diff options
Diffstat (limited to 'fs')
111 files changed, 4684 insertions, 3661 deletions
diff --git a/fs/Makefile b/fs/Makefile index 4fe6df3ec28f..39a824f44e7c 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -53,7 +53,7 @@ obj-$(CONFIG_FHANDLE) += fhandle.o obj-y += quota/ obj-$(CONFIG_PROC_FS) += proc/ -obj-$(CONFIG_SYSFS) += sysfs/ +obj-$(CONFIG_SYSFS) += sysfs/ kernfs/ obj-$(CONFIG_CONFIGFS_FS) += configfs/ obj-y += devpts/ diff --git a/fs/affs/Changes b/fs/affs/Changes index a29409c1ffe0..b41c2c9792ff 100644 --- a/fs/affs/Changes +++ b/fs/affs/Changes @@ -91,7 +91,7 @@ more 2.4 fixes: [Roman Zippel] Version 3.11 ------------ -- Converted to use 2.3.x page cache [Dave Jones <dave@powertweak.com>] +- Converted to use 2.3.x page cache [Dave Jones] - Corruption in truncate() bugfix [Ken Tyler <kent@werple.net.au>] Version 3.10 @@ -244,9 +244,14 @@ static void aio_free_ring(struct kioctx *ctx) int i; for (i = 0; i < ctx->nr_pages; i++) { + struct page *page; pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i, page_count(ctx->ring_pages[i])); - put_page(ctx->ring_pages[i]); + page = ctx->ring_pages[i]; + if (!page) + continue; + ctx->ring_pages[i] = NULL; + put_page(page); } put_aio_ring_file(ctx); @@ -280,18 +285,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, unsigned long flags; int rc; + rc = 0; + + /* Make sure the old page hasn't already been changed */ + spin_lock(&mapping->private_lock); + ctx = mapping->private_data; + if (ctx) { + pgoff_t idx; + spin_lock_irqsave(&ctx->completion_lock, flags); + idx = old->index; + if (idx < (pgoff_t)ctx->nr_pages) { + if (ctx->ring_pages[idx] != old) + rc = -EAGAIN; + } else + rc = -EINVAL; + spin_unlock_irqrestore(&ctx->completion_lock, flags); + } else + rc = -EINVAL; + spin_unlock(&mapping->private_lock); + + if (rc != 0) + return rc; + /* Writeback must be complete */ BUG_ON(PageWriteback(old)); - put_page(old); + get_page(new); - rc = migrate_page_move_mapping(mapping, new, old, NULL, mode); + rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1); if (rc != MIGRATEPAGE_SUCCESS) { - get_page(old); + put_page(new); return rc; } - get_page(new); - /* We can potentially race against kioctx teardown here. Use the * address_space's private data lock to protect the mapping's * private_data. @@ -303,13 +328,24 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, 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; + if (idx < (pgoff_t)ctx->nr_pages) { + /* And only do the move if things haven't changed */ + if (ctx->ring_pages[idx] == old) + ctx->ring_pages[idx] = new; + else + rc = -EAGAIN; + } else + rc = -EINVAL; spin_unlock_irqrestore(&ctx->completion_lock, flags); } else rc = -EBUSY; spin_unlock(&mapping->private_lock); + if (rc == MIGRATEPAGE_SUCCESS) + put_page(old); + else + put_page(new); + return rc; } #endif @@ -326,7 +362,7 @@ static int aio_setup_ring(struct kioctx *ctx) struct aio_ring *ring; unsigned nr_events = ctx->max_reqs; struct mm_struct *mm = current->mm; - unsigned long size, populate; + unsigned long size, unused; int nr_pages; int i; struct file *file; @@ -347,6 +383,20 @@ static int aio_setup_ring(struct kioctx *ctx) return -EAGAIN; } + ctx->aio_ring_file = file; + nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) + / sizeof(struct io_event); + + ctx->ring_pages = ctx->internal_pages; + if (nr_pages > AIO_RING_PAGES) { + ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), + GFP_KERNEL); + if (!ctx->ring_pages) { + put_aio_ring_file(ctx); + return -ENOMEM; + } + } + for (i = 0; i < nr_pages; i++) { struct page *page; page = find_or_create_page(file->f_inode->i_mapping, @@ -358,17 +408,14 @@ static int aio_setup_ring(struct kioctx *ctx) SetPageUptodate(page); SetPageDirty(page); unlock_page(page); + + ctx->ring_pages[i] = page; } - ctx->aio_ring_file = file; - nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) - / sizeof(struct io_event); + ctx->nr_pages = i; - ctx->ring_pages = ctx->internal_pages; - if (nr_pages > AIO_RING_PAGES) { - ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), - GFP_KERNEL); - if (!ctx->ring_pages) - return -ENOMEM; + if (unlikely(i != nr_pages)) { + aio_free_ring(ctx); + return -EAGAIN; } ctx->mmap_size = nr_pages * PAGE_SIZE; @@ -377,9 +424,9 @@ static int aio_setup_ring(struct kioctx *ctx) down_write(&mm->mmap_sem); ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, 0, &populate); + MAP_SHARED, 0, &unused); + up_write(&mm->mmap_sem); if (IS_ERR((void *)ctx->mmap_base)) { - up_write(&mm->mmap_sem); ctx->mmap_size = 0; aio_free_ring(ctx); return -EAGAIN; @@ -387,27 +434,6 @@ static int aio_setup_ring(struct kioctx *ctx) pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); - /* We must do this while still holding mmap_sem for write, as we - * need to be protected against userspace attempting to mremap() - * or munmap() the ring buffer. - */ - ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages, - 1, 0, ctx->ring_pages, NULL); - - /* Dropping the reference here is safe as the page cache will hold - * onto the pages for us. It is also required so that page migration - * can unmap the pages and get the right reference count. - */ - for (i = 0; i < ctx->nr_pages; i++) - put_page(ctx->ring_pages[i]); - - up_write(&mm->mmap_sem); - - if (unlikely(ctx->nr_pages != nr_pages)) { - aio_free_ring(ctx); - return -EAGAIN; - } - ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ @@ -645,12 +671,13 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) aio_nr + nr_events < aio_nr) { spin_unlock(&aio_nr_lock); err = -EAGAIN; - goto err; + goto err_ctx; } aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); - percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ + percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ + percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */ err = ioctx_add_table(ctx, mm); if (err) @@ -662,6 +689,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err_cleanup: aio_nr_sub(ctx->max_reqs); +err_ctx: + aio_free_ring(ctx); err: free_percpu(ctx->cpu); free_percpu(ctx->reqs.pcpu_count); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index b50764bef141..131d82800b3a 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -333,7 +333,6 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx); static int btrfsic_read_block(struct btrfsic_state *state, struct btrfsic_block_data_ctx *block_ctx); static void btrfsic_dump_database(struct btrfsic_state *state); -static void btrfsic_complete_bio_end_io(struct bio *bio, int err); static int btrfsic_test_for_metadata(struct btrfsic_state *state, char **datav, unsigned int num_pages); static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, @@ -1687,7 +1686,6 @@ static int btrfsic_read_block(struct btrfsic_state *state, for (i = 0; i < num_pages;) { struct bio *bio; unsigned int j; - DECLARE_COMPLETION_ONSTACK(complete); bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i); if (!bio) { @@ -1698,8 +1696,6 @@ static int btrfsic_read_block(struct btrfsic_state *state, } bio->bi_bdev = block_ctx->dev->bdev; bio->bi_sector = dev_bytenr >> 9; - bio->bi_end_io = btrfsic_complete_bio_end_io; - bio->bi_private = &complete; for (j = i; j < num_pages; j++) { ret = bio_add_page(bio, block_ctx->pagev[j], @@ -1712,12 +1708,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, "btrfsic: error, failed to add a single page!\n"); return -1; } - submit_bio(READ, bio); - - /* this will also unplug the queue */ - wait_for_completion(&complete); - - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { + if (submit_bio_wait(READ, bio)) { printk(KERN_INFO "btrfsic: read error at logical %llu dev %s!\n", block_ctx->start, block_ctx->dev->name); @@ -1740,11 +1731,6 @@ static int btrfsic_read_block(struct btrfsic_state *state, return block_ctx->len; } -static void btrfsic_complete_bio_end_io(struct bio *bio, int err) -{ - complete((struct completion *)bio->bi_private); -} - static void btrfsic_dump_database(struct btrfsic_state *state) { struct list_head *elem_all; @@ -3008,14 +2994,12 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh) return submit_bh(rw, bh); } -void btrfsic_submit_bio(int rw, struct bio *bio) +static void __btrfsic_submit_bio(int rw, struct bio *bio) { struct btrfsic_dev_state *dev_state; - if (!btrfsic_is_initialized) { - submit_bio(rw, bio); + if (!btrfsic_is_initialized) return; - } mutex_lock(&btrfsic_mutex); /* since btrfsic_submit_bio() is also called before @@ -3106,10 +3090,20 @@ void btrfsic_submit_bio(int rw, struct bio *bio) } leave: mutex_unlock(&btrfsic_mutex); +} +void btrfsic_submit_bio(int rw, struct bio *bio) +{ + __btrfsic_submit_bio(rw, bio); submit_bio(rw, bio); } +int btrfsic_submit_bio_wait(int rw, struct bio *bio) +{ + __btrfsic_submit_bio(rw, bio); + return submit_bio_wait(rw, bio); +} + int btrfsic_mount(struct btrfs_root *root, struct btrfs_fs_devices *fs_devices, int including_extent_data, u32 print_mask) diff --git a/fs/btrfs/check-integrity.h b/fs/btrfs/check-integrity.h index 8b59175cc502..13b8566c97ab 100644 --- a/fs/btrfs/check-integrity.h +++ b/fs/btrfs/check-integrity.h @@ -22,9 +22,11 @@ #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY int btrfsic_submit_bh(int rw, struct buffer_head *bh); void btrfsic_submit_bio(int rw, struct bio *bio); +int btrfsic_submit_bio_wait(int rw, struct bio *bio); #else #define btrfsic_submit_bh submit_bh #define btrfsic_submit_bio submit_bio +#define btrfsic_submit_bio_wait submit_bio_wait #endif int btrfsic_mount(struct btrfs_root *root, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 45d98d01028f..9c01509dd8ab 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -767,20 +767,19 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - if (metadata) { - key.objectid = bytenr; - key.type = BTRFS_METADATA_ITEM_KEY; - key.offset = offset; - } else { - key.objectid = bytenr; - key.type = BTRFS_EXTENT_ITEM_KEY; - key.offset = offset; - } - if (!trans) { path->skip_locking = 1; path->search_commit_root = 1; } + +search_again: + key.objectid = bytenr; + key.offset = offset; + if (metadata) + key.type = BTRFS_METADATA_ITEM_KEY; + else + key.type = BTRFS_EXTENT_ITEM_KEY; + again: ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key, path, 0, 0); @@ -788,7 +787,6 @@ again: goto out_free; if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) { - metadata = 0; if (path->slots[0]) { path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &key, @@ -855,7 +853,7 @@ again: mutex_lock(&head->mutex); mutex_unlock(&head->mutex); btrfs_put_delayed_ref(&head->node); - goto again; + goto search_again; } if (head->extent_op && head->extent_op->update_flags) extent_flags |= head->extent_op->flags_to_set; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 8e457fca0a0b..ff43802a7c88 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1952,11 +1952,6 @@ static int free_io_failure(struct inode *inode, struct io_failure_record *rec, return err; } -static void repair_io_failure_callback(struct bio *bio, int err) -{ - complete(bio->bi_private); -} - /* * this bypasses the standard btrfs submit functions deliberately, as * the standard behavior is to write all copies in a raid setup. here we only @@ -1973,7 +1968,6 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, { struct bio *bio; struct btrfs_device *dev; - DECLARE_COMPLETION_ONSTACK(compl); u64 map_length = 0; u64 sector; struct btrfs_bio *bbio = NULL; @@ -1990,8 +1984,6 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, bio = btrfs_io_bio_alloc(GFP_NOFS, 1); if (!bio) return -EIO; - bio->bi_private = &compl; - bio->bi_end_io = repair_io_failure_callback; bio->bi_size = 0; map_length = length; @@ -2012,10 +2004,8 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, } bio->bi_bdev = dev->bdev; bio_add_page(bio, page, length, start - page_offset(page)); - btrfsic_submit_bio(WRITE_SYNC, bio); - wait_for_completion(&compl); - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { + if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) { /* try to remap that extent elsewhere? */ bio_put(bio); btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a111622598b0..21da5762b0b1 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2121,7 +2121,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT); if (err == -EINTR) - goto out; + goto out_drop_write; dentry = lookup_one_len(vol_args->name, parent, namelen); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); @@ -2284,6 +2284,7 @@ out_dput: dput(dentry); out_unlock_dir: mutex_unlock(&dir->i_mutex); +out_drop_write: mnt_drop_write_file(file); out: kfree(vol_args); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index ce459a7cb16d..429c73c374b8 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -571,7 +571,9 @@ static int is_cowonly_root(u64 root_objectid) root_objectid == BTRFS_CHUNK_TREE_OBJECTID || root_objectid == BTRFS_DEV_TREE_OBJECTID || root_objectid == BTRFS_TREE_LOG_OBJECTID || - root_objectid == BTRFS_CSUM_TREE_OBJECTID) + root_objectid == BTRFS_CSUM_TREE_OBJECTID || + root_objectid == BTRFS_UUID_TREE_OBJECTID || + root_objectid == BTRFS_QUOTA_TREE_OBJECTID) return 1; return 0; } @@ -1264,10 +1266,10 @@ static int __must_check __add_reloc_root(struct btrfs_root *root) } /* - * helper to update/delete the 'address of tree root -> reloc tree' + * helper to delete the 'address of tree root -> reloc tree' * mapping */ -static int __update_reloc_root(struct btrfs_root *root, int del) +static void __del_reloc_root(struct btrfs_root *root) { struct rb_node *rb_node; struct mapping_node *node = NULL; @@ -1275,7 +1277,7 @@ static int __update_reloc_root(struct btrfs_root *root, int del) spin_lock(&rc->reloc_root_tree.lock); rb_node = tree_search(&rc->reloc_root_tree.rb_root, - root->commit_root->start); + root->node->start); if (rb_node) { node = rb_entry(rb_node, struct mapping_node, rb_node); rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root); @@ -1283,23 +1285,45 @@ static int __update_reloc_root(struct btrfs_root *root, int del) spin_unlock(&rc->reloc_root_tree.lock); if (!node) - return 0; + return; BUG_ON((struct btrfs_root *)node->data != root); - if (!del) { - spin_lock(&rc->reloc_root_tree.lock); - node->bytenr = root->node->start; - rb_node = tree_insert(&rc->reloc_root_tree.rb_root, - node->bytenr, &node->rb_node); - spin_unlock(&rc->reloc_root_tree.lock); - if (rb_node) - backref_tree_panic(rb_node, -EEXIST, node->bytenr); - } else { - spin_lock(&root->fs_info->trans_lock); - list_del_init(&root->root_list); - spin_unlock(&root->fs_info->trans_lock); - kfree(node); + spin_lock(&root->fs_info->trans_lock); + list_del_init(&root->root_list); + spin_unlock(&root->fs_info->trans_lock); + kfree(node); +} + +/* + * helper to update the 'address of tree root -> reloc tree' + * mapping + */ +static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr) +{ + struct rb_node *rb_node; + struct mapping_node *node = NULL; + struct reloc_control *rc = root->fs_info->reloc_ctl; + + spin_lock(&rc->reloc_root_tree.lock); + rb_node = tree_search(&rc->reloc_root_tree.rb_root, + root->node->start); + if (rb_node) { + node = rb_entry(rb_node, struct mapping_node, rb_node); + rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root); } + spin_unlock(&rc->reloc_root_tree.lock); + + if (!node) + return 0; + BUG_ON((struct btrfs_root *)node->data != root); + + spin_lock(&rc->reloc_root_tree.lock); + node->bytenr = new_bytenr; + rb_node = tree_insert(&rc->reloc_root_tree.rb_root, + node->bytenr, &node->rb_node); + spin_unlock(&rc->reloc_root_tree.lock); + if (rb_node) + backref_tree_panic(rb_node, -EEXIST, node->bytenr); return 0; } @@ -1420,7 +1444,6 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, { struct btrfs_root *reloc_root; struct btrfs_root_item *root_item; - int del = 0; int ret; if (!root->reloc_root) @@ -1432,11 +1455,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, if (root->fs_info->reloc_ctl->merge_reloc_tree && btrfs_root_refs(root_item) == 0) { root->reloc_root = NULL; - del = 1; + __del_reloc_root(reloc_root); } - __update_reloc_root(reloc_root, del); - if (reloc_root->commit_root != reloc_root->node) { btrfs_set_root_node(root_item, reloc_root->node); free_extent_buffer(reloc_root->commit_root); @@ -2287,7 +2308,7 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); - __update_reloc_root(reloc_root, 1); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); kfree(reloc_root); @@ -2332,7 +2353,7 @@ again: ret = merge_reloc_root(rc, root); if (ret) { - __update_reloc_root(reloc_root, 1); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); kfree(reloc_root); @@ -2388,6 +2409,13 @@ out: btrfs_std_error(root->fs_info, ret); if (!list_empty(&reloc_roots)) free_reloc_roots(&reloc_roots); + + /* new reloc root may be added */ + mutex_lock(&root->fs_info->reloc_mutex); + list_splice_init(&rc->reloc_roots, &reloc_roots); + mutex_unlock(&root->fs_info->reloc_mutex); + if (!list_empty(&reloc_roots)) + free_reloc_roots(&reloc_roots); } BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root)); @@ -4522,6 +4550,11 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, BUG_ON(rc->stage == UPDATE_DATA_PTRS && root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID); + if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { + if (buf == root->node) + __update_reloc_root(root, cow->start); + } + level = btrfs_header_level(buf); if (btrfs_header_generation(buf) <= btrfs_root_last_snapshot(&root->root_item)) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 561e2f16ba3e..1fd3f33c330a 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -208,7 +208,6 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, int is_metadata, int have_csum, const u8 *csum, u64 generation, u16 csum_size); -static void scrub_complete_bio_end_io(struct bio *bio, int err); static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good, int force_write); @@ -1294,7 +1293,6 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, for (page_num = 0; page_num < sblock->page_count; page_num++) { struct bio *bio; struct scrub_page *page = sblock->pagev[page_num]; - DECLARE_COMPLETION_ONSTACK(complete); if (page->dev->bdev == NULL) { page->io_error = 1; @@ -1311,18 +1309,11 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, } bio->bi_bdev = page->dev->bdev; bio->bi_sector = page->physical >> 9; - bio->bi_end_io = scrub_complete_bio_end_io; - bio->bi_private = &complete; bio_add_page(bio, page->page, PAGE_SIZE, 0); - btrfsic_submit_bio(READ, bio); - - /* this will also unplug the queue */ - wait_for_completion(&complete); - - page->io_error = !test_bit(BIO_UPTODATE, &bio->bi_flags); - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) + if (btrfsic_submit_bio_wait(READ, bio)) sblock->no_io_error_seen = 0; + bio_put(bio); } @@ -1391,11 +1382,6 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, sblock->checksum_error = 1; } -static void scrub_complete_bio_end_io(struct bio *bio, int err) -{ - complete((struct completion *)bio->bi_private); -} - static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good, int force_write) @@ -1430,7 +1416,6 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, sblock_bad->checksum_error || page_bad->io_error) { struct bio *bio; int ret; - DECLARE_COMPLETION_ONSTACK(complete); if (!page_bad->dev->bdev) { printk_ratelimited(KERN_WARNING @@ -1443,19 +1428,14 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, return -EIO; bio->bi_bdev = page_bad->dev->bdev; bio->bi_sector = page_bad->physical >> 9; - bio->bi_end_io = scrub_complete_bio_end_io; - bio->bi_private = &complete; ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0); if (PAGE_SIZE != ret) { bio_put(bio); return -EIO; } - btrfsic_submit_bio(WRITE, bio); - /* this will also unplug the queue */ - wait_for_completion(&complete); - if (!bio_flagged(bio, BIO_UPTODATE)) { + if (btrfsic_submit_bio_wait(WRITE, bio)) { btrfs_dev_stat_inc_and_print(page_bad->dev, BTRFS_DEV_STAT_WRITE_ERRS); btrfs_dev_replace_stats_inc( @@ -3375,7 +3355,6 @@ static int write_page_nocow(struct scrub_ctx *sctx, struct bio *bio; struct btrfs_device *dev; int ret; - DECLARE_COMPLETION_ONSTACK(compl); dev = sctx->wr_ctx.tgtdev; if (!dev) @@ -3392,8 +3371,6 @@ static int write_page_nocow(struct scrub_ctx *sctx, spin_unlock(&sctx->stat_lock); return -ENOMEM; } - bio->bi_private = &compl; - bio->bi_end_io = scrub_complete_bio_end_io; bio->bi_size = 0; bio->bi_sector = physical_for_dev_replace >> 9; bio->bi_bdev = dev->bdev; @@ -3404,10 +3381,8 @@ leave_with_eio: btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); return -EIO; } - btrfsic_submit_bio(WRITE_SYNC, bio); - wait_for_completion(&compl); - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) + if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) goto leave_with_eio; bio_put(bio); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 6837fe87f3a6..945d1db98f26 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4723,8 +4723,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) } if (!access_ok(VERIFY_READ, arg->clone_sources, - sizeof(*arg->clone_sources * - arg->clone_sources_count))) { + sizeof(*arg->clone_sources) * + arg->clone_sources_count)) { ret = -EFAULT; goto out; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 2d8ac1bf0cf9..d71a11d13dfa 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -432,7 +432,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) } else { printk(KERN_INFO "btrfs: setting nodatacow\n"); } - info->compress_type = BTRFS_COMPRESS_NONE; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); btrfs_set_opt(info->mount_opt, NODATACOW); @@ -461,7 +460,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_fs_incompat(info, COMPRESS_LZO); } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; - info->compress_type = BTRFS_COMPRESS_NONE; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); compress_force = false; @@ -474,9 +472,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_opt(info->mount_opt, FORCE_COMPRESS); pr_info("btrfs: force %s compression\n", compress_type); - } else + } else if (btrfs_test_opt(root, COMPRESS)) { pr_info("btrfs: use %s compression\n", compress_type); + } break; case Opt_ssd: printk(KERN_INFO "btrfs: use ssd allocation scheme\n"); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6df8bd481425..ec3ba43b9faa 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -210,13 +210,17 @@ static int readpage_nounlock(struct file *filp, struct page *page) if (err < 0) { SetPageError(page); goto out; - } else if (err < PAGE_CACHE_SIZE) { + } else { + if (err < PAGE_CACHE_SIZE) { /* zero fill remainder of page */ - zero_user_segment(page, err, PAGE_CACHE_SIZE); + zero_user_segment(page, err, PAGE_CACHE_SIZE); + } else { + flush_dcache_page(page); + } } SetPageUptodate(page); - if (err == 0) + if (err >= 0) ceph_readpage_to_fscache(inode, page); out: diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 7db2e6ca4b8f..8c44fdd4e1c3 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -324,6 +324,9 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page) { struct ceph_inode_info *ci = ceph_inode(inode); + if (!PageFsCache(page)) + return; + fscache_wait_on_page_write(ci->fscache, page); fscache_uncache_page(ci->fscache, page); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 13976c33332e..3c0a4bd74996 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -897,7 +897,7 @@ static int __ceph_is_any_caps(struct ceph_inode_info *ci) * caller should hold i_ceph_lock. * caller will not hold session s_mutex if called from destroy_inode. */ -void __ceph_remove_cap(struct ceph_cap *cap) +void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) { struct ceph_mds_session *session = cap->session; struct ceph_inode_info *ci = cap->ci; @@ -909,6 +909,16 @@ void __ceph_remove_cap(struct ceph_cap *cap) /* remove from session list */ spin_lock(&session->s_cap_lock); + /* + * s_cap_reconnect is protected by s_cap_lock. no one changes + * s_cap_gen while session is in the reconnect state. + */ + if (queue_release && + (!session->s_cap_reconnect || + cap->cap_gen == session->s_cap_gen)) + __queue_cap_release(session, ci->i_vino.ino, cap->cap_id, + cap->mseq, cap->issue_seq); + if (session->s_cap_iterator == cap) { /* not yet, we are iterating over this very cap */ dout("__ceph_remove_cap delaying %p removal from session %p\n", @@ -1023,7 +1033,6 @@ void __queue_cap_release(struct ceph_mds_session *session, struct ceph_mds_cap_release *head; struct ceph_mds_cap_item *item; - spin_lock(&session->s_cap_lock); BUG_ON(!session->s_num_cap_releases); msg = list_first_entry(&session->s_cap_releases, struct ceph_msg, list_head); @@ -1052,7 +1061,6 @@ void __queue_cap_release(struct ceph_mds_session *session, (int)CEPH_CAPS_PER_RELEASE, (int)msg->front.iov_len); } - spin_unlock(&session->s_cap_lock); } /* @@ -1067,12 +1075,8 @@ void ceph_queue_caps_release(struct inode *inode) p = rb_first(&ci->i_caps); while (p) { struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); - struct ceph_mds_session *session = cap->session; - - __queue_cap_release(session, ceph_ino(inode), cap->cap_id, - cap->mseq, cap->issue_seq); p = rb_next(p); - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, true); } } @@ -2791,7 +2795,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, } spin_unlock(&mdsc->cap_dirty_lock); } - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, false); } /* else, we already released it */ @@ -2931,9 +2935,12 @@ void ceph_handle_caps(struct ceph_mds_session *session, if (!inode) { dout(" i don't have ino %llx\n", vino.ino); - if (op == CEPH_CAP_OP_IMPORT) + if (op == CEPH_CAP_OP_IMPORT) { + spin_lock(&session->s_cap_lock); __queue_cap_release(session, vino.ino, cap_id, mseq, seq); + spin_unlock(&session->s_cap_lock); + } goto flush_cap_releases; } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 868b61d56cac..2a0bcaeb189a 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -352,8 +352,18 @@ more: } /* note next offset and last dentry name */ + rinfo = &req->r_reply_info; + if (le32_to_cpu(rinfo->dir_dir->frag) != frag) { + frag = le32_to_cpu(rinfo->dir_dir->frag); + if (ceph_frag_is_leftmost(frag)) + fi->next_offset = 2; + else + fi->next_offset = 0; + off = fi->next_offset; + } fi->offset = fi->next_offset; fi->last_readdir = req; + fi->frag = frag; if (req->r_reply_info.dir_end) { kfree(fi->last_name); @@ -363,7 +373,6 @@ more: else fi->next_offset = 0; } else { - rinfo = &req->r_reply_info; err = note_last_dentry(fi, rinfo->dir_dname[rinfo->dir_nr-1], rinfo->dir_dname_len[rinfo->dir_nr-1]); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8549a48115f7..278fd2891288 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,6 +577,8 @@ static int fill_inode(struct inode *inode, int issued = 0, implemented; struct timespec mtime, atime, ctime; u32 nsplits; + struct ceph_inode_frag *frag; + struct rb_node *rb_node; struct ceph_buffer *xattr_blob = NULL; int err = 0; int queue_trunc = 0; @@ -751,15 +753,38 @@ no_change: /* FIXME: move me up, if/when version reflects fragtree changes */ nsplits = le32_to_cpu(info->fragtree.nsplits); mutex_lock(&ci->i_fragtree_mutex); + rb_node = rb_first(&ci->i_fragtree); for (i = 0; i < nsplits; i++) { u32 id = le32_to_cpu(info->fragtree.splits[i].frag); - struct ceph_inode_frag *frag = __get_or_create_frag(ci, id); - - if (IS_ERR(frag)) - continue; + frag = NULL; + while (rb_node) { + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + if (ceph_frag_compare(frag->frag, id) >= 0) { + if (frag->frag != id) + frag = NULL; + else + rb_node = rb_next(rb_node); + break; + } + rb_node = rb_next(rb_node); + rb_erase(&frag->node, &ci->i_fragtree); + kfree(frag); + frag = NULL; + } + if (!frag) { + frag = __get_or_create_frag(ci, id); + if (IS_ERR(frag)) + continue; + } frag->split_by = le32_to_cpu(info->fragtree.splits[i].by); dout(" frag %x split by %d\n", frag->frag, frag->split_by); } + while (rb_node) { + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + rb_node = rb_next(rb_node); + rb_erase(&frag->node, &ci->i_fragtree); + kfree(frag); + } mutex_unlock(&ci->i_fragtree_mutex); /* were we issued a capability? */ @@ -953,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; struct ceph_fs_client *fsc = ceph_sb_to_client(sb); - int i = 0; int err = 0; dout("fill_trace %p is_dentry %d is_target %d\n", req, @@ -1014,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, } } + if (rinfo->head->is_target) { + vino.ino = le64_to_cpu(rinfo->targeti.in->ino); + vino.snap = le64_to_cpu(rinfo->targeti.in->snapid); + + in = ceph_get_inode(sb, vino); + if (IS_ERR(in)) { + err = PTR_ERR(in); + goto done; + } + req->r_target_inode = in; + + err = fill_inode(in, &rinfo->targeti, NULL, + session, req->r_request_started, + (le32_to_cpu(rinfo->head->result) == 0) ? + req->r_fmode : -1, + &req->r_caps_reservation); + if (err < 0) { + pr_err("fill_inode badness %p %llx.%llx\n", + in, ceph_vinop(in)); + goto done; + } + } + /* * ignore null lease/binding on snapdir ENOENT, or else we * will have trouble splicing in the virtual snapdir later @@ -1083,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, ceph_dentry(req->r_old_dentry)->offset); dn = req->r_old_dentry; /* use old_dentry */ - in = dn->d_inode; } /* null dentry? */ @@ -1105,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, } /* attach proper inode */ - ininfo = rinfo->targeti.in; - vino.ino = le64_to_cpu(ininfo->ino); - vino.snap = le64_to_cpu(ininfo->snapid); - in = dn->d_inode; - if (!in) { - in = ceph_get_inode(sb, vino); - if (IS_ERR(in)) { - pr_err("fill_trace bad get_inode " - "%llx.%llx\n", vino.ino, vino.snap); - err = PTR_ERR(in); - d_drop(dn); - goto done; - } + if (!dn->d_inode) { + ihold(in); dn = splice_dentry(dn, in, &have_lease, true); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; } req->r_dentry = dn; /* may have spliced */ - ihold(in); - } else if (ceph_ino(in) == vino.ino && - ceph_snap(in) == vino.snap) { - ihold(in); - } else { + } else if (dn->d_inode && dn->d_inode != in) { dout(" %p links to %p %llx.%llx, not %llx.%llx\n", - dn, in, ceph_ino(in), ceph_snap(in), - vino.ino, vino.snap); + dn, dn->d_inode, ceph_vinop(dn->d_inode), + ceph_vinop(in)); have_lease = false; - in = NULL; } if (have_lease) update_dentry_lease(dn, rinfo->dlease, session, req->r_request_started); dout(" final dn %p\n", dn); - i++; - } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP || - req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) { + } else if (!req->r_aborted && + (req->r_op == CEPH_MDS_OP_LOOKUPSNAP || + req->r_op == CEPH_MDS_OP_MKSNAP)) { struct dentry *dn = req->r_dentry; /* fill out a snapdir LOOKUPSNAP dentry */ @@ -1152,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, ininfo = rinfo->targeti.in; vino.ino = le64_to_cpu(ininfo->ino); vino.snap = le64_to_cpu(ininfo->snapid); - in = ceph_get_inode(sb, vino); - if (IS_ERR(in)) { - pr_err("fill_inode get_inode badness %llx.%llx\n", - vino.ino, vino.snap); - err = PTR_ERR(in); - d_delete(dn); - goto done; - } dout(" linking snapped dir %p to dn %p\n", in, dn); + ihold(in); dn = splice_dentry(dn, in, NULL, true); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; } req->r_dentry = dn; /* may have spliced */ - ihold(in); - rinfo->head->is_dentry = 1; /* fool notrace handlers */ - } - - if (rinfo->head->is_target) { - vino.ino = le64_to_cpu(rinfo->targeti.in->ino); - vino.snap = le64_to_cpu(rinfo->targeti.in->snapid); - - if (in == NULL || ceph_ino(in) != vino.ino || - ceph_snap(in) != vino.snap) { - in = ceph_get_inode(sb, vino); - if (IS_ERR(in)) { - err = PTR_ERR(in); - goto done; - } - } - req->r_target_inode = in; - - err = fill_inode(in, - &rinfo->targeti, NULL, - session, req->r_request_started, - (le32_to_cpu(rinfo->head->result) == 0) ? - req->r_fmode : -1, - &req->r_caps_reservation); - if (err < 0) { - pr_err("fill_inode badness %p %llx.%llx\n", - in, ceph_vinop(in)); - goto done; - } } - done: dout("fill_trace done err=%d\n", err); return err; @@ -1247,11 +1240,23 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct qstr dname; struct dentry *dn; struct inode *in; - int err = 0, i; + int err = 0, ret, i; struct inode *snapdir = NULL; struct ceph_mds_request_head *rhead = req->r_request->front.iov_base; - u64 frag = le32_to_cpu(rhead->args.readdir.frag); struct ceph_dentry_info *di; + u64 r_readdir_offset = req->r_readdir_offset; + u32 frag = le32_to_cpu(rhead->args.readdir.frag); + + if (rinfo->dir_dir && + le32_to_cpu(rinfo->dir_dir->frag) != frag) { + dout("readdir_prepopulate got new frag %x -> %x\n", + frag, le32_to_cpu(rinfo->dir_dir->frag)); + frag = le32_to_cpu(rinfo->dir_dir->frag); + if (ceph_frag_is_leftmost(frag)) + r_readdir_offset = 2; + else + r_readdir_offset = 0; + } if (req->r_aborted) return readdir_prepopulate_inodes_only(req, session); @@ -1268,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir); } + /* FIXME: release caps/leases if error occurs */ for (i = 0; i < rinfo->dir_nr; i++) { struct ceph_vino vino; @@ -1292,9 +1298,10 @@ retry_lookup: err = -ENOMEM; goto out; } - err = ceph_init_dentry(dn); - if (err < 0) { + ret = ceph_init_dentry(dn); + if (ret < 0) { dput(dn); + err = ret; goto out; } } else if (dn->d_inode && @@ -1314,9 +1321,6 @@ retry_lookup: spin_unlock(&parent->d_lock); } - di = dn->d_fsdata; - di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset); - /* inode */ if (dn->d_inode) { in = dn->d_inode; @@ -1329,26 +1333,39 @@ retry_lookup: err = PTR_ERR(in); goto out; } - dn = splice_dentry(dn, in, NULL, false); - if (IS_ERR(dn)) - dn = NULL; } if (fill_inode(in, &rinfo->dir_in[i], NULL, session, req->r_request_started, -1, &req->r_caps_reservation) < 0) { pr_err("fill_inode badness on %p\n", in); + if (!dn->d_inode) + iput(in); + d_drop(dn); goto next_item; } - if (dn) - update_dentry_lease(dn, rinfo->dir_dlease[i], - req->r_session, - req->r_request_started); + + if (!dn->d_inode) { + dn = splice_dentry(dn, in, NULL, false); + if (IS_ERR(dn)) { + err = PTR_ERR(dn); + dn = NULL; + goto next_item; + } + } + + di = dn->d_fsdata; + di->offset = ceph_make_fpos(frag, i + r_readdir_offset); + + update_dentry_lease(dn, rinfo->dir_dlease[i], + req->r_session, + req->r_request_started); next_item: if (dn) dput(dn); } - req->r_did_prepopulate = true; + if (err == 0) + req->r_did_prepopulate = true; out: if (snapdir) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index b7bda5d9611d..d90861f45210 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -43,6 +43,7 @@ */ struct ceph_reconnect_state { + int nr_caps; struct ceph_pagelist *pagelist; bool flock; }; @@ -443,6 +444,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, INIT_LIST_HEAD(&s->s_waiting); INIT_LIST_HEAD(&s->s_unsafe); s->s_num_cap_releases = 0; + s->s_cap_reconnect = 0; s->s_cap_iterator = NULL; INIT_LIST_HEAD(&s->s_cap_releases); INIT_LIST_HEAD(&s->s_cap_releases_done); @@ -642,6 +644,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc, req->r_unsafe_dir = NULL; } + complete_all(&req->r_safe_completion); + ceph_mdsc_put_request(req); } @@ -986,7 +990,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, dout("removing cap %p, ci is %p, inode is %p\n", cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, false); if (!