diff options
Diffstat (limited to 'fs')
51 files changed, 610 insertions, 296 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c index 22ea424ee741..073bb57adab1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1242,6 +1242,13 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); + /* + * If the partition is not aligned on a page + * boundary, we can't do dax I/O to it. + */ + if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) || + (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + bdev->bd_inode->i_flags &= ~S_DAX; } } else { if (bdev->bd_contains == bdev) { diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index ecbc63d3143e..9a2ec79e8cfb 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1828,7 +1828,6 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, int found = 0; struct extent_buffer *eb; struct btrfs_inode_extref *extref; - struct extent_buffer *leaf; u32 item_size; u32 cur_offset; unsigned long ptr; @@ -1856,9 +1855,8 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, slot); - ptr = btrfs_item_ptr_offset(leaf, slot); + item_size = btrfs_item_size_nr(eb, slot); + ptr = btrfs_item_ptr_offset(eb, slot); cur_offset = 0; while (cur_offset < item_size) { @@ -1872,7 +1870,7 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, if (ret) break; - cur_offset += btrfs_inode_extref_name_len(leaf, extref); + cur_offset += btrfs_inode_extref_name_len(eb, extref); cur_offset += sizeof(*extref); } btrfs_tree_read_unlock_blocking(eb); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 81220b2203c6..0ef5cc13fae2 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -44,8 +44,6 @@ #define BTRFS_INODE_IN_DELALLOC_LIST 9 #define BTRFS_INODE_READDIO_NEED_LOCK 10 #define BTRFS_INODE_HAS_PROPS 11 -/* DIO is ready to submit */ -#define BTRFS_INODE_DIO_READY 12 /* * The following 3 bits are meant only for the btree inode. * When any of them is set, it means an error happened while writing an diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0d98aee34fee..1e60d00d4ea7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2847,6 +2847,8 @@ int open_ctree(struct super_block *sb, !extent_buffer_uptodate(chunk_root->node)) { printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + if (!IS_ERR(chunk_root->node)) + free_extent_buffer(chunk_root->node); chunk_root->node = NULL; goto fail_tree_roots; } @@ -2885,6 +2887,8 @@ retry_root_backup: !extent_buffer_uptodate(tree_root->node)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); tree_root->node = NULL; goto recovery_tree_root; } @@ -3765,9 +3769,7 @@ void close_ctree(struct btrfs_root *root) * block groups queued for removal, the deletion will be * skipped when we quit the cleaner thread. */ - mutex_lock(&root->fs_info->cleaner_mutex); btrfs_delete_unused_bgs(root->fs_info); - mutex_unlock(&root->fs_info->cleaner_mutex); ret = btrfs_commit_super(root); if (ret) diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 8d052209f473..2513a7f53334 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -112,11 +112,11 @@ static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh, u32 generation; if (fh_type == FILEID_BTRFS_WITH_PARENT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE) return NULL; root_objectid = fid->root_objectid; } else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) return NULL; root_objectid = fid->parent_root_objectid; } else @@ -136,11 +136,11 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, u32 generation; if ((fh_type != FILEID_BTRFS_WITH_PARENT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE) && (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) && (fh_type != FILEID_BTRFS_WITHOUT_PARENT || - fh_len != BTRFS_FID_SIZE_NON_CONNECTABLE)) + fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE)) return NULL; objectid = fid->objectid; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5411f0ab5683..601d7d45d164 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2828,6 +2828,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head; int ret; int run_all = count == (unsigned long)-1; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; /* We'll clean this up in btrfs_cleanup_transaction */ if (trans->aborted) @@ -2844,6 +2845,7 @@ again: #ifdef SCRAMBLE_DELAYED_REFS delayed_refs->run_delayed_start = find_middle(&delayed_refs->root); #endif + trans->can_flush_pending_bgs = false; ret = __btrfs_run_delayed_refs(trans, root, count); if (ret < 0) { btrfs_abort_transaction(trans, root, ret); @@ -2893,6 +2895,7 @@ again: } out: assert_qgroups_uptodate(trans); + trans->can_flush_pending_bgs = can_flush_pending_bgs; return 0; } @@ -3742,10 +3745,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_reserved = 0; found->bytes_readonly = 0; found->bytes_may_use = 0; - if (total_bytes > 0) - found->full = 0; - else - found->full = 1; + found->full = 0; found->force_alloc = CHUNK_ALLOC_NO_FORCE; found->chunk_alloc = 0; found->flush = 0; @@ -4309,7 +4309,8 @@ out: * the block groups that were made dirty during the lifetime of the * transaction. */ - if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { + if (trans->can_flush_pending_bgs && + trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { btrfs_create_pending_block_groups(trans, trans->root); btrfs_trans_release_chunk_metadata(trans); } @@ -8668,7 +8669,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) { - btrfs_drop_and_free_fs_root(tree_root->fs_info, root); + btrfs_add_dropped_root(trans, root); } else { free_extent_buffer(root->node); free_extent_buffer(root->commit_root); @@ -9563,7 +9564,9 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_block_group_item item; struct btrfs_key key; int ret = 0; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; + trans->can_flush_pending_bgs = false; list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { if (ret) goto next; @@ -9584,6 +9587,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, next: list_del_init(&block_group->bg_list); } + trans->can_flush_pending_bgs = can_flush_pending_bgs; } int btrfs_make_block_group(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f1018cfbfefa..3915c9473e94 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2798,7 +2798,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, bio_end_io_t end_io_func, int mirror_num, unsigned long prev_bio_flags, - unsigned long bio_flags) + unsigned long bio_flags, + bool force_bio_submit) { int ret = 0; struct bio *bio; @@ -2814,6 +2815,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, contig = bio_end_sector(bio) == sector; if (prev_bio_flags != bio_flags || !contig || + force_bio_submit || merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) || bio_add_page(bio, page, page_size, offset) < page_size) { ret = submit_one_bio(rw, bio, mirror_num, @@ -2910,7 +2912,8 @@ static int __do_readpage(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode = page->mapping->host; u64 start = page_offset(page); @@ -2958,6 +2961,7 @@ static int __do_readpage(struct extent_io_tree *tree, } while (cur <= end) { unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1; + bool force_bio_submit = false; if (cur >= last_byte) { char *userpage; @@ -3008,6 +3012,49 @@ static int __do_readpage(struct extent_io_tree *tree, block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; + + /* + * If we have a file range that points to a compressed extent + * and it's followed by a consecutive file range that points to + * to the same compressed extent (possibly with a different + * offset and/or length, so it either points to the whole extent + * or only part of it), we must make sure we do not submit a + * single bio to populate the pages for the 2 ranges because + * this makes the compressed extent read zero out the pages + * belonging to the 2nd range. Imagine the following scenario: + * + * File layout + * [0 - 8K] [8K - 24K] + * | | + * | | + * points to extent X, points to extent X, + * offset 4K, length of 8K offset 0, length 16K + * + * [extent X, compressed length = 4K uncompressed length = 16K] + * + * If the bio to read the compressed extent covers both ranges, + * it will decompress extent X into the pages belonging to the + * first range and then it will stop, zeroing out the remaining + * pages that belong to the other range that points to extent X. + * So