diff options
Diffstat (limited to 'fs')
59 files changed, 674 insertions, 621 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index bf7e3f23bba7..670700cb1110 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1761,6 +1761,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) btrfs_err(info, "bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", cache->key.objectid); + btrfs_put_block_group(cache); ret = -EINVAL; goto error; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 19d669d12ca1..fe2b8765d9e6 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -734,8 +734,6 @@ struct btrfs_fs_info { struct btrfs_workqueue *fixup_workers; struct btrfs_workqueue *delayed_workers; - /* the extent workers do delayed refs on the extent allocation tree */ - struct btrfs_workqueue *extent_workers; struct task_struct *transaction_kthread; struct task_struct *cleaner_kthread; u32 thread_pool_size; @@ -2489,8 +2487,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, int nitems, bool use_global_rsv); void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); -void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, - bool qgroup_free); +void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes); int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes); u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index d949d7d2abed..db9f2c58eb4a 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -381,7 +381,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) out_qgroup: btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve); out_fail: - btrfs_inode_rsv_release(inode, true); if (delalloc_lock) mutex_unlock(&inode->delalloc_mutex); return ret; @@ -418,7 +417,6 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, * btrfs_delalloc_release_extents - release our outstanding_extents * @inode: the inode to balance the reservation for. * @num_bytes: the number of bytes we originally reserved with - * @qgroup_free: do we need to free qgroup meta reservation or convert them. * * When we reserve space we increase outstanding_extents for the extents we may * add. Once we've set the range as delalloc or created our ordered extents we @@ -426,8 +424,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, * temporarily tracked outstanding_extents. This _must_ be used in conjunction * with btrfs_delalloc_reserve_metadata. */ -void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, - bool qgroup_free) +void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned num_extents; @@ -441,7 +438,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, if (btrfs_is_testing(fs_info)) return; - btrfs_inode_rsv_release(inode, qgroup_free); + btrfs_inode_rsv_release(inode, true); } /** diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 044981cf6df9..402b61bf345c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2008,7 +2008,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) btrfs_destroy_workqueue(fs_info->readahead_workers); btrfs_destroy_workqueue(fs_info->flush_workers); btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); - btrfs_destroy_workqueue(fs_info->extent_workers); /* * Now that all other work queues are destroyed, we can safely destroy * the queues used for metadata I/O, since tasks from those other work @@ -2214,10 +2213,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, max_active, 2); fs_info->qgroup_rescan_workers = btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0); - fs_info->extent_workers = - btrfs_alloc_workqueue(fs_info, "extent-refs", flags, - min_t(u64, fs_devices->num_devices, - max_active), 8); if (!(fs_info->workers && fs_info->delalloc_workers && fs_info->submit_workers && fs_info->flush_workers && @@ -2228,7 +2223,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, fs_info->endio_freespace_worker && fs_info->rmw_workers && fs_info->caching_workers && fs_info->readahead_workers && fs_info->fixup_workers && fs_info->delayed_workers && - fs_info->extent_workers && fs_info->qgroup_rescan_workers)) { return -ENOMEM; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 8fe4eb7e5045..435a502a3226 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1591,7 +1591,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; - struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; u64 lockstart; @@ -1611,6 +1610,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, return -ENOMEM; while (iov_iter_count(i) > 0) { + struct extent_state *cached_state = NULL; size_t offset = offset_in_page(pos); size_t sector_offset; size_t write_bytes = min(iov_iter_count(i), @@ -1692,7 +1692,7 @@ again: force_page_uptodate); if (ret) { btrfs_delalloc_release_extents(BTRFS_I(inode), - reserve_bytes, true); + reserve_bytes); break; } @@ -1704,7 +1704,7 @@ again: if (extents_locked == -EAGAIN) goto again; btrfs_delalloc_release_extents(BTRFS_I(inode), - reserve_bytes, true); + reserve_bytes); ret = extents_locked; break; } @@ -1758,11 +1758,21 @@ again: if (copied > 0) ret = btrfs_dirty_pages(inode, pages, dirty_pages, pos, copied, &cached_state); + + /* + * If we have not locked the extent range, because the range's + * start offset is >= i_size, we might still have a non-NULL + * cached extent state, acquired while marking the extent range + * as delalloc through btrfs_dirty_pages(). Therefore free any + * possible cached extent state to avoid a memory leak. + */ if (extents_locked) unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); - btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes, - true); + else + free_extent_state(cached_state); + + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); if (ret) { btrfs_drop_pages(pages, num_pages); break; @@ -2057,25 +2067,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; int ret = 0, err; - u64 len; - /* - * If the inode needs a full sync, make sure we use a full range to - * avoid log tree corruption, due to hole detection racing with ordered - * extent completion for adjacent ranges, and assertion failures during - * hole detection. - */ - if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags)) { - start = 0; - end = LLONG_MAX; - } - - /* - * The range length can be represented by u64, we have to do the typecasts - * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() - */ - len = (u64)end - (u64)start + 1; trace_btrfs_sync_file(file, datasync); btrfs_init_log_ctx(&ctx, inode); @@ -2102,6 +2094,19 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges, and assertion failures during + * hole detection. Do this while holding the inode lock, to avoid races + * with other tasks. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * Before we acquired the inode's lock, someone may have dirtied more * pages in the target range. We need to make sure that writeback for * any such pages does not start while we are logging the inode, because @@ -2128,8 +2133,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaction open. + * + * Also, the range length can be represented by u64, we have to do the + * typecasts to avoid signed overflow if it's [0, LLONG_MAX]. */ - ret = btrfs_wait_ordered_range(inode, start, len); + ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1); if (ret) { up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 63cad7865d75..37345fb6191d 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -501,13 +501,13 @@ again: ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc); btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true); goto out_put; } ret = btrfs_write_out_ino_cache(root, trans, path, inode); - btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, false); + btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc); out_put: iput(inode); out_release: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a0546401bc0a..c3f386b7cc0b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2206,7 +2206,7 @@ again: ClearPageChecked(page); set_page_dirty(page); - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); out: unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); @@ -4951,7 +4951,7 @@ again: if (!page) { btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); ret = -ENOMEM; goto out; } @@ -5018,7 +5018,7 @@ out_unlock: if (ret) btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0)); + btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); out: @@ -6305,13 +6305,16 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, u32 sizes[2]; int nitems = name ? 2 : 1; unsigned long ptr; + unsigned int nofs_flag; int ret; path = btrfs_alloc_path(); if (!path) return ERR_PTR(-ENOMEM); + nofs_flag = memalloc_nofs_save(); inode = new_inode(fs_info->sb); + memalloc_nofs_restore(nofs_flag); if (!inode) { btrfs_free_path(path); return ERR_PTR(-ENOMEM); @@ -8706,7 +8709,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } else if (ret >= 0 && (size_t)ret < count) btrfs_delalloc_release_space(inode, data_reserved, offset, count - (size_t)ret, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), count, false); + btrfs_delalloc_release_extents(BTRFS_I(inode), count); } out: if (wakeup) @@ -9056,7 +9059,7 @@ again: unlock_extent_cached(io_tree, page_start, page_end, &cached_state); if (!ret2) { - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); sb_end_pagefault(inode->i_sb); extent_changeset_free(data_reserved); return VM_FAULT_LOCKED; @@ -9065,7 +9068,7 @@ again: out_unlock: unlock_page(page); out: - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0)); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); btrfs_delalloc_release_space(inode, data_reserved, page_start, reserved_space, (ret != 0)); out_noreserve: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index de730e56d3f5..7c145a41decd 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1360,8 +1360,7 @@ again: unlock_page(pages[i]); put_page(pages[i]); } - btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT, - false); + btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return i_done; out: @@ -1372,8 +1371,7 @@ out: btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT, - true); + btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c4bb69941c77..3ad151655eb8 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3629,7 +3629,7 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, return 0; BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); - trace_qgroup_meta_reserve(root, type, (s64)num_bytes); + trace_qgroup_meta_reserve(root, (s64)num_bytes, type); ret = qgroup_reserve(root, num_bytes, enforce, type); if (ret < 0) return ret; @@ -3676,7 +3676,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, */ num_bytes = sub_root_meta_rsv(root, num_bytes, type); BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); - trace_qgroup_meta_reserve(root, type, -(s64)num_bytes); + trace_qgroup_meta_reserve(root, -(s64)num_bytes, type); btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid, num_bytes, type); } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index e87cbdad02a3..b57f3618e58e 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -500,7 +500,7 @@ static int process_leaf(struct btrfs_root *root, struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; u32 count; - int i = 0, tree_block_level = 0, ret; + int i = 0, tree_block_level = 0, ret = 0; struct btrfs_key key; int nritems = btrfs_header_nritems(leaf); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 00504657b602..5cd42b66818c 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3277,6 +3277,8 @@ static int relocate_file_extent_cluster(struct inode *inode, if (!page) { btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), + PAGE_SIZE); ret = -ENOMEM; goto out; } @@ -3297,7 +3299,7 @@ static int relocate_file_extent_cluster(struct inode *inode, btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE, true); btrfs_delalloc_release_extents(BTRFS_I(inode), - PAGE_SIZE, true); + PAGE_SIZE); ret = -EIO; goto out; } @@ -3326,7 +3328,7 @@ static int relocate_file_extent_cluster(struct inode *inode, btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE, true); btrfs_delalloc_release_extents(BTRFS_I(inode), - PAGE_SIZE, true); + PAGE_SIZE); clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, @@ -3342,8 +3344,7 @@ static int relocate_file_extent_cluster(struct inode *inode, put_page(page); index++; - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, - false); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); balance_dirty_pages_ratelimited(inode->i_mapping); btrfs_throttle(fs_info); } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index f3215028235c..123ac54af071 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5085,7 +5085,7 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *path; struct btrfs_key key; int ret; - u64 clone_src_i_size; + u64 clone_src_i_size = 0; /* * Prevent cloning from a zero offset with a length matching the sector diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 29b82a795522..8a6cc600bf18 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2932,7 +2932,8 @@ out: * in the tree of log roots */ static int update_log_root(struct btrfs_trans_handle *trans, - struct btrfs_root *log) + struct btrfs_root *log, + struct btrfs_root_item *root_item) { struct btrfs_fs_info *fs_info = log->fs_info; int ret; @@ -2940,10 +2941,10 @@ static int update_log_root(struct btrfs_trans_handle *trans, if (log->log_transid == 1) { /* insert root item on the first sync */ ret = btrfs_insert_root(trans, fs_info->log_root_tree, - &log->root_key, &log->root_item); + &log->root_key, root_item); } else { ret = btrfs_update_root(trans, fs_info->log_root_tree, - &log->root_key, &log->root_item); + &log->root_key, root_item); } return ret; } @@ -3041,6 +3042,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log = root->log_root; struct btrfs_root *log_root_tree = fs_info->log_root_tree; + struct btrfs_root_item new_root_item; int log_transid = 0; struct btrfs_log_ctx root_log_ctx; struct blk_plug plug; @@ -3104,18 +3106,26 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, goto out; } + /* + * We _must_ update under the root->log_mutex in order to make sure we + * have a consistent view of the log root we are trying to commit at + * this moment. + * + * We _must_ copy this into a local copy, because we are not holding the + * log_root_tree->log_mutex yet. This is important because when we + * commit the log_root_tree we must have a consistent view of the + * log_root_tree when we update the super block to point at the + * log_root_tree bytenr. If we update the log_root_tree here we'll race + * with the commit and possibly point at the new block which we may not + * have written out. + */ btrfs_set_root_node(&log->root_item, log->node); + memcpy(&new_root_item, &log->root_item, sizeof(new_root_item)); root->log_transid++; log->log_transid = root->log_transid; root->log_start_pid = 0; /* - * Update or create log root item under the root's log_mutex to prevent - * races with concurrent log syncs that can lead to failure to update - * log root item because it was not created yet. - */ - ret = update_log_root(trans, log); - /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. @@ -3135,6 +3145,14 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&log_root_tree->log_mutex); mutex_lock(&log_root_tree->log_mutex); + + /* + * Now we are safe to update the log_root_tree because we're under the + * log_mutex, and we're a current writer so we're holding the commit + * open until we drop the log_mutex. + */ + ret = update_log_root(trans, log, &new_root_item); + if (atomic_dec_and_test(&log_root_tree->log_writers)) { /* atomic_dec_and_test implies a barrier */ cond_wake_up_nomb(&log_root_tree->log_writer_wait); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cdd7af424033..bdfe4493e43a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3845,7 +3845,11 @@ static int alloc_profile_is_valid(u64 flags, int extended) return !extended; /* "0" is valid for usual profiles */ /* true if exactly one bit set */ - return is_power_of_2(flags); + /* + * Don't use is_power_of_2(unsigned long) because it won't work + * for the single profile (1ULL << 48) on 32-bit CPUs. + */ + return flags != 0 && (flags & (flags - 1)) == 0; } static inline int balance_need_close(struct btrfs_fs_info *fs_info) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a8a8f84f3bbf..a5163296d9d9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -384,8 +384,8 @@ static int parse_reply_info_readdir(void **p, void *end, } done: - if (*p != end) - goto bad; + /* Skip over any unrecognized fields */ + *p = end; return 0; bad: @@ -406,12 +406,10 @@ static int parse_reply_info_filelock(void **p, void *end, goto bad; info->filelock_reply = *p; - *p += sizeof(*info->filelock_reply); - if (unlikely(*p != end)) - goto bad; + /* Skip over any unrecognized fields */ + *p = end; return 0; - bad: return -EIO; } @@ -425,18 +423,21 @@ static int parse_reply_info_create(void **p, void *end, { if (features == (u64)-1 || (features & CEPH_FEATURE_REPLY_CREATE_INODE)) { + /* Malformed reply? */ if (*p == end) { info->has_create_ino = false; } else { info->has_create_ino = true; - info->ino = ceph_decode_64(p); + ceph_decode_64_safe(p, end, info->ino, bad); } + } else { + if (*p != end) + goto bad; } - if (unlikely(*p != end)) - goto bad; + /* Skip over any unrecognized fields */ + *p = end; return 0; - bad: return -EIO; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 2e9c7f493f99..1a135d1b85bd 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -169,18 +169,32 @@ cifs_read_super(struct super_block *sb) else sb->s_maxbytes = MAX_NON_LFS; - /* BB FIXME fix time_gran to be larger for LANMAN sessions */ - sb->s_time_gran = 100; - - if (tcon->unix_ext) { - ts = cifs_NTtimeToUnix(0); + /* + * Some very old servers like DOS and OS/2 used 2 second granularity + * (while all current servers use 100ns granularity - see MS-DTYP) + * but 1 second is the maximum allowed granularity for the VFS + * so for old servers set time granularity to 1 second while for + * everything else (current servers) set it to 100ns. + */ + if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) && + ((tcon->ses->capabilities & + tcon->ses->server->vals->cap_nt_find) == 0) && + !tcon->unix_ext) { + sb->s_time_gran = 1000000000; /* 1 second is max allowed gran */ + ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MIN), 0, 0); sb->s_time_min = ts.tv_sec; - ts = cifs_NTtimeToUnix(cpu_to_le64(S64_MAX)); + ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MAX), + cpu_to_le16(SMB_TIME_MAX), 0); sb->s_time_max = ts.tv_sec; } else { - ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MIN), 0, 0); + /* + * Almost every server, including all SMB2+, uses DCE TIME + * ie 100 nanosecond units, since 1601. See MS-DTYP and MS-FSCC + */ + sb->s_time_gran = 100; + ts = cifs_NTtimeToUnix(0); sb->s_time_min = ts.tv_sec; - ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MAX), cpu_to_le16(SMB_TIME_MAX), 0); + ts = cifs_NTtimeToUnix(cpu_to_le64(S64_MAX)); sb->s_time_max = ts.tv_sec; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 2e960e1049db..d78bfcc19156 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1210,7 +1210,7 @@ struct cifs_search_info { bool smallBuf:1; /* so we know which buf_release function to call */ }; -#define ACL_NO_MODE -1 +#define ACL_NO_MODE ((umode_t)(-1)) struct cifs_open_parms { struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; @@ -1391,6 +1391,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); struct cifsInodeInfo { bool can_cache_brlcks; struct list_head llist; /* locks helb by this inode */ + /* + * NOTE: Some code paths call down_read(lock_sem) twice, so + * we must always use use cifs_down_write() instead of down_write() + * for this semaphore to avoid deadlocks. + */ struct rw_semaphore lock_sem; /* protect the fields above */ /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index e53e9f62b87b..fe597d3d5208 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -170,6 +170,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile); +extern void cifs_down_write(struct rw_semaphore *sem); extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 2850c3ce4391..ccaa8bad336f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -564,9 +564,11 @@ cifs_reconnect(struct TCP_Server_Info *server) spin_lock(&GlobalMid_Lock); list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { mid_entry = list_entry(tmp, struct mid_q_entry, qhead); + kref_get(&mid_entry->refcount); if (mid_entry->mid_state == MID_REQUEST_SUBMITTED) mid_entry->mid_state = MID_RETRY_NEEDED; list_move(&mid_entry->qhead, &retry_list); + mid_entry->mid_flags |= MID_DELETED; } spin_unlock(&GlobalMid_Lock); mutex_unlock(&server->srv_mutex); @@ -576,6 +578,7 @@ cifs_reconnect(struct TCP_Server_Info *server) mid_entry = list_entry(tmp, struct mid_q_entry, qhead); list_del_init(&mid_entry->qhead); mid_entry->callback(mid_entry); + cifs_mid_q_entry_release(mid_entry); } if (cifs_rdma_enabled(server)) { @@ -895,8 +898,10 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) if (mid->mid_flags & MID_DELETED) printk_once(KERN_WARNING "trying to dequeue a deleted mid\n"); - else + else { list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); } @@ -966,8 +971,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { mid_entry = list_entry(tmp, struct mid_q_entry, qhead); cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid); + kref_get(&mid_entry->refcount); mid_entry->mid_state = MID_SHUTDOWN; list_move(&mid_entry->qhead, &dispose_list); + mid_entry->mid_flags |= MID_DELETED; } spin_unlock(&GlobalMid_Lock); @@ -977,6 +984,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid); list_del_init(&mid_entry->qhead); mid_entry->callback(mid_entry); + cifs_mid_q_entry_release(mid_entry); } /* 1/8th of sec is more than enough time for them to exit */ msleep(125); @@ -3882,8 +3890,12 @@ generic_ip_connect(struct TCP_Server_Info *server) rc = socket->ops->connect(socket, saddr, slen, server->noblockcnt ? O_NONBLOCK : 0); - - if (rc == -EINPROGRESS) + /* + * When mounting SMB root file systems, we do not want to block in + * connect. Otherwise bail out and then let cifs_reconnect() perform + * reconnect failover - if possible. + */ + if (server->noblockcnt && rc == -EINPROGRESS) rc = 0; if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); @@ -4264,7 +4276,7 @@ static int mount_get_conns(struct smb_vol *vol, struct cifs_sb_info *cifs_sb, server->ops->qfs_tcon(*xid, tcon); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) { if (tcon->fsDevInfo.DeviceCharacteristics & - FILE_READ_ONLY_DEVICE) + cpu_to_le32(FILE_READ_ONLY_DEVICE)) cifs_dbg(VFS, "mounted to read only share\n"); else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE) == 0) @@ -4445,7 +4457,7 @@ static int setup_dfs_tgt_conn(const char *path, int rc; struct dfs_info3_param ref = {0}; char *mdata = NULL, *fake_devname = NULL; - struct smb_vol fake_vol = {0}; + struct smb_vol fake_vol = {NULL}; cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index dd5ac841aefa..7ce689d31aa2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -738,10 +738,16 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, static int cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { + struct inode *inode; + if (flags & LOOKUP_RCU) return -ECHILD; if (d_really_is_positive(direntry)) { + inode = d_inode(direntry); + if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) + CIFS_I(inode)->time = 0; /* force reval */ + if (cifs_revalidate_dentry(direntry)) return 0; else { @@ -752,7 +758,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags) * attributes will have been updated by * cifs_revalidate_dentry(). */ - if (IS_AUTOMOUNT(d_inode(direntry)) && + if (IS_AUTOMOUNT(inode) && !