__ceph_is_any_real_caps(ci)) { struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; @@ -1231,9 +1235,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) session->s_trim_caps--; if (oissued) { /* we aren't the only cap.. just remove us */ - __queue_cap_release(session, ceph_ino(inode), cap->cap_id, - cap->mseq, cap->issue_seq); - __ceph_remove_cap(cap); + __ceph_remove_cap(cap, true); } else { /* try to drop referring dentries */ spin_unlock(&ci->i_ceph_lock); @@ -1416,7 +1418,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, unsigned num; dout("discard_cap_releases mds%d\n", session->s_mds); - spin_lock(&session->s_cap_lock); /* zero out the in-progress message */ msg = list_first_entry(&session->s_cap_releases, @@ -1443,8 +1444,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, msg->front.iov_len = sizeof(*head); list_add(&msg->list_head, &session->s_cap_releases); } - - spin_unlock(&session->s_cap_lock); } /* @@ -1875,8 +1874,11 @@ static int __do_request(struct ceph_mds_client *mdsc, int mds = -1; int err = -EAGAIN; - if (req->r_err || req->r_got_result) + if (req->r_err || req->r_got_result) { + if (req->r_aborted) + __unregister_request(mdsc, req); goto out; + } if (req->r_timeout && time_after_eq(jiffies, req->r_started + req->r_timeout)) { @@ -2186,7 +2188,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) if (head->safe) { req->r_got_safe = true; __unregister_request(mdsc, req); - complete_all(&req->r_safe_completion); if (req->r_got_unsafe) { /* @@ -2238,8 +2239,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session); if (err == 0) { if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR || - req->r_op == CEPH_MDS_OP_LSSNAP) && - rinfo->dir_nr) + req->r_op == CEPH_MDS_OP_LSSNAP)) ceph_readdir_prepopulate(req, req->r_session); ceph_unreserve_caps(mdsc, &req->r_caps_reservation); } @@ -2490,6 +2490,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, cap->seq = 0; /* reset cap seq */ cap->issue_seq = 0; /* and issue_seq */ cap->mseq = 0; /* and migrate_seq */ + cap->cap_gen = cap->session->s_cap_gen; if (recon_state->flock) { rec.v2.cap_id = cpu_to_le64(cap->cap_id); @@ -2552,6 +2553,8 @@ encode_again: } else { err = ceph_pagelist_append(pagelist, &rec, reclen); } + + recon_state->nr_caps++; out_free: kfree(path); out_dput: @@ -2579,6 +2582,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, struct rb_node *p; int mds = session->s_mds; int err = -ENOMEM; + int s_nr_caps; struct ceph_pagelist *pagelist; struct ceph_reconnect_state recon_state; @@ -2610,20 +2614,38 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, dout("session %p state %s\n", session, session_state_name(session->s_state)); + spin_lock(&session->s_gen_ttl_lock); + session->s_cap_gen++; + spin_unlock(&session->s_gen_ttl_lock); + + spin_lock(&session->s_cap_lock); + /* + * notify __ceph_remove_cap() that we are composing cap reconnect. + * If a cap get released before being added to the cap reconnect, + * __ceph_remove_cap() should skip queuing cap release. + */ + session->s_cap_reconnect = 1; /* drop old cap expires; we're about to reestablish that state */ discard_cap_releases(mdsc, session); + spin_unlock(&session->s_cap_lock); /* traverse this session's caps */ - err = ceph_pagelist_encode_32(pagelist, session->s_nr_caps); + s_nr_caps = session->s_nr_caps; + err = ceph_pagelist_encode_32(pagelist, s_nr_caps); if (err) goto fail; + recon_state.nr_caps = 0; recon_state.pagelist = pagelist; recon_state.flock = session->s_con.peer_features & CEPH_FEATURE_FLOCK; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; + spin_lock(&session->s_cap_lock); + session->s_cap_reconnect = 0; + spin_unlock(&session->s_cap_lock); + /* * snaprealms. we provide mds with the ino, seq (version), and * parent for all of our realms. If the mds has any newer info, @@ -2646,11 +2668,18 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, if (recon_state.flock) reply->hdr.version = cpu_to_le16(2); - if (pagelist->length) { - /* set up outbound data if we have any */ - reply->hdr.data_len = cpu_to_le32(pagelist->length); - ceph_msg_data_add_pagelist(reply, pagelist); + + /* raced with cap release? */ + if (s_nr_caps != recon_state.nr_caps) { + struct page *page = list_first_entry(&pagelist->head, + struct page, lru); + __le32 *addr = kmap_atomic(page); + *addr = cpu_to_le32(recon_state.nr_caps); + kunmap_atomic(addr); } + + reply->hdr.data_len = cpu_to_le32(pagelist->length); + ceph_msg_data_add_pagelist(reply, pagelist); ceph_con_send(&session->s_con, reply); mutex_unlock(&session->s_mutex); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index c2a19fbbe517..4c053d099ae4 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -132,6 +132,7 @@ struct ceph_mds_session { struct list_head s_caps; /* all caps issued by this session */ int s_nr_caps, s_trim_caps; int s_num_cap_releases; + int s_cap_reconnect; struct list_head s_cap_releases; /* waiting cap_release messages */ struct list_head s_cap_releases_done; /* ready to send */ struct ceph_cap *s_cap_iterator; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6014b0a3c405..ef4ac38bb614 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -741,13 +741,7 @@ extern int ceph_add_cap(struct inode *inode, int fmode, unsigned issued, unsigned wanted, unsigned cap, unsigned seq, u64 realmino, int flags, struct ceph_cap_reservation *caps_reservation); -extern void __ceph_remove_cap(struct ceph_cap *cap); -static inline void ceph_remove_cap(struct ceph_cap *cap) -{ - spin_lock(&cap->ci->i_ceph_lock); - __ceph_remove_cap(cap); - spin_unlock(&cap->ci->i_ceph_lock); -} +extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); extern void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index d9ea7ada1378..f918a998a087 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -384,6 +384,7 @@ struct smb_version_operations { int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file, struct cifsFileInfo *target_file, u64 src_off, u64 len, u64 dest_off); + int (*validate_negotiate)(const unsigned int, struct cifs_tcon *); }; struct smb_version_values { diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index aa3397620342..2c29db6a247e 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -477,9 +477,10 @@ extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon, const int netfid, __u64 *pExtAttrBits, __u64 *pMask); extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb); extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr); -extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr, - const unsigned char *path, - struct cifs_sb_info *cifs_sb, unsigned int xid); +extern int CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, + struct cifs_fattr *fattr, + const unsigned char *path); extern int mdfour(unsigned char *, unsigned char *, int); extern int E_md4hash(const unsigned char *passwd, unsigned char *p16, const struct nls_table *codepage); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 124aa0230c1b..d707edb6b852 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4010,7 +4010,7 @@ QFileInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc); + cifs_dbg(FYI, "Send error in QFileInfo = %d", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4179,7 +4179,7 @@ UnixQFileInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc); + cifs_dbg(FYI, "Send error in UnixQFileInfo = %d", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); @@ -4263,7 +4263,7 @@ UnixQPathInfoRetry: rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); if (rc) { - cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc); + cifs_dbg(FYI, "Send error in UnixQPathInfo = %d", rc); } else { /* decode response */ rc = validate_t2((struct smb_t2_rsp *)pSMBr); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 11ff5f116b20..a514e0a65f69 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -193,7 +193,7 @@ check_name(struct dentry *direntry) static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, struct tcon_link *tlink, unsigned oflags, umode_t mode, - __u32 *oplock, struct cifs_fid *fid, int *created) + __u32 *oplock, struct cifs_fid *fid) { int rc = -ENOENT; int create_options = CREATE_NOT_DIR; @@ -349,7 +349,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, .device = 0, }; - *created |= FILE_CREATED; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { args.uid = current_fsuid(); if (inode->i_mode & S_ISGID) @@ -480,13 +479,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, cifs_add_pending_open(&fid, tlink, &open); rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid, opened); + &oplock, &fid); if (rc) { cifs_del_pending_open(&open); goto out; } + if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + *opened |= FILE_CREATED; + rc = finish_open(file, direntry, generic_file_open, opened); if (rc) { if (server->ops->close) @@ -529,7 +531,6 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, struct TCP_Server_Info *server; struct cifs_fid fid; __u32 oplock; - int created = FILE_CREATED; cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n", inode, direntry->d_name.name, direntry); @@ -546,7 +547,7 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, server->ops->new_lease_key(&fid); rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid, &created); + &oplock, &fid); if (!rc && server->ops->close) server->ops->close(xid, tcon, &fid); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 36f9ebb93ceb..49719b8228e5 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -383,7 +383,8 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* check for Minshall+French symlinks */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { - int tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid); + int tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr, + full_path); if (tmprc) cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc); } @@ -799,7 +800,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, /* check for Minshall+French symlinks */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { - tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid); + tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr, + full_path); if (tmprc) cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc); } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 409b45eefe70..77492301cc2b 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -26,13 +26,15 @@ #include <linux/mount.h> #include <linux/mm.h> #include <linux/pagemap.h> -#include <linux/btrfs.h> #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" #include "cifsfs.h" +#define CIFS_IOCTL_MAGIC 0xCF +#define CIFS_IOC_COPYCHUNK_FILE _IOW(CIFS_IOCTL_MAGIC, 3, int) + static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, unsigned long srcfd, u64 off, u64 len, u64 destoff) { @@ -213,7 +215,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) cifs_dbg(FYI, "set compress flag rc %d\n", rc); } break; - case BTRFS_IOC_CLONE: + case CIFS_IOC_COPYCHUNK_FILE: rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0); break; default: diff --git a/fs/cifs/link.c b/fs/cifs/link.c index cc0234710ddb..92aee08483a5 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -354,34 +354,30 @@ open_query_close_cifs_symlink(const unsigned char *path, char *pbuf, int -CIFSCheckMFSymlink(struct cifs_fattr *fattr, - const unsigned char *path, - struct cifs_sb_info *cifs_sb, unsigned int xid) +CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, + const unsigned char *path) { - int rc = 0; + int rc; u8 *buf = NULL; unsigned int link_len = 0; unsigned int bytes_read = 0; - struct cifs_tcon *ptcon; if (!CIFSCouldBeMFSymlink(fattr)) /* it's not a symlink */ return 0; buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - goto out; - } + if (!buf) + return -ENOMEM; - ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb)); - if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink)) - rc = ptcon->ses->server->ops->query_mf_symlink(path, buf, - &bytes_read, cifs_sb, xid); + if (tcon->ses->server->ops->query_mf_symlink) + rc = tcon->ses->server->ops->query_mf_symlink(path, buf, + &bytes_read, cifs_sb, xid); else - goto out; + rc = -ENOSYS; - if (rc != 0) + if (rc) goto out; if (bytes_read == 0) /* not a symlink */ diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 11dde4b24f8a..757da3e54d3d 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -532,7 +532,10 @@ smb2_clone_range(const unsigned int xid, int rc; unsigned int ret_data_len; struct copychunk_ioctl *pcchunk; - char *retbuf = NULL; + struct copychunk_ioctl_rsp *retbuf = NULL; + struct cifs_tcon *tcon; + int chunks_copied = 0; + bool chunk_sizes_updated = false; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); @@ -547,27 +550,96 @@ smb2_clone_range(const unsigned int xid, /* Note: request_res_key sets res_key null only if rc !=0 */ if (rc) - return rc; + goto cchunk_out; /* For now array only one chunk long, will make more flexible later */ pcchunk->ChunkCount = __constant_cpu_to_le32(1); pcchunk->Reserved = 0; - pcchunk->SourceOffset = cpu_to_le64(src_off); - pcchunk->TargetOffset = cpu_to_le64(dest_off); - pcchunk->Length = cpu_to_le32(len); pcchunk->Reserved2 = 0; - /* Request that server copy to target from src file identified by key */ - rc = SMB2_ioctl(xid, tlink_tcon(trgtfile->tlink), - trgtfile->fid.persistent_fid, - trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, - true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), &retbuf, &ret_data_len); + tcon = tlink_tcon(trgtfile->tlink); - /* BB need to special case rc = EINVAL to alter chunk size */ + while (len > 0) { + pcchunk->SourceOffset = cpu_to_le64(src_off); + pcchunk->TargetOffset = cpu_to_le64(dest_off); + pcchunk->Length = + cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); - cifs_dbg(FYI, "rc %d data length out %d\n", rc, ret_data_len); + /* Request server copy to target from src identified by key */ + rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, + trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, + true /* is_fsctl */, (char *)pcchunk, + sizeof(struct copychunk_ioctl), (char **)&retbuf, + &ret_data_len); + if (rc == 0) { + if (ret_data_len != + sizeof(struct copychunk_ioctl_rsp)) { + cifs_dbg(VFS, "invalid cchunk response size\n"); + rc = -EIO; + goto cchunk_out; + } + if (retbuf->TotalBytesWritten == 0) { + cifs_dbg(FYI, "no bytes copied\n"); + rc = -EIO; + goto cchunk_out; + } + /* + * Check if server claimed to write more than we asked + */ + if (le32_to_cpu(retbuf->TotalBytesWritten) > + le32_to_cpu(pcchunk->Length)) { + cifs_dbg(VFS, "invalid copy chunk response\n"); + rc = -EIO; + goto cchunk_out; + } + if (le32_to_cpu(retbuf->ChunksWritten) != 1) { + cifs_dbg(VFS, "invalid num chunks written\n"); + rc = -EIO; + goto cchunk_out; + } + chunks_copied++; + + src_off += le32_to_cpu(retbuf->TotalBytesWritten); + dest_off += le32_to_cpu(retbuf->TotalBytesWritten); + len -= le32_to_cpu(retbuf->TotalBytesWritten); + + cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n", + le32_to_cpu(retbuf->ChunksWritten), + le32_to_cpu(retbuf->ChunkBytesWritten), + le32_to_cpu(retbuf->TotalBytesWritten)); + } else if (rc == -EINVAL) { + if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) + goto cchunk_out; + + cifs_dbg(FYI, "MaxChunks %d BytesChunk %d MaxCopy %d\n", + le32_to_cpu(retbuf->ChunksWritten), + le32_to_cpu(retbuf->ChunkBytesWritten), + le32_to_cpu(retbuf->TotalBytesWritten)); + + /* + * Check if this is the first request using these sizes, + * (ie check if copy succeed once with original sizes + * and check if the server gave us different sizes after + * we already updated max sizes on previous request). + * if not then why is the server returning an error now + */ + if ((chunks_copied != 0) || chunk_sizes_updated) + goto cchunk_out; + + /* Check that server is not asking us to grow size */ + if (le32_to_cpu(retbuf->ChunkBytesWritten) < + tcon->max_bytes_chunk) + tcon->max_bytes_chunk = + le32_to_cpu(retbuf->ChunkBytesWritten); + else + goto cchunk_out; /* server gave us bogus size */ + + /* No need to change MaxChunks since already set to 1 */ + chunk_sizes_updated = true; + } + } +cchunk_out: kfree(pcchunk); return rc; } @@ -1247,6 +1319,7 @@ struct smb_version_operations smb30_operations = { .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, + .validate_negotiate = smb3_validate_negotiate, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index d65270c290a1..2013234b73ad 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -454,6 +454,81 @@ neg_exit: return rc; } +int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) +{ + int rc = 0; + struct validate_negotiate_info_req vneg_inbuf; + struct validate_negotiate_info_rsp *pneg_rsp; + u32 rsplen; + + cifs_dbg(FYI, "validate negotiate\n"); + + /* + * validation ioctl must be signed, so no point sending this if we + * can not sign it. We could eventually change this to selectively + * sign just this, the first and only signed request on a connection. + * This is good enough for now since a user who wants better security + * would also enable signing on the mount. Having validation of + * negotiate info for signed connections helps reduce attack vectors + */ + if (tcon->ses->server->sign == false) + return 0; /* validation requires signing */ + + vneg_inbuf.Capabilities = + cpu_to_le32(tcon->ses->server->vals->req_capabilities); + memcpy(vneg_inbuf.Guid, cifs_client_guid, SMB2_CLIENT_GUID_SIZE); + + if (tcon->ses->sign) + vneg_inbuf.SecurityMode = + cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED); + else if (global_secflags & CIFSSEC_MAY_SIGN) + vneg_inbuf.SecurityMode = + cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED); + else + vneg_inbuf.SecurityMode = 0; + + vneg_inbuf.DialectCount = cpu_to_le16(1); + vneg_inbuf.Dialects[0] = + cpu_to_le16(tcon->ses->server->vals->protocol_id); + + rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, + FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, + (char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req), + (char **)&pneg_rsp, &rsplen); + + if (rc != 0) { + cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc); + return -EIO; + } + + if (rsplen != sizeof(struct validate_negotiate_info_rsp)) { + cifs_dbg(VFS, "invalid size of protocol negotiate response\n"); + return -EIO; + } + + /* check validate negotiate info response matches what we got earlier */ + if (pneg_rsp->Dialect != + cpu_to_le16(tcon->ses->server->vals->protocol_id)) + goto vneg_out; + + if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode)) + goto vneg_out; + + /* do not validate server guid because not saved at negprot time yet */ + + if ((le32_to_cpu(pneg_rsp->Capabilities) | SMB2_NT_FIND | + SMB2_LARGE_FILES) != tcon->ses->server->capabilities) + goto vneg_out; + + /* validate negotiate successful */ + cifs_dbg(FYI, "validate negotiate info successful\n"); + return 0; + +vneg_out: + cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n"); + return -EIO; +} + int SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, const struct nls_table *nls_cp) @@ -829,6 +904,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0)) cifs_dbg(VFS, "DFS capability contradicts DFS flag\n"); init_copy_chunk_defaults(tcon); + if (tcon->ses->server->ops->validate_negotiate) + rc = tcon->ses->server->ops->validate_negotiate(xid, tcon); tcon_exit: free_rsp_buf(resp_buftype, rsp); kfree(unc_path); @@ -1214,10 +1291,17 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0); rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base; - if (rc != 0) { + if ((rc != 0) && (rc != -EINVAL)) { if (tcon) cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); goto ioctl_exit; + } else if (rc == -EINVAL) { + if ((opcode != FSCTL_SRV_COPYCHUNK_WRITE) && + (opcode != FSCTL_SRV_COPYCHUNK)) { + if (tcon) + cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE); + goto ioctl_exit; + } } /* check if caller wants to look at return data or just return rc */ @@ -2154,11 +2238,9 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, rc = SendReceive2(xid, ses, iov, num, &resp_buftype, 0); rsp = (struct smb2_set_info_rsp *)iov[0].iov_base; - if (rc != 0) { + if (rc != 0) cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE); - goto out; - } -out: + free_rsp_buf(resp_buftype, rsp); kfree(iov); return rc; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f88320bbb477..2022c542ea3a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -577,13 +577,19 @@ struct copychunk_ioctl_rsp { __le32 TotalBytesWritten; } __packed; -/* Response and Request are the same format */ -struct validate_negotiate_info { +struct validate_negotiate_info_req { __le32 Capabilities; __u8 Guid[SMB2_CLIENT_GUID_SIZE]; __le16 SecurityMode; __le16 DialectCount; - __le16 Dialect[1]; + __le16 Dialects[1]; /* dialect (someday maybe list) client asked for */ +} __packed; + +struct validate_negotiate_info_rsp { + __le32 Capabilities; + __u8 Guid[SMB2_CLIENT_GUID_SIZE]; + __le16 SecurityMode; + __le16 Dialect; /* Dialect in use for the connection */ } __packed; #define RSS_CAPABLE 0x00000001 diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index b4eea105b08c..93adc64666f3 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -162,5 +162,6 @@ extern int smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, struct smb2_lock_element *buf); extern int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, __u8 *lease_key, const __le32 lease_state); +extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); #endif /* _SMB2PROTO_H */ diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index a4b2391fe66e..0e538b5c9622 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -90,7 +90,7 @@ #define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */ #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */ #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */ -#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 /* BB add struct */ +#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 /* Perform server-side data movement */ #define FSCTL_SRV_COPYCHUNK 0x001440F2 #define FSCTL_SRV_COPYCHUNK_WRITE 0x001480F2 diff --git a/fs/dcache.c b/fs/dcache.c index 4bdb300b16e2..cb4a10690868 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -192,7 +192,7 @@ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char if (!tcount) return 0; } - mask = ~(~0ul << tcount*8); + mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } @@ -3061,8 +3061,13 @@ char *d_path(const struct path *path, char *buf, int buflen) * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: + * + * Some pseudo inodes are mountable. When they are mounted + * path->dentry == path->mnt->mnt_root. In that case don't call d_dname + * and instead have d_path return the mounted path. */ - if (path->dentry->d_op && path->dentry->d_op->d_dname) + if (path->dentry->d_op && path->dentry->d_op->d_dname && + (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index d90909ec6aa6..a5e34dd6a32c 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -649,6 +649,7 @@ static void process_sctp_notification(struct connection *con, struct msghdr *msg, char *buf) { union sctp_notification *sn = (union sctp_notification *)buf; + struct linger linger; switch (sn->sn_header.sn_type) { case SCTP_SEND_FAILED: @@ -727,6 +728,13 @@ static void process_sctp_notification(struct connection *con, } add_sock(new_con->sock, new_con); + linger.l_onoff = 1; + linger.l_linger = 0; + ret = kernel_setsockopt(new_con->sock, SOL_SOCKET, SO_LINGER, + (char *)&linger, sizeof(linger)); + if (ret < 0) + log_print("set socket option SO_LINGER failed"); + log_print("connecting to %d sctp association %d", nodeid, (int)sn->sn_assoc_change.sac_assoc_id); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 79b65c3b9e87..af903128891c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1852,8 +1852,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) - epds.events &= ~EPOLLWAKEUP; + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor @@ -1908,10 +1907,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } } } - if (op == EPOLL_CTL_DEL && is_file_epoll(tf.file)) { - tep = tf.file->private_data; - mutex_lock_nested(&tep->mtx, 1); - } /* * Try to lookup the file inside our RB tree, Since we grabbed "mtx" diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 288534920fe5..20d6697bd638 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1493,6 +1493,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type, sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; + tmp_bh.b_size = sb->s_blocksize; err = ext2_get_block(inode, blk, &tmp_bh, 1); if (err < 0) goto out; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e6185031c1cc..ece55565b9cd 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -268,6 +268,16 @@ struct ext4_io_submit { /* Translate # of blks to # of clusters */ #define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \ (sbi)->s_cluster_bits) +/* Mask out the low bits to get the starting block of the cluster */ +#define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \ + ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) +#define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \ + ~((ext4_lblk_t) (s)->s_cluster_ratio - 1)) +/* Get the cluster offset */ +#define EXT4_PBLK_COFF(s, pblk) ((pblk) & \ + ((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) +#define EXT4_LBLK_COFF(s, lblk) ((lblk) & \ + ((ext4_lblk_t) (s)->s_cluster_ratio - 1)) /* * Structure of a blocks group descriptor diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 17ac112ab101..3fe29de832c8 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -259,6 +259,15 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, if (WARN_ON_ONCE(err)) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); + ext4_error_inode(inode, where, line, + bh->b_blocknr, + "journal_dirty_metadata failed: " + "handle type %u started at line %u, " + "credits %u/%u, errcode %d", + handle->h_type, + handle->h_line_no, + handle->h_requested_credits, + handle->h_buffer_credits, err); } } else { if (inode) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 35f65cf4f318..3384dc4bed40 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -360,8 +360,10 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); + ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); + ext4_lblk_t last = lblock + len - 1; - if (len == 0) + if (lblock > last) return 0; return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } @@ -387,11 +389,26 @@ static int ext4_valid_extent_entries(struct inode *inode, if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); + struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + ext4_fsblk_t pblock = 0; + ext4_lblk_t lblock = 0; + ext4_lblk_t prev = 0; + int len = 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; + + /* Check for overlapping extents */ + lblock = le32_to_cpu(ext->ee_block); + len = ext4_ext_get_actual_len(ext); + if ((lblock <= prev) && prev) { + pblock = ext4_ext_pblock(ext); + es->s_last_error_block = cpu_to_le64(pblock); + return 0; + } ext++; entries--; + prev = lblock + len - 1; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); @@ -1834,8 +1851,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, depth = ext_depth(inode); if (!path[depth].p_ext) goto out; - b2 = le32_to_cpu(path[depth].p_ext->ee_block); - b2 &= ~(sbi->s_cluster_ratio - 1); + b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block)); /* * get the next allocated block if the extent in the path @@ -1845,7 +1861,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, b2 = ext4_ext_next_allocated_block(path); if (b2 == EXT_MAX_BLOCKS) goto out; - b2 &= ~(sbi->s_cluster_ratio - 1); + b2 = EXT4_LBLK_CMASK(sbi, b2); } /* check for wrap through zero on extent logical start block*/ @@ -2504,7 +2520,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, * extent, we have to mark the cluster as used (store negative * cluster number in partial_cluster). */ - unaligned = pblk & (sbi->s_cluster_ratio - 1); + unaligned = EXT4_PBLK_COFF(sbi, pblk); if (unaligned && (ee_len == num) && (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk)))) *partial_cluster = EXT4_B2C(sbi, pblk); @@ -2598,7 +2614,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * accidentally freeing it later on */ pblk = ext4_ext_pblock(ex); - if (pblk & (sbi->s_cluster_ratio - 1)) + if (EXT4_PBLK_COFF(sbi, pblk)) *partial_cluster = -((long long)EXT4_B2C(sbi, pblk)); ex--; @@ -3753,7 +3769,7 @@ int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; - lblk_start = lblk & (~(sbi->s_cluster_ratio - 1)); + lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return ext4_find_delalloc_range(inode, lblk_start, lblk_end); @@ -3812,9 +3828,9 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks); /* Check towards left side */ - c_offset = lblk_start & (sbi->s_cluster_ratio - 1); + c_offset = EXT4_LBLK_COFF(sbi, lblk_start); if (c_offset) { - lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1)); + lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start); lblk_to = lblk_from + c_offset - 1; if (ext4_find_delalloc_range(inode, lblk_from, lblk_to)) @@ -3822,7 +3838,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, } /* Now check towards right. */ - c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1); + c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks); if (allocated_clusters && c_offset) { lblk_from = lblk_start + num_blks; lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1; @@ -4030,7 +4046,7 @@ static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_ext_path *path) { struct ext4_sb_info *sbi = EXT4_SB(sb); - ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1); + ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start; ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); @@ -4048,8 +4064,7 @@ static int get_implied_cluster_alloc(struct super_block *sb, (rr_cluster_start == ex_cluster_start)) { if (rr_cluster_start == ex_cluster_end) ee_start += ee_len - 1; - map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) + - c_offset; + map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset; map->m_len = min(map->m_len, (unsigned) sbi->s_cluster_ratio - c_offset); /* @@ -4203,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, */ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; newex.ee_block = cpu_to_le32(map->m_lblk); - cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1); + cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned @@ -4271,7 +4286,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * needed so that future calls to get_implied_cluster_alloc() * work correctly. */ - offset = map->m_lblk & (sbi->s_cluster_ratio - 1); + offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ar.len = EXT4_NUM_B2C(sbi, offset+allocated); ar.goal -= offset; ar.logical -= offset; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 075763474118..61d49ff22c81 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1206,7 +1206,6 @@ static int ext4_journalled_write_end(struct file *file, */ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock) { - int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; @@ -1218,7 +1217,6 @@ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock) * in order to allocate nrblocks * worse case is one extent per block */ -repeat: spin_lock(&ei->i_block_reservation_lock); /* * ext4_calc_metadata_amount() has side effects, which we have @@ -1238,10 +1236,6 @@ repeat: ei->i_da_metadata_calc_len = save_len; ei->i_da_metadata_calc_last_lblock = save_last_lblock; spin_unlock(&ei->i_block_reservation_lock); - if (ext4_should_retry_alloc(inode->i_sb, &retries)) { - cond_resched(); - goto repeat; - } return -ENOSPC; } ei->i_reserved_meta_blocks += md_needed; @@ -1255,7 +1249,6 @@ repeat: */ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { - int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; @@ -1277,7 +1270,6 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) * in order to allocate nrblocks * worse case is one extent per block */ -repeat: spin_lock(&ei->i_block_reservation_lock); /* * ext4_calc_metadata_amount() has side effects, which we have @@ -1297,10 +1289,6 @@ repeat: ei->i_da_metadata_calc_len = save_len; ei->i_da_metadata_calc_last_lblock = save_last_lblock; spin_unlock(&ei->i_block_reservation_lock); - if (ext4_should_retry_alloc(inode->i_sb, &retries)) { - cond_resched(); - goto repeat; - } dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4d113efa024c..04a5c7504be9 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3442,6 +3442,9 @@ static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); + + BUG_ON(atomic_read(&pa->pa_count)); + BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } @@ -3455,11 +3458,13 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, ext4_group_t grp; ext4_fsblk_t grp_blk; - if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) - return; - /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); + if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { + spin_unlock(&pa->pa_lock); + return; + } + if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; @@ -4121,7 +4126,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ - ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1); + ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; @@ -4663,7 +4668,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ - overflow = block & (sbi->s_cluster_ratio - 1); + overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; @@ -4677,7 +4682,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, count += overflow; } } - overflow = count & (sbi->s_cluster_ratio - 1); + overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c977f4e4e63b..1f7784de05b6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -792,7 +792,7 @@ static void ext4_put_super(struct super_block *sb) } ext4_es_unregister_shrinker(sbi); - del_timer(&sbi->s_err_report); + del_timer_sync(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); @@ -3316,11 +3316,19 @@ int ext4_calculate_overhead(struct super_block *sb) } -static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi) +static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; /* + * There's no need to reserve anything when we aren't using extents. + * The space estimates are exact, there are no unwritten extents, + * hole punching doesn't need new metadata... This is needed especially + * to keep ext2/3 backward compatibility. + */ + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) + return 0; + /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run * out of space like for example punch hole, or converting @@ -3328,7 +3336,8 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi) * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ - resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits; + resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >> + EXT4_SB(sb)->s_cluster_bits; do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); @@ -4071,10 +4080,10 @@ no_journal: "available"); } - err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi)); + err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb)); if (err) { ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " - "reserved pool", ext4_calculate_resv_clusters(sbi)); + "reserved pool", ext4_calculate_resv_clusters(sb)); goto failed_mount4a; } @@ -4184,7 +4193,7 @@ failed_mount_wq: } failed_mount3: ext4_es_unregister_shrinker(sbi); - del_timer(&sbi->s_err_report); + del_timer_sync(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeclusters_counter); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1f4a10ece2f1..e0259a163f98 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -516,13 +516,16 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, } WARN_ON(inode->i_state & I_SYNC); /* - * Skip inode if it is clean. We don't want to mess with writeback - * lists in this function since flusher thread may be doing for example - * sync in parallel and if we move the inode, it could get skipped. So - * here we make sure inode is on some writeback list and leave it there - * unless we have completely cleaned the inode. + * Skip inode if it is clean and we have no outstanding writeback in + * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this + * function since flusher thread may be doing for example sync in + * parallel and if we move the inode, it could get skipped. So here we + * make sure inode is on some writeback list and leave it there unless + * we have completely cleaned the inode. */ - if (!(inode->i_state & I_DIRTY)) + if (!(inode->i_state & I_DIRTY) && + (wbc->sync_mode != WB_SYNC_ALL || + !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; spin_unlock(&inode->i_lock); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index b7fc035a6943..49436fa7cd4f 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -986,6 +986,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + struct address_space *mapping = inode->i_mapping; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; int rv; @@ -1006,6 +1007,36 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, if (rv != 1) goto out; /* dio not valid, fall back to buffered i/o */ + /* + * Now since we are holding a deferred (CW) lock at this point, you + * might be wondering why this is ever needed. There is a case however + * where we've granted a deferred local lock against a cached exclusive + * glock. That is ok provided all granted local locks are deferred, but + * it also means that it is possible to encounter pages which are + * cached and possibly also mapped. So here we check for that and sort + * them out ahead of the dio. The glock state machine will take care of + * everything else. + * + * If in fact the cached glock state (gl->gl_state) is deferred (CW) in + * the first place, mapping->nr_pages will always be zero. + */ + if (mapping->nrpages) { + loff_t lstart = offset & (PAGE_CACHE_SIZE - 1); + loff_t len = iov_length(iov, nr_segs); + loff_t end = PAGE_ALIGN(offset + len) - 1; + + rv = 0; + if (len == 0) + goto out; + if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) + unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len); + rv = filemap_write_and_wait_range(mapping, lstart, end); + if (rv) + goto out; + if (rw == WRITE) + truncate_inode_pages_range(mapping, lstart, end); + } + rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, gfs2_get_block_direct, NULL, NULL, 0); @@ -1050,30 +1081,22 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) bh = bh->b_this_page; } while(bh != head); spin_unlock(&sdp->sd_ail_lock); - gfs2_log_unlock(sdp); head = bh = page_buffers(page); do { - gfs2_log_lock(sdp); bd = bh->b_private; if (bd) { gfs2_assert_warn(sdp, bd->bd_bh == bh); - if (!list_empty(&bd->bd_list)) { - if (!buffer_pinned(bh)) - list_del_init(&bd->bd_list); - else - bd = NULL; - } - if (bd) - bd->bd_bh = NULL; + if (!list_empty(&bd->bd_list)) + list_del_init(&bd->bd_list); + bd->bd_bh = NULL; bh->b_private = NULL; - } - gfs2_log_unlock(sdp); - if (bd) kmem_cache_free(gfs2_bufdata_cachep, bd); + } bh = bh->b_this_page; } while (bh != head); + gfs2_log_unlock(sdp); return try_to_free_buffers(page); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 2e5fc268d324..fa32655449c8 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -834,6 +834,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct gfs2_leaf *leaf; struct gfs2_dirent *dent; struct qstr name = { .name = "" }; + struct timespec tv = CURRENT_TIME; error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); if (error) @@ -850,7 +851,11 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, leaf->lf_entries = 0; leaf->lf_dirent_format = cpu_to_be32(GFS2_FORMAT_DE); leaf->lf_next = 0; - memset(leaf->lf_reserved, 0, sizeof(leaf->lf_reserved)); + leaf->lf_inode = cpu_to_be64(ip->i_no_addr); + leaf->lf_dist = cpu_to_be32(1); + leaf->lf_nsec = cpu_to_be32(tv.tv_nsec); + leaf->lf_sec = cpu_to_be64(tv.tv_sec); + memset(leaf->lf_reserved2, 0, sizeof(leaf->lf_reserved2)); dent = (struct gfs2_dirent *)(leaf+1); gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent); *pbh = bh; @@ -1612,11 +1617,31 @@ out: return ret; } +/** + * dir_new_leaf - Add a new leaf onto hash chain + * @inode: The directory + * @name: The name we are adding + * + * This adds a new dir leaf onto an existing leaf when there is not + * enough space to add a new dir entry. This is a last resort after + * we've expanded the hash table to max size and also split existing + * leaf blocks, so it will only occur for very large directories. + * + * The dist parameter is set to 1 for leaf blocks directly attached + * to the hash table, 2 for one layer of indirection, 3 for two layers + * etc. We are thus able to tell the difference between an old leaf + * with dist set to zero (i.e. "don't know") and a new one where we + * set this information for debug/fsck purposes. + * + * Returns: 0 on success, or -ve on error + */ + static int dir_new_leaf(struct inode *inode, const struct qstr *name) { struct buffer_head *bh, *obh; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_leaf *leaf, *oleaf; + u32 dist = 1; int error; u32 index; u64 bn; @@ -1626,6 +1651,7 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name) if (error) return error; do { + dist++; oleaf = (struct gfs2_leaf *)obh->b_data; bn = be64_to_cpu(oleaf->lf_next); if (!bn) @@ -1643,6 +1669,7 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name) brelse(obh); return -ENOSPC; } + leaf->lf_dist = cpu_to_be32(dist); oleaf->lf_next = cpu_to_be64(bh->b_blocknr); brelse(bh); brelse(obh); @@ -1659,39 +1686,53 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name) /** * gfs2_dir_add - Add new filename into directory - * @dip: The GFS2 inode - * @filename: The new name - * @inode: The inode number of the entry - * @type: The type of the entry + * @inode: The directory inode + * @name: The new name + * @nip: The GFS2 inode to be linked in to the directory + * @da: The directory addition info + * + * If the call to gfs2_diradd_alloc_required resulted in there being + * no need to allocate any new directory blocks, then it will contain + * a pointer to the directory entry and the bh in which it resides. We + * can use that without having to repeat the search. If there was no + * free space, then we must now create more space. * * Returns: 0 on success, error code on failure */ int gfs2_dir_add(struct inode *inode, const struct qstr *name, - const struct gfs2_inode *nip) + const struct gfs2_inode *nip, struct gfs2_diradd *da) { struct gfs2_inode *ip = GFS2_I(inode); - struct buffer_head *bh; - struct gfs2_dirent *dent; + struct buffer_head *bh = da->bh; + struct gfs2_dirent *dent = da->dent; + struct timespec tv; struct gfs2_leaf *leaf; int error; while(1) { - dent = gfs2_dirent_search(inode, name, gfs2_dirent_find_space, - &bh); + if (da->bh == NULL) { + dent = gfs2_dirent_search(inode, name, + gfs2_dirent_find_space, &bh); + } if (dent) { if (IS_ERR(dent)) return PTR_ERR(dent); dent = gfs2_init_dirent(inode, dent, name, bh); gfs2_inum_out(nip, dent); dent->de_type = cpu_to_be16(IF2DT(nip->i_inode.i_mode)); + tv = CURRENT_TIME; if (ip->i_diskflags & GFS2_DIF_EXHASH) { leaf = (struct gfs2_leaf *)bh->b_data; be16_add_cpu(&leaf->lf_entries, 1); + leaf->lf_nsec = cpu_to_be32(tv.tv_nsec); + leaf->lf_sec = cpu_to_be64(tv.tv_sec); } + da->dent = NULL; + da->bh = NULL; brelse(bh); ip->i_entries++; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = tv; if (S_ISDIR(nip->i_inode.i_mode)) inc_nlink(&ip->i_inode); mark_inode_dirty(inode); @@ -1742,6 +1783,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry) const struct qstr *name = &dentry->d_name; struct gfs2_dirent *dent, *prev = NULL; struct buffer_head *bh; + struct timespec tv = CURRENT_TIME; /* Returns _either_ the entry (if its first in block) or the previous entry otherwise */ @@ -1767,13 +1809,15 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry) if (!entries) gfs2_consist_inode(dip); leaf->lf_entries = cpu_to_be16(--entries); + leaf->lf_nsec = cpu_to_be32(tv.tv_nsec); + leaf->lf_sec = cpu_to_be64(tv.tv_sec); } brelse(bh); if (!dip->i_entries) gfs2_consist_inode(dip); dip->i_entries--; - dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME; + dip->i_inode.i_mtime = dip->i_inode.i_ctime = tv; if (S_ISDIR(dentry->d_inode->i_mode)) drop_nlink(&dip->i_inode); mark_inode_dirty(&dip->i_inode); @@ -2017,22 +2061,36 @@ out: * gfs2_diradd_alloc_required - find if adding entry will require an allocation * @ip: the file being written to * @filname: the filename that's going to be added + * @da: The structure to return dir alloc info * - * Returns: 1 if alloc required, 0 if not, -ve on error + * Returns: 0 if ok, -ve on error */ -int gfs2_diradd_alloc_required(struct inode *inode, const struct qstr *name) +int gfs2_diradd_alloc_required(struct inode *inode, const struct qstr *name, + struct gfs2_diradd *da) { + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); + const unsigned int extra = sizeof(struct gfs2_dinode) - sizeof(struct gfs2_leaf); struct gfs2_dirent *dent; struct buffer_head *bh; + da->nr_blocks = 0; + da->bh = NULL; + da->dent = NULL; + dent = gfs2_dirent_search(inode, name, gfs2_dirent_find_space, &bh); if (!dent) { - return 1; + da->nr_blocks = sdp->sd_max_dirres; + if (!