diff options
Diffstat (limited to 'fs')
90 files changed, 1052 insertions, 654 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 58e6cbce4156..08f2e1e9a7e6 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -603,10 +603,11 @@ static int v9fs_cache_register(void) if (ret < 0) return ret; #ifdef CONFIG_9P_FSCACHE - return fscache_register_netfs(&v9fs_cache_netfs); -#else - return ret; + ret = fscache_register_netfs(&v9fs_cache_netfs); + if (ret < 0) + v9fs_destroy_inode_cache(); #endif + return ret; } static void v9fs_cache_unregister(void) diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 53687bbf2296..a7c481402c46 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -267,14 +267,8 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, } /* Only creates */ - if (!(flags & O_CREAT)) + if (!(flags & O_CREAT) || dentry->d_inode) return finish_no_open(file, res); - else if (dentry->d_inode) { - if ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) - return -EEXIST; - else - return finish_no_open(file, res); - } v9ses = v9fs_inode2v9ses(dir); 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 */ @@ -167,10 +167,25 @@ static int __init aio_setup(void) } __initcall(aio_setup); +static void put_aio_ring_file(struct kioctx *ctx) +{ + struct file *aio_ring_file = ctx->aio_ring_file; + if (aio_ring_file) { + truncate_setsize(aio_ring_file->f_inode, 0); + + /* Prevent further access to the kioctx from migratepages */ + spin_lock(&aio_ring_file->f_inode->i_mapping->private_lock); + aio_ring_file->f_inode->i_mapping->private_data = NULL; + ctx->aio_ring_file = NULL; + spin_unlock(&aio_ring_file->f_inode->i_mapping->private_lock); + + fput(aio_ring_file); + } +} + static void aio_free_ring(struct kioctx *ctx) { int i; - struct file *aio_ring_file = ctx->aio_ring_file; for (i = 0; i < ctx->nr_pages; i++) { pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i, @@ -178,14 +193,10 @@ static void aio_free_ring(struct kioctx *ctx) put_page(ctx->ring_pages[i]); } + put_aio_ring_file(ctx); + if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) kfree(ctx->ring_pages); - - if (aio_ring_file) { - truncate_setsize(aio_ring_file->f_inode, 0); - fput(aio_ring_file); - ctx->aio_ring_file = NULL; - } } static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) @@ -207,9 +218,8 @@ static int aio_set_page_dirty(struct page *page) static int aio_migratepage(struct address_space *mapping, struct page *new, struct page *old, enum migrate_mode mode) { - struct kioctx *ctx = mapping->private_data; + struct kioctx *ctx; unsigned long flags; - unsigned idx = old->index; int rc; /* Writeback must be complete */ @@ -224,10 +234,23 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, get_page(new); - spin_lock_irqsave(&ctx->completion_lock, flags); - migrate_page_copy(new, old); - ctx->ring_pages[idx] = new; - spin_unlock_irqrestore(&ctx->completion_lock, flags); + /* We can potentially race against kioctx teardown here. Use the + * address_space's private data lock to protect the mapping's + * private_data. + */ + spin_lock(&mapping->private_lock); + ctx = mapping->private_data; + if (ctx) { + pgoff_t idx; + spin_lock_irqsave(&ctx->completion_lock, flags); + migrate_page_copy(new, old); + idx = old->index; + if (idx < (pgoff_t)ctx->nr_pages) + ctx->ring_pages[idx] = new; + spin_unlock_irqrestore(&ctx->completion_lock, flags); + } else + rc = -EBUSY; + spin_unlock(&mapping->private_lock); return rc; } @@ -617,8 +640,7 @@ out_freepcpu: out_freeref: free_percpu(ctx->users.pcpu_count); out_freectx: - if (ctx->aio_ring_file) - fput(ctx->aio_ring_file); + put_aio_ring_file(ctx); kmem_cache_free(kioctx_cachep, ctx); pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 3db70dae40d3..689e40d983ad 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -109,13 +109,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, pkt.hdr.proto_version = sbi->version; pkt.hdr.type = type; - mutex_lock(&sbi->wq_mutex); - /* Check if we have become catatonic */ - if (sbi->catatonic) { - mutex_unlock(&sbi->wq_mutex); - return; - } switch (type) { /* Kernel protocol v4 missing and expire packets */ case autofs_ptype_missing: @@ -427,7 +421,6 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, wq->tgid = current->tgid; wq->status = -EINTR; /* Status return if interrupted */ wq->wait_ctr = 2; - mutex_unlock(&sbi->wq_mutex); if (sbi->version < 5) { if (notify == NFY_MOUNT) @@ -449,15 +442,15 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, notify); - /* autofs4_notify_daemon() may block */ + /* autofs4_notify_daemon() may block; it will unlock ->wq_mutex */ autofs4_notify_daemon(sbi, wq, type); } else { wq->wait_ctr++; - mutex_unlock(&sbi->wq_mutex); - kfree(qstr.name); DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d", (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, notify); + mutex_unlock(&sbi->wq_mutex); + kfree(qstr.name); } /* 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/async-thread.c b/fs/btrfs/async-thread.c index 58b7d14b08ee..08cc08f037a6 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -107,7 +107,8 @@ static void check_idle_worker(struct btrfs_worker_thread *worker) worker->idle = 1; /* the list may be empty if the worker is just starting */ - if (!list_empty(&worker->worker_list)) { + if (!list_empty(&worker->worker_list) && + !worker->workers->stopping) { list_move(&worker->worker_list, &worker->workers->idle_list); } @@ -127,7 +128,8 @@ static void check_busy_worker(struct btrfs_worker_thread *worker) spin_lock_irqsave(&worker->workers->lock, flags); worker->idle = 0; - if (!list_empty(&worker->worker_list)) { + if (!list_empty(&worker->worker_list) && + !worker->workers->stopping) { list_move_tail(&worker->worker_list, &worker->workers->worker_list); } @@ -412,6 +414,7 @@ void btrfs_stop_workers(struct btrfs_workers *workers) int can_stop; spin_lock_irq(&workers->lock); + workers->stopping = 1; list_splice_init(&workers->idle_list, &workers->worker_list); while (!list_empty(&workers->worker_list)) { cur = workers->worker_list.next; @@ -455,6 +458,7 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max, workers->ordered = 0; workers->atomic_start_pending = 0; workers->atomic_worker_start = async_helper; + workers->stopping = 0; } /* @@ -480,15 +484,19 @@ static int __btrfs_start_workers(struct btrfs_workers *workers) atomic_set(&worker->num_pending, 0); atomic_set(&worker->refs, 1); worker->workers = workers; - worker->task = kthread_run(worker_loop, worker, - "btrfs-%s-%d", workers->name, - workers->num_workers + 1); + worker->task = kthread_create(worker_loop, worker, + "btrfs-%s-%d", workers->name, + workers->num_workers + 1); if (IS_ERR(worker->task)) { ret = PTR_ERR(worker->task); - kfree(worker); goto fail; } + spin_lock_irq(&workers->lock); + if (workers->stopping) { + spin_unlock_irq(&workers->lock); + goto fail_kthread; + } list_add_tail(&worker->worker_list, &workers->idle_list); worker->idle = 1; workers->num_workers++; @@ -496,8 +504,13 @@ static int __btrfs_start_workers(struct btrfs_workers *workers) WARN_ON(workers->num_workers_starting < 0); spin_unlock_irq(&workers->lock); + wake_up_process(worker->task); return 0; + +fail_kthread: + kthread_stop(worker->task); fail: + kfree(worker); spin_lock_irq(&workers->lock); workers->num_workers_starting--; spin_unlock_irq(&workers->lock); diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 063698b90ce2..1f26792683ed 