diff options
Diffstat (limited to 'fs')
97 files changed, 856 insertions, 529 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 819c75233235..3bc9ce6c575e 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -57,6 +57,8 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq) int err, len; len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); + if (len > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_write_subrequest_terminated(subreq, len ?: err, false); } @@ -80,8 +82,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) if (pos + total >= i_size_read(rreq->inode)) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - if (!err) + if (!err) { subreq->transferred += total; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } netfs_read_subreq_terminated(subreq, err, false); } diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c index a189ff8a5034..c0384201b8fe 100644 --- a/fs/afs/addr_prefs.c +++ b/fs/afs/addr_prefs.c @@ -413,8 +413,10 @@ int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size) do { argc = afs_split_string(&buf, argv, ARRAY_SIZE(argv)); - if (argc < 0) - return argc; + if (argc < 0) { + ret = argc; + goto done; + } if (argc < 2) goto inval; diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b488072aee87..ec3db00bd081 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -10,7 +10,7 @@ #include <linux/in.h> -#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */ +#define AFS_MAXCELLNAME 253 /* Maximum length of a cell name (DNS limited) */ #define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */ #define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */ #define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */ diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index a06296c8827d..b835e25a2c02 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -13,6 +13,7 @@ #define AFS_VL_PORT 7003 /* volume location service port */ #define VL_SERVICE 52 /* RxRPC service ID for the Volume Location service */ #define YFS_VL_SERVICE 2503 /* Service ID for AuriStor upgraded VL service */ +#define YFS_VL_MAXCELLNAME 256 /* Maximum length of a cell name in YFS protocol */ enum AFSVL_Operations { VLGETENTRYBYID = 503, /* AFS Get VLDB entry by ID */ diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 9f36e14f1c2d..f9e76b604f31 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -253,6 +253,7 @@ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; + size_t name_len; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); @@ -264,8 +265,11 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) return 0; } - master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), - NULL, false); + name_len = strlen(cell_name); + if (!name_len || name_len > AFS_MAXCELLNAME) + master = ERR_PTR(-EOPNOTSUPP); + else + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index cac75f89b64a..55dd0fc5aad7 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -697,7 +697,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) return ret; namesz = ntohl(call->tmp); - if (namesz > AFS_MAXCELLNAME) + if (namesz > YFS_VL_MAXCELLNAME) return afs_protocol_error(call, afs_eproto_cellname_len); paddedsz = (namesz + 3) & ~3; call->count = namesz; diff --git a/fs/afs/write.c b/fs/afs/write.c index 34107b55f834..ccb6aa8027c5 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -122,7 +122,7 @@ static void afs_issue_write_worker(struct work_struct *work) if (subreq->debug_index == 3) return netfs_write_subrequest_terminated(subreq, -ENOANO, false); - if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { + if (!subreq->retry_count) { set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); return netfs_write_subrequest_terminated(subreq, -EAGAIN, false); } @@ -149,6 +149,9 @@ static void afs_issue_write_worker(struct work_struct *work) afs_wait_for_operation(op); ret = afs_put_operation(op); switch (ret) { + case 0: + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + break; case -EACCES: case -EPERM: case -ENOKEY: diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index af3db0a7ae4d..7ea6f0b43b95 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -652,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 693dc27ffb89..185985a337b3 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -654,6 +654,8 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, goto error_unlock_cow; } } + + trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); @@ -710,7 +712,6 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; - int ret; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); @@ -751,12 +752,8 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); - ret = btrfs_force_cow_block(trans, root, buf, parent, parent_slot, - cow_ret, search_start, 0, nest); - - trace_btrfs_cow_block(root, buf, *cow_ret); - - return ret; + return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, + cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c70..2c341956a01c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0..3c6f7fecbb9a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 488edca8333a..27b2fe7f735d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9078,9 +9078,9 @@ out: } struct btrfs_encoded_read_private { - wait_queue_head_t wait; + struct completion done; void *uring_ctx; - atomic_t pending; + refcount_t pending_refs; blk_status_t status; }; @@ -9099,14 +9099,14 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio) */ WRITE_ONCE(priv->status, bbio->bio.bi_status); } - if (atomic_dec_and_test(&priv->pending)) { + if (refcount_dec_and_test(&priv->pending_refs)) { int err = blk_status_to_errno(READ_ONCE(priv->status)); if (priv->uring_ctx) { btrfs_uring_read_extent_endio(priv->uring_ctx, err); kfree(priv); } else { - wake_up(&priv->wait); + complete(&priv->done); } } bio_put(&bbio->bio); @@ -9126,8 +9126,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, if (!priv) return -ENOMEM; - init_waitqueue_head(&priv->wait); - atomic_set(&priv->pending, 1); + init_completion(&priv->done); + refcount_set(&priv->pending_refs, 1); priv->status = 0; priv->uring_ctx = uring_ctx; @@ -9140,7 +9140,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE); if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) { - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, @@ -9155,11 +9155,11 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, disk_io_size -= bytes; } while (disk_io_size); - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); if (uring_ctx) { - if (atomic_dec_return(&priv->pending) == 0) { + if (refcount_dec_and_test(&priv->pending_refs)) { ret = blk_status_to_errno(READ_ONCE(priv->status)); btrfs_uring_read_extent_endio(uring_ctx, ret); kfree(priv); @@ -9168,8 +9168,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, return -EIOCBQUEUED; } else { - if (atomic_dec_return(&priv->pending) != 0) - io_wait_event(priv->wait, !atomic_read(&priv->pending)); + if (!refcount_dec_and_test(&priv->pending_refs)) + wait_for_completion_io(&priv->done); /* See btrfs_encoded_read_endio() for ordering. */ ret = blk_status_to_errno(READ_ONCE(priv->status)); kfree(priv); @@ -9799,15 +9799,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; + + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); /* * If the swap file was just created, make sure delalloc is done. If the @@ -9816,22 +9826,32 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; + } + + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; } /* @@ -9846,7 +9866,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9860,7 +9881,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9881,7 +9903,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -9889,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9918,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } + + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9969,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10010,20 +10069,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - start += len; + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + + cond_resched(); } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10036,6 +10098,10 @@ out: btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3af8bb0c8d75..4d9305fa37a8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4878,25 +4878,29 @@ out_fail: return ret; } +struct btrfs_uring_encoded_data { + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov; + struct iov_iter iter; +}; + static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags) { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags); size_t copy_end; - struct btrfs_ioctl_encoded_io_args args = { 0 }; int ret; u64 disk_bytenr, disk_io_size; struct file *file; struct btrfs_inode *inode; struct btrfs_fs_info *fs_info; struct extent_io_tree *io_tree; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; loff_t pos; struct kiocb kiocb; struct extent_state *cached_state = NULL; u64 start, lockend; void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; if (!capable(CAP_SYS_ADMIN)) { ret = -EPERM; @@ -4910,43 +4914,64 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue if (issue_flags & IO_URING_F_COMPAT) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); - if (copy_from_user(&args32, sqe_addr, copy_end)) { - ret = -EFAULT; - goto out_acct; - } - args.iov = compat_ptr(args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags; #else return -ENOTTY; #endif } else { copy_end = copy_end_kernel; - if (copy_from_user(&args, sqe_addr, copy_end)) { - ret = -EFAULT; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; goto out_acct; } - } - if (args.flags != 0) - return -EINVAL; + io_uring_cmd_get_async_data(cmd)->op_data = data; - ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), - &iov, &iter); - if (ret < 0) - goto out_acct; + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; - if (iov_iter_count(&iter) == 0) { - ret = 0; - goto out_free; + if (copy_from_user(&args32, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + + if (data->args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + data->iov = data->iovstack; + ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_free; + } } - pos = args.offset; - ret = rw_verify_area(READ, file, &pos, args.len); + pos = data->args.offset; + ret = rw_verify_area(READ, file, &pos, data->args.len); if (ret < 0) goto out_free; @@ -4959,15 +4984,16 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start = ALIGN_DOWN(pos, fs_info->sectorsize); lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; - ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state, + ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state, &disk_bytenr, &disk_io_size); if (ret < 0 && ret != -EIOCBQUEUED) goto out_free; file_accessed(file); - if (copy_to_user(sqe_addr + copy_end, (const char *)&args + copy_end_kernel, - sizeof(args) - copy_end_kernel)) { + if (copy_to_user(sqe_addr + copy_end, + (const char *)&data->args + copy_end_kernel, + sizeof(data->args) - copy_end_kernel)) { if (ret == -EIOCBQUEUED) { unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); @@ -4977,40 +5003,22 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue } if (ret == -EIOCBQUEUED) { - u64 count; - - /* - * If we've optimized things by storing the iovecs on the stack, - * undo this. - */ - if (!iov) { - iov = kmalloc(sizeof(struct iovec) * args.iovcnt, GFP_NOFS); - if (!iov) { - unlock_extent(io_tree, start, lockend, &cached_state); - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); - ret = -ENOMEM; - goto out_acct; - } - - memcpy(iov, iovstack, sizeof(struct iovec) * args.iovcnt); - } - - count = min_t(u64, iov_iter_count(&iter), disk_io_size); + u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size); /* Match ioctl by not returning past EOF if uncompressed. */ - if (!args.compression) - count = min_t(u64, count, args.len); + if (!data->args.compression) + count = min_t(u64, count, data->args.len); - ret = btrfs_uring_read_extent(&kiocb, &iter, start, lockend, - cached_state, disk_bytenr, - disk_io_size, count, - args.compression, iov, cmd); + ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend, + cached_state, disk_bytenr, disk_io_size, + count, data->args.compression, + data->iov, cmd); goto out_acct; } out_free: - kfree(iov); + kfree(data->iov); out_acct: if (ret > 0) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a6f92836c9b1..f9b214992212 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1121,6 +1121,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -1254,8 +1255,6 @@ out_add_root: spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (simple) - btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index bf267bdfa8f8..db8b42f674b7 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2902,6 +2902,7 @@ static int relocate_one_folio(struct reloc_control *rc, const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags); ASSERT(index <= last_index); +again: folio = filemap_lock_folio(inode->i_mapping, index); if (IS_ERR(folio)) { @@ -2937,6 +2938,11 @@ static int relocate_one_folio(struct reloc_control *rc, ret = -EIO; goto release_folio; } + if (folio->mapping != inode->i_mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } /* diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 204c928beaf9..531312efee8d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1541,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, u64 extent_gen; int ret; + if (unlikely(!extent_root)) { + btrfs_err(fs_info, "no valid extent root for scrub"); + return -EUCLEAN; + } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * stripe->nr_sectors); scrub_stripe_reset_bitmaps(stripe); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7254279c3cc9..498c84323253 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5280,6 +5280,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) unsigned cur_len = min_t(unsigned, len, PAGE_SIZE - pg_offset); +again: folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { page_cache_sync_readahead(mapping, @@ -5312,6 +5313,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) ret = -EIO; break; } + if (folio->mapping != mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } memcpy_from_folio(sctx->send_buf + sctx->send_size, folio, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index fdcbf650ac31..7f09b6c9cc2d 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); + return sysfs_emit(buf, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40e..dfeee033f31f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index ddf0d5a448a7..c9e92c6941ec 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -174,10 +174,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, copy_page(workspace->buf + i * PAGE_SIZE, data_in); start += PAGE_SIZE; - workspace->strm.avail_in = - (in_buf_folios << PAGE_SHIFT); } workspace->strm.next_in = workspace->buf; + workspace->strm.avail_in = min(bytes_left, + in_buf_folios << PAGE_SHIFT); } else { unsigned int pg_off; unsigned int cur_len; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 11ed523e528e..df905ae82929 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -748,8 +748,9 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) (u64)lim->max_segments << PAGE_SHIFT), fs_info->sectorsize); fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; - if (fs_info->max_zone_append_size < fs_info->max_extent_size) - fs_info->max_extent_size = fs_info->max_zone_append_size; + + fs_info->max_extent_size = min_not_zero(fs_info->max_extent_size, + fs_info->max_zone_append_size); /* * Check mount options here, because we might change fs_info->zoned diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 89b11336a836..1806bff8e59b 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -15,6 +15,7 @@ #include <linux/namei.h> #include <linux/poll.h> #include <linux/mount.h> +#include <linux/security.h> #include <linux/statfs.h> #include <linux/ctype.h> #include <linux/string.h> @@ -576,7 +577,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) */ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) { - char *secctx; + int err; _enter(",%s", args); @@ -585,16 +586,16 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) return -EINVAL; } - if (cache->secctx) { + if (cache->have_secid) { pr_err("Second security context specified\n"); return -EINVAL; } - secctx = kstrdup(args, GFP_KERNEL); - if (!secctx) - return -ENOMEM; + err = security_secctx_to_secid(args, strlen(args), &cache->secid); + if (err) + return err; - cache->secctx = secctx; + cache->have_secid = true; return 0; } @@ -820,7 +821,6 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) put_cred(cache->cache_cred); kfree(cache->rootdirname); - kfree(cache->secctx); kfree(cache->tag); _leave(""); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 7b99bd98de75..38c236e38cef 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -122,7 +122,6 @@ struct cachefiles_cache { #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ #define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ - char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ @@ -130,6 +129,8 @@ struct cachefiles_cache { struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; u32 msg_id_next; + u32 secid; /* LSM security id */ + bool have_secid; /* whether "secid" was set */ }; static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index fe777164f1d8..fc6611886b3b 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -18,7 +18,7 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) struct cred *new; int ret; - _enter("{%s}", cache->secctx); + _enter("{%u}", cache->have_secid ? cache->secid : 0); new = prepare_kernel_cred(current); if (!new) { @@ -26,8 +26,8 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) goto error; } - if (cache->secctx) { - ret = set_security_override_from_ctx(new, cache->secctx); + if (cache->have_secid) { + ret = set_security_override(new, cache->secid); if (ret < 0) { put_cred(new); pr_err("Security denies permission to nominate security context: error %d\n", diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4b8d59ebda00..851d70200c6b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, if (ceph_inode_is_shutdown(inode)) return -EIO; - if (!len) + if (!len || !i_size) return 0; /* * flush any page cache pages in this range. this @@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, int num_pages; size_t page_off; bool more; - int idx; + int idx = 0; size_t left; struct ceph_osd_req_op *op; u64 read_off = off; @@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, len = read_off + read_len - off; more = len < iov_iter_count(to); + op = &req->r_ops[0]; + if (sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + num_pages = calc_pages_for(read_off, read_len); page_off = offset_in_page(off); pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); @@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, osd_req_op_extent_osd_data_pages(req, 0, pages, read_len, offset_in_page(read_off), - false, false); - - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } + false, true); ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); @@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, else if (ret == -ENOENT) ret = 0; - if (ret > 0 && IS_ENCRYPTED(inode)) { + if (ret < 0) { + ceph_osdc_put_request(req); + if (ret == -EBLOCKLISTED) + fsc->blocklisted = true; + break; + } + + if (IS_ENCRYPTED(inode)) { int fret; fret = ceph_fscrypt_decrypt_extents(inode, pages, @@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret = min_t(ssize_t, fret, len); } - ceph_osdc_put_request(req); - /* Short read but not EOF? Zero out the remainder. */ - if (ret >= 0 && ret < len && (off + ret < i_size)) { + if (ret < len && (off + ret < i_size)) { int zlen = min(len - ret, i_size - off - ret); int zoff = page_off + ret; @@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret += zlen; } - idx = 0; - if (ret <= 0) - left = 0; - else if (off + ret > i_size) - left = i_size - off; + if (off + ret > i_size) + left = (i_size > off) ? i_size - off : 0; else left = ret; + while (left > 0) { size_t plen, copied; @@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } } - ceph_release_page_vector(pages, num_pages); - if (ret < 0) { - if (ret == -EBLOCKLISTED) - fsc->blocklisted = true; - break; - } + ceph_osdc_put_request(req); if (off >= i_size || !more) break; @@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } + op = &req->r_ops[0]; + if (!write && sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, size); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages); if (len < 0) { ceph_osdc_put_request(req); @@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (len != size) osd_req_op_extent_update(req, 0, len); + osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); + /* * To simplify error handling, allow AIO when IO within i_size * or IO can be satisfied by single OSD request. @@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, req->r_mtime = mtime; } - osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, size); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } - if (aio_req) { aio_req->total_len += len; aio_req->num_reqs++; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 219a2cc2bf3c..785fe489ef4b 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2800,12 +2800,11 @@ retry: if (pos < 0) { /* - * A rename didn't occur, but somehow we didn't end up where - * we thought we would. Throw a warning and try again. + * The path is longer than PATH_MAX and this function + * cannot ever succeed. Creating paths that long is + * possible with Ceph, but Linux cannot use them. */ - pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n", - pos); - goto retry; + return ERR_PTR(-ENAMETOOLONG); } *pbase = base; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index de03cd6eb86e..4344e1f11806 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, switch (token) { case Opt_snapdirname: + if (strlen(param->string) > NAME_MAX) + return invalfc(fc, "snapdirname too long"); kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 1c49f8962021..0cd6b5c4df98 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..33f8539dda4a 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918..686d835eb533 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315e..f5956474bfde 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f147505487..19ef4ff2a134 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1792,9 +1792,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa..0dd65cefce33 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index fe0a9b8a0cd0..3103b932b674 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -122,7 +122,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent type = exfat_get_entry_type(ep); if (type == TYPE_UNUSED) { brelse(bh); - break; + goto out; } if (type != TYPE_FILE && type != TYPE_DIR) { @@ -170,6 +170,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent } } +out: dir_entry->namebuf.lfn[0] = '\0'; *cpos = EXFAT_DEN_TO_B(dentry); return 0; diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 773c320d68f3..9e5492ac409b 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -216,6 +216,16 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain if (err) goto dec_used_clus; + + if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { + /* + * The cluster chain includes a loop, scan the + * bitmap to get the number of used clusters. + */ + exfat_count_used_clusters(sb, &sbi->used_clusters); + + return 0; + } } while (clu != EXFAT_EOF_CLUSTER); } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index fb38769c3e39..05b51e721783 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -545,6 +545,7 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) while (pos < new_valid_size) { u32 len; struct folio *folio; + unsigned long off; len = PAGE_SIZE - (pos & (PAGE_SIZE - 1)); if (pos + len > new_valid_size) @@ -554,6 +555,9 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) if (err) goto out; + off = offset_in_folio(folio, pos); + folio_zero_new_buffers(folio, off, off + len); + err = ops->write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; @@ -563,6 +567,8 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) cond_resched(); } + return 0; + out: return err; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 97d2774760fe..099f80645072 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -330,8 +330,8 @@ static int exfat_find_empty_entry(struct inode *inode, while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir, num_entries, es)) < 0) { - if (dentry == -EIO) - break; + if (dentry != -ENOSPC) + return dentry; if (exfat_check_max_dentries(inode)) return -ENOSPC; diff --git a/fs/file.c b/fs/file.c index fb1011cf6b4a..25c6e53b03f8 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,7 @@ #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> +#include <linux/init_task.h> #include "internal.h" diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 494ac372ace0..e540d05549ff 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1681,6 +1681,8 @@ static int fuse_dir_open(struct inode *inode, struct file *file) */ if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE)) nonseekable_open(inode, file); + if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 88d0946b5bc9..7d92a5479998 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1541,8 +1541,10 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, */ struct page **pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (nbytes < *nbytesp && nr_pages < max_pages) { unsigned nfolios, i; @@ -1557,18 +1559,22 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, nbytes += ret; - ret += start; - /* Currently, all folios in FUSE are one page */ - nfolios = DIV_ROUND_UP(ret, PAGE_SIZE); + nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE); + + for (i = 0; i < nfolios; i++) { + struct folio *folio = page_folio(pages[i]); + unsigned int offset = start + + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT); + unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start); - ap->descs[ap->num_folios].offset = start; - fuse_folio_descs_length_init(ap->descs, ap->num_folios, nfolios); - for (i = 0; i < nfolios; i++) - ap->folios[i + ap->num_folios] = page_folio(pages[i]); + ap->descs[ap->num_folios].offset = offset; + ap->descs[ap->num_folios].length = len; + ap->folios[ap->num_folios] = folio; + start = 0; + ret -= len; + ap->num_folios++; + } - ap->num_folios += nfolios; - ap->descs[ap->num_folios - 1].length -= - (PAGE_SIZE - ret) & (PAGE_SIZE - 1); nr_pages += nfolios; } kfree(pages); @@ -1584,6 +1590,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, else