(ip->i_diskflags & GFS2_DIF_EXHASH) && + (GFS2_DIRENT_SIZE(name->len) < extra)) + da->nr_blocks = 1; + return 0; } if (IS_ERR(dent)) return PTR_ERR(dent); - brelse(bh); + da->bh = bh; + da->dent = dent; return 0; } diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h index 4f03bbd1873f..126c65dda028 100644 --- a/fs/gfs2/dir.h +++ b/fs/gfs2/dir.h @@ -16,6 +16,14 @@ struct inode; struct gfs2_inode; struct gfs2_inum; +struct buffer_head; +struct gfs2_dirent; + +struct gfs2_diradd { + unsigned nr_blocks; + struct gfs2_dirent *dent; + struct buffer_head *bh; +}; extern struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *filename, @@ -23,7 +31,13 @@ extern struct inode *gfs2_dir_search(struct inode *dir, extern int gfs2_dir_check(struct inode *dir, const struct qstr *filename, const struct gfs2_inode *ip); extern int gfs2_dir_add(struct inode *inode, const struct qstr *filename, - const struct gfs2_inode *ip); + const struct gfs2_inode *ip, struct gfs2_diradd *da); +static inline void gfs2_dir_no_add(struct gfs2_diradd *da) +{ + if (da->bh) + brelse(da->bh); + da->bh = NULL; +} extern int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry); extern int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, struct file_ra_state *f_ra); @@ -33,7 +47,8 @@ extern int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename, extern int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip); extern int gfs2_diradd_alloc_required(struct inode *dir, - const struct qstr *filename); + const struct qstr *filename, + struct gfs2_diradd *da); extern int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block, struct buffer_head **bhp); extern void gfs2_dir_hash_inval(struct gfs2_inode *ip); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c8420f7e4db6..ca0be6c69a26 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1552,13 +1552,11 @@ void gfs2_glock_thaw(struct gfs2_sbd *sdp) glock_hash_walk(thaw_glock, sdp); } -static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl) +static void dump_glock(struct seq_file *seq, struct gfs2_glock *gl) { - int ret; spin_lock(&gl->gl_spin); - ret = gfs2_dump_glock(seq, gl); + gfs2_dump_glock(seq, gl); spin_unlock(&gl->gl_spin); - return ret; } static void dump_glock_func(struct gfs2_glock *gl) @@ -1647,14 +1645,14 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags) * @seq: the seq_file struct * @gh: the glock holder * - * Returns: 0 on success, -ENOBUFS when we run out of space */ -static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) +static void dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) { struct task_struct *gh_owner = NULL; char flags_buf[32]; + rcu_read_lock(); if (gh->gh_owner_pid) gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID); gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n", @@ -1664,7 +1662,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1, gh_owner ? gh_owner->comm : "(ended)", (void *)gh->gh_ip); - return 0; + rcu_read_unlock(); } static const char *gflags2str(char *buf, const struct gfs2_glock *gl) @@ -1719,16 +1717,14 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl) * example. The field's are n = number (id of the object), f = flags, * t = type, s = state, r = refcount, e = error, p = pid. * - * Returns: 0 on success, -ENOBUFS when we run out of space */ -int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl) +void gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl) { const struct gfs2_glock_operations *glops = gl->gl_ops; unsigned long long dtime; const struct gfs2_holder *gh; char gflags_buf[32]; - int error = 0; dtime = jiffies - gl->gl_demote_time; dtime *= 1000000/HZ; /* demote time in uSec */ @@ -1745,15 +1741,11 @@ int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl) atomic_read(&gl->gl_revokes), (int)gl->gl_lockref.count, gl->gl_hold_time); - list_for_each_entry(gh, &gl->gl_holders, gh_list) { - error = dump_holder(seq, gh); - if (error) - goto out; - } + list_for_each_entry(gh, &gl->gl_holders, gh_list) + dump_holder(seq, gh); + if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump) - error = glops->go_dump(seq, gl); -out: - return error; + glops->go_dump(seq, gl); } static int gfs2_glstats_seq_show(struct seq_file *seq, void *iter_ptr) @@ -1951,7 +1943,8 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) { - return dump_glock(seq, iter_ptr); + dump_glock(seq, iter_ptr); + return 0; } static void *gfs2_sbstats_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 6647d77366ba..32572f71f027 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -199,7 +199,7 @@ extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, struct gfs2_holder *gh); extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); -extern int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl); +extern void gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl); #define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0) extern __printf(2, 3) void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index db908f697139..3bf0631b5d56 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -133,7 +133,8 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) static void rgrp_go_sync(struct gfs2_glock *gl) { - struct address_space *metamapping = gfs2_glock2aspace(gl); + struct gfs2_sbd *sdp = gl->gl_sbd; + struct address_space *mapping = &sdp->sd_aspace; struct gfs2_rgrpd *rgd; int error; @@ -141,10 +142,10 @@ static void rgrp_go_sync(struct gfs2_glock *gl) return; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); - gfs2_log_flush(gl->gl_sbd, gl); - filemap_fdatawrite(metamapping); - error = filemap_fdatawait(metamapping); - mapping_set_error(metamapping, error); + gfs2_log_flush(sdp, gl); + filemap_fdatawrite_range(mapping, gl->gl_vm.start, gl->gl_vm.end); + error = filemap_fdatawait_range(mapping, gl->gl_vm.start, gl->gl_vm.end); + mapping_set_error(mapping, error); gfs2_ail_empty_gl(gl); spin_lock(&gl->gl_spin); @@ -166,11 +167,12 @@ static void rgrp_go_sync(struct gfs2_glock *gl) static void rgrp_go_inval(struct gfs2_glock *gl, int flags) { - struct address_space *mapping = gfs2_glock2aspace(gl); + struct gfs2_sbd *sdp = gl->gl_sbd; + struct address_space *mapping = &sdp->sd_aspace; WARN_ON_ONCE(!(flags & DIO_METADATA)); - gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count)); - truncate_inode_pages(mapping, 0); + gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count)); + truncate_inode_pages_range(mapping, gl->gl_vm.start, gl->gl_vm.end); if (gl->gl_object) { struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object; @@ -192,8 +194,11 @@ static void inode_go_sync(struct gfs2_glock *gl) if (ip && !S_ISREG(ip->i_inode.i_mode)) ip = NULL; - if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) - unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); + if (ip) { + if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) + unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); + inode_dio_wait(&ip->i_inode); + } if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return; @@ -410,6 +415,9 @@ static int inode_go_lock(struct gfs2_holder *gh) return error; } + if (gh->gh_state != LM_ST_DEFERRED) + inode_dio_wait(&ip->i_inode); + if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) && (gl->gl_state == LM_ST_EXCLUSIVE) && (gh->gh_state == LM_ST_EXCLUSIVE)) { @@ -429,21 +437,19 @@ static int inode_go_lock(struct gfs2_holder *gh) * @seq: The iterator * @ip: the inode * - * Returns: 0 on success, -ENOBUFS when we run out of space */ -static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl) +static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl) { const struct gfs2_inode *ip = gl->gl_object; if (ip == NULL) - return 0; + return; gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n", (unsigned long long)ip->i_no_formal_ino, (unsigned long long)ip->i_no_addr, IF2DT(ip->i_inode.i_mode), ip->i_flags, (unsigned int)ip->i_diskflags, (unsigned long long)i_size_read(&ip->i_inode)); - return 0; } /** @@ -552,7 +558,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_unlock = gfs2_rgrp_go_unlock, .go_dump = gfs2_rgrp_dump, .go_type = LM_TYPE_RGRP, - .go_flags = GLOF_ASPACE | GLOF_LVB, + .go_flags = GLOF_LVB, }; const struct gfs2_glock_operations gfs2_trans_glops = { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index ba1ea67f4eeb..cf0e34400f71 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -93,6 +93,7 @@ struct gfs2_rgrpd { struct gfs2_rgrp_lvb *rd_rgl; u32 rd_last_alloc; u32 rd_flags; + u32 rd_extfail_pt; /* extent failure point */ #define GFS2_RDF_CHECK 0x10000000 /* check for unlinked inodes */ #define GFS2_RDF_UPTODATE 0x20000000 /* rg is up to date */ #define GFS2_RDF_ERROR 0x40000000 /* error in rg */ @@ -217,7 +218,7 @@ struct gfs2_glock_operations { int (*go_demote_ok) (const struct gfs2_glock *gl); int (*go_lock) (struct gfs2_holder *gh); void (*go_unlock) (struct gfs2_holder *gh); - int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl); + void (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl); void (*go_callback)(struct gfs2_glock *gl, bool remote); const int go_type; const unsigned long go_flags; @@ -350,7 +351,15 @@ struct gfs2_glock { atomic_t gl_ail_count; atomic_t gl_revokes; struct delayed_work gl_work; - struct work_struct gl_delete; + union { + /* For inode and iopen glocks only */ + struct work_struct gl_delete; + /* For rgrp glocks only */ + struct { + loff_t start; + loff_t end; + } gl_vm; + }; struct rcu_head gl_rcu; }; @@ -419,10 +428,13 @@ enum { }; struct gfs2_quota_data { + struct hlist_bl_node qd_hlist; struct list_head qd_list; struct kqid qd_id; + struct gfs2_sbd *qd_sbd; struct lockref qd_lockref; struct list_head qd_lru; + unsigned qd_hash; unsigned long qd_flags; /* QDF_... */ @@ -441,6 +453,7 @@ struct gfs2_quota_data { u64 qd_sync_gen; unsigned long qd_last_warn; + struct rcu_head qd_rcu; }; struct gfs2_trans { @@ -720,13 +733,15 @@ struct gfs2_sbd { spinlock_t sd_trunc_lock; unsigned int sd_quota_slots; - unsigned int sd_quota_chunks; - unsigned char **sd_quota_bitmap; + unsigned long *sd_quota_bitmap; + spinlock_t sd_bitmap_lock; u64 sd_quota_sync_gen; /* Log stuff */ + struct address_space sd_aspace; + spinlock_t sd_log_lock; struct gfs2_trans *sd_log_tr; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 7119504159f1..890588c7fb33 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -149,7 +149,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, ip = GFS2_I(inode); if (!inode) - return ERR_PTR(-ENOBUFS); + return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -469,14 +469,36 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip, brelse(dibh); } +/** + * gfs2_trans_da_blocks - Calculate number of blocks to link inode + * @dip: The directory we are linking into + * @da: The dir add information + * @nr_inodes: The number of inodes involved + * + * This calculate the number of blocks we need to reserve in a + * transaction to link @nr_inodes into a directory. In most cases + * @nr_inodes will be 2 (the directory plus the inode being linked in) + * but in case of rename, 4 may be required. + * + * Returns: Number of blocks + */ + +static unsigned gfs2_trans_da_blks(const struct gfs2_inode *dip, + const struct gfs2_diradd *da, + unsigned nr_inodes) +{ + return da->nr_blocks + gfs2_rg_blocks(dip, da->nr_blocks) + + (nr_inodes * RES_DINODE) + RES_QUOTA + RES_STATFS; +} + static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip, int arq) + struct gfs2_inode *ip, struct gfs2_diradd *da) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - struct gfs2_alloc_parms ap = { .target = sdp->sd_max_dirres, }; + struct gfs2_alloc_parms ap = { .target = da->nr_blocks, }; int error; - if (arq) { + if (da->nr_blocks) { error = gfs2_quota_lock_check(dip); if (error) goto fail_quota_locks; @@ -485,10 +507,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, if (error) goto fail_quota_locks; - error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - dip->i_rgd->rd_length + - 2 * RES_DINODE + - RES_STATFS + RES_QUOTA, 0); + error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, da, 2), 0); if (error) goto fail_ipreserv; } else { @@ -497,7 +516,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, goto fail_quota_locks; } - error = gfs2_dir_add(&dip->i_inode, name, ip); + error = gfs2_dir_add(&dip->i_inode, name, ip, da); if (error) goto fail_end_trans; @@ -560,7 +579,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, struct dentry *d; int error; u32 aflags = 0; - int arq; + struct gfs2_diradd da = { .bh = NULL, }; if (!name->len || name->len > GFS2_FNAMESIZE) return -ENAMETOOLONG; @@ -585,6 +604,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = PTR_ERR(inode); if (!IS_ERR(inode)) { d = d_splice_alias(inode, dentry); + error = PTR_ERR(d); + if (IS_ERR(d)) + goto fail_gunlock; error = 0; if (file) { if (S_ISREG(inode->i_mode)) { @@ -602,7 +624,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, goto fail_gunlock; } - arq = error = gfs2_diradd_alloc_required(dir, name); + error = gfs2_diradd_alloc_required(dir, name, &da); if (error < 0) goto fail_gunlock; @@ -690,7 +712,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock3; - error = link_dinode(dip, name, ip, arq); + error = link_dinode(dip, name, ip, &da); if (error) goto fail_gunlock3; @@ -719,6 +741,7 @@ fail_free_inode: free_inode_nonrcu(inode); inode = NULL; fail_gunlock: + gfs2_dir_no_add(&da); gfs2_glock_dq_uninit(ghs); if (inode && !IS_ERR(inode)) { clear_nlink(inode); @@ -779,6 +802,11 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, } d = d_splice_alias(inode, dentry); + if (IS_ERR(d)) { + iput(inode); + gfs2_glock_dq_uninit(&gh); + return d; + } if (file && S_ISREG(inode->i_mode)) error = finish_open(file, dentry, gfs2_open_common, opened); @@ -817,7 +845,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder ghs[2]; struct buffer_head *dibh; - int alloc_required; + struct gfs2_diradd da = { .bh = NULL, }; int error; if (S_ISDIR(inode->i_mode)) @@ -872,13 +900,12 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (ip->i_inode.i_nlink == (u32)-1) goto out_gunlock; - alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name); + error = gfs2_diradd_alloc_required(dir, &dentry->d_name, &da); if (error < 0) goto out_gunlock; - error = 0; - if (alloc_required) { - struct gfs2_alloc_parms ap = { .target = sdp->sd_max_dirres, }; + if (da.nr_blocks) { + struct gfs2_alloc_parms ap = { .target = da.nr_blocks, }; error = gfs2_quota_lock_check(dip); if (error) goto out_gunlock; @@ -887,10 +914,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (error) goto out_gunlock_q; - error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - gfs2_rg_blocks(dip, sdp->sd_max_dirres) + - 2 * RES_DINODE + RES_STATFS + - RES_QUOTA, 0); + error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, &da, 2), 0); if (error) goto out_ipres; } else { @@ -903,7 +927,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (error) goto out_end_trans; - error = gfs2_dir_add(dir, &dentry->d_name, ip); + error = gfs2_dir_add(dir, &dentry->d_name, ip, &da); if (error) goto out_brelse; @@ -919,12 +943,13 @@ out_brelse: out_end_trans: gfs2_trans_end(sdp); out_ipres: - if (alloc_required) + if (da.nr_blocks) gfs2_inplace_release(dip); out_gunlock_q: - if (alloc_required) + if (da.nr_blocks) gfs2_quota_unlock(dip); out_gunlock: + gfs2_dir_no_add(&da); gfs2_glock_dq(ghs + 1); out_child: gfs2_glock_dq(ghs); @@ -1254,7 +1279,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, struct gfs2_rgrpd *nrgd; unsigned int num_gh; int dir_rename = 0; - int alloc_required = 0; + struct gfs2_diradd da = { .nr_blocks = 0, }; unsigned int x; int error; @@ -1388,14 +1413,14 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, goto out_gunlock; } - if (nip == NULL) - alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name); - error = alloc_required; - if (error < 0) - goto out_gunlock; + if (nip == NULL) { + error = gfs2_diradd_alloc_required(ndir, &ndentry->d_name, &da); + if (error) + goto out_gunlock; + } - if (alloc_required) { - struct gfs2_alloc_parms ap = { .target = sdp->sd_max_dirres, }; + if (da.nr_blocks) { + struct gfs2_alloc_parms ap = { .target = da.nr_blocks, }; error = gfs2_quota_lock_check(ndip); if (error) goto out_gunlock; @@ -1404,10 +1429,8 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) goto out_gunlock_q; - error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - gfs2_rg_blocks(ndip, sdp->sd_max_dirres) + - 4 * RES_DINODE + 4 * RES_LEAF + - RES_STATFS + RES_QUOTA + 4, 0); + error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(ndip, &da, 4) + + 4 * RES_LEAF + 4, 0); if (error) goto out_ipreserv; } else { @@ -1441,19 +1464,20 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) goto out_end_trans; - error = gfs2_dir_add(ndir, &ndentry->d_name, ip); + error = gfs2_dir_add(ndir, &ndentry->d_name, ip, &da); if (error) goto out_end_trans; out_end_trans: gfs2_trans_end(sdp); out_ipreserv: - if (alloc_required) + if (da.nr_blocks) gfs2_inplace_release(ndip); out_gunlock_q: - if (alloc_required) + if (da.nr_blocks) gfs2_quota_unlock(ndip); out_gunlock: + gfs2_dir_no_add(&da); while (x--) { gfs2_glock_dq(ghs + x); gfs2_holder_uninit(ghs + x); @@ -1607,10 +1631,22 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid)) ogid = ngid = NO_GID_QUOTA_CHANGE; - error = gfs2_quota_lock(ip, nuid, ngid); + error = get_write_access(inode); if (error) return error; + error = gfs2_rs_alloc(ip); + if (error) + goto out; + + error = gfs2_rindex_update(sdp); + if (error) + goto out; + + error = gfs2_quota_lock(ip, nuid, ngid); + if (error) + goto out; + if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) || !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) { error = gfs2_quota_check(ip, nuid, ngid); @@ -1637,6 +1673,8 @@ out_end_trans: gfs2_trans_end(sdp); out_gunlock_q: gfs2_quota_unlock(ip); +out: + put_write_access(inode); return error; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 610613fb65b5..9dcb9777a5f8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -551,10 +551,10 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct buffer_head *bh = bd->bd_bh; struct gfs2_glock *gl = bd->bd_gl; - gfs2_remove_from_ail(bd); - bd->bd_bh = NULL; bh->b_private = NULL; bd->bd_blkno = bh->b_blocknr; + gfs2_remove_from_ail(bd); /* drops ref on bh */ + bd->bd_bh = NULL; bd->bd_ops = &gfs2_revoke_lops; sdp->sd_log_num_revoke++; atomic_inc(&gl->gl_revokes); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 010b9fb9fec6..58f06400b7b8 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -83,6 +83,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd) bd->bd_bh->b_data + bi->bi_offset, bi->bi_len); clear_bit(GBF_FULL, &bi->bi_flags); rgd->rd_free_clone = rgd->rd_free; + rgd->rd_extfail_pt = rgd->rd_free; } /** @@ -588,8 +589,12 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, static void gfs2_meta_sync(struct gfs2_glock *gl) { struct address_space *mapping = gfs2_glock2aspace(gl); + struct gfs2_sbd *sdp = gl->gl_sbd; int error; + if (mapping == NULL) + mapping = &sdp->sd_aspace; + filemap_fdatawrite(mapping); error = filemap_fdatawait(mapping); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 0650db2541ef..c272e73063de 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -76,6 +76,7 @@ static int __init init_gfs2_fs(void) gfs2_str2qstr(&gfs2_qdot, "."); gfs2_str2qstr(&gfs2_qdotdot, ".."); + gfs2_quota_hash_init(); error = gfs2_sys_init(); if (error) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 932415050540..c7f24690ed05 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -116,6 +116,9 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) unsigned long index; unsigned int bufnum; + if (mapping == NULL) + mapping = &sdp->sd_aspace; + shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift; index = blkno >> shift; /* convert block to page */ bufnum = blkno - (index << shift); /* block buf index within page */ @@ -258,6 +261,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int struct address_space *mapping = bh->b_page->mapping; struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct gfs2_bufdata *bd = bh->b_private; + int was_pinned = 0; if (test_clear_buffer_pinned(bh)) { trace_gfs2_pin(bd, 0); @@ -273,12 +277,16 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int tr->tr_num_databuf_rm++; } tr->tr_touched = 1; + was_pinned = 1; brelse(bh); } if (bd) { spin_lock(&sdp->sd_ail_lock); if (bd->bd_tr) { gfs2_trans_add_revoke(sdp, bd); + } else if (was_pinned) { + bh->b_private = NULL; + kmem_cache_free(gfs2_bufdata_cachep, bd); } spin_unlock(&sdp->sd_ail_lock); } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 82303b474958..1e712b566d76 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -36,6 +36,7 @@ #include "log.h" #include "quota.h" #include "dir.h" +#include "meta_io.h" #include "trace_gfs2.h" #define DO 0 @@ -62,6 +63,7 @@ static void gfs2_tune_init(struct gfs2_tune *gt) static struct gfs2_sbd *init_sbd(struct super_block *sb) { struct gfs2_sbd *sdp; + struct address_space *mapping; sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL); if (!sdp) @@ -97,6 +99,18 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) init_waitqueue_head(&sdp->sd_quota_wait); INIT_LIST_HEAD(&sdp->sd_trunc_list); spin_lock_init(&sdp->sd_trunc_lock); + spin_lock_init(&sdp->sd_bitmap_lock); + + mapping = &sdp->sd_aspace; + + address_space_init_once(mapping); + mapping->a_ops = &gfs2_meta_aops; + mapping->host = sb->s_bdev->bd_inode; + mapping->flags = 0; + mapping_set_gfp_mask(mapping, GFP_NOFS); + mapping->private_data = NULL; + mapping->backing_dev_info = sb->s_bdi; + mapping->writeback_index = 0; spin_lock_init(&sdp->sd_log_lock); atomic_set(&sdp->sd_log_pinned, 0); @@ -217,7 +231,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) page = alloc_page(GFP_NOFS); if (unlikely(!page)) - return -ENOBUFS; + return -ENOMEM; ClearPageUptodate(page); ClearPageDirty(page); @@ -956,40 +970,6 @@ fail: return error; } -static int init_threads(struct gfs2_sbd *sdp, int undo) -{ - struct task_struct *p; - int error = 0; - - if (undo) - goto fail_quotad; - - p = kthread_run(gfs2_logd, sdp, "gfs2_logd"); - if (IS_ERR(p)) { - error = PTR_ERR(p); - fs_err(sdp, "can't start logd thread: %d\n", error); - return error; - } - sdp->sd_logd_process = p; - - p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad"); - if (IS_ERR(p)) { - error = PTR_ERR(p); - fs_err(sdp, "can't start quotad thread: %d\n", error); - goto fail; - } - sdp->sd_quotad_process = p; - - return 0; - - -fail_quotad: - kthread_stop(sdp->sd_quotad_process); -fail: - kthread_stop(sdp->sd_logd_process); - return error; -} - static const match_table_t nolock_tokens = { { Opt_jid, "jid=%d\n", }, { Opt_err, NULL }, @@ -1254,15 +1234,11 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent goto fail_per_node; } - error = init_threads(sdp, DO); - if (error) - goto fail_per_node; - if (!(sb->s_flags & MS_RDONLY)) { error = gfs2_make_fs_rw(sdp); if (error) { fs_err(sdp, "can't make FS RW: %d\n", error); - goto fail_threads; + goto fail_per_node; } } @@ -1270,8 +1246,6 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent gfs2_online_uevent(sdp); return 0; -fail_threads: - init_threads(sdp, UNDO); fail_per_node: init_per_node(sdp, UNDO); fail_inodes: @@ -1366,8 +1340,18 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, if (IS_ERR(s)) goto error_bdev; - if (s->s_root) + if (s->s_root) { + /* + * s_umount nests inside bd_mutex during + * __invalidate_device(). blkdev_put() acquires + * bd_mutex and can't be called under s_umount. Drop + * s_umount temporarily. This is safe as we're + * holding an active reference. + */ + up_write(&s->s_umount); blkdev_put(bdev, mode); + down_write(&s->s_umount); + } memset(&args, 0, sizeof(args)); args.ar_quota = GFS2_QUOTA_DEFAULT; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 98236d0df3ca..8bec0e3192dd 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -52,6 +52,11 @@ #include <linux/dqblk_xfs.h> #include <linux/lockref.h> #include <linux/list_lru.h> +#include <linux/rcupdate.h> +#include <linux/rculist_bl.h> +#include <linux/bit_spinlock.h> +#include <linux/jhash.h> +#include <linux/vmalloc.h> #include "gfs2.h" #include "incore.h" @@ -67,16 +72,44 @@ #include "inode.h" #include "util.h" -struct gfs2_quota_change_host { - u64 qc_change; - u32 qc_flags; /* GFS2_QCF_... */ - struct kqid qc_id; -}; +#define GFS2_QD_HASH_SHIFT 12 +#define GFS2_QD_HASH_SIZE (1 << GFS2_QD_HASH_SHIFT) +#define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1) -/* Lock order: qd_lock -> qd->lockref.lock -> lru lock */ +/* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */ +/* -> sd_bitmap_lock */ static DEFINE_SPINLOCK(qd_lock); struct list_lru gfs2_qd_lru; +static struct hlist_bl_head qd_hash_table[GFS2_QD_HASH_SIZE]; + +static unsigned int gfs2_qd_hash(const struct gfs2_sbd *sdp, + const struct kqid qid) +{ + unsigned int h; + + h = jhash(&sdp, sizeof(struct gfs2_sbd *), 0); + h = jhash(&qid, sizeof(struct kqid), h); + + return h & GFS2_QD_HASH_MASK; +} + +static inline void spin_lock_bucket(unsigned int hash) +{ + hlist_bl_lock(&qd_hash_table[hash]); +} + +static inline void spin_unlock_bucket(unsigned int hash) +{ + hlist_bl_unlock(&qd_hash_table[hash]); +} + +static void gfs2_qd_dealloc(struct rcu_head *rcu) +{ + struct gfs2_quota_data *qd = container_of(rcu, struct gfs2_quota_data, qd_rcu); + kmem_cache_free(gfs2_quotad_cachep, qd); +} + static void gfs2_qd_dispose(struct list_head *list) { struct gfs2_quota_data *qd; @@ -93,6 +126,10 @@ static void gfs2_qd_dispose(struct list_head *list) list_del(&qd->qd_list); spin_unlock(&qd_lock); + spin_lock_bucket(qd->qd_hash); + hlist_bl_del_rcu(&qd->qd_hlist); + spin_unlock_bucket(qd->qd_hash); + gfs2_assert_warn(sdp, !qd->qd_change); gfs2_assert_warn(sdp, !qd->qd_slot_count); gfs2_assert_warn(sdp, !qd->qd_bh_count); @@ -101,7 +138,7 @@ static void gfs2_qd_dispose(struct list_head *list) atomic_dec(&sdp->sd_quota_count); /* Delete it from the common reclaim list */ - kmem_cache_free(gfs2_quotad_cachep, qd); + call_rcu(&qd->qd_rcu, gfs2_qd_dealloc); } } @@ -171,83 +208,95 @@ static u64 qd2offset(struct gfs2_quota_data *qd) return offset; } -static int qd_alloc(struct gfs2_sbd *sdp, struct kqid qid, - struct gfs2_quota_data **qdp) +static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; int error; qd = kmem_cache_zalloc(gfs2_quotad_cachep, GFP_NOFS); if (!qd) - return -ENOMEM; + return NULL; + qd->qd_sbd = sdp; qd->qd_lockref.count = 1; spin_lock_init(&qd->qd_lockref.lock); qd->qd_id = qid; qd->qd_slot = -1; INIT_LIST_HEAD(&qd->qd_lru); + qd->qd_hash = hash; error = gfs2_glock_get(sdp, qd2index(qd), &gfs2_quota_glops, CREATE, &qd->qd_gl); if (error) goto fail; - *qdp = qd; - - return 0; + return qd; fail: kmem_cache_free(gfs2_quotad_cachep, qd); - return error; + return NULL; } -static int qd_get(struct gfs2_sbd *sdp, struct kqid qid, - struct gfs2_quota_data **qdp) +static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash, + const struct gfs2_sbd *sdp, + struct kqid qid) { - struct gfs2_quota_data *qd = NULL, *new_qd = NULL; - int error, found; - - *qdp = NULL; + struct gfs2_quota_data *qd; + struct hlist_bl_node *h; - for (;;) { - found = 0; - spin_lock(&qd_lock); - list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) { - if (qid_eq(qd->qd_id, qid) && - lockref_get_not_dead(&qd->qd_lockref)) { - list_lru_del(&gfs2_qd_lru, &qd->qd_lru); - found = 1; - break; - } + hlist_bl_for_each_entry_rcu(qd, h, &qd_hash_table[hash], qd_hlist) { + if (!qid_eq(qd->qd_id, qid)) + continue; + if (qd->qd_sbd != sdp) + continue; + if (lockref_get_not_dead(&qd->qd_lockref)) { + list_lru_del(&gfs2_qd_lru, &qd->qd_lru); + return qd; } + } - if (!found) - qd = NULL; + return NULL; +} - if (!qd && new_qd) { - qd = new_qd; - list_add(&qd->qd_list, &sdp->sd_quota_list); - atomic_inc(&sdp->sd_quota_count); - new_qd = NULL; - } - spin_unlock(&qd_lock); +static int qd_get(struct gfs2_sbd *sdp, struct kqid qid, + struct gfs2_quota_data **qdp) +{ + struct gfs2_quota_data *qd, *new_qd; + unsigned int hash = gfs2_qd_hash(sdp, qid); - if (qd) { - if (new_qd) { - gfs2_glock_put(new_qd->qd_gl); - kmem_cache_free(gfs2_quotad_cachep, new_qd); - } - *qdp = qd; - return 0; - } + rcu_read_lock(); + *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); + rcu_read_unlock(); - error = qd_alloc(sdp, qid, &new_qd); - if (error) - return error; + if (qd) + return 0; + + new_qd = qd_alloc(hash, sdp, qid); + if (!new_qd) + return -ENOMEM; + + spin_lock(&qd_lock); + spin_lock_bucket(hash); + *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); + if (qd == NULL) { + *qdp = new_qd; + list_add(&new_qd->qd_list, &sdp->sd_quota_list); + hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]); + atomic_inc(&sdp->sd_quota_count); } + spin_unlock_bucket(hash); + spin_unlock(&qd_lock); + + if (qd) { + gfs2_glock_put(new_qd->qd_gl); + kmem_cache_free(gfs2_quotad_cachep, new_qd); + } + + return 0; } + static void qd_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; @@ -268,88 +317,48 @@ static void qd_put(struct gfs2_quota_data *qd) static int slot_get(struct gfs2_quota_data *qd) { - struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; - unsigned int c, o = 0, b; - unsigned char byte = 0; + struct gfs2_sbd *sdp = qd->qd_sbd; + unsigned int bit; + int error = 0; - spin_lock(&qd_lock); + spin_lock(&sdp->sd_bitmap_lock); + if (qd->qd_slot_count != 0) + goto out; - if (qd->qd_slot_count++) { - spin_unlock(&qd_lock); - return 0; + error = -ENOSPC; + bit = find_first_zero_bit(sdp->sd_quota_bitmap, sdp->sd_quota_slots); + if (bit < sdp->sd_quota_slots) { + set_bit(bit, sdp->sd_quota_bitmap); + qd->qd_slot = bit; +out: + qd->qd_slot_count++; } + spin_unlock(&sdp->sd_bitmap_lock); - for (c = 0; c < sdp->sd_quota_chunks; c++) - for (o = 0; o < PAGE_SIZE; o++) { - byte = sdp->sd_quota_bitmap[c][o]; - if (byte != 0xFF) - goto found; - } - - goto fail; - -found: - for (b = 0; b < 8; b++) - if (!(byte & (1 << b))) - break; - qd->qd_slot = c * (8 * PAGE_SIZE) + o * 8 + b; - - if (qd->qd_slot >= sdp->sd_quota_slots) - goto fail; - - sdp->sd_quota_bitmap[c][o] |= 1 << b; - - spin_unlock(&qd_lock); - - return 0; - -fail: - qd->qd_slot_count--; - spin_unlock(&qd_lock); - return -ENOSPC; + return error; } static void slot_hold(struct gfs2_quota_data *qd) { - struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; + struct gfs2_sbd *sdp = qd->qd_sbd; - spin_lock(&qd_lock); + spin_lock(&sdp->sd_bitmap_lock); gfs2_assert(sdp, qd->qd_slot_count); qd->qd_slot_count++; - spin_unlock(&qd_lock); -} - -static void gfs2_icbit_munge(struct gfs2_sbd *sdp, unsigned char **bitmap, - unsigned int bit, int new_value) -{ - unsigned int c, o, b = bit; - int old_value; - - c = b / (8 * PAGE_SIZE); - b %= 8 * PAGE_SIZE; - o = b / 8; - b %= 8; - - old_value = (bitmap[c][o] & (1 << b)); - gfs2_assert_withdraw(sdp, !old_value != !new_value); - - if (new_value) - bitmap[c][o] |= 1 << b; - else - bitmap[c][o] &= ~(1 << b); + spin_unlock(&sdp->sd_bitmap_lock); } static void slot_put(struct gfs2_quota_data *qd) { - struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; + struct gfs2_sbd *sdp = qd->qd_sbd; - spin_lock(&qd_lock); + spin_lock(&sdp->sd_bitmap_lock); gfs2_assert(sdp, qd->qd_slot_count); if (!--qd->qd_slot_count) { - gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, qd->qd_slot, 0); + BUG_ON(!test_and_clear_bit(qd->qd_slot, sdp->sd_quota_bitmap)); qd->qd_slot = -1; } - spin_unlock(&qd_lock); + spin_unlock(&sdp->sd_bitmap_lock); } static int bh_get(struct gfs2_quota_data *qd) @@ -427,8 +436,7 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, list_move_tail(&qd->qd_list, &sdp->sd_quota_list); set_bit(QDF_LOCKED, &qd->qd_flags); qd->qd_change_sync = qd->qd_change; - gfs2_assert_warn(sdp, qd->qd_slot_count); - qd->qd_slot_count++; + slot_hold(qd); return 1; } @@ -1214,17 +1222,6 @@ int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid) return error; } -static void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf) -{ - const struct gfs2_quota_change *str = buf; - - qc->qc_change = be64_to_cpu(str->qc_change); - qc->qc_flags = be32_to_cpu(str->qc_flags); - qc->qc_id = make_kqid(&init_user_ns, - (qc->qc_flags & GFS2_QCF_USER)?USRQUOTA:GRPQUOTA, - be32_to_cpu(str->qc_id)); -} - int gfs2_quota_init(struct gfs2_sbd *sdp) { struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); @@ -1232,6 +1229,8 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift; unsigned int x, slot = 0; unsigned int found = 0; + unsigned int hash; + unsigned int bm_size; u64 dblock; u32 extlen = 0; int error; @@ -1240,23 +1239,20 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) return -EIO; sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block; - sdp->sd_quota_chunks = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * PAGE_SIZE); - + bm_size = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * sizeof(unsigned long)); + bm_size *= sizeof(unsigned long); error = -ENOMEM; - - sdp->sd_quota_bitmap = kcalloc(sdp->sd_quota_chunks, - sizeof(unsigned char *), GFP_NOFS); + sdp->sd_quota_bitmap = kmalloc(bm_size, GFP_NOFS|__GFP_NOWARN); + if (sdp->sd_quota_bitmap == NULL) + sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS, PAGE_KERNEL); if (!sdp->sd_quota_bitmap) return error; - for (x = 0; x < sdp->sd_quota_chunks; x++) { - sdp->sd_quota_bitmap[x] = kzalloc(PAGE_SIZE, GFP_NOFS); - if (!sdp->sd_quota_bitmap[x]) - goto fail; - } + memset(sdp->sd_quota_bitmap, 0, bm_size); for (x = 0; x < blocks; x++) { struct buffer_head *bh; + const struct gfs2_quota_change *qc; unsigned int y; if (!extlen) { @@ -1274,34 +1270,42 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) goto fail; } + qc = (const struct gfs2_quota_change *)(bh->b_data + sizeof(struct gfs2_meta_header)); for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots; y++, slot++) { - struct gfs2_quota_change_host qc; struct gfs2_quota_data *qd; - - gfs2_quota_change_in(&qc, bh->b_data + - sizeof(struct gfs2_meta_header) + - y * sizeof(struct gfs2_quota_change)); - if (!qc.qc_change) + s64 qc_change = be64_to_cpu(qc->qc_change); + u32 qc_flags = be32_to_cpu(qc->qc_flags); + enum quota_type qtype = (qc_flags & GFS2_QCF_USER) ? + USRQUOTA : GRPQUOTA; + struct kqid qc_id = make_kqid(&init_user_ns, qtype, + be32_to_cpu(qc->qc_id)); + qc++; + if (!qc_change) continue; - error = qd_alloc(sdp, qc.qc_id, &qd); - if (error) { + hash = gfs2_qd_hash(sdp, qc_id); + qd = qd_alloc(hash, sdp, qc_id); + if (qd == NULL) { brelse(bh); goto fail; } set_bit(QDF_CHANGE, &qd->qd_flags); - qd->qd_change = qc.qc_change; + qd->qd_change = qc_change; qd->qd_slot = slot; qd->qd_slot_count = 1; spin_lock(&qd_lock); - gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, slot, 1); + BUG_ON(test_and_set_bit(slot, sdp->sd_quota_bitmap)); list_add(&qd->qd_list, &sdp->sd_quota_list); atomic_inc(&sdp->sd_quota_count); spin_unlock(&qd_lock); + spin_lock_bucket(hash); + hlist_bl_add_head_rcu(&qd->qd_hlist, &qd_hash_table[hash]); + spin_unlock_bucket(hash); + found++; } @@ -1324,44 +1328,28 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp) { struct list_head *head = &sdp->sd_quota_list; struct gfs2_quota_data *qd; - unsigned int x; spin_lock(&qd_lock); while (!list_empty(head)) { qd = list_entry(head->prev, struct gfs2_quota_data, qd_list); - /* - * To be removed in due course... we should be able to - * ensure that all refs to the qd have done by this point - * so that this rather odd test is not required - */ - spin_lock(&qd->qd_lockref.lock); - if (qd->qd_lockref.count > 1 || - (qd->qd_lockref.count && !test_bit(QDF_CHANGE, &qd->qd_flags))) { - spin_unlock(&qd->qd_lockref.lock); - list_move(&qd->qd_list, head); - spin_unlock(&qd_lock); - schedule(); - spin_lock(&qd_lock); - continue; - } - spin_unlock(&qd->qd_lockref.lock); - list_del(&qd->qd_list); + /* Also remove if this qd exists in the reclaim list */ list_lru_del(&gfs2_qd_lru, &qd->qd_lru); atomic_dec(&sdp->sd_quota_count); spin_unlock(&qd_lock); - if (!qd->qd_lockref.count) { - gfs2_assert_warn(sdp, !qd->qd_change); - gfs2_assert_warn(sdp, !qd->qd_slot_count); - } else - gfs2_assert_warn(sdp, qd->qd_slot_count == 1); + spin_lock_bucket(qd->qd_hash); + hlist_bl_del_rcu(&qd->qd_hlist); + spin_unlock_bucket(qd->qd_hash); + + gfs2_assert_warn(sdp, !qd->qd_change); + gfs2_assert_warn(sdp, !qd->qd_slot_count); gfs2_assert_warn(sdp, !qd->qd_bh_count); gfs2_glock_put(qd->qd_gl); - kmem_cache_free(gfs2_quotad_cachep, qd); + call_rcu(&qd->qd_rcu, gfs2_qd_dealloc); spin_lock(&qd_lock); } @@ -1370,9 +1358,11 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp) gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count)); if (sdp->sd_quota_bitmap) { - for (x = 0; x < sdp->sd_quota_chunks; x++) - kfree(sdp->sd_quota_bitmap[x]); - kfree(sdp->sd_quota_bitmap); + if (is_vmalloc_addr(sdp->sd_quota_bitmap)) + vfree(sdp->sd_quota_bitmap); + else + kfree(sdp->sd_quota_bitmap); + sdp->sd_quota_bitmap = NULL; } } @@ -1656,3 +1646,11 @@ const struct quotactl_ops gfs2_quotactl_ops = { .get_dqblk = gfs2_get_dqblk, .set_dqblk = gfs2_set_dqblk, }; + +void __init gfs2_quota_hash_init(void) +{ + unsigned i; + + for(i = 0; i < GFS2_QD_HASH_SIZE; i++) + INIT_HLIST_BL_HEAD(&qd_hash_table[i]); +} diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 96e4f34a03b0..55d506eb3c4a 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -57,5 +57,6 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) extern const struct quotactl_ops gfs2_quotactl_ops; extern struct shrinker gfs2_qd_shrinker; extern struct list_lru gfs2_qd_lru; +extern void __init gfs2_quota_hash_init(void); #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index c8d6161bd682..a1da21349235 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -57,6 +57,11 @@ * 3 = Used (metadata) */ +struct gfs2_extent { + struct gfs2_rbm rbm; + u32 len; +}; + static const char valid_change[16] = { /* current */ /* n */ 0, 1, 1, 1, @@ -65,8 +70,9 @@ static const char valid_change[16] = { 1, 0, 0, 0 }; -static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 minext, - const struct gfs2_inode *ip, bool nowrap); +static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, + const struct gfs2_inode *ip, bool nowrap, + const struct gfs2_alloc_parms *ap); /** @@ -635,9 +641,13 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) /* return reserved blocks to the rgrp */ BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free); rs->rs_rbm.rgd->rd_reserved -= rs->rs_free; + /* The rgrp extent failure point is likely not to increase; + it will only do so if the freed blocks are somehow + contiguous with a span of free blocks that follows. Still, + it will force the number to be recalculated later. */ + rgd->rd_extfail_pt += rs->rs_free; rs->rs_free = 0; clear_bit(GBF_FULL, &bi->bi_flags); - smp_mb__after_clear_bit(); } } @@ -876,6 +886,7 @@ static int rgd_insert(struct gfs2_rgrpd *rgd) static int read_rindex_entry(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + const unsigned bsize = sdp->sd_sb.sb_bsize; loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex); struct gfs2_rindex buf; int error; @@ -913,6 +924,8 @@ static int read_rindex_entry(struct gfs2_inode *ip) goto fail; rgd->rd_gl->gl_object = rgd; + rgd->rd_gl->gl_vm.start = rgd->rd_addr * bsize; + rgd->rd_gl->gl_vm.end = rgd->rd_gl->gl_vm.start + (rgd->rd_length * bsize) - 1; rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~GFS2_RDF_UPTODATE; if (rgd->rd_data > sdp->sd_max_rg_data) @@ -1126,6 +1139,8 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data); rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK); rgd->rd_free_clone = rgd->rd_free; + /* max out the rgrp allocation failure point */ + rgd->rd_extfail_pt = rgd->rd_free; } if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) { rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd)); @@ -1184,7 +1199,7 @@ int gfs2_rgrp_go_lock(struct gfs2_holder *gh) if (gh->gh_flags & GL_SKIP && sdp->sd_args.ar_rgrplvb) return 0; - return gfs2_rgrp_bh_get((struct gfs2_rgrpd *)gh->gh_gl->gl_object); + return gfs2_rgrp_bh_get(rgd); } /** @@ -1455,7 +1470,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip, if (WARN_ON(gfs2_rbm_from_block(&rbm, goal))) return; - ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, extlen, ip, true); + ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &extlen, ip, true, ap); if (ret == 0) { rs->rs_rbm = rbm; rs->rs_free = extlen; @@ -1520,6 +1535,7 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block, * @rbm: The current position in the resource group * @ip: The inode for which we are searching for blocks * @minext: The minimum extent length + * @maxext: A pointer to the maximum extent structure * * This checks the current position in the rgrp to see whether there is * a reservation covering this block. If not then this function is a @@ -1532,7 +1548,8 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block, static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm, const struct gfs2_inode *ip, - u32 minext) + u32 minext, + struct gfs2_extent *maxext) { u64 block = gfs2_rbm_to_block(rbm); u32 extlen = 1; @@ -1545,8 +1562,7 @@ static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm, */ if (minext) { extlen = gfs2_free_extlen(rbm, minext); - nblock = block + extlen; - if (extlen < minext) + if (extlen <= maxext->len) goto fail; } @@ -1555,9 +1571,17 @@ static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm, * and skip if parts of it are already reserved */ nblock = gfs2_next_unreserved_block(rbm->rgd, block, extlen, ip); - if (nblock == block) - return 0; + if (nblock == block) { + if (!minext || extlen >= minext) + return 0; + + if (extlen > maxext->len) { + maxext->len = extlen; + maxext->rbm = *rbm; + } fail: + nblock = block + extlen; + } ret = gfs2_rbm_from_block(rbm, nblock); if (ret < 0) return ret; @@ -1568,30 +1592,38 @@ fail: * gfs2_rbm_find - Look for blocks of a particular state * @rbm: Value/result starting position and final position * @state: The state which we want to find - * @minext: The requested extent length (0 for a single block) + * @minext: Pointer to the requested extent length (NULL for a single block) + * This is updated to be the actual reservation size. * @ip: If set, check for reservations * @nowrap: Stop looking at the end of the rgrp, rather than wrapping * around until we've reached the starting point. + * @ap: the allocation parameters * * Side effects: * - If looking for free blocks, we set GBF_FULL on each bitmap which * has no free blocks in it. + * - If looking for free blocks, we set rd_extfail_pt on each rgrp which + * has come up short on a free block search. * * Returns: 0 on success, -ENOSPC if there is no block of the requested state */ -static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 minext, - const struct gfs2_inode *ip, bool nowrap) +static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, + const struct gfs2_inode *ip, bool nowrap, + const struct gfs2_alloc_parms *ap) { struct buffer_head *bh; int initial_bii; u32 initial_offset; + int first_bii = rbm->bii; + u32 first_offset = rbm->offset; u32 offset; u8 *buffer; int n = 0; int iters = rbm->rgd->rd_length; int ret; struct gfs2_bitmap *bi; + struct gfs2_extent maxext = { .rbm.rgd = rbm->rgd, }; /* If we are not starting at the beginning of a bitmap, then we * need to add one to the bitmap count to ensure that we search @@ -1620,7 +1652,9 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 minext, return 0; initial_bii = rbm->bii; - ret = gfs2_reservation_check_and_update(rbm, ip, minext); + ret = gfs2_reservation_check_and_update(rbm, ip, + minext ? *minext : 0, + &maxext); if (ret == 0) return 0; if (ret > 0) { @@ -1655,6 +1689,24 @@ next_iter: break; } + if (minext == NULL || state != GFS2_BLKST_FREE) + return -ENOSPC; + + /* If the extent was too small, and it's smaller than the smallest + to have failed before, remember for future reference that it's + useless to search this rgrp again for this amount or more. */ + if ((first_offset == 0) && (first_bii == 0) && + (*minext < rbm->rgd->rd_extfail_pt)) + rbm->rgd->rd_extfail_pt = *minext; + + /* If the maximum extent we found is big enough to fulfill the + minimum requirements, use it anyway. */ + if (maxext.len) { + *rbm = maxext.rbm; + *minext = maxext.len; + return 0; + } + return -ENOSPC; } @@ -1680,7 +1732,8 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip while (1) { down_write(&sdp->sd_log_flush_lock); - error = gfs2_rbm_find(&rbm, GFS2_BLKST_UNLINKED, 0, NULL, true); + error = gfs2_rbm_find(&rbm, GFS2_BLKST_UNLINKED, NULL, NULL, + true, NULL); up_write(&sdp->sd_log_flush_lock); if (error == -ENOSPC) break; @@ -1891,7 +1944,9 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a } /* Skip unuseable resource groups */ - if (rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) + if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | + GFS2_RDF_ERROR)) || + (ap->target > rs->rs_rbm.rgd->rd_extfail_pt)) goto skip_rgrp; if (sdp->sd_args.ar_rgrplvb) @@ -1911,15 +1966,16 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a return 0; } - /* Drop reservation, if we couldn't use reserved rgrp */ - if (gfs2_rs_active(rs)) - gfs2_rs_deltree(rs); check_rgrp: /* Check for unlinked inodes which can be reclaimed */ if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK) try_rgrp_unlink(rs->rs_rbm.rgd, &last_unlinked, ip->i_no_addr); skip_rgrp: + /* Drop reservation, if we couldn't use reserved rgrp */ + if (gfs2_rs_active(rs)) + gfs2_rs_deltree(rs); + /* Unlock rgrp if required */ if (!rg_locked) gfs2_glock_dq_uninit(&rs->rs_rgd_gh); @@ -2064,25 +2120,24 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, * */ -int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl) +void gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl) { struct gfs2_rgrpd *rgd = gl->gl_object; struct gfs2_blkreserv *trs; const struct rb_node *n; if (rgd == NULL) - return 0; - gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u r:%u\n", + return; + gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u r:%u e:%u\n", (unsigned long long)rgd->rd_addr, rgd->rd_flags, rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes, - rgd->rd_reserved); + rgd->rd_reserved, rgd->rd_extfail_pt); spin_lock(&rgd->rd_rsspin); for (n = rb_first(&rgd->rd_rstree); n; n = rb_next(&trs->rs_node)) { trs = rb_entry(n, struct gfs2_blkreserv, rs_node); dump_rs(seq, trs); } spin_unlock(&rgd->rd_rsspin); - return 0; } static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd) @@ -2184,18 +2239,20 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, int error; gfs2_set_alloc_start(&rbm, ip, dinode); - error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, 0, ip, false); + error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, ip, false, NULL); if (error == -ENOSPC) { gfs2_set_alloc_start(&rbm, ip, dinode); - error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, 0, NULL, false); + error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, NULL, false, + NULL); } /* Since all blocks are reserved in advance, this shouldn't happen */ if (error) { - fs_warn(sdp, "inum=%llu error=%d, nblocks=%u, full=%d\n", + fs_warn(sdp, "inum=%llu error=%d, nblocks=%u, full=%d fail_pt=%d\n", (unsigned long long)ip->i_no_addr, error, *nblocks, - test_bit(GBF_FULL, &rbm.rgd->rd_bits->bi_flags)); + test_bit(GBF_FULL, &rbm.rgd->rd_bits->bi_flags), + rbm.rgd->rd_extfail_pt); goto rgrp_error; } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 3a10d2ffbbe7..463ab2e95d1c 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -68,7 +68,7 @@ extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); extern u64 gfs2_ri_total(struct gfs2_sbd *sdp); -extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl); +extern void gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl); extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, struct buffer_head *bh, const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 35da5b19c0de..60f60f6181f3 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -369,6 +369,33 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd) return 0; } +static int init_threads(struct gfs2_sbd *sdp) +{ + struct task_struct *p; + int error = 0; + + p = kthread_run(gfs2_logd, sdp, "gfs2_logd"); + if (IS_ERR(p)) { + error = PTR_ERR(p); + fs_err(sdp, "can't start logd thread: %d\n", error); + return error; + } + sdp->sd_logd_process = p; + + p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad"); + if (IS_ERR(p)) { + error = PTR_ERR(p); + fs_err(sdp, "can't start quotad thread: %d\n", error); + goto fail; + } + sdp->sd_quotad_process = p; + return 0; + +fail: + kthread_stop(sdp->sd_logd_process); + return error; +} + /** * gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one * @sdp: the filesystem @@ -384,10 +411,14 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) struct gfs2_log_header_host head; int error; - error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh); + error = init_threads(sdp); if (error) return error; + error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh); + if (error) + goto fail_threads; + j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); error = gfs2_find_jhead(sdp->sd_jdesc, &head); @@ -417,7 +448,9 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) fail: t_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&t_gh); - +fail_threads: + kthread_stop(sdp->sd_quotad_process); + kthread_stop(sdp->sd_logd_process); return error; } @@ -800,6 +833,9 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) struct gfs2_holder t_gh; int error; + kthread_stop(sdp->sd_quotad_process); + kthread_stop(sdp->sd_logd_process); + flush_workqueue(gfs2_delete_workqueue); gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); @@ -857,9 +893,6 @@ restart: } spin_unlock(&sdp->sd_jindex_spin); - kthread_stop(sdp->sd_quotad_process); - kthread_stop(sdp->sd_logd_process); - if (!(sb->s_flags & MS_RDONLY)) { error = gfs2_make_fs_ro(sdp); if (error) diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index b51a6079108d..e9a97a0d4314 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -24,13 +24,6 @@ struct hfsplus_wd { u16 embed_count; }; -static void hfsplus_end_io_sync(struct bio *bio, int err) -{ - if (err) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - complete(bio->bi_private); -} - /* * hfsplus_submit_bio - Perfrom block I/O * @sb: super block of volume for I/O @@ -53,7 +46,6 @@ static void hfsplus_end_io_sync(struct bio *bio, int err) int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf, void **data, int rw) { - DECLARE_COMPLETION_ONSTACK(wait); struct bio *bio; int ret = 0; u64 io_size; @@ -73,8 +65,6 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, bio = bio_alloc(GFP_NOIO, 1); bio->bi_sector = sector; bio->bi_bdev = sb->s_bdev; - bio->bi_end_io = hfsplus_end_io_sync; - bio->bi_private = &wait; if (!(rw & WRITE) && data) *data = (u8 *)buf + offset; @@ -93,12 +83,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, buf = (u8 *)buf + len; } - submit_bio(rw, bio); - wait_for_completion(&wait); - - if (!bio_flagged(bio, BIO_UPTODATE)) - ret = -EIO; - + ret = submit_bio_wait(rw, bio); out: bio_put(bio); return ret < 0 ? ret : 0; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 52032647dd4a..5fa344afb49a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -702,7 +702,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) read_lock(&journal->j_state_lock); #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { - printk(KERN_EMERG + printk(KERN_ERR "%s: error: j_commit_request=%d, tid=%d\n", __func__, journal->j_commit_request, tid); } @@ -718,10 +718,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) } read_unlock(&journal->j_state_lock); - if (unlikely(is_journal_aborted(journal))) { - printk(KERN_EMERG "journal commit I/O error\n"); + if (unlikely(is_journal_aborted(journal))) err = -EIO; - } return err; } @@ -1527,13 +1525,13 @@ static int journal_get_superblock(journal_t *journal) if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { /* Can't have checksum v1 and v2 on at the same time! */ - printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 " + printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 " "at the same time!\n"); goto out; } if (!jbd2_verify_csum_type(journal, sb)) { - printk(KERN_ERR "JBD: Unknown checksum type\n"); + printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } @@ -1541,7 +1539,7 @@ static int journal_get_superblock(journal_t *journal) if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD: Cannot load crc32c driver.\n"); + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); err = PTR_ERR(journal->j_chksum_driver); journal->j_chksum_driver = NULL; goto out; @@ -1550,7 +1548,7 @@ static int journal_get_superblock(journal_t *journal) /* Check superblock checksum */ if (!jbd2_superblock_csum_verify(journal, sb)) { - printk(KERN_ERR "JBD: journal checksum error\n"); + printk(KERN_ERR "JBD2: journal checksum error\n"); goto out; } @@ -1836,7 +1834,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD: Cannot load crc32c " + printk(KERN_ERR "JBD2: Cannot load crc32c " "driver.\n"); journal->j_chksum_driver = NULL; return 0; @@ -2645,7 +2643,7 @@ static void __exit journal_exit(void) #ifdef CONFIG_JBD2_DEBUG int n = atomic_read(&nr_journal_heads); if (n) - printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n); + printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n); #endif jbd2_remove_jbd_stats_proc_entry(); jbd2_journal_destroy_caches(); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 3929c50428b1..3b6bb19d60b1 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -594,7 +594,7 @@ static int do_one_pass(journal_t *journal, be32_to_cpu(tmp->h_sequence))) { brelse(obh); success = -EIO; - printk(KERN_ERR "JBD: Invalid " + printk(KERN_ERR "JBD2: Invalid " "checksum recovering " "block %llu in log\n", blocknr); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 7aa9a32573bb..8360674c85bc 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -932,7 +932,7 @@ repeat: jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!frozen_buffer) { - printk(KERN_EMERG + printk(KERN_ERR "%s: OOM for frozen_buffer\n", __func__); JBUFFER_TRACE(jh, "oom!"); @@ -1166,7 +1166,7 @@ repeat: if (!jh->b_committed_data) { committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!committed_data) { - printk(KERN_EMERG "%s: No memory for committed data\n", + printk(KERN_ERR "%s: No memory for committed data\n", __func__); err = -ENOMEM; goto out; @@ -1290,7 +1290,10 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) * once a transaction -bzzz */ jh->b_modified = 1; - J_ASSERT_JH(jh, handle->h_buffer_credits > 0); + if (handle->h_buffer_credits <= 0) { + ret = -ENOSPC; + goto out_unlock_bh; + } handle->h_buffer_credits--; } @@ -1305,7 +1308,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "fastpath"); if (unlikely(jh->b_transaction != journal->j_running_transaction)) { - printk(KERN_EMERG "JBD: %s: " + printk(KERN_ERR "JBD2: %s: " "jh->b_transaction (%llu, %p, %u) != " "journal->j_running_transaction (%p, %u)", journal->j_devname, @@ -1332,7 +1335,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "already on other transaction"); if (unlikely(jh->b_transaction != journal->j_committing_transaction)) { - printk(KERN_EMERG "JBD: %s: " + printk(KERN_ERR "JBD2: %s: " "jh->b_transaction (%llu, %p, %u) != " "journal->j_committing_transaction (%p, %u)", journal->j_devname, @@ -1345,7 +1348,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) ret = -EINVAL; } if (unlikely(jh->b_next_transaction != transaction)) { - printk(KERN_EMERG "JBD: %s: " + printk(KERN_ERR "JBD2: %s: " "jh->b_next_transaction (%llu, %p, %u) != " "transaction (%p, %u)", journal->j_devname, @@ -1373,7 +1376,6 @@ out_unlock_bh: jbd2_journal_put_journal_head(jh); out: JBUFFER_TRACE(jh, "exit"); - WARN_ON(ret); /* All errors are bugs, so dump the stack */ return ret; } diff --git a/fs/kernfs/Makefile b/fs/kernfs/Makefile new file mode 100644 index 000000000000..674337c76673 --- /dev/null +++ b/fs/kernfs/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the kernfs pseudo filesystem +# + +obj-y := mount.o inode.o dir.o file.o symlink.o diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c new file mode 100644 index 000000000000..5104cf5d25c5 --- /dev/null +++ b/fs/kernfs/dir.c @@ -0,0 +1,1073 @@ +/* + * fs/kernfs/dir.c - kernfs directory implementation + * + * Copyright (c) 2001-3 Patrick Mochel + * Copyright (c) 2007 SUSE Linux Products GmbH + * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/idr.h> +#include <linux/slab.h> +#include <linux/security.h> +#include <linux/hash.h> + +#include "kernfs-internal.h" + +DEFINE_MUTEX(kernfs_mutex); + +#define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) + +/** + * kernfs_name_hash + * @name: Null terminated string to hash + * @ns: Namespace tag to hash + * + * Returns 31 bit hash of ns + name (so it fits in an off_t ) + */ +static unsigned int kernfs_name_hash(const char *name, const void *ns) +{ + unsigned long hash = init_name_hash(); + unsigned int len = strlen(name); + while (len--) + hash = partial_name_hash(*name++, hash); + hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31)); + hash &= 0x7fffffffU; + /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ + if (hash < 1) + hash += 2; + if (hash >= INT_MAX) + hash = INT_MAX - 1; + return hash; +} + +static int kernfs_name_compare(unsigned int hash, const char *name, + const void *ns, const struct kernfs_node *kn) +{ + if (hash != kn->hash) + return hash - kn->hash; + if (ns != kn->ns) + return ns - kn->ns; + return strcmp(name, kn->name); +} + +static int kernfs_sd_compare(const struct kernfs_node *left, + const struct kernfs_node *right) +{ + return kernfs_name_compare(left->hash, left->name, left->ns, right); +} + +/** + * kernfs_link_sibling - link kernfs_node into sibling rbtree + * @kn: kernfs_node of interest + * + * Link @kn into its sibling rbtree which starts from + * @kn->parent->dir.children. + * + * Locking: + * mutex_lock(kernfs_mutex) + * + * RETURNS: + * 0 on susccess -EEXIST on failure. + */ +static int kernfs_link_sibling(struct kernfs_node *kn) +{ + struct rb_node **node = &kn->parent->dir.children.rb_node; + struct rb_node *parent = NULL; + + if (kernfs_type(kn) == KERNFS_DIR) + kn->parent->dir.subdirs++; + + while (*node) { + struct kernfs_node *pos; + int result; + + pos = rb_to_kn(*node); + parent = *node; + result = kernfs_sd_compare(kn, pos); + if (result < 0) + node = &pos->rb.rb_left; + else if (result > 0) + node = &pos->rb.rb_right; + else + return -EEXIST; + } + /* add new node and rebalance the tree */ + rb_link_node(&kn->rb, parent, node); + rb_insert_color(&kn->rb, &kn->parent->dir.children); + return 0; +} + +/** + * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree + * @kn: kernfs_node of interest + * + * Unlink @kn from its sibling rbtree which starts from + * kn->parent->dir.children. + * + * Locking: + * mutex_lock(kernfs_mutex) + */ +static void kernfs_unlink_sibling(struct kernfs_node *kn) +{ + if (kernfs_type(kn) == KERNFS_DIR) + kn->parent->dir.subdirs--; + + rb_erase(&kn->rb, &kn->parent->dir.children); +} + +/** + * kernfs_get_active - get an active reference to kernfs_node + * @kn: kernfs_node to get an active reference to + * + * Get an active reference of @kn. This function is noop if @kn + * is NULL. + * + * RETURNS: + * Pointer to @kn on success, NULL on failure. + */ +struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) +{ + if (unlikely(!kn)) + return NULL; + + if (!atomic_inc_unless_negative(&kn->active)) + return NULL; + + if (kn->flags & KERNFS_LOCKDEP) + rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_); + return kn; +} + +/** + * kernfs_put_active - put an active reference to kernfs_node + * @kn: kernfs_node to put an active reference to + * + * Put an active reference to @kn. This function is noop if @kn + * is NULL. + */ +void kernfs_put_active(struct kernfs_node *kn) +{ + int v; + + if (unlikely(!kn)) + return; + + if (kn->flags & KERNFS_LOCKDEP) + rwsem_release(&kn->dep_map, 1, _RET_IP_); + v = atomic_dec_return(&kn->active); + if (likely(v != KN_DEACTIVATED_BIAS)) + return; + + /* + * atomic_dec_return() is a mb(), we'll always see the updated + * kn->u.completion. + */ + complete(kn->u.completion); +} + +/** + * kernfs_deactivate - deactivate kernfs_node + * @kn: kernfs_node to deactivate + * + * Deny new active references and drain existing ones. + */ +static void kernfs_deactivate(struct kernfs_node *kn) +{ + DECLARE_COMPLETION_ONSTACK(wait); + int v; + + BUG_ON(!(kn->flags & KERNFS_REMOVED)); + + if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF)) + return; + + kn->u.completion = (void *)&wait; + + rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); + /* atomic_add_return() is a mb(), put_active() will always see + * the updated kn->u.completion. + */ + v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active); + + if (v != KN_DEACTIVATED_BIAS) { + lock_contended(&kn->dep_map, _RET_IP_); + wait_for_completion(&wait); + } + + lock_acquired(&kn->dep_map, _RET_IP_); + rwsem_release(&kn->dep_map, 1, _RET_IP_); +} + +/** + * kernfs_get - get a reference count on a kernfs_node + * @kn: the target kernfs_node + */ +void kernfs_get(struct kernfs_node *kn) +{ + if (kn) { + WARN_ON(!atomic_read(&kn->count)); + atomic_inc(&kn->count); + } +} +EXPORT_SYMBOL_GPL(kernfs_get); + +/** + * kernfs_put - put a reference count on a kernfs_node + * @kn: the target kernfs_node + * + * Put a reference count of @kn and destroy it if it reached zero. + */ +void kernfs_put(struct kernfs_node *kn) +{ + struct kernfs_node *parent; + struct kernfs_root *root; + + if (!kn || !atomic_dec_and_test(&kn->count)) + return; + root = kernfs_root(kn); + repeat: + /* Moving/renaming is always done while holding reference. + * kn->parent won't change beneath us. + */ + parent = kn->parent; + + WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n", + parent ? parent->name : "", kn->name); + + if (kernfs_type(kn) == KERNFS_LINK) + kernfs_put(kn->symlink.target_kn); + if (!(kn->flags & KERNFS_STATIC_NAME)) + kfree(kn->name); + if (kn->iattr) { + if (kn->iattr->ia_secdata) + security_release_secctx(kn->iattr->ia_secdata, + kn->iattr->ia_secdata_len); + simple_xattrs_free(&kn->iattr->xattrs); + } + kfree(kn->iattr); + ida_simple_remove(&root->ino_ida, kn->ino); + kmem_cache_free(kernfs_node_cache, kn); + + kn = parent; + if (kn) { + if (atomic_dec_and_test(&kn->count)) + goto repeat; + } else { + /* just released the root kn, free @root too */ + ida_destroy(&root->ino_ida); + kfree(root); + } +} +EXPORT_SYMBOL_GPL(kernfs_put); + +static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct kernfs_node *kn; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + /* Always perform fresh lookup for negatives */ + if (!dentry->d_inode) + goto out_bad_unlocked; + + kn = dentry->d_fsdata; + mutex_lock(&kernfs_mutex); + + /* The kernfs node has been deleted */ + if (kn->flags & KERNFS_REMOVED) + goto out_bad; + + /* The kernfs node has been moved? */ + if (dentry->d_parent->d_fsdata != kn->parent) + goto out_bad; + + /* The kernfs node has been renamed */ + if (strcmp(dentry->d_name.name, kn->name) != 0) + goto out_bad; + + /* The kernfs node has been moved to a different namespace */ + if (kn->parent && kernfs_ns_enabled(kn->parent) && + kernfs_info(dentry->d_sb)->ns != kn->ns) + goto out_bad; + + mutex_unlock(&kernfs_mutex); +out_valid: + return 1; +out_bad: + mutex_unlock(&kernfs_mutex); +out_bad_unlocked: + /* + * @dentry doesn't match the underlying kernfs node, drop the + * dentry and force lookup. If we have submounts we must allow the + * vfs caches to lie about the state of the filesystem to prevent + * leaks and other nasty things, so use check_submounts_and_drop() + * instead of d_drop(). + */ + if (check_submounts_and_drop(dentry) != 0) + goto out_valid; + + return 0; +} + +static void kernfs_dop_release(struct dentry *dentry) +{ + kernfs_put(dentry->d_fsdata); +} + +const struct dentry_operations kernfs_dops = { + .d_revalidate = kernfs_dop_revalidate, + .d_release = kernfs_dop_release, +}; + +static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, + const char *name, umode_t mode, + unsigned flags) +{ + char *dup_name = NULL; + struct kernfs_node *kn; + int ret; + + if (!(flags & KERNFS_STATIC_NAME)) { + name = dup_name = kstrdup(name, GFP_KERNEL); + if (!name) + return NULL; + } + + kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL); + if (!kn) + goto err_out1; + + ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL); + if (ret < 0) + goto err_out2; + kn->ino = ret; + + atomic_set(&kn->count, 1); + atomic_set(&kn->active, 0); + + kn->name = name; + kn->mode = mode; + kn->flags = flags | KERNFS_REMOVED; + + return kn; + + err_out2: + kmem_cache_free(kernfs_node_cache, kn); + err_out1: + kfree(dup_name); + return NULL; +} + +struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, + const char *name, umode_t mode, + unsigned flags) +{ + struct kernfs_node *kn; + + kn = __kernfs_new_node(kernfs_root(parent), name, mode, flags); + if (kn) { + kernfs_get(parent); + kn->parent = parent; + } + return kn; +} + +/** + * kernfs_addrm_start - prepare for kernfs_node add/remove + * @acxt: pointer to kernfs_addrm_cxt to be used + * + * This function is called when the caller is about to add or remove + * kernfs_node. This function acquires kernfs_mutex. @acxt is used + * to keep and pass context to other addrm functions. + * + * LOCKING: + * Kernel thread context (may sleep). kernfs_mutex is locked on + * return. + */ +void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt) + __acquires(kernfs_mutex) +{ + memset(acxt, 0, sizeof(*acxt)); + + mutex_lock(&kernfs_mutex); +} + +/** + * kernfs_add_one - add kernfs_node to parent without warning + * @acxt: addrm context to use + * @kn: kernfs_node to be added + * + * The caller must already have initialized @kn->parent. This + * function increments nlink of the parent's inode if @kn is a + * directory and link into the children list of the parent. + * + * This function should be called between calls to + * kernfs_addrm_start() and kernfs_addrm_finish() and should be passed + * the same @acxt as passed to kernfs_addrm_start(). + * + * LOCKING: + * Determined by kernfs_addrm_start(). + * + * RETURNS: + * 0 on success, -EEXIST if entry with the given name already + * exists. + */ +int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn) +{ + struct kernfs_node *parent = kn->parent; + bool has_ns = kernfs_ns_enabled(parent); + struct kernfs_iattrs *ps_iattr; + int ret; + + if (has_ns != (bool)kn->ns) { + WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", + has_ns ? "required" : "invalid", parent->name, kn->name); + return -EINVAL; + } + + if (kernfs_type(parent) != KERNFS_DIR) + return -EINVAL; + + if (parent->flags & KERNFS_REMOVED) + return -ENOENT; + + kn->hash = kernfs_name_hash(kn->name, kn->ns); + + ret = kernfs_link_sibling(kn); + if (ret) + return ret; + + /* Update timestamps on the parent */ + ps_iattr = parent->iattr; + if (ps_iattr) { + struct iattr *ps_iattrs = &ps_iattr->ia_iattr; + ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; + } + + /* Mark the entry added into directory tree */ + kn->flags &= ~KERNFS_REMOVED; + + return 0; +} + +/** + * kernfs_remove_one - remove kernfs_node from parent + * @acxt: addrm context to use + * @kn: kernfs_node to be removed + * + * Mark @kn removed and drop nlink of parent inode if @kn is a + * directory. @kn is unlinked from the children list. + * + * This function should be called between calls to + * kernfs_addrm_start() and kernfs_addrm_finish() and should be + * passed the same @acxt as passed to kernfs_addrm_start(). + * + * LOCKING: + * Determined by kernfs_addrm_start(). + */ +static void kernfs_remove_one(struct kernfs_addrm_cxt *acxt, + struct kernfs_node *kn) +{ + struct kernfs_iattrs *ps_iattr; + + /* + * Removal can be called multiple times on the same node. Only the + * first invocation is effective and puts the base ref. + */ + if (kn->flags & KERNFS_REMOVED) + return; + + if (kn->parent) { + kernfs_unlink_sibling(kn); + + /* Update timestamps on the parent */ + ps_iattr = kn->parent->iattr; + if (ps_iattr) { + ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME; + ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME; + } + } + + kn->flags |= KERNFS_REMOVED; + kn->u.removed_list = acxt->removed; + acxt->removed = kn; +} + +/** + * kernfs_addrm_finish - finish up kernfs_node add/remove + * @acxt: addrm context to finish up + * + * Finish up kernfs_node add/remove. Resources acquired by + * kernfs_addrm_start() are released and removed kernfs_nodes are + * cleaned up. + * + * LOCKING: + * kernfs_mutex is released. + */ +void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt) + __releases(kernfs_mutex) +{ + /* release resources acquired by kernfs_addrm_start() */ + mutex_unlock(&kernfs_mutex); + + /* kill removed kernfs_nodes */ + while (acxt->removed) { + struct kernfs_node *kn = acxt->removed; + + acxt->removed = kn->u.removed_list; + + kernfs_deactivate(kn); + kernfs_unmap_bin_file(kn); + kernfs_put(kn); + } +} + +/** + * kernfs_find_ns - find kernfs_node with the given name + * @parent: kernfs_node to search under + * @name: name to look for + * @ns: the namespace tag to use + * + * Look for kernfs_node with name @name under @parent. Returns pointer to + * the found kernfs_node on success, %NULL on failure. + */ +static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, + const unsigned char *name, + const void *ns) +{ + struct rb_node *node = parent->dir.children.rb_node; + bool has_ns = kernfs_ns_enabled(parent); + unsigned int hash; + + lockdep_assert_held(&kernfs_mutex); + + if (has_ns != (bool)ns) { + WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", + has_ns ? "required" : "invalid", parent->name, name); + return NULL; + } + + hash = kernfs_name_hash(name, ns); + while (node) { + struct kernfs_node *kn; + int result; + + kn = rb_to_kn(node); + result = kernfs_name_compare(hash, name, ns, kn); + if (result < 0) + node = node->rb_left; + else if (result > 0) + node = node->rb_right; + else + return kn; + } + return NULL; +} + +/** + * kernfs_find_and_get_ns - find and get kernfs_node with the given name + * @parent: kernfs_node to search under + * @name: name to look for + * @ns: the namespace tag to use + * + * Look for kernfs_node with name @name under @parent and get a reference + * if found. This function may sleep and returns pointer to the found + * kernfs_node on success, %NULL on failure. + */ +struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, + const char *name, const void *ns) +{ + struct kernfs_node *kn; + + mutex_lock(&kernfs_mutex); + kn = kernfs_find_ns(parent, name, ns); + kernfs_get(kn); + mutex_unlock(&kernfs_mutex); + + return kn; +} +EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); + +/** + * kernfs_create_root - create a new kernfs hierarchy + * @kdops: optional directory syscall operations for the hierarchy + * @priv: opaque data associated with the new directory + * + * Returns the root of the new hierarchy on success, ERR_PTR() value on + * failure. + */ +struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv) +{ + struct kernfs_root *root; + struct kernfs_node *kn; + + root = kzalloc(sizeof(*root), GFP_KERNEL); + if (!root) + return ERR_PTR(-ENOMEM); + + ida_init(&root->ino_ida); + + kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO, + KERNFS_DIR); + if (!kn) { + ida_destroy(&root->ino_ida); + kfree(root); + return ERR_PTR(-ENOMEM); + } + + kn->flags &= ~KERNFS_REMOVED; + kn->priv = priv; + kn->dir.root = root; + + root->dir_ops = kdops; + root->kn = kn; + + return root; +} + +/** + * kernfs_destroy_root - destroy a kernfs hierarchy + * @root: root of the hierarchy to destroy + * + * Destroy the hierarchy anchored at @root by removing all existing + * directories and destroying @root. + */ +void kernfs_destroy_root(struct kernfs_root *root) +{ + kernfs_remove(root->kn); /* will also free @root */ +} + +/** + * kernfs_create_dir_ns - create a directory + * @parent: parent in which to create a new directory + * @name: name of the new directory + * @mode: mode of the new directory + * @priv: opaque data associated with the new directory + * @ns: optional namespace tag of the directory + * + * Returns the created node on success, ERR_PTR() value on failure. + */ +struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, + const char *name, umode_t mode, + void *priv, const void *ns) +{ + struct kernfs_addrm_cxt acxt; + struct kernfs_node *kn; + int rc; + + /* allocate */ + kn = kernfs_new_node(parent, name, mode | S_IFDIR, KERNFS_DIR); + if (!kn) + return ERR_PTR(-ENOMEM); + + kn->dir.root = parent->dir.root; + kn->ns = ns; + kn->priv = priv; + + /* link in */ + kernfs_addrm_start(&acxt); + rc = kernfs_add_one(&acxt, kn); + kernfs_addrm_finish(&acxt); + + if (!rc) + return kn; + + kernfs_put(kn); + return ERR_PTR(rc); +} + +static struct dentry *kernfs_iop_lookup(struct inode *dir, + struct dentry *dentry, + unsigned int flags) +{ + struct dentry *ret; + struct kernfs_node *parent = dentry->d_parent->d_fsdata; + struct kernfs_node *kn; + struct inode *inode; + const void *ns = NULL; + + mutex_lock(&kernfs_mutex); + + if (kernfs_ns_enabled(parent)) + ns = kernfs_info(dir->i_sb)->ns; + + kn = kernfs_find_ns(parent, dentry->d_name.name, ns); + + /* no such entry */ + if (!kn) { + ret = NULL; + goto out_unlock; + } + kernfs_get(kn); + dentry->d_fsdata = kn; + + /* attach dentry and inode */ + inode = kernfs_get_inode(dir->i_sb, kn); + if (!inode) { + ret = ERR_PTR(-ENOMEM); + goto out_unlock; + } + + /* instantiate and hash dentry */ + ret = d_materialise_unique(dentry, inode); + out_unlock: + mutex_unlock(&kernfs_mutex); + return ret; +} + +static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode) +{ + struct kernfs_node *parent = dir->i_private; + struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops; + + if (!kdops || !kdops->mkdir) + return -EPERM; + + return kdops->mkdir(parent, dentry->d_name.name, mode); +} + +static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops; + + if (!kdops || !kdops->rmdir) + return -EPERM; + + return kdops->rmdir(kn); +} + +static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct kernfs_node *kn = old_dentry->d_fsdata; + struct kernfs_node *new_parent = new_dir->i_private; + struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops; + + if (!kdops || !kdops->rename) + return -EPERM; + + return kdops->rename(kn, new_parent, new_dentry->d_name.name); +} + +const struct inode_operations kernfs_dir_iops = { + .lookup = kernfs_iop_lookup, + .permission = kernfs_iop_permission, + .setattr = kernfs_iop_setattr, + .getattr = kernfs_iop_getattr, + .setxattr = kernfs_iop_setxattr, + .removexattr = kernfs_iop_removexattr, + .getxattr = kernfs_iop_getxattr, + .listxattr = kernfs_iop_listxattr, + + .mkdir = kernfs_iop_mkdir, + .rmdir = kernfs_iop_rmdir, + .rename = kernfs_iop_rename, +}; + +static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos) +{ + struct kernfs_node *last; + + while (true) { + struct rb_node *rbn; + + last = pos; + + if (kernfs_type(pos) != KERNFS_DIR) + break; + + rbn = rb_first(&pos->dir.children); + if (!rbn) + break; + + pos = rb_to_kn(rbn); + } + + return last; +} + +/** + * kernfs_next_descendant_post - find the next descendant for post-order walk + * @pos: the current position (%NULL to initiate traversal) + * @root: kernfs_node whose descendants to walk + * + * Find the next descendant to visit for post-order traversal of @root's + * descendants. @root is included in the iteration and the last node to be + * visited. + */ +static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, + struct kernfs_node *root) +{ + struct rb_node *rbn; + + lockdep_assert_held(&kernfs_mutex); + + /* if first iteration, visit leftmost descendant which may be root */ + if (!pos) + return kernfs_leftmost_descendant(root); + + /* if we visited @root, we're done */ + if (pos == root) + return NULL; + + /* if there's an unvisited sibling, visit its leftmost descendant */ + rbn = rb_next(&pos->rb); + if (rbn) + return kernfs_leftmost_descendant(rb_to_kn(rbn)); + + /* no sibling left, visit parent */ + return pos->parent; +} + +static void __kernfs_remove(struct kernfs_addrm_cxt *acxt, + struct kernfs_node *kn) +{ + struct kernfs_node *pos, *next; + + if (!kn) + return; + + pr_debug("kernfs %s: removing\n", kn->name); + + next = NULL; + do { + pos = next; + next = kernfs_next_descendant_post(pos, kn); + if (pos) + kernfs_remove_one(acxt, pos); + } while (next); +} + +/** + * kernfs_remove - remove a kernfs_node recursively + * @kn: the kernfs_node to remove + * + * Remove @kn along with all its subdirectories and files. + */ +void kernfs_remove(struct kernfs_node *kn) +{ + struct kernfs_addrm_cxt acxt; + + kernfs_addrm_start(&acxt); + __kernfs_remove(&acxt, kn); + kernfs_addrm_finish(&acxt); +} + +/** + * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it + * @parent: parent of the target + * @name: name of the kernfs_node to remove + * @ns: namespace tag of the kernfs_node to remove + * + * Look for the kernfs_node with @name and @ns under @parent and remove it. + * Returns 0 on success, -ENOENT if such entry doesn't exist. + */ +int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, + const void *ns) +{ + struct kernfs_addrm_cxt acxt; + struct kernfs_node *kn; + + if (!parent) { + WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n", + name); + return -ENOENT; + } + + kernfs_addrm_start(&acxt); + + kn = kernfs_find_ns(parent, name, ns); + if (kn) + __kernfs_remove(&acxt, kn); + + kernfs_addrm_finish(&acxt); + + if (kn) + return 0; + else + return -ENOENT; +} + +/** + * kernfs_rename_ns - move and rename a kernfs_node + * @kn: target node + * @new_parent: new parent to put @sd under + * @new_name: new name + * @new_ns: new namespace tag + */ +int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, + const char *new_name, const void *new_ns) +{ + int error; + + mutex_lock(&kernfs_mutex); + + error = -ENOENT; + if ((kn->flags | new_parent->flags) & KERNFS_REMOVED) + goto out; + + error = 0; + if ((kn->parent == new_parent) && (kn->ns == new_ns) && + (strcmp(kn->name, new_name) == 0)) + goto out; /* nothing to rename */ + + error = -EEXIST; + if (kernfs_find_ns(new_parent, new_name, new_ns)) + goto out; + + /* rename kernfs_node */ + if (strcmp(kn->name, new_name) != 0) { + error = -ENOMEM; + new_name = kstrdup(new_name, GFP_KERNEL); + if (!new_name) + goto out; + + if (kn->flags & KERNFS_STATIC_NAME) + kn->flags &= ~KERNFS_STATIC_NAME; + else + kfree(kn->name); + + kn->name = new_name; + } + + /* + * Move to the appropriate place in the appropriate directories rbtree. + */ + kernfs_unlink_sibling(kn); + kernfs_get(new_parent); + kernfs_put(kn->parent); + kn->ns = new_ns; + kn->hash = kernfs_name_hash(kn->name, kn->ns); + kn->parent = new_parent; + kernfs_link_sibling(kn); + + error = 0; + out: + mutex_unlock(&kernfs_mutex); + return error; +} + +/* Relationship between s_mode and the DT_xxx types */ +static inline unsigned char dt_type(struct kernfs_node *kn) +{ + return (kn->mode >> 12) & 15; +} + +static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) +{ + kernfs_put(filp->private_data); + return 0; +} + +static struct kernfs_node *kernfs_dir_pos(const void *ns, + struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) +{ + if (pos) { + int valid = !