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -107,6 +107,8 @@ struct btrfs_workers { /* extra name for this worker, used for current->name */ char *name; + + int stopping; }; void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work); 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..9efb94e95858 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)) { @@ -535,10 +535,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list); btrfs_rm_dev_replace_srcdev(fs_info, src_device); - if (src_device->bdev) { - /* zero out the old super */ - btrfs_scratch_superblock(src_device); - } + /* * this is again a consistent state where no dev_replace procedure * is running, the target device is part of the filesystem, the diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4cbb00af92ff..62176ad89846 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" }, }; @@ -1560,8 +1561,9 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, return ret; } -struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, - struct btrfs_key *location) +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *location, + bool check_ref) { struct btrfs_root *root; int ret; @@ -1585,7 +1587,7 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, location->objectid); if (root) { - if (btrfs_root_refs(&root->root_item) == 0) + if (check_ref && btrfs_root_refs(&root->root_item) == 0) return ERR_PTR(-ENOENT); return root; } @@ -1594,7 +1596,7 @@ again: if (IS_ERR(root)) return root; - if (btrfs_root_refs(&root->root_item) == 0) { + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { ret = -ENOENT; goto fail; } @@ -3415,6 +3417,7 @@ 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/disk-io.h b/fs/btrfs/disk-io.h index b71acd6e1e5b..5ce2a7da8b11 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -68,8 +68,17 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, int btrfs_init_fs_root(struct btrfs_root *root); int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); -struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, - struct btrfs_key *location); + +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *key, + bool check_ref); +static inline struct btrfs_root * +btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, + struct btrfs_key *location) +{ + return btrfs_get_fs_root(fs_info, location, true); +} + int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); void btrfs_btree_balance_dirty(struct btrfs_root *root); void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root); 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..51731b76900d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -145,8 +145,16 @@ int __init extent_io_init(void) offsetof(struct btrfs_io_bio, bio)); if (!btrfs_bioset) goto free_buffer_cache; + + if (bioset_integrity_create(btrfs_bioset, BIO_POOL_SIZE)) + goto free_bioset; + return 0; +free_bioset: + bioset_free(btrfs_bioset); + btrfs_bioset = NULL; + free_buffer_cache: kmem_cache_destroy(extent_buffer_cache); extent_buffer_cache = NULL; @@ -1481,11 +1489,11 @@ 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) break; + if (!node) + break; } out: spin_unlock(&tree->lock); @@ -1612,7 +1620,7 @@ again: *start = delalloc_start; *end = delalloc_end; free_extent_state(cached_state); - return found; + return 0; } /* @@ -1625,10 +1633,9 @@ again: /* * make sure to limit the number of pages we try to lock down - * if we're looping. */ - if (delalloc_end + 1 - delalloc_start > max_bytes && loops) - delalloc_end = delalloc_start + PAGE_CACHE_SIZE - 1; + if (delalloc_end + 1 - delalloc_start > max_bytes) + delalloc_end = delalloc_start + max_bytes - 1; /* step two, lock all the pages after the page that has start */ ret = lock_delalloc_pages(inode, locked_page, @@ -1639,8 +1646,7 @@ again: */ free_extent_state(cached_state); if (!loops) { - unsigned long offset = (*start) & (PAGE_CACHE_SIZE - 1); - max_bytes = PAGE_CACHE_SIZE - offset; + max_bytes = PAGE_CACHE_SIZE; loops = 1; goto again; } else { 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..51e3afa78354 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); } @@ -6437,6 +6437,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, if (btrfs_extent_readonly(root, disk_bytenr)) goto out; + btrfs_release_path(path); /* * look for other files referencing this extent, if we @@ -7986,7 +7987,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* check for collisions, even if the name isn't there */ - ret = btrfs_check_dir_item_collision(root, new_dir->i_ino, + ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, new_dentry->d_name.name, new_dentry->d_name.len); @@ -8216,6 +8217,10 @@ 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 +8618,13 @@ 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..4a355726151e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -588,7 +588,7 @@ static struct btrfs_root *read_fs_root(struct btrfs_fs_info *fs_info, else key.offset = (u64)-1; - return btrfs_read_fs_root_no_name(fs_info, &key); + return btrfs_get_fs_root(fs_info, &key, false); } #ifdef BTRFS_COMPAT_EXTENT_TREE_V0 @@ -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/root-tree.c b/fs/btrfs/root-tree.c index 0b1f4ef8db98..ec71ea44d2b4 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -299,11 +299,6 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) continue; } - if (btrfs_root_refs(&root->root_item) == 0) { - btrfs_add_dead_root(root); - continue; - } - err = btrfs_init_fs_root(root); if (err) { btrfs_free_fs_root(root); @@ -318,6 +313,9 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) btrfs_free_fs_root(root); break; } + + if (btrfs_root_refs(&root->root_item) == 0) + btrfs_add_dead_root(root); } btrfs_free_path(path); 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..8c81bdc1ef9b 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, @@ -1838,11 +1838,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, assert_qgroups_uptodate(trans); update_super_roots(root); - if (!root->fs_info->log_root_recovering) { - btrfs_set_super_log_root(root->fs_info->super_copy, 0); - btrfs_set_super_log_root_level(root->fs_info->super_copy, 0); - } - + btrfs_set_super_log_root(root->fs_info->super_copy, 0); + btrfs_set_super_log_root_level(root->fs_info->super_copy, 0); memcpy(root->fs_info->super_for_commit, root->fs_info->super_copy, sizeof(*root->fs_info->super_copy)); 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..043b215769c2 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); @@ -1715,6 +1716,7 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info, struct btrfs_device *srcdev) { WARN_ON(!mutex_is_locked(&fs_info->fs_devices->device_list_mutex)); + list_del_rcu(&srcdev->dev_list); list_del_rcu(&srcdev->dev_alloc_list); fs_info->fs_devices->num_devices--; @@ -1724,9 +1726,13 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info, } if (srcdev->can_discard) fs_info->fs_devices->num_can_discard--; - if (srcdev->bdev) + if (srcdev->bdev) { fs_info->fs_devices->open_devices--; + /* zero out the old super */ + btrfs_scratch_superblock(srcdev); + } + call_rcu(&srcdev->rcu, free_device); } diff --git a/fs/buffer.c b/fs/buffer.c index 4d7433534f5c..6024877335ca 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1005,9 +1005,19 @@ grow_dev_page(struct block_device *bdev, sector_t block, struct buffer_head *bh; sector_t end_block; int ret = 0; /* Will call free_more_memory() */ + gfp_t gfp_mask; - page = find_or_create_page(inode->i_mapping, index, - (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); + gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS; + gfp_mask |= __GFP_MOVABLE; + /* + * XXX: __getblk_slow() can not really deal with failure and + * will endlessly loop on improvised global reclaim. Prefer + * looping in the allocator rather than here, at least that + * code knows what it's doing. + */ + gfp_mask |= __GFP_NOFAIL; + + page = find_or_create_page(inode->i_mapping, index, gfp_mask); if (!page) return ret; diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 25badd1aec5c..f4a08d7fa2f7 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -56,7 +56,7 @@ void __cachefiles_printk_object(struct cachefiles_object *object, object->fscache.cookie->parent, object->fscache.cookie->netfs_data, object->fscache.cookie->flags); - if (keybuf) + if (keybuf && cookie->def) keylen = cookie->def->get_key(cookie->netfs_data, keybuf, CACHEFILES_KEYBUF_SIZE); else diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 34c88b83e39f..12b0eef84183 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -162,8 +162,9 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object, int cachefiles_check_auxdata(struct cachefiles_object *object) { struct cachefiles_xattr *auxbuf; + enum fscache_checkaux validity; struct dentry *dentry = object->dentry; - unsigned int dlen; + ssize_t xlen; int ret; ASSERT(dentry); @@ -174,22 +175,22 @@ int cachefiles_check_auxdata(struct cachefiles_object *object) if (!auxbuf) return -ENOMEM; - auxbuf->len = vfs_getxattr(dentry, cachefiles_xattr_cache, - &auxbuf->type, 512 + 1); - if (auxbuf->len < 1) - return -ESTALE; - - if (auxbuf->type != object->fscache.cookie->def->type) - return -ESTALE; + xlen = vfs_getxattr(dentry, cachefiles_xattr_cache, + &auxbuf->type, 512 + 1); + ret = -ESTALE; + if (xlen < 1 || + auxbuf->type != object->fscache.cookie->def->type) + goto error; - dlen = auxbuf->len - 1; - ret = fscache_check_aux(&object->fscache, &auxbuf->data, dlen); + xlen--; + validity = fscache_check_aux(&object->fscache, &auxbuf->data, xlen); + if (validity != FSCACHE_CHECKAUX_OKAY) + goto error; + ret = 0; +error: kfree(auxbuf); - if (ret != FSCACHE_CHECKAUX_OKAY) - return -ESTALE; - - return 0; + return ret; } /* diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index a16b4e58bcc6..77fc5e181077 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -120,14 +120,16 @@ cifs_read_super(struct super_block *sb) { struct inode *inode; struct cifs_sb_info *cifs_sb; + struct cifs_tcon *tcon; int rc = 0; cifs_sb = CIFS_SB(sb); + tcon = cifs_sb_master_tcon(cifs_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL) sb->s_flags |= MS_POSIXACL; - if (cifs_sb_master_tcon(cifs_sb)->ses->capabilities & CAP_LARGE_FILES) + if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files) sb->s_maxbytes = MAX_LFS_FILESIZE; else sb->s_maxbytes = MAX_NON_LFS; @@ -147,7 +149,7 @@ cifs_read_super(struct super_block *sb) goto out_no_root; } - if (cifs_sb_master_tcon(cifs_sb)->nocase) + if (tcon->nocase) sb->s_d_op = &cifs_ci_dentry_ops; else sb->s_d_op = &cifs_dentry_ops; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index ea723a5e8226..6d0b07217ac9 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -132,5 +132,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.01" +#define CIFS_VERSION "2.02" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index cfa14c80ef3b..52b6f6c26bfc 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -547,9 +547,6 @@ struct TCP_Server_Info { unsigned int max_rw; /* maxRw specifies the maximum */ /* message size the server can send or receive for */ /* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */ - unsigned int max_vcs; /* maximum number of smb sessions, at least - those that can be specified uniquely with - vcnumbers */ unsigned int capabilities; /* selective disabling of caps by smb sess */ int timeAdj; /* Adjust for difference in server time zone in sec */ __u64 CurrentMid; /* multiplex id - rotating counter */ @@ -715,7 +712,6 @@ struct cifs_ses { enum statusEnum status; unsigned overrideSecFlg; /* if non-zero override global sec flags */ __u16 ipc_tid; /* special tid for connection to IPC share */ - __u16 vcnum; char *serverOS; /* name of operating system underlying server */ char *serverNOS; /* name of network operating system of server */ char *serverDomain; /* security realm of server */ @@ -1272,6 +1268,7 @@ struct dfs_info3_param { #define CIFS_FATTR_DELETE_PENDING 0x2 #define CIFS_FATTR_NEED_REVAL 0x4 #define CIFS_FATTR_INO_COLLISION 0x8 +#define CIFS_FATTR_UNKNOWN_NLINK 0x10 struct cifs_fattr { u32 cf_flags; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 948676db8e2e..08f9dfb1a894 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1491,15 +1491,30 @@ struct file_notify_information { __u8 FileName[0]; } __attribute__((packed)); -struct reparse_data { - __u32 ReparseTag; - __u16 ReparseDataLength; +/* For IO_REPARSE_TAG_SYMLINK */ +struct reparse_symlink_data { + __le32 ReparseTag; + __le16 ReparseDataLength; __u16 Reserved; - __u16 SubstituteNameOffset; - __u16 SubstituteNameLength; - __u16 PrintNameOffset; - __u16 PrintNameLength; - __u32 Flags; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __le32 Flags; + char PathBuffer[0]; +} __attribute__((packed)); + +/* For IO_REPARSE_TAG_NFS */ +#define NFS_SPECFILE_LNK 0x00000000014B4E4C +#define NFS_SPECFILE_CHR 0x0000000000524843 +#define NFS_SPECFILE_BLK 0x00000000004B4C42 +#define NFS_SPECFILE_FIFO 0x000000004F464946 +#define NFS_SPECFILE_SOCK 0x000000004B434F53 +struct reparse_posix_data { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le64 InodeType; /* LNK, FIFO, CHR etc. */ char PathBuffer[0]; } __attribute__((packed)); @@ -2652,26 +2667,7 @@ typedef struct file_xattr_info { } __attribute__((packed)) FILE_XATTR_INFO; /* extended attribute info level 0x205 */ - -/* flags for chattr command */ -#define EXT_SECURE_DELETE 0x00000001 /* EXT3_SECRM_FL */ -#define EXT_ENABLE_UNDELETE 0x00000002 /* EXT3_UNRM_FL */ -/* Reserved for compress file 0x4 */ -#define EXT_SYNCHRONOUS 0x00000008 /* EXT3_SYNC_FL */ -#define EXT_IMMUTABLE_FL 0x00000010 /* EXT3_IMMUTABLE_FL */ -#define EXT_OPEN_APPEND_ONLY 0x00000020 /* EXT3_APPEND_FL */ -#define EXT_DO_NOT_BACKUP 0x00000040 /* EXT3_NODUMP_FL */ -#define EXT_NO_UPDATE_ATIME 0x00000080 /* EXT3_NOATIME_FL */ -/* 0x100 through 0x800 reserved for compression flags and are GET-ONLY */ -#define EXT_HASH_TREE_INDEXED_DIR 0x00001000 /* GET-ONLY EXT3_INDEX_FL */ -/* 0x2000 reserved for IMAGIC_FL */ -#define EXT_JOURNAL_THIS_FILE 0x00004000 /* GET-ONLY EXT3_JOURNAL_DATA_FL */ -/* 0x8000 reserved for EXT3_NOTAIL_FL */ -#define EXT_SYNCHRONOUS_DIR 0x00010000 /* EXT3_DIRSYNC_FL */ -#define EXT_TOPDIR 0x00020000 /* EXT3_TOPDIR_FL */ - -#define EXT_SET_MASK 0x000300FF -#define EXT_GET_MASK 0x0003DFFF +/* flags for lsattr and chflags commands removed arein uapi/linux/fs.h */ typedef struct file_chattr_info { __le64 mask; /* list of all possible attribute bits */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a3d74fea1623..ccd31ab815d4 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -463,7 +463,6 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr) cifs_max_pending); set_credits(server, server->maxReq); server->maxBuf = le16_to_cpu(rsp->MaxBufSize); - server->max_vcs = le16_to_cpu(rsp->MaxNumberVcs); /* even though we do not use raw we might as well set this