here we make sure we submit 2 bios, one for the first + * range and another one for the third range. Both will target + * the same physical extent from disk, but we can't currently + * make the compressed bio endio callback populate the pages + * for both ranges because each compressed bio is tightly + * coupled with a single extent map, and each range can have + * an extent map with a different offset value relative to the + * uncompressed data of our extent and different lengths. This + * is a corner case so we prioritize correctness over + * non-optimal behavior (submitting 2 bios for the same extent). + */ + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) && + prev_em_start && *prev_em_start != (u64)-1 && + *prev_em_start != em->orig_start) + force_bio_submit = true; + + if (prev_em_start) + *prev_em_start = em->orig_start; + free_extent_map(em); em = NULL; @@ -3057,7 +3104,8 @@ static int __do_readpage(struct extent_io_tree *tree, bdev, bio, pnr, end_bio_extent_readpage, mirror_num, *bio_flags, - this_bio_flag); + this_bio_flag, + force_bio_submit); if (!ret) { nr++; *bio_flags = this_bio_flag; @@ -3084,7 +3132,8 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode; struct btrfs_ordered_extent *ordered; @@ -3104,7 +3153,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, for (index = 0; index < nr_pages; index++) { __do_readpage(tree, pages[index], get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, prev_em_start); page_cache_release(pages[index]); } } @@ -3114,7 +3163,8 @@ static void __extent_readpages(struct extent_io_tree *tree, int nr_pages, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { u64 start = 0; u64 end = 0; @@ -3135,7 +3185,7 @@ static void __extent_readpages(struct extent_io_tree *tree, index - first_index, start, end, get_extent, em_cached, bio, mirror_num, bio_flags, - rw); + rw, prev_em_start); start = page_start; end = start + PAGE_CACHE_SIZE - 1; first_index = index; @@ -3146,7 +3196,8 @@ static void __extent_readpages(struct extent_io_tree *tree, __do_contiguous_readpages(tree, &pages[first_index], index - first_index, start, end, get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, + prev_em_start); } static int __extent_read_full_page(struct extent_io_tree *tree, @@ -3172,7 +3223,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree, } ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num, - bio_flags, rw); + bio_flags, rw, NULL); return ret; } @@ -3198,7 +3249,7 @@ int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, int ret; ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num, - &bio_flags, READ); + &bio_flags, READ, NULL); if (bio) ret = submit_one_bio(READ, bio, mirror_num, bio_flags); return ret; @@ -3451,7 +3502,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, sector, iosize, pg_offset, bdev, &epd->bio, max_nr, end_bio_extent_writepage, - 0, 0, 0); + 0, 0, 0, false); if (ret) SetPageError(page); } @@ -3754,7 +3805,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = submit_extent_page(rw, tree, wbc, p, offset >> 9, PAGE_CACHE_SIZE, 0, bdev, &epd->bio, -1, end_bio_extent_buffer_writepage, - 0, epd->bio_flags, bio_flags); + 0, epd->bio_flags, bio_flags, false); epd->bio_flags = bio_flags; if (ret) { set_btree_ioerr(p); @@ -4158,6 +4209,7 @@ int extent_readpages(struct extent_io_tree *tree, struct page *page; struct extent_map *em_cached = NULL; int nr = 0; + u64 prev_em_start = (u64)-1; for (page_idx = 0; page_idx < nr_pages; page_idx++) { page = list_entry(pages->prev, struct page, lru); @@ -4174,12 +4226,12 @@ int extent_readpages(struct extent_io_tree *tree, if (nr < ARRAY_SIZE(pagepool)) continue; __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); nr = 0; } if (nr) __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); if (em_cached) free_extent_map(em_cached); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b823fac91c92..8c6f247ba81d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2584,7 +2584,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start); if (ret) goto out; - } else { + } else if (offset + len > inode->i_size) { /* * If we are fallocating from the end of the file onward we * need to zero out the end of the page if i_size lands in the diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a0fa7253a2d7..611b66d73e80 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5084,7 +5084,8 @@ void btrfs_evict_inode(struct inode *inode) goto no_delete; } /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */ - btrfs_wait_ordered_range(inode, 0, (u64)-1); + if (!special_file(inode->i_mode)) + btrfs_wait_ordered_range(inode, 0, (u64)-1); btrfs_free_io_failure_record(inode, 0, (u64)-1); @@ -7408,6 +7409,10 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, return em; } +struct btrfs_dio_data { + u64 outstanding_extents; + u64 reserve; +}; static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -7415,10 +7420,10 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; + struct btrfs_dio_data *dio_data = NULL; u64 start = iblock << inode->i_blkbits; u64 lockstart, lockend; u64 len = bh_result->b_size; - u64 *outstanding_extents = NULL; int unlock_bits = EXTENT_LOCKED; int ret = 0; @@ -7436,7 +7441,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * that anything that needs to check if there's a transction doesn't get * confused. */ - outstanding_extents = current->journal_info; + dio_data = current->journal_info; current->journal_info = NULL; } @@ -7568,17 +7573,18 @@ unlock: * within our reservation, otherwise we need to adjust our inode * counter appropriately. */ - if (*outstanding_extents) { - (*outstanding_extents)--; + if (dio_data->outstanding_extents) { + (dio_data->outstanding_extents)--; } else { spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); } - current->journal_info = outstanding_extents; btrfs_free_reserved_data_space(inode, len); - set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags); + WARN_ON(dio_data->reserve < len); + dio_data->reserve -= len; + current->journal_info = dio_data; } /* @@ -7601,8 +7607,8 @@ unlock: unlock_err: clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, 1, 0, &cached_state, GFP_NOFS); - if (outstanding_extents) - current->journal_info = outstanding_extents; + if (dio_data) + current->journal_info = dio_data; return ret; } @@ -8329,7 +8335,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - u64 outstanding_extents = 0; + struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_dio_data dio_data = { 0 }; size_t count = 0; int flags = 0; bool wakeup = true; @@ -8367,7 +8374,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, ret = btrfs_delalloc_reserve_space(inode, count); if (ret) goto out; - outstanding_extents = div64_u64(count + + dio_data.outstanding_extents = div64_u64(count + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); @@ -8376,7 +8383,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * do the accounting properly if we go over the number we * originally calculated. Abuse current->journal_info for this. */ - current->journal_info = &outstanding_extents; + dio_data.reserve = round_up(count, root->sectorsize); + current->journal_info = &dio_data; } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags)) { inode_dio_end(inode); @@ -8391,16 +8399,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (iov_iter_rw(iter) == WRITE) { current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { - /* - * If the error comes from submitting stage, - * btrfs_get_blocsk_direct() has free'd data space, - * and metadata space will be handled by - * finish_ordered_fn, don't do that again to make - * sure bytes_may_use is correct. - */ - if (!test_and_clear_bit(BTRFS_INODE_DIO_READY, - &BTRFS_I(inode)->runtime_flags)) - btrfs_delalloc_release_space(inode, count); + if (dio_data.reserve) + btrfs_delalloc_release_space(inode, + dio_data.reserve); } else if (ret >= 0 && (size_t)ret < count) btrfs_delalloc_release_space(inode, count - (size_t)ret); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..8d20f3b1cab0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4639,6 +4639,11 @@ locked: bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } + if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_bctl; + } + do_balance: /* * Ownership of bctl and