diff options
Diffstat (limited to 'fs')
55 files changed, 1739 insertions, 514 deletions
diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 646337dc5201..529300327f45 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -600,9 +600,6 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) /* lock down the parent dentry so we can peer at it */ parent = dget_parent(dentry); - if (!parent->d_inode) - goto out_bad; - dir = AFS_FS_I(parent->d_inode); /* validate the parent directory */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 100edcc5e312..4c94a79991bb 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1413,7 +1413,7 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata, * long file_ofs * followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL... */ -static void fill_files_note(struct memelfnote *note) +static int fill_files_note(struct memelfnote *note) { struct vm_area_struct *vma; unsigned count, size, names_ofs, remaining, n; @@ -1428,11 +1428,11 @@ static void fill_files_note(struct memelfnote *note) names_ofs = (2 + 3 * count) * sizeof(data[0]); alloc: if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */ - goto err; + return -EINVAL; size = round_up(size, PAGE_SIZE); data = vmalloc(size); if (!data) - goto err; + return -ENOMEM; start_end_ofs = data + 2; name_base = name_curpos = ((char *)data) + names_ofs; @@ -1485,7 +1485,7 @@ static void fill_files_note(struct memelfnote *note) size = name_curpos - (char *)data; fill_note(note, "CORE", NT_FILE, size, data); - err: ; + return 0; } #ifdef CORE_DUMP_USE_REGSET @@ -1686,8 +1686,8 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, fill_auxv_note(&info->auxv, current->mm); info->size += notesize(&info->auxv); - fill_files_note(&info->files); - info->size += notesize(&info->files); + if (fill_files_note(&info->files) == 0) + info->size += notesize(&info->files); return 1; } @@ -1719,7 +1719,8 @@ static int write_note_info(struct elf_note_info *info, return 0; if (first && !writenote(&info->auxv, file, foffset)) return 0; - if (first && !writenote(&info->files, file, foffset)) + if (first && info->files.data && + !writenote(&info->files, file, foffset)) return 0; for (i = 1; i < info->thread_notes; ++i) @@ -1806,6 +1807,7 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) struct elf_note_info { struct memelfnote *notes; + struct memelfnote *notes_files; struct elf_prstatus *prstatus; /* NT_PRSTATUS */ struct elf_prpsinfo *psinfo; /* NT_PRPSINFO */ struct list_head thread_list; @@ -1896,9 +1898,12 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, fill_siginfo_note(info->notes + 2, &info->csigdata, siginfo); fill_auxv_note(info->notes + 3, current->mm); - fill_files_note(info->notes + 4); + info->numnote = 4; - info->numnote = 5; + if (fill_files_note(info->notes + info->numnote) == 0) { + info->notes_files = info->notes + info->numnote; + info->numnote++; + } /* Try to dump the FPU. */ info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs, @@ -1960,8 +1965,9 @@ static void free_note_info(struct elf_note_info *info) kfree(list_entry(tmp, struct elf_thread_status, list)); } - /* Free data allocated by fill_files_note(): */ - vfree(info->notes[4].data); + /* Free data possibly allocated by fill_files_note(): */ + if (info->notes_files) + vfree(info->notes_files->data); kfree(info->prstatus); kfree(info->psinfo); @@ -2044,7 +2050,7 @@ static int elf_core_dump(struct coredump_params *cprm) struct vm_area_struct *vma, *gate_vma; struct elfhdr *elf = NULL; loff_t offset = 0, dataoff, foffset; - struct elf_note_info info; + struct elf_note_info info = { }; struct elf_phdr *phdr4note = NULL; struct elf_shdr *shdr4extnum = NULL; Elf_Half e_phnum; diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 60250847929f..fc60b31453ee 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -735,7 +735,7 @@ void bioset_integrity_free(struct bio_set *bs) mempool_destroy(bs->bio_integrity_pool); if (bs->bvec_integrity_pool) - mempool_destroy(bs->bio_integrity_pool); + mempool_destroy(bs->bvec_integrity_pool); } EXPORT_SYMBOL(bioset_integrity_free); @@ -917,8 +917,8 @@ void bio_copy_data(struct bio *dst, struct bio *src) src_p = kmap_atomic(src_bv->bv_page); dst_p = kmap_atomic(dst_bv->bv_page); - memcpy(dst_p + dst_bv->bv_offset, - src_p + src_bv->bv_offset, + memcpy(dst_p + dst_offset, + src_p + src_offset, bytes); kunmap_atomic(dst_p); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index d0ae226926ee..71f074e1870b 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -213,7 +213,10 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode) static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) { if (BTRFS_I(inode)->logged_trans == generation && - BTRFS_I(inode)->last_sub_trans <= BTRFS_I(inode)->last_log_commit) + BTRFS_I(inode)->last_sub_trans <= + BTRFS_I(inode)->last_log_commit && + BTRFS_I(inode)->last_sub_trans <= + BTRFS_I(inode)->root->last_log_commit) return 1; return 0; } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 64346721173f..61b5bcd57b7e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1005,8 +1005,11 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } - if (root->ref_cows) - btrfs_reloc_cow_block(trans, root, buf, cow); + if (root->ref_cows) { + ret = btrfs_reloc_cow_block(trans, root, buf, cow); + if (ret) + return ret; + } if (buf == root->node) { WARN_ON(parent && parent != buf); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3c1da6f98a4d..0506f40ede83 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1118,15 +1118,6 @@ struct btrfs_space_info { */ struct percpu_counter total_bytes_pinned; - /* - * we bump reservation progress every time we decrement - * bytes_reserved. This way people waiting for reservations - * know something good has happened and they can check - * for progress. The number here isn't to be trusted, it - * just shows reclaim activity - */ - unsigned long reservation_progress; - unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ @@ -3135,7 +3126,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root, unsigned num_items) { return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) * - 3 * num_items; + 2 * num_items; } /* @@ -3939,9 +3930,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_recover_relocation(struct btrfs_root *root); int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len); -void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf, - struct extent_buffer *cow); +int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf, + struct extent_buffer *cow); void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans, struct btrfs_pending_snapshot *pending, u64 *bytes_to_reserve); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index a64435359385..70681686e8dc 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -400,7 +400,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; btrfs_dev_replace_unlock(dev_replace); - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); /* force writing the updated state information to disk */ trans = btrfs_start_transaction(root, 0); @@ -475,7 +475,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4cbb00af92ff..4ae17ed13b32 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -157,6 +157,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, + { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, { .id = 0, .name_stem = "tree" }, }; @@ -3415,6 +3416,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) if (total_errors > max_errors) { printk(KERN_ERR "btrfs: %d errors while writing supers\n", total_errors); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ btrfs_error(root->fs_info, -EIO, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index cfb3cf711b34..d58bef130a41 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3925,7 +3925,6 @@ static int can_overcommit(struct btrfs_root *root, u64 space_size; u64 avail; u64 used; - u64 to_add; used = space_info->bytes_used + space_info->bytes_reserved + space_info->bytes_pinned + space_info->bytes_readonly; @@ -3959,25 +3958,17 @@ static int can_overcommit(struct btrfs_root *root, BTRFS_BLOCK_GROUP_RAID10)) avail >>= 1; - to_add = space_info->total_bytes; - /* * If we aren't flushing all things, let us overcommit up to * 1/2th of the space. If we can flush, don't let us overcommit * too much, let it overcommit up to 1/8 of the space. */ if (flush == BTRFS_RESERVE_FLUSH_ALL) - to_add >>= 3; + avail >>= 3; else - to_add >>= 1; - - /* - * Limit the overcommit to the amount of free space we could possibly - * allocate for chunks. - */ - to_add = min(avail, to_add); + avail >>= 1; - if (used + bytes < space_info->total_bytes + to_add) + if (used + bytes < space_info->total_bytes + avail) return 1; return 0; } @@ -4000,7 +3991,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root, */ btrfs_start_all_delalloc_inodes(root->fs_info, 0); if (!current->journal_info) - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); } } @@ -4030,7 +4021,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, if (delalloc_bytes == 0) { if (trans) return; - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); return; } @@ -4058,7 +4049,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, loops++; if (wait_ordered && !trans) { - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); } else { time_left = schedule_timeout_killable(1); if (time_left) @@ -4465,7 +4456,6 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info, space_info->bytes_may_use -= num_bytes; trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, num_bytes, 0); - space_info->reservation_progress++; spin_unlock(&space_info->lock); } } @@ -4666,7 +4656,6 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) sinfo->bytes_may_use -= num_bytes; trace_btrfs_space_reservation(fs_info, "space_info", sinfo->flags, num_bytes, 0); - sinfo->reservation_progress++; block_rsv->reserved = block_rsv->size; block_rsv->full = 1; } @@ -5446,7 +5435,6 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, space_info->bytes_readonly += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; - space_info->reservation_progress++; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); @@ -6117,10 +6105,13 @@ enum btrfs_loop_type { /* * walks the btree of allocated extents and find a hole of a given size. * The key ins is changed to record the hole: - * ins->objectid == block start + * ins->objectid == start position * ins->flags = BTRFS_EXTENT_ITEM_KEY - * ins->offset == number of blocks + * ins->offset == the size of the hole. * Any available blocks before search_start are skipped. + * + * If there is no suitable free space, we will record the max size of + * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, u64 num_bytes, u64 empty_size, @@ -6133,6 +6124,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_block_group_cache *block_group = NULL; struct btrfs_block_group_cache *used_block_group; u64 search_start = 0; + u64 max_extent_size = 0; int empty_cluster = 2 * 1024 * 1024; struct btrfs_space_info *space_info; int loop = 0; @@ -6292,7 +6284,10 @@ have_block_group: btrfs_get_block_group(used_block_group); offset = btrfs_alloc_from_cluster(used_block_group, - last_ptr, num_bytes, used_block_group->key.objectid); + last_ptr, + num_bytes, + used_block_group->key.objectid, + &max_extent_size); if (offset) { /* we have a block, we're done */ spin_unlock(&last_ptr->refill_lock); @@ -6355,8 +6350,10 @@ refill_cluster: * cluster */ offset = btrfs_alloc_from_cluster(block_group, - last_ptr, num_bytes, - search_start); + last_ptr, + num_bytes, + search_start, + &max_extent_size); if (offset) { /* we found one, proceed */ spin_unlock(&last_ptr->refill_lock); @@ -6391,13 +6388,18 @@ unclustered_alloc: if (cached && block_group->free_space_ctl->free_space < num_bytes + empty_cluster + empty_size) { + if (block_group->free_space_ctl->free_space > + max_extent_size) + max_extent_size = + block_group->free_space_ctl->free_space; spin_unlock(&block_group->free_space_ctl->tree_lock); goto loop; } spin_unlock(&block_group->free_space_ctl->tree_lock); offset = btrfs_find_space_for_alloc(block_group, search_start, - num_bytes, empty_size); + num_bytes, empty_size, + &max_extent_size); /* * If we didn't find a chunk, and we haven't failed on this * block group before, and this block group is in the middle of @@ -6515,7 +6517,8 @@ loop: ret = 0; } out: - + if (ret == -ENOSPC) + ins->offset = max_extent_size; return ret; } @@ -6573,8 +6576,8 @@ again: flags); if (ret == -ENOSPC) { - if (!final_tried) { - num_bytes = num_bytes >> 1; + if (!final_tried && ins->offset) { + num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); if (num_bytes == min_alloc_size) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 09582b81640c..c09a40db53db 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1481,10 +1481,12 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree, *end = state->end; cur_start = state->end + 1; node = rb_next(node); - if (!node) - break; total_bytes += state->end - state->start + 1; - if (total_bytes >= max_bytes) + if (total_bytes >= max_bytes) { + *end = *start + max_bytes - 1; + break; + } + if (!node) break; } out: diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index bc5072b2db53..72da4df53c9a 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1859,8 +1859,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = btrfs_log_dentry_safe(trans, root, dentry); if (ret < 0) { - mutex_unlock(&inode->i_mutex); - goto out; + /* Fallthrough and commit/free transaction. */ + ret = 1; } /* we've logged all the items and now have a consistent diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 3f0ddfce96e6..b4f9904c4c6b 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1431,13 +1431,19 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl, ctl->free_space += bytes; } +/* + * If we can not find suitable extent, we will use bytes to record + * the size of the max extent. + */ static int search_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes) { unsigned long found_bits = 0; + unsigned long max_bits = 0; unsigned long bits, i; unsigned long next_zero; + unsigned long extent_bits; i = offset_to_bit(bitmap_info->offset, ctl->unit, max_t(u64, *offset, bitmap_info->offset)); @@ -1446,9 +1452,12 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) { next_zero = find_next_zero_bit(bitmap_info->bitmap, BITS_PER_BITMAP, i); - if ((next_zero - i) >= bits) { - found_bits = next_zero - i; + extent_bits = next_zero - i; + if (extent_bits >= bits) { + found_bits = extent_bits; break; + } else if (extent_bits > max_bits) { + max_bits = extent_bits; } i = next_zero; } @@ -1459,38 +1468,41 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, return 0; } + *bytes = (u64)(max_bits) * ctl->unit; return -1; } +/* Cache the size of the max extent in bytes */ static struct btrfs_free_space * find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, - unsigned long align) + unsigned long align, u64 *max_extent_size) { struct btrfs_free_space *entry; struct rb_node *node; - u64 ctl_off; u64 tmp; u64 align_off; int ret; if (!ctl->free_space_offset.rb_node) - return NULL; + goto out; entry = tree_search_offset(ctl, offset_to_bitmap(ctl, *offset), 0, 1); if (!entry) - return NULL; + goto out; for (node = &entry->offset_index; node; node = rb_next(node)) { entry = rb_entry(node, struct btrfs_free_space, offset_index); - if (entry->bytes < *bytes) + if (entry->bytes < *bytes) { + if (entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; continue; + } /* make sure the space returned is big enough * to match our requested alignment */ if (*bytes >= align) { - ctl_off = entry->offset - ctl->start; - tmp = ctl_off + align - 1;; + tmp = entry->offset - ctl->start + align - 1; do_div(tmp, align); tmp = tmp * align + ctl->start; align_off = tmp - entry->offset; @@ -1499,14 +1511,22 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, tmp = entry->offset; } - if (entry->bytes < *bytes + align_off) + if (entry->bytes < *bytes + align_off) { + if (entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; continue; + } if (entry->bitmap) { - ret = search_bitmap(ctl, entry, &tmp, bytes); + u64 size = *bytes; + + ret = search_bitmap(ctl, entry, &tmp, &size); if (!ret) { *offset = tmp; + *bytes = size; return entry; + } else if (size > *max_extent_size) { + *max_extent_size = size; } continue; } @@ -1515,7 +1535,7 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, *bytes = entry->bytes - align_off; return entry; } - +out: return NULL; } @@ -2116,7 +2136,8 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) } u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes, u64 empty_size) + u64 offset, u64 bytes, u64 empty_size, + u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; @@ -2127,7 +2148,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, - block_group->full_stripe_len); + block_group->full_stripe_len, max_extent_size); if (!entry) goto out; @@ -2137,7 +2158,6 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, if (!entry->bytes) free_bitmap(ctl, entry); } else { - unlink_free_space(ctl, entry); align_gap_len = offset - entry->offset; align_gap = entry->offset; @@ -2151,7 +2171,6 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, else link_free_space(ctl, entry); } - out: spin_unlock(&ctl->tree_lock); @@ -2206,7 +2225,8 @@ int btrfs_return_cluster_to_free_space( static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, struct btrfs_free_space *entry, - u64 bytes, u64 min_start) + u64 bytes, u64 min_start, + u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; int err; @@ -2218,8 +2238,11 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, search_bytes = bytes; err = search_bitmap(ctl, entry, &search_start, &search_bytes); - if (err) + if (err) { + if (search_bytes > *max_extent_size) + *max_extent_size = search_bytes; return 0; + } ret = search_start; __bitmap_clear_bits(ctl, entry, ret, bytes); @@ -2234,7 +2257,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, */ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 bytes, - u64 min_start) + u64 min_start, u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; @@ -2254,6 +2277,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, entry = rb_entry(node, struct btrfs_free_space, offset_index); while(1) { + if (entry->bytes < bytes && entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; + if (entry->bytes < bytes || (!entry->bitmap && entry->offset < min_start)) { node = rb_next(&entry->offset_index); @@ -2267,7 +2293,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, if (entry->bitmap) { ret = btrfs_alloc_from_bitmap(block_group, cluster, entry, bytes, - cluster->window_start); + cluster->window_start, + max_extent_size); if (ret == 0) { node = rb_next(&entry->offset_index); if (!node) diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index c74904167476..e737f92cf6d0 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -94,7 +94,8 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl); void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group); u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes, u64 empty_size); + u64 offset, u64 bytes, u64 empty_size, + u64 *max_extent_size); u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, u64 bytes); @@ -105,7 +106,7 @@ int btrfs_find_space_cluster(struct btrfs_root *root, void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 bytes, - u64 min_start); + u64 min_start, u64 *max_extent_size); int btrfs_return_cluster_to_free_space( struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f338c5672d58..22ebc13b6c99 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4688,11 +4688,11 @@ static void inode_tree_add(struct inode *inode) struct btrfs_inode *entry; struct rb_node **p; struct rb_node *parent; + struct rb_node *new = &BTRFS_I(inode)->rb_node; u64 ino = btrfs_ino(inode); if (inode_unhashed(inode)) return; -again: parent = NULL; spin_lock(&root->inode_lock); p = &root->inode_tree.rb_node; @@ -4707,14 +4707,14 @@ again: else { WARN_ON(!(entry->vfs_inode.i_state & (I_WILL_FREE | I_FREEING))); - rb_erase(parent, &root->inode_tree); + rb_replace_node(parent, new, &root->inode_tree); RB_CLEAR_NODE(parent); spin_unlock(&root->inode_lock); - goto again; + return; } } - rb_link_node(&BTRFS_I(inode)->rb_node, parent, p); - rb_insert_color(&BTRFS_I(inode)->rb_node, &root->inode_tree); + rb_link_node(new, parent, p); + rb_insert_color(new, &root->inode_tree); spin_unlock(&root->inode_lock); } @@ -8216,6 +8216,10 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput) work = btrfs_alloc_delalloc_work(inode, 0, delay_iput); if (unlikely(!work)) { + if (delay_iput) + btrfs_add_delayed_iput(inode); + else + iput(inode); ret = -ENOMEM; goto out; } @@ -8613,11 +8617,13 @@ static const struct inode_operations btrfs_dir_inode_operations = { .removexattr = btrfs_removexattr, .permission = btrfs_permission, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct inode_operations btrfs_dir_ro_inode_operations = { .lookup = btrfs_lookup, .permission = btrfs_permission, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct file_operations btrfs_dir_file_operations = { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1a5b9462dd9a..9d46f60cb943 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -574,7 +574,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) return ret; - btrfs_wait_ordered_extents(root, 0); + btrfs_wait_ordered_extents(root); pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS); if (!pending_snapshot) @@ -2696,9 +2696,9 @@ out_unlock: static long btrfs_ioctl_file_extent_same(struct file *file, void __user *argp) { - struct btrfs_ioctl_same_args *args = argp; - struct btrfs_ioctl_same_args same; - struct btrfs_ioctl_same_extent_info info; + struct btrfs_ioctl_same_args tmp; + struct btrfs_ioctl_same_args *same; + struct btrfs_ioctl_same_extent_info *info; struct inode *src = file->f_dentry->d_inode; struct file *dst_file = NULL; struct inode *dst; @@ -2706,6 +2706,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, u64 len; int i; int ret; + unsigned long size; u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; bool is_admin = capable(CAP_SYS_ADMIN); @@ -2716,15 +2717,30 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (ret) return ret; - if (copy_from_user(&same, + if (copy_from_user(&tmp, (struct btrfs_ioctl_same_args __user *)argp, - sizeof(same))) { + sizeof(tmp))) { ret = -EFAULT; goto out; } - off = same.logical_offset; - len = same.length; + size = sizeof(tmp) + + tmp.dest_count * sizeof(struct btrfs_ioctl_same_extent_info); + + same = kmalloc(size, GFP_NOFS); + if (!same) { + ret = -EFAULT; + goto out; + } + + if (copy_from_user(same, + (struct btrfs_ioctl_same_args __user *)argp, size)) { + ret = -EFAULT; + goto out; + } + + off = same->logical_offset; + len = same->length; /* * Limit the total length we will dedupe for each operation. @@ -2752,27 +2768,28 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (!S_ISREG(src->i_mode)) goto out; - ret = 0; - for (i = 0; i < same.dest_count; i++) { - if (copy_from_user(&info, &args->info[i], sizeof(info))) { - ret = -EFAULT; - goto out; - } + /* pre-format output fields to sane values */ + for (i = 0; i < same->dest_count; i++) { + same->info[i].bytes_deduped = 0ULL; + same->info[i].status = 0; + } - info.bytes_deduped = 0; + ret = 0; + for (i = 0; i < same->dest_count; i++) { + info = &same->info[i]; - dst_file = fget(info.fd); + dst_file = fget(info->fd); if (!dst_file) { - info.status = -EBADF; + info->status = -EBADF; goto next; } if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { - info.status = -EINVAL; + info->status = -EINVAL; goto next; } - info.status = -EXDEV; + info->status = -EXDEV; if (file->f_path.mnt != dst_file->f_path.mnt) goto next; @@ -2781,32 +2798,29 @@ static long btrfs_ioctl_file_extent_same(struct file *file, goto next; if (S_ISDIR(dst->i_mode)) { - info.status = -EISDIR; + info->status = -EISDIR; goto next; } if (!S_ISREG(dst->i_mode)) { - info.status = -EACCES; + info->status = -EACCES; goto next; } - info.status = btrfs_extent_same(src, off, len, dst, - info.logical_offset); - if (info.status == 0) - info.bytes_deduped += len; + info->status = btrfs_extent_same(src, off, len, dst, + info->logical_offset); + if (info->status == 0) + info->bytes_deduped += len; next: if (dst_file) fput(dst_file); - - if (__put_user_unaligned(info.status, &args->info[i].status) || - __put_user_unaligned(info.bytes_deduped, - &args->info[i].bytes_deduped)) { - ret = -EFAULT; - goto out; - } } + ret = copy_to_user(argp, same, size); + if (ret) + ret = -EFAULT; + out: mnt_drop_write_file(file); return ret; @@ -3310,7 +3324,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) } if (!objectid) - objectid = root->root_key.objectid; + objectid = BTRFS_FS_TREE_OBJECTID; location.objectid = objectid; location.type = BTRFS_ROOT_ITEM_KEY; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 966b413a33b8..c702cb62f78a 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -563,11 +563,10 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work) * wait for all the ordered extents in a root. This is done when balancing * space between drives. */ -void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) +void btrfs_wait_ordered_extents(struct btrfs_root *root) { struct list_head splice, works; struct btrfs_ordered_extent *ordered, *next; - struct inode *inode; INIT_LIST_HEAD(&splice); INIT_LIST_HEAD(&works); @@ -580,15 +579,6 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) root_extent_list); list_move_tail(&ordered->root_extent_list, &root->ordered_extents); - /* - * the inode may be getting freed (in sys_unlink path). - */ - inode = igrab(ordered->inode); - if (!inode) { - cond_resched_lock(&root->ordered_extent_lock); - continue; - } - atomic_inc(&ordered->refs); spin_unlock(&root->ordered_extent_lock); @@ -605,21 +595,13 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) list_for_each_entry_safe(ordered, next, &works, work_list) { list_del_init(&ordered->work_list); wait_for_completion(&ordered->completion); - - inode = ordered->inode; btrfs_put_ordered_extent(ordered); - if (delay_iput) - btrfs_add_delayed_iput(inode); - else - iput(inode); - cond_resched(); } mutex_unlock(&root->fs_info->ordered_operations_mutex); } -void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, - int delay_iput) +void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; struct list_head splice; @@ -637,7 +619,7 @@ void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); - btrfs_wait_ordered_extents(root, delay_iput); + btrfs_wait_ordered_extents(root); btrfs_put_fs_root(root); spin_lock(&fs_info->ordered_root_lock); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index d9a5aa097b4f..0c0b35612d7a 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -195,9 +195,8 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans, void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); -void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput); -void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, - int delay_iput); +void btrfs_wait_ordered_extents(struct btrfs_root *root); +void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info); void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode); void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid); void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index aacc2121e87c..a5a26320503f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1548,7 +1548,7 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr, btrfs_file_extent_other_encoding(leaf, fi)); if (num_bytes != btrfs_file_extent_disk_num_bytes(leaf, fi)) { - ret = 1; + ret = -EINVAL; goto out; } @@ -1579,7 +1579,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, u64 end; u32 nritems; u32 i; - int ret; + int ret = 0; int first = 1; int dirty = 0; @@ -1642,11 +1642,13 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = get_new_location(rc->data_inode, &new_bytenr, bytenr, num_bytes); - if (ret > 0) { - WARN_ON(1); - continue; + if (ret) { + /* + * Don't have to abort since we've not changed anything + * in the file extent yet. + */ + break; } - BUG_ON(ret < 0); btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr); dirty = 1; @@ -1656,18 +1658,24 @@ int replace_file_extents(struct btrfs_trans_handle *trans, num_bytes, parent, btrfs_header_owner(leaf), key.objectid, key.offset, 1); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + break; + } ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), key.objectid, key.offset, 1); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + break; + } } if (dirty) btrfs_mark_buffer_dirty(leaf); if (inode) btrfs_add_delayed_iput(inode); - return 0; + return ret; } static noinline_for_stack @@ -4238,7 +4246,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) err = ret; goto out; } - btrfs_wait_all_ordered_extents(fs_info, 0); + btrfs_wait_all_ordered_extents(fs_info); while (1) { mutex_lock(&fs_info->cleaner_mutex); @@ -4499,19 +4507,19 @@ out: return ret; } -void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf, - struct extent_buffer *cow) +int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf, + struct extent_buffer *cow) { struct reloc_control *rc; struct backref_node *node; int first_cow = 0; int level; - int ret; + int ret = 0; rc = root->fs_info->reloc_ctl; if (!rc) - return; + return 0; BUG_ON(rc->stage == UPDATE_DATA_PTRS && root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID); @@ -4547,10 +4555,9 @@ void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, rc->nodes_relocated += buf->len; } - if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS) { + if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS) ret = replace_file_extents(trans, rc, root, cow); - BUG_ON(ret); - } + return ret; } /* diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0afcd452fcb3..a18e0e23f6a6 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -158,12 +158,20 @@ struct scrub_fixup_nodatasum { int mirror_num; }; +struct scrub_nocow_inode { + u64 inum; + u64 offset; + u64 root; + struct list_head list; +}; + struct scrub_copy_nocow_ctx { struct scrub_ctx *sctx; u64 logical; u64 len; int mirror_num; u64 physical_for_dev_replace; + struct list_head inodes; struct btrfs_work work; }; @@ -245,7 +253,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work); static int write_page_nocow(struct scrub_ctx *sctx, u64 physical_for_dev_replace, struct page *page); static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, - void *ctx); + struct scrub_copy_nocow_ctx *ctx); static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, int mirror_num, u64 physical_for_dev_replace); static void copy_nocow_pages_worker(struct btrfs_work *work); @@ -3126,12 +3134,30 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, nocow_ctx->mirror_num = mirror_num; nocow_ctx->physical_for_dev_replace = physical_for_dev_replace; nocow_ctx->work.func = copy_nocow_pages_worker; + INIT_LIST_HEAD(&nocow_ctx->inodes); btrfs_queue_worker(&fs_info->scrub_nocow_workers, &nocow_ctx->work); return 0; } +static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx) +{ + struct scrub_copy_nocow_ctx *nocow_ctx = ctx; + struct scrub_nocow_inode *nocow_inode; + + nocow_inode = kzalloc(sizeof(*nocow_inode), GFP_NOFS); + if (!nocow_inode) + return -ENOMEM; + nocow_inode->inum = inum; + nocow_inode->offset = offset; + nocow_inode->root = root; + list_add_tail(&nocow_inode->list, &nocow_ctx->inodes); + return 0; +} + +#define COPY_COMPLETE 1 + static void copy_nocow_pages_worker(struct btrfs_work *work) { struct scrub_copy_nocow_ctx *nocow_ctx = @@ -3167,8 +3193,7 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) } ret = iterate_inodes_from_logical(logical, fs_info, path, - copy_nocow_pages_for_inode, - nocow_ctx); + record_inode_for_nocow, nocow_ctx); if (ret != 0 && ret != -ENOENT) { pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n", logical, physical_for_dev_replace, len, mirror_num, @@ -3177,7 +3202,33 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) goto out; } + btrfs_end_transaction(trans, root); + trans = NULL; + while (!list_empty(&nocow_ctx->inodes)) { + struct scrub_nocow_inode *entry; + entry = list_first_entry(&nocow_ctx->inodes, + struct scrub_nocow_inode, + list); + list_del_init(&entry->list); + ret = copy_nocow_pages_for_inode(entry->inum, entry->offset, + entry->root, nocow_ctx); + kfree(entry); + if (ret == COPY_COMPLETE) { + ret = 0; + break; + } else if (ret) { + break; + } + } out: + while (!list_empty(&nocow_ctx->inodes)) { + struct scrub_nocow_inode *entry; + entry = list_first_entry(&nocow_ctx->inodes, + struct scrub_nocow_inode, + list); + list_del_init(&entry->list); + kfree(entry); + } if (trans && !IS_ERR(trans)) btrfs_end_transaction(trans, root); if (not_written) @@ -3190,20 +3241,25 @@ out: scrub_pending_trans_workers_dec(sctx); } -static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) +static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, + struct scrub_copy_nocow_ctx *nocow_ctx) { - struct scrub_copy_nocow_ctx *nocow_ctx = ctx; struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info; struct btrfs_key key; struct inode *inode; struct page *page; struct btrfs_root *local_root; + struct btrfs_ordered_extent *ordered; + struct extent_map *em; + struct extent_state *cached_state = NULL; + struct extent_io_tree *io_tree; u64 physical_for_dev_replace; - u64 len; + u64 len = nocow_ctx->len; + u64 lockstart = offset, lockend = offset + len - 1; unsigned long index; int srcu_index; - int ret; - int err; + int ret = 0; + int err = 0; key.objectid = root; key.type = BTRFS_ROOT_ITEM_KEY; @@ -3229,9 +3285,33 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) mutex_lock(&inode->i_mutex); inode_dio_wait(inode); - ret = 0; physical_for_dev_replace = nocow_ctx->physical_for_dev_replace; - len = nocow_ctx->len; + io_tree = &BTRFS_I(inode)->io_tree; + + lock_extent_bits(io_tree, lockstart, lockend, 0, &cached_state); + ordered = btrfs_lookup_ordered_range(inode, lockstart, len); + if (ordered) { + btrfs_put_ordered_extent(ordered); + goto out_unlock; + } + + em = btrfs_get_extent(inode, NULL, 0, lockstart, len, 0); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out_unlock; + } + + /* + * This extent does not actually cover the logical extent anymore, + * move on to the next inode. + */ + if (em->block_start > nocow_ctx->logical || + em->block_start + em->block_len < nocow_ctx->logical + len) { + free_extent_map(em); + goto out_unlock; + } + free_extent_map(em); + while (len >= PAGE_CACHE_SIZE) { index = offset >> PAGE_CACHE_SHIFT; again: @@ -3247,10 +3327,9 @@ again: goto next_page; } else { ClearPageError(page); - err = extent_read_full_page(&BTRFS_I(inode)-> - io_tree, - page, btrfs_get_extent, - nocow_ctx->mirror_num); + err = extent_read_full_page_nolock(io_tree, page, + btrfs_get_extent, + nocow_ctx->mirror_num); if (err) { ret = err; goto next_page; @@ -3264,6 +3343,7 @@ again: * page in the page cache. */ if (page->mapping != inode->i_mapping) { + unlock_page(page); page_cache_release(page); goto again; } @@ -3287,6 +3367,10 @@ next_page: physical_for_dev_replace += PAGE_CACHE_SIZE; len -= PAGE_CACHE_SIZE; } + ret = COPY_COMPLETE; +out_unlock: + unlock_extent_cached(io_tree, lockstart, lockend, &cached_state, + GFP_NOFS); out: mutex_unlock(&inode->i_mutex); iput(inode); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3aab10ce63e8..e913328d0f2a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -921,7 +921,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_wait_all_ordered_extents(fs_info, 1); + btrfs_wait_all_ordered_extents(fs_info); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { @@ -1340,6 +1340,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; } else { + if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) { + btrfs_err(fs_info, + "Remounting read-write after error is not allowed\n"); + ret = -EINVAL; + goto restore; + } if (fs_info->fs_devices->rw_devices == 0) { ret = -EACCES; goto restore; @@ -1377,6 +1383,16 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) pr_warn("btrfs: failed to resume dev_replace\n"); goto restore; } + + if (!fs_info->uuid_root) { + pr_info("btrfs: creating UUID tree\n"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + pr_warn("btrfs: failed to create the uuid tree" + "%d\n", ret); + goto restore; + } + } sb->s_flags &= ~MS_RDONLY; } out: @@ -1762,6 +1778,9 @@ static void btrfs_print_info(void) #ifdef CONFIG_BTRFS_DEBUG ", debug=on" #endif +#ifdef CONFIG_BTRFS_ASSERT + ", assert=on" +#endif #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY ", integrity-checker=on" #endif diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index cac4a3f76323..e7a95356df83 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1603,7 +1603,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT)) - btrfs_wait_all_ordered_extents(fs_info, 1); + btrfs_wait_all_ordered_extents(fs_info); } int btrfs_commit_transaction(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 0d9613c3f5e5..79f057c0619a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -93,7 +93,8 @@ */ #define LOG_WALK_PIN_ONLY 0 #define LOG_WALK_REPLAY_INODES 1 -#define LOG_WALK_REPLAY_ALL 2 +#define LOG_WALK_REPLAY_DIR_INDEX 2 +#define LOG_WALK_REPLAY_ALL 3 static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, @@ -393,6 +394,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, if (inode_item) { struct btrfs_inode_item *item; u64 nbytes; + u32 mode; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); @@ -400,9 +402,19 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, nbytes); + + /* + * If this is a directory we need to reset the i_size to + * 0 so that we can set it up properly when replaying + * the rest of the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } } else if (inode_item) { struct btrfs_inode_item *item; + u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out @@ -410,6 +422,15 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, */ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, 0); + + /* + * If this is a directory we need to reset the i_size to 0 so + * that we can set it up properly when replaying the rest of + * the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } insert: btrfs_release_path(path); @@ -1496,6 +1517,7 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, iput(inode); return -EIO; } + ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index); /* FIXME, put inode into FIXUP list */ @@ -1534,6 +1556,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, u8 log_type; int exists; int ret = 0; + bool update_size = (key->type == BTRFS_DIR_INDEX_KEY); dir = read_one_inode(root, key->objectid); if (!dir) @@ -1604,6 +1627,10 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto insert; out: btrfs_release_path(path); + if (!ret && update_size) { + btrfs_i_size_write(dir, dir->i_size + name_len * 2); + ret = btrfs_update_inode(trans, root, dir); + } kfree(name); iput(dir); return ret; @@ -1614,6 +1641,7 @@ insert: name, name_len, log_type, &log_key); if (ret && ret != -ENOENT) goto out; + update_size = false; ret = 0; goto out; } @@ -2027,6 +2055,15 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, if (ret) break; } + + if (key.type == BTRFS_DIR_INDEX_KEY && + wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { + ret = replay_one_dir_item(wc->trans, root, path, + eb, i, &key); + if (ret) + break; + } + if (wc->stage < LOG_WALK_REPLAY_ALL) continue; @@ -2048,8 +2085,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, eb, i, &key); if (ret) break; - } else if (key.type == BTRFS_DIR_ITEM_KEY || - key.type == BTRFS_DIR_INDEX_KEY) { + } else if (key.type == BTRFS_DIR_ITEM_KEY) { ret = replay_one_dir_item(wc->trans, root, path, eb, i, &key); if (ret) @@ -3805,6 +3841,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, int ret = 0; struct btrfs_root *root; struct dentry *old_parent = NULL; + struct inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -3824,7 +3861,14 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, } while (1) { - BTRFS_I(inode)->logged_trans = trans->transid; + /* + * If we are logging a directory then we start with our inode, + * not our parents inode, so we need to skipp setting the + * logged_trans so that further down in the log code we don't + * think this inode has already been logged. + */ + if (inode != orig_inode) + BTRFS_I(inode)->logged_trans = trans->transid; smp_mb(); if (BTRFS_I(inode)->last_unlink_trans > last_committed) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0052ca8264d9..a10645830223 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -796,7 +796,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fs_devices->rotating = 1; fs_devices->open_devices++; - if (device->writeable && !device->is_tgtdev_for_dev_replace) { + if (device->writeable && + device->devid != BTRFS_DEV_REPLACE_DEVID) { fs_devices->rw_devices++; list_add(&device->dev_alloc_list, &fs_devices->alloc_list); @@ -911,9 +912,9 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, if (disk_super->label[0]) { if (disk_super->label[BTRFS_LABEL_SIZE - 1]) disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0'; - printk(KERN_INFO "device label %s ", disk_super->label); + printk(KERN_INFO "btrfs: device label %s ", disk_super->label); } else { - printk(KERN_INFO "device fsid %pU ", disk_super->fsid); + printk(KERN_INFO "btrfs: device fsid %pU ", disk_super->fsid); } printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path); diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index b5e80b0af315..38c1768b4142 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -140,6 +140,17 @@ config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN If the NFS client is unchanged from the upstream kernel, this option should be set to the default "kernel.org". +config NFS_V4_1_MIGRATION + bool "NFSv4.1 client support for migration" + depends on NFS_V4_1 + default n + help + This option makes the NFS client advertise to NFSv4.1 servers that + it can support NFSv4 migration. + + The NFSv4.1 pieces of the Linux NFSv4 migration implementation are + still experimental. If you are not an NFSv4 developer, say N here. + config NFS_V4_SECURITY_LABEL bool depends on NFS_V4_2 && SECURITY diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 67cd73213168..073b4cf67ed9 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -164,8 +164,7 @@ nfs41_callback_up(struct svc_serv *serv) svc_xprt_put(serv->sv_bc_xprt); serv->sv_bc_xprt = NULL; } - dprintk("--> %s return %ld\n", __func__, - IS_ERR(rqstp) ? PTR_ERR(rqstp) : 0); + dprintk("--> %s return %d\n", __func__, PTR_ERR_OR_ZERO(rqstp)); return rqstp; } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 2dceee4db076..1d09289c8f0e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -590,6 +590,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_DISCRTRY; + if (test_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT; 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)) @@ -784,8 +786,10 @@ static int nfs_init_server(struct nfs_server *server, goto error; server->port = data->nfs_server.port; + server->auth_info = data->auth_info; - error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]); + error = nfs_init_server_rpcclient(server, &timeparms, + data->selected_flavor); if (error < 0) goto error; @@ -926,6 +930,7 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour target->acdirmax = source->acdirmax; target->caps = source->caps; target->options = source->options; + target->auth_info = source->auth_info; } EXPORT_SYMBOL_GPL(nfs_server_copy_userdata); @@ -943,7 +948,7 @@ void nfs_server_insert_lists(struct nfs_server *server) } EXPORT_SYMBOL_GPL(nfs_server_insert_lists); -static void nfs_server_remove_lists(struct nfs_server *server) +void nfs_server_remove_lists(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; struct nfs_net *nn; @@ -960,6 +965,7 @@ static void nfs_server_remove_lists(struct nfs_server *server) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nfs_server_remove_lists); /* * Allocate and initialise a server record diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 4c5edcc8b6e9..9a8676f33350 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1139,7 +1139,13 @@ out_zap_parent: if (inode && S_ISDIR(inode->i_mode)) { /* Purge readdir caches. */ nfs_zap_caches(inode); - if (dentry->d_flags & DCACHE_DISCONNECTED) + /* + * We can't d_drop the root of a disconnected tree: + * its d_hash is on the s_anon list and d_drop() would hide + * it from shrink_dcache_for_unmount(), leading to busy + * inodes on unmount and further oopses. + */ + if (IS_ROOT(dentry)) goto out_valid; } /* If we have submounts, don't unhash ! */ @@ -1458,7 +1464,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, trace_nfs_atomic_open_enter(dir, ctx, open_flags); nfs_block_sillyrename(dentry->d_parent); - inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); + inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened); nfs_unblock_sillyrename(dentry->d_parent); if (IS_ERR(inode)) { err = PTR_ERR(inode); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bb90bff0cb7a..471ba59c42f9 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1209,6 +1209,7 @@ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) * not on the result */ return nfs_fhandle_hash(fh); } +EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); /* * _nfs_display_fhandle - display an NFS file handle on the console @@ -1253,6 +1254,7 @@ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) } } } +EXPORT_SYMBOL_GPL(_nfs_display_fhandle); #endif /** diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 38da8c2b81ac..bca6a3e3c49c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -88,8 +88,8 @@ struct nfs_parsed_mount_data { unsigned int namlen; unsigned int options; unsigned int bsize; - unsigned int auth_flavor_len; - rpc_authflavor_t auth_flavors[1]; + struct nfs_auth_info auth_info; + rpc_authflavor_t selected_flavor; char *client_address; unsigned int version; unsigned int minorversion; @@ -154,6 +154,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *, rpc_authflavor_t); int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); void nfs_server_insert_lists(struct nfs_server *); +void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); @@ -174,6 +175,8 @@ extern struct nfs_server *nfs4_create_server( struct nfs_subversion *); extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, struct nfs_fh *); +extern int nfs4_update_server(struct nfs_server *server, const char *hostname, + struct sockaddr *sap, size_t salen); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, @@ -323,6 +326,7 @@ extern struct file_system_type nfs_xdev_fs_type; extern struct file_system_type nfs4_xdev_fs_type; extern struct file_system_type nfs4_referral_fs_type; #endif +bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *); void nfs_initialise_sb(struct super_block *); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 28842abafab4..3ce79b04522e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -29,6 +29,8 @@ enum nfs4_client_state { NFS4CLNT_SERVER_SCOPE_MISMATCH, NFS4CLNT_PURGE_STATE, NFS4CLNT_BIND_CONN_TO_SESSION, + NFS4CLNT_MOVED, + NFS4CLNT_LEASE_MOVED, }; #define NFS4_RENEW_TIMEOUT 0x01 @@ -50,6 +52,7 @@ struct nfs4_minor_version_ops { const struct nfs4_state_recovery_ops *reboot_recovery_ops; const struct nfs4_state_recovery_ops *nograce_recovery_ops; const struct nfs4_state_maintenance_ops *state_renewal_ops; + const struct nfs4_mig_recovery_ops *mig_recovery_ops; }; #define NFS_SEQID_CONFIRMED 1 @@ -203,6 +206,12 @@ struct nfs4_state_maintenance_ops { int (*renew_lease)(struct nfs_client *, struct rpc_cred *); }; +struct nfs4_mig_recovery_ops { + int (*get_locations)(struct inode *, struct nfs4_fs_locations *, + struct page *, struct rpc_cred *); + int (*fsid_present)(struct inode *, struct rpc_cred *); +}; + extern const struct dentry_operations nfs4_dentry_operations; /* dir.c */ @@ -213,10 +222,11 @@ int nfs_atomic_open(struct inode *, struct dentry *, struct file *, extern struct file_system_type nfs4_fs_type; /* nfs4namespace.c */ -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); +int nfs4_replace_transport(struct nfs_server *server, + const struct nfs4_fs_locations *locations); /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); @@ -231,6 +241,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); +extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, + struct page *page, struct rpc_cred *); +extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *, struct nfs_fh *, struct nfs_fattr *); extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); @@ -411,6 +424,8 @@ 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 int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); +extern int nfs4_schedule_migration_recovery(const struct nfs_server *); +extern void nfs4_schedule_lease_moved_recovery(struct nfs_client *); 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 **); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index a860ab566d6e..b4a160a405ce 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -197,6 +197,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; + clp->cl_mig_gen = 1; return clp; error: @@ -368,6 +369,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (clp->cl_minorversion != 0) __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I); if (error == -EINVAL) error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); @@ -924,7 +926,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, dprintk("Server FSID: %llx:%llx\n", (unsigned long long) server->fsid.major, (unsigned long long) server->fsid.minor); - dprintk("Mount FH: %d\n", mntfh->size); + nfs_display_fhandle(mntfh, "Pseudo-fs root FH"); nfs4_session_set_rwsize(server); @@ -947,9 +949,8 @@ out: * Create a version 4 volume record */ static int nfs4_init_server(struct nfs_server *server, - const struct nfs_parsed_mount_data *data) + struct nfs_parsed_mount_data *data) { - rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; struct rpc_timeout timeparms; int error; @@ -961,9 +962,15 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; server->options = data->options; + server->auth_info = data->auth_info; - if (data->auth_flavor_len >= 1) - pseudoflavor = data->auth_flavors[0]; + /* Use the first specified auth flavor. If this flavor isn't + * allowed by the server, use the SECINFO path to try the + * other specified flavors */ + if (data->auth_info.flavor_len >= 1) + data->selected_flavor = data->auth_info.flavors[0]; + else + data->selected_flavor = RPC_AUTH_UNIX; /* Get a client record */ error = nfs4_set_client(server, @@ -971,7 +978,7 @@ static int nfs4_init_server(struct nfs_server *server, (const struct sockaddr *)&data->nfs_server.address, data->nfs_server.addrlen, data->client_address, - pseudoflavor, + data->selected_flavor, data->nfs_server.protocol, &timeparms, data->minorversion, @@ -991,7 +998,8 @@ static int nfs4_init_server(struct nfs_server *server, server->port = data->nfs_server.port; - error = nfs_init_server_rpcclient(server, &timeparms, pseudoflavor); + error = nfs_init_server_rpcclient(server, &timeparms, + data->selected_flavor); error: /* Done */ @@ -1018,7 +1026,7 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, if (!server) return ERR_PTR(-ENOMEM); - auth_probe = mount_info->parsed->auth_flavor_len < 1; + auth_probe = mount_info->parsed->auth_info.flavor_len < 1; /* set up the general RPC client */ error = nfs4_init_server(server, mount_info->parsed); @@ -1046,6 +1054,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, { struct nfs_client *parent_client; struct nfs_server *server, *parent_server; + bool auth_probe; int error; dprintk("--> nfs4_create_referral_server()\n"); @@ -1078,8 +1087,9 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, if (error < 0) goto error; - error = nfs4_server_common_setup(server, mntfh, - !(parent_server->flags & NFS_MOUNT_SECFLAVOUR)); + auth_probe = parent_server->auth_info.flavor_len < 1; + + error = nfs4_server_common_setup(server, mntfh, auth_probe); if (error < 0) goto error; @@ -1091,3 +1101,111 @@ error: dprintk("<-- nfs4_create_referral_server() = error %d\n", error); return ERR_PTR(error); } + +/* + * Grab the destination's particulars, including lease expiry time. + * + * Returns zero if probe succeeded and retrieved FSID matches the FSID + * we have cached. + */ +static int nfs_probe_destination(struct nfs_server *server) +{ + struct inode *inode = server->super->s_root->d_inode; + struct nfs_fattr *fattr; + int error; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + return -ENOMEM; + + /* Sanity: the probe won't work if the destination server + * does not recognize the migrated FH. */ + error = nfs_probe_fsinfo(server, NFS_FH(inode), fattr); + + nfs_free_fattr(fattr); + return error; +} + +/** + * nfs4_update_server - Move an nfs_server to a different nfs_client + * + * @server: represents FSID to be moved + * @hostname: new end-point's hostname + * @sap: new end-point's socket address + * @salen: size of "sap" + * + * The nfs_server must be quiescent before this function is invoked. + * Either its session is drained (NFSv4.1+), or its transport is + * plugged and drained (NFSv4.0). + * + * Returns zero on success, or a negative errno value. + */ +int nfs4_update_server(struct nfs_server *server, const char *hostname, + struct sockaddr *sap, size_t salen) +{ + struct nfs_client *clp = server->nfs_client; + struct rpc_clnt *clnt = server->client; + struct xprt_create xargs = { + .ident = clp->cl_proto, + .net = &init_net, + .dstaddr = sap, + .addrlen = salen, + .servername = hostname, + }; + char buf[INET6_ADDRSTRLEN + 1]; + struct sockaddr_storage address; + struct sockaddr *localaddr = (struct sockaddr *)&address; + int error; + + dprintk("--> %s: move FSID %llx:%llx to \"%s\")\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + hostname); + + error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout); + if (error != 0) { + dprintk("<-- %s(): rpc_switch_client_transport returned %d\n", + __func__, error); + goto out; + } + + error = rpc_localaddr(clnt, localaddr, sizeof(address)); + if (error != 0) { + dprintk("<-- %s(): rpc_localaddr returned %d\n", + __func__, error); + goto out; + } + + error = -EAFNOSUPPORT; + if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0) { + dprintk("<-- %s(): rpc_ntop returned %d\n", + __func__, error); + goto out; + } + + nfs_server_remove_lists(server); + error = nfs4_set_client(server, hostname, sap, salen, buf, + clp->cl_rpcclient->cl_auth->au_flavor, + clp->cl_proto, clnt->cl_timeout, + clp->cl_minorversion, clp->cl_net); + nfs_put_client(clp); + if (error != 0) { + nfs_server_insert_lists(server); + dprintk("<-- %s(): nfs4_set_client returned %d\n", + __func__, error); + goto out; + } + + if (server->nfs_client->cl_hostname == NULL) + server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + nfs_server_insert_lists(server); + + error = nfs_probe_destination(server); + if (error < 0) + goto out; + + dprintk("<-- %s() succeeded\n", __func__); + +out: + return error; +} diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 5b8a618a0f7a..1f01b55692ee 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -19,6 +19,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct inode *dir; unsigned openflags = filp->f_flags; struct iattr attr; + int opened = 0; int err; /* @@ -55,7 +56,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) nfs_wb_all(inode); } - inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, &opened); if (IS_ERR(inode)) { err = PTR_ERR(inode); switch (err) { diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index 95604f64cab8..c7c295e556ed 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -185,6 +185,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds) if (status) goto out_put; + smp_wmb(); ds->ds_clp = clp; dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); out: @@ -801,34 +802,35 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr; struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx]; struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); - - if (filelayout_test_devid_unavailable(devid)) - return NULL; + struct nfs4_pnfs_ds *ret = ds; if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", __func__, ds_idx); filelayout_mark_devid_invalid(devid); - return NULL; + goto out; } + smp_rmb(); if (ds->ds_clp) - return ds; + goto out_test_devid; if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); int err; err = nfs4_ds_connect(s, ds); - if (err) { + if (err) nfs4_mark_deviceid_unavailable(devid); - ds = NULL; - } nfs4_clear_ds_conn_bit(ds); } else { /* Either ds is connected, or ds is NULL */ nfs4_wait_ds_connect(ds); } - return ds; +out_test_devid: + if (filelayout_test_devid_unavailable(devid)) + ret = NULL; +out: + return ret; } module_param(dataserver_retrans, uint, 0644); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 2288cd3c9278..c08cbf40c59e 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -137,6 +137,7 @@ static size_t nfs_parse_server_name(char *string, size_t len, /** * nfs_find_best_sec - Find a security mechanism supported locally + * @server: NFS server struct * @flavors: List of security tuples returned by SECINFO procedure * * Return the pseudoflavor of the first security mechanism in @@ -145,7 +146,8 @@ static size_t nfs_parse_server_name(char *string, size_t len, * 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) +static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server, + struct nfs4_secinfo_flavors *flavors) { rpc_authflavor_t pseudoflavor; struct nfs4_secinfo4 *secinfo; @@ -160,12 +162,19 @@ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) case RPC_AUTH_GSS: pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor, &secinfo->flavor_info); - if (pseudoflavor != RPC_AUTH_MAXFLAVOR) + /* make sure pseudoflavor matches sec= mount opt */ + if (pseudoflavor != RPC_AUTH_MAXFLAVOR && + nfs_auth_info_match(&server->auth_info, + pseudoflavor)) return pseudoflavor; break; } } + /* if there were any sec= options then nothing matched */ + if (server->auth_info.flavor_len > 0) + return -EPERM; + return RPC_AUTH_UNIX; } @@ -187,7 +196,7 @@ static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr goto out; } - flavor = nfs_find_best_sec(flavors); + flavor = nfs_find_best_sec(NFS_SERVER(inode), flavors); out: put_page(page); @@ -390,7 +399,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, if (client->cl_auth->au_flavor != flavor) flavor = client->cl_auth->au_flavor; - else if (!(server->flags & NFS_MOUNT_SECFLAVOUR)) { + else { rpc_authflavor_t new = nfs4_negotiate_security(dir, name); if ((int)new >= 0) flavor = new; @@ -400,3 +409,104 @@ out: rpc_shutdown_client(client); return mnt; } + +/* + * Try one location from the fs_locations array. + * + * Returns zero on success, or a negative errno value. + */ +static int nfs4_try_replacing_one_location(struct nfs_server *server, + char *page, char *page2, + const struct nfs4_fs_location *location) +{ + const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct sockaddr *sap; + unsigned int s; + size_t salen; + int error; + + sap = kmalloc(addr_bufsize, GFP_KERNEL); + if (sap == NULL) + return -ENOMEM; + + error = -ENOENT; + for (s = 0; s < location->nservers; s++) { + const struct nfs4_string *buf = &location->servers[s]; + char *hostname; + + if (buf->len <= 0 || buf->len > PAGE_SIZE) + continue; + + if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len) != NULL) + continue; + + salen = nfs_parse_server_name(buf->data, buf->len, + sap, addr_bufsize, server); + if (salen == 0) + continue; + rpc_set_port(sap, NFS_PORT); + + error = -ENOMEM; + hostname = kstrndup(buf->data, buf->len, GFP_KERNEL); + if (hostname == NULL) + break; + + error = nfs4_update_server(server, hostname, sap, salen); + kfree(hostname); + if (error == 0) + break; + } + + kfree(sap); + return error; +} + +/** + * nfs4_replace_transport - set up transport to destination server + * + * @server: export being migrated + * @locations: fs_locations array + * + * Returns zero on success, or a negative errno value. + * + * The client tries all the entries in the "locations" array, in the + * order returned by the server, until one works or the end of the + * array is reached. + */ +int nfs4_replace_transport(struct nfs_server *server, + const struct nfs4_fs_locations *locations) +{ + char *page = NULL, *page2 = NULL; + int loc, error; + + error = -ENOENT; + if (locations == NULL || locations->nlocations <= 0) + goto out; + + error = -ENOMEM; + page = (char *) __get_free_page(GFP_USER); + if (!page) + goto out; + page2 = (char *) __get_free_page(GFP_USER); + if (!page2) + goto out; + + for (loc = 0; loc < locations->nlocations; loc++) { + const struct nfs4_fs_location *location = + &locations->locations[loc]; + + if (location == NULL || location->nservers <= 0 || + location->rootpath.ncomponents == 0) + continue; + + error = nfs4_try_replacing_one_location(server, page, + page2, location); + if (error == 0) + break; + } + +out: + free_page((unsigned long)page); + free_page((unsigned long)page2); + return error; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 989bb9d3074d..b02c4cc7b0a9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -384,6 +384,14 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc case -NFS4ERR_STALE_CLIENTID: nfs4_schedule_lease_recovery(clp); goto wait_on_recovery; + case -NFS4ERR_MOVED: + ret = nfs4_schedule_migration_recovery(server); + if (ret < 0) + break; + goto wait_on_recovery; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + goto wait_on_recovery; #if defined(CONFIG_NFS_V4_1) case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -431,6 +439,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc return nfs4_map_errors(ret); wait_on_recovery: ret = nfs4_wait_clnt_recover(clp); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -EIO; if (ret == 0) exception->retry = 1; return ret; @@ -912,6 +922,7 @@ struct nfs4_opendata { struct iattr attrs; unsigned long timestamp; unsigned int rpc_done : 1; + unsigned int file_created : 1; unsigned int is_recover : 1; int rpc_status; int cancelled; @@ -1317,31 +1328,24 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) int ret; if (!data->rpc_done) { - ret = data->rpc_status; - goto err; + if (data->rpc_status) { + ret = data->rpc_status; + goto err; + } + /* cached opens have already been processed */ + goto update; } - ret = -ESTALE; - if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) || - !