diff options
Diffstat (limited to 'fs')
219 files changed, 10290 insertions, 5087 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 7b623e9fc1b0..8493a3f0c4b1 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -264,6 +264,7 @@ source "fs/pstore/Kconfig" source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/erofs/Kconfig" +source "fs/vboxsf/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Makefile b/fs/Makefile index 98be354fdb61..96520ba7bd64 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -133,3 +133,4 @@ obj-$(CONFIG_CEPH_FS) += ceph/ obj-$(CONFIG_PSTORE) += pstore/ obj-$(CONFIG_EFIVAR_FS) += efivarfs/ obj-$(CONFIG_EROFS_FS) += erofs/ +obj-$(CONFIG_VBOXSF_FS) += vboxsf/ diff --git a/fs/afs/super.c b/fs/afs/super.c index 7f8a9b3137bf..dda7a9a66848 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -38,13 +38,13 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); static int afs_show_devname(struct seq_file *m, struct dentry *root); static int afs_show_options(struct seq_file *m, struct dentry *root); static int afs_init_fs_context(struct fs_context *fc); -static const struct fs_parameter_description afs_fs_parameters; +static const struct fs_parameter_spec afs_fs_parameters[]; struct file_system_type afs_fs_type = { .owner = THIS_MODULE, .name = "afs", .init_fs_context = afs_init_fs_context, - .parameters = &afs_fs_parameters, + .parameters = afs_fs_parameters, .kill_sb = afs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE, }; @@ -73,28 +73,22 @@ enum afs_param { Opt_source, }; -static const struct fs_parameter_spec afs_param_specs[] = { - fsparam_flag ("autocell", Opt_autocell), - fsparam_flag ("dyn", Opt_dyn), - fsparam_enum ("flock", Opt_flock), - fsparam_string("source", Opt_source), +static const struct constant_table afs_param_flock[] = { + {"local", afs_flock_mode_local }, + {"openafs", afs_flock_mode_openafs }, + {"strict", afs_flock_mode_strict }, + {"write", afs_flock_mode_write }, {} }; -static const struct fs_parameter_enum afs_param_enums[] = { - { Opt_flock, "local", afs_flock_mode_local }, - { Opt_flock, "openafs", afs_flock_mode_openafs }, - { Opt_flock, "strict", afs_flock_mode_strict }, - { Opt_flock, "write", afs_flock_mode_write }, +static const struct fs_parameter_spec afs_fs_parameters[] = { + fsparam_flag ("autocell", Opt_autocell), + fsparam_flag ("dyn", Opt_dyn), + fsparam_enum ("flock", Opt_flock, afs_param_flock), + fsparam_string("source", Opt_source), {} }; -static const struct fs_parameter_description afs_fs_parameters = { - .name = "kAFS", - .specs = afs_param_specs, - .enums = afs_param_enums, -}; - /* * initialise the filesystem */ @@ -323,7 +317,7 @@ static int afs_parse_param(struct fs_context *fc, struct fs_parameter *param) struct afs_fs_context *ctx = fc->fs_private; int opt; - opt = fs_parse(fc, &afs_fs_parameters, param, &result); + opt = fs_parse(fc, afs_fs_parameters, param, &result); if (opt < 0) return opt; @@ -1610,6 +1610,14 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, return 0; } +static void aio_poll_put_work(struct work_struct *work) +{ + struct poll_iocb *req = container_of(work, struct poll_iocb, work); + struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); + + iocb_put(iocb); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1674,6 +1682,8 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del_init(&req->wait.entry); if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { + struct kioctx *ctx = iocb->ki_ctx; + /* * Try to complete the iocb inline if we can. Use * irqsave/irqrestore because not all filesystems (e.g. fuse) @@ -1683,8 +1693,14 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); req->done = true; - spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); - iocb_put(iocb); + if (iocb->ki_eventfd && eventfd_signal_count()) { + iocb = NULL; + INIT_WORK(&req->work, aio_poll_put_work); + schedule_work(&req->work); + } + spin_unlock_irqrestore(&ctx->ctx_lock, flags); + if (iocb) + iocb_put(iocb); } else { schedule_work(&req->work); } diff --git a/fs/attr.c b/fs/attr.c index df28035aa23e..b4bbdbd4c8ca 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -183,18 +183,12 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) inode->i_uid = attr->ia_uid; if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; - if (ia_valid & ATTR_ATIME) { - inode->i_atime = timestamp_truncate(attr->ia_atime, - inode); - } - if (ia_valid & ATTR_MTIME) { - inode->i_mtime = timestamp_truncate(attr->ia_mtime, - inode); - } - if (ia_valid & ATTR_CTIME) { - inode->i_ctime = timestamp_truncate(attr->ia_ctime, - inode); - } + if (ia_valid & ATTR_ATIME) + inode->i_atime = attr->ia_atime; + if (ia_valid & ATTR_MTIME) + inode->i_mtime = attr->ia_mtime; + if (ia_valid & ATTR_CTIME) + inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; @@ -268,8 +262,13 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; + else + attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; + else + attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); + if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 14851584e245..404e050ce8ee 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1191,7 +1191,6 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) { struct btrfs_space_info *sinfo = cache->space_info; u64 num_bytes; - u64 sinfo_used; int ret = -ENOSPC; spin_lock(&sinfo->lock); @@ -1205,19 +1204,38 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) num_bytes = cache->length - cache->reserved - cache->pinned - cache->bytes_super - cache->used; - sinfo_used = btrfs_space_info_used(sinfo, true); /* - * sinfo_used + num_bytes should always <= sinfo->total_bytes. - * - * Here we make sure if we mark this bg RO, we still have enough - * free space as buffer. + * Data never overcommits, even in mixed mode, so do just the straight + * check of left over space in how much we have allocated. */ - if (sinfo_used + num_bytes <= sinfo->total_bytes) { + if (force) { + ret = 0; + } else if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) { + u64 sinfo_used = btrfs_space_info_used(sinfo, true); + + /* + * Here we make sure if we mark this bg RO, we still have enough + * free space as buffer. + */ + if (sinfo_used + num_bytes <= sinfo->total_bytes) + ret = 0; + } else { + /* + * We overcommit metadata, so we need to do the + * btrfs_can_overcommit check here, and we need to pass in + * BTRFS_RESERVE_NO_FLUSH to give ourselves the most amount of + * leeway to allow us to mark this block group as read only. + */ + if (btrfs_can_overcommit(cache->fs_info, sinfo, num_bytes, + BTRFS_RESERVE_NO_FLUSH)) + ret = 0; + } + + if (!ret) { sinfo->bytes_readonly += num_bytes; cache->ro++; list_add_tail(&cache->ro_list, &sinfo->ro_bgs); - ret = 0; } out: spin_unlock(&cache->lock); @@ -1225,9 +1243,6 @@ out: if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) { btrfs_info(cache->fs_info, "unable to make block group %llu ro", cache->start); - btrfs_info(cache->fs_info, - "sinfo_used=%llu bg_num_bytes=%llu", - sinfo_used, num_bytes); btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0); } return ret; @@ -2225,7 +2240,7 @@ again: } } - ret = inc_block_group_ro(cache, !do_chunk_alloc); + ret = inc_block_group_ro(cache, 0); if (!do_chunk_alloc) goto unlock_out; if (!ret) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 24658b5a5787..f2ec1a9bae28 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -326,12 +326,10 @@ u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info, struct seq_list *elem) { write_lock(&fs_info->tree_mod_log_lock); - spin_lock(&fs_info->tree_mod_seq_lock); if (!elem->seq) { elem->seq = btrfs_inc_tree_mod_seq(fs_info); list_add_tail(&elem->list, &fs_info->tree_mod_seq_list); } - spin_unlock(&fs_info->tree_mod_seq_lock); write_unlock(&fs_info->tree_mod_log_lock); return elem->seq; @@ -351,7 +349,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, if (!seq_putting) return; - spin_lock(&fs_info->tree_mod_seq_lock); + write_lock(&fs_info->tree_mod_log_lock); list_del(&elem->list); elem->seq = 0; @@ -362,19 +360,17 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, * blocker with lower sequence number exists, we * cannot remove anything from the log */ - spin_unlock(&fs_info->tree_mod_seq_lock); + write_unlock(&fs_info->tree_mod_log_lock); return; } min_seq = cur_elem->seq; } } - spin_unlock(&fs_info->tree_mod_seq_lock); /* * anything that's lower than the lowest existing (read: blocked) * sequence number can be removed from the tree. */ - write_lock(&fs_info->tree_mod_log_lock); tm_root = &fs_info->tree_mod_log; for (node = rb_first(tm_root); node; node = next) { next = rb_next(node); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f90b82050d2d..36df977b64d9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -714,14 +714,12 @@ struct btrfs_fs_info { atomic_t nr_delayed_iputs; wait_queue_head_t delayed_iputs_wait; - /* this protects tree_mod_seq_list */ - spinlock_t tree_mod_seq_lock; atomic64_t tree_mod_seq; - struct list_head tree_mod_seq_list; - /* this protects tree_mod_log */ + /* this protects tree_mod_log and tree_mod_seq_list */ rwlock_t tree_mod_log_lock; struct rb_root tree_mod_log; + struct list_head tree_mod_seq_list; atomic_t async_delalloc_pages; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index df3bd880061d..dfdb7d4f8406 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -492,7 +492,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, if (head->is_data) return; - spin_lock(&fs_info->tree_mod_seq_lock); + read_lock(&fs_info->tree_mod_log_lock); if (!list_empty(&fs_info->tree_mod_seq_list)) { struct seq_list *elem; @@ -500,7 +500,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, struct seq_list, list); seq = elem->seq; } - spin_unlock(&fs_info->tree_mod_seq_lock); + read_unlock(&fs_info->tree_mod_log_lock); again: for (node = rb_first_cached(&head->ref_tree); node; @@ -518,7 +518,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq) struct seq_list *elem; int ret = 0; - spin_lock(&fs_info->tree_mod_seq_lock); + read_lock(&fs_info->tree_mod_log_lock); if (!list_empty(&fs_info->tree_mod_seq_list)) { elem = list_first_entry(&fs_info->tree_mod_seq_list, struct seq_list, list); @@ -531,7 +531,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq) } } - spin_unlock(&fs_info->tree_mod_seq_lock); + read_unlock(&fs_info->tree_mod_log_lock); return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index aea48d6ddc0c..7fa9bb79ad08 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2697,7 +2697,6 @@ int __cold open_ctree(struct super_block *sb, spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); - spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e2d30287e2d5..c0f202741e09 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1593,21 +1593,25 @@ void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, /* Find first extent with bits cleared */ while (1) { node = __etree_search(tree, start, &next, &prev, NULL, NULL); - if (!node) { + if (!node && !next && !prev) { + /* + * Tree is completely empty, send full range and let + * caller deal with it + */ + *start_ret = 0; + *end_ret = -1; + goto out; + } else if (!node && !next) { + /* + * We are past the last allocated chunk, set start at + * the end of the last extent. + */ + state = rb_entry(prev, struct extent_state, rb_node); + *start_ret = state->end + 1; + *end_ret = -1; + goto out; + } else if (!node) { node = next; - if (!node) { - /* - * We are past the last allocated chunk, - * set start at the end of the last extent. The - * device alloc tree should never be empty so - * prev is always set. - */ - ASSERT(prev); - state = rb_entry(prev, struct extent_state, rb_node); - *start_ret = state->end + 1; - *end_ret = -1; - goto out; - } } /* * At this point 'node' either contains 'start' or start is @@ -3438,11 +3442,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, ret = btrfs_writepage_cow_fixup(page, start, page_end); if (ret) { /* Fixup worker will requeue */ - if (ret == -EBUSY) - wbc->pages_skipped++; - else - redirty_page_for_writepage(wbc, page); - + redirty_page_for_writepage(wbc, page); update_nr_written(wbc, nr_written); unlock_page(page); return 1; @@ -4166,7 +4166,16 @@ retry: */ scanned = 1; index = 0; - goto retry; + + /* + * If we're looping we could run into a page that is locked by a + * writer and that writer could be waiting on writeback for a + * page in our current bio, and thus deadlock, so flush the + * write bio here. + */ + ret = flush_write_bio(epd); + if (!ret) + goto retry; } if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole)) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6d2bb58d277a..5b3ec93ff911 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2189,6 +2189,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, /* see btrfs_writepage_start_hook for details on why this is required */ struct btrfs_writepage_fixup { struct page *page; + struct inode *inode; struct btrfs_work work; }; @@ -2202,27 +2203,71 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) struct inode *inode; u64 page_start; u64 page_end; - int ret; + int ret = 0; + bool free_delalloc_space = true; fixup = container_of(work, struct btrfs_writepage_fixup, work); page = fixup->page; + inode = fixup->inode; + page_start = page_offset(page); + page_end = page_offset(page) + PAGE_SIZE - 1; + + /* + * This is similar to page_mkwrite, we need to reserve the space before + * we take the page lock. + */ + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, + PAGE_SIZE); again: lock_page(page); + + /* + * Before we queued this fixup, we took a reference on the page. + * page->mapping may go NULL, but it shouldn't be moved to a different + * address space. + */ if (!page->mapping || !PageDirty(page) || !PageChecked(page)) { - ClearPageChecked(page); + /* + * Unfortunately this is a little tricky, either + * + * 1) We got here and our page had already been dealt with and + * we reserved our space, thus ret == 0, so we need to just + * drop our space reservation and bail. This can happen the + * first time we come into the fixup worker, or could happen + * while waiting for the ordered extent. + * 2) Our page was already dealt with, but we happened to get an + * ENOSPC above from the btrfs_delalloc_reserve_space. In + * this case we obviously don't have anything to release, but + * because the page was already dealt with we don't want to + * mark the page with an error, so make sure we're resetting + * ret to 0. This is why we have this check _before_ the ret + * check, because we do not want to have a surprise ENOSPC + * when the page was already properly dealt with. + */ + if (!ret) { + btrfs_delalloc_release_extents(BTRFS_I(inode), + PAGE_SIZE); + btrfs_delalloc_release_space(inode, data_reserved, + page_start, PAGE_SIZE, + true); + } + ret = 0; goto out_page; } - inode = page->mapping->host; - page_start = page_offset(page); - page_end = page_offset(page) + PAGE_SIZE - 1; + /* + * We can't mess with the page state unless it is locked, so now that + * it is locked bail if we failed to make our space reservation. + */ + if (ret) + goto out_page; lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); /* already ordered? We're done */ if (PagePrivate2(page)) - goto out; + goto out_reserved; ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start, PAGE_SIZE); @@ -2235,39 +2280,49 @@ again: goto again; } - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, - PAGE_SIZE); - if (ret) { - mapping_set_error(page->mapping, ret); - end_extent_writepage(page, ret, page_start, page_end); - ClearPageChecked(page); - goto out; - } - ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0, &cached_state); - if (ret) { - mapping_set_error(page->mapping, ret); - end_extent_writepage(page, ret, page_start, page_end); - ClearPageChecked(page); + if (ret) goto out_reserved; - } - ClearPageChecked(page); - set_page_dirty(page); + /* + * Everything went as planned, we're now the owner of a dirty page with + * delayed allocation bits set and space reserved for our COW + * destination. + * + * The page was dirty when we started, nothing should have cleaned it. + */ + BUG_ON(!PageDirty(page)); + free_delalloc_space = false; out_reserved: btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); - if (ret) + if (free_delalloc_space) btrfs_delalloc_release_space(inode, data_reserved, page_start, PAGE_SIZE, true); -out: unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); out_page: + if (ret) { + /* + * We hit ENOSPC or other errors. Update the mapping and page + * to reflect the errors and clean the page. + */ + mapping_set_error(page->mapping, ret); + end_extent_writepage(page, ret, page_start, page_end); + clear_page_dirty_for_io(page); + SetPageError(page); + } + ClearPageChecked(page); unlock_page(page); put_page(page); kfree(fixup); extent_changeset_free(data_reserved); + /* + * As a precaution, do a delayed iput in case it would be the last iput + * that could need flushing space. Recursing back to fixup worker would + * deadlock. + */ + btrfs_add_delayed_iput(inode); } /* @@ -2291,6 +2346,13 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end) if (TestClearPagePrivate2(page)) return 0; + /* + * PageChecked is set below when we create a fixup worker for this page, + * don't try to create another one if we're already PageChecked() + * + * The extent_io writepage code will redirty the page if we send back + * EAGAIN. + */ if (PageChecked(page)) return -EAGAIN; @@ -2298,12 +2360,21 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end) if (!fixup) return -EAGAIN; + /* + * We are already holding a reference to this inode from + * write_cache_pages. We need to hold it because the space reservation + * takes place outside of the page lock, and we can't trust + * page->mapping outside of the page lock. + */ + ihold(inode); SetPageChecked(page); get_page(page); btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL); fixup->page = page; + fixup->inode = inode; btrfs_queue_work(fs_info->fixup_workers, &fixup->work); - return -EBUSY; + + return -EAGAIN; } static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 091e5bc8c7ea..a055b657cb85 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1269,7 +1269,8 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_) * destination of the stream. */ if (ino == bctx->cur_objectid && - offset >= bctx->sctx->cur_inode_next_write_offset) + offset + bctx->extent_len > + bctx->sctx->cur_inode_next_write_offset) return 0; } diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 537bc310a673..01297c5b2666 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -159,9 +159,9 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global) return (global->size << 1); } -static int can_overcommit(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, u64 bytes, - enum btrfs_reserve_flush_enum flush) +int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, u64 bytes, + enum btrfs_reserve_flush_enum flush) { u64 profile; u64 avail; @@ -226,7 +226,8 @@ again: /* Check and see if our ticket can be satisified now. */ if ((used + ticket->bytes <= space_info->total_bytes) || - can_overcommit(fs_info, space_info, ticket->bytes, flush)) { + btrfs_can_overcommit(fs_info, space_info, ticket->bytes, + flush)) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, ticket->bytes); @@ -639,13 +640,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, return to_reclaim; to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (can_overcommit(fs_info, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) + if (btrfs_can_overcommit(fs_info, space_info, to_reclaim, + BTRFS_RESERVE_FLUSH_ALL)) return 0; used = btrfs_space_info_used(space_info, true); - if (can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL)) + if (btrfs_can_overcommit(fs_info, space_info, SZ_1M, + BTRFS_RESERVE_FLUSH_ALL)) expected = div_factor_fine(space_info->total_bytes, 95); else expected = div_factor_fine(space_info->total_bytes, 90); @@ -1004,7 +1006,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, */ if (!pending_tickets && ((used + orig_bytes <= space_info->total_bytes) || - can_overcommit(fs_info, space_info, orig_bytes, flush))) { + btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { btrfs_space_info_update_bytes_may_use(fs_info, space_info, orig_bytes); ret = 0; diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 1a349e3f9cc1..24514cd2c6c1 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -127,6 +127,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root, enum btrfs_reserve_flush_enum flush); void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info); +int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, u64 bytes, + enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a906315efd19..0616a5434793 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2135,7 +2135,15 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) */ thresh = SZ_4M; - if (!mixed && total_free_meta - thresh < block_rsv->size) + /* + * We only want to claim there's no available space if we can no longer + * allocate chunks for our metadata profile and our global reserve will + * not fit in the free metadata space. If we aren't ->full then we + * still can allocate chunks and thus are fine using the currently + * calculated f_bavail. + */ + if (!mixed && block_rsv->space_info->full && + total_free_meta - thresh < block_rsv->size) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index c12b91ff5f56..84fb3fa940a6 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -142,7 +142,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) spin_lock_init(&fs_info->qgroup_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); - spin_lock_init(&fs_info->tree_mod_seq_lock); mutex_init(&fs_info->qgroup_ioctl_lock); mutex_init(&fs_info->qgroup_rescan_lock); rwlock_init(&fs_info->tree_mod_log_lock); diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 123d9a614357..df7ce874a74b 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -441,8 +441,17 @@ static int test_find_first_clear_extent_bit(void) int ret = -EINVAL; test_msg("running find_first_clear_extent_bit test"); + extent_io_tree_init(NULL, &tree, IO_TREE_SELFTEST, NULL); + /* Test correct handling of empty tree */ + find_first_clear_extent_bit(&tree, 0, &start, &end, CHUNK_TRIMMED); + if (start != 0 || end != -1) { + test_err( + "error getting a range from completely empty tree: start %llu end %llu", + start, end); + goto out; + } /* * Set 1M-4M alloc/discard and 32M-64M thus leaving a hole between * 4M-32M diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 44a3ce1e4ce4..1dc97f2d6201 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -396,7 +396,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, struct cachefiles_object *object; struct cachefiles_cache *cache; struct inode *inode; - sector_t block0, block; + sector_t block; unsigned shift; int ret; @@ -412,7 +412,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, inode = d_backing_inode(object->backer); ASSERT(S_ISREG(inode->i_mode)); - ASSERT(inode->i_mapping->a_ops->bmap); ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ @@ -428,12 +427,14 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, * enough for this as it doesn't indicate errors, but it's all we've * got for the moment */ - block0 = page->index; - block0 <<= shift; + block = page->index; + block <<= shift; + + ret = bmap(inode, &block); + ASSERT(ret < 0); - block = inode->i_mapping->a_ops->bmap(inode->i_mapping, block0); _debug("%llx -> %llx", - (unsigned long long) block0, + (unsigned long long) (page->index << shift), (unsigned long long) block); if (block) { @@ -711,7 +712,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, inode = d_backing_inode(object->backer); ASSERT(S_ISREG(inode->i_mode)); - ASSERT(inode->i_mapping->a_ops->bmap); ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ @@ -728,7 +728,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, ret = space ? -ENODATA : -ENOBUFS; list_for_each_entry_safe(page, _n, pages, lru) { - sector_t block0, block; + sector_t block; /* we assume the absence or presence of the first block is a * good enough indication for the page as a whole @@ -736,13 +736,14 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, * good enough for this as it doesn't indicate errors, but * it's all we've got for the moment */ - block0 = page->index; - block0 <<= shift; + block = page->index; + block <<= shift; + + ret = bmap(inode, &block); + ASSERT(!ret); - block = inode->i_mapping->a_ops->bmap(inode->i_mapping, - block0); _debug("%llx -> %llx", - (unsigned long long) block0, + (unsigned long long) (page->index << shift), (unsigned long long) block); if (block) { diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile index c1da294418d1..0a0823d378db 100644 --- a/fs/ceph/Makefile +++ b/fs/ceph/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_CEPH_FS) += ceph.o ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \ export.o caps.o snap.o xattr.o quota.o io.o \ mds_client.o mdsmap.o strings.o ceph_frag.o \ - debugfs.o + debugfs.o util.o ceph-$(CONFIG_CEPH_FSCACHE) += cache.o ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index aa55f412a6e3..26be6520d3fb 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -222,8 +222,8 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8); if (err) goto out_err; - err = ceph_pagelist_encode_string(pagelist, - XATTR_NAME_POSIX_ACL_DEFAULT, len); + ceph_pagelist_encode_string(pagelist, + XATTR_NAME_POSIX_ACL_DEFAULT, len); err = posix_acl_to_xattr(&init_user_ns, default_acl, tmp_buf, val_size2); if (err < 0) diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 73f24f307a4a..270b769607a2 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -67,7 +67,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len)) continue; - errorf(fc, "ceph: fscache cookie already registered for fsid %pU, use fsc=<uniquifier> option", + errorfc(fc, "fscache cookie already registered for fsid %pU, use fsc=<uniquifier> option", fsid); err = -EBUSY; goto out_unlock; @@ -96,7 +96,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) list_add_tail(&ent->list, &ceph_fscache_list); } else { kfree(ent); - errorf(fc, "ceph: unable to register fscache cookie for fsid %pU", + errorfc(fc, "unable to register fscache cookie for fsid %pU", fsid); /* all other fs ignore this error */ } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 9d09bb53c1ab..28ae0c134700 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -908,7 +908,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) ci_node); if (!