diff options
author | Thomas Gleixner <tglx@linutronix.de> | 2013-07-04 21:11:22 (GMT) |
---|---|---|
committer | Thomas Gleixner <tglx@linutronix.de> | 2013-07-04 21:11:22 (GMT) |
commit | 2b0f89317e99735bbf32eaede81f707f98ab1b5e (patch) | |
tree | 16daa236e21876b11f1c0b9256cd4046aadba020 /fs | |
parent | 07bd1172902e782f288e4d44b1fde7dec0f08b6f (diff) | |
parent | fa18f7bde3ad4568d1d343b60d963bfbd8dc3991 (diff) | |
download | linux-2b0f89317e99735bbf32eaede81f707f98ab1b5e.tar.xz |
Merge branch 'timers/posix-cpu-timers-for-tglx' of
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into timers/core
Frederic sayed: "Most of these patches have been hanging around for
several month now, in -mmotm for a significant chunk. They already
missed a few releases."
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'fs')
110 files changed, 1617 insertions, 918 deletions
@@ -141,9 +141,6 @@ static void aio_free_ring(struct kioctx *ctx) for (i = 0; i < ctx->nr_pages; i++) put_page(ctx->ring_pages[i]); - if (ctx->mmap_size) - vm_munmap(ctx->mmap_base, ctx->mmap_size); - if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) kfree(ctx->ring_pages); } @@ -307,7 +304,9 @@ static void free_ioctx(struct kioctx *ctx) kunmap_atomic(ring); while (atomic_read(&ctx->reqs_active) > 0) { - wait_event(ctx->wait, head != ctx->tail); + wait_event(ctx->wait, + head != ctx->tail || + atomic_read(&ctx->reqs_active) <= 0); avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head; @@ -320,11 +319,6 @@ static void free_ioctx(struct kioctx *ctx) aio_free_ring(ctx); - spin_lock(&aio_nr_lock); - BUG_ON(aio_nr - ctx->max_reqs > aio_nr); - aio_nr -= ctx->max_reqs; - spin_unlock(&aio_nr_lock); - pr_debug("freeing %p\n", ctx); /* @@ -433,17 +427,24 @@ static void kill_ioctx(struct kioctx *ctx) { if (!atomic_xchg(&ctx->dead, 1)) { hlist_del_rcu(&ctx->list); - /* Between hlist_del_rcu() and dropping the initial ref */ - synchronize_rcu(); /* - * We can't punt to workqueue here because put_ioctx() -> - * free_ioctx() will unmap the ringbuffer, and that has to be - * done in the original process's context. kill_ioctx_rcu/work() - * exist for exit_aio(), as in that path free_ioctx() won't do - * the unmap. + * It'd be more correct to do this in free_ioctx(), after all + * the outstanding kiocbs have finished - but by then io_destroy + * has already returned, so io_setup() could potentially return + * -EAGAIN with no ioctxs actually in use (as far as userspace + * could tell). */ - kill_ioctx_work(&ctx->rcu_work); + spin_lock(&aio_nr_lock); + BUG_ON(aio_nr - ctx->max_reqs > aio_nr); + aio_nr -= ctx->max_reqs; + spin_unlock(&aio_nr_lock); + + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); + + /* Between hlist_del_rcu() and dropping the initial ref */ + call_rcu(&ctx->rcu_head, kill_ioctx_rcu); } } @@ -493,10 +494,7 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - if (!atomic_xchg(&ctx->dead, 1)) { - hlist_del_rcu(&ctx->list); - call_rcu(&ctx->rcu_head, kill_ioctx_rcu); - } + kill_ioctx(ctx); } } @@ -1299,8 +1297,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, * < min_nr if the timeout specified by timeout has elapsed * before sufficient events are available, where timeout == NULL * specifies an infinite timeout. Note that the timeout pointed to by - * timeout is relative and will be updated if not NULL and the - * operation blocks. Will fail with -ENOSYS if not implemented. + * timeout is relative. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, long, min_nr, diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 8615ee8..f95dddc 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -265,8 +265,8 @@ befs_readdir(struct file *filp, void *dirent, filldir_t filldir) result = filldir(dirent, keybuf, keysize, filp->f_pos, (ino_t) value, d_type); } - - filp->f_pos++; + if (!result) + filp->f_pos++; befs_debug(sb, "<--- befs_readdir() filp->f_pos %Ld", filp->f_pos); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b4fb415..290e347 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -918,7 +918,8 @@ again: ref->parent, bsz, 0); if (!eb || !extent_buffer_uptodate(eb)) { free_extent_buffer(eb); - return -EIO; + ret = -EIO; + goto out; } ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 18af6f4..1431a69 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -1700,7 +1700,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, unsigned int j; DECLARE_COMPLETION_ONSTACK(complete); - bio = bio_alloc(GFP_NOFS, num_pages - i); + bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i); if (!bio) { printk(KERN_INFO "btrfsic: bio_alloc() for %u pages failed!\n", diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index de6de8e..02fae7f 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -951,10 +951,12 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, BUG_ON(ret); /* -ENOMEM */ } if (new_flags != 0) { + int level = btrfs_header_level(buf); + ret = btrfs_set_disk_extent_flags(trans, root, buf->start, buf->len, - new_flags, 0); + new_flags, level, 0); if (ret) return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 63c328a..d6dd49b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -88,12 +88,12 @@ struct btrfs_ordered_sum; /* holds checksums of all the data extents */ #define BTRFS_CSUM_TREE_OBJECTID 7ULL -/* for storing balance parameters in the root tree */ -#define BTRFS_BALANCE_OBJECTID -4ULL - /* holds quota configuration and tracking */ #define BTRFS_QUOTA_TREE_OBJECTID 8ULL +/* for storing balance parameters in the root tree */ +#define BTRFS_BALANCE_OBJECTID -4ULL + /* orhpan objectid for tracking unlinked/truncated files */ #define BTRFS_ORPHAN_OBJECTID -5ULL @@ -3075,7 +3075,7 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 flags, - int is_data); + int level, int is_data); int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index f75fcaf..70b962c 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -60,6 +60,7 @@ struct btrfs_delayed_ref_node { struct btrfs_delayed_extent_op { struct btrfs_disk_key key; u64 flags_to_set; + int level; unsigned int update_key:1; unsigned int update_flags:1; unsigned int is_data:1; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 7ba7b39..65241f3 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -313,6 +313,11 @@ int btrfs_dev_replace_start(struct btrfs_root *root, struct btrfs_device *tgt_device = NULL; struct btrfs_device *src_device = NULL; + if (btrfs_fs_incompat(fs_info, RAID56)) { + pr_warn("btrfs: dev_replace cannot yet handle RAID5/RAID6\n"); + return -EINVAL; + } + switch (args->start.cont_reading_from_srcdev_mode) { case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS: case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID: diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4e9ebe1..b8b60b6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -152,7 +152,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_DEV_TREE_OBJECTID, .name_stem = "dev" }, { .id = BTRFS_FS_TREE_OBJECTID, .name_stem = "fs" }, { .id = BTRFS_CSUM_TREE_OBJECTID, .name_stem = "csum" }, - { .id = BTRFS_ORPHAN_OBJECTID, .name_stem = "orphan" }, + { .id = BTRFS_QUOTA_TREE_OBJECTID, .name_stem = "quota" }, { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, @@ -1513,7 +1513,6 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, } root->commit_root = btrfs_root_node(root); - BUG_ON(!root->node); /* -ENOMEM */ out: if (location->objectid != BTRFS_TREE_LOG_OBJECTID) { root->ref_cows = 1; @@ -1988,30 +1987,33 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) { free_extent_buffer(info->tree_root->node); free_extent_buffer(info->tree_root->commit_root); - free_extent_buffer(info->dev_root->node); - free_extent_buffer(info->dev_root->commit_root); - free_extent_buffer(info->extent_root->node); - free_extent_buffer(info->extent_root->commit_root); - free_extent_buffer(info->csum_root->node); - free_extent_buffer(info->csum_root->commit_root); - if (info->quota_root) { - free_extent_buffer(info->quota_root->node); - free_extent_buffer(info->quota_root->commit_root); - } - info->tree_root->node = NULL; info->tree_root->commit_root = NULL; - info->dev_root->node = NULL; - info->dev_root->commit_root = NULL; - info->extent_root->node = NULL; - info->extent_root->commit_root = NULL; - info->csum_root->node = NULL; - info->csum_root->commit_root = NULL; + + if (info->dev_root) { + free_extent_buffer(info->dev_root->node); + free_extent_buffer(info->dev_root->commit_root); + info->dev_root->node = NULL; + info->dev_root->commit_root = NULL; + } + if (info->extent_root) { + free_extent_buffer(info->extent_root->node); + free_extent_buffer(info->extent_root->commit_root); + info->extent_root->node = NULL; + info->extent_root->commit_root = NULL; + } + if (info->csum_root) { + free_extent_buffer(info->csum_root->node); + free_extent_buffer(info->csum_root->commit_root); + info->csum_root->node = NULL; + info->csum_root->commit_root = NULL; + } if (info->quota_root) { + free_extent_buffer(info->quota_root->node); + free_extent_buffer(info->quota_root->commit_root); info->quota_root->node = NULL; info->quota_root->commit_root = NULL; } - if (chunk_root) { free_extent_buffer(info->chunk_root->node); free_extent_buffer(info->chunk_root->commit_root); @@ -2857,8 +2859,8 @@ fail_qgroup: btrfs_free_qgroup_config(fs_info); fail_trans_kthread: kthread_stop(fs_info->transaction_kthread); - del_fs_roots(fs_info); btrfs_cleanup_transaction(fs_info->tree_root); + del_fs_roots(fs_info); fail_cleaner: kthread_stop(fs_info->cleaner_kthread); @@ -3128,7 +3130,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait) * caller */ device->flush_bio = NULL; - bio = bio_alloc(GFP_NOFS, 0); + bio = btrfs_io_bio_alloc(GFP_NOFS, 0); if (!bio) return -ENOMEM; @@ -3510,15 +3512,15 @@ int close_ctree(struct btrfs_root *root) percpu_counter_sum(&fs_info->delalloc_bytes)); } - free_root_pointers(fs_info, 1); - btrfs_free_block_groups(fs_info); + btrfs_stop_all_workers(fs_info); + del_fs_roots(fs_info); - iput(fs_info->btree_inode); + free_root_pointers(fs_info, 1); - btrfs_stop_all_workers(fs_info); + iput(fs_info->btree_inode); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY if (btrfs_test_opt(root, CHECK_INTEGRITY)) @@ -3659,8 +3661,11 @@ static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, ordered_operations); list_del_init(&btrfs_inode->ordered_operations); + spin_unlock(&root->fs_info->ordered_extent_lock); btrfs_invalidate_inodes(btrfs_inode->root); + + spin_lock(&root->fs_info->ordered_extent_lock); } spin_unlock(&root->fs_info->ordered_extent_lock); @@ -3782,8 +3787,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) list_del_init(&btrfs_inode->delalloc_inodes); clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, &btrfs_inode->runtime_flags); + spin_unlock(&root->fs_info->delalloc_lock); btrfs_invalidate_inodes(btrfs_inode->root); + + spin_lock(&root->fs_info->delalloc_lock); } spin_unlock(&root->fs_info->delalloc_lock); @@ -3808,7 +3816,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, while (start <= end) { eb = btrfs_find_tree_block(root, start, root->leafsize); - start += eb->len; + start += root->leafsize; if (!eb) continue; wait_on_extent_buffer_writeback(eb); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2305b5c..df472ab 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2070,8 +2070,7 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, u32 item_size; int ret; int err = 0; - int metadata = (node->type == BTRFS_TREE_BLOCK_REF_KEY || - node->type == BTRFS_SHARED_BLOCK_REF_KEY); + int metadata = !extent_op->is_data; if (trans->aborted) return 0; @@ -2086,11 +2085,8 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, key.objectid = node->bytenr; if (metadata) { - struct btrfs_delayed_tree_ref *tree_ref; - - tree_ref = btrfs_delayed_node_to_tree_ref(node); key.type = BTRFS_METADATA_ITEM_KEY; - key.offset = tree_ref->level; + key.offset = extent_op->level; } else { key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = node->num_bytes; @@ -2719,7 +2715,7 @@ out: int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 flags, - int is_data) + int level, int is_data) { struct btrfs_delayed_extent_op *extent_op; int ret; @@ -2732,6 +2728,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, extent_op->update_flags = 1; extent_op->update_key = 0; extent_op->is_data = is_data ? 1 : 0; + extent_op->level = level; ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr, num_bytes, extent_op); @@ -3109,6 +3106,11 @@ again: WARN_ON(ret); if (i_size_read(inode) > 0) { + ret = btrfs_check_trunc_cache_free_space(root, + &root->fs_info->global_block_rsv); + if (ret) + goto out_put; + ret = btrfs_truncate_free_space_cache(root, trans, path, inode); if (ret) @@ -4562,6 +4564,8 @@ static void init_global_block_rsv(struct btrfs_fs_info *fs_info) fs_info->csum_root->block_rsv = &fs_info->global_block_rsv; fs_info->dev_root->block_rsv = &fs_info->global_block_rsv; fs_info->tree_root->block_rsv = &fs_info->global_block_rsv; + if (fs_info->quota_root) + fs_info->quota_root->block_rsv = &fs_info->global_block_rsv; fs_info->chunk_root->block_rsv = &fs_info->chunk_block_rsv; update_global_block_rsv(fs_info); @@ -6651,51 +6655,51 @@ use_block_rsv(struct btrfs_trans_handle *trans, struct btrfs_block_rsv *block_rsv; struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv; int ret; + bool global_updated = false; block_rsv = get_block_rsv(trans, root); - if (block_rsv->size == 0) { - ret = reserve_metadata_bytes(root, block_rsv, blocksize, - BTRFS_RESERVE_NO_FLUSH); - /* - * If we couldn't reserve metadata bytes try and use some from - * the global reserve. - */ - if (ret && block_rsv != global_rsv) { - ret = block_rsv_use_bytes(global_rsv, blocksize); - if (!ret) - return global_rsv; - return ERR_PTR(ret); - } else if (ret) { - return ERR_PTR(ret); - } + if (unlikely(block_rsv->size == 0)) + goto try_reserve; +again: + ret = block_rsv_use_bytes(block_rsv, blocksize); + if (!ret) return block_rsv; + + if (block_rsv->failfast) + return ERR_PTR(ret); + + if (block_rsv->type == BTRFS_BLOCK_RSV_GLOBAL && !global_updated) { + global_updated = true; + update_global_block_rsv(root->fs_info); + goto again; } - ret = block_rsv_use_bytes(block_rsv, blocksize); + if (btrfs_test_opt(root, ENOSPC_DEBUG)) { + static DEFINE_RATELIMIT_STATE(_rs, + DEFAULT_RATELIMIT_INTERVAL * 10, + /*DEFAULT_RATELIMIT_BURST*/ 1); + if (__ratelimit(&_rs)) + WARN(1, KERN_DEBUG + "btrfs: block rsv returned %d\n", ret); + } +try_reserve: + ret = reserve_metadata_bytes(root, block_rsv, blocksize, + BTRFS_RESERVE_NO_FLUSH); if (!ret) return block_rsv; - if (ret && !block_rsv->failfast) { - if (btrfs_test_opt(root, ENOSPC_DEBUG)) { - static DEFINE_RATELIMIT_STATE(_rs, - DEFAULT_RATELIMIT_INTERVAL * 10, - /*DEFAULT_RATELIMIT_BURST*/ 1); - if (__ratelimit(&_rs)) - WARN(1, KERN_DEBUG - "btrfs: block rsv returned %d\n", ret); - } - ret = reserve_metadata_bytes(root, block_rsv, blocksize, - BTRFS_RESERVE_NO_FLUSH); - if (!ret) { - return block_rsv; - } else if (ret && block_rsv != global_rsv) { - ret = block_rsv_use_bytes(global_rsv, blocksize); - if (!ret) - return global_rsv; - } + /* + * If we couldn't reserve metadata bytes try and use some from + * the global reserve if its space type is the same as the global + * reservation. + */ + if (block_rsv->type != BTRFS_BLOCK_RSV_GLOBAL && + block_rsv->space_info == global_rsv->space_info) { + ret = block_rsv_use_bytes(global_rsv, blocksize); + if (!ret) + return global_rsv; } - - return ERR_PTR(-ENOSPC); + return ERR_PTR(ret); } static void unuse_block_rsv(struct btrfs_fs_info *fs_info, @@ -6763,6 +6767,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, extent_op->update_key = 1; extent_op->update_flags = 1; extent_op->is_data = 0; + extent_op->level = level; ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, ins.objectid, @@ -6934,7 +6939,8 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc); BUG_ON(ret); /* -ENOMEM */ ret = btrfs_set_disk_extent_flags(trans, root, eb->start, - eb->len, flag, 0); + eb->len, flag, + btrfs_header_level(eb), 0); BUG_ON(ret); /* -ENOMEM */ wc->flags[level] |= flag; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 32d67a8..e7e7afb 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -23,6 +23,7 @@ static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; +static struct bio_set *btrfs_bioset; #ifdef CONFIG_BTRFS_DEBUG static LIST_HEAD(buffers); @@ -125,10 +126,20 @@ int __init extent_io_init(void) SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL); if (!extent_buffer_cache) goto free_state_cache; + + btrfs_bioset = bioset_create(BIO_POOL_SIZE, + offsetof(struct btrfs_io_bio, bio)); + if (!btrfs_bioset) + goto free_buffer_cache; return 0; +free_buffer_cache: + kmem_cache_destroy(extent_buffer_cache); + extent_buffer_cache = NULL; + free_state_cache: kmem_cache_destroy(extent_state_cache); + extent_state_cache = NULL; return -ENOMEM; } @@ -145,6 +156,8 @@ void extent_io_exit(void) kmem_cache_destroy(extent_state_cache); if (extent_buffer_cache) kmem_cache_destroy(extent_buffer_cache); + if (btrfs_bioset) + bioset_free(btrfs_bioset); } void extent_io_tree_init(struct extent_io_tree *tree, @@ -1948,28 +1961,6 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page) } /* - * helper function to unlock a page if all the extents in the tree - * for that page are unlocked - */ -static void check_page_locked(struct extent_io_tree *tree, struct page *page) -{ - u64 start = page_offset(page); - u64 end = start + PAGE_CACHE_SIZE - 1; - if (!test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL)) - unlock_page(page); -} - -/* - * helper function to end page writeback if all the extents - * in the tree for that page are done with writeback - */ -static void check_page_writeback(struct extent_io_tree *tree, - struct page *page) -{ - end_page_writeback(page); -} - -/* * When IO fails, either with EIO or csum verification fails, we * try other mirrors that might have a good copy of the data. This * io_failure_record is used to record state as we go through all the @@ -2046,7 +2037,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, if (btrfs_is_parity_mirror(map_tree, logical, length, mirror_num)) return 0; - bio = bio_alloc(GFP_NOFS, 1); + bio = btrfs_io_bio_alloc(GFP_NOFS, 1); if (!bio) return -EIO; bio->bi_private = &compl; @@ -2336,7 +2327,7 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page, return -EIO; } - bio = bio_alloc(GFP_NOFS, 1); + bio = btrfs_io_bio_alloc(GFP_NOFS, 1); if (!bio) { free_io_failure(inode, failrec, 0); return -EIO; @@ -2398,19 +2389,24 @@ static void end_bio_extent_writepage(struct bio *bio, int err) struct extent_io_tree *tree; u64 start; u64 end; - int whole_page; do { struct page *page = bvec->bv_page; tree = &BTRFS_I(page->mapping->host)->io_tree; - start = page_offset(page) + bvec->bv_offset; - end = start + bvec->bv_len - 1; + /* We always issue full-page reads, but if some block + * in a page fails to read, blk_update_request() will + * advance bv_offset and adjust bv_len to compensate. + * Print a warning for nonzero offsets, and an error + * if they don't add up to a full page. */ + if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) + printk("%s page write in btrfs with offset %u and length %u\n", + bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE + ? KERN_ERR "partial" : KERN_INFO "incomplete", + bvec->bv_offset, bvec->bv_len); - if (bvec->bv_offset == 0 && bvec->bv_len == PAGE_CACHE_SIZE) - whole_page = 1; - else - whole_page = 0; + start = page_offset(page); + end = start + bvec->bv_offset + bvec->bv_len - 1; if (--bvec >= bio->bi_io_vec) prefetchw(&bvec->bv_page->flags); @@ -2418,10 +2414,7 @@ static void end_bio_extent_writepage(struct bio *bio, int err) if (end_extent_writepage(page, err, start, end)) continue; - if (whole_page) - end_page_writeback(page); - else - check_page_writeback(tree, page); + end_page_writeback(page); } while (bvec >= bio->bi_io_vec); bio_put(bio); @@ -2446,7 +2439,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err) struct extent_io_tree *tree; u64 start; u64 end; - int whole_page; int mirror; int ret; @@ -2457,19 +2449,26 @@ static void end_bio_extent_readpage(struct bio *bio, int err) struct page *page = bvec->bv_page; struct extent_state *cached = NULL; struct extent_state *state; + struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, " - "mirror=%ld\n", (u64)bio->bi_sector, err, - (long int)bio->bi_bdev); + "mirror=%lu\n", (u64)bio->bi_sector, err, + io_bio->mirror_num); tree = &BTRFS_I(page->mapping->host)->io_tree; - start = page_offset(page) + bvec->bv_offset; - end = start + bvec->bv_len - 1; + /* We always issue full-page reads, but if some block + * in a page fails to read, blk_update_request() will + * advance bv_offset and adjust bv_len to compensate. + * Print a warning for nonzero offsets, and an error + * if they don't add up to a full page. */ + if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) + printk("%s page read in btrfs with offset %u and length %u\n", + bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE + ? KERN_ERR "partial" : KERN_INFO "incomplete", + bvec->bv_offset, bvec->bv_len); - if (bvec->bv_offset == 0 && bvec->bv_len == PAGE_CACHE_SIZE) - whole_page = 1; - else - whole_page = 0; + start = page_offset(page); + end = start + bvec->bv_offset + bvec->bv_len - 1; if (++bvec <= bvec_end) prefetchw(&bvec->bv_page->flags); @@ -2485,7 +2484,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) } spin_unlock(&tree->lock); - mirror = (int)(unsigned long)bio->bi_bdev; + mirror = io_bio->mirror_num; if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { ret = tree->ops->readpage_end_io_hook(page, start, end, state, mirror); @@ -2528,39 +2527,35 @@ static void end_bio_extent_readpage(struct bio *bio, int err) } unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC); - if (whole_page) { - if (uptodate) { - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - unlock_page(page); + if (uptodate) { + SetPageUptodate(page); } else { - if (uptodate) { - check_page_uptodate(tree, page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - check_page_locked(tree, page); + ClearPageUptodate(page); + SetPageError(page); } + unlock_page(page); } while (bvec <= bvec_end); bio_put(bio); } +/* + * this allocates from the btrfs_bioset. We're returning a bio right now + * but you can call btrfs_io_bio for the appropriate container_of magic + */ struct bio * btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, gfp_t gfp_flags) { struct bio *bio; - bio = bio_alloc(gfp_flags, nr_vecs); + bio = bio_alloc_bioset(gfp_flags, nr_vecs, btrfs_bioset); if (bio == NULL && (current->flags & PF_MEMALLOC)) { - while (!bio && (nr_vecs /= 2)) - bio = bio_alloc(gfp_flags, nr_vecs); + while (!bio && (nr_vecs /= 2)) { + bio = bio_alloc_bioset(gfp_flags, + nr_vecs, btrfs_bioset); + } } if (bio) { @@ -2571,6 +2566,19 @@ btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, return bio; } +struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) +{ + return bio_clone_bioset(bio, gfp_mask, btrfs_bioset); +} + + +/* this also allocates from the btrfs_bioset */ +struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) +{ + return bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset); +} + + static int __must_check submit_one_bio(int rw, struct bio *bio, int mirror_num, unsigned long bio_flags) { @@ -3988,7 +3996,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, last_for_get_extent = isize; } - lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0, + lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1, 0, &cached_state); em = get_extent_skip_holes(inode, start, last_for_get_extent, @@ -4075,7 +4083,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, out_free: free_extent_map(em); out: - unlock_extent_cached(&BTRFS_I(inode)->io_tree, start, start + len, + unlock_extent_cached(&BTRFS_I(inode)->io_tree, start, start + len - 1, &cached_state, GFP_NOFS); return ret; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index a2c03a1..41fb81e 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -336,6 +336,8 @@ int extent_clear_unlock_delalloc(struct inode *inode, struct bio * btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, gfp_t gfp_flags); +struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs); +struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask); struct btrfs_fs_info; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ecca6c7..e530096 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -197,30 +197,32 @@ int create_free_space_inode(struct btrfs_root *root, block_group->key.objectid); } -int btrfs_truncate_free_space_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct inode *inode) +int btrfs_check_trunc_cache_free_space(struct btrfs_root *root, + struct btrfs_block_rsv *rsv) { - struct btrfs_block_rsv *rsv; u64 needed_bytes; - loff_t oldsize; - int ret = 0; - - rsv = trans->block_rsv; - trans->block_rsv = &root->fs_info->global_block_rsv; + int ret; /* 1 for slack space, 1 for updating the inode */ needed_bytes = btrfs_calc_trunc_metadata_size(root, 1) + btrfs_calc_trans_metadata_size(root, 1); - spin_lock(&trans->block_rsv->lock); - if (trans->block_rsv->reserved < needed_bytes) { - spin_unlock(&trans->block_rsv->lock); - trans->block_rsv = rsv; - return -ENOSPC; - } - spin_unlock(&trans->block_rsv->lock); + spin_lock(&rsv->lock); + if (rsv->reserved < needed_bytes) + ret = -ENOSPC; + else + ret = 0; + spin_unlock(&rsv->lock); + return 0; +} + +int btrfs_truncate_free_space_cache(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct inode *inode) +{ + loff_t oldsize; + int ret = 0; oldsize = i_size_read(inode); btrfs_i_size_write(inode, 0); @@ -232,9 +234,7 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root, */ ret = btrfs_truncate_inode_items(trans, root, inode, 0, BTRFS_EXTENT_DATA_KEY); - if (ret) { - trans->block_rsv = rsv; btrfs_abort_transaction(trans, root, ret); return ret; } @@ -242,7 +242,6 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root, ret = btrfs_update_inode(trans, root, inode); if (ret) btrfs_abort_transaction(trans, root, ret); - trans->block_rsv = rsv; return ret; } @@ -920,10 +919,8 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, /* Make sure we can fit our crcs into the first page */ if (io_ctl.check_crcs && - (io_ctl.num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE) { - WARN_ON(1); + (io_ctl.num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE) goto out_nospc; - } io_ctl_set_generation(&io_ctl, trans->transid); diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 4dc17d8..8b7f19f 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -54,6 +54,8 @@ int create_free_space_inode(struct btrfs_root *root, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); +int btrfs_check_trunc_cache_free_space(struct btrfs_root *root, + struct btrfs_block_rsv *rsv); int btrfs_truncate_free_space_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans, struct btrfs_path *path, diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index d26f67a..2c66ddb 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -429,11 +429,12 @@ int btrfs_save_ino_cache(struct btrfs_root *root, num_bytes = trans->bytes_reserved; /* * 1 item for inode item insertion if need - * 3 items for inode item update (in the worst case) + * 4 items for inode item update (in the worst case) + * 1 items for slack space if we need do truncation * 1 item for free space object * 3 items for pre-allocation */ - trans->bytes_reserved = btrfs_calc_trans_metadata_size(root, 8); + trans->bytes_reserved = btrfs_calc_trans_metadata_size(root, 10); ret = btrfs_block_rsv_add(root, trans->block_rsv, trans->bytes_reserved, BTRFS_RESERVE_NO_FLUSH); @@ -468,7 +469,8 @@ again: if (i_size_read(inode) > 0) { ret = btrfs_truncate_free_space_cache(root, trans, path, inode); if (ret) { - btrfs_abort_transaction(trans, root, ret); + if (ret != -ENOSPC) + btrfs_abort_transaction(trans, root, ret); goto out_put; } } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9b31b3b..17f3064 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -715,8 +715,10 @@ retry: async_extent->ram_size - 1, 0); em = alloc_extent_map(); - if (!em) + if (!em) { + ret = -ENOMEM; goto out_free_reserve; + } em->start = async_extent->start; em->len = async_extent->ram_size; em->orig_start = em->start; @@ -923,8 +925,10 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans, } em = alloc_extent_map(); - if (!em) + if (!em) { + ret = -ENOMEM; goto out_reserve; + } em->start = start; em->orig_start = em->start; ram_size = ins.offset; @@ -4724,6 +4728,7 @@ void btrfs_evict_inode(struct inode *inode) btrfs_end_transaction(trans, root); btrfs_btree_balance_dirty(root); no_delete: + btrfs_remove_delayed_node(inode); clear_inode(inode); return; } @@ -4839,14 +4844,13 @@ static void inode_tree_add(struct inode *inode) struct rb_node **p; struct rb_node *parent; u64 ino = btrfs_ino(inode); -again: - p = &root->inode_tree.rb_node; - parent = NULL; if (inode_unhashed(inode)) return; - +again: + parent = NULL; spin_lock(&root->inode_lock); + p = &root->inode_tree.rb_node; while (*p) { parent = *p; entry = rb_entry(parent, struct btrfs_inode, rb_node); @@ -6928,7 +6932,11 @@ struct btrfs_dio_private { /* IO errors */ int errors; + /* orig_bio is our btrfs_io_bio */ struct bio *orig_bio; + + /* dio_bio came from fs/direct-io.c */ + struct bio *dio_bio; }; static void btrfs_endio_direct_read(struct bio *bio, int err) @@ -6938,6 +6946,7 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct bio_vec *bvec = bio->bi_io_vec; struct inode *inode = dip->inode; struct btrfs_root *root = BTRFS_I(inode)->root; + struct bio *dio_bio; u64 start; start = dip->logical_offset; @@ -6977,14 +6986,15 @@ failed: unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); - bio->bi_private = dip->private; + dio_bio = dip->dio_bio; kfree(dip); /* If we had a csum failure make sure to clear the uptodate flag */ if (err) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - dio_end_io(bio, err); + clear_bit(BIO_UPTODATE, &dio_bio->bi_flags); + dio_end_io(dio_bio, err); + bio_put(bio); } static void btrfs_endio_direct_write(struct bio *bio, int err) @@ -6995,6 +7005,7 @@ static void btrfs_endio_direct_write(struct bio *bio, int err) struct btrfs_ordered_extent *ordered = NULL; u64 ordered_offset = dip->logical_offset; u64 ordered_bytes = dip->bytes; + struct bio *dio_bio; int ret; if (err) @@ -7022,14 +7033,15 @@ out_test: goto again; } out_done: - bio->bi_private = dip->private; + dio_bio = dip->dio_bio; kfree(dip); /* If we had an error make sure to clear the uptodate flag */ if (err) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - dio_end_io(bio, err); + clear_bit(BIO_UPTODATE, &dio_bio->bi_flags); + dio_end_io(dio_bio, err); + bio_put(bio); } static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw, @@ -7065,10 +7077,10 @@ static void btrfs_end_dio_bio(struct bio *bio, int err) if (!atomic_dec_and_test(&dip->pending_bios)) goto out; - if (dip->errors) + if (dip->errors) { bio_io_error(dip->orig_bio); - else { - set_bit(BIO_UPTODATE, &dip->orig_bio->bi_flags); + } else { + set_bit(BIO_UPTODATE, &dip->dio_bio->bi_flags); bio_endio(dip->orig_bio, 0); } out: @@ -7243,25 +7255,34 @@ out_err: return 0; } -static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, - loff_t file_offset) +static void btrfs_submit_direct(int rw, struct bio *dio_bio, + struct inode *inode, loff_t file_offset) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_dio_private *dip; - struct bio_vec *bvec = bio->bi_io_vec; + struct bio_vec *bvec = dio_bio->bi_io_vec; + struct bio *io_bio; int skip_sum; int write = rw & REQ_WRITE; int ret = 0; skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; + io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS); + + if (!io_bio) { + ret = -ENOMEM; + goto free_ordered; + } + dip = kmalloc(sizeof(*dip), GFP_NOFS); if (!dip) { ret = -ENOMEM; - goto free_ordered; + goto free_io_bio; } - dip->private = bio->bi_private; + dip->private = dio_bio->bi_private; + io_bio->bi_private = dio_bio->bi_private; dip->inode = inode; dip->logical_offset = file_offset; @@ -7269,22 +7290,27 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, do { dip->bytes += bvec->bv_len; bvec++; - } while (bvec <= (bio->bi_io_vec + bio->bi_vcnt - 1)); + } while (bvec <= (dio_bio->bi_io_vec + dio_bio->bi_vcnt - 1)); - dip->disk_bytenr = (u64)bio->bi_sector << 9; - bio->bi_private = dip; + dip->disk_bytenr = (u64)dio_bio->bi_sector << 9; + io_bio->bi_private = dip; dip->errors = 0; - dip->orig_bio = bio; + dip->orig_bio = io_bio; + dip->dio_bio = dio_bio; atomic_set(&dip->pending_bios, 0); if (write) - bio->bi_end_io = btrfs_endio_direct_write; + io_bio->bi_end_io = btrfs_endio_direct_write; else - bio->bi_end_io = btrfs_endio_direct_read; + io_bio->bi_end_io = btrfs_endio_direct_read; ret = btrfs_submit_direct_hook(rw, dip, skip_sum); if (!ret) return; + +free_io_bio: + bio_put(io_bio); + free_ordered: /* * If this is a write, we need to clean up the reserved space and kill @@ -7300,7 +7326,7 @@ free_ordered: btrfs_put_ordered_extent(ordered); btrfs_put_ordered_extent(ordered); } - bio_endio(bio, ret); + bio_endio(dio_bio, ret); } static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb, @@ -7979,7 +8005,6 @@ void btrfs_destroy_inode(struct inode *inode) inode_tree_del(inode); btrfs_drop_extent_cache(inode, 0, (u64)-1, 0); free: - btrfs_remove_delayed_node(inode); call_rcu(&inode->i_rcu, btrfs_i_callback); } @@ -7987,6 +8012,9 @@ int btrfs_drop_inode(struct inode *inode) { struct btrfs_root *root = BTRFS_I(inode)->root; + if (root == NULL) + return 1; + /* the snap/subvol tree is on deleting */ if (btrfs_root_refs(&root->root_item) == 0 && root != root->fs_info->tree_root) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0de4a2f..0f81d67 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1801,7 +1801,11 @@ static noinline int copy_to_sk(struct btrfs_root *root, item_off = btrfs_item_ptr_offset(leaf, i); item_len = btrfs_item_size_nr(leaf, i); - if (item_len > BTRFS_SEARCH_ARGS_BUFSIZE) + btrfs_item_key_to_cpu(leaf, key, i); + if (!key_in_sk(key, sk)) + continue; + + if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE) item_len = 0; if (sizeof(sh) + item_len + *sk_offset > @@ -1810,10 +1814,6 @@ static noinline int copy_to_sk(struct btrfs_root *root, goto overflow; } - btrfs_item_key_to_cpu(leaf, key, i); - if (!key_in_sk(key, sk)) - continue; - sh.objectid = key->objectid; sh.offset = key->offset; sh.type = key->type; diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 0740621..0525e13 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1050,7 +1050,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, } /* put a new bio on the list */ - bio = bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1); + bio = btrfs_io_bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1); if (!bio) return -ENOMEM; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 704a1b8..4febca4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1773,7 +1773,7 @@ again: if (!eb || !extent_buffer_uptodate(eb)) { ret = (!eb) ? -ENOMEM : -EIO; free_extent_buffer(eb); - return ret; + break; } btrfs_tree_lock(eb); if (cow) { @@ -3350,6 +3350,11 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info, } truncate: + ret = btrfs_check_trunc_cache_free_space(root, + &fs_info->global_block_rsv); + if (ret) + goto out; + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; @@ -4077,7 +4082,7 @@ out: return inode; } -static struct reloc_control *alloc_reloc_control(void) +static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) { struct reloc_control *rc; @@ -4088,7 +4093,8 @@ static struct reloc_control *alloc_reloc_control(void) INIT_LIST_HEAD(&rc->reloc_roots); backref_cache_init(&rc->backref_cache); mapping_tree_init(&rc->reloc_root_tree); - extent_io_tree_init(&rc->processed_blocks, NULL); + extent_io_tree_init(&rc->processed_blocks, + fs_info->btree_inode->i_mapping); return rc; } @@ -4105,7 +4111,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) int rw = 0; int err = 0; - rc = alloc_reloc_control(); + rc = alloc_reloc_control(fs_info); if (!rc) return -ENOMEM; @@ -4306,7 +4312,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) if (list_empty(&reloc_roots)) goto out; - rc = alloc_reloc_control(); + rc = alloc_reloc_control(root->fs_info); if (!rc) { err = -ENOMEM; goto out; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f489e24..79bd479 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1296,7 +1296,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, } WARN_ON(!page->page); - bio = bio_alloc(GFP_NOFS, 1); + bio = btrfs_io_bio_alloc(GFP_NOFS, 1); if (!bio) { page->io_error = 1; sblock->no_io_error_seen = 0; @@ -1431,7 +1431,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, return -EIO; } - bio = bio_alloc(GFP_NOFS, 1); + bio = btrfs_io_bio_alloc(GFP_NOFS, 1); if (!bio) return -EIO; bio->bi_bdev = page_bad->dev->bdev; @@ -1522,7 +1522,7 @@ again: sbio->dev = wr_ctx->tgtdev; bio = sbio->bio; if (!bio) { - bio = bio_alloc(GFP_NOFS, wr_ctx->pages_per_wr_bio); + bio = btrfs_io_bio_alloc(GFP_NOFS, wr_ctx->pages_per_wr_bio); if (!bio) { mutex_unlock(&wr_ctx->wr_lock); return -ENOMEM; @@ -1930,7 +1930,7 @@ again: sbio->dev = spage->dev; bio = sbio->bio; if (!bio) { - bio = bio_alloc(GFP_NOFS, sctx->pages_per_rd_bio); + bio = btrfs_io_bio_alloc(GFP_NOFS, sctx->pages_per_rd_bio); if (!bio) return -ENOMEM; sbio->bio = bio; @@ -3307,7 +3307,7 @@ static int write_page_nocow(struct scrub_ctx *sctx, "btrfs: scrub write_page_nocow(bdev == NULL) is unexpected!