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ EXT4_GET_BLOCKS_CREATE) - /* Caller is from the delayed allocation writeout path, - so set the magic i_delalloc_reserve_flag after taking the - inode allocation semaphore for */ + /* Caller is from the delayed allocation writeout path + * finally doing the actual allocation of delayed blocks */ #define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 /* caller is from the direct IO path, request to creation of an unitialized extents if not allocated, split the uninitialized @@ -571,8 +559,9 @@ enum { /* Convert extent to initialized after IO complete */ #define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\ EXT4_GET_BLOCKS_CREATE_UNINIT_EXT) - /* Punch out blocks of an extent */ -#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020 + /* Eventual metadata allocation (due to growing extent tree) + * should not fail, so try to use reserved blocks for that.*/ +#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ @@ -616,6 +605,7 @@ enum { #define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) #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) #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -949,7 +939,7 @@ struct ext4_inode_info { #define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */ /* - * Mount flags + * Mount flags set via mount options or defaults */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ @@ -981,8 +971,16 @@ struct ext4_inode_info { #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ #define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ +/* + * Mount flags set either automatically (could not be set by mount option) + * based on per file system feature or property or in special cases such as + * distinguishing between explicit mount option definition and default. + */ #define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly specified delalloc */ +#define EXT4_MOUNT2_STD_GROUP_SIZE 0x00000002 /* We have standard group + size of blocksize * 8 + blocks */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1179,6 +1177,7 @@ struct ext4_sb_info { unsigned int s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; + atomic64_t s_resv_clusters; kuid_t s_resuid; kgid_t s_resgid; unsigned short s_mount_state; @@ -1333,6 +1332,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) return ino == EXT4_ROOT_INO || ino == EXT4_USR_QUOTA_INO || ino == EXT4_GRP_QUOTA_INO || + ino == EXT4_BOOT_LOADER_INO || ino == EXT4_JOURNAL_INO || ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && @@ -1374,6 +1374,7 @@ enum { EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read nolocking */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ + EXT4_STATE_ORDERED_MODE, /* data=ordered mode */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1784,9 +1785,6 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) */ #define ERR_BAD_DX_DIR -75000 -void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, - ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp); - /* * Timeout and state flag for lazy initialization inode thread. */ @@ -1908,6 +1906,13 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct buffer_head *bh); /* balloc.c */ +extern void ext4_get_group_no_and_offset(struct super_block *sb, + ext4_fsblk_t blocknr, + ext4_group_t *blockgrpp, + ext4_grpblk_t *offsetp); +extern ext4_group_t ext4_get_group_number(struct super_block *sb, + ext4_fsblk_t block); + extern void ext4_validate_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, unsigned int block_group, @@ -2108,8 +2113,9 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, unsigned long nr_segs); extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk); -extern void ext4_ind_truncate(struct inode *inode); -extern int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length); +extern void ext4_ind_truncate(handle_t *, struct inode *inode); +extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, + ext4_lblk_t first, ext4_lblk_t stop); /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); @@ -2117,6 +2123,7 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); +extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ extern int ext4_dirent_csum_verify(struct inode *inode, @@ -2511,6 +2518,11 @@ extern int ext4_try_create_inline_dir(handle_t *handle, extern int ext4_read_inline_dir(struct file *filp, void *dirent, filldir_t filldir, int *has_inline_data); +extern int htree_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, @@ -2547,6 +2559,24 @@ extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, extern int ext4_handle_dirty_dirent_node(handle_t *handle, struct inode *inode, struct buffer_head *bh); +#define S_SHIFT 12 +static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { + [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, + [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, + [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, + [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, + [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, + [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, + [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, +}; + +static inline void ext4_set_de_type(struct super_block *sb, + struct ext4_dir_entry_2 *de, + umode_t mode) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) + de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; +} + /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; @@ -2573,9 +2603,9 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk); extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern void ext4_ext_truncate(struct inode *); -extern int ext4_ext_punch_hole(struct file *file, loff_t offset, - loff_t length); +extern void ext4_ext_truncate(handle_t *, struct inode *); +extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t end); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct file *file, int mode, loff_t offset, @@ -2609,17 +2639,26 @@ extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* move_extent.c */ +extern void ext4_double_down_write_data_sem(struct inode *first, + struct inode *second); +extern void ext4_double_up_write_data_sem(struct inode *orig_inode, + struct inode *donor_inode); +void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2); +void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2); extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); /* page-io.c */ extern int __init ext4_init_pageio(void); -extern void ext4_add_complete_io(ext4_io_end_t *io_end); extern void ext4_exit_pageio(void); extern void ext4_ioend_shutdown(struct inode *); -extern void ext4_free_io_end(ext4_io_end_t *io); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); +extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end); +extern int ext4_put_io_end(ext4_io_end_t *io_end); +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_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, diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 8643ff5..51bc821 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -270,5 +270,10 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, 0xffff); } +#define ext4_ext_dirty(handle, inode, path) \ + __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) +int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, + struct inode *inode, struct ext4_ext_path *path); + #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 7058975..451eb40 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -43,6 +43,8 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, { journal_t *journal; + might_sleep(); + trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); @@ -113,6 +115,8 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line, { int err = 0; + might_sleep(); + if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) @@ -209,6 +213,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, { int err = 0; + might_sleep(); + + set_buffer_meta(bh); + set_buffer_prio(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); if (err) { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 4c216b1..c8c6885 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -29,11 +29,13 @@ * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to - * 5 levels of tree + root which are stored in the inode. */ + * 5 levels of tree, data block (for each of these we need bitmap + group + * summaries), root which is stored in the inode, sb + */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ - ? 27U : 8U) + ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode @@ -194,16 +196,20 @@ 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 */ -static inline void ext4_journal_callback_del(handle_t *handle, +static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) { + bool deleted; struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); spin_lock(&sbi->s_md_lock); + deleted = !list_empty(&jce->jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); + return deleted; } int diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 56efcaa..107936d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -157,11 +157,8 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, * - ENOMEM * - EIO */ -#define ext4_ext_dirty(handle, inode, path) \ - __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) -static int __ext4_ext_dirty(const char *where, unsigned int line, - handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) +int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, + struct inode *inode, struct ext4_ext_path *path) { int err; if (path->p_bh) { @@ -1813,39 +1810,101 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, } depth = ext_depth(inode); ex = path[depth].p_ext; + eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EIO; } /* try to insert block into found extent and return */ - if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO) - && ext4_can_extents_be_merged(inode, ex, newext)) { - ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n", - ext4_ext_is_uninitialized(newext), - ext4_ext_get_actual_len(newext), - le32_to_cpu(ex->ee_block), - ext4_ext_is_uninitialized(ex), - ext4_ext_get_actual_len(ex), - ext4_ext_pblock(ex)); - err = ext4_ext_get_access(handle, inode, path + depth); - if (err) - return err; + if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) { /* - * ext4_can_extents_be_merged should have checked that either - * both extents are uninitialized, or both aren't. Thus we - * need to check only one of them here. + * Try to see whether we should rather test the extent on + * right from ex, or from the left of ex. This is because + * ext4_ext_find_extent() can return either extent on the + * left, or on the right from the searched position. This + * will make merging more effective. */ - if (ext4_ext_is_uninitialized(ex)) - uninitialized = 1; - ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + if (ex < EXT_LAST_EXTENT(eh) && + (le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex) < + le32_to_cpu(newext->ee_block))) { + ex += 1; + goto prepend; + } else if ((ex > EXT_FIRST_EXTENT(eh)) && + (le32_to_cpu(newext->ee_block) + + ext4_ext_get_actual_len(newext) < + le32_to_cpu(ex->ee_block))) + ex -= 1; + + /* Try to append newex to the ex */ + if (ext4_can_extents_be_merged(inode, ex, newext)) { + ext_debug("append [%d]%d block to %u:[%d]%d" + "(from %llu)\n", + ext4_ext_is_uninitialized(newext), + ext4_ext_get_actual_len(newext), + le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), + ext4_ext_get_actual_len(ex), + ext4_ext_pblock(ex)); + err = ext4_ext_get_access(handle, inode, + path + depth); + if (err) + return err; + + /* + * ext4_can_extents_be_merged should have checked + * that either both extents are uninitialized, or + * both aren't. Thus we need to check only one of + * them here. + */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); - if (uninitialized) - ext4_ext_mark_uninitialized(ex); - eh = path[depth].p_hdr; - nearex = ex; - goto merge; + if (uninitialized) + ext4_ext_mark_uninitialized(ex); + eh = path[depth].p_hdr; + nearex = ex; + goto merge; + } + +prepend: + /* Try to prepend newex to the ex */ + if (ext4_can_extents_be_merged(inode, newext, ex)) { + ext_debug("prepend %u[%d]%d block to %u:[%d]%d" + "(from %llu)\n", + le32_to_cpu(newext->ee_block), + ext4_ext_is_uninitialized(newext), + ext4_ext_get_actual_len(newext), + le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), + ext4_ext_get_actual_len(ex), + ext4_ext_pblock(ex)); + err = ext4_ext_get_access(handle, inode, + path + depth); + if (err) + return err; + + /* + * ext4_can_extents_be_merged should have checked + * that either both extents are uninitialized, or + * both aren't. Thus we need to check only one of + * them here. + */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_block = newext->ee_block; + ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + + ext4_ext_get_actual_len(newext)); + if (uninitialized) + ext4_ext_mark_uninitialized(ex); + eh = path[depth].p_hdr; + nearex = ex; + goto merge; + } } depth = ext_depth(inode); @@ -1880,8 +1939,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ - if (flag & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) - flags = EXT4_MB_USE_ROOT_BLOCKS; + if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL) + flags = EXT4_MB_USE_RESERVED; err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext); if (err) goto cleanup; @@ -2599,8 +2658,8 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path) return 1; } -static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, - ext4_lblk_t end) +int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t end) { struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); @@ -2667,12 +2726,14 @@ again: /* * Split the extent in two so that 'end' is the last - * block in the first new extent + * block in the first new extent. Also we should not + * fail removing space due to ENOSPC so try to use + * reserved block if that happens. */ err = ext4_split_extent_at(handle, inode, path, - end + 1, split_flag, - EXT4_GET_BLOCKS_PRE_IO | - EXT4_GET_BLOCKS_PUNCH_OUT_EXT); + end + 1, split_flag, + EXT4_GET_BLOCKS_PRE_IO | + EXT4_GET_BLOCKS_METADATA_NOFAIL); if (err < 0) goto out; @@ -2999,20 +3060,23 @@ static int ext4_split_extent_at(handle_t *handle, if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); zero_ex.ee_block = ex2->ee_block; - zero_ex.ee_len = ext4_ext_get_actual_len(ex2); + zero_ex.ee_len = cpu_to_le16( + ext4_ext_get_actual_len(ex2)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex2)); } else { err = ext4_ext_zeroout(inode, ex); zero_ex.ee_block = ex->ee_block; - zero_ex.ee_len = ext4_ext_get_actual_len(ex); + zero_ex.ee_len = cpu_to_le16( + ext4_ext_get_actual_len(ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex)); } } else { err = ext4_ext_zeroout(inode, &orig_ex); zero_ex.ee_block = orig_ex.ee_block; - zero_ex.ee_len = ext4_ext_get_actual_len(&orig_ex); + zero_ex.ee_len = cpu_to_le16( + ext4_ext_get_actual_len(&orig_ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(&orig_ex)); } @@ -3144,35 +3208,35 @@ out: static int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, - struct ext4_ext_path *path) + struct ext4_ext_path *path, + int flags) { struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex; - struct ext4_extent *ex; + struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; - unsigned int ee_len, depth; - int allocated, max_zeroout = 0; + unsigned int ee_len, depth, map_len = map->m_len; + int allocated = 0, max_zeroout = 0; int err = 0; int split_flag = 0; ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)map->m_lblk, map->m_len); + (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; - if (eof_block < map->m_lblk + map->m_len) - eof_block = map->m_lblk + map->m_len; + if (eof_block < map->m_lblk + map_len) + eof_block = map->m_lblk + map_len; depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - allocated = ee_len - (map->m_lblk - ee_block); zero_ex.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); @@ -3183,77 +3247,121 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, /* * Attempt to transfer newly initialized blocks from the currently - * uninitialized extent to its left neighbor. This is much cheaper + * uninitialized extent to its neighbor. This is much cheaper * than an insertion followed by a merge as those involve costly - * memmove() calls. This is the common case in steady state for - * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append - * writes. + * memmove() calls. Transferring to the left is the common case in + * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE) + * followed by append writes. * * Limitations of the current logic: - * - L1: we only deal with writes at the start of the extent. - * The approach could be extended to writes at the end - * of the extent but this scenario was deemed less common. - * - L2: we do not deal with writes covering the whole extent. + * - L1: we do not deal with writes covering the whole extent. * This would require removing the extent if the transfer * is possible. - * - L3: we only attempt to merge with an extent stored in the + * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ - if ((map->m_lblk == ee_block) && /*L1*/ - (map->m_len < ee_len) && /*L2*/ - (ex > EXT_FIRST_EXTENT(eh))) { /*L3*/ - struct ext4_extent *prev_ex; + if ((map->m_lblk == ee_block) && + /* See if we can merge left */ + (map_len < ee_len) && /*L1*/ + (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/ ext4_lblk_t prev_lblk; ext4_fsblk_t prev_pblk, ee_pblk; - unsigned int prev_len, write_len; + unsigned int prev_len; - prev_ex = ex - 1; - prev_lblk = le32_to_cpu(prev_ex->ee_block); - prev_len = ext4_ext_get_actual_len(prev_ex); - prev_pblk = ext4_ext_pblock(prev_ex); + abut_ex = ex - 1; + prev_lblk = le32_to_cpu(abut_ex->ee_block); + prev_len = ext4_ext_get_actual_len(abut_ex); + prev_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); - write_len = map->m_len; /* - * A transfer of blocks from 'ex' to 'prev_ex' is allowed + * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: - * - C1: prev_ex is initialized, - * - C2: prev_ex is logically abutting ex, - * - C3: prev_ex is physically abutting ex, - * - C4: prev_ex can receive the additional blocks without + * - C1: abut_ex is initialized, + * - C2: abut_ex is logically abutting ex, + * - C3: abut_ex is physically abutting ex, + * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ - if ((!ext4_ext_is_uninitialized(prev_ex)) && /*C1*/ + if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/ ((prev_lblk + prev_len) == ee_block) && /*C2*/ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/ - (prev_len < (EXT_INIT_MAX_LEN - write_len))) { /*C4*/ + (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; trace_ext4_ext_convert_to_initialized_fastpath(inode, - map, ex, prev_ex); + map, ex, abut_ex); - /* Shift the start of ex by 'write_len' blocks */ - ex->ee_block = cpu_to_le32(ee_block + write_len); - ext4_ext_store_pblock(ex, ee_pblk + write_len); - ex->ee_len = cpu_to_le16(ee_len - write_len); + /* Shift the start of ex by 'map_len' blocks */ + ex->ee_block = cpu_to_le32(ee_block + map_len); + ext4_ext_store_pblock(ex, ee_pblk + map_len); + ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_uninitialized(ex); /* Restore the flag */ - /* Extend prev_ex by 'write_len' blocks */ - prev_ex->ee_len = cpu_to_le16(prev_len + write_len); + /* Extend abut_ex by 'map_len' blocks */ + abut_ex->ee_len = cpu_to_le16(prev_len + map_len); - /* Mark the block containing both extents as dirty */ - ext4_ext_dirty(handle, inode, path + depth); + /* Result: number of initialized blocks past m_lblk */ + allocated = map_len; + } + } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && + (map_len < ee_len) && /*L1*/ + ex < EXT_LAST_EXTENT(eh)) { /*L2*/ + /* See if we can merge right */ + ext4_lblk_t next_lblk; + ext4_fsblk_t next_pblk, ee_pblk; + unsigned int next_len; + + abut_ex = ex + 1; + next_lblk = le32_to_cpu(abut_ex->ee_block); + next_len = ext4_ext_get_actual_len(abut_ex); + next_pblk = ext4_ext_pblock(abut_ex); + ee_pblk = ext4_ext_pblock(ex); - /* Update path to point to the right extent */ - path[depth].p_ext = prev_ex; + /* + * A transfer of blocks from 'ex' to 'abut_ex' is allowed + * upon those conditions: + * - C1: abut_ex is initialized, + * - C2: abut_ex is logically abutting ex, + * - C3: abut_ex is physically abutting ex, + * - C4: abut_ex can receive the additional blocks without + * overflowing the (initialized) length limit. + */ + if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/ + ((map->m_lblk + map_len) == next_lblk) && /*C2*/ + ((ee_pblk + ee_len) == next_pblk) && /*C3*/ + (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + + trace_ext4_ext_convert_to_initialized_fastpath(inode, + map, ex, abut_ex); + + /* Shift the start of abut_ex by 'map_len' blocks */ + abut_ex->ee_block = cpu_to_le32(next_lblk - map_len); + ext4_ext_store_pblock(abut_ex, next_pblk - map_len); + ex->ee_len = cpu_to_le16(ee_len - map_len); + ext4_ext_mark_uninitialized(ex); /* Restore the flag */ + + /* Extend abut_ex by 'map_len' blocks */ + abut_ex->ee_len = cpu_to_le16(next_len + map_len); /* Result: number of initialized blocks past m_lblk */ - allocated = write_len; - goto out; + allocated = map_len; } } + if (allocated) { + /* Mark the block containing both extents as dirty */ + ext4_ext_dirty(handle, inode, path + depth); + + /* Update path to point to the right extent */ + path[depth].p_ext = abut_ex; + goto out; + } else + allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* @@ -3272,7 +3380,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, if (err) goto out; zero_ex.ee_block = ex->ee_block; - zero_ex.ee_len = ext4_ext_get_actual_len(ex); + zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); @@ -3327,7 +3435,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, } allocated = ext4_split_extent(handle, inode, path, - &split_map, split_flag, 0); + &split_map, split_flag, flags); if (allocated < 0) err = allocated; @@ -3647,6 +3755,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, flags, allocated); ext4_ext_show_leaf(inode, path); + /* + * When writing into uninitialized space, we should not fail to + * allocate metadata blocks for the new extent block if needed. + */ + flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; + trace_ext4_ext_handle_uninitialized_extents(inode, map, flags, allocated, newblock); @@ -3710,7 +3824,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, } /* buffered write, writepage time, convert*/ - ret = ext4_ext_convert_to_initialized(handle, inode, map, path); + ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags); if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); out: @@ -4254,48 +4368,13 @@ out3: return err ? err : allocated; } -void ext4_ext_truncate(struct inode *inode) +void ext4_ext_truncate(handle_t *handle, struct inode *inode) { - struct address_space *mapping = inode->i_mapping; struct super_block *sb = inode->i_sb; ext4_lblk_t last_block; - handle_t *handle; - loff_t page_len; int err = 0; /* - * finish any pending end_io work so we won't run the risk of - * converting any truncated blocks to initialized later - */ - ext4_flush_unwritten_io(inode); - - /* - * probably first extent we're gonna free will be last in block - */ - err = ext4_writepage_trans_blocks(inode); - handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, err); - if (IS_ERR(handle)) - return; - - if (inode->i_size % PAGE_CACHE_SIZE != 0) { - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - - if (err) - goto out_stop; - } - - if (ext4_orphan_add(handle, inode)) - goto out_stop; - - down_write(&EXT4_I(inode)->i_data_sem); - - ext4_discard_preallocations(inode); - - /* * TODO: optimization is possible here. * Probably we need not scan at all, * because page truncation is enough. @@ -4310,29 +4389,6 @@ void ext4_ext_truncate(struct inode *inode) err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); - - /* In a multi-transaction truncate, we only make the final - * transaction synchronous. - */ - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - - up_write(&EXT4_I(inode)->i_data_sem); - -out_stop: - /* - * If this was a simple ftruncate() and the file will remain alive, - * then we need to clear up the orphan record which we created above. - * However, if this was a real unlink then we were called by - * ext4_delete_inode(), and we allow that function to clean up the - * orphan info for us. - */ - if (inode->i_nlink) - ext4_orphan_del(handle, inode); - - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); } static void ext4_falloc_update_inode(struct inode *inode, @@ -4620,187 +4676,6 @@ static int ext4_xattr_fiemap(struct inode *inode, return (error < 0 ? error : 0); } -/* - * ext4_ext_punch_hole - * - * Punches a hole of "length" bytes in a file starting - * at byte "offset" - * - * @inode: The inode of the file to punch a hole in - * @offset: The starting byte offset of the hole - * @length: The length of the hole - * - * Returns the number of blocks removed or negative on err - */ -int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) -{ - struct inode *inode = file_inode(file); - struct super_block *sb = inode->i_sb; - ext4_lblk_t first_block, stop_block; - struct address_space *mapping = inode->i_mapping; - handle_t *handle; - loff_t first_page, last_page, page_len; - loff_t first_page_offset, last_page_offset; - int credits, err = 0; - - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - - if (err) - return err; - } - - mutex_lock(&inode->i_mutex); - /* It's not possible punch hole on append only file */ - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { - err = -EPERM; - goto out_mutex; - } - if (IS_SWAPFILE(inode)) { - err = -ETXTBSY; - goto out_mutex; - } - - /* No need to punch hole beyond i_size */ - if (offset >= inode->i_size) - goto out_mutex; - - /* - * If the hole extends beyond i_size, set the hole - * to end after the page that contains i_size - */ - if (offset + length > inode->i_size) { - length = inode->i_size + - PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - - offset; - } - - first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - last_page = (offset + length) >> PAGE_CACHE_SHIFT; - - first_page_offset = first_page << PAGE_CACHE_SHIFT; - last_page_offset = last_page << PAGE_CACHE_SHIFT; - - /* Now release the pages */ - if (last_page_offset > first_page_offset) { - truncate_pagecache_range(inode, first_page_offset, - last_page_offset - 1); - } - - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - err = ext4_flush_unwritten_io(inode); - if (err) - goto out_dio; - inode_dio_wait(inode); - - credits = ext4_writepage_trans_blocks(inode); - handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - goto out_dio; - } - - - /* - * Now we need to zero out the non-page-aligned data in the - * pages at the start and tail of the hole, and unmap the buffer - * heads for the block aligned regions of the page that were - * completely zeroed. - */ - if (first_page > last_page) { - /* - * If the file space being truncated is contained within a page - * just zero out and unmap the middle of that page - */ - err = ext4_discard_partial_page_buffers(handle, - mapping, offset, length, 0); - - if (err) - goto out; - } else { - /* - * zero out and unmap the partial page that contains - * the start of the hole - */ - page_len = first_page_offset - offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - offset, page_len, 0); - if (err) - goto out; - } - - /* - * zero out and unmap the partial page that contains - * the end of the hole - */ - page_len = offset + length - last_page_offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - last_page_offset, page_len, 0); - if (err) - goto out; - } - } - - /* - * If i_size is contained in the last page, we need to - * unmap and zero the partial page after i_size - */ - if (inode->i_size >> PAGE_CACHE_SHIFT == last_page && - inode->i_size % PAGE_CACHE_SIZE != 0) { - - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - - if (err) - goto out; - } - } - - first_block = (offset + sb->s_blocksize - 1) >> - EXT4_BLOCK_SIZE_BITS(sb); - stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); - - /* If there are no blocks to remove, return now */ - if (first_block >= stop_block) - goto out; - - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); - - err = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - err = ext4_ext_remove_space(inode, first_block, stop_block - 1); - - ext4_discard_preallocations(inode); - - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - - up_write(&EXT4_I(inode)->i_data_sem); - -out: - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); -out_dio: - ext4_inode_resume_unlocked_dio(inode); -out_mutex: - mutex_unlock(&inode->i_mutex); - return err; -} - int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 3278e64..e0ba8a4 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -166,8 +166,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) needs_barrier = true; - jbd2_log_start_commit(journal, commit_tid); - ret = jbd2_log_wait_commit(journal, commit_tid); + ret = jbd2_complete_transaction(journal, commit_tid); if (needs_barrier) { err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); if (!ret) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 6c5bb8d..00a818d 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -166,7 +166,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) trace_ext4_load_inode_bitmap(sb, block_group); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(READ, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { put_bh(bh); @@ -666,6 +666,23 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, ei = EXT4_I(inode); sbi = EXT4_SB(sb); + /* + * Initalize owners and quota early so that we don't have to account + * for quota initialization worst case in standard inode creating + * transaction + */ + if (owner) { + inode->i_mode = mode; + i_uid_write(inode, owner[0]); + i_gid_write(inode, owner[1]); + } else if (test_opt(sb, GRPID)) { + inode->i_mode = mode; + inode->i_uid = current_fsuid(); + inode->i_gid = dir->i_gid; + } else + inode_init_owner(inode, dir, mode); + dquot_initialize(inode); + if (!goal) goal = sbi->s_inode_goal; @@ -697,7 +714,7 @@ got_group: gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp) - goto fail; + goto out; /* * Check free inodes count before loading bitmap. @@ -711,7 +728,7 @@ got_group: brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); if (!inode_bitmap_bh) - goto fail; + goto out; repeat_in_this_group: ino = ext4_find_next_zero_bit((unsigned long *) @@ -733,13 +750,16 @@ repeat_in_this_group: handle_type, nblocks); if (IS_ERR(handle)) { err = PTR_ERR(handle); - goto fail; + ext4_std_error(sb, err); + goto out; } } BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode_bitmap_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); ext4_unlock_group(sb, group); @@ -755,8 +775,10 @@ repeat_in_this_group: got: BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && @@ -768,7 +790,8 @@ got: err = ext4_journal_get_write_access(handle, block_bitmap_bh); if (err) { brelse(block_bitmap_bh); - goto fail; + ext4_std_error(sb, err); + goto out; } BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); @@ -787,14 +810,18 @@ got: ext4_unlock_group(sb, group); brelse(block_bitmap_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } } BUFFER_TRACE(group_desc_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, group_desc_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { @@ -840,8 +867,10 @@ got: BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); - if (err) - goto fail; + if (err) { + ext4_std_error(sb, err); + goto out; + } percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) @@ -851,16 +880,6 @@ got: flex_group = ext4_flex_group(sbi, group); atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); } - if (owner) { - inode->i_mode = mode; - i_uid_write(inode, owner[0]); - i_gid_write(inode, owner[1]); - } else if (test_opt(sb, GRPID)) { - inode->i_mode = mode; - inode->i_uid = current_fsuid(); - inode->i_gid = dir->i_gid; - } else - inode_init_owner(inode, dir, mode); inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ @@ -889,7 +908,9 @@ got: * twice. */ err = -EIO; - goto fail; + ext4_error(sb, "failed to insert inode %lu: doubly allocated?", + inode->i_ino); + goto out; } spin_lock(&sbi->s_next_gen_lock); inode->i_generation = sbi->s_next_generation++; @@ -899,7 +920,6 @@ got: if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { __u32 csum; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, @@ -918,7 +938,6 @@ got: ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ret = inode; - dquot_initialize(inode); err = dquot_alloc_inode(inode); if (err) goto fail_drop; @@ -952,24 +971,17 @@ got: ext4_debug("allocating inode %lu\n", inode->i_ino); trace_ext4_allocate_inode(inode, dir, mode); - goto really_out; -fail: - ext4_std_error(sb, err); -out: - iput(inode); - ret = ERR_PTR(err); -really_out: brelse(inode_bitmap_bh); return ret; fail_free_drop: dquot_free_inode(inode); - fail_drop: - dquot_drop(inode); - inode->i_flags |= S_NOQUOTA; clear_nlink(inode); unlock_new_inode(inode); +out: + dquot_drop(inode); + inode->i_flags |= S_NOQUOTA; iput(inode); brelse(inode_bitmap_bh); return ERR_PTR(err); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index b505a14..98be6f6 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -292,131 +292,6 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, } /** - * ext4_alloc_blocks: multiple allocate blocks needed for a branch - * @handle: handle for this transaction - * @inode: inode which needs allocated blocks - * @iblock: the logical block to start allocated at - * @goal: preferred physical block of allocation - * @indirect_blks: the number of blocks need to allocate for indirect - * blocks - * @blks: number of desired blocks - * @new_blocks: on return it will store the new block numbers for - * the indirect blocks(if needed) and the first direct block, - * @err: on return it will store the error code - * - * This function will return the number of blocks allocated as - * requested by the passed-in parameters. - */ -static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t iblock, ext4_fsblk_t goal, - int indirect_blks, int blks, - ext4_fsblk_t new_blocks[4], int *err) -{ - struct ext4_allocation_request ar; - int target, i; - unsigned long count = 0, blk_allocated = 0; - int index = 0; - ext4_fsblk_t current_block = 0; - int ret = 0; - - /* - * Here we try to allocate the requested multiple blocks at once, - * on a best-effort basis. - * To build a branch, we should allocate blocks for - * the indirect blocks(if not allocated yet), and at least - * the first direct block of this branch. That's the - * minimum number of blocks need to allocate(required) - */ - /* first we try to allocate the indirect blocks */ - target = indirect_blks; - while (target > 0) { - count = target; - /* allocating blocks for indirect blocks and direct blocks */ - current_block = ext4_new_meta_blocks(handle, inode, goal, - 0, &count, err); - if (*err) - goto failed_out; - - if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) { - EXT4_ERROR_INODE(inode, - "current_block %llu + count %lu > %d!", - current_block, count, - EXT4_MAX_BLOCK_FILE_PHYS); - *err = -EIO; - goto failed_out; - } - - target -= count; - /* allocate blocks for indirect blocks */ - while (index < indirect_blks && count) { - new_blocks[index++] = current_block++; - count--; - } - if (count > 0) { - /* - * save the new block number - * for the first direct block - */ - new_blocks[index] = current_block; - WARN(1, KERN_INFO "%s returned more blocks than " - "requested\n", __func__); - break; - } - } - - target = blks - count ; - blk_allocated = count; - if (!target) - goto allocated; - /* Now allocate data blocks */ - memset(&ar, 0, sizeof(ar)); - ar.inode = inode; - ar.goal = goal; - ar.len = target; - ar.logical = iblock; - if (S_ISREG(inode->i_mode)) - /* enable in-core preallocation only for regular files */ - ar.flags = EXT4_MB_HINT_DATA; - - current_block = ext4_mb_new_blocks(handle, &ar, err); - if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) { - EXT4_ERROR_INODE(inode, - "current_block %llu + ar.len %d > %d!", - current_block, ar.len, - EXT4_MAX_BLOCK_FILE_PHYS); - *err = -EIO; - goto failed_out; - } - - if (*err && (target == blks)) { - /* - * if the allocation failed and we didn't allocate - * any blocks before - */ - goto failed_out; - } - if (!*err) { - if (target == blks) { - /* - * save the new block number - * for the first direct block - */ - new_blocks[index] = current_block; - } - blk_allocated += ar.len; - } -allocated: - /* total number of blocks allocated for direct blocks */ - ret = blk_allocated; - *err = 0; - return ret; -failed_out: - for (i = 0; i < index; i++) - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - return ret; -} - -/** * ext4_alloc_branch - allocate and set up a chain of blocks. * @handle: handle for this transaction * @inode: owner @@ -448,60 +323,59 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, int *blks, ext4_fsblk_t goal, ext4_lblk_t *offsets, Indirect *branch) { - int blocksize = inode->i_sb->s_blocksize; - int i, n = 0; - int err = 0; - struct buffer_head *bh; - int num; - ext4_fsblk_t new_blocks[4]; - ext4_fsblk_t current_block; - - num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks, - *blks, new_blocks, &err); - if (err) - return err; + struct ext4_allocation_request ar; + struct buffer_head * bh; + ext4_fsblk_t b, new_blocks[4]; + __le32 *p; + int i, j, err, len = 1; - branch[0].key = cpu_to_le32(new_blocks[0]); /* - * metadata blocks and data blocks are allocated. + * Set up for the direct block allocation */ - for (n = 1; n <= indirect_blks; n++) { - /* - * Get buffer_head for parent block, zero it out - * and set the pointer to new one, then send - * parent to disk. - */ - bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + memset(&ar, 0, sizeof(ar)); + ar.inode = inode; + ar.len = *blks; + ar.logical = iblock; + if (S_ISREG(inode->i_mode)) + ar.flags = EXT4_MB_HINT_DATA; + + for (i = 0; i <= indirect_blks; i++) { + if (i == indirect_blks) { + ar.goal = goal; + new_blocks[i] = ext4_mb_new_blocks(handle, &ar, &err); + } else + goal = new_blocks[i] = ext4_new_meta_blocks(handle, inode, + goal, 0, NULL, &err); + if (err) { + i--; + goto failed; + } + branch[i].key = cpu_to_le32(new_blocks[i]); + if (i == 0) + continue; + + bh = branch[i].bh = sb_getblk(inode->i_sb, new_blocks[i-1]); if (unlikely(!bh)) { err = -ENOMEM; goto failed; } - - branch[n].bh = bh; lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, bh); if (err) { - /* Don't brelse(bh) here; it's done in - * ext4_journal_forget() below */ unlock_buffer(bh); goto failed; } - memset(bh->b_data, 0, blocksize); - branch[n].p = (__le32 *) bh->b_data + offsets[n]; - branch[n].key = cpu_to_le32(new_blocks[n]); - *branch[n].p = branch[n].key; - if (n == indirect_blks) { - current_block = new_blocks[n]; - /* - * End of chain, update the last new metablock of - * the chain to point to the new allocated - * data blocks numbers - */ - for (i = 1; i < num; i++) - *(branch[n].p + i) = cpu_to_le32(++current_block); - } + memset(bh->b_data, 0, bh->b_size); + p = branch[i].p = (__le32 *) bh->b_data + offsets[i]; + b = new_blocks[i]; + + if (i == indirect_blks) + len = ar.len; + for (j = 0; j < len; j++) + *p++ = cpu_to_le32(b++); + BUFFER_TRACE(bh, "marking uptodate"); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -511,25 +385,16 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, if (err) goto failed; } - *blks = num; - return err; + *blks = ar.len; + return 0; failed: - /* Allocation failed, free what we already allocated */ - ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0); - for (i = 1; i <= n ; i++) { - /* - * branch[i].bh is newly allocated, so there is no - * need to revoke the block, which is why we don't - * need to set EXT4_FREE_BLOCKS_METADATA. - */ - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, - EXT4_FREE_BLOCKS_FORGET); + for (; i >= 0; i--) { + if (i != indirect_blks && branch[i].bh) + ext4_forget(handle, 1, inode, branch[i].bh, + branch[i].bh->b_blocknr); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], + (i == indirect_blks) ? ar.len : 1, 0); } - for (i = n+1; i < indirect_blks; i++) - ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - - ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0); - return err; } @@ -941,26 +806,9 @@ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk) * be able to restart the transaction at a conventient checkpoint to make * sure we don't overflow the journal. * - * start_transaction gets us a new handle for a truncate transaction, - * and extend_transaction tries to extend the existing one a bit. If + * Try to extend this transaction for the purposes of truncation. If * extend fails, we need to propagate the failure up and restart the * transaction in the top-level truncate loop. --sct - */ -static handle_t *start_transaction(struct inode *inode) -{ - handle_t *result; - - result = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)); - if (!IS_ERR(result)) - return result; - - ext4_std_error(inode->i_sb, PTR_ERR(result)); - return result; -} - -/* - * Try to extend this transaction for the purposes of truncation. * * Returns 0 if we managed to create more room. If we can't create more * room, and the transaction must be restarted we return 1. @@ -1353,68 +1201,30 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, } } -void ext4_ind_truncate(struct inode *inode) +void ext4_ind_truncate(handle_t *handle, struct inode *inode) { - handle_t *handle; struct ext4_inode_info *ei = EXT4_I(inode); __le32 *i_data = ei->i_data; int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); - struct address_space *mapping = inode->i_mapping; ext4_lblk_t offsets[4]; Indirect chain[4]; Indirect *partial; __le32 nr = 0; int n = 0; ext4_lblk_t last_block, max_block; - loff_t page_len; unsigned blocksize = inode->i_sb->s_blocksize; - int err; - - handle = start_transaction(inode); - if (IS_ERR(handle)) - return; /* AKPM: return what? */ last_block = (inode->i_size + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); - if (inode->i_size % PAGE_CACHE_SIZE != 0) { - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - - if (err) - goto out_stop; - } - if (last_block != max_block) { n = ext4_block_to_path(inode, last_block, offsets, NULL); if (n == 0) - goto out_stop; /* error */ + return; } - /* - * OK. This truncate is going to happen. We add the inode to the - * orphan list, so that if this truncate spans multiple transactions, - * and we crash, we will resume the truncate when the filesystem - * recovers. It also marks the inode dirty, to catch the new size. - * - * Implication: the file must always be in a sane, consistent - * truncatable state while each transaction commits. - */ - if (ext4_orphan_add(handle, inode)) - goto out_stop; - - /* - * From here we block out all ext4_get_block() callers who want to - * modify the block allocation tree. - */ - down_write(&ei->i_data_sem); - - ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); /* @@ -1431,7 +1241,7 @@ void ext4_ind_truncate(struct inode *inode) * It is unnecessary to free any data blocks if last_block is * equal to the indirect block limit. */ - goto out_unlock; + return; } else if (n == 1) { /* direct blocks */ ext4_free_data(handle, inode, NULL, i_data+offsets[0], i_data + EXT4_NDIR_BLOCKS); @@ -1491,31 +1301,6 @@ do_indirects: case EXT4_TIND_BLOCK: ; } - -out_unlock: - up_write(&ei->i_data_sem); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - - /* - * In a multi-transaction truncate, we only make the final transaction - * synchronous - */ - if (IS_SYNC(inode)) - ext4_handle_sync(handle); -out_stop: - /* - * If this was a simple ftruncate(), and the file will remain alive - * then we need to clear up the orphan record which we created above. - * However, if this was a real unlink then we were called by - * ext4_delete_inode(), and we allow that function to clean up the - * orphan info for us. - */ - if (inode->i_nlink) - ext4_orphan_del(handle, inode); - - ext4_journal_stop(handle); - trace_ext4_truncate_exit(inode); } static int free_hole_blocks(handle_t *handle, struct inode *inode, @@ -1539,9 +1324,9 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode, blk = *i_data; if (level > 0) { ext4_lblk_t first2; - bh = sb_bread(inode->i_sb, blk); + bh = sb_bread(inode->i_sb, le32_to_cpu(blk)); if (!bh) { - EXT4_ERROR_INODE_BLOCK(inode, blk, + EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk), "Read failure"); return -EIO; } @@ -1569,8 +1354,8 @@ err: return ret; } -static int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t first, ext4_lblk_t stop) +int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, + ext4_lblk_t first, ext4_lblk_t stop) { int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); int level, ret = 0; @@ -1604,157 +1389,3 @@ err: return ret; } -int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length) -{ - struct inode *inode = file_inode(file); - struct super_block *sb = inode->i_sb; - ext4_lblk_t first_block, stop_block; - struct address_space *mapping = inode->i_mapping; - handle_t *handle = NULL; - loff_t first_page, last_page, page_len; - loff_t first_page_offset, last_page_offset; - int err = 0; - - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - if (err) - return err; - } - - mutex_lock(&inode->i_mutex); - /* It's not possible punch hole on append only file */ - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { - err = -EPERM; - goto out_mutex; - } - if (IS_SWAPFILE(inode)) { - err = -ETXTBSY; - goto out_mutex; - } - - /* No need to punch hole beyond i_size */ - if (offset >= inode->i_size) - goto out_mutex; - - /* - * If the hole extents beyond i_size, set the hole - * to end after the page that contains i_size - */ - if (offset + length > inode->i_size) { - length = inode->i_size + - PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - - offset; - } - - first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - last_page = (offset + length) >> PAGE_CACHE_SHIFT; - - first_page_offset = first_page << PAGE_CACHE_SHIFT; - last_page_offset = last_page << PAGE_CACHE_SHIFT; - - /* Now release the pages */ - if (last_page_offset > first_page_offset) { - truncate_pagecache_range(inode, first_page_offset, - last_page_offset - 1); - } - - /* Wait all existing dio works, newcomers will block on i_mutex */ - inode_dio_wait(inode); - - handle = start_transaction(inode); - if (IS_ERR(handle)) - goto out_mutex; - - /* - * Now we need to zero out the non-page-aligned data in the - * pages at the start and tail of the hole, and unmap the buffer - * heads for the block aligned regions of the page that were - * completely zerod. - */ - if (first_page > last_page) { - /* - * If the file space being truncated is contained within a page - * just zero out and unmap the middle of that page - */ - err = ext4_discard_partial_page_buffers(handle, - mapping, offset, length, 0); - if (err) - goto out; - } else { - /* - * Zero out and unmap the paritial page that contains - * the start of the hole - */ - page_len = first_page_offset - offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - offset, page_len, 0); - if (err) - goto out; - } - - /* - * Zero out and unmap the partial page that contains - * the end of the hole - */ - page_len = offset + length - last_page_offset; - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, mapping, - last_page_offset, page_len, 0); - if (err) - goto out; - } - } - - /* - * If i_size contained in the last page, we need to - * unmap and zero the paritial page after i_size - */ - if (inode->i_size >> PAGE_CACHE_SHIFT == last_page && - inode->i_size % PAGE_CACHE_SIZE != 0) { - page_len = PAGE_CACHE_SIZE - - (inode->i_size & (PAGE_CACHE_SIZE - 1)); - if (page_len > 0) { - err = ext4_discard_partial_page_buffers(handle, - mapping, inode->i_size, page_len, 0); - if (err) - goto out; - } - } - - first_block = (offset + sb->s_blocksize - 1) >> - EXT4_BLOCK_SIZE_BITS(sb); - stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); - - if (first_block >= stop_block) - goto out; - - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); - - err = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - err = ext4_free_hole_blocks(handle, inode, first_block, stop_block); - - ext4_discard_preallocations(inode); - - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - - up_write(&EXT4_I(inode)->i_data_sem); - -out: - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_journal_stop(handle); - -out_mutex: - mutex_unlock(&inode->i_mutex); - - return err; -} diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index c0fd1a1..3e2bf87 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -19,7 +19,8 @@ #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) -#define EXT4_INLINE_DOTDOT_SIZE 4 +#define EXT4_INLINE_DOTDOT_OFFSET 2 +#define EXT4_INLINE_DOTDOT_SIZE 4 int ext4_get_inline_size(struct inode *inode) { @@ -1289,6 +1290,120 @@ out: return ret; } +/* + * This function fills a red-black tree with information from an + * inlined dir. It returns the number directory entries loaded + * into the tree. If there is an error it is returned in err. + */ +int htree_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data) +{ + int err = 0, count = 0; + unsigned int parent_ino; + int pos; + struct ext4_dir_entry_2 *de; + struct inode *inode = file_inode(dir_file); + int ret, inline_size = 0; + struct ext4_iloc iloc; + void *dir_buf = NULL; + struct ext4_dir_entry_2 fake; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + up_read(&EXT4_I(inode)->xattr_sem); + *has_inline_data = 0; + goto out; + } + + inline_size = ext4_get_inline_size(inode); + dir_buf = kmalloc(inline_size, GFP_NOFS); + if (!dir_buf) { + ret = -ENOMEM; + up_read(&EXT4_I(inode)->xattr_sem); + goto out; + } + + ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); + up_read(&EXT4_I(inode)->xattr_sem); + if (ret < 0) + goto out; + + pos = 0; + parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); + while (pos < inline_size) { + /* + * As inlined dir doesn't store any information about '.' and + * only the inode number of '..' is stored, we have to handle + * them differently. + */ + if (pos == 0) { + fake.inode = cpu_to_le32(inode->i_ino); + fake.name_len = 1; + strcpy(fake.name, "."); + fake.rec_len = ext4_rec_len_to_disk( + EXT4_DIR_REC_LEN(fake.name_len), + inline_size); + ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); + de = &fake; + pos = EXT4_INLINE_DOTDOT_OFFSET; + } else if (pos == EXT4_INLINE_DOTDOT_OFFSET) { + fake.inode = cpu_to_le32(parent_ino); + fake.name_len = 2; + strcpy(fake.name, ".."); + fake.rec_len = ext4_rec_len_to_disk( + EXT4_DIR_REC_LEN(fake.name_len), + inline_size); + ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); + de = &fake; + pos = EXT4_INLINE_DOTDOT_SIZE; + } else { + de = (struct ext4_dir_entry_2 *)(dir_buf + pos); + pos += ext4_rec_len_from_disk(de->rec_len, inline_size); + if (ext4_check_dir_entry(inode, dir_file, de, + iloc.bh, dir_buf, + inline_size, pos)) { + ret = count; + goto out; + } + } + + ext4fs_dirhash(de->name, de->name_len, hinfo); + if ((hinfo->hash < start_hash) || + ((hinfo->hash == start_hash) && + (hinfo->minor_hash < start_minor_hash))) + continue; + if (de->inode == 0) + continue; + err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de); + if (err) { + count = err; + goto out; + } + count++; + } + ret = count; +out: + kfree(dir_buf); + brelse(iloc.bh); + return ret; +} + +/* + * So this function is called when the volume is mkfsed with + * dir_index disabled. In order to keep f_pos persistent + * after we convert from an inlined dir to a blocked based, + * we just pretend that we are a normal dir and return the + * offset as if '.' and '..' really take place. + * + */ int ext4_read_inline_dir(struct file *filp, void *dirent, filldir_t filldir, int *has_inline_data) @@ -1302,6 +1417,7 @@ int ext4_read_inline_dir(struct file *filp, int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; + int dotdot_offset, dotdot_size, extra_offset, extra_size; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -1330,8 +1446,21 @@ int ext4_read_inline_dir(struct file *filp, sb = inode->i_sb; stored = 0; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); + offset = filp->f_pos; - while (!error && !stored && filp->f_pos < inode->i_size) { + /* + * dotdot_offset and dotdot_size is the real offset and + * size for ".." and "." if the dir is block based while + * the real size for them are only EXT4_INLINE_DOTDOT_SIZE. + * So we will use extra_offset and extra_size to indicate them + * during the inline dir iteration. + */ + dotdot_offset = EXT4_DIR_REC_LEN(1); + dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2); + extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; + extra_size = extra_offset + inline_size; + + while (!error && !stored && filp->f_pos < extra_size) { revalidate: /* * If the version has changed since the last call to @@ -1340,15 +1469,23 @@ revalidate: * dir to make sure. */ if (filp->f_version != inode->i_version) { - for (i = 0; - i < inode->i_size && i < offset;) { + for (i = 0; i < extra_size && i < offset;) { + /* + * "." is with offset 0 and + * ".." is dotdot_offset. + */ if (!i) { - /* skip "." and ".." if needed. */ - i += EXT4_INLINE_DOTDOT_SIZE; + i = dotdot_offset; + continue; + } else if (i == dotdot_offset) { + i = dotdot_size; continue; } + /* for other entry, the real offset in + * the buf has to be tuned accordingly. + */ de = (struct ext4_dir_entry_2 *) - (dir_buf + i); + (dir_buf + i - extra_offset); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at @@ -1356,43 +1493,47 @@ revalidate: * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, - inline_size) < EXT4_DIR_REC_LEN(1)) + extra_size) < EXT4_DIR_REC_LEN(1)) break; i += ext4_rec_len_from_disk(de->rec_len, - inline_size); + extra_size); } offset = i; filp->f_pos = offset; filp->f_version = inode->i_version; } - while (!error && filp->f_pos < inode->i_size) { + while (!error && filp->f_pos < extra_size) { if (filp->f_pos == 0) { error = filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR); if (error) break; stored++; + filp->f_pos = dotdot_offset; + continue; + } - error = filldir(dirent, "..", 2, 0, parent_ino, - DT_DIR); + if (filp->f_pos == dotdot_offset) { + error = filldir(dirent, "..", 2, + dotdot_offset, + parent_ino, DT_DIR); if (error) break; stored++; - filp->f_pos = offset = EXT4_INLINE_DOTDOT_SIZE; + filp->f_pos = dotdot_size; continue; } - de = (struct ext4_dir_entry_2 *)(dir_buf + offset); + de = (struct ext4_dir_entry_2 *) + (dir_buf + filp->f_pos - extra_offset); if (ext4_check_dir_entry(inode, filp, de, iloc.bh, dir_buf, - inline_size, offset)) { + extra_size, filp->f_pos)) { ret = stored; goto out; } - offset += ext4_rec_len_from_disk(de->rec_len, - inline_size); if (le32_to_cpu(de->inode)) { /* We might block in the next section * if the data destination is @@ -1415,9 +1556,8 @@ revalidate: stored++; } filp->f_pos += ext4_rec_len_from_disk(de->rec_len, - inline_size); + extra_size); } - offset = 0; } out: kfree(dir_buf); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b3a5213..793d44b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -55,21 +55,21 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, __u16 csum_hi = 0; __u32 csum; - csum_lo = raw->i_checksum_lo; + csum_lo = le16_to_cpu(raw->i_checksum_lo); raw->i_checksum_lo = 0; if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { - csum_hi = raw->i_checksum_hi; + csum_hi = le16_to_cpu(raw->i_checksum_hi); raw->i_checksum_hi = 0; } csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, EXT4_INODE_SIZE(inode->i_sb)); - raw->i_checksum_lo = csum_lo; + raw->i_checksum_lo = cpu_to_le16(csum_lo); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) - raw->i_checksum_hi = csum_hi; + raw->i_checksum_hi = cpu_to_le16(csum_hi); return csum; } @@ -210,8 +210,7 @@ void ext4_evict_inode(struct inode *inode) journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; - jbd2_log_start_commit(journal, commit_tid); - jbd2_log_wait_commit(journal, commit_tid); + jbd2_complete_transaction(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } truncate_inode_pages(&inode->i_data, 0); @@ -1081,20 +1080,42 @@ retry_journal: /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct buffer_head *bh) { + int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; set_buffer_uptodate(bh); - return ext4_handle_dirty_metadata(handle, NULL, bh); + ret = ext4_handle_dirty_metadata(handle, NULL, bh); + clear_buffer_meta(bh); + clear_buffer_prio(bh); + return ret; } -static int ext4_generic_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +/* + * We need to pick up the new inode size which generic_commit_write gave us + * `file' can be NULL - eg, when called from page_symlink(). + * + * ext4 never places buffers on inode->i_mapping->private_list. metadata + * buffers are managed internally. + */ +static int ext4_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { - int i_size_changed = 0; - struct inode *inode = mapping->host; handle_t *handle = ext4_journal_current_handle(); + struct inode *inode = mapping->host; + int ret = 0, ret2; + int i_size_changed = 0; + + trace_ext4_write_end(inode, pos, len, copied); + if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) { + ret = ext4_jbd2_file_inode(handle, inode); + if (ret) { + unlock_page(page); + page_cache_release(page); + goto errout; + } + } if (ext4_has_inline_data(inode)) copied = ext4_write_inline_data_end(inode, pos, len, @@ -1105,7 +1126,7 @@ static int ext4_generic_write_end(struct file *file, /* * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. + * cannot change under us because we hole i_mutex. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. @@ -1115,10 +1136,10 @@ static int ext4_generic_write_end(struct file *file, i_size_changed = 1; } - if (pos + copied > EXT4_I(inode)->i_disksize) { + if (pos + copied > EXT4_I(inode)->i_disksize) { /* We need to mark inode dirty even if * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) + * but greater than i_disksize. (hint delalloc) */ ext4_update_i_disksize(inode, (pos + copied)); i_size_changed = 1; @@ -1135,87 +1156,15 @@ static int ext4_generic_write_end(struct file *file, if (i_size_changed) ext4_mark_inode_dirty(handle, inode); - return copied; -} - -/* - * We need to pick up the new inode size which generic_commit_write gave us - * `file' can be NULL - eg, when called from page_symlink(). - * - * ext4 never places buffers on inode->i_mapping->private_list. metadata - * buffers are managed internally. - */ -static int ext4_ordered_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - handle_t *handle = ext4_journal_current_handle(); - struct inode *inode = mapping->host; - int ret = 0, ret2; - - trace_ext4_ordered_write_end(inode, pos, len, copied); - ret = ext4_jbd2_file_inode(handle, inode); - - if (ret == 0) { - ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - copied = ret2; - if (pos + len > inode->i_size && ext4_can_truncate(inode)) - /* if we have allocated more blocks and copied - * less. We will have blocks allocated outside - * inode->i_size. So truncate them - */ - ext4_orphan_add(handle, inode); - if (ret2 < 0) - ret = ret2; - } else { - unlock_page(page); - page_cache_release(page); - } - - ret2 = ext4_journal_stop(handle); - if (!ret) - ret = ret2; - - if (pos + len > inode->i_size) { - ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode - * is removed from the orphan list in that case. - */ - if (inode->i_nlink) - ext4_orphan_del(NULL, inode); - } - - - return ret ? ret : copied; -} - -static int ext4_writeback_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - handle_t *handle = ext4_journal_current_handle(); - struct inode *inode = mapping->host; - int ret = 0, ret2; - - trace_ext4_writeback_write_end(inode, pos, len, copied); - ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - copied = ret2; + if (copied < 0) + ret = copied; if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); - - if (ret2 < 0) - ret = ret2; - +errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1538,7 +1487,10 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, struct ext4_io_submit io_submit; BUG_ON(mpd->next_page <= mpd->first_page); - memset(&io_submit, 0, sizeof(io_submit)); + ext4_io_submit_init(&io_submit, mpd->wbc); + io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_submit.io_end) + return -ENOMEM; /* * We need to start from the first_page to the next_page - 1 * to make sure we also write the mapped dirty buffer_heads. @@ -1626,6 +1578,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, pagevec_release(&pvec); } ext4_io_submit(&io_submit); + /* Drop io_end reference we got from init */ + ext4_put_io_end_defer(io_submit.io_end); return ret; } @@ -1670,22 +1624,25 @@ static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct super_block *sb = inode->i_sb; + struct ext4_inode_info *ei = EXT4_I(inode); ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld", EXT4_C2B(EXT4_SB(inode->i_sb), - ext4_count_free_clusters(inode->i_sb))); + ext4_count_free_clusters(sb))); ext4_msg(sb, KERN_CRIT, "Free/Dirty block details"); ext4_msg(sb, KERN_CRIT, "free_blocks=%lld", - (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld", - (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_dirtyclusters_counter))); ext4_msg(sb, KERN_CRIT, "Block reservation details"); ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u", - EXT4_I(inode)->i_reserved_data_blocks); + ei->i_reserved_data_blocks); ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u", - EXT4_I(inode)->i_reserved_meta_blocks); + ei->i_reserved_meta_blocks); + ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u", + ei->i_allocated_meta_blocks); return; } @@ -1740,12 +1697,21 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) */ map.m_lblk = next; map.m_len = max_blocks; - get_blocks_flags = EXT4_GET_BLOCKS_CREATE; + /* + * We're in delalloc path and it is possible that we're going to + * need more metadata blocks than previously reserved. However + * we must not fail because we're in writeback and there is + * nothing we can do about it so it might result in data loss. + * So use reserved blocks to allocate metadata if possible. + */ + get_blocks_flags = EXT4_GET_BLOCKS_CREATE | + EXT4_GET_BLOCKS_METADATA_NOFAIL; if (ext4_should_dioread_nolock(mpd->inode)) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; if (mpd->b_state & (1 << BH_Delay)) get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; + blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags); if (blks < 0) { struct super_block *sb = mpd->inode->i_sb; @@ -2272,9 +2238,16 @@ static int ext4_writepage(struct page *page, */ return __ext4_journalled_writepage(page, len); - memset(&io_submit, 0, sizeof(io_submit)); + ext4_io_submit_init(&io_submit, wbc); + io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_submit.io_end) { + redirty_page_for_writepage(wbc, page); + return -ENOMEM; + } ret = ext4_bio_write_page(&io_submit, page, len, wbc); ext4_io_submit(&io_submit); + /* Drop io_end reference we got from init */ + ext4_put_io_end_defer(io_submit.io_end); return ret; } @@ -2661,7 +2634,7 @@ out_writepages: static int ext4_nonda_switch(struct super_block *sb) { - s64 free_blocks, dirty_blocks; + s64 free_clusters, dirty_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* @@ -2672,17 +2645,18 @@ static int ext4_nonda_switch(struct super_block *sb) * Delalloc need an accurate free block accounting. So switch * to non delalloc when we are near to error range. */ - free_blocks = EXT4_C2B(sbi, - percpu_counter_read_positive(&sbi->s_freeclusters_counter)); - dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); + free_clusters = + percpu_counter_read_positive(&sbi->s_freeclusters_counter); + dirty_clusters = + percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); /* * Start pushing delalloc when 1/2 of free blocks are dirty. */ - if (dirty_blocks && (free_blocks < 2 * dirty_blocks)) + if (dirty_clusters && (free_clusters < 2 * dirty_clusters)) try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); - if (2 * free_blocks < 3 * dirty_blocks || - free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { + if (2 * free_clusters < 3 * dirty_clusters || + free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) { /* * free block count is less than 150% of dirty blocks * or free blocks is less than watermark @@ -2818,18 +2792,9 @@ static int ext4_da_write_end(struct file *file, unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; - if (write_mode == FALL_BACK_TO_NONDELALLOC) { - switch (ext4_inode_journal_mode(inode)) { - case EXT4_INODE_ORDERED_DATA_MODE: - return ext4_ordered_write_end(file, mapping, pos, - len, copied, page, fsdata); - case EXT4_INODE_WRITEBACK_DATA_MODE: - return ext4_writeback_write_end(file, mapping, pos, - len, copied, page, fsdata); - default: - BUG(); - } - } + if (write_mode == FALL_BACK_TO_NONDELALLOC) + return ext4_write_end(file, mapping, pos, + len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); start = pos & (PAGE_CACHE_SIZE - 1); @@ -3113,9 +3078,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, struct inode *inode = file_inode(iocb->ki_filp); ext4_io_end_t *io_end = iocb->private; - /* if not async direct IO or dio with 0 bytes write, just return */ - if (!io_end || !size) - goto out; + /* if not async direct IO just return */ + if (!io_end) { + inode_dio_done(inode); + if (is_async) + aio_complete(iocb, ret, 0); + return; + } ext_debug("ext4_end_io_dio(): io_end 0x%p " "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", @@ -3123,25 +3092,13 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, size); iocb->private = NULL; - - /* if not aio dio with unwritten extents, just free io and return */ - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - ext4_free_io_end(io_end); -out: - inode_dio_done(inode); - if (is_async) - aio_complete(iocb, ret, 0); - return; - } - io_end->offset = offset; io_end->size = size; if (is_async) { io_end->iocb = iocb; io_end->result = ret; } - - ext4_add_complete_io(io_end); + ext4_put_io_end_defer(io_end); } /* @@ -3175,6 +3132,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, get_block_t *get_block_func = NULL; int dio_flags = 0; loff_t final_size = offset + count; + ext4_io_end_t *io_end = NULL; /* Use the old path for reads and writes beyond i_size. */ if (rw != WRITE || final_size > inode->i_size) @@ -3213,13 +3171,16 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, iocb->private = NULL; ext4_inode_aio_set(inode, NULL); if (!is_sync_kiocb(iocb)) { - ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); + io_end = ext4_init_io_end(inode, GFP_NOFS); if (!io_end) { ret = -ENOMEM; goto retake_lock; } io_end->flag |= EXT4_IO_END_DIRECT; - iocb->private = io_end; + /* + * Grab reference for DIO. Will be dropped in ext4_end_io_dio() + */ + iocb->private = ext4_get_io_end(io_end); /* * we save the io structure for current async direct * IO, so that later ext4_map_blocks() could flag the @@ -3243,26 +3204,27 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, NULL, dio_flags); - if (iocb->private) - ext4_inode_aio_set(inode, NULL); /* - * The io_end structure takes a reference to the inode, that - * structure needs to be destroyed and the reference to the - * inode need to be dropped, when IO is complete, even with 0 - * byte write, or failed. - * - * In the successful AIO DIO case, the io_end structure will - * be destroyed and the reference to the inode will be dropped - * after the end_io call back function is called. - * - * In the case there is 0 byte write, or error case, since VFS - * direct IO won't invoke the end_io call back function, we - * need to free the end_io structure here. + * Put our reference to io_end. This can free the io_end structure e.g. + * in sync IO case or in case of error. It can even perform extent + * conversion if all bios we submitted finished before we got here. + * Note that in that case iocb->private can be already set to NULL + * here. */ - if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { - ext4_free_io_end(iocb->private); - iocb->private = NULL; - } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode, + if (io_end) { + ext4_inode_aio_set(inode, NULL); + ext4_put_io_end(io_end); + /* + * In case of error or no write ext4_end_io_dio() was not + * called so we have to put iocb's reference. + */ + if (ret <= 0 && ret != -EIOCBQUEUED) { + WARN_ON(iocb->private != io_end); + ext4_put_io_end(io_end); + iocb->private = NULL; + } + } + if (ret > 0 && !overwrite && ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN)) { int err; /* @@ -3334,27 +3296,12 @@ static int ext4_journalled_set_page_dirty(struct page *page) return __set_page_dirty_nobuffers(page); } -static const struct address_space_operations ext4_ordered_aops = { +static const struct address_space_operations ext4_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, .write_begin = ext4_write_begin, - .write_end = ext4_ordered_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, - .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, -}; - -static const struct address_space_operations ext4_writeback_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_writepage, - .write_begin = ext4_write_begin, - .write_end = ext4_writeback_write_end, + .write_end = ext4_write_end, .bmap = ext4_bmap, .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, @@ -3399,23 +3346,21 @@ void ext4_set_aops(struct inode *inode) { switch (ext4_inode_journal_mode(inode)) { case EXT4_INODE_ORDERED_DATA_MODE: - if (test_opt(inode->i_sb, DELALLOC)) - inode->i_mapping->a_ops = &ext4_da_aops; - else - inode->i_mapping->a_ops = &ext4_ordered_aops; + ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE); break; case EXT4_INODE_WRITEBACK_DATA_MODE: - if (test_opt(inode->i_sb, DELALLOC)) - inode->i_mapping->a_ops = &ext4_da_aops; - else - inode->i_mapping->a_ops = &ext4_writeback_aops; + ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE); break; case EXT4_INODE_JOURNAL_DATA_MODE: inode->i_mapping->a_ops = &ext4_journalled_aops; - break; + return; default: BUG(); } + if (test_opt(inode->i_sb, DELALLOC)) + inode->i_mapping->a_ops = &ext4_da_aops; + else + inode->i_mapping->a_ops = &ext4_aops; } @@ -3646,20 +3591,190 @@ int ext4_can_truncate(struct inode *inode) int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { struct inode *inode = file_inode(file); + struct super_block *sb = inode->i_sb; + ext4_lblk_t first_block, stop_block; + struct address_space *mapping = inode->i_mapping; + loff_t first_page, last_page, page_len; + loff_t first_page_offset, last_page_offset; + handle_t *handle; + unsigned int credits; + int ret = 0; + if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return ext4_ind_punch_hole(file, offset, length); - - if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) { + if (EXT4_SB(sb)->s_cluster_ratio > 1) { /* TODO: Add support for bigalloc file systems */ return -EOPNOTSUPP; } trace_ext4_punch_hole(inode, offset, length); - return ext4_ext_punch_hole(file, offset, length); + /* + * Write out all dirty pages to avoid race conditions + * Then release them. + */ + if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + ret = filemap_write_and_wait_range(mapping, offset, + offset + length - 1); + if (ret) + return ret; + } + + mutex_lock(&inode->i_mutex); + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + ret = -EPERM; + goto out_mutex; + } + if (IS_SWAPFILE(inode)) { + ret = -ETXTBSY; + goto out_mutex; + } + + /* No need to punch hole beyond i_size */ + if (offset >= inode->i_size) + goto out_mutex; + + /* + * If the hole extends beyond i_size, set the hole + * to end after the page that contains i_size + */ + if (offset + length > inode->i_size) { + length = inode->i_size + + PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) - + offset; + } + + first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + last_page = (offset + length) >> PAGE_CACHE_SHIFT; + + first_page_offset = first_page << PAGE_CACHE_SHIFT; + last_page_offset = last_page << PAGE_CACHE_SHIFT; + + /* Now release the pages */ + if (last_page_offset > first_page_offset) { + truncate_pagecache_range(inode, first_page_offset, + last_page_offset - 1); + } + + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + ret = ext4_flush_unwritten_io(inode); + if (ret) + goto out_dio; + inode_dio_wait(inode); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + credits = ext4_writepage_trans_blocks(inode); + else + credits = ext4_blocks_for_truncate(inode); + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + ext4_std_error(sb, ret); + goto out_dio; + } + + /* + * Now we need to zero out the non-page-aligned data in the + * pages at the start and tail of the hole, and unmap the + * buffer heads for the block aligned regions of the page that + * were completely zeroed. + */ + if (first_page > last_page) { + /* + * If the file space being truncated is contained + * within a page just zero out and unmap the middle of + * that page + */ + ret = ext4_discard_partial_page_buffers(handle, + mapping, offset, length, 0); + + if (ret) + goto out_stop; + } else { + /* + * zero out and unmap the partial page that contains + * the start of the hole + */ + page_len = first_page_offset - offset; + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers(handle, mapping, + offset, page_len, 0); + if (ret) + goto out_stop; + } + + /* + * zero out and unmap the partial page that contains + * the end of the hole + */ + page_len = offset + length - last_page_offset; + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers(handle, mapping, + last_page_offset, page_len, 0); + if (ret) + goto out_stop; + } + } + + /* + * If i_size is contained in the last page, we need to + * unmap and zero the partial page after i_size + */ + if (inode->i_size >> PAGE_CACHE_SHIFT == last_page && + inode->i_size % PAGE_CACHE_SIZE != 0) { + page_len = PAGE_CACHE_SIZE - + (inode->i_size & (PAGE_CACHE_SIZE - 1)); + + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers(handle, + mapping, inode->i_size, page_len, 0); + + if (ret) + goto out_stop; + } + } + + first_block = (offset + sb->s_blocksize - 1) >> + EXT4_BLOCK_SIZE_BITS(sb); + stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); + + /* If there are no blocks to remove, return now */ + if (first_block >= stop_block) + goto out_stop; + + down_write(&EXT4_I(inode)->i_data_sem); + ext4_discard_preallocations(inode); + + ret = ext4_es_remove_extent(inode, first_block, + stop_block - first_block); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + ret = ext4_ext_remove_space(inode, first_block, + stop_block - 1); + else + ret = ext4_free_hole_blocks(handle, inode, first_block, + stop_block); + + ext4_discard_preallocations(inode); + up_write(&EXT4_I(inode)->i_data_sem); + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); +out_stop: + ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); + return ret; } /* @@ -3692,6 +3807,19 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) */ void ext4_truncate(struct inode *inode) { + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int credits; + handle_t *handle; + struct address_space *mapping = inode->i_mapping; + loff_t page_len; + + /* + * There is a possibility that we're either freeing the inode + * or it completely new indode. In those cases we might not + * have i_mutex locked because it's not necessary. + */ + if (!(inode->i_state & (I_NEW|I_FREEING))) + WARN_ON(!mutex_is_locked(&inode->i_mutex)); trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) @@ -3710,10 +3838,72 @@ void ext4_truncate(struct inode *inode) return; } + /* + * finish any pending end_io work so we won't run the risk of + * converting any truncated blocks to initialized later + */ + ext4_flush_unwritten_io(inode); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + credits = ext4_writepage_trans_blocks(inode); + else + credits = ext4_blocks_for_truncate(inode); + + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); + if (IS_ERR(handle)) { + ext4_std_error(inode->i_sb, PTR_ERR(handle)); + return; + } + + if (inode->i_size % PAGE_CACHE_SIZE != 0) { + page_len = PAGE_CACHE_SIZE - + (inode->i_size & (PAGE_CACHE_SIZE - 1)); + + if (ext4_discard_partial_page_buffers(handle, + mapping, inode->i_size, page_len, 0)) + goto out_stop; + } + + /* + * We add the inode to the orphan list, so that if this + * truncate spans multiple transactions, and we crash, we will + * resume the truncate when the filesystem recovers. It also + * marks the inode dirty, to catch the new size. + * + * Implication: the file must always be in a sane, consistent + * truncatable state while each transaction commits. + */ + if (ext4_orphan_add(handle, inode)) + goto out_stop; + + down_write(&EXT4_I(inode)->i_data_sem); + + ext4_discard_preallocations(inode); + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ext4_ext_truncate(inode); + ext4_ext_truncate(handle, inode); else - ext4_ind_truncate(inode); + ext4_ind_truncate(handle, inode); + + up_write(&ei->i_data_sem); + + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + +out_stop: + /* + * If this was a simple ftruncate() and the file will remain alive, + * then we need to clear up the orphan record which we created above. + * However, if this was a real unlink then we were called by + * ext4_delete_inode(), and we allow that function to clean up the + * orphan info for us. + */ + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); trace_ext4_truncate_exit(inode); } @@ -3821,13 +4011,14 @@ make_io: if (EXT4_SB(sb)->s_inode_readahead_blks) { ext4_fsblk_t b, end, table; unsigned num; + __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks; table = ext4_inode_table(sb, gdp); /* s_inode_readahead_blks is always a power of 2 */ - b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1); + b = block & ~((ext4_fsblk_t) ra_blks - 1); if (table > b) b = table; - end = b + EXT4_SB(sb)->s_inode_readahead_blks; + end = b + ra_blks; num = EXT4_INODES_PER_GROUP(sb); if (ext4_has_group_desc_csum(sb)) num -= ext4_itable_unused_count(sb, gdp); @@ -4024,8 +4215,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { - if (inode->i_mode == 0 || - !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { + if ((inode->i_mode == 0 || + !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && + ino != EXT4_BOOT_LOADER_INO) { /* this inode is deleted */ ret = -ESTALE; goto bad_inode; @@ -4033,7 +4225,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) /* The only unlinked inodes we let through here have * valid i_mode and are being read by the orphan * recovery code: that's fine, we're about to complete - * the process of deleting those. */ + * the process of deleting those. + * OR it is the EXT4_BOOT_LOADER_INO which is + * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); @@ -4153,6 +4347,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); + } else if (ino == EXT4_BOOT_LOADER_INO) { + make_bad_inode(inode); } else { ret = -EIO; EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 721f4d3..9491ac0 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -17,9 +17,201 @@ #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) +/** + * Swap memory between @a and @b for @len bytes. + * + * @a: pointer to first memory area + * @b: pointer to second memory area + * @len: number of bytes to swap + * + */ +static void memswap(void *a, void *b, size_t len) +{ + unsigned char *ap, *bp; + unsigned char tmp; + + ap = (unsigned char *)a; + bp = (unsigned char *)b; + while (len-- > 0) { + tmp = *ap; + *ap = *bp; + *bp = tmp; + ap++; + bp++; + } +} + +/** + * Swap i_data and associated attributes between @inode1 and @inode2. + * This function is used for the primary swap between inode1 and inode2 + * and also to revert this primary swap in case of errors. + * + * Therefore you have to make sure, that calling this method twice + * will revert all changes. + * + * @inode1: pointer to first inode + * @inode2: pointer to second inode + */ +static void swap_inode_data(struct inode *inode1, struct inode *inode2) +{ + loff_t isize; + struct ext4_inode_info *ei1; + struct ext4_inode_info *ei2; + + ei1 = EXT4_I(inode1); + ei2 = EXT4_I(inode2); + + memswap(&inode1->i_flags, &inode2->i_flags, sizeof(inode1->i_flags)); + memswap(&inode1->i_version, &inode2->i_version, + sizeof(inode1->i_version)); + memswap(&inode1->i_blocks, &inode2->i_blocks, + sizeof(inode1->i_blocks)); + memswap(&inode1->i_bytes, &inode2->i_bytes, sizeof(inode1->i_bytes)); + memswap(&inode1->i_atime, &inode2->i_atime, sizeof(inode1->i_atime)); + memswap(&inode1->i_mtime, &inode2->i_mtime, sizeof(inode1->i_mtime)); + + 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)); + + isize = i_size_read(inode1); + i_size_write(inode1, i_size_read(inode2)); + i_size_write(inode2, isize); +} + +/** + * Swap the information from the given @inode and the inode + * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other + * important fields of the inodes. + * + * @sb: the super block of the filesystem + * @inode: the inode to swap with EXT4_BOOT_LOADER_INO + * + */ +static long swap_inode_boot_loader(struct super_block *sb, + struct inode *inode) +{ + handle_t *handle; + int err; + struct inode *inode_bl; + struct ext4_inode_info *ei; + struct ext4_inode_info *ei_bl; + struct ext4_sb_info *sbi; + + if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) { + err = -EINVAL; + goto swap_boot_out; + } + + if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto swap_boot_out; + } + + sbi = EXT4_SB(sb); + ei = EXT4_I(inode); + + inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO); + if (IS_ERR(inode_bl)) { + err = PTR_ERR(inode_bl); + goto swap_boot_out; + } + ei_bl = EXT4_I(inode_bl); + + filemap_flush(inode->i_mapping); + filemap_flush(inode_bl->i_mapping); + + /* Protect orig inodes against a truncate and make sure, + * that only 1 swap_inode_boot_loader is running. */ + ext4_inode_double_lock(inode, inode_bl); + + truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages(&inode_bl->i_data, 0); + + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(inode); + ext4_inode_block_unlocked_dio(inode_bl); + inode_dio_wait(inode); + inode_dio_wait(inode_bl); + + handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); + if (IS_ERR(handle)) { + err = -EINVAL; + goto swap_boot_out; + } + + /* Protect extent tree against block allocations via delalloc */ + ext4_double_down_write_data_sem(inode, inode_bl); + + if (inode_bl->i_nlink == 0) { + /* this inode has never been used as a BOOT_LOADER */ + set_nlink(inode_bl, 1); + i_uid_write(inode_bl, 0); + i_gid_write(inode_bl, 0); + inode_bl->i_flags = 0; + ei_bl->i_flags = 0; + inode_bl->i_version = 1; + i_size_write(inode_bl, 0); + inode_bl->i_mode = S_IFREG; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_EXTENTS)) { + ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); + ext4_ext_tree_init(handle, inode_bl); + } else + memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); + } + + swap_inode_data(inode, inode_bl); + + inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode); + + spin_lock(&sbi->s_next_gen_lock); + inode->i_generation = sbi->s_next_generation++; + inode_bl->i_generation = sbi->s_next_generation++; + spin_unlock(&sbi->s_next_gen_lock); + + ext4_discard_preallocations(inode); + + err = ext4_mark_inode_dirty(handle, inode); + if (err < 0) { + ext4_warning(inode->i_sb, + "couldn't mark inode #%lu dirty (err %d)", + inode->i_ino, err); + /* Revert all changes: */ + swap_inode_data(inode, inode_bl); + } else { + err = ext4_mark_inode_dirty(handle, inode_bl); + if (err < 0) { + ext4_warning(inode_bl->i_sb, + "couldn't mark inode #%lu dirty (err %d)", + inode_bl->i_ino, err); + /* Revert all changes: */ + swap_inode_data(inode, inode_bl); + ext4_mark_inode_dirty(handle, inode); + } + } + + ext4_journal_stop(handle); + + ext4_double_up_write_data_sem(inode, inode_bl); + + ext4_inode_resume_unlocked_dio(inode); + ext4_inode_resume_unlocked_dio(inode_bl); + + ext4_inode_double_unlock(inode, inode_bl); + + iput(inode_bl); + +swap_boot_out: + return err; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -83,17 +275,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } - if (oldflags & EXT4_EXTENTS_FL) { - /* We don't support clearning extent flags */ - if (!(flags & EXT4_EXTENTS_FL)) { - err = -EOPNOTSUPP; - goto flags_out; - } - } else if (flags & EXT4_EXTENTS_FL) { - /* migrate the file */ + if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; - flags &= ~EXT4_EXTENTS_FL; - } if (flags & EXT4_EOFBLOCKS_FL) { /* we don't support adding EOFBLOCKS flag */ @@ -137,8 +320,13 @@ flags_err: err = ext4_change_inode_journal_flag(inode, jflag); if (err) goto flags_out; - if (migrate) - err = ext4_ext_migrate(inode); + if (migrate) { + if (flags & EXT4_EXTENTS_FL) + err = ext4_ext_migrate(inode); + else + err = ext4_ind_migrate(inode); + } + flags_out: mutex_unlock(&inode->i_mutex); mnt_drop_write_file(filp); @@ -357,9 +545,13 @@ group_add_out: return err; } + case EXT4_IOC_SWAP_BOOT: + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + return swap_inode_boot_loader(sb, inode); + case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; - struct super_block *sb = inode->i_sb; int err = 0, err2 = 0; ext4_group_t o_group = EXT4_SB(sb)->s_groups_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 28e421c..b1ed9e0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -405,6 +405,12 @@ static inline void mb_clear_bit(int bit, void *addr) ext4_clear_bit(bit, addr); } +static inline int mb_test_and_clear_bit(int bit, void *addr) +{ + addr = mb_correct_addr_and_bit(&bit, addr); + return ext4_test_and_clear_bit(bit, addr); +} + static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; @@ -764,6 +770,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, spin_unlock(&EXT4_SB(sb)->s_bal_lock); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) { + ext4_set_bits(buddy, 0, count); + } + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -860,8 +884,6 @@ static int ext4_mb_init_cache(struct page *page, char *incore) first_block = page->index * blocks_per_page; for (i = 0; i < blocks_per_page; i++) { - int group; - group = (first_block + i) >> 1; if (group >= ngroups) break; @@ -1011,6 +1033,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) struct page *page; int ret = 0; + might_sleep(); mb_debug(1, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); /* @@ -1082,6 +1105,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; + might_sleep(); mb_debug(1, "load group %u\n", group); blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; @@ -1244,6 +1268,33 @@ static void mb_clear_bits(void *bm, int cur, int len) } } +/* clear bits in given range + * will return first found zero bit if any, -1 otherwise + */ +static int mb_test_and_clear_bits(void *bm, int cur, int len) +{ + __u32 *addr; + int zero_bit = -1; + + len = cur + len; + while (cur < len) { + if ((cur & 31) == 0 && (len - cur) >= 32) { + /* fast path: clear whole word at once */ + addr = bm + (cur >> 3); + if (*addr != (__u32)(-1) && zero_bit == -1) + zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); + *addr = 0; + cur += 32; + continue; + } + if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) + zero_bit = cur; + cur++; + } + + return zero_bit; +} + void ext4_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1262,17 +1313,90 @@ void ext4_set_bits(void *bm, int cur, int len) } } +/* + * _________________________________________________________________ */ + +static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) +{ + if (mb_test_bit(*bit + side, bitmap)) { + mb_clear_bit(*bit, bitmap); + (*bit) -= side; + return 1; + } + else { + (*bit) += side; + mb_set_bit(*bit, bitmap); + return -1; + } +} + +static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) +{ + int max; + int order = 1; + void *buddy = mb_find_buddy(e4b, order, &max); + + while (buddy) { + void *buddy2; + + /* Bits in range [first; last] are known to be set since + * corresponding blocks were allocated. Bits in range + * (first; last) will stay set because they form buddies on + * upper layer. We just deal with borders if they don't + * align with upper layer and then go up. + * Releasing entire group is all about clearing + * single bit of highest order buddy. + */ + + /* Example: + * --------------------------------- + * | 1 | 1 | 1 | 1 | + * --------------------------------- + * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | + * --------------------------------- + * 0 1 2 3 4 5 6 7 + * \_____________________/ + * + * Neither [1] nor [6] is aligned to above layer. + * Left neighbour [0] is free, so mark it busy, + * decrease bb_counters and extend range to + * [0; 6] + * Right neighbour [7] is busy. It can't be coaleasced with [6], so + * mark [6] free, increase bb_counters and shrink range to + * [0; 5]. + * Then shift range to [0; 2], go up and do the same. + */ + + + if (first & 1) + e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); + if (!(last & 1)) + e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); + if (first > last) + break; + order++; + + if (first == last || !(buddy2 = mb_find_buddy(e4b, order, &max))) { + mb_clear_bits(buddy, first, last - first + 1); + e4b->bd_info->bb_counters[order - 1] += last - first + 1; + break; + } + first >>= 1; + last >>= 1; + buddy = buddy2; + } +} + static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, - int first, int count) + int first, int count) { - int block = 0; - int max = 0; - int order; - void *buddy; - void *buddy2; + int left_is_free = 0; + int right_is_free = 0; + int block; + int last = first + count - 1; struct super_block *sb = e4b->bd_sb; - BUG_ON(first + count > (sb->s_blocksize << 3)); + BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); @@ -1281,67 +1405,54 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; - /* let's maintain fragments counter */ + /* access memory sequentially: check left neighbour, + * clear range and then check right neighbour + */ if (first != 0) - block = !mb_test_bit(first - 1, e4b->bd_bitmap); - if (first + count < EXT4_SB(sb)->s_mb_maxs[0]) - max = !mb_test_bit(first + count, e4b->bd_bitmap); - if (block && max) - e4b->bd_info->bb_fragments--; - else if (!block && !max) - e4b->bd_info->bb_fragments++; + left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); + block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); + if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) + right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); - /* let's maintain buddy itself */ - while (count-- > 0) { - block = first++; - order = 0; + if (unlikely(block != -1)) { + ext4_fsblk_t blocknr; - if (!mb_test_bit(block, e4b->bd_bitmap)) { - ext4_fsblk_t blocknr; - - blocknr = ext4_group_first_block_no(sb, e4b->bd_group); - blocknr += EXT4_C2B(EXT4_SB(sb), block); - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block " - "(bit %u)", block); - } - mb_clear_bit(block, e4b->bd_bitmap); - e4b->bd_info->bb_counters[order]++; - - /* start of the buddy */ - buddy = mb_find_buddy(e4b, order, &max); - - do { - block &= ~1UL; - if (mb_test_bit(block, buddy) || - mb_test_bit(block + 1, buddy)) - break; - - /* both the buddies are free, try to coalesce them */ - buddy2 = mb_find_buddy(e4b, order + 1, &max); + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); + blocknr += EXT4_C2B(EXT4_SB(sb), block); + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, + blocknr, + "freeing already freed block " + "(bit %u)", block); + mb_regenerate_buddy(e4b); + goto done; + } - if (!buddy2) - break; + /* let's maintain fragments counter */ + if (left_is_free && right_is_free) + e4b->bd_info->bb_fragments--; + else if (!left_is_free && !right_is_free) + e4b->bd_info->bb_fragments++; - if (order > 0) { - /* for special purposes, we don't set - * free bits in bitmap */ - mb_set_bit(block, buddy); - mb_set_bit(block + 1, buddy); - } - e4b->bd_info->bb_counters[order]--; - e4b->bd_info->bb_counters[order]--; + /* buddy[0] == bd_bitmap is a special case, so handle + * it right away and let mb_buddy_mark_free stay free of + * zero order checks. + * Check if neighbours are to be coaleasced, + * adjust bitmap bb_counters and borders appropriately. + */ + if (first & 1) { + first += !left_is_free; + e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; + } + if (!