(pos->flags & KERNFS_REMOVED) && + pos->parent == parent && hash == pos->hash; + kernfs_put(pos); + if (!valid) + pos = NULL; + } + if (!pos && (hash > 1) && (hash < INT_MAX)) { + struct rb_node *node = parent->dir.children.rb_node; + while (node) { + pos = rb_to_kn(node); + + if (hash < pos->hash) + node = node->rb_left; + else if (hash > pos->hash) + node = node->rb_right; + else + break; + } + } + /* Skip over entries in the wrong namespace */ + while (pos && pos->ns != ns) { + struct rb_node *node = rb_next(&pos->rb); + if (!node) + pos = NULL; + else + pos = rb_to_kn(node); + } + return pos; +} + +static struct kernfs_node *kernfs_dir_next_pos(const void *ns, + struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) +{ + pos = kernfs_dir_pos(ns, parent, ino, pos); + if (pos) + do { + struct rb_node *node = rb_next(&pos->rb); + if (!node) + pos = NULL; + else + pos = rb_to_kn(node); + } while (pos && pos->ns != ns); + return pos; +} + +static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) +{ + struct dentry *dentry = file->f_path.dentry; + struct kernfs_node *parent = dentry->d_fsdata; + struct kernfs_node *pos = file->private_data; + const void *ns = NULL; + + if (!dir_emit_dots(file, ctx)) + return 0; + mutex_lock(&kernfs_mutex); + + if (kernfs_ns_enabled(parent)) + ns = kernfs_info(dentry->d_sb)->ns; + + for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); + pos; + pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { + const char *name = pos->name; + unsigned int type = dt_type(pos); + int len = strlen(name); + ino_t ino = pos->ino; + + ctx->pos = pos->hash; + file->private_data = pos; + kernfs_get(pos); + + mutex_unlock(&kernfs_mutex); + if (!dir_emit(ctx, name, len, ino, type)) + return 0; + mutex_lock(&kernfs_mutex); + } + mutex_unlock(&kernfs_mutex); + file->private_data = NULL; + ctx->pos = INT_MAX; + return 0; +} + +static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset, + int whence) +{ + struct inode *inode = file_inode(file); + loff_t ret; + + mutex_lock(&inode->i_mutex); + ret = generic_file_llseek(file, offset, whence); + mutex_unlock(&inode->i_mutex); + + return ret; +} + +const struct file_operations kernfs_dir_fops = { + .read = generic_read_dir, + .iterate = kernfs_fop_readdir, + .release = kernfs_dir_fop_release, + .llseek = kernfs_dir_fop_llseek, +}; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c new file mode 100644 index 000000000000..dbf397bfdff2 --- /dev/null +++ b/fs/kernfs/file.c @@ -0,0 +1,867 @@ +/* + * fs/kernfs/file.c - kernfs file implementation + * + * Copyright (c) 2001-3 Patrick Mochel + * Copyright (c) 2007 SUSE Linux Products GmbH + * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + */ + +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/poll.h> +#include <linux/pagemap.h> +#include <linux/sched.h> + +#include "kernfs-internal.h" + +/* + * There's one kernfs_open_file for each open file and one kernfs_open_node + * for each kernfs_node with one or more open files. + * + * kernfs_node->attr.open points to kernfs_open_node. attr.open is + * protected by kernfs_open_node_lock. + * + * filp->private_data points to seq_file whose ->private points to + * kernfs_open_file. kernfs_open_files are chained at + * kernfs_open_node->files, which is protected by kernfs_open_file_mutex. + */ +static DEFINE_SPINLOCK(kernfs_open_node_lock); +static DEFINE_MUTEX(kernfs_open_file_mutex); + +struct kernfs_open_node { + atomic_t refcnt; + atomic_t event; + wait_queue_head_t poll; + struct list_head files; /* goes through kernfs_open_file.list */ +}; + +static struct kernfs_open_file *kernfs_of(struct file *file) +{ + return ((struct seq_file *)file->private_data)->private; +} + +/* + * Determine the kernfs_ops for the given kernfs_node. This function must + * be called while holding an active reference. + */ +static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) +{ + if (kn->flags & KERNFS_LOCKDEP) + lockdep_assert_held(kn); + return kn->attr.ops; +} + +/* + * As kernfs_seq_stop() is also called after kernfs_seq_start() or + * kernfs_seq_next() failure, it needs to distinguish whether it's stopping + * a seq_file iteration which is fully initialized with an active reference + * or an aborted kernfs_seq_start() due to get_active failure. The + * position pointer is the only context for each seq_file iteration and + * thus the stop condition should be encoded in it. As the return value is + * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable + * choice to indicate get_active failure. + * + * Unfortunately, this is complicated due to the optional custom seq_file + * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() + * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or + * custom seq_file operations and thus can't decide whether put_active + * should be performed or not only on ERR_PTR(-ENODEV). + * + * This is worked around by factoring out the custom seq_stop() and + * put_active part into kernfs_seq_stop_active(), skipping it from + * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after + * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures + * that kernfs_seq_stop_active() is skipped only after get_active failure. + */ +static void kernfs_seq_stop_active(struct seq_file *sf, void *v) +{ + struct kernfs_open_file *of = sf->private; + const struct kernfs_ops *ops = kernfs_ops(of->kn); + + if (ops->seq_stop) + ops->seq_stop(sf, v); + kernfs_put_active(of->kn); +} + +static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) +{ + struct kernfs_open_file *of = sf->private; + const struct kernfs_ops *ops; + + /* + * @of->mutex nests outside active ref and is just to ensure that + * the ops aren't called concurrently for the same open file. + */ + mutex_lock(&of->mutex); + if (!kernfs_get_active(of->kn)) + return ERR_PTR(-ENODEV); + + ops = kernfs_ops(of->kn); + if (ops->seq_start) { + void *next = ops->seq_start(sf, ppos); + /* see the comment above kernfs_seq_stop_active() */ + if (next == ERR_PTR(-ENODEV)) + kernfs_seq_stop_active(sf, next); + return next; + } else { + /* + * The same behavior and code as single_open(). Returns + * !NULL if pos is at the beginning; otherwise, NULL. + */ + return NULL + !*ppos; + } +} + +static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) +{ + struct kernfs_open_file *of = sf->private; + const struct kernfs_ops *ops = kernfs_ops(of->kn); + + if (ops->seq_next) { + void *next = ops->seq_next(sf, v, ppos); + /* see the comment above kernfs_seq_stop_active() */ + if (next == ERR_PTR(-ENODEV)) + kernfs_seq_stop_active(sf, next); + return next; + } else { + /* + * The same behavior and code as single_open(), always + * terminate after the initial read. + */ + ++*ppos; + return NULL; + } +} + +static void kernfs_seq_stop(struct seq_file *sf, void *v) +{ + struct kernfs_open_file *of = sf->private; + + if (v != ERR_PTR(-ENODEV)) + kernfs_seq_stop_active(sf, v); + mutex_unlock(&of->mutex); +} + +static int kernfs_seq_show(struct seq_file *sf, void *v) +{ + struct kernfs_open_file *of = sf->private; + + of->event = atomic_read(&of->kn->attr.open->event); + + return of->kn->attr.ops->seq_show(sf, v); +} + +static const struct seq_operations kernfs_seq_ops = { + .start = kernfs_seq_start, + .next = kernfs_seq_next, + .stop = kernfs_seq_stop, + .show = kernfs_seq_show, +}; + +/* + * As reading a bin file can have side-effects, the exact offset and bytes + * specified in read(2) call should be passed to the read callback making + * it difficult to use seq_file. Implement simplistic custom buffering for + * bin files. + */ +static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, + char __user *user_buf, size_t count, + loff_t *ppos) +{ + ssize_t len = min_t(size_t, count, PAGE_SIZE); + const struct kernfs_ops *ops; + char *buf; + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* + * @of->mutex nests outside active ref and is just to ensure that + * the ops aren't called concurrently for the same open file. + */ + mutex_lock(&of->mutex); + if (!kernfs_get_active(of->kn)) { + len = -ENODEV; + mutex_unlock(&of->mutex); + goto out_free; + } + + ops = kernfs_ops(of->kn); + if (ops->read) + len = ops->read(of, buf, len, *ppos); + else + len = -EINVAL; + + kernfs_put_active(of->kn); + mutex_unlock(&of->mutex); + + if (len < 0) + goto out_free; + + if (copy_to_user(user_buf, buf, len)) { + len = -EFAULT; + goto out_free; + } + + *ppos += len; + + out_free: + kfree(buf); + return len; +} + +/** + * kernfs_fop_read - kernfs vfs read callback + * @file: file pointer + * @user_buf: data to write + * @count: number of bytes + * @ppos: starting offset + */ +static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct kernfs_open_file *of = kernfs_of(file); + + if (of->kn->flags & KERNFS_HAS_SEQ_SHOW) + return seq_read(file, user_buf, count, ppos); + else + return kernfs_file_direct_read(of, user_buf, count, ppos); +} + +/** + * kernfs_fop_write - kernfs vfs write callback + * @file: file pointer + * @user_buf: data to write + * @count: number of bytes + * @ppos: starting offset + * + * Copy data in from userland and pass it to the matching kernfs write + * operation. + * + * There is no easy way for us to know if userspace is only doing a partial + * write, so we don't support them. We expect the entire buffer to come on + * the first write. Hint: if you're writing a value, first read the file, + * modify only the the value you're changing, then write entire buffer + * back. + */ +static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct kernfs_open_file *of = kernfs_of(file); + ssize_t len = min_t(size_t, count, PAGE_SIZE); + const struct kernfs_ops *ops; + char *buf; + + buf = kmalloc(len + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, user_buf, len)) { + len = -EFAULT; + goto out_free; + } + buf[len] = '\0'; /* guarantee string termination */ + + /* + * @of->mutex nests outside active ref and is just to ensure that + * the ops aren't called concurrently for the same open file. + */ + mutex_lock(&of->mutex); + if (!kernfs_get_active(of->kn)) { + mutex_unlock(&of->mutex); + len = -ENODEV; + goto out_free; + } + + ops = kernfs_ops(of->kn); + if (ops->write) + len = ops->write(of, buf, len, *ppos); + else + len = -EINVAL; + + kernfs_put_active(of->kn); + mutex_unlock(&of->mutex); + + if (len > 0) + *ppos += len; +out_free: + kfree(buf); + return len; +} + +static void kernfs_vma_open(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + + if (!of->vm_ops) + return; + + if (!kernfs_get_active(of->kn)) + return; + + if (of->vm_ops->open) + of->vm_ops->open(vma); + + kernfs_put_active(of->kn); +} + +static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + int ret; + + if (!of->vm_ops) + return VM_FAULT_SIGBUS; + + if (!kernfs_get_active(of->kn)) + return VM_FAULT_SIGBUS; + + ret = VM_FAULT_SIGBUS; + if (of->vm_ops->fault) + ret = of->vm_ops->fault(vma, vmf); + + kernfs_put_active(of->kn); + return ret; +} + +static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + int ret; + + if (!of->vm_ops) + return VM_FAULT_SIGBUS; + + if (!kernfs_get_active(of->kn)) + return VM_FAULT_SIGBUS; + + ret = 0; + if (of->vm_ops->page_mkwrite) + ret = of->vm_ops->page_mkwrite(vma, vmf); + else + file_update_time(file); + + kernfs_put_active(of->kn); + return ret; +} + +static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + int ret; + + if (!of->vm_ops) + return -EINVAL; + + if (!kernfs_get_active(of->kn)) + return -EINVAL; + + ret = -EINVAL; + if (of->vm_ops->access) + ret = of->vm_ops->access(vma, addr, buf, len, write); + + kernfs_put_active(of->kn); + return ret; +} + +#ifdef CONFIG_NUMA +static int kernfs_vma_set_policy(struct vm_area_struct *vma, + struct mempolicy *new) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + int ret; + + if (!of->vm_ops) + return 0; + + if (!kernfs_get_active(of->kn)) + return -EINVAL; + + ret = 0; + if (of->vm_ops->set_policy) + ret = of->vm_ops->set_policy(vma, new); + + kernfs_put_active(of->kn); + return ret; +} + +static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + struct mempolicy *pol; + + if (!of->vm_ops) + return vma->vm_policy; + + if (!kernfs_get_active(of->kn)) + return vma->vm_policy; + + pol = vma->vm_policy; + if (of->vm_ops->get_policy) + pol = of->vm_ops->get_policy(vma, addr); + + kernfs_put_active(of->kn); + return pol; +} + +static int kernfs_vma_migrate(struct vm_area_struct *vma, + const nodemask_t *from, const nodemask_t *to, + unsigned long flags) +{ + struct file *file = vma->vm_file; + struct kernfs_open_file *of = kernfs_of(file); + int ret; + + if (!of->vm_ops) + return 0; + + if (!kernfs_get_active(of->kn)) + return 0; + + ret = 0; + if (of->vm_ops->migrate) + ret = of->vm_ops->migrate(vma, from, to, flags); + + kernfs_put_active(of->kn); + return ret; +} +#endif + +static const struct vm_operations_struct kernfs_vm_ops = { + .open = kernfs_vma_open, + .fault = kernfs_vma_fault, + .page_mkwrite = kernfs_vma_page_mkwrite, + .access = kernfs_vma_access, +#ifdef CONFIG_NUMA + .set_policy = kernfs_vma_set_policy, + .get_policy = kernfs_vma_get_policy, + .migrate = kernfs_vma_migrate, +#endif +}; + +static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct kernfs_open_file *of = kernfs_of(file); + const struct kernfs_ops *ops; + int rc; + + /* + * mmap path and of->mutex are prone to triggering spurious lockdep + * warnings and we don't want to add spurious locking dependency + * between the two. Check whether mmap is actually implemented + * without grabbing @of->mutex by testing HAS_MMAP flag. See the + * comment in kernfs_file_open() for more details. + */ + if (!(of->kn->flags & KERNFS_HAS_MMAP)) + return -ENODEV; + + mutex_lock(&of->mutex); + + rc = -ENODEV; + if (!kernfs_get_active(of->kn)) + goto out_unlock; + + ops = kernfs_ops(of->kn); + rc = ops->mmap(of, vma); + + /* + * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() + * to satisfy versions of X which crash if the mmap fails: that + * substitutes a new vm_file, and we don't then want bin_vm_ops. + */ + if (vma->vm_file != file) + goto out_put; + + rc = -EINVAL; + if (of->mmapped && of->vm_ops != vma->vm_ops) + goto out_put; + + /* + * It is not possible to successfully wrap close. + * So error if someone is trying to use close. + */ + rc = -EINVAL; + if (vma->vm_ops && vma->vm_ops->close) + goto out_put; + + rc = 0; + of->mmapped = 1; + of->vm_ops = vma->vm_ops; + vma->vm_ops = &kernfs_vm_ops; +out_put: + kernfs_put_active(of->kn); +out_unlock: + mutex_unlock(&of->mutex); + + return rc; +} + +/** + * kernfs_get_open_node - get or create kernfs_open_node + * @kn: target kernfs_node + * @of: kernfs_open_file for this instance of open + * + * If @kn->attr.open exists, increment its reference count; otherwise, + * create one. @of is chained to the files list. + * + * LOCKING: + * Kernel thread context (may sleep). + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static int kernfs_get_open_node(struct kernfs_node *kn, + struct kernfs_open_file *of) +{ + struct kernfs_open_node *on, *new_on = NULL; + + retry: + mutex_lock(&kernfs_open_file_mutex); + spin_lock_irq(&kernfs_open_node_lock); + + if (!kn->attr.open && new_on) { + kn->attr.open = new_on; + new_on = NULL; + } + + on = kn->attr.open; + if (on) { + atomic_inc(&on->refcnt); + list_add_tail(&of->list, &on->files); + } + + spin_unlock_irq(&kernfs_open_node_lock); + mutex_unlock(&kernfs_open_file_mutex); + + if (on) { + kfree(new_on); + return 0; + } + + /* not there, initialize a new one and retry */ + new_on = kmalloc(sizeof(*new_on), GFP_KERNEL); + if (!new_on) + return -ENOMEM; + + atomic_set(&new_on->refcnt, 0); + atomic_set(&new_on->event, 1); + init_waitqueue_head(&new_on->poll); + INIT_LIST_HEAD(&new_on->files); + goto retry; +} + +/** + * kernfs_put_open_node - put kernfs_open_node + * @kn: target kernfs_nodet + * @of: associated kernfs_open_file + * + * Put @kn->attr.open and unlink @of from the files list. If + * reference count reaches zero, disassociate and free it. + * + * LOCKING: + * None. + */ +static void kernfs_put_open_node(struct kernfs_node *kn, + struct kernfs_open_file *of) +{ + struct kernfs_open_node *on = kn->attr.open; + unsigned long flags; + + mutex_lock(&kernfs_open_file_mutex); + spin_lock_irqsave(&kernfs_open_node_lock, flags); + + if (of) + list_del(&of->list); + + if (atomic_dec_and_test(&on->refcnt)) + kn->attr.open = NULL; + else + on = NULL; + + spin_unlock_irqrestore(&kernfs_open_node_lock, flags); + mutex_unlock(&kernfs_open_file_mutex); + + kfree(on); +} + +static int kernfs_fop_open(struct inode *inode, struct file *file) +{ + struct kernfs_node *kn = file->f_path.dentry->d_fsdata; + const struct kernfs_ops *ops; + struct kernfs_open_file *of; + bool has_read, has_write, has_mmap; + int error = -EACCES; + + if (!kernfs_get_active(kn)) + return -ENODEV; + + ops = kernfs_ops(kn); + + has_read = ops->seq_show || ops->read || ops->mmap; + has_write = ops->write || ops->mmap; + has_mmap = ops->mmap; + + /* check perms and supported operations */ + if ((file->f_mode & FMODE_WRITE) && + (!(inode->i_mode & S_IWUGO) || !has_write)) + goto err_out; + + if ((file->f_mode & FMODE_READ) && + (!(inode->i_mode & S_IRUGO) || !has_read)) + goto err_out; + + /* allocate a kernfs_open_file for the file */ + error = -ENOMEM; + of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL); + if (!of) + goto err_out; + + /* + * The following is done to give a different lockdep key to + * @of->mutex for files which implement mmap. This is a rather + * crude way to avoid false positive lockdep warning around + * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and + * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under + * which mm->mmap_sem nests, while holding @of->mutex. As each + * open file has a separate mutex, it's okay as long as those don't + * happen on the same file. At this point, we can't easily give + * each file a separate locking class. Let's differentiate on + * whether the file has mmap or not for now. + * + * Both paths of the branch look the same. They're supposed to + * look that way and give @of->mutex different static lockdep keys. + */ + if (has_mmap) + mutex_init(&of->mutex); + else + mutex_init(&of->mutex); + + of->kn = kn; + of->file = file; + + /* + * Always instantiate seq_file even if read access doesn't use + * seq_file or is not requested. This unifies private data access + * and readable regular files are the vast majority anyway. + */ + if (ops->seq_show) + error = seq_open(file, &kernfs_seq_ops); + else + error = seq_open(file, NULL); + if (error) + goto err_free; + + ((struct seq_file *)file->private_data)->private = of; + + /* seq_file clears PWRITE unconditionally, restore it if WRITE */ + if (file->f_mode & FMODE_WRITE) + file->f_mode |= FMODE_PWRITE; + + /* make sure we have open node struct */ + error = kernfs_get_open_node(kn, of); + if (error) + goto err_close; + + /* open succeeded, put active references */ + kernfs_put_active(kn); + return 0; + +err_close: + seq_release(inode, file); +err_free: + kfree(of); +err_out: + kernfs_put_active(kn); + return error; +} + +static int kernfs_fop_release(struct inode *inode, struct file *filp) +{ + struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; + struct kernfs_open_file *of = kernfs_of(filp); + + kernfs_put_open_node(kn, of); + seq_release(inode, filp); + kfree(of); + + return 0; +} + +void kernfs_unmap_bin_file(struct kernfs_node *kn) +{ + struct kernfs_open_node *on; + struct kernfs_open_file *of; + + if (!(kn->flags & KERNFS_HAS_MMAP)) + return; + + spin_lock_irq(&kernfs_open_node_lock); + on = kn->attr.open; + if (on) + atomic_inc(&on->refcnt); + spin_unlock_irq(&kernfs_open_node_lock); + if (!on) + return; + + mutex_lock(&kernfs_open_file_mutex); + list_for_each_entry(of, &on->files, list) { + struct inode *inode = file_inode(of->file); + unmap_mapping_range(inode->i_mapping, 0, 0, 1); + } + mutex_unlock(&kernfs_open_file_mutex); + + kernfs_put_open_node(kn, NULL); +} + +/* + * Kernfs attribute files are pollable. The idea is that you read + * the content and then you use 'poll' or 'select' to wait for + * the content to change. When the content changes (assuming the + * manager for the kobject supports notification), poll will + * return POLLERR|POLLPRI, and select will return the fd whether + * it is waiting for read, write, or exceptions. + * Once poll/select indicates that the value has changed, you + * need to close and re-open the file, or seek to 0 and read again. + * Reminder: this only works for attributes which actively support + * it, and it is not possible to test an attribute from userspace + * to see if it supports poll (Neither 'poll' nor 'select' return + * an appropriate error code). When in doubt, set a suitable timeout value. + */ +static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait) +{ + struct kernfs_open_file *of = kernfs_of(filp); + struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; + struct kernfs_open_node *on = kn->attr.open; + + /* need parent for the kobj, grab both */ + if (!kernfs_get_active(kn)) + goto trigger; + + poll_wait(filp, &on->poll, wait); + + kernfs_put_active(kn); + + if (of->event != atomic_read(&on->event)) + goto trigger; + + return DEFAULT_POLLMASK; + + trigger: + return DEFAULT_POLLMASK|POLLERR|POLLPRI; +} + +/** + * kernfs_notify - notify a kernfs file + * @kn: file to notify + * + * Notify @kn such that poll(2) on @kn wakes up. + */ +void kernfs_notify(struct kernfs_node *kn) +{ + struct kernfs_open_node *on; + unsigned long flags; + + spin_lock_irqsave(&kernfs_open_node_lock, flags); + + if (!WARN_ON(kernfs_type(kn) != KERNFS_FILE)) { + on = kn->attr.open; + if (on) { + atomic_inc(&on->event); + wake_up_interruptible(&on->poll); + } + } + + spin_unlock_irqrestore(&kernfs_open_node_lock, flags); +} +EXPORT_SYMBOL_GPL(kernfs_notify); + +const struct file_operations kernfs_file_fops = { + .read = kernfs_fop_read, + .write = kernfs_fop_write, + .llseek = generic_file_llseek, + .mmap = kernfs_fop_mmap, + .open = kernfs_fop_open, + .release = kernfs_fop_release, + .poll = kernfs_fop_poll, +}; + +/** + * __kernfs_create_file - kernfs internal function to create a file + * @parent: directory to create the file in + * @name: name of the file + * @mode: mode of the file + * @size: size of the file + * @ops: kernfs operations for the file + * @priv: private data for the file + * @ns: optional namespace tag of the file + * @static_name: don't copy file name + * @key: lockdep key for the file's active_ref, %NULL to disable lockdep + * + * Returns the created node on success, ERR_PTR() value on error. + */ +struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, + const char *name, + umode_t mode, loff_t size, + const struct kernfs_ops *ops, + void *priv, const void *ns, + bool name_is_static, + struct lock_class_key *key) +{ + struct kernfs_addrm_cxt acxt; + struct kernfs_node *kn; + unsigned flags; + int rc; + + flags = KERNFS_FILE; + if (name_is_static) + flags |= KERNFS_STATIC_NAME; + + kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, flags); + if (!kn) + return ERR_PTR(-ENOMEM); + + kn->attr.ops = ops; + kn->attr.size = size; + kn->ns = ns; + kn->priv = priv; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (key) { + lockdep_init_map(&kn->dep_map, "s_active", key, 0); + kn->flags |= KERNFS_LOCKDEP; + } +#endif + + /* + * kn->attr.ops is accesible only while holding active ref. We + * need to know whether some ops are implemented outside active + * ref. Cache their existence in flags. + */ + if (ops->seq_show) + kn->flags |= KERNFS_HAS_SEQ_SHOW; + if (ops->mmap) + kn->flags |= KERNFS_HAS_MMAP; + + kernfs_addrm_start(&acxt); + rc = kernfs_add_one(&acxt, kn); + kernfs_addrm_finish(&acxt); + + if (rc) { + kernfs_put(kn); + return ERR_PTR(rc); + } + return kn; +} diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c new file mode 100644 index 000000000000..e55126f85bd2 --- /dev/null +++ b/fs/kernfs/inode.c @@ -0,0 +1,377 @@ +/* + * fs/kernfs/inode.c - kernfs inode implementation + * + * Copyright (c) 2001-3 Patrick Mochel + * Copyright (c) 2007 SUSE Linux Products GmbH + * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + */ + +#include <linux/pagemap.h> +#include <linux/backing-dev.h> +#include <linux/capability.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/xattr.h> +#include <linux/security.h> + +#include "kernfs-internal.h" + +static const struct address_space_operations kernfs_aops = { + .readpage = simple_readpage, + .write_begin = simple_write_begin, + .write_end = simple_write_end, +}; + +static struct backing_dev_info kernfs_bdi = { + .name = "kernfs", + .ra_pages = 0, /* No readahead */ + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, +}; + +static const struct inode_operations kernfs_iops = { + .permission = kernfs_iop_permission, + .setattr = kernfs_iop_setattr, + .getattr = kernfs_iop_getattr, + .setxattr = kernfs_iop_setxattr, + .removexattr = kernfs_iop_removexattr, + .getxattr = kernfs_iop_getxattr, + .listxattr = kernfs_iop_listxattr, +}; + +void __init kernfs_inode_init(void) +{ + if (bdi_init(&kernfs_bdi)) + panic("failed to init kernfs_bdi"); +} + +static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) +{ + struct iattr *iattrs; + + if (kn->iattr) + return kn->iattr; + + kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL); + if (!kn->iattr) + return NULL; + iattrs = &kn->iattr->ia_iattr; + + /* assign default attributes */ + iattrs->ia_mode = kn->mode; + iattrs->ia_uid = GLOBAL_ROOT_UID; + iattrs->ia_gid = GLOBAL_ROOT_GID; + iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME; + + simple_xattrs_init(&kn->iattr->xattrs); + + return kn->iattr; +} + +static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) +{ + struct kernfs_iattrs *attrs; + struct iattr *iattrs; + unsigned int ia_valid = iattr->ia_valid; + + attrs = kernfs_iattrs(kn); + if (!attrs) + return -ENOMEM; + + iattrs = &attrs->ia_iattr; + + if (ia_valid & ATTR_UID) + iattrs->ia_uid = iattr->ia_uid; + if (ia_valid & ATTR_GID) + iattrs->ia_gid = iattr->ia_gid; + if (ia_valid & ATTR_ATIME) + iattrs->ia_atime = iattr->ia_atime; + if (ia_valid & ATTR_MTIME) + iattrs->ia_mtime = iattr->ia_mtime; + if (ia_valid & ATTR_CTIME) + iattrs->ia_ctime = iattr->ia_ctime; + if (ia_valid & ATTR_MODE) { + umode_t mode = iattr->ia_mode; + iattrs->ia_mode = kn->mode = mode; + } + return 0; +} + +/** + * kernfs_setattr - set iattr on a node + * @kn: target node + * @iattr: iattr to set + * + * Returns 0 on success, -errno on failure. + */ +int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) +{ + int ret; + + mutex_lock(&kernfs_mutex); + ret = __kernfs_setattr(kn, iattr); + mutex_unlock(&kernfs_mutex); + return ret; +} + +int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = dentry->d_inode; + struct kernfs_node *kn = dentry->d_fsdata; + int error; + + if (!kn) + return -EINVAL; + + mutex_lock(&kernfs_mutex); + error = inode_change_ok(inode, iattr); + if (error) + goto out; + + error = __kernfs_setattr(kn, iattr); + if (error) + goto out; + + /* this ignores size changes */ + setattr_copy(inode, iattr); + +out: + mutex_unlock(&kernfs_mutex); + return error; +} + +static int kernfs_node_setsecdata(struct kernfs_node *kn, void **secdata, + u32 *secdata_len) +{ + struct kernfs_iattrs *attrs; + void *old_secdata; + size_t old_secdata_len; + + attrs = kernfs_iattrs(kn); + if (!attrs) + return -ENOMEM; + + old_secdata = attrs->ia_secdata; + old_secdata_len = attrs->ia_secdata_len; + + attrs->ia_secdata = *secdata; + attrs->ia_secdata_len = *secdata_len; + + *secdata = old_secdata; + *secdata_len = old_secdata_len; + return 0; +} + +int kernfs_iop_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_iattrs *attrs; + void *secdata; + int error; + u32 secdata_len = 0; + + attrs = kernfs_iattrs(kn); + if (!attrs) + return -ENOMEM; + + if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { + const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; + error = security_inode_setsecurity(dentry->d_inode, suffix, + value, size, flags); + if (error) + return error; + error = security_inode_getsecctx(dentry->d_inode, + &secdata, &secdata_len); + if (error) + return error; + + mutex_lock(&kernfs_mutex); + error = kernfs_node_setsecdata(kn, &secdata, &secdata_len); + mutex_unlock(&kernfs_mutex); + + if (secdata) + security_release_secctx(secdata, secdata_len); + return error; + } else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { + return simple_xattr_set(&attrs->xattrs, name, value, size, + flags); + } + + return -EINVAL; +} + +int kernfs_iop_removexattr(struct dentry *dentry, const char *name) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_iattrs *attrs; + + attrs = kernfs_iattrs(kn); + if (!attrs) + return -ENOMEM; + + return simple_xattr_remove(&attrs->xattrs, name); +} + +ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, + size_t size) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_iattrs *attrs; + + attrs = kernfs_iattrs(kn); + if (!attrs) + return -ENOMEM; + + return simple_xattr_get(&attrs->xattrs, name, buf, size); +} + +ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_iattrs *attrs; + + attrs = kernfs_iattrs(kn); + if (!attrs) + return -ENOMEM; + + return simple_xattr_list(&attrs->xattrs, buf, size); +} + +static inline void set_default_inode_attr(struct inode *inode, umode_t mode) +{ + inode->i_mode = mode; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; +} + +static inline void set_inode_attr(struct inode *inode, struct iattr *iattr) +{ + inode->i_uid = iattr->ia_uid; + inode->i_gid = iattr->ia_gid; + inode->i_atime = iattr->ia_atime; + inode->i_mtime = iattr->ia_mtime; + inode->i_ctime = iattr->ia_ctime; +} + +static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) +{ + struct kernfs_iattrs *attrs = kn->iattr; + + inode->i_mode = kn->mode; + if (attrs) { + /* + * kernfs_node has non-default attributes get them from + * persistent copy in kernfs_node. + */ + set_inode_attr(inode, &attrs->ia_iattr); + security_inode_notifysecctx(inode, attrs->ia_secdata, + attrs->ia_secdata_len); + } + + if (kernfs_type(kn) == KERNFS_DIR) + set_nlink(inode, kn->dir.subdirs + 2); +} + +int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct inode *inode = dentry->d_inode; + + mutex_lock(&kernfs_mutex); + kernfs_refresh_inode(kn, inode); + mutex_unlock(&kernfs_mutex); + + generic_fillattr(inode, stat); + return 0; +} + +static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) +{ + kernfs_get(kn); + inode->i_private = kn; + inode->i_mapping->a_ops = &kernfs_aops; + inode->i_mapping->backing_dev_info = &kernfs_bdi; + inode->i_op = &kernfs_iops; + + set_default_inode_attr(inode, kn->mode); + kernfs_refresh_inode(kn, inode); + + /* initialize inode according to type */ + switch (kernfs_type(kn)) { + case KERNFS_DIR: + inode->i_op = &kernfs_dir_iops; + inode->i_fop = &kernfs_dir_fops; + break; + case KERNFS_FILE: + inode->i_size = kn->attr.size; + inode->i_fop = &kernfs_file_fops; + break; + case KERNFS_LINK: + inode->i_op = &kernfs_symlink_iops; + break; + default: + BUG(); + } + + unlock_new_inode(inode); +} + +/** + * kernfs_get_inode - get inode for kernfs_node + * @sb: super block + * @kn: kernfs_node to allocate inode for + * + * Get inode for @kn. If such inode doesn't exist, a new inode is + * allocated and basics are initialized. New inode is returned + * locked. + * + * LOCKING: + * Kernel thread context (may sleep). + * + * RETURNS: + * Pointer to allocated inode on success, NULL on failure. + */ +struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) +{ + struct inode *inode; + + inode = iget_locked(sb, kn->ino); + if (inode && (inode->i_state & I_NEW)) + kernfs_init_inode(kn, inode); + + return inode; +} + +/* + * The kernfs_node serves as both an inode and a directory entry for + * kernfs. To prevent the kernfs inode numbers from being freed + * prematurely we take a reference to kernfs_node from the kernfs inode. A + * super_operations.evict_inode() implementation is needed to drop that + * reference upon inode destruction. + */ +void kernfs_evict_inode(struct inode *inode) +{ + struct kernfs_node *kn = inode->i_private; + + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + kernfs_put(kn); +} + +int kernfs_iop_permission(struct inode *inode, int mask) +{ + struct kernfs_node *kn; + + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + + kn = inode->i_private; + + mutex_lock(&kernfs_mutex); + kernfs_refresh_inode(kn, inode); + mutex_unlock(&kernfs_mutex); + + return generic_permission(inode, mask); +} diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h new file mode 100644 index 000000000000..eb536b76374a --- /dev/null +++ b/fs/kernfs/kernfs-internal.h @@ -0,0 +1,122 @@ +/* + * fs/kernfs/kernfs-internal.h - kernfs internal header file + * + * Copyright (c) 2001-3 Patrick Mochel + * Copyright (c) 2007 SUSE Linux Products GmbH + * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de> + * + * This file is released under the GPLv2. + */ + +#ifndef __KERNFS_INTERNAL_H +#define __KERNFS_INTERNAL_H + +#include <linux/lockdep.h> +#include <linux/fs.h> +#include <linux/mutex.h> +#include <linux/xattr.h> + +#include <linux/kernfs.h> + +struct kernfs_iattrs { + struct iattr ia_iattr; + void *ia_secdata; + u32 ia_secdata_len; + + struct simple_xattrs xattrs; +}; + +#define KN_DEACTIVATED_BIAS INT_MIN + +/* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */ + +/** + * kernfs_root - find out the kernfs_root a kernfs_node belongs to + * @kn: kernfs_node of interest + * + * Return the kernfs_root @kn belongs to. + */ +static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) +{ + /* if parent exists, it's always a dir; otherwise, @sd is a dir */ + if (kn->parent) + kn = kn->parent; + return kn->dir.root; +} + +/* + * Context structure to be used while adding/removing nodes. + */ +struct kernfs_addrm_cxt { + struct kernfs_node *removed; +}; + +/* + * mount.c + */ +struct kernfs_super_info { + /* + * The root associated with this super_block. Each super_block is + * identified by the root and ns it's associated with. + */ + struct kernfs_root *root; + + /* + * Each sb is associated with one namespace tag, currently the + * network namespace of the task which mounted this kernfs + * instance. If multiple tags become necessary, make the following + * an array and compare kernfs_node tag against every entry. + */ + const void *ns; +}; +#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) + +extern struct kmem_cache *kernfs_node_cache; + +/* + * inode.c + */ +struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); +void kernfs_evict_inode(struct inode *inode); +int kernfs_iop_permission(struct inode *inode, int mask); +int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr); +int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat); +int kernfs_iop_setxattr(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags); +int kernfs_iop_removexattr(struct dentry *dentry, const char *name); +ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, + size_t size); +ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); +void kernfs_inode_init(void); + +/* + * dir.c + */ +extern struct mutex kernfs_mutex; +extern const struct dentry_operations kernfs_dops; +extern const struct file_operations kernfs_dir_fops; +extern const struct inode_operations kernfs_dir_iops; + +struct kernfs_node *kernfs_get_active(struct kernfs_node *kn); +void kernfs_put_active(struct kernfs_node *kn); +void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt); +int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn); +void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt); +struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, + const char *name, umode_t mode, + unsigned flags); + +/* + * file.c + */ +extern const struct file_operations kernfs_file_fops; + +void kernfs_unmap_bin_file(struct kernfs_node *kn); + +/* + * symlink.c + */ +extern const struct inode_operations kernfs_symlink_iops; + +#endif /* __KERNFS_INTERNAL_H */ diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c new file mode 100644 index 000000000000..0d6ce895a9ee --- /dev/null +++ b/fs/kernfs/mount.c @@ -0,0 +1,165 @@ +/* + * fs/kernfs/mount.c - kernfs mount implementation + * + * Copyright (c) 2001-3 Patrick Mochel + * Copyright (c) 2007 SUSE Linux Products GmbH + * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + */ + +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/init.h> +#include <linux/magic.h> +#include <linux/slab.h> +#include <linux/pagemap.h> + +#include "kernfs-internal.h" + +struct kmem_cache *kernfs_node_cache; + +static const struct super_operations kernfs_sops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .evict_inode = kernfs_evict_inode, +}; + +static int kernfs_fill_super(struct super_block *sb) +{ + struct kernfs_super_info *info = kernfs_info(sb); + struct inode *inode; + struct dentry *root; + + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_magic = SYSFS_MAGIC; + sb->s_op = &kernfs_sops; + sb->s_time_gran = 1; + + /* get root inode, initialize and unlock it */ + mutex_lock(&kernfs_mutex); + inode = kernfs_get_inode(sb, info->root->kn); + mutex_unlock(&kernfs_mutex); + if (!inode) { + pr_debug("kernfs: could not get root inode\n"); + return -ENOMEM; + } + + /* instantiate and link root dentry */ + root = d_make_root(inode); + if (!root) { + pr_debug("%s: could not get root dentry!\n", __func__); + return -ENOMEM; + } + kernfs_get(info->root->kn); + root->d_fsdata = info->root->kn; + sb->s_root = root; + sb->s_d_op = &kernfs_dops; + return 0; +} + +static int kernfs_test_super(struct super_block *sb, void *data) +{ + struct kernfs_super_info *sb_info = kernfs_info(sb); + struct kernfs_super_info *info = data; + + return sb_info->root == info->root && sb_info->ns == info->ns; +} + +static int kernfs_set_super(struct super_block *sb, void *data) +{ + int error; + error = set_anon_super(sb, data); + if (!error) + sb->s_fs_info = data; + return error; +} + +/** + * kernfs_super_ns - determine the namespace tag of a kernfs super_block + * @sb: super_block of interest + * + * Return the namespace tag associated with kernfs super_block @sb. + */ +const void *kernfs_super_ns(struct super_block *sb) +{ + struct kernfs_super_info *info = kernfs_info(sb); + + return info->ns; +} + +/** + * kernfs_mount_ns - kernfs mount helper + * @fs_type: file_system_type of the fs being mounted + * @flags: mount flags specified for the mount + * @root: kernfs_root of the hierarchy being mounted + * @ns: optional namespace tag of the mount + * + * This is to be called from each kernfs user's file_system_type->mount() + * implementation, which should pass through the specified @fs_type and + * @flags, and specify the hierarchy and namespace tag to mount via @root + * and @ns, respectively. + * + * The return value can be passed to the vfs layer verbatim. + */ +struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, + struct kernfs_root *root, const void *ns) +{ + struct super_block *sb; + struct kernfs_super_info *info; + int error; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return ERR_PTR(-ENOMEM); + + info->root = root; + info->ns = ns; + + sb = sget(fs_type, kernfs_test_super, kernfs_set_super, flags, info); + if (IS_ERR(sb) || sb->s_fs_info != info) + kfree(info); + if (IS_ERR(sb)) + return ERR_CAST(sb); + if (!sb->s_root) { + error = kernfs_fill_super(sb); + if (error) { + deactivate_locked_super(sb); + return ERR_PTR(error); + } + sb->s_flags |= MS_ACTIVE; + } + + return dget(sb->s_root); +} + +/** + * kernfs_kill_sb - kill_sb for kernfs + * @sb: super_block being killed + * + * This can be used directly for file_system_type->kill_sb(). If a kernfs + * user needs extra cleanup, it can implement its own kill_sb() and call + * this function at the end. + */ +void kernfs_kill_sb(struct super_block *sb) +{ + struct kernfs_super_info *info = kernfs_info(sb); + struct kernfs_node *root_kn = sb->s_root->d_fsdata; + + /* + * Remove the superblock from fs_supers/s_instances + * so we can't find it, before freeing kernfs_super_info. + */ + kill_anon_super(sb); + kfree(info); + kernfs_put(root_kn); +} + +void __init kernfs_init(void) +{ + kernfs_node_cache = kmem_cache_create("kernfs_node_cache", + sizeof(struct kernfs_node), + 0, SLAB_PANIC, NULL); + kernfs_inode_init(); +} diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c new file mode 100644 index 000000000000..4d457055acb9 --- /dev/null +++ b/fs/kernfs/symlink.c @@ -0,0 +1,151 @@ +/* + * fs/kernfs/symlink.c - kernfs symlink implementation + * + * Copyright (c) 2001-3 Patrick Mochel + * Copyright (c) 2007 SUSE Linux Products GmbH + * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + */ + +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/namei.h> + +#include "kernfs-internal.h" + +/** + * kernfs_create_link - create a symlink + * @parent: directory to create the symlink in + * @name: name of the symlink + * @target: target node for the symlink to point to + * + * Returns the created node on success, ERR_PTR() value on error. + */ +struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, + const char *name, + struct kernfs_node *target) +{ + struct kernfs_node *kn; + struct kernfs_addrm_cxt acxt; + int error; + + kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK); + if (!kn) + return ERR_PTR(-ENOMEM); + + if (kernfs_ns_enabled(parent)) + kn->ns = target->ns; + kn->symlink.target_kn = target; + kernfs_get(target); /* ref owned by symlink */ + + kernfs_addrm_start(&acxt); + error = kernfs_add_one(&acxt, kn); + kernfs_addrm_finish(&acxt); + + if (!error) + return kn; + + kernfs_put(kn); + return ERR_PTR(error); +} + +static int kernfs_get_target_path(struct kernfs_node *parent, + struct kernfs_node *target, char *path) +{ + struct kernfs_node *base, *kn; + char *s = path; + int len = 0; + + /* go up to the root, stop at the base */ + base = parent; + while (base->parent) { + kn = target->parent; + while (kn->parent && base != kn) + kn = kn->parent; + + if (base == kn) + break; + + strcpy(s, "../"); + s += 3; + base = base->parent; + } + + /* determine end of target string for reverse fillup */ + kn = target; + while (kn->parent && kn != base) { + len += strlen(kn->name) + 1; + kn = kn->parent; + } + + /* check limits */ + if (len < 2) + return -EINVAL; + len--; + if ((s - path) + len > PATH_MAX) + return -ENAMETOOLONG; + + /* reverse fillup of target string from target to base */ + kn = target; + while (kn->parent && kn != base) { + int slen = strlen(kn->name); + + len -= slen; + strncpy(s + len, kn->name, slen); + if (len) + s[--len] = '/'; + + kn = kn->parent; + } + + return 0; +} + +static int kernfs_getlink(struct dentry *dentry, char *path) +{ + struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_node *parent = kn->parent; + struct kernfs_node *target = kn->symlink.target_kn; + int error; + + mutex_lock(&kernfs_mutex); + error = kernfs_get_target_path(parent, target, path); + mutex_unlock(&kernfs_mutex); + + return error; +} + +static void *kernfs_iop_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + int error = -ENOMEM; + unsigned long page = get_zeroed_page(GFP_KERNEL); + if (page) { + error = kernfs_getlink(dentry, (char *) page); + if (error < 0) + free_page((unsigned long)page); + } + nd_set_link(nd, error ? ERR_PTR(error) : (char *)page); + return NULL; +} + +static void kernfs_iop_put_link(struct dentry *dentry, struct nameidata *nd, + void *cookie) +{ + char *page = nd_get_link(nd); + if (!IS_ERR(page)) + free_page((unsigned long)page); +} + +const struct inode_operations kernfs_symlink_iops = { + .setxattr = kernfs_iop_setxattr, + .removexattr = kernfs_iop_removexattr, + .getxattr = kernfs_iop_getxattr, + .listxattr = kernfs_iop_listxattr, + .readlink = generic_readlink, + .follow_link = kernfs_iop_follow_link, + .put_link = kernfs_iop_put_link, + .setattr = kernfs_iop_setattr, + .getattr = kernfs_iop_getattr, + .permission = kernfs_iop_permission, +}; diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index 550475ca6a0e..0f95f0d0b313 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -14,16 +14,10 @@ #define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1)) -static void request_complete(struct bio *bio, int err) -{ - complete((struct completion *)bio->bi_private); -} - static int sync_request(struct page *page, struct block_device *bdev, int rw) { struct bio bio; struct bio_vec bio_vec; - struct completion complete; bio_init(&bio); bio.bi_max_vecs = 1; @@ -35,13 +29,8 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw) bio.bi_size = PAGE_SIZE; bio.bi_bdev = bdev; bio.bi_sector = page->index * (PAGE_SIZE >> 9); - init_completion(&complete); - bio.bi_private = &complete; - bio.bi_end_io = request_complete; - submit_bio(rw, &bio); - wait_for_completion(&complete); - return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO; + return submit_bio_wait(rw, &bio); } static int bdev_readpage(void *_sb, struct page *page) diff --git a/fs/namei.c b/fs/namei.c index 8f77a8cea289..3531deebad30 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -513,8 +513,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) if (!lockref_get_not_dead(&parent->d_lockref)) { nd->path.dentry = NULL; - rcu_read_unlock(); - return -ECHILD; + goto out; } /* @@ -1599,11 +1598,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) * do a "get_unaligned()" if this helps and is sufficiently * fast. * - * - Little-endian machines (so that we can generate the mask - * of low bytes efficiently). Again, we *could* do a byte - * swapping load on big-endian architectures if that is not - * expensive enough to make the optimization worthless. - * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. @@ -1647,7 +1641,7 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len) if (!len) goto done; } - mask = ~(~0ul << len*8); + mask = bytemask_from_count(len); hash += mask & a; done: return fold_hash(hash); diff --git a/fs/namespace.c b/fs/namespace.c index ac2ce8a766e1..22e536705c45 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2790,6 +2790,8 @@ void __init mnt_init(void) for (u = 0; u < HASH_SIZE; u++) INIT_LIST_HEAD(&mountpoint_hashtable[u]); + kernfs_init(); + err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", @@ -2886,7 +2888,7 @@ bool fs_fully_visible(struct file_system_type *type) struct inode *inode = child->mnt_mountpoint->d_inode; if (!S_ISDIR(inode->i_mode)) goto next; - if (inode->i_nlink != 2) + if (inode->i_nlink > 2) goto next; } visible = true; diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 8485978993e8..9838fb020473 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -36,6 +36,7 @@ #include <linux/nfs_fs.