(direntry->d_flags & DCACHE_NEED_AUTOMOUNT)) { spin_lock(&direntry->d_lock); direntry->d_flags |= DCACHE_NEED_AUTOMOUNT; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4b95700c507c..fa7b0fa72bb3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -253,6 +253,12 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, xid, fid); + if (rc) { + server->ops->close(xid, tcon, fid); + if (rc == -ESTALE) + rc = -EOPENSTALE; + } + out: kfree(buf); return rc; @@ -275,6 +281,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode) return has_locks; } +void +cifs_down_write(struct rw_semaphore *sem) +{ + while (!down_write_trylock(sem)) + msleep(10); +} + struct cifsFileInfo * cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock) @@ -300,7 +313,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, INIT_LIST_HEAD(&fdlocks->locks); fdlocks->cfile = cfile; cfile->llist = fdlocks; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_add(&fdlocks->llist, &cinode->llist); up_write(&cinode->lock_sem); @@ -399,10 +412,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) bool oplock_break_cancelled; spin_lock(&tcon->open_file_lock); - + spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); + spin_unlock(&cifsi->open_file_lock); spin_unlock(&tcon->open_file_lock); return; } @@ -415,9 +429,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open); /* remove it from the lists */ - spin_lock(&cifsi->open_file_lock); list_del(&cifs_file->flist); - spin_unlock(&cifsi->open_file_lock); list_del(&cifs_file->tlist); atomic_dec(&tcon->num_local_opens); @@ -434,6 +446,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) cifs_set_oplock_level(cifsi, 0); } + spin_unlock(&cifsi->open_file_lock); spin_unlock(&tcon->open_file_lock); oplock_break_cancelled = wait_oplock_handler ? @@ -458,7 +471,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) * Delete any outstanding lock records. We'll lose them when the file * is closed anyway. */ - down_write(&cifsi->lock_sem); + cifs_down_write(&cifsi->lock_sem); list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) { list_del(&li->llist); cifs_del_lock_waiters(li); @@ -1021,7 +1034,7 @@ static void cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock) { struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry)); - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_add_tail(&lock->llist, &cfile->llist->locks); up_write(&cinode->lock_sem); } @@ -1043,7 +1056,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock, try_again: exist = false; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length, lock->type, lock->flags, &conf_lock, @@ -1066,7 +1079,7 @@ try_again: (lock->blist.next == &lock->blist)); if (!rc) goto try_again; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_del_init(&lock->blist); } @@ -1119,7 +1132,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock) return rc; try_again: - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); return rc; @@ -1325,7 +1338,7 @@ cifs_push_locks(struct cifsFileInfo *cfile) int rc = 0; /* we are going to update can_cache_brlcks here - need a write access */ - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); return rc; @@ -1516,7 +1529,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, if (!buf) return -ENOMEM; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); for (i = 0; i < 2; i++) { cur = buf; num = 0; @@ -1840,13 +1853,12 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, { struct cifsFileInfo *open_file = NULL; struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); - struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); /* only filter by fsuid on multiuser mounts */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; - spin_lock(&tcon->open_file_lock); + spin_lock(&cifs_inode->open_file_lock); /* we could simply get the first_list_entry since write-only entries are always at the end of the list but since the first entry might have a close pending, we go through the whole list */ @@ -1858,7 +1870,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, /* found a good file */ /* lock it so it will not be closed on us */ cifsFileInfo_get(open_file); - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); return open_file; } /* else might as well continue, and look for another, or simply have the caller reopen it @@ -1866,7 +1878,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, } else /* write only file */ break; /* write only files are last so must be done */ } - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); return NULL; } @@ -1877,7 +1889,6 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only, { struct cifsFileInfo *open_file, *inv_file = NULL; struct cifs_sb_info *cifs_sb; - struct cifs_tcon *tcon; bool any_available = false; int rc = -EBADF; unsigned int refind = 0; @@ -1897,16 +1908,15 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only, } cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); - tcon = cifs_sb_master_tcon(cifs_sb); /* only filter by fsuid on multiuser mounts */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; - spin_lock(&tcon->open_file_lock); + spin_lock(&cifs_inode->open_file_lock); refind_writable: if (refind > MAX_REOPEN_ATT) { - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); return rc; } list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { @@ -1918,7 +1928,7 @@ refind_writable: if (!open_file->invalidHandle) { /* found a good writable file */ cifsFileInfo_get(open_file); - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); *ret_file = open_file; return 0; } else { @@ -1938,7 +1948,7 @@ refind_writable: cifsFileInfo_get(inv_file); } - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); if (inv_file) { rc = cifs_reopen_file(inv_file, false); @@ -1953,7 +1963,7 @@ refind_writable: cifsFileInfo_put(inv_file); ++refind; inv_file = NULL; - spin_lock(&tcon->open_file_lock); + spin_lock(&cifs_inode->open_file_lock); goto refind_writable; } @@ -4461,17 +4471,15 @@ static int cifs_readpage(struct file *file, struct page *page) static int is_inode_writable(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *open_file; - struct cifs_tcon *tcon = - cifs_sb_master_tcon(CIFS_SB(cifs_inode->vfs_inode.i_sb)); - spin_lock(&tcon->open_file_lock); + spin_lock(&cifs_inode->open_file_lock); list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); return 1; } } - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); return 0; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 3bae2e53f0b8..df9377828e2f 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -414,6 +414,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* if uniqueid is different, return error */ if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM && CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) { + CIFS_I(*pinode)->time = 0; /* force reval */ rc = -ESTALE; goto cgiiu_exit; } @@ -421,6 +422,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* if filetype is different, return error */ if (unlikely(((*pinode)->i_mode & S_IFMT) != (fattr.cf_mode & S_IFMT))) { + CIFS_I(*pinode)->time = 0; /* force reval */ rc = -ESTALE; goto cgiiu_exit; } @@ -933,6 +935,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, /* if uniqueid is different, return error */ if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM && CIFS_I(*inode)->uniqueid != fattr.cf_uniqueid)) { + CIFS_I(*inode)->time = 0; /* force reval */ rc = -ESTALE; goto cgii_exit; } @@ -940,6 +943,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, /* if filetype is different, return error */ if (unlikely(((*inode)->i_mode & S_IFMT) != (fattr.cf_mode & S_IFMT))) { + CIFS_I(*inode)->time = 0; /* force reval */ rc = -ESTALE; goto cgii_exit; } @@ -2471,9 +2475,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); cifsFileInfo_put(wfile); if (rc) - return rc; + goto cifs_setattr_exit; } else if (rc != -EBADF) - return rc; + goto cifs_setattr_exit; else rc = 0; } diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 49c17ee18254..9b41436fb8db 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -117,10 +117,6 @@ static const struct smb_to_posix_error mapping_table_ERRSRV[] = { {0, 0} }; -static const struct smb_to_posix_error mapping_table_ERRHRD[] = { - {0, 0} -}; - /* * Convert a string containing text IPv4 or IPv6 address to binary form. * diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index b7421a096319..514810694c0f 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -171,6 +171,9 @@ cifs_get_next_mid(struct TCP_Server_Info *server) /* we do not want to loop forever */ last_mid = cur_mid; cur_mid++; + /* avoid 0xFFFF MID */ + if (cur_mid == 0xffff) + cur_mid++; /* * This nested loop looks more expensive than it is. diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index e6a1fc72018f..8b0b512c5792 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -145,7 +145,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, cur = buf; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) { if (flock->fl_start > li->offset || (flock->fl_start + length) < diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 85f9d614d968..05149862aea4 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -751,8 +751,8 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) unsigned int num = *num_iovec; iov[num].iov_base = create_posix_buf(mode); - if (mode == -1) - cifs_dbg(VFS, "illegal mode\n"); /* BB REMOVEME */ + if (mode == ACL_NO_MODE) + cifs_dbg(FYI, "illegal mode\n"); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_posix); @@ -2521,11 +2521,8 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock, return rc; } - /* TODO: add handling for the mode on create */ - if (oparms->disposition == FILE_CREATE) - cifs_dbg(VFS, "mode is 0x%x\n", oparms->mode); /* BB REMOVEME */ - - if ((oparms->disposition == FILE_CREATE) && (oparms->mode != -1)) { + if ((oparms->disposition == FILE_CREATE) && + (oparms->mode != ACL_NO_MODE)) { if (n_iov > 2) { struct create_context *ccontext = (struct create_context *)iov[n_iov-1].iov_base; @@ -3217,7 +3214,8 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst, req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; - req->OutputBufferLength = SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE; + req->OutputBufferLength = + cpu_to_le32(SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE); req->CompletionFilter = cpu_to_le32(completion_filter); if (watch_tree) req->Flags = cpu_to_le16(SMB2_WATCH_TREE); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index da3a6d580808..71b2930b8e0b 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -150,6 +150,10 @@ extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, bool is_fsctl, char *in_data, u32 indatalen, __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); +extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, bool watch_tree, + u32 completion_filter); + extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 308ad0f495e1..ca3de62688d6 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -86,22 +86,8 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) static void _cifs_mid_q_entry_release(struct kref *refcount) { - struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry, - refcount); - - mempool_free(mid, cifs_mid_poolp); -} - -void cifs_mid_q_entry_release(struct mid_q_entry *midEntry) -{ - spin_lock(&GlobalMid_Lock); - kref_put(&midEntry->refcount, _cifs_mid_q_entry_release); - spin_unlock(&GlobalMid_Lock); -} - -void -DeleteMidQEntry(struct mid_q_entry *midEntry) -{ + struct mid_q_entry *midEntry = + container_of(refcount, struct mid_q_entry, refcount); #ifdef CONFIG_CIFS_STATS2 __le16 command = midEntry->server->vals->lock_cmd; __u16 smb_cmd = le16_to_cpu(midEntry->command); @@ -166,6 +152,19 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) } } #endif + + mempool_free(midEntry, cifs_mid_poolp); +} + +void cifs_mid_q_entry_release(struct mid_q_entry *midEntry) +{ + spin_lock(&GlobalMid_Lock); + kref_put(&midEntry->refcount, _cifs_mid_q_entry_release); + spin_unlock(&GlobalMid_Lock); +} + +void DeleteMidQEntry(struct mid_q_entry *midEntry) +{ cifs_mid_q_entry_release(midEntry); } @@ -173,8 +172,10 @@ void cifs_delete_mid(struct mid_q_entry *mid) { spin_lock(&GlobalMid_Lock); - list_del_init(&mid->qhead); - mid->mid_flags |= MID_DELETED; + if (!(mid->mid_flags & MID_DELETED)) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); DeleteMidQEntry(mid); @@ -872,7 +873,10 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) rc = -EHOSTDOWN; break; default: - list_del_init(&mid->qhead); + if (!(mid->mid_flags & MID_DELETED)) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n", __func__, mid->mid, mid->mid_state); rc = -EIO; @@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order) for (;;) { entry = xas_find_conflict(xas); + if (!entry || WARN_ON_ONCE(!xa_is_value(entry))) + return entry; if (dax_entry_order(entry) < order) return XA_RETRY_ENTRY; - if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) || - !dax_is_locked(entry)) + if (!dax_is_locked(entry)) return entry; wq = dax_entry_waitqueue(xas, entry, &ewait.key); diff --git a/fs/direct-io.c b/fs/direct-io.c index ae196784f487..9329ced91f1d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp) } } -/** +/* * dio_complete() - called when all DIO BIO I/O has been completed - * @offset: the byte offset in the file of the completed operation * * This drops i_dio_count, lets interested parties know that a DIO operation * has completed, and calculates the resulting return code for the operation. diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8aaa7eec7b74..8461a6322039 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -164,8 +164,13 @@ static void finish_writeback_work(struct bdi_writeback *wb, if (work->auto_free) kfree(work); - if (done && atomic_dec_and_test(&done->cnt)) - wake_up_all(done->waitq); + if (done) { + wait_queue_head_t *waitq = done->waitq; + + /* @done can't be accessed after the following dec */ + if (atomic_dec_and_test(&done->cnt)) + wake_up_all(waitq); + } } static void wb_queue_work(struct bdi_writeback *wb, @@ -900,7 +905,7 @@ restart: * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id - * @nr_pages: number of pages to write, 0 for best-effort dirty flushing + * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 681b44682b0d..dc61af2c4d5e 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1600,6 +1600,7 @@ static int gfs2_meta_get_tree(struct fs_context *fc) } static const struct fs_context_operations gfs2_meta_context_ops = { + .free = gfs2_fc_free, .get_tree = gfs2_meta_get_tree, }; diff --git a/fs/io_uring.c b/fs/io_uring.c index 8a0381f1a43b..a30c4f622cb3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -197,6 +197,7 @@ struct io_ring_ctx { unsigned sq_entries; unsigned sq_mask; unsigned sq_thread_idle; + unsigned cached_sq_dropped; struct io_uring_sqe *sq_sqes; struct list_head defer_list; @@ -212,6 +213,7 @@ struct io_ring_ctx { struct { unsigned cached_cq_tail; + atomic_t cached_cq_overflow; unsigned cq_entries; unsigned cq_mask; struct wait_queue_head cq_wait; @@ -322,6 +324,8 @@ struct io_kiocb { #define REQ_F_FAIL_LINK 256 /* fail rest of links */ #define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */ #define REQ_F_TIMEOUT 1024 /* timeout request */ +#define REQ_F_ISREG 2048 /* regular file */ +#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */ u64 user_data; u32 result; u32 sequence; @@ -415,27 +419,28 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) return ctx; } +static inline bool __io_sequence_defer(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped + + atomic_read(&ctx->cached_cq_overflow); +} + static inline bool io_sequence_defer(struct io_ring_ctx *ctx, struct io_kiocb *req) { - /* timeout requests always honor sequence */ - if (!(req->flags & REQ_F_TIMEOUT) && - (req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) + if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) return false; - return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped; + return __io_sequence_defer(ctx, req); } -static struct io_kiocb *__io_get_deferred_req(struct io_ring_ctx *ctx, - struct list_head *list) +static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) { struct io_kiocb *req; - if (list_empty(list)) - return NULL; - - req = list_first_entry(list, struct io_kiocb, list); - if (!io_sequence_defer(ctx, req)) { + req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list); + if (req && !io_sequence_defer(ctx, req)) { list_del_init(&req->list); return req; } @@ -443,14 +448,17 @@ static struct io_kiocb *__io_get_deferred_req(struct io_ring_ctx *ctx, return NULL; } -static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) -{ - return __io_get_deferred_req(ctx, &ctx->defer_list); -} - static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx) { - return __io_get_deferred_req(ctx, &ctx->timeout_list); + struct io_kiocb *req; + + req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list); + if (req && !__io_sequence_defer(ctx, req)) { + list_del_init(&req->list); + return req; + } + + return NULL; } static void __io_commit_cqring(struct io_ring_ctx *ctx) @@ -562,9 +570,8 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, 0); } else { - unsigned overflow = READ_ONCE(ctx->rings->cq_overflow); - - WRITE_ONCE(ctx->rings->cq_overflow, overflow + 1); + WRITE_ONCE(ctx->rings->cq_overflow, + atomic_inc_return(&ctx->cached_cq_overflow)); } } @@ -591,14 +598,6 @@ static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, io_cqring_ev_posted(ctx); } -static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) -{ - percpu_ref_put_many(&ctx->refs, refs); - - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); -} - static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, struct io_submit_state *state) { @@ -646,7 +645,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, req->result = 0; return req; out: - io_ring_drop_ctx_refs(ctx, 1); + percpu_ref_put(&ctx->refs); return NULL; } @@ -654,7 +653,7 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) { if (*nr) { kmem_cache_free_bulk(req_cachep, *nr, reqs); - io_ring_drop_ctx_refs(ctx, *nr); + percpu_ref_put_many(&ctx->refs, *nr); *nr = 0; } } @@ -663,7 +662,7 @@ static void __io_free_req(struct io_kiocb *req) { if (req->file && !(req->flags & REQ_F_FIXED_FILE)) fput(req->file); - io_ring_drop_ctx_refs(req->ctx, 1); + percpu_ref_put(&req->ctx->refs); kmem_cache_free(req_cachep, req); } @@ -738,6 +737,14 @@ static unsigned io_cqring_events(struct io_rings *rings) return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head); } +static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* make sure SQ entry isn't read before tail */ + return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; +} + /* * Find and free completed poll iocbs */ @@ -867,19 +874,11 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) +static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) { - int iters, ret = 0; - - /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); + int iters = 0, ret = 0; - iters = 0; do { int tmin = 0; @@ -915,30 +914,45 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, ret = 0; } while (min && !*nr_events && !need_resched()); + return ret; +} + +static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) +{ + int ret; + + /* + * We disallow the app entering submit/complete with polling, but we + * still need to lock the ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); + ret = __io_iopoll_check(ctx, nr_events, min); mutex_unlock(&ctx->uring_lock); return ret; } -static void kiocb_end_write(struct kiocb *kiocb) +static void kiocb_end_write(struct io_kiocb *req) { - if (kiocb->ki_flags & IOCB_WRITE) { - struct inode *inode = file_inode(kiocb->ki_filp); + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + if (req->flags & REQ_F_ISREG) { + struct inode *inode = file_inode(req->file); - /* - * Tell lockdep we inherited freeze protection from submission - * thread. - */ - if (S_ISREG(inode->i_mode)) - __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); - file_end_write(kiocb->ki_filp); + __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); } + file_end_write(req->file); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); - kiocb_end_write(kiocb); + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); if ((req->flags & REQ_F_LINK) && res != req->result) req->flags |= REQ_F_FAIL_LINK; @@ -950,7 +964,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); - kiocb_end_write(kiocb); + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); if ((req->flags & REQ_F_LINK) && res != req->result) req->flags |= REQ_F_FAIL_LINK; @@ -1064,8 +1079,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, if (!req->file) return -EBADF; - if (force_nonblock && !io_file_supports_async(req->file)) - force_nonblock = false; + if (S_ISREG(file_inode(req->file)->i_mode)) + req->flags |= REQ_F_ISREG; + + /* + * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so + * we know to async punt it even if it was opened O_NONBLOCK + */ + if (force_nonblock && !io_file_supports_async(req->file)) { + req->flags |= REQ_F_MUST_PUNT; + return -EAGAIN; + } kiocb->ki_pos = READ_ONCE(sqe->off); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); @@ -1086,7 +1110,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, return ret; /* don't allow async punt if RWF_NOWAIT was requested */ - if (kiocb->ki_flags & IOCB_NOWAIT) + if ((kiocb->ki_flags & IOCB_NOWAIT) || + (req->file->f_flags & O_NONBLOCK)) req->flags |= REQ_F_NOWAIT; if (force_nonblock) @@ -1387,7 +1412,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, * need async punt anyway, so it's more efficient to do it * here. */ - if (force_nonblock && ret2 > 0 && ret2 < read_size) + if (force_nonblock && !