(last & 1)) { + last -= !right_is_free; + e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; + } - block = block >> 1; - order++; - e4b->bd_info->bb_counters[order]++; + if (first <= last) + mb_buddy_mark_free(e4b, first >> 1, last >> 1); - mb_clear_bit(block, buddy2); - buddy = buddy2; - } while (1); - } +done: mb_set_largest_free_order(sb, e4b->bd_info); mb_check_buddy(e4b); } @@ -3342,7 +3453,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, if (pa->pa_type == MB_GROUP_PA) grp_blk--; - ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL); + grp = ext4_get_group_number(sb, grp_blk); /* * possible race: @@ -3807,7 +3918,7 @@ repeat: list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); - ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL); + group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { @@ -4069,7 +4180,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { - ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL); + group = ext4_get_group_number(sb, pa->pa_pstart); if (ext4_mb_load_buddy(sb, group, &e4b)) { ext4_error(sb, "Error loading buddy information for %u", group); @@ -4217,6 +4328,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); @@ -4420,11 +4532,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(entry, new_entry)) { + if (can_merge(entry, new_entry) && + ext4_journal_callback_try_del(handle, &entry->efd_jce)) { new_entry->efd_start_cluster = entry->efd_start_cluster; new_entry->efd_count += entry->efd_count; rb_erase(node, &(db->bb_free_root)); - ext4_journal_callback_del(handle, &entry->efd_jce); kmem_cache_free(ext4_free_data_cachep, entry); } } @@ -4432,10 +4544,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(new_entry, entry)) { + if (can_merge(new_entry, entry) && + ext4_journal_callback_try_del(handle, &entry->efd_jce)) { new_entry->efd_count += entry->efd_count; rb_erase(node, &(db->bb_free_root)); - ext4_journal_callback_del(handle, &entry->efd_jce); kmem_cache_free(ext4_free_data_cachep, entry); } } @@ -4470,6 +4582,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, int err = 0; int ret; + might_sleep(); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 480acf4..49e8bdf 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -426,7 +426,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) return retval; } return retval; - } int ext4_ext_migrate(struct inode *inode) @@ -606,3 +605,64 @@ out: return retval; } + +/* + * Migrate a simple extent-based inode to use the i_blocks[] array + */ +int ext4_ind_migrate(struct inode *inode) +{ + struct ext4_extent_header *eh; + struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_extent *ex; + unsigned int i, len; + ext4_fsblk_t blk; + handle_t *handle; + int ret; + + if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_INCOMPAT_EXTENTS) || + (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + return -EINVAL; + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + return -EOPNOTSUPP; + + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + down_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_ext_check_inode(inode); + if (ret) + goto errout; + + eh = ext_inode_hdr(inode); + ex = EXT_FIRST_EXTENT(eh); + if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS || + eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) { + ret = -EOPNOTSUPP; + goto errout; + } + if (eh->eh_entries == 0) + blk = len = 0; + else { + len = le16_to_cpu(ex->ee_len); + blk = ext4_ext_pblock(ex); + if (len > EXT4_NDIR_BLOCKS) { + ret = -EOPNOTSUPP; + goto errout; + } + } + + ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); + memset(ei->i_data, 0, sizeof(ei->i_data)); + for (i=0; i < len; i++) + ei->i_data[i] = cpu_to_le32(blk++); + ext4_mark_inode_dirty(handle, inode); +errout: + ext4_journal_stop(handle); + up_write(&EXT4_I(inode)->i_data_sem); + return ret; +} diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index f9b5515..214461e 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -7,7 +7,7 @@ #include "ext4.h" /* Checksumming functions */ -static __u32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) +static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct mmp_struct, mmp_checksum); @@ -54,7 +54,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); - submit_bh(WRITE_SYNC, bh); + submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) @@ -86,7 +86,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh, get_bh(*bh); lock_buffer(*bh); (*bh)->b_end_io = end_buffer_read_sync; - submit_bh(READ_SYNC, *bh); + submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh); wait_on_buffer(*bh); if (!buffer_uptodate(*bh)) { brelse(*bh); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 33e1c08..3dcbf36 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -144,12 +144,13 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, } /** - * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem + * ext4_double_down_write_data_sem - Acquire two inodes' write lock + * of i_data_sem * * Acquire write lock of i_data_sem of the two inodes */ -static void -double_down_write_data_sem(struct inode *first, struct inode *second) +void +ext4_double_down_write_data_sem(struct inode *first, struct inode *second) { if (first < second) { down_write(&EXT4_I(first)->i_data_sem); @@ -162,14 +163,15 @@ double_down_write_data_sem(struct inode *first, struct inode *second) } /** - * double_up_write_data_sem - Release two inodes' write lock of i_data_sem + * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem * * @orig_inode: original inode structure to be released its lock first * @donor_inode: donor inode structure to be released its lock second * Release write lock of i_data_sem of two inodes (orig and donor). */ -static void -double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) +void +ext4_double_up_write_data_sem(struct inode *orig_inode, + struct inode *donor_inode) { up_write(&EXT4_I(orig_inode)->i_data_sem); up_write(&EXT4_I(donor_inode)->i_data_sem); @@ -407,18 +409,7 @@ mext_insert_extents(handle_t *handle, struct inode *orig_inode, mext_insert_inside_block(o_start, o_end, start_ext, new_ext, end_ext, eh, range_to_move); - if (depth) { - ret = ext4_handle_dirty_metadata(handle, orig_inode, - orig_path->p_bh); - if (ret) - return ret; - } else { - ret = ext4_mark_inode_dirty(handle, orig_inode); - if (ret < 0) - return ret; - } - - return 0; + return ext4_ext_dirty(handle, orig_inode, orig_path); } /** @@ -737,6 +728,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, donor_off += dext_alen; orig_off += dext_alen; + BUG_ON(replaced_count > count); /* Already moved the expected blocks */ if (replaced_count >= count) break; @@ -814,7 +806,13 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, page_cache_release(page[0]); return -ENOMEM; } - + /* + * grab_cache_page_write_begin() may not wait on page's writeback if + * BDI not demand that. But it is reasonable to be very conservative + * here and explicitly wait on page's writeback + */ + wait_on_page_writeback(page[0]); + wait_on_page_writeback(page[1]); if (inode1 > inode2) { struct page *tmp; tmp = page[0]; @@ -856,7 +854,6 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { - int err = 0; err = ext4_get_block(inode, block, bh, 0); if (err) { SetPageError(page); @@ -976,7 +973,7 @@ again: * necessary, just swap data blocks between orig and donor. */ if (uninit) { - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); /* If any of extents in range became initialized we have to * fallback to data copying */ uninit = mext_check_coverage(orig_inode, orig_blk_offset, @@ -990,7 +987,7 @@ again: goto drop_data_sem; if (!uninit) { - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); goto data_copy; } if ((page_has_private(pagep[0]) && @@ -1004,7 +1001,7 @@ again: donor_inode, orig_blk_offset, block_len_in_page, err); drop_data_sem: - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); goto unlock_pages; } data_copy: @@ -1033,7 +1030,7 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, from + replaced_size, + *err = __block_write_begin(pagep[0], from, replaced_size, ext4_get_block); if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); @@ -1065,11 +1062,11 @@ repair_branches: * Extents are swapped already, but we are not able to copy data. * Try to swap extents to it's original places */ - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = mext_replace_branches(handle, donor_inode, orig_inode, orig_blk_offset, block_len_in_page, &err2); - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); if (replaced_count != block_len_in_page) { EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset), "Unable to copy data block," @@ -1209,15 +1206,15 @@ mext_check_arguments(struct inode *orig_inode, } /** - * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2 + * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2 * * @inode1: the inode structure * @inode2: the inode structure * * Lock two inodes' i_mutex */ -static void -mext_inode_double_lock(struct inode *inode1, struct inode *inode2) +void +ext4_inode_double_lock(struct inode *inode1, struct inode *inode2) { BUG_ON(inode1 == inode2); if (inode1 < inode2) { @@ -1230,15 +1227,15 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2) } /** - * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2 + * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2 * * @inode1: the inode that is released first * @inode2: the inode that is released second * */ -static void -mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) +void +ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2) { mutex_unlock(&inode1->i_mutex); mutex_unlock(&inode2->i_mutex); @@ -1333,7 +1330,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, return -EINVAL; } /* Protect orig and donor inodes against a truncate */ - mext_inode_double_lock(orig_inode, donor_inode); + ext4_inode_double_lock(orig_inode, donor_inode); /* Wait for all existing dio workers */ ext4_inode_block_unlocked_dio(orig_inode); @@ -1342,7 +1339,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, inode_dio_wait(donor_inode); /* Protect extent tree against block allocations via delalloc */ - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ ret = mext_check_arguments(orig_inode, donor_inode, orig_start, donor_start, &len); @@ -1466,7 +1463,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, * b. racing with ->readpage, ->write_begin, and ext4_get_block * in move_extent_per_page */ - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); while (orig_page_offset <= seq_end_page) { @@ -1500,7 +1497,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, block_len_in_page = rest_blocks; } - double_down_write_data_sem(orig_inode, donor_inode); + ext4_double_down_write_data_sem(orig_inode, donor_inode); if (ret < 0) break; @@ -1538,10 +1535,10 @@ out: ext4_ext_drop_refs(holecheck_path); kfree(holecheck_path); } - double_up_write_data_sem(orig_inode, donor_inode); + ext4_double_up_write_data_sem(orig_inode, donor_inode); ext4_inode_resume_unlocked_dio(orig_inode); ext4_inode_resume_unlocked_dio(donor_inode); - mext_inode_double_unlock(orig_inode, donor_inode); + ext4_inode_double_unlock(orig_inode, donor_inode); return ret; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 3825d6a..6653fc3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -416,15 +416,16 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); - __u32 csum, old_csum; + __u32 csum; + __le32 save_csum; int size; size = count_offset + (count * sizeof(struct dx_entry)); - old_csum = t->dt_checksum; + save_csum = t->dt_checksum; t->dt_checksum = 0; csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size); csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail)); - t->dt_checksum = old_csum; + t->dt_checksum = save_csum; return cpu_to_le32(csum); } @@ -971,6 +972,17 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; + if (ext4_has_inline_data(dir)) { + int has_inline_data = 1; + count = htree_inlinedir_to_tree(dir_file, dir, 0, + &hinfo, start_hash, + start_minor_hash, + &has_inline_data); + if (has_inline_data) { + *next_hash = ~0; + return count; + } + } count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo, start_hash, start_minor_hash); *next_hash = ~0; @@ -1455,24 +1467,6 @@ struct dentry *ext4_get_parent(struct dentry *child) return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); } -#define S_SHIFT 12 -static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { - [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, - [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, - [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, -}; - -static inline void ext4_set_de_type(struct super_block *sb, - struct ext4_dir_entry_2 *de, - umode_t mode) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) - de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; -} - /* * Move count entries from end of map between two memory locations. * Returns pointer to last entry moved. @@ -2251,8 +2245,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, dquot_initialize(dir); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -2286,8 +2279,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry, dquot_initialize(dir); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -2396,8 +2388,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) dquot_initialize(dir); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); retry: inode = ext4_new_inode_start_handle(dir, S_IFDIR | mode, &dentry->d_name, @@ -2826,8 +2817,7 @@ static int ext4_symlink(struct inode *dir, * quota blocks, sb is already counted in previous macros). */ credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb); + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; } retry: inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO, diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 047a6de..5929cd0 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -29,25 +29,19 @@ #include "xattr.h" #include "acl.h" -static struct kmem_cache *io_page_cachep, *io_end_cachep; +static struct kmem_cache *io_end_cachep; int __init ext4_init_pageio(void) { - io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT); - if (io_page_cachep == NULL) - return -ENOMEM; io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT); - if (io_end_cachep == NULL) { - kmem_cache_destroy(io_page_cachep); + if (io_end_cachep == NULL) return -ENOMEM; - } return 0; } void ext4_exit_pageio(void) { kmem_cache_destroy(io_end_cachep); - kmem_cache_destroy(io_page_cachep); } /* @@ -67,29 +61,28 @@ void ext4_ioend_shutdown(struct inode *inode) cancel_work_sync(&EXT4_I(inode)->i_unwritten_work); } -static void put_io_page(struct ext4_io_page *io_page) +static void ext4_release_io_end(ext4_io_end_t *io_end) { - if (atomic_dec_and_test(&io_page->p_count)) { - end_page_writeback(io_page->p_page); - put_page(io_page->p_page); - kmem_cache_free(io_page_cachep, io_page); - } + BUG_ON(!list_empty(&io_end->list)); + BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN); + + if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count)) + wake_up_all(ext4_ioend_wq(io_end->inode)); + 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); } -void ext4_free_io_end(ext4_io_end_t *io) +static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) { - int i; - - BUG_ON(!io); - BUG_ON(!list_empty(&io->list)); - BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN); + struct inode *inode = io_end->inode; - for (i = 0; i < io->num_io_pages; i++) - put_io_page(io->pages[i]); - io->num_io_pages = 0; - if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count)) - wake_up_all(ext4_ioend_wq(io->inode)); - kmem_cache_free(io_end_cachep, io); + io_end->flag &= ~EXT4_IO_END_UNWRITTEN; + /* Wake up anyone waiting on unwritten extent conversion */ + if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) + wake_up_all(ext4_ioend_wq(inode)); } /* check a range of space and convert unwritten extents to written. */ @@ -112,13 +105,8 @@ static int ext4_end_io(ext4_io_end_t *io) "(inode %lu, offset %llu, size %zd, error %d)", inode->i_ino, offset, size, ret); } - /* Wake up anyone waiting on unwritten extent conversion */ - if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) - wake_up_all(ext4_ioend_wq(inode)); - if (io->flag & EXT4_IO_END_DIRECT) - inode_dio_done(inode); - if (io->iocb) - aio_complete(io->iocb, io->result, 0); + ext4_clear_io_unwritten_flag(io); + ext4_release_io_end(io); return ret; } @@ -149,7 +137,7 @@ static void dump_completed_IO(struct inode *inode) } /* Add the io_end to per-inode completed end_io list. */ -void ext4_add_complete_io(ext4_io_end_t *io_end) +static void ext4_add_complete_io(ext4_io_end_t *io_end) { struct ext4_inode_info *ei = EXT4_I(io_end->inode); struct workqueue_struct *wq; @@ -186,8 +174,6 @@ static int ext4_do_flush_completed_IO(struct inode *inode) err = ext4_end_io(io); if (unlikely(!ret && err)) ret = err; - io->flag &= ~EXT4_IO_END_UNWRITTEN; - ext4_free_io_end(io); } return ret; } @@ -219,10 +205,43 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) atomic_inc(&EXT4_I(inode)->i_ioend_count); io->inode = inode; INIT_LIST_HEAD(&io->list); + atomic_set(&io->count, 1); } return io; } +void ext4_put_io_end_defer(ext4_io_end_t *io_end) +{ + if (atomic_dec_and_test(&io_end->count)) { + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) { + ext4_release_io_end(io_end); + return; + } + ext4_add_complete_io(io_end); + } +} + +int ext4_put_io_end(ext4_io_end_t *io_end) +{ + int err = 0; + + if (atomic_dec_and_test(&io_end->count)) { + if (io_end->flag & EXT4_IO_END_UNWRITTEN) { + err = ext4_convert_unwritten_extents(io_end->inode, + io_end->offset, io_end->size); + ext4_clear_io_unwritten_flag(io_end); + } + ext4_release_io_end(io_end); + } + return err; +} + +ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) +{ + atomic_inc(&io_end->count); + return io_end; +} + /* * Print an buffer I/O error compatible with the fs/buffer.c. This * provides compatibility with dmesg scrapers that look for a specific @@ -243,45 +262,56 @@ static void ext4_end_bio(struct bio *bio, int error) ext4_io_end_t *io_end = bio->bi_private; struct inode *inode; int i; + int blocksize; sector_t bi_sector = bio->bi_sector; BUG_ON(!io_end); + inode = io_end->inode; + blocksize = 1 << inode->i_blkbits; bio->bi_private = NULL; bio->bi_end_io = NULL; if (test_bit(BIO_UPTODATE, &bio->bi_flags)) error = 0; - bio_put(bio); - - for (i = 0; i < io_end->num_io_pages; i++) { - struct page *page = io_end->pages[i]->p_page; + for (i = 0; i < bio->bi_vcnt; i++) { + struct bio_vec *bvec = &bio->bi_io_vec[i]; + struct page *page = bvec->bv_page; struct buffer_head *bh, *head; - loff_t offset; - loff_t io_end_offset; + unsigned bio_start = bvec->bv_offset; + unsigned bio_end = bio_start + bvec->bv_len; + unsigned under_io = 0; + unsigned long flags; + + if (!page) + continue; if (error) { SetPageError(page); set_bit(AS_EIO, &page->mapping->flags); - head = page_buffers(page); - BUG_ON(!head); - - io_end_offset = io_end->offset + io_end->size; - - offset = (sector_t) page->index << PAGE_CACHE_SHIFT; - bh = head; - do { - if ((offset >= io_end->offset) && - (offset+bh->b_size <= io_end_offset)) - buffer_io_error(bh); - - offset += bh->b_size; - bh = bh->b_this_page; - } while (bh != head); } - - put_io_page(io_end->pages[i]); + bh = head = page_buffers(page); + /* + * We check all buffers in the page under BH_Uptodate_Lock + * to avoid races with other end io clearing async_write flags + */ + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &head->b_state); + do { + if (bh_offset(bh) < bio_start || + bh_offset(bh) + blocksize > bio_end) { + if (buffer_async_write(bh)) + under_io++; + continue; + } + clear_buffer_async_write(bh); + if (error) + buffer_io_error(bh); + } while ((bh = bh->b_this_page) != head); + bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); + local_irq_restore(flags); + if (!under_io) + end_page_writeback(page); } - io_end->num_io_pages = 0; - inode = io_end->inode; + bio_put(bio); if (error) { io_end->flag |= EXT4_IO_END_ERROR; @@ -294,12 +324,7 @@ static void ext4_end_bio(struct bio *bio, int error) bi_sector >> (inode->i_blkbits - 9)); } - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - ext4_free_io_end(io_end); - return; - } - - ext4_add_complete_io(io_end); + ext4_put_io_end_defer(io_end); } void ext4_io_submit(struct ext4_io_submit *io) @@ -313,76 +338,59 @@ void ext4_io_submit(struct ext4_io_submit *io) bio_put(io->io_bio); } io->io_bio = NULL; - io->io_op = 0; +} + +void ext4_io_submit_init(struct ext4_io_submit *io, + struct writeback_control *wbc) +{ + io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); + io->io_bio = NULL; io->io_end = NULL; } -static int io_submit_init(struct ext4_io_submit *io, - struct inode *inode, - struct writeback_control *wbc, - struct buffer_head *bh) +static int io_submit_init_bio(struct ext4_io_submit *io, + struct buffer_head *bh) { - ext4_io_end_t *io_end; - struct page *page = bh->b_page; int nvecs = bio_get_nr_vecs(bh->b_bdev); struct bio *bio; - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) - return -ENOMEM; bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES)); bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; - bio->bi_private = io->io_end = io_end; bio->bi_end_io = ext4_end_bio; - - io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh); - + bio->bi_private = ext4_get_io_end(io->io_end); + if (!io->io_end->size) + io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT) + + bh_offset(bh); io->io_bio = bio; - io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); io->io_next_block = bh->b_blocknr; return 0; } static int io_submit_add_bh(struct ext4_io_submit *io, - struct ext4_io_page *io_page, struct inode *inode, - struct writeback_control *wbc, struct buffer_head *bh) { ext4_io_end_t *io_end; int ret; - if (buffer_new(bh)) { - clear_buffer_new(bh); - unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); - } - if (io->io_bio && bh->b_blocknr != io->io_next_block) { submit_and_retry: ext4_io_submit(io); } if (io->io_bio == NULL) { - ret = io_submit_init(io, inode, wbc, bh); + ret = io_submit_init_bio(io, bh); if (ret) return ret; } - io_end = io->io_end; - if ((io_end->num_io_pages >= MAX_IO_PAGES) && - (io_end->pages[io_end->num_io_pages-1] != io_page)) - goto submit_and_retry; - if (buffer_uninit(bh)) - ext4_set_io_unwritten_flag(inode, io_end); - io->io_end->size += bh->b_size; - io->io_next_block++; ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - if ((io_end->num_io_pages == 0) || - (io_end->pages[io_end->num_io_pages-1] != io_page)) { - io_end->pages[io_end->num_io_pages++] = io_page; - atomic_inc(&io_page->p_count); - } + io_end = io->io_end; + if (test_clear_buffer_uninit(bh)) + ext4_set_io_unwritten_flag(inode, io_end); + io_end->size += bh->b_size; + io->io_next_block++; return 0; } @@ -392,33 +400,29 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; - unsigned block_start, block_end, blocksize; - struct ext4_io_page *io_page; + unsigned block_start, blocksize; struct buffer_head *bh, *head; int ret = 0; + int nr_submitted = 0; blocksize = 1 << inode->i_blkbits; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS); - if (!io_page) { - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return -ENOMEM; - } - io_page->p_page = page; - atomic_set(&io_page->p_count, 1); - get_page(page); set_page_writeback(page); ClearPageError(page); - for (bh = head = page_buffers(page), block_start = 0; - bh != head || !block_start; - block_start = block_end, bh = bh->b_this_page) { - - block_end = block_start + blocksize; + /* + * In the first loop we prepare and mark buffers to submit. We have to + * mark all buffers in the page before submitting so that + * end_page_writeback() cannot be called from ext4_bio_end_io() when IO + * on the first buffer finishes and we are still working on submitting + * the second buffer. + */ + bh = head = page_buffers(page); + do { + block_start = bh_offset(bh); if (block_start >= len) { /* * Comments copied from block_write_full_page_endio: @@ -431,7 +435,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io, * mapped, and writes to that region are not written * out to the file." */ - zero_user_segment(page, block_start, block_end); + zero_user_segment(page, block_start, + block_start + blocksize); clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; @@ -445,7 +450,19 @@ int ext4_bio_write_page(struct ext4_io_submit *io, ext4_io_submit(io); continue; } - ret = io_submit_add_bh(io, io_page, inode, wbc, bh); + if (buffer_new(bh)) { + clear_buffer_new(bh); + unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); + } + set_buffer_async_write(bh); + } while ((bh = bh->b_this_page) != head); + + /* Now submit buffers to write */ + bh = head = page_buffers(page); + do { + if (!buffer_async_write(bh)) + continue; + ret = io_submit_add_bh(io, inode, bh); if (ret) { /* * We only get here on ENOMEM. Not much else @@ -455,17 +472,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io, redirty_page_for_writepage(wbc, page); break; } + nr_submitted++; clear_buffer_dirty(bh); + } while ((bh = bh->b_this_page) != head); + + /* Error stopped previous loop? Clean up buffers... */ + if (ret) { + do { + clear_buffer_async_write(bh); + bh = bh->b_this_page; + } while (bh != head); } unlock_page(page); - /* - * If the page was truncated before we could do the writeback, - * or we had a memory allocation error while trying to write - * the first buffer head, we won't have submitted any pages for - * I/O. In that case we need to make sure we've cleared the - * PageWriteback bit from the page to prevent the system from - * wedging later on. - */ - put_io_page(io_page); + /* Nothing submitted - we have to end page writeback */ + if (!nr_submitted) + end_page_writeback(page); return ret; } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c169477..b27c96d 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -272,7 +272,7 @@ next_group: if (start_blk >= last_blk) goto next_group; group_data[bb_index].block_bitmap = start_blk++; - ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL); + group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; if (flexbg_size > 1) @@ -284,7 +284,7 @@ next_group: if (start_blk >= last_blk) goto next_group; group_data[ib_index].inode_bitmap = start_blk++; - ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL); + group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; if (flexbg_size > 1) @@ -296,7 +296,7 @@ next_group: if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk) goto next_group; group_data[it_index].inode_table = start_blk; - ext4_get_group_no_and_offset(sb, start_blk, &group, NULL); + group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count -= EXT4_SB(sb)->s_itb_per_group; @@ -392,7 +392,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, ext4_group_t group; int err; - ext4_get_group_no_and_offset(sb, block, &group, NULL); + group = ext4_get_group_number(sb, block); start = ext4_group_first_block_no(sb, group); group -= flex_gd->groups[0].group; @@ -1341,6 +1341,8 @@ static void ext4_update_super(struct super_block *sb, /* Update the global fs size fields */ sbi->s_groups_count += flex_gd->count; + sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, + (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); /* Update the reserved block counts only once the new group is * active. */ @@ -1879,7 +1881,11 @@ retry: /* Nothing need to do */ return 0; - ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset); + n_group = ext4_get_group_number(sb, n_blocks_count - 1); + if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) { + ext4_warning(sb, "resize would cause inodes_count overflow"); + return -EINVAL; + } ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset); n_desc_blocks = num_desc_blocks(sb, n_group + 1); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c655105..24a146b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -81,6 +81,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); +static int ext4_reserve_clusters(struct ext4_sb_info *, ext4_fsblk_t); #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext2_fs_type = { @@ -353,10 +354,13 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int error = is_journal_aborted(journal); - struct ext4_journal_cb_entry *jce, *tmp; + struct ext4_journal_cb_entry *jce; + BUG_ON(txn->t_state == T_FINISHED); spin_lock(&sbi->s_md_lock); - list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) { + while (!list_empty(&txn->t_private_list)) { + jce = list_entry(txn->t_private_list.next, + struct ext4_journal_cb_entry, jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); jce->jce_func(sb, jce, error); @@ -1948,16 +1952,16 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, if ((sbi->s_es->s_feature_ro_compat & cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { /* Use new metadata_csum algorithm */ - __u16 old_csum; + __le16 save_csum; __u32 csum32; - old_csum = gdp->bg_checksum; + save_csum = gdp->bg_checksum; gdp->bg_checksum = 0; csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, sbi->s_desc_size); - gdp->bg_checksum = old_csum; + gdp->bg_checksum = save_csum; crc = csum32 & 0xFFFF; goto out; @@ -2379,17 +2383,15 @@ struct ext4_attr { int offset; }; -static int parse_strtoul(const char *buf, - unsigned long max, unsigned long *value) +static int parse_strtoull(const char *buf, + unsigned long long max, unsigned long long *value) { - char *endp; - - *value = simple_strtoul(skip_spaces(buf), &endp, 0); - endp = skip_spaces(endp); - if (*endp || *value > max) - return -EINVAL; + int ret; - return 0; + ret = kstrtoull(skip_spaces(buf), 0, value); + if (!ret && *value > max) + ret = -EINVAL; + return ret; } static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, @@ -2431,11 +2433,13 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, const char *buf, size_t count) { unsigned long t; + int ret; - if (parse_strtoul(buf, 0x40000000, &t)) - return -EINVAL; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; - if (t && !is_power_of_2(t)) + if (t && (!is_power_of_2(t) || t > 0x40000000)) return -EINVAL; sbi->s_inode_readahead_blks = t; @@ -2456,13 +2460,36 @@ static ssize_t sbi_ui_store(struct ext4_attr *a, { unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset); unsigned long t; + int ret; - if (parse_strtoul(buf, 0xffffffff, &t)) - return -EINVAL; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; *ui = t; return count; } +static ssize_t reserved_clusters_show(struct ext4_attr *a, + struct ext4_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long) atomic64_read(&sbi->s_resv_clusters)); +} + +static ssize_t reserved_clusters_store(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned long long val; + int ret; + + if (parse_strtoull(buf, -1ULL, &val)) + return -EINVAL; + ret = ext4_reserve_clusters(sbi, val); + + return ret ? ret : count; +} + static ssize_t trigger_test_error(struct ext4_attr *a, struct ext4_sb_info *sbi, const char *buf, size_t count) @@ -2500,6 +2527,7 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) EXT4_RO_ATTR(delayed_allocation_blocks); EXT4_RO_ATTR(session_write_kbytes); EXT4_RO_ATTR(lifetime_write_kbytes); +EXT4_RW_ATTR(reserved_clusters); EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show, inode_readahead_blks_store, s_inode_readahead_blks); EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); @@ -2517,6 +2545,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(delayed_allocation_blocks), ATTR_LIST(session_write_kbytes), ATTR_LIST(lifetime_write_kbytes), + ATTR_LIST(reserved_clusters), ATTR_LIST(inode_readahead_blks), ATTR_LIST(inode_goal), ATTR_LIST(mb_stats), @@ -3192,6 +3221,40 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } + +static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi) +{ + ext4_fsblk_t resv_clusters; + + /* + * By default we reserve 2% or 4096 clusters, whichever is smaller. + * This should cover the situations where we can not afford to run + * out of space like for example punch hole, or converting + * uninitialized extents in delalloc path. In most cases such + * allocation would require 1, or 2 blocks, higher numbers are + * very rare. + */ + resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits; + + do_div(resv_clusters, 50); + resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); + + return resv_clusters; +} + + +static int ext4_reserve_clusters(struct ext4_sb_info *sbi, ext4_fsblk_t count) +{ + ext4_fsblk_t clusters = ext4_blocks_count(sbi->s_es) >> + sbi->s_cluster_bits; + + if (count >= clusters) + return -EINVAL; + + atomic64_set(&sbi->s_resv_clusters, count); + return 0; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); @@ -3526,6 +3589,10 @@ 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; @@ -3698,6 +3765,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.function = print_daily_error_info; sbi->s_err_report.data = (unsigned long) sb; + /* Register extent status tree shrinker */ + ext4_es_register_shrinker(sb); + err = percpu_counter_init(&sbi->s_freeclusters_counter, ext4_count_free_clusters(sb)); if (!err) { @@ -3723,9 +3793,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_max_writeback_mb_bump = 128; sbi->s_extent_max_zeroout_kb = 32; - /* Register extent status tree shrinker */ - ext4_es_register_shrinker(sb); - /* * set up enough so that it can read an inode */ @@ -3911,6 +3978,13 @@ no_journal: "available"); } + err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi)); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " + "reserved pool", ext4_calculate_resv_clusters(sbi)); + goto failed_mount4a; + } + err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " @@ -4010,6 +4084,7 @@ failed_mount_wq: sbi->s_journal = NULL; } failed_mount3: + ext4_es_unregister_shrinker(sb); del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); @@ -4177,7 +4252,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, goto out_bdev; } journal->j_private = sb; - ll_rw_block(READ, 1, &journal->j_sb_buffer); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer); wait_on_buffer(journal->j_sb_buffer); if (!buffer_uptodate(journal->j_sb_buffer)) { ext4_msg(sb, KERN_ERR, "I/O error on journal device"); @@ -4742,9 +4817,10 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; - ext4_fsblk_t overhead = 0; + ext4_fsblk_t overhead = 0, resv_blocks; u64 fsid; s64 bfree; + resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters)); if (!test_opt(sb, MINIX_DF)) overhead = sbi->s_overhead; @@ -4756,8 +4832,9 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); - buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); - if (buf->f_bfree < ext4_r_blocks_count(es)) + buf->f_bavail = buf->f_bfree - + (ext4_r_blocks_count(es) + resv_blocks); + if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); @@ -4945,6 +5022,8 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, return PTR_ERR(qf_inode); } + /* Don't account quota for quota files to avoid recursion */ + qf_inode->i_flags |= S_NOQUOTA; err = dquot_enable(qf_inode, type, format_id, flags); iput(qf_inode); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 3a120b2..c081e34 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -122,17 +122,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - __u32 csum, old; + __u32 csum; + __le32 save_csum; + __le64 dsk_block_nr = cpu_to_le64(block_nr); - old = hdr->h_checksum; + save_csum = hdr->h_checksum; hdr->h_checksum = 0; - block_nr = cpu_to_le64(block_nr); - csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, - sizeof(block_nr)); + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr, + sizeof(dsk_block_nr)); csum = ext4_chksum(sbi, csum, (__u8 *)hdr, EXT4_BLOCK_SIZE(inode->i_sb)); - hdr->h_checksum = old; + hdr->h_checksum = save_csum; return cpu_to_le32(csum); } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index aa25deb..c767dbd 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -22,6 +22,7 @@ #define EXT4_XATTR_INDEX_LUSTRE 5 #define EXT4_XATTR_INDEX_SECURITY 6 #define EXT4_XATTR_INDEX_SYSTEM 7 +#define EXT4_XATTR_INDEX_RICHACL 8 struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cc2213a..201c8d3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -137,7 +137,7 @@ struct extent_info { rwlock_t ext_lock; /* rwlock for consistency */ unsigned int fofs; /* start offset in a file */ u32 blk_addr; /* start block address of the extent */ - unsigned int len; /* lenth of the extent */ + unsigned int len; /* length of the extent */ }; /* diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 94b8a0c..2e3eb2d 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -222,7 +222,7 @@ static unsigned int get_gc_cost(struct f2fs_sb_info *sbi, unsigned int segno, } /* - * This function is called from two pathes. + * This function is called from two paths. * One is garbage collection and the other is SSR segment selection. * When it is called during GC, it just gets a victim segment * and it does not remove it from dirty seglist. diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index fea6e58..62e0177 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -82,7 +82,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) init_once((void *) fi); - /* Initilize f2fs-specific inode info */ + /* Initialize f2fs-specific inode info */ fi->vfs_inode.i_version = 1; atomic_set(&fi->dirty_dents, 0); fi->i_current_depth = 1; diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 165012e..7a6f02c 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -964,6 +964,29 @@ int fat_scan(struct inode *dir, const unsigned char *name, } EXPORT_SYMBOL_GPL(fat_scan); +/* + * Scans a directory for a given logstart. + * Returns an error code or zero. + */ +int fat_scan_logstart(struct inode *dir, int i_logstart, + struct fat_slot_info *sinfo) +{ + struct super_block *sb = dir->i_sb; + + sinfo->slot_off = 0; + sinfo->bh = NULL; + while (fat_get_short_entry(dir, &sinfo->slot_off, &sinfo->bh, + &sinfo->de) >= 0) { + if (fat_get_start(MSDOS_SB(sb), sinfo->de) == i_logstart) { + sinfo->slot_off -= sizeof(*sinfo->de); + sinfo->nr_slots = 1; + sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de); + return 0; + } + } + return -ENOENT; +} + static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots) { struct super_block *sb = dir->i_sb; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index e9cc3f0..21664fc 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -23,6 +23,9 @@ #define FAT_ERRORS_PANIC 2 /* panic on error */ #define FAT_ERRORS_RO 3 /* remount r/o on error */ +#define FAT_NFS_STALE_RW 1 /* NFS RW support, can cause ESTALE */ +#define FAT_NFS_NOSTALE_RO 2 /* NFS RO support, no ESTALE issue */ + struct fat_mount_options { kuid_t fs_uid; kgid_t fs_gid; @@ -34,6 +37,7 @@ struct fat_mount_options { unsigned short shortname; /* flags for shortname display/create rule */ unsigned char name_check; /* r = relaxed, n = normal, s = strict */ unsigned char errors; /* On error: continue, panic, remount-ro */ + unsigned char nfs; /* NFS support: nostale_ro, stale_rw */ unsigned short allow_utime;/* permission for setting the [am]time */ unsigned quiet:1, /* set = fake successful chmods and chowns */ showexec:1, /* set = only set x bit for com/exe/bat */ @@ -48,8 +52,7 @@ struct fat_mount_options { usefree:1, /* Use free_clusters for FAT32 */ tz_set:1, /* Filesystem timestamps' offset set */ rodir:1, /* allow ATTR_RO for directory */ - discard:1, /* Issue discard requests on deletions */ - nfs:1; /* Do extra work needed for NFS export */ + discard:1; /* Issue discard requests on deletions */ }; #define FAT_HASH_BITS 8 @@ -72,6 +75,7 @@ struct msdos_sb_info { unsigned long root_cluster; /* first cluster of the root directory */ unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */ struct mutex fat_lock; + struct mutex nfs_build_inode_lock; struct mutex s_lock; unsigned int prev_free; /* previously allocated cluster number */ unsigned int free_clusters; /* -1 if undefined */ @@ -215,6 +219,27 @@ static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus) + sbi->data_start; } +static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi, + loff_t i_pos, sector_t *blknr, int *offset) +{ + *blknr = i_pos >> sbi->dir_per_block_bits; + *offset = i_pos & (sbi->dir_per_block - 1); +} + +static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi, + struct inode *inode) +{ + loff_t i_pos; +#if BITS_PER_LONG == 32 + spin_lock(&sbi->inode_hash_lock); +#endif + i_pos = MSDOS_I(inode)->i_pos; +#if BITS_PER_LONG == 32 + spin_unlock(&sbi->inode_hash_lock); +#endif + return i_pos; +} + static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len) { #ifdef __BIG_ENDIAN @@ -271,6 +296,8 @@ extern int fat_dir_empty(struct inode *dir); extern int fat_subdirs(struct inode *dir); extern int fat_scan(struct inode *dir, const unsigned char *name, struct fat_slot_info *sinfo); +extern int fat_scan_logstart(struct inode *dir, int i_logstart, + struct fat_slot_info *sinfo); extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, struct msdos_dir_entry **de); extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts); @@ -348,6 +375,7 @@ extern struct inode *fat_build_inode(struct super_block *sb, extern int fat_sync_inode(struct inode *inode); extern int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, void (*setup)(struct super_block *)); +extern int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de); extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); @@ -382,12 +410,8 @@ int fat_cache_init(void); void fat_cache_destroy(void); /* fat/nfs.c */ -struct fid; -extern struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type); -extern struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type); -extern struct dentry *fat_get_parent(struct dentry *child_dir); +extern const struct export_operations fat_export_ops; +extern const struct export_operations fat_export_ops_nostale; /* helper for printk */ typedef unsigned long long llu; diff --git a/fs/fat/file.c b/fs/fat/file.c index 3978f8c..b0b632e 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -306,6 +306,11 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) struct inode *inode = dentry->d_inode; generic_fillattr(inode, stat); stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size; + + if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) { + /* Use i_pos for ino. This is used as fileid of nfs. */ + stat->ino = fat_i_pos_read(MSDOS_SB(inode->i_sb), inode); + } return 0; } EXPORT_SYMBOL_GPL(fat_getattr); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index acf6e47..4ff9016 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -18,7 +18,6 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/buffer_head.h> -#include <linux/exportfs.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/parser.h> @@ -385,7 +384,7 @@ static int fat_calc_dir_size(struct inode *inode) } /* doesn't deal with root inode */ -static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) +int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; @@ -444,12 +443,25 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) return 0; } +static inline void fat_lock_build_inode(struct msdos_sb_info *sbi) +{ + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) + mutex_lock(&sbi->nfs_build_inode_lock); +} + +static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi) +{ + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) + mutex_unlock(&sbi->nfs_build_inode_lock); +} + struct inode *fat_build_inode(struct super_block *sb, struct msdos_dir_entry *de, loff_t i_pos) { struct inode *inode; int err; + fat_lock_build_inode(MSDOS_SB(sb)); inode = fat_iget(sb, i_pos); if (inode) goto out; @@ -469,6 +481,7 @@ struct inode *fat_build_inode(struct super_block *sb, fat_attach(inode, i_pos); insert_inode_hash(inode); out: + fat_unlock_build_inode(MSDOS_SB(sb)); return inode; } @@ -655,20 +668,6 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi, - struct inode *inode) -{ - loff_t i_pos; -#if BITS_PER_LONG == 32 - spin_lock(&sbi->inode_hash_lock); -#endif - i_pos = MSDOS_I(inode)->i_pos; -#if BITS_PER_LONG == 32 - spin_unlock(&sbi->inode_hash_lock); -#endif - return i_pos; -} - static int __fat_write_inode(struct inode *inode, int wait) { struct super_block *sb = inode->i_sb; @@ -676,7 +675,8 @@ static int __fat_write_inode(struct inode *inode, int wait) struct buffer_head *bh; struct msdos_dir_entry *raw_entry; loff_t i_pos; - int err; + sector_t blocknr; + int err, offset; if (inode->i_ino == MSDOS_ROOT_INO) return 0; @@ -686,7 +686,8 @@ retry: if (!i_pos) return 0; - bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits); + fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); + bh = sb_bread(sb, blocknr); if (!bh) { fat_msg(sb, KERN_ERR, "unable to read inode block " "for updating (i_pos %lld)", i_pos); @@ -699,8 +700,7 @@ retry: goto retry; } - raw_entry = &((struct msdos_dir_entry *) (bh->b_data)) - [i_pos & (sbi->dir_per_block - 1)]; + raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset]; if (S_ISDIR(inode->i_mode)) raw_entry->size = 0; else @@ -761,12 +761,6 @@ static const struct super_operations fat_sops = { .show_options = fat_show_options, }; -static const struct export_operations fat_export_ops = { - .fh_to_dentry = fat_fh_to_dentry, - .fh_to_parent = fat_fh_to_parent, - .get_parent = fat_get_parent, -}; - static int fat_show_options(struct seq_file *m, struct dentry *root) { struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); @@ -814,8 +808,6 @@ static int fat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",usefree"); if (opts->quiet) seq_puts(m, ",quiet"); - if (opts->nfs) - seq_puts(m, ",nfs"); if (opts->showexec) seq_puts(m, ",showexec"); if (opts->sys_immutable) @@ -849,6 +841,10 @@ static int fat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); + if (opts->nfs == FAT_NFS_NOSTALE_RO) + seq_puts(m, ",nfs=nostale_ro"); + else if (opts->nfs) + seq_puts(m, ",nfs=stale_rw"); if (opts->discard) seq_puts(m, ",discard"); @@ -865,7 +861,7 @@ enum { Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes, Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset, - Opt_err, + Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, }; static const match_table_t fat_tokens = { @@ -895,7 +891,9 @@ static const match_table_t fat_tokens = { {Opt_err_panic, "errors=panic"}, {Opt_err_ro, "errors=remount-ro"}, {Opt_discard, "discard"}, - {Opt_nfs, "nfs"}, + {Opt_nfs_stale_rw, "nfs"}, + {Opt_nfs_stale_rw, "nfs=stale_rw"}, + {Opt_nfs_nostale_ro, "nfs=nostale_ro"}, {Opt_obsolete, "conv=binary"}, {Opt_obsolete, "conv=text"}, {Opt_obsolete, "conv=auto"}, @@ -1092,6 +1090,12 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, case Opt_err_ro: opts->errors = FAT_ERRORS_RO; break; + case Opt_nfs_stale_rw: + opts->nfs = FAT_NFS_STALE_RW; + break; + case Opt_nfs_nostale_ro: + opts->nfs = FAT_NFS_NOSTALE_RO; + break; /* msdos specific */ case Opt_dots: @@ -1150,9 +1154,6 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, case Opt_discard: opts->discard = 1; break; - case Opt_nfs: - opts->nfs = 1; - break; /* obsolete mount options */ case Opt_obsolete: @@ -1183,6 +1184,10 @@ out: opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH); if (opts->unicode_xlate) opts->utf8 = 0; + if (opts->nfs == FAT_NFS_NOSTALE_RO) { + sb->s_flags |= MS_RDONLY; + sb->s_export_op = &fat_export_ops_nostale; + } return 0; } @@ -1193,7 +1198,7 @@ static int fat_read_root(struct inode *inode) struct msdos_sb_info *sbi = MSDOS_SB(sb); int error; - MSDOS_I(inode)->i_pos = 0; + MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode->i_version++; @@ -1256,6 +1261,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, sb->s_magic = MSDOS_SUPER_MAGIC; sb->s_op = &fat_sops; sb->s_export_op = &fat_export_ops; + mutex_init(&sbi->nfs_build_inode_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index 499c104..93e1493 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -14,6 +14,18 @@ #include <linux/exportfs.h> #include "fat.h" +struct fat_fid { + u32 i_gen; + u32 i_pos_low; + u16 i_pos_hi; + u16 parent_i_pos_hi; + u32 parent_i_pos_low; + u32 parent_i_gen; +}; + +#define FAT_FID_SIZE_WITHOUT_PARENT 3 +#define FAT_FID_SIZE_WITH_PARENT (sizeof(struct fat_fid)/sizeof(u32)) + /** * Look up a directory inode given its starting cluster. */ @@ -38,63 +50,252 @@ static struct inode *fat_dget(struct super_block *sb, int i_logstart) return inode; } -static struct inode *fat_nfs_get_inode(struct super_block *sb, - u64 ino, u32 generation) +static struct inode *fat_ilookup(struct super_block *sb, u64 ino, loff_t i_pos) { - struct inode *inode; + if (MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO) + return fat_iget(sb, i_pos); - if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO)) - return NULL; + else { + if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO)) + return NULL; + return ilookup(sb, ino); + } +} + +static struct inode *__fat_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation, loff_t i_pos) +{ + struct inode *inode = fat_ilookup(sb, ino, i_pos); - inode = ilookup(sb, ino); if (inode && generation && (inode->i_generation != generation)) { iput(inode); inode = NULL; } + if (inode == NULL && MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO) { + struct buffer_head *bh = NULL; + struct msdos_dir_entry *de ; + sector_t blocknr; + int offset; + fat_get_blknr_offset(MSDOS_SB(sb), i_pos, &blocknr, &offset); + bh = sb_bread(sb, blocknr); + if (!bh) { + fat_msg(sb, KERN_ERR, + "unable to read block(%llu) for building NFS inode", + (llu)blocknr); + return inode; + } + de = (struct msdos_dir_entry *)bh->b_data; + /* If a file is deleted on server and client is not updated + * yet, we must not build the inode upon a lookup call. + */ + if (IS_FREE(de[offset].name)) + inode = NULL; + else + inode = fat_build_inode(sb, &de[offset], i_pos); + brelse(bh); + } return inode; } +static struct inode *fat_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + + return __fat_nfs_get_inode(sb, ino, generation, 0); +} + +static int +fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, + struct inode *parent) +{ + int len = *lenp; + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + struct fat_fid *fid = (struct fat_fid *) fh; + loff_t i_pos; + int type = FILEID_FAT_WITHOUT_PARENT; + + if (parent) { + if (len < FAT_FID_SIZE_WITH_PARENT) { + *lenp = FAT_FID_SIZE_WITH_PARENT; + return FILEID_INVALID; + } + } else { + if (len < FAT_FID_SIZE_WITHOUT_PARENT) { + *lenp = FAT_FID_SIZE_WITHOUT_PARENT; + return FILEID_INVALID; + } + } + + i_pos = fat_i_pos_read(sbi, inode); + *lenp = FAT_FID_SIZE_WITHOUT_PARENT; + fid->i_gen = inode->i_generation; + fid->i_pos_low = i_pos & 0xFFFFFFFF; + fid->i_pos_hi = (i_pos >> 32) & 0xFFFF; + if (parent) { + i_pos = fat_i_pos_read(sbi, parent); + fid->parent_i_pos_hi = (i_pos >> 32) & 0xFFFF; + fid->parent_i_pos_low = i_pos & 0xFFFFFFFF; + fid->parent_i_gen = parent->i_generation; + type = FILEID_FAT_WITH_PARENT; + *lenp = FAT_FID_SIZE_WITH_PARENT; + } + + return type; +} + /** * Map a NFS file handle to a corresponding dentry. * The dentry may or may not be connected to the filesystem root. */ -struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid, +static struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, fat_nfs_get_inode); } +static struct dentry *fat_fh_to_dentry_nostale(struct super_block *sb, + struct fid *fh, int fh_len, + int fh_type) +{ + struct inode *inode = NULL; + struct fat_fid *fid = (struct fat_fid *)fh; + loff_t i_pos; + + switch (fh_type) { + case FILEID_FAT_WITHOUT_PARENT: + if (fh_len < FAT_FID_SIZE_WITHOUT_PARENT) + return NULL; + break; + case FILEID_FAT_WITH_PARENT: + if (fh_len < FAT_FID_SIZE_WITH_PARENT) + return NULL; + break; + default: + return NULL; + } + i_pos = fid->i_pos_hi; + i_pos = (i_pos << 32) | (fid->i_pos_low); + inode = __fat_nfs_get_inode(sb, 0, fid->i_gen, i_pos); + + return d_obtain_alias(inode); +} + /* * Find the parent for a file specified by NFS handle. * This requires that the handle contain the i_ino of the parent. */ -struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid, +static struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, fat_nfs_get_inode); } +static struct dentry *fat_fh_to_parent_nostale(struct super_block *sb, + struct fid *fh, int fh_len, + int fh_type) +{ + struct inode *inode = NULL; + struct fat_fid *fid = (struct fat_fid *)fh; + loff_t i_pos; + + if (fh_len < FAT_FID_SIZE_WITH_PARENT) + return NULL; + + switch (fh_type) { + case FILEID_FAT_WITH_PARENT: + i_pos = fid->parent_i_pos_hi; + i_pos = (i_pos << 32) | (fid->parent_i_pos_low); + inode = __fat_nfs_get_inode(sb, 0, fid->parent_i_gen, i_pos); + break; + } + + return d_obtain_alias(inode); +} + +/* + * Rebuild