__cap_is_valid(cap)) continue; - __touch_cap(cap); + if (cap->issued & mask) + __touch_cap(cap); } } return 1; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index c281f32b54f7..fb7cabd98e7b 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -33,7 +33,7 @@ static int mdsmap_show(struct seq_file *s, void *p) seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds); seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout); seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose); - for (i = 0; i < mdsmap->m_num_mds; i++) { + for (i = 0; i < mdsmap->possible_max_rank; i++) { struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr; int state = mdsmap->m_info[i].state; seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 2e4764fd1872..d0cd0aba5843 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1186,7 +1186,7 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di) struct dentry *dn = di->dentry; struct ceph_mds_client *mdsc; - dout("dentry_dir_lease_touch %p %p '%pd' (offset %lld)\n", + dout("dentry_dir_lease_touch %p %p '%pd' (offset 0x%llx)\n", di, dn, dn, di->offset); if (!list_empty(&di->lease_list)) { @@ -1567,7 +1567,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) inode = d_inode(dentry); } - dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry, + dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry, dentry, inode, ceph_dentry(dentry)->offset); /* always trust cached snapped dentries, snapdir dentry */ diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 11929d2bb594..c3b8e8e0bf17 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1974,6 +1974,9 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, if (ceph_test_mount_opt(src_fsc, NOCOPYFROM)) return -EOPNOTSUPP; + if (!src_fsc->have_copy_from2) + return -EOPNOTSUPP; + /* * Striped file layouts require that we copy partial objects, but the * OSD copy-from operation only supports full-object copies. Limit @@ -2101,8 +2104,14 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, CEPH_OSD_OP_FLAG_FADVISE_NOCACHE, &dst_oid, &dst_oloc, CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, 0); + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, + dst_ci->i_truncate_seq, dst_ci->i_truncate_size, + CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); if (err) { + if (err == -EOPNOTSUPP) { + src_fsc->have_copy_from2 = false; + pr_notice("OSDs don't support copy-from2; disabling copy offload\n"); + } dout("ceph_osdc_copy_from returned %d\n", err); if (!ret) ret = err; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index c07407586ce8..d01710a16a4a 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -55,11 +55,9 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino) inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino); if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) { + if (inode->i_state & I_NEW) dout("get_inode created new inode %p %llx.%llx ino %llx\n", inode, ceph_vinop(inode), (u64)inode->i_ino); - unlock_new_inode(inode); - } dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino, vino.snap, inode); @@ -88,6 +86,10 @@ struct inode *ceph_get_snapdir(struct inode *parent) inode->i_fop = &ceph_snapdir_fops; ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */ ci->i_rbytes = 0; + + if (inode->i_state & I_NEW) + unlock_new_inode(inode); + return inode; } @@ -728,8 +730,7 @@ void ceph_fill_file_time(struct inode *inode, int issued, static int fill_inode(struct inode *inode, struct page *locked_page, struct ceph_mds_reply_info_in *iinfo, struct ceph_mds_reply_dirfrag *dirinfo, - struct ceph_mds_session *session, - unsigned long ttl_from, int cap_fmode, + struct ceph_mds_session *session, int cap_fmode, struct ceph_cap_reservation *caps_reservation) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; @@ -754,8 +755,11 @@ static int fill_inode(struct inode *inode, struct page *locked_page, info_caps = le32_to_cpu(info->cap.caps); /* prealloc new cap struct */ - if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) + if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) { new_cap = ceph_get_cap(mdsc, caps_reservation); + if (!new_cap) + return -ENOMEM; + } /* * prealloc xattr data, if it looks like we'll need it. only @@ -1237,7 +1241,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) if (dir) { err = fill_inode(dir, NULL, &rinfo->diri, rinfo->dirfrag, - session, req->r_request_started, -1, + session, -1, &req->r_caps_reservation); if (err < 0) goto done; @@ -1302,18 +1306,22 @@ retry_lookup: err = PTR_ERR(in); goto done; } - req->r_target_inode = in; err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL, - session, req->r_request_started, + session, (!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) && - rinfo->head->result == 0) ? req->r_fmode : -1, + rinfo->head->result == 0) ? req->r_fmode : -1, &req->r_caps_reservation); if (err < 0) { pr_err("fill_inode badness %p %llx.%llx\n", in, ceph_vinop(in)); + if (in->i_state & I_NEW) + discard_new_inode(in); goto done; } + req->r_target_inode = in; + if (in->i_state & I_NEW) + unlock_new_inode(in); } /* @@ -1493,12 +1501,18 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req, continue; } rc = fill_inode(in, NULL, &rde->inode, NULL, session, - req->r_request_started, -1, - &req->r_caps_reservation); + -1, &req->r_caps_reservation); if (rc < 0) { pr_err("fill_inode badness on %p got %d\n", in, rc); err = rc; + if (in->i_state & I_NEW) { + ihold(in); + discard_new_inode(in); + } + } else if (in->i_state & I_NEW) { + unlock_new_inode(in); } + /* avoid calling iput_final() in mds dispatch threads */ ceph_async_iput(in); } @@ -1694,19 +1708,24 @@ retry_lookup: } ret = fill_inode(in, NULL, &rde->inode, NULL, session, - req->r_request_started, -1, - &req->r_caps_reservation); + -1, &req->r_caps_reservation); if (ret < 0) { pr_err("fill_inode badness on %p\n", in); if (d_really_is_negative(dn)) { /* avoid calling iput_final() in mds * dispatch threads */ + if (in->i_state & I_NEW) { + ihold(in); + discard_new_inode(in); + } ceph_async_iput(in); } d_drop(dn); err = ret; goto next_item; } + if (in->i_state & I_NEW) + unlock_new_inode(in); if (d_really_is_negative(dn)) { if (ceph_security_xattr_deadlock(in)) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 145d46ba25ae..bbbbddf71326 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -9,6 +9,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/ratelimit.h> +#include <linux/bits.h> #include "super.h" #include "mds_client.h" @@ -530,6 +531,7 @@ const char *ceph_session_state_name(int s) case CEPH_MDS_SESSION_OPEN: return "open"; case CEPH_MDS_SESSION_HUNG: return "hung"; case CEPH_MDS_SESSION_CLOSING: return "closing"; + case CEPH_MDS_SESSION_CLOSED: return "closed"; case CEPH_MDS_SESSION_RESTARTING: return "restarting"; case CEPH_MDS_SESSION_RECONNECTING: return "reconnecting"; case CEPH_MDS_SESSION_REJECTED: return "rejected"; @@ -537,7 +539,7 @@ const char *ceph_session_state_name(int s) } } -static struct ceph_mds_session *get_session(struct ceph_mds_session *s) +struct ceph_mds_session *ceph_get_mds_session(struct ceph_mds_session *s) { if (refcount_inc_not_zero(&s->s_ref)) { dout("mdsc get_session %p %d -> %d\n", s, @@ -568,7 +570,7 @@ struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc, { if (mds >= mdsc->max_sessions || !mdsc->sessions[mds]) return NULL; - return get_session(mdsc->sessions[mds]); + return ceph_get_mds_session(mdsc->sessions[mds]); } static bool __have_session(struct ceph_mds_client *mdsc, int mds) @@ -597,7 +599,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, { struct ceph_mds_session *s; - if (mds >= mdsc->mdsmap->m_num_mds) + if (mds >= mdsc->mdsmap->possible_max_rank) return ERR_PTR(-EINVAL); s = kzalloc(sizeof(*s), GFP_NOFS); @@ -674,7 +676,6 @@ static void __unregister_session(struct ceph_mds_client *mdsc, dout("__unregister_session mds%d %p\n", s->s_mds, s); BUG_ON(mdsc->sessions[s->s_mds] != s); mdsc->sessions[s->s_mds] = NULL; - s->s_state = 0; ceph_con_close(&s->s_con); ceph_put_mds_session(s); atomic_dec(&mdsc->num_sessions); @@ -878,7 +879,8 @@ static struct inode *get_nonsnap_parent(struct dentry *dentry) * Called under mdsc->mutex. */ static int __choose_mds(struct ceph_mds_client *mdsc, - struct ceph_mds_request *req) + struct ceph_mds_request *req, + bool *random) { struct inode *inode; struct ceph_inode_info *ci; @@ -888,6 +890,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc, u32 hash = req->r_direct_hash; bool is_hash = test_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags); + if (random) + *random = false; + /* * is there a specific mds we should try? ignore hint if we have * no session and the mds is not up (active or recovering). @@ -895,7 +900,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, if (req->r_resend_mds >= 0 && (__have_session(mdsc, req->r_resend_mds) || ceph_mdsmap_get_state(mdsc->mdsmap, req->r_resend_mds) > 0)) { - dout("choose_mds using resend_mds mds%d\n", + dout("%s using resend_mds mds%d\n", __func__, req->r_resend_mds); return req->r_resend_mds; } @@ -913,7 +918,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, rcu_read_lock(); inode = get_nonsnap_parent(req->r_dentry); rcu_read_unlock(); - dout("__choose_mds using snapdir's parent %p\n", inode); + dout("%s using snapdir's parent %p\n", __func__, inode); } } else if (req->r_dentry) { /* ignore race with rename; old or new d_parent is okay */ @@ -933,7 +938,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, /* direct snapped/virtual snapdir requests * based on parent dir inode */ inode = get_nonsnap_parent(parent); - dout("__choose_mds using nonsnap parent %p\n", inode); + dout("%s using nonsnap parent %p\n", __func__, inode); } else { /* dentry target */ inode = d_inode(req->r_dentry); @@ -949,8 +954,8 @@ static int __choose_mds(struct ceph_mds_client *mdsc, rcu_read_unlock(); } - dout("__choose_mds %p is_hash=%d (%d) mode %d\n", inode, (int)is_hash, - (int)hash, mode); + dout("%s %p is_hash=%d (0x%x) mode %d\n", __func__, inode, (int)is_hash, + hash, mode); if (!inode) goto random; ci = ceph_inode(inode); @@ -968,30 +973,33 @@ static int __choose_mds(struct ceph_mds_client *mdsc, get_random_bytes(&r, 1); r %= frag.ndist; mds = frag.dist[r]; - dout("choose_mds %p %llx.%llx " - "frag %u mds%d (%d/%d)\n", - inode, ceph_vinop(inode), - frag.frag, mds, - (int)r, frag.ndist); + dout("%s %p %llx.%llx frag %u mds%d (%d/%d)\n", + __func__, inode, ceph_vinop(inode), + frag.frag, mds, (int)r, frag.ndist); if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >= - CEPH_MDS_STATE_ACTIVE) + CEPH_MDS_STATE_ACTIVE && + !ceph_mdsmap_is_laggy(mdsc->mdsmap, mds)) goto out; } /* since this file/dir wasn't known to be * replicated, then we want to look for the * authoritative mds. */ - mode = USE_AUTH_MDS; if (frag.mds >= 0) { /* choose auth mds */ mds = frag.mds; - dout("choose_mds %p %llx.%llx " - "frag %u mds%d (auth)\n", - inode, ceph_vinop(inode), frag.frag, mds); + dout("%s %p %llx.%llx frag %u mds%d (auth)\n", + __func__, inode, ceph_vinop(inode), + frag.frag, mds); if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >= - CEPH_MDS_STATE_ACTIVE) - goto out; + CEPH_MDS_STATE_ACTIVE) { + if (mode == USE_ANY_MDS && + !ceph_mdsmap_is_laggy(mdsc->mdsmap, + mds)) + goto out; + } } + mode = USE_AUTH_MDS; } } @@ -1007,7 +1015,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, goto random; } mds = cap->session->s_mds; - dout("choose_mds %p %llx.%llx mds%d (%scap %p)\n", + dout("%s %p %llx.%llx mds%d (%scap %p)\n", __func__, inode, ceph_vinop(inode), mds, cap == ci->i_auth_cap ? "auth " : "", cap); spin_unlock(&ci->i_ceph_lock); @@ -1018,8 +1026,11 @@ out: return mds; random: + if (random) + *random = true; + mds = ceph_mdsmap_get_random_mds(mdsc->mdsmap); - dout("choose_mds chose random mds%d\n", mds); + dout("%s chose random mds%d\n", __func__, mds); return mds; } @@ -1045,20 +1056,21 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq) return msg; } +static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED; +#define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8) static void encode_supported_features(void **p, void *end) { - static const unsigned char bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED; - static const size_t count = ARRAY_SIZE(bits); + static const size_t count = ARRAY_SIZE(feature_bits); if (count > 0) { size_t i; - size_t size = ((size_t)bits[count - 1] + 64) / 64 * 8; + size_t size = FEATURE_BYTES(count); BUG_ON(*p + 4 + size > end); ceph_encode_32(p, size); memset(*p, 0, size); for (i = 0; i < count; i++) - ((unsigned char*)(*p))[i / 8] |= 1 << (bits[i] % 8); + ((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8); *p += size; } else { BUG_ON(*p + 4 > end); @@ -1079,6 +1091,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 int metadata_key_count = 0; struct ceph_options *opt = mdsc->fsc->client->options; struct ceph_mount_options *fsopt = mdsc->fsc->mount_options; + size_t size, count; void *p, *end; const char* metadata[][2] = { @@ -1096,8 +1109,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 strlen(metadata[i][1]); metadata_key_count++; } + /* supported feature */ - extra_bytes += 4 + 8; + size = 0; + count = ARRAY_SIZE(feature_bits); + if (count > 0) + size = FEATURE_BYTES(count); + extra_bytes += 4 + size; /* Allocate the message */ msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes, @@ -1117,7 +1135,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 * Serialize client metadata into waiting buffer space, using * the format that userspace expects for map<string, string> * - * ClientSession messages with metadata are v2 + * ClientSession messages with metadata are v3 */ msg->hdr.version = cpu_to_le16(3); msg->hdr.compat_version = cpu_to_le16(1); @@ -1219,7 +1237,7 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc, struct ceph_mds_session *ts; int i, mds = session->s_mds; - if (mds >= mdsc->mdsmap->m_num_mds) + if (mds >= mdsc->mdsmap->possible_max_rank) return; mi = &mdsc->mdsmap->m_info[mds]; @@ -1967,7 +1985,7 @@ void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, if (mdsc->stopping) return; - get_session(session); + ceph_get_mds_session(session); if (queue_work(mdsc->fsc->cap_wq, &session->s_cap_release_work)) { dout("cap release work queued\n"); @@ -2072,7 +2090,6 @@ struct ceph_mds_request * ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode) { struct ceph_mds_request *req = kzalloc(sizeof(*req), GFP_NOFS); - struct timespec64 ts; if (!req) return ERR_PTR(-ENOMEM); @@ -2091,8 +2108,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode) init_completion(&req->r_safe_completion); INIT_LIST_HEAD(&req->r_unsafe_item); - ktime_get_coarse_real_ts64(&ts); - req->r_stamp = timespec64_trunc(ts, mdsc->fsc->sb->s_time_gran); + ktime_get_coarse_real_ts64(&req->r_stamp); req->r_op = op; req->r_direct_mode = mode; @@ -2518,6 +2534,26 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc, } /* + * called under mdsc->mutex + */ +static int __send_request(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session, + struct ceph_mds_request *req, + bool drop_cap_releases) +{ + int err; + + err = __prepare_send_request(mdsc, req, session->s_mds, + drop_cap_releases); + if (!err) { + ceph_msg_get(req->r_request); + ceph_con_send(&session->s_con, req->r_request); + } + + return err; +} + +/* * send request, or put it on the appropriate wait list. */ static void __do_request(struct ceph_mds_client *mdsc, @@ -2526,6 +2562,7 @@ static void __do_request(struct ceph_mds_client *mdsc, struct ceph_mds_session *session = NULL; int mds = -1; int err = 0; + bool random; if (req->r_err || test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) { if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) @@ -2558,15 +2595,14 @@ static void __do_request(struct ceph_mds_client *mdsc, if (!(mdsc->fsc->mount_options->flags & CEPH_MOUNT_OPT_MOUNTWAIT) && !ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) { - err = -ENOENT; - pr_info("probably no mds server is up\n"); + err = -EHOSTUNREACH; goto finish; } } put_request_session(req); - mds = __choose_mds(mdsc, req); + mds = __choose_mds(mdsc, req, &random); if (mds < 0 || ceph_mdsmap_get_state(mdsc->mdsmap, mds) < CEPH_MDS_STATE_ACTIVE) { dout("do_request no mds or not active, waiting for map\n"); @@ -2583,7 +2619,7 @@ static void __do_request(struct ceph_mds_client *mdsc, goto finish; } } - req->r_session = get_session(session); + req->r_session = ceph_get_mds_session(session); dout("do_request mds%d session %p state %s\n", mds, session, ceph_session_state_name(session->s_state)); @@ -2594,8 +2630,12 @@ static void __do_request(struct ceph_mds_client *mdsc, goto out_session; } if (session->s_state == CEPH_MDS_SESSION_NEW || - session->s_state == CEPH_MDS_SESSION_CLOSING) + session->s_state == CEPH_MDS_SESSION_CLOSING) { __open_session(mdsc, session); + /* retry the same mds later */ + if (random) + req->r_resend_mds = mds; + } list_add(&req->r_wait, &session->s_waiting); goto out_session; } @@ -2606,11 +2646,7 @@ static void __do_request(struct ceph_mds_client *mdsc, if (req->r_request_started == 0) /* note request start time */ req->r_request_started = jiffies; - err = __prepare_send_request(mdsc, req, mds, false); - if (!err) { - ceph_msg_get(req->r_request); - ceph_con_send(&session->s_con, req->r_request); - } + err = __send_request(mdsc, session, req, false); out_session: ceph_put_mds_session(session); @@ -2863,7 +2899,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) mutex_unlock(&mdsc->mutex); goto out; } else { - int mds = __choose_mds(mdsc, req); + int mds = __choose_mds(mdsc, req, NULL); if (mds >= 0 && mds != req->r_session->s_mds) { dout("but auth changed, so resending\n"); __do_request(mdsc, req); @@ -2879,6 +2915,10 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) set_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags); __unregister_request(mdsc, req); + /* last request during umount? */ + if (mdsc->stopping && !__get_oldest_req(mdsc)) + complete_all(&mdsc->safe_umount_waiters); + if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) { /* * We already handled the unsafe response, now do the @@ -2889,9 +2929,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) */ dout("got safe reply %llu, mds%d\n", tid, mds); - /* last unsafe request during umount? */ - if (mdsc->stopping && !__get_oldest_req(mdsc)) - complete_all(&mdsc->safe_umount_waiters); mutex_unlock(&mdsc->mutex); goto out; } @@ -3106,7 +3143,7 @@ static void handle_session(struct ceph_mds_session *session, mutex_lock(&mdsc->mutex); if (op == CEPH_SESSION_CLOSE) { - get_session(session); + ceph_get_mds_session(session); __unregister_session(mdsc, session); } /* FIXME: this ttl calculation is generous */ @@ -3144,6 +3181,7 @@ static void handle_session(struct ceph_mds_session *session, case CEPH_SESSION_CLOSE: if (session->s_state == CEPH_MDS_SESSION_RECONNECTING) pr_info("mds%d reconnect denied\n", session->s_mds); + session->s_state = CEPH_MDS_SESSION_CLOSED; cleanup_session_requests(mdsc, session); remove_session_caps(session); wake = 2; /* for good measure */ @@ -3211,7 +3249,6 @@ bad: return; } - /* * called under session->mutex. */ @@ -3220,18 +3257,12 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc, { struct ceph_mds_request *req, *nreq; struct rb_node *p; - int err; dout("replay_unsafe_requests mds%d\n", session->s_mds); mutex_lock(&mdsc->mutex); - list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item) { - err = __prepare_send_request(mdsc, req, session->s_mds, true); - if (!err) { - ceph_msg_get(req->r_request); - ceph_con_send(&session->s_con, req->r_request); - } - } + list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item) + __send_request(mdsc, session, req, true); /* * also re-send old requests when MDS enters reconnect stage. So that MDS @@ -3246,14 +3277,8 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc, if (req->r_attempts == 0) continue; /* only old requests */ if (req->r_session && - req->r_session->s_mds == session->s_mds) { - err = __prepare_send_request(mdsc, req, - session->s_mds, true); - if (!err) { - ceph_msg_get(req->r_request); - ceph_con_send(&session->s_con, req->r_request); - } - } + req->r_session->s_mds == session->s_mds) + __send_request(mdsc, session, req, true); } mutex_unlock(&mdsc->mutex); } @@ -3764,7 +3789,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, dout("check_new_map new %u old %u\n", newmap->m_epoch, oldmap->m_epoch); - for (i = 0; i < oldmap->m_num_mds && i < mdsc->max_sessions; i++) { + for (i = 0; i < oldmap->possible_max_rank && i < mdsc->max_sessions; i++) { if (!mdsc->sessions[i]) continue; s = mdsc->sessions[i]; @@ -3778,9 +3803,9 @@ static void check_new_map(struct ceph_mds_client *mdsc, ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "", ceph_session_state_name(s->s_state)); - if (i >= newmap->m_num_mds) { + if (i >= newmap->possible_max_rank) { /* force close session for stopped mds */ - get_session(s); + ceph_get_mds_session(s); __unregister_session(mdsc, s); __wake_requests(mdsc, &s->s_waiting); mutex_unlock(&mdsc->mutex); @@ -3835,7 +3860,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, } } - for (i = 0; i < newmap->m_num_mds && i < mdsc->max_sessions; i++) { + for (i = 0; i < newmap->possible_max_rank && i < mdsc->max_sessions; i++) { s = mdsc->sessions[i]; if (!s) continue; @@ -4381,7 +4406,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) mutex_lock(&mdsc->mutex); for (i = 0; i < mdsc->max_sessions; i++) { if (mdsc->sessions[i]) { - session = get_session(mdsc->sessions[i]); + session = ceph_get_mds_session(mdsc->sessions[i]); __unregister_session(mdsc, session); mutex_unlock(&mdsc->mutex); mutex_lock(&session->s_mutex); @@ -4609,11 +4634,8 @@ static struct ceph_connection *con_get(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; - if (get_session(s)) { - dout("mdsc con_get %p ok (%d)\n", s, refcount_read(&s->s_ref)); + if (ceph_get_mds_session(s)) return con; - } - dout("mdsc con_get %p FAIL\n", s); return NULL; } @@ -4621,7 +4643,6 @@ static void con_put(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; - dout("mdsc con_put %p (%d)\n", s, refcount_read(&s->s_ref) - 1); ceph_put_mds_session(s); } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 14c7e8c49970..27a7446e10d3 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -17,22 +17,31 @@ #include <linux/ceph/auth.h> /* The first 8 bits are reserved for old ceph releases */ -#define CEPHFS_FEATURE_MIMIC 8 -#define CEPHFS_FEATURE_REPLY_ENCODING 9 -#define CEPHFS_FEATURE_RECLAIM_CLIENT 10 -#define CEPHFS_FEATURE_LAZY_CAP_WANTED 11 -#define CEPHFS_FEATURE_MULTI_RECONNECT 12 +enum ceph_feature_type { + CEPHFS_FEATURE_MIMIC = 8, + CEPHFS_FEATURE_REPLY_ENCODING, + CEPHFS_FEATURE_RECLAIM_CLIENT, + CEPHFS_FEATURE_LAZY_CAP_WANTED, + CEPHFS_FEATURE_MULTI_RECONNECT, + + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MULTI_RECONNECT, +}; -#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ +/* + * This will always have the highest feature bit value + * as the last element of the array. + */ +#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ 0, 1, 2, 3, 4, 5, 6, 7, \ CEPHFS_FEATURE_MIMIC, \ CEPHFS_FEATURE_REPLY_ENCODING, \ CEPHFS_FEATURE_LAZY_CAP_WANTED, \ CEPHFS_FEATURE_MULTI_RECONNECT, \ + \ + CEPHFS_FEATURE_MAX, \ } #define CEPHFS_FEATURES_CLIENT_REQUIRED {} - /* * Some lock dependencies: * @@ -151,7 +160,8 @@ enum { CEPH_MDS_SESSION_RESTARTING = 5, CEPH_MDS_SESSION_RECONNECTING = 6, CEPH_MDS_SESSION_CLOSING = 7, - CEPH_MDS_SESSION_REJECTED = 8, + CEPH_MDS_SESSION_CLOSED = 8, + CEPH_MDS_SESSION_REJECTED = 9, }; struct ceph_mds_session { @@ -174,6 +184,7 @@ struct ceph_mds_session { /* protected by s_cap_lock */ spinlock_t s_cap_lock; + refcount_t s_ref; struct list_head s_caps; /* all caps issued by this session */ struct ceph_cap *s_cap_iterator; int s_nr_caps; @@ -188,7 +199,6 @@ struct ceph_mds_session { unsigned long s_renew_requested; /* last