accurately, in case we ever find a need for it */ if ((le16_to_cpu(rsp->RawMode) & RAW_ENABLE) == RAW_ENABLE) { @@ -3089,7 +3088,8 @@ CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, bool is_unicode; unsigned int sub_len; char *sub_start; - struct reparse_data *reparse_buf; + struct reparse_symlink_data *reparse_buf; + struct reparse_posix_data *posix_buf; __u32 data_offset, data_count; char *end_of_smb; @@ -3138,20 +3138,47 @@ CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, goto qreparse_out; } end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount; - reparse_buf = (struct reparse_data *) + reparse_buf = (struct reparse_symlink_data *) ((char *)&pSMBr->hdr.Protocol + data_offset); if ((char *)reparse_buf >= end_of_smb) { rc = -EIO; goto qreparse_out; } - if ((reparse_buf->PathBuffer + reparse_buf->PrintNameOffset + - reparse_buf->PrintNameLength) > end_of_smb) { + if (reparse_buf->ReparseTag == cpu_to_le32(IO_REPARSE_TAG_NFS)) { + cifs_dbg(FYI, "NFS style reparse tag\n"); + posix_buf = (struct reparse_posix_data *)reparse_buf; + + if (posix_buf->InodeType != cpu_to_le64(NFS_SPECFILE_LNK)) { + cifs_dbg(FYI, "unsupported file type 0x%llx\n", + le64_to_cpu(posix_buf->InodeType)); + rc = -EOPNOTSUPP; + goto qreparse_out; + } + is_unicode = true; + sub_len = le16_to_cpu(reparse_buf->ReparseDataLength); + if (posix_buf->PathBuffer + sub_len > end_of_smb) { + cifs_dbg(FYI, "reparse buf beyond SMB\n"); + rc = -EIO; + goto qreparse_out; + } + *symlinkinfo = cifs_strndup_from_utf16(posix_buf->PathBuffer, + sub_len, is_unicode, nls_codepage); + goto qreparse_out; + } else if (reparse_buf->ReparseTag != + cpu_to_le32(IO_REPARSE_TAG_SYMLINK)) { + rc = -EOPNOTSUPP; + goto qreparse_out; + } + + /* Reparse tag is NTFS symlink */ + sub_start = le16_to_cpu(reparse_buf->SubstituteNameOffset) + + reparse_buf->PathBuffer; + sub_len = le16_to_cpu(reparse_buf->SubstituteNameLength); + if (sub_start + sub_len > end_of_smb) { cifs_dbg(FYI, "reparse buf beyond SMB\n"); rc = -EIO; goto qreparse_out; } - sub_start = reparse_buf->SubstituteNameOffset + reparse_buf->PathBuffer; - sub_len = reparse_buf->SubstituteNameLength; if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) is_unicode = true; else diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index d3e2eaa503a6..5384c2a640ca 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -500,6 +500,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, if (server->ops->close) server->ops->close(xid, tcon, &fid); cifs_del_pending_open(&open); + fput(file); rc = -ENOMEM; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index eb955b525e55..7ddddf2e2504 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3254,6 +3254,9 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, /* * Reads as many pages as possible from fscache. Returns -ENOBUFS * immediately if the cookie is negative + * + * After this point, every page in the list might have PG_fscache set, + * so we will need to clean that up off of every page we don't use. */ rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list, &num_pages); @@ -3376,6 +3379,11 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, kref_put(&rdata->refcount, cifs_readdata_release); } + /* Any pages that have been shown to fscache but didn't get added to + * the pagecache must be uncached before they get returned to the + * allocator. + */ + cifs_fscache_readpages_cancel(mapping->host, page_list); return rc; } diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 2f4bc5a58054..b3258f35e88a 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -223,6 +223,13 @@ void __cifs_readpage_to_fscache(struct inode *inode, struct page *page) fscache_uncache_page(CIFS_I(inode)->fscache, page); } +void __cifs_fscache_readpages_cancel(struct inode *inode, struct list_head *pages) +{ + cifs_dbg(FYI, "%s: (fsc: %p, i: %p)\n", + __func__, CIFS_I(inode)->fscache, inode); + fscache_readpages_cancel(CIFS_I(inode)->fscache, pages); +} + void __cifs_fscache_invalidate_page(struct page *page, struct inode *inode) { struct cifsInodeInfo *cifsi = CIFS_I(inode); diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 63539323e0b9..24794b6cd8ec 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -54,6 +54,7 @@ extern int __cifs_readpages_from_fscache(struct inode *, struct address_space *, struct list_head *, unsigned *); +extern void __cifs_fscache_readpages_cancel(struct inode *, struct list_head *); extern void __cifs_readpage_to_fscache(struct inode *, struct page *); @@ -91,6 +92,13 @@ static inline void cifs_readpage_to_fscache(struct inode *inode, __cifs_readpage_to_fscache(inode, page); } +static inline void cifs_fscache_readpages_cancel(struct inode *inode, + struct list_head *pages) +{ + if (CIFS_I(inode)->fscache) + return __cifs_fscache_readpages_cancel(inode, pages); +} + #else /* CONFIG_CIFS_FSCACHE */ static inline int cifs_fscache_register(void) { return 0; } static inline void cifs_fscache_unregister(void) {} @@ -131,6 +139,11 @@ static inline int cifs_readpages_from_fscache(struct inode *inode, static inline void cifs_readpage_to_fscache(struct inode *inode, struct page *page) {} +static inline void cifs_fscache_readpages_cancel(struct inode *inode, + struct list_head *pages) +{ +} + #endif /* CONFIG_CIFS_FSCACHE */ #endif /* _CIFS_FSCACHE_H */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index f9ff9c173f78..867b7cdc794a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -120,6 +120,33 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) cifs_i->invalid_mapping = true; } +/* + * copy nlink to the inode, unless it wasn't provided. Provide + * sane values if we don't have an existing one and none was provided + */ +static void +cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) +{ + /* + * if we're in a situation where we can't trust what we + * got from the server (readdir, some non-unix cases) + * fake reasonable values + */ + if (fattr->cf_flags & CIFS_FATTR_UNKNOWN_NLINK) { + /* only provide fake values on a new inode */ + if (inode->i_state & I_NEW) { + if (fattr->cf_cifsattrs & ATTR_DIRECTORY) + set_nlink(inode, 2); + else + set_nlink(inode, 1); + } + return; + } + + /* we trust the server, so update it */ + set_nlink(inode, fattr->cf_nlink); +} + /* populate an inode with info from a cifs_fattr struct */ void cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) @@ -134,7 +161,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) inode->i_mtime = fattr->cf_mtime; inode->i_ctime = fattr->cf_ctime; inode->i_rdev = fattr->cf_rdev; - set_nlink(inode, fattr->cf_nlink); + cifs_nlink_fattr_to_inode(inode, fattr); inode->i_uid = fattr->cf_uid; inode->i_gid = fattr->cf_gid; @@ -541,6 +568,7 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, fattr->cf_bytes = le64_to_cpu(info->AllocationSize); fattr->cf_createtime = le64_to_cpu(info->CreationTime); + fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks); if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { fattr->cf_mode = S_IFDIR | cifs_sb->mnt_dir_mode; fattr->cf_dtype = DT_DIR; @@ -548,7 +576,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, * Server can return wrong NumberOfLinks value for directories * when Unix extensions are disabled - fake it. */ - fattr->cf_nlink = 2; + if (!tcon->unix_ext) + fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK; } else if (fattr->cf_cifsattrs & ATTR_REPARSE) { fattr->cf_mode = S_IFLNK; fattr->cf_dtype = DT_LNK; @@ -561,11 +590,15 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, if (fattr->cf_cifsattrs & ATTR_READONLY) fattr->cf_mode &= ~(S_IWUGO); - fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks); - if (fattr->cf_nlink < 1) { - cifs_dbg(1, "replacing bogus file nlink value %u\n", + /* + * Don't accept zero nlink from non-unix servers unless + * delete is pending. Instead mark it as unknown. + */ + if ((fattr->cf_nlink < 1) && !tcon->unix_ext && + !info->DeletePending) { + cifs_dbg(1, "bogus file nlink value %u\n", fattr->cf_nlink); - fattr->cf_nlink = 1; + fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK; } } diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index af847e1cf1c1..651a5279607b 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -780,7 +780,9 @@ static const struct { ERRDOS, ERRnoaccess, 0xc0000290}, { ERRDOS, ERRbadfunc, 0xc000029c}, { ERRDOS, ERRsymlink, NT_STATUS_STOPPED_ON_SYMLINK}, { - ERRDOS, ERRinvlevel, 0x007c0001}, }; + ERRDOS, ERRinvlevel, 0x007c0001}, { + 0, 0, 0 } +}; /***************************************************************************** Print an error message from the status code diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 42ef03be089f..53a75f3d0179 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -180,6 +180,9 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) fattr->cf_dtype = DT_REG; } + /* non-unix readdir doesn't provide nlink */ + fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK; + if (fattr->cf_cifsattrs & ATTR_READONLY) fattr->cf_mode &= ~S_IWUGO; diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 5f99b7f19e78..e87387dbf39f 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -32,88 +32,6 @@ #include <linux/slab.h> #include "cifs_spnego.h" -/* - * Checks if this is the first smb session to be reconnected after - * the socket has been reestablished (so we know whether to use vc 0). - * Called while holding the cifs_tcp_ses_lock, so do not block - */ -static bool is_first_ses_reconnect(struct cifs_ses *ses) -{ - struct list_head *tmp; - struct cifs_ses *tmp_ses; - - list_for_each(tmp, &ses->server->smb_ses_list) { - tmp_ses = list_entry(tmp, struct cifs_ses, - smb_ses_list); - if (tmp_ses->need_reconnect == false) - return false; - } - /* could not find a session that was already connected, - this must be the first one we are reconnecting */ - return true; -} - -/* - * vc number 0 is treated specially by some servers, and should be the - * first one we request. After that we can use vcnumbers up to maxvcs, - * one for each smb session (some Windows versions set maxvcs incorrectly - * so maxvc=1 can be ignored). If we have too many vcs, we can reuse - * any vc but zero (some servers reset the connection on vcnum zero) - * - */ -static __le16 get_next_vcnum(struct cifs_ses *ses) -{ - __u16 vcnum = 0; - struct list_head *tmp; - struct cifs_ses *tmp_ses; - __u16 max_vcs = ses->server->max_vcs; - __u16 i; - int free_vc_found = 0; - - /* Quoting the MS-SMB specification: "Windows-based SMB servers set this - field to one but do not enforce this limit, which allows an SMB client - to establish more virtual circuits than allowed by this value ... but - other server implementations can enforce this limit." */ - if (max_vcs < 2) - max_vcs = 0xFFFF; - - spin_lock(&cifs_tcp_ses_lock); - if ((ses->need_reconnect) && is_first_ses_reconnect(ses)) - goto get_vc_num_exit; /* vcnum will be zero */ - for (i = ses->server->srv_count - 1; i < max_vcs; i++) { - if (i == 0) /* this is the only connection, use vc 0 */ - break; - - free_vc_found = 1; - - list_for_each(tmp, &ses->server->smb_ses_list) { - tmp_ses = list_entry(tmp, struct cifs_ses, - smb_ses_list); - if (tmp_ses->vcnum == i) { - free_vc_found = 0; - break; /* found duplicate, try next vcnum */ - } - } - if (free_vc_found) - break; /* we found a vcnumber that will work - use it */ - } - - if (i == 0) - vcnum = 0; /* for most common case, ie if one smb session, use - vc zero. Also for case when no free vcnum, zero - is safest to send (some clients only send zero) */ - else if (free_vc_found == 0) - vcnum = 1; /* we can not reuse vc=0 safely, since some servers - reset all uids on that, but 1 is ok. */ - else - vcnum = i; - ses->vcnum = vcnum; -get_vc_num_exit: - spin_unlock(&cifs_tcp_ses_lock); - - return cpu_to_le16(vcnum); -} - static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB) { __u32 capabilities = 0; @@ -128,7 +46,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB) CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4, USHRT_MAX)); pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq); - pSMB->req.VcNumber = get_next_vcnum(ses); + pSMB->req.VcNumber = __constant_cpu_to_le16(1); /* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */ @@ -582,9 +500,9 @@ select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) return NTLMv2; if (global_secflags & CIFSSEC_MAY_NTLM) return NTLM; - /* Fallthrough */ default: - return Unspecified; + /* Fallthrough to attempt LANMAN authentication next */ + break; } case CIFS_NEGFLAVOR_LANMAN: switch (requested) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index eba0efde66d7..edccb5252462 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -687,6 +687,10 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) else return -EIO; + /* no need to send SMB logoff if uid already closed due to reconnect */ + if (ses->need_reconnect) + goto smb2_session_already_dead; + rc = small_smb2_init(SMB2_LOGOFF, NULL, (void **) &req); if (rc) return rc; @@ -701,6 +705,8 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) * No tcon so can't do * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]); */ + +smb2_session_already_dead: return rc; } diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index d952ee48f4dc..a4b2391fe66e 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -97,9 +97,23 @@ #define FSCTL_QUERY_NETWORK_INTERFACE_INFO 0x001401FC /* BB add struct */ #define FSCTL_SRV_READ_HASH 0x001441BB /* BB add struct */ +/* See FSCC 2.1.2.5 */ #define IO_REPARSE_TAG_MOUNT_POINT 0xA0000003 #define IO_REPARSE_TAG_HSM 0xC0000004 #define IO_REPARSE_TAG_SIS 0x80000007 +#define IO_REPARSE_TAG_HSM2 0x80000006 +#define IO_REPARSE_TAG_DRIVER_EXTENDER 0x80000005 +/* Used by the DFS filter. See MS-DFSC */ +#define IO_REPARSE_TAG_DFS 0x8000000A +/* Used by the DFS filter See MS-DFSC */ +#define IO_REPARSE_TAG_DFSR 0x80000012 +#define IO_REPARSE_TAG_FILTER_MANAGER 0x8000000B +/* See section MS-FSCC 2.1.2.4 */ +#define IO_REPARSE_TAG_SYMLINK 0xA000000C +#define IO_REPARSE_TAG_DEDUP 0x80000013 +#define IO_REPARSE_APPXSTREAM 0xC0000014 +/* NFS symlinks, Win 8/SMB3 and later */ +#define IO_REPARSE_TAG_NFS 0x80000014 /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 6fdcb1b4a106..800b938e4061 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -410,8 +410,13 @@ static int wait_for_free_request(struct TCP_Server_Info *server, const int timeout, const int optype) { - return wait_for_free_credits(server, timeout, - server->ops->get_credits_field(server, optype)); + int *val; + + val = server->ops->get_credits_field(server, optype); + /* Since an echo is already inflight, no need to wait to send another */ + if (*val <= 0 && optype == CIFS_ECHO_OP) + return -EAGAIN; + return wait_for_free_credits(server, timeout, val); } static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf, diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 