the parent for a directory that is not connected + * to the filesystem root + */ +static +struct inode *fat_rebuild_parent(struct super_block *sb, int parent_logstart) +{ + int search_clus, clus_to_match; + struct msdos_dir_entry *de; + struct inode *parent = NULL; + struct inode *dummy_grand_parent = NULL; + struct fat_slot_info sinfo; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + sector_t blknr = fat_clus_to_blknr(sbi, parent_logstart); + struct buffer_head *parent_bh = sb_bread(sb, blknr); + if (!parent_bh) { + fat_msg(sb, KERN_ERR, + "unable to read cluster of parent directory"); + return NULL; + } + + de = (struct msdos_dir_entry *) parent_bh->b_data; + clus_to_match = fat_get_start(sbi, &de[0]); + search_clus = fat_get_start(sbi, &de[1]); + + dummy_grand_parent = fat_dget(sb, search_clus); + if (!dummy_grand_parent) { + dummy_grand_parent = new_inode(sb); + if (!dummy_grand_parent) { + brelse(parent_bh); + return parent; + } + + dummy_grand_parent->i_ino = iunique(sb, MSDOS_ROOT_INO); + fat_fill_inode(dummy_grand_parent, &de[1]); + MSDOS_I(dummy_grand_parent)->i_pos = -1; + } + + if (!fat_scan_logstart(dummy_grand_parent, clus_to_match, &sinfo)) + parent = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + + brelse(parent_bh); + iput(dummy_grand_parent); + + return parent; +} + /* * Find the parent for a directory that is not currently connected to * the filesystem root. * * On entry, the caller holds child_dir->d_inode->i_mutex. */ -struct dentry *fat_get_parent(struct dentry *child_dir) +static struct dentry *fat_get_parent(struct dentry *child_dir) { struct super_block *sb = child_dir->d_sb; struct buffer_head *bh = NULL; struct msdos_dir_entry *de; struct inode *parent_inode = NULL; + struct msdos_sb_info *sbi = MSDOS_SB(sb); if (!fat_get_dotdot_entry(child_dir->d_inode, &bh, &de)) { - int parent_logstart = fat_get_start(MSDOS_SB(sb), de); + int parent_logstart = fat_get_start(sbi, de); parent_inode = fat_dget(sb, parent_logstart); + if (!parent_inode && sbi->options.nfs == FAT_NFS_NOSTALE_RO) + parent_inode = fat_rebuild_parent(sb, parent_logstart); } brelse(bh); return d_obtain_alias(parent_inode); } + +const struct export_operations fat_export_ops = { + .fh_to_dentry = fat_fh_to_dentry, + .fh_to_parent = fat_fh_to_parent, + .get_parent = fat_get_parent, +}; + +const struct export_operations fat_export_ops_nostale = { + .encode_fh = fat_encode_fh_nostale, + .fh_to_dentry = fat_fh_to_dentry_nostale, + .fh_to_parent = fat_fh_to_parent_nostale, + .get_parent = fat_get_parent, +}; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 21f46fb..798d445 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1028,6 +1028,7 @@ int bdi_writeback_thread(void *data) struct backing_dev_info *bdi = wb->bdi; long pages_written; + set_worker_desc("flush-%s", dev_name(bdi->dev)); current->flags |= PF_SWAPWRITE; set_freezable(); wb->last_active = jiffies; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 8179e8b..40d13c7 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -287,5 +287,5 @@ const struct file_operations fscache_stats_fops = { .open = fscache_stats_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 24f414f..9883694 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1055,7 +1055,7 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) if (atomic_read(&bh->b_count)) goto cannot_release; bd = bh->b_private; - if (bd && bd->bd_ail) + if (bd && bd->bd_tr) goto cannot_release; if (buffer_pinned(bh) || buffer_dirty(bh)) goto not_possible; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 5e83657..1dc9a13 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -787,7 +787,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, goto out_rlist; if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */ - gfs2_rs_deltree(ip, ip->i_res); + gfs2_rs_deltree(ip->i_res); error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE + RES_INDIRECT + RES_STATFS + RES_QUOTA, diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 019f45e..d79c2da 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -923,8 +923,11 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) cmd = F_SETLK; fl->fl_type = F_UNLCK; } - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { + if (fl->fl_type == F_UNLCK) + posix_lock_file_wait(file, fl); return -EIO; + } if (IS_GETLK(cmd)) return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl); else if (fl->fl_type == F_UNLCK) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index cf35155..9435384 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -912,7 +912,7 @@ int gfs2_glock_wait(struct gfs2_holder *gh) */ static void handle_callback(struct gfs2_glock *gl, unsigned int state, - unsigned long delay) + unsigned long delay, bool remote) { int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE; @@ -925,8 +925,8 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state, gl->gl_demote_state = LM_ST_UNLOCKED; } if (gl->gl_ops->go_callback) - gl->gl_ops->go_callback(gl); - trace_gfs2_demote_rq(gl); + gl->gl_ops->go_callback(gl, remote); + trace_gfs2_demote_rq(gl, remote); } void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...) @@ -1017,11 +1017,11 @@ do_cancel: return; trap_recursive: - print_symbol(KERN_ERR "original: %s\n", gh2->gh_ip); + printk(KERN_ERR "original: %pSR\n", (void *)gh2->gh_ip); printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid)); printk(KERN_ERR "lock type: %d req lock state : %d\n", gh2->gh_gl->gl_name.ln_type, gh2->gh_state); - print_symbol(KERN_ERR "new: %s\n", gh->gh_ip); + printk(KERN_ERR "new: %pSR\n", (void *)gh->gh_ip); printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid)); printk(KERN_ERR "lock type: %d req lock state : %d\n", gh->gh_gl->gl_name.ln_type, gh->gh_state); @@ -1091,7 +1091,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) spin_lock(&gl->gl_spin); if (gh->gh_flags & GL_NOCACHE) - handle_callback(gl, LM_ST_UNLOCKED, 0); + handle_callback(gl, LM_ST_UNLOCKED, 0, false); list_del_init(&gh->gh_list); if (find_first_holder(gl) == NULL) { @@ -1279,19 +1279,6 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs) gfs2_glock_dq(&ghs[num_gh]); } -/** - * gfs2_glock_dq_uninit_m - release multiple glocks - * @num_gh: the number of structures - * @ghs: an array of struct gfs2_holder structures - * - */ - -void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs) -{ - while (num_gh--) - gfs2_glock_dq_uninit(&ghs[num_gh]); -} - void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) { unsigned long delay = 0; @@ -1309,7 +1296,7 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) } spin_lock(&gl->gl_spin); - handle_callback(gl, state, delay); + handle_callback(gl, state, delay, true); spin_unlock(&gl->gl_spin); if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) gfs2_glock_put(gl); @@ -1422,7 +1409,7 @@ __acquires(&lru_lock) spin_unlock(&lru_lock); spin_lock(&gl->gl_spin); if (demote_ok(gl)) - handle_callback(gl, LM_ST_UNLOCKED, 0); + 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) @@ -1547,7 +1534,7 @@ static void clear_glock(struct gfs2_glock *gl) spin_lock(&gl->gl_spin); if (gl->gl_state != LM_ST_UNLOCKED) - handle_callback(gl, LM_ST_UNLOCKED, 0); + 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) @@ -1590,6 +1577,7 @@ static void dump_glock_func(struct gfs2_glock *gl) void gfs2_gl_hash_clear(struct gfs2_sbd *sdp) { set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags); + flush_workqueue(glock_workqueue); glock_hash_walk(clear_glock, sdp); flush_workqueue(glock_workqueue); wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0); diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index fd580b7..69f66e3 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -201,7 +201,6 @@ extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, struct gfs2_holder *gh); extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); -extern void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs); extern int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl); #define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0) extern __printf(2, 3) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 444b650..c66e99c 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -515,12 +515,12 @@ static int trans_go_demote_ok(const struct gfs2_glock *gl) * * gl_spin lock is held while calling this */ -static void iopen_go_callback(struct gfs2_glock *gl) +static void iopen_go_callback(struct gfs2_glock *gl, bool remote) { struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object; struct gfs2_sbd *sdp = gl->gl_sbd; - if (sdp->sd_vfs->s_flags & MS_RDONLY) + if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY)) return; if (gl->gl_demote_state == LM_ST_UNLOCKED && diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 156e42e..26aabd7 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -31,7 +31,6 @@ struct gfs2_holder; struct gfs2_glock; struct gfs2_quota_data; struct gfs2_trans; -struct gfs2_ail; struct gfs2_jdesc; struct gfs2_sbd; struct lm_lockops; @@ -53,7 +52,7 @@ struct gfs2_log_header_host { struct gfs2_log_operations { void (*lo_before_commit) (struct gfs2_sbd *sdp); - void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai); + void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr); void (*lo_before_scan) (struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, int pass); int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start, @@ -139,7 +138,7 @@ struct gfs2_bufdata { struct list_head bd_list; const struct gfs2_log_operations *bd_ops; - struct gfs2_ail *bd_ail; + struct gfs2_trans *bd_tr; struct list_head bd_ail_st_list; struct list_head bd_ail_gl_list; }; @@ -211,7 +210,7 @@ struct gfs2_glock_operations { int (*go_lock) (struct gfs2_holder *gh); void (*go_unlock) (struct gfs2_holder *gh); int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl); - void (*go_callback) (struct gfs2_glock *gl); + void (*go_callback)(struct gfs2_glock *gl, bool remote); const int go_type; const unsigned long go_flags; #define GLOF_ASPACE 1 @@ -433,6 +432,7 @@ struct gfs2_trans { struct gfs2_holder tr_t_gh; int tr_touched; + int tr_attached; unsigned int tr_num_buf_new; unsigned int tr_num_databuf_new; @@ -440,14 +440,12 @@ struct gfs2_trans { unsigned int tr_num_databuf_rm; unsigned int tr_num_revoke; unsigned int tr_num_revoke_rm; -}; -struct gfs2_ail { - struct list_head ai_list; + struct list_head tr_list; - unsigned int ai_first; - struct list_head ai_ail1_list; - struct list_head ai_ail2_list; + unsigned int tr_first; + struct list_head tr_ail1_list; + struct list_head tr_ail2_list; }; struct gfs2_journal_extent { @@ -588,6 +586,7 @@ struct lm_lockstruct { struct dlm_lksb ls_control_lksb; /* control_lock */ char ls_control_lvb[GDLM_LVB_SIZE]; /* control_lock lvb */ struct completion ls_sync_wait; /* {control,mounted}_{lock,unlock} */ + char *ls_lvb_bits; spinlock_t ls_recover_spin; /* protects following fields */ unsigned long ls_recover_flags; /* DFL_ */ @@ -709,6 +708,7 @@ struct gfs2_sbd { spinlock_t sd_log_lock; + struct gfs2_trans *sd_log_tr; unsigned int sd_log_blks_reserved; unsigned int sd_log_commited_buf; unsigned int sd_log_commited_databuf; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index cc00bd1..8833a4f 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -392,11 +392,15 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags) int error; int dblocks = 1; - error = gfs2_inplace_reserve(ip, RES_DINODE, flags); + error = gfs2_quota_lock_check(ip); if (error) goto out; - error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS, 0); + error = gfs2_inplace_reserve(ip, RES_DINODE, flags); + if (error) + goto out_quota; + + error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 0); if (error) goto out_ipreserv; @@ -409,6 +413,8 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags) out_ipreserv: gfs2_inplace_release(ip); +out_quota: + gfs2_quota_unlock(ip); out: return error; } @@ -440,59 +446,27 @@ static void gfs2_init_dir(struct buffer_head *dibh, */ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip, - const char *symname, struct buffer_head **bhp) + const char *symname) { - struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_dinode *di; struct buffer_head *dibh; - struct timespec tv = CURRENT_TIME; dibh = gfs2_meta_new(ip->i_gl, ip->i_no_addr); gfs2_trans_add_meta(ip->i_gl, dibh); - gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI); - gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); di = (struct gfs2_dinode *)dibh->b_data; + gfs2_dinode_out(ip, di); - di->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino); - di->di_num.no_addr = cpu_to_be64(ip->i_no_addr); - di->di_mode = cpu_to_be32(ip->i_inode.i_mode); - di->di_uid = cpu_to_be32(i_uid_read(&ip->i_inode)); - di->di_gid = cpu_to_be32(i_gid_read(&ip->i_inode)); - di->di_nlink = 0; - di->di_size = cpu_to_be64(ip->i_inode.i_size); - di->di_blocks = cpu_to_be64(1); - di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec); di->di_major = cpu_to_be32(MAJOR(ip->i_inode.i_rdev)); di->di_minor = cpu_to_be32(MINOR(ip->i_inode.i_rdev)); - di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_no_addr); - di->di_generation = cpu_to_be64(ip->i_generation); - di->di_flags = 0; di->__pad1 = 0; - di->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) ? GFS2_FORMAT_DE : 0); - di->di_height = 0; di->__pad2 = 0; di->__pad3 = 0; - di->di_depth = 0; - di->di_entries = 0; memset(&di->__pad4, 0, sizeof(di->__pad4)); - di->di_eattr = 0; - di->di_atime_nsec = cpu_to_be32(tv.tv_nsec); - di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec); - di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec); memset(&di->di_reserved, 0, sizeof(di->di_reserved)); + gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); switch(ip->i_inode.i_mode & S_IFMT) { - case S_IFREG: - if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) || - gfs2_tune_get(sdp, gt_new_files_jdata)) - di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA); - break; case S_IFDIR: - di->di_flags |= cpu_to_be32(dip->i_diskflags & - GFS2_DIF_INHERIT_JDATA); - di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA); - di->di_size = cpu_to_be64(sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)); - di->di_entries = cpu_to_be32(2); gfs2_init_dir(dibh, dip); break; case S_IFLNK: @@ -501,63 +475,17 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip, } set_buffer_uptodate(dibh); - - *bhp = dibh; -} - -static int make_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip, - const char *symname, struct buffer_head **bhp) -{ - struct inode *inode = &ip->i_inode; - struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - int error; - - error = gfs2_rindex_update(sdp); - if (error) - return error; - - error = gfs2_quota_lock(dip, inode->i_uid, inode->i_gid); - if (error) - return error; - - error = gfs2_quota_check(dip, inode->i_uid, inode->i_gid); - if (error) - goto out_quota; - - error = gfs2_trans_begin(sdp, RES_DINODE + RES_QUOTA, 0); - if (error) - goto out_quota; - - init_dinode(dip, ip, symname, bhp); - gfs2_quota_change(dip, +1, inode->i_uid, inode->i_gid); - gfs2_trans_end(sdp); - -out_quota: - gfs2_quota_unlock(dip); - return error; + brelse(dibh); } static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip) + struct gfs2_inode *ip, int arq) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - int alloc_required; - struct buffer_head *dibh; int error; - error = gfs2_rindex_update(sdp); - if (error) - return error; - - error = gfs2_quota_lock(dip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); - if (error) - goto fail; - - error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name); - if (alloc_required < 0) - goto fail_quota_locks; - if (alloc_required) { - error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid); + if (arq) { + error = gfs2_quota_lock_check(dip); if (error) goto fail_quota_locks; @@ -581,26 +509,12 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, if (error) goto fail_end_trans; - error = gfs2_meta_inode_buffer(ip, &dibh); - if (error) - goto fail_end_trans; - set_nlink(&ip->i_inode, S_ISDIR(ip->i_inode.i_mode) ? 2 : 1); - gfs2_trans_add_meta(ip->i_gl, dibh); - gfs2_dinode_out(ip, dibh->b_data); - brelse(dibh); - return 0; - fail_end_trans: gfs2_trans_end(sdp); - fail_ipreserv: - if (alloc_required) - gfs2_inplace_release(dip); - + gfs2_inplace_release(dip); fail_quota_locks: gfs2_quota_unlock(dip); - -fail: return error; } @@ -650,8 +564,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_glock *io_gl; int error; - struct buffer_head *bh = NULL; u32 aflags = 0; + int arq; if (!name->len || name->len > GFS2_FNAMESIZE) return -ENAMETOOLONG; @@ -660,6 +574,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) return error; + error = gfs2_rindex_update(sdp); + if (error) + return error; + error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs); if (error) goto fail; @@ -674,22 +592,48 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock; + arq = error = gfs2_diradd_alloc_required(dir, name); + if (error < 0) + goto fail_gunlock; + inode = new_inode(sdp->sd_vfs); - if (!inode) { - gfs2_glock_dq_uninit(ghs); - return -ENOMEM; - } + error = -ENOMEM; + if (!inode) + goto fail_gunlock; + ip = GFS2_I(inode); error = gfs2_rs_alloc(ip); if (error) goto fail_free_inode; - set_bit(GIF_INVALID, &ip->i_flags); inode->i_mode = mode; + set_nlink(inode, S_ISDIR(mode) ? 2 : 1); inode->i_rdev = dev; inode->i_size = size; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + gfs2_set_inode_blocks(inode, 1); munge_mode_uid_gid(dip, inode); ip->i_goal = dip->i_goal; + ip->i_diskflags = 0; + ip->i_eattr = 0; + ip->i_height = 0; + ip->i_depth = 0; + ip->i_entries = 0; + + switch(mode & S_IFMT) { + case S_IFREG: + if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) || + gfs2_tune_get(sdp, gt_new_files_jdata)) + ip->i_diskflags |= GFS2_DIF_JDATA; + gfs2_set_aops(inode); + break; + case S_IFDIR: + ip->i_diskflags |= (dip->i_diskflags & GFS2_DIF_INHERIT_JDATA); + ip->i_diskflags |= GFS2_DIF_JDATA; + ip->i_entries = 2; + break; + } + gfs2_set_inode_flags(inode); if ((GFS2_I(sdp->sd_root_dir->d_inode) == dip) || (dip->i_diskflags & GFS2_DIF_TOPDIR)) @@ -708,10 +652,13 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_free_inode; - error = make_dinode(dip, ip, symname, &bh); + error = gfs2_trans_begin(sdp, RES_DINODE, 0); if (error) goto fail_gunlock2; + init_dinode(dip, ip, symname); + gfs2_trans_end(sdp); + error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_gunlock2; @@ -725,10 +672,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_set_iop(inode); insert_inode_hash(inode); - error = gfs2_inode_refresh(ip); - if (error) - goto fail_gunlock3; - error = gfs2_acl_create(dip, inode); if (error) goto fail_gunlock3; @@ -737,18 +680,13 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock3; - error = link_dinode(dip, name, ip); + error = link_dinode(dip, name, ip, arq); if (error) goto fail_gunlock3; - if (bh) - brelse(bh); - - gfs2_trans_end(sdp); - gfs2_inplace_release(dip); - gfs2_quota_unlock(dip); mark_inode_dirty(inode); - gfs2_glock_dq_uninit_m(2, ghs); + gfs2_glock_dq_uninit(ghs); + gfs2_glock_dq_uninit(ghs + 1); d_instantiate(dentry, inode); return 0; @@ -769,12 +707,12 @@ fail_free_inode: fail_gunlock: gfs2_glock_dq_uninit(ghs); if (inode && !IS_ERR(inode)) { + clear_nlink(inode); + mark_inode_dirty(inode); set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags); iput(inode); } fail: - if (bh) - brelse(bh); return error; } @@ -1151,7 +1089,9 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry, static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { - return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0, 0); + struct gfs2_sbd *sdp = GFS2_SB(dir); + unsigned dsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode); + return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, dsize, 0); } /** diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 9802de0..c8423d6 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -483,12 +483,8 @@ static void control_lvb_write(struct lm_lockstruct *ls, uint32_t lvb_gen, static int all_jid_bits_clear(char *lvb) { - int i; - for (i = JID_BITMAP_OFFSET; i < GDLM_LVB_SIZE; i++) { - if (lvb[i]) - return 0; - } - return 1; + return !memchr_inv(lvb + JID_BITMAP_OFFSET, 0, + GDLM_LVB_SIZE - JID_BITMAP_OFFSET); } static void sync_wait_cb(void *arg) @@ -580,7 +576,6 @@ static void gfs2_control_func(struct work_struct *work) { struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_control_work.work); struct lm_lockstruct *ls = &sdp->sd_lockstruct; - char lvb_bits[GDLM_LVB_SIZE]; uint32_t block_gen, start_gen, lvb_gen, flags; int recover_set = 0; int write_lvb = 0; @@ -634,7 +629,7 @@ static void gfs2_control_func(struct work_struct *work) return; } - control_lvb_read(ls, &lvb_gen, lvb_bits); + control_lvb_read(ls, &lvb_gen, ls->ls_lvb_bits); spin_lock(&ls->ls_recover_spin); if (block_gen != ls->ls_recover_block || @@ -664,10 +659,10 @@ static void gfs2_control_func(struct work_struct *work) ls->ls_recover_result[i] = 0; - if (!test_bit_le(i, lvb_bits + JID_BITMAP_OFFSET)) + if (!test_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET)) continue; - __clear_bit_le(i, lvb_bits + JID_BITMAP_OFFSET); + __clear_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET); write_lvb = 1; } } @@ -691,7 +686,7 @@ static void gfs2_control_func(struct work_struct *work) continue; if (ls->ls_recover_submit[i] < start_gen) { ls->ls_recover_submit[i] = 0; - __set_bit_le(i, lvb_bits + JID_BITMAP_OFFSET); + __set_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET); } } /* even if there are no bits to set, we need to write the @@ -705,7 +700,7 @@ static void gfs2_control_func(struct work_struct *work) spin_unlock(&ls->ls_recover_spin); if (write_lvb) { - control_lvb_write(ls, start_gen, lvb_bits); + control_lvb_write(ls, start_gen, ls->ls_lvb_bits); flags = DLM_LKF_CONVERT | DLM_LKF_VALBLK; } else { flags = DLM_LKF_CONVERT; @@ -725,7 +720,7 @@ static void gfs2_control_func(struct work_struct *work) */ for (i = 0; i < recover_size; i++) { - if (test_bit_le(i, lvb_bits + JID_BITMAP_OFFSET)) { + if (test_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET)) { fs_info(sdp, "recover generation %u jid %d\n", start_gen, i); gfs2_recover_set(sdp, i); @@ -758,7 +753,6 @@ static void gfs2_control_func(struct work_struct *work) static int control_mount(struct gfs2_sbd *sdp) { struct lm_lockstruct *ls = &sdp->sd_lockstruct; - char lvb_bits[GDLM_LVB_SIZE]; uint32_t start_gen, block_gen, mount_gen, lvb_gen; int mounted_mode; int retries = 0; @@ -857,7 +851,7 @@ locks_done: * lvb_gen will be non-zero. */ - control_lvb_read(ls, &lvb_gen, lvb_bits); + control_lvb_read(ls, &lvb_gen, ls->ls_lvb_bits); if (lvb_gen == 0xFFFFFFFF) { /* special value to force mount attempts to fail */ @@ -887,7 +881,7 @@ locks_done: * and all lvb bits to be clear (no pending journal recoveries.) */ - if (!all_jid_bits_clear(lvb_bits)) { + if (!all_jid_bits_clear(ls->ls_lvb_bits)) { /* journals need recovery, wait until all are clear */ fs_info(sdp, "control_mount wait for journal recovery\n"); goto restart; @@ -949,7 +943,6 @@ static int dlm_recovery_wait(void *word) static int control_first_done(struct gfs2_sbd *sdp) { struct lm_lockstruct *ls = &sdp->sd_lockstruct; - char lvb_bits[GDLM_LVB_SIZE]; uint32_t start_gen, block_gen; int error; @@ -991,8 +984,8 @@ restart: memset(ls->ls_recover_result, 0, ls->ls_recover_size*sizeof(uint32_t)); spin_unlock(&ls->ls_recover_spin); - memset(lvb_bits, 0, sizeof(lvb_bits)); - control_lvb_write(ls, start_gen, lvb_bits); + memset(ls->ls_lvb_bits, 0, GDLM_LVB_SIZE); + control_lvb_write(ls, start_gen, ls->ls_lvb_bits); error = mounted_lock(sdp, DLM_LOCK_PR, DLM_LKF_CONVERT); if (error) @@ -1022,6 +1015,12 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots, uint32_t old_size, new_size; int i, max_jid; + if (!ls->ls_lvb_bits) { + ls->ls_lvb_bits = kzalloc(GDLM_LVB_SIZE, GFP_NOFS); + if (!ls->ls_lvb_bits) + return -ENOMEM; + } + max_jid = 0; for (i = 0; i < num_slots; i++) { if (max_jid < slots[i].slot - 1) @@ -1057,6 +1056,7 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots, static void free_recover_size(struct lm_lockstruct *ls) { + kfree(ls->ls_lvb_bits); kfree(ls->ls_recover_submit); kfree(ls->ls_recover_result); ls->ls_recover_submit = NULL; @@ -1205,6 +1205,7 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table) ls->ls_recover_size = 0; ls->ls_recover_submit = NULL; ls->ls_recover_result = NULL; + ls->ls_lvb_bits = NULL; error = set_recover_size(sdp, NULL, 0); if (error) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 9a2ca8b..b404f48 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -73,7 +73,7 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, void gfs2_remove_from_ail(struct gfs2_bufdata *bd) { - bd->bd_ail = NULL; + bd->bd_tr = NULL; list_del_init(&bd->bd_ail_st_list); list_del_init(&bd->bd_ail_gl_list); atomic_dec(&bd->bd_gl->gl_ail_count); @@ -90,7 +90,7 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd) static int gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct writeback_control *wbc, - struct gfs2_ail *ai) + struct gfs2_trans *tr) __releases(&sdp->sd_ail_lock) __acquires(&sdp->sd_ail_lock) { @@ -99,15 +99,15 @@ __acquires(&sdp->sd_ail_lock) struct gfs2_bufdata *bd, *s; struct buffer_head *bh; - list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, bd_ail_st_list) { + list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) { bh = bd->bd_bh; - gfs2_assert(sdp, bd->bd_ail == ai); + gfs2_assert(sdp, bd->bd_tr == tr); if (!buffer_busy(bh)) { if (!buffer_uptodate(bh)) gfs2_io_error_bh(sdp, bh); - list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); + list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list); continue; } @@ -116,7 +116,7 @@ __acquires(&sdp->sd_ail_lock) if (gl == bd->bd_gl) continue; gl = bd->bd_gl; - list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list); + list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list); mapping = bh->b_page->mapping; if (!mapping) continue; @@ -144,15 +144,15 @@ __acquires(&sdp->sd_ail_lock) void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc) { struct list_head *head = &sdp->sd_ail1_list; - struct gfs2_ail *ai; + struct gfs2_trans *tr; trace_gfs2_ail_flush(sdp, wbc, 1); spin_lock(&sdp->sd_ail_lock); restart: - list_for_each_entry_reverse(ai, head, ai_list) { + list_for_each_entry_reverse(tr, head, tr_list) { if (wbc->nr_to_write <= 0) break; - if (gfs2_ail1_start_one(sdp, wbc, ai)) + if (gfs2_ail1_start_one(sdp, wbc, tr)) goto restart; } spin_unlock(&sdp->sd_ail_lock); @@ -183,20 +183,20 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp) * */ -static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) +static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { struct gfs2_bufdata *bd, *s; struct buffer_head *bh; - list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, + list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) { bh = bd->bd_bh; - gfs2_assert(sdp, bd->bd_ail == ai); + gfs2_assert(sdp, bd->bd_tr == tr); if (buffer_busy(bh)) continue; if (!buffer_uptodate(bh)) gfs2_io_error_bh(sdp, bh); - list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); + list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list); } } @@ -210,14 +210,14 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) static int gfs2_ail1_empty(struct gfs2_sbd *sdp) { - struct gfs2_ail *ai, *s; + struct gfs2_trans *tr, *s; int ret; spin_lock(&sdp->sd_ail_lock); - list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) { - gfs2_ail1_empty_one(sdp, ai); - if (list_empty(&ai->ai_ail1_list)) - list_move(&ai->ai_list, &sdp->sd_ail2_list); + list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) { + gfs2_ail1_empty_one(sdp, tr); + if (list_empty(&tr->tr_ail1_list)) + list_move(&tr->tr_list, &sdp->sd_ail2_list); else break; } @@ -229,13 +229,13 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp) static void gfs2_ail1_wait(struct gfs2_sbd *sdp) { - struct gfs2_ail *ai; + struct gfs2_trans *tr; struct gfs2_bufdata *bd; struct buffer_head *bh; spin_lock(&sdp->sd_ail_lock); - list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) { - list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) { + list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) { + list_for_each_entry(bd, &tr->tr_ail1_list, bd_ail_st_list) { bh = bd->bd_bh; if (!buffer_locked(bh)) continue; @@ -256,40 +256,40 @@ static void gfs2_ail1_wait(struct gfs2_sbd *sdp) * */ -static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) +static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { - struct list_head *head = &ai->ai_ail2_list; + struct list_head *head = &tr->tr_ail2_list; struct gfs2_bufdata *bd; while (!list_empty(head)) { bd = list_entry(head->prev, struct gfs2_bufdata, bd_ail_st_list); - gfs2_assert(sdp, bd->bd_ail == ai); + gfs2_assert(sdp, bd->bd_tr == tr); gfs2_remove_from_ail(bd); } } static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail) { - struct gfs2_ail *ai, *safe; + struct gfs2_trans *tr, *safe; unsigned int old_tail = sdp->sd_log_tail; int wrap = (new_tail < old_tail); int a, b, rm; spin_lock(&sdp->sd_ail_lock); - list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) { - a = (old_tail <= ai->ai_first); - b = (ai->ai_first < new_tail); + list_for_each_entry_safe(tr, safe, &sdp->sd_ail2_list, tr_list) { + a = (old_tail <= tr->tr_first); + b = (tr->tr_first < new_tail); rm = (wrap) ? (a || b) : (a && b); if (!rm) continue; - gfs2_ail2_empty_one(sdp, ai); - list_del(&ai->ai_list); - gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list)); - gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list)); - kfree(ai); + gfs2_ail2_empty_one(sdp, tr); + list_del(&tr->tr_list); + gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list)); + gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list)); + kfree(tr); } spin_unlock(&sdp->sd_ail_lock); @@ -435,7 +435,7 @@ static unsigned int calc_reserved(struct gfs2_sbd *sdp) static unsigned int current_tail(struct gfs2_sbd *sdp) { - struct gfs2_ail *ai; + struct gfs2_trans *tr; unsigned int tail; spin_lock(&sdp->sd_ail_lock); @@ -443,8 +443,9 @@ static unsigned int current_tail(struct gfs2_sbd *sdp) if (list_empty(&sdp->sd_ail1_list)) { tail = sdp->sd_log_head; } else { - ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list); - tail = ai->ai_first; + tr = list_entry(sdp->sd_ail1_list.prev, struct gfs2_trans, + tr_list); + tail = tr->tr_first; } spin_unlock(&sdp->sd_ail_lock); @@ -600,7 +601,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags) void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) { - struct gfs2_ail *ai; + struct gfs2_trans *tr; down_write(&sdp->sd_log_flush_lock); @@ -611,9 +612,12 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) } trace_gfs2_log_flush(sdp, 1); - ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL); - INIT_LIST_HEAD(&ai->ai_ail1_list); - INIT_LIST_HEAD(&ai->ai_ail2_list); + tr = sdp->sd_log_tr; + if (tr) { + sdp->sd_log_tr = NULL; + INIT_LIST_HEAD(&tr->tr_ail1_list); + INIT_LIST_HEAD(&tr->tr_ail2_list); + } if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) { printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf, @@ -630,7 +634,8 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) sdp->sd_log_flush_head = sdp->sd_log_head; sdp->sd_log_flush_wrapped = 0; - ai->ai_first = sdp->sd_log_flush_head; + if (tr) + tr->tr_first = sdp->sd_log_flush_head; gfs2_ordered_write(sdp); lops_before_commit(sdp); @@ -643,7 +648,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) trace_gfs2_log_blocks(sdp, -1); log_write_header(sdp, 0); } - lops_after_commit(sdp, ai); + lops_after_commit(sdp, tr); gfs2_log_lock(sdp); sdp->sd_log_head = sdp->sd_log_flush_head; @@ -653,16 +658,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) sdp->sd_log_commited_revoke = 0; spin_lock(&sdp->sd_ail_lock); - if (!list_empty(&ai->ai_ail1_list)) { - list_add(&ai->ai_list, &sdp->sd_ail1_list); - ai = NULL; + if (tr && !list_empty(&tr->tr_ail1_list)) { + list_add(&tr->tr_list, &sdp->sd_ail1_list); + tr = NULL; } spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); trace_gfs2_log_flush(sdp, 0); up_write(&sdp->sd_log_flush_lock); - kfree(ai); + kfree(tr); } static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) @@ -687,6 +692,12 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) sdp->sd_jdesc->jd_blocks); sdp->sd_log_blks_reserved = reserved; + if (sdp->sd_log_tr == NULL && + (tr->tr_num_buf_new || tr->tr_num_databuf_new)) { + gfs2_assert_withdraw(sdp, tr->tr_t_gh.gh_gl); + sdp->sd_log_tr = tr; + tr->tr_attached = 1; + } gfs2_log_unlock(sdp); } @@ -708,7 +719,6 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { log_refund(sdp, tr); - up_read(&sdp->sd_log_flush_lock); if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) || ((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) > diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index a505597..7318abf 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -53,8 +53,8 @@ void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh) * to in-place disk block, remove it from the AIL. */ spin_lock(&sdp->sd_ail_lock); - if (bd->bd_ail) - list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list); + if (bd->bd_tr) + list_move(&bd->bd_ail_st_list, &bd->bd_tr->tr_ail2_list); spin_unlock(&sdp->sd_ail_lock); get_bh(bh); atomic_inc(&sdp->sd_log_pinned); @@ -94,7 +94,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd) */ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, - struct gfs2_ail *ai) + struct gfs2_trans *tr) { struct gfs2_bufdata *bd = bh->b_private; @@ -109,7 +109,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, maybe_release_space(bd); spin_lock(&sdp->sd_ail_lock); - if (bd->bd_ail) { + if (bd->bd_tr) { list_del(&bd->bd_ail_st_list); brelse(bh); } else { @@ -117,8 +117,8 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list); atomic_inc(&gl->gl_ail_count); } - bd->bd_ail = ai; - list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list); + bd->bd_tr = tr; + list_add(&bd->bd_ail_st_list, &tr->tr_ail1_list); spin_unlock(&sdp->sd_ail_lock); clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); @@ -480,17 +480,22 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) &sdp->sd_log_le_buf, 0); } -static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) +static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { struct list_head *head = &sdp->sd_log_le_buf; struct gfs2_bufdata *bd; + if (tr == NULL) { + gfs2_assert(sdp, list_empty(head)); + return; + } + while (!list_empty(head)) { bd = list_entry(head->next, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); sdp->sd_log_num_buf--; - gfs2_unpin(sdp, bd->bd_bh, ai); + gfs2_unpin(sdp, bd->bd_bh, tr); } gfs2_assert_warn(sdp, !sdp->sd_log_num_buf); } @@ -613,7 +618,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_write_page(sdp, page); } -static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) +static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { struct list_head *head = &sdp->sd_log_le_revoke; struct gfs2_bufdata *bd; @@ -791,16 +796,21 @@ static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks); } -static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) +static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { struct list_head *head = &sdp->sd_log_le_databuf; struct gfs2_bufdata *bd; + if (tr == NULL) { + gfs2_assert(sdp, list_empty(head)); + return; + } + while (!list_empty(head)) { bd = list_entry(head->next, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); sdp->sd_log_num_databuf--; - gfs2_unpin(sdp, bd->bd_bh, ai); + gfs2_unpin(sdp, bd->bd_bh, tr); } gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf); } diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index ba77b7d..87e062e 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -55,12 +55,13 @@ static inline void lops_before_commit(struct gfs2_sbd *sdp) gfs2_log_ops[x]->lo_before_commit(sdp); } -static inline void lops_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) +static inline void lops_after_commit(struct gfs2_sbd *sdp, + struct gfs2_trans *tr) { int x; for (x = 0; gfs2_log_ops[x]; x++) if (gfs2_log_ops[x]->lo_after_commit) - gfs2_log_ops[x]->lo_after_commit(sdp, ai); + gfs2_log_ops[x]->lo_after_commit(sdp, tr); } static inline void lops_before_scan(struct gfs2_jdesc *jd, diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index b059bbb..1a89afb 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -295,7 +295,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int } if (bd) { spin_lock(&sdp->sd_ail_lock); - if (bd->bd_ail) { + if (bd->bd_tr) { gfs2_remove_from_ail(bd); bh->b_private = NULL; bd->bd_bh = NULL; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index d1f51fd..0c5a575 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -576,7 +576,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) RB_CLEAR_NODE(&ip->i_res->rs_node); out: up_write(&ip->i_rw_mutex); - return 0; + return error; } static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) @@ -592,7 +592,7 @@ static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) * @rs: The reservation to remove * */ -static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs) +static void __rs_deltree(struct gfs2_blkreserv *rs) { struct gfs2_rgrpd *rgd; @@ -605,7 +605,7 @@ static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs) RB_CLEAR_NODE(&rs->rs_node); if (rs->rs_free) { - /* return reserved blocks to the rgrp and the ip */ + /* return reserved blocks to the rgrp */ BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free); rs->rs_rbm.rgd->rd_reserved -= rs->rs_free; rs->rs_free = 0; @@ -619,14 +619,14 @@ static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs) * @rs: The reservation to remove * */ -void gfs2_rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs) +void gfs2_rs_deltree(struct gfs2_blkreserv *rs) { struct gfs2_rgrpd *rgd; rgd = rs->rs_rbm.rgd; if (rgd) { spin_lock(&rgd->rd_rsspin); - __rs_deltree(ip, rs); + __rs_deltree(rs); spin_unlock(&rgd->rd_rsspin); } } @@ -640,7 +640,7 @@ void gfs2_rs_delete(struct gfs2_inode *ip) { down_write(&ip->i_rw_mutex); if (ip->i_res) { - gfs2_rs_deltree(ip, ip->i_res); + gfs2_rs_deltree(ip->i_res); BUG_ON(ip->i_res->rs_free); kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); ip->i_res = NULL; @@ -664,7 +664,7 @@ static void return_all_reservations(struct gfs2_rgrpd *rgd) spin_lock(&rgd->rd_rsspin); while ((n = rb_first(&rgd->rd_rstree))) { rs = rb_entry(n, struct gfs2_blkreserv, rs_node); - __rs_deltree(NULL, rs); + __rs_deltree(rs); } spin_unlock(&rgd->rd_rsspin); } @@ -1181,12 +1181,9 @@ int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed) { struct super_block *sb = sdp->sd_vfs; - struct block_device *bdev = sb->s_bdev; - const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize / - bdev_logical_block_size(sb->s_bdev); u64 blk; sector_t start = 0; - sector_t nr_sects = 0; + sector_t nr_blks = 0; int rv; unsigned int x; u32 trimmed = 0; @@ -1206,35 +1203,34 @@ int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, if (diff == 0) continue; blk = offset + ((bi->bi_start + x) * GFS2_NBBY); - blk *= sects_per_blk; /* convert to sectors */ while(diff) { if (diff & 1) { - if (nr_sects == 0) + if (nr_blks == 0) goto start_new_extent; - if ((start + nr_sects) != blk) { - if (nr_sects >= minlen) { - rv = blkdev_issue_discard(bdev, - start, nr_sects, + if ((start + nr_blks) != blk) { + if (nr_blks >= minlen) { + rv = sb_issue_discard(sb, + start, nr_blks, GFP_NOFS, 0); if (rv) goto fail; - trimmed += nr_sects; + trimmed += nr_blks; } - nr_sects = 0; + nr_blks = 0; start_new_extent: start = blk; } - nr_sects += sects_per_blk; + nr_blks++; } diff >>= 2; - blk += sects_per_blk; + blk++; } } - if (nr_sects >= minlen) { - rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0); + if (nr_blks >= minlen) { + rv = sb_issue_discard(sb, start, nr_blks, GFP_NOFS, 0); if (rv) goto fail; - trimmed += nr_sects; + trimmed += nr_blks; } if (ptrimmed) *ptrimmed = trimmed; @@ -1878,7 +1874,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, u32 requested, u32 aflags) /* Drop reservation, if we couldn't use reserved rgrp */ if (gfs2_rs_active(rs)) - gfs2_rs_deltree(ip, rs); + gfs2_rs_deltree(rs); check_rgrp: /* Check for unlinked inodes which can be reclaimed */ if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK) @@ -2091,7 +2087,7 @@ static void gfs2_adjust_reservation(struct gfs2_inode *ip, if (rs->rs_free && !ret) goto out; } - __rs_deltree(ip, rs); + __rs_deltree(rs); } out: spin_unlock(&rgd->rd_rsspin); @@ -2184,13 +2180,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, if (dinode) gfs2_trans_add_unrevoke(sdp, block, 1); - /* - * This needs reviewing to see why we cannot do the quota change - * at this point in the dinode case. - */ - if (ndata) - gfs2_quota_change(ip, ndata, ip->i_inode.i_uid, - ip->i_inode.i_gid); + gfs2_quota_change(ip, *nblocks, ip->i_inode.i_uid, ip->i_inode.i_gid); rbm.rgd->rd_free_clone -= *nblocks; trace_gfs2_block_alloc(ip, rbm.rgd, block, *nblocks, diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 8421858..5b3f4a8 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -47,7 +47,7 @@ extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, bool dinode, u64 *generation); extern int gfs2_rs_alloc(struct gfs2_inode *ip); -extern void gfs2_rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs); +extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); extern void gfs2_rs_delete(struct gfs2_inode *ip); extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index cab77b8..917c8e1 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1512,7 +1512,7 @@ out_truncate: out_unlock: /* Error path for case 1 */ if (gfs2_rs_active(ip->i_res)) - gfs2_rs_deltree(ip, ip->i_res); + gfs2_rs_deltree(ip->i_res); if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) gfs2_glock_dq(&ip->i_iopen_gh); diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h index 2ee13e8..20c007d 100644 --- a/fs/gfs2/trace_gfs2.h +++ b/fs/gfs2/trace_gfs2.h @@ -159,9 +159,9 @@ TRACE_EVENT(gfs2_glock_put, /* Callback (local or remote) requesting lock demotion */ TRACE_EVENT(gfs2_demote_rq, - TP_PROTO(const struct gfs2_glock *gl), + TP_PROTO(const struct gfs2_glock *gl, bool remote), - TP_ARGS(gl), + TP_ARGS(gl, remote), TP_STRUCT__entry( __field( dev_t, dev ) @@ -170,6 +170,7 @@ TRACE_EVENT(gfs2_demote_rq, __field( u8, cur_state ) __field( u8, dmt_state ) __field( unsigned long, flags ) + __field( bool, remote ) ), TP_fast_assign( @@ -179,14 +180,16 @@ TRACE_EVENT(gfs2_demote_rq, __entry->cur_state = glock_trace_state(gl->gl_state); __entry->dmt_state = glock_trace_state(gl->gl_demote_state); __entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0); + __entry->remote = remote; ), - TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s", + TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype, (unsigned long long)__entry->glnum, glock_trace_name(__entry->cur_state), glock_trace_name(__entry->dmt_state), - show_glock_flags(__entry->flags)) + show_glock_flags(__entry->flags), + __entry->remote ? "remote" : "local") ); diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 88162fa..7374907 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -96,7 +96,8 @@ static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) static void gfs2_print_trans(const struct gfs2_trans *tr) { - print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); + printk(KERN_WARNING "GFS2: Transaction created at: %pSR\n", + (void *)tr->tr_ip); printk(KERN_WARNING "GFS2: blocks=%u revokes=%u reserved=%u touched=%d\n", tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched); printk(KERN_WARNING "GFS2: Buf %u/%u Databuf %u/%u Revoke %u/%u\n", @@ -135,8 +136,10 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) if (tr->tr_t_gh.gh_gl) { gfs2_glock_dq(&tr->tr_t_gh); gfs2_holder_uninit(&tr->tr_t_gh); - kfree(tr); + if (!tr->tr_attached) + kfree(tr); } + up_read(&sdp->sd_log_flush_lock); if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS) gfs2_log_flush(sdp, NULL); diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index 571abe9..de69d8a 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -22,7 +22,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) return -ENOMEM; fd->search_key = ptr; fd->key = ptr + tree->max_key_len + 2; - dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); + hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", + tree->cnid, __builtin_return_address(0)); mutex_lock(&tree->tree_lock); return 0; } @@ -31,7 +32,8 @@ void hfs_find_exit(struct hfs_find_data *fd) { hfs_bnode_put(fd->bnode); kfree(fd->search_key); - dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0)); + hfs_dbg(BNODE_REFS, "find_exit: %d (%p)\n", + fd->tree->cnid, __builtin_return_address(0)); mutex_unlock(&fd->tree->tree_lock); fd->tree = NULL; } @@ -135,8 +137,8 @@ int hfs_brec_find(struct hfs_find_data *fd) return res; invalid: - printk(KERN_ERR "hfs: inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", - height, bnode->height, bnode->type, nidx, parent); + pr_err("inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", + height, bnode->height, bnode->type, nidx, parent); res = -EIO; release: hfs_bnode_put(bnode); diff --git a/fs/hfs/bitmap.c b/fs/hfs/bitmap.c index c6e9736..28307bc 100644 --- a/fs/hfs/bitmap.c +++ b/fs/hfs/bitmap.c @@ -158,7 +158,7 @@ u32 hfs_vbm_search_free(struct super_block *sb, u32 goal, u32 *num_bits) } } - dprint(DBG_BITMAP, "alloc_bits: %u,%u\n", pos, *num_bits); + hfs_dbg(BITMAP, "alloc_bits: %u,%u\n", pos, *num_bits); HFS_SB(sb)->free_ablocks -= *num_bits; hfs_bitmap_dirty(sb); out: @@ -200,7 +200,7 @@ int hfs_clear_vbm_bits(struct super_block *sb, u16 start, u16 count) if (!count) return 0; - dprint(DBG_BITMAP, "clear_bits: %u,%u\n", start, count); + hfs_dbg(BITMAP, "clear_bits: %u,%u\n", start, count); /* are all of the bits in range? */ if ((start + count) > HFS_SB(sb)->fs_ablocks) return -2; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index cdb41a1..f3b1a15 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -100,7 +100,7 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, struct hfs_btree *tree; struct page *src_page, *dst_page; - dprint(DBG_BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); if (!len) return; tree = src_node->tree; @@ -120,7 +120,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) struct page *page; void *ptr; - dprint(DBG_BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += node->page_offset; @@ -138,16 +138,16 @@ void hfs_bnode_dump(struct hfs_bnode *node) __be32 cnid; int i, off, key_off; - dprint(DBG_BNODE_MOD, "bnode: %d\n", node->this); + hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this); hfs_bnode_read(node, &desc, 0, sizeof(desc)); - dprint(DBG_BNODE_MOD, "%d, %d, %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n", be32_to_cpu(desc.next), be32_to_cpu(desc.prev), desc.type, desc.height, be16_to_cpu(desc.num_recs)); off = node->tree->node_size - 2; for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) { key_off = hfs_bnode_read_u16(node, off); - dprint(DBG_BNODE_MOD, " %d", key_off); + hfs_dbg_cont(BNODE_MOD, " %d", key_off); if (i && node->type == HFS_NODE_INDEX) { int tmp; @@ -155,17 +155,18 @@ void hfs_bnode_dump(struct hfs_bnode *node) tmp = (hfs_bnode_read_u8(node, key_off) | 1) + 1; else tmp = node->tree->max_key_len + 1; - dprint(DBG_BNODE_MOD, " (%d,%d", tmp, hfs_bnode_read_u8(node, key_off)); + hfs_dbg_cont(BNODE_MOD, " (%d,%d", + tmp, hfs_bnode_read_u8(node, key_off)); hfs_bnode_read(node, &cnid, key_off + tmp, 4); - dprint(DBG_BNODE_MOD, ",%d)", be32_to_cpu(cnid)); + hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid)); } else if (i && node->type == HFS_NODE_LEAF) { int tmp; tmp = hfs_bnode_read_u8(node, key_off); - dprint(DBG_BNODE_MOD, " (%d)", tmp); + hfs_dbg_cont(BNODE_MOD, " (%d)", tmp); } } - dprint(DBG_BNODE_MOD, "\n"); + hfs_dbg_cont(BNODE_MOD, "\n"); } void hfs_bnode_unlink(struct hfs_bnode *node) @@ -220,7 +221,7 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid) struct hfs_bnode *node; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node %d in B*Tree\n", cnid); + pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } @@ -243,7 +244,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) loff_t off; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node %d in B*Tree\n", cnid); + pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } @@ -257,8 +258,8 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); atomic_set(&node->refcnt, 1); - dprint(DBG_BNODE_REFS, "new_node(%d:%d): 1\n", - node->tree->cnid, node->this); + hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n", + node->tree->cnid, node->this); init_waitqueue_head(&node->lock_wq); spin_lock(&tree->hash_lock); node2 = hfs_bnode_findhash(tree, cnid); @@ -301,7 +302,7 @@ void hfs_bnode_unhash(struct hfs_bnode *node) { struct hfs_bnode **p; - dprint(DBG_BNODE_REFS, "remove_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)]; *p && *p != node; p = &(*p)->next_hash) @@ -443,8 +444,9 @@ void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); - dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n", - node->tree->cnid, node->this, atomic_read(&node->refcnt)); + hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n", + node->tree->cnid, node->this, + atomic_read(&node->refcnt)); } } @@ -455,8 +457,9 @@ void hfs_bnode_put(struct hfs_bnode *node) struct hfs_btree *tree = node->tree; int i; - dprint(DBG_BNODE_REFS, "put_node(%d:%d): %d\n", - node->tree->cnid, node->this, atomic_read(&node->refcnt)); + hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n", + node->tree->cnid, node->this, + atomic_read(&node->refcnt)); BUG_ON(!atomic_read(&node->refcnt)); if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) return; diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 92fb358..9f4ee7f 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -47,15 +47,13 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) if (node->tree->attributes & HFS_TREE_BIGKEYS) { retval = hfs_bnode_read_u16(node, recoff) + 2; if (retval > node->tree->max_key_len + 2) { - printk(KERN_ERR "hfs: keylen %d too large\n", - retval); + pr_err("keylen %d too large\n", retval); retval = 0; } } else { retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1; if (retval > node->tree->max_key_len + 1) { - printk(KERN_ERR "hfs: keylen %d too large\n", - retval); + pr_err("keylen %d too large\n", retval); retval = 0; } } @@ -94,7 +92,8 @@ again: end_rec_off = tree->node_size - (node->num_recs + 1) * 2; end_off = hfs_bnode_read_u16(node, end_rec_off); end_rec_off -= 2; - dprint(DBG_BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", rec, size, end_off, end_rec_off); + hfs_dbg(BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", + rec, size, end_off, end_rec_off); if (size > end_rec_off - end_off) { if (new_node) panic("not enough room!