diff options
Diffstat (limited to 'fs')
71 files changed, 1021 insertions, 818 deletions
diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 6e2c967fa..07dc4ec73 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -473,16 +473,6 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; } - /* Don't expose silly rename entries to userspace. */ - if (nlen > 6 && - dire->u.name[0] == '.' && - ctx->actor != afs_lookup_filldir && - ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) { - ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); - continue; - } - /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, ntohl(dire->u.vnode), @@ -591,8 +591,8 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; /* @@ -602,9 +602,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) if (!(iocb->ki_flags & IOCB_AIO_RW)) return; + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9f77565bd..5993b627b 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1413,7 +1413,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * needing to allocate extents from the block group. */ used = btrfs_space_info_used(space_info, true); - if (space_info->total_bytes - block_group->length < used) { + if (space_info->total_bytes - block_group->length < used && + block_group->zone_unusable < block_group->length) { /* * Add a reference for the list, compensate for the ref * drop under the "next" label for the diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 507b44d18..4cbf38616 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -512,7 +512,7 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans, block_rsv = get_block_rsv(trans, root); - if (unlikely(block_rsv->size == 0)) + if (unlikely(btrfs_block_rsv_size(block_rsv) == 0)) goto try_reserve; again: ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize); diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h index 578c3497a..df87c4949 100644 --- a/fs/btrfs/block-rsv.h +++ b/fs/btrfs/block-rsv.h @@ -101,4 +101,36 @@ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv) return data_race(rsv->full); } +/* + * Get the reserved mount of a block reserve in a context where getting a stale + * value is acceptable, instead of accessing it directly and trigger data race + * warning from KCSAN. + */ +static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv) +{ + u64 ret; + + spin_lock(&rsv->lock); + ret = rsv->reserved; + spin_unlock(&rsv->lock); + + return ret; +} + +/* + * Get the size of a block reserve in a context where getting a stale value is + * acceptable, instead of accessing it directly and trigger data race warning + * from KCSAN. + */ +static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv) +{ + u64 ret; + + spin_lock(&rsv->lock); + ret = rsv->size; + spin_unlock(&rsv->lock); + + return ret; +} + #endif /* BTRFS_BLOCK_RSV_H */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index b3472bf6b..c14d4f70e 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2800,11 +2800,6 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) goto cleanup; } - /* Free the reserved data space */ - btrfs_qgroup_free_refroot(fs_info, - record->data_rsv_refroot, - record->data_rsv, - BTRFS_QGROUP_RSV_DATA); /* * Use BTRFS_SEQ_LAST as time_seq to do special search, * which doesn't lock tree or delayed_refs and search @@ -2826,6 +2821,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) record->old_roots = NULL; new_roots = NULL; } + /* Free the reserved data space */ + btrfs_qgroup_free_refroot(fs_info, + record->data_rsv_refroot, + record->data_rsv, + BTRFS_QGROUP_RSV_DATA); cleanup: ulist_free(record->old_roots); ulist_free(new_roots); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 1672d4846..12a2b1e3f 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -4177,7 +4177,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, gen = fs_info->last_trans_committed; for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr); + if (ret == -ENOENT) + break; + + if (ret) { + spin_lock(&sctx->stat_lock); + sctx->stat.super_errors++; + spin_unlock(&sctx->stat_lock); + continue; + } + if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 2635fb4bf..8b75f436a 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -847,7 +847,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info) { - u64 global_rsv_size = fs_info->global_block_rsv.reserved; + const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv); u64 ordered, delalloc; u64 total = writable_total_bytes(fs_info, space_info); u64 thresh; @@ -948,8 +948,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, ordered = percpu_counter_read_positive(&fs_info->ordered_bytes) >> 1; delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes); if (ordered >= delalloc) - used += fs_info->delayed_refs_rsv.reserved + - fs_info->delayed_block_rsv.reserved; + used += btrfs_block_rsv_reserved(&fs_info->delayed_refs_rsv) + + btrfs_block_rsv_reserved(&fs_info->delayed_block_rsv); else used += space_info->bytes_may_use - global_rsv_size; @@ -1164,7 +1164,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) enum btrfs_flush_state flush; u64 delalloc_size = 0; u64 to_reclaim, block_rsv_size; - u64 global_rsv_size = global_rsv->reserved; + const u64 global_rsv_size = btrfs_block_rsv_reserved(global_rsv); loops++; @@ -1176,9 +1176,9 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * assume it's tied up in delalloc reservations. */ block_rsv_size = global_rsv_size + - delayed_block_rsv->reserved + - delayed_refs_rsv->reserved + - trans_rsv->reserved; + btrfs_block_rsv_reserved(delayed_block_rsv) + + btrfs_block_rsv_reserved(delayed_refs_rsv) + + btrfs_block_rsv_reserved(trans_rsv); if (block_rsv_size < space_info->bytes_may_use) delalloc_size = space_info->bytes_may_use - block_rsv_size; @@ -1198,16 +1198,16 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) to_reclaim = delalloc_size; flush = FLUSH_DELALLOC; } else if (space_info->bytes_pinned > - (delayed_block_rsv->reserved + - delayed_refs_rsv->reserved)) { + (btrfs_block_rsv_reserved(delayed_block_rsv) + + btrfs_block_rsv_reserved(delayed_refs_rsv))) { to_reclaim = space_info->bytes_pinned; flush = COMMIT_TRANS; - } else if (delayed_block_rsv->reserved > - delayed_refs_rsv->reserved) { - to_reclaim = delayed_block_rsv->reserved; + } else if (btrfs_block_rsv_reserved(delayed_block_rsv) > + btrfs_block_rsv_reserved(delayed_refs_rsv)) { + to_reclaim = btrfs_block_rsv_reserved(delayed_block_rsv); flush = FLUSH_DELAYED_ITEMS_NR; } else { - to_reclaim = delayed_refs_rsv->reserved; + to_reclaim = btrfs_block_rsv_reserved(delayed_refs_rsv); flush = FLUSH_DELAYED_REFS_NR; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc2d9927..03cfb425e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1444,7 +1444,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } @@ -896,6 +896,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 6a3e27771..bc0ca45a5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4684,10 +4684,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_g_ex.fe_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -4699,7 +4705,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal and still * cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -4709,7 +4715,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -4717,7 +4723,6 @@ adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f2ed15af7..38ce42396 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1606,7 +1606,8 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index eb4d69f53..3ec203bbd 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -70,7 +70,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .old_blkaddr = index, .new_blkaddr = index, .encrypted_page = NULL, - .is_por = !is_meta, + .is_por = !is_meta ? 1 : 0, }; int err; @@ -234,8 +234,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, .op = REQ_OP_READ, .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD, .encrypted_page = NULL, - .in_list = false, - .is_por = (type == META_POR), + .in_list = 0, + .is_por = (type == META_POR) ? 1 : 0, }; struct blk_plug plug; int err; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 967262c37..df6dfd7de 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1249,10 +1249,11 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, .page = NULL, .encrypted_page = NULL, .compressed_page = NULL, - .submitted = false, + .submitted = 0, .io_type = io_type, .io_wbc = wbc, - .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode), + .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ? + 1 : 0, }; struct dnode_of_data dn; struct node_info ni; @@ -1387,8 +1388,6 @@ unlock_continue: add_compr_block_stat(inode, cc->valid_nr_cpages); set_inode_flag(cc->inode, FI_APPEND_WRITE); - if (cc->cluster_idx == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); f2fs_put_dnode(&dn); if (quota_inode) @@ -1436,6 +1435,8 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) struct f2fs_sb_info *sbi = bio->bi_private; struct compress_io_ctx *cic = (struct compress_io_ctx *)page_private(page); + enum count_type type = WB_DATA_TYPE(page, + f2fs_is_compressed_page(page)); int i; if (unlikely(bio->bi_status)) @@ -1443,7 +1444,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) f2fs_compress_free_page(page); - dec_page_count(sbi, F2FS_WB_DATA); + dec_page_count(sbi, type); if (atomic_dec_return(&cic->pending_pages)) return; @@ -1459,12 +1460,14 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) } static int f2fs_write_raw_pages(struct compress_ctx *cc, - int *submitted, + int *submitted_p, struct writeback_control *wbc, enum iostat_type io_type) { struct address_space *mapping = cc->inode->i_mapping; - int _submitted, compr_blocks, ret, i; + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + int submitted, compr_blocks, i; + int ret = 0; compr_blocks = f2fs_compressed_blocks(cc); @@ -1479,6 +1482,10 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc, if (compr_blocks < 0) return compr_blocks; + /* overwrite compressed cluster w/ normal cluster */ + if (compr_blocks > 0) + f2fs_lock_op(sbi); + for (i = 0; i < cc->cluster_size; i++) { if (!cc->rpages[i]) continue; @@ -1503,7 +1510,7 @@ continue_unlock: if (!clear_page_dirty_for_io(cc->rpages[i])) goto continue_unlock; - ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted, + ret = f2fs_write_single_data_page(cc->rpages[i], &submitted, NULL, NULL, wbc, io_type, compr_blocks, false); if (ret) { @@ -1511,26 +1518,29 @@ continue_unlock: unlock_page(cc->rpages[i]); ret = 0; } else if (ret == -EAGAIN) { + ret = 0; /* * for quota file, just redirty left pages to * avoid deadlock caused by cluster update race * from foreground operation. */ if (IS_NOQUOTA(cc->inode)) - return 0; - ret = 0; + goto out; f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry_write; } - return ret; + goto out; } - *submitted += _submitted; + *submitted_p += submitted; } - f2fs_balance_fs(F2FS_M_SB(mapping), true); +out: + if (compr_blocks > 0) + f2fs_unlock_op(sbi); - return 0; + f2fs_balance_fs(sbi, true); + return ret; } int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -1833,16 +1843,18 @@ void f2fs_put_page_dic(struct page *page, bool in_task) * check whether cluster blocks are contiguous, and add extent cache entry * only if cluster blocks are logically and physically contiguous. */ -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node) { - bool compressed = f2fs_data_blkaddr(dn) == COMPRESS_ADDR; + bool compressed = data_blkaddr(dn->inode, dn->node_page, + ofs_in_node) == COMPRESS_ADDR; int i = compressed ? 1 : 0; block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); if (!