1194b1f0f839..f8cde46de9cd 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1783,7 +1783,7 @@ retry: d_tmpfile(dentry, inode); err = ext3_orphan_add(handle, inode); if (err) - goto err_drop_inode; + goto err_unlock_inode; mark_inode_dirty(inode); unlock_new_inode(inode); } @@ -1791,10 +1791,9 @@ retry: if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; -err_drop_inode: +err_unlock_inode: ext3_journal_stop(handle); unlock_new_inode(inode); - iput(inode); return err; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0d424d7ac02b..e274e9c1171f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2563,7 +2563,7 @@ retry: break; } blk_finish_plug(&plug); - if (!ret && !cycled) { + if (!ret && !cycled && wbc->nr_to_write > 0) { cycled = 1; mpd.last_page = writeback_index - 1; mpd.first_page = 0; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 1bec5a5c1e45..5a0408d7b114 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2319,7 +2319,7 @@ retry: d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); if (err) - goto err_drop_inode; + goto err_unlock_inode; mark_inode_dirty(inode); unlock_new_inode(inode); } @@ -2328,10 +2328,9 @@ retry: if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; -err_drop_inode: +err_unlock_inode: ext4_journal_stop(handle); unlock_new_inode(inode); - iput(inode); return err; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index c081e34f717f..03e9bebba198 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1350,6 +1350,8 @@ retry: s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; + kfree(is); is = NULL; + kfree(bs); bs = NULL; goto retry; } error = -1; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 318e8433527c..b2a86e324aac 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -586,7 +586,8 @@ int __fscache_check_consistency(struct fscache_cookie *cookie) fscache_operation_init(op, NULL, NULL); op->flags = FSCACHE_OP_MYTHREAD | - (1 << FSCACHE_OP_WAITING); + (1 << FSCACHE_OP_WAITING) | + (1 << FSCACHE_OP_UNUSE_COOKIE); spin_lock(&cookie->lock); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 62b43b577bfc..b7989f2ab4c4 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -182,6 +182,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) struct inode *inode; struct dentry *parent; struct fuse_conn *fc; + struct fuse_inode *fi; int ret; inode = ACCESS_ONCE(entry->d_inode); @@ -228,7 +229,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (!err && !outarg.nodeid) err = -ENOENT; if (!err) { - struct fuse_inode *fi = get_fuse_inode(inode); + fi = get_fuse_inode(inode); if (outarg.nodeid != get_node_id(inode)) { fuse_queue_forget(fc, forget, outarg.nodeid, 1); goto invalid; @@ -246,8 +247,11 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) attr_version); fuse_change_entry_timeout(entry, &outarg); } else if (inode) { - fc = get_fuse_conn(inode); - if (fc->readdirplus_auto) { + fi = get_fuse_inode(inode); + if (flags & LOOKUP_RCU) { + if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state)) + return -ECHILD; + } else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) { parent = dget_parent(entry); fuse_advise_use_readdirplus(parent->d_inode); dput(parent); @@ -259,7 +263,8 @@ out: invalid: ret = 0; - if (check_submounts_and_drop(entry) != 0) + + if (!(flags & LOOKUP_RCU) && check_submounts_and_drop(entry) != 0) ret = 1; goto out; } @@ -1063,6 +1068,8 @@ static int fuse_access(struct inode *inode, int mask) struct fuse_access_in inarg; int err; + BUG_ON(mask & MAY_NOT_BLOCK); + if (fc->no_access) return 0; @@ -1150,9 +1157,6 @@ static int fuse_permission(struct inode *inode, int mask) noticed immediately, only after the attribute timeout has expired */ } else if (mask & (MAY_ACCESS | MAY_CHDIR)) { - if (mask & MAY_NOT_BLOCK) - return -ECHILD; - err = fuse_access(inode, mask); } else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) { if (!(inode->i_mode & S_IXUGO)) { @@ -1291,6 +1295,8 @@ static int fuse_direntplus_link(struct file *file, } found: + if (fc->readdirplus_auto) + set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); fuse_change_entry_timeout(dentry, o); err = 0; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index d409deafc67b..4598345ab87d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2467,6 +2467,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, { struct fuse_file *ff = file->private_data; struct inode *inode = file->f_inode; + struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = ff->fc; struct fuse_req *req; struct fuse_fallocate_in inarg = { @@ -2484,10 +2485,20 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, if (lock_inode) { mutex_lock(&inode->i_mutex); - if (mode & FALLOC_FL_PUNCH_HOLE) - fuse_set_nowrite(inode); + if (mode & FALLOC_FL_PUNCH_HOLE) { + loff_t endbyte = offset + length - 1; + err = filemap_write_and_wait_range(inode->i_mapping, + offset, endbyte); + if (err) + goto out; + + fuse_sync_writes(inode); + } } + if (!(mode & FALLOC_FL_KEEP_SIZE)) + set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); + req = fuse_get_req_nopages(fc); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -2520,11 +2531,11 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, fuse_invalidate_attr(inode); out: - if (lock_inode) { - if (mode & FALLOC_FL_PUNCH_HOLE) - fuse_release_nowrite(inode); + if (!(mode & FALLOC_FL_KEEP_SIZE)) + clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); + + if (lock_inode) mutex_unlock(&inode->i_mutex); - } return err; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 5ced199b50bb..5b9e6f3b6aef 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -115,6 +115,8 @@ struct fuse_inode { enum { /** Advise readdirplus */ FUSE_I_ADVISE_RDPLUS, + /** Initialized with readdirplus */ + FUSE_I_INIT_RDPLUS, /** An operation changing file size is in progress */ FUSE_I_SIZE_UNSTABLE, }; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 64915eeae5a7..ced3257f06e8 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -694,8 +694,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, mark_inode_dirty(inode); d_instantiate(dentry, inode); - if (file) + if (file) { + *opened |= FILE_CREATED; error = finish_open(file, dentry, gfs2_open_common, opened); + } gfs2_glock_dq_uninit(ghs); gfs2_glock_dq_uninit(ghs + 1); return error; diff --git a/fs/namei.c b/fs/namei.c index 0dc4cbf21f37..645268f23eb6 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2656,6 +2656,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, int acc_mode; int create_error = 0; struct dentry *const DENTRY_NOT_SET = (void *) -1UL; + bool excl; BUG_ON(dentry->d_inode); @@ -2669,10 +2670,9 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) mode &= ~current_umask(); - if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT)) { + excl = (open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT); + if (excl) open_flag &= ~O_TRUNC; - *opened |= FILE_CREATED; - } /* * Checking write permission is tricky, bacuse we don't know if we are @@ -2725,12 +2725,6 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, goto out; } - acc_mode = op->acc_mode; - if (*opened & FILE_CREATED) { - fsnotify_create(dir, dentry); - acc_mode = MAY_OPEN; - } - if (error) { /* returned 1, that is */ if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; @@ -2740,9 +2734,19 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, dput(dentry); dentry = file->f_path.dentry; } - if (create_error && dentry->d_inode == NULL) { - error = create_error; - goto out; + if (*opened & FILE_CREATED) + fsnotify_create(dir, dentry); + if (!dentry->d_inode) { + WARN_ON(*opened & FILE_CREATED); + if (create_error) { + error = create_error; + goto out; + } + } else { + if (excl && !