\n"); @@ -190,7 +189,8 @@ again: mark_inode_dirty(tree->inode); } hfs_bnode_dump(node); - dprint(DBG_BNODE_MOD, "remove_rec: %d, %d\n", fd->record, fd->keylength + fd->entrylength); + hfs_dbg(BNODE_MOD, "remove_rec: %d, %d\n", + fd->record, fd->keylength + fd->entrylength); if (!--node->num_recs) { hfs_bnode_unlink(node); if (!node->parent) @@ -240,7 +240,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) if (IS_ERR(new_node)) return new_node; hfs_bnode_get(node); - dprint(DBG_BNODE_MOD, "split_nodes: %d - %d - %d\n", + hfs_dbg(BNODE_MOD, "split_nodes: %d - %d - %d\n", node->this, new_node->this, node->next); new_node->next = node->next; new_node->prev = node->this; @@ -374,7 +374,8 @@ again: newkeylen = (hfs_bnode_read_u8(node, 14) | 1) + 1; else fd->keylength = newkeylen = tree->max_key_len + 1; - dprint(DBG_BNODE_MOD, "update_rec: %d, %d, %d\n", rec, fd->keylength, newkeylen); + hfs_dbg(BNODE_MOD, "update_rec: %d, %d, %d\n", + rec, fd->keylength, newkeylen); rec_off = tree->node_size - (rec + 2) * 2; end_rec_off = tree->node_size - (parent->num_recs + 1) * 2; @@ -385,7 +386,7 @@ again: end_off = hfs_bnode_read_u16(parent, end_rec_off); if (end_rec_off - end_off < diff) { - printk(KERN_DEBUG "hfs: splitting index node...\n"); + printk(KERN_DEBUG "splitting index node...\n"); fd->bnode = parent; new_node = hfs_bnode_split(fd); if (IS_ERR(new_node)) diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 1cbdeea..1ab19e6 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -48,7 +48,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke mdb->drXTFlSize, be32_to_cpu(mdb->drXTClpSiz)); if (HFS_I(tree->inode)->alloc_blocks > HFS_I(tree->inode)->first_blocks) { - printk(KERN_ERR "hfs: invalid btree extent records\n"); + pr_err("invalid btree extent records\n"); unlock_new_inode(tree->inode); goto free_inode; } @@ -60,8 +60,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke mdb->drCTFlSize, be32_to_cpu(mdb->drCTClpSiz)); if (!HFS_I(tree->inode)->first_blocks) { - printk(KERN_ERR "hfs: invalid btree extent records " - "(0 size).\n"); + pr_err("invalid btree extent records (0 size)\n"); unlock_new_inode(tree->inode); goto free_inode; } @@ -100,15 +99,15 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke switch (id) { case HFS_EXT_CNID: if (tree->max_key_len != HFS_MAX_EXT_KEYLEN) { - printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", - tree->max_key_len); + pr_err("invalid extent max_key_len %d\n", + tree->max_key_len); goto fail_page; } break; case HFS_CAT_CNID: if (tree->max_key_len != HFS_MAX_CAT_KEYLEN) { - printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", - tree->max_key_len); + pr_err("invalid catalog max_key_len %d\n", + tree->max_key_len); goto fail_page; } break; @@ -146,8 +145,9 @@ void hfs_btree_close(struct hfs_btree *tree) while ((node = tree->node_hash[i])) { tree->node_hash[i] = node->next_hash; if (atomic_read(&node->refcnt)) - printk(KERN_ERR "hfs: node %d:%d still has %d user(s)!\n", - node->tree->cnid, node->this, atomic_read(&node->refcnt)); + pr_err("node %d:%d still has %d user(s)!\n", + node->tree->cnid, node->this, + atomic_read(&node->refcnt)); hfs_bnode_free(node); tree->node_hash_cnt--; } @@ -290,7 +290,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) kunmap(*pagep); nidx = node->next; if (!nidx) { - printk(KERN_DEBUG "hfs: create new bmap node...\n"); + printk(KERN_DEBUG "create new bmap node...\n"); next_node = hfs_bmap_new_bmap(node, idx); } else next_node = hfs_bnode_find(tree, nidx); @@ -316,7 +316,7 @@ void hfs_bmap_free(struct hfs_bnode *node) u32 nidx; u8 *data, byte, m; - dprint(DBG_BNODE_MOD, "btree_free_node: %u\n", node->this); + hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this); tree = node->tree; nidx = node->this; node = hfs_bnode_find(tree, 0); @@ -331,7 +331,8 @@ void hfs_bmap_free(struct hfs_bnode *node) hfs_bnode_put(node); if (!i) { /* panic */; - printk(KERN_CRIT "hfs: unable to free bnode %u. bmap not found!\n", node->this); + pr_crit("unable to free bnode %u. bmap not found!\n", + node->this); return; } node = hfs_bnode_find(tree, i); @@ -339,7 +340,8 @@ void hfs_bmap_free(struct hfs_bnode *node) return; if (node->type != HFS_NODE_MAP) { /* panic */; - printk(KERN_CRIT "hfs: invalid bmap found! (%u,%d)\n", node->this, node->type); + pr_crit("invalid bmap found! (%u,%d)\n", + node->this, node->type); hfs_bnode_put(node); return; } @@ -352,7 +354,8 @@ void hfs_bmap_free(struct hfs_bnode *node) m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { - printk(KERN_CRIT "hfs: trying to free free bnode %u(%d)\n", node->this, node->type); + pr_crit("trying to free free bnode %u(%d)\n", + node->this, node->type); kunmap(page); hfs_bnode_put(node); return; diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 424b033..ff0316b 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -87,12 +87,15 @@ int hfs_cat_create(u32 cnid, struct inode *dir, struct qstr *str, struct inode * int entry_size; int err; - dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink); + hfs_dbg(CAT_MOD, "create_cat: %s,%u(%d)\n", + str->name, cnid, inode->i_nlink); if (dir->i_size >= HFS_MAX_VALENCE) return -ENOSPC; sb = dir->i_sb; - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (err) + return err; hfs_cat_build_key(sb, fd.search_key, cnid, NULL); entry_size = hfs_cat_build_thread(sb, &entry, S_ISDIR(inode->i_mode) ? @@ -184,14 +187,14 @@ int hfs_cat_find_brec(struct super_block *sb, u32 cnid, type = rec.type; if (type != HFS_CDR_THD && type != HFS_CDR_FTH) { - printk(KERN_ERR "hfs: found bad thread record in catalog\n"); + pr_err("found bad thread record in catalog\n"); return -EIO; } fd->search_key->cat.ParID = rec.thread.ParID; len = fd->search_key->cat.CName.len = rec.thread.CName.len; if (len > HFS_NAMELEN) { - printk(KERN_ERR "hfs: bad catalog namelength\n"); + pr_err("bad catalog namelength\n"); return -EIO; } memcpy(fd->search_key->cat.CName.name, rec.thread.CName.name, len); @@ -212,9 +215,11 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str) struct list_head *pos; int res, type; - dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); + hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); sb = dir->i_sb; - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (res) + return res; hfs_cat_build_key(sb, fd.search_key, dir->i_ino, str); res = hfs_brec_find(&fd); @@ -278,10 +283,13 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, int entry_size, type; int err; - dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name, + hfs_dbg(CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", + cnid, src_dir->i_ino, src_name->name, dst_dir->i_ino, dst_name->name); sb = src_dir->i_sb; - hfs_find_init(HFS_SB(sb)->cat_tree, &src_fd); + err = hfs_find_init(HFS_SB(sb)->cat_tree, &src_fd); + if (err) + return err; dst_fd = src_fd; /* find the old dir entry and read the data */ diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 5f7f1ab..17c22a8 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -25,7 +25,9 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry, struct inode *inode = NULL; int res; - hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + if (res) + return ERR_PTR(res); hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name); res = hfs_brec_read(&fd, &rec, sizeof(rec)); if (res) { @@ -63,7 +65,9 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) if (filp->f_pos >= inode->i_size) return 0; - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (err) + return err; hfs_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); err = hfs_brec_find(&fd); if (err) @@ -84,12 +88,12 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (entry.type != HFS_CDR_THD) { - printk(KERN_ERR "hfs: bad catalog folder thread\n"); + pr_err("bad catalog folder thread\n"); err = -EIO; goto out; } //if (fd.entrylength < HFS_MIN_THREAD_SZ) { - // printk(KERN_ERR "hfs: truncated catalog thread\n"); + // pr_err("truncated catalog thread\n"); // err = -EIO; // goto out; //} @@ -108,7 +112,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) for (;;) { if (be32_to_cpu(fd.key->cat.ParID) != inode->i_ino) { - printk(KERN_ERR "hfs: walked past end of dir\n"); + pr_err("walked past end of dir\n"); err = -EIO; goto out; } @@ -123,7 +127,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) len = hfs_mac2asc(sb, strbuf, &fd.key->cat.CName); if (type == HFS_CDR_DIR) { if (fd.entrylength < sizeof(struct hfs_cat_dir)) { - printk(KERN_ERR "hfs: small dir entry\n"); + pr_err("small dir entry\n"); err = -EIO; goto out; } @@ -132,7 +136,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) break; } else if (type == HFS_CDR_FIL) { if (fd.entrylength < sizeof(struct hfs_cat_file)) { - printk(KERN_ERR "hfs: small file entry\n"); + pr_err("small file entry\n"); err = -EIO; goto out; } @@ -140,7 +144,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) be32_to_cpu(entry.file.FlNum), DT_REG)) break; } else { - printk(KERN_ERR "hfs: bad catalog entry type %d\n", type); + pr_err("bad catalog entry type %d\n", type); err = -EIO; goto out; } diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index a67955a..e33a0d3 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -107,7 +107,7 @@ static u16 hfs_ext_lastblock(struct hfs_extent *ext) return be16_to_cpu(ext->block) + be16_to_cpu(ext->count); } -static void __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) +static int __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) { int res; @@ -116,26 +116,31 @@ static void __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd res = hfs_brec_find(fd); if (HFS_I(inode)->flags & HFS_FLG_EXT_NEW) { if (res != -ENOENT) - return; + return res; hfs_brec_insert(fd, HFS_I(inode)->cached_extents, sizeof(hfs_extent_rec)); HFS_I(inode)->flags &= ~(HFS_FLG_EXT_DIRTY|HFS_FLG_EXT_NEW); } else { if (res) - return; + return res; hfs_bnode_write(fd->bnode, HFS_I(inode)->cached_extents, fd->entryoffset, fd->entrylength); HFS_I(inode)->flags &= ~HFS_FLG_EXT_DIRTY; } + return 0; } -void hfs_ext_write_extent(struct inode *inode) +int hfs_ext_write_extent(struct inode *inode) { struct hfs_find_data fd; + int res = 0; if (HFS_I(inode)->flags & HFS_FLG_EXT_DIRTY) { - hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); - __hfs_ext_write_extent(inode, &fd); + res = hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); + if (res) + return res; + res = __hfs_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } + return res; } static inline int __hfs_ext_read_extent(struct hfs_find_data *fd, struct hfs_extent *extent, @@ -161,8 +166,11 @@ static inline int __hfs_ext_cache_extent(struct hfs_find_data *fd, struct inode { int res; - if (HFS_I(inode)->flags & HFS_FLG_EXT_DIRTY) - __hfs_ext_write_extent(inode, fd); + if (HFS_I(inode)->flags & HFS_FLG_EXT_DIRTY) { + res = __hfs_ext_write_extent(inode, fd); + if (res) + return res; + } res = __hfs_ext_read_extent(fd, HFS_I(inode)->cached_extents, inode->i_ino, block, HFS_IS_RSRC(inode) ? HFS_FK_RSRC : HFS_FK_DATA); @@ -185,9 +193,11 @@ static int hfs_ext_read_extent(struct inode *inode, u16 block) block < HFS_I(inode)->cached_start + HFS_I(inode)->cached_blocks) return 0; - hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); - res = __hfs_ext_cache_extent(&fd, inode, block); - hfs_find_exit(&fd); + res = hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); + if (!res) { + res = __hfs_ext_cache_extent(&fd, inode, block); + hfs_find_exit(&fd); + } return res; } @@ -195,11 +205,12 @@ static void hfs_dump_extent(struct hfs_extent *extent) { int i; - dprint(DBG_EXTENT, " "); + hfs_dbg(EXTENT, " "); for (i = 0; i < 3; i++) - dprint(DBG_EXTENT, " %u:%u", be16_to_cpu(extent[i].block), - be16_to_cpu(extent[i].count)); - dprint(DBG_EXTENT, "\n"); + hfs_dbg_cont(EXTENT, " %u:%u", + be16_to_cpu(extent[i].block), + be16_to_cpu(extent[i].count)); + hfs_dbg_cont(EXTENT, "\n"); } static int hfs_add_extent(struct hfs_extent *extent, u16 offset, @@ -298,7 +309,9 @@ int hfs_free_fork(struct super_block *sb, struct hfs_cat_file *file, int type) if (total_blocks == blocks) return 0; - hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + if (res) + return res; do { res = __hfs_ext_read_extent(&fd, extent, cnid, total_blocks, type); if (res) @@ -392,10 +405,10 @@ int hfs_extend_file(struct inode *inode) goto out; } - dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); + hfs_dbg(EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); if (HFS_I(inode)->alloc_blocks == HFS_I(inode)->first_blocks) { if (!HFS_I(inode)->first_blocks) { - dprint(DBG_EXTENT, "first extents\n"); + hfs_dbg(EXTENT, "first extents\n"); /* no extents yet */ HFS_I(inode)->first_extents[0].block = cpu_to_be16(start); HFS_I(inode)->first_extents[0].count = cpu_to_be16(len); @@ -437,8 +450,10 @@ out: return res; insert_extent: - dprint(DBG_EXTENT, "insert new extent\n"); - hfs_ext_write_extent(inode); + hfs_dbg(EXTENT, "insert new extent\n"); + res = hfs_ext_write_extent(inode); + if (res) + goto out; memset(HFS_I(inode)->cached_extents, 0, sizeof(hfs_extent_rec)); HFS_I(inode)->cached_extents[0].block = cpu_to_be16(start); @@ -460,13 +475,13 @@ void hfs_file_truncate(struct inode *inode) u32 size; int res; - dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n", inode->i_ino, - (long long)HFS_I(inode)->phys_size, inode->i_size); + hfs_dbg(INODE, "truncate: %lu, %Lu -> %Lu\n", + inode->i_ino, (long long)HFS_I(inode)->phys_size, + inode->i_size); if (inode->i_size > HFS_I(inode)->phys_size) { struct address_space *mapping = inode->i_mapping; void *fsdata; struct page *page; - int res; /* XXX: Can use generic_cont_expand? */ size = inode->i_size - 1; @@ -488,7 +503,12 @@ void hfs_file_truncate(struct inode *inode) goto out; mutex_lock(&HFS_I(inode)->extents_lock); - hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + if (res) { + mutex_unlock(&HFS_I(inode)->extents_lock); + /* XXX: We lack error handling of hfs_file_truncate() */ + return; + } while (1) { if (alloc_cnt == HFS_I(inode)->first_blocks) { hfs_free_extents(sb, HFS_I(inode)->first_extents, diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 693df9f..a73b118 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -9,6 +9,12 @@ #ifndef _LINUX_HFS_FS_H #define _LINUX_HFS_FS_H +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/slab.h> #include <linux/types.h> #include <linux/mutex.h> @@ -34,8 +40,18 @@ //#define DBG_MASK (DBG_CAT_MOD|DBG_BNODE_REFS|DBG_INODE|DBG_EXTENT) #define DBG_MASK (0) -#define dprint(flg, fmt, args...) \ - if (flg & DBG_MASK) printk(fmt , ## args) +#define hfs_dbg(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ +} while (0) + +#define hfs_dbg_cont(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + pr_cont(fmt, ##__VA_ARGS__); \ +} while (0) + /* * struct hfs_inode_info @@ -174,7 +190,7 @@ extern const struct inode_operations hfs_dir_inode_operations; /* extent.c */ extern int hfs_ext_keycmp(const btree_key *, const btree_key *); extern int hfs_free_fork(struct super_block *, struct hfs_cat_file *, int); -extern void hfs_ext_write_extent(struct inode *); +extern int hfs_ext_write_extent(struct inode *); extern int hfs_extend_file(struct inode *); extern void hfs_file_truncate(struct inode *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 3031dfd..716e1aa 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -237,7 +237,7 @@ void hfs_delete_inode(struct inode *inode) { struct super_block *sb = inode->i_sb; - dprint(DBG_INODE, "delete_inode: %lu\n", inode->i_ino); + hfs_dbg(INODE, "delete_inode: %lu\n", inode->i_ino); if (S_ISDIR(inode->i_mode)) { HFS_SB(sb)->folder_count--; if (HFS_I(inode)->cat_key.ParID == cpu_to_be32(HFS_ROOT_CNID)) @@ -416,9 +416,12 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) struct inode *main_inode = inode; struct hfs_find_data fd; hfs_cat_rec rec; + int res; - dprint(DBG_INODE, "hfs_write_inode: %lu\n", inode->i_ino); - hfs_ext_write_extent(inode); + hfs_dbg(INODE, "hfs_write_inode: %lu\n", inode->i_ino); + res = hfs_ext_write_extent(inode); + if (res) + return res; if (inode->i_ino < HFS_FIRSTUSER_CNID) { switch (inode->i_ino) { @@ -515,7 +518,11 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, if (!inode) return ERR_PTR(-ENOMEM); - hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + if (res) { + iput(inode); + return ERR_PTR(res); + } fd.search_key->cat = HFS_I(dir)->cat_key; res = hfs_brec_read(&fd, &rec, sizeof(rec)); if (!res) { diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index b7ec224..aa3f0d6 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -48,7 +48,7 @@ static int hfs_get_last_session(struct super_block *sb, *start = (sector_t)te.cdte_addr.lba << 2; return 0; } - printk(KERN_ERR "hfs: invalid session number or type of track\n"); + pr_err("invalid session number or type of track\n"); return -EINVAL; } ms_info.addr_format = CDROM_LBA; @@ -101,7 +101,7 @@ int hfs_mdb_get(struct super_block *sb) HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz); if (!size || (size & (HFS_SECTOR_SIZE - 1))) { - printk(KERN_ERR "hfs: bad allocation block size %d\n", size); + pr_err("bad allocation block size %d\n", size); goto out_bh; } @@ -118,7 +118,7 @@ int hfs_mdb_get(struct super_block *sb) size >>= 1; brelse(bh); if (!sb_set_blocksize(sb, size)) { - printk(KERN_ERR "hfs: unable to set blocksize to %u\n", size); + pr_err("unable to set blocksize to %u\n", size); goto out; } @@ -162,8 +162,8 @@ int hfs_mdb_get(struct super_block *sb) } if (!HFS_SB(sb)->alt_mdb) { - printk(KERN_WARNING "hfs: unable to locate alternate MDB\n"); - printk(KERN_WARNING "hfs: continuing without an alternate MDB\n"); + pr_warn("unable to locate alternate MDB\n"); + pr_warn("continuing without an alternate MDB\n"); } HFS_SB(sb)->bitmap = (__be32 *)__get_free_pages(GFP_KERNEL, PAGE_SIZE < 8192 ? 1 : 0); @@ -178,7 +178,7 @@ int hfs_mdb_get(struct super_block *sb) while (size) { bh = sb_bread(sb, off >> sb->s_blocksize_bits); if (!bh) { - printk(KERN_ERR "hfs: unable to read volume bitmap\n"); + pr_err("unable to read volume bitmap\n"); goto out; } off2 = off & (sb->s_blocksize - 1); @@ -192,23 +192,22 @@ int hfs_mdb_get(struct super_block *sb) HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp); if (!HFS_SB(sb)->ext_tree) { - printk(KERN_ERR "hfs: unable to open extent tree\n"); + pr_err("unable to open extent tree\n"); goto out; } HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp); if (!HFS_SB(sb)->cat_tree) { - printk(KERN_ERR "hfs: unable to open catalog tree\n"); + pr_err("unable to open catalog tree\n"); goto out; } attrib = mdb->drAtrb; if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { - printk(KERN_WARNING "hfs: filesystem was not cleanly unmounted, " - "running fsck.hfs is recommended. mounting read-only.\n"); + pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) { - printk(KERN_WARNING "hfs: filesystem is marked locked, mounting read-only.\n"); + pr_warn("filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } if (!(sb->s_flags & MS_RDONLY)) { @@ -312,7 +311,7 @@ void hfs_mdb_commit(struct super_block *sb) while (size) { bh = sb_bread(sb, block); if (!bh) { - printk(KERN_ERR "hfs: unable to read volume bitmap\n"); + pr_err("unable to read volume bitmap\n"); break; } len = min((int)sb->s_blocksize - off, size); diff --git a/fs/hfs/super.c b/fs/hfs/super.c index bbaaa8a..2d2039e 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -117,12 +117,11 @@ static int hfs_remount(struct super_block *sb, int *flags, char *data) return 0; if (!(*flags & MS_RDONLY)) { if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { - printk(KERN_WARNING "hfs: filesystem was not cleanly unmounted, " - "running fsck.hfs is recommended. leaving read-only.\n"); + pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } else if (HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_SLOCK)) { - printk(KERN_WARNING "hfs: filesystem is marked locked, leaving read-only.\n"); + pr_warn("filesystem is marked locked, leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } @@ -253,29 +252,29 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) switch (token) { case opt_uid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: uid requires an argument\n"); + pr_err("uid requires an argument\n"); return 0; } hsb->s_uid = make_kuid(current_user_ns(), (uid_t)tmp); if (!uid_valid(hsb->s_uid)) { - printk(KERN_ERR "hfs: invalid uid %d\n", tmp); + pr_err("invalid uid %d\n", tmp); return 0; } break; case opt_gid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: gid requires an argument\n"); + pr_err("gid requires an argument\n"); return 0; } hsb->s_gid = make_kgid(current_user_ns(), (gid_t)tmp); if (!gid_valid(hsb->s_gid)) { - printk(KERN_ERR "hfs: invalid gid %d\n", tmp); + pr_err("invalid gid %d\n", tmp); return 0; } break; case opt_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: umask requires a value\n"); + pr_err("umask requires a value\n"); return 0; } hsb->s_file_umask = (umode_t)tmp; @@ -283,39 +282,39 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) break; case opt_file_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: file_umask requires a value\n"); + pr_err("file_umask requires a value\n"); return 0; } hsb->s_file_umask = (umode_t)tmp; break; case opt_dir_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: dir_umask requires a value\n"); + pr_err("dir_umask requires a value\n"); return 0; } hsb->s_dir_umask = (umode_t)tmp; break; case opt_part: if (match_int(&args[0], &hsb->part)) { - printk(KERN_ERR "hfs: part requires an argument\n"); + pr_err("part requires an argument\n"); return 0; } break; case opt_session: if (match_int(&args[0], &hsb->session)) { - printk(KERN_ERR "hfs: session requires an argument\n"); + pr_err("session requires an argument\n"); return 0; } break; case opt_type: if (match_fourchar(&args[0], &hsb->s_type)) { - printk(KERN_ERR "hfs: type requires a 4 character value\n"); + pr_err("type requires a 4 character value\n"); return 0; } break; case opt_creator: if (match_fourchar(&args[0], &hsb->s_creator)) { - printk(KERN_ERR "hfs: creator requires a 4 character value\n"); + pr_err("creator requires a 4 character value\n"); return 0; } break; @@ -324,14 +323,14 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) break; case opt_codepage: if (hsb->nls_disk) { - printk(KERN_ERR "hfs: unable to change codepage\n"); + pr_err("unable to change codepage\n"); return 0; } p = match_strdup(&args[0]); if (p) hsb->nls_disk = load_nls(p); if (!hsb->nls_disk) { - printk(KERN_ERR "hfs: unable to load codepage \"%s\"\n", p); + pr_err("unable to load codepage \"%s\"\n", p); kfree(p); return 0; } @@ -339,14 +338,14 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) break; case opt_iocharset: if (hsb->nls_io) { - printk(KERN_ERR "hfs: unable to change iocharset\n"); + pr_err("unable to change iocharset\n"); return 0; } p = match_strdup(&args[0]); if (p) hsb->nls_io = load_nls(p); if (!hsb->nls_io) { - printk(KERN_ERR "hfs: unable to load iocharset \"%s\"\n", p); + pr_err("unable to load iocharset \"%s\"\n", p); kfree(p); return 0; } @@ -360,7 +359,7 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) if (hsb->nls_disk && !hsb->nls_io) { hsb->nls_io = load_nls_default(); if (!hsb->nls_io) { - printk(KERN_ERR "hfs: unable to load default iocharset\n"); + pr_err("unable to load default iocharset\n"); return 0; } } @@ -400,7 +399,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) res = -EINVAL; if (!parse_options((char *)data, sbi)) { - printk(KERN_ERR "hfs: unable to parse mount options.\n"); + pr_err("unable to parse mount options\n"); goto bail; } @@ -411,14 +410,16 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) res = hfs_mdb_get(sb); if (res) { if (!silent) - printk(KERN_WARNING "hfs: can't find a HFS filesystem on dev %s.\n", + pr_warn("can't find a HFS filesystem on dev %s\n", hfs_mdb_name(sb)); res = -EINVAL; goto bail; } /* try to get the root inode */ - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (res) + goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { @@ -447,7 +448,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) return 0; bail_no_root: - printk(KERN_ERR "hfs: get root inode failed.\n"); + pr_err("get root inode failed\n"); bail: hfs_mdb_put(sb); return res; diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c index 8d691f1..0f47890 100644 --- a/fs/hfsplus/attributes.c +++ b/fs/hfsplus/attributes.c @@ -56,7 +56,7 @@ int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key, if (name) { len = strlen(name); if (len > HFSPLUS_ATTR_MAX_STRLEN) { - printk(KERN_ERR "hfs: invalid xattr name's length\n"); + pr_err("invalid xattr name's length\n"); return -EINVAL; } hfsplus_asc2uni(sb, @@ -166,10 +166,10 @@ int hfsplus_find_attr(struct super_block *sb, u32 cnid, { int err = 0; - dprint(DBG_ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid); + hfs_dbg(ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid); if (!HFSPLUS_SB(sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -228,11 +228,11 @@ int hfsplus_create_attr(struct inode *inode, int entry_size; int err; - dprint(DBG_ATTR_MOD, "create_attr: %s,%ld\n", + hfs_dbg(ATTR_MOD, "create_attr: %s,%ld\n", name ? name : NULL, inode->i_ino); if (!HFSPLUS_SB(sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -307,10 +307,10 @@ static int __hfsplus_delete_attr(struct inode *inode, u32 cnid, break; case HFSPLUS_ATTR_FORK_DATA: case HFSPLUS_ATTR_EXTENTS: - printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + pr_err("only inline data xattr are supported\n"); return -EOPNOTSUPP; default: - printk(KERN_ERR "hfs: invalid extended attribute record\n"); + pr_err("invalid extended attribute record\n"); return -ENOENT; } @@ -328,11 +328,11 @@ int hfsplus_delete_attr(struct inode *inode, const char *name) struct super_block *sb = inode->i_sb; struct hfs_find_data fd; - dprint(DBG_ATTR_MOD, "delete_attr: %s,%ld\n", + hfs_dbg(ATTR_MOD, "delete_attr: %s,%ld\n", name ? name : NULL, inode->i_ino); if (!HFSPLUS_SB(sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -346,7 +346,7 @@ int hfsplus_delete_attr(struct inode *inode, const char *name) if (err) goto out; } else { - printk(KERN_ERR "hfs: invalid extended attribute name\n"); + pr_err("invalid extended attribute name\n"); err = -EINVAL; goto out; } @@ -369,10 +369,10 @@ int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid) int err = 0; struct hfs_find_data fd; - dprint(DBG_ATTR_MOD, "delete_all_attrs: %d\n", cnid); + hfs_dbg(ATTR_MOD, "delete_all_attrs: %d\n", cnid); if (!HFSPLUS_SB(dir->i_sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -384,7 +384,7 @@ int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid) err = hfsplus_find_attr(dir->i_sb, cnid, NULL, &fd); if (err) { if (err != -ENOENT) - printk(KERN_ERR "hfs: xattr search failed.\n"); + pr_err("xattr search failed\n"); goto end_delete_all; } diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c index d73c98d..c1422d9 100644 --- a/fs/hfsplus/bfind.c +++ b/fs/hfsplus/bfind.c @@ -22,7 +22,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) return -ENOMEM; fd->search_key = ptr; fd->key = ptr + tree->max_key_len + 2; - dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", + hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); switch (tree->cnid) { case HFSPLUS_CAT_CNID: @@ -44,7 +44,7 @@ void hfs_find_exit(struct hfs_find_data *fd) { hfs_bnode_put(fd->bnode); kfree(fd->search_key); - dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", + hfs_dbg(BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0)); mutex_unlock(&fd->tree->tree_lock); fd->tree = NULL; @@ -56,7 +56,8 @@ int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, int *end, int *cur_rec) { - __be32 cur_cnid, search_cnid; + __be32 cur_cnid; + __be32 search_cnid; if (bnode->tree->cnid == HFSPLUS_EXT_CNID) { cur_cnid = fd->key->ext.cnid; @@ -67,8 +68,11 @@ int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) { cur_cnid = fd->key->attr.cnid; search_cnid = fd->search_key->attr.cnid; - } else + } else { + cur_cnid = 0; /* used-uninitialized warning */ + search_cnid = 0; BUG(); + } if (cur_cnid == search_cnid) { (*end) = (*cur_rec); @@ -204,7 +208,7 @@ int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare) return res; invalid: - printk(KERN_ERR "hfs: inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", + pr_err("inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", height, bnode->height, bnode->type, nidx, parent); res = -EIO; release: diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c index 6feefc0..d2954451 100644 --- a/fs/hfsplus/bitmap.c +++ b/fs/hfsplus/bitmap.c @@ -30,7 +30,7 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, if (!len) return size; - dprint(DBG_BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len); + hfs_dbg(BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len); mutex_lock(&sbi->alloc_mutex); mapping = sbi->alloc_file->i_mapping; page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL); @@ -89,14 +89,14 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, else end = pptr + ((size + 31) & (PAGE_CACHE_BITS - 1)) / 32; } - dprint(DBG_BITMAP, "bitmap full\n"); + hfs_dbg(BITMAP, "bitmap full\n"); start = size; goto out; found: start = offset + (curr - pptr) * 32 + i; if (start >= size) { - dprint(DBG_BITMAP, "bitmap full\n"); + hfs_dbg(BITMAP, "bitmap full\n"); goto out; } /* do any partial u32 at the start */ @@ -154,7 +154,7 @@ done: *max = offset + (curr - pptr) * 32 + i - start; sbi->free_blocks -= *max; hfsplus_mark_mdb_dirty(sb); - dprint(DBG_BITMAP, "-> %u,%u\n", start, *max); + hfs_dbg(BITMAP, "-> %u,%u\n", start, *max); out: mutex_unlock(&sbi->alloc_mutex); return start; @@ -173,7 +173,7 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count) if (!count) return 0; - dprint(DBG_BITMAP, "block_free: %u,%u\n", offset, count); + hfs_dbg(BITMAP, "block_free: %u,%u\n", offset, count); /* are all of the bits in range? */ if ((offset + count) > sbi->total_blocks) return -ENOENT; @@ -238,8 +238,7 @@ out: return 0; kaboom: - printk(KERN_CRIT "hfsplus: unable to mark blocks free: error %ld\n", - PTR_ERR(page)); + pr_crit("unable to mark blocks free: error %ld\n", PTR_ERR(page)); mutex_unlock(&sbi->alloc_mutex); return -EIO; diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index f31ac6f..11c8602 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -130,7 +130,7 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, struct page **src_page, **dst_page; int l; - dprint(DBG_BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); if (!len) return; tree = src_node->tree; @@ -188,7 +188,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) struct page **src_page, **dst_page; int l; - dprint(DBG_BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += node->page_offset; @@ -302,16 +302,16 @@ void hfs_bnode_dump(struct hfs_bnode *node) __be32 cnid; int i, off, key_off; - dprint(DBG_BNODE_MOD, "bnode: %d\n", node->this); + hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this); hfs_bnode_read(node, &desc, 0, sizeof(desc)); - dprint(DBG_BNODE_MOD, "%d, %d, %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n", be32_to_cpu(desc.next), be32_to_cpu(desc.prev), desc.type, desc.height, be16_to_cpu(desc.num_recs)); off = node->tree->node_size - 2; for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) { key_off = hfs_bnode_read_u16(node, off); - dprint(DBG_BNODE_MOD, " %d", key_off); + hfs_dbg(BNODE_MOD, " %d", key_off); if (i && node->type == HFS_NODE_INDEX) { int tmp; @@ -320,17 +320,17 @@ void hfs_bnode_dump(struct hfs_bnode *node) tmp = hfs_bnode_read_u16(node, key_off) + 2; else tmp = node->tree->max_key_len + 2; - dprint(DBG_BNODE_MOD, " (%d", tmp); + hfs_dbg_cont(BNODE_MOD, " (%d", tmp); hfs_bnode_read(node, &cnid, key_off + tmp, 4); - dprint(DBG_BNODE_MOD, ",%d)", be32_to_cpu(cnid)); + hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid)); } else if (i && node->type == HFS_NODE_LEAF) { int tmp; tmp = hfs_bnode_read_u16(node, key_off); - dprint(DBG_BNODE_MOD, " (%d)", tmp); + hfs_dbg_cont(BNODE_MOD, " (%d)", tmp); } } - dprint(DBG_BNODE_MOD, "\n"); + hfs_dbg_cont(BNODE_MOD, "\n"); } void hfs_bnode_unlink(struct hfs_bnode *node) @@ -366,7 +366,7 @@ void hfs_bnode_unlink(struct hfs_bnode *node) /* move down? */ if (!node->prev && !node->next) - dprint(DBG_BNODE_MOD, "hfs_btree_del_level\n"); + hfs_dbg(BNODE_MOD, "hfs_btree_del_level\n"); if (!node->parent) { tree->root = 0; tree->depth = 0; @@ -386,7 +386,7 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid) struct hfs_bnode *node; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node " + pr_err("request for non-existent node " "%d in B*Tree\n", cnid); return NULL; @@ -409,7 +409,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) loff_t off; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node " + pr_err("request for non-existent node " "%d in B*Tree\n", cnid); return NULL; @@ -425,8 +425,8 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); atomic_set(&node->refcnt, 1); - dprint(DBG_BNODE_REFS, "new_node(%d:%d): 1\n", - node->tree->cnid, node->this); + hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n", + node->tree->cnid, node->this); init_waitqueue_head(&node->lock_wq); spin_lock(&tree->hash_lock); node2 = hfs_bnode_findhash(tree, cnid); @@ -470,7 +470,7 @@ void hfs_bnode_unhash(struct hfs_bnode *node) { struct hfs_bnode **p; - dprint(DBG_BNODE_REFS, "remove_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)]; *p && *p != node; p = &(*p)->next_hash) @@ -588,7 +588,7 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) node = hfs_bnode_findhash(tree, num); spin_unlock(&tree->hash_lock); if (node) { - printk(KERN_CRIT "new node %u already hashed?\n", num); + pr_crit("new node %u already hashed?\n", num); WARN_ON(1); return node; } @@ -620,7 +620,7 @@ void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); - dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); } @@ -633,7 +633,7 @@ void hfs_bnode_put(struct hfs_bnode *node) struct hfs_btree *tree = node->tree; int i; - dprint(DBG_BNODE_REFS, "put_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); BUG_ON(!atomic_read(&node->refcnt)); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 298d4e4..6e560d5 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -45,13 +45,13 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) if (!recoff) return 0; if (recoff > node->tree->node_size - 2) { - printk(KERN_ERR "hfs: recoff %d too large\n", recoff); + pr_err("recoff %d too large\n", recoff); return 0; } retval = hfs_bnode_read_u16(node, recoff) + 2; if (retval > node->tree->max_key_len + 2) { - printk(KERN_ERR "hfs: keylen %d too large\n", + pr_err("keylen %d too large\n", retval); retval = 0; } @@ -90,7 +90,7 @@ again: end_rec_off = tree->node_size - (node->num_recs + 1) * 2; end_off = hfs_bnode_read_u16(node, end_rec_off); end_rec_off -= 2; - dprint(DBG_BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", rec, size, end_off, end_rec_off); if (size > end_rec_off - end_off) { if (new_node) @@ -191,7 +191,7 @@ again: mark_inode_dirty(tree->inode); } hfs_bnode_dump(node); - dprint(DBG_BNODE_MOD, "remove_rec: %d, %d\n", + hfs_dbg(BNODE_MOD, "remove_rec: %d, %d\n", fd->record, fd->keylength + fd->entrylength); if (!--node->num_recs) { hfs_bnode_unlink(node); @@ -244,7 +244,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) if (IS_ERR(new_node)) return new_node; hfs_bnode_get(node); - dprint(DBG_BNODE_MOD, "split_nodes: %d - %d - %d\n", + hfs_dbg(BNODE_MOD, "split_nodes: %d - %d - %d\n", node->this, new_node->this, node->next); new_node->next = node->next; new_node->prev = node->this; @@ -379,7 +379,7 @@ again: newkeylen = hfs_bnode_read_u16(node, 14) + 2; else fd->keylength = newkeylen = tree->max_key_len + 2; - dprint(DBG_BNODE_MOD, "update_rec: %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "update_rec: %d, %d, %d\n", rec, fd->keylength, newkeylen); rec_off = tree->node_size - (rec + 2) * 2; @@ -391,7 +391,7 @@ again: end_off = hfs_bnode_read_u16(parent, end_rec_off); if (end_rec_off - end_off < diff) { - dprint(DBG_BNODE_MOD, "hfs: splitting index node.\n"); + hfs_dbg(BNODE_MOD, "splitting index node\n"); fd->bnode = parent; new_node = hfs_bnode_split(fd); if (IS_ERR(new_node)) diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index efb689c..0c6540c 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -40,8 +40,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) tree->inode = inode; if (!HFSPLUS_I(tree->inode)->first_blocks) { - printk(KERN_ERR - "hfs: invalid btree extent records (0 size).\n"); + pr_err("invalid btree extent records (0 size)\n"); goto free_inode; } @@ -68,12 +67,12 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) switch (id) { case HFSPLUS_EXT_CNID: if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) { - printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", + pr_err("invalid extent max_key_len %d\n", tree->max_key_len); goto fail_page; } if (tree->attributes & HFS_TREE_VARIDXKEYS) { - printk(KERN_ERR "hfs: invalid extent btree flag\n"); + pr_err("invalid extent btree flag\n"); goto fail_page; } @@ -81,12 +80,12 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) break; case HFSPLUS_CAT_CNID: if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) { - printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", + pr_err("invalid catalog max_key_len %d\n", tree->max_key_len); goto fail_page; } if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) { - printk(KERN_ERR "hfs: invalid catalog btree flag\n"); + pr_err("invalid catalog btree flag\n"); goto fail_page; } @@ -100,19 +99,19 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) break; case HFSPLUS_ATTR_CNID: if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) { - printk(KERN_ERR "hfs: invalid attributes max_key_len %d\n", + pr_err("invalid attributes max_key_len %d\n", tree->max_key_len); goto fail_page; } tree->keycmp = hfsplus_attr_bin_cmp_key; break; default: - printk(KERN_ERR "hfs: unknown B*Tree requested\n"); + pr_err("unknown B*Tree requested\n"); goto fail_page; } if (!(tree->attributes & HFS_TREE_BIGKEYS)) { - printk(KERN_ERR "hfs: invalid btree flag\n"); + pr_err("invalid btree flag\n"); goto fail_page; } @@ -155,7 +154,7 @@ void hfs_btree_close(struct hfs_btree *tree) while ((node = tree->node_hash[i])) { tree->node_hash[i] = node->next_hash; if (atomic_read(&node->refcnt)) - printk(KERN_CRIT "hfs: node %d:%d " + pr_crit("node %d:%d " "still has %d user(s)!\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); @@ -303,7 +302,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) kunmap(*pagep); nidx = node->next; if (!nidx) { - dprint(DBG_BNODE_MOD, "hfs: create new bmap node.