ap->args.out_pages = true; +out: *nbytesp = nbytes; return ret < 0 ? ret : 0; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 3bee9b5dba5e..fe09c2093a93 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -349,11 +349,13 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc) goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { - if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { + if (fd.entrylength != sizeof(rec.dir)) { res = -EIO; goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); + if (rec.type != HFS_CDR_DIR) + res = -EIO; } if (res) goto bail_hfs_find; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 90f883d6b8fd..fc1ae5132127 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -825,7 +825,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, error = PTR_ERR(folio); goto out; } - folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size)); + folio_zero_user(folio, addr); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 955f19e27e47..d303e6c8900c 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1138,7 +1138,7 @@ static void iomap_write_delalloc_scan(struct inode *inode, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_next_index(folio) << PAGE_SHIFT; + start_byte = folio_pos(folio) + folio_size(folio); folio_unlock(folio); folio_put(folio); } @@ -1774,7 +1774,8 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos) */ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, loff_t pos, unsigned len) + struct inode *inode, loff_t pos, loff_t end_pos, + unsigned len) { struct iomap_folio_state *ifs = folio->private; size_t poff = offset_in_folio(folio, pos); @@ -1793,15 +1794,60 @@ new_ioend: if (ifs) atomic_add(len, &ifs->write_bytes_pending); + + /* + * Clamp io_offset and io_size to the incore EOF so that ondisk + * file size updates in the ioend completion are byte-accurate. + * This avoids recovering files with zeroed tail regions when + * writeback races with appending writes: + * + * Thread 1: Thread 2: + * ------------ ----------- + * write [A, A+B] + * update inode size to A+B + * submit I/O [A, A+BS] + * write [A+B, A+B+C] + * update inode size to A+B+C + * <I/O completes, updates disk size to min(A+B+C, A+BS)> + * <power failure> + * + * After reboot: + * 1) with A+B+C < A+BS, the file has zero padding in range + * [A+B, A+B+C] + * + * |< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000| + * ^ ^ ^ + * A A+B A+B+C + * (EOF) + * + * 2) with A+B+C > A+BS, the file has zero padding in range + * [A+B, A+BS] + * + * |< Block Size (BS) >|< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000|00000000000000000000000000| + * ^ ^ ^ ^ + * A A+B A+BS A+B+C + * (EOF) + * + * D = Valid Data + * 0 = Zero Padding + * + * Note that this defeats the ability to chain the ioends of + * appending writes. + */ wpc->ioend->io_size += len; + if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) + wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + wbc_account_cgroup_owner(wbc, folio, len); return 0; } static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, u64 pos, unsigned dirty_len, - unsigned *count) + struct inode *inode, u64 pos, u64 end_pos, + unsigned dirty_len, unsigned *count) { int error; @@ -1826,7 +1872,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, break; default: error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos, - map_len); + end_pos, map_len); if (!error) (*count)++; break; @@ -1897,11 +1943,11 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, * remaining memory is zeroed when mapped, and writes to that * region are not written out to the file. * - * Also adjust the writeback range to skip all blocks entirely - * beyond i_size. + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); - *end_pos = round_up(isize, i_blocksize(inode)); + *end_pos = isize; } return true; @@ -1914,6 +1960,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct inode *inode = folio->mapping->host; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; unsigned count = 0; int error = 0; u32 rlen; @@ -1955,9 +2002,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, /* * Walk through the folio to find dirty areas to write back. */ - while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) { + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writepage_map_blocks(wpc, wbc, folio, inode, - pos, rlen, &count); + pos, end_pos, rlen, &count); if (error) break; pos += rlen; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 9153ff3a08e7..e8e80761ac73 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -772,9 +772,9 @@ start_journal_io: /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue - * the commit record + * the commit record and update the journal tail sequence. */ - if (commit_transaction->t_need_data_flush && + if ((commit_transaction->t_need_data_flush || update_tail) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(journal->j_fs_dev); diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 4556e4689024..ce63d5fde9c3 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -654,7 +654,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(descriptor); BUFFER_TRACE(descriptor, "write"); set_buffer_dirty(descriptor); - write_dirty_buffer(descriptor, REQ_SYNC); + write_dirty_buffer(descriptor, JBD2_JOURNAL_REQ_FLAGS); } #endif diff --git a/fs/mount.h b/fs/mount.h index 185fc56afc13..179f690a0c72 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -38,6 +38,7 @@ struct mount { struct dentry *mnt_mountpoint; struct vfsmount mnt; union { + struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; @@ -51,10 +52,7 @@ struct mount { struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ - union { - struct rb_node mnt_node; /* Under ns->mounts */ - struct list_head mnt_list; - }; + struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ @@ -145,11 +143,16 @@ static inline bool is_anon_ns(struct mnt_namespace *ns) return ns->seq == 0; } +static inline bool mnt_ns_attached(const struct mount *mnt) +{ + return !RB_EMPTY_NODE(&mnt->mnt_node); +} + static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { - WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); - mnt->mnt.mnt_flags &= ~MNT_ONRB; + WARN_ON(!mnt_ns_attached(mnt)); rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); + RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } diff --git a/fs/namespace.c b/fs/namespace.c index 23e81c2a1e3f..eac057e56948 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -344,6 +344,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + RB_CLEAR_NODE(&mnt->mnt_node); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; @@ -1124,7 +1125,7 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; - WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); + WARN_ON(mnt_ns_attached(mnt)); mnt->mnt_ns = ns; while (*link) { parent = *link; @@ -1135,7 +1136,6 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) } rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); - mnt->mnt.mnt_flags |= MNT_ONRB; } /* @@ -1305,7 +1305,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags; - mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); + mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); @@ -1763,7 +1763,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; - if (p->mnt.mnt_flags & MNT_ONRB) + if (mnt_ns_attached(p)) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); @@ -1912,16 +1912,14 @@ static int do_umount(struct mount *mnt, int flags) event++; if (flags & MNT_DETACH) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } @@ -2055,9 +2053,15 @@ SYSCALL_DEFINE1(oldumount, char __user *, name) static bool is_mnt_ns_file(struct dentry *dentry) { + struct ns_common *ns; + /* Is this a proxy for a mount namespace? */ - return dentry->d_op == &ns_dentry_operations && - dentry->d_fsdata == &mntns_operations; + if (dentry->d_op != &ns_dentry_operations) + return false; + + ns = d_inode(dentry)->i_private; + + return ns->ops == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7ac34550c403..4dc9b8286355 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -275,22 +275,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); - if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, - netfs_sreq_trace_put_cancel); - break; - } + if (ret < 0) + goto prep_failed; trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); } slice = netfs_prepare_read_iterator(subreq); - if (slice < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); - ret = slice; - break; - } + if (slice < 0) + goto prep_iter_failed; rreq->netfs_ops->issue_read(subreq); goto done; @@ -302,6 +294,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_stat(&netfs_n_rh_zero); slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) + goto prep_iter_failed; __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_read_subreq_terminated(subreq, 0, false); goto done; @@ -310,6 +304,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) if (source == NETFS_READ_FROM_CACHE) { trace_netfs_sreq(subreq, netfs_sreq_trace_submit); slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) + goto prep_iter_failed; netfs_read_cache_to_pagecache(rreq, subreq); goto done; } @@ -318,6 +314,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) WARN_ON_ONCE(1); break; + prep_iter_failed: + ret = slice; + prep_failed: + subreq->error = ret; + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + done: size -= slice; start += slice; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 88f2adfab75e..f9421f3e6d37 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -67,7 +67,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * * allocate a sufficiently large bvec array and may shorten the * request. */ - if (async || user_backed_iter(iter)) { + if (user_backed_iter(iter)) { n = netfs_extract_user_iter(iter, len, &wreq->iter, 0); if (n < 0) { ret = n; @@ -77,6 +77,11 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * wreq->direct_bv_count = n; wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); } else { + /* If this is a kernel-generated async DIO request, + * assume that any resources the iterator points to + * (eg. a bio_vec array) will persist till the end of + * the op. + */ wreq->iter = *iter; } @@ -104,7 +109,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - smp_rmb(); /* Read error/transferred after RIP flag */ ret = wreq->error; if (ret == 0) { ret = wreq->transferred; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3cbb289535a8..e8624f5c7fcc 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -62,10 +62,14 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } else { trace_netfs_folio(folio, netfs_folio_trace_read_done); } + + folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + else + folioq_clear(folioq, slot); } if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { @@ -77,8 +81,6 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, folio_unlock(folio); } } - - folioq_clear(folioq, slot); } /* @@ -247,16 +249,17 @@ donation_changed: /* Deal with the trickiest case: that this subreq is in the middle of a * folio, not touching either edge, but finishes first. In such a - * case, we donate to the previous subreq, if there is one, so that the - * donation is only handled when that completes - and remove this - * subreq from the list. + * case, we donate to the previous subreq, if there is one and if it is + * contiguous, so that the donation is only handled when that completes + * - and remove this subreq from the list. * * If the previous subreq finished first, we will have acquired their * donation and should be able to unlock folios and/or donate nextwards. */ if (!subreq->consumed && !prev_donated && - !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + !list_is_first(&subreq->rreq_link, &rreq->subrequests) && + subreq->start == prev->start + prev->len) { prev = list_prev_entry(subreq, rreq_link); WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); subreq->start += subreq->len; @@ -378,8 +381,7 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq) task_io_account_read(rreq->transferred); trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_done); netfs_clear_subrequests(rreq, false); @@ -438,7 +440,7 @@ void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE)) { netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); } } EXPORT_SYMBOL(netfs_read_subreq_progress); @@ -497,7 +499,7 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE)) { netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); } rreq->transferred += subreq->transferred; } @@ -511,10 +513,13 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, } else { trace_netfs_sreq(subreq, netfs_sreq_trace_short); if (subreq->transferred > subreq->consumed) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + /* If we didn't read new data, abandon retry. */ + if (subreq->retry_count && + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } + } else if (test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); } else { diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index ba5af89d37fa..54d5004fec18 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -170,6 +170,10 @@ void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); + if (!wreq->io_streams[1].avail) { + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + goto couldnt_start; + } for (;;) { error = netfs_pgpriv2_copy_folio(wreq, folio); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 0350592ea804..16b676c68dcd 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -49,13 +49,15 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * up to the first permanently failed one. */ if (!rreq->netfs_ops->prepare_read && - !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { + !rreq->cache_resources.ops) { struct netfs_io_subrequest *subreq; list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; netfs_reset_iter(subreq); netfs_reissue_read(rreq, subreq); } @@ -137,7 +139,8 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) stream0->sreq_max_len = subreq->len; __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; spin_lock_bh(&rreq->lock); list_add_tail(&subreq->rreq_link, &rreq->subrequests); @@ -149,7 +152,8 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) BUG_ON(!len); /* Renegotiate max_len (rsize) */ - if (rreq->netfs_ops->prepare_read(subreq) < 0) { + if (rreq->netfs_ops->prepare_read && + rreq->netfs_ops->prepare_read(subreq) < 0) { trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); __set_bit(NETFS_SREQ_FAILED, &subreq->flags); } @@ -213,7 +217,6 @@ abandon: subreq->error = -ENOMEM; __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); } spin_lock_bh(&rreq->lock); list_splice_tail_init(&queue, &rreq->subrequests); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 1d438be2e1b4..ca3a11ed9b54 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -179,7 +179,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, struct iov_iter source = subreq->io_iter; iov_iter_revert(&source, subreq->len - source.count); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_write(stream, subreq, &source); } @@ -234,7 +233,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, /* Renegotiate max_len (wsize) */ trace_netfs_sreq(subreq, netfs_sreq_trace_retry); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + subreq->retry_count++; stream->prepare_write(subreq); part = min(len, stream->sreq_max_len); @@ -279,7 +278,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq->start = start; subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); subreq->stream_nr = to->stream_nr; - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + subreq->retry_count = 1; trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), @@ -501,8 +500,7 @@ reassess_streams: goto need_retry; if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_unpause); - clear_bit_unlock(NETFS_RREQ_PAUSE, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_PAUSE); + clear_and_wake_up_bit(NETFS_RREQ_PAUSE, &wreq->flags); } if (notes & NEED_REASSESS) { @@ -605,8 +603,7 @@ void netfs_write_collection_worker(struct work_struct *work) _debug("finished"); trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags); if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); @@ -714,8 +711,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - wake_up_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); /* If we are at the head of the queue, wake up the collector, * transferring a ref to it if we were the ones to do so. diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index bf6d507578e5..ff0e82505a0b 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -244,6 +244,8 @@ void netfs_reissue_write(struct netfs_io_stream *stream, iov_iter_advance(source, size); iov_iter_truncate(&subreq->io_iter, size); + subreq->retry_count++; + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_do_issue_write(stream, subreq); } diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 810269ee0a50..d49e4ce27999 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -263,6 +263,12 @@ int nfs_netfs_readahead(struct readahead_control *ractl) static atomic_t nfs_netfs_debug_id; static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { + if (!file) { + if (WARN_ON_ONCE(rreq->origin != NETFS_PGPRIV2_COPY_TO_CACHE)) + return -EIO; + return 0; + } + rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ @@ -274,7 +280,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi static void nfs_netfs_free_request(struct netfs_io_request *rreq) { - put_nfs_open_context(rreq->netfs_priv); + if (rreq->netfs_priv) + put_nfs_open_context(rreq->netfs_priv); } static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0d16b383a452..5f582713bf05 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1308,7 +1308,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, enum pnfs_iomode *iomode) { /* Serialise LAYOUTGET/LAYOUTRETURN */ - if (atomic_read(&lo->plh_outstanding) != 0) + if (atomic_read(&lo->plh_outstanding) != 0 && lo->plh_return_seq == 0) return false; if (test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) return false; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ae5c5e39afa0..aeb715b4a690 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -73,6 +73,7 @@ #include "nfs.h" #include "netns.h" #include "sysfs.h" +#include "nfs4idmap.h" #define NFSDBG_FACILITY NFSDBG_VFS diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index eacafe46e3b6..aa4712362b3b 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -40,24 +40,15 @@ #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put_work(struct work_struct *work) +static void expkey_put(struct kref *ref) { - struct svc_expkey *key = - container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work); + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree(key); -} - -static void expkey_put(struct kref *ref) -{ - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); - - INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work); - queue_rcu_work(system_wq, &key->ek_rcu_work); + kfree_rcu(key, ek_rcu); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -364,26 +355,16 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_put_work(struct work_struct *work) +static void svc_export_put(struct kref *ref) { - struct svc_export *exp = - container_of(to_rcu_work(work), struct svc_export, ex_rcu_work); - + struct svc_export *exp = container_of(ref, struct svc_export, h.ref); path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); kfree(exp->ex_uuid); - kfree(exp); -} - -static void svc_export_put(struct kref *ref) -{ - struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - - INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work); - queue_rcu_work(system_wq, &exp->ex_rcu_work); + kfree_rcu(exp, ex_rcu); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 6f2fbaae01fa..4d92b99c1ffd 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -75,7 +75,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_work ex_rcu_work; + struct rcu_head ex_rcu; unsigned long ex_xprtsec_modes; struct export_stats *ex_stats; }; @@ -92,7 +92,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_work ek_rcu_work; + struct rcu_head ek_rcu; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3877b53e429f..c083e539e898 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1100,7 +1100,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -1522,8 +1522,6 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) ses = c->cn_session; } spin_unlock(&clp->cl_lock); - if (!c) - return; err = setup_callback_client(clp, &conn, ses); if (err) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f8a10f90bc7a..ad44ad49274f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1347,7 +1347,6 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; - atomic_dec(©->cp_nn->pending_async_copies); kfree(copy->cp_src); kfree(copy); } @@ -1870,6 +1869,7 @@ do_callback: set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); trace_nfsd_copy_async_done(copy); nfsd4_send_cb_offload(copy); + atomic_dec(©->cp_nn->pending_async_copies); return 0; } @@ -1927,19 +1927,19 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > (int)rqstp->rq_pool->sp_nrthreads) - goto out_err; + goto out_dec_async_copy_err; async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) - goto out_err; + goto out_dec_async_copy_err; if (!nfs4_init_copy_state(nn, copy)) - goto out_err; + goto out_dec_async_copy_err; memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) - goto out_err; + goto out_dec_async_copy_err; spin_lock(&async_copy->cp_clp->async_lock); list_add(&async_copy->copies, &async_copy->cp_clp->async_copies); @@ -1954,6 +1954,9 @@ out: trace_nfsd_copy_done(copy, status); release_copy_files(copy); return status; +out_dec_async_copy_err: + if (async_copy) + atomic_dec(&nn->pending_async_copies); out_err: if (nfsd4_ssc_is_inter(copy)) { /* diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 501ad7be5174..54a3fa0cf67e 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode) ii->i_flags = 0; memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); + btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; } void nilfs_btnode_cache_clear(struct address_space *btnc) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index ace22253fed0..2dbb15767df1 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -163,7 +163,7 @@ int nilfs_init_gcinode(struct inode *inode) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - inode->i_mapping->a_ops = &empty_aops; + inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index cf9ba481ae37..23f3a75edd50 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -276,6 +276,10 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +const struct address_space_operations nilfs_buffer_cache_aops = { + .invalidate_folio = block_invalidate_folio, +}; + static int nilfs_insert_inode_locked(struct inode *inode, struct nilfs_root *root, unsigned long ino) @@ -544,8 +548,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, inode = nilfs_iget_locked(sb, root, ino); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + + if (!(inode->i_state & I_NEW)) { + if (!inode->i_nlink) { + iput(inode); + return ERR_PTR(-ESTALE); + } return inode; + } err = __nilfs_read_inode(sb, root, ino, inode); if (unlikely(err)) { @@ -675,6 +685,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode) NILFS_I(s_inode)->i_flags = 0; memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; err = nilfs_attach_btree_node_cache(s_inode); if (unlikely(err)) { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9b108052d9f7..1d836a5540f3 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + if (inode == ERR_PTR(-ESTALE)) { + nilfs_error(dir->i_sb, + "deleted inode referenced: %lu", ino); + return ERR_PTR(-EIO); + } } return d_splice_alias(inode, dentry); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 45d03826eaf1..dff241c53fc5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; +extern const struct address_space_operations nilfs_buffer_cache_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; extern const struct inode_operations nilfs_symlink_inode_operations; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index dec553034027..e933f9c65d90 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -47,10 +47,8 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); - if ((ret == FILEID_INVALID) || (ret < 0)) { - WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); + if ((ret == FILEID_INVALID) || (ret < 0)) return; - } f->handle_type = ret; f->handle_bytes = size * sizeof(u32); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 8ac42ea81a17..d1aa04a5af1b 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < - left) { - if (bit_off == start) { + while (1) { + bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); + if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; @@ -998,29 +998,12 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, } } + if (bit_off >= left) + break; count = 1; start = bit_off + 1; } - /* clear the contiguous bits until the end boundary */ - if (count) { - blkno = la_start_blk + - ocfs2_clusters_to_blocks(osb->sb, - start - count); - - trace_ocfs2_sync_local_to_main_free( - count, start - count, - (unsigned long long)la_start_blk, - (unsigned long long)blkno); - - status = ocfs2_release_clusters(handle, - main_bm_inode, - main_bm_bh, blkno, - count); - if (status < 0) - mlog_errno(status); - } - bail: if (status) mlog_errno(status); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2b0daced98eb..3404e7a30c33 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -893,7 +893,7 @@ static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid) int status = 0; trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type); - if (!sb_has_quota_loaded(sb, type)) { + if (!sb_has_quota_active(sb, type)) { status = -ESRCH; goto out; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 73d3367c533b..2956d888c131 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -867,6 +867,7 @@ out: brelse(oinfo->dqi_libh); brelse(oinfo->dqi_lqi_bh); kfree(oinfo); + info->dqi_priv = NULL; return status; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 3601ddfeddc2..0c28e5fa3407 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -415,13 +415,13 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, return err; } -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; - uuid_t *uuid = &real->d_sb->s_uuid; + uuid_t *uuid = &realinode->i_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ @@ -438,13 +438,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, * the price or reconnecting the dentry. */ dwords = buflen >> 2; - fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); + fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid, + &dwords, NULL, 0); buflen = (dwords << 2); err = -EIO; - if (WARN_ON(fh_type < 0) || - WARN_ON(buflen > MAX_HANDLE_SZ) || - WARN_ON(fh_type == FILEID_INVALID)) + if (fh_type < 0 || fh_type == FILEID_INVALID || + WARN_ON(buflen > MAX_HANDLE_SZ)) goto out_err; fh->fb.version = OVL_FH_VERSION; @@ -480,7 +480,7 @@ struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) if (!ovl_can_decode_fh(origin->d_sb)) return NULL; - return ovl_encode_real_fh(ofs, origin, false); + return ovl_encode_real_fh(ofs, d_inode(origin), false); } int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, @@ -505,7 +505,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, upper, true); + fh = ovl_encode_real_fh(ofs, d_inode(upper), true); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 5868cb222955..444aeeccb6da 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -176,35 +176,37 @@ static int ovl_connect_layer(struct dentry *dentry) * * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static int ovl_check_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct inode *inode) { - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); bool decodable = ofs->config.nfs_export; + struct dentry *dentry; + int err; /* No upper layer? */ if (!ovl_upper_mnt(ofs)) return 1; /* Lower file handle for non-upper non-decodable */ - if (!ovl_dentry_upper(dentry) && !decodable) + if (!ovl_inode_upper(inode) && !decodable) return 1; /* Upper file handle for pure upper */ - if (!ovl_dentry_lower(dentry)) + if (!ovl_inode_lower(inode)) return 0; /* * Root is never indexed, so if there's an upper layer, encode upper for * root. */ - if (dentry == dentry->d_sb->s_root) + if (inode == d_inode(inode->i_sb->s_root)) return 0; /* * Upper decodable file handle for non-indexed upper. */ - if (ovl_dentry_upper(dentry) && decodable && - !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (ovl_inode_upper(inode) && decodable && + !ovl_test_flag(OVL_INDEX, inode)) return 0; /* @@ -213,14 +215,23 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && decodable) - return ovl_connect_layer(dentry); + if (!decodable || !S_ISDIR(inode->i_mode)) + return 1; + + dentry = d_find_any_alias(inode); + if (!dentry) + return -ENOENT; + + err = ovl_connect_layer(dentry); + dput(dentry); + if (err < 0) + return err; /* Lower file handle for indexed and non-upper dir/non-dir */ return 1; } -static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, +static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode, u32 *fid, int buflen) { struct ovl_fh *fh = NULL; @@ -231,13 +242,13 @@ static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, * Check if we should encode a lower or upper file handle and maybe * copy up an ancestor to make lower file handle connectable. */ - err = enc_lower = ovl_check_encode_origin(dentry); + err = enc_lower = ovl_check_encode_origin(inode); if (enc_lower < 0) goto fail; /* Encode an upper or lower file handle */ - fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_dentry_lower(dentry) : - ovl_dentry_upper(dentry), !enc_lower); + fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) : + ovl_inode_upper(inode), !enc_lower); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -251,8 +262,8 @@ out: return err; fail: - pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i)\n", - dentry, err); + pr_warn_ratelimited("failed to encode file handle (ino=%lu, err=%i)\n", + inode->i_ino, err); goto out; } @@ -260,19 +271,13 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, struct inode *parent) { struct ovl_fs *ofs = OVL_FS(inode->i_sb); - struct dentry *dentry; int bytes, buflen = *max_len << 2; /* TODO: encode connectable file handles */ if (parent) return FILEID_INVALID; - dentry = d_find_any_alias(inode); - if (!dentry) - return FILEID_INVALID; - - bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); - dput(dentry); + bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen); if (bytes <= 0) return FILEID_INVALID; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 7e27b7d4adee..cea820cb3b55 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -542,7 +542,7 @@ int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, real, is_upper); + fh = ovl_encode_real_fh(ofs, d_inode(real), is_upper); err = PTR_ERR(fh); if (IS_ERR(fh)) { fh = NULL; @@ -738,7 +738,7 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, origin, false); + fh = ovl_encode_real_fh(ofs, d_inode(origin), false); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b361f35762be..0021e2025020 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -865,7 +865,7 @@ int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 38a5a3e9cba2..f02cd362309a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1810,7 +1810,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } for (; addr != end; addr += PAGE_SIZE, idx++) { - unsigned long cur_flags = flags; + u64 cur_flags = flags; pagemap_entry_t pme; if (folio && (flags & PM_PRESENT) && diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 85925ec0051a..3310d1ad4d0e 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -179,8 +179,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf) */ static const char *qnx6_checkroot(struct super_block *s) { - static char match_root[2][3] = {".\0\0", "..\0"}; - int i, error = 0; + int error = 0; struct qnx6_dir_entry *dir_entry; struct inode *root = d_inode(s->s_root); struct address_space *mapping = root->i_mapping; @@ -189,11 +188,9 @@ static const char *qnx6_checkroot(struct super_block *s) if (IS_ERR(folio)) return "error reading root directory"; dir_entry = kmap_local_folio(folio, 0); - for (i = 0; i < 2; i++) { - /* maximum 3 bytes - due to match_root limitation */ - if (strncmp(dir_entry[i].de_fname, match_root[i], 3)) - error = 1; - } + if (memcmp(dir_entry[0].de_fname, ".", 2) || + memcmp(dir_entry[1].de_fname, "..", 3)) + error = 1; folio_release_kmap(folio, dir_entry); if (error) return "error reading root directory."; diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig index 2aff6d1395ce..9f05f94e265a 100644 --- a/fs/smb/client/Kconfig +++ b/fs/smb/client/Kconfig @@ -2,7 +2,6 @@ config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET - select NETFS_SUPPORT select NLS select NLS_UCS2_UTILS select CRYPTO diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 9d96b833015c..b800c9f585d8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -398,7 +398,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode = alloc_inode_sb(sb, cifs_inode_cachep, GFP_KERNEL); if (!cifs_inode) return NULL; - cifs_inode->cifsAttrs = 0x20; /* default */ + cifs_inode->cifsAttrs = ATTR_ARCHIVE; /* default */ cifs_inode->time = 0; /* * Until the file is open and we have gotten oplock info back from the diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 754417cb3294..d26f9bbb5382 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -614,8 +614,6 @@ int cifs_alloc_hash(const char *name, struct shash_desc **sdesc); void cifs_free_hash(struct shash_desc **sdesc); int cifs_try_adding_channels(struct cifs_ses *ses); -bool is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface); bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); void cifs_ses_mark_for_reconnect(struct cifs_ses *ses); diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index bd42a419458e..6cb1e81993f8 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1319,14 +1319,16 @@ cifs_readv_callback(struct mid_q_entry *mid) } if (rdata->result == -ENODATA) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && rdata->subreq.start + trans == ictx->remote_i_size) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + } else if (rdata->got_bytes > 0) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } } @@ -1670,10 +1672,13 @@ cifs_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + if (written < wdata->subreq.len) { result = -ENOSPC; - else + } else { result = written; + if (written > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 2372538a1211..ddcc9e514a0e 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -987,9 +987,13 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); + if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; + + /* Release netns reference for the socket. */ + put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1037,6 +1041,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } + /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); kfree(server); @@ -1713,6 +1718,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; + + /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId); @@ -1844,6 +1851,7 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); + /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1852,8 +1860,10 