(*opened & FILE_CREATED)) { + error = -EEXIST; + goto out; + } } goto looked_up; } @@ -2751,6 +2755,12 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, * We didn't have the inode before the open, so check open permission * here. */ + acc_mode = op->acc_mode; + if (*opened & FILE_CREATED) { + WARN_ON(!(open_flag & O_CREAT)); + fsnotify_create(dir, dentry); + acc_mode = MAY_OPEN; + } error = may_open(&file->f_path, acc_mode, open_flag); if (error) fput(file); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index de434f309af0..02b0df769e2d 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1392,6 +1392,9 @@ static int nfs_finish_open(struct nfs_open_context *ctx, { int err; + if ((open_flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + *opened |= FILE_CREATED; + err = finish_open(file, dentry, do_open, opened); if (err) goto out; @@ -1455,7 +1458,7 @@ 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/nfs4file.c b/fs/nfs/nfs4file.c index e5b804dd944c..77efaf15ec90 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/nfs4proc.c b/fs/nfs/nfs4proc.c index 989bb9d3074d..d53d6785cba2 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -912,6 +912,7 @@ 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; @@ -1946,8 +1947,13 @@ 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 +2197,8 @@ 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 +2268,8 @@ 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 +2298,8 @@ 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 +2307,7 @@ 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 +2669,8 @@ 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 +2678,7 @@ 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); @@ -3332,6 +3343,7 @@ 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 +3353,7 @@ 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; @@ -7564,8 +7576,10 @@ 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 +7601,31 @@ 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 (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); 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/open.c b/fs/open.c index 2a731b0d08bc..d420331ca32a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -744,14 +744,24 @@ cleanup_file: /** * finish_open - finish opening a file - * @od: opaque open data + * @file: file pointer * @dentry: pointer to dentry * @open: open callback + * @opened: state of open * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. + * + * NB: the dentry reference is _not_ consumed. If, for example, the dentry is + * the return value of d_splice_alias(), then the caller needs to perform dput() + * on it after finish_open(). + * + * On successful return @file is a fully instantiated open file. After this, if + * an error occurs in ->atomic_open(), it needs to clean up with fput(). + * + * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *), @@ -772,11 +782,16 @@ EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * - * @od: opaque open data + * @file: file pointer * @dentry: dentry or NULL (as returned from ->lookup()) * * This can be used to set the result of a successful lookup in ->atomic_open(). - * The filesystem's atomic_open() method shall return NULL after calling this. + * + * NB: unlike finish_open() this function does consume the dentry reference and + * the caller need not dput() it. + * + * Returns "1" which must be the return value of ->atomic_open() after having + * called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 9f8ef9b7674d..8eaa1ba793fc 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -288,10 +288,14 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct proc_dir_entry *pde = PDE(file_inode(file)); - int rv = -EIO; - unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long rv = -EIO; + unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; if (use_pde(pde)) { - get_unmapped_area = pde->proc_fops->get_unmapped_area; +#ifdef CONFIG_MMU + get_unmapped_area = current->mm->get_unmapped_area; +#endif + if (pde->proc_fops->get_unmapped_area) + get_unmapped_area = pde->proc_fops->get_unmapped_area; if (get_unmapped_area) rv = get_unmapped_area(file, orig_addr, len, pgoff, flags); unuse_pde(pde); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7366e9d63cee..390bdab01c3c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -941,6 +941,8 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, frame = pte_pfn(pte); flags = PM_PRESENT; page = vm_normal_page(vma, addr, pte); + if (pte_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; } else if (is_swap_pte(pte)) { swp_entry_t entry; if (pte_swp_soft_dirty(pte)) @@ -960,7 +962,7 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, if (page && !PageAnon(page)) flags |= PM_FILE; - if ((vma->vm_flags & VM_SOFTDIRTY) || pte_soft_dirty(pte)) + if ((vma->vm_flags & VM_SOFTDIRTY)) flags2 |= __PM_SOFT_DIRTY; *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 4ffb7ab5e397..b8e93a40a5d3 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -168,7 +168,7 @@ static int pstore_decompress(void *in, void *out, size_t inlen, size_t outlen) int err, ret; ret = -EIO; - err = zlib_inflateInit(&stream); + err = zlib_inflateInit2(&stream, WINDOW_BITS); if (err != Z_OK) goto error; @@ -195,8 +195,29 @@ error: static void allocate_buf_for_compression(void) { size_t size; + size_t cmpr; + + switch (psinfo->bufsize) { + /* buffer range for efivars */ + case 1000 ... 2000: + cmpr = 56; + break; + case 2001 ... 3000: + cmpr = 54; + break; + case 3001 ... 3999: + cmpr = 52; + break; + /* buffer range for nvram, erst */ + case 4000 ... 10000: + cmpr = 45; + break; + default: + cmpr = 60; + break; + } - big_oops_buf_sz = (psinfo->bufsize * 100) / 45; + big_oops_buf_sz = (psinfo->bufsize * 100) / cmpr; big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); if (big_oops_buf) { size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL), @@ -295,10 +316,6 @@ static void pstore_dump(struct kmsg_dumper *dumper, compressed = true; total_len = zipped_len; } else { - pr_err("pstore: compression failed for Part %d" - " returned %d\n", part, zipped_len); - pr_err("pstore: Capture uncompressed" - " oops/panic report of Part %d\n", part); compressed = false; total_len = copy_kmsg_to_buffer(hsize, len); } 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/statfs.c b/fs/statfs.c index c219e733f553..083dc0ac9140 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -94,7 +94,7 @@ retry: int fd_statfs(int fd, struct kstatfs *st) { - struct fd f = fdget(fd); + struct fd f = fdget_raw(fd); int error = -EBADF; if (f.file) { error = vfs_statfs(&f.file->f_path, st); diff --git a/fs/super.c b/fs/super.c index 3a96c9783a8b..0225c20f8770 100644 --- a/fs/super.c +++ b/fs/super.c @@ -264,6 +264,8 @@ out_free_sb: */ static inline void destroy_super(struct super_block *s) { + list_lru_destroy(&s->s_dentry_lru); + list_lru_destroy(&s->s_inode_lru); #ifdef CONFIG_SMP free_percpu(s->s_files); #endif @@ -323,8 +325,6 @@ void deactivate_locked_super(struct super_block *s) /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); - list_lru_destroy(&s->s_dentry_lru); - list_lru_destroy(&s->s_inode_lru); put_filesystem(fs); put_super(s); 