\n"); + hfs_dbg(BNODE_MOD, "create new bmap node\n"); next_node = hfs_bmap_new_bmap(node, idx); } else next_node = hfs_bnode_find(tree, nidx); @@ -329,7 +328,7 @@ void hfs_bmap_free(struct hfs_bnode *node) u32 nidx; u8 *data, byte, m; - dprint(DBG_BNODE_MOD, "btree_free_node: %u\n", node->this); + hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this); BUG_ON(!node->this); tree = node->tree; nidx = node->this; @@ -345,7 +344,7 @@ void hfs_bmap_free(struct hfs_bnode *node) hfs_bnode_put(node); if (!i) { /* panic */; - printk(KERN_CRIT "hfs: unable to free bnode %u. " + pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); return; @@ -355,7 +354,7 @@ void hfs_bmap_free(struct hfs_bnode *node) return; if (node->type != HFS_NODE_MAP) { /* panic */; - printk(KERN_CRIT "hfs: invalid bmap found! " + pr_crit("invalid bmap found! " "(%u,%d)\n", node->this, node->type); hfs_bnode_put(node); @@ -370,7 +369,7 @@ void hfs_bmap_free(struct hfs_bnode *node) m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { - printk(KERN_CRIT "hfs: trying to free free bnode " + pr_crit("trying to free free bnode " "%u(%d)\n", node->this, node->type); kunmap(page); diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 840d71e..968ce41 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -188,12 +188,12 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, type = be16_to_cpu(tmp.type); if (type != HFSPLUS_FOLDER_THREAD && type != HFSPLUS_FILE_THREAD) { - printk(KERN_ERR "hfs: found bad thread record in catalog\n"); + pr_err("found bad thread record in catalog\n"); return -EIO; } if (be16_to_cpu(tmp.thread.nodeName.length) > 255) { - printk(KERN_ERR "hfs: catalog name length corrupted\n"); + pr_err("catalog name length corrupted\n"); return -EIO; } @@ -212,7 +212,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, int entry_size; int err; - dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", + hfs_dbg(CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) @@ -271,8 +271,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) int err, off; u16 type; - dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", - str ? str->name : NULL, cnid); + hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) return err; @@ -361,7 +360,7 @@ int hfsplus_rename_cat(u32 cnid, int entry_size, type; int err; - dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", + hfs_dbg(CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name, dst_dir->i_ino, dst_name->name); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 031c24e..a37ac93 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -103,7 +103,7 @@ again: } else if (!dentry->d_fsdata) dentry->d_fsdata = (void *)(unsigned long)cnid; } else { - printk(KERN_ERR "hfs: invalid catalog entry type in lookup\n"); + pr_err("invalid catalog entry type in lookup\n"); err = -EIO; goto fail; } @@ -159,12 +159,12 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (be16_to_cpu(entry.type) != HFSPLUS_FOLDER_THREAD) { - printk(KERN_ERR "hfs: bad catalog folder thread\n"); + pr_err("bad catalog folder thread\n"); err = -EIO; goto out; } if (fd.entrylength < HFSPLUS_MIN_THREAD_SZ) { - printk(KERN_ERR "hfs: truncated catalog thread\n"); + pr_err("truncated catalog thread\n"); err = -EIO; goto out; } @@ -183,7 +183,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) for (;;) { if (be32_to_cpu(fd.key->cat.parent) != inode->i_ino) { - printk(KERN_ERR "hfs: walked past end of dir\n"); + pr_err("walked past end of dir\n"); err = -EIO; goto out; } @@ -203,7 +203,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) if (type == HFSPLUS_FOLDER) { if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) { - printk(KERN_ERR "hfs: small dir entry\n"); + pr_err("small dir entry\n"); err = -EIO; goto out; } @@ -216,7 +216,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) break; } else if (type == HFSPLUS_FILE) { if (fd.entrylength < sizeof(struct hfsplus_cat_file)) { - printk(KERN_ERR "hfs: small file entry\n"); + pr_err("small file entry\n"); err = -EIO; goto out; } @@ -224,7 +224,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) be32_to_cpu(entry.file.id), DT_REG)) break; } else { - printk(KERN_ERR "hfs: bad catalog entry type\n"); + pr_err("bad catalog entry type\n"); err = -EIO; goto out; } diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index a94f0f7..fbb212f 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -83,7 +83,7 @@ static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext) return be32_to_cpu(ext->start_block) + be32_to_cpu(ext->block_count); } -static void __hfsplus_ext_write_extent(struct inode *inode, +static int __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); @@ -98,13 +98,13 @@ static void __hfsplus_ext_write_extent(struct inode *inode, res = hfs_brec_find(fd, hfs_find_rec_by_key); if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) - return; + return res; hfs_brec_insert(fd, hip->cached_extents, sizeof(hfsplus_extent_rec)); hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } else { if (res) - return; + return res; hfs_bnode_write(fd->bnode, hip->cached_extents, fd->entryoffset, fd->entrylength); hip->extent_state &= ~HFSPLUS_EXT_DIRTY; @@ -117,11 +117,13 @@ static void __hfsplus_ext_write_extent(struct inode *inode, * to explicily mark the inode dirty, too. */ set_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags); + + return 0; } static int hfsplus_ext_write_extent_locked(struct inode *inode) { - int res; + int res = 0; if (HFSPLUS_I(inode)->extent_state & HFSPLUS_EXT_DIRTY) { struct hfs_find_data fd; @@ -129,10 +131,10 @@ static int hfsplus_ext_write_extent_locked(struct inode *inode) res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); if (res) return res; - __hfsplus_ext_write_extent(inode, &fd); + res = __hfsplus_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } - return 0; + return res; } int hfsplus_ext_write_extent(struct inode *inode) @@ -175,8 +177,11 @@ static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, WARN_ON(!mutex_is_locked(&hip->extents_lock)); - if (hip->extent_state & HFSPLUS_EXT_DIRTY) - __hfsplus_ext_write_extent(inode, fd); + if (hip->extent_state & HFSPLUS_EXT_DIRTY) { + res = __hfsplus_ext_write_extent(inode, fd); + if (res) + return res; + } res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino, block, HFSPLUS_IS_RSRC(inode) ? @@ -265,7 +270,7 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, mutex_unlock(&hip->extents_lock); done: - dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", + hfs_dbg(EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock); mask = (1 << sbi->fs_shift) - 1; @@ -288,11 +293,12 @@ static void hfsplus_dump_extent(struct hfsplus_extent *extent) { int i; - dprint(DBG_EXTENT, " "); + hfs_dbg(EXTENT, " "); for (i = 0; i < 8; i++) - dprint(DBG_EXTENT, " %u:%u", be32_to_cpu(extent[i].start_block), - be32_to_cpu(extent[i].block_count)); - dprint(DBG_EXTENT, "\n"); + hfs_dbg_cont(EXTENT, " %u:%u", + be32_to_cpu(extent[i].start_block), + be32_to_cpu(extent[i].block_count)); + hfs_dbg_cont(EXTENT, "\n"); } static int hfsplus_add_extent(struct hfsplus_extent *extent, u32 offset, @@ -348,8 +354,8 @@ found: if (count <= block_nr) { err = hfsplus_block_free(sb, start, count); if (err) { - printk(KERN_ERR "hfs: can't free extent\n"); - dprint(DBG_EXTENT, " start: %u count: %u\n", + pr_err("can't free extent\n"); + hfs_dbg(EXTENT, " start: %u count: %u\n", start, count); } extent->block_count = 0; @@ -359,8 +365,8 @@ found: count -= block_nr; err = hfsplus_block_free(sb, start + count, block_nr); if (err) { - printk(KERN_ERR "hfs: can't free extent\n"); - dprint(DBG_EXTENT, " start: %u count: %u\n", + pr_err("can't free extent\n"); + hfs_dbg(EXTENT, " start: %u count: %u\n", start, count); } extent->block_count = cpu_to_be32(count); @@ -432,7 +438,7 @@ int hfsplus_file_extend(struct inode *inode) if (sbi->alloc_file->i_size * 8 < sbi->total_blocks - sbi->free_blocks + 8) { /* extend alloc file */ - printk(KERN_ERR "hfs: extend alloc file! " + pr_err("extend alloc file! " "(%llu,%u,%u)\n", sbi->alloc_file->i_size * 8, sbi->total_blocks, sbi->free_blocks); @@ -459,11 +465,11 @@ int hfsplus_file_extend(struct inode *inode) } } - dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); + hfs_dbg(EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); if (hip->alloc_blocks <= hip->first_blocks) { if (!hip->first_blocks) { - dprint(DBG_EXTENT, "first extents\n"); + hfs_dbg(EXTENT, "first extents\n"); /* no extents yet */ hip->first_extents[0].start_block = cpu_to_be32(start); hip->first_extents[0].block_count = cpu_to_be32(len); @@ -500,7 +506,7 @@ out: return res; insert_extent: - dprint(DBG_EXTENT, "insert new extent\n"); + hfs_dbg(EXTENT, "insert new extent\n"); res = hfsplus_ext_write_extent_locked(inode); if (res) goto out; @@ -525,15 +531,14 @@ void hfsplus_file_truncate(struct inode *inode) u32 alloc_cnt, blk_cnt, start; int res; - dprint(DBG_INODE, "truncate: %lu, %llu -> %llu\n", - inode->i_ino, (long long)hip->phys_size, - inode->i_size); + hfs_dbg(INODE, "truncate: %lu, %llu -> %llu\n", + inode->i_ino, (long long)hip->phys_size, inode->i_size); if (inode->i_size > hip->phys_size) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata; - u32 size = inode->i_size; + loff_t size = inode->i_size; res = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_UNINTERRUPTIBLE, diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 05b11f3..60b0a33 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -10,6 +10,12 @@ #ifndef _LINUX_HFSPLUS_FS_H #define _LINUX_HFSPLUS_FS_H +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/fs.h> #include <linux/mutex.h> #include <linux/buffer_head.h> @@ -32,9 +38,17 @@ #endif #define DBG_MASK (0) -#define dprint(flg, fmt, args...) \ - if (flg & DBG_MASK) \ - printk(fmt , ## args) +#define hfs_dbg(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ +} while (0) + +#define hfs_dbg_cont(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + pr_cont(fmt, ##__VA_ARGS__); \ +} while (0) /* Runtime config options */ #define HFSPLUS_DEF_CR_TYPE 0x3F3F3F3F /* '????' */ diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 160ccc9..7faaa96 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -357,7 +357,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, if (!error) error = error2; } else { - printk(KERN_ERR "hfs: sync non-existent attributes tree\n"); + pr_err("sync non-existent attributes tree\n"); } } @@ -573,7 +573,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date); HFSPLUS_I(inode)->create_date = file->create_date; } else { - printk(KERN_ERR "hfs: bad catalog entry used to create inode\n"); + pr_err("bad catalog entry used to create inode\n"); res = -EIO; } return res; diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index ed257c6..968eab5 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -113,67 +113,67 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) switch (token) { case opt_creator: if (match_fourchar(&args[0], &sbi->creator)) { - printk(KERN_ERR "hfs: creator requires a 4 character value\n"); + pr_err("creator requires a 4 character value\n"); return 0; } break; case opt_type: if (match_fourchar(&args[0], &sbi->type)) { - printk(KERN_ERR "hfs: type requires a 4 character value\n"); + pr_err("type requires a 4 character value\n"); return 0; } break; case opt_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: umask requires a value\n"); + pr_err("umask requires a value\n"); return 0; } sbi->umask = (umode_t)tmp; break; case opt_uid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: uid requires an argument\n"); + pr_err("uid requires an argument\n"); return 0; } sbi->uid = make_kuid(current_user_ns(), (uid_t)tmp); if (!uid_valid(sbi->uid)) { - printk(KERN_ERR "hfs: invalid uid specified\n"); + pr_err("invalid uid specified\n"); return 0; } break; case opt_gid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: gid requires an argument\n"); + pr_err("gid requires an argument\n"); return 0; } sbi->gid = make_kgid(current_user_ns(), (gid_t)tmp); if (!gid_valid(sbi->gid)) { - printk(KERN_ERR "hfs: invalid gid specified\n"); + pr_err("invalid gid specified\n"); return 0; } break; case opt_part: if (match_int(&args[0], &sbi->part)) { - printk(KERN_ERR "hfs: part requires an argument\n"); + pr_err("part requires an argument\n"); return 0; } break; case opt_session: if (match_int(&args[0], &sbi->session)) { - printk(KERN_ERR "hfs: session requires an argument\n"); + pr_err("session requires an argument\n"); return 0; } break; case opt_nls: if (sbi->nls) { - printk(KERN_ERR "hfs: unable to change nls mapping\n"); + pr_err("unable to change nls mapping\n"); return 0; } p = match_strdup(&args[0]); if (p) sbi->nls = load_nls(p); if (!sbi->nls) { - printk(KERN_ERR "hfs: unable to load " + pr_err("unable to load " "nls mapping \"%s\"\n", p); kfree(p); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 7b87284..4c4d142 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -132,7 +132,7 @@ static int hfsplus_system_write_inode(struct inode *inode) if (tree) { int err = hfs_btree_write(tree); if (err) { - printk(KERN_ERR "hfs: b-tree write err: %d, ino %lu\n", + pr_err("b-tree write err: %d, ino %lu\n", err, inode->i_ino); return err; } @@ -145,7 +145,7 @@ static int hfsplus_write_inode(struct inode *inode, { int err; - dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino); + hfs_dbg(INODE, "hfsplus_write_inode: %lu\n", inode->i_ino); err = hfsplus_ext_write_extent(inode); if (err) @@ -160,7 +160,7 @@ static int hfsplus_write_inode(struct inode *inode, static void hfsplus_evict_inode(struct inode *inode) { - dprint(DBG_INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); + hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); truncate_inode_pages(&inode->i_data, 0); clear_inode(inode); if (HFSPLUS_IS_RSRC(inode)) { @@ -179,7 +179,7 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait) if (!wait) return 0; - dprint(DBG_SUPER, "hfsplus_sync_fs\n"); + hfs_dbg(SUPER, "hfsplus_sync_fs\n"); /* * Explicitly write out the special metadata inodes. @@ -251,7 +251,7 @@ static void delayed_sync_fs(struct work_struct *work) err = hfsplus_sync_fs(sbi->alloc_file->i_sb, 1); if (err) - printk(KERN_ERR "hfs: delayed sync fs err %d\n", err); + pr_err("delayed sync fs err %d\n", err); } void hfsplus_mark_mdb_dirty(struct super_block *sb) @@ -275,7 +275,7 @@ static void hfsplus_put_super(struct super_block *sb) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); - dprint(DBG_SUPER, "hfsplus_put_super\n"); + hfs_dbg(SUPER, "hfsplus_put_super\n"); cancel_delayed_work_sync(&sbi->sync_work); @@ -333,25 +333,19 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { - printk(KERN_WARNING "hfs: filesystem was " - "not cleanly unmounted, " - "running fsck.hfsplus is recommended. " - "leaving read-only.\n"); + pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } else if (force) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { - printk(KERN_WARNING "hfs: filesystem is marked locked, " - "leaving read-only.\n"); + pr_warn("filesystem is marked locked, leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) { - printk(KERN_WARNING "hfs: filesystem is " - "marked journaled, " - "leaving read-only.\n"); + pr_warn("filesystem is marked journaled, leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } @@ -397,7 +391,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) err = -EINVAL; if (!hfsplus_parse_options(data, sbi)) { - printk(KERN_ERR "hfs: unable to parse mount options\n"); + pr_err("unable to parse mount options\n"); goto out_unload_nls; } @@ -405,14 +399,14 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) nls = sbi->nls; sbi->nls = load_nls("utf8"); if (!sbi->nls) { - printk(KERN_ERR "hfs: unable to load nls for utf8\n"); + pr_err("unable to load nls for utf8\n"); goto out_unload_nls; } /* Grab the volume header */ if (hfsplus_read_wrapper(sb)) { if (!silent) - printk(KERN_WARNING "hfs: unable to find HFS+ superblock\n"); + pr_warn("unable to find HFS+ superblock\n"); goto out_unload_nls; } vhdr = sbi->s_vhdr; @@ -421,7 +415,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = HFSPLUS_VOLHEAD_SIG; if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION || be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) { - printk(KERN_ERR "hfs: wrong filesystem version\n"); + pr_err("wrong filesystem version\n"); goto out_free_vhdr; } sbi->total_blocks = be32_to_cpu(vhdr->total_blocks); @@ -445,7 +439,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { - printk(KERN_ERR "hfs: filesystem size too large.\n"); + pr_err("filesystem size too large\n"); goto out_free_vhdr; } @@ -454,22 +448,16 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = MAX_LFS_FILESIZE; if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { - printk(KERN_WARNING "hfs: Filesystem was " - "not cleanly unmounted, " - "running fsck.hfsplus is recommended. " - "mounting read-only.\n"); + pr_warn("Filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { - printk(KERN_WARNING "hfs: Filesystem is marked locked, mounting read-only.\n"); + pr_warn("Filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) && !(sb->s_flags & MS_RDONLY)) { - printk(KERN_WARNING "hfs: write access to " - "a journaled filesystem is not supported, " - "use the force option at your own risk, " - "mounting read-only.\n"); + pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } @@ -478,18 +466,18 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) /* Load metadata objects (B*Trees) */ sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID); if (!sbi->ext_tree) { - printk(KERN_ERR "hfs: failed to load extents file\n"); + pr_err("failed to load extents file\n"); goto out_free_vhdr; } sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID); if (!sbi->cat_tree) { - printk(KERN_ERR "hfs: failed to load catalog file\n"); + pr_err("failed to load catalog file\n"); goto out_close_ext_tree; } if (vhdr->attr_file.total_blocks != 0) { sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); if (!sbi->attr_tree) { - printk(KERN_ERR "hfs: failed to load attributes file\n"); + pr_err("failed to load attributes file\n"); goto out_close_cat_tree; } } @@ -497,7 +485,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID); if (IS_ERR(inode)) { - printk(KERN_ERR "hfs: failed to load allocation file\n"); + pr_err("failed to load allocation file\n"); err = PTR_ERR(inode); goto out_close_attr_tree; } @@ -506,7 +494,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) /* Load the root directory */ root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID); if (IS_ERR(root)) { - printk(KERN_ERR "hfs: failed to load root directory\n"); + pr_err("failed to load root directory\n"); err = PTR_ERR(root); goto out_put_alloc_file; } diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 90effcc..b51a607 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -156,7 +156,7 @@ static int hfsplus_get_last_session(struct super_block *sb, *start = (sector_t)te.cdte_addr.lba << 2; return 0; } - printk(KERN_ERR "hfs: invalid session number or type of track\n"); + pr_err("invalid session number or type of track\n"); return -EINVAL; } ms_info.addr_format = CDROM_LBA; @@ -234,8 +234,7 @@ reread: error = -EINVAL; if (sbi->s_backup_vhdr->signature != sbi->s_vhdr->signature) { - printk(KERN_WARNING - "hfs: invalid secondary volume header\n"); + pr_warn("invalid secondary volume header\n"); goto out_free_backup_vhdr; } @@ -259,8 +258,7 @@ reread: blocksize >>= 1; if (sb_set_blocksize(sb, blocksize) != blocksize) { - printk(KERN_ERR "hfs: unable to set blocksize to %u!\n", - blocksize); + pr_err("unable to set blocksize to %u!\n", blocksize); goto out_free_backup_vhdr; } diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index e8a4b08..f6634615 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -107,19 +107,19 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); if (err) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return err; } err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); if (err) { - printk(KERN_ERR "hfs: catalog searching failed\n"); + pr_err("catalog searching failed\n"); goto end_setxattr; } if (!strcmp_xattr_finder_info(name)) { if (flags & XATTR_CREATE) { - printk(KERN_ERR "hfs: xattr exists yet\n"); + pr_err("xattr exists yet\n"); err = -EOPNOTSUPP; goto end_setxattr; } @@ -165,7 +165,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, if (hfsplus_attr_exists(inode, name)) { if (flags & XATTR_CREATE) { - printk(KERN_ERR "hfs: xattr exists yet\n"); + pr_err("xattr exists yet\n"); err = -EOPNOTSUPP; goto end_setxattr; } @@ -177,7 +177,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, goto end_setxattr; } else { if (flags & XATTR_REPLACE) { - printk(KERN_ERR "hfs: cannot replace xattr\n"); + pr_err("cannot replace xattr\n"); err = -EOPNOTSUPP; goto end_setxattr; } @@ -210,7 +210,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, cat_entry_flags); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); } else { - printk(KERN_ERR "hfs: invalid catalog entry type\n"); + pr_err("invalid catalog entry type\n"); err = -EIO; goto end_setxattr; } @@ -269,7 +269,7 @@ static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry, if (size >= record_len) { res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); if (res) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return res; } res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); @@ -340,13 +340,13 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, entry = hfsplus_alloc_attr_entry(); if (!entry) { - printk(KERN_ERR "hfs: can't allocate xattr entry\n"); + pr_err("can't allocate xattr entry\n"); return -ENOMEM; } res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); if (res) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); goto failed_getxattr_init; } @@ -355,7 +355,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, if (res == -ENOENT) res = -ENODATA; else - printk(KERN_ERR "hfs: xattr searching failed\n"); + pr_err("xattr searching failed\n"); goto out; } @@ -368,17 +368,17 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, offsetof(struct hfsplus_attr_inline_data, length)); if (record_length > HFSPLUS_MAX_INLINE_DATA_SIZE) { - printk(KERN_ERR "hfs: invalid xattr record size\n"); + pr_err("invalid xattr record size\n"); res = -EIO; goto out; } } else if (record_type == HFSPLUS_ATTR_FORK_DATA || record_type == HFSPLUS_ATTR_EXTENTS) { - printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + pr_err("only inline data xattr are supported\n"); res = -EOPNOTSUPP; goto out; } else { - printk(KERN_ERR "hfs: invalid xattr record\n"); + pr_err("invalid xattr record\n"); res = -EIO; goto out; } @@ -427,7 +427,7 @@ static ssize_t hfsplus_listxattr_finder_info(struct dentry *dentry, res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); if (res) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return res; } @@ -506,7 +506,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); if (err) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return err; } @@ -525,8 +525,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) for (;;) { key_len = hfs_bnode_read_u16(fd.bnode, fd.keyoffset); if (key_len == 0 || key_len > fd.tree->max_key_len) { - printk(KERN_ERR "hfs: invalid xattr key length: %d\n", - key_len); + pr_err("invalid xattr key length: %d\n", key_len); res = -EIO; goto end_listxattr; } @@ -541,7 +540,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) if (hfsplus_uni2asc(inode->i_sb, (const struct hfsplus_unistr *)&fd.key->attr.key_name, strbuf, &xattr_name_len)) { - printk(KERN_ERR "hfs: unicode conversion failed\n"); + pr_err("unicode conversion failed\n"); res = -EIO; goto end_listxattr; } @@ -598,13 +597,13 @@ int hfsplus_removexattr(struct dentry *dentry, const char *name) err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); if (err) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return err; } err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); if (err) { - printk(KERN_ERR "hfs: catalog searching failed\n"); + pr_err("catalog searching failed\n"); goto end_removexattr; } @@ -643,7 +642,7 @@ int hfsplus_removexattr(struct dentry *dentry, const char *name) flags); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); } else { - printk(KERN_ERR "hfs: invalid catalog entry type\n"); + pr_err("invalid catalog entry type\n"); err = -EIO; goto end_removexattr; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 84e3d85..523464e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -110,7 +110,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) * way when do_mmap_pgoff unwinds (may be important on powerpc * and ia64). */ - vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) @@ -725,7 +725,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan) * inode to the back of the list so we don't spin on it. */ if (!spin_trylock(&inode->i_lock)) { - list_move_tail(&inode->i_lru, &sb->s_inode_lru); + list_move(&inode->i_lru, &sb->s_inode_lru); continue; } diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 86b39b1..11bb11f 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -162,8 +162,17 @@ static void journal_do_submit_data(struct buffer_head **wbuf, int bufs, for (i = 0; i < bufs; i++) { wbuf[i]->b_end_io = end_buffer_write_sync; - /* We use-up our safety reference in submit_bh() */ - submit_bh(write_op, wbuf[i]); + /* + * Here we write back pagecache data that may be mmaped. Since + * we cannot afford to clean the page and set PageWriteback + * here due to lock ordering (page lock ranks above transaction + * start), the data can change while IO is in flight. Tell the + * block layer it should bounce the bio pages if stable data + * during write is required. + * + * We use up our safety reference in submit_bh(). + */ + _submit_bh(write_op, wbuf[i], 1 << BIO_SNAP_STABLE); } } @@ -667,7 +676,17 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(write_op, bh); + /* + * In data=journal mode, here we can end up + * writing pagecache data that might be + * mmapped. Since we can't afford to clean the + * page and set PageWriteback (see the comment + * near the other use of _submit_bh()), the + * data can change while the write is in + * flight. Tell the block layer to bounce the + * bio pages if stable pages are required. + */ + _submit_bh(write_op, bh, 1 << BIO_SNAP_STABLE); } cond_resched(); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 81cc7ea..865c430 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -310,8 +310,6 @@ int journal_write_metadata_buffer(transaction_t *transaction, new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL); /* keep subsequent assertions sane */ - new_bh->b_state = 0; - init_buffer(new_bh, NULL, NULL); atomic_set(&new_bh->b_count, 1); new_jh = journal_add_journal_head(new_bh); /* This sleeps */ diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 750c701..0f53946 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -382,7 +382,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) int space_left = 0; int first_tag = 0; int tag_flag; - int i, to_free = 0; + int i; int tag_bytes = journal_tag_bytes(journal); struct buffer_head *cbh = NULL; /* For transactional checksums */ __u32 crc32_sum = ~0; @@ -1134,7 +1134,7 @@ restart_loop: journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged; spin_unlock(&journal->j_history_lock); - commit_transaction->t_state = T_FINISHED; + commit_transaction->t_state = T_COMMIT_CALLBACK; J_ASSERT(commit_transaction == journal->j_committing_transaction); journal->j_commit_sequence = commit_transaction->t_tid; journal->j_committing_transaction = NULL; @@ -1149,38 +1149,44 @@ restart_loop: journal->j_average_commit_time*3) / 4; else journal->j_average_commit_time = commit_time; + write_unlock(&journal->j_state_lock); - if (commit_transaction->t_checkpoint_list == NULL && - commit_transaction->t_checkpoint_io_list == NULL) { - __jbd2_journal_drop_transaction(journal, commit_transaction); - to_free = 1; + if (journal->j_checkpoint_transactions == NULL) { + journal->j_checkpoint_transactions = commit_transaction; + commit_transaction->t_cpnext = commit_transaction; + commit_transaction->t_cpprev = commit_transaction; } else { - if (journal->j_checkpoint_transactions == NULL) { - journal->j_checkpoint_transactions = commit_transaction; - commit_transaction->t_cpnext = commit_transaction; - commit_transaction->t_cpprev = commit_transaction; - } else { - commit_transaction->t_cpnext = - journal->j_checkpoint_transactions; - commit_transaction->t_cpprev = - commit_transaction->t_cpnext->t_cpprev; - commit_transaction->t_cpnext->t_cpprev = - commit_transaction; - commit_transaction->t_cpprev->t_cpnext = + commit_transaction->t_cpnext = + journal->j_checkpoint_transactions; + commit_transaction->t_cpprev = + commit_transaction->t_cpnext->t_cpprev; + commit_transaction->t_cpnext->t_cpprev = + commit_transaction; + commit_transaction->t_cpprev->t_cpnext = commit_transaction; - } } spin_unlock(&journal->j_list_lock); - + /* Drop all spin_locks because commit_callback may be block. + * __journal_remove_checkpoint() can not destroy transaction + * under us because it is not marked as T_FINISHED yet */ if (journal->j_commit_callback) journal->j_commit_callback(journal, commit_transaction); trace_jbd2_end_commit(journal, commit_transaction); jbd_debug(1, "JBD2: commit %d complete, head %d\n", journal->j_commit_sequence, journal->j_tail_sequence); - if (to_free) - jbd2_journal_free_transaction(commit_transaction); + write_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + commit_transaction->t_state = T_FINISHED; + /* Recheck checkpoint lists after j_list_lock was dropped */ + if (commit_transaction->t_checkpoint_list == NULL && + commit_transaction->t_checkpoint_io_list == NULL) { + __jbd2_journal_drop_transaction(journal, commit_transaction); + jbd2_journal_free_transaction(commit_transaction); + } + spin_unlock(&journal->j_list_lock); + write_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_done_commit); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 154592e..9545757 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -367,8 +367,6 @@ retry_alloc: } /* keep subsequent assertions sane */ - new_bh->b_state = 0; - init_buffer(new_bh, NULL, NULL); atomic_set(&new_bh->b_count, 1); new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */ @@ -710,6 +708,37 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) } /* + * When this function returns the transaction corresponding to tid + * will be completed. If the transaction has currently running, start + * committing that transaction before waiting for it to complete. If + * the transaction id is stale, it is by definition already completed, + * so just return SUCCESS. + */ +int jbd2_complete_transaction(journal_t *journal, tid_t tid) +{ + int need_to_wait = 1; + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == tid) { + if (journal->j_commit_request != tid) { + /* transaction not yet started, so request it */ + read_unlock(&journal->j_state_lock); + jbd2_log_start_commit(journal, tid); + goto wait_commit; + } + } else if (!(journal->j_committing_transaction && + journal->j_committing_transaction->t_tid == tid)) + need_to_wait = 0; + read_unlock(&journal->j_state_lock); + if (!need_to_wait) + return 0; +wait_commit: + return jbd2_log_wait_commit(journal, tid); +} +EXPORT_SYMBOL(jbd2_complete_transaction); + +/* * Log buffer allocation routines: */ diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 325bc01..10f524c 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -332,7 +332,6 @@ static handle_t *new_handle(int nblocks) handle_t *handle = jbd2_alloc_handle(GFP_NOFS); if (!handle) return NULL; - memset(handle, 0, sizeof(*handle)); handle->h_buffer_credits = nblocks; handle->h_ref = 1; @@ -640,6 +639,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, int error; char *frozen_buffer = NULL; int need_copy = 0; + unsigned long start_lock, time_lock; if (is_handle_aborted(handle)) return -EROFS; @@ -655,9 +655,16 @@ repeat: /* @@@ Need to check for errors here at some point. */ + start_lock = jiffies; lock_buffer(bh); jbd_lock_bh_state(bh); + /* If it takes too long to lock the buffer, trace it */ + time_lock = jbd2_time_diff(start_lock, jiffies); + if (time_lock > HZ/10) + trace_jbd2_lock_buffer_stall(bh->b_bdev->bd_dev, + jiffies_to_msecs(time_lock)); + /* We now hold the buffer lock so it is safe to query the buffer * state. Is the buffer dirty? * diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 0796c45..01bfe766 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -144,6 +144,9 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) timeout); if (ret < 0) return -ERESTARTSYS; + /* Reset the lock status after a server reboot so we resend */ + if (block->b_status == nlm_lck_denied_grace_period) + block->b_status = nlm_lck_blocked; req->a_res.status = block->b_status; return 0; } diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 7e529c3..9760ecb 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -550,9 +550,6 @@ again: status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT); if (status < 0) break; - /* Resend the blocking lock request after a server reboot */ - if (resp->status == nlm_lck_denied_grace_period) - continue; if (resp->status != nlm_lck_blocked) break; } diff --git a/fs/namespace.c b/fs/namespace.c index 0f0cf93..b4f96a5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -22,6 +22,7 @@ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/uaccess.h> #include <linux/proc_ns.h> +#include <linux/magic.h> #include "pnode.h" #include "internal.h" @@ -826,6 +827,10 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; + /* Don't allow unprivileged users to change mount flags */ + if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY)) + mnt->mnt.mnt_flags |= MNT_LOCK_READONLY; + atomic_inc(&sb->s_active); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); @@ -1759,6 +1764,9 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) if (readonly_request == __mnt_is_readonly(mnt)) return 0; + if (mnt->mnt_flags & MNT_LOCK_READONLY) + return -EPERM; + if (readonly_request) error = mnt_make_readonly(real_mount(mnt)); else @@ -2384,7 +2392,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, /* First pass: copy the tree topology */ copy_flags = CL_COPY_ALL | CL_EXPIRE; if (user_ns != mnt_ns->user_ns) - copy_flags |= CL_SHARED_TO_SLAVE; + copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); @@ -2780,6 +2788,51 @@ bool our_mnt(struct vfsmount *mnt) return check_mnt(real_mount(mnt)); } +bool current_chrooted(void) +{ + /* Does the current process have a non-standard root */ + struct path ns_root; + struct path fs_root; + bool chrooted; + + /* Find the namespace root */ + ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; + ns_root.dentry = ns_root.mnt->mnt_root; + path_get(&ns_root); + while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) + ; + + get_fs_root(current->fs, &fs_root); + + chrooted = !path_equal(&fs_root, &ns_root); + + path_put(&fs_root); + path_put(&ns_root); + + return chrooted; +} + +void update_mnt_policy(struct user_namespace *userns) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + struct mount *mnt; + + down_read(&namespace_sem); + 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; + } + if (userns->may_mount_sysfs && userns->may_mount_proc) + break; + } + up_read(&namespace_sem); +} + static void *mntns_get(struct task_struct *task) { struct mnt_namespace *ns = NULL; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 5088b57..cff089a 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -125,6 +125,9 @@ nfs41_callback_svc(void *vrqstp) set_freezable(); while (!kthread_should_stop()) { + if (try_to_freeze()) + continue; + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 2960512..a13d26e 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -500,7 +500,7 @@ __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy, &args->craa_type_mask)) pnfs_recall_all_layouts(cps->clp); if (flags) - nfs_expire_all_delegation_types(cps->clp, flags); + nfs_expire_unused_delegation_types(cps->clp, flags); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); return status; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 84d8eae..c513b0c 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -593,6 +593,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, args.flags |= RPC_CLNT_CREATE_DISCRTRY; if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS; if (!IS_ERR(clp->cl_rpcclient)) return 0; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 6390a4b..57db324 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -64,17 +64,15 @@ int nfs4_have_delegation(struct inode *inode, fmode_t flags) return ret; } -static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state) +static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) { struct inode *inode = state->inode; struct file_lock *fl; int status = 0; if (inode->i_flock == NULL) - return 0; - - if (inode->i_flock == NULL) goto out; + /* Protect inode->i_flock using the file locks lock */ lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { @@ -83,7 +81,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ if (nfs_file_open_context(fl->fl_file) != ctx) continue; unlock_flocks(); - status = nfs4_lock_delegation_recall(state, fl); + status = nfs4_lock_delegation_recall(fl, state, stateid); if (status < 0) goto out; lock_flocks(); @@ -120,7 +118,7 @@ again: seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); err = nfs4_open_delegation_recall(ctx, state, stateid); if (!err) - err = nfs_delegation_claim_locks(ctx, state); + err = nfs_delegation_claim_locks(ctx, state, stateid); if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) err = -EAGAIN; mutex_unlock(&sp->so_delegreturn_mutex); @@ -389,6 +387,24 @@ out: return err; } +static bool nfs_delegation_need_return(struct nfs_delegation *delegation) +{ + bool ret = false; + + if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags)) + ret = true; + if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) { + struct inode *inode; + + spin_lock(&delegation->lock); + inode = delegation->inode; + if (inode && list_empty(&NFS_I(inode)->open_files)) + ret = true; + spin_unlock(&delegation->lock); + } + return ret; +} + /** * nfs_client_return_marked_delegations - return previously marked delegations * @clp: nfs_client to process @@ -411,8 +427,7 @@ restart: list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { list_for_each_entry_rcu(delegation, &server->delegations, super_list) { - if (!test_and_clear_bit(NFS_DELEGATION_RETURN, - &delegation->flags)) + if (!nfs_delegation_need_return(delegation)) continue; inode = nfs_delegation_grab_inode(delegation); if (inode == NULL) @@ -471,6 +486,13 @@ int nfs4_inode_return_delegation(struct inode *inode) return err; } +static void nfs_mark_return_if_closed_delegation(struct nfs_server *server, + struct nfs_delegation *delegation) +{ + set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); + set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); +} + static void nfs_mark_return_delegation(struct nfs_server *server, struct nfs_delegation *delegation) { @@ -478,6 +500,45 @@ static void nfs_mark_return_delegation(struct nfs_server *server, set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); } +static bool nfs_server_mark_return_all_delegations(struct nfs_server *server) +{ + struct nfs_delegation *delegation; + bool ret = false; + + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + nfs_mark_return_delegation(server, delegation); + ret = true; + } + return ret; +} + +static void nfs_client_mark_return_all_delegations(struct nfs_client *clp) +{ + struct nfs_server *server; + + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) + nfs_server_mark_return_all_delegations(server); + rcu_read_unlock(); +} + +static void nfs_delegation_run_state_manager(struct nfs_client *clp) +{ + if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) + nfs4_schedule_state_manager(clp); +} + +/** + * nfs_expire_all_delegations + * @clp: client to process + * + */ +void nfs_expire_all_delegations(struct nfs_client *clp) +{ + nfs_client_mark_return_all_delegations(clp); + nfs_delegation_run_state_manager(clp); +} + /** * nfs_super_return_all_delegations - return delegations for one superblock * @sb: sb to process @@ -486,24 +547,22 @@ static void nfs_mark_return_delegation(struct nfs_server *server, void nfs_server_return_all_delegations(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; - struct nfs_delegation *delegation; + bool need_wait; if (clp == NULL) return; rcu_read_lock(); - list_for_each_entry_rcu(delegation, &server->delegations, super_list) { - spin_lock(&delegation->lock); - set_bit(NFS_DELEGATION_RETURN, &delegation->flags); - spin_unlock(&delegation->lock); - } + need_wait = nfs_server_mark_return_all_delegations(server); rcu_read_unlock(); - if (nfs_client_return_marked_delegations(clp) != 0) + if (need_wait) { nfs4_schedule_state_manager(clp); + nfs4_wait_clnt_recover(clp); + } } -static void nfs_mark_return_all_delegation_types(struct nfs_server *server, +static void nfs_mark_return_unused_delegation_types(struct nfs_server *server, fmode_t flags) { struct nfs_delegation *delegation; @@ -512,27 +571,21 @@ static void nfs_mark_return_all_delegation_types(struct nfs_server *server, if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE)) continue; if (delegation->type & flags) - nfs_mark_return_delegation(server, delegation); + nfs_mark_return_if_closed_delegation(server, delegation); } } -static void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp, +static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *clp, fmode_t flags) { struct nfs_server *server; rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) - nfs_mark_return_all_delegation_types(server, flags); + nfs_mark_return_unused_delegation_types(server, flags); rcu_read_unlock(); } -static void nfs_delegation_run_state_manager(struct nfs_client *clp) -{ - if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) - nfs4_schedule_state_manager(clp); -} - void nfs_remove_bad_delegation(struct inode *inode) { struct nfs_delegation *delegation; @@ -546,27 +599,17 @@ void nfs_remove_bad_delegation(struct inode *inode) EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation); /** - * nfs_expire_all_delegation_types + * nfs_expire_unused_delegation_types * @clp: client to process * @flags: delegation types to expire * */ -void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags) +void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags) { - nfs_client_mark_return_all_delegation_types(clp, flags); + nfs_client_mark_return_unused_delegation_types(clp, flags); nfs_delegation_run_state_manager(clp); } -/** - * nfs_expire_all_delegations - * @clp: client to process - * - */ -void nfs_expire_all_delegations(struct nfs_client *clp) -{ - nfs_expire_all_delegation_types(clp, FMODE_READ|FMODE_WRITE); -} - static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server) { struct nfs_delegation *delegation; @@ -574,7 +617,7 @@ static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server) list_for_each_entry_rcu(delegation, &server->delegations, super_list) { if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags)) continue; - nfs_mark_return_delegation(server, delegation); + nfs_mark_return_if_closed_delegation(server, delegation); } } diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index d54d4fc..9a79c7a 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -28,6 +28,7 @@ struct nfs_delegation { enum { NFS_DELEGATION_NEED_RECLAIM = 0, NFS_DELEGATION_RETURN, + NFS_DELEGATION_RETURN_IF_CLOSED, NFS_DELEGATION_REFERENCED, NFS_DELEGATION_RETURNING, }; @@ -41,7 +42,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode); struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle); void nfs_server_return_all_delegations(struct nfs_server *); void nfs_expire_all_delegations(struct nfs_client *clp); -void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags); +void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags); void nfs_expire_unreferenced_delegations(struct nfs_client *clp); int nfs_client_return_marked_delegations(struct nfs_client *clp); int nfs_delegations_present(struct nfs_client *clp); @@ -53,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync); int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid); -int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl); +int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags); void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index f23f455..e093e73 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1486,6 +1486,8 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) goto no_open; if (d_mountpoint(dentry)) goto no_open; + if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1) + goto no_open; inode = dentry->d_inode; parent = dget_parent(dentry); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 29f4a48..a87a44f 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -744,6 +744,7 @@ static int do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) { struct inode *inode = filp->f_mapping->host; + struct nfs_lock_context *l_ctx; int status; /* @@ -752,6 +753,14 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) */ nfs_sync_mapping(filp->f_mapping); + l_ctx = nfs_get_lock_context(nfs_file_open_context(filp)); + if (!IS_ERR(l_ctx)) { + status = nfs_iocounter_wait(&l_ctx->io_count); + nfs_put_lock_context(l_ctx); + if (status < 0) + return status; + } + /* NOTE: special case * If we're signalled while cleaning up locks on process exit, we * still need to complete the unlock. diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 1f94167..c1c7a9d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -561,20 +561,22 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) l_ctx->lockowner.l_owner = current->files; l_ctx->lockowner.l_pid = current->tgid; INIT_LIST_HEAD(&l_ctx->list); + nfs_iocounter_init(&l_ctx->io_count); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) { - struct nfs_lock_context *pos; + struct nfs_lock_context *head = &ctx->lock_context; + struct nfs_lock_context *pos = head; - list_for_each_entry(pos, &ctx->lock_context.list, list) { + do { if (pos->lockowner.l_owner != current->files) continue; if (pos->lockowner.l_pid != current->tgid) continue; atomic_inc(&pos->count); return pos; - } + } while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head); return NULL; } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 541c9eb..91e59a3 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -229,6 +229,13 @@ extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); +int nfs_iocounter_wait(struct nfs_io_counter *c); + +static inline void nfs_iocounter_init(struct nfs_io_counter *c) +{ + c->flags = 0; + atomic_set(&c->io_count, 0); +} /* nfs2xdr.c */ extern struct rpc_procinfo nfs_procedures[]; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 944c9a5..553a83c 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -36,6 +36,7 @@ enum nfs4_client_state { struct nfs4_minor_version_ops { u32 minor_version; + unsigned init_caps; int (*call_sync)(struct rpc_clnt *clnt, struct nfs_server *server, @@ -143,12 +144,14 @@ struct nfs4_lock_state { enum { LK_STATE_IN_USE, NFS_DELEGATED_STATE, /* Current stateid is delegation */ + NFS_OPEN_STATE, /* OPEN stateid is set */ NFS_O_RDONLY_STATE, /* OPEN stateid has read-only state */ NFS_O_WRONLY_STATE, /* OPEN stateid has write-only state */ NFS_O_RDWR_STATE, /* OPEN stateid has read/write state */ NFS_STATE_RECLAIM_REBOOT, /* OPEN stateid server rebooted */ NFS_STATE_RECLAIM_NOGRACE, /* OPEN stateid needs to recover state */ NFS_STATE_POSIX_LOCKS, /* Posix locks are supported */ + NFS_STATE_RECOVERY_FAILED, /* OPEN stateid state recovery failed */ }; struct nfs4_state { @@ -233,6 +236,10 @@ extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); extern int nfs4_release_lockowner(struct nfs4_lock_state *); extern const struct xattr_handler *nfs4_xattr_handlers[]; +extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, + const struct nfs_open_context *ctx, + const struct nfs_lock_context *l_ctx, + fmode_t fmode); #if defined(CONFIG_NFS_V4_1) static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server) @@ -347,13 +354,13 @@ extern int nfs4_wait_clnt_recover(struct nfs_client *clp); extern int nfs4_client_recover_expired_lease(struct nfs_client *clp); extern void nfs4_schedule_state_manager(struct nfs_client *); extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp); -extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); +extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_server_scope(struct nfs_client *, struct nfs41_server_scope **); extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); -extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *, +extern int nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *, fmode_t, const struct nfs_lockowner *); extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask); @@ -412,6 +419,11 @@ static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_statei return memcmp(dst, src, sizeof(*dst)) == 0; } +static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state) +{ + return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0; +} + #else #define nfs4_close_state(a, b) do { } while (0) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ac4fc9a..947b0c9 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -198,8 +198,12 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, /* Check NFS protocol revision and initialize RPC op vector */ clp->rpc_ops = &nfs_v4_clientops; + if (clp->cl_minorversion != 0) + __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); - error = nfs_create_rpc_client(clp, timeparms, authflavour); + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I); + if (error == -EINVAL) + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_NULL); if (error < 0) goto error; @@ -300,7 +304,7 @@ int nfs40_walk_client_list(struct nfs_client *new, struct rpc_cred *cred) { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); - struct nfs_client *pos, *n, *prev = NULL; + struct nfs_client *pos, *prev = NULL; struct nfs4_setclientid_res clid = { .clientid = new->cl_clientid, .confirm = new->cl_confirm, @@ -308,10 +312,23 @@ int nfs40_walk_client_list(struct nfs_client *new, int status = -NFS4ERR_STALE_CLIENTID; spin_lock(&nn->nfs_client_lock); - list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) { + list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos" */ - if (pos->cl_cons_state < NFS_CS_READY) + if (pos->cl_cons_state > NFS_CS_READY) { + atomic_inc(&pos->cl_count); + spin_unlock(&nn->nfs_client_lock); + + if (prev) + nfs_put_client(prev); + prev = pos; + + status = nfs_wait_client_init_complete(pos); + spin_lock(&nn->nfs_client_lock); + if (status < 0) + continue; + } + if (pos->cl_cons_state != NFS_CS_READY) continue; if (pos->rpc_ops != new->rpc_ops) @@ -423,16 +440,16 @@ int nfs41_walk_client_list(struct nfs_client *new, struct rpc_cred *cred) { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); - struct nfs_client *pos, *n, *prev = NULL; + struct nfs_client *pos, *prev = NULL; int status = -NFS4ERR_STALE_CLIENTID; spin_lock(&nn->nfs_client_lock); - list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) { + list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos", especially the client * ID and serverowner fields. Wait for CREATE_SESSION * to finish. */ - if (pos->cl_cons_state < NFS_CS_READY) { + if (pos->cl_cons_state > NFS_CS_READY) { atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); @@ -440,18 +457,17 @@ int nfs41_walk_client_list(struct nfs_client *new, nfs_put_client(prev); prev = pos; - nfs4_schedule_lease_recovery(pos); status = nfs_wait_client_init_complete(pos); - if (status < 0) { - nfs_put_client(pos); - spin_lock(&nn->nfs_client_lock); - continue; + if (status == 0) { + nfs4_schedule_lease_recovery(pos); + status = nfs4_wait_clnt_recover(pos); } - status = pos->cl_cons_state; spin_lock(&nn->nfs_client_lock); if (status < 0) continue; } + if (pos->cl_cons_state != NFS_CS_READY) + continue; if (pos->rpc_ops != new->rpc_ops) continue; @@ -469,17 +485,18 @@ int nfs41_walk_client_list(struct nfs_client *new, continue; atomic_inc(&pos->cl_count); - spin_unlock(&nn->nfs_client_lock); + *result = pos; + status = 0; dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n", __func__, pos, atomic_read(&pos->cl_count)); - - *result = pos; - return 0; + break; } /* No matching nfs_client found. */ spin_unlock(&nn->nfs_client_lock); dprintk("NFS: <-- %s status = %d\n", __func__, status); + if (prev) + nfs_put_client(prev); return status; } #endif /* CONFIG_NFS_V4_1 */ @@ -717,6 +734,19 @@ static int nfs4_server_common_setup(struct nfs_server *server, if (error < 0) goto out; + /* Set the basic capabilities */ + server->caps |= server->nfs_client->cl_mvops->init_caps; + if (server->flags & NFS_MOUNT_NORDIRPLUS) + server->caps &= ~NFS_CAP_READDIRPLUS; + /* + * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower + * authentication. + */ + if (nfs4_disable_idmapping && + server->client->cl_auth->au_flavor == RPC_AUTH_UNIX) + server->caps |= NFS_CAP_UIDGID_NOMAP; + + /* Probe the root fh to retrieve its FSID and filehandle */ error = nfs4_get_rootfh(server, mntfh); if (error < 0) @@ -760,9 +790,6 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; - server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK; - if (!