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) + if (tcp_ses->ssocket) { sock_release(tcp_ses->ssocket); + put_net(cifs_net_ns(tcp_ses)); + } kfree(tcp_ses); } return ERR_PTR(rc); @@ -3131,20 +3141,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); - struct sock *sk; - rc = __sock_create(net, sfamily, SOCK_STREAM, - IPPROTO_TCP, &server->ssocket, 1); + rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - sk = server->ssocket->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + /* + * Grab netns reference for the socket. + * + * It'll be released here, on error, or in clean_demultiplex_info() upon server + * teardown. + */ + get_net(net); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3158,8 +3168,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) + if (rc < 0) { + put_net(cifs_net_ns(server)); return rc; + } /* * Eventually check for other socket options to change from @@ -3196,6 +3208,7 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); + put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; @@ -3204,6 +3217,9 @@ generic_ip_connect(struct TCP_Server_Info *server) if (sport == htons(RFC1001_PORT)) rc = ip_rfc1001_connect(server); + if (rc < 0) + put_net(cifs_net_ns(server)); + return rc; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a58a3333ecc3..3b2d33291a7e 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -990,7 +990,11 @@ int cifs_open(struct inode *inode, struct file *file) } /* Get the cached handle as SMB2 close is deferred */ - rc = cifs_get_readable_path(tcon, full_path, &cfile); + if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { + rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + } else { + rc = cifs_get_readable_path(tcon, full_path, &cfile); + } if (rc == 0) { if (file->f_flags == cfile->f_flags) { file->private_data = cfile; diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index 0f788031b740..e3f9213131c4 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -196,11 +196,28 @@ static struct vfsmount *cifs_do_automount(struct path *path) struct smb3_fs_context tmp; char *full_path; struct vfsmount *mnt; + struct cifs_sb_info *mntpt_sb; + struct cifs_ses *ses; if (IS_ROOT(mntpt)) return ERR_PTR(-ESTALE); - cur_ctx = CIFS_SB(mntpt->d_sb)->ctx; + mntpt_sb = CIFS_SB(mntpt->d_sb); + ses = cifs_sb_master_tcon(mntpt_sb)->ses; + cur_ctx = mntpt_sb->ctx; + + /* + * At this point, the root session should be in the mntpt sb. We should + * bring the sb context passwords in sync with the root session's + * passwords. This would help prevent unnecessary retries and password + * swaps for automounts. + */ + mutex_lock(&ses->session_mutex); + rc = smb3_sync_session_ctx_passwords(mntpt_sb, ses); + mutex_unlock(&ses->session_mutex); + + if (rc) + return ERR_PTR(rc); fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, mntpt); if (IS_ERR(fc)) diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 3306fb655136..91d4d409cb1d 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -27,31 +27,6 @@ static int cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface); -bool -is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface) -{ - struct sockaddr_in *i4 = (struct sockaddr_in *)&iface->sockaddr; - struct sockaddr_in6 *i6 = (struct sockaddr_in6 *)&iface->sockaddr; - struct sockaddr_in *s4 = (struct sockaddr_in *)&server->dstaddr; - struct sockaddr_in6 *s6 = (struct sockaddr_in6 *)&server->dstaddr; - - if (server->dstaddr.ss_family != iface->sockaddr.ss_family) - return false; - if (server->dstaddr.ss_family == AF_INET) { - if (s4->sin_addr.s_addr != i4->sin_addr.s_addr) - return false; - } else if (server->dstaddr.ss_family == AF_INET6) { - if (memcmp(&s6->sin6_addr, &i6->sin6_addr, - sizeof(i6->sin6_addr)) != 0) - return false; - } else { - /* unknown family.. */ - return false; - } - return true; -} - bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) { int i; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 010eae9d6c47..0577556f0a41 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4615,6 +4615,7 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, @@ -4840,10 +4841,14 @@ smb2_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + cifs_stats_bytes_written(tcon, written); + + if (written < wdata->subreq.len) { wdata->result = -ENOSPC; - else + } else if (written > 0) { wdata->subreq.len = written; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -5012,7 +5017,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) } #endif - if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) + if (wdata->subreq.retry_count > 0) smb2_set_replay(server, &rqst); cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n", @@ -5156,6 +5161,7 @@ replay_again: cifs_dbg(VFS, "Send error in write = %d\n", rc); } else { *nbytes = le32_to_cpu(rsp->DataLength); + cifs_stats_bytes_written(io_parms->tcon, *nbytes); trace_smb3_write_done(0, 0, xid, req->PersistentFileId, io_parms->tcon->tid, @@ -6204,7 +6210,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, req->StructureSize = cpu_to_le16(36); total_len += 12; - memcpy(req->LeaseKey, lease_key, 16); + memcpy(req->LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE); req->LeaseState = lease_state; flags |= CIFS_NO_RSP_BUF; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b30..f8a40f65db6a 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3ba95bd8edeb..601e7fcbcf1e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..94187628ff08 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,6 +42,7 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 803b35b89513..772deec5b90f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -695,6 +695,9 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) struct smb2_hdr *rsp_hdr; struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); + if (!in_work) + return; + if (allocate_interim_rsp_buf(in_work)) { pr_err("smb_allocate_rsp_buf failed!\n"); ksmbd_free_work_struct(in_work); @@ -1097,6 +1100,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1251,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; @@ -3989,6 +3994,26 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->DeviceId = cpu_to_le32(ksmbd_kstat->kstat->rdev); posix_info->HardLinks = cpu_to_le32(ksmbd_kstat->kstat->nlink); posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode & 0777); + switch (ksmbd_kstat->kstat->mode & S_IFMT) { + case S_IFDIR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = S_ISDIR(ksmbd_kstat->kstat->mode) ? @@ -5179,6 +5204,26 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->HardLinks = cpu_to_le32(stat.nlink); file_info->Mode = cpu_to_le32(stat.mode & 0777); + switch (stat.mode & S_IFMT) { + case S_IFDIR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + file_info->DeviceId = cpu_to_le32(stat.rdev); /* diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 649dacf7e8c4..17a0b18a8406 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -502,4 +502,14 @@ static inline void *smb2_get_msg(void *buf) return buf + 4; } +#define POSIX_TYPE_FILE 0 +#define POSIX_TYPE_DIR 1 +#define POSIX_TYPE_SYMLINK 2 +#define POSIX_TYPE_CHARDEV 3 +#define POSIX_TYPE_BLKDEV 4 +#define POSIX_TYPE_FIFO 5 +#define POSIX_TYPE_SOCKET 6 + +#define POSIX_FILETYPE_SHIFT 12 + #endif /* _SMB2PDU_H */ diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a..befaf42b84cc 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 0ef3c9f0bfeb..c3785a5434f9 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2283,8 +2283,7 @@ out: ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN); if (ibdev) { - if (rdma_frwr_is_supported(&ibdev->attrs)) - rdma_capable = true; + rdma_capable = rdma_frwr_is_supported(&ibdev->attrs); ib_device_put(ibdev); } } diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 88d167a5f8b7..40f08eac519c 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1264,6 +1264,8 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, filepath, flags, path); + if (!is_last) + next[0] = '/'; if (err) goto out2; else if (is_last) @@ -1271,7 +1273,6 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, path_put(parent_path); *parent_path = *path; - next[0] = '/'; remain_len -= filename_len + 1; } diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 7e7e491ff06f..2d7822644eff 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -272,7 +272,7 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, } # define xfs_rtgroup_extents(mp, rgno) (0) -# define xfs_update_last_rtgroup_size(mp, rgno) (-EOPNOTSUPP) +# define xfs_update_last_rtgroup_size(mp, rgno) (0) # define xfs_rtgroup_lock(rtg, gf) ((void)0) # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f11d475898f2..201c26322ede 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -87,8 +87,9 @@ xfs_dquot_detach_buf( } spin_unlock(&qlip->qli_lock); if (bp) { + xfs_buf_lock(bp); list_del_init(&qlip->qli_item.li_bio_list); - xfs_buf_rele(bp); + xfs_buf_relse(bp); } } |