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_dir2_block.c b/fs/xfs/xfs_dir2_block.c index 0957aa98b6c0..12dad188939d 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -1158,7 +1158,7 @@ xfs_dir2_sf_to_block( /* * Create entry for . */ - dep = xfs_dir3_data_dot_entry_p(hdr); + dep = xfs_dir3_data_dot_entry_p(mp, hdr); dep->inumber = cpu_to_be64(dp->i_ino); dep->namelen = 1; dep->name[0] = '.'; @@ -1172,7 +1172,7 @@ xfs_dir2_sf_to_block( /* * Create entry for .. */ - dep = xfs_dir3_data_dotdot_entry_p(hdr); + dep = xfs_dir3_data_dotdot_entry_p(mp, hdr); dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp)); dep->namelen = 2; dep->name[0] = dep->name[1] = '.'; @@ -1183,7 +1183,7 @@ xfs_dir2_sf_to_block( blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot); blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp, (char *)dep - (char *)hdr)); - offset = xfs_dir3_data_first_offset(hdr); + offset = xfs_dir3_data_first_offset(mp); /* * Loop over existing entries, stuff them in. */ diff --git a/fs/xfs/xfs_dir2_format.h b/fs/xfs/xfs_dir2_format.h index a0961a61ac1a..9cf67381adf6 100644 --- a/fs/xfs/xfs_dir2_format.h +++ b/fs/xfs/xfs_dir2_format.h @@ -497,69 +497,58 @@ xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr) /* * Offsets of . and .. in data space (always block 0) * - * The macros are used for shortform directories as they have no headers to read - * the magic number out of. Shortform directories need to know the size of the - * data block header because the sfe embeds the block offset of the entry into - * it so that it doesn't change when format conversion occurs. Bad Things Happen - * if we don't follow this rule. - * * XXX: there is scope for significant optimisation of the logic here. Right * now we are checking for "dir3 format" over and over again. Ideally we should * only do it once for each operation. */ -#define XFS_DIR3_DATA_DOT_OFFSET(mp) \ - xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&(mp)->m_sb)) -#define XFS_DIR3_DATA_DOTDOT_OFFSET(mp) \ - (XFS_DIR3_DATA_DOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 1)) -#define XFS_DIR3_DATA_FIRST_OFFSET(mp) \ - (XFS_DIR3_DATA_DOTDOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 2)) - static inline xfs_dir2_data_aoff_t -xfs_dir3_data_dot_offset(struct xfs_dir2_data_hdr *hdr) +xfs_dir3_data_dot_offset(struct xfs_mount *mp) { - return xfs_dir3_data_entry_offset(hdr); + return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb)); } static inline xfs_dir2_data_aoff_t -xfs_dir3_data_dotdot_offset(struct xfs_dir2_data_hdr *hdr) +xfs_dir3_data_dotdot_offset(struct xfs_mount *mp) { - bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) || - hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC); - return xfs_dir3_data_dot_offset(hdr) + - __xfs_dir3_data_entsize(dir3, 1); + return xfs_dir3_data_dot_offset(mp) + + xfs_dir3_data_entsize(mp, 1); } static inline xfs_dir2_data_aoff_t -xfs_dir3_data_first_offset(struct xfs_dir2_data_hdr *hdr) +xfs_dir3_data_first_offset(struct xfs_mount *mp) { - bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) || - hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC); - return xfs_dir3_data_dotdot_offset(hdr) + - __xfs_dir3_data_entsize(dir3, 2); + return xfs_dir3_data_dotdot_offset(mp) + + xfs_dir3_data_entsize(mp, 2); } /* * location of . and .. in data space (always block 0) */ static inline struct xfs_dir2_data_entry * -xfs_dir3_data_dot_entry_p(struct xfs_dir2_data_hdr *hdr) +xfs_dir3_data_dot_entry_p( + struct xfs_mount *mp, + struct xfs_dir2_data_hdr *hdr) { return (struct xfs_dir2_data_entry *) - ((char *)hdr + xfs_dir3_data_dot_offset(hdr)); + ((char *)hdr + xfs_dir3_data_dot_offset(mp)); } static inline struct xfs_dir2_data_entry * -xfs_dir3_data_dotdot_entry_p(struct xfs_dir2_data_hdr *hdr) +xfs_dir3_data_dotdot_entry_p( + struct xfs_mount *mp, + struct xfs_dir2_data_hdr *hdr) { return (struct xfs_dir2_data_entry *) - ((char *)hdr + xfs_dir3_data_dotdot_offset(hdr)); + ((char *)hdr + xfs_dir3_data_dotdot_offset(mp)); } static inline struct xfs_dir2_data_entry * -xfs_dir3_data_first_entry_p(struct xfs_dir2_data_hdr *hdr) +xfs_dir3_data_first_entry_p( + struct xfs_mount *mp, + struct xfs_dir2_data_hdr *hdr) { return (struct xfs_dir2_data_entry *) - ((char *)hdr + xfs_dir3_data_first_offset(hdr)); + ((char *)hdr + xfs_dir3_data_first_offset(mp)); } /* diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 8993ec17452c..8f84153e98a8 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -119,9 +119,9 @@ xfs_dir2_sf_getdents( * mp->m_dirdatablk. */ dot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, - XFS_DIR3_DATA_DOT_OFFSET(mp)); + xfs_dir3_data_dot_offset(mp)); dotdot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, - XFS_DIR3_DATA_DOTDOT_OFFSET(mp)); + xfs_dir3_data_dotdot_offset(mp)); /* * Put . entry unless we're starting past it. diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c index bb6e2848f473..3ef6d402084c 100644 --- a/fs/xfs/xfs_dir2_sf.c +++ b/fs/xfs/xfs_dir2_sf.c @@ -557,7 +557,7 @@ xfs_dir2_sf_addname_hard( * to insert the new entry. * If it's going to end up at the end then oldsfep will point there. */ - for (offset = XFS_DIR3_DATA_FIRST_OFFSET(mp), + for (offset = xfs_dir3_data_first_offset(mp), oldsfep = xfs_dir2_sf_firstentry(oldsfp), add_datasize = xfs_dir3_data_entsize(mp, args->namelen), eof = (char *)oldsfep == &buf[old_isize]; @@ -640,7 +640,7 @@ xfs_dir2_sf_addname_pick( sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; size = xfs_dir3_data_entsize(mp, args->namelen); - offset = XFS_DIR3_DATA_FIRST_OFFSET(mp); + offset = xfs_dir3_data_first_offset(mp); sfep = xfs_dir2_sf_firstentry(sfp); holefit = 0; /* @@ -713,7 +713,7 @@ xfs_dir2_sf_check( mp = dp->i_mount; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; - offset = XFS_DIR3_DATA_FIRST_OFFSET(mp); + offset = xfs_dir3_data_first_offset(mp); ino = xfs_dir2_sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 71520e6e5d65..1ee776d477c3 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -64,7 +64,8 @@ int xfs_dqerror_mod = 33; struct kmem_zone *xfs_qm_dqtrxzone; static struct kmem_zone *xfs_qm_dqzone; -static struct lock_class_key xfs_dquot_other_class; +static struct lock_class_key xfs_dquot_group_class; +static struct lock_class_key xfs_dquot_project_class; /* * This is called to free all the memory associated with a dquot @@ -703,8 +704,20 @@ xfs_qm_dqread( * Make sure group quotas have a different lock class than user * quotas. */ - if (!(type & XFS_DQ_USER)) - lockdep_set_class(&dqp->q_qlock, &xfs_dquot_other_class); + switch (type) { + case XFS_DQ_USER: + /* uses the default lock class */ + break; + case XFS_DQ_GROUP: + lockdep_set_class(&dqp->q_qlock, &xfs_dquot_group_class); + break; + case XFS_DQ_PROJ: + lockdep_set_class(&dqp->q_qlock, &xfs_dquot_project_class); + break; + default: + ASSERT(0); + break; + } XFS_STATS_INC(xs_qm_dquot); 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..39797490a1f1 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1585,6 +1585,7 @@ xlog_recover_add_to_trans( "bad number of regions (%d) in inode log format", in_f->ilf_size); ASSERT(0); + kmem_free(ptr); return XFS_ERROR(EIO); } @@ -1970,6 +1971,13 @@ 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 +1988,8 @@ 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 +2002,79 @@ 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 |