mutually_exclusive_operation_running @@ -4650,12 +4655,15 @@ do_balance: need_unlock = false; ret = btrfs_balance(bctl, bargs); + bctl = NULL; if (arg) { if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; } +out_bctl: + kfree(bctl); out_bargs: kfree(bargs); out_unlock: diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index aa72bfd28f7d..a739b825bdd3 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1920,10 +1920,12 @@ static int did_overwrite_ref(struct send_ctx *sctx, /* * We know that it is or will be overwritten. Check this now. * The current inode being processed might have been the one that caused - * inode 'ino' to be orphanized, therefore ow_inode can actually be the - * same as sctx->send_progress. + * inode 'ino' to be orphanized, therefore check if ow_inode matches + * the current inode being processed. */ - if (ow_inode <= sctx->send_progress) + if ((ow_inode < sctx->send_progress) || + (ino != sctx->cur_ino && ow_inode == sctx->cur_ino && + gen == sctx->cur_inode_gen)) ret = 1; else ret = 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 2b07b3581781..11d1eab9234d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1658,9 +1658,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) * groups on disk until we're mounted read-write again * unless we clean them up here. */ - mutex_lock(&root->fs_info->cleaner_mutex); btrfs_delete_unused_bgs(fs_info); - mutex_unlock(&root->fs_info->cleaner_mutex); btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8f259b3a66b3..a5b06442f0bf 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -117,6 +117,18 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans, btrfs_unpin_free_ino(root); clear_btree_io_tree(&root->dirty_log_pages); } + + /* We can free old roots now. */ + spin_lock(&trans->dropped_roots_lock); + while (!list_empty(&trans->dropped_roots)) { + root = list_first_entry(&trans->dropped_roots, + struct btrfs_root, root_list); + list_del_init(&root->root_list); + spin_unlock(&trans->dropped_roots_lock); + btrfs_drop_and_free_fs_root(fs_info, root); + spin_lock(&trans->dropped_roots_lock); + } + spin_unlock(&trans->dropped_roots_lock); up_write(&fs_info->commit_root_sem); } @@ -255,11 +267,13 @@ loop: INIT_LIST_HEAD(&cur_trans->pending_ordered); INIT_LIST_HEAD(&cur_trans->dirty_bgs); INIT_LIST_HEAD(&cur_trans->io_bgs); + INIT_LIST_HEAD(&cur_trans->dropped_roots); mutex_init(&cur_trans->cache_write_mutex); cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->deleted_bgs_lock); + spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, fs_info->btree_inode->i_mapping); @@ -336,6 +350,24 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, } +void btrfs_add_dropped_root(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct btrfs_transaction *cur_trans = trans->transaction; + + /* Add ourselves to the transaction dropped list */ + spin_lock(&cur_trans->dropped_roots_lock); + list_add_tail(&root->root_list, &cur_trans->dropped_roots); + spin_unlock(&cur_trans->dropped_roots_lock); + + /* Make sure we don't try to update the root at commit time */ + spin_lock(&root->fs_info->fs_roots_radix_lock); + radix_tree_tag_clear(&root->fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&root->fs_info->fs_roots_radix_lock); +} + int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -525,6 +557,7 @@ again: h->delayed_ref_elem.seq = 0; h->type = type; h->allocating_chunk = false; + h->can_flush_pending_bgs = true; h->reloc_reserved = false; h->sync = false; INIT_LIST_HEAD(&h->qgroup_ref_list); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index edc2fbc262d7..a994bb097ee5 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -65,6 +65,7 @@ struct btrfs_transaction { struct list_head switch_commits; struct list_head dirty_bgs; struct list_head io_bgs; + struct list_head dropped_roots; u64 num_dirty_bgs; /* @@ -76,6 +77,7 @@ struct btrfs_transaction { spinlock_t dirty_bgs_lock; struct list_head deleted_bgs; spinlock_t deleted_bgs_lock; + spinlock_t dropped_roots_lock; struct btrfs_delayed_ref_root delayed_refs; int aborted; int dirty_bg_run; @@ -116,6 +118,7 @@ struct btrfs_trans_handle { short aborted; short adding_csums; bool allocating_chunk; + bool can_flush_pending_bgs; bool reloc_reserved; bool sync; unsigned int type; @@ -216,5 +219,6 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info); int btrfs_transaction_in_commit(struct btrfs_fs_info *info); void btrfs_put_transaction(struct btrfs_transaction *transaction); void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info); - +void btrfs_add_dropped_root(struct btrfs_trans_handle *trans, + struct btrfs_root *root); #endif diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2ca784a14e84..595279a8b99f 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -376,6 +376,14 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT) + /* * Profile changing flags. When SOFT is set we won't relocate chunk if * it already has the target profile (even though it may be diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index aa0dc2573374..afa09fce8151 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -444,6 +444,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) return 0; } +/* Server has provided av pairs/target info in the type 2 challenge + * packet and we have plucked it and stored within smb session. + * We parse that blob here to find the server given timestamp + * as part of ntlmv2 authentication (or local current time as + * default in case of failure) + */ +static __le64 +find_timestamp(struct cifs_ses *ses) +{ + unsigned int attrsize; + unsigned int type; + unsigned int onesize = sizeof(struct ntlmssp2_name); + unsigned char *blobptr; + unsigned char *blobend; + struct ntlmssp2_name *attrptr; + + if (!ses->auth_key.len || !ses->auth_key.response) + return 0; + + blobptr = ses->auth_key.response; + blobend = blobptr + ses->auth_key.len; + + while (blobptr + onesize < blobend) { + attrptr = (struct ntlmssp2_name *) blobptr; + type = le16_to_cpu(attrptr->type); + if (type == NTLMSSP_AV_EOL) + break; + blobptr += 2; /* advance attr type */ + attrsize = le16_to_cpu(attrptr->length); + blobptr += 2; /* advance attr size */ + if (blobptr + attrsize > blobend) + break; + if (type == NTLMSSP_AV_TIMESTAMP) { + if (attrsize == sizeof(u64)) + return *((__le64 *)blobptr); + } + blobptr += attrsize; /* advance attr value */ + } + + return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); +} + static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, const struct nls_table *nls_cp) { @@ -641,6 +683,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) struct ntlmv2_resp *ntlmv2; char ntlmv2_hash[16]; unsigned char *tiblob = NULL; /* target info blob */ + __le64 rsp_timestamp; if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) { if (!ses->domainName) { @@ -659,6 +702,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) } } + /* Must be within 5 minutes of the server (or in range +/-2h + * in case of Mac OS X), so simply carry over server timestamp + * (as Windows 7 does) + */ + rsp_timestamp = find_timestamp(ses); + baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp); tilen = ses->auth_key.len; tiblob = ses->auth_key.response; @@ -675,8 +724,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) (ses->auth_key.response + CIFS_SESS_KEY_SIZE); ntlmv2->blob_signature = cpu_to_le32(0x00000101); ntlmv2->reserved = 0; - /* Must be within 5 minutes of the server */ - ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); + ntlmv2->time = rsp_timestamp; + get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal)); ntlmv2->reserved2 = 0; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 6a1119e87fbb..e739950ca084 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -325,8 +325,11 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server) static void cifs_show_security(struct seq_file *s, struct cifs_ses *ses) { - if (ses->sectype == Unspecified) + if (ses->sectype == Unspecified) { + if (ses->user_name == NULL) + seq_puts(s, ",sec=none"); return; + } seq_puts(s, ",sec="); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 27aea110e923..c3cc1609025f 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -136,5 +136,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.07" +#define CIFS_VERSION "2.08" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e2a6af1508af..62203c387db4 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3380,6 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, struct page *page, *tpage; unsigned int expected_index; int rc; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); INIT_LIST_HEAD(tmplist); @@ -3392,7 +3393,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, */ __set_page_locked(page); rc = add_to_page_cache_locked(page, mapping, - page->index, GFP_KERNEL); + page->index, gfp); /* give up if we can't stick it in the cache */ if (rc) { @@ -3418,8 +3419,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __set_page_locked(page); - if (add_to_page_cache_locked(page, mapping, page->index, - GFP_KERNEL)) { + if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { __clear_page_locked(page); break; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index f621b44cb800..6b66dd5d1540 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2034,7 +2034,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, struct tcon_link *tlink = NULL; struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; - struct cifs_io_parms io_parms; /* * To avoid spurious oplock breaks from server, in the case of @@ -2056,18 +2055,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, rc = -ENOSYS; cifsFileInfo_put(open_file); cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - unsigned int bytes_written; - - io_parms.netfid = open_file->fid.netfid; - io_parms.pid = open_file->pid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, - NULL, NULL, 1); - cifs_dbg(FYI, "Wrt seteof rc %d\n", rc); - } } else rc = -EINVAL; @@ -2093,28 +2080,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, else rc = -ENOSYS; cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - __u16 netfid; - int oplock = 0; - rc = SMBLegacyOpen(xid, tcon, full_path, FILE_OPEN, - GENERIC_WRITE, CREATE_NOT_DIR, &netfid, - &oplock, NULL, cifs_sb->local_nls, - cifs_remap(cifs_sb)); - if (rc == 0) { - unsigned int bytes_written; - - io_parms.netfid = netfid; - io_parms.pid = current->tgid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, NULL, - NULL, 1); - cifs_dbg(FYI, "wrt seteof rc %d\n", rc); - CIFSSMBClose(xid, tcon, netfid); - } - } if (tlink) cifs_put_tlink(tlink); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index c63f5227b681..28a77bf1d559 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -67,6 +67,12 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, goto out_drop_write; } + if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { + rc = -EBADF; + cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); + goto out_fput; + } + if ((!src_file.file->private_data) || (!dst_file->private_data)) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index df91bcf56d67..18da19f4f811 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server) break; default: server->echoes = true; - server->oplocks = true; + if (enable_oplocks) { + server->oplocks = true; + server->oplock_credits = 1; + } else + server->oplocks = false; + server->echo_credits = 1; - server->oplock_credits = 1; } server->credits -= server->echo_credits + server->oplock_credits; return 0; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 070fb2ad85ce..597a417ba94d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -46,6 +46,7 @@ #include "smb2status.h" #include "smb2glob.h" #include "cifspdu.h" +#include "cifs_spnego.h" /* * The following table defines the expected "StructureSize" of SMB2 requests @@ -486,19 +487,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) cifs_dbg(FYI, "missing security blob on negprot\n"); rc = cifs_enable_signing(server, ses->sign); -#ifdef CONFIG_SMB2_ASN1 /* BB REMOVEME when updated asn1.c ready */ if (rc) goto neg_exit; - if (blob_length) + if (blob_length) { rc = decode_negTokenInit(security_blob, blob_length, server); - if (rc == 1) - rc = 0; - else if (rc == 0) { - rc = -EIO; - goto neg_exit; + if (rc == 1) + rc = 0; + else if (rc == 0) + rc = -EIO; } -#endif - neg_exit: free_rsp_buf(resp_buftype, rsp); return rc; @@ -592,7 +589,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, __le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */ struct TCP_Server_Info *server = ses->server; u16 blob_length = 0; - char *security_blob; + struct key *spnego_key = NULL; + char *security_blob = NULL; char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ @@ -620,7 +618,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, ses->ntlmssp->sesskey_per_smbsess = true; /* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */ - ses->sectype = RawNTLMSSP; + if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP) + ses->sectype = RawNTLMSSP; ssetup_ntlmssp_authenticate: if (phase == NtLmChallenge) @@ -649,7 +648,48 @@ ssetup_ntlmssp_authenticate: iov[0].iov_base = (char *)req; /* 4 for rfc1002 length field and 1 for pad */ iov[0].iov_len = get_rfc1002_length(req) + 4 - 1; - if (phase == NtLmNegotiate) { + + if (ses->sectype == Kerberos) { +#ifdef CONFIG_CIFS_UPCALL + struct cifs_spnego_msg *msg; + + spnego_key = cifs_get_spnego_key(ses); + if (IS_ERR(spnego_key)) { + rc = PTR_ERR(spnego_key); + spnego_key = NULL; + goto ssetup_exit; + } + + msg = spnego_key->payload.data; + /* + * check version field to make sure that cifs.upcall is + * sending us a response in an expected form + */ + if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) { + cifs_dbg(VFS, + "bad cifs.upcall version. Expected %d got %d", + CIFS_SPNEGO_UPCALL_VERSION, msg->version); + rc = -EKEYREJECTED; + goto ssetup_exit; + } + ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, + GFP_KERNEL); + if (!ses->auth_key.response) { + cifs_dbg(VFS, + "Kerberos can't allocate (%u bytes) memory", + msg->sesskey_len); + rc = -ENOMEM; + goto ssetup_exit; + } + ses->auth_key.len = msg->sesskey_len; + blob_length = msg->secblob_len; + iov[1].iov_base = msg->data + msg->sesskey_len; + iov[1].iov_len = blob_length; +#else + rc = -EOPNOTSUPP; + goto ssetup_exit; +#endif /* CONFIG_CIFS_UPCALL */ + } else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */ ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE), GFP_KERNEL); if (ntlmssp_blob == NULL) { @@ -672,6 +712,8 @@ ssetup_ntlmssp_authenticate: /* with raw NTLMSSP we don't encapsulate in SPNEGO */ security_blob = ntlmssp_blob; } + iov[1].iov_base = security_blob; + iov[1].iov_len = blob_length; } else if (phase == NtLmAuthenticate) { req->hdr.SessionId = ses->Suid; ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500, @@ -699,6 +741,8 @@ ssetup_ntlmssp_authenticate: } else { security_blob = ntlmssp_blob; } + iov[1].iov_base = security_blob; + iov[1].iov_len = blob_length; } else { cifs_dbg(VFS, "illegal ntlmssp phase\n"); rc = -EIO; @@ -710,8 +754,6 @@ ssetup_ntlmssp_authenticate: cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */ - 4 /* rfc1001 len */); req->SecurityBufferLength = cpu_to_le16(blob_length); - iov[1].iov_base = security_blob; - iov[1].iov_len = blob_length; inc_rfc1001_len(req, blob_length - 1 /* pad */); @@ -722,6 +764,7 @@ ssetup_ntlmssp_authenticate: kfree(security_blob); rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base; + ses->Suid = rsp->hdr.SessionId; if (resp_buftype != CIFS_NO_BUFFER && rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) { if (phase != NtLmNegotiate) { @@ -739,7 +782,6 @@ ssetup_ntlmssp_authenticate: /* NTLMSSP Negotiate sent now processing challenge (response) */ phase = NtLmChallenge; /* process ntlmssp challenge */ rc = 0; /* MORE_PROCESSING is not an error here but expected */ - ses->Suid = rsp->hdr.SessionId; rc = decode_ntlmssp_challenge(rsp->Buffer, le16_to_cpu(rsp->SecurityBufferLength), ses); } @@ -796,6 +838,10 @@ keygen_exit: kfree(ses->auth_key.response); ses->auth_key.response = NULL; } + if (spnego_key) { + key_invalidate(spnego_key); + key_put(spnego_key); + } kfree(ses->ntlmssp); return rc; @@ -876,6 +922,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, if (tcon && tcon->bad_network_name) return -ENOENT; + if ((tcon && tcon->seal) && + ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) { + cifs_dbg(VFS, "encryption requested but no server support"); + return -EOPNOTSUPP; + } + unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL); if (unc_path == NULL) return -ENOMEM; @@ -955,6 +1007,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0)) cifs_dbg(VFS, "DFS capability contradicts DFS flag\n"); init_copy_chunk_defaults(tcon); + if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA) + cifs_dbg(VFS, "Encrypted shares not supported"); if (tcon->ses->server->ops->validate_negotiate) rc = tcon->ses->server->ops->validate_negotiate(xid, tcon); tcon_exit: @@ -119,7 +119,8 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, size_t len; if (pos == max) { unsigned blkbits = inode->i_blkbits; - sector_t block = pos >> blkbits; + long page = pos >> PAGE_SHIFT; + sector_t block = page << (PAGE_SHIFT - blkbits); unsigned first = pos - (block << blkbits); long size; @@ -284,6 +285,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh, static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { + struct address_space *mapping = inode->i_mapping; sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; void __pmem *addr; @@ -291,6 +293,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, pgoff_t size; int error; + i_mmap_lock_read(mapping); + /* * Check truncate didn't happen while we were allocating a block. * If it did, this block may or may not be still allocated to the @@ -320,6 +324,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, error = vm_insert_mixed(vma, vaddr, pfn); out: + i_mmap_unlock_read(mapping); + return error; } @@ -381,17 +387,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * from a read fault and we've raced with a truncate */ error = -EIO; - goto unlock; + goto unlock_page; } - } else { - i_mmap_lock_write(mapping); } error = get_block(inode, block, &bh, 0); if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; /* fs corruption? */ if (error) - goto unlock; + goto unlock_page; if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) { if (vmf->flags & FAULT_FLAG_WRITE) { @@ -402,9 +406,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; if (error) - goto unlock; + goto unlock_page; } else { - i_mmap_unlock_write(mapping); return dax_load_hole(mapping, page, vmf); } } @@ -416,15 +419,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, else clear_user_highpage(new_page, vaddr); if (error) - goto unlock; + goto unlock_page; vmf->page = page; if (!page) { + i_mmap_lock_read(mapping); /* Check we didn't race with truncate */ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) { + i_mmap_unlock_read(mapping); error = -EIO; - goto unlock; + goto out; } } return VM_FAULT_LOCKED; @@ -460,8 +465,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); } - if (!page) - i_mmap_unlock_write(mapping); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; @@ -470,14 +473,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; - unlock: + unlock_page: if (page) { unlock_page(page); page_cache_release(page); - } else { - i_mmap_unlock_write(mapping); } - goto out; } EXPORT_SYMBOL(__dax_fault); @@ -555,10 +555,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - i_mmap_lock_write(mapping); length = get_block(inode, block, &bh, write); if (length) return VM_FAULT_SIGBUS; + i_mmap_lock_read(mapping); /* * If the filesystem isn't willing to tell us the length of a hole, @@ -568,24 +568,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) goto fallback; - if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); - wmb_pmem(); - count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); - result |= VM_FAULT_MAJOR; - } - /* * If we allocated new storage, make sure no process has any * zero pages covering this hole */ if (buffer_new(&bh)) { - i_mmap_unlock_write(mapping); + i_mmap_unlock_read(mapping); unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0); - i_mmap_lock_write(mapping); + i_mmap_lock_read(mapping); } /* @@ -632,15 +622,25 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) goto fallback; + if (buffer_unwritten(&bh) || buffer_new(&bh)) { + int i; + for (i = 0; i < PTRS_PER_PMD; i++) + clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + wmb_pmem(); + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + result |= VM_FAULT_MAJOR; + } + result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write); } out: + i_mmap_unlock_read(mapping); + if (buffer_unwritten(&bh)) complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); - i_mmap_unlock_write(mapping); - return result; fallback: diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 47728da7702c..b46e9fc64196 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -63,7 +63,7 @@ config EXT4_FS If unsure, say N. config EXT4_USE_FOR_EXT2 - bool "Use ext4 for ext2/ext3 file systems" + bool "Use ext4 for ext2 file systems" depends on EXT4_FS depends on EXT2_FS=n default y diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index e26803fb210d..560af0437704 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -165,8 +165,8 @@ int ext4_mpage_readpages(struct address_space *mapping, if (pages) { page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) + if (add_to_page_cache_lru(page, mapping, page->index, + GFP_KERNEL & mapping_gfp_mask(mapping))) goto next_page; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 587ac08eabb6..29e4599f6fc1 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -778,19 +778,24 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { - int next_memcg_id = 0; - struct bdi_writeback *wb; - struct wb_iter iter; + struct bdi_writeback *last_wb = NULL; + struct bdi_writeback *wb = list_entry_rcu(&bdi->wb_list, + struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); - bdi_for_each_wb(wb, bdi, &iter, next_memcg_id) { + list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; + if (last_wb) { + wb_put(last_wb); + last_wb = NULL; + } + /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || @@ -819,12 +824,22 @@ restart: wb_queue_work(wb, work); - next_memcg_id = wb->memcg_css->id + 1; + /* + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + wb_get(wb); + last_wb = wb; + rcu_read_unlock(); wb_wait_for_completion(bdi, &fallback_work_done); goto restart; } rcu_read_unlock(); + + if (last_wb) + wb_put(last_wb); } #else /* CONFIG_CGROUP_WRITEBACK */ @@ -1481,6 +1496,21 @@ static long writeback_sb_inodes(struct super_block *sb, wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; + + if (need_resched()) { + /* + * We're trying to balance between building up a nice + * long list of IOs to improve our merge rate, and + * getting those IOs out quickly for anyone throttling + * in balance_dirty_pages(). cond_resched() doesn't + * unplug, so get our IOs out the door before we + * give up the CPU. + */ + blk_flush_plug(current); + cond_resched(); + } + + spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) @@ -1488,7 +1518,7 @@ static long writeback_sb_inodes(struct super_block *sb, requeue_inode(inode, wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); - cond_resched_lock(&wb->list_lock); + /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. @@ -1842,12 +1872,11 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; if (!bdi_has_dirty_io(bdi)) continue; - bdi_for_each_wb(wb, bdi, &iter, 0) + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages), false, reason); } @@ -1879,11 +1908,10 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; - bdi_for_each_wb(wb, bdi, &iter, 0) - if (!list_empty(&bdi->wb.b_dirty_time)) - wb_wakeup(&bdi->wb); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) + if (!list_empty(&wb->b_dirty_time)) + wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); diff --git a/fs/mpage.c b/fs/mpage.c index 778a4ddef77a..a7c34274f207 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -139,7 +139,8 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) static struct bio * do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, sector_t *last_block_in_bio, struct buffer_head *map_bh, - unsigned long *first_logical_block, get_block_t get_block) + unsigned long *first_logical_block, get_block_t get_block, + gfp_t gfp) { struct inode *inode = page->mapping->host; const unsigned blkbits = inode->i_blkbits; @@ -277,8 +278,7 @@ alloc_new: goto out; } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - min_t(int, nr_pages, BIO_MAX_PAGES), - GFP_KERNEL); + min_t(int, nr_pages, BIO_MAX_PAGES), gfp); if (bio == NULL) goto confused; } @@ -361,6 