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include "../nfs4_fs.h" #include "../pnfs.h" #include "../netns.h" diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c index 9c3e117c3ed1..4d0161442565 100644 --- a/fs/nfs/blocklayout/extents.c +++ b/fs/nfs/blocklayout/extents.c @@ -44,7 +44,7 @@ static inline sector_t normalize(sector_t s, int base) { sector_t tmp = s; /* Since do_div modifies its argument */ - return s - do_div(tmp, base); + return s - sector_div(tmp, base); } static inline sector_t normalize_up(sector_t s, int base) diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index fc0f95ec7358..d25f10fb4926 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -46,7 +46,9 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, #include <linux/sunrpc/cache.h> #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" #include "dns_resolve.h" #include "cache_lib.h" #include "netns.h" diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 18ab2da4eeb6..00ad1c2b217d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -312,7 +312,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else -void inline nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label) { } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index bca6a3e3c49c..8b5cc04a8611 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -269,6 +269,21 @@ extern const u32 nfs41_maxgetdevinfo_overhead; extern struct rpc_procinfo nfs4_procedures[]; #endif +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); +static inline void nfs4_label_free(struct nfs4_label *label) +{ + if (label) { + kfree(label->label); + kfree(label); + } + return; +} +#else +static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } +static inline void nfs4_label_free(void *label) {} +#endif /* CONFIG_NFS_V4_SECURITY_LABEL */ + /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3ce79b04522e..5609edc742a0 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -9,6 +9,14 @@ #ifndef __LINUX_FS_NFS_NFS4_FS_H #define __LINUX_FS_NFS_NFS4_FS_H +#if defined(CONFIG_NFS_V4_2) +#define NFS4_MAX_MINOR_VERSION 2 +#elif defined(CONFIG_NFS_V4_1) +#define NFS4_MAX_MINOR_VERSION 1 +#else +#define NFS4_MAX_MINOR_VERSION 0 +#endif + #if IS_ENABLED(CONFIG_NFS_V4) #define NFS4_MAX_LOOP_ON_RECOVER (10) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 659990c0109e..15052b81df42 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2518,9 +2518,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data) calldata->roc_barrier); nfs_set_open_stateid(state, &calldata->res.stateid, 0); renew_lease(server, calldata->timestamp); - nfs4_close_clear_stateid_flags(state, - calldata->arg.fmode); break; + case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: @@ -2528,9 +2527,13 @@ static void nfs4_close_done(struct rpc_task *task, void *data) if (calldata->arg.fmode == 0) break; default: - if (nfs4_async_handle_error(task, server, state) == -EAGAIN) + if (nfs4_async_handle_error(task, server, state) == -EAGAIN) { rpc_restart_call_prepare(task); + goto out_release; + } } + nfs4_close_clear_stateid_flags(state, calldata->arg.fmode); +out_release: nfs_release_seqid(calldata->arg.seqid); nfs_refresh_inode(calldata->inode, calldata->res.fattr); dprintk("%s: done, ret = %d!\n", __func__, task->tk_status); @@ -4802,7 +4805,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, dprintk("%s ERROR %d, Reset session\n", __func__, task->tk_status); nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - goto restart_call; + goto wait_on_recovery; #endif /* CONFIG_NFS_V4_1 */ case -NFS4ERR_DELAY: nfs_inc_server_stats(server, NFSIOS_DELAY); @@ -4987,11 +4990,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status); switch (task->tk_status) { - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_EXPIRED: case 0: renew_lease(data->res.server, data->timestamp); break; + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + task->tk_status = 0; + break; default: if (nfs4_async_handle_error(task, data->res.server, NULL) == -EAGAIN) { @@ -7589,7 +7598,14 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) return; server = NFS_SERVER(lrp->args.inode); - if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { + switch (task->tk_status) { + default: + task->tk_status = 0; + case 0: + break; + case -NFS4ERR_DELAY: + if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN) + break; rpc_restart_call_prepare(task); return; } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 9186c7ce0b14..b6af150c96b8 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -132,6 +132,13 @@ nfsd_reply_cache_alloc(void) } static void +nfsd_reply_cache_unhash(struct svc_cacherep *rp) +{ + hlist_del_init(&rp->c_hash); + list_del_init(&rp->c_lru); +} + +static void nfsd_reply_cache_free_locked(struct svc_cacherep *rp) { if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) { @@ -417,7 +424,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru); if (nfsd_cache_entry_expired(rp) || num_drc_entries >= max_drc_entries) { - lru_put_end(rp); + nfsd_reply_cache_unhash(rp); prune_cache_entries(); goto search_cache; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 9f6b486b6c01..a1a191634abc 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1440,17 +1440,19 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nilfs_clear_logs(&sci->sc_segbufs); - err = nilfs_segctor_extend_segments(sci, nilfs, nadd); - if (unlikely(err)) - return err; - if (sci->sc_stage.flags & NILFS_CF_SUFREED) { err = nilfs_sufile_cancel_freev(nilfs->ns_sufile, sci->sc_freesegs, sci->sc_nfreesegs, NULL); WARN_ON(err); /* do not happen */ + sci->sc_stage.flags &= ~NILFS_CF_SUFREED; } + + err = nilfs_segctor_extend_segments(sci, nilfs, nadd); + if (unlikely(err)) + return err; + nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } diff --git a/fs/pipe.c b/fs/pipe.c index d2c45e14e6d8..0e0752ef2715 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -726,11 +726,25 @@ pipe_poll(struct file *filp, poll_table *wait) return mask; } +static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) +{ + int kill = 0; + + spin_lock(&inode->i_lock); + if (!--pipe->files) { + inode->i_pipe = NULL; + kill = 1; + } + spin_unlock(&inode->i_lock); + + if (kill) + free_pipe_info(pipe); +} + static int pipe_release(struct inode *inode, struct file *file) { - struct pipe_inode_info *pipe = inode->i_pipe; - int kill = 0; + struct pipe_inode_info *pipe = file->private_data; __pipe_lock(pipe); if (file->f_mode & FMODE_READ) @@ -743,17 +757,9 @@ pipe_release(struct inode *inode, struct file *file) kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } - spin_lock(&inode->i_lock); - if (!--pipe->files) { - inode->i_pipe = NULL; - kill = 1; - } - spin_unlock(&inode->i_lock); __pipe_unlock(pipe); - if (kill) - free_pipe_info(pipe); - + put_pipe_info(inode, pipe); return 0; } @@ -1014,7 +1020,6 @@ static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; - int kill = 0; int ret; filp->f_version = 0; @@ -1130,15 +1135,9 @@ err_wr: goto err; err: - spin_lock(&inode->i_lock); - if (!--pipe->files) { - inode->i_pipe = NULL; - kill = 1; - } - spin_unlock(&inode->i_lock); __pipe_unlock(pipe); - if (kill) - free_pipe_info(pipe); + + put_pipe_info(inode, pipe); return ret; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 28955d4b7218..124fc43c7090 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -292,16 +292,20 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, { struct proc_dir_entry *pde = PDE(file_inode(file)); unsigned long rv = -EIO; - unsigned long (*get_area)(struct file *, unsigned long, unsigned long, - unsigned long, unsigned long) = NULL; + if (use_pde(pde)) { + typeof(proc_reg_get_unmapped_area) *get_area; + + get_area = pde->proc_fops->get_unmapped_area; #ifdef CONFIG_MMU - get_area = current->mm->get_unmapped_area; + if (!get_area) + get_area = current->mm->get_unmapped_area; #endif - if (pde->proc_fops->get_unmapped_area) - get_area = pde->proc_fops->get_unmapped_area; + if (get_area) rv = get_area(file, orig_addr, len, pgoff, flags); + else + rv = orig_addr; unuse_pde(pde); } return rv; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index b8e93a40a5d3..78c3c2097787 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -443,8 +443,11 @@ int pstore_register(struct pstore_info *psi) pstore_get_records(0); kmsg_dump_register(&pstore_dumper); - pstore_register_console(); - pstore_register_ftrace(); + + if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) { + pstore_register_console(); + pstore_register_ftrace(); + } if (pstore_update_ms >= 0) { pstore_timer.expires = jiffies + diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index 2943b2bfae48..62a0de6632e1 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -84,6 +84,9 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) */ res = squashfs_read_cache(target_page, block, bsize, pages, page); + if (res < 0) + goto mark_errored; + goto out; } @@ -119,7 +122,7 @@ mark_errored: * dealt with by the caller */ for (i = 0; i < pages; i++) { - if (page[i] == target_page) + if (page[i] == NULL || page[i] == target_page) continue; flush_dcache_page(page[i]); SetPageError(page[i]); diff --git a/fs/sysfs/Makefile b/fs/sysfs/Makefile index 8876ac183373..6eff6e1205a5 100644 --- a/fs/sysfs/Makefile +++ b/fs/sysfs/Makefile @@ -2,4 +2,4 @@ # Makefile for the sysfs virtual filesystem # -obj-y := inode.o file.o dir.o symlink.o mount.o group.o +obj-y := file.o dir.o symlink.o mount.o group.o diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 5e73d6626e50..ee0d761c3179 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -13,465 +13,31 @@ #undef DEBUG #include <linux/fs.h> -#include <linux/mount.h> -#include <linux/module.h> #include <linux/kobject.h> -#include <linux/namei.h> -#include <linux/idr.h> -#include <linux/completion.h> -#include <linux/mutex.h> #include <linux/slab.h> -#include <linux/security.h> -#include <linux/hash.h> #include "sysfs.h" -DEFINE_MUTEX(sysfs_mutex); DEFINE_SPINLOCK(sysfs_symlink_target_lock); -#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb) - -static DEFINE_SPINLOCK(sysfs_ino_lock); -static DEFINE_IDA(sysfs_ino_ida); - -/** - * sysfs_name_hash - * @name: Null terminated string to hash - * @ns: Namespace tag to hash - * - * Returns 31 bit hash of ns + name (so it fits in an off_t ) - */ -static unsigned int sysfs_name_hash(const char *name, const void *ns) -{ - unsigned long hash = init_name_hash(); - unsigned int len = strlen(name); - while (len--) - hash = partial_name_hash(*name++, hash); - hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31)); - hash &= 0x7fffffffU; - /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ - if (hash < 1) - hash += 2; - if (hash >= INT_MAX) - hash = INT_MAX - 1; - return hash; -} - -static int sysfs_name_compare(unsigned int hash, const char *name, - const void *ns, const struct sysfs_dirent *sd) -{ - if (hash != sd->s_hash) - return hash - sd->s_hash; - if (ns != sd->s_ns) - return ns - sd->s_ns; - return strcmp(name, sd->s_name); -} - -static int sysfs_sd_compare(const struct sysfs_dirent *left, - const struct sysfs_dirent *right) -{ - return sysfs_name_compare(left->s_hash, left->s_name, left->s_ns, - right); -} - -/** - * sysfs_link_sibling - link sysfs_dirent into sibling rbtree - * @sd: sysfs_dirent of interest - * - * Link @sd into its sibling rbtree which starts from - * sd->s_parent->s_dir.children. - * - * Locking: - * mutex_lock(sysfs_mutex) - * - * RETURNS: - * 0 on susccess -EEXIST on failure. - */ -static int sysfs_link_sibling(struct sysfs_dirent *sd) -{ - struct rb_node **node = &sd->s_parent->s_dir.children.rb_node; - struct rb_node *parent = NULL; - - if (sysfs_type(sd) == SYSFS_DIR) - sd->s_parent->s_dir.subdirs++; - - while (*node) { - struct sysfs_dirent *pos; - int result; - - pos = to_sysfs_dirent(*node); - parent = *node; - result = sysfs_sd_compare(sd, pos); - if (result < 0) - node = &pos->s_rb.rb_left; - else if (result > 0) - node = &pos->s_rb.rb_right; - else - return -EEXIST; - } - /* add new node and rebalance the tree */ - rb_link_node(&sd->s_rb, parent, node); - rb_insert_color(&sd->s_rb, &sd->s_parent->s_dir.children); - return 0; -} - -/** - * sysfs_unlink_sibling - unlink sysfs_dirent from sibling rbtree - * @sd: sysfs_dirent of interest - * - * Unlink @sd from its sibling rbtree which starts from - * sd->s_parent->s_dir.children. - * - * Locking: - * mutex_lock(sysfs_mutex) - */ -static void sysfs_unlink_sibling(struct sysfs_dirent *sd) -{ - if (sysfs_type(sd) == SYSFS_DIR) - sd->s_parent->s_dir.subdirs--; - - rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children); -} - -/** - * sysfs_get_active - get an active reference to sysfs_dirent - * @sd: sysfs_dirent to get an active reference to - * - * Get an active reference of @sd. This function is noop if @sd - * is NULL. - * - * RETURNS: - * Pointer to @sd on success, NULL on failure. - */ -struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) -{ - if (unlikely(!sd)) - return NULL; - - if (!atomic_inc_unless_negative(&sd->s_active)) - return NULL; - - if (likely(!sysfs_ignore_lockdep(sd))) - rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); - return sd; -} - -/** - * sysfs_put_active - put an active reference to sysfs_dirent - * @sd: sysfs_dirent to put an active reference to - * - * Put an active reference to @sd. This function is noop if @sd - * is NULL. - */ -void sysfs_put_active(struct sysfs_dirent *sd) -{ - int v; - - if (unlikely(!sd)) - return; - - if (likely(!sysfs_ignore_lockdep(sd))) - rwsem_release(&sd->dep_map, 1, _RET_IP_); - v = atomic_dec_return(&sd->s_active); - if (likely(v != SD_DEACTIVATED_BIAS)) - return; - - /* atomic_dec_return() is a mb(), we'll always see the updated - * sd->u.completion. - */ - complete(sd->u.completion); -} - -/** - * sysfs_deactivate - deactivate sysfs_dirent - * @sd: sysfs_dirent to deactivate - * - * Deny new active references and drain existing ones. - */ -static void sysfs_deactivate(struct sysfs_dirent *sd) -{ - DECLARE_COMPLETION_ONSTACK(wait); - int v; - - BUG_ON(!(sd->s_flags & SYSFS_FLAG_REMOVED)); - - if (!(sysfs_type(sd) & SYSFS_ACTIVE_REF)) - return; - - sd->u.completion = (void *)&wait; - - rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_); - /* atomic_add_return() is a mb(), put_active() will always see - * the updated sd->u.completion. - */ - v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active); - - if (v != SD_DEACTIVATED_BIAS) { - lock_contended(&sd->dep_map, _RET_IP_); - wait_for_completion(&wait); - } - - lock_acquired(&sd->dep_map, _RET_IP_); - rwsem_release(&sd->dep_map, 1, _RET_IP_); -} - -static int sysfs_alloc_ino(unsigned int *pino) -{ - int ino, rc; - - retry: - spin_lock(&sysfs_ino_lock); - rc = ida_get_new_above(&sysfs_ino_ida, 2, &ino); - spin_unlock(&sysfs_ino_lock); - - if (rc == -EAGAIN) { - if (ida_pre_get(&sysfs_ino_ida, GFP_KERNEL)) - goto retry; - rc = -ENOMEM; - } - - *pino = ino; - return rc; -} - -static void sysfs_free_ino(unsigned int ino) -{ - spin_lock(&sysfs_ino_lock); - ida_remove(&sysfs_ino_ida, ino); - spin_unlock(&sysfs_ino_lock); -} - -void release_sysfs_dirent(struct sysfs_dirent *sd) -{ - struct sysfs_dirent *parent_sd; - - repeat: - /* Moving/renaming is always done while holding reference. - * sd->s_parent won't change beneath us. - */ - parent_sd = sd->s_parent; - - WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED), - "sysfs: free using entry: %s/%s\n", - parent_sd ? parent_sd->s_name : "", sd->s_name); - - if (sysfs_type(sd) == SYSFS_KOBJ_LINK) - sysfs_put(sd->s_symlink.target_sd); - if (sysfs_type(sd) & SYSFS_COPY_NAME) - kfree(sd->s_name); - if (sd->s_iattr && sd->s_iattr->ia_secdata) - security_release_secctx(sd->s_iattr->ia_secdata, - sd->s_iattr->ia_secdata_len); - kfree(sd->s_iattr); - sysfs_free_ino(sd->s_ino); - kmem_cache_free(sysfs_dir_cachep, sd); - - sd = parent_sd; - if (sd && atomic_dec_and_test(&sd->s_count)) - goto repeat; -} - -static int sysfs_dentry_delete(const struct dentry *dentry) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED)); -} - -static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags) -{ - struct sysfs_dirent *sd; - int type; - - if (flags & LOOKUP_RCU) - return -ECHILD; - - sd = dentry->d_fsdata; - mutex_lock(&sysfs_mutex); - - /* The sysfs dirent has been deleted */ - if (sd->s_flags & SYSFS_FLAG_REMOVED) - goto out_bad; - - /* The sysfs dirent has been moved? */ - if (dentry->d_parent->d_fsdata != sd->s_parent) - goto out_bad; - - /* The sysfs dirent has been renamed */ - if (strcmp(dentry->d_name.name, sd->s_name) != 0) - goto out_bad; - - /* The sysfs dirent has been moved to a different namespace */ - type = KOBJ_NS_TYPE_NONE; - if (sd->s_parent) { - type = sysfs_ns_type(sd->s_parent); - if (type != KOBJ_NS_TYPE_NONE && - sysfs_info(dentry->d_sb)->ns[type] != sd->s_ns) - goto out_bad; - } - - mutex_unlock(&sysfs_mutex); -out_valid: - return 1; -out_bad: - /* Remove the dentry from the dcache hashes. - * If this is a deleted dentry we use d_drop instead of d_delete - * so sysfs doesn't need to cope with negative dentries. - * - * If this is a dentry that has simply been renamed we - * use d_drop to remove it from the dcache lookup on its - * old parent. If this dentry persists later when a lookup - * is performed at its new name the dentry will be readded - * to the dcache hashes. - */ - mutex_unlock(&sysfs_mutex); - - /* If we have submounts we must allow the vfs caches - * to lie about the state of the filesystem to prevent - * leaks and other nasty things. - */ - if (check_submounts_and_drop(dentry) != 0) - goto out_valid; - - return 0; -} - -static void sysfs_dentry_release(struct dentry *dentry) -{ - sysfs_put(dentry->d_fsdata); -} - -const struct dentry_operations sysfs_dentry_ops = { - .d_revalidate = sysfs_dentry_revalidate, - .d_delete = sysfs_dentry_delete, - .d_release = sysfs_dentry_release, -}; - -struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type) -{ - char *dup_name = NULL; - struct sysfs_dirent *sd; - - if (type & SYSFS_COPY_NAME) { - name = dup_name = kstrdup(name, GFP_KERNEL); - if (!name) - return NULL; - } - - sd = kmem_cache_zalloc(sysfs_dir_cachep, GFP_KERNEL); - if (!sd) - goto err_out1; - - if (sysfs_alloc_ino(&sd->s_ino)) - goto err_out2; - - atomic_set(&sd->s_count, 1); - atomic_set(&sd->s_active, 0); - - sd->s_name = name; - sd->s_mode = mode; - sd->s_flags = type | SYSFS_FLAG_REMOVED; - - return sd; - - err_out2: - kmem_cache_free(sysfs_dir_cachep, sd); - err_out1: - kfree(dup_name); - return NULL; -} - -/** - * sysfs_addrm_start - prepare for sysfs_dirent add/remove - * @acxt: pointer to sysfs_addrm_cxt to be used - * - * This function is called when the caller is about to add or remove - * sysfs_dirent. This function acquires sysfs_mutex. @acxt is used - * to keep and pass context to other addrm functions. - * - * LOCKING: - * Kernel thread context (may sleep). sysfs_mutex is locked on - * return. - */ -void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt) - __acquires(sysfs_mutex) -{ - memset(acxt, 0, sizeof(*acxt)); - - mutex_lock(&sysfs_mutex); -} - -/** - * __sysfs_add_one - add sysfs_dirent to parent without warning - * @acxt: addrm context to use - * @sd: sysfs_dirent to be added - * @parent_sd: the parent sysfs_dirent to add @sd to - * - * Get @parent_sd and set @sd->s_parent to it and increment nlink of - * the parent inode if @sd is a directory and link into the children - * list of the parent. - * - * This function should be called between calls to - * sysfs_addrm_start() and sysfs_addrm_finish() and should be - * passed the same @acxt as passed to sysfs_addrm_start(). - * - * LOCKING: - * Determined by sysfs_addrm_start(). - * - * RETURNS: - * 0 on success, -EEXIST if entry with the given name already - * exists. - */ -int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd, - struct sysfs_dirent *parent_sd) -{ - struct sysfs_inode_attrs *ps_iattr; - int ret; - - if (!!sysfs_ns_type(parent_sd) != !!sd->s_ns) { - WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n", - sysfs_ns_type(parent_sd) ? "required" : "invalid", - parent_sd->s_name, sd->s_name); - return -EINVAL; - } - - sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns); - sd->s_parent = sysfs_get(parent_sd); - - ret = sysfs_link_sibling(sd); - if (ret) - return ret; - - /* Update timestamps on the parent */ - ps_iattr = parent_sd->s_iattr; - if (ps_iattr) { - struct iattr *ps_iattrs = &ps_iattr->ia_iattr; - ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; - } - - /* Mark the entry added into directory tree */ - sd->s_flags &= ~SYSFS_FLAG_REMOVED; - - return 0; -} - /** * sysfs_pathname - return full path to sysfs dirent - * @sd: sysfs_dirent whose path we want + * @kn: kernfs_node whose path we want * @path: caller allocated buffer of size PATH_MAX * * Gives the name "/" to the sysfs_root entry; any path returned * is relative to wherever sysfs is mounted. */ -static char *sysfs_pathname(struct sysfs_dirent *sd, char *path) +static char *sysfs_pathname(struct kernfs_node *kn, char *path) { - if (sd->s_parent) { - sysfs_pathname(sd->s_parent, path); + if (kn->parent) { + sysfs_pathname(kn->parent, path); strlcat(path, "/", PATH_MAX); } - strlcat(path, sd->s_name, PATH_MAX); + strlcat(path, kn->name, PATH_MAX); return path; } -void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name) +void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { char *path; @@ -489,445 +55,34 @@ void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name) } /** - * sysfs_add_one - add sysfs_dirent to parent - * @acxt: addrm context to use - * @sd: sysfs_dirent to be added - * @parent_sd: the parent sysfs_dirent to add @sd to - * - * Get @parent_sd and set @sd->s_parent to it and increment nlink of - * the parent inode if @sd is a directory and link into the children - * list of the parent. - * - * This function should be called between calls to - * sysfs_addrm_start() and sysfs_addrm_finish() and should be - * passed the same @acxt as passed to sysfs_addrm_start(). - * - * LOCKING: - * Determined by sysfs_addrm_start(). - * - * RETURNS: - * 0 on success, -EEXIST if entry with the given name already - * exists. - */ -int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd, - struct sysfs_dirent *parent_sd) -{ - int ret; - - ret = __sysfs_add_one(acxt, sd, parent_sd); - - if (ret == -EEXIST) - sysfs_warn_dup(parent_sd, sd->s_name); - return ret; -} - -/** - * sysfs_remove_one - remove sysfs_dirent from parent - * @acxt: addrm context to use - * @sd: sysfs_dirent to be removed - * - * Mark @sd removed and drop nlink of parent inode if @sd is a - * directory. @sd is unlinked from the children list. - * - * This function should be called between calls to - * sysfs_addrm_start() and sysfs_addrm_finish() and should be - * passed the same @acxt as passed to sysfs_addrm_start(). - * - * LOCKING: - * Determined by sysfs_addrm_start(). - */ -static void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, - struct sysfs_dirent *sd) -{ - struct sysfs_inode_attrs *ps_iattr; - - /* - * Removal can be called multiple times on the same node. Only the - * first invocation is effective and puts the base ref. - */ - if (sd->s_flags & SYSFS_FLAG_REMOVED) - return; - - sysfs_unlink_sibling(sd); - - /* Update timestamps on the parent */ - ps_iattr = sd->s_parent->s_iattr; - if (ps_iattr) { - struct iattr *ps_iattrs = &ps_iattr->ia_iattr; - ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; - } - - sd->s_flags |= SYSFS_FLAG_REMOVED; - sd->u.removed_list = acxt->removed; - acxt->removed = sd; -} - -/** - * sysfs_addrm_finish - finish up sysfs_dirent add/remove - * @acxt: addrm context to finish up - * - * Finish up sysfs_dirent add/remove. Resources acquired by - * sysfs_addrm_start() are released and removed sysfs_dirents are - * cleaned up. - * - * LOCKING: - * sysfs_mutex is released. - */ -void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt) - __releases(sysfs_mutex) -{ - /* release resources acquired by sysfs_addrm_start() */ - mutex_unlock(&sysfs_mutex); - - /* kill removed sysfs_dirents */ - while (acxt->removed) { - struct sysfs_dirent *sd = acxt->removed; - - acxt->removed = sd->u.removed_list; - - sysfs_deactivate(sd); - sysfs_unmap_bin_file(sd); - sysfs_put(sd); - } -} - -/** - * sysfs_find_dirent - find sysfs_dirent with the given name - * @parent_sd: sysfs_dirent to search under - * @name: name to look for - * @ns: the namespace tag to use - * - * Look for sysfs_dirent with name @name under @parent_sd. - * - * LOCKING: - * mutex_lock(sysfs_mutex) - * - * RETURNS: - * Pointer to sysfs_dirent if found, NULL if not. - */ -struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, - const unsigned char *name, - const void *ns) -{ - struct rb_node *node = parent_sd->s_dir.children.rb_node; - unsigned int hash; - - if (!!sysfs_ns_type(parent_sd) != !!ns) { - WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n", - sysfs_ns_type(parent_sd) ? "required" : "invalid", - parent_sd->s_name, name); - return NULL; - } - - hash = sysfs_name_hash(name, ns); - while (node) { - struct sysfs_dirent *sd; - int result; - - sd = to_sysfs_dirent(node); - result = sysfs_name_compare(hash, name, ns, sd); - if (result < 0) - node = node->rb_left; - else if (result > 0) - node = node->rb_right; - else - return sd; - } - return NULL; -} - -/** - * sysfs_get_dirent_ns - find and get sysfs_dirent with the given name - * @parent_sd: sysfs_dirent to search under - * @name: name to look for - * @ns: the namespace tag to use - * - * Look for sysfs_dirent with name @name under @parent_sd and get - * it if found. - * - * LOCKING: - * Kernel thread context (may sleep). Grabs sysfs_mutex. - * - * RETURNS: - * Pointer to sysfs_dirent if found, NULL if not. - */ -struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd, - const unsigned char *name, - const void *ns) -{ - struct sysfs_dirent *sd; - - mutex_lock(&sysfs_mutex); - sd = sysfs_find_dirent(parent_sd, name, ns); - sysfs_get(sd); - mutex_unlock(&sysfs_mutex); - - return sd; -} -EXPORT_SYMBOL_GPL(sysfs_get_dirent_ns); - -static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd, - enum kobj_ns_type type, - const char *name, const void *ns, - struct sysfs_dirent **p_sd) -{ - umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; - struct sysfs_addrm_cxt acxt; - struct sysfs_dirent *sd; - int rc; - - /* allocate */ - sd = sysfs_new_dirent(name, mode, SYSFS_DIR); - if (!sd) - return -ENOMEM; - - sd->s_flags |= (type << SYSFS_NS_TYPE_SHIFT); - sd->s_ns = ns; - sd->s_dir.kobj = kobj; - - /* link in */ - sysfs_addrm_start(&acxt); - rc = sysfs_add_one(&acxt, sd, parent_sd); - sysfs_addrm_finish(&acxt); - - if (rc == 0) - *p_sd = sd; - else - sysfs_put(sd); - - return rc; -} - -int sysfs_create_subdir(struct kobject *kobj, const char *name, - struct sysfs_dirent **p_sd) -{ - return create_dir(kobj, kobj->sd, - KOBJ_NS_TYPE_NONE, name, NULL, p_sd); -} - -/** - * sysfs_read_ns_type: return associated ns_type - * @kobj: the kobject being queried - * - * Each kobject can be tagged with exactly one namespace type - * (i.e. network or user). Return the ns_type associated with - * this object if any - */ -static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj) -{ - const struct kobj_ns_type_operations *ops; - enum kobj_ns_type type; - - ops = kobj_child_ns_ops(kobj); - if (!ops) - return KOBJ_NS_TYPE_NONE; - - type = ops->type; - BUG_ON(type <= KOBJ_NS_TYPE_NONE); - BUG_ON(type >= KOBJ_NS_TYPES); - BUG_ON(!kobj_ns_type_registered(type)); - - return type; -} - -/** * sysfs_create_dir_ns - create a directory for an object with a namespace tag * @kobj: object we're creating directory for * @ns: the namespace tag to use */ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { - enum kobj_ns_type type; - struct sysfs_dirent *parent_sd, *sd; - int error = 0; + struct kernfs_node *parent, *kn; BUG_ON(!kobj); if (kobj->parent) - parent_sd = kobj->parent->sd; + parent = kobj->parent->sd; else - parent_sd = &sysfs_root; + parent = sysfs_root_kn; - if (!parent_sd) + if (!parent) return -ENOENT; - type = sysfs_read_ns_type(kobj); - - error = create_dir(kobj, parent_sd, type, kobject_name(kobj), ns, &sd); - if (!error) - kobj->sd = sd; - return error; -} - -static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry, - unsigned int flags) -{ - struct dentry *ret = NULL; - struct dentry *parent = dentry->d_parent; - struct sysfs_dirent *parent_sd = parent->d_fsdata; - struct sysfs_dirent *sd; - struct inode *inode; - enum kobj_ns_type type; - const void *ns; - - mutex_lock(&sysfs_mutex); - - type = sysfs_ns_type(parent_sd); - ns = sysfs_info(dir->i_sb)->ns[type]; - - sd = sysfs_find_dirent(parent_sd, dentry->d_name.name, ns); - - /* no such entry */ - if (!sd) { - ret = ERR_PTR(-ENOENT); - goto out_unlock; - } - dentry->d_fsdata = sysfs_get(sd); - - /* attach dentry and inode */ - inode = sysfs_get_inode(dir->i_sb, sd); - if (!inode) { - ret = ERR_PTR(-ENOMEM); - goto out_unlock; - } - - /* instantiate and hash dentry */ - ret = d_materialise_unique(dentry, inode); - out_unlock: - mutex_unlock(&sysfs_mutex); - return ret; -} - -const struct inode_operations sysfs_dir_inode_operations = { - .lookup = sysfs_lookup, - .permission = sysfs_permission, - .setattr = sysfs_setattr, - .getattr = sysfs_getattr, - .setxattr = sysfs_setxattr, -}; - -static struct sysfs_dirent *sysfs_leftmost_descendant(struct sysfs_dirent *pos) -{ - struct sysfs_dirent *last; - - while (true) { - struct rb_node *rbn; - - last = pos; - - if (sysfs_type(pos) != SYSFS_DIR) - break; - - rbn = rb_first(&pos->s_dir.children); - if (!rbn) - break; - - pos = to_sysfs_dirent(rbn); - } - - return last; -} - -/** - * sysfs_next_descendant_post - find the next descendant for post-order walk - * @pos: the current position (%NULL to initiate traversal) - * @root: sysfs_dirent whose descendants to walk - * - * Find the next descendant to visit for post-order traversal of @root's - * descendants. @root is included in the iteration and the last node to be - * visited. - */ -static struct sysfs_dirent *sysfs_next_descendant_post(struct sysfs_dirent *pos, - struct sysfs_dirent *root) -{ - struct rb_node *rbn; - - lockdep_assert_held(&sysfs_mutex); - - /* if first iteration, visit leftmost descendant which may be root */ - if (!pos) - return sysfs_leftmost_descendant(root); - - /* if we visited @root, we're done */ - if (pos == root) - return NULL; - - /* if there's an unvisited sibling, visit its leftmost descendant */ - rbn = rb_next(&pos->s_rb); - if (rbn) - return sysfs_leftmost_descendant(to_sysfs_dirent(rbn)); - - /* no sibling left, visit parent */ - return pos->s_parent; -} - -static void __sysfs_remove(struct sysfs_addrm_cxt *acxt, - struct sysfs_dirent *sd) -{ - struct sysfs_dirent *pos, *next; - - if (!sd) - return; - - pr_debug("sysfs %s: removing\n", sd->s_name); - - next = NULL; - do { - pos = next; - next = sysfs_next_descendant_post(pos, sd); - if (pos) - sysfs_remove_one(acxt, pos); - } while (next); -} - -/** - * sysfs_remove - remove a sysfs_dirent recursively - * @sd: the sysfs_dirent to remove - * - * Remove @sd along with all its subdirectories and files. - */ -void sysfs_remove(struct sysfs_dirent *sd) -{ - struct sysfs_addrm_cxt acxt; - - sysfs_addrm_start(&acxt); - __sysfs_remove(&acxt, sd); - sysfs_addrm_finish(&acxt); -} - -/** - * sysfs_hash_and_remove - find a sysfs_dirent by name and remove it - * @dir_sd: parent of the target - * @name: name of the sysfs_dirent to remove - * @ns: namespace tag of the sysfs_dirent to remove - * - * Look for the sysfs_dirent with @name and @ns under @dir_sd and remove - * it. Returns 0 on success, -ENOENT if such entry doesn't exist. - */ -int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name, - const void *ns) -{ - struct sysfs_addrm_cxt acxt; - struct sysfs_dirent *sd; - - if (!dir_sd) { - WARN(1, KERN_WARNING "sysfs: can not remove '%s', no directory\n", - name); - return -ENOENT; + kn = kernfs_create_dir_ns(parent, kobject_name(kobj), + S_IRWXU | S_IRUGO | S_IXUGO, kobj, ns); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, kobject_name(kobj)); + return PTR_ERR(kn); } - sysfs_addrm_start(&acxt); - - sd = sysfs_find_dirent(dir_sd, name, ns); - if (sd) - __sysfs_remove(&acxt, sd); - - sysfs_addrm_finish(&acxt); - - if (sd) - return 0; - else - return -ENOENT; + kobj->sd = kn; + return 0; } /** @@ -940,207 +95,47 @@ int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name, */ void sysfs_remove_dir(struct kobject *kobj) { - struct sysfs_dirent *sd = kobj->sd; + struct kernfs_node *kn = kobj->sd; /* * In general, kboject owner is responsible for ensuring removal * doesn't race with other operations and sysfs doesn't provide any * protection; however, when @kobj is used as a symlink target, the * symlinking entity usually doesn't own @kobj and thus has no - * control over removal. @kobj->sd may be removed anytime and - * symlink code may end up dereferencing an already freed sd. + * control over removal. @kobj->sd may be removed anytime + * and symlink code may end up dereferencing an already freed node. * - * sysfs_symlink_target_lock synchronizes @kobj->sd disassociation - * against symlink operations so that symlink code can safely - * dereference @kobj->sd. + * sysfs_symlink_target_lock synchronizes @kobj->sd + * disassociation against symlink operations so that symlink code + * can safely dereference @kobj->sd. */ spin_lock(&sysfs_symlink_target_lock); kobj->sd = NULL; spin_unlock(&sysfs_symlink_target_lock); - if (sd) { - WARN_ON_ONCE(sysfs_type(sd) != SYSFS_DIR); - sysfs_remove(sd); + if (kn) { + WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); + kernfs_remove(kn); } } -int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd, - const char *new_name, const void *new_ns) -{ - int error; - - mutex_lock(&sysfs_mutex); - - error = 0; - if ((sd->s_parent == new_parent_sd) && (sd->s_ns == new_ns) && - (strcmp(sd->s_name, new_name) == 0)) - goto out; /* nothing to rename */ - - error = -EEXIST; - if (sysfs_find_dirent(new_parent_sd, new_name, new_ns)) - goto out; - - /* rename sysfs_dirent */ - if (strcmp(sd->s_name, new_name) != 0) { - error = -ENOMEM; - new_name = kstrdup(new_name, GFP_KERNEL); - if (!new_name) - goto out; - - kfree(sd->s_name); - sd->s_name = new_name; - } - - /* - * Move to the appropriate place in the appropriate directories rbtree. - */ - sysfs_unlink_sibling(sd); - sysfs_get(new_parent_sd); - sysfs_put(sd->s_parent); - sd->s_ns = new_ns; - sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns); - sd->s_parent = new_parent_sd; - sysfs_link_sibling(sd); - - error = 0; - out: - mutex_unlock(&sysfs_mutex); - return error; -} - int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, const void *new_ns) { - struct sysfs_dirent *parent_sd = kobj->sd->s_parent; + struct kernfs_node *parent = kobj->sd->parent; - return sysfs_rename(kobj->sd, parent_sd, new_name, new_ns); + return kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns) { - struct sysfs_dirent *sd = kobj->sd; - struct sysfs_dirent *new_parent_sd; + struct kernfs_node *kn = kobj->sd; + struct kernfs_node *new_parent; - BUG_ON(!sd->s_parent); - new_parent_sd = new_parent_kobj && new_parent_kobj->sd ? - new_parent_kobj->sd : &sysfs_root; + BUG_ON(!kn->parent); + new_parent = new_parent_kobj && new_parent_kobj->sd ? + new_parent_kobj->sd : sysfs_root_kn; - return sysfs_rename(sd, new_parent_sd, sd->s_name, new_ns); + return kernfs_rename_ns(kn, new_parent, kn->name, new_ns); } - -/* Relationship between s_mode and the DT_xxx types */ -static inline unsigned char dt_type(struct sysfs_dirent *sd) -{ - return (sd->s_mode >> 12) & 15; -} - -static int sysfs_dir_release(struct inode *inode, struct file *filp) -{ - sysfs_put(filp->private_data); - return 0; -} - -static struct sysfs_dirent *sysfs_dir_pos(const void *ns, - struct sysfs_dirent *parent_sd, loff_t hash, struct sysfs_dirent *pos) -{ - if (pos) { - int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) && - pos->s_parent == parent_sd && - hash == pos->s_hash; - sysfs_put(pos); - if (!valid) - pos = NULL; - } - if (!pos && (hash > 1) && (hash < INT_MAX)) { - struct rb_node *node = parent_sd->s_dir.children.rb_node; - while (node) { - pos = to_sysfs_dirent(node); - - if (hash < pos->s_hash) - node = node->rb_left; - else if (hash > pos->s_hash) - node = node->rb_right; - else - break; - } - } - /* Skip over entries in the wrong namespace */ - while (pos && pos->s_ns != ns) { - struct rb_node *node = rb_next(&pos->s_rb); - if (!node) - pos = NULL; - else - pos = to_sysfs_dirent(node); - } - return pos; -} - -static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns, - struct sysfs_dirent *parent_sd, ino_t