\n"); return -EIO; } - bio = bio_alloc(GFP_NOFS, 1); + bio = btrfs_io_bio_alloc(GFP_NOFS, 1); if (!bio) { spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a4807ce..f0857e0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1263,6 +1263,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); + btrfs_pause_balance(fs_info); ret = btrfs_commit_super(root); if (ret) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0e925ce..8bffb91 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3120,14 +3120,13 @@ int btrfs_balance(struct btrfs_balance_control *bctl, allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE; if (num_devices == 1) allowed |= BTRFS_BLOCK_GROUP_DUP; - else if (num_devices < 4) + else if (num_devices > 1) allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1); - else - allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID10 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID6); - + if (num_devices > 2) + allowed |= BTRFS_BLOCK_GROUP_RAID5; + if (num_devices > 3) + allowed |= (BTRFS_BLOCK_GROUP_RAID10 | + BTRFS_BLOCK_GROUP_RAID6); if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && (!alloc_profile_is_valid(bctl->data.target, 1) || (bctl->data.target & ~allowed))) { @@ -5019,42 +5018,16 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, return 0; } -static void *merge_stripe_index_into_bio_private(void *bi_private, - unsigned int stripe_index) -{ - /* - * with single, dup, RAID0, RAID1 and RAID10, stripe_index is - * at most 1. - * The alternative solution (instead of stealing bits from the - * pointer) would be to allocate an intermediate structure - * that contains the old private pointer plus the stripe_index. - */ - BUG_ON((((uintptr_t)bi_private) & 3) != 0); - BUG_ON(stripe_index > 3); - return (void *)(((uintptr_t)bi_private) | stripe_index); -} - -static struct btrfs_bio *extract_bbio_from_bio_private(void *bi_private) -{ - return (struct btrfs_bio *)(((uintptr_t)bi_private) & ~((uintptr_t)3)); -} - -static unsigned int extract_stripe_index_from_bio_private(void *bi_private) -{ - return (unsigned int)((uintptr_t)bi_private) & 3; -} - static void btrfs_end_bio(struct bio *bio, int err) { - struct btrfs_bio *bbio = extract_bbio_from_bio_private(bio->bi_private); + struct btrfs_bio *bbio = bio->bi_private; int is_orig_bio = 0; if (err) { atomic_inc(&bbio->error); if (err == -EIO || err == -EREMOTEIO) { unsigned int stripe_index = - extract_stripe_index_from_bio_private( - bio->bi_private); + btrfs_io_bio(bio)->stripe_index; struct btrfs_device *dev; BUG_ON(stripe_index >= bbio->num_stripes); @@ -5084,8 +5057,7 @@ static void btrfs_end_bio(struct bio *bio, int err) } bio->bi_private = bbio->private; bio->bi_end_io = bbio->end_io; - bio->bi_bdev = (struct block_device *) - (unsigned long)bbio->mirror_num; + btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; /* only send an error to the higher layers if it is * beyond the tolerance of the btrfs bio */ @@ -5211,8 +5183,7 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio, struct btrfs_device *dev = bbio->stripes[dev_nr].dev; bio->bi_private = bbio; - bio->bi_private = merge_stripe_index_into_bio_private( - bio->bi_private, (unsigned int)dev_nr); + btrfs_io_bio(bio)->stripe_index = dev_nr; bio->bi_end_io = btrfs_end_bio; bio->bi_sector = physical >> 9; #ifdef DEBUG @@ -5273,8 +5244,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) if (atomic_dec_and_test(&bbio->stripes_pending)) { bio->bi_private = bbio->private; bio->bi_end_io = bbio->end_io; - bio->bi_bdev = (struct block_device *) - (unsigned long)bbio->mirror_num; + btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; bio->bi_sector = logical >> 9; kfree(bbio); bio_endio(bio, -EIO); @@ -5352,7 +5322,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, } if (dev_nr < total_devs - 1) { - bio = bio_clone(first_bio, GFP_NOFS); + bio = btrfs_bio_clone(first_bio, GFP_NOFS); BUG_ON(!bio); /* -ENOMEM */ } else { bio = first_bio; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 845ccbb..f6247e2 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -152,6 +152,26 @@ struct btrfs_fs_devices { int rotating; }; +/* + * we need the mirror number and stripe index to be passed around + * the call chain while we are processing end_io (especially errors). + * Really, what we need is a btrfs_bio structure that has this info + * and is properly sized with its stripe array, but we're not there + * quite yet. We have our own btrfs bioset, and all of the bios + * we allocate are actually btrfs_io_bios. We'll cram as much of + * struct btrfs_bio as we can into this over time. + */ +struct btrfs_io_bio { + unsigned long mirror_num; + unsigned long stripe_index; + struct bio bio; +}; + +static inline struct btrfs_io_bio *btrfs_io_bio(struct bio *bio) +{ + return container_of(bio, struct btrfs_io_bio, bio); +} + struct btrfs_bio_stripe { struct btrfs_device *dev; u64 physical; diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 202dd3d6..ebbf680 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -191,27 +191,23 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) } /** - * Encode the flock and fcntl locks for the given inode into the pagelist. - * Format is: #fcntl locks, sequential fcntl locks, #flock locks, - * sequential flock locks. - * Must be called with lock_flocks() already held. - * If we encounter more of a specific lock type than expected, - * we return the value 1. + * Encode the flock and fcntl locks for the given inode into the ceph_filelock + * array. Must be called with lock_flocks() already held. + * If we encounter more of a specific lock type than expected, return -ENOSPC. */ -int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist, - int num_fcntl_locks, int num_flock_locks) +int ceph_encode_locks_to_buffer(struct inode *inode, + struct ceph_filelock *flocks, + int num_fcntl_locks, int num_flock_locks) { struct file_lock *lock; - struct ceph_filelock cephlock; int err = 0; int seen_fcntl = 0; int seen_flock = 0; + int l = 0; dout("encoding %d flock and %d fcntl locks", num_flock_locks, num_fcntl_locks); - err = ceph_pagelist_append(pagelist, &num_fcntl_locks, sizeof(u32)); - if (err) - goto fail; + for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { if (lock->fl_flags & FL_POSIX) { ++seen_fcntl; @@ -219,19 +215,12 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist, err = -ENOSPC; goto fail; } - err = lock_to_ceph_filelock(lock, &cephlock); + err = lock_to_ceph_filelock(lock, &flocks[l]); if (err) goto fail; - err = ceph_pagelist_append(pagelist, &cephlock, - sizeof(struct ceph_filelock)); + ++l; } - if (err) - goto fail; } - - err = ceph_pagelist_append(pagelist, &num_flock_locks, sizeof(u32)); - if (err) - goto fail; for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { if (lock->fl_flags & FL_FLOCK) { ++seen_flock; @@ -239,19 +228,51 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist, err = -ENOSPC; goto fail; } - err = lock_to_ceph_filelock(lock, &cephlock); + err = lock_to_ceph_filelock(lock, &flocks[l]); if (err) goto fail; - err = ceph_pagelist_append(pagelist, &cephlock, - sizeof(struct ceph_filelock)); + ++l; } - if (err) - goto fail; } fail: return err; } +/** + * Copy the encoded flock and fcntl locks into the pagelist. + * Format is: #fcntl locks, sequential fcntl locks, #flock locks, + * sequential flock locks. + * Returns zero on success. + */ +int ceph_locks_to_pagelist(struct ceph_filelock *flocks, + struct ceph_pagelist *pagelist, + int num_fcntl_locks, int num_flock_locks) +{ + int err = 0; + __le32 nlocks; + + nlocks = cpu_to_le32(num_fcntl_locks); + err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks)); + if (err) + goto out_fail; + + err = ceph_pagelist_append(pagelist, flocks, + num_fcntl_locks * sizeof(*flocks)); + if (err) + goto out_fail; + + nlocks = cpu_to_le32(num_flock_locks); + err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks)); + if (err) + goto out_fail; + + err = ceph_pagelist_append(pagelist, + &flocks[num_fcntl_locks], + num_flock_locks * sizeof(*flocks)); +out_fail: + return err; +} + /* * Given a pointer to a lock, convert it to a ceph filelock */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 4f22671..4d29203 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2478,39 +2478,44 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, if (recon_state->flock) { int num_fcntl_locks, num_flock_locks; - struct ceph_pagelist_cursor trunc_point; - - ceph_pagelist_set_cursor(pagelist, &trunc_point); - do { - lock_flocks(); - ceph_count_locks(inode, &num_fcntl_locks, - &num_flock_locks); - rec.v2.flock_len = (2*sizeof(u32) + - (num_fcntl_locks+num_flock_locks) * - sizeof(struct ceph_filelock)); - unlock_flocks(); - - /* pre-alloc pagelist */ - ceph_pagelist_truncate(pagelist, &trunc_point); - err = ceph_pagelist_append(pagelist, &rec, reclen); - if (!err) - err = ceph_pagelist_reserve(pagelist, - rec.v2.flock_len); - - /* encode locks */ - if (!err) { - lock_flocks(); - err = ceph_encode_locks(inode, - pagelist, - num_fcntl_locks, - num_flock_locks); - unlock_flocks(); - } - } while (err == -ENOSPC); + struct ceph_filelock *flocks; + +encode_again: + lock_flocks(); + ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks); + unlock_flocks(); + flocks = kmalloc((num_fcntl_locks+num_flock_locks) * + sizeof(struct ceph_filelock), GFP_NOFS); + if (!flocks) { + err = -ENOMEM; + goto out_free; + } + lock_flocks(); + err = ceph_encode_locks_to_buffer(inode, flocks, + num_fcntl_locks, + num_flock_locks); + unlock_flocks(); + if (err) { + kfree(flocks); + if (err == -ENOSPC) + goto encode_again; + goto out_free; + } + /* + * number of encoded locks is stable, so copy to pagelist + */ + rec.v2.flock_len = cpu_to_le32(2*sizeof(u32) + + (num_fcntl_locks+num_flock_locks) * + sizeof(struct ceph_filelock)); + err = ceph_pagelist_append(pagelist, &rec, reclen); + if (!err) + err = ceph_locks_to_pagelist(flocks, pagelist, + num_fcntl_locks, + num_flock_locks); + kfree(flocks); } else { err = ceph_pagelist_append(pagelist, &rec, reclen); } - out_free: kfree(path); out_dput: diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 8696be2..7ccfdb4 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -822,8 +822,13 @@ extern const struct export_operations ceph_export_ops; extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl); extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl); extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num); -extern int ceph_encode_locks(struct inode *i, struct ceph_pagelist *p, - int p_locks, int f_locks); +extern int ceph_encode_locks_to_buffer(struct inode *inode, + struct ceph_filelock *flocks, + int num_fcntl_locks, + int num_flock_locks); +extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks, + struct ceph_pagelist *pagelist, + int num_fcntl_locks, int num_flock_locks); extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c); /* debugfs.c */ diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 8e33ec6..58df174 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/vfs.h> #include <linux/fs.h> +#include <linux/inet.h> #include "cifsglob.h" #include "cifsproto.h" #include "cifsfs.h" @@ -48,58 +49,74 @@ void cifs_dfs_release_automount_timer(void) } /** - * cifs_get_share_name - extracts share name from UNC - * @node_name: pointer to UNC string + * cifs_build_devname - build a devicename from a UNC and optional prepath + * @nodename: pointer to UNC string + * @prepath: pointer to prefixpath (or NULL if there isn't one) * - * Extracts sharename form full UNC. - * i.e. strips from UNC trailing path that is not part of share - * name and fixup missing '\' in the beginning of DFS node refferal - * if necessary. - * Returns pointer to share name on success or ERR_PTR on error. - * Caller is responsible for freeing returned string. + * Build a new cifs devicename after chasing a DFS referral. Allocate a buffer + * big enough to hold the final thing. Copy the UNC from the nodename, and + * concatenate the prepath onto the end of it if there is one. + * + * Returns pointer to the built string, or a ERR_PTR. Caller is responsible + * for freeing the returned string. */ -static char *cifs_get_share_name(const char *node_name) +static char * +cifs_build_devname(char *nodename, const char *prepath) { - int len; - char *UNC; - char *pSep; - - len = strlen(node_name); - UNC = kmalloc(len+2 /*for term null and additional \ if it's missed */, - GFP_KERNEL); - if (!UNC) - return ERR_PTR(-ENOMEM); + size_t pplen; + size_t unclen; + char *dev; + char *pos; + + /* skip over any preceding delimiters */ + nodename += strspn(nodename, "\\"); + if (!*nodename) + return ERR_PTR(-EINVAL); - /* get share name and server name */ - if (node_name[1] != '\\') { - UNC[0] = '\\'; - strncpy(UNC+1, node_name, len); - len++; - UNC[len] = 0; - } else { - strncpy(UNC, node_name, len); - UNC[len] = 0; - } + /* get length of UNC and set pos to last char */ + unclen = strlen(nodename); + pos = nodename + unclen - 1; - /* find server name end */ - pSep = memchr(UNC+2, '\\', len-2); - if (!pSep) { - cifs_dbg(VFS, "%s: no server name end in node name: %s\n", - __func__, node_name); - kfree(UNC); - return ERR_PTR(-EINVAL); + /* trim off any trailing delimiters */ + while (*pos == '\\') { + --pos; + --unclen; } - /* find sharename end */ - pSep++; - pSep = memchr(UNC+(pSep-UNC), '\\', len-(pSep-UNC)); - if (pSep) { - /* trim path up to sharename end - * now we have share name in UNC */ - *pSep = 0; + /* allocate a buffer: + * +2 for preceding "//" + * +1 for delimiter between UNC and prepath + * +1 for trailing NULL + */ + pplen = prepath ? strlen(prepath) : 0; + dev = kmalloc(2 + unclen + 1 + pplen + 1, GFP_KERNEL); + if (!dev) + return ERR_PTR(-ENOMEM); + + pos = dev; + /* add the initial "//" */ + *pos = '/'; + ++pos; + *pos = '/'; + ++pos; + + /* copy in the UNC portion from referral */ + memcpy(pos, nodename, unclen); + pos += unclen; + + /* copy the prefixpath remainder (if there is one) */ + if (pplen) { + *pos = '/'; + ++pos; + memcpy(pos, prepath, pplen); + pos += pplen; } - return UNC; + /* NULL terminator */ + *pos = '\0'; + + convert_delimiter(dev, '/'); + return dev; } @@ -123,6 +140,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, { int rc; char *mountdata = NULL; + const char *prepath = NULL; int md_len; char *tkn_e; char *srvIP = NULL; @@ -132,7 +150,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata, if (sb_mountdata == NULL) return ERR_PTR(-EINVAL); - *devname = cifs_get_share_name(ref->node_name); + if (strlen(fullpath) - ref->path_consumed) + prepath = fullpath + ref->path_consumed; + + *devname = cifs_build_devname(ref->node_name, prepath); if (IS_ERR(*devname)) { rc = PTR_ERR(*devname); *devname = NULL; @@ -146,12 +167,14 @@ char *cifs_compose_mount_options(const char *sb_mountdata, goto compose_mount_options_err; } - /* md_len = strlen(...) + 12 for 'sep+prefixpath=' - * assuming that we have 'unc=' and 'ip=' in - * the original sb_mountdata + /* + * In most cases, we'll be building a shorter string than the original, + * but we do have to assume that the address in the ip= option may be + * much longer than the original. Add the max length of an address + * string to the length of the original string to allow for worst case. */ - md_len = strlen(sb_mountdata) + rc + strlen(ref->node_name) + 12; - mountdata = kzalloc(md_len+1, GFP_KERNEL); + md_len = strlen(sb_mountdata) + INET6_ADDRSTRLEN; + mountdata = kzalloc(md_len + 1, GFP_KERNEL); if (mountdata == NULL) { rc = -ENOMEM; goto compose_mount_options_err; @@ -195,26 +218,6 @@ char *cifs_compose_mount_options(const char *sb_mountdata, strncat(mountdata, &sep, 1); strcat(mountdata, "ip="); strcat(mountdata, srvIP); - strncat(mountdata, &sep, 1); - strcat(mountdata, "unc="); - strcat(mountdata, *devname); - - /* find & copy prefixpath */ - tkn_e = strchr(ref->node_name + 2, '\\'); - if (tkn_e == NULL) { - /* invalid unc, missing share name*/ - rc = -EINVAL; - goto compose_mount_options_err; - } - - tkn_e = strchr(tkn_e + 1, '\\'); - if (tkn_e || (strlen(fullpath) - ref->path_consumed)) { - strncat(mountdata, &sep, 1); - strcat(mountdata, "prefixpath="); - if (tkn_e) - strcat(mountdata, tkn_e + 1); - strcat(mountdata, fullpath + ref->path_consumed); - } /*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/ /*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 72e4efe..3752b9f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -372,9 +372,6 @@ cifs_show_options(struct seq_file *s, struct dentry *root) cifs_show_security(s, tcon->ses->server); cifs_show_cache_flavor(s, cifs_sb); - seq_printf(s, ",unc="); - seq_escape(s, tcon->treeName, " \t\n\\"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) seq_printf(s, ",multiuser"); else if (tcon->ses->user_name) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 99eeaa1..e3bc39b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1061,6 +1061,7 @@ static int cifs_parse_security_flavors(char *value, #endif case Opt_sec_none: vol->nullauth = 1; + vol->secFlg |= CIFSSEC_MAY_NTLM; break; default: cifs_dbg(VFS, "bad security option: %s\n", value); @@ -1257,14 +1258,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->backupuid_specified = false; /* no backup intent for a user */ vol->backupgid_specified = false; /* no backup intent for a group */ - /* - * For now, we ignore -EINVAL errors under the assumption that the - * unc= and prefixpath= options will be usable. - */ - if (cifs_parse_devname(devname, vol) == -ENOMEM) { - printk(KERN_ERR "CIFS: Unable to allocate memory to parse " - "device string.\n"); - goto out_nomem; + switch (cifs_parse_devname(devname, vol)) { + case 0: + break; + case -ENOMEM: + cifs_dbg(VFS, "Unable to allocate memory for devname.\n"); + goto cifs_parse_mount_err; + case -EINVAL: + cifs_dbg(VFS, "Malformed UNC in devname.\n"); + goto cifs_parse_mount_err; + default: + cifs_dbg(VFS, "Unknown error parsing devname.\n"); + goto cifs_parse_mount_err; } while ((data = strsep(&options, separator)) != NULL) { @@ -1826,7 +1831,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } #endif if (!vol->UNC) { - cifs_dbg(VFS, "CIFS mount error: No usable UNC path provided in device string or in unc= option!\n"); + cifs_dbg(VFS, "CIFS mount error: No usable UNC path provided in device string!\n"); goto cifs_parse_mount_err; } @@ -3274,8 +3279,8 @@ build_unc_path_to_root(const struct smb_vol *vol, pos = full_path + unc_len; if (pplen) { - *pos++ = CIFS_DIR_SEP(cifs_sb); - strncpy(pos, vol->prepath, pplen); + *pos = CIFS_DIR_SEP(cifs_sb); + strncpy(pos + 1, vol->prepath, pplen); pos += pplen; } diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index e7512e4..7ede730 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -34,7 +34,7 @@ /** * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address. - * @unc: UNC path specifying the server + * @unc: UNC path specifying the server (with '/' as delimiter) * @ip_addr: Where to return the IP address. * * The IP address will be returned in string form, and the caller is @@ -64,7 +64,7 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) hostname = unc + 2; /* Search for server name delimiter */ - sep = memchr(hostname, '\\', len); + sep = memchr(hostname, '/', len); if (sep) len = sep - hostname; else diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index fc30251..20efd81 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -171,7 +171,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL) inode->i_flags |= S_AUTOMOUNT; - cifs_set_ops(inode); + if (inode->i_state & I_NEW) + cifs_set_ops(inode); } void diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 201f0a0..a7abbea 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -295,6 +295,12 @@ static int ecryptfs_release(struct inode *inode, struct file *file) static int ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { + int rc; + + rc = filemap_write_and_wait(file->f_mapping); + if (rc) + return rc; + return vfs_fsync(ecryptfs_file_to_lower(file), datasync); } diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index bfb5315..8dd524f 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -44,8 +44,11 @@ static ssize_t efivarfs_file_write(struct file *file, bytes = efivar_entry_set_get_size(var, attributes, &datasize, data, &set); - if (!set && bytes) + if (!set && bytes) { + if (bytes == -ENOENT) + bytes = -EIO; goto out; + } if (bytes == -ENOENT) { drop_nlink(inode); @@ -76,7 +79,14 @@ static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf, int err; err = efivar_entry_size(var, &datasize); - if (err) + + /* + * efivarfs represents uncommitted variables with + * zero-length files. Reading them should return EOF. + */ + if (err == -ENOENT) + return 0; + else if (err) return err; data = kmalloc(datasize + sizeof(attributes), GFP_KERNEL); @@ -1135,13 +1135,6 @@ void setup_new_exec(struct linux_binprm * bprm) set_dumpable(current->mm, suid_dumpable); } - /* - * Flush performance counters when crossing a - * security domain: - */ - if (!get_dumpable(current->mm)) - perf_event_exit_task(current); - /* An exec changes our domain. We are no longer part of the thread group */ @@ -1205,6 +1198,15 @@ void install_exec_creds(struct linux_binprm *bprm) commit_creds(bprm->cred); bprm->cred = NULL; + + /* + * Disable monitoring for regular users + * when executing setuid binaries. Must + * wait until new credentials are committed + * by commit_creds() above + */ + if (get_dumpable(current->mm) != SUID_DUMP_USER) + perf_event_exit_task(current); /* * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's diff --git a/fs/fat/inode.c b/fs/fat/inode.c index dfce656..5d4513c 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1229,6 +1229,19 @@ static int fat_read_root(struct inode *inode) return 0; } +static unsigned long calc_fat_clusters(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + /* Divide first to avoid overflow */ + if (sbi->fat_bits != 12) { + unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; + return ent_per_sec * sbi->fat_length; + } + + return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; +} + /* * Read the super block of an MS-DOS FS. */ @@ -1434,7 +1447,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, sbi->dirty = b->fat16.state & FAT_STATE_DIRTY; /* check that FAT table does not overflow */ - fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; + fat_clusters = calc_fat_clusters(sb); total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); if (total_clusters > MAX_FAT(sb)) { if (!silent) diff --git a/fs/file_table.c b/fs/file_table.c index cd4d87a..485dc0e 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -306,17 +306,18 @@ void fput(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; + unsigned