time we sent a renew req */ u64 s_renew_seq; - refcount_t s_ref; struct list_head s_waiting; /* waiting requests */ struct list_head s_unsafe; /* unsafe requests */ }; @@ -224,6 +234,7 @@ struct ceph_mds_request { struct rb_node r_node; struct ceph_mds_client *r_mdsc; + struct kref r_kref; int r_op; /* mds op code */ /* operation on what? */ @@ -294,7 +305,6 @@ struct ceph_mds_request { int r_resend_mds; /* mds to resend to next, if any*/ u32 r_sent_on_mseq; /* cap mseq request was sent at*/ - struct kref r_kref; struct list_head r_wait; struct completion r_completion; struct completion r_safe_completion; @@ -451,15 +461,10 @@ extern const char *ceph_mds_op_name(int op); extern struct ceph_mds_session * __ceph_lookup_mds_session(struct ceph_mds_client *, int mds); -static inline struct ceph_mds_session * -ceph_get_mds_session(struct ceph_mds_session *s) -{ - refcount_inc(&s->s_ref); - return s; -} - extern const char *ceph_session_state_name(int s); +extern struct ceph_mds_session * +ceph_get_mds_session(struct ceph_mds_session *s); extern void ceph_put_mds_session(struct ceph_mds_session *s); extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc, diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 471bac335fae..889627817e52 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -13,30 +13,25 @@ #include "super.h" +#define CEPH_MDS_IS_READY(i, ignore_laggy) \ + (m->m_info[i].state > 0 && ignore_laggy ? true : !m->m_info[i].laggy) -/* - * choose a random mds that is "up" (i.e. has a state > 0), or -1. - */ -int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) +static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy) { int n = 0; int i, j; - /* special case for one mds */ - if (1 == m->m_num_mds && m->m_info[0].state > 0) - return 0; - /* count */ - for (i = 0; i < m->m_num_mds; i++) - if (m->m_info[i].state > 0) + for (i = 0; i < m->possible_max_rank; i++) + if (CEPH_MDS_IS_READY(i, ignore_laggy)) n++; if (n == 0) return -1; /* pick */ n = prandom_u32() % n; - for (j = 0, i = 0; i < m->m_num_mds; i++) { - if (m->m_info[i].state > 0) + for (j = 0, i = 0; i < m->possible_max_rank; i++) { + if (CEPH_MDS_IS_READY(i, ignore_laggy)) j++; if (j > n) break; @@ -45,6 +40,20 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) return i; } +/* + * choose a random mds that is "up" (i.e. has a state > 0), or -1. + */ +int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) +{ + int mds; + + mds = __mdsmap_get_random_mds(m, false); + if (mds == m->possible_max_rank || mds == -1) + mds = __mdsmap_get_random_mds(m, true); + + return mds == m->possible_max_rank ? -1 : mds; +} + #define __decode_and_drop_type(p, end, type, bad) \ do { \ if (*p + sizeof(type) > end) \ @@ -138,14 +147,29 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) m->m_session_autoclose = ceph_decode_32(p); m->m_max_file_size = ceph_decode_64(p); m->m_max_mds = ceph_decode_32(p); - m->m_num_mds = m->m_max_mds; - m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS); + /* + * pick out the active nodes as the m_num_active_mds, the + * m_num_active_mds maybe larger than m_max_mds when decreasing + * the max_mds in cluster side, in other case it should less + * than or equal to m_max_mds. + */ + m->m_num_active_mds = n = ceph_decode_32(p); + + /* + * the possible max rank, it maybe larger than the m_num_active_mds, + * for example if the mds_max == 2 in the cluster, when the MDS(0) + * was laggy and being replaced by a new MDS, we will temporarily + * receive a new mds map with n_num_mds == 1 and the active MDS(1), + * and the mds rank >= m_num_active_mds. + */ + m->possible_max_rank = max(m->m_num_active_mds, m->m_max_mds); + + m->m_info = kcalloc(m->possible_max_rank, sizeof(*m->m_info), GFP_NOFS); if (!m->m_info) goto nomem; /* pick out active nodes from mds_info (state > 0) */ - n = ceph_decode_32(p); for (i = 0; i < n; i++) { u64 global_id; u32 namelen; @@ -215,18 +239,15 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) ceph_mds_state_name(state), laggy ? "(laggy)" : ""); - if (mds < 0 || state <= 0) + if (mds < 0 || mds >= m->possible_max_rank) { + pr_warn("mdsmap_decode got incorrect mds(%d)\n", mds); continue; + } - if (mds >= m->m_num_mds) { - int new_num = max(mds + 1, m->m_num_mds * 2); - void *new_m_info = krealloc(m->m_info, - new_num * sizeof(*m->m_info), - GFP_NOFS | __GFP_ZERO); - if (!new_m_info) - goto nomem; - m->m_info = new_m_info; - m->m_num_mds = new_num; + if (state <= 0) { + pr_warn("mdsmap_decode got incorrect state(%s)\n", + ceph_mds_state_name(state)); + continue; } info = &m->m_info[mds]; @@ -247,14 +268,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) info->export_targets = NULL; } } - if (m->m_num_mds > m->m_max_mds) { - /* find max up mds */ - for (i = m->m_num_mds; i >= m->m_max_mds; i--) { - if (i == 0 || m->m_info[i-1].state > 0) - break; - } - m->m_num_mds = i; - } /* pg_pools */ ceph_decode_32_safe(p, end, n, bad); @@ -296,14 +309,14 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) for (i = 0; i < n; i++) { s32 mds = ceph_decode_32(p); - if (mds >= 0 && mds < m->m_num_mds) { + if (mds >= 0 && mds < m->possible_max_rank) { if (m->m_info[mds].laggy) num_laggy++; } } m->m_num_laggy = num_laggy; - if (n > m->m_num_mds) { + if (n > m->possible_max_rank) { void *new_m_info = krealloc(m->m_info, n * sizeof(*m->m_info), GFP_NOFS | __GFP_ZERO); @@ -311,7 +324,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) goto nomem; m->m_info = new_m_info; } - m->m_num_mds = n; + m->possible_max_rank = n; } /* inc */ @@ -382,7 +395,7 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m) { int i; - for (i = 0; i < m->m_num_mds; i++) + for (i = 0; i < m->possible_max_rank; i++) kfree(m->m_info[i].export_targets); kfree(m->m_info); kfree(m->m_data_pg_pools); @@ -396,9 +409,9 @@ bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m) return false; if (m->m_damaged) return false; - if (m->m_num_laggy > 0) + if (m->m_num_laggy == m->m_num_active_mds) return false; - for (i = 0; i < m->m_num_mds; i++) { + for (i = 0; i < m->possible_max_rank; i++) { if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE) nr_active++; } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 29a795f975df..1d9f083b8a11 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -107,7 +107,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } - static int ceph_sync_fs(struct super_block *sb, int wait) { struct ceph_fs_client *fsc = ceph_sb_to_client(sb); @@ -163,13 +162,13 @@ enum ceph_recover_session_mode { ceph_recover_session_clean }; -static const struct fs_parameter_enum ceph_mount_param_enums[] = { - { Opt_recover_session, "no", ceph_recover_session_no }, - { Opt_recover_session, "clean", ceph_recover_session_clean }, +static const struct constant_table ceph_param_recover[] = { + { "no", ceph_recover_session_no }, + { "clean", ceph_recover_session_clean }, {} }; -static const struct fs_parameter_spec ceph_mount_param_specs[] = { +static const struct fs_parameter_spec ceph_mount_parameters[] = { fsparam_flag_no ("acl", Opt_acl), fsparam_flag_no ("asyncreaddir", Opt_asyncreaddir), fsparam_s32 ("caps_max", Opt_caps_max), @@ -179,8 +178,8 @@ static const struct fs_parameter_spec ceph_mount_param_specs[] = { fsparam_flag_no ("copyfrom", Opt_copyfrom), fsparam_flag_no ("dcache", Opt_dcache), fsparam_flag_no ("dirstat", Opt_dirstat), - __fsparam (fs_param_is_string, "fsc", Opt_fscache, - fs_param_neg_with_no | fs_param_v_optional), + fsparam_flag_no ("fsc", Opt_fscache), // fsc|nofsc + fsparam_string ("fsc", Opt_fscache), // fsc=... fsparam_flag_no ("ino32", Opt_ino32), fsparam_string ("mds_namespace", Opt_mds_namespace), fsparam_flag_no ("poolperm", Opt_poolperm), @@ -189,7 +188,7 @@ static const struct fs_parameter_spec ceph_mount_param_specs[] = { fsparam_flag_no ("rbytes", Opt_rbytes), fsparam_u32 ("readdir_max_bytes", Opt_readdir_max_bytes), fsparam_u32 ("readdir_max_entries", Opt_readdir_max_entries), - fsparam_enum ("recover_session", Opt_recover_session), + fsparam_enum ("recover_session", Opt_recover_session, ceph_param_recover), fsparam_flag_no ("require_active_mds", Opt_require_active_mds), fsparam_u32 ("rsize", Opt_rsize), fsparam_string ("snapdirname", Opt_snapdirname), @@ -198,12 +197,6 @@ static const struct fs_parameter_spec ceph_mount_param_specs[] = { {} }; -static const struct fs_parameter_description ceph_mount_parameters = { - .name = "ceph", - .specs = ceph_mount_param_specs, - .enums = ceph_mount_param_enums, -}; - struct ceph_parse_opts_ctx { struct ceph_options *copts; struct ceph_mount_options *opts; @@ -211,7 +204,6 @@ struct ceph_parse_opts_ctx { /* * Parse the source parameter. Distinguish the server list from the path. - * Internally we do not include the leading '/' in the path. * * The source will look like: * <server_spec>[,<server_spec>...]:[<path>] @@ -228,30 +220,33 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) dout("%s '%s'\n", __func__, dev_name); if (!dev_name || !*dev_name) - return invalf(fc, "ceph: Empty source"); + return invalfc(fc, "Empty source"); dev_name_end = strchr(dev_name, '/'); if (dev_name_end) { - if (strlen(dev_name_end) > 1) { - kfree(fsopt->server_path); - fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); - if (!fsopt->server_path) - return -ENOMEM; - } + kfree(fsopt->server_path); + + /* + * The server_path will include the whole chars from userland + * including the leading '/'. + */ + fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); + if (!fsopt->server_path) + return -ENOMEM; } else { dev_name_end = dev_name + strlen(dev_name); } dev_name_end--; /* back up to ':' separator */ if (dev_name_end < dev_name || *dev_name_end != ':') - return invalf(fc, "ceph: No path or : separator in source"); + return invalfc(fc, "No path or : separator in source"); dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); if (fsopt->server_path) dout("server path '%s'\n", fsopt->server_path); ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name, - pctx->copts, fc); + pctx->copts, fc->log.log); if (ret) return ret; @@ -269,11 +264,11 @@ static int ceph_parse_mount_param(struct fs_context *fc, unsigned int mode; int token, ret; - ret = ceph_parse_param(param, pctx->copts, fc); + ret = ceph_parse_param(param, pctx->copts, fc->log.log); if (ret != -ENOPARAM) return ret; - token = fs_parse(fc, &ceph_mount_parameters, param, &result); + token = fs_parse(fc, ceph_mount_parameters, param, &result); dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); if (token < 0) return token; @@ -300,7 +295,7 @@ static int ceph_parse_mount_param(struct fs_context *fc, break; case Opt_source: if (fc->source) - return invalf(fc, "ceph: Multiple sources specified"); + return invalfc(fc, "Multiple sources specified"); return ceph_parse_source(param, fc); case Opt_wsize: if (result.uint_32 < PAGE_SIZE || @@ -391,7 +386,7 @@ static int ceph_parse_mount_param(struct fs_context *fc, } break; #else - return invalf(fc, "ceph: fscache support is disabled"); + return invalfc(fc, "fscache support is disabled"); #endif case Opt_poolperm: if (!result.negated) @@ -422,7 +417,7 @@ static int ceph_parse_mount_param(struct fs_context *fc, #ifdef CONFIG_CEPH_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; #else - return invalf(fc, "ceph: POSIX ACL support is disabled"); + return invalfc(fc, "POSIX ACL support is disabled"); #endif } else { fc->sb_flags &= ~SB_POSIXACL; @@ -434,7 +429,7 @@ static int ceph_parse_mount_param(struct fs_context *fc, return 0; out_of_range: - return invalf(fc, "ceph: %s out of range", param->key); + return invalfc(fc, "%s out of range", param->key); } static void destroy_mount_options(struct ceph_mount_options *args) @@ -461,6 +456,73 @@ static int strcmp_null(const char *s1, const char *s2) return strcmp(s1, s2); } +/** + * path_remove_extra_slash - Remove the extra slashes in the server path + * @server_path: the server path and could be NULL + * + * Return NULL if the path is NULL or only consists of "/", or a string + * without any extra slashes including the leading slash(es) and the + * slash(es) at the end of the server path, such as: + * "//dir1////dir2///" --> "dir1/dir2" + */ +static char *path_remove_extra_slash(const char *server_path) +{ + const char *path = server_path; + const char *cur, *end; + char *buf, *p; + int len; + + /* if the server path is omitted */ + if (!path) + return NULL; + + /* remove all the leading slashes */ + while (*path == '/') + path++; + + /* if the server path only consists of slashes */ + if (*path == '\0') + return NULL; + + len = strlen(path); + + buf = kmalloc(len + 1, GFP_KERNEL); + if (!buf) + return ERR_PTR(-ENOMEM); + + end = path + len; + p = buf; + do { + cur = strchr(path, '/'); + if (!cur) + cur = end; + + len = cur - path; + + /* including one '/' */ + if (cur != end) + len += 1; + + memcpy(p, path, len); + p += len; + + while (cur <= end && *cur == '/') + cur++; + path = cur; + } while (path < end); + + *p = '\0'; + + /* + * remove the last slash if there has and just to make sure that + * we will get something like "dir1/dir2" + */ + if (*(--p) == '/') + *p = '\0'; + + return buf; +} + static int compare_mount_options(struct ceph_mount_options *new_fsopt, struct ceph_options *new_opt, struct ceph_fs_client *fsc) @@ -468,6 +530,7 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, struct ceph_mount_options *fsopt1 = new_fsopt; struct ceph_mount_options *fsopt2 = fsc->mount_options; int ofs = offsetof(struct ceph_mount_options, snapdir_name); + char *p1, *p2; int ret; ret = memcmp(fsopt1, fsopt2, ofs); @@ -480,9 +543,21 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace); if (ret) return ret; - ret = strcmp_null(fsopt1->server_path, fsopt2->server_path); + + p1 = path_remove_extra_slash(fsopt1->server_path); + if (IS_ERR(p1)) + return PTR_ERR(p1); + p2 = path_remove_extra_slash(fsopt2->server_path); + if (IS_ERR(p2)) { + kfree(p1); + return PTR_ERR(p2); + } + ret = strcmp_null(p1, p2); + kfree(p1); + kfree(p2); if (ret) return ret; + ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq); if (ret) return ret; @@ -637,6 +712,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, fsc->sb = NULL; fsc->mount_state = CEPH_MOUNT_MOUNTING; fsc->filp_gen = 1; + fsc->have_copy_from2 = true; atomic_long_set(&fsc->writeback_count, 0); @@ -788,7 +864,6 @@ static void destroy_caches(void) ceph_fscache_unregister(); } - /* * ceph_umount_begin - initiate forced umount. Tear down down the * mount, skipping steps that may hang while waiting for server(s). @@ -868,9 +943,6 @@ out: return root; } - - - /* * mount: join the ceph cluster, and open root directory. */ @@ -885,7 +957,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, mutex_lock(&fsc->client->mount_mutex); if (!fsc->sb->s_root) { - const char *path; + const char *path, *p; err = __ceph_open_session(fsc->client, started); if (err < 0) goto out; @@ -897,17 +969,22 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, goto out; } - if (!fsc->mount_options->server_path) { - path = ""; - dout("mount opening path \\t\n"); - } else { - path = fsc->mount_options->server_path + 1; - dout("mount opening path %s\n", path); + p = path_remove_extra_slash(fsc->mount_options->server_path); + if (IS_ERR(p)) { + err = PTR_ERR(p); + goto out; } + /* if the server path is omitted or just consists of '/' */ + if (!p) + path = ""; + else + path = p; + dout("mount opening path '%s'\n", path); ceph_fs_debugfs_init(fsc); root = open_root_dentry(fsc, path, started); + kfree(p); if (IS_ERR(root)) { err = PTR_ERR(root); goto out; @@ -1018,7 +1095,7 @@ static int ceph_get_tree(struct fs_context *fc) dout("ceph_get_tree\n"); if (!fc->source) - return invalf(fc, "ceph: No source"); + return invalfc(fc, "No source"); #ifdef CONFIG_CEPH_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; @@ -1070,6 +1147,11 @@ static int ceph_get_tree(struct fs_context *fc) return 0; out_splat: + if (!ceph_mdsmap_is_cluster_available(fsc->mdsc->mdsmap)) { + pr_info("No mds server is up or the cluster is laggy\n"); + err = -EHOSTUNREACH; + } + ceph_mdsc_close_sessions(fsc->mdsc); deactivate_locked_super(sb); goto out_final; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 3bf1a01cd536..1e456a9011bb 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -106,6 +106,8 @@ struct ceph_fs_client { unsigned long last_auto_reconnect; bool blacklisted; + bool have_copy_from2; + u32 filp_gen; loff_t max_file_size; diff --git a/fs/ceph/util.c b/fs/ceph/util.c new file mode 100644 index 000000000000..2c34875675bf --- /dev/null +++ b/fs/ceph/util.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Some non-inline ceph helpers + */ +#include <linux/module.h> +#include <linux/ceph/types.h> + +/* + * return true if @layout appears to be valid + */ +int ceph_file_layout_is_valid(const struct ceph_file_layout *layout) +{ + __u32 su = layout->stripe_unit; + __u32 sc = layout->stripe_count; + __u32 os = layout->object_size; + + /* stripe unit, object size must be non-zero, 64k increment */ + if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1))) + return 0; + if (!os || (os & (CEPH_MIN_STRIPE_UNIT-1))) + return 0; + /* object size must be a multiple of stripe unit */ + if (os < su || os % su) + return 0; + /* stripe count must be non-zero */ + if (!sc) + return 0; + return 1; +} + +void ceph_file_layout_from_legacy(struct ceph_file_layout *fl, + struct ceph_file_layout_legacy *legacy) +{ + fl->stripe_unit = le32_to_cpu(legacy->fl_stripe_unit); + fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count); + fl->object_size = le32_to_cpu(legacy->fl_object_size); + fl->pool_id = le32_to_cpu(legacy->fl_pg_pool); + if (fl->pool_id == 0 && fl->stripe_unit == 0 && + fl->stripe_count == 0 && fl->object_size == 0) + fl->pool_id = -1; +} + +void ceph_file_layout_to_legacy(struct ceph_file_layout *fl, + struct ceph_file_layout_legacy *legacy) +{ + legacy->fl_stripe_unit = cpu_to_le32(fl->stripe_unit); + legacy->fl_stripe_count = cpu_to_le32(fl->stripe_count); + legacy->fl_object_size = cpu_to_le32(fl->object_size); + if (fl->pool_id >= 0) + legacy->fl_pg_pool = cpu_to_le32(fl->pool_id); + else + legacy->fl_pg_pool = 0; +} + +int ceph_flags_to_mode(int flags) +{ + int mode; + +#ifdef O_DIRECTORY /* fixme */ + if ((flags & O_DIRECTORY) == O_DIRECTORY) + return CEPH_FILE_MODE_PIN; +#endif + + switch (flags & O_ACCMODE) { + case O_WRONLY: + mode = CEPH_FILE_MODE_WR; + break; + case O_RDONLY: + mode = CEPH_FILE_MODE_RD; + break; + case O_RDWR: + case O_ACCMODE: /* this is what the VFS does */ + mode = CEPH_FILE_MODE_RDWR; + break; + } +#ifdef O_LAZY + if (flags & O_LAZY) + mode |= CEPH_FILE_MODE_LAZY; +#endif + + return mode; +} + +int ceph_caps_for_mode(int mode) +{ + int caps = CEPH_CAP_PIN; + + if (mode & CEPH_FILE_MODE_RD) + caps |= CEPH_CAP_FILE_SHARED | + CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE; + if (mode & CEPH_FILE_MODE_WR) + caps |= CEPH_CAP_FILE_EXCL | + CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER | + CEPH_CAP_AUTH_SHARED | CEPH_CAP_AUTH_EXCL | + CEPH_CAP_XATTR_SHARED | CEPH_CAP_XATTR_EXCL; + if (mode & CEPH_FILE_MODE_LAZY) + caps |= CEPH_CAP_FILE_LAZYIO; + + return caps; +} diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index cb18ee637cb7..7b8a070a782d 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -655,7 +655,7 @@ static int __build_xattrs(struct inode *inode) u32 len; const char *name, *val; struct ceph_inode_info *ci = ceph_inode(inode); - int xattr_version; + u64 xattr_version; struct ceph_inode_xattr **xattrs = NULL; int err = 0; int i; @@ -851,7 +851,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, req_mask = __get_request_mask(inode); spin_lock(&ci->i_ceph_lock); - dout("getxattr %p ver=%lld index_ver=%lld\n", inode, + dout("getxattr %p name '%s' ver=%lld index_ver=%lld\n", inode, name, ci->i_xattrs.version, ci->i_xattrs.index_version); if (ci->i_xattrs.version == 0 || @@ -1078,7 +1078,8 @@ retry: } } - dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued)); + dout("setxattr %p name '%s' issued %s\n", inode, name, + ceph_cap_string(issued)); __build_xattrs(inode); required_blob_size = __get_required_blob_size(ci, name_len, val_len); diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 19f6e592b941..276e4b5ea8e0 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -611,12 +611,12 @@ static int cifs_stats_proc_open(struct inode *inode, struct file *file) return single_open(file, cifs_stats_proc_show, NULL); } -static const struct file_operations cifs_stats_proc_fops = { - .open = cifs_stats_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_stats_proc_write, +static const struct proc_ops cifs_stats_proc_ops = { + .proc_open = cifs_stats_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_stats_proc_write, }; #ifdef CONFIG_CIFS_SMB_DIRECT @@ -640,12 +640,12 @@ static int name##_open(struct inode *inode, struct file *file) \ return single_open(file, name##_proc_show, NULL); \ } \ \ -static const struct file_operations cifs_##name##_proc_fops = { \ - .open = name##_open, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ - .write = name##_write, \ +static const struct proc_ops cifs_##name##_proc_fops = { \ + .proc_open = name##_open, \ + .proc_read = seq_read, \ + .proc_lseek = seq_lseek, \ + .proc_release = single_release, \ + .proc_write = name##_write, \ } PROC_FILE_DEFINE(rdma_readwrite_threshold); @@ -659,11 +659,11 @@ PROC_FILE_DEFINE(smbd_receive_credit_max); #endif static struct proc_dir_entry *proc_fs_cifs; -static const struct file_operations cifsFYI_proc_fops; -static const struct file_operations cifs_lookup_cache_proc_fops; -static const struct file_operations traceSMB_proc_fops; -static const struct file_operations cifs_security_flags_proc_fops; -static const struct file_operations cifs_linux_ext_proc_fops; +static const struct proc_ops cifsFYI_proc_ops; +static const struct proc_ops cifs_lookup_cache_proc_ops; +static const struct proc_ops traceSMB_proc_ops; +static const struct proc_ops cifs_security_flags_proc_ops; +static const struct proc_ops cifs_linux_ext_proc_ops; void cifs_proc_init(void) @@ -678,18 +678,18 @@ cifs_proc_init(void) proc_create_single("open_files", 0400, proc_fs_cifs, cifs_debug_files_proc_show); - proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops); - proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops); - proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops); + proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_ops); + proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_ops); + proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_ops); proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs, - &cifs_linux_ext_proc_fops); + &cifs_linux_ext_proc_ops); proc_create("SecurityFlags", 0644, proc_fs_cifs, - &cifs_security_flags_proc_fops); + &cifs_security_flags_proc_ops); proc_create("LookupCacheEnabled", 0644, proc_fs_cifs, - &cifs_lookup_cache_proc_fops); + &cifs_lookup_cache_proc_ops); #ifdef CONFIG_CIFS_DFS_UPCALL - proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_fops); + proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_ops); #endif #ifdef CONFIG_CIFS_SMB_DIRECT @@ -774,12 +774,12 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer, return count; } -static const struct file_operations cifsFYI_proc_fops = { - .open = cifsFYI_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifsFYI_proc_write, +static const struct proc_ops cifsFYI_proc_ops = { + .proc_open = cifsFYI_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifsFYI_proc_write, }; static int cifs_linux_ext_proc_show(struct seq_file *m, void *v) @@ -805,12 +805,12 @@ static ssize_t cifs_linux_ext_proc_write(struct file *file, return count; } -static const struct file_operations cifs_linux_ext_proc_fops = { - .open = cifs_linux_ext_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_linux_ext_proc_write, +static const struct proc_ops cifs_linux_ext_proc_ops = { + .proc_open = cifs_linux_ext_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_linux_ext_proc_write, }; static int cifs_lookup_cache_proc_show(struct seq_file *m, void *v) @@ -836,12 +836,12 @@ static ssize_t cifs_lookup_cache_proc_write(struct file *file, return count; } -static const struct file_operations cifs_lookup_cache_proc_fops = { - .open = cifs_lookup_cache_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_lookup_cache_proc_write, +static const struct proc_ops cifs_lookup_cache_proc_ops = { + .proc_open = cifs_lookup_cache_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_lookup_cache_proc_write, }; static int traceSMB_proc_show(struct seq_file *m, void *v) @@ -867,12 +867,12 @@ static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer, return count; } -static const struct file_operations traceSMB_proc_fops = { - .open = traceSMB_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = traceSMB_proc_write, +static const struct proc_ops traceSMB_proc_ops = { + .proc_open = traceSMB_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = traceSMB_proc_write, }; static int cifs_security_flags_proc_show(struct seq_file *m, void *v) @@ -978,12 +978,12 @@ static ssize_t cifs_security_flags_proc_write(struct file *file, return count; } -static const struct file_operations cifs_security_flags_proc_fops = { - .open = cifs_security_flags_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_security_flags_proc_write, +static const struct proc_ops cifs_security_flags_proc_ops = { + .proc_open = cifs_security_flags_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_security_flags_proc_write, }; #else inline void cifs_proc_init(void) diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 9a384d1e27b4..43c1b43a07ec 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -8,6 +8,7 @@ #include <linux/jhash.h> #include <linux/ktime.h> #include <linux/slab.h> +#include <linux/proc_fs.h> #include <linux/nls.h> #include <linux/workqueue.h> #include "cifsglob.h" @@ -211,12 +212,12 @@ static int dfscache_proc_open(struct inode *inode, struct file *file) return single_open(file, dfscache_proc_show, NULL); } -const struct file_operations dfscache_proc_fops = { - .open = dfscache_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = dfscache_proc_write, +const struct proc_ops dfscache_proc_ops = { + .proc_open = dfscache_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = dfscache_proc_write, }; #ifdef CONFIG_CIFS_DEBUG2 diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index 76c732943f5f..99ee44f8ad07 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -24,7 +24,7 @@ struct dfs_cache_tgt_iterator { extern int dfs_cache_init(void); extern void dfs_cache_destroy(void); -extern const struct file_operations dfscache_proc_fops; +extern const struct proc_ops dfscache_proc_ops; extern int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nls_table *nls_codepage, int remap, diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index b1383c524b98..9ba623b601ec 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -113,6 +113,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) } /* revalidate if mtime or size have changed */ + fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) && cifs_i->server_eof == fattr->cf_eof) { cifs_dbg(FYI, "%s: inode %llu is unchanged\n", @@ -162,6 +163,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) cifs_revalidate_cache(inode, fattr); spin_lock(&inode->i_lock); + fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); + fattr->cf_atime = timestamp_truncate(fattr->cf_atime, inode); + fattr->cf_ctime = timestamp_truncate(fattr->cf_ctime, inode); /* we do not want atime to be less than mtime, it broke some apps */ if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime) < 0) inode->i_atime = fattr->cf_mtime; @@ -329,8 +333,7 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb) fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU; fattr->cf_uid = cifs_sb->mnt_uid; fattr->cf_gid = cifs_sb->mnt_gid; - ktime_get_real_ts64(&fattr->cf_mtime); - fattr->cf_mtime = timespec64_trunc(fattr->cf_mtime, sb->s_time_gran); + ktime_get_coarse_real_ts64(&fattr->cf_mtime); fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime; fattr->cf_nlink = 2; fattr->cf_flags = CIFS_FATTR_DFS_REFERRAL; @@ -607,10 +610,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, if (info->LastAccessTime) fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime); - else { - ktime_get_real_ts64(&fattr->cf_atime); - fattr->cf_atime = timespec64_trunc(fattr->cf_atime, sb->s_time_gran); - } + else + ktime_get_coarse_real_ts64(&fattr->cf_atime); fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime); fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime); diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 680aba9c00d5..fd0b5dd68f9e 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -76,14 +76,11 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr) if (ia_valid & ATTR_GID) sd_iattr->ia_gid = iattr->ia_gid; if (ia_valid & ATTR_ATIME) - sd_iattr->ia_atime = timestamp_truncate(iattr->ia_atime, - inode); + sd_iattr->ia_atime = iattr->ia_atime; if (ia_valid & ATTR_MTIME) - sd_iattr->ia_mtime = timestamp_truncate(iattr->ia_mtime, - inode); + sd_iattr->ia_mtime = iattr->ia_mtime; if (ia_valid & ATTR_CTIME) - sd_iattr->ia_ctime = timestamp_truncate(iattr->ia_ctime, - inode); + sd_iattr->ia_ctime = iattr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = iattr->ia_mode; diff --git a/fs/coredump.c b/fs/coredump.c index b1ea7dfbd149..f8296a82d01d 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -517,7 +517,7 @@ static void wait_for_dump_helpers(struct file *file) pipe_lock(pipe); pipe->readers++; pipe->writers--; - wake_up_interruptible_sync(&pipe->wait); + wake_up_interruptible_sync(&pipe->rd_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); pipe_unlock(pipe); @@ -525,7 +525,7 @@ static void wait_for_dump_helpers(struct file *file) * We actually want wait_event_freezable() but then we need * to clear TIF_SIGPENDING and improve dump_interrupted(). */ - wait_event_interruptible(pipe->wait, pipe->readers == 1); + wait_event_interruptible(pipe->rd_wait, pipe->readers == 1); pipe_lock(pipe); pipe->readers--; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 2f04024c3588..912308600d39 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -534,7 +534,7 @@ static int cramfs_read_super(struct super_block *sb, struct fs_context *fc, /* check for wrong endianness */ if (super->magic == CRAMFS_MAGIC_WEND) { if (!silent) - errorf(fc, "cramfs: wrong endianness"); + errorfc(fc, "wrong endianness"); return -EINVAL; } @@ -546,22 +546,22 @@ static int cramfs_read_super(struct super_block *sb, struct fs_context *fc, mutex_unlock(&read_mutex); if (super->magic != CRAMFS_MAGIC) { if (super->magic == CRAMFS_MAGIC_WEND && !silent) - errorf(fc, "cramfs: wrong endianness"); + errorfc(fc, "wrong endianness"); else if (!silent) - errorf(fc, "cramfs: wrong magic"); + errorfc(fc, "wrong magic"); return -EINVAL; } } /* get feature flags first */ if (super->flags & ~CRAMFS_SUPPORTED_FLAGS) { - errorf(fc, "cramfs: unsupported filesystem features"); + errorfc(fc, "unsupported filesystem features"); return -EINVAL; } /* Check that the root inode is in a sane state */ if (!S_ISDIR(super->root.mode)) { - errorf(fc, "cramfs: root is not a directory"); + errorfc(fc, "root is not a directory"); return -EINVAL; } /* correct strange, hard-coded permissions of mkcramfs */ @@ -580,12 +580,12 @@ static int cramfs_read_super(struct super_block *sb, struct fs_context *fc, sbi->magic = super->magic; sbi->flags = super->flags; if (root_offset == 0) - infof(fc, "cramfs: empty filesystem"); + infofc(fc, "empty filesystem"); else if (!(super->flags & CRAMFS_FLAG_SHIFTED_ROOT_OFFSET) && ((root_offset != sizeof(struct cramfs_super)) && (root_offset != 512 + sizeof(struct cramfs_super)))) { - errorf(fc, "cramfs: bad root offset %lu", root_offset); + errorfc(fc, "bad root offset %lu", root_offset); return -EINVAL; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index dc6cffc4feba..e742dfc66933 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -332,7 +332,10 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) parent = debugfs_mount->mnt_root; inode_lock(d_inode(parent)); - dentry = lookup_one_len(name, parent, strlen(name)); + if (unlikely(IS_DEADDIR(d_inode(parent)))) + dentry = ERR_PTR(-ENOENT); + else + dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { if (d_is_dir(dentry)) pr_err("Directory '%s' with parent '%s' already present!\n", @@ -681,62 +684,15 @@ static void __debugfs_file_removed(struct dentry *dentry) wait_for_completion(&fsd->active_users_drained); } -static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) -{ - int ret = 0; - - if (simple_positive(dentry)) { - dget(dentry); - if (d_is_dir(dentry)) { - ret = simple_rmdir(d_inode(parent), dentry); - if (!ret) - fsnotify_rmdir(d_inode(parent), dentry); - } else { - simple_unlink(d_inode(parent), dentry); - fsnotify_unlink(d_inode(parent), dentry); - } - if (!ret) - d_delete(dentry); - if (d_is_reg(dentry)) - __debugfs_file_removed(dentry); - dput(dentry); - } - return ret; -} - -/** - * debugfs_remove - removes a file or directory from the debugfs filesystem - * @dentry: a pointer to a the dentry of the file or directory to be - * removed. If this parameter is NULL or an error value, nothing - * will be done. - * - * This function removes a file or directory in debugfs that was previously - * created with a call to another debugfs function (like - * debugfs_create_file() or variants thereof.) - * - * This function is required to be called in order for the file to be - * removed, no automatic cleanup of files will happen when a module is - * removed, you are responsible here. - */ -void debugfs_remove(struct dentry *dentry) +static void remove_one(struct dentry *victim) { - struct dentry *parent; - int ret; - - if (IS_ERR_OR_NULL(dentry)) - return; - - parent = dentry->d_parent; - inode_lock(d_inode(parent)); - ret = __debugfs_remove(dentry, parent); - inode_unlock(d_inode(parent)); - if (!ret) - simple_release_fs(&debugfs_mount, &debugfs_mount_count); + if (d_is_reg(victim)) + __debugfs_file_removed(victim); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); } -EXPORT_SYMBOL_GPL(debugfs_remove); /** - * debugfs_remove_recursive - recursively removes a directory + * debugfs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. If this * parameter is NULL or an error value, nothing will be done. * @@ -748,65 +704,16 @@ EXPORT_SYMBOL_GPL(debugfs_remove); * removed, no automatic cleanup of files will happen when a module is * removed, you are responsible here. */ -void debugfs_remove_recursive(struct dentry *dentry) +void debugfs_remove(struct dentry *dentry) { - struct dentry *child, *parent; - if (IS_ERR_OR_NULL(dentry)) return; - parent = dentry; - down: - inode_lock(d_inode(parent)); - loop: - /* - * The parent->d_subdirs is protected by the d_lock. Outside that - * lock, the child can be unlinked and set to be freed which can - * use the d_u.d_child as the rcu head and corrupt this list. - */ - spin_lock(&parent->d_lock); - list_for_each_entry(child, &parent->d_subdirs, d_child) { - if (!simple_positive(child)) - continue; - - /* perhaps simple_empty(child) makes more sense */ - if (!list_empty(&child->d_subdirs)) { - spin_unlock(&parent->d_lock); - inode_unlock(d_inode(parent)); - parent = child; - goto down; - } - - spin_unlock(&parent->d_lock); - - if (!__debugfs_remove(child, parent)) - simple_release_fs(&debugfs_mount, &debugfs_mount_count); - - /* - * The parent->d_lock protects agaist child from unlinking - * from d_subdirs. When releasing the parent->d_lock we can - * no longer trust that the next pointer is valid. - * Restart the loop. We'll skip this one with the - * simple_positive() check. - */ - goto loop; - } - spin_unlock(&parent->d_lock); - - inode_unlock(d_inode(parent)); - child = parent; - parent = parent->d_parent; - inode_lock(d_inode(parent)); - - if (child != dentry) - /* go up */ - goto loop; - - if (!__debugfs_remove(child, parent)) - simple_release_fs(&debugfs_mount, &debugfs_mount_count); - inode_unlock(d_inode(parent)); + simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); + simple_recursive_removal(dentry, remove_one); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); } -EXPORT_SYMBOL_GPL(debugfs_remove_recursive); +EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_rename - rename a file/directory in the debugfs filesystem diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index cffa0c1ec829..019572c6b39a 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -524,16 +524,12 @@ out: static sector_t ecryptfs_bmap(struct address_space *mapping, sector_t block) { - int rc = 0; - struct inode *inode; - struct inode *lower_inode; - - inode = (struct inode *)mapping->host; - lower_inode = ecryptfs_inode_to_lower(inode); - if (lower_inode->i_mapping->a_ops->bmap) - rc = lower_inode->i_mapping->a_ops->bmap(lower_inode->i_mapping, - block); - return rc; + struct inode *lower_inode = ecryptfs_inode_to_lower(mapping->host); + int ret = bmap(lower_inode, &block); + + if (ret) + return 0; + return block; } const struct address_space_operations ecryptfs_aops = { diff --git a/fs/eventfd.c b/fs/eventfd.c index 8aa0ea8c55e8..78e41c7c3d05 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -24,6 +24,8 @@ #include <linux/seq_file.h> #include <linux/idr.h> +DEFINE_PER_CPU(int, eventfd_wake_count); + static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { @@ -60,12 +62,25 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) { unsigned long flags; + /* + * Deadlock or stack overflow issues can happen if we recurse here + * through waitqueue wakeup handlers. If the caller users potentially + * nested waitqueues with custom wakeup handlers, then it should + * check eventfd_signal_count() before calling this function. If + * it returns true, the eventfd_signal() call should be deferred to a + * safe context. + */ + if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count))) + return 0; + spin_lock_irqsave(&ctx->wqh.lock, flags); + this_cpu_inc(eventfd_wake_count); if (ULLONG_MAX - ctx->count < n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); + this_cpu_dec(eventfd_wake_count); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 88b213bd32bc..8434217549b3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6043,7 +6043,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); - } while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) && + } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8bd9afa81c54..b27b72107911 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3666,12 +3666,16 @@ static int check_swap_activate(struct swap_info_struct *sis, page_no < sis->max) { unsigned block_in_page; sector_t first_block; + sector_t block = 0; + int err = 0; cond_resched(); - first_block = bmap(inode, probe_block); - if (first_block == 0) + block = probe_block; + err = bmap(inode, &block); + if (err || !block) goto bad_bmap; + first_block = block; /* * It must be PAGE_SIZE aligned on-disk @@ -3683,11 +3687,13 @@ static int check_swap_activate(struct swap_info_struct *sis, for (block_in_page = 1; block_in_page < blocks_per_page; block_in_page++) { - sector_t block; - block = bmap(inode, probe_block + block_in_page); - if (block == 0) + block = probe_block + block_in_page; + err = bmap(inode, &block); + + if (err || !block) goto bad_bmap; + if (block != first_block + block_in_page) { /* Discontiguity */ probe_block++; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 86ddbb55d2b1..0d4da644df3b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -829,18 +829,12 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) inode->i_uid = attr->ia_uid; if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; - if (ia_valid & ATTR_ATIME) { - inode->i_atime = timestamp_truncate(attr->ia_atime, - inode); - } - if (ia_valid & ATTR_MTIME) { - inode->i_mtime = timestamp_truncate(attr->ia_mtime, - inode); - } - if (ia_valid & ATTR_CTIME) { - inode->i_ctime = timestamp_truncate(attr->ia_ctime, - inode); - } + if (ia_valid & ATTR_ATIME) + inode->i_atime = attr->ia_atime; + if (ia_valid & ATTR_MTIME) + inode->i_mtime = attr->ia_mtime; + if (ia_valid & ATTR_CTIME) + inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3314a0f3405e..9d02cdcdbb07 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -875,7 +875,7 @@ static int truncate_dnode(struct dnode_of_data *dn) /* get direct node */ page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); - if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) + if (PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 1e08bd54c5fb..f1b2a1fc2a6a 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -271,6 +271,14 @@ static inline struct timespec64 fat_timespec64_trunc_2secs(struct timespec64 ts) { return (struct timespec64){ ts.tv_sec & ~1ULL, 0 }; } + +static inline struct timespec64 fat_timespec64_trunc_10ms(struct timespec64 ts) +{ + if (ts.tv_nsec) + ts.tv_nsec -= ts.tv_nsec % 10000000UL; + return ts; +} + /* * truncate the various times with appropriate granularity: * root inode: @@ -308,7 +316,7 @@ int fat_truncate_time(struct inode *inode, struct timespec64 *now, int flags) } if (flags & S_CTIME) { if (sbi->options.isvfat) - inode->i_ctime = timespec64_trunc(*now, 10000000); + inode->i_ctime = fat_timespec64_trunc_10ms(*now); else inode->i_ctime = fat_timespec64_trunc_2secs(*now); } diff --git a/fs/filesystems.c b/fs/filesystems.c index 9135646e41ac..77bf5f95362d 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -74,7 +74,8 @@ int register_filesystem(struct file_system_type * fs) int res = 0; struct file_system_type ** p; - if (fs->parameters && !fs_validate_description(fs->parameters)) + if (fs->parameters && + !fs_validate_description(fs->name, fs->parameters)) return -EINVAL; BUG_ON(strchr(fs->name, '.')); diff --git a/fs/fs_context.c b/fs/fs_context.c index 138b5b4d621d..fc9f6ef93b55 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -45,6 +45,7 @@ static const struct constant_table common_set_sb_flag[] = { { "posixacl", SB_POSIXACL }, { "ro", SB_RDONLY }, { "sync", SB_SYNCHRONOUS }, + { }, }; static const struct constant_table common_clear_sb_flag[] = { @@ -53,6 +54,7 @@ static const struct constant_table common_clear_sb_flag[] = { { "nomand", SB_MANDLOCK }, { "rw", SB_RDONLY }, { "silent", SB_SILENT }, + { }, }; static const char *const forbidden_sb_flag[] = { @@ -175,14 +177,15 @@ int vfs_parse_fs_string(struct fs_context *fc, const char *key, struct fs_parameter param = { .key = key, - .type = fs_value_is_string, + .type = fs_value_is_flag, .size = v_size, }; - if (v_size > 0) { + if (value) { param.string = kmemdup_nul(value, v_size, GFP_KERNEL); if (!param.string) return -ENOMEM; + param.type = fs_value_is_string; } ret = vfs_parse_fs_param(fc, ¶m); @@ -268,6 +271,7 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, fc->fs_type = get_filesystem(fs_type); fc->cred = get_current_cred(); fc->net_ns = get_net(current->nsproxy->net_ns); + fc->log.prefix = fs_type->name; mutex_init(&fc->uapi_mutex); @@ -361,8 +365,8 @@ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) get_net(fc->net_ns); get_user_ns(fc->user_ns); get_cred(fc->cred); - if (fc->log) - refcount_inc(&fc->log->usage); + if (fc->log.log) + refcount_inc(&fc->log.log->usage); /* Can't call put until we've called ->dup */ ret = fc->ops->dup(fc, src_fc); @@ -385,64 +389,33 @@ EXPORT_SYMBOL(vfs_dup_fs_context); * @fc: The filesystem context to log to. * @fmt: The format of the buffer. */ -void logfc(struct fs_context *fc, const char *fmt, ...) +void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...) { - static const char store_failure[] = "OOM: Can't store error string"; - struct fc_log *log = fc ? fc->log : NULL; - const char *p; va_list va; - char *q; - u8 freeable; + struct va_format vaf = {.fmt = fmt, .va = &va}; va_start(va, fmt); - if (!strchr(fmt, '%')) { - p = fmt; - goto unformatted_string; - } - if (strcmp(fmt, "%s") == 0) { - p = va_arg(va, const char *); - goto unformatted_string; - } - - q = kvasprintf(GFP_KERNEL, fmt, va); -copied_string: - if (!q) - goto store_failure; - freeable = 1; - goto store_string; - -unformatted_string: - if ((unsigned long)p >= (unsigned long)__start_rodata && - (unsigned long)p < (unsigned long)__end_rodata) - goto const_string; - if (log && within_module_core((unsigned long)p, log->owner)) - goto const_string; - q = kstrdup(p, GFP_KERNEL); - goto copied_string; - -store_failure: - p = store_failure; -const_string: - q = (char *)p; - freeable = 0; -store_string: if (!log) { - switch (fmt[0]) { + switch (level) { case 'w': - printk(KERN_WARNING "%s\n", q + 2); + printk(KERN_WARNING "%s%s%pV\n", prefix ? prefix : "", + prefix ? ": " : "", &vaf); break; case 'e': - printk(KERN_ERR "%s\n", q + 2); + printk(KERN_ERR "%s%s%pV\n", prefix ? prefix : "", + prefix ? ": " : "", &vaf); break; default: - printk(KERN_NOTICE "%s\n", q + 2); + printk(KERN_NOTICE "%s%s%pV\n", prefix ? prefix : "", + prefix ? ": " : "", &vaf); break; } - if (freeable) - kfree(q); } else { unsigned int logsize = ARRAY_SIZE(log->buffer); u8 index; + char *q = kasprintf(GFP_KERNEL, "%c %s%s%pV\n", level, + prefix ? prefix : "", + prefix ? ": " : "", &vaf); index = log->head & (logsize - 1); BUILD_BUG_ON(sizeof(log->head) != sizeof(u8) || @@ -454,9 +427,11 @@ store_string: log->tail++; } - log->buffer[index] = q; - log->need_free &= ~(1 << index); - log->need_free |= freeable << index; + log->buffer[index] = q ? q : "OOM: Can't store error string"; + if (q) + log->need_free |= 1 << index; + else + log->need_free &= ~(1 << index); log->head++; } va_end(va); @@ -468,12 +443,12 @@ EXPORT_SYMBOL(logfc); */ static void put_fc_log(struct fs_context *fc) { - struct fc_log *log = fc->log; + struct fc_log *log = fc->log.log; int i; if (log) { if (refcount_dec_and_test(&log->usage)) { - fc->log = NULL; + fc->log.log = NULL; for (i = 0; i <= 7; i++) if (log->need_free & (1 << i)) kfree(log->buffer[i]); diff --git a/fs/fs_parser.c b/fs/fs_parser.c index d1930adce68d..7e6fb43f9541 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -20,42 +20,66 @@ static const struct constant_table bool_names[] = { { "no", false }, { "true", true }, { "yes", true }, + { }, }; +static const struct constant_table * +__lookup_constant(const struct constant_table *tbl, const char *name) +{ + for ( ; tbl->name; tbl++) + if (strcmp(name, tbl->name) == 0) + return tbl; + return NULL; +} + /** * lookup_constant - Look up a constant by name in an ordered table * @tbl: The table of constants to search. - * @tbl_size: The size of the table. * @name: The name to look up. * @not_found: The value to return if the name is not found. */ -int __lookup_constant(const struct constant_table *tbl, size_t tbl_size, - const char *name, int not_found) +int lookup_constant(const struct constant_table *tbl, const char *name, int not_found) { - unsigned int i; + const struct constant_table *p = __lookup_constant(tbl, name); - for (i = 0; i < tbl_size; i++) - if (strcmp(name, tbl[i].name) == 0) - return tbl[i].value; + return p ? p->value : not_found; +} +EXPORT_SYMBOL(lookup_constant); - return not_found; +static inline bool is_flag(const struct fs_parameter_spec *p) +{ + return p->type == NULL; } -EXPORT_SYMBOL(__lookup_constant); static const struct fs_parameter_spec *fs_lookup_key( - const struct fs_parameter_description *desc, - const char *name) + const struct fs_parameter_spec *desc, + struct fs_parameter *param, bool *negated) { - const struct fs_parameter_spec *p; - - if (!desc->specs) - return NULL; - - for (p = desc->specs; p->name; p++) - if (strcmp(p->name, name) == 0) + const struct fs_parameter_spec *p, *other = NULL; + const char *name = param->key; + bool want_flag = param->type == fs_value_is_flag; + + *negated = false; + for (p = desc; p->name; p++) { + if (strcmp(p->name, name) != 0) + continue; + if (likely(is_flag(p) == want_flag)) return p; - - return NULL; + other = p; + } + if (want_flag) { + if (name[0] == 'n' && name[1] == 'o' && name[2]) { + for (p = desc; p->name; p++) { + if (strcmp(p->name, name + 2) != 0) + continue; + if (!(p->flags & fs_param_neg_with_no)) + continue; + *negated = true; + return p; + } + } + } + return other; } /* @@ -76,172 +100,38 @@ static const struct fs_parameter_spec *fs_lookup_key( * unknown parameters are okay and -EINVAL if there was a conversion issue or * the parameter wasn't recognised and unknowns aren't okay. */ -int fs_parse(struct fs_context *fc, - const struct fs_parameter_description *desc, +int __fs_parse(struct p_log *log, + const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { const struct fs_parameter_spec *p; - const struct fs_parameter_enum *e; - int ret = -ENOPARAM, b; - result->has_value = !!param->string; - result->negated = false; result->uint_64 = 0; - p = fs_lookup_key(desc, param->key); - if (!p) { - /* If we didn't find something that looks like "noxxx", see if - * "xxx" takes the "no"-form negative - but only if there - * wasn't an value. - */ - if (result->has_value) - goto unknown_parameter; - if (param->key[0] != 'n' || param->key[1] != 'o' || !param->key[2]) - goto unknown_parameter; - - p = fs_lookup_key(desc, param->key + 2); - if (!p) - goto unknown_parameter; - if (!