ino, struct sysfs_dirent *pos) -{ - pos = sysfs_dir_pos(ns, parent_sd, ino, pos); - if (pos) - do { - struct rb_node *node = rb_next(&pos->s_rb); - if (!node) - pos = NULL; - else - pos = to_sysfs_dirent(node); - } while (pos && pos->s_ns != ns); - return pos; -} - -static int sysfs_readdir(struct file *file, struct dir_context *ctx) -{ - struct dentry *dentry = file->f_path.dentry; - struct sysfs_dirent *parent_sd = dentry->d_fsdata; - struct sysfs_dirent *pos = file->private_data; - enum kobj_ns_type type; - const void *ns; - - type = sysfs_ns_type(parent_sd); - ns = sysfs_info(dentry->d_sb)->ns[type]; - - if (!dir_emit_dots(file, ctx)) - return 0; - mutex_lock(&sysfs_mutex); - for (pos = sysfs_dir_pos(ns, parent_sd, ctx->pos, pos); - pos; - pos = sysfs_dir_next_pos(ns, parent_sd, ctx->pos, pos)) { - const char *name = pos->s_name; - unsigned int type = dt_type(pos); - int len = strlen(name); - ino_t ino = pos->s_ino; - ctx->pos = pos->s_hash; - file->private_data = sysfs_get(pos); - - mutex_unlock(&sysfs_mutex); - if (!dir_emit(ctx, name, len, ino, type)) - return 0; - mutex_lock(&sysfs_mutex); - } - mutex_unlock(&sysfs_mutex); - file->private_data = NULL; - ctx->pos = INT_MAX; - return 0; -} - -static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence) -{ - struct inode *inode = file_inode(file); - loff_t ret; - - mutex_lock(&inode->i_mutex); - ret = generic_file_llseek(file, offset, whence); - mutex_unlock(&inode->i_mutex); - - return ret; -} - -const struct file_operations sysfs_dir_operations = { - .read = generic_read_dir, - .iterate = sysfs_readdir, - .release = sysfs_dir_release, - .llseek = sysfs_dir_llseek, -}; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 79b5da2acbe1..810cf6e613e5 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -14,70 +14,23 @@ #include <linux/kobject.h> #include <linux/kallsyms.h> #include <linux/slab.h> -#include <linux/fsnotify.h> -#include <linux/namei.h> -#include <linux/poll.h> #include <linux/list.h> #include <linux/mutex.h> -#include <linux/limits.h> -#include <linux/uaccess.h> #include <linux/seq_file.h> -#include <linux/mm.h> #include "sysfs.h" +#include "../kernfs/kernfs-internal.h" /* - * There's one sysfs_open_file for each open file and one sysfs_open_dirent - * for each sysfs_dirent with one or more open files. - * - * sysfs_dirent->s_attr.open points to sysfs_open_dirent. s_attr.open is - * protected by sysfs_open_dirent_lock. - * - * filp->private_data points to seq_file whose ->private points to - * sysfs_open_file. sysfs_open_files are chained at - * sysfs_open_dirent->files, which is protected by sysfs_open_file_mutex. - */ -static DEFINE_SPINLOCK(sysfs_open_dirent_lock); -static DEFINE_MUTEX(sysfs_open_file_mutex); - -struct sysfs_open_dirent { - atomic_t refcnt; - atomic_t event; - wait_queue_head_t poll; - struct list_head files; /* goes through sysfs_open_file.list */ -}; - -struct sysfs_open_file { - struct sysfs_dirent *sd; - struct file *file; - struct mutex mutex; - int event; - struct list_head list; - - bool mmapped; - const struct vm_operations_struct *vm_ops; -}; - -static bool sysfs_is_bin(struct sysfs_dirent *sd) -{ - return sysfs_type(sd) == SYSFS_KOBJ_BIN_ATTR; -} - -static struct sysfs_open_file *sysfs_of(struct file *file) -{ - return ((struct seq_file *)file->private_data)->private; -} - -/* - * Determine ktype->sysfs_ops for the given sysfs_dirent. This function + * Determine ktype->sysfs_ops for the given kernfs_node. This function * must be called while holding an active reference. */ -static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd) +static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) { - struct kobject *kobj = sd->s_parent->s_dir.kobj; + struct kobject *kobj = kn->parent->priv; - if (!sysfs_ignore_lockdep(sd)) - lockdep_assert_held(sd); + if (kn->flags & KERNFS_LOCKDEP) + lockdep_assert_held(kn); return kobj->ktype ? kobj->ktype->sysfs_ops : NULL; } @@ -86,13 +39,13 @@ static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd) * details like buffering and seeking. The following function pipes * sysfs_ops->show() result through seq_file. */ -static int sysfs_seq_show(struct seq_file *sf, void *v) +static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { - struct sysfs_open_file *of = sf->private; - struct kobject *kobj = of->sd->s_parent->s_dir.kobj; - const struct sysfs_ops *ops; - char *buf; + struct kernfs_open_file *of = sf->private; + struct kobject *kobj = of->kn->parent->priv; + const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; + char *buf; /* acquire buffer and ensure that it's >= PAGE_SIZE */ count = seq_get_buf(sf, &buf); @@ -102,34 +55,15 @@ static int sysfs_seq_show(struct seq_file *sf, void *v) } /* - * Need @of->sd for attr and ops, its parent for kobj. @of->mutex - * nests outside active ref and is just to ensure that the ops - * aren't called concurrently for the same open file. + * Invoke show(). Control may reach here via seq file lseek even + * if @ops->show() isn't implemented. */ - mutex_lock(&of->mutex); - if (!sysfs_get_active(of->sd)) { - mutex_unlock(&of->mutex); - return -ENODEV; + if (ops->show) { + count = ops->show(kobj, of->kn->priv, buf); + if (count < 0) + return count; } - of->event = atomic_read(&of->sd->s_attr.open->event); - - /* - * Lookup @ops and invoke show(). Control may reach here via seq - * file lseek even if @ops->show() isn't implemented. - */ - ops = sysfs_file_ops(of->sd); - if (ops->show) - count = ops->show(kobj, of->sd->s_attr.attr, buf); - else - count = 0; - - sysfs_put_active(of->sd); - mutex_unlock(&of->mutex); - - if (count < 0) - return count; - /* * The code works fine with PAGE_SIZE return but it's likely to * indicate truncated result or overflow in normal use cases. @@ -144,710 +78,194 @@ static int sysfs_seq_show(struct seq_file *sf, void *v) return 0; } -/* - * Read method for bin files. As reading a bin file can have side-effects, - * the exact offset and bytes specified in read(2) call should be passed to - * the read callback making it difficult to use seq_file. Implement - * simplistic custom buffering for bin files. - */ -static ssize_t sysfs_bin_read(struct file *file, char __user *userbuf, - size_t bytes, loff_t *off) +static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) { - struct sysfs_open_file *of = sysfs_of(file); - struct bin_attribute *battr = of->sd->s_attr.bin_attr; - struct kobject *kobj = of->sd->s_parent->s_dir.kobj; - loff_t size = file_inode(file)->i_size; - int count = min_t(size_t, bytes, PAGE_SIZE); - loff_t offs = *off; - char *buf; + struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = of->kn->parent->priv; + loff_t size = file_inode(of->file)->i_size; - if (!bytes) + if (!count) return 0; if (size) { - if (offs > size) + if (pos > size) return 0; - if (offs + count > size) - count = size - offs; + if (pos + count > size) + count = size - pos; } - buf = kmalloc(count, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - /* need of->sd for battr, its parent for kobj */ - mutex_lock(&of->mutex); - if (!sysfs_get_active(of->sd)) { - count = -ENODEV; - mutex_unlock(&of->mutex); - goto out_free; - } + if (!battr->read) + return -EIO; - if (battr->read) - count = battr->read(file, kobj, battr, buf, offs, count); - else - count = -EIO; - - sysfs_put_active(of->sd); - mutex_unlock(&of->mutex); - - if (count < 0) - goto out_free; - - if (copy_to_user(userbuf, buf, count)) { - count = -EFAULT; - goto out_free; - } - - pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count); - - *off = offs + count; - - out_free: - kfree(buf); - return count; + return battr->read(of->file, kobj, battr, buf, pos, count); } -/** - * flush_write_buffer - push buffer to kobject - * @of: open file - * @buf: data buffer for file - * @off: file offset to write to - * @count: number of bytes - * - * Get the correct pointers for the kobject and the attribute we're dealing - * with, then call the store() method for it with @buf. - */ -static int flush_write_buffer(struct sysfs_open_file *of, char *buf, loff_t off, - size_t count) +/* kernfs write callback for regular sysfs files */ +static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) { - struct kobject *kobj = of->sd->s_parent->s_dir.kobj; - int rc = 0; - - /* - * Need @of->sd for attr and ops, its parent for kobj. @of->mutex - * nests outside active ref and is just to ensure that the ops - * aren't called concurrently for the same open file. - */ - mutex_lock(&of->mutex); - if (!sysfs_get_active(of->sd)) { - mutex_unlock(&of->mutex); - return -ENODEV; - } - - if (sysfs_is_bin(of->sd)) { - struct bin_attribute *battr = of->sd->s_attr.bin_attr; - - rc = -EIO; - if (battr->write) - rc = battr->write(of->file, kobj, battr, buf, off, - count); - } else { - const struct sysfs_ops *ops = sysfs_file_ops(of->sd); + const struct sysfs_ops *ops = sysfs_file_ops(of->kn); + struct kobject *kobj = of->kn->parent->priv; - rc = ops->store(kobj, of->sd->s_attr.attr, buf, count); - } - - sysfs_put_active(of->sd); - mutex_unlock(&of->mutex); + if (!count) + return 0; - return rc; + return ops->store(kobj, of->kn->priv, buf, count); } -/** - * sysfs_write_file - write an attribute - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - * - * Copy data in from userland and pass it to the matching - * sysfs_ops->store() by invoking flush_write_buffer(). - * - * There is no easy way for us to know if userspace is only doing a partial - * write, so we don't support them. We expect the entire buffer to come on - * the first write. Hint: if you're writing a value, first read the file, - * modify only the the value you're changing, then write entire buffer - * back. - */ -static ssize_t sysfs_write_file(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) +/* kernfs write callback for bin sysfs files */ +static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) { - struct sysfs_open_file *of = sysfs_of(file); - ssize_t len = min_t(size_t, count, PAGE_SIZE); - loff_t size = file_inode(file)->i_size; - char *buf; + struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = of->kn->parent->priv; + loff_t size = file_inode(of->file)->i_size; - if (sysfs_is_bin(of->sd) && size) { - if (size <= *ppos) + if (size) { + if (size <= pos) return 0; - len = min_t(ssize_t, len, size - *ppos); + count = min_t(ssize_t, count, size - pos); } - - if (!len) + if (!count) return 0; - buf = kmalloc(len + 1, GFP_KERNEL); - if (!buf) - return -ENOMEM; + if (!battr->write) + return -EIO; - if (copy_from_user(buf, user_buf, len)) { - len = -EFAULT; - goto out_free; - } - buf[len] = '\0'; /* guarantee string termination */ - - len = flush_write_buffer(of, buf, *ppos, len); - if (len > 0) - *ppos += len; -out_free: - kfree(buf); - return len; + return battr->write(of->file, kobj, battr, buf, pos, count); } -static void sysfs_bin_vma_open(struct vm_area_struct *vma) +static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, + struct vm_area_struct *vma) { - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - - if (!of->vm_ops) - return; - - if (!sysfs_get_active(of->sd)) - return; + struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = of->kn->parent->priv; - if (of->vm_ops->open) - of->vm_ops->open(vma); - - sysfs_put_active(of->sd); + return battr->mmap(of->file, kobj, battr, vma); } -static int sysfs_bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr) { - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - int ret; - - if (!of->vm_ops) - return VM_FAULT_SIGBUS; - - if (!sysfs_get_active(of->sd)) - return VM_FAULT_SIGBUS; - - ret = VM_FAULT_SIGBUS; - if (of->vm_ops->fault) - ret = of->vm_ops->fault(vma, vmf); + struct kernfs_node *kn = kobj->sd, *tmp; - sysfs_put_active(of->sd); - return ret; -} - -static int sysfs_bin_page_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) -{ - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - int ret; - - if (!of->vm_ops) - return VM_FAULT_SIGBUS; - - if (!sysfs_get_active(of->sd)) - return VM_FAULT_SIGBUS; - - ret = 0; - if (of->vm_ops->page_mkwrite) - ret = of->vm_ops->page_mkwrite(vma, vmf); + if (kn && dir) + kn = kernfs_find_and_get(kn, dir); else - file_update_time(file); - - sysfs_put_active(of->sd); - return ret; -} - -static int sysfs_bin_access(struct vm_area_struct *vma, unsigned long addr, - void *buf, int len, int write) -{ - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - int ret; - - if (!of->vm_ops) - return -EINVAL; - - if (!sysfs_get_active(of->sd)) - return -EINVAL; - - ret = -EINVAL; - if (of->vm_ops->access) - ret = of->vm_ops->access(vma, addr, buf, len, write); - - sysfs_put_active(of->sd); - return ret; -} - -#ifdef CONFIG_NUMA -static int sysfs_bin_set_policy(struct vm_area_struct *vma, - struct mempolicy *new) -{ - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - int ret; - - if (!of->vm_ops) - return 0; - - if (!sysfs_get_active(of->sd)) - return -EINVAL; - - ret = 0; - if (of->vm_ops->set_policy) - ret = of->vm_ops->set_policy(vma, new); - - sysfs_put_active(of->sd); - return ret; -} - -static struct mempolicy *sysfs_bin_get_policy(struct vm_area_struct *vma, - unsigned long addr) -{ - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - struct mempolicy *pol; - - if (!of->vm_ops) - return vma->vm_policy; - - if (!sysfs_get_active(of->sd)) - return vma->vm_policy; - - pol = vma->vm_policy; - if (of->vm_ops->get_policy) - pol = of->vm_ops->get_policy(vma, addr); - - sysfs_put_active(of->sd); - return pol; -} - -static int sysfs_bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, - const nodemask_t *to, unsigned long flags) -{ - struct file *file = vma->vm_file; - struct sysfs_open_file *of = sysfs_of(file); - int ret; - - if (!of->vm_ops) - return 0; - - if (!sysfs_get_active(of->sd)) - return 0; - - ret = 0; - if (of->vm_ops->migrate) - ret = of->vm_ops->migrate(vma, from, to, flags); + kernfs_get(kn); - sysfs_put_active(of->sd); - return ret; -} -#endif - -static const struct vm_operations_struct sysfs_bin_vm_ops = { - .open = sysfs_bin_vma_open, - .fault = sysfs_bin_fault, - .page_mkwrite = sysfs_bin_page_mkwrite, - .access = sysfs_bin_access, -#ifdef CONFIG_NUMA - .set_policy = sysfs_bin_set_policy, - .get_policy = sysfs_bin_get_policy, - .migrate = sysfs_bin_migrate, -#endif -}; - -static int sysfs_bin_mmap(struct file *file, struct vm_area_struct *vma) -{ - struct sysfs_open_file *of = sysfs_of(file); - struct bin_attribute *battr = of->sd->s_attr.bin_attr; - struct kobject *kobj = of->sd->s_parent->s_dir.kobj; - int rc; - - mutex_lock(&of->mutex); - - /* need of->sd for battr, its parent for kobj */ - rc = -ENODEV; - if (!sysfs_get_active(of->sd)) - goto out_unlock; - - if (!battr->mmap) - goto out_put; - - rc = battr->mmap(file, kobj, battr, vma); - if (rc) - goto out_put; - - /* - * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() - * to satisfy versions of X which crash if the mmap fails: that - * substitutes a new vm_file, and we don't then want bin_vm_ops. - */ - if (vma->vm_file != file) - goto out_put; - - rc = -EINVAL; - if (of->mmapped && of->vm_ops != vma->vm_ops) - goto out_put; - - /* - * It is not possible to successfully wrap close. - * So error if someone is trying to use close. - */ - rc = -EINVAL; - if (vma->vm_ops && vma->vm_ops->close) - goto out_put; - - rc = 0; - of->mmapped = 1; - of->vm_ops = vma->vm_ops; - vma->vm_ops = &sysfs_bin_vm_ops; -out_put: - sysfs_put_active(of->sd); -out_unlock: - mutex_unlock(&of->mutex); - - return rc; -} - -/** - * sysfs_get_open_dirent - get or create sysfs_open_dirent - * @sd: target sysfs_dirent - * @of: sysfs_open_file for this instance of open - * - * If @sd->s_attr.open exists, increment its reference count; - * otherwise, create one. @of is chained to the files list. - * - * LOCKING: - * Kernel thread context (may sleep). - * - * RETURNS: - * 0 on success, -errno on failure. - */ -static int sysfs_get_open_dirent(struct sysfs_dirent *sd, - struct sysfs_open_file *of) -{ - struct sysfs_open_dirent *od, *new_od = NULL; - - retry: - mutex_lock(&sysfs_open_file_mutex); - spin_lock_irq(&sysfs_open_dirent_lock); - - if (!sd->s_attr.open && new_od) { - sd->s_attr.open = new_od; - new_od = NULL; - } - - od = sd->s_attr.open; - if (od) { - atomic_inc(&od->refcnt); - list_add_tail(&of->list, &od->files); + if (kn && attr) { + tmp = kernfs_find_and_get(kn, attr); + kernfs_put(kn); + kn = tmp; } - spin_unlock_irq(&sysfs_open_dirent_lock); - mutex_unlock(&sysfs_open_file_mutex); - - if (od) { - kfree(new_od); - return 0; + if (kn) { + kernfs_notify(kn); + kernfs_put(kn); } +} +EXPORT_SYMBOL_GPL(sysfs_notify); - /* not there, initialize a new one and retry */ - new_od = kmalloc(sizeof(*new_od), GFP_KERNEL); - if (!new_od) - return -ENOMEM; +static const struct kernfs_ops sysfs_file_kfops_empty = { +}; - atomic_set(&new_od->refcnt, 0); - atomic_set(&new_od->event, 1); - init_waitqueue_head(&new_od->poll); - INIT_LIST_HEAD(&new_od->files); - goto retry; -} +static const struct kernfs_ops sysfs_file_kfops_ro = { + .seq_show = sysfs_kf_seq_show, +}; -/** - * sysfs_put_open_dirent - put sysfs_open_dirent - * @sd: target sysfs_dirent - * @of: associated sysfs_open_file - * - * Put @sd->s_attr.open and unlink @of from the files list. If - * reference count reaches zero, disassociate and free it. - * - * LOCKING: - * None. - */ -static void sysfs_put_open_dirent(struct sysfs_dirent *sd, - struct sysfs_open_file *of) -{ - struct sysfs_open_dirent *od = sd->s_attr.open; - unsigned long flags; +static const struct kernfs_ops sysfs_file_kfops_wo = { + .write = sysfs_kf_write, +}; - mutex_lock(&sysfs_open_file_mutex); - spin_lock_irqsave(&sysfs_open_dirent_lock, flags); +static const struct kernfs_ops sysfs_file_kfops_rw = { + .seq_show = sysfs_kf_seq_show, + .write = sysfs_kf_write, +}; - if (of) - list_del(&of->list); +static const struct kernfs_ops sysfs_bin_kfops_ro = { + .read = sysfs_kf_bin_read, +}; - if (atomic_dec_and_test(&od->refcnt)) - sd->s_attr.open = NULL; - else - od = NULL; +static const struct kernfs_ops sysfs_bin_kfops_wo = { + .write = sysfs_kf_bin_write, +}; - spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags); - mutex_unlock(&sysfs_open_file_mutex); +static const struct kernfs_ops sysfs_bin_kfops_rw = { + .read = sysfs_kf_bin_read, + .write = sysfs_kf_bin_write, +}; - kfree(od); -} +static const struct kernfs_ops sysfs_bin_kfops_mmap = { + .read = sysfs_kf_bin_read, + .write = sysfs_kf_bin_write, + .mmap = sysfs_kf_bin_mmap, +}; -static int sysfs_open_file(struct inode *inode, struct file *file) +int sysfs_add_file_mode_ns(struct kernfs_node *parent, + const struct attribute *attr, bool is_bin, + umode_t mode, const void *ns) { - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_open_file *of; - bool has_read, has_write; - int error = -EACCES; - - /* need attr_sd for attr and ops, its parent for kobj */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; + struct lock_class_key *key = NULL; + const struct kernfs_ops *ops; + struct kernfs_node *kn; + loff_t size; - if (sysfs_is_bin(attr_sd)) { - struct bin_attribute *battr = attr_sd->s_attr.bin_attr; - - has_read = battr->read || battr->mmap; - has_write = battr->write || battr->mmap; - } else { - const struct sysfs_ops *ops = sysfs_file_ops(attr_sd); + if (!is_bin) { + struct kobject *kobj = parent->priv; + const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops; /* every kobject with an attribute needs a ktype assigned */ - if (WARN(!ops, KERN_ERR + if (WARN(!sysfs_ops, KERN_ERR "missing sysfs attribute operations for kobject: %s\n", kobject_name(kobj))) - goto err_out; - - has_read = ops->show; - has_write = ops->store; - } - - /* check perms and supported operations */ - if ((file->f_mode & FMODE_WRITE) && - (!(inode->i_mode & S_IWUGO) || !has_write)) - goto err_out; - - if ((file->f_mode & FMODE_READ) && - (!(inode->i_mode & S_IRUGO) || !has_read)) - goto err_out; - - /* allocate a sysfs_open_file for the file */ - error = -ENOMEM; - of = kzalloc(sizeof(struct sysfs_open_file), GFP_KERNEL); - if (!of) - goto err_out; - - mutex_init(&of->mutex); - of->sd = attr_sd; - of->file = file; - - /* - * Always instantiate seq_file even if read access doesn't use - * seq_file or is not requested. This unifies private data access - * and readable regular files are the vast majority anyway. - */ - if (sysfs_is_bin(attr_sd)) - error = single_open(file, NULL, of); - else - error = single_open(file, sysfs_seq_show, of); - if (error) - goto err_free; - - /* seq_file clears PWRITE unconditionally, restore it if WRITE */ - if (file->f_mode & FMODE_WRITE) - file->f_mode |= FMODE_PWRITE; - - /* make sure we have open dirent struct */ - error = sysfs_get_open_dirent(attr_sd, of); - if (error) - goto err_close; - - /* open succeeded, put active references */ - sysfs_put_active(attr_sd); - return 0; - -err_close: - single_release(inode, file); -err_free: - kfree(of); -err_out: - sysfs_put_active(attr_sd); - return error; -} - -static int sysfs_release(struct inode *inode, struct file *filp) -{ - struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata; - struct sysfs_open_file *of = sysfs_of(filp); - - sysfs_put_open_dirent(sd, of); - single_release(inode, filp); - kfree(of); - - return 0; -} - -void sysfs_unmap_bin_file(struct sysfs_dirent *sd) -{ - struct sysfs_open_dirent *od; - struct sysfs_open_file *of; - - if (!sysfs_is_bin(sd)) - return; - - spin_lock_irq(&sysfs_open_dirent_lock); - od = sd->s_attr.open; - if (od) - atomic_inc(&od->refcnt); - spin_unlock_irq(&sysfs_open_dirent_lock); - if (!od) - return; - - mutex_lock(&sysfs_open_file_mutex); - list_for_each_entry(of, &od->files, list) { - struct inode *inode = file_inode(of->file); - unmap_mapping_range(inode->i_mapping, 0, 0, 1); + return -EINVAL; + + if (sysfs_ops->show && sysfs_ops->store) + ops = &sysfs_file_kfops_rw; + else if (sysfs_ops->show) + ops = &sysfs_file_kfops_ro; + else if (sysfs_ops->store) + ops = &sysfs_file_kfops_wo; + else + ops = &sysfs_file_kfops_empty; + + size = PAGE_SIZE; + } else { + struct bin_attribute *battr = (void *)attr; + + if (battr->mmap) + ops = &sysfs_bin_kfops_mmap; + else if (battr->read && battr->write) + ops = &sysfs_bin_kfops_rw; + else if (battr->read) + ops = &sysfs_bin_kfops_ro; + else if (battr->write) + ops = &sysfs_bin_kfops_wo; + else + ops = &sysfs_file_kfops_empty; + + size = battr->size; } - mutex_unlock(&sysfs_open_file_mutex); - - sysfs_put_open_dirent(sd, NULL); -} - -/* Sysfs attribute files are pollable. The idea is that you read - * the content and then you use 'poll' or 'select' to wait for - * the content to change. When the content changes (assuming the - * manager for the kobject supports notification), poll will - * return POLLERR|POLLPRI, and select will return the fd whether - * it is waiting for read, write, or exceptions. - * Once poll/select indicates that the value has changed, you - * need to close and re-open the file, or seek to 0 and read again. - * Reminder: this only works for attributes which actively support - * it, and it is not possible to test an attribute from userspace - * to see if it supports poll (Neither 'poll' nor 'select' return - * an appropriate error code). When in doubt, set a suitable timeout value. - */ -static unsigned int sysfs_poll(struct file *filp, poll_table *wait) -{ - struct sysfs_open_file *of = sysfs_of(filp); - struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata; - struct sysfs_open_dirent *od = attr_sd->s_attr.open; - - /* need parent for the kobj, grab both */ - if (!sysfs_get_active(attr_sd)) - goto trigger; - - poll_wait(filp, &od->poll, wait); - sysfs_put_active(attr_sd); - - if (of->event != atomic_read(&od->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|POLLERR|POLLPRI; -} - -void sysfs_notify_dirent(struct sysfs_dirent *sd) -{ - struct sysfs_open_dirent *od; - unsigned long flags; - - spin_lock_irqsave(&sysfs_open_dirent_lock, flags); - - if (!WARN_ON(sysfs_type(sd) != SYSFS_KOBJ_ATTR)) { - od = sd->s_attr.open; - if (od) { - atomic_inc(&od->event); - wake_up_interruptible(&od->poll); - } +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (!attr->ignore_lockdep) + key = attr->key ?: (struct lock_class_key *)&attr->skey; +#endif + kn = __kernfs_create_file(parent, attr->name, mode, size, ops, + (void *)attr, ns, true, key); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, attr->name); + return PTR_ERR(kn); } - - spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags); -} -EXPORT_SYMBOL_GPL(sysfs_notify_dirent); - -void sysfs_notify(struct kobject *k, const char *dir, const char *attr) -{ - struct sysfs_dirent *sd = k->sd; - - mutex_lock(&sysfs_mutex); - - if (sd && dir) - sd = sysfs_find_dirent(sd, dir, NULL); - if (sd && attr) - sd = sysfs_find_dirent(sd, attr, NULL); - if (sd) - sysfs_notify_dirent(sd); - - mutex_unlock(&sysfs_mutex); -} -EXPORT_SYMBOL_GPL(sysfs_notify); - -const struct file_operations sysfs_file_operations = { - .read = seq_read, - .write = sysfs_write_file, - .llseek = generic_file_llseek, - .open = sysfs_open_file, - .release = sysfs_release, - .poll = sysfs_poll, -}; - -const struct file_operations sysfs_bin_operations = { - .read = sysfs_bin_read, - .write = sysfs_write_file, - .llseek = generic_file_llseek, - .mmap = sysfs_bin_mmap, - .open = sysfs_open_file, - .release = sysfs_release, - .poll = sysfs_poll, -}; - -int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd, - const struct attribute *attr, int type, - umode_t amode, const void *ns) -{ - umode_t mode = (amode & S_IALLUGO) | S_IFREG; - struct sysfs_addrm_cxt acxt; - struct sysfs_dirent *sd; - int rc; - - sd = sysfs_new_dirent(attr->name, mode, type); - if (!sd) - return -ENOMEM; - - sd->s_ns = ns; - sd->s_attr.attr = (void *)attr; - sysfs_dirent_init_lockdep(sd); - - sysfs_addrm_start(&acxt); - rc = sysfs_add_one(&acxt, sd, dir_sd); - sysfs_addrm_finish(&acxt); - - if (rc) - sysfs_put(sd); - - return rc; + return 0; } - -int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr, - int type) +int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr, + bool is_bin) { - return sysfs_add_file_mode_ns(dir_sd, attr, type, attr->mode, NULL); + return sysfs_add_file_mode_ns(parent, attr, is_bin, attr->mode, NULL); } /** @@ -861,8 +279,7 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, { BUG_ON(!kobj || !kobj->sd || !attr); - return sysfs_add_file_mode_ns(kobj->sd, attr, SYSFS_KOBJ_ATTR, - attr->mode, ns); + return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, ns); } EXPORT_SYMBOL_GPL(sysfs_create_file_ns); @@ -890,19 +307,21 @@ EXPORT_SYMBOL_GPL(sysfs_create_files); int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; int error; - if (group) - dir_sd = sysfs_get_dirent(kobj->sd, group); - else - dir_sd = sysfs_get(kobj->sd); + if (group) { + parent = kernfs_find_and_get(kobj->sd, group); + } else { + parent = kobj->sd; + kernfs_get(parent); + } - if (!dir_sd) + if (!parent) return -ENOENT; - error = sysfs_add_file(dir_sd, attr, SYSFS_KOBJ_ATTR); - sysfs_put(dir_sd); + error = sysfs_add_file(parent, attr, false); + kernfs_put(parent); return error; } @@ -918,23 +337,20 @@ EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode) { - struct sysfs_dirent *sd; + struct kernfs_node *kn; struct iattr newattrs; int rc; - mutex_lock(&sysfs_mutex); - - rc = -ENOENT; - sd = sysfs_find_dirent(kobj->sd, attr->name, NULL); - if (!sd) - goto out; + kn = kernfs_find_and_get(kobj->sd, attr->name); + if (!kn) + return -ENOENT; - newattrs.ia_mode = (mode & S_IALLUGO) | (sd->s_mode & ~S_IALLUGO); + newattrs.ia_mode = (mode & S_IALLUGO) | (kn->mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE; - rc = sysfs_sd_setattr(sd, &newattrs); - out: - mutex_unlock(&sysfs_mutex); + rc = kernfs_setattr(kn, &newattrs); + + kernfs_put(kn); return rc; } EXPORT_SYMBOL_GPL(sysfs_chmod_file); @@ -950,9 +366,9 @@ EXPORT_SYMBOL_GPL(sysfs_chmod_file); void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) { - struct sysfs_dirent *dir_sd = kobj->sd; + struct kernfs_node *parent = kobj->sd; - sysfs_hash_and_remove(dir_sd, attr->name, ns); + kernfs_remove_by_name_ns(parent, attr->name, ns); } EXPORT_SYMBOL_GPL(sysfs_remove_file_ns); @@ -973,15 +389,18 @@ EXPORT_SYMBOL_GPL(sysfs_remove_files); void sysfs_remove_file_from_group(struct kobject *kobj, const struct attribute *attr, const char *group) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; - if (group) - dir_sd = sysfs_get_dirent(kobj->sd, group); - else - dir_sd = sysfs_get(kobj->sd); - if (dir_sd) { - sysfs_hash_and_remove(dir_sd, attr->name, NULL); - sysfs_put(dir_sd); + if (group) { + parent = kernfs_find_and_get(kobj->sd, group); + } else { + parent = kobj->sd; + kernfs_get(parent); + } + + if (parent) { + kernfs_remove_by_name(parent, attr->name); + kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); @@ -996,7 +415,7 @@ int sysfs_create_bin_file(struct kobject *kobj, { BUG_ON(!kobj || !kobj->sd || !attr); - return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR); + return sysfs_add_file(kobj->sd, &attr->attr, true); } EXPORT_SYMBOL_GPL(sysfs_create_bin_file); @@ -1008,7 +427,7 @@ EXPORT_SYMBOL_GPL(sysfs_create_bin_file); void sysfs_remove_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { - sysfs_hash_and_remove(kobj->sd, attr->attr.name, NULL); + kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 1898a10e38ce..6b579387c67a 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -18,7 +18,7 @@ #include "sysfs.h" -static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, +static void remove_files(struct kernfs_node *parent, struct kobject *kobj, const struct attribute_group *grp) { struct attribute *const *attr; @@ -26,13 +26,13 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, if (grp->attrs) for (attr = grp->attrs; *attr; attr++) - sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL); + kernfs_remove_by_name(parent, (*attr)->name); if (grp->bin_attrs) for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) sysfs_remove_bin_file(kobj, *bin_attr); } -static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, +static int create_files(struct kernfs_node *parent, struct kobject *kobj, const struct attribute_group *grp, int update) { struct attribute *const *attr; @@ -49,22 +49,20 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, * re-adding (if required) the file. */ if (update) - sysfs_hash_and_remove(dir_sd, (*attr)->name, - NULL); + kernfs_remove_by_name(parent, (*attr)->name); if (grp->is_visible) { mode = grp->is_visible(kobj, *attr, i); if (!mode) continue; } - error = sysfs_add_file_mode_ns(dir_sd, *attr, - SYSFS_KOBJ_ATTR, + error = sysfs_add_file_mode_ns(parent, *attr, false, (*attr)->mode | mode, NULL); if (unlikely(error)) break; } if (error) { - remove_files(dir_sd, kobj, grp); + remove_files(parent, kobj, grp); goto exit; } } @@ -78,7 +76,7 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, break; } if (error) - remove_files(dir_sd, kobj, grp); + remove_files(parent, kobj, grp); } exit: return error; @@ -88,7 +86,7 @@ exit: static int internal_create_group(struct kobject *kobj, int update, const struct attribute_group *grp) { - struct sysfs_dirent *sd; + struct kernfs_node *kn; int error; BUG_ON(!kobj || (!update && !kobj->sd)); @@ -102,18 +100,22 @@ static int internal_create_group(struct kobject *kobj, int update, return -EINVAL; } if (grp->name) { - error = sysfs_create_subdir(kobj, grp->name, &sd); - if (error) - return error; + kn = kernfs_create_dir(kobj->sd, grp->name, + S_IRWXU | S_IRUGO | S_IXUGO, kobj); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(kobj->sd, grp->name); + return PTR_ERR(kn); + } } else - sd = kobj->sd; - sysfs_get(sd); - error = create_files(sd, kobj, grp, update); + kn = kobj->sd; + kernfs_get(kn); + error = create_files(kn, kobj, grp, update); if (error) { if (grp->name) - sysfs_remove(sd); + kernfs_remove(kn); } - sysfs_put(sd); + kernfs_put(kn); return error; } @@ -203,25 +205,27 @@ EXPORT_SYMBOL_GPL(sysfs_update_group); void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp) { - struct sysfs_dirent *dir_sd = kobj->sd; - struct sysfs_dirent *sd; + struct kernfs_node *parent = kobj->sd; + struct kernfs_node *kn; if (grp->name) { - sd = sysfs_get_dirent(dir_sd, grp->name); - if (!sd) { - WARN(!sd, KERN_WARNING + kn = kernfs_find_and_get(parent, grp->name); + if (!kn) { + WARN(!kn, KERN_WARNING "sysfs group %p not found for kobject '%s'\n", grp, kobject_name(kobj)); return; } - } else - sd = sysfs_get(dir_sd); + } else { + kn = parent; + kernfs_get(kn); + } - remove_files(sd, kobj, grp); + remove_files(kn, kobj, grp); if (grp->name) - sysfs_remove(sd); + kernfs_remove(kn); - sysfs_put(sd); + kernfs_put(kn); } EXPORT_SYMBOL_GPL(sysfs_remove_group); @@ -257,22 +261,22 @@ EXPORT_SYMBOL_GPL(sysfs_remove_groups); int sysfs_merge_group(struct kobject *kobj, const struct attribute_group *grp) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; int error = 0; struct attribute *const *attr; int i; - dir_sd = sysfs_get_dirent(kobj->sd, grp->name); - if (!dir_sd) + parent = kernfs_find_and_get(kobj->sd, grp->name); + if (!parent) return -ENOENT; for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr)) - error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR); + error = sysfs_add_file(parent, *attr, false); if (error) { while (--i >= 0) - sysfs_hash_and_remove(dir_sd, (*--attr)->name, NULL); + kernfs_remove_by_name(parent, (*--attr)->name); } - sysfs_put(dir_sd); + kernfs_put(parent); return error; } @@ -286,14 +290,14 @@ EXPORT_SYMBOL_GPL(sysfs_merge_group); void sysfs_unmerge_group(struct kobject *kobj, const struct attribute_group *grp) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; struct attribute *const *attr; - dir_sd = sysfs_get_dirent(kobj->sd, grp->name); - if (dir_sd) { + parent = kernfs_find_and_get(kobj->sd, grp->name); + if (parent) { for (attr = grp->attrs; *attr; ++attr) - sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL); - sysfs_put(dir_sd); + kernfs_remove_by_name(parent, (*attr)->name); + kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_unmerge_group); @@ -308,15 +312,15 @@ EXPORT_SYMBOL_GPL(sysfs_unmerge_group); int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name, struct kobject *target, const char *link_name) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; int error = 0; - dir_sd = sysfs_get_dirent(kobj->sd, group_name); - if (!dir_sd) + parent = kernfs_find_and_get(kobj->sd, group_name); + if (!parent) return -ENOENT; - error = sysfs_create_link_sd(dir_sd, target, link_name); - sysfs_put(dir_sd); + error = sysfs_create_link_sd(parent, target, link_name); + kernfs_put(parent); return error; } @@ -331,12 +335,12 @@ EXPORT_SYMBOL_GPL(sysfs_add_link_to_group); void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, const char *link_name) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; - dir_sd = sysfs_get_dirent(kobj->sd, group_name); - if (dir_sd) { - sysfs_hash_and_remove(dir_sd, link_name, NULL); - sysfs_put(dir_sd); + parent = kernfs_find_and_get(kobj->sd, group_name); + if (parent) { + kernfs_remove_by_name(parent, link_name); + kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c deleted file mode 100644 index 1750f790af3b..000000000000 --- a/fs/sysfs/inode.c +++ /dev/null @@ -1,331 +0,0 @@ -/* - * fs/sysfs/inode.c - basic sysfs inode and dentry operations - * - * Copyright (c) 2001-3 Patrick Mochel - * Copyright (c) 2007 SUSE Linux Products GmbH - * Copyright (c) 2007 Tejun Heo <teheo@suse.de> - * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. - */ - -#undef DEBUG - -#include <linux/pagemap.h> -#include <linux/namei.h> -#include <linux/backing-dev.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/sysfs.h> -#include <linux/xattr.h> -#include <linux/security.h> -#include "sysfs.h" - -static const struct address_space_operations sysfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, -}; - -static struct backing_dev_info sysfs_backing_dev_info = { - .name = "sysfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - -static const struct inode_operations sysfs_inode_operations = { - .permission = sysfs_permission, - .setattr = sysfs_setattr, - .getattr = sysfs_getattr, - .setxattr = sysfs_setxattr, -}; - -int __init sysfs_inode_init(void) -{ - return bdi_init(&sysfs_backing_dev_info); -} - -static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd) -{ - struct sysfs_inode_attrs *attrs; - struct iattr *iattrs; - - attrs = kzalloc(sizeof(struct sysfs_inode_attrs), GFP_KERNEL); - if (!attrs) - return NULL; - iattrs = &attrs->ia_iattr; - - /* assign default attributes */ - iattrs->ia_mode = sd->s_mode; - iattrs->ia_uid = GLOBAL_ROOT_UID; - iattrs->ia_gid = GLOBAL_ROOT_GID; - iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME; - - return attrs; -} - -int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr) -{ - struct sysfs_inode_attrs *sd_attrs; - struct iattr *iattrs; - unsigned int ia_valid = iattr->ia_valid; - - sd_attrs = sd->s_iattr; - - if (!sd_attrs) { - /* setting attributes for the first time, allocate now */ - sd_attrs = sysfs_init_inode_attrs(sd); - if (!sd_attrs) - return -ENOMEM; - sd->s_iattr = sd_attrs; - } - /* attributes were changed at least once in past */ - iattrs = &sd_attrs->ia_iattr; - - if (ia_valid & ATTR_UID) - iattrs->ia_uid = iattr->ia_uid; - if (ia_valid & ATTR_GID) - iattrs->ia_gid = iattr->ia_gid; - if (ia_valid & ATTR_ATIME) - iattrs->ia_atime = iattr->ia_atime; - if (ia_valid & ATTR_MTIME) - iattrs->ia_mtime = iattr->ia_mtime; - if (ia_valid & ATTR_CTIME) - iattrs->ia_ctime = iattr->ia_ctime; - if (ia_valid & ATTR_MODE) { - umode_t mode = iattr->ia_mode; - iattrs->ia_mode = sd->s_mode = mode; - } - return 0; -} - -int sysfs_setattr(struct dentry *dentry, struct iattr *iattr) -{ - struct inode *inode = dentry->d_inode; - struct sysfs_dirent *sd = dentry->d_fsdata; - int error; - - if (!sd) - return -EINVAL; - - mutex_lock(&sysfs_mutex); - error = inode_change_ok(inode, iattr); - if (error) - goto out; - - error = sysfs_sd_setattr(sd, iattr); - if (error) - goto out; - - /* this ignores size changes */ - setattr_copy(inode, iattr); - -out: - mutex_unlock(&sysfs_mutex); - return error; -} - -static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, - u32 *secdata_len) -{ - struct sysfs_inode_attrs *iattrs; - void *old_secdata; - size_t old_secdata_len; - - if (!sd->s_iattr) { - sd->s_iattr = sysfs_init_inode_attrs(sd); - if (!sd->s_iattr) - return -ENOMEM; - } - - iattrs = sd->s_iattr; - old_secdata = iattrs->ia_secdata; - old_secdata_len = iattrs->ia_secdata_len; - - iattrs->ia_secdata = *secdata; - iattrs->ia_secdata_len = *secdata_len; - - *secdata = old_secdata; - *secdata_len = old_secdata_len; - return 0; -} - -int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - void *secdata; - int error; - u32 secdata_len = 0; - - if (!sd) - return -EINVAL; - - if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { - const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - error = security_inode_setsecurity(dentry->d_inode, suffix, - value, size, flags); - if (error) - goto out; - error = security_inode_getsecctx(dentry->d_inode, - &secdata, &secdata_len); - if (error) - goto out; - - mutex_lock(&sysfs_mutex); - error = sysfs_sd_setsecdata(sd, &secdata, &secdata_len); - mutex_unlock(&sysfs_mutex); - - if (secdata) - security_release_secctx(secdata, secdata_len); - } else - return -EINVAL; -out: - return error; -} - -static inline void set_default_inode_attr(struct inode *inode, umode_t mode) -{ - inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; -} - -static inline void set_inode_attr(struct inode *inode, struct iattr *iattr) -{ - inode->i_uid = iattr->ia_uid; - inode->i_gid = iattr->ia_gid; - inode->i_atime = iattr->ia_atime; - inode->i_mtime = iattr->ia_mtime; - inode->i_ctime = iattr->ia_ctime; -} - -static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode) -{ - struct sysfs_inode_attrs *iattrs = sd->s_iattr; - - inode->i_mode = sd->s_mode; - if (iattrs) { - /* sysfs_dirent has non-default attributes - * get them from persistent copy in sysfs_dirent - */ - set_inode_attr(inode, &iattrs->ia_iattr); - security_inode_notifysecctx(inode, - iattrs->ia_secdata, - iattrs->ia_secdata_len); - } - - if (sysfs_type(sd) == SYSFS_DIR) - set_nlink(inode, sd->s_dir.subdirs + 2); -} - -int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - struct inode *inode = dentry->d_inode; - - mutex_lock(&sysfs_mutex); - sysfs_refresh_inode(sd, inode); - mutex_unlock(&sysfs_mutex); - - generic_fillattr(inode, stat); - return 0; -} - -static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode) -{ - struct bin_attribute *bin_attr; - - inode->i_private = sysfs_get(sd); - inode->i_mapping->a_ops = &sysfs_aops; - inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; - inode->i_op = &sysfs_inode_operations; - - set_default_inode_attr(inode, sd->s_mode); - sysfs_refresh_inode(sd, inode); - - /* initialize inode according to type */ - switch (sysfs_type(sd)) { - case SYSFS_DIR: - inode->i_op = &sysfs_dir_inode_operations; - inode->i_fop = &sysfs_dir_operations; - break; - case SYSFS_KOBJ_ATTR: - inode->i_size = PAGE_SIZE; - inode->i_fop = &sysfs_file_operations; - break; - case SYSFS_KOBJ_BIN_ATTR: - bin_attr = sd->s_attr.bin_attr; - inode->i_size = bin_attr->size; - inode->i_fop = &sysfs_bin_operations; - break; - case SYSFS_KOBJ_LINK: - inode->i_op = &sysfs_symlink_inode_operations; - break; - default: - BUG(); - } - - unlock_new_inode(inode); -} - -/** - * sysfs_get_inode - get inode for sysfs_dirent - * @sb: super block - * @sd: sysfs_dirent to allocate inode for - * - * Get inode for @sd. If such inode doesn't exist, a new inode - * is allocated and basics are initialized. New inode is - * returned locked. - * - * LOCKING: - * Kernel thread context (may sleep). - * - * RETURNS: - * Pointer to allocated inode on success, NULL on failure. - */ -struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd) -{ - struct inode *inode; - - inode = iget_locked(sb, sd->s_ino); - if (inode && (inode->i_state & I_NEW)) - sysfs_init_inode(sd, inode); - - return inode; -} - -/* - * The sysfs_dirent serves as both an inode and a directory entry for sysfs. - * To prevent the sysfs inode numbers from being freed prematurely we take a - * reference to sysfs_dirent from the sysfs inode. A - * super_operations.evict_inode() implementation is needed to drop that - * reference upon inode destruction. - */ -void sysfs_evict_inode(struct inode *inode) -{ - struct sysfs_dirent *sd = inode->i_private; - - truncate_inode_pages(&inode->i_data, 0); - clear_inode(inode); - sysfs_put(sd); -} - -int sysfs_permission(struct inode *inode, int mask) -{ - struct sysfs_dirent *sd; - - if (mask & MAY_NOT_BLOCK) - return -ECHILD; - - sd = inode->i_private; - - mutex_lock(&sysfs_mutex); - sysfs_refresh_inode(sd, inode); - mutex_unlock(&sysfs_mutex); - - return generic_permission(inode, mask); -} diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 834ec2cdb7a3..6211230814fd 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -14,146 +14,41 @@ #include <linux/fs.h> #include <linux/mount.h> -#include <linux/pagemap.h> #include <linux/init.h> -#include <linux/module.h> -#include <linux/magic.h> -#include <linux/slab.h> #include <linux/user_namespace.h> #include "sysfs.h" - -static struct vfsmount *sysfs_mnt; -struct kmem_cache *sysfs_dir_cachep; - -static const struct super_operations sysfs_ops = { - .statfs = simple_statfs, - .drop_inode = generic_delete_inode, - .evict_inode = sysfs_evict_inode, -}; - -struct sysfs_dirent sysfs_root = { - .s_name = "", - .s_count = ATOMIC_INIT(1), - .s_flags = SYSFS_DIR | (KOBJ_NS_TYPE_NONE << SYSFS_NS_TYPE_SHIFT), - .s_mode = S_IFDIR | S_IRUGO | S_IXUGO, - .s_ino = 1, -}; - -static int sysfs_fill_super(struct super_block *sb, void *data, int silent) -{ - struct inode *inode; - struct dentry *root; - - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; - sb->s_magic = SYSFS_MAGIC; - sb->s_op = &sysfs_ops; - sb->s_time_gran = 1; - - /* get root inode, initialize and unlock it */ - mutex_lock(&sysfs_mutex); - inode = sysfs_get_inode(sb, &sysfs_root); - mutex_unlock(&sysfs_mutex); - if (!inode) { - pr_debug("sysfs: could not get root inode\n"); - return -ENOMEM; - } - - /* instantiate and link root dentry */ - root = d_make_root(inode); - if (!root) { - pr_debug("%s: could not get root dentry!