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); map_bh.b_state = 0; map_bh.b_size = 0; @@ -370,12 +371,13 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, prefetchw(&page->flags); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) { + page->index, + gfp)) { bio = do_mpage_readpage(bio, page, nr_pages - page_idx, &last_block_in_bio, &map_bh, &first_logical_block, - get_block); + get_block, gfp); } page_cache_release(page); } @@ -395,11 +397,12 @@ int mpage_readpage(struct page *page, get_block_t get_block) sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping); map_bh.b_state = 0; map_bh.b_size = 0; bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio, - &map_bh, &first_logical_block, get_block); + &map_bh, &first_logical_block, get_block, gfp); if (bio) mpage_bio_submit(READ, bio); return 0; diff --git a/fs/namei.c b/fs/namei.c index 726d211db484..33e9495a3129 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1558,8 +1558,6 @@ static int lookup_fast(struct nameidata *nd, negative = d_is_negative(dentry); if (read_seqcount_retry(&dentry->d_seq, seq)) return -ECHILD; - if (negative) - return -ENOENT; /* * This sequence count validates that the parent had no @@ -1580,6 +1578,12 @@ static int lookup_fast(struct nameidata *nd, goto unlazy; } } + /* + * Note: do negative dentry check after revalidation in + * case that drops it. + */ + if (negative) + return -ENOENT; path->mnt = mnt; path->dentry = dentry; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2714ef835bdd..be806ead7f4d 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -113,7 +113,8 @@ out: return status; } -static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid) +static int nfs_delegation_claim_opens(struct inode *inode, + const nfs4_stateid *stateid, fmode_t type) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; @@ -140,7 +141,7 @@ again: /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); - err = nfs4_open_delegation_recall(ctx, state, stateid); + err = nfs4_open_delegation_recall(ctx, state, stateid, type); if (!err) err = nfs_delegation_claim_locks(ctx, state, stateid); if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) @@ -411,7 +412,8 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation do { if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) break; - err = nfs_delegation_claim_opens(inode, &delegation->stateid); + err = nfs_delegation_claim_opens(inode, &delegation->stateid, + delegation->type); if (!issync || err != -EAGAIN) break; /* diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index a44829173e57..333063e032f0 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -54,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync); -int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid); +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type); int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 38678d9a5cc4..4b1d08f56aba 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -166,8 +166,11 @@ nfs_direct_select_verf(struct nfs_direct_req *dreq, struct nfs_writeverf *verfp = &dreq->verf; #ifdef CONFIG_NFS_V4_1 - if (ds_clp) { - /* pNFS is in use, use the DS verf */ + /* + * pNFS is in use, use the DS verf except commit_through_mds is set + * for layout segment where nbuckets is zero. + */ + if (ds_clp && dreq->ds_cinfo.nbuckets > 0) { if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets) verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf; else diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index b34f2e228601..02ec07973bc4 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -629,23 +629,18 @@ out_put: goto out; } -static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl) +static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl) { int i; - for (i = 0; i < fl->num_fh; i++) { - if (!fl->fh_array[i]) - break; - kfree(fl->fh_array[i]); + if (fl->fh_array) { + for (i = 0; i < fl->num_fh; i++) { + if (!fl->fh_array[i]) + break; + kfree(fl->fh_array[i]); + } + kfree(fl->fh_array); } - kfree(fl->fh_array); - fl->fh_array = NULL; -} - -static void -_filelayout_free_lseg(struct nfs4_filelayout_segment *fl) -{ - filelayout_free_fh_array(fl); kfree(fl); } @@ -716,21 +711,21 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, /* Do we want to use a mempool here? */ fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags); if (!fl->fh_array[i]) - goto out_err_free; + goto out_err; p = xdr_inline_decode(&stream, 4); if (unlikely(!p)) - goto out_err_free; + goto out_err; fl->fh_array[i]->size = be32_to_cpup(p++); if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { printk(KERN_ERR "NFS: Too big fh %d received %d\n", i, fl->fh_array[i]->size); - goto out_err_free; + goto out_err; } p = xdr_inline_decode(&stream, fl->fh_array[i]->size); if (unlikely(!p)) - goto out_err_free; + goto out_err; memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); dprintk("DEBUG: %s: fh len %d\n", __func__, fl->fh_array[i]->size); @@ -739,8 +734,6 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, __free_page(scratch); return 0; -out_err_free: - filelayout_free_fh_array(fl); out_err: __free_page(scratch); return -EIO; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d731bbf974aa..0f020e4d8421 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -175,10 +175,12 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; - int err; + loff_t err; do { err = _nfs42_proc_llseek(filep, offset, whence); + if (err >= 0) + break; if (err == -ENOTSUPP) return -EOPNOTSUPP; err = nfs4_handle_exception(server, err, &exception); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 693b903b48bd..5133bb18830e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1127,6 +1127,21 @@ static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task) return ret; } +static bool nfs4_mode_match_open_stateid(struct nfs4_state *state, + fmode_t fmode) +{ + switch(fmode & (FMODE_READ|FMODE_WRITE)) { + case FMODE_READ|FMODE_WRITE: + return state->n_rdwr != 0; + case FMODE_WRITE: + return state->n_wronly != 0; + case FMODE_READ: + return state->n_rdonly != 0; + } + WARN_ON_ONCE(1); + return false; +} + static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode) { int ret = 0; @@ -1443,12 +1458,18 @@ nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state) if (delegation) delegation_flags = delegation->flags; rcu_read_unlock(); - if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) { + switch (data->o_arg.claim) { + default: + break; + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: pr_err_ratelimited("NFS: Broken NFSv4 server %s is " "returning a delegation for " "OPEN(CLAIM_DELEGATE_CUR)\n", clp->cl_hostname); - } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) + return; + } + if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) nfs_inode_set_delegation(state->inode, data->owner->so_cred, &data->o_res); @@ -1571,17 +1592,13 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context return opendata; } -static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res) +static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, + fmode_t fmode) { struct nfs4_state *newstate; int ret; - if ((opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR || - opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEG_CUR_FH) && - (opendata->o_arg.u.delegation_type & fmode) != fmode) - /* This mode can't have been delegated, so we must have - * a valid open_stateid to cover it - not need to reclaim. - */ + if (!nfs4_mode_match_open_stateid(opendata->state, fmode)) return 0; opendata->o_arg.open_flags = 0; opendata->o_arg.fmode = fmode; @@ -1597,14 +1614,14 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod newstate = nfs4_opendata_to_nfs4_state(opendata); if (IS_ERR(newstate)) return PTR_ERR(newstate); + if (newstate != opendata->state) + ret = -ESTALE; nfs4_close_state(newstate, fmode); - *res = newstate; - return 0; + return ret; } static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state) { - struct nfs4_state *newstate; int ret; /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */ @@ -1615,27 +1632,15 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * clear_bit(NFS_DELEGATED_STATE, &state->flags); clear_bit(NFS_OPEN_STATE, &state->flags); smp_rmb(); - if (state->n_rdwr != 0) { - ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate); - if (ret != 0) - return ret; - if (newstate != state) - return -ESTALE; - } - if (state->n_wronly != 0) { - ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate); - if (ret != 0) - return ret; - if (newstate != state) - return -ESTALE; - } - if (state->n_rdonly != 0) { - ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate); - if (ret != 0) - return ret; - if (newstate != state) - return -ESTALE; - } + ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); + if (ret != 0) + return ret; + ret = nfs4_open_recover_helper(opendata, FMODE_WRITE); + if (ret != 0) + return ret; + ret = nfs4_open_recover_helper(opendata, FMODE_READ); + if (ret != 0) + return ret; /* * We may have performed cached opens for all three recoveries. * Check if we need to update the current stateid. @@ -1759,18 +1764,35 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct return err; } -int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, + struct nfs4_state *state, const nfs4_stateid *stateid, + fmode_t type) { struct nfs_server *server = NFS_SERVER(state->inode); struct nfs4_opendata *opendata; - int err; + int err = 0; opendata = nfs4_open_recoverdata_alloc(ctx, state, NFS4_OPEN_CLAIM_DELEG_CUR_FH); if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - err = nfs4_open_recover(opendata, state); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); + switch (type & (FMODE_READ|FMODE_WRITE)) { + case FMODE_READ|FMODE_WRITE: + case FMODE_WRITE: + err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); + if (err) + break; + err = nfs4_open_recover_helper(opendata, FMODE_WRITE); + if (err) + break; + case FMODE_READ: + err = nfs4_open_recover_helper(opendata, FMODE_READ); + } nfs4_opendata_put(opendata); return nfs4_handle_delegation_recall_error(server, state, stateid, err); } @@ -1850,6 +1872,8 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) data->rpc_done = 0; data->rpc_status = 0; data->timestamp = jiffies; + if (data->is_recover) + nfs4_set_sequence_privileged(&data->c_arg.seq_args); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -2645,6 +2669,15 @@ out: return err; } +static bool +nfs4_wait_on_layoutreturn(struct inode *inode, struct rpc_task *task) +{ + if (inode == NULL || !nfs_have_layout(inode)) + return false; + + return pnfs_wait_on_layoutreturn(inode, task); +} + struct nfs4_closedata { struct inode *inode; struct nfs4_state *state; @@ -2763,6 +2796,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_no_action; } + if (nfs4_wait_on_layoutreturn(inode, task)) { + nfs_release_seqid(calldata->arg.seqid); + goto out_wait; + } + if (calldata->arg.fmode == 0) task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE]; if (calldata->roc) @@ -5308,6 +5346,9 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) d_data = (struct nfs4_delegreturndata *)data; + if (nfs4_wait_on_layoutreturn(d_data->inode, task)) + return; + if (d_data->roc) pnfs_roc_get_barrier(d_data->inode, &d_data->roc_barrier); @@ -7800,39 +7841,46 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n", __func__, delay); rpc_delay(task, delay); - task->tk_status = 0; - rpc_restart_call_prepare(task); - goto out; /* Do not call nfs4_async_handle_error() */ + /* Do not call nfs4_async_handle_error() */ + goto out_restart; } break; case -NFS4ERR_EXPIRED: case -NFS4ERR_BAD_STATEID: spin_lock(&inode->i_lock); - lo = NFS_I(inode)->layout; - if (!lo || list_empty(&lo->plh_segs)) { + if (nfs4_stateid_match(&lgp->args.stateid, + &lgp->args.ctx->state->stateid)) { spin_unlock(&inode->i_lock); /* If the open stateid was bad, then recover it. */ state = lgp->args.ctx->state; - } else { + break; + } + lo = NFS_I(inode)->layout; + if (lo && nfs4_stateid_match(&lgp->args.stateid, + &lo->plh_stateid)) { LIST_HEAD(head); /* * Mark the bad layout state as invalid, then retry * with the current stateid. */ + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); pnfs_mark_matching_lsegs_invalid(lo, &head, NULL); spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&head); - - task->tk_status = 0; - rpc_restart_call_prepare(task); - } + } else + spin_unlock(&inode->i_lock); + goto out_restart; } if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) - rpc_restart_call_prepare(task); + goto out_restart; out: dprintk("<-- %s\n", __func__); return; +out_restart: + task->tk_status = 0; + rpc_restart_call_prepare(task); + return; out_overflow: task->tk_status = -EOVERFLOW; goto out; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index da73bc443238..d854693a15b0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1481,7 +1481,7 @@ restart: spin_unlock(&state->state_lock); } nfs4_put_open_state(state); - clear_bit(NFS4CLNT_RECLAIM_NOGRACE, + clear_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags); spin_lock(&sp->so_lock); goto restart; @@ -1725,7 +1725,8 @@ restart: if (!test_and_clear_bit(ops->owner_flag_bit, &sp->so_flags)) continue; - atomic_inc(&sp->so_count); + if (!atomic_inc_not_zero(&sp->so_count)) + continue; spin_unlock(&clp->cl_lock); rcu_read_unlock(); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 28df12e525ba..671cf68fe56b 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -409,7 +409,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->flags = flags; __entry->fmode = (__force unsigned int)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; - if (!IS_ERR(state)) + if (!IS_ERR_OR_NULL(state)) inode = state->inode; if (inode != NULL) { __entry->fileid = NFS_FILEID(inode); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 7c5718ba625e..fe3ddd20ff89 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -508,7 +508,7 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, * for it without upsetting the slab allocator. */ if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) * - sizeof(struct page) > PAGE_SIZE) + sizeof(struct page *) > PAGE_SIZE) return 0; return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index ba1246433794..8abe27165ad0 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1104,20 +1104,15 @@ bool pnfs_roc(struct inode *ino) mark_lseg_invalid(lseg, &tmp_list); found = true; } - /* pnfs_prepare_layoutreturn() grabs lo ref and it will be put - * in pnfs_roc_release(). We don't really send a layoutreturn but - * still want others to view us like we are sending one! - * - * If pnfs_prepare_layoutreturn() fails, it means someone else is doing - * LAYOUTRETURN, so we proceed like there are no layouts to return. - * - * ROC in three conditions: + /* ROC in two conditions: * 1. there are ROC lsegs * 2. we don't send layoutreturn - * 3. no others are sending layoutreturn */ - if (found && !layoutreturn && pnfs_prepare_layoutreturn(lo)) + if (found && !layoutreturn) { + /* lo ref dropped in pnfs_roc_release() */ + pnfs_get_layout_hdr(lo); roc = true; + } out_noroc: spin_unlock(&ino->i_lock); @@ -1172,6 +1167,26 @@ void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier) spin_unlock(&ino->i_lock); } +bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *lo; + bool sleep = false; + + /* we might not have grabbed lo reference. so need to check under + * i_lock */ + spin_lock(&ino->i_lock); + lo = nfsi->layout; + if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + sleep = true; + spin_unlock(&ino->i_lock); + + if (sleep) + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + + return sleep; +} + /* * Compare two layout segments for sorting into layout cache. * We want to preferentially return RW over RO layouts, so ensure those diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 78c9351ff117..d1990e90e7a0 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -270,6 +270,7 @@ bool pnfs_roc(struct inode *ino); void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier); +bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task); void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t); void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); int pnfs_layoutcommit_inode(struct inode *inode, bool sync); @@ -639,6 +640,12 @@ pnfs_roc_get_barrier(struct inode *ino, u32 *barrier) { } +static inline bool +pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task) +{ + return false; +} + static inline void set_pnfs_layoutdriver(struct nfs_server *s, const struct nfs_fh *mntfh, u32 id) { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index