long flags; + file_sb_list_del(file); - if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) { - unsigned long flags; - spin_lock_irqsave(&delayed_fput_lock, flags); - list_add(&file->f_u.fu_list, &delayed_fput_list); - schedule_work(&delayed_fput_work); - spin_unlock_irqrestore(&delayed_fput_lock, flags); - return; + if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { + init_task_work(&file->f_u.fu_rcuhead, ____fput); + if (!task_work_add(task, &file->f_u.fu_rcuhead, true)) + return; } - init_task_work(&file->f_u.fu_rcuhead, ____fput); - task_work_add(task, &file->f_u.fu_rcuhead, true); + spin_lock_irqsave(&delayed_fput_lock, flags); + list_add(&file->f_u.fu_list, &delayed_fput_list); + schedule_work(&delayed_fput_work); + spin_unlock_irqrestore(&delayed_fput_lock, flags); } } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 254df56..f3f783d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -180,6 +180,8 @@ u64 fuse_get_attr_version(struct fuse_conn *fc) static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) { struct inode *inode; + struct dentry *parent; + struct fuse_conn *fc; inode = ACCESS_ONCE(entry->d_inode); if (inode && is_bad_inode(inode)) @@ -187,10 +189,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) else if (fuse_dentry_time(entry) < get_jiffies_64()) { int err; struct fuse_entry_out outarg; - struct fuse_conn *fc; struct fuse_req *req; struct fuse_forget_link *forget; - struct dentry *parent; u64 attr_version; /* For negative dentries, always do a fresh lookup */ @@ -241,8 +241,14 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) entry_attr_timeout(&outarg), attr_version); fuse_change_entry_timeout(entry, &outarg); + } else if (inode) { + fc = get_fuse_conn(inode); + if (fc->readdirplus_auto) { + parent = dget_parent(entry); + fuse_advise_use_readdirplus(parent->d_inode); + dput(parent); + } } - fuse_advise_use_readdirplus(inode); return 1; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index d1c9b85..35f2810 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -16,6 +16,7 @@ #include <linux/compat.h> #include <linux/swap.h> #include <linux/aio.h> +#include <linux/falloc.h> static const struct file_operations fuse_direct_io_file_operations; @@ -1278,7 +1279,10 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, iov_iter_init(&ii, iov, nr_segs, count, 0); - req = fuse_get_req(fc, fuse_iter_npages(&ii)); + if (io->async) + req = fuse_get_req_for_background(fc, fuse_iter_npages(&ii)); + else + req = fuse_get_req(fc, fuse_iter_npages(&ii)); if (IS_ERR(req)) return PTR_ERR(req); @@ -1314,7 +1318,11 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, break; if (count) { fuse_put_request(fc, req); - req = fuse_get_req(fc, fuse_iter_npages(&ii)); + if (io->async) + req = fuse_get_req_for_background(fc, + fuse_iter_npages(&ii)); + else + req = fuse_get_req(fc, fuse_iter_npages(&ii)); if (IS_ERR(req)) break; } @@ -2365,6 +2373,11 @@ static void fuse_do_truncate(struct file *file) fuse_do_setattr(inode, &attr, file); } +static inline loff_t fuse_round_up(loff_t off) +{ + return round_up(off, FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); +} + static ssize_t fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, unsigned long nr_segs) @@ -2372,6 +2385,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; + bool async_dio = ff->fc->async_dio; loff_t pos = 0; struct inode *inode; loff_t i_size; @@ -2383,10 +2397,10 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, i_size = i_size_read(inode); /* optimization for short read */ - if (rw != WRITE && offset + count > i_size) { + if (async_dio && rw != WRITE && offset + count > i_size) { if (offset >= i_size) return 0; - count = i_size - offset; + count = min_t(loff_t, count, fuse_round_up(i_size - offset)); } io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); @@ -2404,7 +2418,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * By default, we want to optimize all I/Os with async request * submission to the client filesystem if supported. */ - io->async = ff->fc->async_dio; + io->async = async_dio; io->iocb = iocb; /* @@ -2412,7 +2426,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * to wait on real async I/O requests, so we must submit this request * synchronously. */ - if (!is_sync_kiocb(iocb) && (offset + count > i_size)) + if (!is_sync_kiocb(iocb) && (offset + count > i_size) && rw == WRITE) io->async = false; if (rw == WRITE) @@ -2424,7 +2438,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, fuse_aio_complete(io, ret < 0 ? ret : 0, -1); /* we have a non-extending, async request, so return */ - if (ret > 0 && !is_sync_kiocb(iocb)) + if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; ret = wait_on_sync_kiocb(iocb); @@ -2446,6 +2460,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, loff_t length) { struct fuse_file *ff = file->private_data; + struct inode *inode = file->f_inode; struct fuse_conn *fc = ff->fc; struct fuse_req *req; struct fuse_fallocate_in inarg = { @@ -2455,13 +2470,23 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, .mode = mode }; int err; + bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) || + (mode & FALLOC_FL_PUNCH_HOLE); if (fc->no_fallocate) return -EOPNOTSUPP; + if (lock_inode) { + mutex_lock(&inode->i_mutex); + if (mode & FALLOC_FL_PUNCH_HOLE) + fuse_set_nowrite(inode); + } + req = fuse_get_req_nopages(fc); - if (IS_ERR(req)) - return PTR_ERR(req); + if (IS_ERR(req)) { + err = PTR_ERR(req); + goto out; + } req->in.h.opcode = FUSE_FALLOCATE; req->in.h.nodeid = ff->nodeid; @@ -2476,6 +2501,25 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, } fuse_put_request(fc, req); + if (err) + goto out; + + /* we could have extended the file */ + if (!(mode & FALLOC_FL_KEEP_SIZE)) + fuse_write_update_size(inode, offset + length); + + if (mode & FALLOC_FL_PUNCH_HOLE) + truncate_pagecache_range(inode, offset, offset + length - 1); + + fuse_invalidate_attr(inode); + +out: + if (lock_inode) { + if (mode & FALLOC_FL_PUNCH_HOLE) + fuse_release_nowrite(inode); + mutex_unlock(&inode->i_mutex); + } + return err; } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 6201f81..9a0cdde 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -867,10 +867,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->dont_mask = 1; if (arg->flags & FUSE_AUTO_INVAL_DATA) fc->auto_inval_data = 1; - if (arg->flags & FUSE_DO_READDIRPLUS) + if (arg->flags & FUSE_DO_READDIRPLUS) { fc->do_readdirplus = 1; - if (arg->flags & FUSE_READDIRPLUS_AUTO) - fc->readdirplus_auto = 1; + if (arg->flags & FUSE_READDIRPLUS_AUTO) + fc->readdirplus_auto = 1; + } if (arg->flags & FUSE_ASYNC_DIO) fc->async_dio = 1; } else { diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index eb08c9e..5a376ab 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -26,7 +26,7 @@ config GFS2_FS config GFS2_FS_LOCKING_DLM bool "GFS2 DLM locking" depends on (GFS2_FS!=n) && NET && INET && (IPV6 || IPV6=n) && \ - HOTPLUG && DLM && CONFIGFS_FS && SYSFS + HOTPLUG && CONFIGFS_FS && SYSFS && (DLM=y || DLM=GFS2_FS) help Multiple node locking module for GFS2 diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 1dc9a13..93b5809 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1286,17 +1286,26 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) if (ret) return ret; + ret = get_write_access(inode); + if (ret) + return ret; + inode_dio_wait(inode); ret = gfs2_rs_alloc(GFS2_I(inode)); if (ret) - return ret; + goto out; oldsize = inode->i_size; - if (newsize >= oldsize) - return do_grow(inode, newsize); + if (newsize >= oldsize) { + ret = do_grow(inode, newsize); + goto out; + } - return do_shrink(inode, oldsize, newsize); + ret = do_shrink(inode, oldsize, newsize); +out: + put_write_access(inode); + return ret; } int gfs2_truncatei_resume(struct gfs2_inode *ip) diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index c3e82bd..b631c90 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -354,22 +354,31 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) return ERR_PTR(-EIO); } - hc = kmalloc(hsize, GFP_NOFS); - ret = -ENOMEM; + hc = kmalloc(hsize, GFP_NOFS | __GFP_NOWARN); + if (hc == NULL) + hc = __vmalloc(hsize, GFP_NOFS, PAGE_KERNEL); + if (hc == NULL) return ERR_PTR(-ENOMEM); ret = gfs2_dir_read_data(ip, hc, hsize); if (ret < 0) { - kfree(hc); + if (is_vmalloc_addr(hc)) + vfree(hc); + else + kfree(hc); return ERR_PTR(ret); } spin_lock(&inode->i_lock); - if (ip->i_hash_cache) - kfree(hc); - else + if (ip->i_hash_cache) { + if (is_vmalloc_addr(hc)) + vfree(hc); + else + kfree(hc); + } else { ip->i_hash_cache = hc; + } spin_unlock(&inode->i_lock); return ip->i_hash_cache; @@ -385,7 +394,10 @@ void gfs2_dir_hash_inval(struct gfs2_inode *ip) { __be64 *hc = ip->i_hash_cache; ip->i_hash_cache = NULL; - kfree(hc); + if (is_vmalloc_addr(hc)) + vfree(hc); + else + kfree(hc); } static inline int gfs2_dirent_sentinel(const struct gfs2_dirent *dent) @@ -1113,7 +1125,10 @@ static int dir_double_exhash(struct gfs2_inode *dip) if (IS_ERR(hc)) return PTR_ERR(hc); - h = hc2 = kmalloc(hsize_bytes * 2, GFP_NOFS); + h = hc2 = kmalloc(hsize_bytes * 2, GFP_NOFS | __GFP_NOWARN); + if (hc2 == NULL) + hc2 = __vmalloc(hsize_bytes * 2, GFP_NOFS, PAGE_KERNEL); + if (!hc2) return -ENOMEM; @@ -1145,7 +1160,10 @@ fail: gfs2_dinode_out(dip, dibh->b_data); brelse(dibh); out_kfree: - kfree(hc2); + if (is_vmalloc_addr(hc2)) + vfree(hc2); + else + kfree(hc2); return error; } @@ -1846,6 +1864,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, memset(&rlist, 0, sizeof(struct gfs2_rgrp_list)); ht = kzalloc(size, GFP_NOFS); + if (ht == NULL) + ht = vzalloc(size); if (!ht) return -ENOMEM; @@ -1933,7 +1953,10 @@ out_rlist: gfs2_rlist_free(&rlist); gfs2_quota_unhold(dip); out: - kfree(ht); + if (is_vmalloc_addr(ht)) + vfree(ht); + else + kfree(ht); return error; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index acd1676..ad0dc38 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -402,16 +402,20 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) /* Update file times before taking page lock */ file_update_time(vma->vm_file); + ret = get_write_access(inode); + if (ret) + goto out; + ret = gfs2_rs_alloc(ip); if (ret) - return ret; + goto out_write_access; gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); if (ret) - goto out; + goto out_uninit; set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); set_bit(GIF_SW_PAGED, &ip->i_flags); @@ -480,12 +484,15 @@ out_quota_unlock: gfs2_quota_unlock(ip); out_unlock: gfs2_glock_dq(&gh); -out: +out_uninit: gfs2_holder_uninit(&gh); if (ret == 0) { set_page_dirty(page); wait_for_stable_page(page); } +out_write_access: + put_write_access(inode); +out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); } @@ -594,10 +601,10 @@ static int gfs2_release(struct inode *inode, struct file *file) kfree(file->private_data); file->private_data = NULL; - if ((file->f_mode & FMODE_WRITE) && - (atomic_read(&inode->i_writecount) == 1)) - gfs2_rs_delete(ip); + if (!(file->f_mode & FMODE_WRITE)) + return 0; + gfs2_rs_delete(ip); return 0; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 8833a4f..62b484e 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -189,6 +189,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, return inode; fail_refresh: + ip->i_iopen_gh.gh_flags |= GL_NOCACHE; ip->i_iopen_gh.gh_gl->gl_object = NULL; gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_iopen: diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index c5fa758..6c33d7b 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -212,7 +212,7 @@ static void gfs2_end_log_write(struct bio *bio, int error) fs_err(sdp, "Error %d writing to log\n", error); } - bio_for_each_segment(bvec, bio, i) { + bio_for_each_segment_all(bvec, bio, i) { page = bvec->bv_page; if (page_has_buffers(page)) gfs2_end_log_write_bh(sdp, bvec, error); @@ -419,7 +419,9 @@ static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit, if (total > limit) num = limit; gfs2_log_unlock(sdp); - page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA, num + 1, num); + page = gfs2_get_log_desc(sdp, + is_databuf ? GFS2_LOG_DESC_JDATA : + GFS2_LOG_DESC_METADATA, num + 1, num); ld = page_address(page); gfs2_log_lock(sdp); ptr = (__be64 *)(ld + 1); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c7c840e..c253b13 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -121,7 +121,7 @@ static u64 qd2index(struct gfs2_quota_data *qd) { struct kqid qid = qd->qd_id; return (2 * (u64)from_kqid(&init_user_ns, qid)) + - (qid.type == USRQUOTA) ? 0 : 1; + ((qid.type == USRQUOTA) ? 0 : 1); } static u64 qd2offset(struct gfs2_quota_data *qd) @@ -721,7 +721,7 @@ get_a_page: goto unlock_out; } - gfs2_trans_add_meta(ip->i_gl, bh); + gfs2_trans_add_data(ip->i_gl, bh); kaddr = kmap_atomic(page); if (offset + sizeof(struct gfs2_quota) > PAGE_CACHE_SIZE) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 0c5a575..9809156 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -638,8 +638,10 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs) */ void gfs2_rs_delete(struct gfs2_inode *ip) { + struct inode *inode = &ip->i_inode; + down_write(&ip->i_rw_mutex); - if (ip->i_res) { + if (ip->i_res && atomic_read(&inode->i_writecount) <= 1) { gfs2_rs_deltree(ip->i_res); BUG_ON(ip->i_res->rs_free); kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); @@ -1401,9 +1403,14 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip, u32 extlen; u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved; int ret; + struct inode *inode = &ip->i_inode; - extlen = max_t(u32, atomic_read(&rs->rs_sizehint), requested); - extlen = clamp(extlen, RGRP_RSRV_MINBLKS, free_blocks); + if (S_ISDIR(inode->i_mode)) + extlen = 1; + else { + extlen = max_t(u32, atomic_read(&rs->rs_sizehint), requested); + extlen = clamp(extlen, RGRP_RSRV_MINBLKS, free_blocks); + } if ((rgd->rd_free_clone < rgd->rd_reserved) || (free_blocks < extlen)) return; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 917c8e1..e5639de 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1444,6 +1444,7 @@ static void gfs2_evict_inode(struct inode *inode) /* Must not read inode block until block type has been verified */ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh); if (unlikely(error)) { + ip->i_iopen_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&ip->i_iopen_gh); goto out; } @@ -1514,8 +1515,10 @@ out_unlock: if (gfs2_rs_active(ip->i_res)) gfs2_rs_deltree(ip->i_res); - if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) + if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { + ip->i_iopen_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq(&ip->i_iopen_gh); + } gfs2_holder_uninit(&ip->i_iopen_gh); gfs2_glock_dq_uninit(&gh); if (error && error != GLR_TRYFAILED && error != -EROFS) @@ -1534,6 +1537,7 @@ out: ip->i_gl = NULL; if (ip->i_iopen_gh.gh_gl) { ip->i_iopen_gh.gh_gl->gl_object = NULL; + ip->i_iopen_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&ip->i_iopen_gh); } } diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index f3b1a15..d3fa6bd 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -415,7 +415,11 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, num); spin_unlock(&tree->hash_lock); - BUG_ON(node); + if (node) { + pr_crit("new node %u already hashed?\n", num); + WARN_ON(1); + return node; + } node = __hfs_bnode_create(tree, num); if (!node) return ERR_PTR(-ENOMEM); diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index 546f6d3..834ac13 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -33,25 +33,27 @@ static loff_t hpfs_dir_lseek(struct file *filp, loff_t off, int whence) if (whence == SEEK_DATA || whence == SEEK_HOLE) return -EINVAL; + mutex_lock(&i->i_mutex); hpfs_lock(s); /*printk("dir lseek\n");*/ if (new_off == 0 || new_off == 1 || new_off == 11 || new_off == 12 || new_off == 13) goto ok; - mutex_lock(&i->i_mutex); pos = ((loff_t) hpfs_de_as_down_as_possible(s, hpfs_inode->i_dno) << 4) + 1; while (pos != new_off) { if (map_pos_dirent(i, &pos, &qbh)) hpfs_brelse4(&qbh); else goto fail; if (pos == 12) goto fail; } - mutex_unlock(&i->i_mutex); + hpfs_add_pos(i, &filp->f_pos); ok: + filp->f_pos = new_off; hpfs_unlock(s); - return filp->f_pos = new_off; -fail: mutex_unlock(&i->i_mutex); + return new_off; +fail: /*printk("illegal lseek: %016llx\n", new_off);*/ hpfs_unlock(s); + mutex_unlock(&i->i_mutex); return -ESPIPE; } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 3027f4d..e4ba5fe 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -109,10 +109,14 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; + hpfs_lock(inode->i_sb); + if (to > inode->i_size) { truncate_pagecache(inode, to, inode->i_size); hpfs_truncate(inode); } + + hpfs_unlock(inode->i_sb); } static int hpfs_write_begin(struct file *file, struct address_space *mapping, diff --git a/fs/internal.h b/fs/internal.h index eaa75f7..6812158 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -132,6 +132,12 @@ extern struct dentry *__d_alloc(struct super_block *, const struct qstr *); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); /* + * splice.c + */ +extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len, unsigned int flags); + +/* * pipe.c */ extern const struct file_operations pipefifo_fops; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index c57499d..360d27c 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -2009,7 +2009,13 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bio->bi_end_io = lbmIODone; bio->bi_private = bp; - submit_bio(READ_SYNC, bio); + /*check if journaling to disk has been disabled*/ + if (log->no_integrity) { + bio->bi_size = 0; + lbmIODone(bio, 0); + } else { + submit_bio(READ_SYNC, bio); + } wait_event(bp->l_ioevent, (bp->l_flag != lbmREAD)); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 2003e83..788e0a9 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -611,11 +611,28 @@ static int jfs_freeze(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; + int rc = 0; if (!(sb->s_flags & MS_RDONLY)) { txQuiesce(sb); - lmLogShutdown(log); - updateSuper(sb, FM_CLEAN); + rc = lmLogShutdown(log); + if (rc) { + jfs_error(sb, "jfs_freeze: lmLogShutdown failed"); + + /* let operations fail rather than hang */ + txResume(sb); + + return rc; + } + rc = updateSuper(sb, FM_CLEAN); + if (rc) { + jfs_err("jfs_freeze: updateSuper failed\n"); + /* + * Don't fail here. Everything succeeded except + * marking the superblock clean, so there's really + * no harm in leaving it frozen for now. + */ + } } return 0; } @@ -627,13 +644,18 @@ static int jfs_unfreeze(struct super_block *sb) int rc = 0; if (!