(data->flags & NFS_MOUNT_NORDIRPLUS)) - server->caps |= NFS_CAP_READDIRPLUS; server->options = data->options; /* Get a client record */ @@ -779,13 +806,6 @@ static int nfs4_init_server(struct nfs_server *server, if (error < 0) goto error; - /* - * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower - * authentication. - */ - if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX) - server->caps |= NFS_CAP_UIDGID_NOMAP; - if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); if (data->wsize) @@ -863,7 +883,6 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, /* Initialise the client representation from the parent server */ nfs_server_copy_userdata(server, parent_server); - server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; /* Get a client representation. * Note: NFSv4 always uses TCP, */ diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 4fb234d..22d1062 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -158,11 +158,14 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -NFS4ERR_OPENMODE: if (state == NULL) break; - nfs4_schedule_stateid_recovery(mds_server, state); + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; goto wait_on_recovery; case -NFS4ERR_EXPIRED: - if (state != NULL) - nfs4_schedule_stateid_recovery(mds_server, state); + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + } nfs4_schedule_lease_recovery(mds_client); goto wait_on_recovery; /* DS session errors */ @@ -226,6 +229,9 @@ reset: out: task->tk_status = 0; return -EAGAIN; +out_bad_stateid: + task->tk_status = -EIO; + return 0; wait_on_recovery: rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) @@ -299,6 +305,10 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) { struct nfs_read_data *rdata = data; + if (unlikely(test_bit(NFS_CONTEXT_BAD, &rdata->args.context->flags))) { + rpc_exit(task, -EIO); + return; + } if (filelayout_reset_to_mds(rdata->header->lseg)) { dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); filelayout_reset_read(rdata); @@ -307,10 +317,13 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) } rdata->read_done_cb = filelayout_read_done_cb; - nfs41_setup_sequence(rdata->ds_clp->cl_session, + if (nfs41_setup_sequence(rdata->ds_clp->cl_session, &rdata->args.seq_args, &rdata->res.seq_res, - task); + task)) + return; + nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context, + rdata->args.lock_context, FMODE_READ); } static void filelayout_read_call_done(struct rpc_task *task, void *data) @@ -401,16 +414,23 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data) { struct nfs_write_data *wdata = data; + if (unlikely(test_bit(NFS_CONTEXT_BAD, &wdata->args.context->flags))) { + rpc_exit(task, -EIO); + return; + } if (filelayout_reset_to_mds(wdata->header->lseg)) { dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); filelayout_reset_write(wdata); rpc_exit(task, 0); return; } - nfs41_setup_sequence(wdata->ds_clp->cl_session, + if (nfs41_setup_sequence(wdata->ds_clp->cl_session, &wdata->args.seq_args, &wdata->res.seq_res, - task); + task)) + return; + nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context, + wdata->args.lock_context, FMODE_WRITE); } static void filelayout_write_call_done(struct rpc_task *task, void *data) diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 0dd7660..cdb0b41 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -134,33 +134,38 @@ static size_t nfs_parse_server_name(char *string, size_t len, return ret; } +/** + * nfs_find_best_sec - Find a security mechanism supported locally + * @flavors: List of security tuples returned by SECINFO procedure + * + * Return the pseudoflavor of the first security mechanism in + * "flavors" that is locally supported. Return RPC_AUTH_UNIX if + * no matching flavor is found in the array. The "flavors" array + * is searched in the order returned from the server, per RFC 3530 + * recommendation. + */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) { - struct gss_api_mech *mech; - struct xdr_netobj oid; - int i; - rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; + rpc_authflavor_t pseudoflavor; + struct nfs4_secinfo4 *secinfo; + unsigned int i; for (i = 0; i < flavors->num_flavors; i++) { - struct nfs4_secinfo_flavor *flavor; - flavor = &flavors->flavors[i]; - - if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { - pseudoflavor = flavor->flavor; - break; - } else if (flavor->flavor == RPC_AUTH_GSS) { - oid.len = flavor->gss.sec_oid4.len; - oid.data = flavor->gss.sec_oid4.data; - mech = gss_mech_get_by_OID(&oid); - if (!mech) - continue; - pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); - gss_mech_put(mech); + secinfo = &flavors->flavors[i]; + + switch (secinfo->flavor) { + case RPC_AUTH_NULL: + case RPC_AUTH_UNIX: + case RPC_AUTH_GSS: + pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor, + &secinfo->flavor_info); + if (pseudoflavor != RPC_AUTH_MAXFLAVOR) + return pseudoflavor; break; } } - return pseudoflavor; + return RPC_AUTH_UNIX; } static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 26431cf..9da4bd5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -107,6 +107,8 @@ static int nfs4_map_errors(int err) return -EPROTONOSUPPORT; case -NFS4ERR_ACCESS: return -EACCES; + case -NFS4ERR_FILE_OPEN: + return -EBUSY; default: dprintk("%s could not handle NFSv4 error %d\n", __func__, -err); @@ -295,19 +297,30 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc } if (state == NULL) break; - nfs4_schedule_stateid_recovery(server, state); + ret = nfs4_schedule_stateid_recovery(server, state); + if (ret < 0) + break; goto wait_on_recovery; case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: + if (inode != NULL && nfs4_have_delegation(inode, FMODE_READ)) { + nfs_remove_bad_delegation(inode); + exception->retry = 1; + break; + } if (state == NULL) break; - nfs_remove_bad_delegation(state->inode); - nfs4_schedule_stateid_recovery(server, state); + ret = nfs4_schedule_stateid_recovery(server, state); + if (ret < 0) + break; goto wait_on_recovery; case -NFS4ERR_EXPIRED: - if (state != NULL) - nfs4_schedule_stateid_recovery(server, state); + if (state != NULL) { + ret = nfs4_schedule_stateid_recovery(server, state); + if (ret < 0) + break; + } case -NFS4ERR_STALE_STATEID: case -NFS4ERR_STALE_CLIENTID: nfs4_schedule_lease_recovery(clp); @@ -756,10 +769,40 @@ struct nfs4_opendata { struct iattr attrs; unsigned long timestamp; unsigned int rpc_done : 1; + unsigned int is_recover : 1; int rpc_status; int cancelled; }; +static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, + int err, struct nfs4_exception *exception) +{ + if (err != -EINVAL) + return false; + if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1)) + return false; + server->caps &= ~NFS_CAP_ATOMIC_OPEN_V1; + exception->retry = 1; + return true; +} + +static enum open_claim_type4 +nfs4_map_atomic_open_claim(struct nfs_server *server, + enum open_claim_type4 claim) +{ + if (server->caps & NFS_CAP_ATOMIC_OPEN_V1) + return claim; + switch (claim) { + default: + return claim; + case NFS4_OPEN_CLAIM_FH: + return NFS4_OPEN_CLAIM_NULL; + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + return NFS4_OPEN_CLAIM_DELEGATE_CUR; + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + return NFS4_OPEN_CLAIM_DELEGATE_PREV; + } +} static void nfs4_init_opendata_res(struct nfs4_opendata *p) { @@ -775,6 +818,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p) static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct nfs4_state_owner *sp, fmode_t fmode, int flags, const struct iattr *attrs, + enum open_claim_type4 claim, gfp_t gfp_mask) { struct dentry *parent = dget_parent(dentry); @@ -793,7 +837,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->dir = parent; p->owner = sp; atomic_inc(&sp->so_count); - p->o_arg.fh = NFS_FH(dir); p->o_arg.open_flags = flags; p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS @@ -811,7 +854,19 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.server = server; p->o_arg.bitmask = server->attr_bitmask; p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; - p->o_arg.claim = NFS4_OPEN_CLAIM_NULL; + p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim); + switch (p->o_arg.claim) { + case NFS4_OPEN_CLAIM_NULL: + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + p->o_arg.fh = NFS_FH(dir); + break; + case NFS4_OPEN_CLAIM_PREVIOUS: + case NFS4_OPEN_CLAIM_FH: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + p->o_arg.fh = NFS_FH(dentry->d_inode); + } if (attrs != NULL && attrs->ia_valid != 0) { __be32 verf[2]; @@ -924,6 +979,7 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid * if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) nfs4_stateid_copy(&state->stateid, stateid); nfs4_stateid_copy(&state->open_stateid, stateid); + set_bit(NFS_OPEN_STATE, &state->flags); switch (fmode) { case FMODE_READ: set_bit(NFS_O_RDONLY_STATE, &state->flags); @@ -1046,9 +1102,12 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) /* Save the delegation */ nfs4_stateid_copy(&stateid, &delegation->stateid); rcu_read_unlock(); - ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode); - if (ret != 0) - goto out; + nfs_release_seqid(opendata->o_arg.seqid); + if (!opendata->is_recover) { + ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode); + if (ret != 0) + goto out; + } ret = -EAGAIN; /* Try to update the stateid using the delegation */ @@ -1193,11 +1252,13 @@ static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state * return ERR_PTR(-ENOENT); } -static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx, struct nfs4_state *state) +static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx, + struct nfs4_state *state, enum open_claim_type4 claim) { struct nfs4_opendata *opendata; - opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, NULL, GFP_NOFS); + opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, + NULL, claim, GFP_NOFS); if (opendata == NULL) return ERR_PTR(-ENOMEM); opendata->state = state; @@ -1233,6 +1294,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * /* memory barrier prior to reading state->n_* */ clear_bit(NFS_DELEGATED_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); smp_rmb(); if (state->n_rdwr != 0) { clear_bit(NFS_O_RDWR_STATE, &state->flags); @@ -1283,11 +1345,10 @@ static int _nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state fmode_t delegation_type = 0; int status; - opendata = nfs4_open_recoverdata_alloc(ctx, state); + opendata = nfs4_open_recoverdata_alloc(ctx, state, + NFS4_OPEN_CLAIM_PREVIOUS); if (IS_ERR(opendata)) return PTR_ERR(opendata); - opendata->o_arg.claim = NFS4_OPEN_CLAIM_PREVIOUS; - opendata->o_arg.fh = NFS_FH(state->inode); rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); if (delegation != NULL && test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) != 0) @@ -1306,6 +1367,8 @@ static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state int err; do { err = _nfs4_do_open_reclaim(ctx, state); + if (nfs4_clear_cap_atomic_open_v1(server, err, &exception)) + continue; if (err != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, err, &exception); @@ -1320,71 +1383,72 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta ctx = nfs4_state_find_open_context(state); if (IS_ERR(ctx)) - return PTR_ERR(ctx); + return -EAGAIN; ret = nfs4_do_open_reclaim(ctx, state); put_nfs_open_context(ctx); return ret; } -static int _nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) +static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err) { - struct nfs4_opendata *opendata; - int ret; - - opendata = nfs4_open_recoverdata_alloc(ctx, state); - if (IS_ERR(opendata)) - return PTR_ERR(opendata); - opendata->o_arg.claim = NFS4_OPEN_CLAIM_DELEGATE_CUR; - nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - ret = nfs4_open_recover(opendata, state); - nfs4_opendata_put(opendata); - return ret; + switch (err) { + default: + printk(KERN_ERR "NFS: %s: unhandled error " + "%d.\n", __func__, err); + case 0: + case -ENOENT: + case -ESTALE: + break; + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_DEADSESSION: + set_bit(NFS_DELEGATED_STATE, &state->flags); + nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); + return -EAGAIN; + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_STALE_STATEID: + set_bit(NFS_DELEGATED_STATE, &state->flags); + case -NFS4ERR_EXPIRED: + /* Don't recall a delegation if it was lost */ + nfs4_schedule_lease_recovery(server->nfs_client); + return -EAGAIN; + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OPENMODE: + nfs_inode_find_state_and_recover(state->inode, + stateid); + nfs4_schedule_stateid_recovery(server, state); + return 0; + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + set_bit(NFS_DELEGATED_STATE, &state->flags); + ssleep(1); + return -EAGAIN; + case -ENOMEM: + case -NFS4ERR_DENIED: + /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + return 0; + } + return err; } int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) { - struct nfs4_exception exception = { }; struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs4_opendata *opendata; int err; - do { - err = _nfs4_open_delegation_recall(ctx, state, stateid); - switch (err) { - case 0: - case -ENOENT: - case -ESTALE: - goto out; - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - case -NFS4ERR_DEADSESSION: - set_bit(NFS_DELEGATED_STATE, &state->flags); - nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); - err = -EAGAIN; - goto out; - case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_STALE_STATEID: - set_bit(NFS_DELEGATED_STATE, &state->flags); - case -NFS4ERR_EXPIRED: - /* Don't recall a delegation if it was lost */ - nfs4_schedule_lease_recovery(server->nfs_client); - err = -EAGAIN; - goto out; - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - nfs_inode_find_state_and_recover(state->inode, - stateid); - nfs4_schedule_stateid_recovery(server, state); - case -ENOMEM: - err = 0; - goto out; - } - set_bit(NFS_DELEGATED_STATE, &state->flags); - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); -out: - return err; + + opendata = nfs4_open_recoverdata_alloc(ctx, state, + NFS4_OPEN_CLAIM_DELEG_CUR_FH); + if (IS_ERR(opendata)) + return PTR_ERR(opendata); + nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); + err = nfs4_open_recover(opendata, state); + nfs4_opendata_put(opendata); + return nfs4_handle_delegation_recall_error(server, state, stateid, err); } static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) @@ -1467,6 +1531,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; struct nfs4_state_owner *sp = data->owner; + struct nfs_client *clp = sp->so_server->nfs_client; if (nfs_wait_on_sequence(data->o_arg.seqid, task) != 0) goto out_wait; @@ -1482,15 +1547,20 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) rcu_read_lock(); delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR && + data->o_arg.claim != NFS4_OPEN_CLAIM_DELEG_CUR_FH && can_open_delegated(delegation, data->o_arg.fmode)) goto unlock_no_action; rcu_read_unlock(); } /* Update client id. */ - data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid; - if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) { - task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; + data->o_arg.clientid = clp->cl_clientid; + switch (data->o_arg.claim) { + case NFS4_OPEN_CLAIM_PREVIOUS: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0]; + case NFS4_OPEN_CLAIM_FH: + task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; nfs_copy_fh(&data->o_res.fh, data->o_arg.fh); } data->timestamp = jiffies; @@ -1499,6 +1569,16 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) &data->o_res.seq_res, task) != 0) nfs_release_seqid(data->o_arg.seqid); + + /* Set the create mode (note dependency on the session type) */ + data->o_arg.createmode = NFS4_CREATE_UNCHECKED; + if (data->o_arg.open_flags & O_EXCL) { + data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE; + if (nfs4_has_persistent_session(clp)) + data->o_arg.createmode = NFS4_CREATE_GUARDED; + else if (clp->cl_mvops->minor_version > 0) + data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1; + } return; unlock_no_action: rcu_read_unlock(); @@ -1594,8 +1674,11 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover) data->rpc_done = 0; data->rpc_status = 0; data->cancelled = 0; - if (isrecover) + data->is_recover = 0; + if (isrecover) { nfs4_set_sequence_privileged(&o_arg->seq_args); + data->is_recover = 1; + } task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -1720,7 +1803,8 @@ static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *s struct nfs4_opendata *opendata; int ret; - opendata = nfs4_open_recoverdata_alloc(ctx, state); + opendata = nfs4_open_recoverdata_alloc(ctx, state, + NFS4_OPEN_CLAIM_FH); if (IS_ERR(opendata)) return PTR_ERR(opendata); ret = nfs4_open_recover(opendata, state); @@ -1738,6 +1822,8 @@ static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state do { err = _nfs4_open_expired(ctx, state); + if (nfs4_clear_cap_atomic_open_v1(server, err, &exception)) + continue; switch (err) { default: goto out; @@ -1758,7 +1844,7 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta ctx = nfs4_state_find_open_context(state); if (IS_ERR(ctx)) - return PTR_ERR(ctx); + return -EAGAIN; ret = nfs4_do_open_expired(ctx, state); put_nfs_open_context(ctx); return ret; @@ -1820,6 +1906,7 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) clear_bit(NFS_O_RDONLY_STATE, &state->flags); clear_bit(NFS_O_WRONLY_STATE, &state->flags); clear_bit(NFS_O_RDWR_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); } return status; } @@ -1880,10 +1967,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, if (ret != 0) goto out; - if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) { + if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) nfs4_schedule_stateid_recovery(server, state); - nfs4_wait_clnt_recover(server->nfs_client); - } *res = state; out: return ret; @@ -1905,6 +1990,7 @@ static int _nfs4_do_open(struct inode *dir, struct nfs4_state *state = NULL; struct nfs_server *server = NFS_SERVER(dir); struct nfs4_opendata *opendata; + enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; int status; /* Protect against reboot recovery conflicts */ @@ -1920,7 +2006,10 @@ static int _nfs4_do_open(struct inode *dir, if (dentry->d_inode != NULL) nfs4_return_incompatible_delegation(dentry->d_inode, fmode); status = -ENOMEM; - opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, GFP_KERNEL); + if (dentry->d_inode) + claim = NFS4_OPEN_CLAIM_FH; + opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, + claim, GFP_KERNEL); if (opendata == NULL) goto err_put_state_owner; @@ -1937,7 +2026,8 @@ static int _nfs4_do_open(struct inode *dir, if (status != 0) goto err_opendata_put; - if (opendata->o_arg.open_flags & O_EXCL) { + if ((opendata->o_arg.open_flags & O_EXCL) && + (opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) { nfs4_exclusive_attrset(opendata, sattr); nfs_fattr_init(opendata->o_res.f_attr); @@ -1978,6 +2068,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct rpc_cred *cred, struct nfs4_threshold **ctx_th) { + struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { }; struct nfs4_state *res; int status; @@ -2021,7 +2112,9 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, exception.retry = 1; continue; } - res = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir), + if (nfs4_clear_cap_atomic_open_v1(server, status, &exception)) + continue; + res = ERR_PTR(nfs4_handle_exception(server, status, &exception)); } while (exception.retry); return res; @@ -2049,20 +2142,25 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, .rpc_cred = cred, }; unsigned long timestamp = jiffies; + fmode_t fmode; + bool truncate; int status; nfs_fattr_init(fattr); - if (state != NULL) { + /* Servers should only apply open mode checks for file size changes */ + truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false; + fmode = truncate ? FMODE_WRITE : FMODE_READ; + + if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) { + /* Use that stateid */ + } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) { struct nfs_lockowner lockowner = { .l_owner = current->files, .l_pid = current->tgid, }; nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE, &lockowner); - } else if (nfs4_copy_delegation_stateid(&arg.stateid, inode, - FMODE_WRITE)) { - /* Use that stateid */ } else nfs4_stateid_copy(&arg.stateid, &zero_stateid); @@ -2086,6 +2184,13 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, err = _nfs4_do_setattr(inode, cred, fattr, sattr, state); switch (err) { case -NFS4ERR_OPENMODE: + if (!(sattr->ia_valid & ATTR_SIZE)) { + pr_warn_once("NFSv4: server %s is incorrectly " + "applying open mode checks to " + "a SETATTR that is not " + "changing file size.\n", + server->nfs_client->cl_hostname); + } if (state && !(state->state & FMODE_WRITE)) { err = -EBADF; if (sattr->ia_valid & ATTR_OPEN) @@ -2129,11 +2234,19 @@ static void nfs4_close_clear_stateid_flags(struct nfs4_state *state, fmode_t fmode) { spin_lock(&state->owner->so_lock); - if (!(fmode & FMODE_READ)) + clear_bit(NFS_O_RDWR_STATE, &state->flags); + switch (fmode & (FMODE_READ|FMODE_WRITE)) { + case FMODE_WRITE: clear_bit(NFS_O_RDONLY_STATE, &state->flags); - if (!(fmode & FMODE_WRITE)) + break; + case FMODE_READ: clear_bit(NFS_O_WRONLY_STATE, &state->flags); - clear_bit(NFS_O_RDWR_STATE, &state->flags); + break; + case 0: + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); + } spin_unlock(&state->owner->so_lock); } @@ -2201,6 +2314,8 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) calldata->arg.fmode &= ~FMODE_WRITE; } } + if (!nfs4_valid_open_stateid(state)) + call_close = 0; spin_unlock(&state->owner->so_lock); if (!call_close) { @@ -2211,8 +2326,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) if (calldata->arg.fmode == 0) { task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE]; if (calldata->roc && - pnfs_roc_drain(inode, &calldata->roc_barrier, task)) + pnfs_roc_drain(inode, &calldata->roc_barrier, task)) { + nfs_release_seqid(calldata->arg.seqid); goto out_wait; + } } nfs_fattr_init(calldata->res.fattr); @@ -2443,7 +2560,7 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl auth = rpcauth_create(flavor, server->client); if (IS_ERR(auth)) { - ret = -EIO; + ret = -EACCES; goto out; } ret = nfs4_lookup_root(server, fhandle, info); @@ -2451,27 +2568,36 @@ out: return ret; } +/* + * Retry pseudoroot lookup with various security flavors. We do this when: + * + * NFSv4.0: the PUTROOTFH operation returns NFS4ERR_WRONGSEC + * NFSv4.1: the server does not support the SECINFO_NO_NAME operation + * + * Returns zero on success, or a negative NFS4ERR value, or a + * negative errno value. + */ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { - int i, len, status = 0; - rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS]; - - len = rpcauth_list_flavors(flav_array, ARRAY_SIZE(flav_array)); - if (len < 0) - return len; - - for (i = 0; i < len; i++) { - /* AUTH_UNIX is the default flavor if none was specified, - * thus has already been tried. */ - if (flav_array[i] == RPC_AUTH_UNIX) - continue; + /* Per 3530bis 15.33.5 */ + static const rpc_authflavor_t flav_array[] = { + RPC_AUTH_GSS_KRB5P, + RPC_AUTH_GSS_KRB5I, + RPC_AUTH_GSS_KRB5, + RPC_AUTH_UNIX, /* courtesy */ + RPC_AUTH_NULL, + }; + int status = -EPERM; + size_t i; + for (i = 0; i < ARRAY_SIZE(flav_array); i++) { status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]); if (status == -NFS4ERR_WRONGSEC || status == -EACCES) continue; break; } + /* * -EACCESS could mean that the user doesn't have correct permissions * to access the mount. It could also mean that we tried to mount @@ -2484,24 +2610,36 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, return status; } -/* - * get the file handle for the "/" directory on the server +static int nfs4_do_find_root_sec(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs_fsinfo *info) +{ + int mv = server->nfs_client->cl_minorversion; + return nfs_v4_minor_ops[mv]->find_root_sec(server, fhandle, info); +} + +/** + * nfs4_proc_get_rootfh - get file handle for server's pseudoroot + * @server: initialized nfs_server handle + * @fhandle: we fill in the pseudo-fs root file handle + * @info: we fill in an FSINFO struct + * + * 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) { - int minor_version = server->nfs_client->cl_minorversion; - int status = nfs4_lookup_root(server, fhandle, info); - if ((status == -NFS4ERR_WRONGSEC) && !(server->flags & NFS_MOUNT_SECFLAVOUR)) - /* - * A status of -NFS4ERR_WRONGSEC will be mapped to -EPERM - * by nfs4_map_errors() as this function exits. - */ - status = nfs_v4_minor_ops[minor_version]->find_root_sec(server, fhandle, info); + int status; + + status = nfs4_lookup_root(server, fhandle, info); + if ((status == -NFS4ERR_WRONGSEC) && + !(server->flags & NFS_MOUNT_SECFLAVOUR)) + status = nfs4_do_find_root_sec(server, fhandle, info); + if (status == 0) status = nfs4_server_capabilities(server, fhandle); if (status == 0) status = nfs4_do_fsinfo(server, fhandle, info); + return nfs4_map_errors(status); } @@ -3380,12 +3518,21 @@ static int _nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo) { struct nfs4_exception exception = { }; + unsigned long now = jiffies; int err; do { - err = nfs4_handle_exception(server, - _nfs4_do_fsinfo(server, fhandle, fsinfo), - &exception); + err = _nfs4_do_fsinfo(server, fhandle, fsinfo); + if (err == 0) { + struct nfs_client *clp = server->nfs_client; + + spin_lock(&clp->cl_lock); + clp->cl_lease_time = fsinfo->lease_time * HZ; + clp->cl_last_renewal = now; + spin_unlock(&clp->cl_lock); + break; + } + err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); return err; } @@ -3445,6 +3592,46 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return err; } +int nfs4_set_rw_stateid(nfs4_stateid *stateid, + const struct nfs_open_context *ctx, + const struct nfs_lock_context *l_ctx, + fmode_t fmode) +{ + const struct nfs_lockowner *lockowner = NULL; + + if (l_ctx != NULL) + lockowner = &l_ctx->lockowner; + return nfs4_select_rw_stateid(stateid, ctx->state, fmode, lockowner); +} +EXPORT_SYMBOL_GPL(nfs4_set_rw_stateid); + +static bool nfs4_stateid_is_current(nfs4_stateid *stateid, + const struct nfs_open_context *ctx, + const struct nfs_lock_context *l_ctx, + fmode_t fmode) +{ + nfs4_stateid current_stateid; + + if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode)) + return false; + return nfs4_stateid_match(stateid, ¤t_stateid); +} + +static bool nfs4_error_stateid_expired(int err) +{ + switch (err) { + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_OPENMODE: + case -NFS4ERR_EXPIRED: + return true; + } + return false; +} + void __nfs4_read_done_cb(struct nfs_read_data *data) { nfs_invalidate_atime(data->header->inode); @@ -3465,6 +3652,20 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) return 0; } +static bool nfs4_read_stateid_changed(struct rpc_task *task, + struct nfs_readargs *args) +{ + + if (!nfs4_error_stateid_expired(task->tk_status) || + nfs4_stateid_is_current(&args->stateid, + args->context, + args->lock_context, + FMODE_READ)) + return false; + rpc_restart_call_prepare(task); + return true; +} + static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data) { @@ -3472,7 +3673,8 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data) if (!nfs4_sequence_done(task, &data->res.seq_res)) return -EAGAIN; - + if (nfs4_read_stateid_changed(task, &data->args)) + return -EAGAIN; return data->read_done_cb ? data->read_done_cb(task, data) : nfs4_read_done_cb(task, data); } @@ -3487,10 +3689,13 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { - nfs4_setup_sequence(NFS_SERVER(data->header->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, - task); + task)) + return; + nfs4_set_rw_stateid(&data->args.stateid, data->args.context, + data->args.lock_context, FMODE_READ); } static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) @@ -3508,10 +3713,26 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data return 0; } +static bool nfs4_write_stateid_changed(struct rpc_task *task, + struct nfs_writeargs *args) +{ + + if (!nfs4_error_stateid_expired(task->tk_status) || + nfs4_stateid_is_current(&args->stateid, + args->context, + args->lock_context, + FMODE_WRITE)) + return false; + rpc_restart_call_prepare(task); + return true; +} + static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data) { if (!nfs4_sequence_done(task, &data->res.seq_res)) return -EAGAIN; + if (nfs4_write_stateid_changed(task, &data->args)) + return -EAGAIN; return data->write_done_cb ? data->write_done_cb(task, data) : nfs4_write_done_cb(task, data); } @@ -3551,10 +3772,13 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { - nfs4_setup_sequence(NFS_SERVER(data->header->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, - task); + task)) + return; + nfs4_set_rw_stateid(&data->args.stateid, data->args.context, + data->args.lock_context, FMODE_WRITE); } static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) @@ -3656,7 +3880,7 @@ static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, return -ENOMEM; data->client = clp; data->timestamp = jiffies; - return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_SOFT, + return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT, &nfs4_renew_ops, data); } @@ -3670,7 +3894,7 @@ static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred) unsigned long now = jiffies; int status; - status = rpc_call_sync(clp->cl_rpcclient, &msg, 0); + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status < 0) return status; do_renew_lease(clp, now); @@ -3980,11 +4204,14 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, case -NFS4ERR_OPENMODE: if (state == NULL) break; - nfs4_schedule_stateid_recovery(server, state); + if (nfs4_schedule_stateid_recovery(server, state) < 0) + goto stateid_invalid; goto wait_on_recovery; case -NFS4ERR_EXPIRED: - if (state != NULL) - nfs4_schedule_stateid_recovery(server, state); + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(server, state) < 0) + goto stateid_invalid; + } case -NFS4ERR_STALE_STATEID: case -NFS4ERR_STALE_CLIENTID: nfs4_schedule_lease_recovery(clp); @@ -4016,6 +4243,9 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, } task->tk_status = nfs4_map_errors(task->tk_status); return 0; +stateid_invalid: + task->tk_status = -EIO; + return 0; wait_on_recovery: rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) @@ -4143,27 +4373,17 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct nfs4_setclientid_res *arg, struct rpc_cred *cred) { - struct nfs_fsinfo fsinfo; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID_CONFIRM], .rpc_argp = arg, - .rpc_resp = &fsinfo, .rpc_cred = cred, }; - unsigned long now; int status; dprintk("NFS call setclientid_confirm auth=%s, (client ID %llx)\n", clp->cl_rpcclient->cl_auth->au_ops->au_name, clp->cl_clientid); - now = jiffies; status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); - if (status == 0) { - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo.lease_time * HZ; - clp->cl_last_renewal = now; - spin_unlock(&clp->cl_lock); - } dprintk("NFS reply setclientid_confirm: %d\n", status); return status; } @@ -4627,17 +4847,23 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) { goto out_release_lock_seqid; } - data->arg.open_stateid = &state->stateid; + data->arg.open_stateid = &state->open_stateid; data->arg.new_lock_owner = 1; data->res.open_seqid = data->arg.open_seqid; } else data->arg.new_lock_owner = 0; + if (!nfs4_valid_open_stateid(state)) { + data->rpc_status = -EBADF; + task->tk_action = NULL; + goto out_release_open_seqid; + } data->timestamp = jiffies; if (nfs4_setup_sequence(data->server, &data->arg.seq_args, &data->res.seq_res, task) == 0) return; +out_release_open_seqid: nfs_release_seqid(data->arg.open_seqid); out_release_lock_seqid: nfs_release_seqid(data->arg.lock_seqid); @@ -4983,58 +5209,16 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request) return status; } -int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl) +int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid) { struct nfs_server *server = NFS_SERVER(state->inode); - struct nfs4_exception exception = { }; int err; err = nfs4_set_lock_state(state, fl); if (err != 0) - goto out; - do { - err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); - switch (err) { - default: - printk(KERN_ERR "NFS: %s: unhandled error " - "%d.\n", __func__, err); - case 0: - case -ESTALE: - goto out; - case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_STALE_STATEID: - set_bit(NFS_DELEGATED_STATE, &state->flags); - case -NFS4ERR_EXPIRED: - nfs4_schedule_lease_recovery(server->nfs_client); - err = -EAGAIN; - goto out; - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - case -NFS4ERR_DEADSESSION: - set_bit(NFS_DELEGATED_STATE, &state->flags); - nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); - err = -EAGAIN; - goto out; - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_OPENMODE: - nfs4_schedule_stateid_recovery(server, state); - err = 0; - goto out; - case -ENOMEM: - case -NFS4ERR_DENIED: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ - err = 0; - goto out; - } - set_bit(NFS_DELEGATED_STATE, &state->flags); - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); -out: - return err; + return err; + err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); + return nfs4_handle_delegation_recall_error(server, state, stateid, err); } struct nfs_release_lockowner_data { @@ -5848,7 +6032,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, .rpc_client = clp->cl_rpcclient, .rpc_message = &msg, .callback_ops = &nfs41_sequence_ops, - .flags = RPC_TASK_ASYNC | RPC_TASK_SOFT, + .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT, }; if (!atomic_inc_not_zero(&clp->cl_count)) @@ -6725,6 +6909,10 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = { static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, + .init_caps = NFS_CAP_READDIRPLUS + | NFS_CAP_ATOMIC_OPEN + | NFS_CAP_CHANGE_ATTR + | NFS_CAP_POSIX_LOCK, .call_sync = _nfs4_call_sync, .match_stateid = nfs4_match_stateid, .find_root_sec = nfs4_find_root_sec, @@ -6736,6 +6924,12 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { #if defined(CONFIG_NFS_V4_1) static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .minor_version = 1, + .init_caps = NFS_CAP_READDIRPLUS + | NFS_CAP_ATOMIC_OPEN + | NFS_CAP_CHANGE_ATTR + | NFS_CAP_POSIX_LOCK + | NFS_CAP_STATEID_NFSV41 + | NFS_CAP_ATOMIC_OPEN_V1, .call_sync = nfs4_call_sync_sequence, .match_stateid = nfs41_match_stateid, .find_root_sec = nfs41_find_root_sec, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 6ace365..0b32f94 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -154,18 +154,6 @@ struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp) return cred; } -static void nfs4_clear_machine_cred(struct nfs_client *clp) -{ - struct rpc_cred *cred; - - spin_lock(&clp->cl_lock); - cred = clp->cl_machine_cred; - clp->cl_machine_cred = NULL; - 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) { @@ -699,6 +687,8 @@ __nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner) list_for_each_entry(state, &nfsi->open_states, inode_states) { if (state->owner != owner) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (atomic_inc_not_zero(&state->count)) return state; } @@ -987,13 +977,14 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl) return 0; } -static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state, +static int nfs4_copy_lock_stateid(nfs4_stateid *dst, + struct nfs4_state *state, const struct nfs_lockowner *lockowner) { struct nfs4_lock_state *lsp; fl_owner_t fl_owner; pid_t fl_pid; - bool ret = false; + int ret = -ENOENT; if (lockowner == NULL) @@ -1008,7 +999,10 @@ static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state, 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) { nfs4_stateid_copy(dst, &lsp->ls_stateid); - ret = true; + ret = 0; + smp_rmb(); + if (!list_empty(&lsp->ls_seqid.list)) + ret = -EWOULDBLOCK; } spin_unlock(&state->state_lock); nfs4_put_lock_state(lsp); @@ -1016,28 +1010,44 @@ out: return ret; } -static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) +static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) { + const nfs4_stateid *src; + int ret; int seq; do { + src = &zero_stateid; seq = read_seqbegin(&state->seqlock); - nfs4_stateid_copy(dst, &state->stateid); + if (test_bit(NFS_OPEN_STATE, &state->flags)) + src = &state->open_stateid; + nfs4_stateid_copy(dst, src); + ret = 0; + smp_rmb(); + if (!list_empty(&state->owner->so_seqid.list)) + ret = -EWOULDBLOCK; } while (read_seqretry(&state->seqlock, seq)); + return ret; } /* * Byte-range lock aware utility to initialize the stateid of read/write * requests. */ -void nfs4_select_rw_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; if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) - return; - if (nfs4_copy_lock_stateid(dst, state, lockowner)) - return; - nfs4_copy_open_stateid(dst, state); + goto out; + ret = nfs4_copy_lock_stateid(dst, state, lockowner); + if (ret != -ENOENT) + goto out; + ret = nfs4_copy_open_stateid(dst, state); +out: + if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41)) + dst->seqid = 0; + return ret; } struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask) @@ -1286,14 +1296,17 @@ static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_s return 1; } -void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state) +int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state) { struct nfs_client *clp = server->nfs_client; + if (!nfs4_valid_open_stateid(state)) + return -EBADF; nfs4_state_mark_reclaim_nograce(clp, state); dprintk("%s: scheduling stateid recovery for server %s\n", __func__, clp->cl_hostname); nfs4_schedule_state_manager(clp); + return 0; } EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery); @@ -1323,6 +1336,27 @@ void nfs_inode_find_state_and_recover(struct inode *inode, nfs4_schedule_state_manager(clp); } +static void nfs4_state_mark_open_context_bad(struct nfs4_state *state) +{ + struct inode *inode = state->inode; + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_open_context *ctx; + + spin_lock(&inode->i_lock); + list_for_each_entry(ctx, &nfsi->open_files, list) { + if (ctx->state != state) + continue; + set_bit(NFS_CONTEXT_BAD, &ctx->flags); + } + spin_unlock(&inode->i_lock); +} + +static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error) +{ + set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags); + nfs4_state_mark_open_context_bad(state); +} + static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops) { @@ -1398,6 +1432,8 @@ restart: list_for_each_entry(state, &sp->so_states, open_states) { if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (state->state == 0) continue; atomic_inc(&state->count); @@ -1430,11 +1466,10 @@ restart: * Open state on this file cannot be recovered * All we can do is revert to using the zero stateid. */ - memset(&state->stateid, 0, - sizeof(state->stateid)); - /* Mark the file as being 'closed' */ - state->state = 0; + nfs4_state_mark_recovery_failed(state, status); break; + case -EAGAIN: + ssleep(1); case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_BAD_STATEID: @@ -1696,6 +1731,10 @@ static int nfs4_check_lease(struct nfs_client *clp) } status = ops->renew_lease(clp, cred); put_rpccred(cred); + if (status == -ETIMEDOUT) { + set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + return 0; + } out: return nfs4_recovery_handle_error(clp, status); } @@ -1725,10 +1764,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); return -EPERM; case -EACCES: - if (clp->cl_machine_cred == NULL) - return -EACCES; - /* Handle case where the user hasn't set up machine creds */ - nfs4_clear_machine_cred(clp); case -NFS4ERR_DELAY: case -ETIMEDOUT: case -EAGAIN: @@ -1823,31 +1858,18 @@ int nfs4_discover_server_trunking(struct nfs_client *clp, { const struct nfs4_state_recovery_ops *ops = clp->cl_mvops->reboot_recovery_ops; - rpc_authflavor_t *flavors, flav, save; struct rpc_clnt *clnt; struct rpc_cred *cred; - int i, len, status; + int i, status; dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname); - len = NFS_MAX_SECFLAVORS; - flavors = kcalloc(len, sizeof(*flavors), GFP_KERNEL); - if (flavors == NULL) { - status = -ENOMEM; - goto out; - } - len = rpcauth_list_flavors(flavors, len); - if (len < 0) { - status = len; - goto out_free; - } clnt = clp->cl_rpcclient; - save = clnt->cl_auth->au_flavor; i = 0; mutex_lock(&nfs_clid_init_mutex); - status = -ENOENT; again: + status = -ENOENT; cred = ops->get_clid_cred(clp); if (cred == NULL) goto out_unlock; @@ -1857,12 +1879,6 @@ again: switch (status) { case 0: break; - - case -EACCES: - if (clp->cl_machine_cred == NULL) - break; - /* Handle case where the user hasn't set up machine creds */ - nfs4_clear_machine_cred(clp); case -NFS4ERR_DELAY: case -ETIMEDOUT: case -EAGAIN: @@ -1871,22 +1887,23 @@ again: dprintk("NFS: %s after status %d, retrying\n", __func__, status); goto again; - + case -EACCES: + if (i++) + break; case -NFS4ERR_CLID_INUSE: case -NFS4ERR_WRONGSEC: - status = -EPERM; - if (i >= len) - break; - - flav = flavors[i++]; - if (flav == save) - flav = flavors[i++]; - clnt = rpc_clone_client_set_auth(clnt, flav); + clnt = rpc_clone_client_set_auth(clnt, RPC_AUTH_UNIX); if (IS_ERR(clnt)) { status = PTR_ERR(clnt); break; } - clp->cl_rpcclient = clnt; + /* Note: this is safe because we haven't yet marked the + * client as ready, so we are the only user of + * clp->cl_rpcclient + */ + clnt = xchg(&clp->cl_rpcclient, clnt); + rpc_shutdown_client(clnt); + clnt = clp->cl_rpcclient; goto again; case -NFS4ERR_MINOR_VERS_MISMATCH: @@ -1897,13 +1914,15 @@ again: case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery * in nfs4_exchange_id */ status = -EKEYEXPIRED; + break; + default: + pr_warn("NFS: %s unhandled error %d. Exiting with error EIO\n", + __func__, status); + status = -EIO; } out_unlock: mutex_unlock(&nfs_clid_init_mutex); -out_free: - kfree(flavors); -out: dprintk("NFS: %s: status = %d\n", __func__, status); return status; } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 569b166..a5e1a30 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -252,6 +252,8 @@ 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/nfs4xdr.c b/fs/nfs/nfs4xdr.c index e3edda5..3c79c58 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -530,14 +530,10 @@ static int nfs4_stat_to_errno(int); decode_setclientid_maxsz) #define NFS4_enc_setclientid_confirm_sz \ (compound_encode_hdr_maxsz + \ - encode_setclientid_confirm_maxsz + \ - encode_putrootfh_maxsz + \ - encode_fsinfo_maxsz) + encode_setclientid_confirm_maxsz) #define NFS4_dec_setclientid_confirm_sz \ (compound_decode_hdr_maxsz + \ - decode_setclientid_confirm_maxsz + \ - decode_putrootfh_maxsz + \ - decode_fsinfo_maxsz) + decode_setclientid_confirm_maxsz) #define NFS4_enc_lock_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -1058,8 +1054,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const if (iap->ia_valid & ATTR_ATIME_SET) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(iap->ia_atime.tv_sec); + 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) { @@ -1069,8 +1064,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const if (iap->ia_valid & ATTR_MTIME_SET) { bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(iap->ia_mtime.tv_sec); + 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) { @@ -1366,33 +1360,28 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) { + struct iattr dummy; __be32 *p; - struct nfs_client *clp; p = reserve_space(xdr, 4); - switch(arg->open_flags & O_EXCL) { - case 0: + switch(arg->createmode) { + case NFS4_CREATE_UNCHECKED: *p = cpu_to_be32(NFS4_CREATE_UNCHECKED); encode_attrs(xdr, arg->u.attrs, arg->server); break; - default: - clp = arg->server->nfs_client; - if (clp->cl_mvops->minor_version > 0) { - if (nfs4_has_persistent_session(clp)) { - *p = cpu_to_be32(NFS4_CREATE_GUARDED); - encode_attrs(xdr, arg->u.attrs, arg->server); - } else { - struct iattr dummy; - - *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1); - encode_nfs4_verifier(xdr, &arg->u.verifier); - dummy.ia_valid = 0; - encode_attrs(xdr, &dummy, arg->server); - } - } else { - *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); - encode_nfs4_verifier(xdr, &arg->u.verifier); - } + case NFS4_CREATE_GUARDED: + *p = cpu_to_be32(NFS4_CREATE_GUARDED); + encode_attrs(xdr, arg->u.attrs, arg->server); + break; + case NFS4_CREATE_EXCLUSIVE: + *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); + encode_nfs4_verifier(xdr, &arg->u.verifier); + break; + case NFS4_CREATE_EXCLUSIVE4_1: + *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1); + encode_nfs4_verifier(xdr, &arg->u.verifier); + dummy.ia_valid = 0; + encode_attrs(xdr, &dummy, arg->server); } } @@ -1459,6 +1448,23 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc encode_string(xdr, name->len, name->name); } +static inline void encode_claim_fh(struct xdr_stream *xdr) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_FH); +} + +static inline void encode_claim_delegate_cur_fh(struct xdr_stream *xdr, const nfs4_stateid *stateid) +{ + __be32 *p; + + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_DELEG_CUR_FH); + encode_nfs4_stateid(xdr, stateid); +} + static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_OPEN, decode_open_maxsz, hdr); @@ -1474,6 +1480,12 @@ static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg, case NFS4_OPEN_CLAIM_DELEGATE_CUR: encode_claim_delegate_cur(xdr, arg->name, &arg->u.delegation); break; + case NFS4_OPEN_CLAIM_FH: + encode_claim_fh(xdr); + break; + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + encode_claim_delegate_cur_fh(xdr, &arg->u.delegation); + break; default: BUG(); } @@ -1506,35 +1518,12 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr); } -static void encode_open_stateid(struct xdr_stream *xdr, - const struct nfs_open_context *ctx, - const struct nfs_lock_context *l_ctx, - fmode_t fmode, - int zero_seqid) -{ - nfs4_stateid stateid; - - if (ctx->state != NULL) { - const struct nfs_lockowner *lockowner = NULL; - - if (l_ctx != NULL) - lockowner = &l_ctx->lockowner; - nfs4_select_rw_stateid(&stateid, ctx->state, - fmode, lockowner); - if (zero_seqid) - stateid.seqid = 0; - encode_nfs4_stateid(xdr, &stateid); - } else - encode_nfs4_stateid(xdr, &zero_stateid); -} - static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr) { __be32 *p; encode_op_hdr(xdr, OP_READ, decode_read_maxsz, hdr); - encode_open_stateid(xdr, args->context, args->lock_context, - FMODE_READ, hdr->minorversion); + encode_nfs4_stateid(xdr, &args->stateid); p = reserve_space(xdr, 12); p = xdr_encode_hyper(p, args->offset); @@ -1670,8 +1659,7 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg __be32 *p; encode_op_hdr(xdr, OP_WRITE, decode_write_maxsz, hdr); - encode_open_stateid(xdr, args->context, args->lock_context, - FMODE_WRITE, hdr->minorversion); + encode_nfs4_stateid(xdr, &args->stateid); p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, args->offset); @@ -2609,12 +2597,9 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, struct compound_hdr hdr = { .nops = 0, }; - const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME }; encode_compound_hdr(xdr, req, &hdr); encode_setclientid_confirm(xdr, arg, &hdr); - encode_putrootfh(xdr, &hdr); - encode_fsinfo(xdr, lease_bitmap, &hdr); encode_nops(&hdr); } @@ -3497,8 +3482,11 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) if (n == 0) goto root_path; dprintk("pathname4: "); - path->ncomponents = 0; - while (path->ncomponents < n) { + if (n > NFS4_PATHNAME_MAXCOMPONENTS) { + dprintk("cannot parse %d components in path\n", n); + goto out_eio; + } + for (path->ncomponents = 0; path->ncomponents < n; path->ncomponents++) { struct nfs4_string *component = &path->components[path->ncomponents]; status = decode_opaque_inline(xdr, &component->len, &component->data); if (unlikely(status != 0)) @@ -3507,12 +3495,6 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) pr_cont("%s%.