(req->flags & REQ_F_NOWAIT) && + (req->flags & REQ_F_ISREG) && + ret2 > 0 && ret2 < read_size) ret2 = -EAGAIN; /* Catch -EAGAIN return for forced non-blocking submission */ if (!force_nonblock || ret2 != -EAGAIN) { @@ -1452,7 +1479,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, * released so that it doesn't complain about the held lock when * we return to userspace. */ - if (S_ISREG(file_inode(file)->i_mode)) { + if (req->flags & REQ_F_ISREG) { __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); __sb_writers_release(file_inode(file)->i_sb, @@ -1867,7 +1894,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) { struct io_ring_ctx *ctx; - struct io_kiocb *req; + struct io_kiocb *req, *prev; unsigned long flags; req = container_of(timer, struct io_kiocb, timeout.timer); @@ -1875,6 +1902,15 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) atomic_inc(&ctx->cq_timeouts); spin_lock_irqsave(&ctx->completion_lock, flags); + /* + * Adjust the reqs sequence before the current one because it + * will consume a slot in the cq_ring and the the cq_tail pointer + * will be increased, otherwise other timeout reqs may return in + * advance without waiting for enough wait_nr. + */ + prev = req; + list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list) + prev->sequence++; list_del(&req->list); io_cqring_fill_event(ctx, req->user_data, -ETIME); @@ -1889,10 +1925,11 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - unsigned count, req_dist, tail_index; + unsigned count; struct io_ring_ctx *ctx = req->ctx; struct list_head *entry; struct timespec64 ts; + unsigned span = 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; @@ -1912,23 +1949,46 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) count = 1; req->sequence = ctx->cached_sq_head + count - 1; + /* reuse it to store the count */ + req->submit.sequence = count; req->flags |= REQ_F_TIMEOUT; /* * Insertion sort, ensuring the first entry in the list is always * the one we need first. */ - tail_index = ctx->cached_cq_tail - ctx->rings->sq_dropped; - req_dist = req->sequence - tail_index; spin_lock_irq(&ctx->completion_lock); list_for_each_prev(entry, &ctx->timeout_list) { struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list); - unsigned dist; + unsigned nxt_sq_head; + long long tmp, tmp_nxt; - dist = nxt->sequence - tail_index; - if (req_dist >= dist) + /* + * Since cached_sq_head + count - 1 can overflow, use type long + * long to store it. + */ + tmp = (long long)ctx->cached_sq_head + count - 1; + nxt_sq_head = nxt->sequence - nxt->submit.sequence + 1; + tmp_nxt = (long long)nxt_sq_head + nxt->submit.sequence - 1; + + /* + * cached_sq_head may overflow, and it will never overflow twice + * once there is some timeout req still be valid. + */ + if (ctx->cached_sq_head < nxt_sq_head) + tmp += UINT_MAX; + + if (tmp > tmp_nxt) break; + + /* + * Sequence of reqs after the insert one and itself should + * be adjusted because each timeout req consumes a slot. + */ + span++; + nxt->sequence++; } + req->sequence -= span; list_add(&req->list, entry); spin_unlock_irq(&ctx->completion_lock); @@ -2267,12 +2327,18 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, } static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, bool force_nonblock) + struct sqe_submit *s) { int ret; - ret = __io_submit_sqe(ctx, req, s, force_nonblock); - if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { + ret = __io_submit_sqe(ctx, req, s, true); + + /* + * We async punt it if the file wasn't marked NOWAIT, or if the file + * doesn't support non-blocking read/write attempts + */ + if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) || + (req->flags & REQ_F_MUST_PUNT))) { struct io_uring_sqe *sqe_copy; sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL); @@ -2312,7 +2378,7 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, } static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, bool force_nonblock) + struct sqe_submit *s) { int ret; @@ -2325,18 +2391,17 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } - return __io_queue_sqe(ctx, req, s, force_nonblock); + return __io_queue_sqe(ctx, req, s); } static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, struct io_kiocb *shadow, - bool force_nonblock) + struct sqe_submit *s, struct io_kiocb *shadow) { int ret; int need_submit = false; if (!shadow) - return io_queue_sqe(ctx, req, s, force_nonblock); + return io_queue_sqe(ctx, req, s); /* * Mark the first IO in link list as DRAIN, let all the following @@ -2365,7 +2430,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, spin_unlock_irq(&ctx->completion_lock); if (need_submit) - return __io_queue_sqe(ctx, req, s, force_nonblock); + return __io_queue_sqe(ctx, req, s); return 0; } @@ -2373,8 +2438,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK) static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, - struct io_submit_state *state, struct io_kiocb **link, - bool force_nonblock) + struct io_submit_state *state, struct io_kiocb **link) { struct io_uring_sqe *sqe_copy; struct io_kiocb *req; @@ -2401,6 +2465,8 @@ err: return; } + req->user_data = s->sqe->user_data; + /* * If we already have a head request, queue this one for async * submittal once the head completes. If we don't have a head but @@ -2427,7 +2493,7 @@ err: INIT_LIST_HEAD(&req->link_list); *link = req; } else { - io_queue_sqe(ctx, req, s, force_nonblock); + io_queue_sqe(ctx, req, s); } } @@ -2507,12 +2573,13 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) /* drop invalid entries */ ctx->cached_sq_head++; - rings->sq_dropped++; + ctx->cached_sq_dropped++; + WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped); return false; } -static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, - unsigned int nr, bool has_user, bool mm_fault) +static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, + bool has_user, bool mm_fault) { struct io_submit_state state, *statep = NULL; struct io_kiocb *link = NULL; @@ -2526,19 +2593,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, } for (i = 0; i < nr; i++) { + struct sqe_submit s; + + if (!io_get_sqring(ctx, &s)) + break; + /* * If previous wasn't linked and we have a linked command, * that's the end of the chain. Submit the previous link. */ if (!prev_was_link && link) { - io_queue_link_head(ctx, link, &link->submit, shadow_req, - true); + io_queue_link_head(ctx, link, &link->submit, shadow_req); link = NULL; shadow_req = NULL; } - prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0; + prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0; - if (link && (sqes[i].sqe->flags & IOSQE_IO_DRAIN)) { + if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) { if (!shadow_req) { shadow_req = io_get_req(ctx, NULL); if (unlikely(!shadow_req)) @@ -2546,24 +2617,24 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN); refcount_dec(&shadow_req->refs); } - shadow_req->sequence = sqes[i].sequence; + shadow_req->sequence = s.sequence; } out: if (unlikely(mm_fault)) { - io_cqring_add_event(ctx, sqes[i].sqe->user_data, + io_cqring_add_event(ctx, s.sqe->user_data, -EFAULT); } else { - sqes[i].has_user = has_user; - sqes[i].needs_lock = true; - sqes[i].needs_fixed_file = true; - io_submit_sqe(ctx, &sqes[i], statep, &link, true); + s.has_user = has_user; + s.needs_lock = true; + s.needs_fixed_file = true; + io_submit_sqe(ctx, &s, statep, &link); submitted++; } } if (link) - io_queue_link_head(ctx, link, &link->submit, shadow_req, true); + io_queue_link_head(ctx, link, &link->submit, shadow_req); if (statep) io_submit_state_end(&state); @@ -2572,7 +2643,6 @@ out: static int io_sq_thread(void *data) { - struct sqe_submit sqes[IO_IOPOLL_BATCH]; struct io_ring_ctx *ctx = data; struct mm_struct *cur_mm = NULL; mm_segment_t old_fs; @@ -2587,14 +2657,27 @@ static int io_sq_thread(void *data) timeout = inflight = 0; while (!kthread_should_park()) { - bool all_fixed, mm_fault = false; - int i; + bool mm_fault = false; + unsigned int to_submit; if (inflight) { unsigned nr_events = 0; if (ctx->flags & IORING_SETUP_IOPOLL) { - io_iopoll_check(ctx, &nr_events, 0); + /* + * inflight is the count of the maximum possible + * entries we submitted, but it can be smaller + * if we dropped some of them. If we don't have + * poll entries available, then we know that we + * have nothing left to poll for. Reset the + * inflight count to zero in that case. + */ + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->poll_list)) + __io_iopoll_check(ctx, &nr_events, 0); + else + inflight = 0; + mutex_unlock(&ctx->uring_lock); } else { /* * Normal IO, just pretend everything completed. @@ -2608,7 +2691,8 @@ static int io_sq_thread(void *data) timeout = jiffies + ctx->sq_thread_idle; } - if (!io_get_sqring(ctx, &sqes[0])) { + to_submit = io_sqring_entries(ctx); + if (!to_submit) { /* * We're polling. If we're within the defined idle * period, then let us spin without work before going @@ -2639,7 +2723,8 @@ static int io_sq_thread(void *data) /* make sure to read SQ tail after writing flags */ smp_mb(); - if (!io_get_sqring(ctx, &sqes[0])) { + to_submit = io_sqring_entries(ctx); + if (!to_submit) { if (kthread_should_park()) { finish_wait(&ctx->sqo_wait, &wait); break; @@ -2657,19 +2742,8 @@ static int io_sq_thread(void *data) ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; } - i = 0; - all_fixed = true; - do { - if (all_fixed && io_sqe_needs_user(sqes[i].sqe)) - all_fixed = false; - - i++; - if (i == ARRAY_SIZE(sqes)) - break; - } while (io_get_sqring(ctx, &sqes[i])); - /* Unless all new commands are FIXED regions, grab mm */ - if (!all_fixed && !cur_mm) { + if (!cur_mm) { mm_fault = !mmget_not_zero(ctx->sqo_mm); if (!mm_fault) { use_mm(ctx->sqo_mm); @@ -2677,8 +2751,9 @@ static int io_sq_thread(void *data) } } - inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL, - mm_fault); + to_submit = min(to_submit, ctx->sq_entries); + inflight += io_submit_sqes(ctx, to_submit, cur_mm != NULL, + mm_fault); /* Commit SQ ring head once we've consumed all SQEs */ io_commit_sqring(ctx); @@ -2695,8 +2770,7 @@ static int io_sq_thread(void *data) return 0; } -static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit, - bool block_for_last) +static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) { struct io_submit_state state, *statep = NULL; struct io_kiocb *link = NULL; @@ -2710,7 +2784,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit, } for (i = 0; i < to_submit; i++) { - bool force_nonblock = true; struct sqe_submit s; if (!io_get_sqring(ctx, &s)) @@ -2721,8 +2794,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit, * that's the end of the chain. Submit the previous link. */ if (!prev_was_link && link) { - io_queue_link_head(ctx, link, &link->submit, shadow_req, - force_nonblock); + io_queue_link_head(ctx, link, &link->submit, shadow_req); link = NULL; shadow_req = NULL; } @@ -2744,27 +2816,16 @@ out: s.needs_lock = false; s.needs_fixed_file = false; submit++; - - /* - * The caller will block for events after submit, submit the - * last IO non-blocking. This is either the only IO it's - * submitting, or it already submitted the previous ones. This - * improves performance by avoiding an async punt that we don't - * need to do. - */ - if (block_for_last && submit == to_submit) - force_nonblock = false; - - io_submit_sqe(ctx, &s, statep, &link, force_nonblock); + io_submit_sqe(ctx, &s, statep, &link); } - io_commit_sqring(ctx); if (link) - io_queue_link_head(ctx, link, &link->submit, shadow_req, - block_for_last); + io_queue_link_head(ctx, link, &link->submit, shadow_req); if (statep) io_submit_state_end(statep); + io_commit_sqring(ctx); + return submit; } @@ -2920,8 +2981,12 @@ static void io_finish_async(struct io_ring_ctx *ctx) static void io_destruct_skb(struct sk_buff *skb) { struct io_ring_ctx *ctx = skb->sk->sk_user_data; + int i; + + for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) + if (ctx->sqo_wq[i]) + flush_workqueue(ctx->sqo_wq[i]); - io_finish_async(ctx); unix_destruct_scm(skb); } @@ -3601,21 +3666,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, wake_up(&ctx->sqo_wait); submitted = to_submit; } else if (to_submit) { - bool block_for_last = false; - to_submit = min(to_submit, ctx->sq_entries); - /* - * Allow last submission to block in a series, IFF the caller - * asked to wait for events and we don't currently have - * enough. This potentially avoids an async punt. - */ - if (to_submit == min_complete && - io_cqring_events(ctx->rings) < min_complete) - block_for_last = true; - mutex_lock(&ctx->uring_lock); - submitted = io_ring_submit(ctx, to_submit, block_for_last); + submitted = io_ring_submit(ctx, to_submit); mutex_unlock(&ctx->uring_lock); } if (flags & IORING_ENTER_GETEVENTS) { @@ -3630,7 +3684,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } } - io_ring_drop_ctx_refs(ctx, 1); + percpu_ref_put(&ctx->refs); out_fput: fdput(f); return submitted ? submitted : ret; diff --git a/fs/libfs.c b/fs/libfs.c index c9b2850c0f7c..1463b038ffc4 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -89,58 +89,45 @@ int dcache_dir_close(struct inode *inode, struct file *file) EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ -static struct dentry *next_positive(struct dentry *parent, - struct list_head *from, - int count) +/* + * Returns an element of siblings' list. + * We are looking for <count>th positive after <p>; if + * found, dentry is grabbed and returned to caller. + * If no such element exists, NULL is returned. + */ +static struct dentry *scan_positives(struct dentry *cursor, + struct list_head *p, + loff_t count, + struct dentry *last) { - unsigned *seq = &parent->d_inode->i_dir_seq, n; - struct dentry *res; - struct list_head *p; - bool skipped; - int i; + struct dentry *dentry = cursor->d_parent, *found = NULL; -retry: - i = count; - skipped = false; - n = smp_load_acquire(seq) & ~1; - res = NULL; - rcu_read_lock(); - for (p = from->next; p != &parent->d_subdirs; p = p->next) { + spin_lock(&dentry->d_lock); + while ((p = p->next) != &dentry->d_subdirs) { struct dentry *d = list_entry(p, struct dentry, d_child); - if (!simple_positive(d)) { - skipped = true; - } else if (!--i) { - res = d; - break; + // we must at least skip cursors, to avoid livelocks + if (d->d_flags & DCACHE_DENTRY_CURSOR) + continue; + if (simple_positive(d) && !--count) { + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(d)) + found = dget_dlock(d); + spin_unlock(&d->d_lock); + if (likely(found)) + break; + count = 1; + } + if (need_resched()) { + list_move(&cursor->d_child, p); + p = &cursor->d_child; + spin_unlock(&dentry->d_lock); + cond_resched(); + spin_lock(&dentry->d_lock); } } - rcu_read_unlock(); - if (skipped) { - smp_rmb(); - if (unlikely(*seq != n)) - goto retry; - } - return res; -} - -static void move_cursor(struct dentry *cursor, struct list_head *after) -{ - struct dentry *parent = cursor->d_parent; - unsigned n, *seq = &parent->d_inode->i_dir_seq; - spin_lock(&parent->d_lock); - for (;;) { - n = *seq; - if (!(n & 1) && cmpxchg(seq, n, n + 1) == n) - break; - cpu_relax(); - } - __list_del(cursor->d_child.prev, cursor->d_child.next); - if (after) - list_add(&cursor->d_child, after); - else - list_add_tail(&cursor->d_child, &parent->d_subdirs); - smp_store_release(seq, n + 2); - spin_unlock(&parent->d_lock); + spin_unlock(&dentry->d_lock); + dput(last); + return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) @@ -158,17 +145,25 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) return -EINVAL; } if (offset != file->f_pos) { + struct dentry *cursor = file->private_data; + struct dentry *to = NULL; + + inode_lock_shared(dentry->d_inode); + + if (offset > 2) + to = scan_positives(cursor, &dentry->d_subdirs, + offset - 2, NULL); + spin_lock(&dentry->d_lock); + if (to) + list_move(&cursor->d_child, &to->d_child); + else + list_del_init(&cursor->d_child); + spin_unlock(&dentry->d_lock); + dput(to); + file->f_pos = offset; - if (file->f_pos >= 2) { - struct dentry *cursor = file->private_data; - struct dentry *to; - loff_t n = file->f_pos - 2; - - inode_lock_shared(dentry->d_inode); - to = next_positive(dentry, &dentry->d_subdirs, n); - move_cursor(cursor, to ? &to->d_child : NULL); - inode_unlock_shared(dentry->d_inode); - } + + inode_unlock_shared(dentry->d_inode); } return offset; } @@ -190,25 +185,35 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p = &cursor->d_child; - struct dentry *next; - bool moved = false; + struct list_head *anchor = &dentry->d_subdirs; + struct dentry *next = NULL; + struct list_head *p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) - p = &dentry->d_subdirs; - while ((next = next_positive(dentry, p, 1)) != NULL) { + p = anchor; + else if (!list_empty(&cursor->d_child)) + p = &cursor->d_child; + else + return 0; + + while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, dt_type(d_inode(next)))) break; - moved = true; - p = &next->d_child; ctx->pos++; + p = &next->d_child; } - if (moved) - move_cursor(cursor, p); + spin_lock(&dentry->d_lock); + if (next) + list_move_tail(&cursor->d_child, &next->d_child); + else + list_del_init(&cursor->d_child); + spin_unlock(&dentry->d_lock); + dput(next); + return 0; } EXPORT_SYMBOL(dcache_readdir); @@ -468,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes - * @available: See .write_end of address_space_operations - * @file: " + * @file: See .write_end of address_space_operations * @mapping: " * @pos: " * @len: " diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 222d7115db71..040a50fd9bf3 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -64,13 +64,6 @@ static struct kmem_cache *nfs_direct_cachep; -/* - * This represents a set of asynchronous requests that we're waiting on - */ -struct nfs_direct_mirror { - ssize_t count; -}; - struct nfs_direct_req { struct kref kref; /* release manager */ @@ -84,9 +77,6 @@ struct nfs_direct_req { atomic_t io_count; /* i/os we're waiting for */ spinlock_t lock; /* protect completion state */ - struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX]; - int mirror_count; - loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ @@ -123,32 +113,42 @@ static inline int put_dreq(struct nfs_direct_req *dreq) } static void -nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) +nfs_direct_handle_truncated(struct nfs_direct_req *dreq, + const struct nfs_pgio_header *hdr, + ssize_t dreq_len) { - int i; - ssize_t count; + if (!(test_bit(NFS_IOHDR_ERROR, &hdr->flags) || + test_bit(NFS_IOHDR_EOF, &hdr->flags))) + return; + if (dreq->max_count >= dreq_len) { + dreq->max_count = dreq_len; + if (dreq->count > dreq_len) + dreq->count = dreq_len; + + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) + dreq->error = hdr->error; + else /* Clear outstanding error if this is EOF */ + dreq->error = 0; + } +} - WARN_ON_ONCE(dreq->count >= dreq->max_count); +static void +nfs_direct_count_bytes(struct nfs_direct_req *dreq, + const struct nfs_pgio_header *hdr) +{ + loff_t hdr_end = hdr->io_start + hdr->good_bytes; + ssize_t dreq_len = 0; - if (dreq->mirror_count == 1) { - dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes; - dreq->count += hdr->good_bytes; - } else { - /* mirrored writes */ - count = dreq->mirrors[hdr->pgio_mirror_idx].count; - if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) { - count = hdr->io_start + hdr->good_bytes - dreq->io_start; - dreq->mirrors[hdr->pgio_mirror_idx].count = count; - } - /* update the dreq->count by finding the minimum agreed count from all - * mirrors */ - count = dreq->mirrors[0].count; + if (hdr_end > dreq->io_start) + dreq_len = hdr_end - dreq->io_start; - for (i = 1; i < dreq->mirror_count; i++) - count = min(count, dreq->mirrors[i].count); + nfs_direct_handle_truncated(dreq, hdr, dreq_len); - dreq->count = count; - } + if (dreq_len > dreq->max_count) + dreq_len = dreq->max_count; + + if (dreq->count < dreq_len) + dreq->count = dreq_len; } /* @@ -293,18 +293,6 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, cinfo->completion_ops = &nfs_direct_commit_completion_ops; } -static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq, - struct nfs_pageio_descriptor *pgio, - struct nfs_page *req) -{ - int mirror_count = 1; - - if (pgio->pg_ops->pg_get_mirror_count) - mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); - - dreq->mirror_count = mirror_count; -} - static inline struct nfs_direct_req *nfs_direct_req_alloc(void) { struct nfs_direct_req *dreq; @@ -319,7 +307,6 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void) INIT_LIST_HEAD(&dreq->mds_cinfo.list); dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */ INIT_WORK(&dreq->work, nfs_direct_write_schedule_work); - dreq->mirror_count = 1; spin_lock_init(&dreq->lock); return dreq; @@ -402,20 +389,12 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) struct nfs_direct_req *dreq = hdr->dreq; spin_lock(&dreq->lock); - if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) - dreq->error = hdr->error; - if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) { spin_unlock(&dreq->lock); goto out_put; } - if (hdr->good_bytes != 0) - nfs_direct_good_bytes(dreq, hdr); - - if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) - dreq->error = 0; - + nfs_direct_count_bytes(dreq, hdr); spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { @@ -646,29 +625,22 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) LIST_HEAD(reqs); struct nfs_commit_info cinfo; LIST_HEAD(failed); - int i; nfs_init_cinfo_from_dreq(&cinfo, dreq); nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); dreq->count = 0; + dreq->max_count = 0; + list_for_each_entry(req, &reqs, wb_list) + dreq->max_count += req->wb_bytes; dreq->verf.committed = NFS_INVALID_STABLE_HOW; nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo); - for (i = 0; i < dreq->mirror_count; i++) - dreq->mirrors[i].count = 0; get_dreq(dreq); nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; - req = nfs_list_entry(reqs.next); - nfs_direct_setup_mirroring(dreq, &desc, req); - if (desc.pg_error < 0) { - list_splice_init(&reqs, &failed); - goto out_failed; - } - list_for_each_entry_safe(req, tmp, &reqs, wb_list) { /* Bump the transmission count */ req->wb_nio++; @@ -686,7 +658,6 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) } nfs_pageio_complete(&desc); -out_failed: while (!list_empty(&failed)) { req = nfs_list_entry(failed.next); nfs_list_remove_request(req); @@ -791,17 +762,13 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) nfs_init_cinfo_from_dreq(&cinfo, dreq); spin_lock(&dreq->lock); - - if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) - dreq->error = hdr->error; - if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) { spin_unlock(&dreq->lock); goto out_put; } + nfs_direct_count_bytes(dreq, hdr); if (hdr->good_bytes != 0) { - nfs_direct_good_bytes(dreq, hdr); if (nfs_write_need_commit(hdr)) { if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) request_commit = true; @@ -923,7 +890,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, break; } - nfs_direct_setup_mirroring(dreq, &desc, req); if (desc.pg_error < 0) { nfs_free_request(req); result = desc.pg_error; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 11eafcfc490b..ab8ca20fd579 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6106,6 +6106,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, status = nfs4_call_sync_custom(&task_setup_data); if (setclientid.sc_cred) { + kfree(clp->cl_acceptor); clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred); put_rpccred(setclientid.sc_cred); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 85ca49549b39..52cab65f91cf 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -786,7 +786,6 @@ static void nfs_inode_remove_request(struct nfs_page *req) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *head; - atomic_long_dec(&nfsi->nrequests); if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { head = req->wb_head; @@ -799,8 +798,10 @@ static void nfs_inode_remove_request(struct nfs_page *req) spin_unlock(&mapping->private_lock); } - if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) + if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { nfs_release_request(req); + atomic_long_dec(&nfsi->nrequests); + } } static void diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 8de1c9d644f6..9cd0a6815933 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2049,7 +2049,8 @@ out_write_size: inode->i_mtime = inode->i_ctime = current_time(inode); di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); - ocfs2_update_inode_fsync_trans(handle, inode, 1); + if (handle) + ocfs2_update_inode_fsync_trans(handle, inode, 1); } if (handle) ocfs2_journal_dirty(handle, wc->w_di_bh); @@ -2146,13 +2147,30 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct ocfs2_dio_write_ctxt *dwc = NULL; struct buffer_head *di_bh = NULL; u64 p_blkno; - loff_t pos = iblock << inode->i_sb->s_blocksize_bits; + unsigned int i_blkbits = inode->i_sb->s_blocksize_bits; + loff_t pos = iblock << i_blkbits; + sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits; unsigned len, total_len = bh_result->b_size; int ret = 0, first_get_block = 0; len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); len = min(total_len, len); + /* + * bh_result->b_size is count in get_more_blocks according to write + * "pos" and "end", we need map twice to return different buffer state: + * 1. area in file size, not set NEW; + * 2. area out file size, set NEW. + * + * iblock endblk + * |--------|---------|---------|--------- + * |<-------area in file------->| + */ + + if ((iblock <= endblk) && + ((iblock + ((len - 1) >> i_blkbits)) > endblk)) + len = (endblk - iblock + 1) << i_blkbits; + mlog(0, "get block of %lu at %llu:%u req %u\n", inode->i_ino, pos, len, total_len); @@ -2236,6 +2254,9 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, if (desc->c_needs_zero) set_buffer_new(bh_result); + if (iblock > endblk) + set_buffer_new(bh_result); + /* May sleep in end_io. It should not happen in a irq context. So defer * it to dio work queue. */ set_buffer_defer_completion(bh_result); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2e982db3e1ae..53939bf9d7d2 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1230,6 +1230,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid)); if (IS_ERR(transfer_to[USRQUOTA])) { status = PTR_ERR(transfer_to[USRQUOTA]); + transfer_to[USRQUOTA] = NULL; goto bail_unlock; } } @@ -1239,6 +1240,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid)); if (IS_ERR(transfer_to[GRPQUOTA])) { status = PTR_ERR(transfer_to[GRPQUOTA]); + transfer_to[GRPQUOTA] = NULL; goto bail_unlock; } } diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index d6f7b299eb23..efeea208fdeb 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -283,7 +283,7 @@ static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb, if (inode_alloc) inode_lock(inode_alloc); - if (o2info_coherent(&fi->ifi_req)) { + if (inode_alloc && o2info_coherent(&fi->ifi_req)) { status = ocfs2_inode_lock(inode_alloc, &bh, 0); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 930e3d388579..699a560efbb0 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -217,7 +217,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb) /* At this point, we know that no more recovery threads can be * launched, so wait for any recovery completion work to * complete. */ - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); /* * Now that recovery is shut down, and the osb is about to be diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 158e5af767fd..720e9f94957e 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -377,7 +377,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 90c830e3758e..d8507972ee13 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1490,18 +1490,6 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc, return loc->xl_ops->xlo_check_space(loc, xi); } -static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash) -{ - loc->xl_ops->xlo_add_entry(loc, name_hash); - loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash); - /* - * We can't leave the new entry's xe_name_offset at zero or - * add_namevalue() will go nuts. We set it to the size of our - * storage so that it can never be less than any other entry. - */ - loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size); -} - static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc, struct ocfs2_xattr_info *xi) { @@ -2133,29 +2121,31 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc, if (rc) goto out; - if (loc->xl_entry) { - if (ocfs2_xa_can_reuse_entry(loc, xi)) { - orig_value_size = loc->xl_entry->xe_value_size; - rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); - if (rc) - goto out; - goto alloc_value; - } + if (!loc->xl_entry) { + rc = -EINVAL; + goto out; + } - if (!ocfs2_xattr_is_local(loc->xl_entry)) { - orig_clusters = ocfs2_xa_value_clusters(loc); - rc = ocfs2_xa_value_truncate(loc, 0, ctxt); - if (rc) { - mlog_errno(rc); - ocfs2_xa_cleanup_value_truncate(loc, - "overwriting", - orig_clusters); - goto out; - } + if (ocfs2_xa_can_reuse_entry(loc, xi)) { + orig_value_size = loc->xl_entry->xe_value_size; + rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); + if (rc) + goto out; + goto alloc_value; + } + + if (!ocfs2_xattr_is_local(loc->xl_entry)) { + orig_clusters = ocfs2_xa_value_clusters(loc); + rc = ocfs2_xa_value_truncate(loc, 0, ctxt); + if (rc) { + mlog_errno(rc); + ocfs2_xa_cleanup_value_truncate(loc, + "overwriting", + orig_clusters); + goto out; } - ocfs2_xa_wipe_namevalue(loc); - } else - ocfs2_xa_add_entry(loc, name_hash); + } + ocfs2_xa_wipe_namevalue(loc); /* * If we get here, we have a blank entry. Fill it. We grow our diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index ac9247371871..8c1f1bb1a5ce 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -132,9 +132,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); - show_val_kb(m, "FileHugePages: ", + show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR); - show_val_kb(m, "FilePmdMapped: ", + show_val_kb(m, "FilePmdMapped: ", global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); #endif diff --git a/fs/proc/page.c b/fs/proc/page.c index 544d1ee15aee..7c952ee732e6 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); + if (!ppage || PageSlab(ppage) || page_has_type(ppage)) pcount = 0; else @@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (put_user(stable_page_flags(ppage), out)) { ret = -EFAULT; @@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (ppage) ino = page_cgroup_ino(ppage); diff --git a/fs/readdir.c b/fs/readdir.c index 19bea591c3f1..d26d5ea4de7b 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -27,53 +27,13 @@ /* * Note the "unsafe_put_user() semantics: we goto a * label for errors. - * - * Also note how we use a "while()" loop here, even though - * only the biggest size needs to loop. The compiler (well, - * at least gcc) is smart enough to turn the smaller sizes - * into just if-statements, and this way we don't need to - * care whether 'u64' or 'u32' is the biggest size. - */ -#define unsafe_copy_loop(dst, src, len, type, label) \ - while (len >= sizeof(type)) { \ - unsafe_put_user(get_unaligned((type *)src), \ - (type __user *)dst, label); \ - dst += sizeof(type); \ - src += sizeof(type); \ - len -= sizeof(type); \ - } - -/* - * We avoid doing 64-bit copies on 32-bit architectures. They - * might be better, but the component names are mostly small, - * and the 64-bit cases can end up being much more complex and - * put much more register pressure on the code, so it's likely - * not worth the pain of unaligned accesses etc. - * - * So limit the copies to "unsigned long" size. I did verify - * that at least the x86-32 case is ok without this limiting, - * but I worry about random other legacy 32-bit cases that - * might not do as well. - */ -#define unsafe_copy_type(dst, src, len, type, label) do { \ - if (sizeof(type) <= sizeof(unsigned long)) \ - unsafe_copy_loop(dst, src, len, type, label); \ -} while (0) - -/* - * Copy the dirent name to user space, and NUL-terminate - * it. This should not be a function call, since we're doing - * the copy inside a "user_access_begin/end()" section. */ #define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \ char __user *dst = (_dst); \ const char *src = (_src); \ size_t len = (_len); \ - unsafe_copy_type(dst, src, len, u64, label); \ - unsafe_copy_type(dst, src, len, u32, label); \ - unsafe_copy_type(dst, src, len, u16, label); \ - unsafe_copy_type(dst, src, len, u8, label); \ - unsafe_put_user(0, dst, label); \ + unsafe_put_user(0, dst+len, label); \ + unsafe_copy_to_user(dst, src, len, label); \ } while (0) @@ -145,9 +105,9 @@ EXPORT_SYMBOL(iterate_dir); */ static int verify_dirent_name(const char *name, int len) { - if (WARN_ON_ONCE(!len)) + if (!len) return -EIO; - if (WARN_ON_ONCE(memchr(name, '/', len))) + if (memchr(name, '/', len)) return -EIO; return 0; } diff --git a/fs/super.c b/fs/super.c index f627b7c53d2b..cfadab2cbf35 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1300,6 +1300,7 @@ int get_tree_bdev(struct fs_context *fc, mutex_lock(&bdev->bd_fsfreeze_mutex); if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); + blkdev_put(bdev, mode); warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); return -EBUSY; } @@ -1308,8 +1309,10 @@ int get_tree_bdev(struct fs_context *fc, fc->sget_key = bdev; s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc); mutex_unlock(&bdev->bd_fsfreeze_mutex); - if (IS_ERR(s)) + if (IS_ERR(s)) { + blkdev_put(bdev, mode); return PTR_ERR(s); + } if (s->s_root) { /* Don't summarily change the RO/RW state. */ diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 9fc14e38927f..0caa151cae4e 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -16,11 +16,11 @@ #include <linux/namei.h> #include <linux/tracefs.h> #include <linux/fsnotify.h> +#include <linux/security.h> #include <linux/seq_file.h> #include <linux/parser.h> #include <linux/magic.h> #include <linux/slab.h> -#include <linux/security.h> #define TRACEFS_DEFAULT_MODE 0700 @@ -28,25 +28,6 @@ static struct vfsmount *tracefs_mount; static int tracefs_mount_count; static bool tracefs_registered; -static int default_open_file(struct inode *inode, struct file *filp) -{ - struct dentry *dentry = filp->f_path.dentry; - struct file_operations *real_fops; - int ret; - - if (!dentry) - return -EINVAL; - - ret = security_locked_down(LOCKDOWN_TRACEFS); - if (ret) - return ret; - - real_fops = dentry->d_fsdata; - if (!real_fops->open) - return 0; - return real_fops->open(inode, filp); -} - static ssize_t default_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -241,12 +222,6 @@ static int tracefs_apply_options(struct super_block *sb) return 0; } -static void tracefs_destroy_inode(struct inode *inode) -{ - if (S_ISREG(inode->i_mode)) - kfree(inode->i_fop); -} - static int tracefs_remount(struct super_block *sb, int *flags, char *data) { int err; @@ -283,7 +258,6 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root) static const struct super_operations tracefs_super_operations = { .statfs = simple_statfs, .remount_fs = tracefs_remount, - .destroy_inode = tracefs_destroy_inode, .show_options = tracefs_show_options, }; @@ -414,10 +388,12 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { - struct file_operations *proxy_fops; struct dentry *dentry; struct inode *inode; + if (security_locked_down(LOCKDOWN_TRACEFS)) + return NULL; + if (!(mode & S_IFMT)) mode |= S_IFREG; BUG_ON(!S_ISREG(mode)); @@ -430,20 +406,8 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, if (unlikely(!inode)) return failed_creating(dentry); - proxy_fops = kzalloc(sizeof(struct file_operations), GFP_KERNEL); - if (unlikely(!proxy_fops)) { - iput(inode); - return failed_creating(dentry); - } - - if (!fops) - fops = &tracefs_file_operations; - - dentry->d_fsdata = (void *)fops; - memcpy(proxy_fops, fops, sizeof(*proxy_fops)); - proxy_fops->open = default_open_file; inode->i_mode = mode; - inode->i_fop = proxy_fops; + inode->i_fop = fops ? fops : &tracefs_file_operations; inode->i_private = data; d_instantiate(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 5de296b34ab1..14fbdf22b7e7 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -28,12 +28,11 @@ xfs_get_aghdr_buf( struct xfs_mount *mp, xfs_daddr_t blkno, size_t numblks, - int flags, const struct xfs_buf_ops *ops) { struct xfs_buf *bp; - bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags); + bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0); if (!bp) return NULL; @@ -345,7 +344,7 @@ xfs_ag_init_hdr( { struct xfs_buf *bp; - bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, 0, ops); + bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, ops); if (!bp) return -ENOMEM; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index b9f019603d0b..f0089e862216 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -826,32 +826,17 @@ xfs_attr_shortform_to_leaf( sf = (xfs_attr_shortform_t *)tmpbuffer; xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); - xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK); + xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK); bp = NULL; error = xfs_da_grow_inode(args, &blkno); - if (error) { - /* - * If we hit an IO error middle of the transaction inside - * grow_inode(), we may have inconsistent data. Bail out. - */ - if (error == -EIO) - goto out; - xfs_idata_realloc(dp, size, XFS_ATTR_FORK); /* try to put */ - memcpy(ifp->if_u1.if_data, tmpbuffer, size); /* it back */ + if (error) goto out; - } ASSERT(blkno == 0); error = xfs_attr3_leaf_create(args, blkno, &bp); - if (error) { - /* xfs_attr3_leaf_create may not have instantiated a block */ - if (bp && (xfs_da_shrink_inode(args, 0, bp) != 0)) - goto out; - xfs_idata_realloc(dp, size, XFS_ATTR_FORK); /* try to put */ - memcpy(ifp->if_u1.if_data, tmpbuffer, size); /* it back */ + if (error) goto out; - } memset((char *)&nargs, 0, sizeof(nargs)); nargs.dp = dp; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 4edc25a2ba80..02469d59c787 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -792,6 +792,7 @@ out_root_realloc: */ void xfs_bmap_local_to_extents_empty( + struct xfs_trans *tp, struct xfs_inode *ip, int whichfork) { @@ -808,6 +809,7 @@ xfs_bmap_local_to_extents_empty( ifp->if_u1.if_root = NULL; ifp->if_height = 0; XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } @@ -840,7 +842,7 @@ xfs_bmap_local_to_extents( ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); if (!ifp->if_bytes) { - xfs_bmap_local_to_extents_empty(ip, whichfork); + xfs_bmap_local_to_extents_empty(tp, ip, whichfork); flags = XFS_ILOG_CORE; goto done; } @@ -887,7 +889,7 @@ xfs_bmap_local_to_extents( /* account for the change in fork size */ xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); - xfs_bmap_local_to_extents_empty(ip, whichfork); + xfs_bmap_local_to_extents_empty(tp, ip, whichfork); flags |= XFS_ILOG_CORE; ifp->if_u1.if_root = NULL; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 5bb446d80542..e2798c6f3a5f 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -182,7 +182,8 @@ void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); int xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version); -void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); +void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp, + struct xfs_inode *ip, int whichfork); void __xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, bool skip_discard); diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index 9595ced393dc..49e4bc39e7bb 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -1096,7 +1096,7 @@ xfs_dir2_sf_to_block( memcpy(sfp, oldsfp, ifp->if_bytes); xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK); - xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK); + xfs_bmap_local_to_extents_empty(tp, dp, XFS_DATA_FORK); dp->i_d.di_size = 0; /* diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 39dd2b908106..e9371a8e0e26 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -366,11 +366,11 @@ struct xfs_bulkstat { uint64_t bs_blocks; /* number of blocks */ uint64_t bs_xflags; /* extended flags */ - uint64_t bs_atime; /* access time, seconds */ - uint64_t bs_mtime; /* modify time, seconds */ + int64_t bs_atime; /* access time, seconds */ + int64_t bs_mtime; /* modify time, seconds */ - uint64_t bs_ctime; /* inode change time, seconds */ - uint64_t bs_btime; /* creation time, seconds */ + int64_t bs_ctime; /* inode change time, seconds */ + int64_t bs_btime; /* creation time, seconds */ uint32_t bs_gen; /* generation count */ uint32_t bs_uid; /* user id */ diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 93b3793bc5b3..0cab11a5d390 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -341,7 +341,6 @@ xchk_refcountbt_rec( xfs_extlen_t len; xfs_nlink_t refcount; bool has_cowflag; - int error = 0; bno = be32_to_cpu(rec->refc.rc_startblock); len = be32_to_cpu(rec->refc.rc_blockcount); @@ -366,7 +365,7 @@ xchk_refcountbt_rec( xchk_refcountbt_xref(bs->sc, bno, len, refcount); - return error; + return 0; } /* Make sure we have as many refc blocks as the rmap says. */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 0910cb75b65d..4f443703065e 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -864,6 +864,7 @@ xfs_alloc_file_space( xfs_filblks_t allocatesize_fsb; xfs_extlen_t extsz, temp; xfs_fileoff_t startoffset_fsb; + xfs_fileoff_t endoffset_fsb; int nimaps; int quota_flag; int rt; @@ -891,7 +892,8 @@ xfs_alloc_file_space( imapp = &imaps[0]; nimaps = 1; startoffset_fsb = XFS_B_TO_FSBT(mp, offset); - allocatesize_fsb = XFS_B_TO_FSB(mp, count); + endoffset_fsb = XFS_B_TO_FSB(mp, offset + count); + allocatesize_fsb = endoffset_fsb - startoffset_fsb; /* * Allocate file space until done or until there is an error diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 21c243622a79..0abba171aa89 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -345,6 +345,15 @@ xfs_buf_allocate_memory( unsigned short page_count, i; xfs_off_t start, end; int error; + xfs_km_flags_t kmflag_mask = 0; + + /* + * assure zeroed buffer for non-read cases. + */ + if (!(flags & XBF_READ)) { + kmflag_mask |= KM_ZERO; + gfp_mask |= __GFP_ZERO; + } /* * for buffers that are contained within a single page, just allocate @@ -354,7 +363,8 @@ xfs_buf_allocate_memory( size = BBTOB(bp->b_length); if (size < PAGE_SIZE) { int align_mask = xfs_buftarg_dma_alignment(bp->b_target); - bp->b_addr = kmem_alloc_io(size, align_mask, KM_NOFS); + bp->b_addr = kmem_alloc_io(size, align_mask, + KM_NOFS | kmflag_mask); if (!bp->b_addr) { /* low memory - use alloc_page loop instead */ goto use_alloc_page; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a2beee9f74da..641d07f30a27 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1443,7 +1443,7 @@ xlog_alloc_log( prev_iclog = iclog; iclog->ic_data = kmem_alloc_io(log->l_iclog_size, align_mask, - KM_MAYFAIL); + KM_MAYFAIL | KM_ZERO); if (!iclog->ic_data) goto out_free_iclog; #ifdef DEBUG diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 508319039dce..c1a514ffff55 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -127,7 +127,7 @@ xlog_alloc_buffer( if (nbblks > 1 && log->l_sectBBsize > 1) nbblks += log->l_sectBBsize; nbblks = round_up(nbblks, log->l_sectBBsize); - return kmem_alloc_io(BBTOB(nbblks), align_mask, KM_MAYFAIL); + return kmem_alloc_io(BBTOB(nbblks), align_mask, KM_MAYFAIL | KM_ZERO); } /* |