__is_valid_data_blkaddr(blkaddr)) break; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8b561af37..b83b8ac29 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -50,7 +50,7 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static bool __is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; struct inode *inode; @@ -67,8 +67,6 @@ static bool __is_cp_guaranteed(struct page *page) S_ISDIR(inode->i_mode)) return true; - if (f2fs_is_compressed_page(page)) - return false; if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) || page_private_gcing(page)) return true; @@ -327,7 +325,7 @@ static void f2fs_write_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; - enum count_type type = WB_DATA_TYPE(page); + enum count_type type = WB_DATA_TYPE(page, false); if (page_private_dummy(page)) { clear_page_private_dummy(page); @@ -733,7 +731,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page) : WB_DATA_TYPE(fio->page)); + __read_io_type(page) : WB_DATA_TYPE(fio->page, false)); __submit_bio(fio->sbi, bio, fio->type); return 0; @@ -941,7 +939,7 @@ alloc_new: if (fio->io_wbc) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); - inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + inc_page_count(fio->sbi, WB_DATA_TYPE(page, false)); *fio->last_block = fio->new_blkaddr; *fio->bio = bio; @@ -955,6 +953,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; + enum count_type type; f2fs_bug_on(sbi, is_read_io(fio->op)); @@ -982,9 +981,10 @@ next: bio_page = fio->page; /* set submitted = true as a return value */ - fio->submitted = true; + fio->submitted = 1; - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); + type = WB_DATA_TYPE(bio_page, fio->compressed_page); + inc_page_count(sbi, type); if (io->bio && (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, @@ -997,8 +997,9 @@ alloc_new: if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); - fio->retry = true; + dec_page_count(sbi, WB_DATA_TYPE(bio_page, + fio->compressed_page)); + fio->retry = 1; goto skip; } io->bio = __bio_alloc(fio, BIO_MAX_VECS); @@ -1102,18 +1103,12 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, return 0; } -static void __set_data_blkaddr(struct dnode_of_data *dn) +static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - struct f2fs_node *rn = F2FS_NODE(dn->node_page); - __le32 *addr_array; - int base = 0; - - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); + __le32 *addr = get_dnode_addr(dn->inode, dn->node_page); - /* Get physical address of data block */ - addr_array = blkaddr_in_node(rn); - addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); + dn->data_blkaddr = blkaddr; + addr[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); } /* @@ -1122,18 +1117,17 @@ static void __set_data_blkaddr(struct dnode_of_data *dn) * ->node_page * update block addresses in the node page */ -void f2fs_set_data_blkaddr(struct dnode_of_data *dn) +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, blkaddr); if (set_page_dirty(dn->node_page)) dn->node_changed = true; } void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - dn->data_blkaddr = blkaddr; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, blkaddr); f2fs_update_read_extent_cache(dn); } @@ -1148,7 +1142,8 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) return err; trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, @@ -1160,8 +1155,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) block_t blkaddr = f2fs_data_blkaddr(dn); if (blkaddr == NULL_ADDR) { - dn->data_blkaddr = NEW_ADDR; - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, NEW_ADDR); count--; } } @@ -1419,13 +1413,12 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) return err; dn->data_blkaddr = f2fs_data_blkaddr(dn); - if (dn->data_blkaddr != NULL_ADDR) - goto alloc; - - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) - return err; + if (dn->data_blkaddr == NULL_ADDR) { + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) + return err; + } -alloc: set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); old_blkaddr = dn->data_blkaddr; f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, @@ -2739,8 +2732,6 @@ got_it: f2fs_outplace_write_data(&dn, fio); trace_f2fs_do_write_data_page(page, OPU); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); out_writepage: f2fs_put_dnode(&dn); out: @@ -2776,10 +2767,10 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .old_blkaddr = NULL_ADDR, .page = page, .encrypted_page = NULL, - .submitted = false, + .submitted = 0, .compr_blocks = compr_blocks, - .need_lock = LOCK_RETRY, - .post_read = f2fs_post_read_required(inode), + .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, + .post_read = f2fs_post_read_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, .bio = bio, @@ -2819,9 +2810,6 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, zero_user_segment(page, offset, PAGE_SIZE); write: - if (f2fs_is_drop_cache(inode)) - goto out; - /* Dentry/quota blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode) || quota_inode) { /* @@ -2858,6 +2846,7 @@ write: if (err == -EAGAIN) { err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { + f2fs_bug_on(sbi, compr_blocks); fio.need_lock = LOCK_REQ; err = f2fs_do_write_data_page(&fio); } @@ -2902,7 +2891,7 @@ out: } if (submitted) - *submitted = fio.submitted ? 1 : 0; + *submitted = fio.submitted; return 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e5a9498b8..b54d681c6 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -74,6 +74,11 @@ struct f2fs_fault_info { extern const char *f2fs_fault_name[FAULT_MAX]; #define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) + +/* maximum retry count for injected failure */ +#define DEFAULT_FAILURE_RETRY_COUNT 8 +#else +#define DEFAULT_FAILURE_RETRY_COUNT 1 #endif /* @@ -764,8 +769,6 @@ enum { FI_UPDATE_WRITE, /* inode has in-place-update data */ FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ - FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ - FI_DROP_CACHE, /* drop dirty page cache */ FI_DATA_EXIST, /* indicate data exists */ FI_INLINE_DOTS, /* indicate inline dot dentries */ FI_SKIP_WRITES, /* should skip data page writeback */ @@ -1067,7 +1070,8 @@ struct f2fs_sm_info { * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ -#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) +#define WB_DATA_TYPE(p, f) \ + (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, @@ -1183,19 +1187,19 @@ struct f2fs_io_info { struct page *encrypted_page; /* encrypted page */ struct page *compressed_page; /* compressed page */ struct list_head list; /* serialize IOs */ - bool submitted; /* indicate IO submission */ - int need_lock; /* indicate we need to lock cp_rwsem */ - bool in_list; /* indicate fio is in io_list */ - bool is_por; /* indicate IO is from recovery or not */ - bool retry; /* need to reallocate block address */ - int compr_blocks; /* # of compressed block addresses */ - bool encrypted; /* indicate file is encrypted */ - bool post_read; /* require post read */ + unsigned int compr_blocks; /* # of compressed block addresses */ + unsigned int need_lock:8; /* indicate we need to lock cp_rwsem */ + unsigned int version:8; /* version of the node */ + unsigned int submitted:1; /* indicate IO submission */ + unsigned int in_list:1; /* indicate fio is in io_list */ + unsigned int is_por:1; /* indicate IO is from recovery or not */ + unsigned int retry:1; /* need to reallocate block address */ + unsigned int encrypted:1; /* indicate file is encrypted */ + unsigned int post_read:1; /* require post read */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ struct bio **bio; /* bio for ipu */ sector_t *last_block; /* last block number in bio */ - unsigned char version; /* version of the node */ }; struct bio_entry { @@ -2287,7 +2291,7 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, - struct inode *inode, blkcnt_t *count) + struct inode *inode, blkcnt_t *count, bool partial) { blkcnt_t diff = 0, release = 0; block_t avail_user_block_count; @@ -2328,6 +2332,11 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, avail_user_block_count = 0; } if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { + if (!partial) { + spin_unlock(&sbi->stat_lock); + goto enospc; + } + diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) diff = *count; @@ -2991,6 +3000,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_INLINE_DOTS: case FI_PIN_FILE: case FI_COMPRESS_RELEASED: + case FI_ATOMIC_COMMITTED: f2fs_mark_inode_dirty_sync(inode, true); } } @@ -3247,22 +3257,13 @@ static inline bool f2fs_is_cow_file(struct inode *inode) return is_inode_flag_set(inode, FI_COW_FILE); } -static inline bool f2fs_is_first_block_written(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN); -} - -static inline bool f2fs_is_drop_cache(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_DROP_CACHE); -} - +static inline __le32 *get_dnode_addr(struct inode *inode, + struct page *node_page); static inline void *inline_data_addr(struct inode *inode, struct page *page) { - struct f2fs_inode *ri = F2FS_INODE(page); - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, page); - return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]); + return (void *)(addr + DEF_INLINE_RESERVED_SIZE); } static inline int f2fs_has_inline_dentry(struct inode *inode) @@ -3397,6 +3398,17 @@ static inline int get_inline_xattr_addrs(struct inode *inode) return F2FS_I(inode)->i_inline_xattr_size; } +static inline __le32 *get_dnode_addr(struct inode *inode, + struct page *node_page) +{ + int base = 0; + + if (IS_INODE(node_page) && f2fs_has_extra_attr(inode)) + base = get_extra_isize(inode); + + return blkaddr_in_node(F2FS_NODE(node_page)) + base; +} + #define f2fs_get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -3761,6 +3773,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); +bool f2fs_is_cp_guaranteed(struct page *page); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_bio(struct f2fs_sb_info *sbi, @@ -3779,7 +3792,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, sector_t *sector); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); -void f2fs_set_data_blkaddr(struct dnode_of_data *dn); +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); int f2fs_reserve_new_block(struct dnode_of_data *dn); @@ -4246,7 +4259,8 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task); void f2fs_put_page_dic(struct page *page, bool in_task); -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn); +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); @@ -4303,7 +4317,8 @@ static inline void f2fs_put_page_dic(struct page *page, bool in_task) { WARN_ON_ONCE(1); } -static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; } +static inline unsigned int f2fs_cluster_blocks_are_contiguous( + struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; } static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; } static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { } @@ -4360,15 +4375,24 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); - if (!f2fs_compressed_file(inode)) + f2fs_down_write(&F2FS_I(inode)->i_sem); + + if (!f2fs_compressed_file(inode)) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; - if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) + } + if (f2fs_is_mmap_file(inode) || + (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return false; + } fi->i_flags &= ~F2FS_COMPR_FL; stat_dec_compr_inode(inode); clear_inode_flag(inode, FI_COMPRESSED_FILE); f2fs_mark_inode_dirty_sync(inode, true); + + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 46e4960a9..2fbc8d89c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -560,20 +560,14 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - struct f2fs_node *raw_node; int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; - int base = 0; bool compressed_cluster = false; int cluster_index = 0, valid_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks); - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); - - raw_node = F2FS_NODE(dn->node_page); - addr = blkaddr_in_node(raw_node) + base + ofs; + addr = get_dnode_addr(dn->inode, dn->node_page) + ofs; /* Assumption: truncateion starts with cluster */ for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) { @@ -591,8 +585,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) if (blkaddr == NULL_ADDR) continue; - dn->data_blkaddr = NULL_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NULL_ADDR); if (__is_valid_data_blkaddr(blkaddr)) { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, @@ -602,9 +595,6 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) valid_blocks++; } - if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) - clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); - f2fs_invalidate_blocks(sbi, blkaddr); if (!released || blkaddr != COMPRESS_ADDR) @@ -1497,8 +1487,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, } f2fs_invalidate_blocks(sbi, dn->data_blkaddr); - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NEW_ADDR); } f2fs_update_read_extent_cache_range(dn, start, 0, index - start); @@ -3449,8 +3438,7 @@ static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count) if (blkaddr != NEW_ADDR) continue; - dn->data_blkaddr = NULL_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NULL_ADDR); } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false); @@ -3474,7 +3462,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) int ret; int writecount; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) @@ -3487,7 +3475,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -3573,10 +3561,10 @@ out: return ret; } -static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count, + unsigned int *reserved_blocks) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - unsigned int reserved_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; block_t blkaddr; int i; @@ -3599,41 +3587,53 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) blkcnt_t reserved; int ret; - for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { - blkaddr = f2fs_data_blkaddr(dn); + for (i = 0; i < cluster_size; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_page, + dn->ofs_in_node + i); if (i == 0) { - if (blkaddr == COMPRESS_ADDR) - continue; - dn->ofs_in_node += cluster_size; - goto next; + if (blkaddr != COMPRESS_ADDR) { + dn->ofs_in_node += cluster_size; + goto next; + } + continue; } - if (__is_valid_data_blkaddr(blkaddr)) { + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR || + __is_valid_data_blkaddr(blkaddr)) { compr_blocks++; continue; } - - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); } reserved = cluster_size - compr_blocks; - ret = inc_valid_block_count(sbi, dn->inode, &reserved); - if (ret) + + /* for the case all blocks in cluster were reserved */ + if (reserved == 1) + goto next; + + ret = inc_valid_block_count(sbi, dn->inode, &reserved, false); + if (unlikely(ret)) return ret; - if (reserved != cluster_size - compr_blocks) - return -ENOSPC; + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + if (f2fs_data_blkaddr(dn) == NULL_ADDR) + f2fs_set_data_blkaddr(dn, NEW_ADDR); + } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true); - reserved_blocks += reserved; + *reserved_blocks += reserved; next: count -= cluster_size; } - return reserved_blocks; + return 0; } static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) @@ -3644,7 +3644,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) unsigned int reserved_blocks = 0; int ret; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) @@ -3657,10 +3657,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) - goto out; - - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -3669,6 +3666,9 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) goto unlock_inode; } + if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) + goto unlock_inode; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); @@ -3694,7 +3694,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); count = round_up(count, F2FS_I(inode)->i_cluster_size); - ret = reserve_compress_blocks(&dn, count); + ret = reserve_compress_blocks(&dn, count, &reserved_blocks); f2fs_put_dnode(&dn); @@ -3702,23 +3702,21 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) break; page_idx += count; - reserved_blocks += ret; } filemap_invalidate_unlock(inode->i_mapping); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (ret >= 0) { + if (!ret) { clear_inode_flag(inode, FI_COMPRESS_RELEASED); inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, true); } unlock_inode: inode_unlock(inode); -out: mnt_drop_write_file(filp); - if (ret >= 0) { + if (!ret) { ret = put_user(reserved_blocks, (u64 __user *)arg); } else if (reserved_blocks && atomic_read(&F2FS_I(inode)->i_compr_blocks)) { @@ -3967,16 +3965,20 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) sizeof(option))) return -EFAULT; - if (!f2fs_compressed_file(inode) || - option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || - option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || - option.algorithm >= COMPRESS_MAX) + if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) return -EINVAL; file_start_write(filp); inode_lock(inode); f2fs_down_write(&F2FS_I(inode)->i_sem); + if (!f2fs_compressed_file(inode)) { + ret = -EINVAL; + goto out; + } + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { ret = -EBUSY; goto out; @@ -4066,7 +4068,7 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg) if (!f2fs_compressed_file(inode)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); file_start_write(filp); inode_lock(inode); @@ -4138,7 +4140,7 @@ static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg) if (!f2fs_compressed_file(inode)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); file_start_write(filp); inode_lock(inode); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ec7212f7a..d4662ccb9 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1187,8 +1187,8 @@ static int ra_data_block(struct inode *inode, pgoff_t index) .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, - .in_list = false, - .retry = false, + .in_list = 0, + .retry = 0, }; int err; @@ -1276,8 +1276,8 @@ static int move_data_block(struct inode *inode, block_t bidx, .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, - .in_list = false, - .retry = false, + .in_list = 0, + .retry = 0, }; struct dnode_of_data dn; struct f2fs_summary sum; @@ -1410,8 +1410,6 @@ static int move_data_block(struct inode *inode, block_t bidx, f2fs_update_data_blkaddr(&dn, newaddr); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0010579f1..869bb6ec1 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -59,49 +59,31 @@ void f2fs_set_inode_flags(struct inode *inode) S_ENCRYPTED|S_VERITY|S_CASEFOLD); } -static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) +static void __get_inode_rdev(struct inode *inode, struct page *node_page) { - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, node_page); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { - if (ri->i_addr[extra_size]) - inode->i_rdev = old_decode_dev( - le32_to_cpu(ri->i_addr[extra_size])); + if (addr[0]) + inode->i_rdev = old_decode_dev(le32_to_cpu(addr[0])); else - inode->i_rdev = new_decode_dev( - le32_to_cpu(ri->i_addr[extra_size + 1])); + inode->i_rdev = new_decode_dev(le32_to_cpu(addr[1])); } } -static int __written_first_block(struct f2fs_sb_info *sbi, - struct f2fs_inode *ri) +static void __set_inode_rdev(struct inode *inode, struct page *node_page) { - block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]); - - if (!__is_valid_data_blkaddr(addr)) - return 1; - if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) { - f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); - return -EFSCORRUPTED; - } - return 0; -} - -static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) -{ - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, node_page); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { - ri->i_addr[extra_size] = - cpu_to_le32(old_encode_dev(inode->i_rdev)); - ri->i_addr[extra_size + 1] = 0; + addr[0] = cpu_to_le32(old_encode_dev(inode->i_rdev)); + addr[1] = 0; } else { - ri->i_addr[extra_size] = 0; - ri->i_addr[extra_size + 1] = - cpu_to_le32(new_encode_dev(inode->i_rdev)); - ri->i_addr[extra_size + 2] = 0; + addr[0] = 0; + addr[1] = cpu_to_le32(new_encode_dev(inode->i_rdev)); + addr[2] = 0; } } } @@ -336,7 +318,6 @@ static int do_read_inode(struct inode *inode) struct page *node_page; struct f2fs_inode *ri; projid_t i_projid; - int err; /* Check if ino is within scope */ if (f2fs_check_nid_range(sbi, inode->i_ino)) @@ -415,17 +396,7 @@ static int do_read_inode(struct inode *inode) } /* get rdev by using inline_info */ - __get_inode_rdev(inode, ri); - - if (S_ISREG(inode->i_mode)) { - err = __written_first_block(sbi, ri); - if (err < 0) { - f2fs_put_page(node_page, 1); - return err; - } - if (!err) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); - } + __get_inode_rdev(inode, node_page); if (!f2fs_need_inode_block_update(sbi, inode->i_ino)) fi->last_disk_size = inode->i_size; @@ -697,7 +668,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) } } - __set_inode_rdev(inode, ri); + __set_inode_rdev(inode, node_page); /* deleted inode */ if (inode->i_nlink == 0) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index c6d0e0709..fcf22a50f 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -850,21 +850,29 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (is_inode_flag_set(dn->inode, FI_COMPRESSED_FILE) && f2fs_sb_has_readonly(sbi)) { - unsigned int c_len = f2fs_cluster_blocks_are_contiguous(dn); + unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + unsigned int ofs_in_node = dn->ofs_in_node; + pgoff_t fofs = index; + unsigned int c_len; block_t blkaddr; + /* should align fofs and ofs_in_node to cluster_size */ + if (fofs % cluster_size) { + fofs = round_down(fofs, cluster_size); + ofs_in_node = round_down(ofs_in_node, cluster_size); + } + + c_len = f2fs_cluster_blocks_are_contiguous(dn, ofs_in_node); if (!c_len) goto out; - blkaddr = f2fs_data_blkaddr(dn); + blkaddr = data_blkaddr(dn->inode, dn->node_page, ofs_in_node); if (blkaddr == COMPRESS_ADDR) blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + 1); + ofs_in_node + 1); f2fs_update_read_extent_tree_range_compressed(dn->inode, - index, blkaddr, - F2FS_I(dn->inode)->i_cluster_size, - c_len); + fofs, blkaddr, cluster_size, c_len); } out: return 0; @@ -1587,7 +1595,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, .op_flags = wbc_to_write_flags(wbc), .page = page, .encrypted_page = NULL, - .submitted = false, + .submitted = 0, .io_type = io_type, .io_wbc = wbc, }; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 53a6487f9..f5efc37a2 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -582,6 +582,19 @@ truncate_out: return 0; } +static int f2fs_reserve_new_block_retry(struct dnode_of_data *dn) +{ + int i, err = 0; + + for (i = DEFAULT_FAILURE_RETRY_COUNT; i > 0; i--) { + err = f2fs_reserve_new_block(dn); + if (!err) + break; + } + + return err; +} + static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page) { @@ -683,14 +696,8 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; continue; @@ -698,16 +705,8 @@ retry_dn: /* dest is valid block, try to recover from src to dest */ if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { - if (src == NULL_ADDR) { - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 16bf9d5c8..205216c1d 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -192,6 +192,9 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) if (!f2fs_is_atomic_file(inode)) return; + if (clean) + truncate_inode_pages_final(inode->i_mapping); + release_atomic_write_cnt(inode); clear_inode_flag(inode, FI_ATOMIC_COMMITTED); clear_inode_flag(inode, FI_ATOMIC_FILE); @@ -200,7 +203,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) F2FS_I(inode)->atomic_write_task = NULL; if (clean) { - truncate_inode_pages_final(inode->i_mapping); f2fs_i_size_write(inode, fi->original_i_size); fi->original_i_size = 0; } @@ -247,7 +249,7 @@ retry: } else { blkcnt_t count = 1; - err = inc_valid_block_count(sbi, inode, &count); + err = inc_valid_block_count(sbi, inode, &count, true); if (err) { f2fs_put_dnode(&dn); return err; @@ -3312,10 +3314,10 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, struct f2fs_bio_info *io; if (F2FS_IO_ALIGNED(sbi)) - fio->retry = false; + fio->retry = 0; INIT_LIST_HEAD(&fio->list); - fio->in_list = true; + fio->in_list = 1; io = sbi->write_io[fio->type] + fio->temp; spin_lock(&io->io_lock); list_add_tail(&fio->list, &io->io_list); @@ -3396,7 +3398,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, .new_blkaddr = page->index, .page = page, .encrypted_page = NULL, - .in_list = false, + .in_list = 0, }; if (unlikely(page->index >= MAIN_BLKADDR(sbi))) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index f3951e8ad..aa9ad85e0 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -586,23 +586,22 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, unsigned int node_blocks, unsigned int dent_blocks) { - unsigned int segno, left_blocks; + unsigned segno, left_blocks; int i; - /* check current node segment */ + /* check current node sections in the worst case. */ for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) { segno = CURSEG_I(sbi, i)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; - + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (node_blocks > left_blocks) return false; } - /* check current data segment */ + /* check current data section for dentry blocks. */ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (dent_blocks > left_blocks) return false; return true; @@ -651,7 +650,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, if (free_secs > upper_secs) return false; - else if (free_secs <= lower_secs) + if (free_secs <= lower_secs) return true; return !curseg_space; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 0c0d0671f..c529ce5d9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -649,7 +649,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) #ifdef CONFIG_F2FS_FS_ZSTD static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) { - unsigned int level; + int level; int len = 4; if (strlen(str) == len) { @@ -663,9 +663,15 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>"); return -EINVAL; } - if (kstrtouint(str + 1, 10, &level)) + if (kstrtoint(str + 1, 10, &level)) return -EINVAL; + /* f2fs does not support negative compress level now */ + if (level < 0) { + f2fs_info(sbi, "do not support negative compress level: %d", level); + return -ERANGE; + } + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index af191371c..bab63eeaf 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fcntl.c b/fs/fcntl.c index 146c9ab0c..0964e5dbf 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -267,7 +267,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) } #endif -static bool rw_hint_valid(enum rw_hint hint) +static bool rw_hint_valid(u64 hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: @@ -287,19 +287,17 @@ static long fcntl_rw_hint(struct file *file, unsigned int cmd, { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; - enum rw_hint hint; - u64 h; + u64 hint; switch (cmd) { case F_GET_RW_HINT: - h = inode->i_write_hint; - if (copy_to_user(argp, &h, sizeof(*argp))) + hint = inode->i_write_hint; + if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: - if (copy_from_user(&h, argp, sizeof(h))) + if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; - hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; diff --git a/fs/fhandle.c b/fs/fhandle.c index f2bc27d19..a8c25557c 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -37,7 +37,7 @@ static long do_sys_name_to_handle(const struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5e408e7ec..936a24b64 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -399,6 +399,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name goto out_put_forget; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, entry_attr_timeout(outarg), diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index a9681fecb..253b9b78d 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -923,7 +923,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index f81000d96..367e3b276 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -445,8 +445,11 @@ retry: } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 8fdb65e1b..b555efca0 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -647,10 +647,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 01596f2d0..9fe9586a5 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -156,7 +156,10 @@ const struct export_operations nfs_export_ops = { .fh_to_dentry = nfs_fh_to_dentry, .get_parent = nfs_get_parent, .fetch_iversion = nfs_fetch_iversion, - .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| - EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR, + .flags = EXPORT_OP_NOWCC | + EXPORT_OP_NOSUBTREECHK | + EXPORT_OP_CLOSE_BEFORE_UNLINK | + EXPORT_OP_REMOTE_FS | + EXPORT_OP_NOATOMIC_ATTR | + EXPORT_OP_FLUSH_ON_CLOSE, }; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 81bbafab1..4376881be 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2016,7 +2016,7 @@ static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg) for (idx = 0; idx < flseg->mirror_array_cnt; idx++) { mirror = flseg->mirror_array[idx]; mirror_ds = mirror->mirror_ds; - if (!mirror_ds) + if (IS_ERR_OR_NULL(mirror_ds)) continue; ds = mirror->mirror_ds->ds; if (!ds) diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index b59876b01..0282d93c8 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -55,11 +55,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name); * They would be 7 bytes long in the eventual buffer ("user.x\0"), and * 8 bytes long XDR-encoded. * - * Include the trailing eof word as well. + * Include the trailing eof word as well and make the result a multiple + * of 4 bytes. */ static inline u32 nfs42_listxattr_xdrsize(u32 buflen) { - return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; + u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4; + + return (size + 3) & ~3; } #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ec3f0103e..7cc74f745 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10592,29 +10592,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { ssize_t error, error2, error3; + size_t left = size; - error = generic_listxattr(dentry, list, size); + error = generic_listxattr(dentry, list, left); if (error < 0) return error; if (list) { list += error; - size -= error; + left -= error; } - error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left); if (error2 < 0) return error2; if (list) { list += error2; - size -= error2; + left -= error2; } - error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; - return error + error2 + error3; + error += error2 + error3; + if (size && error > size) + return -ERANGE; + return error; } static void nfs4_enable_swap(struct inode *inode) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 620329b7e..0b1c1d2e0 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src, size_t len = strlen(dest); if (len && dest[len - 1] != ',') - if (strlcat(dest, ",", destlen) > destlen) + if (strlcat(dest, ",", destlen) >= destlen) return -1; - if (strlcat(dest, src, destlen) > destlen) + if (strlcat(dest, src, destlen) >= destlen) return -1; return 0; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6a0606668..8e21caae4 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1656,7 +1656,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 697acf5c3..ee9c92319 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -74,70 +74,9 @@ static struct list_lru nfsd_file_lru; static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static struct delayed_work nfsd_filecache_laundrette; -static struct rhashtable nfsd_file_rhash_tbl +static struct rhltable nfsd_file_rhltable ____cacheline_aligned_in_smp; -enum nfsd_file_lookup_type { - NFSD_FILE_KEY_INODE, - NFSD_FILE_KEY_FULL, -}; - -struct nfsd_file_lookup_key { - struct inode *inode; - struct net *net; - const struct cred *cred; - unsigned char need; - bool gc; - enum nfsd_file_lookup_type type; -}; - -/* - * The returned hash value is based solely on the address of an in-code - * inode, a pointer to a slab-allocated object. The entropy in such a - * pointer is concentrated in its middle bits. - */ -static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed) -{ - unsigned long ptr = (unsigned long)inode; - u32 k; - - k = ptr >> L1_CACHE_SHIFT; - k &= 0x00ffffff; - return jhash2(&k, 1, seed); -} - -/** - * nfsd_file_key_hashfn - Compute the hash value of a lookup key - * @data: key on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file_lookup_key *key = data; - - return nfsd_file_inode_hash(key->inode, seed); -} - -/** - * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file - * @data: object on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file *nf = data; - - return nfsd_file_inode_hash(nf->nf_inode, seed); -} - static bool nfsd_match_cred(const struct cred *c1, const struct cred *c2) { @@ -158,53 +97,16 @@ nfsd_match_cred(const struct cred *c1, const struct cred *c2) return true; } -/** - * nfsd_file_obj_cmpfn - Match a cache item against search criteria - * @arg: search criteria - * @ptr: cache item to check - * - * Return values: - * %0 - Item matches search criteria - * %1 - Item does not match search criteria - */ -static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct nfsd_file_lookup_key *key = arg->key; - const struct nfsd_file *nf = ptr; - - switch (key->type) { - case NFSD_FILE_KEY_INODE: - if (nf->nf_inode != key->inode) - return 1; - break; - case NFSD_FILE_KEY_FULL: - if (nf->nf_inode != key->inode) - return 1; - if (nf->nf_may != key->need) - return 1; - if (nf->nf_net != key->net) - return 1; - if (!nfsd_match_cred(nf->nf_cred, key->cred)) - return 1; - if (!!test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) - return 1; - if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) - return 1; - break; - } - return 0; -} - static const struct rhashtable_params nfsd_file_rhash_params = { .key_len = sizeof_field(struct nfsd_file, nf_inode), .key_offset = offsetof(struct nfsd_file, nf_inode), - .head_offset = offsetof(struct nfsd_file, nf_rhash), - .hashfn = nfsd_file_key_hashfn, - .obj_hashfn = nfsd_file_obj_hashfn, - .obj_cmpfn = nfsd_file_obj_cmpfn, - /* Reduce resizing churn on light workloads */ - .min_size = 512, /* buckets */ + .head_offset = offsetof(struct nfsd_file, nf_rlist), + + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, .automatic_shrinking = true, }; @@ -307,27 +209,27 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) } static struct nfsd_file * -nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) +nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need, + bool want_gc) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); - if (nf) { - INIT_LIST_HEAD(&nf->nf_lru); - nf->nf_birthtime = ktime_get(); - nf->nf_file = NULL; - nf->nf_cred = get_current_cred(); - nf->nf_net = key->net; - nf->nf_flags = 0; - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - if (key->gc) - __set_bit(NFSD_FILE_GC, &nf->nf_flags); - nf->nf_inode = key->inode; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = key->need; - nf->nf_mark = NULL; - } + if (unlikely(!nf)) + return NULL; + + INIT_LIST_HEAD(&nf->nf_lru); + nf->nf_birthtime = ktime_get(); + nf->nf_file = NULL; + nf->nf_cred = get_current_cred(); + nf->nf_net = net; + nf->nf_flags = want_gc ? + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) : + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING); + nf->nf_inode = inode; + refcount_set(&nf->nf_ref, 1); + nf->nf_may = need; + nf->nf_mark = NULL; return nf; } @@ -352,8 +254,8 @@ static void nfsd_file_hash_remove(struct nfsd_file *nf) { trace_nfsd_file_unhash(nf); - rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash, - nfsd_file_rhash_params); + rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); } static bool @@ -380,10 +282,8 @@ nfsd_file_free(struct nfsd_file *nf) if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); if (nf->nf_file) { - get_file(nf->nf_file); - filp_close(nf->nf_file, NULL); nfsd_file_check_write_error(nf); - fput(nf->nf_file); + filp_close(nf->nf_file, NULL); } /* @@ -402,13 +302,23 @@ nfsd_file_check_writeback(struct nfsd_file *nf) struct file *file = nf->nf_file; struct address_space *mapping; - if (!file || !