*s ", (path->ncomponents != n ? "/ " : ""), component->len, component->data); - if (path->ncomponents < NFS4_PATHNAME_MAXCOMPONENTS) - path->ncomponents++; - else { - dprintk("cannot parse %d components in path\n", n); - goto out_eio; - } } out: return status; @@ -3557,27 +3539,23 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st n = be32_to_cpup(p); if (n <= 0) goto out_eio; - res->nlocations = 0; - while (res->nlocations < n) { + for (res->nlocations = 0; res->nlocations < n; res->nlocations++) { u32 m; - struct nfs4_fs_location *loc = &res->locations[res->nlocations]; + struct nfs4_fs_location *loc; + if (res->nlocations == NFS4_FS_LOCATIONS_MAXENTRIES) + break; + loc = &res->locations[res->nlocations]; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; m = be32_to_cpup(p); - loc->nservers = 0; dprintk("%s: servers:\n", __func__); - while (loc->nservers < m) { - struct nfs4_string *server = &loc->servers[loc->nservers]; - status = decode_opaque_inline(xdr, &server->len, &server->data); - if (unlikely(status != 0)) - goto out_eio; - dprintk("%s ", server->data); - if (loc->nservers < NFS4_FS_LOCATION_MAXSERVERS) - loc->nservers++; - else { + for (loc->nservers = 0; loc->nservers < m; loc->nservers++) { + struct nfs4_string *server; + + if (loc->nservers == NFS4_FS_LOCATION_MAXSERVERS) { unsigned int i; dprintk("%s: using first %u of %u servers " "returned for location %u\n", @@ -3591,13 +3569,17 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (unlikely(status != 0)) goto out_eio; } + break; } + server = &loc->servers[loc->nservers]; + status = decode_opaque_inline(xdr, &server->len, &server->data); + if (unlikely(status != 0)) + goto out_eio; + dprintk("%s ", server->data); } status = decode_pathname(xdr, &loc->rootpath); if (unlikely(status != 0)) goto out_eio; - if (res->nlocations < NFS4_FS_LOCATIONS_MAXENTRIES) - res->nlocations++; } if (res->nlocations != 0) status = NFS_ATTR_FATTR_V4_LOCATIONS; @@ -5209,27 +5191,30 @@ static int decode_delegreturn(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_DELEGRETURN); } -static int decode_secinfo_gss(struct xdr_stream *xdr, struct nfs4_secinfo_flavor *flavor) +static int decode_secinfo_gss(struct xdr_stream *xdr, + struct nfs4_secinfo4 *flavor) { + u32 oid_len; __be32 *p; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - flavor->gss.sec_oid4.len = be32_to_cpup(p); - if (flavor->gss.sec_oid4.len > GSS_OID_MAX_LEN) + oid_len = be32_to_cpup(p); + if (oid_len > GSS_OID_MAX_LEN) goto out_err; - p = xdr_inline_decode(xdr, flavor->gss.sec_oid4.len); + p = xdr_inline_decode(xdr, oid_len); if (unlikely(!p)) goto out_overflow; - memcpy(flavor->gss.sec_oid4.data, p, flavor->gss.sec_oid4.len); + memcpy(flavor->flavor_info.oid.data, p, oid_len); + flavor->flavor_info.oid.len = oid_len; p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - flavor->gss.qop4 = be32_to_cpup(p++); - flavor->gss.service = be32_to_cpup(p); + flavor->flavor_info.qop = be32_to_cpup(p++); + flavor->flavor_info.service = be32_to_cpup(p); return 0; @@ -5242,10 +5227,10 @@ out_err: static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) { - struct nfs4_secinfo_flavor *sec_flavor; + struct nfs4_secinfo4 *sec_flavor; + unsigned int i, num_flavors; int status; __be32 *p; - int i, num_flavors; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) @@ -6648,8 +6633,7 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, * Decode SETCLIENTID_CONFIRM response */ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, - struct xdr_stream *xdr, - struct nfs_fsinfo *fsinfo) + struct xdr_stream *xdr) { struct compound_hdr hdr; int status; @@ -6657,10 +6641,6 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, status = decode_compound_hdr(xdr, &hdr); if (!status) status = decode_setclientid_confirm(xdr); - if (!status) - status = decode_putrootfh(xdr); - if (!status) - status = decode_fsinfo(xdr, fsinfo); return status; } diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 88f9611..5457745 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -234,7 +234,7 @@ static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags, lseg = kzalloc(lseg_size, gfp_flags); if (unlikely(!lseg)) { - dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__, + dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__, numdevs, lseg_size); return -ENOMEM; } diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h index 880ba08..87aa1de 100644 --- a/fs/nfs/objlayout/objlayout.h +++ b/fs/nfs/objlayout/objlayout.h @@ -114,7 +114,7 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp, gfp_t gfp_flags); extern void objio_free_lseg(struct pnfs_layout_segment *lseg); -/* objio_free_result will free these @oir structs recieved from +/* objio_free_result will free these @oir structs received from * objlayout_{read,write}_done */ extern void objio_free_result(struct objlayout_io_res *oir); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index e56e846..29cfb7a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -84,6 +84,55 @@ nfs_page_free(struct nfs_page *p) kmem_cache_free(nfs_page_cachep, p); } +static void +nfs_iocounter_inc(struct nfs_io_counter *c) +{ + atomic_inc(&c->io_count); +} + +static void +nfs_iocounter_dec(struct nfs_io_counter *c) +{ + if (atomic_dec_and_test(&c->io_count)) { + clear_bit(NFS_IO_INPROGRESS, &c->flags); + smp_mb__after_clear_bit(); + wake_up_bit(&c->flags, NFS_IO_INPROGRESS); + } +} + +static int +__nfs_iocounter_wait(struct nfs_io_counter *c) +{ + wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS); + DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS); + int ret = 0; + + do { + prepare_to_wait(wq, &q.wait, TASK_KILLABLE); + set_bit(NFS_IO_INPROGRESS, &c->flags); + if (atomic_read(&c->io_count) == 0) + break; + ret = nfs_wait_bit_killable(&c->flags); + } while (atomic_read(&c->io_count) != 0); + finish_wait(wq, &q.wait); + return ret; +} + +/** + * nfs_iocounter_wait - wait for i/o to complete + * @c: nfs_io_counter to use + * + * returns -ERESTARTSYS if interrupted by a fatal signal. + * Otherwise returns 0 once the io_count hits 0. + */ +int +nfs_iocounter_wait(struct nfs_io_counter *c) +{ + if (atomic_read(&c->io_count) == 0) + return 0; + return __nfs_iocounter_wait(c); +} + /** * nfs_create_request - Create an NFS read/write request. * @ctx: open context to use @@ -104,6 +153,8 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, struct nfs_page *req; struct nfs_lock_context *l_ctx; + if (test_bit(NFS_CONTEXT_BAD, &ctx->flags)) + return ERR_PTR(-EBADF); /* try to allocate the request struct */ req = nfs_page_alloc(); if (req == NULL) @@ -116,6 +167,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, return ERR_CAST(l_ctx); } req->wb_lock_context = l_ctx; + nfs_iocounter_inc(&l_ctx->io_count); /* Initialize the request struct. Initially, we assume a * long write-back delay. This will be adjusted in @@ -175,6 +227,7 @@ static void nfs_clear_request(struct nfs_page *req) req->wb_page = NULL; } if (l_ctx != NULL) { + nfs_iocounter_dec(&l_ctx->io_count); nfs_put_lock_context(l_ctx); req->wb_lock_context = NULL; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 4bdffe0..c5bd758e 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -718,6 +718,8 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, spin_lock(&lo->plh_inode->i_lock); if (pnfs_layoutgets_blocked(lo, 1)) { status = -EAGAIN; + } else if (!nfs4_valid_open_stateid(open_state)) { + status = -EBADF; } else if (list_empty(&lo->plh_segs)) { int seq; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index a5e5d98..70a26c6 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -514,6 +514,8 @@ 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); } static const struct rpc_call_ops nfs_read_common_ops = { diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2f8a29d..1bb071d 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -920,7 +920,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) data->mount_server.port = NFS_UNSPEC_PORT; data->nfs_server.port = NFS_UNSPEC_PORT; data->nfs_server.protocol = XPRT_TRANSPORT_TCP; - data->auth_flavors[0] = RPC_AUTH_UNIX; + data->auth_flavors[0] = RPC_AUTH_MAXFLAVOR; data->auth_flavor_len = 1; data->minorversion = 0; data->need_mount = true; @@ -1608,49 +1608,57 @@ out_security_failure: } /* - * Match the requested auth flavors with the list returned by - * the server. Returns zero and sets the mount's authentication - * flavor on success; returns -EACCES if server does not support - * the requested flavor. + * Select a security flavor for this mount. The selected flavor + * is planted in args->auth_flavors[0]. */ -static int nfs_walk_authlist(struct nfs_parsed_mount_data *args, - struct nfs_mount_request *request) +static void nfs_select_flavor(struct nfs_parsed_mount_data *args, + struct nfs_mount_request *request) { - unsigned int i, j, server_authlist_len = *(request->auth_flav_len); + unsigned int i, count = *(request->auth_flav_len); + rpc_authflavor_t flavor; + + if (args->auth_flavors[0] != RPC_AUTH_MAXFLAVOR) + goto out; + + /* + * The NFSv2 MNT operation does not return a flavor list. + */ + if (args->mount_server.version != NFS_MNT3_VERSION) + goto out_default; /* * Certain releases of Linux's mountd return an empty - * flavor list. To prevent behavioral regression with - * these servers (ie. rejecting mounts that used to - * succeed), revert to pre-2.6.32 behavior (no checking) - * if the returned flavor list is empty. + * flavor list in some cases. */ - if (server_authlist_len == 0) - return 0; + if (count == 0) + goto out_default; /* - * We avoid sophisticated negotiating here, as there are - * plenty of cases where we can get it wrong, providing - * either too little or too much security. - * * RFC 2623, section 2.7 suggests we SHOULD prefer the * flavor listed first. However, some servers list - * AUTH_NULL first. Our caller plants AUTH_SYS, the - * preferred default, in args->auth_flavors[0] if user - * didn't specify sec= mount option. + * AUTH_NULL first. Avoid ever choosing AUTH_NULL. */ - for (i = 0; i < args->auth_flavor_len; i++) - for (j = 0; j < server_authlist_len; j++) - if (args->auth_flavors[i] == request->auth_flavs[j]) { - dfprintk(MOUNT, "NFS: using auth flavor %d\n", - request->auth_flavs[j]); - args->auth_flavors[0] = request->auth_flavs[j]; - return 0; - } + for (i = 0; i < count; i++) { + struct rpcsec_gss_info info; + + flavor = request->auth_flavs[i]; + switch (flavor) { + case RPC_AUTH_UNIX: + goto out_set; + case RPC_AUTH_NULL: + continue; + default: + if (rpcauth_get_gssinfo(flavor, &info) == 0) + goto out_set; + } + } - dfprintk(MOUNT, "NFS: server does not support requested auth flavor\n"); - nfs_umount(request); - return -EACCES; +out_default: + flavor = RPC_AUTH_UNIX; +out_set: + args->auth_flavors[0] = flavor; +out: + dfprintk(MOUNT, "NFS: using auth flavor %d\n", args->auth_flavors[0]); } /* @@ -1713,12 +1721,8 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args, return status; } - /* - * MNTv1 (NFSv2) does not support auth flavor negotiation. - */ - if (args->mount_server.version != NFS_MNT3_VERSION) - return 0; - return nfs_walk_authlist(args, &request); + nfs_select_flavor(args, &request); + return 0; } struct dentry *nfs_try_mount(int flags, const char *dev_name, @@ -2381,10 +2385,9 @@ int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, struct nfs_mount_info *mount_info) { /* clone any lsm security options from the parent to the new sb */ - security_sb_clone_mnt_opts(mount_info->cloned->sb, s); if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) return -ESTALE; - return 0; + return security_sb_clone_mnt_opts(mount_info->cloned->sb, s); } EXPORT_SYMBOL_GPL(nfs_clone_sb_security); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index c483cc5..a2c7c28 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1251,6 +1251,8 @@ 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); } void nfs_commit_prepare(struct rpc_task *task, void *calldata) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2e27430..417c848 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -234,7 +234,6 @@ static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab) { struct idr *stateids = &cl->cl_stateids; - static int min_stateid = 0; struct nfs4_stid *stid; int new_id; @@ -242,7 +241,7 @@ kmem_cache *slab) if (!stid) return NULL; - new_id = idr_alloc(stateids, stid, min_stateid, 0, GFP_KERNEL); + new_id = idr_alloc_cyclic(stateids, stid, 0, 0, GFP_KERNEL); if (new_id < 0) goto out_free; stid->sc_client = cl; @@ -261,10 +260,6 @@ kmem_cache *slab) * amount of time until an id is reused, by ensuring they always * "increase" (mod INT_MAX): */ - - min_stateid = new_id+1; - if (min_stateid == INT_MAX) - min_stateid = 0; return stid; out_free: kfree(stid); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 0116886..2502951 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -264,7 +264,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, iattr->ia_valid |= ATTR_SIZE; } if (bmval[0] & FATTR4_WORD0_ACL) { - int nace; + u32 nace; struct nfs4_ace *ace; READ_BUF(4); len += 4; @@ -3138,10 +3138,9 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ static __be32 nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, - __be32 nfserr,struct svc_export *exp) + __be32 nfserr, struct svc_export *exp) { - int i = 0; - u32 nflavs; + u32 i, nflavs; struct exp_flavor_info *flavs; struct exp_flavor_info def_flavs[2]; __be32 *p; @@ -3172,30 +3171,29 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp, WRITE32(nflavs); ADJUST_ARGS(); for (i = 0; i < nflavs; i++) { - u32 flav = flavs[i].pseudoflavor; - struct gss_api_mech *gm = gss_mech_get_by_pseudoflavor(flav); + struct rpcsec_gss_info info; - if (gm) { + if (rpcauth_get_gssinfo(flavs[i].pseudoflavor, &info) == 0) { RESERVE_SPACE(4); WRITE32(RPC_AUTH_GSS); ADJUST_ARGS(); - RESERVE_SPACE(4 + gm->gm_oid.len); - WRITE32(gm->gm_oid.len); - WRITEMEM(gm->gm_oid.data, gm->gm_oid.len); + RESERVE_SPACE(4 + info.oid.len); + WRITE32(info.oid.len); + WRITEMEM(info.oid.data, info.oid.len); ADJUST_ARGS(); RESERVE_SPACE(4); - WRITE32(0); /* qop */ + WRITE32(info.qop); ADJUST_ARGS(); RESERVE_SPACE(4); - WRITE32(gss_pseudoflavor_to_service(gm, flav)); + WRITE32(info.service); ADJUST_ARGS(); - gss_mech_put(gm); } else { RESERVE_SPACE(4); - WRITE32(flav); + WRITE32(flavs[i].pseudoflavor); ADJUST_ARGS(); } } + out: if (exp) exp_put(exp); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6b49f14..cf02f55 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -175,6 +175,11 @@ static int nilfs_writepages(struct address_space *mapping, struct inode *inode = mapping->host; int err = 0; + if (inode->i_sb->s_flags & MS_RDONLY) { + nilfs_clear_dirty_pages(mapping, false); + return -EROFS; + } + if (wbc->sync_mode == WB_SYNC_ALL) err = nilfs_construct_dsync_segment(inode->i_sb, inode, wbc->range_start, @@ -187,6 +192,18 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = page->mapping->host; int err; + if (inode->i_sb->s_flags & MS_RDONLY) { + /* + * It means that filesystem was remounted in read-only + * mode because of error or metadata corruption. But we + * have dirty pages that try to be flushed in background. + * So, here we simply discard this dirty page. + */ + nilfs_clear_dirty_page(page, false); + unlock_page(page); + return -EROFS; + } + redirty_page_for_writepage(wbc, page); unlock_page(page); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index f9897d0..c4dcd1d 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -375,14 +375,25 @@ int nilfs_mdt_fetch_dirty(struct inode *inode) static int nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) { - struct inode *inode; + struct inode *inode = page->mapping->host; struct super_block *sb; int err = 0; + if (inode && (inode->i_sb->s_flags & MS_RDONLY)) { + /* + * It means that filesystem was remounted in read-only + * mode because of error or metadata corruption. But we + * have dirty pages that try to be flushed in background. + * So, here we simply discard this dirty page. + */ + nilfs_clear_dirty_page(page, false); + unlock_page(page); + return -EROFS; + } + redirty_page_for_writepage(wbc, page); unlock_page(page); - inode = page->mapping->host; if (!inode) return 0; @@ -561,10 +572,10 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) if (mi->mi_palloc_cache) nilfs_palloc_clear_cache(inode); - nilfs_clear_dirty_pages(inode->i_mapping); + nilfs_clear_dirty_pages(inode->i_mapping, true); nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data); - nilfs_clear_dirty_pages(&ii->i_btnode_cache); + nilfs_clear_dirty_pages(&ii->i_btnode_cache, true); nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes); nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 07f76db..0ba6798 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -370,7 +370,12 @@ repeat: goto repeat; } -void nilfs_clear_dirty_pages(struct address_space *mapping) +/** + * nilfs_clear_dirty_pages - discard dirty pages in address space + * @mapping: address space with dirty pages for discarding + * @silent: suppress [true] or print [false] warning messages + */ +void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) { struct pagevec pvec; unsigned int i; @@ -382,25 +387,9 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) PAGEVEC_SIZE)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - struct buffer_head *bh, *head; lock_page(page); - ClearPageUptodate(page); - ClearPageMappedToDisk(page); - bh = head = page_buffers(page); - do { - lock_buffer(bh); - clear_buffer_dirty(bh); - clear_buffer_nilfs_volatile(bh); - clear_buffer_nilfs_checked(bh); - clear_buffer_nilfs_redirected(bh); - clear_buffer_uptodate(bh); - clear_buffer_mapped(bh); - unlock_buffer(bh); - bh = bh->b_this_page; - } while (bh != head); - - __nilfs_clear_page_dirty(page); + nilfs_clear_dirty_page(page, silent); unlock_page(page); } pagevec_release(&pvec); @@ -408,6 +397,51 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) } } +/** + * nilfs_clear_dirty_page - discard dirty page + * @page: dirty page that will be discarded + * @silent: suppress [true] or print [false] warning messages + */ +void nilfs_clear_dirty_page(struct page *page, bool silent) +{ + struct inode *inode = page->mapping->host; + struct super_block *sb = inode->i_sb; + + BUG_ON(!PageLocked(page)); + + if (!silent) { + nilfs_warning(sb, __func__, + "discard page: offset %lld, ino %lu", + page_offset(page), inode->i_ino); + } + + ClearPageUptodate(page); + ClearPageMappedToDisk(page); + + if (page_has_buffers(page)) { + struct buffer_head *bh, *head; + + bh = head = page_buffers(page); + do { + lock_buffer(bh); + if (!silent) { + nilfs_warning(sb, __func__, + "discard block %llu, size %zu", + (u64)bh->b_blocknr, bh->b_size); + } + clear_buffer_dirty(bh); + clear_buffer_nilfs_volatile(bh); + clear_buffer_nilfs_checked(bh); + clear_buffer_nilfs_redirected(bh); + clear_buffer_uptodate(bh); + clear_buffer_mapped(bh); + unlock_buffer(bh); + } while (bh = bh->b_this_page, bh != head); + } + + __nilfs_clear_page_dirty(page); +} + unsigned nilfs_page_count_clean_buffers(struct page *page, unsigned from, unsigned to) { diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index fb7de71..ef30c5c 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -55,7 +55,8 @@ void nilfs_page_bug(struct page *); int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); -void nilfs_clear_dirty_pages(struct address_space *); +void nilfs_clear_dirty_page(struct page *, bool); +void nilfs_clear_dirty_pages(struct address_space *, bool); void nilfs_mapping_init(struct address_space *mapping, struct inode *inode, struct backing_dev_info *bdi); unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 5d84442..d0be29f 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -755,9 +755,9 @@ out_destroy_group: return fd; } -SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags, - __u64 mask, int dfd, - const char __user * pathname) +SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, + __u64, mask, int, dfd, + const char __user *, pathname) { struct inode *inode = NULL; struct vfsmount *mnt = NULL; @@ -857,17 +857,6 @@ fput_and_out: return ret; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_fanotify_mark(long fanotify_fd, long flags, __u64 mask, - long dfd, long pathname) -{ - return SYSC_fanotify_mark((int) fanotify_fd, (unsigned int) flags, - mask, (int) dfd, - (const char __user *) pathname); -} -SYSCALL_ALIAS(sys_fanotify_mark, SyS_fanotify_mark); -#endif - /* * fanotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 1db6d886..959815c 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -356,7 +356,6 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns } static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock, - int *last_wd, struct inotify_inode_mark *i_mark) { int ret; @@ -364,11 +363,10 @@ static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock, idr_preload(GFP_KERNEL); spin_lock(idr_lock); - ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT); + ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT); if (ret >= 0) { /* we added the mark to the idr, take a reference */ i_mark->wd = ret; - *last_wd = i_mark->wd; fsnotify_get_mark(&i_mark->fsn_mark); } @@ -569,7 +567,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, int add = (arg & IN_MASK_ADD); int ret; - /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); fsn_mark = fsnotify_find_inode_mark(group, inode); @@ -620,7 +617,6 @@ static int inotify_new_watch(struct fsnotify_group *group, struct idr *idr = &group->inotify_data.idr; spinlock_t *idr_lock = &group->inotify_data.idr_lock; - /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL); @@ -635,8 +631,7 @@ static int inotify_new_watch(struct fsnotify_group *group, if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches) goto out_err; - ret = inotify_add_to_idr(idr, idr_lock, &group->inotify_data.last_wd, - tmp_i_mark); + ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark); if (ret) goto out_err; @@ -694,7 +689,6 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) spin_lock_init(&group->inotify_data.idr_lock); idr_init(&group->inotify_data.idr); - group->inotify_data.last_wd = 0; group->inotify_data.user = get_current_user(); if (atomic_inc_return(&group->inotify_data.user->inotify_devs) > @@ -748,6 +742,10 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, int ret; unsigned flags = 0; + /* don't allow invalid bits: we don't want flags set */ + if (unlikely(!(mask & ALL_INOTIFY_BITS))) + return -EINVAL; + f = fdget(fd); if (unlikely(!f.file)) return -EBADF; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index eeac97b..b3fdd1a 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1498,10 +1498,8 @@ leave: dlm_put(dlm); if (ret < 0) { - if (buf) - kfree(buf); - if (item) - kfree(item); + kfree(buf); + kfree(item); mlog_errno(ret); } diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 752f0b2..0c60ef2 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -101,13 +101,6 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, if (!S_ISDIR(inode->i_mode)) flags &= ~OCFS2_DIRSYNC_FL; - handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto bail_unlock; - } - oldflags = ocfs2_inode->ip_attr; flags = flags & mask; flags |= oldflags & ~mask; @@ -120,7 +113,14 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) & (OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) { if (!capable(CAP_LINUX_IMMUTABLE)) - goto bail_commit; + goto bail_unlock; + } + + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + status = PTR_ERR(handle); + mlog_errno(status); + goto bail_unlock; } ocfs2_inode->ip_attr = flags; @@ -130,8 +130,8 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, if (status < 0) mlog_errno(status); -bail_commit: ocfs2_commit_trans(osb, handle); + bail_unlock: ocfs2_inode_unlock(inode, 1); bail: @@ -706,8 +706,10 @@ int ocfs2_info_handle_freefrag(struct inode *inode, o2info_set_request_filled(&oiff->iff_req); - if (o2info_to_user(*oiff, req)) + if (o2info_to_user(*oiff, req)) { + status = -EFAULT; goto bail; + } status = 0; bail: diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 9f8dcad..f1fc172 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -471,7 +471,7 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode, int ret, goal_bit = 0; struct buffer_head *gd_bh = NULL; - struct ocfs2_group_desc *bg = NULL; + struct ocfs2_group_desc *bg; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int c_to_b = 1 << (osb->s_clustersize_bits - inode->i_sb->s_blocksize_bits); @@ -482,13 +482,6 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode, range->me_goal = ocfs2_block_to_cluster_start(inode->i_sb, range->me_goal); /* - * moving goal is not allowd to start with a group desc blok(#0 blk) - * let's compromise to the latter cluster. - */ - if (range->me_goal == le64_to_cpu(bg->bg_blkno)) - range->me_goal += c_to_b; - - /* * validate goal sits within global_bitmap, and return the victim * group desc */ @@ -502,6 +495,13 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode, bg = (struct ocfs2_group_desc *)gd_bh->b_data; /* + * moving goal is not allowd to start with a group desc blok(#0 blk) + * let's compromise to the latter cluster. + */ + if (range->me_goal == le64_to_cpu(bg->bg_blkno)) + range->me_goal += c_to_b; + + /* * movement is not gonna cross two groups. */ if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize < @@ -1057,42 +1057,40 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) struct inode *inode = file_inode(filp); struct ocfs2_move_extents range; - struct ocfs2_move_extents_context *context = NULL; + struct ocfs2_move_extents_context *context; + + if (!argp) + return -EINVAL; status = mnt_want_write_file(filp); if (status) return status; if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE)) - goto out; + goto out_drop; if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) { status = -EPERM; - goto out; + goto out_drop; } context = kzalloc(sizeof(struct ocfs2_move_extents_context), GFP_NOFS); if (!context) { status = -ENOMEM; mlog_errno(status); - goto out; + goto out_drop; } context->inode = inode; context->file = filp; - if (argp) { - if (copy_from_user(&range, argp, sizeof(range))) { - status = -EFAULT; - goto out; - } - } else { - status = -EINVAL; - goto out; + if (copy_from_user(&range, argp, sizeof(range))) { + status = -EFAULT; + goto out_free; } if (range.me_start > i_size_read(inode)) - goto out; + goto out_free; if (range.me_start + range.me_len > i_size_read(inode)) range.me_len = i_size_read(inode) - range.me_start; @@ -1124,25 +1122,24 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) status = ocfs2_validate_and_adjust_move_goal(inode, &range); if (status) - goto out; + goto out_copy; } status = ocfs2_move_extents(context); if (status) mlog_errno(status); -out: +out_copy: /* * movement/defragmentation may end up being partially completed, * that's the reason why we need to return userspace the finished * length and new_offset even if failure happens somewhere. */ - if (argp) { - if (copy_to_user(argp, &range, sizeof(range))) - status = -EFAULT; - } + if (copy_to_user(argp, &range, sizeof(range))) + status = -EFAULT; +out_free: kfree(context); - +out_drop: mnt_drop_write_file(filp); return status; @@ -197,10 +197,7 @@ out: SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length) { - long ret = do_sys_ftruncate(fd, length, 1); - /* avoid REGPARM breakage on x86: */ - asmlinkage_protect(2, ret, fd, length); - return ret; + return do_sys_ftruncate(fd, length, 1); } #ifdef CONFIG_COMPAT @@ -212,32 +209,15 @@ COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length) /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 -SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length) +SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return do_sys_truncate(path, length); } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_truncate64(long path, loff_t length) -{ - return SYSC_truncate64((const char __user *) path, length); -} -SYSCALL_ALIAS(sys_truncate64, SyS_truncate64); -#endif -SYSCALL_DEFINE(ftruncate64)(unsigned int fd, loff_t length) +SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { - long ret = do_sys_ftruncate(fd, length, 0); - /* avoid REGPARM breakage on x86: */ - asmlinkage_protect(2, ret, fd, length); - return ret; -} -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_ftruncate64(long fd, loff_t length) -{ - return SYSC_ftruncate64((unsigned int) fd, length); + return do_sys_ftruncate(fd, length, 0); } -SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64); -#endif #endif /* BITS_PER_LONG == 32 */ @@ -299,7 +279,7 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return ret; } -SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) +SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { struct fd f = fdget(fd); int error = -EBADF; @@ -311,14 +291,6 @@ SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) return error; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len) -{ - return SYSC_fallocate((int)fd, (int)mode, offset, len); -} -SYSCALL_ALIAS(sys_fallocate, SyS_fallocate); -#endif - /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and @@ -983,29 +955,19 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { - long ret; - if (force_o_largefile()) flags |= O_LARGEFILE; - ret = do_sys_open(AT_FDCWD, filename, flags, mode); - /* avoid REGPARM breakage on x86: */ - asmlinkage_protect(3, ret, filename, flags, mode); - return ret; + return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { - long ret; - if (force_o_largefile()) flags |= O_LARGEFILE; - ret = do_sys_open(dfd, filename, flags, mode); - /* avoid REGPARM breakage on x86: */ - asmlinkage_protect(4, ret, dfd, filename, flags, mode); - return ret; + return do_sys_open(dfd, filename, flags, mode); } #ifndef __alpha__ @@ -9,6 +9,7 @@ #include <linux/mnt_namespace.h> #include <linux/mount.h> #include <linux/fs.h> +#include <linux/nsproxy.h> #include "internal.h" #include "pnode.h" @@ -220,6 +221,7 @@ static struct mount *get_source(struct mount *dest, int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, struct mount *source_mnt, struct list_head *tree_list) { + struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mount *m, *child; int ret = 0; struct mount *prev_dest_mnt = dest_mnt; @@ -236,6 +238,10 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, source = get_source(m, prev_dest_mnt, prev_src_mnt, &type); + /* Notice when we are propagating across user namespaces */ + if (m->mnt_ns->user_ns != user_ns) + type |= CL_UNPRIVILEGED; + child = copy_tree(source, source->mnt.mnt_root, type); if (IS_ERR(child)) { ret = PTR_ERR(child); @@ -23,6 +23,7 @@ #define CL_MAKE_SHARED 0x08 #define CL_PRIVATE 0x10 #define CL_SHARED_TO_SLAVE 0x20 +#define CL_UNPRIVILEGED 0x40 static inline void set_mnt_shared(struct mount *mnt) { diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 712f24d..ab30716 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -5,7 +5,7 @@ obj-y += proc.o proc-y := nommu.o task_nommu.o -proc-$(CONFIG_MMU) := mmu.o task_mmu.o +proc-$(CONFIG_MMU) := task_mmu.o proc-y += inode.o root.o base.o generic.o array.o \ fd.o diff --git a/fs/proc/array.c b/fs/proc/array.c index f7ed9ee..cbd0f1b 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -143,6 +143,7 @@ static const char * const task_state_array[] = { "x (dead)", /* 64 */ "K (wakekill)", /* 128 */ "W (waking)", /* 256 */ + "P (parked)", /* 512 */ }; static inline const char *get_task_state(struct task_struct *tsk) diff --git a/fs/proc/base.c b/fs/proc/base.c index 8281986..dd51e50 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -86,6 +86,7 @@ #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/flex_array.h> +#include <linux/posix-timers.h> #ifdef CONFIG_HARDWALL #include <asm/hardwall.h> #endif @@ -1378,11 +1379,10 @@ static ssize_t comm_write(struct file *file, const char __user *buf, struct inode *inode = file_inode(file); struct task_struct *p; char buffer[TASK_COMM_LEN]; + const size_t maxlen = sizeof(buffer) - 1; memset(buffer, 0, sizeof(buffer)); - if (count > sizeof(buffer) - 1) - count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) + if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) return -EFAULT; p = get_proc_task(inode); @@ -2053,6 +2053,102 @@ static const struct file_operations proc_map_files_operations = { .llseek = default_llseek, }; +struct timers_private { + struct pid *pid; + struct task_struct *task; + struct sighand_struct *sighand; + struct pid_namespace *ns; + unsigned long flags; +}; + +static void *timers_start(struct seq_file *m, loff_t *pos) +{ + struct timers_private *tp = m->private; + + tp->task = get_pid_task(tp->pid, PIDTYPE_PID); + if (!tp->task) + return ERR_PTR(-ESRCH); + + tp->sighand = lock_task_sighand(tp->task, &tp->flags); + if (!tp->sighand) + return ERR_PTR(-ESRCH); + + return seq_list_start(&tp->task->signal->posix_timers, *pos); +} + +static void *timers_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct timers_private *tp = m->private; + return seq_list_next(v, &tp->task->signal->posix_timers, pos); +} + +static void timers_stop(struct seq_file *m, void *v) +{ + struct timers_private *tp = m->private; + + if (tp->sighand) { + unlock_task_sighand(tp->task, &tp->flags); + tp->sighand = NULL; + } + + if (tp->task) { + put_task_struct(tp->task); + tp->task = NULL; + } +} + +static int show_timer(struct seq_file *m, void *v) +{ + struct k_itimer *timer; + struct timers_private *tp = m->private; + int notify; + static char *nstr[] = { + [SIGEV_SIGNAL] = "signal", + [SIGEV_NONE] = "none", + [SIGEV_THREAD] = "thread", + }; + + timer = list_entry((struct list_head *)v, struct k_itimer, list); + notify = timer->it_sigev_notify; + + seq_printf(m, "ID: %d\n", timer->it_id); + seq_printf(m, "signal: %d/%p\n", timer->sigq->info.si_signo, + timer->sigq->info.si_value.sival_ptr); + seq_printf(m, "notify: %s/%s.%d\n", + nstr[notify & ~SIGEV_THREAD_ID], + (notify & SIGEV_THREAD_ID) ? "tid" : "pid", + pid_nr_ns(timer->it_pid, tp->ns)); + + return 0; +} + +static const struct seq_operations proc_timers_seq_ops = { + .start = timers_start, + .next = timers_next, + .stop = timers_stop, + .show = show_timer, +}; + +static int proc_timers_open(struct inode *inode, struct file *file) +{ + struct timers_private *tp; + + tp = __seq_open_private(file, &proc_timers_seq_ops, + sizeof(struct timers_private)); + if (!tp) + return -ENOMEM; + + tp->pid = proc_pid(inode); + tp->ns = inode->i_sb->s_fs_info; + return 0; +} + +static const struct file_operations proc_timers_operations = { + .open = proc_timers_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; #endif /* CONFIG_CHECKPOINT_RESTORE */ static struct dentry *proc_pident_instantiate(struct inode *dir, @@ -2623,6 +2719,9 @@ static const struct pid_entry tgid_base_stuff[] = { REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), #endif +#ifdef CONFIG_CHECKPOINT_RESTORE + REG("timers", S_IRUGO, proc_timers_operations), +#endif }; static int proc_tgid_base_readdir(struct file * filp, diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 04255b6..d600fb0 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -211,27 +211,6 @@ extern int proc_fill_super(struct super_block *); extern void proc_entry_rundown(struct proc_dir_entry *); /* - * mmu.c - */ -struct vmalloc_info { - unsigned long used; - unsigned long largest_chunk; -}; - -#ifdef CONFIG_MMU -#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) -extern void get_vmalloc_info(struct vmalloc_info *); - -#else -#define VMALLOC_TOTAL 0UL -static inline void get_vmalloc_info(struct vmalloc_info *vmi) -{ - vmi->used = 0; - vmi->largest_chunk = 0; -} -#endif - -/* * proc_devtree.c */ #ifdef CONFIG_PROC_DEVICETREE diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 13cf87c..0a22194 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -16,6 +16,7 @@ #include <linux/capability.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/notifier.h> #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/printk.h> @@ -566,7 +567,6 @@ static const struct file_operations proc_kcore_operations = { .llseek = default_llseek, }; -#ifdef CONFIG_MEMORY_HOTPLUG /* just remember that we have to update kcore */ static int __meminit kcore_callback(struct notifier_block *self, unsigned long action, void *arg) @@ -580,8 +580,11 @@ static int __meminit kcore_callback(struct notifier_block *self, } return NOTIFY_OK; } -#endif +static struct notifier_block kcore_callback_nb __meminitdata = { + .notifier_call = kcore_callback, + .priority = 0, +}; static struct kcore_list kcore_vmalloc; @@ -633,7 +636,7 @@ static int __init proc_kcore_init(void) add_modules_range(); /* Store direct-map area from physical memory map */ kcore_update_ram(); - hotplug_memory_notifier(kcore_callback, 0); + register_hotmemory_notifier(&kcore_callback_nb); return 0; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 1efaaa1..5aa847a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -11,6 +11,7 @@ #include <linux/swap.h> #include <linux/vmstat.h> #include <linux/atomic.h> +#include <linux/vmalloc.h> #include <asm/page.h> #include <asm/pgtable.h> #include "internal.h" diff --git a/fs/proc/mmu.c b/fs/proc/mmu.c deleted file mode 100644 index 8ae221d..0000000 --- a/fs/proc/mmu.c +++ /dev/null @@ -1,60 +0,0 @@ -/* mmu.c: mmu memory info files - * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * 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. - */ -#include <linux/spinlock.h> -#include <linux/vmalloc.h> -#include <linux/highmem.h> -#include <asm/pgtable.h> -#include "internal.h" - -void get_vmalloc_info(struct vmalloc_info *vmi) -{ - struct vm_struct *vma; - unsigned long free_area_size; - unsigned long prev_end; - - vmi->used = 0; - - if (!vmlist) { - vmi->largest_chunk = VMALLOC_TOTAL; - } - else { - vmi->largest_chunk = 0; - - prev_end = VMALLOC_START; - - read_lock(&vmlist_lock); - - for (vma = vmlist; vma; vma = vma->next) { - unsigned long addr = (unsigned long) vma->addr; - - /* - * Some archs keep another range for modules in vmlist - */ - if (addr < VMALLOC_START) - continue; - if (addr >= VMALLOC_END) - break; - - vmi->used += vma->size; - - free_area_size = addr - prev_end; - if (vmi->largest_chunk < free_area_size) - vmi->largest_chunk = free_area_size; - - prev_end = vma->size + addr; - } - - if (VMALLOC_END - prev_end > vmi->largest_chunk) - vmi->largest_chunk = VMALLOC_END - prev_end; - - read_unlock(&vmlist_lock); - } -} diff --git a/fs/proc/root.c b/fs/proc/root.c index 20834b3..41a6ea9 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -16,6 +16,7 @@ #include <linux/sched.h> #include <linux/module.h> #include <linux/bitops.h> +#include <linux/user_namespace.h> #include <linux/mount.h> #include <linux/pid_namespace.h> #include <linux/parser.h> @@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, } else { ns = task_active_pid_ns(current); options = data; + + if (!current_user_ns()->may_mount_proc) + return ERR_PTR(-EPERM); } sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns); diff --git a/fs/read_write.c b/fs/read_write.c index a1f4d44..605dbbc 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -128,7 +128,7 @@ EXPORT_SYMBOL(generic_file_llseek_size); * * This is a generic implemenation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by - * @offset and @whence under i_mutex. + * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { @@ -424,6 +424,9 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t const char __user *p; ssize_t ret; + if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write)) + return -EINVAL; + old_fs = get_fs(); set_fs(get_ds()); p = (__force const char __user *)buf; @@ -514,8 +517,8 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, return ret; } -SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf, - size_t count, loff_t pos) +SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, + size_t, count, loff_t, pos) { struct fd f; ssize_t ret = -EBADF; @@ -533,17 +536,9 @@ SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf, return ret; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos) -{ - return SYSC_pread64((unsigned int) fd, (char __user *) buf, - (size_t) count, pos); -} -SYSCALL_ALIAS(sys_pread64, SyS_pread64); -#endif -SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf, - size_t count, loff_t pos) +SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, + size_t, count, loff_t, pos) { struct fd f; ssize_t ret = -EBADF; @@ -561,14 +556,6 @@ SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf, return ret; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos) -{ - return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf, - (size_t) count, pos); -} -SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64); -#endif /* * Reduce an iovec's length in-place. Return the resulting number of segments @@ -1095,8 +1082,8 @@ COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd, } #endif -ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, - loff_t max) +static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, + size_t count, loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; @@ -1220,3 +1207,43 @@ SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, si return do_sendfile(out_fd, in_fd, NULL, count, 0); } + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, + compat_off_t __user *, offset, compat_size_t, count) +{ + loff_t pos; + off_t off; + ssize_t ret; + + if (offset) { + if (unlikely(get_user(off, offset))) + return -EFAULT; + pos = off; + ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); + if (unlikely(put_user(pos, offset))) + return -EFAULT; + return ret; + } + + return do_sendfile(out_fd, in_fd, NULL, count, 0); +} + +COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, + compat_loff_t __user *, offset, compat_size_t, count) +{ + loff_t pos; + ssize_t ret; + + if (offset) { + if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) + return -EFAULT; + ret = do_sendfile(out_fd, in_fd, &pos, count, 0); + if (unlikely(put_user(pos, offset))) + return -EFAULT; + return ret; + } + + return do_sendfile(out_fd, in_fd, NULL, count, 0); +} +#endif diff --git a/fs/read_write.h b/fs/read_write.h index b987806..0ec530d 100644 --- a/fs/read_write.h +++ b/fs/read_write.h @@ -7,6 +7,3 @@ typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *, unsigned long, loff_t); - -ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, - loff_t max); diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index c196369..4cce1d9 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -187,8 +187,8 @@ fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset, if (dbuf->count == ARRAY_SIZE(dbuf->dentries)) return -ENOSPC; - if (name[0] == '.' && (name[1] == '\0' || - (name[1] == '.' && name[2] == '\0'))) + if (name[0] == '.' && (namelen < 2 || + (namelen == 2 && name[1] == '.'))) return 0; dentry = lookup_one_len(name, dbuf->xadir, namelen); diff --git a/fs/signalfd.c b/fs/signalfd.c index b534869..424b7b6 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -30,6 +30,7 @@ #include <linux/signalfd.h> #include <linux/syscalls.h> #include <linux/proc_fs.h> +#include <linux/compat.h> void signalfd_cleanup(struct sighand_struct *sighand) { @@ -311,3 +312,33 @@ SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask, { return sys_signalfd4(ufd, user_mask, sizemask, 0); } + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd, + const compat_sigset_t __user *,sigmask, + compat_size_t, sigsetsize, + int, flags) +{ + compat_sigset_t ss32; + sigset_t tmp; + sigset_t __user *ksigmask; + + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&tmp, &ss32); + ksigmask = compat_alloc_user_space(sizeof(sigset_t)); + if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t))) + return -EFAULT; + + return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); +} + +COMPAT_SYSCALL_DEFINE3(signalfd, int, ufd, + const compat_sigset_t __user *,sigmask, + compat_size_t, sigsetsize) +{ + return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0); +} +#endif diff --git a/fs/splice.c b/fs/splice.c index 45e645b..e6b2559 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -31,6 +31,7 @@ #include <linux/security.h> #include <linux/gfp.h> #include <linux/socket.h> +#include <linux/compat.h> #include "internal.h" /* @@ -1690,6 +1691,27 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, return error; } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32, + unsigned int, nr_segs, unsigned int, flags) +{ + unsigned i; + struct iovec __user *iov; + if (nr_segs > UIO_MAXIOV) + return -EINVAL; + iov = compat_alloc_user_space(nr_segs * sizeof(struct iovec)); + for (i = 0; i < nr_segs; i++) { + struct compat_iovec v; + if (get_user(v.iov_base, &iov32[i].iov_base) || + get_user(v.iov_len, &iov32[i].iov_len) || + put_user(compat_ptr(v.iov_base), &iov[i].iov_base) || + put_user(v.iov_len, &iov[i].iov_len)) + return -EFAULT; + } + return sys_vmsplice(fd, iov, nr_segs, flags); +} +#endif + SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) @@ -283,8 +283,8 @@ EXPORT_SYMBOL(generic_write_sync); * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ -SYSCALL_DEFINE(sync_file_range)(int fd, loff_t offset, loff_t nbytes, - unsigned int flags) +SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, + unsigned int, flags) { int ret; struct fd f; @@ -365,29 +365,11 @@ out_put: out: return ret; } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_sync_file_range(long fd, loff_t offset, loff_t nbytes, - long flags) -{ - return SYSC_sync_file_range((int) fd, offset, nbytes, - (unsigned int) flags); -} -SYSCALL_ALIAS(sys_sync_file_range, SyS_sync_file_range); -#endif /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ -SYSCALL_DEFINE(sync_file_range2)(int fd, unsigned int flags, - loff_t offset, loff_t nbytes) +SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags, + loff_t, offset, loff_t, nbytes) { return sys_sync_file_range(fd, offset, nbytes, flags); } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_sync_file_range2(long fd, long flags, - loff_t offset, loff_t nbytes) -{ - return SYSC_sync_file_range2((int) fd, (unsigned int) flags, - offset, nbytes); -} -SYSCALL_ALIAS(sys_sync_file_range2, SyS_sync_file_range2); -#endif diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 2fbdff6..e8e0e71 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -165,21 +165,8 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) if (unlikely(!sd)) return NULL; - while (1) { - int v, t; - - v = atomic_read(&sd->s_active); - if (unlikely(v < 0)) - return NULL; - - t = atomic_cmpxchg(&sd->s_active, v, v + 1); - if (likely(t == v)) - break; - if (t < 0) - return NULL; - - cpu_relax(); - } + if (!atomic_inc_unless_negative(&sd->s_active)) + return NULL; if (likely(!ignore_lockdep(sd))) rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); @@ -281,6 +268,10 @@ void release_sysfs_dirent(struct sysfs_dirent * sd) */ parent_sd = sd->s_parent; + WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED), + "sysfs: free using entry: %s/%s\n", + parent_sd ? parent_sd->s_name : "", sd->s_name); + if (sysfs_type(sd) == SYSFS_KOBJ_LINK) sysfs_put(sd->s_symlink.target_sd); if (sysfs_type(sd) & SYSFS_COPY_NAME) @@ -399,7 +390,7 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type) sd->s_name = name; sd->s_mode = mode; - sd->s_flags = type; + sd->s_flags = type | SYSFS_FLAG_REMOVED; return sd; @@ -479,6 +470,9 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; } + /* Mark the entry added into directory tree */ + sd->s_flags &= ~SYSFS_FLAG_REMOVED; + return 0; } @@ -1012,6 +1006,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) enum kobj_ns_type type; const void *ns; ino_t ino; + loff_t off; type = sysfs_ns_type(parent_sd); ns = sysfs_info(dentry->d_sb)->ns[type]; @@ -1020,6 +1015,8 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) ino = parent_sd->s_ino; if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0) filp->f_pos++; + else + return 0; } if (filp->f_pos == 1) { if (parent_sd->s_parent) @@ -1028,8 +1025,11 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) ino = parent_sd->s_ino; if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0) filp->f_pos++; + else + return 0; } mutex_lock(&sysfs_mutex); + off = filp->f_pos; for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos); pos; pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) { @@ -1041,27 +1041,43 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) len = strlen(name); ino = pos->s_ino; type = dt_type(pos); - filp->f_pos = pos->s_hash; + off = filp->f_pos = pos->s_hash; filp->private_data = sysfs_get(pos); mutex_unlock(&sysfs_mutex); - ret = filldir(dirent, name, len, filp->f_pos, ino, type); + ret = filldir(dirent, name, len, off, ino, type); mutex_lock(&sysfs_mutex); if (ret < 0) break; } mutex_unlock(&sysfs_mutex); - if ((filp->f_pos > 1) && !pos) { /* EOF */ - filp->f_pos = INT_MAX; + + /* don't reference last entry if its refcount is dropped */ + if (!pos) { filp->private_data = NULL; + + /* EOF and not changed as 0 or 1 in read/write path */ + if (off == filp->f_pos && off > 1) + filp->f_pos = INT_MAX; } return 0; } +static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + struct inode *inode = file_inode(file); + loff_t ret; + + mutex_lock(&inode->i_mutex); + ret = generic_file_llseek(file, offset, whence); + mutex_unlock(&inode->i_mutex); + + return ret; +} const struct file_operations sysfs_dir_operations = { .read = generic_read_dir, .readdir = sysfs_readdir, .release = sysfs_dir_release, - .llseek = generic_file_llseek, + .llseek = sysfs_dir_llseek, }; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 8d924b5..afd8327 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/magic.h> #include <linux/slab.h> +#include <linux/user_namespace.h> #include "sysfs.h" @@ -111,6 +112,9 @@ 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); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index ac838b8..f21acf0 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1568,6 +1568,12 @@ static int ubifs_remount_rw(struct ubifs_info *c) c->remounting_rw = 1; c->ro_mount = 0; + if (c->space_fixup) { + err = ubifs_fixup_free_space(c); + if (err) + return err; + } + err = check_free_space(c); if (err) goto out; @@ -1684,12 +1690,6 @@ static int ubifs_remount_rw(struct ubifs_info *c) err = dbg_check_space_info(c); } - if (c->space_fixup) { - err = ubifs_fixup_free_space(c); - if (err) - goto out; - } - mutex_unlock(&c->umount_mutex); return err; diff --git a/fs/ufs/util.c b/fs/ufs/util.c index 95425b5..b6c2f94 100644 --- a/fs/ufs/util.c +++ b/fs/ufs/util.c @@ -26,8 +26,7 @@ struct ufs_buffer_head * _ubh_bread_ (struct ufs_sb_private_info * uspi, count = size >> uspi->s_fshift; if (count > UFS_MAXFRAG) return NULL; - ubh = (struct ufs_buffer_head *) - kmalloc (sizeof (struct ufs_buffer_head), GFP_NOFS); + ubh = kmalloc (sizeof (struct ufs_buffer_head), GFP_NOFS); if (!ubh) return NULL; ubh->fragment = fragment; |