(sb->s_flags & MS_RDONLY)) { - updateSuper(sb, FM_MOUNT); - if ((rc = lmLogInit(log))) - jfs_err("jfs_unlock failed with return code %d", rc); - else - txResume(sb); + rc = updateSuper(sb, FM_MOUNT); + if (rc) { + jfs_error(sb, "jfs_unfreeze: updateSuper failed"); + goto out; + } + rc = lmLogInit(log); + if (rc) + jfs_error(sb, "jfs_unfreeze: lmLogInit failed"); +out: + txResume(sb); } - return 0; + return rc; } static struct dentry *jfs_do_mount(struct file_system_type *fs_type, @@ -1976,7 +1976,7 @@ static int path_lookupat(int dfd, const char *name, err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) { - if (!nd->inode->i_op->lookup) { + if (!can_lookup(nd->inode)) { path_put(&nd->path); err = -ENOTDIR; } @@ -2850,7 +2850,7 @@ finish_lookup: if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode)) goto out; error = -ENOTDIR; - if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup) + if ((nd->flags & LOOKUP_DIRECTORY) && !can_lookup(nd->inode)) goto out; audit_inode(name, nd->path.dentry, 0); finish_open: diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 8163260..6792ce1 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -1029,15 +1029,6 @@ static int ncp_rmdir(struct inode *dir, struct dentry *dentry) DPRINTK("ncp_rmdir: removing %s/%s\n", dentry->d_parent->d_name.name, dentry->d_name.name); - /* - * fail with EBUSY if there are still references to this - * directory. - */ - dentry_unhash(dentry); - error = -EBUSY; - if (!d_unhashed(dentry)) - goto out; - len = sizeof(__name); error = ncp_io2vol(server, __name, &len, dentry->d_name.name, dentry->d_name.len, !ncp_preserve_case(dir)); diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index a13d26e..0bc2768 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -414,7 +414,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, spin_lock(&tbl->slot_tbl_lock); /* state manager is resetting the session */ - if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) { + if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) { spin_unlock(&tbl->slot_tbl_lock); status = htonl(NFS4ERR_DELAY); /* Return NFS4ERR_BADSESSION if we're draining the session diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 59461c9..a35582c 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -763,7 +763,7 @@ static void nfs4_callback_free_slot(struct nfs4_session *session) * A single slot, so highest used slotid is either 0 or -1 */ tbl->highest_used_slotid = NFS4_NO_SLOT; - nfs4_session_drain_complete(session, tbl); + nfs4_slot_tbl_drain_complete(tbl); spin_unlock(&tbl->slot_tbl_lock); } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 947b0c9..4cbad5d 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -203,7 +203,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I); if (error == -EINVAL) - error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_NULL); + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); if (error < 0) goto error; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8fbc100..d7ba561 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -572,7 +572,7 @@ int nfs41_setup_sequence(struct nfs4_session *session, task->tk_timeout = 0; spin_lock(&tbl->slot_tbl_lock); - if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) && + if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state) && !args->sa_privileged) { /* The state manager will wait until the slot table is empty */ dprintk("%s session is draining\n", __func__); @@ -1078,7 +1078,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) struct nfs4_state *state = opendata->state; struct nfs_inode *nfsi = NFS_I(state->inode); struct nfs_delegation *delegation; - int open_mode = opendata->o_arg.open_flags & (O_EXCL|O_TRUNC); + int open_mode = opendata->o_arg.open_flags; fmode_t fmode = opendata->o_arg.fmode; nfs4_stateid stateid; int ret = -EAGAIN; diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index ebda5f4..c4e225e 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -73,7 +73,7 @@ void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot) tbl->highest_used_slotid = new_max; else { tbl->highest_used_slotid = NFS4_NO_SLOT; - nfs4_session_drain_complete(tbl->session, tbl); + nfs4_slot_tbl_drain_complete(tbl); } } dprintk("%s: slotid %u highest_used_slotid %d\n", __func__, @@ -226,7 +226,7 @@ static bool nfs41_assign_slot(struct rpc_task *task, void *pslot) struct nfs4_slot *slot = pslot; struct nfs4_slot_table *tbl = slot->table; - if (nfs4_session_draining(tbl->session) && !args->sa_privileged) + if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged) return false; slot->generation = tbl->generation; args->sa_slot = slot; diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 6f3cb39..ff7d9f0 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -25,6 +25,10 @@ struct nfs4_slot { }; /* Sessions */ +enum nfs4_slot_tbl_state { + NFS4_SLOT_TBL_DRAINING, +}; + #define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long)) struct nfs4_slot_table { struct nfs4_session *session; /* Parent session */ @@ -43,6 +47,7 @@ struct nfs4_slot_table { unsigned long generation; /* Generation counter for target_highest_slotid */ struct completion complete; + unsigned long slot_tbl_state; }; /* @@ -68,7 +73,6 @@ struct nfs4_session { enum nfs4_session_state { NFS4_SESSION_INITING, - NFS4_SESSION_DRAINING, }; #if defined(CONFIG_NFS_V4_1) @@ -88,12 +92,11 @@ extern void nfs4_destroy_session(struct nfs4_session *session); extern int nfs4_init_session(struct nfs_server *server); extern int nfs4_init_ds_session(struct nfs_client *, unsigned long); -extern void nfs4_session_drain_complete(struct nfs4_session *session, - struct nfs4_slot_table *tbl); +extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); -static inline bool nfs4_session_draining(struct nfs4_session *session) +static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl) { - return !!test_bit(NFS4_SESSION_DRAINING, &session->session_state); + return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); } bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 300d17d..1fab140 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -241,7 +241,7 @@ static void nfs4_end_drain_session(struct nfs_client *clp) if (ses == NULL) return; tbl = &ses->fc_slot_table; - if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) { + if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) { spin_lock(&tbl->slot_tbl_lock); nfs41_wake_slot_table(tbl); spin_unlock(&tbl->slot_tbl_lock); @@ -251,15 +251,15 @@ static void nfs4_end_drain_session(struct nfs_client *clp) /* * Signal state manager thread if session fore channel is drained */ -void nfs4_session_drain_complete(struct nfs4_session *session, - struct nfs4_slot_table *tbl) +void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl) { - if (nfs4_session_draining(session)) + if (nfs4_slot_tbl_draining(tbl)) complete(&tbl->complete); } -static int nfs4_wait_on_slot_tbl(struct nfs4_slot_table *tbl) +static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl) { + set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); spin_lock(&tbl->slot_tbl_lock); if (tbl->highest_used_slotid != NFS4_NO_SLOT) { INIT_COMPLETION(tbl->complete); @@ -275,13 +275,12 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) struct nfs4_session *ses = clp->cl_session; int ret = 0; - set_bit(NFS4_SESSION_DRAINING, &ses->session_state); /* back channel */ - ret = nfs4_wait_on_slot_tbl(&ses->bc_slot_table); + ret = nfs4_drain_slot_tbl(&ses->bc_slot_table); if (ret) return ret; /* fore channel */ - return nfs4_wait_on_slot_tbl(&ses->fc_slot_table); + return nfs4_drain_slot_tbl(&ses->fc_slot_table); } static void nfs41_finish_session_reset(struct nfs_client *clp) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a366107..2d7525f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1942,6 +1942,7 @@ static int nfs23_validate_mount_data(void *options, args->namlen = data->namlen; args->bsize = data->bsize; + args->auth_flavors[0] = RPC_AUTH_UNIX; if (data->flags & NFS_MOUNT_SECFLAVOUR) args->auth_flavors[0] = data->pseudoflavor; if (!args->nfs_server.hostname) @@ -2637,6 +2638,7 @@ static int nfs4_validate_mount_data(void *options, goto out_no_address; args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); + args->auth_flavors[0] = RPC_AUTH_UNIX; if (data->auth_flavourlen) { if (data->auth_flavourlen > 1) goto out_inval_auth; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 689fb60..bccfec8 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -219,13 +219,32 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) static int nilfs_set_page_dirty(struct page *page) { - int ret = __set_page_dirty_buffers(page); + int ret = __set_page_dirty_nobuffers(page); - if (ret) { + if (page_has_buffers(page)) { struct inode *inode = page->mapping->host; - unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits); + unsigned nr_dirty = 0; + struct buffer_head *bh, *head; - nilfs_set_file_dirty(inode, nr_dirty); + /* + * This page is locked by callers, and no other thread + * concurrently marks its buffers dirty since they are + * only dirtied through routines in fs/buffer.c in + * which call sites of mark_buffer_dirty are protected + * by page lock. + */ + bh = head = page_buffers(page); + do { + /* Do not mark hole blocks dirty */ + if (buffer_dirty(bh) || !buffer_mapped(bh)) + continue; + + set_buffer_dirty(bh); + nr_dirty++; + } while (bh = bh->b_this_page, bh != head); + + if (nr_dirty) + nilfs_set_file_dirty(inode, nr_dirty); } return ret; } diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index b3fdd1a..e68588e 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1408,6 +1408,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, mres->lockname_len, mres->lockname); ret = -EFAULT; spin_unlock(&res->spinlock); + dlm_lockres_put(res); goto leave; } res->state |= DLM_LOCK_RES_MIGRATING; diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 1c39efb..2487116 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -790,7 +790,7 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, &hole_size, &rec, &is_last); if (ret) { mlog_errno(ret); - goto out; + goto out_unlock; } if (rec.e_blkno == 0ULL) { diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8a7509f..ff54014 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2288,7 +2288,7 @@ relock: ret = ocfs2_inode_lock(inode, NULL, 1); if (ret < 0) { mlog_errno(ret); - goto out_sems; + goto out; } ocfs2_inode_unlock(inode, 1); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 04ee1b5..b4a5cdf 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -947,7 +947,7 @@ leave: ocfs2_free_dir_lookup_result(&orphan_insert); ocfs2_free_dir_lookup_result(&lookup); - if (status) + if (status && (status != -ENOTEMPTY)) mlog_errno(status); return status; @@ -2216,7 +2216,7 @@ out: brelse(orphan_dir_bh); - return 0; + return ret; } int ocfs2_create_inode_in_orphan(struct inode *dir, @@ -83,7 +83,8 @@ static int do_make_slave(struct mount *mnt) if (peer_mnt == mnt) peer_mnt = NULL; } - if (IS_MNT_SHARED(mnt) && list_empty(&mnt->mnt_share)) + if (mnt->mnt_group_id && IS_MNT_SHARED(mnt) && + list_empty(&mnt->mnt_share)) mnt_release_group_id(mnt); list_del_init(&mnt->mnt_share); diff --git a/fs/proc/base.c b/fs/proc/base.c index dd51e50..c3834da 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2118,6 +2118,7 @@ static int show_timer(struct seq_file *m, void *v) nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", pid_nr_ns(timer->it_pid, tp->ns)); + seq_printf(m, "ClockID: %d\n", timer->it_clock); return 0; } diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index bd4b5a7..bdfabda 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -21,12 +21,12 @@ extern wait_queue_head_t log_wait; static int kmsg_open(struct inode * inode, struct file * file) { - return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_FILE); + return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC); } static int kmsg_release(struct inode * inode, struct file * file) { - (void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_FILE); + (void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC); return 0; } @@ -34,15 +34,15 @@ static ssize_t kmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { if ((file->f_flags & O_NONBLOCK) && - !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE)) + !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) return -EAGAIN; - return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_FILE); + return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC); } static unsigned int kmsg_poll(struct file *file, poll_table *wait) { poll_wait(file, &log_wait, wait); - if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE)) + if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) return POLLIN | POLLRDNORM; return 0; } diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c index 8798d06..afa6be6 100644 --- a/fs/qnx6/dir.c +++ b/fs/qnx6/dir.c @@ -120,7 +120,7 @@ static int qnx6_readdir(struct file *filp, void *dirent, filldir_t filldir) struct inode *inode = file_inode(filp); struct super_block *s = inode->i_sb; struct qnx6_sb_info *sbi = QNX6_SB(s); - loff_t pos = filp->f_pos & (QNX6_DIR_ENTRY_SIZE - 1); + loff_t pos = filp->f_pos & ~(QNX6_DIR_ENTRY_SIZE - 1); unsigned long npages = dir_pages(inode); unsigned long n = pos >> PAGE_CACHE_SHIFT; unsigned start = (pos & ~PAGE_CACHE_MASK) / QNX6_DIR_ENTRY_SIZE; diff --git a/fs/read_write.c b/fs/read_write.c index 0343000..2cefa41 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1064,6 +1064,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, struct fd in, out; struct inode *in_inode, *out_inode; loff_t pos; + loff_t out_pos; ssize_t retval; int fl; @@ -1077,12 +1078,14 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (!(in.file->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; - if (!ppos) - ppos = &in.file->f_pos; - else + if (!ppos) { + pos = in.file->f_pos; + } else { + pos = *ppos; if (!(in.file->f_mode & FMODE_PREAD)) goto fput_in; - retval = rw_verify_area(READ, in.file, ppos, count); + } + retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; count = retval; @@ -1099,7 +1102,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, retval = -EINVAL; in_inode = file_inode(in.file); out_inode = file_inode(out.file); - retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count); + out_pos = out.file->f_pos; + retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; count = retval; @@ -1107,7 +1111,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); - pos = *ppos; if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) @@ -1126,18 +1129,23 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - retval = do_splice_direct(in.file, ppos, out.file, count, fl); + retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(in.file); fsnotify_modify(out.file); + out.file->f_pos = out_pos; + if (ppos) + *ppos = pos; + else + in.file->f_pos = pos; } inc_syscr(current); inc_syscw(current); - if (*ppos > max) + if (pos > max) retval = -EOVERFLOW; fput_out: diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 66c53b6..6c2d136 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -204,6 +204,8 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent, next_pos = deh_offset(deh) + 1; if (item_moved(&tmp_ih, &path_to_entry)) { + set_cpu_key_k_offset(&pos_key, + next_pos); goto research; } } /* for */ diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 77d6d47..f844533 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1811,11 +1811,16 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, TYPE_STAT_DATA, SD_SIZE, MAX_US_INT); memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE); args.dirid = le32_to_cpu(ih.ih_key.k_dir_id); - if (insert_inode_locked4(inode, args.objectid, - reiserfs_find_actor, &args) < 0) { + + reiserfs_write_unlock(inode->i_sb); + err = insert_inode_locked4(inode, args.objectid, + reiserfs_find_actor, &args); + reiserfs_write_lock(inode->i_sb); + if (err) { err = -EINVAL; goto out_bad_inode; } + if (old_format_only(sb)) /* not a perfect generation count, as object ids can be reused, but ** this is as good as reiserfs can do right now. diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 4cce1d9..821bcf7 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -318,7 +318,19 @@ static int delete_one_xattr(struct dentry *dentry, void *data) static int chown_one_xattr(struct dentry *dentry, void *data) { struct iattr *attrs = data; - return reiserfs_setattr(dentry, attrs); + int ia_valid = attrs->ia_valid; + int err; + + /* + * We only want the ownership bits. Otherwise, we'll do + * things like change a directory to a regular file if + * ATTR_MODE is set. + */ + attrs->ia_valid &= (ATTR_UID|ATTR_GID); + err = reiserfs_setattr(dentry, attrs); + attrs->ia_valid = ia_valid; + + return err; } /* No i_mutex, but the inode is unconnected. */ diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index d7c01ef..6c8767f 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -443,6 +443,9 @@ int reiserfs_acl_chmod(struct inode *inode) int depth; int error; + if (IS_PRIVATE(inode)) + return 0; + if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; diff --git a/fs/splice.c b/fs/splice.c index e6b2559..d37431d 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1274,7 +1274,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, { struct file *file = sd->u.file; - return do_splice_from(pipe, file, &file->f_pos, sd->total_len, + return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); } @@ -1283,6 +1283,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, * @in: file to splice from * @ppos: input file offset * @out: file to splice to + * @opos: output file offset * @len: number of bytes to splice * @flags: splice modifier flags * @@ -1294,7 +1295,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, * */ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - size_t len, unsigned int flags) + loff_t *opos, size_t len, unsigned int flags) { struct splice_desc sd = { .len = len, @@ -1302,6 +1303,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, .flags = flags, .pos = *ppos, .u.file = out, + .opos = opos, }; long ret; @@ -1325,7 +1327,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; - loff_t offset, *off; + loff_t offset; long ret; ipipe = get_pipe_info(in); @@ -1356,13 +1358,15 @@ static long do_splice(struct file *in, loff_t __user *off_in, return -EINVAL; if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; - off = &offset; - } else - off = &out->f_pos; + } else { + offset = out->f_pos; + } - ret = do_splice_from(ipipe, out, off, len, flags); + ret = do_splice_from(ipipe, out, &offset, len, flags); - if (off_out && copy_to_user(off_out, off, sizeof(loff_t))) + if (!off_out) + out->f_pos = offset; + else if (copy_to_user(off_out, &offset, sizeof(loff_t))) ret = -EFAULT; return ret; @@ -1376,13 +1380,15 @@ static long do_splice(struct file *in, loff_t __user *off_in, return -EINVAL; if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; - off = &offset; - } else - off = &in->f_pos; + } else { + offset = in->f_pos; + } - ret = do_splice_to(in, off, opipe, len, flags); + ret = do_splice_to(in, &offset, opipe, len, flags); - if (off_in && copy_to_user(off_in, off, sizeof(loff_t))) + if (!off_in) + in->f_pos = offset; + else if (copy_to_user(off_in, &offset, sizeof(loff_t))) ret = -EFAULT; return ret; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index de08c92f..605af51 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -349,31 +349,50 @@ static unsigned int vfs_dent_type(uint8_t type) static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir) { int err, over = 0; + loff_t pos = file->f_pos; struct qstr nm; union ubifs_key key; struct ubifs_dent_node *dent; struct inode *dir = file_inode(file); struct ubifs_info *c = dir->i_sb->s_fs_info; - dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, file->f_pos); + dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, pos); - if (file->f_pos > UBIFS_S_KEY_HASH_MASK || file->f_pos == 2) + if (pos > UBIFS_S_KEY_HASH_MASK || pos == 2) /* * The directory was seek'ed to a senseless position or there * are no more entries. */ return 0; + if (file->f_version == 0) { + /* + * The file was seek'ed, which means that @file->private_data + * is now invalid. This may also be just the first + * 'ubifs_readdir()' invocation, in which case + * @file->private_data is NULL, and the below code is + * basically a no-op. + */ + kfree(file->private_data); + file->private_data = NULL; + } + + /* + * 'generic_file_llseek()' unconditionally sets @file->f_version to + * zero, and we use this for detecting whether the file was seek'ed. + */ + file->f_version = 1; + /* File positions 0 and 1 correspond to "." and ".." */ - if (file->f_pos == 0) { + if (pos == 0) { ubifs_assert(!file->private_data); over = filldir(dirent, ".", 1, 0, dir->i_ino, DT_DIR); if (over) return 0; - file->f_pos = 1; + file->f_pos = pos = 1; } - if (file->f_pos == 1) { + if (pos == 1) { ubifs_assert(!file->private_data); over = filldir(dirent, "..", 2, 1, parent_ino(file->f_path.dentry), DT_DIR); @@ -389,7 +408,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir) goto out; } - file->f_pos = key_hash_flash(c, &dent->key); + file->f_pos = pos = key_hash_flash(c, &dent->key); file->private_data = dent; } @@ -397,17 +416,16 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir) if (!dent) { /* * The directory was seek'ed to and is now readdir'ed. - * Find the entry corresponding to @file->f_pos or the - * closest one. + * Find the entry corresponding to @pos or the closest one. */ - dent_key_init_hash(c, &key, dir->i_ino, file->f_pos); + dent_key_init_hash(c, &key, dir->i_ino, pos); nm.name = NULL; dent = ubifs_tnc_next_ent(c, &key, &nm); if (IS_ERR(dent)) { err = PTR_ERR(dent); goto out; } - file->f_pos = key_hash_flash(c, &dent->key); + file->f_pos = pos = key_hash_flash(c, &dent->key); file->private_data = dent; } @@ -419,7 +437,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir) ubifs_inode(dir)->creat_sqnum); nm.len = le16_to_cpu(dent->nlen); - over = filldir(dirent, dent->name, nm.len, file->f_pos, + over = filldir(dirent, dent->name, nm.len, pos, le64_to_cpu(dent->inum), vfs_dent_type(dent->type)); if (over) @@ -435,9 +453,17 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir) } kfree(file->private_data); - file->f_pos = key_hash_flash(c, &dent->key); + file->f_pos = pos = key_hash_flash(c, &dent->key); file->private_data = dent; cond_resched(); + + if (file->f_version == 0) + /* + * The file was seek'ed meanwhile, lets return and start + * reading direntries from the new position on the next + * invocation. + */ + return 0; } out: @@ -448,15 +474,13 @@ out: kfree(file->private_data); file->private_data = NULL; + /* 2 is a special value indicating that there are no more direntries */ file->f_pos = 2; return 0; } -/* If a directory is seeked, we have to free saved readdir() state */ static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int whence) { - kfree(file->private_data); - file->private_data = NULL; return generic_file_llseek(file, offset, whence); } diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 1d32f1d..306d883 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -21,6 +21,8 @@ #include "xfs_bmap_btree.h" #include "xfs_inode.h" #include "xfs_vnodeops.h" +#include "xfs_sb.h" +#include "xfs_mount.h" #include "xfs_trace.h" #include <linux/slab.h> #include <linux/xattr.h> @@ -34,7 +36,9 @@ */ STATIC struct posix_acl * -xfs_acl_from_disk(struct xfs_acl *aclp) +xfs_acl_from_disk( + struct xfs_acl *aclp, + int max_entries) { struct posix_acl_entry *acl_e; struct posix_acl *acl; @@ -42,7 +46,7 @@ xfs_acl_from_disk(struct xfs_acl *aclp) unsigned int count, i; count = be32_to_cpu(aclp->acl_cnt); - if (count > XFS_ACL_MAX_ENTRIES) + if (count > max_entries) return ERR_PTR(-EFSCORRUPTED); acl = posix_acl_alloc(count, GFP_KERNEL); @@ -108,9 +112,9 @@ xfs_get_acl(struct inode *inode, int type) struct xfs_inode *ip = XFS_I(inode); struct posix_acl *acl; struct xfs_acl *xfs_acl; - int len = sizeof(struct xfs_acl); unsigned char *ea_name; int error; + int len; acl = get_cached_acl(inode, type); if (acl != ACL_NOT_CACHED) @@ -133,8 +137,8 @@ xfs_get_acl(struct inode *inode, int type) * If we have a cached ACLs value just return it, not need to * go out to the disk. */ - - xfs_acl = kzalloc(sizeof(struct xfs_acl), GFP_KERNEL); + len = XFS_ACL_MAX_SIZE(ip->i_mount); + xfs_acl = kzalloc(len, GFP_KERNEL); if (!xfs_acl) return ERR_PTR(-ENOMEM); @@ -153,7 +157,7 @@ xfs_get_acl(struct inode *inode, int type) goto out; } - acl = xfs_acl_from_disk(xfs_acl); + acl = xfs_acl_from_disk(xfs_acl, XFS_ACL_MAX_ENTRIES(ip->i_mount)); if (IS_ERR(acl)) goto out; @@ -189,16 +193,17 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) if (acl) { struct xfs_acl *xfs_acl; - int len; + int len = XFS_ACL_MAX_SIZE(ip->i_mount); - xfs_acl = kzalloc(sizeof(struct xfs_acl), GFP_KERNEL); + xfs_acl = kzalloc(len, GFP_KERNEL); if (!xfs_acl) return -ENOMEM; xfs_acl_to_disk(xfs_acl, acl); - len = sizeof(struct xfs_acl) - - (sizeof(struct xfs_acl_entry) * - (XFS_ACL_MAX_ENTRIES - acl->a_count)); + + /* subtract away the unused acl entries */ + len -= sizeof(struct xfs_acl_entry) * + (XFS_ACL_MAX_ENTRIES(ip->i_mount) - acl->a_count); error = -xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl, len, ATTR_ROOT); @@ -243,7 +248,7 @@ xfs_set_mode(struct inode *inode, umode_t mode) static int xfs_acl_exists(struct inode *inode, unsigned char *name) { - int len = sizeof(struct xfs_acl); + int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb)); return (xfs_attr_get(XFS_I(inode), name, NULL, &len, ATTR_ROOT|ATTR_KERNOVAL) == 0); @@ -379,7 +384,7 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name, goto out_release; error = -EINVAL; - if (acl->a_count > XFS_ACL_MAX_ENTRIES) + if (acl->a_count > XFS_ACL_MAX_ENTRIES(XFS_M(inode->i_sb))) goto out_release; if (type == ACL_TYPE_ACCESS) { diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 39632d9..4016a56 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -22,19 +22,36 @@ struct inode; struct posix_acl; struct xfs_inode; -#define XFS_ACL_MAX_ENTRIES 25 #define XFS_ACL_NOT_PRESENT (-1) /* On-disk XFS access control list structure */ +struct xfs_acl_entry { + __be32 ae_tag; + __be32 ae_id; + __be16 ae_perm; + __be16 ae_pad; /* fill the implicit hole in the structure */ +}; + struct xfs_acl { - __be32 acl_cnt; - struct xfs_acl_entry { - __be32 ae_tag; - __be32 ae_id; - __be16 ae_perm; - } acl_entry[XFS_ACL_MAX_ENTRIES]; + __be32 acl_cnt; + struct xfs_acl_entry acl_entry[0]; }; +/* + * The number of ACL entries allowed is defined by the on-disk format. + * For v4 superblocks, that is limited to 25 entries. For v5 superblocks, it is + * limited only by the maximum size of the xattr that stores the information. + */ +#define XFS_ACL_MAX_ENTRIES(mp) \ + (xfs_sb_version_hascrc(&mp->m_sb) \ + ? (XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \ + sizeof(struct xfs_acl_entry) \ + : 25) + +#define XFS_ACL_MAX_SIZE(mp) \ + (sizeof(struct xfs_acl) + \ + sizeof(struct xfs_acl_entry) * XFS_ACL_MAX_ENTRIES((mp))) + /* On-disk XFS extended attribute names */ #define SGI_ACL_FILE (unsigned char *)"SGI_ACL_FILE" #define SGI_ACL_DEFAULT (unsigned char *)"SGI_ACL_DEFAULT" diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2b2691b..41a6950 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -725,6 +725,25 @@ xfs_convert_page( (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT, i_size_read(inode)); + /* + * If the current map does not span the entire page we are about to try + * to write, then give up. The only way we can write a page that spans + * multiple mappings in a single writeback iteration is via the + * xfs_vm_writepage() function. Data integrity writeback requires the + * entire page to be written in a single attempt, otherwise the part of + * the page we don't write here doesn't get written as part of the data + * integrity sync. + * + * For normal writeback, we also don't attempt to write partial pages + * here as it simply means that write_cache_pages() will see it under + * writeback and ignore the page until some point in the future, at + * which time this will be the only page in the file that needs + * writeback. Hence for more optimal IO patterns, we should always + * avoid partial page writeback due to multiple mappings on a page here. + */ + if (!xfs_imap_valid(inode, imap, end_offset)) + goto fail_unlock_page; + len = 1 << inode->i_blkbits; p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1), PAGE_CACHE_SIZE); diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 08d5457..31d3cd1 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -931,20 +931,22 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) */ int xfs_attr_shortform_allfit( - struct xfs_buf *bp, - struct xfs_inode *dp) + struct xfs_buf *bp, + struct xfs_inode *dp) { - xfs_attr_leafblock_t *leaf; - xfs_attr_leaf_entry_t *entry; + struct xfs_attr_leafblock *leaf; + struct xfs_attr_leaf_entry *entry; xfs_attr_leaf_name_local_t *name_loc; - int bytes, i; + struct xfs_attr3_icleaf_hdr leafhdr; + int bytes; + int i; leaf = bp->b_addr; - ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf); + entry = xfs_attr3_leaf_entryp(leaf); - entry = &leaf->entries[0]; bytes = sizeof(struct xfs_attr_sf_hdr); - for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) { + for (i = 0; i < leafhdr.count; entry++, i++) { if (entry->flags & XFS_ATTR_INCOMPLETE) continue; /* don't copy partial entries */ if (!(entry->flags & XFS_ATTR_LOCAL)) @@ -954,15 +956,15 @@ xfs_attr_shortform_allfit( return(0); if (be16_to_cpu(name_loc->valuelen) >= XFS_ATTR_SF_ENTSIZE_MAX) return(0); - bytes += sizeof(struct xfs_attr_sf_entry)-1 + bytes += sizeof(struct xfs_attr_sf_entry) - 1 + name_loc->namelen + be16_to_cpu(name_loc->valuelen); } if ((dp->i_mount->m_flags & XFS_MOUNT_ATTR2) && (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) && (bytes == sizeof(struct xfs_attr_sf_hdr))) - return(-1); - return(xfs_attr_shortform_bytesfit(dp, bytes)); + return -1; + return xfs_attr_shortform_bytesfit(dp, bytes); } /* @@ -1410,7 +1412,7 @@ xfs_attr3_leaf_add_work( name_rmt->valuelen = 0; name_rmt->valueblk = 0; args->rmtblkno = 1; - args->rmtblkcnt = XFS_B_TO_FSB(mp, args->valuelen); + args->rmtblkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen); } xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index), @@ -1443,11 +1445,12 @@ xfs_attr3_leaf_add_work( STATIC void xfs_attr3_leaf_compact( struct xfs_da_args *args, - struct xfs_attr3_icleaf_hdr *ichdr_d, + struct xfs_attr3_icleaf_hdr *ichdr_dst, struct xfs_buf *bp) { - xfs_attr_leafblock_t *leaf_s, *leaf_d; - struct xfs_attr3_icleaf_hdr ichdr_s; + struct xfs_attr_leafblock *leaf_src; + struct xfs_attr_leafblock *leaf_dst; + struct xfs_attr3_icleaf_hdr ichdr_src; struct xfs_trans *trans = args->trans; struct xfs_mount *mp = trans->t_mountp; char *tmpbuffer; @@ -1455,29 +1458,38 @@ xfs_attr3_leaf_compact( trace_xfs_attr_leaf_compact(args); tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP); - ASSERT(tmpbuffer != NULL); memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp)); memset(bp->b_addr, 0, XFS_LBSIZE(mp)); + leaf_src = (xfs_attr_leafblock_t *)tmpbuffer; + leaf_dst = bp->b_addr; /* - * Copy basic information + * Copy the on-disk header back into the destination buffer to ensure + * all the information in the header that is not part of the incore + * header structure is preserved. */ - leaf_s = (xfs_attr_leafblock_t *)tmpbuffer; - leaf_d = bp->b_addr; - ichdr_s = *ichdr_d; /* struct copy */ - ichdr_d->firstused = XFS_LBSIZE(mp); - ichdr_d->usedbytes = 0; - ichdr_d->count = 0; - ichdr_d->holes = 0; - ichdr_d->freemap[0].base = xfs_attr3_leaf_hdr_size(leaf_s); - ichdr_d->freemap[0].size = ichdr_d->firstused - ichdr_d->freemap[0].base; + memcpy(bp->b_addr, tmpbuffer, xfs_attr3_leaf_hdr_size(leaf_src)); + + /* Initialise the incore headers */ + ichdr_src = *ichdr_dst; /* struct copy */ + ichdr_dst->firstused = XFS_LBSIZE(mp); + ichdr_dst->usedbytes = 0; + ichdr_dst->count = 0; + ichdr_dst->holes = 0; + ichdr_dst->freemap[0].base = xfs_attr3_leaf_hdr_size(leaf_src); + ichdr_dst->freemap[0].size = ichdr_dst->firstused - + ichdr_dst->freemap[0].base; + + + /* write the header back to initialise the underlying buffer */ + xfs_attr3_leaf_hdr_to_disk(leaf_dst, ichdr_dst); /* * Copy all entry's in the same (sorted) order, * but allocate name/value pairs packed and in sequence. */ - xfs_attr3_leaf_moveents(leaf_s, &ichdr_s, 0, leaf_d, ichdr_d, 0, - ichdr_s.count, mp); + xfs_attr3_leaf_moveents(leaf_src, &ichdr_src, 0, leaf_dst, ichdr_dst, 0, + ichdr_src.count, mp); /* * this logs the entire buffer, but the caller must write the header * back to the buffer when it is finished modifying it. @@ -2179,14 +2191,24 @@ xfs_attr3_leaf_unbalance( struct xfs_attr_leafblock *tmp_leaf; struct xfs_attr3_icleaf_hdr tmphdr; - tmp_leaf = kmem_alloc(state->blocksize, KM_SLEEP); - memset(tmp_leaf, 0, state->blocksize); - memset(&tmphdr, 0, sizeof(tmphdr)); + tmp_leaf = kmem_zalloc(state->blocksize, KM_SLEEP); + + /* + * Copy the header into the temp leaf so that all the stuff + * not in the incore header is present and gets copied back in + * once we've moved all the entries. + */ + memcpy(tmp_leaf, save_leaf, xfs_attr3_leaf_hdr_size(save_leaf)); + memset(&tmphdr, 0, sizeof(tmphdr)); tmphdr.magic = savehdr.magic; tmphdr.forw = savehdr.forw; tmphdr.back = savehdr.back; tmphdr.firstused = state->blocksize; + + /* write the header to the temp buffer to initialise it */ + xfs_attr3_leaf_hdr_to_disk(tmp_leaf, &tmphdr); + if (xfs_attr3_leaf_order(save_blk->bp, &savehdr, drop_blk->bp, &drophdr)) { xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0, @@ -2330,9 +2352,11 @@ xfs_attr3_leaf_lookup_int( if (!xfs_attr_namesp_match(args->flags, entry->flags)) continue; args->index = probe; + args->valuelen = be32_to_cpu(name_rmt->valuelen); args->rmtblkno = be32_to_cpu(name_rmt->valueblk); - args->rmtblkcnt = XFS_B_TO_FSB(args->dp->i_mount, - be32_to_cpu(name_rmt->valuelen)); + args->rmtblkcnt = xfs_attr3_rmt_blocks( + args->dp->i_mount, + args->valuelen); return XFS_ERROR(EEXIST); } } @@ -2383,7 +2407,8 @@ xfs_attr3_leaf_getvalue( ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0); valuelen = be32_to_cpu(name_rmt->valuelen); args->rmtblkno = be32_to_cpu(name_rmt->valueblk); - args->rmtblkcnt = XFS_B_TO_FSB(args->dp->i_mount, valuelen); + args->rmtblkcnt = xfs_attr3_rmt_blocks(args->dp->i_mount, + valuelen); if (args->flags & ATTR_KERNOVAL) { args->valuelen = valuelen; return 0; @@ -2709,7 +2734,8 @@ xfs_attr3_leaf_list_int( args.valuelen = valuelen; args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS); args.rmtblkno = be32_to_cpu(name_rmt->valueblk); - args.rmtblkcnt = XFS_B_TO_FSB(args.dp->i_mount, valuelen); + args.rmtblkcnt = xfs_attr3_rmt_blocks( + args.dp->i_mount, valuelen); retval = xfs_attr_rmtval_get(&args); if (retval) return retval; @@ -3232,7 +3258,7 @@ xfs_attr3_leaf_inactive( name_rmt = xfs_attr3_leaf_name_remote(leaf, i); if (name_rmt->valueblk) { lp->valueblk = be32_to_cpu(name_rmt->valueblk); - lp->valuelen = XFS_B_TO_FSB(dp->i_mount, + lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount, be32_to_cpu(name_rmt->valuelen)); lp++; } diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h index f9d7846..444a770 100644 --- a/fs/xfs/xfs_attr_leaf.h +++ b/fs/xfs/xfs_attr_leaf.h @@ -128,6 +128,7 @@ struct xfs_attr3_leaf_hdr { __u8 holes; __u8 pad1; struct xfs_attr_leaf_map freemap[XFS_ATTR_LEAF_MAPSIZE]; + __be32 pad2; /* 64 bit alignment */ }; #define XFS_ATTR3_LEAF_CRC_OFF (offsetof(struct xfs_attr3_leaf_hdr, info.crc)) diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c index dee8446..ef6b0c1 100644 --- a/fs/xfs/xfs_attr_remote.c +++ b/fs/xfs/xfs_attr_remote.c @@ -47,22 +47,55 @@ * Each contiguous block has a header, so it is not just a simple attribute * length to FSB conversion. */ -static int +int xfs_attr3_rmt_blocks( struct xfs_mount *mp, int attrlen) { - int buflen = XFS_ATTR3_RMT_BUF_SPACE(mp, - mp->m_sb.sb_blocksize); - return (attrlen + buflen - 1) / buflen; + if (xfs_sb_version_hascrc(&mp->m_sb)) { + int buflen = XFS_ATTR3_RMT_BUF_SPACE(mp, mp->m_sb.sb_blocksize); + return (attrlen + buflen - 1) / buflen; + } + return XFS_B_TO_FSB(mp, attrlen); +} + +/* + * Checking of the remote attribute header is split into two parts. The verifier + * does CRC, location and bounds checking, the unpacking function checks the + * attribute parameters and owner. + */ +static bool +xfs_attr3_rmt_hdr_ok( + struct xfs_mount *mp, + void *ptr, + xfs_ino_t ino, + uint32_t offset, + uint32_t size, + xfs_daddr_t bno) +{ + struct xfs_attr3_rmt_hdr *rmt = ptr; + + if (bno != be64_to_cpu(rmt->rm_blkno)) + return false; + if (offset != be32_to_cpu(rmt->rm_offset)) + return false; + if (size != be32_to_cpu(rmt->rm_bytes)) + return false; + if (ino != be64_to_cpu(rmt->rm_owner)) + return false; + + /* ok */ + return true; } static bool xfs_attr3_rmt_verify( - struct xfs_buf *bp) + struct xfs_mount *mp, + void *ptr, + int fsbsize, + xfs_daddr_t bno) { - struct xfs_mount *mp = bp->b_target->bt_mount; - struct xfs_attr3_rmt_hdr *rmt = bp->b_addr; + struct xfs_attr3_rmt_hdr *rmt = ptr; if (!xfs_sb_version_hascrc(&mp->m_sb)) return false; @@ -70,7 +103,9 @@ xfs_attr3_rmt_verify( return false; if (!uuid_equal(&rmt->rm_uuid, &mp->m_sb.sb_uuid)) return false; - if (bp->b_bn != be64_to_cpu(rmt->rm_blkno)) + if (be64_to_cpu(rmt->rm_blkno) != bno) + return false; + 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) @@ -86,17 +121,40 @@ xfs_attr3_rmt_read_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_target->bt_mount; + char *ptr; + int len; + bool corrupt = false; + xfs_daddr_t bno; /* no verification of non-crc buffers */ if (!xfs_sb_version_hascrc(&mp->m_sb)) return; - if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), - XFS_ATTR3_RMT_CRC_OFF) || - !xfs_attr3_rmt_verify(bp)) { + ptr = bp->b_addr; + bno = bp->b_bn; + len = BBTOB(bp->b_length); + ASSERT(len >= XFS_LBSIZE(mp)); + + while (len > 0) { + if (!xfs_verify_cksum(ptr, XFS_LBSIZE(mp), + XFS_ATTR3_RMT_CRC_OFF)) { + corrupt = true; + break; + } + if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) { + corrupt = true; + break; + } + len -= XFS_LBSIZE(mp); + ptr += XFS_LBSIZE(mp); + bno += mp->m_bsize; + } + + if (corrupt) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); xfs_buf_ioerror(bp, EFSCORRUPTED); - } + } else + ASSERT(len == 0); } static void @@ -105,23 +163,39 @@ xfs_attr3_rmt_write_verify( { struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_buf_log_item *bip = bp->b_fspriv; + char *ptr; + int len; + xfs_daddr_t bno; /* no verification of non-crc buffers */ if (!xfs_sb_version_hascrc(&mp->m_sb)) return; - if (!xfs_attr3_rmt_verify(bp)) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); - xfs_buf_ioerror(bp, EFSCORRUPTED); - return; - } + ptr = bp->b_addr; + bno = bp->b_bn; + len = BBTOB(bp->b_length); + ASSERT(len >= XFS_LBSIZE(mp)); + + while (len > 0) { + if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) { + XFS_CORRUPTION_ERROR(__func__, + XFS_ERRLEVEL_LOW, mp, bp->b_addr); + xfs_buf_ioerror(bp, EFSCORRUPTED); + return; + } + if (bip) { + struct xfs_attr3_rmt_hdr *rmt; + + rmt = (struct xfs_attr3_rmt_hdr *)ptr; + rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn); + } + xfs_update_cksum(ptr, XFS_LBSIZE(mp), XFS_ATTR3_RMT_CRC_OFF); - if (bip) { - struct xfs_attr3_rmt_hdr *rmt = bp->b_addr; - rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn); + len -= XFS_LBSIZE(mp); + ptr += XFS_LBSIZE(mp); + bno += mp->m_bsize; } - xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), - XFS_ATTR3_RMT_CRC_OFF); + ASSERT(len == 0); } const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = { @@ -129,15 +203,16 @@ const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = { .verify_write = xfs_attr3_rmt_write_verify, }; -static int +STATIC int xfs_attr3_rmt_hdr_set( struct xfs_mount *mp, + void *ptr, xfs_ino_t ino, uint32_t offset, uint32_t size, - struct xfs_buf *bp) + xfs_daddr_t bno) { - struct xfs_attr3_rmt_hdr *rmt = bp->b_addr; + struct xfs_attr3_rmt_hdr *rmt = ptr; if (!xfs_sb_version_hascrc(&mp->m_sb)) return 0; @@ -147,36 +222,107 @@ xfs_attr3_rmt_hdr_set( rmt->rm_bytes = cpu_to_be32(size); uuid_copy(&rmt->rm_uuid, &mp->m_sb.sb_uuid); rmt->rm_owner = cpu_to_be64(ino); - rmt->rm_blkno = cpu_to_be64(bp->b_bn); - bp->b_ops = &xfs_attr3_rmt_buf_ops; + rmt->rm_blkno = cpu_to_be64(bno); return sizeof(struct xfs_attr3_rmt_hdr); } /* - * Checking of the remote attribute header is split into two parts. the verifier - * does CRC, location and bounds checking, the unpacking function checks the - * attribute parameters and owner. + * Helper functions to copy attribute data in and out of the one disk extents */ -static bool -xfs_attr3_rmt_hdr_ok( - struct xfs_mount *mp, - xfs_ino_t ino, - uint32_t offset, - uint32_t size, - struct xfs_buf *bp) +STATIC int +xfs_attr_rmtval_copyout( + struct xfs_mount *mp, + struct xfs_buf *bp, + xfs_ino_t ino, + int *offset, + int *valuelen, + char **dst) { - struct xfs_attr3_rmt_hdr *rmt = bp->b_addr; + char *src = bp->b_addr; + xfs_daddr_t bno = bp->b_bn; + int len = BBTOB(bp->b_length); - if (offset != be32_to_cpu(rmt->rm_offset)) - return false; - if (size != be32_to_cpu(rmt->rm_bytes)) - return false; - if (ino != be64_to_cpu(rmt->rm_owner)) - return false; + ASSERT(len >= XFS_LBSIZE(mp)); - /* ok */ - return true; + while (len > 0 && *valuelen > 0) { + int hdr_size = 0; + int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp)); + + byte_cnt = min_t(int, *valuelen, byte_cnt); + + if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (!xfs_attr3_rmt_hdr_ok(mp, src, ino, *offset, + byte_cnt, bno)) { + xfs_alert(mp, +"remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)", + bno, *offset, byte_cnt, ino); + return EFSCORRUPTED; + } + hdr_size = sizeof(struct xfs_attr3_rmt_hdr); + } + + memcpy(*dst, src + hdr_size, byte_cnt); + + /* roll buffer forwards */ + len -= XFS_LBSIZE(mp); + src += XFS_LBSIZE(mp); + bno += mp->m_bsize; + + /* roll attribute data forwards */ + *valuelen -= byte_cnt; + *dst += byte_cnt; + *offset += byte_cnt; + } + return 0; +} + +STATIC void +xfs_attr_rmtval_copyin( + struct xfs_mount *mp, + struct xfs_buf *bp, + xfs_ino_t ino, + int *offset, + int *valuelen, + char **src) +{ + char *dst = bp->b_addr; + xfs_daddr_t bno = bp->b_bn; + int len = BBTOB(bp->b_length); + + ASSERT(len >= XFS_LBSIZE(mp)); + + while (len > 0 && *valuelen > 0) { + int hdr_size; + int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp)); + + byte_cnt = min(*valuelen, byte_cnt); + hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset, + byte_cnt, bno); + + memcpy(dst + hdr_size, *src, byte_cnt); + + /* + * If this is the last block, zero the remainder of it. + * Check that we are actually the last block, too. + */ + if (byte_cnt + hdr_size < XFS_LBSIZE(mp)) { + ASSERT(*valuelen - byte_cnt == 0); + ASSERT(len == XFS_LBSIZE(mp)); + memset(dst + hdr_size + byte_cnt, 0, + XFS_LBSIZE(mp) - hdr_size - byte_cnt); + } + + /* roll buffer forwards */ + len -= XFS_LBSIZE(mp); + dst += XFS_LBSIZE(mp); + bno += mp->m_bsize; + + /* roll attribute data forwards */ + *valuelen -= byte_cnt; + *src += byte_cnt; + *offset += byte_cnt; + } } /* @@ -190,13 +336,12 @@ xfs_attr_rmtval_get( struct xfs_bmbt_irec map[ATTR_RMTVALUE_MAPSIZE]; struct xfs_mount *mp = args->dp->i_mount; struct xfs_buf *bp; - xfs_daddr_t dblkno; xfs_dablk_t lblkno = args->rmtblkno; - void *dst = args->value; + char *dst = args->value; int valuelen = args->valuelen; int nmap; int error; - int blkcnt; + int blkcnt = args->rmtblkcnt; int i; int offset = 0; @@ -207,52 +352,36 @@ xfs_attr_rmtval_get( while (valuelen > 0) { nmap = ATTR_RMTVALUE_MAPSIZE; error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno, - args->rmtblkcnt, map, &nmap, + blkcnt, map, &nmap, XFS_BMAPI_ATTRFORK); if (error) return error; ASSERT(nmap >= 1); for (i = 0; (i < nmap) && (valuelen > 0); i++) { - int byte_cnt; - char *src; + xfs_daddr_t dblkno; + int dblkcnt; ASSERT((map[i].br_startblock != DELAYSTARTBLOCK) && (map[i].br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock); - blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); + dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, - dblkno, blkcnt, 0, &bp, + dblkno, dblkcnt, 0, &bp, &xfs_attr3_rmt_buf_ops); if (error) return error; - byte_cnt = min_t(int, valuelen, BBTOB(bp->b_length)); - byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, byte_cnt); - - src = bp->b_addr; - if (xfs_sb_version_hascrc(&mp->m_sb)) { - if (!xfs_attr3_rmt_hdr_ok(mp, args->dp->i_ino, - offset, byte_cnt, bp)) { - xfs_alert(mp, -"remote attribute header does not match required off/len/owner (0x%x/Ox%x,0x%llx)", - offset, byte_cnt, args->dp->i_ino); - xfs_buf_relse(bp); - return EFSCORRUPTED; - - } - - src += sizeof(struct xfs_attr3_rmt_hdr); - } - - memcpy(dst, src, byte_cnt); + error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino, + &offset, &valuelen, + &dst); xfs_buf_relse(bp); + if (error) + return error; - offset += byte_cnt; - dst += byte_cnt; - valuelen -= byte_cnt; - + /* roll attribute extent map forwards */ lblkno += map[i].br_blockcount; + blkcnt -= map[i].br_blockcount; } } ASSERT(valuelen == 0); @@ -270,17 +399,13 @@ xfs_attr_rmtval_set( struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_bmbt_irec map; - struct xfs_buf *bp; - xfs_daddr_t dblkno; xfs_dablk_t lblkno; xfs_fileoff_t lfileoff = 0; - void *src = args->value; + char *src = args->value; int blkcnt; int valuelen; int nmap; int error; - int hdrcnt = 0; - bool crcs = xfs_sb_version_hascrc(&mp->m_sb); int offset = 0; trace_xfs_attr_rmtval_set(args); @@ -289,24 +414,14 @@ xfs_attr_rmtval_set( * Find a "hole" in the attribute address space large enough for * us to drop the new attribute's value into. Because CRC enable * attributes have headers, we can't just do a straight byte to FSB - * conversion. We calculate the worst case block count in this case - * and we may not need that many, so we have to handle this when - * allocating the blocks below. + * conversion and have to take the header space into account. */ - if (!crcs) - blkcnt = XFS_B_TO_FSB(mp, args->valuelen); - else - blkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen); - + blkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen); error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff, XFS_ATTR_FORK); if (error) return error; - /* Start with the attribute data. We'll allocate the rest afterwards. */ - if (crcs) - blkcnt = XFS_B_TO_FSB(mp, args->valuelen); - args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff; args->rmtblkcnt = blkcnt; @@ -349,26 +464,6 @@ xfs_attr_rmtval_set( (map.br_startblock != HOLESTARTBLOCK)); lblkno += map.br_blockcount; blkcnt -= map.br_blockcount; - hdrcnt++; - - /* - * If we have enough blocks for the attribute data, calculate - * how many extra blocks we need for headers. We might run - * through this multiple times in the case that the additional - * headers in the blocks needed for the data fragments spills - * into requiring more blocks. e.g. for 512 byte blocks, we'll - * spill for another block every 9 headers we require in this - * loop. - */ - if (crcs && blkcnt == 0) { - int total_len; - - total_len = args->valuelen + - hdrcnt * sizeof(struct xfs_attr3_rmt_hdr); - blkcnt = XFS_B_TO_FSB(mp, total_len); - blkcnt -= args->rmtblkcnt; - args->rmtblkcnt += blkcnt; - } /* * Start the next trans in the chain. @@ -385,18 +480,19 @@ xfs_attr_rmtval_set( * the INCOMPLETE flag. */ lblkno = args->rmtblkno; + blkcnt = args->rmtblkcnt; valuelen = args->valuelen; while (valuelen > 0) { - int byte_cnt; - char *buf; + struct xfs_buf *bp; + xfs_daddr_t dblkno; + int dblkcnt; + + ASSERT(blkcnt > 0); - /* - * Try to remember where we decided to put the value. - */ xfs_bmap_init(args->flist, args->firstblock); nmap = 1; error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno, - args->rmtblkcnt, &map, &nmap, + blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK); if (error) return(error); @@ -405,41 +501,27 @@ xfs_attr_rmtval_set( (map.br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock), - blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); + dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); - bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt, 0); + bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0); if (!bp) return ENOMEM; bp->b_ops = &xfs_attr3_rmt_buf_ops; - byte_cnt = BBTOB(bp->b_length); - byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, byte_cnt); - if (valuelen < byte_cnt) - byte_cnt = valuelen; - - buf = bp->b_addr; - buf += xfs_attr3_rmt_hdr_set(mp, dp->i_ino, offset, - byte_cnt, bp); - memcpy(buf, src, byte_cnt); - - if (byte_cnt < BBTOB(bp->b_length)) - xfs_buf_zero(bp, byte_cnt, - BBTOB(bp->b_length) - byte_cnt); + xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset, + &valuelen, &src); error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */ xfs_buf_relse(bp); if (error) return error; - src += byte_cnt; - valuelen -= byte_cnt; - offset += byte_cnt; - hdrcnt--; + /* roll attribute extent map forwards */ lblkno += map.br_blockcount; + blkcnt -= map.br_blockcount; } ASSERT(valuelen == 0); - ASSERT(hdrcnt == 0); return 0; } @@ -448,33 +530,40 @@ xfs_attr_rmtval_set( * out-of-line buffer that it is stored on. */ int -xfs_attr_rmtval_remove(xfs_da_args_t *args) +xfs_attr_rmtval_remove( + struct xfs_da_args *args) { - xfs_mount_t *mp; - xfs_bmbt_irec_t map; - xfs_buf_t *bp; - xfs_daddr_t dblkno; - xfs_dablk_t lblkno; - int valuelen, blkcnt, nmap, error, done, committed; + struct xfs_mount *mp = args->dp->i_mount; + xfs_dablk_t lblkno; + int blkcnt; + int error; + int done; trace_xfs_attr_rmtval_remove(args); - mp = args->dp->i_mount; - /* - * Roll through the "value", invalidating the attribute value's - * blocks. + * Roll through the "value", invalidating the attribute value's blocks. + * Note that args->rmtblkcnt is the minimum number of data blocks we'll + * see for a CRC enabled remote attribute. Each extent will have a + * header, and so we may have more blocks than we realise here. If we + * fail to map the blocks correctly, we'll have problems with the buffer + * lookups. */ lblkno = args->rmtblkno; - valuelen = args->rmtblkcnt; - while (valuelen > 0) { + blkcnt = args->rmtblkcnt; + while (blkcnt > 0) { + struct xfs_bmbt_irec map; + struct xfs_buf *bp; + xfs_daddr_t dblkno; + int dblkcnt; + int nmap; + /* * Try to remember where we decided to put the value. */ nmap = 1; error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno, - args->rmtblkcnt, &map, &nmap, - XFS_BMAPI_ATTRFORK); + blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK); if (error) return(error); ASSERT(nmap == 1); @@ -482,21 +571,20 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args) (map.br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock), - blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); + dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); /* * If the "remote" value is in the cache, remove it. */ - bp = xfs_incore(mp->m_ddev_targp, dblkno, blkcnt, XBF_TRYLOCK); + bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK); if (bp) { xfs_buf_stale(bp); xfs_buf_relse(bp); bp = NULL; } - valuelen -= map.br_blockcount; - lblkno += map.br_blockcount; + blkcnt -= map.br_blockcount; } /* @@ -506,6 +594,8 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args) blkcnt = args->rmtblkcnt; done = 0; while (!done) { + int committed; + xfs_bmap_init(args->flist, args->firstblock); error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt, XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA, diff --git a/fs/xfs/xfs_attr_remote.h b/fs/xfs/xfs_attr_remote.h index c7cca60..92a8fd7 100644 --- a/fs/xfs/xfs_attr_remote.h +++ b/fs/xfs/xfs_attr_remote.h @@ -20,6 +20,14 @@ #define XFS_ATTR3_RMT_MAGIC 0x5841524d /* XARM */ +/* + * There is one of these headers per filesystem block in a remote attribute. + * This is done to ensure there is a 1:1 mapping between the attribute value + * length and the number of blocks needed to store the attribute. This makes the + * verification of a buffer a little more complex, but greatly simplifies the + * allocation, reading and writing of these attributes as we don't have to guess + * the number of blocks needed to store the attribute data. + */ struct xfs_attr3_rmt_hdr { __be32 rm_magic; __be32 rm_offset; @@ -39,6 +47,8 @@ struct xfs_attr3_rmt_hdr { extern const struct xfs_buf_ops xfs_attr3_rmt_buf_ops; +int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen); + int xfs_attr_rmtval_get(struct xfs_da_args *args); int xfs_attr_rmtval_set(struct xfs_da_args *args); int xfs_attr_rmtval_remove(struct xfs_da_args *args); diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index 8804b8a..0903960 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -2544,7 +2544,17 @@ xfs_btree_new_iroot( if (error) goto error0; + /* + * we can't just memcpy() the root in for CRC enabled btree blocks. + * In that case have to also ensure the blkno remains correct + */ memcpy(cblock, block, xfs_btree_block_len(cur)); + if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) { + if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + cblock->bb_u.l.bb_blkno = cpu_to_be64(cbp->b_bn); + else + cblock->bb_u.s.bb_blkno = cpu_to_be64(cbp->b_bn); + } be16_add_cpu(&block->bb_level, 1); xfs_btree_set_numrecs(block, 1); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 82b70bd..1b2472a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -513,6 +513,7 @@ _xfs_buf_find( xfs_alert(btp->bt_mount, "%s: Block out of range: block 0x%llx, EOFS 0x%llx ", __func__, blkno, eofs); + WARN_ON(1); return NULL; } @@ -1649,7 +1650,7 @@ xfs_alloc_buftarg( { xfs_buftarg_t *btp; - btp = kmem_zalloc(sizeof(*btp), KM_SLEEP); + btp = kmem_zalloc(sizeof(*btp), KM_SLEEP | KM_NOFS); btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index cf26347..4ec4317 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -262,12 +262,7 @@ xfs_buf_item_format_segment( vecp->i_addr = xfs_buf_offset(bp, buffer_offset); vecp->i_len = nbits * XFS_BLF_CHUNK; vecp->i_type = XLOG_REG_TYPE_BCHUNK; -/* - * You would think we need to bump the nvecs here too, but we do not - * this number is used by recovery, and it gets confused by the boundary - * split here - * nvecs++; - */ + nvecs++; vecp++; first_bit = next_bit; last_bit = next_bit; diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 9b26a99..0b8b2a1 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -270,6 +270,7 @@ xfs_da3_node_read_verify( break; return; case XFS_ATTR_LEAF_MAGIC: + case XFS_ATTR3_LEAF_MAGIC: bp->b_ops = &xfs_attr3_leaf_buf_ops; bp->b_ops->verify_read(bp); return; @@ -2464,7 +2465,8 @@ xfs_buf_map_from_irec( ASSERT(nirecs >= 1); if (nirecs > 1) { - map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map), KM_SLEEP); + map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map), + KM_SLEEP | KM_NOFS); if (!map) return ENOMEM; *mapp = map; @@ -2520,7 +2522,8 @@ xfs_dabuf_map( * Optimize the one-block case. */ if (nfsb != 1) - irecs = kmem_zalloc(sizeof(irec) * nfsb, KM_SLEEP); + irecs = kmem_zalloc(sizeof(irec) * nfsb, + KM_SLEEP | KM_NOFS); nirecs = nfsb; error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, irecs, diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index f852b08..c407e1c 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -219,6 +219,14 @@ xfs_swap_extents( int taforkblks = 0; __uint64_t tmp; + /* + * We have no way of updating owner information in the BMBT blocks for + * each inode on CRC enabled filesystems, so to avoid corrupting the + * this metadata we simply don't allow extent swaps to occur. + */ + if (xfs_sb_version_hascrc(&mp->m_sb)) + return XFS_ERROR(EINVAL); + tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL); if (!tempifp) { error = XFS_ERROR(ENOMEM); diff --git a/fs/xfs/xfs_dir2_format.h b/fs/xfs/xfs_dir2_format.h index a3b1bd8..7826782b 100644 --- a/fs/xfs/xfs_dir2_format.h +++ b/fs/xfs/xfs_dir2_format.h @@ -266,6 +266,7 @@ struct xfs_dir3_blk_hdr { struct xfs_dir3_data_hdr { struct xfs_dir3_blk_hdr hdr; xfs_dir2_data_free_t best_free[XFS_DIR2_DATA_FD_COUNT]; + __be32 pad; /* 64 bit alignment */ }; #define XFS_DIR3_DATA_CRC_OFF offsetof(struct xfs_dir3_data_hdr, hdr.crc) @@ -477,7 +478,7 @@ struct xfs_dir3_leaf_hdr { struct xfs_da3_blkinfo info; /* header for da routines */ __be16 count; /* count of entries */ __be16 stale; /* count of stale entries */ - __be32 pad; + __be32 pad; /* 64 bit alignment */ }; struct xfs_dir3_icleaf_hdr { @@ -715,6 +716,7 @@ struct xfs_dir3_free_hdr { __be32 firstdb; /* db of first entry */ __be32 nvalid; /* count of valid entries */ __be32 nused; /* count of used entries */ + __be32 pad; /* 64 bit alignment */ }; struct xfs_dir3_free { diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index 721ba2f..da71a18 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -1336,7 +1336,7 @@ xfs_dir2_leaf_getdents( mp->m_sb.sb_blocksize); map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) + (length * sizeof(struct xfs_bmbt_irec)), - KM_SLEEP); + KM_SLEEP | KM_NOFS); map_info->map_size = length; /* diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c index 5246de4..2226a00 100644 --- a/fs/xfs/xfs_dir2_node.c +++ b/fs/xfs/xfs_dir2_node.c @@ -263,18 +263,19 @@ xfs_dir3_free_get_buf( * Initialize the new block to be empty, and remember * its first slot as our empty slot. */ - hdr.magic = XFS_DIR2_FREE_MAGIC; - hdr.firstdb = 0; - hdr.nused = 0; - hdr.nvalid = 0; + memset(bp->b_addr, 0, sizeof(struct xfs_dir3_free_hdr)); + memset(&hdr, 0, sizeof(hdr)); + if (xfs_sb_version_hascrc(&mp->m_sb)) { struct xfs_dir3_free_hdr *hdr3 = bp->b_addr; hdr.magic = XFS_DIR3_FREE_MAGIC; + hdr3->hdr.blkno = cpu_to_be64(bp->b_bn); hdr3->hdr.owner = cpu_to_be64(dp->i_ino); uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_uuid); - } + } else + hdr.magic = XFS_DIR2_FREE_MAGIC; xfs_dir3_free_hdr_to_disk(bp->b_addr, &hdr); *bpp = bp; return 0; @@ -1921,8 +1922,6 @@ xfs_dir2_node_addname_int( */ freehdr.firstdb = (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) * xfs_dir3_free_max_bests(mp); - free->hdr.nvalid = 0; - free->hdr.nused = 0; } else { free = fbp->b_addr; bests = xfs_dir3_free_bests_p(mp, free); diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index a41f8bf..044e97a 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -249,8 +249,11 @@ xfs_qm_init_dquot_blk( d->dd_diskdq.d_version = XFS_DQUOT_VERSION; d->dd_diskdq.d_id = cpu_to_be32(curid); d->dd_diskdq.d_flags = type; - if (xfs_sb_version_hascrc(&mp->m_sb)) + if (xfs_sb_version_hascrc(&mp->m_sb)) { uuid_copy(&d->dd_uuid, &mp->m_sb.sb_uuid); + xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); + } } xfs_trans_dquot_buf(tp, bp, @@ -286,23 +289,6 @@ xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp) dqp->q_low_space[XFS_QLOWSP_5_PCNT] = space * 5; } -STATIC void -xfs_dquot_buf_calc_crc( - struct xfs_mount *mp, - struct xfs_buf *bp) -{ - struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr; - int i; - - if (!xfs_sb_version_hascrc(&mp->m_sb)) - return; - - for (i = 0; i < mp->m_quotainfo->qi_dqperchunk; i++, d++) { - xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk), - offsetof(struct xfs_dqblk, dd_crc)); - } -} - STATIC bool xfs_dquot_buf_verify_crc( struct xfs_mount *mp, @@ -328,12 +314,11 @@ xfs_dquot_buf_verify_crc( for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), - offsetof(struct xfs_dqblk, dd_crc))) + XFS_DQUOT_CRC_OFF)) return false; if (!uuid_equal(&d->dd_uuid, &mp->m_sb.sb_uuid)) return false; } - return true; } @@ -393,6 +378,11 @@ xfs_dquot_buf_read_verify( } } +/* + * we don't calculate the CRC here as that is done when the dquot is flushed to + * the buffer after the update is done. This ensures that the dquot in the + * buffer always has an up-to-date CRC value. + */ void xfs_dquot_buf_write_verify( struct xfs_buf *bp) @@ -404,7 +394,6 @@ xfs_dquot_buf_write_verify( xfs_buf_ioerror(bp, EFSCORRUPTED); return; } - xfs_dquot_buf_calc_crc(mp, bp); } const struct xfs_buf_ops xfs_dquot_buf_ops = { @@ -1151,11 +1140,17 @@ xfs_qm_dqflush( * copy the lsn into the on-disk dquot now while we have the in memory * dquot here. This can't be done later in the write verifier as we * can't get access to the log item at that point in time. + * + * We also calculate the CRC here so that the on-disk dquot in the + * buffer always has a valid CRC. This ensures there is no possibility + * of a dquot without an up-to-date CRC getting to disk. */ if (xfs_sb_version_hascrc(&mp->m_sb)) { struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddqp; dqb->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn); + xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); } /* diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index c0f3750..452920a 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -305,11 +305,12 @@ xfs_efi_release(xfs_efi_log_item_t *efip, { ASSERT(atomic_read(&efip->efi_next_extent) >= nextents); if (atomic_sub_and_test(nextents, &efip->efi_next_extent)) { - __xfs_efi_release(efip); - /* recovery needs us to drop the EFI reference, too */ if (test_bit(XFS_EFI_RECOVERED, &efip->efi_flags)) __xfs_efi_release(efip); + + __xfs_efi_release(efip); + /* efip may now have been freed, do not reference it again. */ } } diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index 6dda3f9..d046955 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -236,6 +236,7 @@ typedef struct xfs_fsop_resblks { #define XFS_FSOP_GEOM_FLAGS_PROJID32 0x0800 /* 32-bit project IDs */ #define XFS_FSOP_GEOM_FLAGS_DIRV2CI 0x1000 /* ASCII