ae0ff7a11b40..01b8cc8e8cfc 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -72,6 +72,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; + if (pgio->pg_ops && pgio->pg_ops->pg_cleanup) + pgio->pg_ops->pg_cleanup(pgio); + pgio->pg_ops = &nfs_pgio_rw_ops; /* read path should never have more than one mirror */ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 388f48079c43..75ab7622e0cc 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -569,19 +569,17 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, if (!nfs_pageio_add_request(pgio, req)) { nfs_redirty_request(req); ret = pgio->pg_error; - } + } else + nfs_add_stats(page_file_mapping(page)->host, + NFSIOS_WRITEPAGES, 1); out: return ret; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { - struct inode *inode = page_file_mapping(page)->host; int ret; - nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); - nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { @@ -597,9 +595,11 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) { struct nfs_pageio_descriptor pgio; + struct inode *inode = page_file_mapping(page)->host; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); @@ -1223,7 +1223,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino return 1; if (!flctx || (list_empty_careful(&flctx->flc_flock) && list_empty_careful(&flctx->flc_posix))) - return 0; + return 1; /* Check to see if there are whole file write locks */ ret = 0; @@ -1351,6 +1351,9 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; + if (pgio->pg_ops && pgio->pg_ops->pg_cleanup) + pgio->pg_ops->pg_cleanup(pgio); + pgio->pg_ops = &nfs_pgio_rw_ops; nfs_pageio_stop_mirroring(pgio); diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index cdefaa331a07..c29d9421bd5e 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -56,14 +56,6 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, u32 device_generation = 0; int error; - /* - * We do not attempt to support I/O smaller than the fs block size, - * or not aligned to it. - */ - if (args->lg_minlength < block_size) { - dprintk("pnfsd: I/O too small\n"); - goto out_layoutunavailable; - } if (seg->offset & (block_size - 1)) { dprintk("pnfsd: I/O misaligned\n"); goto out_layoutunavailable; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 46b8b2bbc95a..ce38b4ccc9ab 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data, int found, ret; int set_maybe; int dispatch_assert = 0; + int dispatched = 0; if (!dlm_grab(dlm)) return DLM_MASTER_RESP_NO; @@ -1657,16 +1658,20 @@ send_response: if (ret < 0) { mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; + spin_unlock(&res->spinlock); dlm_lockres_put(res); - } else + } else { + dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); - spin_unlock(&res->spinlock); + spin_unlock(&res->spinlock); + } } else { if (res) dlm_lockres_put(res); } - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return response; } @@ -2090,7 +2095,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm, /* queue up work for dlm_assert_master_worker */ - dlm_grab(dlm); /* get an extra ref for the work item */ dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL); item->u.am.lockres = res; /* already have a ref */ /* can optionally ignore node numbers higher than this node */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index ce12e0b1a31f..58eaa5c0d387 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, unsigned int hash; int master = DLM_LOCK_RES_OWNER_UNKNOWN; u32 flags = DLM_ASSERT_MASTER_REQUERY; + int dispatched = 0; if (!dlm_grab(dlm)) { /* since the domain has gone away on this @@ -1719,9 +1720,11 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, dlm_put(dlm); /* sender will take care of this and retry */ return ret; - } else + } else { + dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); - spin_unlock(&res->spinlock); + spin_unlock(&res->spinlock); + } } else { /* put.. incase we are not the master */ spin_unlock(&res->spinlock); @@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, } spin_unlock(&dlm->spinlock); - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return master; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 84d693d37428..871fcb67be97 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -81,11 +81,11 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) if (len == 0) return 0; - old_file = ovl_path_open(old, O_RDONLY); + old_file = ovl_path_open(old, O_LARGEFILE | O_RDONLY); if (IS_ERR(old_file)) return PTR_ERR(old_file); - new_file = ovl_path_open(new, O_WRONLY); + new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY); if (IS_ERR(new_file)) { error = PTR_ERR(new_file); goto out_fput; @@ -267,7 +267,7 @@ out: out_cleanup: ovl_cleanup(wdir, newdentry); - goto out; + goto out2; } /* diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d9da5a4e9382..ec0c2a050043 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -363,6 +363,9 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) ovl_path_upper(dentry, &realpath); } + if (realpath.dentry->d_flags & DCACHE_OP_SELECT_INODE) + return realpath.dentry->d_op->d_select_inode(realpath.dentry, file_flags); + return d_backing_inode(realpath.dentry); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 79073d68b475..e38ee0fed24a 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -544,6 +544,7 @@ static void ovl_put_super(struct super_block *sb) mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); kfree(ufs->config.lowerdir); kfree(ufs->config.upperdir); @@ -1048,6 +1049,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) oe->lowerstack[i].dentry = stack[i].dentry; oe->lowerstack[i].mnt = ufs->lower_mnt[i]; } + kfree(stack); root_dentry->d_fsdata = oe; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index ba1323a94924..a586467f6ff6 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -70,6 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) unsigned order; void *data; int ret; + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); /* make various checks */ order = get_order(newsize); @@ -84,7 +85,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* allocate enough contiguous pages to be able to satisfy the * request */ - pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order); + pages = alloc_pages(gfp, order); if (!pages) return -ENOMEM; @@ -108,7 +109,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) struct page *page = pages + loop; ret = add_to_page_cache_lru(page, inode->i_mapping, loop, - GFP_KERNEL); + gfp); if (ret < 0) goto add_error; diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 96f3448b6eb4..fd65b3f1923c 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -652,11 +652,8 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode, { int err; - mutex_lock(&inode->i_mutex); err = security_inode_init_security(inode, dentry, qstr, &init_xattrs, 0); - mutex_unlock(&inode->i_mutex); - if (err) { struct ubifs_info *c = dentry->i_sb->s_fs_info; ubifs_err(c, "cannot initialize security for inode %lu, error %d", diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 634e676072cb..50311703135b 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * the fault_*wqh. */ spin_lock(&ctx->fault_pending_wqh.lock); - __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range); - __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range); + __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); + __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range); spin_unlock(&ctx->fault_pending_wqh.lock); wake_up_poll(&ctx->fd_wqh, POLLHUP); @@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx, spin_lock(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) - __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, + __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) - __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range); + __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range); spin_unlock(&ctx->fault_pending_wqh.lock); } @@ -1287,8 +1287,10 @@ static struct file *userfaultfd_file_create(int flags) file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx, O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS)); - if (IS_ERR(file)) + if (IS_ERR(file)) { + mmput(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); + } out: return file; } |