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) || - !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE)) - goto err; - - ret = -ENOMEM; - state = nfs4_get_open_state(inode, data->owner); - if (state == NULL) - goto err; - ret = nfs_refresh_inode(inode, &data->f_attr); if (ret) goto err; - nfs_setsecurity(inode, &data->f_attr, data->f_label); - if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); +update: update_open_stateid(state, &data->o_res.stateid, NULL, data->o_arg.fmode); + atomic_inc(&state->count); return state; err: @@ -1574,6 +1578,12 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct /* Don't recall a delegation if it was lost */ nfs4_schedule_lease_recovery(server->nfs_client); return -EAGAIN; + case -NFS4ERR_MOVED: + nfs4_schedule_migration_recovery(server); + return -EAGAIN; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(server->nfs_client); + return -EAGAIN; case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: @@ -1946,8 +1956,13 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(server, &data->f_attr); - if (o_arg->open_flags & O_CREAT) + if (o_arg->open_flags & O_CREAT) { update_changeattr(dir, &o_res->cinfo); + if (o_arg->open_flags & O_EXCL) + data->file_created = 1; + else if (o_res->cinfo.before != o_res->cinfo.after) + data->file_created = 1; + } if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) server->caps &= ~NFS_CAP_POSIX_LOCK; if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { @@ -2191,7 +2206,8 @@ static int _nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, struct iattr *sattr, - struct nfs4_label *label) + struct nfs4_label *label, + int *opened) { struct nfs4_state_owner *sp; struct nfs4_state *state = NULL; @@ -2261,6 +2277,8 @@ static int _nfs4_do_open(struct inode *dir, nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel); } } + if (opendata->file_created) + *opened |= FILE_CREATED; if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) *ctx_th = opendata->f_attr.mdsthreshold; @@ -2289,7 +2307,8 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, struct iattr *sattr, - struct nfs4_label *label) + struct nfs4_label *label, + int *opened) { struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { }; @@ -2297,7 +2316,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, int status; do { - status = _nfs4_do_open(dir, ctx, flags, sattr, label); + status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened); res = ctx->state; trace_nfs4_open_file(ctx, flags, status); if (status == 0) @@ -2659,7 +2678,8 @@ out: } static struct inode * -nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags, struct iattr *attr) +nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, + int open_flags, struct iattr *attr, int *opened) { struct nfs4_state *state; struct nfs4_label l = {0, 0, 0, NULL}, *label = NULL; @@ -2667,7 +2687,7 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags label = nfs4_label_init_security(dir, ctx->dentry, attr, &l); /* Protect against concurrent sillydeletes */ - state = nfs4_do_open(dir, ctx, open_flags, attr, label); + state = nfs4_do_open(dir, ctx, open_flags, attr, label, opened); nfs4_label_release_security(label); @@ -2853,11 +2873,24 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, 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; + if (server->auth_info.flavor_len > 0) { + /* try each flavor specified by user */ + for (i = 0; i < server->auth_info.flavor_len; i++) { + status = nfs4_lookup_root_sec(server, fhandle, info, + server->auth_info.flavors[i]); + if (status == -NFS4ERR_WRONGSEC || status == -EACCES) + continue; + break; + } + } else { + /* no flavors specified by user, try default list */ + 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; + } } /* @@ -2899,9 +2932,6 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle, status = nfs4_lookup_root(server, fhandle, info); if (status != -NFS4ERR_WRONGSEC) break; - /* Did user force a 'sec=' mount option? */ - if (server->flags & NFS_MOUNT_SECFLAVOUR) - break; default: status = nfs4_do_find_root_sec(server, fhandle, info); } @@ -2970,11 +3000,16 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, status = nfs4_proc_fs_locations(client, dir, name, locations, page); if (status != 0) goto out; - /* Make sure server returned a different fsid for the referral */ + + /* + * If the fsid didn't change, this is a migration event, not a + * referral. Cause us to drop into the exception handler, which + * will kick off migration recovery. + */ if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) { dprintk("%s: server did not return a different fsid for" " a referral at %s\n", __func__, name->name); - status = -EIO; + status = -NFS4ERR_MOVED; goto out; } /* Fixup attributes for the nfs_lookup() call to nfs_fhget() */ @@ -3154,9 +3189,6 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, err = -EPERM; if (client != *clnt) goto out; - /* No security negotiation if the user specified 'sec=' */ - if (NFS_SERVER(dir)->flags & NFS_MOUNT_SECFLAVOUR) - goto out; client = nfs4_create_sec_client(client, dir, name); if (IS_ERR(client)) return PTR_ERR(client); @@ -3332,6 +3364,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, struct nfs4_label l, *ilabel = NULL; struct nfs_open_context *ctx; struct nfs4_state *state; + int opened = 0; int status = 0; ctx = alloc_nfs_open_context(dentry, FMODE_READ); @@ -3341,7 +3374,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, ilabel = nfs4_label_init_security(dir, dentry, sattr, &l); sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, ctx, flags, sattr, ilabel); + state = nfs4_do_open(dir, ctx, flags, sattr, ilabel, &opened); if (IS_ERR(state)) { status = PTR_ERR(state); goto out; @@ -4209,7 +4242,13 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata) unsigned long timestamp = data->timestamp; trace_nfs4_renew_async(clp, task->tk_status); - if (task->tk_status < 0) { + switch (task->tk_status) { + case 0: + break; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + break; + default: /* Unless we're shutting down, schedule state recovery! */ if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0) return; @@ -4723,17 +4762,24 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, if (state == NULL) break; if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto stateid_invalid; + goto recovery_failed; goto wait_on_recovery; case -NFS4ERR_EXPIRED: if (state != NULL) { if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto stateid_invalid; + goto recovery_failed; } case -NFS4ERR_STALE_STATEID: case -NFS4ERR_STALE_CLIENTID: nfs4_schedule_lease_recovery(clp); goto wait_on_recovery; + case -NFS4ERR_MOVED: + if (nfs4_schedule_migration_recovery(server) < 0) + goto recovery_failed; + goto wait_on_recovery; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + goto wait_on_recovery; #if defined(CONFIG_NFS_V4_1) case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -4745,29 +4791,28 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, dprintk("%s ERROR %d, Reset session\n", __func__, task->tk_status); nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - task->tk_status = 0; - return -EAGAIN; + goto restart_call; #endif /* CONFIG_NFS_V4_1 */ case -NFS4ERR_DELAY: nfs_inc_server_stats(server, NFSIOS_DELAY); case -NFS4ERR_GRACE: rpc_delay(task, NFS4_POLL_RETRY_MAX); - task->tk_status = 0; - return -EAGAIN; case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_OLD_STATEID: - task->tk_status = 0; - return -EAGAIN; + goto restart_call; } task->tk_status = nfs4_map_errors(task->tk_status); return 0; -stateid_invalid: +recovery_failed: 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) rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + goto recovery_failed; +restart_call: task->tk_status = 0; return -EAGAIN; } @@ -5094,6 +5139,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock status = 0; } request->fl_ops->fl_release_private(request); + request->fl_ops = NULL; out: return status; } @@ -5767,6 +5813,7 @@ struct nfs_release_lockowner_data { struct nfs_release_lockowner_args args; struct nfs4_sequence_args seq_args; struct nfs4_sequence_res seq_res; + unsigned long timestamp; }; static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata) @@ -5774,12 +5821,27 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata struct nfs_release_lockowner_data *data = calldata; nfs40_setup_sequence(data->server, &data->seq_args, &data->seq_res, task); + data->timestamp = jiffies; } static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) { struct nfs_release_lockowner_data *data = calldata; + struct nfs_server *server = data->server; + nfs40_sequence_done(task, &data->seq_res); + + switch (task->tk_status) { + case 0: + renew_lease(server, data->timestamp); + break; + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_EXPIRED: + case -NFS4ERR_LEASE_MOVED: + case -NFS4ERR_DELAY: + if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) + rpc_restart_call_prepare(task); + } } static void nfs4_release_lockowner_release(void *calldata) @@ -5978,6 +6040,283 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, return err; } +/* + * This operation also signals the server that this client is + * performing migration recovery. The server can stop returning + * NFS4ERR_LEASE_MOVED to this client. A RENEW operation is + * appended to this compound to identify the client ID which is + * performing recovery. + */ +static int _nfs40_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .clientid = server->nfs_client->cl_clientid, + .fh = NFS_FH(inode), + .page = page, + .bitmask = bitmask, + .migration = 1, /* skip LOOKUP */ + .renew = 1, /* append RENEW */ + }; + struct nfs4_fs_locations_res res = { + .fs_locations = locations, + .migration = 1, + .renew = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + nfs_fattr_init(&locations->fattr); + locations->server = server; + locations->nlocations = 0; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + if (status) + return status; + + renew_lease(server, now); + return 0; +} + +#ifdef CONFIG_NFS_V4_1 + +/* + * This operation also signals the server that this client is + * performing migration recovery. The server can stop asserting + * SEQ4_STATUS_LEASE_MOVED for this client. The client ID + * performing this operation is identified in the SEQUENCE + * operation in this compound. + * + * When the client supports GETATTR(fs_locations_info), it can + * be plumbed in here. + */ +static int _nfs41_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .fh = NFS_FH(inode), + .page = page, + .bitmask = bitmask, + .migration = 1, /* skip LOOKUP */ + }; + struct nfs4_fs_locations_res res = { + .fs_locations = locations, + .migration = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + nfs_fattr_init(&locations->fattr); + locations->server = server; + locations->nlocations = 0; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + if (status == NFS4_OK && + res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) + status = -NFS4ERR_LEASE_MOVED; + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_proc_get_locations - discover locations for a migrated FSID + * @inode: inode on FSID that is migrating + * @locations: result of query + * @page: buffer + * @cred: credential to use for this operation + * + * Returns NFS4_OK on success, a negative NFS4ERR status code if the + * operation failed, or a negative errno if a local error occurred. + * + * On success, "locations" is filled in, but if the server has + * no locations information, NFS_ATTR_FATTR_V4_LOCATIONS is not + * asserted. + * + * -NFS4ERR_LEASE_MOVED is returned if the server still has leases + * from this client that require migration recovery. + */ +int nfs4_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + const struct nfs4_mig_recovery_ops *ops = + clp->cl_mvops->mig_recovery_ops; + struct nfs4_exception exception = { }; + int status; + + dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + nfs_display_fhandle(NFS_FH(inode), __func__); + + do { + status = ops->get_locations(inode, locations, page, cred); + if (status != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, status, &exception); + } while (exception.retry); + return status; +} + +/* + * This operation also signals the server that this client is + * performing "lease moved" recovery. The server can stop + * returning NFS4ERR_LEASE_MOVED to this client. A RENEW operation + * is appended to this compound to identify the client ID which is + * performing recovery. + */ +static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + struct rpc_clnt *clnt = server->client; + struct nfs4_fsid_present_arg args = { + .fh = NFS_FH(inode), + .clientid = clp->cl_clientid, + .renew = 1, /* append RENEW */ + }; + struct nfs4_fsid_present_res res = { + .renew = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + res.fh = nfs_alloc_fhandle(); + if (res.fh == NULL) + return -ENOMEM; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + nfs_free_fhandle(res.fh); + if (status) + return status; + + do_renew_lease(clp, now); + return 0; +} + +#ifdef CONFIG_NFS_V4_1 + +/* + * This operation also signals the server that this client is + * performing "lease moved" recovery. The server can stop asserting + * SEQ4_STATUS_LEASE_MOVED for this client. The client ID performing + * this operation is identified in the SEQUENCE operation in this + * compound. + */ +static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + struct nfs4_fsid_present_arg args = { + .fh = NFS_FH(inode), + }; + struct nfs4_fsid_present_res res = { + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + res.fh = nfs_alloc_fhandle(); + if (res.fh == NULL) + return -ENOMEM; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + nfs_free_fhandle(res.fh); + if (status == NFS4_OK && + res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) + status = -NFS4ERR_LEASE_MOVED; + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_proc_fsid_present - Is this FSID present or absent on server? + * @inode: inode on FSID to check + * @cred: credential to use for this operation + * + * Server indicates whether the FSID is present, moved, or not + * recognized. This operation is necessary to clear a LEASE_MOVED + * condition for this client ID. + * + * Returns NFS4_OK if the FSID is present on this server, + * -NFS4ERR_MOVED if the FSID is no longer present, a negative + * NFS4ERR code if some error occurred on the server, or a + * negative errno if a local failure occurred. + */ +int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + const struct nfs4_mig_recovery_ops *ops = + clp->cl_mvops->mig_recovery_ops; + struct nfs4_exception exception = { }; + int status; + + dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + nfs_display_fhandle(NFS_FH(inode), __func__); + + do { + status = ops->fsid_present(inode, cred); + if (status != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, status, &exception); + } while (exception.retry); + return status; +} + /** * If 'use_integrity' is true and the state managment nfs_client * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient @@ -6264,8 +6603,14 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, struct nfs41_exchange_id_args args = { .verifier = &verifier, .client = clp, +#ifdef CONFIG_NFS_V4_1_MIGRATION .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | - EXCHGID4_FLAG_BIND_PRINC_STATEID, + EXCHGID4_FLAG_BIND_PRINC_STATEID | + EXCHGID4_FLAG_SUPP_MOVED_MIGR, +#else + .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | + EXCHGID4_FLAG_BIND_PRINC_STATEID, +#endif }; struct nfs41_exchange_id_res res = { 0 @@ -7564,8 +7909,10 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, { int err; struct page *page; - rpc_authflavor_t flavor; + rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; struct nfs4_secinfo_flavors *flavors; + struct nfs4_secinfo4 *secinfo; + int i; page = alloc_page(GFP_KERNEL); if (!page) { @@ -7587,9 +7934,34 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, if (err) goto out_freepage; - flavor = nfs_find_best_sec(flavors); - if (err == 0) - err = nfs4_lookup_root_sec(server, fhandle, info, flavor); + for (i = 0; i < flavors->num_flavors; i++) { + secinfo = &flavors->flavors[i]; + + switch (secinfo->flavor) { + case RPC_AUTH_NULL: + case RPC_AUTH_UNIX: + case RPC_AUTH_GSS: + flavor = rpcauth_get_pseudoflavor(secinfo->flavor, + &secinfo->flavor_info); + break; + default: + flavor = RPC_AUTH_MAXFLAVOR; + break; + } + + if (!nfs_auth_info_match(&server->auth_info, flavor)) + flavor = RPC_AUTH_MAXFLAVOR; + + if (flavor != RPC_AUTH_MAXFLAVOR) { + err = nfs4_lookup_root_sec(server, fhandle, + info, flavor); + if (!err) + break; + } + } + + if (flavor == RPC_AUTH_MAXFLAVOR) + err = -EPERM; out_freepage: put_page(page); @@ -7851,6 +8223,18 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = { }; #endif +static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = { + .get_locations = _nfs40_proc_get_locations, + .fsid_present = _nfs40_proc_fsid_present, +}; + +#if defined(CONFIG_NFS_V4_1) +static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = { + .get_locations = _nfs41_proc_get_locations, + .fsid_present = _nfs41_proc_fsid_present, +}; +#endif /* CONFIG_NFS_V4_1 */ + static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, .init_caps = NFS_CAP_READDIRPLUS @@ -7866,6 +8250,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .reboot_recovery_ops = &nfs40_reboot_recovery_ops, .nograce_recovery_ops = &nfs40_nograce_recovery_ops, .state_renewal_ops = &nfs40_state_renewal_ops, + .mig_recovery_ops = &nfs40_mig_recovery_ops, }; #if defined(CONFIG_NFS_V4_1) @@ -7886,6 +8271,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, .state_renewal_ops = &nfs41_state_renewal_ops, + .mig_recovery_ops = &nfs41_mig_recovery_ops, }; #endif diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index cc14cbb78b73..452f4c8dadea 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -239,8 +239,6 @@ static void nfs4_end_drain_session(struct nfs_client *clp) } } -#if defined(CONFIG_NFS_V4_1) - static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl) { set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); @@ -270,6 +268,8 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) return nfs4_drain_slot_tbl(&ses->fc_slot_table); } +#if defined(CONFIG_NFS_V4_1) + static int nfs41_setup_state_renewal(struct nfs_client *clp) { int status; @@ -1197,20 +1197,74 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp) } EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery); +/** + * nfs4_schedule_migration_recovery - trigger migration recovery + * + * @server: FSID that is migrating + * + * Returns zero if recovery has started, otherwise a negative NFS4ERR + * value is returned. + */ +int nfs4_schedule_migration_recovery(const struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + + if (server->fh_expire_type != NFS4_FH_PERSISTENT) { + pr_err("NFS: volatile file handles not supported (server %s)\n", + clp->cl_hostname); + return -NFS4ERR_IO; + } + + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -NFS4ERR_IO; + + dprintk("%s: scheduling migration recovery for (%llx:%llx) on %s\n", + __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + + set_bit(NFS_MIG_IN_TRANSITION, + &((struct nfs_server *)server)->mig_status); + set_bit(NFS4CLNT_MOVED, &clp->cl_state); + + nfs4_schedule_state_manager(clp); + return 0; +} +EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery); + +/** + * nfs4_schedule_lease_moved_recovery - start lease-moved recovery + * + * @clp: server to check for moved leases + * + */ +void nfs4_schedule_lease_moved_recovery(struct nfs_client *clp) +{ + dprintk("%s: scheduling lease-moved recovery for client ID %llx on %s\n", + __func__, clp->cl_clientid, clp->cl_hostname); + + set_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state); + nfs4_schedule_state_manager(clp); +} +EXPORT_SYMBOL_GPL(nfs4_schedule_lease_moved_recovery); + int nfs4_wait_clnt_recover(struct nfs_client *clp) { int res; might_sleep(); + atomic_inc(&clp->cl_count); res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, nfs_wait_bit_killable, TASK_KILLABLE); if (res) - return res; - + goto out; if (clp->cl_cons_state < 0) - return clp->cl_cons_state; - return 0; + res = clp->cl_cons_state; +out: + nfs_put_client(clp); + return res; } int nfs4_client_recover_expired_lease(struct nfs_client *clp) @@ -1375,8 +1429,8 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: goto out; default: - printk(KERN_ERR "NFS: %s: unhandled error %d. " - "Zeroing state\n", __func__, status); + printk(KERN_ERR "NFS: %s: unhandled error %d\n", + __func__, status); case -ENOMEM: case -NFS4ERR_DENIED: case -NFS4ERR_RECLAIM_BAD: @@ -1439,15 +1493,12 @@ restart: } switch (status) { default: - printk(KERN_ERR "NFS: %s: unhandled error %d. " - "Zeroing state\n", __func__, status); + printk(KERN_ERR "NFS: %s: unhandled error %d\n", + __func__, status); case -ENOENT: case -ENOMEM: case -ESTALE: - /* - * Open state on this file cannot be recovered - * All we can do is revert to using the zero stateid. - */ + /* Open state on this file cannot be recovered */ nfs4_state_mark_recovery_failed(state, status); break; case -EAGAIN: @@ -1628,7 +1679,6 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) nfs4_state_end_reclaim_reboot(clp); break; case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_LEASE_MOVED: set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); @@ -1829,6 +1879,168 @@ static int nfs4_purge_lease(struct nfs_client *clp) return 0; } +/* + * Try remote migration of one FSID from a source server to a + * destination server. The source server provides a list of + * potential destinations. + * + * Returns zero or a negative NFS4ERR status code. + */ +static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_fs_locations *locations = NULL; + struct inode *inode; + struct page *page; + int status, result; + + dprintk("--> %s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + + result = 0; + page = alloc_page(GFP_KERNEL); + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (page == NULL || locations == NULL) { + dprintk("<-- %s: no memory\n", __func__); + goto out; + } + + inode = server->super->s_root->d_inode; + result = nfs4_proc_get_locations(inode, locations, page, cred); + if (result) { + dprintk("<-- %s: failed to retrieve fs_locations: %d\n", + __func__, result); + goto out; + } + + result = -NFS4ERR_NXIO; + if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { + dprintk("<-- %s: No fs_locations data, migration skipped\n", + __func__); + goto out; + } + + nfs4_begin_drain_session(clp); + + status = nfs4_replace_transport(server, locations); + if (status != 0) { + dprintk("<-- %s: failed to replace transport: %d\n", + __func__, status); + goto out; + } + + result = 0; + dprintk("<-- %s: migration succeeded\n", __func__); + +out: + if (page != NULL) + __free_page(page); + kfree(locations); + if (result) { + pr_err("NFS: migration recovery failed (server %s)\n", + clp->cl_hostname); + set_bit(NFS_MIG_FAILED, &server->mig_status); + } + return result; +} + +/* + * Returns zero or a negative NFS4ERR status code. + */ +static int nfs4_handle_migration(struct nfs_client *clp) +{ + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + struct nfs_server *server; + struct rpc_cred *cred; + + dprintk("%s: migration reported on \"%s\"\n", __func__, + clp->cl_hostname); + + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) + return -NFS4ERR_NOENT; + + clp->cl_mig_gen++; +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + int status; + + if (server->mig_gen == clp->cl_mig_gen) + continue; + server->mig_gen = clp->cl_mig_gen; + + if (!test_and_clear_bit(NFS_MIG_IN_TRANSITION, + &server->mig_status)) + continue; + + rcu_read_unlock(); + status = nfs4_try_migration(server, cred); + if (status < 0) { + put_rpccred(cred); + return status; + } + goto restart; + } + rcu_read_unlock(); + put_rpccred(cred); + return 0; +} + +/* + * Test each nfs_server on the clp's cl_superblocks list to see + * if it's moved to another server. Stop when the server no longer + * returns NFS4ERR_LEASE_MOVED. + */ +static int nfs4_handle_lease_moved(struct nfs_client *clp) +{ + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + struct nfs_server *server; + struct rpc_cred *cred; + + dprintk("%s: lease moved reported on \"%s\"\n", __func__, + clp->cl_hostname); + + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) + return -NFS4ERR_NOENT; + + clp->cl_mig_gen++; +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + struct inode *inode; + int status; + + if (server->mig_gen == clp->cl_mig_gen) + continue; + server->mig_gen = clp->cl_mig_gen; + + rcu_read_unlock(); + + inode = server->super->s_root->d_inode; + status = nfs4_proc_fsid_present(inode, cred); + if (status != -NFS4ERR_MOVED) + goto restart; /* wasn't this one */ + if (nfs4_try_migration(server, cred) == -NFS4ERR_LEASE_MOVED) + goto restart; /* there are more */ + goto out; + } + rcu_read_unlock(); + +out: + put_rpccred(cred); + return 0; +} + /** * nfs4_discover_server_trunking - Detect server IP address trunking * @@ -2017,9 +2229,10 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) nfs41_handle_server_reboot(clp); if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | - SEQ4_STATUS_ADMIN_STATE_REVOKED | - SEQ4_STATUS_LEASE_MOVED)) + SEQ4_STATUS_ADMIN_STATE_REVOKED)) nfs41_handle_state_revoked(clp); + if (flags & SEQ4_STATUS_LEASE_MOVED) + nfs4_schedule_lease_moved_recovery(clp); if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) nfs41_handle_recallable_state_revoked(clp); if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT) @@ -2157,7 +2370,20 @@ static void nfs4_state_manager(struct nfs_client *clp) status = nfs4_check_lease(clp); if (status < 0) goto out_error; - continue; + } + + if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { + section = "migration"; + status = nfs4_handle_migration(clp); + if (status < 0) + goto out_error; + } + + if (test_and_clear_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state)) { + section = "lease moved"; + status = nfs4_handle_lease_moved(clp); + if (status < 0) + goto out_error; } /* First recover reboot state... */ diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index e26acdd1a645..65ab0a0ca1c4 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -261,9 +261,9 @@ struct dentry *nfs4_try_mount(int flags, const char *dev_name, res = nfs_follow_remote_path(root_mnt, export_path); - dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n", - IS_ERR(res) ? PTR_ERR(res) : 0, - IS_ERR(res) ? " [error]" : ""); + dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", + PTR_ERR_OR_ZERO(res), + IS_ERR(res) ? " [error]" : ""); return res; } @@ -319,9 +319,9 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, data->mnt_path = export_path; res = nfs_follow_remote_path(root_mnt, export_path); - dprintk("<-- nfs4_referral_mount() = %ld%s\n", - IS_ERR(res) ? PTR_ERR(res) : 0, - IS_ERR(res) ? " [error]" : ""); + dprintk("<-- nfs4_referral_mount() = %d%s\n", + PTR_ERR_OR_ZERO(res), + IS_ERR(res) ? " [error]" : ""); return res; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 79210d23f607..f903389d90f1 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -595,11 +595,13 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_getattr_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_getattr_maxsz) + encode_getattr_maxsz + \ + encode_renew_maxsz) #define NFS4_dec_getattr_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_getattr_maxsz) + decode_getattr_maxsz + \ + decode_renew_maxsz) #define NFS4_enc_lookup_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -736,13 +738,15 @@ static int nfs4_stat_to_errno(int); encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_lookup_maxsz + \ - encode_fs_locations_maxsz) + encode_fs_locations_maxsz + \ + encode_renew_maxsz) #define NFS4_dec_fs_locations_sz \ (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_lookup_maxsz + \ - decode_fs_locations_maxsz) + decode_fs_locations_maxsz + \ + decode_renew_maxsz) #define NFS4_enc_secinfo_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -751,6 +755,18 @@ static int nfs4_stat_to_errno(int); decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_secinfo_maxsz) +#define NFS4_enc_fsid_present_sz \ + (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getfh_maxsz + \ + encode_renew_maxsz) +#define NFS4_dec_fsid_present_sz \ + (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getfh_maxsz + \ + decode_renew_maxsz) #if defined(CONFIG_NFS_V4_1) #define NFS4_enc_bind_conn_to_session_sz \ (compound_encode_hdr_maxsz + \ @@ -2687,11 +2703,20 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); - encode_putfh(xdr, args->dir_fh, &hdr); - encode_lookup(xdr, args->name, &hdr); - replen = hdr.replen; /* get the attribute into args->page */ - encode_fs_locations(xdr, args->bitmask, &hdr); + if (args->migration) { + encode_putfh(xdr, args->fh, &hdr); + replen = hdr.replen; + encode_fs_locations(xdr, args->bitmask, &hdr); + if (args->renew) + encode_renew(xdr, args->clientid, &hdr); + } else { + encode_putfh(xdr, args->dir_fh, &hdr); + encode_lookup(xdr, args->name, &hdr); + replen = hdr.replen; + encode_fs_locations(xdr, args->bitmask, &hdr); + } + /* Set up reply kvec to capture returned fs_locations array. */ xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page, 0, PAGE_SIZE); encode_nops(&hdr); @@ -2715,6 +2740,26 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode FSID_PRESENT request + */ +static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_fsid_present_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getfh(xdr, &hdr); + if (args->renew) + encode_renew(xdr, args->clientid, &hdr); + encode_nops(&hdr); +} + #if defined(CONFIG_NFS_V4_1) /* * BIND_CONN_TO_SESSION request @@ -6824,13 +6869,26 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, status = decode_putfh(xdr); if (status) goto out; - status = decode_lookup(xdr); - if (status) - goto