\n", __func__); - return -ENOMEM; - } - root->d_fsdata = &sysfs_root; - sb->s_root = root; - sb->s_d_op = &sysfs_dentry_ops; - return 0; -} - -static int sysfs_test_super(struct super_block *sb, void *data) -{ - struct sysfs_super_info *sb_info = sysfs_info(sb); - struct sysfs_super_info *info = data; - enum kobj_ns_type type; - int found = 1; - - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) { - if (sb_info->ns[type] != info->ns[type]) - found = 0; - } - return found; -} - -static int sysfs_set_super(struct super_block *sb, void *data) -{ - int error; - error = set_anon_super(sb, data); - if (!error) - sb->s_fs_info = data; - return error; -} - -static void free_sysfs_super_info(struct sysfs_super_info *info) -{ - int type; - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) - kobj_ns_drop(type, info->ns[type]); - kfree(info); -} +static struct kernfs_root *sysfs_root; +struct kernfs_node *sysfs_root_kn; static struct dentry *sysfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - struct sysfs_super_info *info; - enum kobj_ns_type type; - struct super_block *sb; - int error; + struct dentry *root; + void *ns; if (!(flags & MS_KERNMOUNT)) { if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) return ERR_PTR(-EPERM); - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) { - if (!kobj_ns_current_may_mount(type)) - return ERR_PTR(-EPERM); - } - } - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return ERR_PTR(-ENOMEM); - - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) - info->ns[type] = kobj_ns_grab_current(type); - - sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info); - if (IS_ERR(sb) || sb->s_fs_info != info) - free_sysfs_super_info(info); - if (IS_ERR(sb)) - return ERR_CAST(sb); - if (!sb->s_root) { - error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); - if (error) { - deactivate_locked_super(sb); - return ERR_PTR(error); - } - sb->s_flags |= MS_ACTIVE; + if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) + return ERR_PTR(-EPERM); } - return dget(sb->s_root); + ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); + root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns); + if (IS_ERR(root)) + kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); + return root; } static void sysfs_kill_sb(struct super_block *sb) { - struct sysfs_super_info *info = sysfs_info(sb); - /* Remove the superblock from fs_supers/s_instances - * so we can't find it, before freeing sysfs_super_info. - */ - kill_anon_super(sb); - free_sysfs_super_info(info); + void *ns = (void *)kernfs_super_ns(sb); + + kernfs_kill_sb(sb); + kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); } static struct file_system_type sysfs_fs_type = { @@ -165,48 +60,19 @@ static struct file_system_type sysfs_fs_type = { int __init sysfs_init(void) { - int err = -ENOMEM; + int err; - sysfs_dir_cachep = kmem_cache_create("sysfs_dir_cache", - sizeof(struct sysfs_dirent), - 0, 0, NULL); - if (!sysfs_dir_cachep) - goto out; + sysfs_root = kernfs_create_root(NULL, NULL); + if (IS_ERR(sysfs_root)) + return PTR_ERR(sysfs_root); - err = sysfs_inode_init(); - if (err) - goto out_err; + sysfs_root_kn = sysfs_root->kn; err = register_filesystem(&sysfs_fs_type); - if (!err) { - sysfs_mnt = kern_mount(&sysfs_fs_type); - if (IS_ERR(sysfs_mnt)) { - printk(KERN_ERR "sysfs: could not mount!\n"); - err = PTR_ERR(sysfs_mnt); - sysfs_mnt = NULL; - unregister_filesystem(&sysfs_fs_type); - goto out_err; - } - } else - goto out_err; -out: - return err; -out_err: - kmem_cache_destroy(sysfs_dir_cachep); - sysfs_dir_cachep = NULL; - goto out; -} - -#undef sysfs_get -struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd) -{ - return __sysfs_get(sd); -} -EXPORT_SYMBOL_GPL(sysfs_get); + if (err) { + kernfs_destroy_root(sysfs_root); + return err; + } -#undef sysfs_put -void sysfs_put(struct sysfs_dirent *sd) -{ - __sysfs_put(sd); + return 0; } -EXPORT_SYMBOL_GPL(sysfs_put); diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 3ae3f1bf1a09..aecb15f84557 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -11,109 +11,73 @@ */ #include <linux/fs.h> -#include <linux/gfp.h> -#include <linux/mount.h> #include <linux/module.h> #include <linux/kobject.h> -#include <linux/namei.h> #include <linux/mutex.h> #include <linux/security.h> #include "sysfs.h" -static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd, - struct kobject *target, +static int sysfs_do_create_link_sd(struct kernfs_node *parent, + struct kobject *target_kobj, const char *name, int warn) { - struct sysfs_dirent *target_sd = NULL; - struct sysfs_dirent *sd = NULL; - struct sysfs_addrm_cxt acxt; - enum kobj_ns_type ns_type; - int error; + struct kernfs_node *kn, *target = NULL; - BUG_ON(!name || !parent_sd); + BUG_ON(!name || !parent); /* - * We don't own @target and it may be removed at any time. + * We don't own @target_kobj and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See * sysfs_remove_dir() for details. */ spin_lock(&sysfs_symlink_target_lock); - if (target->sd) - target_sd = sysfs_get(target->sd); + if (target_kobj->sd) { + target = target_kobj->sd; + kernfs_get(target); + } spin_unlock(&sysfs_symlink_target_lock); - error = -ENOENT; - if (!target_sd) - goto out_put; - - error = -ENOMEM; - sd = sysfs_new_dirent(name, S_IFLNK|S_IRWXUGO, SYSFS_KOBJ_LINK); - if (!sd) - goto out_put; + if (!target) + return -ENOENT; - ns_type = sysfs_ns_type(parent_sd); - if (ns_type) - sd->s_ns = target_sd->s_ns; - sd->s_symlink.target_sd = target_sd; - target_sd = NULL; /* reference is now owned by the symlink */ - - sysfs_addrm_start(&acxt); - /* Symlinks must be between directories with the same ns_type */ - if (!ns_type || - (ns_type == sysfs_ns_type(sd->s_symlink.target_sd->s_parent))) { - if (warn) - error = sysfs_add_one(&acxt, sd, parent_sd); - else - error = __sysfs_add_one(&acxt, sd, parent_sd); - } else { - error = -EINVAL; - WARN(1, KERN_WARNING - "sysfs: symlink across ns_types %s/%s -> %s/%s\n", - parent_sd->s_name, - sd->s_name, - sd->s_symlink.target_sd->s_parent->s_name, - sd->s_symlink.target_sd->s_name); - } - sysfs_addrm_finish(&acxt); + kn = kernfs_create_link(parent, name, target); + kernfs_put(target); - if (error) - goto out_put; + if (!IS_ERR(kn)) + return 0; - return 0; - - out_put: - sysfs_put(target_sd); - sysfs_put(sd); - return error; + if (warn && PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, name); + return PTR_ERR(kn); } /** * sysfs_create_link_sd - create symlink to a given object. - * @sd: directory we're creating the link in. + * @kn: directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. */ -int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target, +int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target, const char *name) { - return sysfs_do_create_link_sd(sd, target, name, 1); + return sysfs_do_create_link_sd(kn, target, name, 1); } static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target, const char *name, int warn) { - struct sysfs_dirent *parent_sd = NULL; + struct kernfs_node *parent = NULL; if (!kobj) - parent_sd = &sysfs_root; + parent = sysfs_root_kn; else - parent_sd = kobj->sd; + parent = kobj->sd; - if (!parent_sd) + if (!parent) return -EFAULT; - return sysfs_do_create_link_sd(parent_sd, target, name, warn); + return sysfs_do_create_link_sd(parent, target, name, warn); } /** @@ -164,10 +128,10 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, * sysfs_remove_dir() for details. */ spin_lock(&sysfs_symlink_target_lock); - if (targ->sd && sysfs_ns_type(kobj->sd)) - ns = targ->sd->s_ns; + if (targ->sd && kernfs_ns_enabled(kobj->sd)) + ns = targ->sd->ns; spin_unlock(&sysfs_symlink_target_lock); - sysfs_hash_and_remove(kobj->sd, name, ns); + kernfs_remove_by_name_ns(kobj->sd, name, ns); } /** @@ -177,14 +141,14 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, */ void sysfs_remove_link(struct kobject *kobj, const char *name) { - struct sysfs_dirent *parent_sd = NULL; + struct kernfs_node *parent = NULL; if (!kobj) - parent_sd = &sysfs_root; + parent = sysfs_root_kn; else - parent_sd = kobj->sd; + parent = kobj->sd; - sysfs_hash_and_remove(parent_sd, name, NULL); + kernfs_remove_by_name(parent, name); } EXPORT_SYMBOL_GPL(sysfs_remove_link); @@ -201,130 +165,33 @@ EXPORT_SYMBOL_GPL(sysfs_remove_link); int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ, const char *old, const char *new, const void *new_ns) { - struct sysfs_dirent *parent_sd, *sd = NULL; + struct kernfs_node *parent, *kn = NULL; const void *old_ns = NULL; int result; if (!kobj) - parent_sd = &sysfs_root; + parent = sysfs_root_kn; else - parent_sd = kobj->sd; + parent = kobj->sd; if (targ->sd) - old_ns = targ->sd->s_ns; + old_ns = targ->sd->ns; result = -ENOENT; - sd = sysfs_get_dirent_ns(parent_sd, old, old_ns); - if (!sd) + kn = kernfs_find_and_get_ns(parent, old, old_ns); + if (!kn) goto out; result = -EINVAL; - if (sysfs_type(sd) != SYSFS_KOBJ_LINK) + if (kernfs_type(kn) != KERNFS_LINK) goto out; - if (sd->s_symlink.target_sd->s_dir.kobj != targ) + if (kn->symlink.target_kn->priv != targ) goto out; - result = sysfs_rename(sd, parent_sd, new, new_ns); + result = kernfs_rename_ns(kn, parent, new, new_ns); out: - sysfs_put(sd); + kernfs_put(kn); return result; } EXPORT_SYMBOL_GPL(sysfs_rename_link_ns); - -static int sysfs_get_target_path(struct sysfs_dirent *parent_sd, - struct sysfs_dirent *target_sd, char *path) -{ - struct sysfs_dirent *base, *sd; - char *s = path; - int len = 0; - - /* go up to the root, stop at the base */ - base = parent_sd; - while (base->s_parent) { - sd = target_sd->s_parent; - while (sd->s_parent && base != sd) - sd = sd->s_parent; - - if (base == sd) - break; - - strcpy(s, "../"); - s += 3; - base = base->s_parent; - } - - /* determine end of target string for reverse fillup */ - sd = target_sd; - while (sd->s_parent && sd != base) { - len += strlen(sd->s_name) + 1; - sd = sd->s_parent; - } - - /* check limits */ - if (len < 2) - return -EINVAL; - len--; - if ((s - path) + len > PATH_MAX) - return -ENAMETOOLONG; - - /* reverse fillup of target string from target to base */ - sd = target_sd; - while (sd->s_parent && sd != base) { - int slen = strlen(sd->s_name); - - len -= slen; - strncpy(s + len, sd->s_name, slen); - if (len) - s[--len] = '/'; - - sd = sd->s_parent; - } - - return 0; -} - -static int sysfs_getlink(struct dentry *dentry, char *path) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - struct sysfs_dirent *parent_sd = sd->s_parent; - struct sysfs_dirent *target_sd = sd->s_symlink.target_sd; - int error; - - mutex_lock(&sysfs_mutex); - error = sysfs_get_target_path(parent_sd, target_sd, path); - mutex_unlock(&sysfs_mutex); - - return error; -} - -static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - int error = -ENOMEM; - unsigned long page = get_zeroed_page(GFP_KERNEL); - if (page) { - error = sysfs_getlink(dentry, (char *) page); - if (error < 0) - free_page((unsigned long)page); - } - nd_set_link(nd, error ? ERR_PTR(error) : (char *)page); - return NULL; -} - -static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd, - void *cookie) -{ - char *page = nd_get_link(nd); - if (!IS_ERR(page)) - free_page((unsigned long)page); -} - -const struct inode_operations sysfs_symlink_inode_operations = { - .setxattr = sysfs_setxattr, - .readlink = generic_readlink, - .follow_link = sysfs_follow_link, - .put_link = sysfs_put_link, - .setattr = sysfs_setattr, - .getattr = sysfs_getattr, - .permission = sysfs_permission, -}; diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 0af09fbfb3f6..0e2f1cccb812 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -8,248 +8,36 @@ * This file is released under the GPLv2. */ -#include <linux/lockdep.h> -#include <linux/kobject_ns.h> -#include <linux/fs.h> -#include <linux/rbtree.h> +#ifndef __SYSFS_INTERNAL_H +#define __SYSFS_INTERNAL_H -struct sysfs_open_dirent; - -/* type-specific structures for sysfs_dirent->s_* union members */ -struct sysfs_elem_dir { - struct kobject *kobj; - - unsigned long subdirs; - /* children rbtree starts here and goes through sd->s_rb */ - struct rb_root children; -}; - -struct sysfs_elem_symlink { - struct sysfs_dirent *target_sd; -}; - -struct sysfs_elem_attr { - union { - struct attribute *attr; - struct bin_attribute *bin_attr; - }; - struct sysfs_open_dirent *open; -}; - -struct sysfs_inode_attrs { - struct iattr ia_iattr; - void *ia_secdata; - u32 ia_secdata_len; -}; - -/* - * sysfs_dirent - the building block of sysfs hierarchy. Each and - * every sysfs node is represented by single sysfs_dirent. - * - * As long as s_count reference is held, the sysfs_dirent itself is - * accessible. Dereferencing s_elem or any other outer entity - * requires s_active reference. - */ -struct sysfs_dirent { - atomic_t s_count; - atomic_t s_active; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif - struct sysfs_dirent *s_parent; - const char *s_name; - - struct rb_node s_rb; - - union { - struct completion *completion; - struct sysfs_dirent *removed_list; - } u; - - const void *s_ns; /* namespace tag */ - unsigned int s_hash; /* ns + name hash */ - union { - struct sysfs_elem_dir s_dir; - struct sysfs_elem_symlink s_symlink; - struct sysfs_elem_attr s_attr; - }; - - unsigned short s_flags; - umode_t s_mode; - unsigned int s_ino; - struct sysfs_inode_attrs *s_iattr; -}; - -#define SD_DEACTIVATED_BIAS INT_MIN - -#define SYSFS_TYPE_MASK 0x00ff -#define SYSFS_DIR 0x0001 -#define SYSFS_KOBJ_ATTR 0x0002 -#define SYSFS_KOBJ_BIN_ATTR 0x0004 -#define SYSFS_KOBJ_LINK 0x0008 -#define SYSFS_COPY_NAME (SYSFS_DIR | SYSFS_KOBJ_LINK) -#define SYSFS_ACTIVE_REF (SYSFS_KOBJ_ATTR | SYSFS_KOBJ_BIN_ATTR) - -/* identify any namespace tag on sysfs_dirents */ -#define SYSFS_NS_TYPE_MASK 0xf00 -#define SYSFS_NS_TYPE_SHIFT 8 - -#define SYSFS_FLAG_MASK ~(SYSFS_NS_TYPE_MASK|SYSFS_TYPE_MASK) -#define SYSFS_FLAG_REMOVED 0x02000 - -static inline unsigned int sysfs_type(struct sysfs_dirent *sd) -{ - return sd->s_flags & SYSFS_TYPE_MASK; -} - -/* - * Return any namespace tags on this dirent. - * enum kobj_ns_type is defined in linux/kobject.h - */ -static inline enum kobj_ns_type sysfs_ns_type(struct sysfs_dirent *sd) -{ - return (sd->s_flags & SYSFS_NS_TYPE_MASK) >> SYSFS_NS_TYPE_SHIFT; -} - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - -#define sysfs_dirent_init_lockdep(sd) \ -do { \ - struct attribute *attr = sd->s_attr.attr; \ - struct lock_class_key *key = attr->key; \ - if (!key) \ - key = &attr->skey; \ - \ - lockdep_init_map(&sd->dep_map, "s_active", key, 0); \ -} while (0) - -/* Test for attributes that want to ignore lockdep for read-locking */ -static inline bool sysfs_ignore_lockdep(struct sysfs_dirent *sd) -{ - int type = sysfs_type(sd); - - return (type == SYSFS_KOBJ_ATTR || type == SYSFS_KOBJ_BIN_ATTR) && - sd->s_attr.attr->ignore_lockdep; -} - -#else - -#define sysfs_dirent_init_lockdep(sd) do {} while (0) - -static inline bool sysfs_ignore_lockdep(struct sysfs_dirent *sd) -{ - return true; -} - -#endif - -/* - * Context structure to be used while adding/removing nodes. - */ -struct sysfs_addrm_cxt { - struct sysfs_dirent *removed; -}; +#include <linux/sysfs.h> /* * mount.c */ - -/* - * Each sb is associated with a set of namespace tags (i.e. - * the network namespace of the task which mounted this sysfs - * instance). - */ -struct sysfs_super_info { - void *ns[KOBJ_NS_TYPES]; -}; -#define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info)) -extern struct sysfs_dirent sysfs_root; -extern struct kmem_cache *sysfs_dir_cachep; +extern struct kernfs_node *sysfs_root_kn; /* * dir.c */ -extern struct mutex sysfs_mutex; extern spinlock_t sysfs_symlink_target_lock; -extern const struct dentry_operations sysfs_dentry_ops; - -extern const struct file_operations sysfs_dir_operations; -extern const struct inode_operations sysfs_dir_inode_operations; -struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd); -void sysfs_put_active(struct sysfs_dirent *sd); -void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt); -void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name); -int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd, - struct sysfs_dirent *parent_sd); -int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd, - struct sysfs_dirent *parent_sd); -void sysfs_remove(struct sysfs_dirent *sd); -int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name, - const void *ns); -void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt); - -struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, - const unsigned char *name, - const void *ns); -struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type); - -void release_sysfs_dirent(struct sysfs_dirent *sd); - -int sysfs_create_subdir(struct kobject *kobj, const char *name, - struct sysfs_dirent **p_sd); - -int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd, - const char *new_name, const void *new_ns); - -static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd) -{ - if (sd) { - WARN_ON(!atomic_read(&sd->s_count)); - atomic_inc(&sd->s_count); - } - return sd; -} -#define sysfs_get(sd) __sysfs_get(sd) - -static inline void __sysfs_put(struct sysfs_dirent *sd) -{ - if (sd && atomic_dec_and_test(&sd->s_count)) - release_sysfs_dirent(sd); -} -#define sysfs_put(sd) __sysfs_put(sd) - -/* - * inode.c - */ -struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd); -void sysfs_evict_inode(struct inode *inode); -int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr); -int sysfs_permission(struct inode *inode, int mask); -int sysfs_setattr(struct dentry *dentry, struct iattr *iattr); -int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat); -int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags); -int sysfs_inode_init(void); +void sysfs_warn_dup(struct kernfs_node *parent, const char *name); /* * file.c */ -extern const struct file_operations sysfs_file_operations; -extern const struct file_operations sysfs_bin_operations; - -int sysfs_add_file(struct sysfs_dirent *dir_sd, - const struct attribute *attr, int type); - -int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd, - const struct attribute *attr, int type, +int sysfs_add_file(struct kernfs_node *parent, + const struct attribute *attr, bool is_bin); +int sysfs_add_file_mode_ns(struct kernfs_node *parent, + const struct attribute *attr, bool is_bin, umode_t amode, const void *ns); -void sysfs_unmap_bin_file(struct sysfs_dirent *sd); /* * symlink.c */ -extern const struct inode_operations sysfs_symlink_inode_operations; -int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target, +int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target, const char *name); + +#endif /* __SYSFS_INTERNAL_H */ diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c index 739e0a52deda..5549d69ddb45 100644 --- a/fs/xfs/xfs_attr_remote.c +++ b/fs/xfs/xfs_attr_remote.c @@ -110,7 +110,7 @@ xfs_attr3_rmt_verify( if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt)) return false; if (be32_to_cpu(rmt->rm_offset) + - be32_to_cpu(rmt->rm_bytes) >= XATTR_SIZE_MAX) + be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX) return false; if (rmt->rm_owner == 0) return false; diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 3ef11b22e750..3b2c14b6f0fb 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -1635,7 +1635,7 @@ xfs_bmap_last_extent( * blocks at the end of the file which do not start at the previous data block, * we will try to align the new blocks at stripe unit boundaries. * - * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be + * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be * at, or past the EOF. */ STATIC int @@ -1650,9 +1650,14 @@ xfs_bmap_isaeof( bma->aeof = 0; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); - if (error || is_empty) + if (error) return error; + if (is_empty) { + bma->aeof = 1; + return 0; + } + /* * Check if we are allocation or past the last extent, or at least into * the last delayed allocated extent. @@ -3643,10 +3648,19 @@ xfs_bmap_btalloc( int isaligned; int tryagain; int error; + int stripe_align; ASSERT(ap->length); mp = ap->ip->i_mount; + + /* stripe alignment for allocation is determined by mount parameters */ + stripe_align = 0; + if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC)) + stripe_align = mp->m_swidth; + else if (mp->m_dalign) + stripe_align = mp->m_dalign; + align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0; if (unlikely(align)) { error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, @@ -3655,6 +3669,8 @@ xfs_bmap_btalloc( ASSERT(!error); ASSERT(ap->length); } + + nullfb = *ap->firstblock == NULLFSBLOCK; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock); if (nullfb) { @@ -3730,7 +3746,7 @@ xfs_bmap_btalloc( */ if (!ap->flist->xbf_low && ap->aeof) { if (!ap->offset) { - args.alignment = mp->m_dalign; + args.alignment = stripe_align; atype = args.type; isaligned = 1; /* @@ -3755,13 +3771,13 @@ xfs_bmap_btalloc( * of minlen+alignment+slop doesn't go up * between the calls. */ - if (blen > mp->m_dalign && blen <= args.maxlen) - nextminlen = blen - mp->m_dalign; + if (blen > stripe_align && blen <= args.maxlen) + nextminlen = blen - stripe_align; else nextminlen = args.minlen; - if (nextminlen + mp->m_dalign > args.minlen + 1) + if (nextminlen + stripe_align > args.minlen + 1) args.minalignslop = - nextminlen + mp->m_dalign - + nextminlen + stripe_align - args.minlen - 1; else args.minalignslop = 0; @@ -3783,7 +3799,7 @@ xfs_bmap_btalloc( */ args.type = atype; args.fsbno = ap->blkno; - args.alignment = mp->m_dalign; + args.alignment = stripe_align; args.minlen = nextminlen; args.minalignslop = 0; isaligned = 1; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 5887e41c0323..82e0dab46ee5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -287,6 +287,7 @@ xfs_bmapi_allocate( INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); queue_work(xfs_alloc_wq, &args->work); wait_for_completion(&done); + destroy_work_on_stack(&args->work); return args->result; } @@ -1187,7 +1188,12 @@ xfs_zero_remaining_bytes( XFS_BUF_UNWRITE(bp); XFS_BUF_READ(bp); XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock)); - xfsbdstrat(mp, bp); + + if (XFS_FORCED_SHUTDOWN(mp)) { + error = XFS_ERROR(EIO); + break; + } + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, @@ -1200,7 +1206,12 @@ xfs_zero_remaining_bytes( XFS_BUF_UNDONE(bp); XFS_BUF_UNREAD(bp); XFS_BUF_WRITE(bp); - xfsbdstrat(mp, bp); + + if (XFS_FORCED_SHUTDOWN(mp)) { + error = XFS_ERROR(EIO); + break; + } + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c7f0b77dcb00..afe7645e4b2b 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -698,7 +698,11 @@ xfs_buf_read_uncached( bp->b_flags |= XBF_READ; bp->b_ops = ops; - xfsbdstrat(target->bt_mount, bp); + if (XFS_FORCED_SHUTDOWN(target->bt_mount)) { + xfs_buf_relse(bp); + return NULL; + } + xfs_buf_iorequest(bp); xfs_buf_iowait(bp); return bp; } @@ -1089,7 +1093,7 @@ xfs_bioerror( * This is meant for userdata errors; metadata bufs come with * iodone functions attached, so that we can track down errors. */ -STATIC int +int xfs_bioerror_relse( struct xfs_buf *bp) { @@ -1152,7 +1156,7 @@ xfs_bwrite( ASSERT(xfs_buf_islocked(bp)); bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL); xfs_bdstrat_cb(bp); @@ -1164,25 +1168,6 @@ xfs_bwrite( return error; } -/* - * Wrapper around bdstrat so that we can stop data from going to disk in case - * we are shutting down the filesystem. Typically user data goes thru this - * path; one of the exceptions is the superblock. - */ -void -xfsbdstrat( - struct xfs_mount *mp, - struct xfs_buf *bp) -{ - if (XFS_FORCED_SHUTDOWN(mp)) { - trace_xfs_bdstrat_shut(bp, _RET_IP_); - xfs_bioerror_relse(bp); - return; - } - - xfs_buf_iorequest(bp); -} - STATIC void _xfs_buf_ioend( xfs_buf_t *bp, @@ -1516,6 +1501,12 @@ xfs_wait_buftarg( struct xfs_buf *bp; bp = list_first_entry(&dispose, struct xfs_buf, b_lru); list_del_init(&bp->b_lru); + if (bp->b_flags & XBF_WRITE_FAIL) { + xfs_alert(btp->bt_mount, +"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n" +"Please run xfs_repair to determine the extent of the problem.", + (long long)bp->b_bn); + } xfs_buf_rele(bp); } if (loop++ != 0) @@ -1799,7 +1790,7 @@ __xfs_buf_delwri_submit( blk_start_plug(&plug); list_for_each_entry_safe(bp, n, io_list, b_list) { - bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL); bp->b_flags |= XBF_WRITE; if (!wait) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index e65683361017..1cf21a4a9f22 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -45,6 +45,7 @@ typedef enum { #define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ #define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ #define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ +#define XBF_WRITE_FAIL (1 << 24)/* async writes have failed on this buffer */ /* I/O hints for the BIO layer */ #define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ @@ -70,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t; { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ + { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ { XBF_SYNCIO, "SYNCIO" }, \ { XBF_FUA, "FUA" }, \ { XBF_FLUSH, "FLUSH" }, \ @@ -80,6 +82,7 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_DELWRI_Q, "DELWRI_Q" }, \ { _XBF_COMPOUND, "COMPOUND" } + /* * Internal state flags. */ @@ -269,9 +272,6 @@ extern void xfs_buf_unlock(xfs_buf_t *); /* Buffer Read and Write Routines */ extern int xfs_bwrite(struct xfs_buf *bp); - -extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *); - extern void xfs_buf_ioend(xfs_buf_t *, int); extern void xfs_buf_ioerror(xfs_buf_t *, int); extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func); @@ -282,6 +282,8 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, #define xfs_buf_zero(bp, off, len) \ xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO) +extern int xfs_bioerror_relse(struct xfs_buf *); + static inline int xfs_buf_geterror(xfs_buf_t *bp) { return bp ? bp->b_error : ENOMEM; @@ -301,7 +303,8 @@ extern void xfs_buf_terminate(void); #define XFS_BUF_ZEROFLAGS(bp) \ ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \ - XBF_SYNCIO|XBF_FUA|XBF_FLUSH)) + XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \ + XBF_WRITE_FAIL)) void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index a64f67ba25d3..2227b9b050bb 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -496,6 +496,14 @@ xfs_buf_item_unpin( } } +/* + * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30 + * seconds so as to not spam logs too much on repeated detection of the same + * buffer being bad.. + */ + +DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10); + STATIC uint xfs_buf_item_push( struct xfs_log_item *lip, @@ -524,6 +532,14 @@ xfs_buf_item_push( trace_xfs_buf_item_push(bip); + /* has a previous flush failed due to IO errors? */ + if ((bp->b_flags & XBF_WRITE_FAIL) && + ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) { + xfs_warn(bp->b_target->bt_mount, +"Detected failing async write on buffer block 0x%llx. Retrying async write.\n", + (long long)bp->b_bn); + } + if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; xfs_buf_unlock(bp); @@ -1096,8 +1112,9 @@ xfs_buf_iodone_callbacks( xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */ - if (!XFS_BUF_ISSTALE(bp)) { - bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE; + if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) { + bp->b_flags |= XBF_WRITE | XBF_ASYNC | + XBF_DONE | XBF_WRITE_FAIL; xfs_buf_iorequest(bp); } else { xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c index 56369d4509d5..48c7d18f68c3 100644 --- a/fs/xfs/xfs_dir2_node.c +++ b/fs/xfs/xfs_dir2_node.c @@ -2067,12 +2067,12 @@ xfs_dir2_node_lookup( */ int /* error */ xfs_dir2_node_removename( - xfs_da_args_t *args) /* operation arguments */ + struct xfs_da_args *args) /* operation arguments */ { - xfs_da_state_blk_t *blk; /* leaf block */ + struct xfs_da_state_blk *blk; /* leaf block */ int error; /* error return value */ int rval; /* operation return value */ - xfs_da_state_t *state; /* btree cursor */ + struct xfs_da_state *state; /* btree cursor */ trace_xfs_dir2_node_removename(args); @@ -2084,19 +2084,18 @@ xfs_dir2_node_removename( state->mp = args->dp->i_mount; state->blocksize = state->mp->m_dirblksize; state->node_ents = state->mp->m_dir_node_ents; - /* - * Look up the entry we're deleting, set up the cursor. - */ + + /* Look up the entry we're deleting, set up the cursor. */ error = xfs_da3_node_lookup_int(state, &rval); if (error) - rval = error; - /* - * Didn't find it, upper layer screwed up. - */ + goto out_free; + + /* Didn't find it, upper layer screwed up. */ if (rval != EEXIST) { - xfs_da_state_free(state); - return rval; + error = rval; + goto out_free; } + blk = &state->path.blk[state->path.active - 1]; ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC); ASSERT(state->extravalid); @@ -2107,7 +2106,7 @@ xfs_dir2_node_removename( error = xfs_dir2_leafn_remove(args, blk->bp, blk->index, &state->extrablk, &rval); if (error) - return error; + goto out_free; /* * Fix the hash values up the btree. */ @@ -2122,6 +2121,7 @@ xfs_dir2_node_removename( */ if (!error) error = xfs_dir2_node_to_leaf(state); +out_free: xfs_da_state_free(state); return error; } diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 8367d6dc18c9..4f11ef011139 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -157,7 +157,7 @@ xfs_ioc_trim( struct xfs_mount *mp, struct fstrim_range __user *urange) { - struct request_queue *q = mp->m_ddev_targp->bt_bdev->bd_disk->queue; + struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev); unsigned int granularity = q->limits.discard_granularity; struct fstrim_range range; xfs_daddr_t start, end, minlen; @@ -180,7 +180,8 @@ xfs_ioc_trim( * matter as trimming blocks is an advisory interface. */ if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) || - range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp))) + range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) || + range.len < mp->m_sb.sb_blocksize) return -XFS_ERROR(EINVAL); start = BTOBB(range.start); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index a6e54b3319bd..02fb943cbf22 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -220,6 +220,8 @@ xfs_growfs_data_private( */ nfree = 0; for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) { + __be32 *agfl_bno; + /* * AG freespace header block */ @@ -279,8 +281,10 @@ xfs_growfs_data_private( agfl->agfl_seqno = cpu_to_be32(agno); uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_uuid); } + + agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp); for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++) - agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK); + agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK); error = xfs_bwrite(bp); xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 4d613401a5e0..33ad9a77791f 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -442,7 +442,8 @@ xfs_attrlist_by_handle( return -XFS_ERROR(EPERM); if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t))) return -XFS_ERROR(EFAULT); - if (al_hreq.buflen > XATTR_LIST_MAX) + if (al_hreq.buflen < sizeof(struct attrlist) || + al_hreq.buflen > XATTR_LIST_MAX) return -XFS_ERROR(EINVAL); /* diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index e8fb1231db81..a7992f8de9d3 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -356,7 +356,8 @@ xfs_compat_attrlist_by_handle( if (copy_from_user(&al_hreq, arg, sizeof(compat_xfs_fsop_attrlist_handlereq_t))) return -XFS_ERROR(EFAULT); - if (al_hreq.buflen > XATTR_LIST_MAX) + if (al_hreq.buflen < sizeof(struct attrlist) || + al_hreq.buflen > XATTR_LIST_MAX) return -XFS_ERROR(EINVAL); /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 27e0e544e963..104455b8046c 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -618,7 +618,8 @@ xfs_setattr_nonsize( } if (!gid_eq(igid, gid)) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) { - ASSERT(!XFS_IS_PQUOTA_ON(mp)); + ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) || + !XFS_IS_PQUOTA_ON(mp)); ASSERT(mask & ATTR_GID); ASSERT(gdqp); olddquot2 = xfs_qm_vop_chown(tp, ip, diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index b6b669df40f3..eae16920655b 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -193,7 +193,10 @@ xlog_bread_noalign( bp->b_io_length = nbblks; bp->b_error = 0; - xfsbdstrat(log->l_mp, bp); + if (XFS_FORCED_SHUTDOWN(log->l_mp)) + return XFS_ERROR(EIO); + + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) xfs_buf_ioerror_alert(bp, __func__); @@ -4397,7 +4400,13 @@ xlog_do_recover( XFS_BUF_READ(bp); XFS_BUF_UNASYNC(bp); bp->b_ops = &xfs_sb_buf_ops; - xfsbdstrat(log->l_mp, bp); + + if (XFS_FORCED_SHUTDOWN(log->l_mp)) { + xfs_buf_relse(bp); + return XFS_ERROR(EIO); + } + + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, __func__); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 14a4996cfec6..dd88f0e27bd8 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -134,8 +134,6 @@ xfs_qm_dqpurge( { struct xfs_mount *mp = dqp->q_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; - struct xfs_dquot *gdqp = NULL; - struct xfs_dquot *pdqp = NULL; xfs_dqlock(dqp); if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) { @@ -143,21 +141,6 @@ xfs_qm_dqpurge( return EAGAIN; } - /* - * If this quota has a hint attached, prepare for releasing it now. - */ - gdqp = dqp->q_gdquot; - if (gdqp) { - xfs_dqlock(gdqp); - dqp->q_gdquot = NULL; - } - - pdqp = dqp->q_pdquot; - if (pdqp) { - xfs_dqlock(pdqp); - dqp->q_pdquot = NULL; - } - dqp->dq_flags |= XFS_DQ_FREEING; xfs_dqflock(dqp); @@ -206,11 +189,47 @@ xfs_qm_dqpurge( XFS_STATS_DEC(xs_qm_dquot_unused); xfs_qm_dqdestroy(dqp); + return 0; +} + +/* + * Release the group or project dquot pointers the user dquots maybe carrying + * around as a hint, and proceed to purge the user dquot cache if requested. +*/ +STATIC int +xfs_qm_dqpurge_hints( + struct xfs_dquot *dqp, + void *data) +{ + struct xfs_dquot *gdqp = NULL; + struct xfs_dquot *pdqp = NULL; + uint flags = *((uint *)data); + + xfs_dqlock(dqp); + if (dqp->dq_flags & XFS_DQ_FREEING) { + xfs_dqunlock(dqp); + return EAGAIN; + } + + /* If this quota has a hint attached, prepare for releasing it now */ + gdqp = dqp->q_gdquot; + if (gdqp) + dqp->q_gdquot = NULL; + + pdqp = dqp->q_pdquot; + if (pdqp) + dqp->q_pdquot = NULL; + + xfs_dqunlock(dqp); if (gdqp) - xfs_qm_dqput(gdqp); + xfs_qm_dqrele(gdqp); if (pdqp) - xfs_qm_dqput(pdqp); + xfs_qm_dqrele(pdqp); + + if (flags & XFS_QMOPT_UQUOTA) + return xfs_qm_dqpurge(dqp, NULL); + return 0; } @@ -222,8 +241,18 @@ xfs_qm_dqpurge_all( struct xfs_mount *mp, uint flags) { - if (flags & XFS_QMOPT_UQUOTA) - xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL); + /* + * We have to release group/project dquot hint(s) from the user dquot + * at first if they are there, otherwise we would run into an infinite + * loop while walking through radix tree to purge other type of dquots + * since their refcount is not zero if the user dquot refers to them + * as hint. + * + * Call the special xfs_qm_dqpurge_hints() will end up go through the + * general xfs_qm_dqpurge() against user dquot cache if requested. + */ + xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags); + if (flags & XFS_QMOPT_GQUOTA) xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL); if (flags & XFS_QMOPT_PQUOTA) @@ -2082,24 +2111,21 @@ xfs_qm_vop_create_dqattach( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(XFS_IS_QUOTA_RUNNING(mp)); - if (udqp) { + if (udqp && XFS_IS_UQUOTA_ON(mp)) { ASSERT(ip->i_udquot == NULL); - ASSERT(XFS_IS_UQUOTA_ON(mp)); ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id)); ip->i_udquot = xfs_qm_dqhold(udqp); xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1); } - if (gdqp) { + if (gdqp && XFS_IS_GQUOTA_ON(mp)) { ASSERT(ip->i_gdquot == NULL); - ASSERT(XFS_IS_GQUOTA_ON(mp)); ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id)); ip->i_gdquot = xfs_qm_dqhold(gdqp); xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1); } - if (pdqp) { + if (pdqp && XFS_IS_PQUOTA_ON(mp)) { ASSERT(ip->i_pdquot == NULL); - ASSERT(XFS_IS_PQUOTA_ON(mp)); ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id)); ip->i_pdquot = xfs_qm_dqhold(pdqp); diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index c035d11b7734..647b6f1d8923 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -314,7 +314,18 @@ xfs_trans_read_buf_map( ASSERT(bp->b_iodone == NULL); XFS_BUF_READ(bp); bp->b_ops = ops; - xfsbdstrat(tp->t_mountp, bp); + + /* + * XXX(hch): clean up the error handling here to be less + * of a mess.. + */ + if (XFS_FORCED_SHUTDOWN(mp)) { + trace_xfs_bdstrat_shut(bp, _RET_IP_); + xfs_bioerror_relse(bp); + } else { + xfs_buf_iorequest(bp); + } + error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, __func__); |