only CI names */ #define XFS_FSOP_GEOM_FLAGS_LAZYSB 0x4000 /* lazy superblock counters */ +#define XFS_FSOP_GEOM_FLAGS_V5SB 0x8000 /* version 5 superblock */ /* diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 87595b2..3c3644e 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -99,7 +99,9 @@ xfs_fs_geometry( (xfs_sb_version_hasattr2(&mp->m_sb) ? XFS_FSOP_GEOM_FLAGS_ATTR2 : 0) | (xfs_sb_version_hasprojid32bit(&mp->m_sb) ? - XFS_FSOP_GEOM_FLAGS_PROJID32 : 0); + XFS_FSOP_GEOM_FLAGS_PROJID32 : 0) | + (xfs_sb_version_hascrc(&mp->m_sb) ? + XFS_FSOP_GEOM_FLAGS_V5SB : 0); geo->logsectsize = xfs_sb_version_hassector(&mp->m_sb) ? mp->m_sb.sb_logsectsize : BBSIZE; geo->rtsectsize = mp->m_sb.sb_blocksize; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index efbe1ac..7f7be5f 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1638,6 +1638,10 @@ xfs_iunlink( dip->di_next_unlinked = agi->agi_unlinked[bucket_index]; offset = ip->i_imap.im_boffset + offsetof(xfs_dinode_t, di_next_unlinked); + + /* need to recalc the inode CRC if appropriate */ + xfs_dinode_calc_crc(mp, dip); + xfs_trans_inode_buf(tp, ibp); xfs_trans_log_buf(tp, ibp, offset, (offset + sizeof(xfs_agino_t) - 1)); @@ -1723,6 +1727,10 @@ xfs_iunlink_remove( dip->di_next_unlinked = cpu_to_be32(NULLAGINO); offset = ip->i_imap.im_boffset + offsetof(xfs_dinode_t, di_next_unlinked); + + /* need to recalc the inode CRC if appropriate */ + xfs_dinode_calc_crc(mp, dip); + xfs_trans_inode_buf(tp, ibp); xfs_trans_log_buf(tp, ibp, offset, (offset + sizeof(xfs_agino_t) - 1)); @@ -1796,6 +1804,10 @@ xfs_iunlink_remove( dip->di_next_unlinked = cpu_to_be32(NULLAGINO); offset = ip->i_imap.im_boffset + offsetof(xfs_dinode_t, di_next_unlinked); + + /* need to recalc the inode CRC if appropriate */ + xfs_dinode_calc_crc(mp, dip); + xfs_trans_inode_buf(tp, ibp); xfs_trans_log_buf(tp, ibp, offset, (offset + sizeof(xfs_agino_t) - 1)); @@ -1809,6 +1821,10 @@ xfs_iunlink_remove( last_dip->di_next_unlinked = cpu_to_be32(next_agino); ASSERT(next_agino != 0); offset = last_offset + offsetof(xfs_dinode_t, di_next_unlinked); + + /* need to recalc the inode CRC if appropriate */ + xfs_dinode_calc_crc(mp, last_dip); + xfs_trans_inode_buf(tp, last_ibp); xfs_trans_log_buf(tp, last_ibp, offset, (offset + sizeof(xfs_agino_t) - 1)); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index d82efaa..ca9ecaa 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -455,6 +455,28 @@ xfs_vn_getattr( return 0; } +static void +xfs_setattr_mode( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct iattr *iattr) +{ + struct inode *inode = VFS_I(ip); + umode_t mode = iattr->ia_mode; + + ASSERT(tp); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + + ip->i_d.di_mode &= S_IFMT; + ip->i_d.di_mode |= mode & ~S_IFMT; + + inode->i_mode &= S_IFMT; + inode->i_mode |= mode & ~S_IFMT; +} + int xfs_setattr_nonsize( struct xfs_inode *ip, @@ -606,18 +628,8 @@ xfs_setattr_nonsize( /* * Change file access modes. */ - if (mask & ATTR_MODE) { - umode_t mode = iattr->ia_mode; - - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) - mode &= ~S_ISGID; - - ip->i_d.di_mode &= S_IFMT; - ip->i_d.di_mode |= mode & ~S_IFMT; - - inode->i_mode &= S_IFMT; - inode->i_mode |= mode & ~S_IFMT; - } + if (mask & ATTR_MODE) + xfs_setattr_mode(tp, ip, iattr); /* * Change file access or modified times. @@ -714,9 +726,8 @@ xfs_setattr_size( return XFS_ERROR(error); ASSERT(S_ISREG(ip->i_d.di_mode)); - ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID| - ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| + ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); if (!(flags & XFS_ATTR_NOLOCK)) { lock_flags |= XFS_IOLOCK_EXCL; @@ -860,6 +871,12 @@ xfs_setattr_size( xfs_inode_clear_eofblocks_tag(ip); } + /* + * Change file access modes. + */ + if (mask & ATTR_MODE) + xfs_setattr_mode(tp, ip, iattr); + if (mask & ATTR_CTIME) { inode->i_ctime = iattr->ia_ctime; ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index e3d0b85..d0833b5 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -139,7 +139,7 @@ xlog_cil_prepare_log_vecs( new_lv = kmem_zalloc(sizeof(*new_lv) + niovecs * sizeof(struct xfs_log_iovec), - KM_SLEEP); + KM_SLEEP|KM_NOFS); /* The allocated iovec region lies beyond the log vector. */ new_lv->lv_iovecp = (struct xfs_log_iovec *)&new_lv[1]; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 93f03ec..7cf5e4e 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1599,10 +1599,43 @@ xlog_recover_add_to_trans( } /* - * Sort the log items in the transaction. Cancelled buffers need - * to be put first so they are processed before any items that might - * modify the buffers. If they are cancelled, then the modifications - * don't need to be replayed. + * Sort the log items in the transaction. + * + * The ordering constraints are defined by the inode allocation and unlink + * behaviour. The rules are: + * + * 1. Every item is only logged once in a given transaction. Hence it + * represents the last logged state of the item. Hence ordering is + * dependent on the order in which operations need to be performed so + * required initial conditions are always met. + * + * 2. Cancelled buffers are recorded in pass 1 in a separate table and + * there's nothing to replay from them so we can simply cull them + * from the transaction. However, we can't do that until after we've + * replayed all the other items because they may be dependent on the + * cancelled buffer and replaying the cancelled buffer can remove it + * form the cancelled buffer table. Hence they have tobe done last. + * + * 3. Inode allocation buffers must be replayed before inode items that + * read the buffer and replay changes into it. + * + * 4. Inode unlink buffers must be replayed after inode items are replayed. + * This ensures that inodes are completely flushed to the inode buffer + * in a "free" state before we remove the unlinked inode list pointer. + * + * Hence the ordering needs to be inode allocation buffers first, inode items + * second, inode unlink buffers third and cancelled buffers last. + * + * But there's a problem with that - we can't tell an inode allocation buffer + * apart from a regular buffer, so we can't separate them. We can, however, + * tell an inode unlink buffer from the others, and so we can separate them out + * from all the other buffers and move them to last. + * + * Hence, 4 lists, in order from head to tail: + * - buffer_list for all buffers except cancelled/inode unlink buffers + * - item_list for all non-buffer items + * - inode_buffer_list for inode unlink buffers + * - cancel_list for the cancelled buffers */ STATIC int xlog_recover_reorder_trans( @@ -1612,6 +1645,10 @@ xlog_recover_reorder_trans( { xlog_recover_item_t *item, *n; LIST_HEAD(sort_list); + LIST_HEAD(cancel_list); + LIST_HEAD(buffer_list); + LIST_HEAD(inode_buffer_list); + LIST_HEAD(inode_list); list_splice_init(&trans->r_itemq, &sort_list); list_for_each_entry_safe(item, n, &sort_list, ri_list) { @@ -1619,12 +1656,18 @@ xlog_recover_reorder_trans( switch (ITEM_TYPE(item)) { case XFS_LI_BUF: - if (!(buf_f->blf_flags & XFS_BLF_CANCEL)) { + if (buf_f->blf_flags & XFS_BLF_CANCEL) { trace_xfs_log_recover_item_reorder_head(log, trans, item, pass); - list_move(&item->ri_list, &trans->r_itemq); + list_move(&item->ri_list, &cancel_list); + break; + } + if (buf_f->blf_flags & XFS_BLF_INODE_BUF) { + list_move(&item->ri_list, &inode_buffer_list); break; } + list_move_tail(&item->ri_list, &buffer_list); + break; case XFS_LI_INODE: case XFS_LI_DQUOT: case XFS_LI_QUOTAOFF: @@ -1632,7 +1675,7 @@ xlog_recover_reorder_trans( case XFS_LI_EFI: trace_xfs_log_recover_item_reorder_tail(log, trans, item, pass); - list_move_tail(&item->ri_list, &trans->r_itemq); + list_move_tail(&item->ri_list, &inode_list); break; default: xfs_warn(log->l_mp, @@ -1643,6 +1686,14 @@ xlog_recover_reorder_trans( } } ASSERT(list_empty(&sort_list)); + if (!list_empty(&buffer_list)) + list_splice(&buffer_list, &trans->r_itemq); + if (!list_empty(&inode_list)) + list_splice_tail(&inode_list, &trans->r_itemq); + if (!list_empty(&inode_buffer_list)) + list_splice_tail(&inode_buffer_list, &trans->r_itemq); + if (!list_empty(&cancel_list)) + list_splice_tail(&cancel_list, &trans->r_itemq); return 0; } @@ -1794,7 +1845,13 @@ xlog_recover_do_inode_buffer( xfs_agino_t *buffer_nextp; trace_xfs_log_recover_buf_inode_buf(mp->m_log, buf_f); - bp->b_ops = &xfs_inode_buf_ops; + + /* + * Post recovery validation only works properly on CRC enabled + * filesystems. + */ + if (xfs_sb_version_hascrc(&mp->m_sb)) + bp->b_ops = &xfs_inode_buf_ops; inodes_per_buf = BBTOB(bp->b_io_length) >> mp->m_sb.sb_inodelog; for (i = 0; i < inodes_per_buf; i++) { @@ -1861,6 +1918,15 @@ xlog_recover_do_inode_buffer( buffer_nextp = (xfs_agino_t *)xfs_buf_offset(bp, next_unlinked_offset); *buffer_nextp = *logged_nextp; + + /* + * If necessary, recalculate the CRC in the on-disk inode. We + * have to leave the inode in a consistent state for whoever + * reads it next.... + */ + xfs_dinode_calc_crc(mp, (struct xfs_dinode *) + xfs_buf_offset(bp, i * mp->m_sb.sb_inodesize)); + } return 0; @@ -2097,6 +2163,17 @@ xlog_recover_do_reg_buffer( ((uint)bit << XFS_BLF_SHIFT) + (nbits << XFS_BLF_SHIFT)); /* + * The dirty regions logged in the buffer, even though + * contiguous, may span multiple chunks. This is because the + * dirty region may span a physical page boundary in a buffer + * and hence be split into two separate vectors for writing into + * the log. Hence we need to trim nbits back to the length of + * the current region being copied out of the log. + */ + if (item->ri_buf[i].i_len < (nbits << XFS_BLF_SHIFT)) + nbits = item->ri_buf[i].i_len >> XFS_BLF_SHIFT; + + /* * Do a sanity check if this is a dquot buffer. Just checking * the first dquot in the buffer should do. XXXThis is * probably a good thing to do for other buf types also. @@ -2134,7 +2211,16 @@ xlog_recover_do_reg_buffer( /* Shouldn't be any more regions */ ASSERT(i == item->ri_total); - xlog_recovery_validate_buf_type(mp, bp, buf_f); + /* + * We can only do post recovery validation on items on CRC enabled + * fielsystems as we need to know when the buffer was written to be able + * to determine if we should have replayed the item. If we replay old + * metadata over a newer buffer, then it will enter a temporarily + * inconsistent state resulting in verification failures. Hence for now + * just avoid the verification stage for non-crc filesystems + */ + if (xfs_sb_version_hascrc(&mp->m_sb)) + xlog_recovery_validate_buf_type(mp, bp, buf_f); } /* @@ -2255,6 +2341,12 @@ xfs_qm_dqcheck( d->dd_diskdq.d_flags = type; d->dd_diskdq.d_id = cpu_to_be32(id); + if (xfs_sb_version_hascrc(&mp->m_sb)) { + uuid_copy(&d->dd_uuid, &mp->m_sb.sb_uuid); + xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); + } + return errs; } @@ -2782,6 +2874,10 @@ xlog_recover_dquot_pass2( } memcpy(ddq, recddq, item->ri_buf[1].i_len); + if (xfs_sb_version_hascrc(&mp->m_sb)) { + xfs_update_cksum((char *)ddq, sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); + } ASSERT(dq_f->qlf_size == 2); ASSERT(bp->b_target->bt_mount == mp); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index f6bfbd7..e8e310c 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -314,7 +314,8 @@ STATIC int xfs_mount_validate_sb( xfs_mount_t *mp, xfs_sb_t *sbp, - bool check_inprogress) + bool check_inprogress, + bool check_version) { /* @@ -337,9 +338,10 @@ xfs_mount_validate_sb( /* * Version 5 superblock feature mask validation. Reject combinations the - * kernel cannot support up front before checking anything else. + * kernel cannot support up front before checking anything else. For + * write validation, we don't need to check feature masks. */ - if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) { + if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) { xfs_alert(mp, "Version 5 superblock detected. This kernel has EXPERIMENTAL support enabled!\n" "Use of these features in this kernel is at your own risk!"); @@ -675,7 +677,8 @@ xfs_sb_to_disk( static int xfs_sb_verify( - struct xfs_buf *bp) + struct xfs_buf *bp, + bool check_version) { struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_sb sb; @@ -686,7 +689,8 @@ xfs_sb_verify( * Only check the in progress field for the primary superblock as * mkfs.xfs doesn't clear it from secondary superblocks. */ - return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR); + return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR, + check_version); } /* @@ -719,7 +723,7 @@ xfs_sb_read_verify( goto out_error; } } - error = xfs_sb_verify(bp); + error = xfs_sb_verify(bp, true); out_error: if (error) { @@ -758,7 +762,7 @@ xfs_sb_write_verify( struct xfs_buf_log_item *bip = bp->b_fspriv; int error; - error = xfs_sb_verify(bp); + error = xfs_sb_verify(bp, false); if (error) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); xfs_buf_ioerror(bp, error); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index f41702b..b75c9bb 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -41,6 +41,7 @@ #include "xfs_qm.h" #include "xfs_trace.h" #include "xfs_icache.h" +#include "xfs_cksum.h" /* * The global quota manager. There is only one of these for the entire @@ -839,7 +840,7 @@ xfs_qm_reset_dqcounts( xfs_dqid_t id, uint type) { - xfs_disk_dquot_t *ddq; + struct xfs_dqblk *dqb; int j; trace_xfs_reset_dqcounts(bp, _RET_IP_); @@ -853,8 +854,12 @@ xfs_qm_reset_dqcounts( do_div(j, sizeof(xfs_dqblk_t)); ASSERT(mp->m_quotainfo->qi_dqperchunk == j); #endif - ddq = bp->b_addr; + dqb = bp->b_addr; for (j = 0; j < mp->m_quotainfo->qi_dqperchunk; j++) { + struct xfs_disk_dquot *ddq; + + ddq = (struct xfs_disk_dquot *)&dqb[j]; + /* * Do a sanity check, and if needed, repair the dqblk. Don't * output any warnings because it's perfectly possible to @@ -871,7 +876,12 @@ xfs_qm_reset_dqcounts( ddq->d_bwarns = 0; ddq->d_iwarns = 0; ddq->d_rtbwarns = 0; - ddq = (xfs_disk_dquot_t *) ((xfs_dqblk_t *)ddq + 1); + + if (xfs_sb_version_hascrc(&mp->m_sb)) { + xfs_update_cksum((char *)&dqb[j], + sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); + } } } @@ -907,19 +917,29 @@ xfs_qm_dqiter_bufs( XFS_FSB_TO_DADDR(mp, bno), mp->m_quotainfo->qi_dqchunklen, 0, &bp, &xfs_dquot_buf_ops); - if (error) - break; /* - * XXX(hch): need to figure out if it makes sense to validate - * the CRC here. + * CRC and validation errors will return a EFSCORRUPTED here. If + * this occurs, re-read without CRC validation so that we can + * repair the damage via xfs_qm_reset_dqcounts(). This process + * will leave a trace in the log indicating corruption has + * been detected. */ + if (error == EFSCORRUPTED) { + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, bno), + mp->m_quotainfo->qi_dqchunklen, 0, &bp, + NULL); + } + + if (error) + break; + xfs_qm_reset_dqcounts(mp, bp, firstid, type); xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); - /* - * goto the next block. - */ + + /* goto the next block. */ bno++; firstid += mp->m_quotainfo->qi_dqperchunk; } diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index c41190c..6cdf6ff 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -489,31 +489,36 @@ xfs_qm_scall_setqlim( if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0) return 0; - tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM); - error = xfs_trans_reserve(tp, 0, XFS_QM_SETQLIM_LOG_RES(mp), - 0, 0, XFS_DEFAULT_LOG_COUNT); - if (error) { - xfs_trans_cancel(tp, 0); - return (error); - } - /* * We don't want to race with a quotaoff so take the quotaoff lock. - * (We don't hold an inode lock, so there's nothing else to stop - * a quotaoff from happening). (XXXThis doesn't currently happen - * because we take the vfslock before calling xfs_qm_sysent). + * We don't hold an inode lock, so there's nothing else to stop + * a quotaoff from happening. */ mutex_lock(&q->qi_quotaofflock); /* - * Get the dquot (locked), and join it to the transaction. - * Allocate the dquot if this doesn't exist. + * Get the dquot (locked) before we start, as we need to do a + * transaction to allocate it if it doesn't exist. Once we have the + * dquot, unlock it so we can start the next transaction safely. We hold + * a reference to the dquot, so it's safe to do this unlock/lock without + * it being reclaimed in the mean time. */ - if ((error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp))) { - xfs_trans_cancel(tp, XFS_TRANS_ABORT); + error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp); + if (error) { ASSERT(error != ENOENT); goto out_unlock; } + xfs_dqunlock(dqp); + + tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM); + error = xfs_trans_reserve(tp, 0, XFS_QM_SETQLIM_LOG_RES(mp), + 0, 0, XFS_DEFAULT_LOG_COUNT); + if (error) { + xfs_trans_cancel(tp, 0); + goto out_rele; + } + + xfs_dqlock(dqp); xfs_trans_dqjoin(tp, dqp); ddq = &dqp->q_core; @@ -621,9 +626,10 @@ xfs_qm_scall_setqlim( xfs_trans_log_dquot(tp, dqp); error = xfs_trans_commit(tp, 0); - xfs_qm_dqrele(dqp); - out_unlock: +out_rele: + xfs_qm_dqrele(dqp); +out_unlock: mutex_unlock(&q->qi_quotaofflock); return error; } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index c61e31c..c38068f 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -87,6 +87,8 @@ typedef struct xfs_dqblk { uuid_t dd_uuid; /* location information */ } xfs_dqblk_t; +#define XFS_DQUOT_CRC_OFF offsetof(struct xfs_dqblk, dd_crc) + /* * flags for q_flags field in the dquot. */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index ea341ce..3033ba5 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1373,6 +1373,17 @@ xfs_finish_flags( } /* + * V5 filesystems always use attr2 format for attributes. + */ + if (xfs_sb_version_hascrc(&mp->m_sb) && + (mp->m_flags & XFS_MOUNT_NOATTR2)) { + xfs_warn(mp, +"Cannot mount a V5 filesystem as %s. %s is always enabled for V5 filesystems.", + MNTOPT_NOATTR2, MNTOPT_ATTR2); + return XFS_ERROR(EINVAL); + } + + /* * mkfs'ed attr2 will turn on attr2 mount unless explicitly * told by noattr2 to turn it off */ diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 5f234389..195a403 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -56,16 +56,9 @@ xfs_symlink_blocks( struct xfs_mount *mp, int pathlen) { - int fsblocks = 0; - int len = pathlen; + int buflen = XFS_SYMLINK_BUF_SPACE(mp, mp->m_sb.sb_blocksize); - do { - fsblocks++; - len -= XFS_SYMLINK_BUF_SPACE(mp, mp->m_sb.sb_blocksize); - } while (len > 0); - - ASSERT(fsblocks <= XFS_SYMLINK_MAPS); - return fsblocks; + return (pathlen + buflen - 1) / buflen; } static int @@ -405,7 +398,7 @@ xfs_symlink( if (pathlen <= XFS_LITINO(mp, dp->i_d.di_version)) fs_blocks = 0; else - fs_blocks = XFS_B_TO_FSB(mp, pathlen); + fs_blocks = xfs_symlink_blocks(mp, pathlen); resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks); error = xfs_trans_reserve(tp, resblks, XFS_SYMLINK_LOG_RES(mp), 0, XFS_TRANS_PERM_LOG_RES, XFS_SYMLINK_LOG_COUNT); @@ -512,7 +505,7 @@ xfs_symlink( cur_chunk = target_path; offset = 0; for (n = 0; n < nmaps; n++) { - char *buf; + char *buf; d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); @@ -525,9 +518,7 @@ xfs_symlink( bp->b_ops = &xfs_symlink_buf_ops; byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt); - if (pathlen < byte_cnt) { - byte_cnt = pathlen; - } + byte_cnt = min(byte_cnt, pathlen); buf = bp->b_addr; buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, @@ -542,6 +533,7 @@ xfs_symlink( xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) - (char *)bp->b_addr); } + ASSERT(pathlen == 0); } /* diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 1501f4f..0176bb2 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -1453,7 +1453,7 @@ xfs_free_file_space( xfs_mount_t *mp; int nimap; uint resblks; - uint rounding; + xfs_off_t rounding; int rt; xfs_fileoff_t startoffset_fsb; xfs_trans_t *tp; @@ -1482,7 +1482,7 @@ xfs_free_file_space( inode_dio_wait(VFS_I(ip)); } - rounding = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE); + rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE); ioffset = offset & ~(rounding - 1); error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ioffset, -1); |