out; - xdr_enter_page(xdr, PAGE_SIZE); - status = decode_getfattr_generic(xdr, &res->fs_locations->fattr, + if (res->migration) { + xdr_enter_page(xdr, PAGE_SIZE); + status = decode_getfattr_generic(xdr, + &res->fs_locations->fattr, NULL, res->fs_locations, NULL, res->fs_locations->server); + if (status) + goto out; + if (res->renew) + status = decode_renew(xdr); + } else { + status = decode_lookup(xdr); + if (status) + goto out; + xdr_enter_page(xdr, PAGE_SIZE); + status = decode_getfattr_generic(xdr, + &res->fs_locations->fattr, + NULL, res->fs_locations, + NULL, res->fs_locations->server); + } out: return status; } @@ -6859,6 +6917,34 @@ out: return status; } +/* + * Decode FSID_PRESENT response + */ +static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_fsid_present_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + if (res->renew) + status = decode_renew(xdr); +out: + return status; +} + #if defined(CONFIG_NFS_V4_1) /* * Decode BIND_CONN_TO_SESSION response @@ -7373,6 +7459,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(FS_LOCATIONS, enc_fs_locations, dec_fs_locations), PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), PROC(SECINFO, enc_secinfo, dec_secinfo), + PROC(FSID_PRESENT, enc_fsid_present, dec_fsid_present), #if defined(CONFIG_NFS_V4_1) PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a03b9c6f9489..317d6fc2160e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -497,7 +497,8 @@ static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour) static const struct { rpc_authflavor_t flavour; const char *str; - } sec_flavours[] = { + } sec_flavours[NFS_AUTH_INFO_MAX_FLAVORS] = { + /* update NFS_AUTH_INFO_MAX_FLAVORS when this list changes! */ { RPC_AUTH_NULL, "null" }, { RPC_AUTH_UNIX, "sys" }, { RPC_AUTH_GSS_KRB5, "krb5" }, @@ -923,8 +924,7 @@ 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_MAXFLAVOR; - data->auth_flavor_len = 0; + data->selected_flavor = RPC_AUTH_MAXFLAVOR; data->minorversion = 0; data->need_mount = true; data->net = current->nsproxy->net_ns; @@ -1019,12 +1019,51 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) } } -static void nfs_set_auth_parsed_mount_data(struct nfs_parsed_mount_data *data, - rpc_authflavor_t pseudoflavor) +/* + * Add 'flavor' to 'auth_info' if not already present. + * Returns true if 'flavor' ends up in the list, false otherwise + */ +static bool nfs_auth_info_add(struct nfs_auth_info *auth_info, + rpc_authflavor_t flavor) +{ + unsigned int i; + unsigned int max_flavor_len = (sizeof(auth_info->flavors) / + sizeof(auth_info->flavors[0])); + + /* make sure this flavor isn't already in the list */ + for (i = 0; i < auth_info->flavor_len; i++) { + if (flavor == auth_info->flavors[i]) + return true; + } + + if (auth_info->flavor_len + 1 >= max_flavor_len) { + dfprintk(MOUNT, "NFS: too many sec= flavors\n"); + return false; + } + + auth_info->flavors[auth_info->flavor_len++] = flavor; + return true; +} + +/* + * Return true if 'match' is in auth_info or auth_info is empty. + * Return false otherwise. + */ +bool nfs_auth_info_match(const struct nfs_auth_info *auth_info, + rpc_authflavor_t match) { - data->auth_flavors[0] = pseudoflavor; - data->auth_flavor_len = 1; + int i; + + if (!auth_info->flavor_len) + return true; + + for (i = 0; i < auth_info->flavor_len; i++) { + if (auth_info->flavors[i] == match) + return true; + } + return false; } +EXPORT_SYMBOL_GPL(nfs_auth_info_match); /* * Parse the value of the 'sec=' option. @@ -1034,49 +1073,55 @@ static int nfs_parse_security_flavors(char *value, { substring_t args[MAX_OPT_ARGS]; rpc_authflavor_t pseudoflavor; + char *p; dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value); - switch (match_token(value, nfs_secflavor_tokens, args)) { - case Opt_sec_none: - pseudoflavor = RPC_AUTH_NULL; - break; - case Opt_sec_sys: - pseudoflavor = RPC_AUTH_UNIX; - break; - case Opt_sec_krb5: - pseudoflavor = RPC_AUTH_GSS_KRB5; - break; - case Opt_sec_krb5i: - pseudoflavor = RPC_AUTH_GSS_KRB5I; - break; - case Opt_sec_krb5p: - pseudoflavor = RPC_AUTH_GSS_KRB5P; - break; - case Opt_sec_lkey: - pseudoflavor = RPC_AUTH_GSS_LKEY; - break; - case Opt_sec_lkeyi: - pseudoflavor = RPC_AUTH_GSS_LKEYI; - break; - case Opt_sec_lkeyp: - pseudoflavor = RPC_AUTH_GSS_LKEYP; - break; - case Opt_sec_spkm: - pseudoflavor = RPC_AUTH_GSS_SPKM; - break; - case Opt_sec_spkmi: - pseudoflavor = RPC_AUTH_GSS_SPKMI; - break; - case Opt_sec_spkmp: - pseudoflavor = RPC_AUTH_GSS_SPKMP; - break; - default: - return 0; + while ((p = strsep(&value, ":")) != NULL) { + switch (match_token(p, nfs_secflavor_tokens, args)) { + case Opt_sec_none: + pseudoflavor = RPC_AUTH_NULL; + break; + case Opt_sec_sys: + pseudoflavor = RPC_AUTH_UNIX; + break; + case Opt_sec_krb5: + pseudoflavor = RPC_AUTH_GSS_KRB5; + break; + case Opt_sec_krb5i: + pseudoflavor = RPC_AUTH_GSS_KRB5I; + break; + case Opt_sec_krb5p: + pseudoflavor = RPC_AUTH_GSS_KRB5P; + break; + case Opt_sec_lkey: + pseudoflavor = RPC_AUTH_GSS_LKEY; + break; + case Opt_sec_lkeyi: + pseudoflavor = RPC_AUTH_GSS_LKEYI; + break; + case Opt_sec_lkeyp: + pseudoflavor = RPC_AUTH_GSS_LKEYP; + break; + case Opt_sec_spkm: + pseudoflavor = RPC_AUTH_GSS_SPKM; + break; + case Opt_sec_spkmi: + pseudoflavor = RPC_AUTH_GSS_SPKMI; + break; + case Opt_sec_spkmp: + pseudoflavor = RPC_AUTH_GSS_SPKMP; + break; + default: + dfprintk(MOUNT, + "NFS: sec= option '%s' not recognized\n", p); + return 0; + } + + if (!nfs_auth_info_add(&mnt->auth_info, pseudoflavor)) + return 0; } - mnt->flags |= NFS_MOUNT_SECFLAVOUR; - nfs_set_auth_parsed_mount_data(mnt, pseudoflavor); return 1; } @@ -1623,12 +1668,14 @@ out_security_failure: } /* - * Ensure that the specified authtype in args->auth_flavors[0] is supported by - * the server. Returns 0 if it's ok, and -EACCES if not. + * Ensure that a specified authtype in args->auth_info is supported by + * the server. Returns 0 and sets args->selected_flavor if it's ok, and + * -EACCES if not. */ -static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args, +static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, rpc_authflavor_t *server_authlist, unsigned int count) { + rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; unsigned int i; /* @@ -1640,17 +1687,20 @@ static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args, * can be used. */ for (i = 0; i < count; i++) { - if (args->auth_flavors[0] == server_authlist[i] || - server_authlist[i] == RPC_AUTH_NULL) + flavor = server_authlist[i]; + + if (nfs_auth_info_match(&args->auth_info, flavor) || + flavor == RPC_AUTH_NULL) goto out; } - dfprintk(MOUNT, "NFS: auth flavor %u not supported by server\n", - args->auth_flavors[0]); + dfprintk(MOUNT, + "NFS: specified auth flavors not supported by server\n"); return -EACCES; out: - dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]); + args->selected_flavor = flavor; + dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor); return 0; } @@ -1738,9 +1788,10 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf * Was a sec= authflavor specified in the options? First, verify * whether the server supports it, and then just try to use it if so. */ - if (args->auth_flavor_len > 0) { - status = nfs_verify_authflavor(args, authlist, authlist_len); - dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]); + if (args->auth_info.flavor_len > 0) { + status = nfs_verify_authflavors(args, authlist, authlist_len); + dfprintk(MOUNT, "NFS: using auth flavor %u\n", + args->selected_flavor); if (status) return ERR_PTR(status); return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); @@ -1769,7 +1820,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Fallthrough */ } dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor); - nfs_set_auth_parsed_mount_data(args, flavor); + args->selected_flavor = flavor; server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); if (!IS_ERR(server)) return server; @@ -1785,7 +1836,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Last chance! Try AUTH_UNIX */ dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX); - nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); } @@ -1972,9 +2023,9 @@ static int nfs23_validate_mount_data(void *options, args->bsize = data->bsize; if (data->flags & NFS_MOUNT_SECFLAVOUR) - nfs_set_auth_parsed_mount_data(args, data->pseudoflavor); + args->selected_flavor = data->pseudoflavor; else - nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; if (!args->nfs_server.hostname) goto out_nomem; @@ -2108,9 +2159,6 @@ static int nfs_validate_text_mount_data(void *options, nfs_set_port(sap, &args->nfs_server.port, port); - if (args->auth_flavor_len > 1) - goto out_bad_auth; - return nfs_parse_devname(dev_name, &args->nfs_server.hostname, max_namelen, @@ -2130,10 +2178,6 @@ out_invalid_transport_udp: out_no_address: dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); return -EINVAL; - -out_bad_auth: - dfprintk(MOUNT, "NFS: Too many RPC auth flavours specified\n"); - return -EINVAL; } static int @@ -2143,8 +2187,10 @@ nfs_compare_remount_data(struct nfs_server *nfss, if (data->flags != nfss->flags || data->rsize != nfss->rsize || data->wsize != nfss->wsize || + data->version != nfss->nfs_client->rpc_ops->version || + data->minorversion != nfss->nfs_client->cl_minorversion || data->retrans != nfss->client->cl_timeout->to_retries || - data->auth_flavors[0] != nfss->client->cl_auth->au_flavor || + data->selected_flavor != nfss->client->cl_auth->au_flavor || data->acregmin != nfss->acregmin / HZ || data->acregmax != nfss->acregmax / HZ || data->acdirmin != nfss->acdirmin / HZ || @@ -2189,7 +2235,8 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->rsize = nfss->rsize; data->wsize = nfss->wsize; data->retrans = nfss->client->cl_timeout->to_retries; - nfs_set_auth_parsed_mount_data(data, nfss->client->cl_auth->au_flavor); + data->selected_flavor = nfss->client->cl_auth->au_flavor; + data->auth_info = nfss->auth_info; data->acregmin = nfss->acregmin / HZ; data->acregmax = nfss->acregmax / HZ; data->acdirmin = nfss->acdirmin / HZ; @@ -2197,12 +2244,14 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; data->nfs_server.port = nfss->port; data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; + data->version = nfsvers; + data->minorversion = nfss->nfs_client->cl_minorversion; memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr, data->nfs_server.addrlen); /* overwrite those values with any that were specified */ - error = nfs_parse_mount_options((char *)options, data); - if (error < 0) + error = -EINVAL; + if (!nfs_parse_mount_options((char *)options, data)) goto out; /* @@ -2332,7 +2381,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->acdirmax != b->acdirmax) goto Ebusy; - if (b->flags & NFS_MOUNT_SECFLAVOUR && + if (b->auth_info.flavor_len > 0 && clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) goto Ebusy; return 1; @@ -2530,6 +2579,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, mntroot = ERR_PTR(error); goto error_splat_bdi; } + server->super = s; } if (!s->s_root) { @@ -2713,9 +2763,9 @@ static int nfs4_validate_mount_data(void *options, data->auth_flavours, sizeof(pseudoflavor))) return -EFAULT; - nfs_set_auth_parsed_mount_data(args, pseudoflavor); + args->selected_flavor = pseudoflavor; } else - nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); if (IS_ERR(c)) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index bb939edd4c99..0c29b1bb3936 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -493,7 +493,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) unsigned long long fileid; struct dentry *sdentry; struct rpc_task *task; - int error = -EIO; + int error = -EBUSY; dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n", dentry->d_parent->d_name.name, dentry->d_name.name, @@ -503,7 +503,6 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) /* * We don't allow a dentry to be silly-renamed twice. */ - error = -EBUSY; if (dentry->d_flags & DCACHE_NFSFS_RENAMED) goto out; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 0ba679866e50..da276640f776 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -94,6 +94,7 @@ void nilfs_forget_buffer(struct buffer_head *bh) clear_buffer_nilfs_volatile(bh); clear_buffer_nilfs_checked(bh); clear_buffer_nilfs_redirected(bh); + clear_buffer_async_write(bh); clear_buffer_dirty(bh); if (nilfs_page_buffers_clean(page)) __nilfs_clear_page_dirty(page); @@ -429,6 +430,7 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) "discard block %llu, size %zu", (u64)bh->b_blocknr, bh->b_size); } + clear_buffer_async_write(bh); clear_buffer_dirty(bh); clear_buffer_nilfs_volatile(bh); clear_buffer_nilfs_checked(bh); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index bd88a7461063..9f6b486b6c01 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -665,7 +665,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, bh = head = page_buffers(page); do { - if (!buffer_dirty(bh)) + if (!buffer_dirty(bh) || buffer_async_write(bh)) continue; get_bh(bh); list_add_tail(&bh->b_assoc_buffers, listp); @@ -699,7 +699,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); do { - if (buffer_dirty(bh)) { + if (buffer_dirty(bh) && + !buffer_async_write(bh)) { get_bh(bh); list_add_tail(&bh->b_assoc_buffers, listp); @@ -1579,6 +1580,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + set_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) { lock_page(bd_page); @@ -1592,6 +1594,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { + set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1677,6 +1680,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1686,6 +1690,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { + clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { end_page_writeback(bd_page); @@ -1755,6 +1760,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) b_assoc_buffers) { set_buffer_uptodate(bh); clear_buffer_dirty(bh); + clear_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1776,6 +1782,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) b_assoc_buffers) { set_buffer_uptodate(bh); clear_buffer_dirty(bh); + clear_buffer_async_write(bh); clear_buffer_delay(bh); clear_buffer_nilfs_volatile(bh); clear_buffer_nilfs_redirected(bh); diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index ef999729e274..0d3a97d2d5f6 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -70,9 +70,10 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) */ if (inode == NULL) { unsigned long gen = (unsigned long) dentry->d_fsdata; - unsigned long pgen = - OCFS2_I(dentry->d_parent->d_inode)->ip_dir_lock_gen; - + unsigned long pgen; + spin_lock(&dentry->d_lock); + pgen = OCFS2_I(dentry->d_parent->d_inode)->ip_dir_lock_gen; + spin_unlock(&dentry->d_lock); trace_ocfs2_dentry_revalidate_negative(dentry->d_name.len, dentry->d_name.name, pgen, gen); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 121da2dc3be8..d4e81e4a9b04 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1924,7 +1924,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) { int tmp, hangup_needed = 0; struct ocfs2_super *osb = NULL; - char nodestr[8]; + char nodestr[12]; trace_ocfs2_dismount_volume(sb); diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 73feacc49b2e..fd777032c2ba 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1163,21 +1163,6 @@ static struct reiserfs_journal_list *find_newer_jl_for_cn(struct return NULL; } -static int newer_jl_done(struct reiserfs_journal_cnode *cn) -{ - struct super_block *sb = cn->sb; - b_blocknr_t blocknr = cn->blocknr; - - cn = cn->hprev; - while (cn) { - if (cn->sb == sb && cn->blocknr == blocknr && cn->jlist && - atomic_read(&cn->jlist->j_commit_left) != 0) - return 0; - cn = cn->hprev; - } - return 1; -} - static void remove_journal_hash(struct super_block *, struct reiserfs_journal_cnode **, struct reiserfs_journal_list *, unsigned long, @@ -1353,7 +1338,6 @@ static int flush_journal_list(struct super_block *s, reiserfs_warning(s, "clm-2048", "called with wcount %d", atomic_read(&journal->j_wcount)); } - BUG_ON(jl->j_trans_id == 0); /* if flushall == 0, the lock is already held */ if (flushall) { @@ -1593,31 +1577,6 @@ static int flush_journal_list(struct super_block *s, return err; } -static int test_transaction(struct super_block *s, - struct reiserfs_journal_list *jl) -{ - struct reiserfs_journal_cnode *cn; - - if (jl->j_len == 0 || atomic_read(&jl->j_nonzerolen) == 0) - return 1; - - cn = jl->j_realblock; - while (cn) { - /* if the blocknr == 0, this has been cleared from the hash, - ** skip it - */ - if (cn->blocknr == 0) { - goto next; - } - if (cn->bh && !newer_jl_done(cn)) - return 0; - next: - cn = cn->next; - cond_resched(); - } - return 0; -} - static int write_one_transaction(struct super_block *s, struct reiserfs_journal_list *jl, struct buffer_chunk *chunk) @@ -1805,6 +1764,8 @@ static int flush_used_journal_lists(struct super_block *s, break; tjl = JOURNAL_LIST_ENTRY(tjl->j_list.next); } + get_journal_list(jl); + get_journal_list(flush_jl); /* try to find a group of blocks we can flush across all the ** transactions, but only bother if we've actually spanned ** across multiple lists @@ -1813,6 +1774,8 @@ static int flush_used_journal_lists(struct super_block *s, ret = kupdate_transactions(s, jl, &tjl, &trans_id, len, i); } flush_journal_list(s, flush_jl, 1); + put_journal_list(s, flush_jl); + put_journal_list(s, jl); return 0; } @@ -3868,27 +3831,6 @@ int reiserfs_prepare_for_journal(struct super_block *sb, return 1; } -static void flush_old_journal_lists(struct super_block *s) -{ - struct reiserfs_journal *journal = SB_JOURNAL(s); - struct reiserfs_journal_list *jl; - struct list_head *entry; - time_t now = get_seconds(); - - while (!list_empty(&journal->j_journal_list)) { - entry = journal->j_journal_list.next; - jl = JOURNAL_LIST_ENTRY(entry); - /* this check should always be run, to send old lists to disk */ - if (jl->j_timestamp < (now - (JOURNAL_MAX_TRANS_AGE * 4)) && - atomic_read(&jl->j_commit_left) == 0 && - test_transaction(s, jl)) { - flush_used_journal_lists(s, jl); - } else { - break; - } - } -} - /* ** long and ugly. If flush, will not return until all commit ** blocks and all real buffers in the trans are on disk. @@ -4232,7 +4174,6 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, } } } - flush_old_journal_lists(sb); journal->j_current_jl->j_list_bitmap = get_list_bitmap(sb, journal->j_current_jl); diff --git a/fs/sysv/super.c b/fs/sysv/super.c index d0c6a007ce83..eda10959714f 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -487,6 +487,7 @@ static int v7_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sb = sb; sbi->s_block_base = 0; sbi->s_type = FSTYPE_V7; + mutex_init(&sbi->s_lock); sb->s_fs_info = sbi; sb_set_blocksize(sb, 512); diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index 7e5aae4bf46f..6eaf5edf1ea1 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -30,18 +30,17 @@ void udf_free_inode(struct inode *inode) { struct super_block *sb = inode->i_sb; struct udf_sb_info *sbi = UDF_SB(sb); + struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); - mutex_lock(&sbi->s_alloc_mutex); - if (sbi->s_lvid_bh) { - struct logicalVolIntegrityDescImpUse *lvidiu = - udf_sb_lvidiu(sbi); + if (lvidiu) { + mutex_lock(&sbi->s_alloc_mutex); if (S_ISDIR(inode->i_mode)) le32_add_cpu(&lvidiu->numDirs, -1); else le32_add_cpu(&lvidiu->numFiles, -1); udf_updated_lvid(sb); + mutex_unlock(&sbi->s_alloc_mutex); } - mutex_unlock(&sbi->s_alloc_mutex); udf_free_blocks(sb, NULL, &UDF_I(inode)->i_location, 0, 1); } @@ -55,6 +54,7 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err) uint32_t start = UDF_I(dir)->i_location.logicalBlockNum; struct udf_inode_info *iinfo; struct udf_inode_info *dinfo = UDF_I(dir); + struct logicalVolIntegrityDescImpUse *lvidiu; inode = new_inode(sb); @@ -92,12 +92,10 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err) return NULL; } - if (sbi->s_lvid_bh) { - struct logicalVolIntegrityDescImpUse *lvidiu; - + lvidiu = udf_sb_lvidiu(sb); + if (lvidiu) { iinfo->i_unique = lvid_get_unique_id(sb); mutex_lock(&sbi->s_alloc_mutex); - lvidiu = udf_sb_lvidiu(sbi); if (S_ISDIR(mode)) le32_add_cpu(&lvidiu->numDirs, 1); else diff --git a/fs/udf/super.c b/fs/udf/super.c index 839a2bad7f45..91219385691d 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -94,13 +94,25 @@ static unsigned int udf_count_free(struct super_block *); static int udf_statfs(struct dentry *, struct kstatfs *); static int udf_show_options(struct seq_file *, struct dentry *); -struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi) +struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb) { - struct logicalVolIntegrityDesc *lvid = - (struct logicalVolIntegrityDesc *)sbi->s_lvid_bh->b_data; - __u32 number_of_partitions = le32_to_cpu(lvid->numOfPartitions); - __u32 offset = number_of_partitions * 2 * - sizeof(uint32_t)/sizeof(uint8_t); + struct logicalVolIntegrityDesc *lvid; + unsigned int partnum; + unsigned int offset; + + if (!UDF_SB(sb)->s_lvid_bh) + return NULL; + lvid = (struct logicalVolIntegrityDesc *)UDF_SB(sb)->s_lvid_bh->b_data; + partnum = le32_to_cpu(lvid->numOfPartitions); + if ((sb->s_blocksize - sizeof(struct logicalVolIntegrityDescImpUse) - + offsetof(struct logicalVolIntegrityDesc, impUse)) / + (2 * sizeof(uint32_t)) < partnum) { + udf_err(sb, "Logical volume integrity descriptor corrupted " + "(numOfPartitions = %u)!\n", partnum); + return NULL; + } + /* The offset is to skip freeSpaceTable and sizeTable arrays */ + offset = partnum * 2 * sizeof(uint32_t); return (struct logicalVolIntegrityDescImpUse *)&(lvid->impUse[offset]); } @@ -629,9 +641,10 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) struct udf_options uopt; struct udf_sb_info *sbi = UDF_SB(sb); int error = 0; + struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); - if (sbi->s_lvid_bh) { - int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev); + if (lvidiu) { + int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev); if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY)) return -EACCES; } @@ -1905,11 +1918,12 @@ static void udf_open_lvid(struct super_block *sb) if (!bh) return; - - mutex_lock(&sbi->s_alloc_mutex); lvid = (struct logicalVolIntegrityDesc *)bh->b_data; - lvidiu = udf_sb_lvidiu(sbi); + lvidiu = udf_sb_lvidiu(sb); + if (!lvidiu) + return; + mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; udf_time_to_disk_stamp(&lvid->recordingDateAndTime, @@ -1937,10 +1951,12 @@ static void udf_close_lvid(struct super_block *sb) if (!bh) return; + lvid = (struct logicalVolIntegrityDesc *)bh->b_data; + lvidiu = udf_sb_lvidiu(sb); + if (!lvidiu) + return; mutex_lock(&sbi->s_alloc_mutex); - lvid = (struct logicalVolIntegrityDesc *)bh->b_data; - lvidiu = udf_sb_lvidiu(sbi); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; udf_time_to_disk_stamp(&lvid->recordingDateAndTime, CURRENT_TIME); @@ -2093,15 +2109,19 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (sbi->s_lvid_bh) { struct logicalVolIntegrityDescImpUse *lvidiu = - udf_sb_lvidiu(sbi); - uint16_t minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev); - uint16_t minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev); - /* uint16_t maxUDFWriteRev = - le16_to_cpu(lvidiu->maxUDFWriteRev); */ + udf_sb_lvidiu(sb); + uint16_t minUDFReadRev; + uint16_t minUDFWriteRev; + if (!lvidiu) { + ret = -EINVAL; + goto error_out; + } + minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev); + minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev); if (minUDFReadRev > UDF_MAX_READ_VERSION) { udf_err(sb, "minUDFReadRev=%x (max is %x)\n", - le16_to_cpu(lvidiu->minUDFReadRev), + minUDFReadRev, UDF_MAX_READ_VERSION); ret = -EINVAL; goto error_out; @@ -2265,11 +2285,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf) struct logicalVolIntegrityDescImpUse *lvidiu; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); - if (sbi->s_lvid_bh != NULL) - lvidiu = udf_sb_lvidiu(sbi); - else - lvidiu = NULL; - + lvidiu = udf_sb_lvidiu(sb); buf->f_type = UDF_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = sbi->s_partmaps[sbi->s_partition].s_partition_len; diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index ed401e94aa8c..1f32c7bd9f57 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -162,7 +162,7 @@ static inline struct udf_sb_info *UDF_SB(struct super_block *sb) return sb->s_fs_info; } -struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi); +struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb); int udf_compute_nr_groups(struct super_block *sb, u32 partition); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 88c5ea75ebf6..f1d85cfc0a54 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -628,6 +628,7 @@ xfs_buf_item_unlock( else if (aborted) { ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); if (lip->li_flags & XFS_LI_IN_AIL) { + spin_lock(&lip->li_ailp->xa_lock); xfs_trans_ail_delete(lip->li_ailp, lip, SHUTDOWN_LOG_IO_ERROR); } diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 069537c845e5..20bf8e8002d6 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -1224,6 +1224,7 @@ xfs_da3_node_toosmall( /* start with smaller blk num */ forward = nodehdr.forw < nodehdr.back; for (i = 0; i < 2; forward = !forward, i++) { + struct xfs_da3_icnode_hdr thdr; if (forward) blkno = nodehdr.forw; else @@ -1236,10 +1237,10 @@ xfs_da3_node_toosmall( return(error); node = bp->b_addr; - xfs_da3_node_hdr_from_disk(&nodehdr, node); + xfs_da3_node_hdr_from_disk(&thdr, node); xfs_trans_brelse(state->args->trans, bp); - if (count - nodehdr.count >= 0) + if (count - thdr.count >= 0) break; /* fits with at least 25% to spare */ } if (i >= 2) { diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index 1edb5cc3e5f4..18272c766a50 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -515,7 +515,7 @@ typedef struct xfs_swapext /* XFS_IOC_GETBIOSIZE ---- deprecated 47 */ #define XFS_IOC_GETBMAPX _IOWR('X', 56, struct getbmap) #define XFS_IOC_ZERO_RANGE _IOW ('X', 57, struct xfs_flock64) -#define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_eofblocks) +#define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_fs_eofblocks) /* * ioctl commands that replace IRIX syssgi()'s diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 193206ba4358..474807a401c8 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -119,11 +119,6 @@ xfs_inode_free( ip->i_itemp = NULL; } - /* asserts to verify all state is correct here */ - ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!spin_is_locked(&ip->i_flags_lock)); - ASSERT(!xfs_isiflocked(ip)); - /* * Because we use RCU freeing we need to ensure the inode always * appears to be reclaimed with an invalid inode number when in the @@ -135,6 +130,10 @@ xfs_inode_free( ip->i_ino = 0; spin_unlock(&ip->i_flags_lock); + /* asserts to verify all state is correct here */ + ASSERT(atomic_read(&ip->i_pincount) == 0); + ASSERT(!xfs_isiflocked(ip)); + call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index dabda9521b4b..cc179878fe41 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1970,6 +1970,13 @@ xlog_recover_do_inode_buffer( * magic number. If we don't recognise the magic number in the buffer, then * return a LSN of -1 so that the caller knows it was an unrecognised block and * so can recover the buffer. + * + * Note: we cannot rely solely on magic number matches to determine that the + * buffer has a valid LSN - we also need to verify that it belongs to this + * filesystem, so we need to extract the object's LSN and compare it to that + * which we read from the superblock. If the UUIDs don't match, then we've got a + * stale metadata block from an old filesystem instance that we need to recover + * over the top of. */ static xfs_lsn_t xlog_recover_get_buf_lsn( @@ -1980,6 +1987,8 @@ xlog_recover_get_buf_lsn( __uint16_t magic16; __uint16_t magicda; void *blk = bp->b_addr; + uuid_t *uuid; + xfs_lsn_t lsn = -1; /* v4 filesystems always recover immediately */ if (!xfs_sb_version_hascrc(&mp->m_sb)) @@ -1992,43 +2001,79 @@ xlog_recover_get_buf_lsn( case XFS_ABTB_MAGIC: case XFS_ABTC_MAGIC: case XFS_IBT_CRC_MAGIC: - case XFS_IBT_MAGIC: - return be64_to_cpu( - ((struct xfs_btree_block *)blk)->bb_u.s.bb_lsn); + case XFS_IBT_MAGIC: { + struct xfs_btree_block *btb = blk; + + lsn = be64_to_cpu(btb->bb_u.s.bb_lsn); + uuid = &btb->bb_u.s.bb_uuid; + break; + } case XFS_BMAP_CRC_MAGIC: - case XFS_BMAP_MAGIC: - return be64_to_cpu( - ((struct xfs_btree_block *)blk)->bb_u.l.bb_lsn); + case XFS_BMAP_MAGIC: { + struct xfs_btree_block *btb = blk; + + lsn = be64_to_cpu(btb->bb_u.l.bb_lsn); + uuid = &btb->bb_u.l.bb_uuid; + break; + } case XFS_AGF_MAGIC: - return be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn); + lsn = be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn); + uuid = &((struct xfs_agf *)blk)->agf_uuid; + break; case XFS_AGFL_MAGIC: - return be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn); + lsn = be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn); + uuid = &((struct xfs_agfl *)blk)->agfl_uuid; + break; case XFS_AGI_MAGIC: - return be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn); + lsn = be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn); + uuid = &((struct xfs_agi *)blk)->agi_uuid; + break; case XFS_SYMLINK_MAGIC: - return be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn); + lsn = be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn); + uuid = &((struct xfs_dsymlink_hdr *)blk)->sl_uuid; + break; case XFS_DIR3_BLOCK_MAGIC: case XFS_DIR3_DATA_MAGIC: case XFS_DIR3_FREE_MAGIC: - return be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn); + lsn = be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn); + uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid; + break; case XFS_ATTR3_RMT_MAGIC: - return be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn); + lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn); + uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid; + break; case XFS_SB_MAGIC: - return be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn); + lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn); + uuid = &((struct xfs_dsb *)blk)->sb_uuid; + break; default: break; } + if (lsn != (xfs_lsn_t)-1) { + if (!uuid_equal(&mp->m_sb.sb_uuid, uuid)) + goto recover_immediately; + return lsn; + } + magicda = be16_to_cpu(((struct xfs_da_blkinfo *)blk)->magic); switch (magicda) { case XFS_DIR3_LEAF1_MAGIC: case XFS_DIR3_LEAFN_MAGIC: case XFS_DA3_NODE_MAGIC: - return be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn); + lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn); + uuid = &((struct xfs_da3_blkinfo *)blk)->uuid; + break; default: break; } + if (lsn != (xfs_lsn_t)-1) { + if (!uuid_equal(&mp->m_sb.sb_uuid, uuid)) + goto recover_immediately; + return lsn; + } + /* * We do individual object checks on dquot and inode buffers as they * have their own individual LSN records. Also, we could have a stale |