(file->f_mode & FMODE_WRITE)) + /* File not open for write? */ + if (!(file->f_mode & FMODE_WRITE)) + return false; + + /* + * Some filesystems (e.g. NFS) flush all dirty data on close. + * On others, there is no need to wait for writeback. + */ + if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE)) return false; + mapping = file->f_mapping; return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); } + static bool nfsd_file_lru_add(struct nfsd_file *nf) { set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); @@ -431,7 +341,7 @@ static bool nfsd_file_lru_remove(struct nfsd_file *nf) struct nfsd_file * nfsd_file_get(struct nfsd_file *nf) { - if (likely(refcount_inc_not_zero(&nf->nf_ref))) + if (nf && refcount_inc_not_zero(&nf->nf_ref)) return nf; return NULL; } @@ -492,49 +402,26 @@ nfsd_file_dispose_list(struct list_head *dispose) } } -static void -nfsd_file_list_remove_disposal(struct list_head *dst, - struct nfsd_fcache_disposal *l) -{ - spin_lock(&l->lock); - list_splice_init(&l->freeme, dst); - spin_unlock(&l->lock); -} - -static void -nfsd_file_list_add_disposal(struct list_head *files, struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd_fcache_disposal *l = nn->fcache_disposal; - - spin_lock(&l->lock); - list_splice_tail_init(files, &l->freeme); - spin_unlock(&l->lock); - queue_work(nfsd_filecache_wq, &l->work); -} - -static void -nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, - struct net *net) -{ - struct nfsd_file *nf, *tmp; - - list_for_each_entry_safe(nf, tmp, src, nf_lru) { - if (nf->nf_net == net) - list_move_tail(&nf->nf_lru, dst); - } -} - +/** + * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list + * @dispose: list of nfsd_files to be disposed + * + * Transfers each file to the "freeme" list for its nfsd_net, to eventually + * be disposed of by the per-net garbage collector. + */ static void nfsd_file_dispose_list_delayed(struct list_head *dispose) { - LIST_HEAD(list); - struct nfsd_file *nf; - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); - nfsd_file_list_add_disposal(&list, nf->nf_net); + struct nfsd_file *nf = list_first_entry(dispose, + struct nfsd_file, nf_lru); + struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; + + spin_lock(&l->lock); + list_move_tail(&nf->nf_lru, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); } } @@ -678,8 +565,8 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out * - * An nfsd_file represents a struct file being held open on behalf of nfsd. An - * open file however can block other activity (such as leases), or cause + * An nfsd_file represents a struct file being held open on behalf of nfsd. + * An open file however can block other activity (such as leases), or cause * undesirable behavior (e.g. spurious silly-renames when reexporting NFS). * * This function is intended to find open nfsd_files when this sort of @@ -692,20 +579,17 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) static void nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - }; + struct rhlist_head *tmp, *list; struct nfsd_file *nf; rcu_read_lock(); - do { - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (!nf) - break; + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (!test_bit(NFSD_FILE_GC, &nf->nf_flags)) + continue; nfsd_file_cond_queue(nf, dispose); - } while (1); + } rcu_read_unlock(); } @@ -758,8 +642,8 @@ nfsd_file_close_inode_sync(struct inode *inode) * nfsd_file_delayed_close - close unused nfsd_files * @work: dummy * - * Walk the LRU list and destroy any entries that have not been used since - * the last scan. + * Scrape the freeme list for this nfsd_net, and then dispose of them + * all. */ static void nfsd_file_delayed_close(struct work_struct *work) @@ -768,7 +652,10 @@ nfsd_file_delayed_close(struct work_struct *work) struct nfsd_fcache_disposal *l = container_of(work, struct nfsd_fcache_disposal, work); - nfsd_file_list_remove_disposal(&head, l); + spin_lock(&l->lock); + list_splice_init(&l->freeme, &head); + spin_unlock(&l->lock); + nfsd_file_dispose_list(&head); } @@ -829,7 +716,7 @@ nfsd_file_cache_init(void) if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; - ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params); + ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); if (ret) return ret; @@ -897,7 +784,7 @@ out_err: nfsd_file_mark_slab = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); goto out; } @@ -906,7 +793,8 @@ out_err: * @net: net-namespace to shut down the cache (may be NULL) * * Walk the nfsd_file cache and close out any that match @net. If @net is NULL, - * then close out everything. Called when an nfsd instance is being shut down. + * then close out everything. Called when an nfsd instance is being shut down, + * and when the exports table is flushed. */ static void __nfsd_file_cache_purge(struct net *net) @@ -915,7 +803,7 @@ __nfsd_file_cache_purge(struct net *net) struct nfsd_file *nf; LIST_HEAD(dispose); - rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter); + rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); @@ -1021,7 +909,7 @@ nfsd_file_cache_shutdown(void) nfsd_file_mark_slab = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); for_each_possible_cpu(i) { per_cpu(nfsd_file_cache_hits, i) = 0; @@ -1032,6 +920,35 @@ nfsd_file_cache_shutdown(void) } } +static struct nfsd_file * +nfsd_file_lookup_locked(const struct net *net, const struct cred *cred, + struct inode *inode, unsigned char need, + bool want_gc) +{ + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; + + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (nf->nf_may != need) + continue; + if (nf->nf_net != net) + continue; + if (!nfsd_match_cred(nf->nf_cred, cred)) + continue; + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc) + continue; + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) + continue; + + if (!nfsd_file_get(nf)) + continue; + return nf; + } + return NULL; +} + /** * nfsd_file_is_cached - are there any cached open files for this inode? * @inode: inode to check @@ -1046,15 +963,20 @@ nfsd_file_cache_shutdown(void) bool nfsd_file_is_cached(struct inode *inode) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - }; + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; bool ret = false; - if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params) != NULL) - ret = true; + rcu_read_lock(); + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) { + ret = true; + break; + } + rcu_read_unlock(); + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } @@ -1064,14 +986,12 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf, bool want_gc) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_FULL, - .need = may_flags & NFSD_FILE_MAY_MASK, - .net = SVC_NET(rqstp), - .gc = want_gc, - }; + unsigned char need = may_flags & NFSD_FILE_MAY_MASK; + struct net *net = SVC_NET(rqstp); + struct nfsd_file *new, *nf; + const struct cred *cred; bool open_retry = true; - struct nfsd_file *nf; + struct inode *inode; __be32 status; int ret; @@ -1079,81 +999,88 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, may_flags|NFSD_MAY_OWNER_OVERRIDE); if (status != nfs_ok) return status; - key.inode = d_inode(fhp->fh_dentry); - key.cred = get_current_cred(); + inode = d_inode(fhp->fh_dentry); + cred = get_current_cred(); retry: rcu_read_lock(); - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (nf) - nf = nfsd_file_get(nf); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); rcu_read_unlock(); if (nf) { + /* + * If the nf is on the LRU then it holds an extra reference + * that must be put if it's removed. It had better not be + * the last one however, since we should hold another. + */ if (nfsd_file_lru_remove(nf)) WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref)); goto wait_for_construction; } - nf = nfsd_file_alloc(&key, may_flags); - if (!nf) { + new = nfsd_file_alloc(net, inode, need, want_gc); + if (!new) { status = nfserr_jukebox; - goto out_status; + goto out; } - ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl, - &key, &nf->nf_rhash, - nfsd_file_rhash_params); + rcu_read_lock(); + spin_lock(&inode->i_lock); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); + if (unlikely(nf)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + nfsd_file_slab_free(&new->nf_rcu); + goto wait_for_construction; + } + nf = new; + ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); + spin_unlock(&inode->i_lock); + rcu_read_unlock(); if (likely(ret == 0)) goto open_file; - nfsd_file_slab_free(&nf->nf_rcu); - nf = NULL; if (ret == -EEXIST) goto retry; - trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, ret); + trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret); status = nfserr_jukebox; - goto out_status; + goto construction_err; wait_for_construction: wait_on_bit(&nf->nf_flags, NFSD_FILE_PENDING, TASK_UNINTERRUPTIBLE); /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); + trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf); if (!open_retry) { status = nfserr_jukebox; - goto out; + goto construction_err; } open_retry = false; - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); goto retry; } - this_cpu_inc(nfsd_file_cache_hits); status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); + if (status != nfs_ok) { + nfsd_file_put(nf); + nf = NULL; + } + out: if (status == nfs_ok) { this_cpu_inc(nfsd_file_acquisitions); nfsd_file_check_write_error(nf); *pnf = nf; - } else { - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); - nf = NULL; } - -out_status: - put_cred(key.cred); - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + put_cred(cred); + trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); - nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); + nf->nf_mark = nfsd_file_mark_find_or_create(nf, inode); if (nf->nf_mark) { if (file) { get_file(file); @@ -1171,13 +1098,16 @@ open_file: * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status == nfs_ok && key.inode->i_nlink == 0) - status = nfserr_jukebox; - if (status != nfs_ok) + if (status != nfs_ok || inode->i_nlink == 0) nfsd_file_unhash(nf); - clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); - smp_mb__after_atomic(); - wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); + clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); + if (status == nfs_ok) + goto out; + +construction_err: + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; goto out; } @@ -1193,8 +1123,11 @@ open_file: * seconds after the final nfsd_file_put() in case the caller * wants to re-use it. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1214,8 +1147,11 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, * but not garbage-collected. The object is unhashed after the * final nfsd_file_put(). * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1236,8 +1172,11 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * and @file is non-NULL, use it to instantiate a new nfsd_file instead of * opening a new one. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1268,7 +1207,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) lru = list_lru_count(&nfsd_file_lru); rcu_read_lock(); - ht = &nfsd_file_rhash_tbl; + ht = &nfsd_file_rhltable.ht; count = atomic_read(&ht->nelems); tbl = rht_dereference_rcu(ht->tbl, ht); buckets = tbl->size; @@ -1284,7 +1223,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) evictions += per_cpu(nfsd_file_evictions, i); } - seq_printf(m, "total entries: %u\n", count); + seq_printf(m, "total inodes: %u\n", count); seq_printf(m, "hash buckets: %u\n", buckets); seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 41516a426..e54165a32 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -29,9 +29,8 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct rhash_head nf_rhash; - struct list_head nf_lru; - struct rcu_head nf_rcu; + struct rhlist_head nf_rlist; + void *nf_inode; struct file *nf_file; const struct cred *nf_cred; struct net *nf_net; @@ -40,10 +39,12 @@ struct nfsd_file { #define NFSD_FILE_REFERENCED (2) #define NFSD_FILE_GC (3) unsigned long nf_flags; - struct inode *nf_inode; /* don't deref */ refcount_t nf_ref; unsigned char nf_may; + struct nfsd_file_mark *nf_mark; + struct list_head nf_lru; + struct rcu_head nf_rcu; ktime_t nf_birthtime; }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index b9d694ec2..8d1595900 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -602,9 +602,7 @@ put_nfs4_file(struct nfs4_file *fi) static struct nfsd_file * __nfs4_get_fd(struct nfs4_file *f, int oflag) { - if (f->fi_fds[oflag]) - return nfsd_file_get(f->fi_fds[oflag]); - return NULL; + return nfsd_file_get(f->fi_fds[oflag]); } static struct nfsd_file * @@ -2891,12 +2889,9 @@ static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - spin_lock(&nn->client_lock); clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); - put_client_renew_locked(clp); - spin_unlock(&nn->client_lock); + drop_client(clp); } static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { @@ -6233,7 +6228,7 @@ deleg_reaper(struct nfsd_net *nn) list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ - atomic_inc(&clp->cl_rpc_users); + kref_get(&clp->cl_nfsdfs.cl_ref); set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); clp->cl_ra_time = ktime_get_boottime_seconds(); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 597f14a80..4ed9fef14 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2541,6 +2541,20 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, return p; } +static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr, + struct timespec64 *tv) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 3); + if (!p) + return nfserr_resource; + + p = xdr_encode_hyper(p, (s64)tv->tv_sec); + *p = cpu_to_be32(tv->tv_nsec); + return nfs_ok; +} + /* * ctime (in NFSv4, time_metadata) is not writeable, and the client * doesn't really care what resolution could theoretically be stored by @@ -3346,11 +3360,14 @@ out_acl: p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); - *p++ = cpu_to_be32(stat.atime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.atime); + if (status) + goto out; + } + if (bmval1 & FATTR4_WORD1_TIME_CREATE) { + status = nfsd4_encode_nfstime4(xdr, &stat.btime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_DELTA) { p = xdr_reserve_space(xdr, 12); @@ -3359,25 +3376,14 @@ out_acl: p = encode_time_delta(p, d_inode(dentry)); } if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); - *p++ = cpu_to_be32(stat.ctime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.ctime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); - *p++ = cpu_to_be32(stat.mtime.tv_nsec); - } - if (bmval1 & FATTR4_WORD1_TIME_CREATE) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.btime.tv_sec); - *p++ = cpu_to_be32(stat.btime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.mtime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { u64 ino = stat.ino; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 4183819ea..84f26f281 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -842,7 +842,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __array(unsigned char, addr, sizeof(struct sockaddr_in6)) __field(unsigned long, flavor) __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) - __string_len(name, name, clp->cl_name.len) + __string_len(name, clp->cl_name.data, clp->cl_name.len) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 40ce92a33..146640f06 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -781,6 +781,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index a35f2795b..8f802f7b0 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index f62587232..8eb4288d4 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; @@ -424,6 +424,18 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) bool was_empty = false; bool wake_next_writer = false; + /* + * Reject writing to watch queue pipes before the point where we lock + * the pipe. + * Otherwise, lockdep would be unhappy if the caller already has another + * pipe locked. + * If we had to support locking a normal pipe and a notification pipe at + * the same time, we could set up lockdep annotations for that, but + * since we don't actually need that, it's simpler to just bail here. + */ + if (pipe_has_watch_queue(pipe)) + return -EXDEV; + /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; @@ -436,11 +448,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } - if (pipe_has_watch_queue(pipe)) { - ret = -EXDEV; - goto out; - } - /* * If it wasn't empty we try to merge new data into * the last buffer. diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index ffbadb8b3..ea3f10437 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -182,25 +182,21 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = d_inode(dentry)->i_private; struct pstore_record *record = p->record; - int rc = 0; if (!record->psi->erase) return -EPERM; /* Make sure we can't race while removing this file. */ - mutex_lock(&records_list_lock); - if (!list_empty(&p->list)) - list_del_init(&p->list); - else - rc = -ENOENT; - p->dentry = NULL; - mutex_unlock(&records_list_lock); - if (rc) - return rc; - - mutex_lock(&record->psi->read_mutex); - record->psi->erase(record); - mutex_unlock(&record->psi->read_mutex); + scoped_guard(mutex, &records_list_lock) { + if (!list_empty(&p->list)) + list_del_init(&p->list); + else + return -ENOENT; + p->dentry = NULL; + } + + scoped_guard(mutex, &record->psi->read_mutex) + record->psi->erase(record); return simple_unlink(dir, dentry); } @@ -292,19 +288,16 @@ static struct dentry *psinfo_lock_root(void) { struct dentry *root; - mutex_lock(&pstore_sb_lock); + guard(mutex)(&pstore_sb_lock); /* * Having no backend is fine -- no records appear. * Not being mounted is fine -- nothing to do. */ - if (!psinfo || !pstore_sb) { - mutex_unlock(&pstore_sb_lock); + if (!psinfo || !pstore_sb) return NULL; - } root = pstore_sb->s_root; inode_lock(d_inode(root)); - mutex_unlock(&pstore_sb_lock); return root; } @@ -313,29 +306,25 @@ int pstore_put_backend_records(struct pstore_info *psi) { struct pstore_private *pos, *tmp; struct dentry *root; - int rc = 0; root = psinfo_lock_root(); if (!root) return 0; - mutex_lock(&records_list_lock); - list_for_each_entry_safe(pos, tmp, &records_list, list) { - if (pos->record->psi == psi) { - list_del_init(&pos->list); - rc = simple_unlink(d_inode(root), pos->dentry); - if (WARN_ON(rc)) - break; - d_drop(pos->dentry); - dput(pos->dentry); - pos->dentry = NULL; + scoped_guard(mutex, &records_list_lock) { + list_for_each_entry_safe(pos, tmp, &records_list, list) { + if (pos->record->psi == psi) { + list_del_init(&pos->list); + d_invalidate(pos->dentry); + simple_unlink(d_inode(root), pos->dentry); + pos->dentry = NULL; + } } } - mutex_unlock(&records_list_lock); inode_unlock(d_inode(root)); - return rc; + return 0; } /* @@ -355,20 +344,20 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) if (WARN_ON(!inode_is_locked(d_inode(root)))) return -EINVAL; - rc = -EEXIST; + guard(mutex)(&records_list_lock); + /* Skip records that are already present in the filesystem. */ - mutex_lock(&records_list_lock); list_for_each_entry(pos, &records_list, list) { if (pos->record->type == record->type && pos->record->id == record->id && pos->record->psi == record->psi) - goto fail; + return -EEXIST; } rc = -ENOMEM; inode = pstore_get_inode(root->d_sb); if (!inode) - goto fail; + return -ENOMEM; inode->i_mode = S_IFREG | 0444; inode->i_fop = &pstore_file_operations; scnprintf(name, sizeof(name), "%s-%s-%llu%s", @@ -395,7 +384,6 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) d_add(dentry, inode); list_add(&private->list, &records_list); - mutex_unlock(&records_list_lock); return 0; @@ -403,8 +391,6 @@ fail_private: free_pstore_private(private); fail_inode: iput(inode); -fail: - mutex_unlock(&records_list_lock); return rc; } @@ -450,9 +436,8 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) if (!sb->s_root) return -ENOMEM; - mutex_lock(&pstore_sb_lock); - pstore_sb = sb; - mutex_unlock(&pstore_sb_lock); + scoped_guard(mutex, &pstore_sb_lock) + pstore_sb = sb; pstore_get_records(0); @@ -467,17 +452,14 @@ static struct dentry *pstore_mount(struct file_system_type *fs_type, static void pstore_kill_sb(struct super_block *sb) { - mutex_lock(&pstore_sb_lock); + guard(mutex)(&pstore_sb_lock); WARN_ON(pstore_sb && pstore_sb != sb); kill_litter_super(sb); pstore_sb = NULL; - mutex_lock(&records_list_lock); + guard(mutex)(&records_list_lock); INIT_LIST_HEAD(&records_list); - mutex_unlock(&records_list_lock); - - mutex_unlock(&pstore_sb_lock); } static struct file_system_type pstore_fs_type = { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b0cf3869d..b67557647 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -399,15 +399,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ -static inline int mark_all_dquot_dirty(struct dquot * const *dquot) +static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; + struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquot[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) /* Even in case of error we have to continue */ - ret = mark_dquot_dirty(dquot[cnt]); + ret = mark_dquot_dirty(dquot); if (!err) err = ret; } @@ -1004,14 +1006,15 @@ out: } EXPORT_SYMBOL(dqget); -static inline struct dquot **i_dquot(struct inode *inode) +static inline struct dquot __rcu **i_dquot(struct inode *inode) { - return inode->i_sb->s_op->get_dquots(inode); + /* Force __rcu for now until filesystems are fixed */ + return (struct dquot __rcu **)inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1084,59 +1087,7 @@ out: return err; } -/* - * Remove references to dquots from inode and add dquot to list for freeing - * if we have the last reference to dquot - */ -static void remove_inode_dquot_ref(struct inode *inode, int type, - struct list_head *tofree_head) -{ - struct dquot **dquots = i_dquot(inode); - struct dquot *dquot = dquots[type]; - - if (!dquot) - return; - - dquots[type] = NULL; - if (list_empty(&dquot->dq_free)) { - /* - * The inode still has reference to dquot so it can't be in the - * free list - */ - spin_lock(&dq_list_lock); - list_add(&dquot->dq_free, tofree_head); - spin_unlock(&dq_list_lock); - } else { - /* - * Dquot is already in a list to put so we won't drop the last - * reference here. - */ - dqput(dquot); - } -} - -/* - * Free list of dquots - * Dquots are removed from inodes and no new references can be got so we are - * the only ones holding reference - */ -static void put_dquot_list(struct list_head *tofree_head) -{ - struct list_head *act_head; - struct dquot *dquot; - - act_head = tofree_head->next; - while (act_head != tofree_head) { - dquot = list_entry(act_head, struct dquot, dq_free); - act_head = act_head->next; - /* Remove dquot from the list so we won't have problems... */ - list_del_init(&dquot->dq_free); - dqput(dquot); - } -} - -static void remove_dquot_ref(struct super_block *sb, int type, - struct list_head *tofree_head) +static void remove_dquot_ref(struct super_block *sb, int type) { struct inode *inode; #ifdef CONFIG_QUOTA_DEBUG @@ -1153,11 +1104,18 @@ static void remove_dquot_ref(struct super_block *sb, int type, */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { + struct dquot __rcu **dquots = i_dquot(inode); + struct dquot *dquot = srcu_dereference_check( + dquots[type], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif - remove_inode_dquot_ref(inode, type, tofree_head); + rcu_assign_pointer(dquots[type], NULL); + if (dquot) + dqput(dquot); } spin_unlock(&dq_data_lock); } @@ -1174,13 +1132,8 @@ static void remove_dquot_ref(struct super_block *sb, int type, /* Gather all references from inodes and drop them */ static void drop_dquot_ref(struct super_block *sb, int type) { - LIST_HEAD(tofree_head); - - if (sb->dq_op) { - remove_dquot_ref(sb, type, &tofree_head); - synchronize_srcu(&dquot_srcu); - put_dquot_list(&tofree_head); - } + if (sb->dq_op) + remove_dquot_ref(sb, type); } static inline @@ -1513,7 +1466,8 @@ static int inode_quota_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS] = {}; + struct dquot __rcu **dquots; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1588,7 +1542,7 @@ static int __dquot_initialize(struct inode *inode, int type) if (!got[cnt]) continue; if (!dquots[cnt]) { - dquots[cnt] = got[cnt]; + rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1596,12 +1550,16 @@ static int __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { + struct dquot *dquot = srcu_dereference_check( + dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } @@ -1623,7 +1581,7 @@ EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { - struct dquot **dquots; + struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) @@ -1648,13 +1606,14 @@ EXPORT_SYMBOL(dquot_initialize_needed); static void __dquot_drop(struct inode *inode) { int cnt; - struct dquot **dquots = i_dquot(inode); + struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = dquots[cnt]; - dquots[cnt] = NULL; + put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1662,7 +1621,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1735,7 +1694,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { @@ -1755,27 +1715,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; if (reserve) { - ret = dquot_add_space(dquots[cnt], 0, number, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { - ret = dquot_add_space(dquots[cnt], number, 0, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); if (reserve) - dquot_free_reserved_space(dquots[cnt], - number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; @@ -1805,7 +1764,8 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) return 0; @@ -1816,17 +1776,19 @@ int dquot_alloc_inode(struct inode *inode) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; /* Back out changes we already did */ - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } @@ -1847,7 +1809,8 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1863,9 +1826,8 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; @@ -1889,7 +1851,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1905,9 +1868,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; @@ -1933,7 +1895,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { @@ -1954,17 +1917,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_bdq_free(dquots[cnt], number); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); + prepare_warning(&warn[cnt], dquot, wtype); if (reserve) - dquot_free_reserved_space(dquots[cnt], number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; @@ -1988,7 +1952,8 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; int index; if (!inode_quota_active(inode)) @@ -1999,16 +1964,16 @@ void dquot_free_inode(struct inode *inode) spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; - warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_idq_free(dquots[cnt], 1); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + prepare_warning(&warn[cnt], dquot, wtype); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); @@ -2034,8 +1999,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; + struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; - int cnt, ret = 0; + int cnt, index, ret = 0; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; @@ -2066,6 +2032,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); + dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. @@ -2080,7 +2047,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = i_dquot(inode)[cnt]; + transfer_from[cnt] = srcu_dereference_check(dquots[cnt], + &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) @@ -2119,13 +2087,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - i_dquot(inode)[cnt] = transfer_to[cnt]; + rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(transfer_from); - mark_all_dquot_dirty(transfer_to); + /* + * These arrays are local and we hold dquot references so we don't need + * the srcu protection but still take dquot_srcu to avoid warning in + * mark_all_dquot_dirty(). + */ + index = srcu_read_lock(&dquot_srcu); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); + srcu_read_unlock(&dquot_srcu, index); + flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); diff --git a/fs/select.c b/fs/select.c index 0ee55af1a..d4d881d43 100644 --- a/fs/select.c +++ b/fs/select.c @@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index fd082151c..f4ad343b0 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -218,7 +218,8 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, .tcon = tcon, .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), - .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES, + .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES | + FILE_READ_EA, .disposition = FILE_OPEN, .fid = pfid, }; @@ -369,6 +370,7 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); + int rc; spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->on_list) { @@ -382,9 +384,10 @@ smb2_close_cached_fid(struct kref *ref) cfid->dentry = NULL; if (cfid->is_open) { - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc != -EBUSY && rc != -EAGAIN) + atomic_dec(&cfid->tcon->num_remote_opens); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 5df8d9323..a2afdf9c5 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -186,6 +186,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { @@ -566,6 +568,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } #endif /* CONFIG_CIFS_STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); @@ -644,6 +648,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->tree_name); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 7286a56ae..0a79771c8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -154,6 +154,7 @@ struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *serverclose_wq; __u32 cifs_lock_secret; /* @@ -1866,6 +1867,13 @@ init_cifs(void) goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) goto out_destroy_deferredclose_wq; @@ -1940,6 +1948,8 @@ out_destroy_decrypt_wq: destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: destroy_workqueue(cifsiod_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_clean_proc: cifs_proc_clean(); return rc; @@ -1969,6 +1979,7 @@ exit_cifs(void) destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); + destroy_workqueue(serverclose_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 58bb54994..e5a72f9c7 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -389,10 +389,10 @@ struct smb_version_operations { /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ - void (*close)(const unsigned int, struct cifs_tcon *, + int (*close)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* close a file, returning file attributes and timestamps */ - void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, + int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *pfile_info); /* send a flush request to the server */ int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); @@ -1359,6 +1359,7 @@ struct cifsFileInfo { bool invalidHandle:1; /* file closed via session abend */ bool swapfile:1; bool oplock_break_cancelled:1; + bool offload:1; /* offload final part of _put to a wq */ unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; @@ -1367,6 +1368,7 @@ struct cifsFileInfo { struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ + struct work_struct serverclose; /* work for serverclose */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ char *symlink_target; @@ -2005,6 +2007,7 @@ extern struct workqueue_struct *decrypt_wq; extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern struct workqueue_struct *deferredclose_wq; +extern struct workqueue_struct *serverclose_wq; extern __u32 cifs_lock_secret; extern mempool_t *cifs_mid_poolp; @@ -2175,4 +2178,14 @@ static inline struct scatterlist *cifs_sg_set_buf(struct scatterlist *sg, return sg; } +static inline bool cifs_ses_exiting(struct cifs_ses *ses) +{ + bool ret; + + spin_lock(&ses->ses_lock); + ret = ses->ses_status == SES_EXITING; + spin_unlock(&ses->ses_lock); + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 49fdc6dfd..8c2a78420 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -216,6 +216,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { spin_lock(&ses->chans[i].server->srv_lock); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index e382b794a..863c7bc3d 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -180,6 +180,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; *oplock = 0; if (tcon->ses->server->oplocks) @@ -191,6 +192,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned return PTR_ERR(full_path); } + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -267,6 +272,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned desired_access |= GENERIC_READ; /* is this too little? */ if (OPEN_FMODE(oflags) & FMODE_WRITE) desired_access |= GENERIC_WRITE; + if (rdwr_for_fscache == 1) + desired_access |= GENERIC_READ; disposition = FILE_OVERWRITE_IF; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -295,6 +302,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -308,8 +316,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access &= ~GENERIC_READ; + rdwr_for_fscache = 2; + goto retry_open; + } goto out; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 0f3405e0f..d23dfc83d 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -77,12 +77,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } -static inline int cifs_convert_flags(unsigned int flags) +static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache) { if ((flags & O_ACCMODE) == O_RDONLY) return GENERIC_READ; else if ((flags & O_ACCMODE) == O_WRONLY) - return GENERIC_WRITE; + return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE; else if ((flags & O_ACCMODE) == O_RDWR) { /* GENERIC_ALL is too much permission to request can cause unnecessary access denied on create */ @@ -219,11 +219,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ int create_options = CREATE_NOT_DIR; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; if (!server->ops->open) return -ENOSYS; - desired_access = cifs_convert_flags(f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache); /********************************************************************* * open flag mapping table: @@ -260,6 +265,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ if (f_flags & O_DIRECT) create_options |= CREATE_NO_BUFFER; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -271,8 +277,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ }; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) + if (rc) { + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } return rc; + } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -316,6 +330,7 @@ cifs_down_write(struct rw_semaphore *sem) } static void cifsFileInfo_put_work(struct work_struct *work); +void serverclose_work(struct work_struct *work); struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock, @@ -362,6 +377,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); + INIT_WORK(&cfile->serverclose, serverclose_work); INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -453,6 +469,40 @@ static void cifsFileInfo_put_work(struct work_struct *work) cifsFileInfo_put_final(cifs_file); } +void serverclose_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, serverclose); + + struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); + + struct TCP_Server_Info *server = tcon->ses->server; + int rc = 0; + int retries = 0; + int MAX_RETRIES = 4; + + do { + if (server->ops->close_getattr) + rc = server->ops->close_getattr(0, tcon, cifs_file); + else if (server->ops->close) + rc = server->ops->close(0, tcon, &cifs_file->fid); + + if (rc == -EBUSY || rc == -EAGAIN) { + retries++; + msleep(250); + } + } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES) + ); + + if (retries == MAX_RETRIES) + pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES); + + if (cifs_file->offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -493,10 +543,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; + bool serverclose_offloaded = false; spin_lock(&tcon->open_file_lock); spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); + + cifs_file->offload = offload; if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); spin_unlock(&cifsi->open_file_lock); @@ -538,13 +591,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; + int rc = 0; xid = get_xid(); if (server->ops->close_getattr) - server->ops->close_getattr(xid, tcon, cifs_file); + rc = server->ops->close_getattr(xid, tcon, cifs_file); else if (server->ops->close) - server->ops->close(xid, tcon, &cifs_file->fid); + rc = server->ops->close(xid, tcon, &cifs_file->fid); _free_xid(xid); + + if (rc == -EBUSY || rc == -EAGAIN) { + // Server close failed, hence offloading it as an async op + queue_work(serverclose_wq, &cifs_file->serverclose); + serverclose_offloaded = true; + } } if (oplock_break_cancelled) @@ -552,10 +612,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, cifs_del_pending_open(&open); - if (offload) - queue_work(fileinfo_put_wq, &cifs_file->put); - else - cifsFileInfo_put_final(cifs_file); + // if serverclose has been offloaded to wq (on failure), it will + // handle offloading put as well. If serverclose not offloaded, + // we need to handle offloading put here. + if (!serverclose_offloaded) { + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); + } } int cifs_open(struct inode *inode, struct file *file) @@ -705,11 +770,11 @@ int cifs_open(struct inode *inode, struct file *file) use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), file->f_mode & FMODE_WRITE); - if (file->f_flags & O_DIRECT && - (!((file->f_flags & O_ACCMODE) != O_RDONLY) || - file->f_flags & O_APPEND)) - cifs_invalidate_cache(file_inode(file), - FSCACHE_INVAL_DIO_WRITE); + if (!(file->f_flags & O_DIRECT)) + goto out; + if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY) + goto out; + cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE); out: free_dentry_path(page); @@ -774,6 +839,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -837,7 +903,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - desired_access = cifs_convert_flags(cfile->f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) @@ -849,6 +919,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -874,6 +945,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) /* indicate that we need to relock the file */ oparms.reconnect = true; } + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(cfile->f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } if (rc) { mutex_unlock(&cfile->fh_mutex); @@ -882,6 +958,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index f64bad513..6df4ab2a6 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -12,6 +12,16 @@ #include "cifs_fs_sb.h" #include "cifsproto.h" +/* + * Key for fscache inode. [!] Contents must match comparisons in cifs_find_inode(). + */ +struct cifs_fscache_inode_key { + + __le64 uniqueid; /* server inode number */ + __le64 createtime; /* creation time on server */ + u8 type; /* S_IFMT file type */ +} __packed; + static void cifs_fscache_fill_volume_coherency( struct cifs_tcon *tcon, struct cifs_fscache_volume_coherency_data *cd) @@ -97,15 +107,19 @@ void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) void cifs_fscache_get_inode_cookie(struct inode *inode) { struct cifs_fscache_inode_coherency_data cd; + struct cifs_fscache_inode_key key; struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + key.uniqueid = cpu_to_le64(cifsi->uniqueid); + key.createtime = cpu_to_le64(cifsi->createtime); + key.type = (inode->i_mode & S_IFMT) >> 12; cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd); cifsi->netfs.cache = fscache_acquire_cookie(tcon->fscache, 0, - &cifsi->uniqueid, sizeof(cifsi->uniqueid), + &key, sizeof(key), &cd, sizeof(cd), i_size_read(&cifsi->netfs.inode)); if (cifsi->netfs.cache) diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index 67b601041..c691b98b4 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -108,6 +108,11 @@ static inline void cifs_readpage_to_fscache(struct inode *inode, __cifs_readpage_to_fscache(inode, page); } +static inline bool cifs_fscache_enabled(struct inode *inode) +{ + return fscache_cookie_enabled(cifs_inode_cookie(inode)); +} + #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -123,6 +128,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {} static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {} static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} +static inline bool cifs_fscache_enabled(struct inode *inode) { return false; } static inline int cifs_fscache_query_occupancy(struct inode *inode, pgoff_t first, unsigned int nr_pages, diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 5343898ba..634f28f0d 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1274,6 +1274,8 @@ cifs_find_inode(struct inode *inode, void *opaque) { struct cifs_fattr *fattr = opaque; + /* [!] The compared values must be the same in struct cifs_fscache_inode_key. */ + /* don't match inode with different uniqueid */ if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid) return 0; diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 41290c12d..3826f7176 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -476,6 +476,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 7d1b3fc01..d4045925f 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -750,11 +750,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } -static void +static int cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - CIFSSMBClose(xid, tcon, fid->netfid); + return CIFSSMBClose(xid, tcon, fid->netfid); } static int diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 15fa022e7..8c149cb53 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( @@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 34d126200..229108165 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1392,14 +1392,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) memcpy(cfile->fid.create_guid, fid->create_guid, 16); } -static void +static int smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); + return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } -static void +static int smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { @@ -1410,7 +1410,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, &file_inf); if (rc) - return; + return rc; inode = d_inode(cfile->dentry); @@ -1436,6 +1436,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* End of file and Attributes should not have to be updated on close */ spin_unlock(&inode->i_lock); + return rc; } static int @@ -2436,6 +2437,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 4c1231496..cc425a616 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3452,9 +3452,9 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, memcpy(&pbuf->network_open_info, &rsp->network_open_info, sizeof(pbuf->network_open_info)); + atomic_dec(&tcon->num_remote_opens); } - atomic_dec(&tcon->num_remote_opens); close_exit: SMB2_close_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 0ebf91ffa..4464a6222 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -166,7 +166,8 @@ struct ksmbd_share_config_response { __u16 force_uid; __u16 force_gid; __s8 share_name[KSMBD_REQ_MAX_SHARE_NAME]; - __u32 reserved[112]; /* Reserved room */ + __u32 reserved[111]; /* Reserved room */ + __u32 payload_sz; __u32 veto_list_sz; __s8 ____payload[]; }; diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a41225..a2f0a2edc 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -158,7 +158,12 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, share->name = kstrdup(name, GFP_KERNEL); if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - share->path = kstrdup(ksmbd_share_config_path(resp), + int path_len = PATH_MAX; + + if (resp->payload_sz) + path_len = resp->payload_sz - resp->veto_list_sz; + + share->path = kstrndup(ksmbd_share_config_path(resp), path_len, GFP_KERNEL); if (share->path) share->path_sz = strlen(share->path); diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index 27a9dce3e..8600f32c9 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; } @@ -275,11 +280,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || - (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && - conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 66d25d0e3..c02b1772c 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -5579,8 +5579,9 @@ static int smb2_rename(struct ksmbd_work *work, if (!file_info->ReplaceIfExists) flags = RENAME_NOREPLACE; - smb_break_all_levII_oplock(work, fp, 0); rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); + if (!rc) + smb_break_all_levII_oplock(work, fp, 0); out: kfree(new_name); return rc; @@ -5757,15 +5758,21 @@ static int set_file_allocation_info(struct ksmbd_work *work, loff_t alloc_blks; struct inode *inode; + struct kstat stat; int rc; if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; + rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; + alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); - if (alloc_blks > inode->i_blocks) { + if (alloc_blks > stat.blocks) { smb_break_all_levII_oplock(work, fp, 1); rc = vfs_fallocate(fp->filp, FALLOC_FL_KEEP_SIZE, 0, alloc_blks * 512); @@ -5773,7 +5780,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, pr_err("vfs_fallocate is failed : %d\n", rc); return rc; } - } else if (alloc_blks < inode->i_blocks) { + } else if (alloc_blks < stat.blocks) { loff_t size; /* diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index f29bb03f0..8752ac82c 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -65,6 +65,7 @@ struct ipc_msg_table_entry { struct hlist_node ipc_table_hlist; void *response; + unsigned int msg_sz; }; static struct delayed_work ipc_timer_work; @@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz) } memcpy(entry->response, payload, sz); + entry->msg_sz = sz; wake_up_interruptible(&entry->wait); ret = 0; break; @@ -453,6 +455,34 @@ out: return ret; } +static int ipc_validate_msg(struct ipc_msg_table_entry *entry) +{ + unsigned int msg_sz = entry->msg_sz; + + if (entry->type == KSMBD_EVENT_RPC_REQUEST) { + struct ksmbd_rpc_command *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz; + } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) { + struct ksmbd_spnego_authen_response *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_spnego_authen_response) + + resp->session_key_len + resp->spnego_blob_len; + } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) { + struct ksmbd_share_config_response *resp = entry->response; + + if (resp->payload_sz) { + if (resp->payload_sz < resp->veto_list_sz) + return -EINVAL; + + msg_sz = sizeof(struct ksmbd_share_config_response) + + resp->payload_sz; + } + } + + return entry->msg_sz != msg_sz ? -EINVAL : 0; +} + static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle) { struct ipc_msg_table_entry entry; @@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle ret = wait_event_interruptible_timeout(entry.wait, entry.response != NULL, IPC_WAIT_TIMEOUT); + if (entry.response) { + ret = ipc_validate_msg(&entry); + if (ret) { + kvfree(entry.response); + entry.response = NULL; + } + } out: down_write(&ipc_msg_table_lock); hash_del(&entry.ipc_table_hlist); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 10c1779af..f7b1f9ece 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -261,9 +261,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -462,9 +459,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -474,10 +468,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -568,6 +560,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index d2f6df69f..74952e58c 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } @@ -224,6 +224,7 @@ fail_free: ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; |