(p->flags & fs_param_neg_with_no)) - goto unknown_parameter; - result->boolean = false; - result->negated = true; - } + p = fs_lookup_key(desc, param, &result->negated); + if (!p) + return -ENOPARAM; if (p->flags & fs_param_deprecated) - warnf(fc, "%s: Deprecated parameter '%s'", - desc->name, param->key); - - if (result->negated) - goto okay; - - /* Certain parameter types only take a string and convert it. */ - switch (p->type) { - case __fs_param_wasnt_defined: - return -EINVAL; - case fs_param_is_u32: - case fs_param_is_u32_octal: - case fs_param_is_u32_hex: - case fs_param_is_s32: - case fs_param_is_u64: - case fs_param_is_enum: - case fs_param_is_string: - if (param->type != fs_value_is_string) - goto bad_value; - if (!result->has_value) { - if (p->flags & fs_param_v_optional) - goto okay; - goto bad_value; - } - /* Fall through */ - default: - break; - } + warn_plog(log, "Deprecated parameter '%s'", param->key); /* Try to turn the type we were given into the type desired by the * parameter and give an error if we can't. */ - switch (p->type) { - case fs_param_is_flag: - if (param->type != fs_value_is_flag && - (param->type != fs_value_is_string || result->has_value)) - return invalf(fc, "%s: Unexpected value for '%s'", - desc->name, param->key); - result->boolean = true; - goto okay; - - case fs_param_is_bool: - switch (param->type) { - case fs_value_is_flag: - result->boolean = true; - goto okay; - case fs_value_is_string: - if (param->size == 0) { - result->boolean = true; - goto okay; - } - b = lookup_constant(bool_names, param->string, -1); - if (b == -1) - goto bad_value; - result->boolean = b; - goto okay; - default: - goto bad_value; - } - - case fs_param_is_u32: - ret = kstrtouint(param->string, 0, &result->uint_32); - goto maybe_okay; - case fs_param_is_u32_octal: - ret = kstrtouint(param->string, 8, &result->uint_32); - goto maybe_okay; - case fs_param_is_u32_hex: - ret = kstrtouint(param->string, 16, &result->uint_32); - goto maybe_okay; - case fs_param_is_s32: - ret = kstrtoint(param->string, 0, &result->int_32); - goto maybe_okay; - case fs_param_is_u64: - ret = kstrtoull(param->string, 0, &result->uint_64); - goto maybe_okay; - - case fs_param_is_enum: - for (e = desc->enums; e->name[0]; e++) { - if (e->opt == p->opt && - strcmp(e->name, param->string) == 0) { - result->uint_32 = e->value; - goto okay; - } - } - goto bad_value; - - case fs_param_is_string: - goto okay; - case fs_param_is_blob: - if (param->type != fs_value_is_blob) - goto bad_value; - goto okay; - - case fs_param_is_fd: { - switch (param->type) { - case fs_value_is_string: - if (!result->has_value) - goto bad_value; - - ret = kstrtouint(param->string, 0, &result->uint_32); - break; - case fs_value_is_file: - result->uint_32 = param->dirfd; - ret = 0; - default: - goto bad_value; - } - - if (result->uint_32 > INT_MAX) - goto bad_value; - goto maybe_okay; - } - - case fs_param_is_blockdev: - case fs_param_is_path: - goto okay; - default: - BUG(); + if (is_flag(p)) { + if (param->type != fs_value_is_flag) + return inval_plog(log, "Unexpected value for '%s'", + param->key); + result->boolean = !result->negated; + } else { + int ret = p->type(log, p, param, result); + if (ret) + return ret; } - -maybe_okay: - if (ret < 0) - goto bad_value; -okay: return p->opt; - -bad_value: - return invalf(fc, "%s: Bad value for '%s'", desc->name, param->key); -unknown_parameter: - return -ENOPARAM; } -EXPORT_SYMBOL(fs_parse); +EXPORT_SYMBOL(__fs_parse); /** * fs_lookup_param - Look up a path referred to by a parameter @@ -267,9 +157,6 @@ int fs_lookup_param(struct fs_context *fc, return PTR_ERR(f); put_f = true; break; - case fs_value_is_filename_empty: - flags = LOOKUP_EMPTY; - /* Fall through */ case fs_value_is_filename: f = param->name; put_f = false; @@ -302,6 +189,124 @@ out: } EXPORT_SYMBOL(fs_lookup_param); +int fs_param_bad_value(struct p_log *log, struct fs_parameter *param) +{ + return inval_plog(log, "Bad value for '%s'", param->key); +} + +int fs_param_is_bool(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + int b; + if (param->type != fs_value_is_string) + return fs_param_bad_value(log, param); + b = lookup_constant(bool_names, param->string, -1); + if (b == -1) + return fs_param_bad_value(log, param); + result->boolean = b; + return 0; +} +EXPORT_SYMBOL(fs_param_is_bool); + +int fs_param_is_u32(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + int base = (unsigned long)p->data; + if (param->type != fs_value_is_string || + kstrtouint(param->string, base, &result->uint_32) < 0) + return fs_param_bad_value(log, param); + return 0; +} +EXPORT_SYMBOL(fs_param_is_u32); + +int fs_param_is_s32(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + if (param->type != fs_value_is_string || + kstrtoint(param->string, 0, &result->int_32) < 0) + return fs_param_bad_value(log, param); + return 0; +} +EXPORT_SYMBOL(fs_param_is_s32); + +int fs_param_is_u64(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + if (param->type != fs_value_is_string || + kstrtoull(param->string, 0, &result->uint_64) < 0) + return fs_param_bad_value(log, param); + return 0; +} +EXPORT_SYMBOL(fs_param_is_u64); + +int fs_param_is_enum(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + const struct constant_table *c; + if (param->type != fs_value_is_string) + return fs_param_bad_value(log, param); + c = __lookup_constant(p->data, param->string); + if (!c) + return fs_param_bad_value(log, param); + result->uint_32 = c->value; + return 0; +} +EXPORT_SYMBOL(fs_param_is_enum); + +int fs_param_is_string(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + if (param->type != fs_value_is_string || !*param->string) + return fs_param_bad_value(log, param); + return 0; +} +EXPORT_SYMBOL(fs_param_is_string); + +int fs_param_is_blob(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + if (param->type != fs_value_is_blob) + return fs_param_bad_value(log, param); + return 0; +} +EXPORT_SYMBOL(fs_param_is_blob); + +int fs_param_is_fd(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + switch (param->type) { + case fs_value_is_string: + if (kstrtouint(param->string, 0, &result->uint_32) < 0) + break; + if (result->uint_32 <= INT_MAX) + return 0; + break; + case fs_value_is_file: + result->uint_32 = param->dirfd; + if (result->uint_32 <= INT_MAX) + return 0; + break; + default: + break; + } + return fs_param_bad_value(log, param); +} +EXPORT_SYMBOL(fs_param_is_fd); + +int fs_param_is_blockdev(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + return 0; +} +EXPORT_SYMBOL(fs_param_is_blockdev); + +int fs_param_is_path(struct p_log *log, const struct fs_parameter_spec *p, + struct fs_parameter *param, struct fs_parse_result *result) +{ + return 0; +} +EXPORT_SYMBOL(fs_param_is_path); + #ifdef CONFIG_VALIDATE_FS_PARSER /** * validate_constant_table - Validate a constant table @@ -357,102 +362,26 @@ bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, * fs_validate_description - Validate a parameter description * @desc: The parameter description to validate. */ -bool fs_validate_description(const struct fs_parameter_description *desc) +bool fs_validate_description(const char *name, + const struct fs_parameter_spec *desc) { const struct fs_parameter_spec *param, *p2; - const struct fs_parameter_enum *e; - const char *name = desc->name; - unsigned int nr_params = 0; - bool good = true, enums = false; + bool good = true; pr_notice("*** VALIDATE %s ***\n", name); - if (!name[0]) { - pr_err("VALIDATE Parser: No name\n"); - name = "Unknown"; - good = false; - } - - if (desc->specs) { - for (param = desc->specs; param->name; param++) { - enum fs_parameter_type t = param->type; - - /* Check that the type is in range */ - if (t == __fs_param_wasnt_defined || - t >= nr__fs_parameter_type) { - pr_err("VALIDATE %s: PARAM[%s] Bad type %u\n", - name, param->name, t); - good = false; - } else if (t == fs_param_is_enum) { - enums = true; - } - - /* Check for duplicate parameter names */ - for (p2 = desc->specs; p2 < param; p2++) { - if (strcmp(param->name, p2->name) == 0) { - pr_err("VALIDATE %s: PARAM[%s]: Duplicate\n", - name, param->name); - good = false; - } - } - } - - nr_params = param - desc->specs; - } - - if (desc->enums) { - if (!nr_params) { - pr_err("VALIDATE %s: Enum table but no parameters\n", - name); - good = false; - goto no_enums; - } - if (!enums) { - pr_err("VALIDATE %s: Enum table but no enum-type values\n", - name); - good = false; - goto no_enums; - } - - for (e = desc->enums; e->name[0]; e++) { - /* Check that all entries in the enum table have at - * least one parameter that uses them. - */ - for (param = desc->specs; param->name; param++) { - if (param->opt == e->opt && - param->type != fs_param_is_enum) { - pr_err("VALIDATE %s: e[%tu] enum val for %s\n", - name, e - desc->enums, param->name); - good = false; - } - } - } - - /* Check that all enum-type parameters have at least one enum - * value in the enum table. - */ - for (param = desc->specs; param->name; param++) { - if (param->type != fs_param_is_enum) - continue; - for (e = desc->enums; e->name[0]; e++) - if (e->opt == param->opt) - break; - if (!e->name[0]) { - pr_err("VALIDATE %s: PARAM[%s] enum with no values\n", + for (param = desc; param->name; param++) { + /* Check for duplicate parameter names */ + for (p2 = desc; p2 < param; p2++) { + if (strcmp(param->name, p2->name) == 0) { + if (is_flag(param) != is_flag(p2)) + continue; + pr_err("VALIDATE %s: PARAM[%s]: Duplicate\n", name, param->name); good = false; } } - } else { - if (enums) { - pr_err("VALIDATE %s: enum-type values, but no enum table\n", - name); - good = false; - goto no_enums; - } } - -no_enums: return good; } #endif /* CONFIG_VALIDATE_FS_PARSER */ diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 9616af3768e1..08e91efbce53 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -111,7 +111,7 @@ extern void fscache_enqueue_object(struct fscache_object *); * object-list.c */ #ifdef CONFIG_FSCACHE_OBJECT_LIST -extern const struct file_operations fscache_objlist_fops; +extern const struct proc_ops fscache_objlist_proc_ops; extern void fscache_objlist_add(struct fscache_object *); extern void fscache_objlist_remove(struct fscache_object *); diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 72ebfe578f40..e106a1a1600d 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -7,6 +7,7 @@ #define FSCACHE_DEBUG_LEVEL COOKIE #include <linux/module.h> +#include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/key.h> @@ -405,9 +406,9 @@ static int fscache_objlist_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -const struct file_operations fscache_objlist_fops = { - .open = fscache_objlist_open, - .read = seq_read, - .llseek = seq_lseek, - .release = fscache_objlist_release, +const struct proc_ops fscache_objlist_proc_ops = { + .proc_open = fscache_objlist_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = fscache_objlist_release, }; diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 5523446e2952..90a7bc22f7e1 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -35,7 +35,7 @@ int __init fscache_proc_init(void) #ifdef CONFIG_FSCACHE_OBJECT_LIST if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, - &fscache_objlist_fops)) + &fscache_objlist_proc_ops)) goto error_objects; #endif diff --git a/fs/fsopen.c b/fs/fsopen.c index 043ffa8dc263..2fa3f241b762 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -25,7 +25,7 @@ static ssize_t fscontext_read(struct file *file, char __user *_buf, size_t len, loff_t *pos) { struct fs_context *fc = file->private_data; - struct fc_log *log = fc->log; + struct fc_log *log = fc->log.log; unsigned int logsize = ARRAY_SIZE(log->buffer); ssize_t ret; char *p; @@ -97,11 +97,11 @@ static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags) static int fscontext_alloc_log(struct fs_context *fc) { - fc->log = kzalloc(sizeof(*fc->log), GFP_KERNEL); - if (!fc->log) + fc->log.log = kzalloc(sizeof(*fc->log.log), GFP_KERNEL); + if (!fc->log.log) return -ENOMEM; - refcount_set(&fc->log->usage, 1); - fc->log->owner = fc->fs_type->owner; + refcount_set(&fc->log.log->usage, 1); + fc->log.log->owner = fc->fs_type->owner; return 0; } @@ -321,6 +321,7 @@ SYSCALL_DEFINE5(fsconfig, struct fs_context *fc; struct fd f; int ret; + int lookup_flags = 0; struct fs_parameter param = { .type = fs_value_is_undefined, @@ -409,19 +410,12 @@ SYSCALL_DEFINE5(fsconfig, goto out_key; } break; + case FSCONFIG_SET_PATH_EMPTY: + lookup_flags = LOOKUP_EMPTY; + /* fallthru */ case FSCONFIG_SET_PATH: param.type = fs_value_is_filename; - param.name = getname_flags(_value, 0, NULL); - if (IS_ERR(param.name)) { - ret = PTR_ERR(param.name); - goto out_key; - } - param.dirfd = aux; - param.size = strlen(param.name->name); - break; - case FSCONFIG_SET_PATH_EMPTY: - param.type = fs_value_is_filename_empty; - param.name = getname_flags(_value, LOOKUP_EMPTY, NULL); + param.name = getname_flags(_value, lookup_flags, NULL); if (IS_ERR(param.name)) { ret = PTR_ERR(param.name); goto out_key; diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 00015d851382..030f094910c3 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -451,8 +451,8 @@ static int cuse_send_init(struct cuse_conn *cc) ap->args.out_args[0].size = sizeof(ia->out); ap->args.out_args[0].value = &ia->out; ap->args.out_args[1].size = CUSE_INIT_INFO_MAX; - ap->args.out_argvar = 1; - ap->args.out_pages = 1; + ap->args.out_argvar = true; + ap->args.out_pages = true; ap->num_pages = 1; ap->pages = &ia->page; ap->descs = &ia->desc; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index ee190119f45c..de1e2fde60bd 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -818,7 +818,7 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent, struct fuse_conn *fc = get_fuse_conn(olddir); int err; - if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index ce715380143c..9d67b830fb7a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -803,6 +803,10 @@ static int fuse_do_readpage(struct file *file, struct page *page) attr_ver = fuse_get_attr_version(fc); + /* Don't overflow end offset */ + if (pos + (desc.length - 1) == LLONG_MAX) + desc.length--; + fuse_read_args_fill(&ia, file, pos, desc.length, FUSE_READ); res = fuse_simple_request(fc, &ia.ap.args); if (res < 0) @@ -888,6 +892,14 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file) ap->args.out_pages = true; ap->args.page_zeroing = true; ap->args.page_replace = true; + + /* Don't overflow end offset */ + if (pos + (count - 1) == LLONG_MAX) { + count--; + ap->descs[ap->num_pages - 1].length--; + } + WARN_ON((loff_t) (pos + count) < 0); + fuse_read_args_fill(ia, file, pos, count, FUSE_READ); ia->read.attr_ver = fuse_get_attr_version(fc); if (fc->async_read) { @@ -1397,9 +1409,9 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, } if (write) - ap->args.in_pages = 1; + ap->args.in_pages = true; else - ap->args.out_pages = 1; + ap->args.out_pages = true; *nbytesp = nbytes; @@ -1465,6 +1477,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, } ia = NULL; if (nres < 0) { + iov_iter_revert(iter, nbytes); err = nres; break; } @@ -1473,8 +1486,10 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, count -= nres; res += nres; pos += nres; - if (nres != nbytes) + if (nres != nbytes) { + iov_iter_revert(iter, nbytes - nres); break; + } if (count) { max_pages = iov_iter_npages(iter, fc->max_pages); ia = fuse_io_alloc(io, max_pages); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 16aec32f7f3d..95d712d44ca1 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -448,7 +448,7 @@ enum { OPT_ERR }; -static const struct fs_parameter_spec fuse_param_specs[] = { +static const struct fs_parameter_spec fuse_fs_parameters[] = { fsparam_string ("source", OPT_SOURCE), fsparam_u32 ("fd", OPT_FD), fsparam_u32oct ("rootmode", OPT_ROOTMODE), @@ -462,68 +462,63 @@ static const struct fs_parameter_spec fuse_param_specs[] = { {} }; -static const struct fs_parameter_description fuse_fs_parameters = { - .name = "fuse", - .specs = fuse_param_specs, -}; - static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct fuse_fs_context *ctx = fc->fs_private; int opt; - opt = fs_parse(fc, &fuse_fs_parameters, param, &result); + opt = fs_parse(fc, fuse_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case OPT_SOURCE: if (fc->source) - return invalf(fc, "fuse: Multiple sources specified"); + return invalfc(fc, "Multiple sources specified"); fc->source = param->string; param->string = NULL; break; case OPT_SUBTYPE: if (ctx->subtype) - return invalf(fc, "fuse: Multiple subtypes specified"); + return invalfc(fc, "Multiple subtypes specified"); ctx->subtype = param->string; param->string = NULL; return 0; case OPT_FD: ctx->fd = result.uint_32; - ctx->fd_present = 1; + ctx->fd_present = true; break; case OPT_ROOTMODE: if (!fuse_valid_type(result.uint_32)) - return invalf(fc, "fuse: Invalid rootmode"); + return invalfc(fc, "Invalid rootmode"); ctx->rootmode = result.uint_32; - ctx->rootmode_present = 1; + ctx->rootmode_present = true; break; case OPT_USER_ID: ctx->user_id = make_kuid(fc->user_ns, result.uint_32); if (!uid_valid(ctx->user_id)) - return invalf(fc, "fuse: Invalid user_id"); - ctx->user_id_present = 1; + return invalfc(fc, "Invalid user_id"); + ctx->user_id_present = true; break; case OPT_GROUP_ID: ctx->group_id = make_kgid(fc->user_ns, result.uint_32); if (!gid_valid(ctx->group_id)) - return invalf(fc, "fuse: Invalid group_id"); - ctx->group_id_present = 1; + return invalfc(fc, "Invalid group_id"); + ctx->group_id_present = true; break; case OPT_DEFAULT_PERMISSIONS: - ctx->default_permissions = 1; + ctx->default_permissions = true; break; case OPT_ALLOW_OTHER: - ctx->allow_other = 1; + ctx->allow_other = true; break; case OPT_MAX_READ: @@ -532,7 +527,7 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_BLKSIZE: if (!ctx->is_bdev) - return invalf(fc, "fuse: blksize only supported for fuseblk"); + return invalfc(fc, "blksize only supported for fuseblk"); ctx->blksize = result.uint_32; break; @@ -997,7 +992,7 @@ void fuse_send_init(struct fuse_conn *fc) /* Variable length argument used for backward compatibility with interface version < 7.5. Rest of init_out is zeroed by do_get_request(), so a short reply is not a problem */ - ia->args.out_argvar = 1; + ia->args.out_argvar = true; ia->args.out_args[0].size = sizeof(ia->out); ia->args.out_args[0].value = &ia->out; ia->args.force = true; @@ -1347,7 +1342,7 @@ static struct file_system_type fuse_fs_type = { .name = "fuse", .fs_flags = FS_HAS_SUBTYPE | FS_USERNS_MOUNT, .init_fs_context = fuse_init_fs_context, - .parameters = &fuse_fs_parameters, + .parameters = fuse_fs_parameters, .kill_sb = fuse_kill_sb_anon, }; MODULE_ALIAS_FS("fuse"); @@ -1363,7 +1358,7 @@ static struct file_system_type fuseblk_fs_type = { .owner = THIS_MODULE, .name = "fuseblk", .init_fs_context = fuse_init_fs_context, - .parameters = &fuse_fs_parameters, + .parameters = fuse_fs_parameters, .kill_sb = fuse_kill_sb_blk, .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE, }; diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 6a40f75a0d25..90e3f01bd796 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -332,7 +332,7 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx) return -ENOMEM; plus = fuse_use_readdirplus(inode, ctx); - ap->args.out_pages = 1; + ap->args.out_pages = true; ap->num_pages = 1; ap->pages = &page; ap->descs = &desc; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 9d58295ccf7a..cb26be6f4351 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -847,7 +847,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct gfs2_inode *ip = GFS2_I(inode); - ssize_t written = 0, ret; + ssize_t ret; ret = gfs2_rsqa_alloc(ip); if (ret) @@ -867,68 +867,58 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret <= 0) - goto out; - - /* We can write back this queue in page reclaim */ - current->backing_dev_info = inode_to_bdi(inode); + goto out_unlock; ret = file_remove_privs(file); if (ret) - goto out2; + goto out_unlock; ret = file_update_time(file); if (ret) - goto out2; + goto out_unlock; if (iocb->ki_flags & IOCB_DIRECT) { struct address_space *mapping = file->f_mapping; - loff_t pos, endbyte; - ssize_t buffered; + ssize_t buffered, ret2; - written = gfs2_file_direct_write(iocb, from); - if (written < 0 || !iov_iter_count(from)) - goto out2; + ret = gfs2_file_direct_write(iocb, from); + if (ret < 0 || !iov_iter_count(from)) + goto out_unlock; - ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); - if (unlikely(ret < 0)) - goto out2; - buffered = ret; + iocb->ki_flags |= IOCB_DSYNC; + current->backing_dev_info = inode_to_bdi(inode); + buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); + current->backing_dev_info = NULL; + if (unlikely(buffered <= 0)) + goto out_unlock; /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT - * semantics. + * semantics. If the writeback or invalidate fails, only report + * the direct I/O range as we don't know if the buffered pages + * made it to disk. */ - pos = iocb->ki_pos; - endbyte = pos + buffered - 1; - ret = filemap_write_and_wait_range(mapping, pos, endbyte); - if (!ret) { - iocb->ki_pos += buffered; - written += buffered; - invalidate_mapping_pages(mapping, - pos >> PAGE_SHIFT, - endbyte >> PAGE_SHIFT); - } else { - /* - * We don't know how much we wrote, so just return - * the number of bytes which were direct-written - */ - } + iocb->ki_pos += buffered; + ret2 = generic_write_sync(iocb, buffered); + invalidate_mapping_pages(mapping, + (iocb->ki_pos - buffered) >> PAGE_SHIFT, + (iocb->ki_pos - 1) >> PAGE_SHIFT); + if (!ret || ret2 > 0) + ret += ret2; } else { + current->backing_dev_info = inode_to_bdi(inode); ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); - if (likely(ret > 0)) + current->backing_dev_info = NULL; + if (likely(ret > 0)) { iocb->ki_pos += ret; + ret = generic_write_sync(iocb, ret); + } } -out2: - current->backing_dev_info = NULL; -out: +out_unlock: inode_unlock(inode); - if (likely(ret > 0)) { - /* Handle various SYNC-type writes */ - ret = generic_write_sync(iocb, ret); - } - return written ? written : ret; + return ret; } static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len, diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index d9431724b788..c090d5ad3f22 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -422,7 +422,7 @@ static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) + if (lh.lh_sequence >= head->lh_sequence) *head = lh; else { ret = true; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b3e904bcc02c..a1a8ef7ed3fd 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1252,6 +1252,7 @@ enum gfs2_param { Opt_upgrade, Opt_acl, Opt_quota, + Opt_quota_flag, Opt_suiddir, Opt_data, Opt_meta, @@ -1266,17 +1267,11 @@ enum gfs2_param { Opt_loccookie, }; -enum opt_quota { - Opt_quota_unset = 0, - Opt_quota_off, - Opt_quota_account, - Opt_quota_on, -}; - -static const unsigned int opt_quota_values[] = { - [Opt_quota_off] = GFS2_QUOTA_OFF, - [Opt_quota_account] = GFS2_QUOTA_ACCOUNT, - [Opt_quota_on] = GFS2_QUOTA_ON, +static const struct constant_table gfs2_param_quota[] = { + {"off", GFS2_QUOTA_OFF}, + {"account", GFS2_QUOTA_ACCOUNT}, + {"on", GFS2_QUOTA_ON}, + {} }; enum opt_data { @@ -1284,12 +1279,24 @@ enum opt_data { Opt_data_ordered = GFS2_DATA_ORDERED, }; +static const struct constant_table gfs2_param_data[] = { + {"writeback", Opt_data_writeback }, + {"ordered", Opt_data_ordered }, + {} +}; + enum opt_errors { Opt_errors_withdraw = GFS2_ERRORS_WITHDRAW, Opt_errors_panic = GFS2_ERRORS_PANIC, }; -static const struct fs_parameter_spec gfs2_param_specs[] = { +static const struct constant_table gfs2_param_errors[] = { + {"withdraw", Opt_errors_withdraw }, + {"panic", Opt_errors_panic }, + {} +}; + +static const struct fs_parameter_spec gfs2_fs_parameters[] = { fsparam_string ("lockproto", Opt_lockproto), fsparam_string ("locktable", Opt_locktable), fsparam_string ("hostdata", Opt_hostdata), @@ -1302,11 +1309,11 @@ static const struct fs_parameter_spec gfs2_param_specs[] = { fsparam_flag ("upgrade", Opt_upgrade), fsparam_flag_no("acl", Opt_acl), fsparam_flag_no("suiddir", Opt_suiddir), - fsparam_enum ("data", Opt_data), + fsparam_enum ("data", Opt_data, gfs2_param_data), fsparam_flag ("meta", Opt_meta), fsparam_flag_no("discard", Opt_discard), fsparam_s32 ("commit", Opt_commit), - fsparam_enum ("errors", Opt_errors), + fsparam_enum ("errors", Opt_errors, gfs2_param_errors), fsparam_s32 ("statfs_quantum", Opt_statfs_quantum), fsparam_s32 ("statfs_percent", Opt_statfs_percent), fsparam_s32 ("quota_quantum", Opt_quota_quantum), @@ -1314,27 +1321,11 @@ static const struct fs_parameter_spec gfs2_param_specs[] = { fsparam_flag_no("rgrplvb", Opt_rgrplvb), fsparam_flag_no("loccookie", Opt_loccookie), /* quota can be a flag or an enum so it gets special treatment */ - __fsparam(fs_param_is_enum, "quota", Opt_quota, fs_param_neg_with_no|fs_param_v_optional), - {} -}; - -static const struct fs_parameter_enum gfs2_param_enums[] = { - { Opt_quota, "off", Opt_quota_off }, - { Opt_quota, "account", Opt_quota_account }, - { Opt_quota, "on", Opt_quota_on }, - { Opt_data, "writeback", Opt_data_writeback }, - { Opt_data, "ordered", Opt_data_ordered }, - { Opt_errors, "withdraw", Opt_errors_withdraw }, - { Opt_errors, "panic", Opt_errors_panic }, + fsparam_flag_no("quota", Opt_quota_flag), + fsparam_enum("quota", Opt_quota, gfs2_param_quota), {} }; -static const struct fs_parameter_description gfs2_fs_parameters = { - .name = "gfs2", - .specs = gfs2_param_specs, - .enums = gfs2_param_enums, -}; - /* Parse a single mount parameter */ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) { @@ -1342,7 +1333,7 @@ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) struct fs_parse_result result; int o; - o = fs_parse(fc, &gfs2_fs_parameters, param, &result); + o = fs_parse(fc, gfs2_fs_parameters, param, &result); if (o < 0) return o; @@ -1370,7 +1361,7 @@ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_debug: if (result.boolean && args->ar_errors == GFS2_ERRORS_PANIC) - return invalf(fc, "gfs2: -o debug and -o errors=panic are mutually exclusive"); + return invalfc(fc, "-o debug and -o errors=panic are mutually exclusive"); args->ar_debug = result.boolean; break; case Opt_upgrade: @@ -1379,17 +1370,11 @@ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_acl: args->ar_posix_acl = result.boolean; break; + case Opt_quota_flag: + args->ar_quota = result.negated ? GFS2_QUOTA_OFF : GFS2_QUOTA_ON; + break; case Opt_quota: - /* The quota option can be a flag or an enum. A non-zero int_32 - result means that we have an enum index. Otherwise we have - to rely on the 'negated' flag to tell us whether 'quota' or - 'noquota' was specified. */ - if (result.negated) - args->ar_quota = GFS2_QUOTA_OFF; - else if (result.int_32 > 0) - args->ar_quota = opt_quota_values[result.int_32]; - else - args->ar_quota = GFS2_QUOTA_ON; + args->ar_quota = result.int_32; break; case Opt_suiddir: args->ar_suiddir = result.boolean; @@ -1406,27 +1391,27 @@ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_commit: if (result.int_32 <= 0) - return invalf(fc, "gfs2: commit mount option requires a positive numeric argument"); + return invalfc(fc, "commit mount option requires a positive numeric argument"); args->ar_commit = result.int_32; break; case Opt_statfs_quantum: if (result.int_32 < 0) - return invalf(fc, "gfs2: statfs_quantum mount option requires a non-negative numeric argument"); + return invalfc(fc, "statfs_quantum mount option requires a non-negative numeric argument"); args->ar_statfs_quantum = result.int_32; break; case Opt_quota_quantum: if (result.int_32 <= 0) - return invalf(fc, "gfs2: quota_quantum mount option requires a positive numeric argument"); + return invalfc(fc, "quota_quantum mount option requires a positive numeric argument"); args->ar_quota_quantum = result.int_32; break; case Opt_statfs_percent: if (result.int_32 < 0 || result.int_32 > 100) - return invalf(fc, "gfs2: statfs_percent mount option requires a numeric argument between 0 and 100"); + return invalfc(fc, "statfs_percent mount option requires a numeric argument between 0 and 100"); args->ar_statfs_percent = result.int_32; break; case Opt_errors: if (args->ar_debug && result.uint_32 == GFS2_ERRORS_PANIC) - return invalf(fc, "gfs2: -o debug and -o errors=panic are mutually exclusive"); + return invalfc(fc, "-o debug and -o errors=panic are mutually exclusive"); args->ar_errors = result.uint_32; break; case Opt_barrier: @@ -1439,7 +1424,7 @@ static int gfs2_parse_param(struct fs_context *fc, struct fs_parameter *param) args->ar_loccookie = result.boolean; break; default: - return invalf(fc, "gfs2: invalid mount option: %s", param->key); + return invalfc(fc, "invalid mount option: %s", param->key); } return 0; } @@ -1465,27 +1450,27 @@ static int gfs2_reconfigure(struct fs_context *fc) spin_unlock(>->gt_spin); if (strcmp(newargs->ar_lockproto, oldargs->ar_lockproto)) { - errorf(fc, "gfs2: reconfiguration of locking protocol not allowed"); + errorfc(fc, "reconfiguration of locking protocol not allowed"); return -EINVAL; } if (strcmp(newargs->ar_locktable, oldargs->ar_locktable)) { - errorf(fc, "gfs2: reconfiguration of lock table not allowed"); + errorfc(fc, "reconfiguration of lock table not allowed"); return -EINVAL; } if (strcmp(newargs->ar_hostdata, oldargs->ar_hostdata)) { - errorf(fc, "gfs2: reconfiguration of host data not allowed"); + errorfc(fc, "reconfiguration of host data not allowed"); return -EINVAL; } if (newargs->ar_spectator != oldargs->ar_spectator) { - errorf(fc, "gfs2: reconfiguration of spectator mode not allowed"); + errorfc(fc, "reconfiguration of spectator mode not allowed"); return -EINVAL; } if (newargs->ar_localflocks != oldargs->ar_localflocks) { - errorf(fc, "gfs2: reconfiguration of localflocks not allowed"); + errorfc(fc, "reconfiguration of localflocks not allowed"); return -EINVAL; } if (newargs->ar_meta != oldargs->ar_meta) { - errorf(fc, "gfs2: switching between gfs2 and gfs2meta not allowed"); + errorfc(fc, "switching between gfs2 and gfs2meta not allowed"); return -EINVAL; } if (oldargs->ar_spectator) @@ -1495,11 +1480,11 @@ static int gfs2_reconfigure(struct fs_context *fc) if (fc->sb_flags & SB_RDONLY) { error = gfs2_make_fs_ro(sdp); if (error) - errorf(fc, "gfs2: unable to remount read-only"); + errorfc(fc, "unable to remount read-only"); } else { error = gfs2_make_fs_rw(sdp); if (error) - errorf(fc, "gfs2: unable to remount read-write"); + errorfc(fc, "unable to remount read-write"); } } sdp->sd_args = *newargs; @@ -1644,7 +1629,7 @@ struct file_system_type gfs2_fs_type = { .name = "gfs2", .fs_flags = FS_REQUIRES_DEV, .init_fs_context = gfs2_init_fs_context, - .parameters = &gfs2_fs_parameters, + .parameters = gfs2_fs_parameters, .kill_sb = gfs2_kill_sb, .owner = THIS_MODULE, }; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a66e425884d1..aff8642f0c2e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -73,7 +73,7 @@ enum hugetlb_param { Opt_uid, }; -static const struct fs_parameter_spec hugetlb_param_specs[] = { +static const struct fs_parameter_spec hugetlb_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_string("min_size", Opt_min_size), fsparam_u32 ("mode", Opt_mode), @@ -84,11 +84,6 @@ static const struct fs_parameter_spec hugetlb_param_specs[] = { {} }; -static const struct fs_parameter_description hugetlb_fs_parameters = { - .name = "hugetlbfs", - .specs = hugetlb_param_specs, -}; - #ifdef CONFIG_NUMA static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma, struct inode *inode, pgoff_t index) @@ -1171,7 +1166,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par unsigned long ps; int opt; - opt = fs_parse(fc, &hugetlb_fs_parameters, param, &result); + opt = fs_parse(fc, hugetlb_fs_parameters, param, &result); if (opt < 0) return opt; @@ -1233,7 +1228,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par } bad_val: - return invalf(fc, "hugetlbfs: Bad value '%s' for mount option '%s'\n", + return invalfc(fc, "Bad value '%s' for mount option '%s'\n", param->string, param->key); } @@ -1358,7 +1353,7 @@ static int hugetlbfs_init_fs_context(struct fs_context *fc) static struct file_system_type hugetlbfs_fs_type = { .name = "hugetlbfs", .init_fs_context = hugetlbfs_init_fs_context, - .parameters = &hugetlb_fs_parameters, + .parameters = hugetlb_fs_parameters, .kill_sb = kill_litter_super, }; diff --git a/fs/inode.c b/fs/inode.c index ea15c6d9f274..7d57068b6b7a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1599,25 +1599,31 @@ retry: } EXPORT_SYMBOL(iput); +#ifdef CONFIG_BLOCK /** * bmap - find a block number in a file - * @inode: inode of file - * @block: block to find - * - * Returns the block number on the device holding the inode that - * is the disk block number for the block of the file requested. - * That is, asked for block 4 of inode 1 the function will return the - * disk block relative to the disk start that holds that block of the - * file. + * @inode: inode owning the block number being requested + * @block: pointer containing the block to find + * + * Replaces the value in *block with the block number on the device holding + * corresponding to the requested block number in the file. + * That is, asked for block 4 of inode 1 the function will replace the + * 4 in *block, with disk block relative to the disk start that holds that + * block of the file. + * + * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a + * hole, returns 0 and *block is also set to 0. */ -sector_t bmap(struct inode *inode, sector_t block) +int bmap(struct inode *inode, sector_t *block) { - sector_t res = 0; - if (inode->i_mapping->a_ops->bmap) - res = inode->i_mapping->a_ops->bmap(inode->i_mapping, block); - return res; + if (!inode->i_mapping->a_ops->bmap) + return -EINVAL; + + *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); + return 0; } EXPORT_SYMBOL(bmap); +#endif /* * With relative atime, only update atime if the previous atime is @@ -1683,12 +1689,9 @@ EXPORT_SYMBOL(generic_update_time); */ static int update_time(struct inode *inode, struct timespec64 *time, int flags) { - int (*update_time)(struct inode *, struct timespec64 *, int); - - update_time = inode->i_op->update_time ? inode->i_op->update_time : - generic_update_time; - - return update_time(inode, time, flags); + if (inode->i_op->update_time) + return inode->i_op->update_time(inode, time, flags); + return generic_update_time(inode, time, flags); } /** @@ -2154,30 +2157,6 @@ void inode_nohighmem(struct inode *inode) EXPORT_SYMBOL(inode_nohighmem); /** - * timespec64_trunc - Truncate timespec64 to a granularity - * @t: Timespec64 - * @gran: Granularity in ns. - * - * Truncate a timespec64 to a granularity. Always rounds down. gran must - * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). - */ -struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran) -{ - /* Avoid division in the common cases 1 ns and 1 s. */ - if (gran == 1) { - /* nothing */ - } else if (gran == NSEC_PER_SEC) { - t.tv_nsec = 0; - } else if (gran > 1 && gran < NSEC_PER_SEC) { - t.tv_nsec -= t.tv_nsec % gran; - } else { - WARN(1, "illegal file time granularity: %u", gran); - } - return t; -} -EXPORT_SYMBOL(timespec64_trunc); - -/** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated diff --git a/fs/io_uring.c b/fs/io_uring.c index 1806afddfea5..77f22c3da30f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -585,8 +585,7 @@ struct io_submit_state { * io_kiocb alloc cache */ void *reqs[IO_IOPOLL_BATCH]; - unsigned int free_reqs; - unsigned int cur_req; + unsigned int free_reqs; /* * File reference cache @@ -754,6 +753,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_files_update *ip, unsigned nr_args); static int io_grab_files(struct io_kiocb *req); +static void io_ring_file_ref_flush(struct fixed_file_data *data); static struct kmem_cache *req_cachep; @@ -1020,21 +1020,28 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) { + if (!ctx->cq_ev_fd) + return false; if (!ctx->eventfd_async) return true; return io_wq_current_is_worker() || in_interrupt(); } -static void io_cqring_ev_posted(struct io_ring_ctx *ctx) +static void __io_cqring_ev_posted(struct io_ring_ctx *ctx, bool trigger_ev) { if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); if (waitqueue_active(&ctx->sqo_wait)) wake_up(&ctx->sqo_wait); - if (ctx->cq_ev_fd && io_should_trigger_evfd(ctx)) + if (trigger_ev) eventfd_signal(ctx->cq_ev_fd, 1); } +static void io_cqring_ev_posted(struct io_ring_ctx *ctx) +{ + __io_cqring_ev_posted(ctx, io_should_trigger_evfd(ctx)); +} + /* Returns true if there are no backlogged entries after the flush */ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { @@ -1183,12 +1190,10 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, ret = 1; } state->free_reqs = ret - 1; - state->cur_req = 1; - req = state->reqs[0]; + req = state->reqs[ret - 1]; } else { - req = state->reqs[state->cur_req]; state->free_reqs--; - state->cur_req++; + req = state->reqs[state->free_reqs]; } got_it: @@ -1855,9 +1860,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, unsigned ioprio; int ret; - if (!req->file) - return -EBADF; - if (S_ISREG(file_inode(req->file)->i_mode)) req->flags |= REQ_F_ISREG; @@ -1866,8 +1868,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, req->flags |= REQ_F_CUR_POS; kiocb->ki_pos = req->file->f_pos; } - kiocb->ki_flags = iocb_flags(kiocb->ki_filp); kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); + kiocb->ki_flags = iocb_flags(kiocb->ki_filp); + ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); + if (unlikely(ret)) + return ret; ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -1879,10 +1884,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, } else kiocb->ki_ioprio = get_current_ioprio(); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - /* don't allow async punt if RWF_NOWAIT was requested */ if ((kiocb->ki_flags & IOCB_NOWAIT) || (req->file->f_flags & O_NONBLOCK)) @@ -2164,10 +2165,12 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, { if (!io_op_defs[req->opcode].async_ctx) return 0; - if (!req->io && io_alloc_async_ctx(req)) - return -ENOMEM; + if (!req->io) { + if (io_alloc_async_ctx(req)) + return -ENOMEM; - io_req_map_rw(req, io_size, iovec, fast_iov, iter); + io_req_map_rw(req, io_size, iovec, fast_iov, iter); + } req->work.func = io_rw_async; return 0; } @@ -2724,9 +2727,16 @@ static int io_fadvise(struct io_kiocb *req, struct io_kiocb **nxt, struct io_fadvise *fa = &req->fadvise; int ret; - /* DONTNEED may block, others _should_ not */ - if (fa->advice == POSIX_FADV_DONTNEED && force_nonblock) - return -EAGAIN; + if (force_nonblock) { + switch (fa->advice) { + case POSIX_FADV_NORMAL: + case POSIX_FADV_RANDOM: + case POSIX_FADV_SEQUENTIAL: + break; + default: + return -EAGAIN; + } + } ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); if (ret < 0) @@ -2837,16 +2847,13 @@ static void io_close_finish(struct io_wq_work **workptr) int ret; ret = filp_close(req->close.put_file, req->work.files); - if (ret < 0) { + if (ret < 0) req_set_fail_links(req); - } io_cqring_add_event(req, ret); } fput(req->close.put_file); - /* we bypassed the re-issue, drop the submission reference */ - io_put_req(req); io_put_req_find_next(req, &nxt); if (nxt) io_wq_assign_next(workptr, nxt); @@ -2888,7 +2895,13 @@ static int io_close(struct io_kiocb *req, struct io_kiocb **nxt, eagain: req->work.func = io_close_finish; - return -EAGAIN; + /* + * Do manual async queue here to avoid grabbing files - we don't + * need the files, and it'll cause io_close_finish() to close + * the file again and cause a double CQE entry for this request + */ + io_queue_async_work(req); + return 0; } static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -3083,7 +3096,8 @@ static int io_send(struct io_kiocb *req, struct io_kiocb **nxt, else if (force_nonblock) flags |= MSG_DONTWAIT; - ret = __sys_sendmsg_sock(sock, &msg, flags); + msg.msg_flags = flags; + ret = sock_sendmsg(sock, &msg); if (force_nonblock && ret == -EAGAIN) return -EAGAIN; if (ret == -ERESTARTSYS) @@ -3109,6 +3123,7 @@ static int io_recvmsg_prep(struct io_kiocb *req, sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); if (!io || req->opcode == IORING_OP_RECV) return 0; @@ -3227,7 +3242,7 @@ static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt, else if (force_nonblock) flags |= MSG_DONTWAIT; - ret = __sys_recvmsg_sock(sock, &msg, NULL, NULL, flags); + ret = sock_recvmsg(sock, &msg, flags); if (force_nonblock && ret == -EAGAIN) return -EAGAIN; if (ret == -ERESTARTSYS) @@ -3561,6 +3576,14 @@ static void io_poll_flush(struct io_wq_work **workptr) __io_poll_flush(req->ctx, nodes); } +static void io_poll_trigger_evfd(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + + eventfd_signal(req->ctx->cq_ev_fd, 1); + io_put_req(req); +} + static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { @@ -3586,14 +3609,22 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (llist_empty(&ctx->poll_llist) && spin_trylock_irqsave(&ctx->completion_lock, flags)) { + bool trigger_ev; + hash_del(&req->hash_node); io_poll_complete(req, mask, 0); - req->flags |= REQ_F_COMP_LOCKED; - io_put_req(req); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); - req = NULL; + trigger_ev = io_should_trigger_evfd(ctx); + if (trigger_ev && eventfd_signal_count()) { + trigger_ev = false; + req->work.func = io_poll_trigger_evfd; + } else { + req->flags |= REQ_F_COMP_LOCKED; + io_put_req(req); + req = NULL; + } + spin_unlock_irqrestore(&ctx->completion_lock, flags); + __io_cqring_ev_posted(ctx, trigger_ev); } else { req->result = mask; req->llist_node.next = NULL; @@ -4815,8 +4846,7 @@ static void io_submit_state_end(struct io_submit_state *state) blk_finish_plug(&state->plug); io_file_put(state); if (state->free_reqs) - kmem_cache_free_bulk(req_cachep, state->free_reqs, - &state->reqs[state->cur_req]); + kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); } /* @@ -5041,7 +5071,8 @@ static int io_sq_thread(void *data) * reap events and wake us up. */ if (inflight || - (!time_after(jiffies, timeout) && ret != -EBUSY)) { + (!time_after(jiffies, timeout) && ret != -EBUSY && + !percpu_ref_is_dying(&ctx->refs))) { cond_resched(); continue; } @@ -5231,15 +5262,10 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) if (!data) return -ENXIO; - /* protect against inflight atomic switch, which drops the ref */ - percpu_ref_get(&data->refs); - /* wait for existing switches */ - flush_work(&data->ref_work); percpu_ref_kill_and_confirm(&data->refs, io_file_ref_kill); - wait_for_completion(&data->done); - percpu_ref_put(&data->refs); - /* flush potential new switch */ flush_work(&data->ref_work); + wait_for_completion(&data->done); + io_ring_file_ref_flush(data); percpu_ref_exit(&data->refs); __io_sqe_files_unregister(ctx); @@ -5477,14 +5503,11 @@ struct io_file_put { struct completion *done; }; -static void io_ring_file_ref_switch(struct work_struct *work) +static void io_ring_file_ref_flush(struct fixed_file_data *data) { struct io_file_put *pfile, *tmp; - struct fixed_file_data *data; struct llist_node *node; - data = container_of(work, struct fixed_file_data, ref_work); - while ((node = llist_del_all(&data->put_llist)) != NULL) { llist_for_each_entry_safe(pfile, tmp, node, llist) { io_ring_file_put(data->ctx, pfile->file); @@ -5494,7 +5517,14 @@ static void io_ring_file_ref_switch(struct work_struct *work) kfree(pfile); } } +} +static void io_ring_file_ref_switch(struct work_struct *work) +{ + struct fixed_file_data *data; + + data = container_of(work, struct fixed_file_data, ref_work); + io_ring_file_ref_flush(data); percpu_ref_get(&data->refs); percpu_ref_switch_to_percpu(&data->refs); } @@ -5505,8 +5535,14 @@ static void io_file_data_ref_zero(struct percpu_ref *ref) data = container_of(ref, struct fixed_file_data, refs); - /* we can't safely switch from inside this context, punt to wq */ - queue_work(system_wq, &data->ref_work); + /* + * We can't safely switch from inside this context, punt to wq. If + * the table ref is going away, the table is being unregistered. + * Don't queue up the async work for that case, the caller will + * handle it. + */ + if (!percpu_ref_is_dying(&data->refs)) + queue_work(system_wq, &data->ref_work); } static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, @@ -6295,6 +6331,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) percpu_ref_kill(&ctx->refs); mutex_unlock(&ctx->uring_lock); + /* + * Wait for sq thread to idle, if we have one. It won't spin on new + * work after we've killed the ctx ref above. This is important to do + * before we cancel existing commands, as the thread could otherwise + * be queueing new work post that. If that's work we need to cancel, + * it could cause shutdown to hang. + */ + while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait)) + cpu_relax(); + io_kill_timeouts(ctx); io_poll_remove_all(ctx); @@ -6501,6 +6547,80 @@ out_fput: return submitted ? submitted : ret; } +static int io_uring_show_cred(int id, void *p, void *data) +{ + const struct cred *cred = p; + struct seq_file *m = data; + struct user_namespace *uns = seq_user_ns(m); + struct group_info *gi; + kernel_cap_t cap; + unsigned __capi; + int g; + + seq_printf(m, "%5d\n", id); + seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid)); + seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid)); + seq_puts(m, "\n\tGroups:\t"); + gi = cred->group_info; + for (g = 0; g < gi->ngroups; g++) { + seq_put_decimal_ull(m, g ? " " : "", + from_kgid_munged(uns, gi->gid[g])); + } + seq_puts(m, "\n\tCapEff:\t"); + cap = cred->cap_effective; + CAP_FOR_EACH_U32(__capi) + seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8); + seq_putc(m, '\n'); + return 0; +} + +static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) +{ + int i; + + mutex_lock(&ctx->uring_lock); + seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); + for (i = 0; i < ctx->nr_user_files; i++) { + struct fixed_file_table *table; + struct file *f; + + table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; + f = table->files[i & IORING_FILE_TABLE_MASK]; + if (f) + seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); + else + seq_printf(m, "%5u: <none>\n", i); + } + seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); + for (i = 0; i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *buf = &ctx->user_bufs[i]; + + seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, + (unsigned int) buf->len); + } + if (!idr_is_empty(&ctx->personality_idr)) { + seq_printf(m, "Personalities:\n"); + idr_for_each(&ctx->personality_idr, io_uring_show_cred, m); + } + mutex_unlock(&ctx->uring_lock); +} + +static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct io_ring_ctx *ctx = f->private_data; + + if (percpu_ref_tryget(&ctx->refs)) { + __io_uring_show_fdinfo(ctx, m); + percpu_ref_put(&ctx->refs); + } +} + static const struct file_operations io_uring_fops = { .release = io_uring_release, .flush = io_uring_flush, @@ -6511,6 +6631,7 @@ static const struct file_operations io_uring_fops = { #endif .poll = io_uring_poll, .fasync = io_uring_fasync, + .show_fdinfo = io_uring_show_fdinfo, }; static int io_allocate_scq_urings(struct io_ring_ctx *ctx, @@ -6963,6 +7084,39 @@ out_fput: static int __init io_uring_init(void) { +#define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \ + BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \ + BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \ +} while (0) + +#define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \ + __BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename) + BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64); + BUILD_BUG_SQE_ELEM(0, __u8, opcode); + BUILD_BUG_SQE_ELEM(1, __u8, flags); + BUILD_BUG_SQE_ELEM(2, __u16, ioprio); + BUILD_BUG_SQE_ELEM(4, __s32, fd); + BUILD_BUG_SQE_ELEM(8, __u64, off); + BUILD_BUG_SQE_ELEM(8, __u64, addr2); + BUILD_BUG_SQE_ELEM(16, __u64, addr); + BUILD_BUG_SQE_ELEM(24, __u32, len); + BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags); + BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags); + BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags); + BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags); + BUILD_BUG_SQE_ELEM(28, __u16, poll_events); + BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags); + BUILD_BUG_SQE_ELEM(28, __u32, msg_flags); + BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags); + BUILD_BUG_SQE_ELEM(28, __u32, accept_flags); + BUILD_BUG_SQE_ELEM(28, __u32, cancel_flags); + BUILD_BUG_SQE_ELEM(28, __u32, open_flags); + BUILD_BUG_SQE_ELEM(28, __u32, statx_flags); + BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice); + BUILD_BUG_SQE_ELEM(32, __u64, user_data); + BUILD_BUG_SQE_ELEM(40, __u16, buf_index); + BUILD_BUG_SQE_ELEM(42, __u16, personality); + BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); return 0; diff --git a/fs/ioctl.c b/fs/ioctl.c index 7c9a5df5a597..282d45be6f45 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -54,19 +54,32 @@ EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { - struct address_space *mapping = filp->f_mapping; - int res, block; + struct inode *inode = file_inode(filp); + int error, ur_block; + sector_t block; - /* do we support this mess? */ - if (!mapping->a_ops->bmap) - return -EINVAL; if (!capable(CAP_SYS_RAWIO)) return -EPERM; - res = get_user(block, p); - if (res) - return res; - res = mapping->a_ops->bmap(mapping, block); - return put_user(res, p); + + error = get_user(ur_block, p); + if (error) + return error; + + if (ur_block < 0) + return -EINVAL; + + block = ur_block; + error = bmap(inode, &block); + + if (error) + ur_block = 0; + else + ur_block = block; + + if (put_user(ur_block, p)) + error = -EFAULT; + + return error; } /** @@ -523,13 +536,9 @@ static int compat_ioctl_preallocate(struct file *file, int mode, static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { - struct inode *inode = file_inode(filp); - switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); - case FIONREAD: - return put_user(i_size_read(inode) - filp->f_pos, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); @@ -721,6 +730,13 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd, case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); + case FIONREAD: + if (!S_ISREG(inode->i_mode)) + return vfs_ioctl(filp, cmd, arg); + + return put_user(i_size_read(inode) - filp->f_pos, + (int __user *)argp); + default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 60bf8ff78913..a49d0e670ddf 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -794,18 +794,22 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, { int err = 0; unsigned long long ret; + sector_t block = 0; if (journal->j_inode) { - ret = bmap(journal->j_inode, blocknr); - if (ret) - *retp = ret; - else { + block = blocknr; + ret = bmap(journal->j_inode, &block); + + if (ret || !block) { printk(KERN_ALERT "%s: journal block not found " "at offset %lu on %s\n", __func__, blocknr, journal->j_devname); err = -EIO; jbd2_journal_abort(journal, err); + } else { + *retp = block; } + } else { *retp = blocknr; /* +journal->j_blk_offset */ } @@ -1074,12 +1078,11 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations jbd2_seq_info_fops = { - .owner = THIS_MODULE, - .open = jbd2_seq_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = jbd2_seq_info_release, +static const struct proc_ops jbd2_info_proc_ops = { + .proc_open = jbd2_seq_info_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = jbd2_seq_info_release, }; static struct proc_dir_entry *proc_jbd2_stats; @@ -1089,7 +1092,7 @@ static void jbd2_stats_proc_init(journal_t *journal) journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { proc_create_data("info", S_IRUGO, journal->j_proc_entry, - &jbd2_seq_info_fops, journal); + &jbd2_info_proc_ops, journal); } } @@ -1244,11 +1247,14 @@ journal_t *jbd2_journal_init_dev(struct block_device *bdev, journal_t *jbd2_journal_init_inode(struct inode *inode) { journal_t *journal; + sector_t blocknr; char *p; - unsigned long long blocknr; + int err = 0; + + blocknr = 0; + err = bmap(inode, &blocknr); - blocknr = bmap(inode, 0); - if (!blocknr) { + if (err || !blocknr) { pr_err("%s: Cannot locate journal superblock\n", __func__); return NULL; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 0e6406c4f362..05d7878dfad1 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -167,27 +167,21 @@ enum { Opt_rp_size, }; -static const struct fs_parameter_spec jffs2_param_specs[] = { - fsparam_enum ("compr", Opt_override_compr), - fsparam_u32 ("rp_size", Opt_rp_size), - {} -}; - -static const struct fs_parameter_enum jffs2_param_enums[] = { - { Opt_override_compr, "none", JFFS2_COMPR_MODE_NONE }, +static const struct constant_table jffs2_param_compr[] = { + {"none", JFFS2_COMPR_MODE_NONE }, #ifdef CONFIG_JFFS2_LZO - { Opt_override_compr, "lzo", JFFS2_COMPR_MODE_FORCELZO }, + {"lzo", JFFS2_COMPR_MODE_FORCELZO }, #endif #ifdef CONFIG_JFFS2_ZLIB - { Opt_override_compr, "zlib", JFFS2_COMPR_MODE_FORCEZLIB }, + {"zlib", JFFS2_COMPR_MODE_FORCEZLIB }, #endif {} }; -const struct fs_parameter_description jffs2_fs_parameters = { - .name = "jffs2", - .specs = jffs2_param_specs, - .enums = jffs2_param_enums, +static const struct fs_parameter_spec jffs2_fs_parameters[] = { + fsparam_enum ("compr", Opt_override_compr, jffs2_param_compr), + fsparam_u32 ("rp_size", Opt_rp_size), + {} }; static int jffs2_parse_param(struct fs_context *fc, struct fs_parameter *param) @@ -196,7 +190,7 @@ static int jffs2_parse_param(struct fs_context *fc, struct fs_parameter *param) struct jffs2_sb_info *c = fc->s_fs_info; int opt; - opt = fs_parse(fc, &jffs2_fs_parameters, param, &result); + opt = fs_parse(fc, jffs2_fs_parameters, param, &result); if (opt < 0) return opt; @@ -339,7 +333,7 @@ static struct file_system_type jffs2_fs_type = { .owner = THIS_MODULE, .name = "jffs2", .init_fs_context = jffs2_init_fs_context, - .parameters = &jffs2_fs_parameters, + .parameters = jffs2_fs_parameters, .kill_sb = jffs2_kill_sb, }; MODULE_ALIAS_FS("jffs2"); diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c index 888cdd685a1e..44b62b3c322e 100644 --- a/fs/jfs/jfs_debug.c +++ b/fs/jfs/jfs_debug.c @@ -43,12 +43,12 @@ static ssize_t jfs_loglevel_proc_write(struct file *file, return count; } -static const struct file_operations jfs_loglevel_proc_fops = { - .open = jfs_loglevel_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = jfs_loglevel_proc_write, +static const struct proc_ops jfs_loglevel_proc_ops = { + .proc_open = jfs_loglevel_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = jfs_loglevel_proc_write, }; #endif @@ -68,7 +68,7 @@ void jfs_proc_init(void) #endif #ifdef CONFIG_JFS_DEBUG proc_create_single("TxAnchor", 0, base, jfs_txanchor_proc_show); - proc_create("loglevel", 0, base, &jfs_loglevel_proc_fops); + proc_create("loglevel", 0, base, &jfs_loglevel_proc_ops); #endif } diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index caade185e568..7dfcab2a2da6 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -4027,7 +4027,6 @@ static int dbGetL2AGSize(s64 nblocks) */ #define MAXL0PAGES (1 + LPERCTL) #define MAXL1PAGES (1 + LPERCTL * MAXL0PAGES) -#define MAXL2PAGES (1 + LPERCTL * MAXL1PAGES) /* * convert number of map pages to the zero origin top dmapctl level diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index eac277c63d42..d0f7a5abd9a9 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -160,9 +160,9 @@ static inline void set_inode_attr(struct inode *inode, { inode->i_uid = attrs->ia_uid; inode->i_gid = attrs->ia_gid; - inode->i_atime = timestamp_truncate(attrs->ia_atime, inode); - inode->i_mtime = timestamp_truncate(attrs->ia_mtime, inode); - inode->i_ctime = timestamp_truncate(attrs->ia_ctime, inode); + inode->i_atime = attrs->ia_atime; + inode->i_mtime = attrs->ia_mtime; + inode->i_ctime = attrs->ia_ctime; } static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) diff --git a/fs/libfs.c b/fs/libfs.c index 1463b038ffc4..c686bd9caac6 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -19,6 +19,7 @@ #include <linux/buffer_head.h> /* sync_mapping_buffers */ #include <linux/fs_context.h> #include <linux/pseudo_fs.h> +#include <linux/fsnotify.h> #include <linux/uaccess.h> @@ -239,6 +240,75 @@ const struct inode_operations simple_dir_inode_operations = { }; EXPORT_SYMBOL(simple_dir_inode_operations); +static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) +{ + struct dentry *child = NULL; + struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs; + + spin_lock(&parent->d_lock); + while ((p = p->next) != &parent->d_subdirs) { + struct dentry *d = container_of(p, struct dentry, d_child); + if (simple_positive(d)) { + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(d)) + child = dget_dlock(d); + spin_unlock(&d->d_lock); + if (likely(child)) + break; + } + } + spin_unlock(&parent->d_lock); + dput(prev); + return child; +} + +void simple_recursive_removal(struct dentry *dentry, + void (*callback)(struct dentry *)) +{ + struct dentry *this = dget(dentry); + while (true) { + struct dentry *victim = NULL, *child; + struct inode *inode = this->d_inode; + + inode_lock(inode); + if (d_is_dir(this)) + inode->i_flags |= S_DEAD; + while ((child = find_next_child(this, victim)) == NULL) { + // kill and ascend + // update metadata while it's still locked + inode->i_ctime = current_time(inode); + clear_nlink(inode); + inode_unlock(inode); + victim = this; + this = this->d_parent; + inode = this->d_inode; + inode_lock(inode); + if (simple_positive(victim)) { + d_invalidate(victim); // avoid lost mounts + if (d_is_dir(victim)) + fsnotify_rmdir(inode, victim); + else + fsnotify_unlink(inode, victim); + if (callback) + callback(victim); + dput(victim); // unpin it + } + if (victim == dentry) { + inode->i_ctime = inode->i_mtime = + current_time(inode); + if (d_is_dir(dentry)) + drop_nlink(inode); + inode_unlock(inode); + dput(dentry); + return; + } + } + inode_unlock(inode); + this = child; + } +} +EXPORT_SYMBOL(simple_recursive_removal); + static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; diff --git a/fs/lockd/procfs.c b/fs/lockd/procfs.c index ca9228a56d65..a01f08c8c2f3 100644 --- a/fs/lockd/procfs.c +++ b/fs/lockd/procfs.c @@ -60,11 +60,11 @@ nlm_end_grace_read(struct file *file, char __user *buf, size_t size, return simple_read_from_buffer(buf, size, pos, resp, sizeof(resp)); } -static const struct file_operations lockd_end_grace_operations = { - .write = nlm_end_grace_write, - .read = nlm_end_grace_read, - .llseek = default_llseek, - .release = simple_transaction_release, +static const struct proc_ops lockd_end_grace_proc_ops = { + .proc_write = nlm_end_grace_write, + .proc_read = nlm_end_grace_read, + .proc_lseek = default_llseek, + .proc_release = simple_transaction_release, }; int __init @@ -76,7 +76,7 @@ lockd_create_procfs(void) if (!entry) return -ENOMEM; entry = proc_create("nlm_end_grace", S_IRUGO|S_IWUSR, entry, - &lockd_end_grace_operations); + &lockd_end_grace_proc_ops); if (!entry) { remove_proc_entry("fs/lockd", NULL); return -ENOMEM; diff --git a/fs/namespace.c b/fs/namespace.c index 5e1bf611a9eb..85b5f7bea82e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2979,39 +2979,10 @@ static void shrink_submounts(struct mount *mnt) } } -/* - * Some copy_from_user() implementations do not return the exact number of - * bytes remaining to copy on a fault. But copy_mount_options() requires that. - * Note that this function differs from copy_from_user() in that it will oops - * on bad values of `to', rather than returning a short copy. - */ -static long exact_copy_from_user(void *to, const void __user * from, - unsigned long n) -{ - char *t = to; - const char __user *f = from; - char c; - - if (!access_ok(from, n)) - return n; - - while (n) { - if (__get_user(c, f)) { - memset(t, 0, n); - break; - } - *t++ = c; - f++; - n--; - } - return n; -} - void *copy_mount_options(const void __user * data) { - int i; - unsigned long size; char *copy; + unsigned size; if (!data) return NULL; @@ -3020,22 +2991,16 @@ void *copy_mount_options(const void __user * data) if (!copy) return ERR_PTR(-ENOMEM); - /* We only care that *some* data at the address the user - * gave us is valid. Just in case, we'll zero - * the remainder of the page. - */ - /* copy_from_user cannot cross TASK_SIZE ! */ - size = TASK_SIZE - (unsigned long)untagged_addr(data); - if (size > PAGE_SIZE) - size = PAGE_SIZE; + size = PAGE_SIZE - offset_in_page(data); - i = size - exact_copy_from_user(copy, data, size); - if (!i) { + if (copy_from_user(copy, data, size)) { kfree(copy); return ERR_PTR(-EFAULT); } - if (i != PAGE_SIZE) - memset(copy + i, 0, PAGE_SIZE - i); + if (size != PAGE_SIZE) { + if (copy_from_user(copy + size, data + size, PAGE_SIZE - size)) + memset(copy + size, 0, PAGE_SIZE - size); + } return copy; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 295a7a21b774..40b6c5ac46c0 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -90,7 +90,7 @@ config NFS_V4 config NFS_SWAP bool "Provide swap over NFS support" default n - depends on NFS_FS + depends on NFS_FS && SWAP select SUNRPC_SWAP help This option enables swapon to work on files located on NFS mounts. @@ -196,3 +196,12 @@ config NFS_DEBUG depends on NFS_FS && SUNRPC_DEBUG select CRC32 default y + +config NFS_DISABLE_UDP_SUPPORT + bool "NFS: Disable NFS UDP protocol support" + depends on NFS_FS + default y + help + Choose Y here to disable the use of NFS over UDP. NFS over UDP + on modern networks (1Gb+) can lead to data corruption caused by + fragmentation during high loads. diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 34cdeaecccf6..2433c3e03cfa 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -9,7 +9,7 @@ CFLAGS_nfstrace.o += -I$(src) nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ io.o direct.o pagelist.o read.o symlink.o unlink.o \ write.o namespace.o mount_clnt.o nfstrace.o \ - export.o sysfs.o + export.o sysfs.o fs_context.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 03a20f5716c7..79ff172eb1c8 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -18,6 +18,7 @@ #include "callback.h" #include "internal.h" #include "nfs4session.h" +#include "nfs4trace.h" #define CB_OP_TAGLEN_MAXSZ (512) #define CB_OP_HDR_RES_MAXSZ (2 * 4) // opcode, status @@ -946,9 +947,13 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) if (hdr_arg.minorversion == 0) { cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident); - if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp)) { - if (cps.clp) - nfs_put_client(cps.clp); + if (!cps.clp) { + trace_nfs_cb_no_clp(rqstp->rq_xid, hdr_arg.cb_ident); + goto out_invalidcred; + } + if (!check_gss_callback_principal(cps.clp, rqstp)) { + trace_nfs_cb_badprinc(rqstp->rq_xid, hdr_arg.cb_ident); + nfs_put_client(cps.clp); goto out_invalidcred; } } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 02110a30a49e..989c30c98511 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -474,6 +474,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, to->to_maxval = to->to_initval; to->to_exponential = 0; break; +#ifndef CONFIG_NFS_DISABLE_UDP_SUPPORT case XPRT_TRANSPORT_UDP: if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_UDP_RETRANS; @@ -484,6 +485,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, to->to_maxval = NFS_MAX_UDP_TIMEOUT; to->to_exponential = 1; break; +#endif default: BUG(); } @@ -580,8 +582,10 @@ static int nfs_start_lockd(struct nfs_server *server) default: nlm_init.protocol = IPPROTO_TCP; break; +#ifndef CONFIG_NFS_DISABLE_UDP_SUPPORT case XPRT_TRANSPORT_UDP: nlm_init.protocol = IPPROTO_UDP; +#endif } host = nlmclnt_init(&nlm_init); @@ -658,28 +662,28 @@ EXPORT_SYMBOL_GPL(nfs_init_client); * Create a version 2 or 3 client */ static int nfs_init_server(struct nfs_server *server, - const struct nfs_parsed_mount_data *data, - struct nfs_subversion *nfs_mod) + const struct fs_context *fc) { + const struct nfs_fs_context *ctx = nfs_fc2context(fc); struct rpc_timeout timeparms; struct nfs_client_initdata cl_init = { - .hostname = data->nfs_server.hostname, - .addr = (const struct sockaddr *)&data->nfs_server.address, - .addrlen = data->nfs_server.addrlen, - .nfs_mod = nfs_mod, - .proto = data->nfs_server.protocol, - .net = data->net, + .hostname = ctx->nfs_server.hostname, + .addr = (const struct sockaddr *)&ctx->nfs_server.address, + .addrlen = ctx->nfs_server.addrlen, + .nfs_mod = ctx->nfs_mod, + .proto = ctx->nfs_server.protocol, + .net = fc->net_ns, .timeparms = &timeparms, .cred = server->cred, - .nconnect = data->nfs_server.nconnect, + .nconnect = ctx->nfs_server.nconnect, .init_flags = (1UL << NFS_CS_REUSEPORT), }; struct nfs_client *clp; int error; - nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, - data->timeo, data->retrans); - if (data->flags & NFS_MOUNT_NORESVPORT) + nfs_init_timeout_values(&timeparms, ctx->nfs_server.protocol, + ctx->timeo, ctx->retrans); + if (ctx->flags & NFS_MOUNT_NORESVPORT) set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); /* Allocate or find a client reference we can use */ @@ -690,46 +694,46 @@ static int nfs_init_server(struct nfs_server *server, server->nfs_client = clp; /* Initialise the client representation from the mount data */ - server->flags = data->flags; - server->options = data->options; + server->flags = ctx->flags; + server->options = ctx->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; - if (data->rsize) - server->rsize = nfs_block_size(data->rsize, NULL); - if (data->wsize) - server->wsize = nfs_block_size(data->wsize, NULL); + if (ctx->rsize) + server->rsize = nfs_block_size(ctx->rsize, NULL); + if (ctx->wsize) + server->wsize = nfs_block_size(ctx->wsize, NULL); - server->acregmin = data->acregmin * HZ; - server->acregmax = data->acregmax * HZ; - server->acdirmin = data->acdirmin * HZ; - server->acdirmax = data->acdirmax * HZ; + server->acregmin = ctx->acregmin * HZ; + server->acregmax = ctx->acregmax * HZ; + server->acdirmin = ctx->acdirmin * HZ; + server->acdirmax = ctx->acdirmax * HZ; /* Start lockd here, before we might error out */ error = nfs_start_lockd(server); if (error < 0) goto error; - server->port = data->nfs_server.port; - server->auth_info = data->auth_info; + server->port = ctx->nfs_server.port; + server->auth_info = ctx->auth_info; error = nfs_init_server_rpcclient(server, &timeparms, - data->selected_flavor); + ctx->selected_flavor); if (error < 0) goto error; /* Preserve the values of mount_server-related mount options */ - if (data->mount_server.addrlen) { - memcpy(&server->mountd_address, &data->mount_server.address, - data->mount_server.addrlen); - server->mountd_addrlen = data->mount_server.addrlen; + if (ctx->mount_server.addrlen) { + memcpy(&server->mountd_address, &ctx->mount_server.address, + ctx->mount_server.addrlen); + server->mountd_addrlen = ctx->mount_server.addrlen; } - server->mountd_version = data->mount_server.version; - server->mountd_port = data->mount_server.port; - server->mountd_protocol = data->mount_server.protocol; + server->mountd_version = ctx->mount_server.version; + server->mountd_port = ctx->mount_server.port; + server->mountd_protocol = ctx->mount_server.protocol; - server->namelen = data->namlen; + server->namelen = ctx->namlen; return 0; error: @@ -951,9 +955,9 @@ EXPORT_SYMBOL_GPL(nfs_free_server); * Create a version 2 or 3 volume record * - keyed on server and FSID */ -struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) +struct nfs_server *nfs_create_server(struct fs_context *fc) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_server *server; struct nfs_fattr *fattr; int error; @@ -970,18 +974,18 @@ struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info, goto error; /* Get a client representation */ - error = nfs_init_server(server, mount_info->parsed, nfs_mod); + error = nfs_init_server(server, fc); if (error < 0) goto error; /* Probe the root fh to retrieve its FSID */ - error = nfs_probe_fsinfo(server, mount_info->mntfh, fattr); + error = nfs_probe_fsinfo(server, ctx->mntfh, fattr); if (error < 0) goto error; if (server->nfs_client->rpc_ops->version == 3) { if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN) server->namelen = NFS3_MAXNAMLEN; - if (!(mount_info->parsed->flags & NFS_MOUNT_NORDIRPLUS)) + if (!(ctx->flags & NFS_MOUNT_NORDIRPLUS)) server->caps |= NFS_CAP_READDIRPLUS; } else { if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) @@ -989,8 +993,8 @@ struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info, } if (!(fattr->valid & NFS_ATTR_FATTR)) { - error = nfs_mod->rpc_ops->getattr(server, mount_info->mntfh, - fattr, NULL, NULL); + error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, + fattr, NULL, NULL); if (error < 0) { dprintk("nfs_create_server: getattr error = %d\n", -error); goto error; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index fe57b2b5314a..4a841071d8a7 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -25,13 +25,32 @@ #include "internal.h" #include "nfs4trace.h" -static void nfs_free_delegation(struct nfs_delegation *delegation) +#define NFS_DEFAULT_DELEGATION_WATERMARK (5000U) + +static atomic_long_t nfs_active_delegations; +static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK; + +static void __nfs_free_delegation(struct nfs_delegation *delegation) { put_cred(delegation->cred); delegation->cred = NULL; kfree_rcu(delegation, rcu); } +static void nfs_mark_delegation_revoked(struct nfs_delegation *delegation) +{ + if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + delegation->stateid.type = NFS4_INVALID_STATEID_TYPE; + atomic_long_dec(&nfs_active_delegations); + } +} + +static void nfs_free_delegation(struct nfs_delegation *delegation) +{ + nfs_mark_delegation_revoked(delegation); + __nfs_free_delegation(delegation); +} + /** * nfs_mark_delegation_referenced - set delegation's REFERENCED flag * @delegation: delegation to process @@ -343,7 +362,8 @@ nfs_update_inplace_delegation(struct nfs_delegation *delegation, delegation->stateid.seqid = update->stateid.seqid; smp_wmb(); delegation->type = update->type; - clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); } } @@ -423,6 +443,8 @@ add_new: rcu_assign_pointer(nfsi->delegation, delegation); delegation = NULL; + atomic_long_inc(&nfs_active_delegations); + trace_nfs4_set_delegation(inode, type); spin_lock(&inode->i_lock); @@ -432,7 +454,7 @@ add_new: out: spin_unlock(&clp->cl_lock); if (delegation != NULL) - nfs_free_delegation(delegation); + __nfs_free_delegation(delegation); if (freeme != NULL) { nfs_do_return_delegation(inode, freeme, 0); nfs_free_delegation(freeme); @@ -479,7 +501,7 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation) if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags)) ret = true; - if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) { + else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) { struct inode *inode; spin_lock(&delegation->lock); @@ -488,6 +510,8 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation) ret = true; spin_unlock(&delegation->lock); } + if (ret) + clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) || test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) ret = false; @@ -607,6 +631,7 @@ void nfs_inode_evict_delegation(struct inode *inode) delegation = nfs_inode_detach_delegation(inode); if (delegation != NULL) { + set_bit(NFS_DELEGATION_RETURNING, &delegation->flags); set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags); nfs_do_return_delegation(inode, delegation, 1); nfs_free_delegation(delegation); @@ -637,6 +662,40 @@ int nfs4_inode_return_delegation(struct inode *inode) } /** + * nfs_inode_return_delegation_on_close - asynchronously return a delegation + * @inode: inode to process + * + * This routine is called on file close in order to determine if the + * inode delegation needs to be returned immediately. + */ +void nfs4_inode_return_delegation_on_close(struct inode *inode) +{ + struct nfs_delegation *delegation; + struct nfs_delegation *ret = NULL; + + if (!inode) + return; + rcu_read_lock(); + delegation = nfs4_get_valid_delegation(inode); + if (!delegation) + goto out; + if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) || + atomic_long_read(&nfs_active_delegations) >= nfs_delegation_watermark) { + spin_lock(&delegation->lock); + if (delegation->inode && + list_empty(&NFS_I(inode)->open_files) && + !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); + ret = delegation; + } + spin_unlock(&delegation->lock); + } +out: + rcu_read_unlock(); + nfs_end_delegation_return(inode, ret, 0); +} + +/** * nfs4_inode_make_writeable * @inode: pointer to inode * @@ -760,13 +819,6 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl rcu_read_unlock(); } -static void nfs_mark_delegation_revoked(struct nfs_server *server, - struct nfs_delegation *delegation) -{ - set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); - delegation->stateid.type = NFS4_INVALID_STATEID_TYPE; -} - static void nfs_revoke_delegation(struct inode *inode, const nfs4_stateid *stateid) { @@ -794,7 +846,7 @@ static void nfs_revoke_delegation(struct inode *inode, } spin_unlock(&delegation->lock); } - nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation); + nfs_mark_delegation_revoked(delegation); ret = true; out: rcu_read_unlock(); @@ -833,7 +885,7 @@ void nfs_delegation_mark_returned(struct inode *inode, delegation->stateid.seqid = stateid->seqid; } - nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation); + nfs_mark_delegation_revoked(delegation); out_clear_returning: clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags); @@ -1317,3 +1369,5 @@ out: rcu_read_unlock(); return ret; } + +module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 15d3484be028..31b84604d383 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -42,6 +42,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit); int nfs4_inode_return_delegation(struct inode *inode); +void nfs4_inode_return_delegation_on_close(struct inode *inode); int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid); void nfs_inode_evict_delegation(struct inode *inode); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e180033e35cf..1320288ff9ec 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -58,7 +58,7 @@ static void nfs_readdir_clear_array(struct page*); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, .read = generic_read_dir, - .iterate = nfs_readdir, + .iterate_shared = nfs_readdir, .open = nfs_opendir, .release = nfs_closedir, .fsync = nfs_fsync_dir, @@ -162,6 +162,17 @@ typedef struct { bool eof; } nfs_readdir_descriptor_t; +static +void nfs_readdir_init_array(struct page *page) +{ + struct nfs_cache_array *array; + + array = kmap_atomic(page); + memset(array, 0, sizeof(struct nfs_cache_array)); + array->eof_index = -1; + kunmap_atomic(array); +} + /* * we are freeing strings created by nfs_add_to_readdir_array() */ @@ -174,6 +185,7 @@ void nfs_readdir_clear_array(struct page *page) array = kmap_atomic(page); for (i = 0; i < array->size; i++) kfree(array->array[i].string.name); + array->size = 0; kunmap_atomic(array); } @@ -186,7 +198,7 @@ static int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len) { string->len = len; - string->name = kmemdup(name, len, GFP_KERNEL); + string->name = kmemdup_nul(name, len, GFP_KERNEL); if (string->name == NULL) return -ENOMEM; /* @@ -437,7 +449,8 @@ void nfs_force_use_readdirplus(struct inode *dir) if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && !list_empty(&nfsi->open_files)) { set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); - invalidate_mapping_pages(dir->i_mapping, 0, -1); + invalidate_mapping_pages(dir->i_mapping, + nfsi->page_index + 1, -1); } } @@ -610,6 +623,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, int status = -ENOMEM; unsigned int array_size = ARRAY_SIZE(pages); + nfs_readdir_init_array(page); + entry.prev_cookie = 0; entry.cookie = desc->last_cookie; entry.eof = 0; @@ -626,8 +641,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, } array = kmap(page); - memset(array, 0, sizeof(struct nfs_cache_array)); - array->eof_index = -1; status = nfs_readdir_alloc_pages(pages, array_size); if (status < 0) @@ -682,6 +695,7 @@ int nfs_readdir_filler(void *data, struct page* page) unlock_page(page); return 0; error: + nfs_readdir_clear_array(page); unlock_page(page); return ret; } @@ -689,8 +703,6 @@ int nfs_readdir_filler(void *data, struct page* page) static void cache_page_release(nfs_readdir_descriptor_t *desc) { - if (!desc->page->mapping) - nfs_readdir_clear_array(desc->page); put_page(desc->page); desc->page = NULL; } @@ -704,19 +716,32 @@ struct page *get_cache_page(nfs_readdir_descriptor_t *desc) /* * Returns 0 if desc->dir_cookie was found on page desc->page_index + * and locks the page to prevent removal from the page cache. */ static -int find_cache_page(nfs_readdir_descriptor_t *desc) +int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc) { + struct inode *inode = file_inode(desc->file); + struct nfs_inode *nfsi = NFS_I(inode); int res; desc->page = get_cache_page(desc); if (IS_ERR(desc->page)) return PTR_ERR(desc->page); - - res = nfs_readdir_search_array(desc); + res = lock_page_killable(desc->page); if (res != 0) - cache_page_release(desc); + goto error; + res = -EAGAIN; + if (desc->page->mapping != NULL) { + res = nfs_readdir_search_array(desc); + if (res == 0) { + nfsi->page_index = desc->page_index; + return 0; + } + } + unlock_page(desc->page); +error: + cache_page_release(desc); return res; } @@ -731,7 +756,7 @@ int readdir_search_pagecache(nfs_readdir_descriptor_t *desc) desc->last_cookie = 0; } do { - res = find_cache_page(desc); + res = find_and_lock_cache_page(desc); } while (res == -EAGAIN); return res; } @@ -770,7 +795,6 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc) desc->eof = true; kunmap(desc->page); - cache_page_release(desc); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n", (unsigned long long)*desc->dir_cookie, res); return res; @@ -816,13 +840,13 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc) status = nfs_do_filldir(desc); + out_release: + nfs_readdir_clear_array(desc->page); + cache_page_release(desc); out: dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; - out_release: - cache_page_release(desc); - goto out; } /* The file offset position represents the dirent entry number. A @@ -887,6 +911,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; res = nfs_do_filldir(desc); + unlock_page(desc->page); + cache_page_release(desc); if (res < 0) break; } while (!desc->eof); @@ -1142,10 +1168,17 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, if (fhandle == NULL || fattr == NULL || IS_ERR(label)) goto out; - ret = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); if (ret < 0) { - if (ret == -ESTALE || ret == -ENOENT) + switch (ret) { + case -ESTALE: + case -ENOENT: ret = 0; + break; + case -ETIMEDOUT: + if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL) + ret = 1; + } goto out; } ret = 0; @@ -1408,7 +1441,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in goto out; trace_nfs_lookup_enter(dir, dentry, flags); - error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); if (error == -ENOENT) goto no_entry; if (error < 0) { @@ -1683,7 +1716,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, d_drop(dentry); if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, NULL); + error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, NULL); if (error) goto out_error; } @@ -2312,11 +2345,11 @@ static int nfs_access_get_cached(struct inode *inode, const struct cred *cred, s /* Found an entry, is our attribute cache valid? */ if (!nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) break; + if (!retry) + break; err = -ECHILD; if (!may_block) goto out; - if (!retry) - goto out_zap; spin_unlock(&inode->i_lock); err = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (err) @@ -2353,7 +2386,7 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre lh = rcu_dereference(nfsi->access_cache_entry_lru.prev); cache = list_entry(lh, struct nfs_access_entry, lru); if (lh == &nfsi->access_cache_entry_lru || - cred != cache->cred) + cred_fscmp(cred, cache->cred) != 0) cache = NULL; if (cache == NULL) goto out; @@ -2476,7 +2509,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) { struct nfs_access_entry cache; bool may_block = (mask & MAY_NOT_BLOCK) == 0; - int cache_mask; + int cache_mask = -1; int status; trace_nfs_access_enter(inode); @@ -2515,7 +2548,7 @@ out_cached: if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) status = -EACCES; out: - trace_nfs_access_exit(inode, status); + trace_nfs_access_exit(inode, mask, cache_mask, status); return status; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 040a50fd9bf3..b768a0b42e82 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -245,10 +245,10 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, data->ds_commit_index); /* verifier not set so always fail */ - if (verfp->committed < 0) + if (verfp->committed < 0 || data->res.verf->committed <= NFS_UNSTABLE) return 1; - return nfs_direct_cmp_verf(verfp, &data->verf); + return nfs_direct_cmp_verf(verfp, data->res.verf); } /** @@ -824,7 +824,8 @@ static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) dreq->flags = NFS_ODIRECT_RESCHED_WRITES; /* fake unstable write to let common nfs resend pages */ hdr->verf.committed = NFS_UNSTABLE; - hdr->good_bytes = hdr->args.count; + hdr->good_bytes = hdr->args.offset + hdr->args.count - + hdr->io_start; } spin_unlock(&dreq->lock); } diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index aec769a500a1..89bd5581f317 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -93,7 +93,7 @@ static void nfs_dns_ent_init(struct cache_head *cnew, key = container_of(ckey, struct nfs_dns_ent, h); kfree(new->hostname); - new->hostname = kstrndup(key->hostname, key->namelen, GFP_KERNEL); + new->hostname = kmemdup_nul(key->hostname, key->namelen, GFP_KERNEL); if (new->hostname) { new->namelen = key->namelen; nfs_dns_ent_update(cnew, ckey); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 8eb731d9be3e..f96367a2463e 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -204,44 +204,39 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap); static int nfs_file_fsync_commit(struct file *file, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); - int do_resend, status; - int ret = 0; + int ret; dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync); nfs_inc_stats(inode, NFSIOS_VFSFSYNC); - do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); - status = nfs_commit_inode(inode, FLUSH_SYNC); - if (status == 0) - status = file_check_and_advance_wb_err(file); - if (status < 0) { - ret = status; - goto out; - } - do_resend |= test_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); - if (do_resend) - ret = -EAGAIN; -out: - return ret; + ret = nfs_commit_inode(inode, FLUSH_SYNC); + if (ret < 0) + return ret; + return file_check_and_advance_wb_err(file); } int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - int ret; + struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + int ret; trace_nfs_fsync_enter(inode); - do { + for (;;) { ret = file_write_and_wait_range(file, start, end); if (ret != 0) break; ret = nfs_file_fsync_commit(file, datasync); - if (!ret) - ret = pnfs_sync_inode(inode, !!datasync); + if (ret != 0) + break; + ret = pnfs_sync_inode(inode, !!datasync); + if (ret != 0) + break; + if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + break; /* * If nfs_file_fsync_commit detected a server reboot, then * resend all dirty pages that might have been covered by @@ -249,7 +244,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ start = 0; end = LLONG_MAX; - } while (ret == -EAGAIN); + } trace_nfs_fsync_exit(inode, ret); return ret; @@ -489,7 +484,19 @@ static int nfs_launder_page(struct page *page) static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, sector_t *span) { + unsigned long blocks; + long long isize; struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); + struct inode *inode = file->f_mapping->host; + + spin_lock(&inode->i_lock); + blocks = inode->i_blocks; + isize = inode->i_size; + spin_unlock(&inode->i_lock); + if (blocks*512 < isize) { + pr_warn("swap activate: swapfile has holes\n"); + return -EINVAL; + } *span = sis->pages; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 5657b7f2611f..bb9148b83166 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1266,9 +1266,10 @@ static int ff_layout_async_handle_error(struct rpc_task *task, static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, int idx, u64 offset, u64 length, - u32 status, int opnum, int error) + u32 *op_status, int opnum, int error) { struct nfs4_ff_layout_mirror *mirror; + u32 status = *op_status; int err; if (status == 0) { @@ -1286,10 +1287,10 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -ENOBUFS: case -EPIPE: case -EPERM: - status = NFS4ERR_NXIO; + *op_status = status = NFS4ERR_NXIO; break; case -EACCES: - status = NFS4ERR_ACCESS; + *op_status = status = NFS4ERR_ACCESS; break; default: return; @@ -1321,16 +1322,19 @@ static int ff_layout_read_done_cb(struct rpc_task *task, int new_idx = hdr->pgio_mirror_idx; int err; - trace_nfs4_pnfs_read(hdr, task->tk_status); - if (task->tk_status < 0) + if (task->tk_status < 0) { ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, hdr->args.offset, hdr->args.count, - hdr->res.op_status, OP_READ, + &hdr->res.op_status, OP_READ, task->tk_status); + trace_ff_layout_read_error(hdr); + } + err = ff_layout_async_handle_error(task, hdr->args.context->state, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); + trace_nfs4_pnfs_read(hdr, err); clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); switch (err) { @@ -1494,16 +1498,19 @@ static int ff_layout_write_done_cb(struct rpc_task *task, loff_t end_offs = 0; int err; - trace_nfs4_pnfs_write(hdr, task->tk_status); - if (task->tk_status < 0) + if (task->tk_status < 0) { ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, hdr->args.offset, hdr->args.count, - hdr->res.op_status, OP_WRITE, + &hdr->res.op_status, OP_WRITE, task->tk_status); + trace_ff_layout_write_error(hdr); + } + err = ff_layout_async_handle_error(task, hdr->args.context->state, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); + trace_nfs4_pnfs_write(hdr, err); clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags); switch (err) { @@ -1537,15 +1544,18 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, { int err; - trace_nfs4_pnfs_commit_ds(data, task->tk_status); - if (task->tk_status < 0) + if (task->tk_status < 0) { ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index, data->args.offset, data->args.count, - data->res.op_status, OP_COMMIT, + &data->res.op_status, OP_COMMIT, task->tk_status); + trace_ff_layout_commit_error(data); + } + err = ff_layout_async_handle_error(task, NULL, data->ds_clp, data->lseg, data->ds_commit_index); + trace_nfs4_pnfs_commit_ds(data, err); switch (err) { case -NFS4ERR_RESET_TO_PNFS: pnfs_generic_prepare_to_resend_writes(data); diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c new file mode 100644 index 000000000000..e1b938457ab9 --- /dev/null +++ b/fs/nfs/fs_context.c @@ -0,0 +1,1440 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/nfs/fs_context.c + * + * Copyright (C) 1992 Rick Sladkey + * Conversion to new mount api Copyright (C) David Howells + * + * NFS mount handling. + * + * Split from fs/nfs/super.c by David Howells <dhowells@redhat.com> + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs4_mount.h> +#include "nfs.h" +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_MOUNT + +#if IS_ENABLED(CONFIG_NFS_V3) +#define NFS_DEFAULT_VERSION 3 +#else +#define NFS_DEFAULT_VERSION 2 +#endif + +#define NFS_MAX_CONNECTIONS 16 + +enum nfs_param { + Opt_ac, + Opt_acdirmax, + Opt_acdirmin, + Opt_acl, + Opt_acregmax, + Opt_acregmin, + Opt_actimeo, + Opt_addr, + Opt_bg, + Opt_bsize, + Opt_clientaddr, + Opt_cto, + Opt_fg, + Opt_fscache, + Opt_fscache_flag, + Opt_hard, + Opt_intr, + Opt_local_lock, + Opt_lock, + Opt_lookupcache, + Opt_migration, + Opt_minorversion, + Opt_mountaddr, + Opt_mounthost, + Opt_mountport, + Opt_mountproto, + Opt_mountvers, + Opt_namelen, + Opt_nconnect, + Opt_port, + Opt_posix, + Opt_proto, + Opt_rdirplus, + Opt_rdma, + Opt_resvport, + Opt_retrans, + Opt_retry, + Opt_rsize, + Opt_sec, + Opt_sharecache, + Opt_sloppy, + Opt_soft, + Opt_softerr, + Opt_softreval, + Opt_source, + Opt_tcp, + Opt_timeo, + Opt_udp, + Opt_v, + Opt_vers, + Opt_wsize, +}; + +enum { + Opt_local_lock_all, + Opt_local_lock_flock, + Opt_local_lock_none, + Opt_local_lock_posix, +}; + +static const struct constant_table nfs_param_enums_local_lock[] = { + { "all", Opt_local_lock_all }, + { "flock", Opt_local_lock_flock }, + { "none", Opt_local_lock_none }, + {} +}; + +enum { + Opt_lookupcache_all, + Opt_lookupcache_none, + Opt_lookupcache_positive, +}; + +static const struct constant_table nfs_param_enums_lookupcache[] = { + { "all", Opt_lookupcache_all }, + { "none", Opt_lookupcache_none }, + { "pos", Opt_lookupcache_positive }, + { "positive", Opt_lookupcache_positive }, + {} +}; + +static const struct fs_parameter_spec nfs_fs_parameters[] = { + fsparam_flag_no("ac", Opt_ac), + fsparam_u32 ("acdirmax", Opt_acdirmax), + fsparam_u32 ("acdirmin", Opt_acdirmin), + fsparam_flag_no("acl", Opt_acl), + fsparam_u32 ("acregmax", Opt_acregmax), + fsparam_u32 ("acregmin", Opt_acregmin), + fsparam_u32 ("actimeo", Opt_actimeo), + fsparam_string("addr", Opt_addr), + fsparam_flag ("bg", Opt_bg), + fsparam_u32 ("bsize", Opt_bsize), + fsparam_string("clientaddr", Opt_clientaddr), + fsparam_flag_no("cto", Opt_cto), + fsparam_flag ("fg", Opt_fg), + fsparam_flag_no("fsc", Opt_fscache_flag), + fsparam_string("fsc", Opt_fscache), + fsparam_flag ("hard", Opt_hard), + __fsparam(NULL, "intr", Opt_intr, + fs_param_neg_with_no|fs_param_deprecated, NULL), + fsparam_enum ("local_lock", Opt_local_lock, nfs_param_enums_local_lock), + fsparam_flag_no("lock", Opt_lock), + fsparam_enum ("lookupcache", Opt_lookupcache, nfs_param_enums_lookupcache), + fsparam_flag_no("migration", Opt_migration), + fsparam_u32 ("minorversion", Opt_minorversion), + fsparam_string("mountaddr", Opt_mountaddr), + fsparam_string("mounthost", Opt_mounthost), + fsparam_u32 ("mountport", Opt_mountport), + fsparam_string("mountproto", Opt_mountproto), + fsparam_u32 ("mountvers", Opt_mountvers), + fsparam_u32 ("namlen", Opt_namelen), + fsparam_u32 ("nconnect", Opt_nconnect), + fsparam_string("nfsvers", Opt_vers), + fsparam_u32 ("port", Opt_port), + fsparam_flag_no("posix", Opt_posix), + fsparam_string("proto", Opt_proto), + fsparam_flag_no("rdirplus", Opt_rdirplus), + fsparam_flag ("rdma", Opt_rdma), + fsparam_flag_no("resvport", Opt_resvport), + fsparam_u32 ("retrans", Opt_retrans), + fsparam_string("retry", Opt_retry), + fsparam_u32 ("rsize", Opt_rsize), + fsparam_string("sec", Opt_sec), + fsparam_flag_no("sharecache", Opt_sharecache), + fsparam_flag ("sloppy", Opt_sloppy), + fsparam_flag ("soft", Opt_soft), + fsparam_flag ("softerr", Opt_softerr), + fsparam_flag ("softreval", Opt_softreval), + fsparam_string("source", Opt_source), + fsparam_flag ("tcp", Opt_tcp), + fsparam_u32 ("timeo", Opt_timeo), + fsparam_flag ("udp", Opt_udp), + fsparam_flag ("v2", Opt_v), + fsparam_flag ("v3", Opt_v), + fsparam_flag ("v4", Opt_v), + fsparam_flag ("v4.0", Opt_v), + fsparam_flag ("v4.1", Opt_v), + fsparam_flag ("v4.2", Opt_v), + fsparam_string("vers", Opt_vers), + fsparam_u32 ("wsize", Opt_wsize), + {} +}; + +enum { + Opt_vers_2, + Opt_vers_3, + Opt_vers_4, + Opt_vers_4_0, + Opt_vers_4_1, + Opt_vers_4_2, +}; + +static const struct constant_table nfs_vers_tokens[] = { + { "2", Opt_vers_2 }, + { "3", Opt_vers_3 }, + { "4", Opt_vers_4 }, + { "4.0", Opt_vers_4_0 }, + { "4.1", Opt_vers_4_1 }, + { "4.2", Opt_vers_4_2 }, +}; + +enum { + Opt_xprt_rdma, + Opt_xprt_rdma6, + Opt_xprt_tcp, + Opt_xprt_tcp6, + Opt_xprt_udp, + Opt_xprt_udp6, + nr__Opt_xprt +}; + +static const struct constant_table nfs_xprt_protocol_tokens[nr__Opt_xprt] = { + { "rdma", Opt_xprt_rdma }, + { "rdma6", Opt_xprt_rdma6 }, + { "tcp", Opt_xprt_tcp }, + { "tcp6", Opt_xprt_tcp6 }, + { "udp", Opt_xprt_udp }, + { "udp6", Opt_xprt_udp6 }, +}; + +enum { + Opt_sec_krb5, + Opt_sec_krb5i, + Opt_sec_krb5p, + Opt_sec_lkey, + Opt_sec_lkeyi, + Opt_sec_lkeyp, + Opt_sec_none, + Opt_sec_spkm, + Opt_sec_spkmi, + Opt_sec_spkmp, + Opt_sec_sys, + nr__Opt_sec +}; + +static const struct constant_table nfs_secflavor_tokens[] = { + { "krb5", Opt_sec_krb5 }, + { "krb5i", Opt_sec_krb5i }, + { "krb5p", Opt_sec_krb5p }, + { "lkey", Opt_sec_lkey }, + { "lkeyi", Opt_sec_lkeyi }, + { "lkeyp", Opt_sec_lkeyp }, + { "none", Opt_sec_none }, + { "null", Opt_sec_none }, + { "spkm3", Opt_sec_spkm }, + { "spkm3i", Opt_sec_spkmi }, + { "spkm3p", Opt_sec_spkmp }, + { "sys", Opt_sec_sys }, +}; + +/* + * Sanity-check a server address provided by the mount command. + * + * Address family must be initialized, and address must not be + * the ANY address for that family. + */ +static int nfs_verify_server_address(struct sockaddr *addr) +{ + switch (addr->sa_family) { + case AF_INET: { + struct sockaddr_in *sa = (struct sockaddr_in *)addr; + return sa->sin_addr.s_addr != htonl(INADDR_ANY); + } + case AF_INET6: { + struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr; + return !ipv6_addr_any(sa); + } + } + + dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); + return 0; +} + +/* + * Sanity check the NFS transport protocol. + * + */ +static void nfs_validate_transport_protocol(struct nfs_fs_context *ctx) +{ + switch (ctx->nfs_server.protocol) { + case XPRT_TRANSPORT_UDP: + case XPRT_TRANSPORT_TCP: + case XPRT_TRANSPORT_RDMA: + break; + default: + ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; + } +} + +/* + * For text based NFSv2/v3 mounts, the mount protocol transport default + * settings should depend upon the specified NFS transport. + */ +static void nfs_set_mount_transport_protocol(struct nfs_fs_context *ctx) +{ + nfs_validate_transport_protocol(ctx); + + if (ctx->mount_server.protocol == XPRT_TRANSPORT_UDP || + ctx->mount_server.protocol == XPRT_TRANSPORT_TCP) + return; + switch (ctx->nfs_server.protocol) { + case XPRT_TRANSPORT_UDP: + ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; + break; + case XPRT_TRANSPORT_TCP: + case XPRT_TRANSPORT_RDMA: + ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; + } +} + +/* + * Add 'flavor' to 'auth_info' if not already present. + * Returns true if 'flavor' ends up in the list, false otherwise + */ +static int nfs_auth_info_add(struct fs_context *fc, + struct nfs_auth_info *auth_info, + rpc_authflavor_t flavor) +{ + unsigned int i; + unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors); + + /* make sure this flavor isn't already in the list */ + for (i = 0; i < auth_info->flavor_len; i++) { + if (flavor == auth_info->flavors[i]) + return 0; + } + + if (auth_info->flavor_len + 1 >= max_flavor_len) + return nfs_invalf(fc, "NFS: too many sec= flavors"); + + auth_info->flavors[auth_info->flavor_len++] = flavor; + return 0; +} + +/* + * Parse the value of the 'sec=' option. + */ +static int nfs_parse_security_flavors(struct fs_context *fc, + struct fs_parameter *param) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + rpc_authflavor_t pseudoflavor; + char *string = param->string, *p; + int ret; + + dfprintk(MOUNT, "NFS: parsing %s=%s option\n", param->key, param->string); + + while ((p = strsep(&string, ":")) != NULL) { + if (!*p) + continue; + switch (lookup_constant(nfs_secflavor_tokens, p, -1)) { + case Opt_sec_none: + pseudoflavor = RPC_AUTH_NULL; + break; + case Opt_sec_sys: + pseudoflavor = RPC_AUTH_UNIX; + break; + case Opt_sec_krb5: + pseudoflavor = RPC_AUTH_GSS_KRB5; + break; + case Opt_sec_krb5i: + pseudoflavor = RPC_AUTH_GSS_KRB5I; + break; + case Opt_sec_krb5p: + pseudoflavor = RPC_AUTH_GSS_KRB5P; + break; + case Opt_sec_lkey: + pseudoflavor = RPC_AUTH_GSS_LKEY; + break; + case Opt_sec_lkeyi: + pseudoflavor = RPC_AUTH_GSS_LKEYI; + break; + case Opt_sec_lkeyp: + pseudoflavor = RPC_AUTH_GSS_LKEYP; + break; + case Opt_sec_spkm: + pseudoflavor = RPC_AUTH_GSS_SPKM; + break; + case Opt_sec_spkmi: + pseudoflavor = RPC_AUTH_GSS_SPKMI; + break; + case Opt_sec_spkmp: + pseudoflavor = RPC_AUTH_GSS_SPKMP; + break; + default: + return nfs_invalf(fc, "NFS: sec=%s option not recognized", p); + } + + ret = nfs_auth_info_add(fc, &ctx->auth_info, pseudoflavor); + if (ret < 0) + return ret; + } + + return 0; +} + +static int nfs_parse_version_string(struct fs_context *fc, + const char *string) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + + ctx->flags &= ~NFS_MOUNT_VER3; + switch (lookup_constant(nfs_vers_tokens, string, -1)) { + case Opt_vers_2: + ctx->version = 2; + break; + case Opt_vers_3: + ctx->flags |= NFS_MOUNT_VER3; + ctx->version = 3; + break; + case Opt_vers_4: + /* Backward compatibility option. In future, + * the mount program should always supply + * a NFSv4 minor version number. + */ + ctx->version = 4; + break; + case Opt_vers_4_0: + ctx->version = 4; + ctx->minorversion = 0; + break; + case Opt_vers_4_1: + ctx->version = 4; + ctx->minorversion = 1; + break; + case Opt_vers_4_2: + ctx->version = 4; + ctx->minorversion = 2; + break; + default: + return nfs_invalf(fc, "NFS: Unsupported NFS version"); + } + return 0; +} + +/* + * Parse a single mount parameter. + */ +static int nfs_fs_context_parse_param(struct fs_context *fc, + struct fs_parameter *param) +{ + struct fs_parse_result result; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + unsigned short protofamily, mountfamily; + unsigned int len; + int ret, opt; + + dfprintk(MOUNT, "NFS: parsing nfs mount option '%s'\n", param->key); + + opt = fs_parse(fc, nfs_fs_parameters, param, &result); + if (opt < 0) + return ctx->sloppy ? 1 : opt; + + switch (opt) { + case Opt_source: + if (fc->source) + return nfs_invalf(fc, "NFS: Multiple sources not supported"); + fc->source = param->string; + param->string = NULL; + break; + + /* + * boolean options: foo/nofoo + */ + case Opt_soft: + ctx->flags |= NFS_MOUNT_SOFT; + ctx->flags &= ~NFS_MOUNT_SOFTERR; + break; + case Opt_softerr: + ctx->flags |= NFS_MOUNT_SOFTERR | NFS_MOUNT_SOFTREVAL; + ctx->flags &= ~NFS_MOUNT_SOFT; + break; + case Opt_hard: + ctx->flags &= ~(NFS_MOUNT_SOFT | + NFS_MOUNT_SOFTERR | + NFS_MOUNT_SOFTREVAL); + break; + case Opt_softreval: + if (result.negated) + ctx->flags &= ~NFS_MOUNT_SOFTREVAL; + else + ctx->flags &= NFS_MOUNT_SOFTREVAL; + break; + case Opt_posix: + if (result.negated) + ctx->flags &= ~NFS_MOUNT_POSIX; + else + ctx->flags |= NFS_MOUNT_POSIX; + break; + case Opt_cto: + if (result.negated) + ctx->flags |= NFS_MOUNT_NOCTO; + else + ctx->flags &= ~NFS_MOUNT_NOCTO; + break; + case Opt_ac: + if (result.negated) + ctx->flags |= NFS_MOUNT_NOAC; + else + ctx->flags &= ~NFS_MOUNT_NOAC; + break; + case Opt_lock: + if (result.negated) { + ctx->flags |= NFS_MOUNT_NONLM; + ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); + } else { + ctx->flags &= ~NFS_MOUNT_NONLM; + ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); + } + break; + case Opt_udp: + ctx->flags &= ~NFS_MOUNT_TCP; + ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; + break; + case Opt_tcp: + ctx->flags |= NFS_MOUNT_TCP; + ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; + break; + case Opt_rdma: + ctx->flags |= NFS_MOUNT_TCP; /* for side protocols */ + ctx->nfs_server.protocol = XPRT_TRANSPORT_RDMA; + xprt_load_transport(param->key); + break; + case Opt_acl: + if (result.negated) + ctx->flags |= NFS_MOUNT_NOACL; + else + ctx->flags &= ~NFS_MOUNT_NOACL; + break; + case Opt_rdirplus: + if (result.negated) + ctx->flags |= NFS_MOUNT_NORDIRPLUS; + else + ctx->flags &= ~NFS_MOUNT_NORDIRPLUS; + break; + case Opt_sharecache: + if (result.negated) + ctx->flags |= NFS_MOUNT_UNSHARED; + else + ctx->flags &= ~NFS_MOUNT_UNSHARED; + break; + case Opt_resvport: + if (result.negated) + ctx->flags |= NFS_MOUNT_NORESVPORT; + else + ctx->flags &= ~NFS_MOUNT_NORESVPORT; + break; + case Opt_fscache_flag: + if (result.negated) + ctx->options &= ~NFS_OPTION_FSCACHE; + else + ctx->options |= NFS_OPTION_FSCACHE; + kfree(ctx->fscache_uniq); + ctx->fscache_uniq = NULL; + break; + case Opt_fscache: + ctx->options |= NFS_OPTION_FSCACHE; + kfree(ctx->fscache_uniq); + ctx->fscache_uniq = param->string; + param->string = NULL; + break; + case Opt_migration: + if (result.negated) + ctx->options &= ~NFS_OPTION_MIGRATION; + else + ctx->options |= NFS_OPTION_MIGRATION; + break; + + /* + * options that take numeric values + */ + case Opt_port: + if (result.uint_32 > USHRT_MAX) + goto out_of_bounds; + ctx->nfs_server.port = result.uint_32; + break; + case Opt_rsize: + ctx->rsize = result.uint_32; + break; + case Opt_wsize: + ctx->wsize = result.uint_32; + break; + case Opt_bsize: + ctx->bsize = result.uint_32; + break; + case Opt_timeo: + if (result.uint_32 < 1 || result.uint_32 > INT_MAX) + goto out_of_bounds; + ctx->timeo = result.uint_32; + break; + case Opt_retrans: + if (result.uint_32 > INT_MAX) + goto out_of_bounds; + ctx->retrans = result.uint_32; + break; + case Opt_acregmin: + ctx->acregmin = result.uint_32; + break; + case Opt_acregmax: + ctx->acregmax = result.uint_32; + break; + case Opt_acdirmin: + ctx->acdirmin = result.uint_32; + break; + case Opt_acdirmax: + ctx->acdirmax = result.uint_32; + break; + case Opt_actimeo: + ctx->acregmin = result.uint_32; + ctx->acregmax = result.uint_32; + ctx->acdirmin = result.uint_32; + ctx->acdirmax = result.uint_32; + break; + case Opt_namelen: + ctx->namlen = result.uint_32; + break; + case Opt_mountport: + if (result.uint_32 > USHRT_MAX) + goto out_of_bounds; + ctx->mount_server.port = result.uint_32; + break; + case Opt_mountvers: + if (result.uint_32 < NFS_MNT_VERSION || + result.uint_32 > NFS_MNT3_VERSION) + goto out_of_bounds; + ctx->mount_server.version = result.uint_32; + break; + case Opt_minorversion: + if (result.uint_32 > NFS4_MAX_MINOR_VERSION) + goto out_of_bounds; + ctx->minorversion = result.uint_32; + break; + + /* + * options that take text values + */ + case Opt_v: + ret = nfs_parse_version_string(fc, param->key + 1); + if (ret < 0) + return ret; + break; + case Opt_vers: + ret = nfs_parse_version_string(fc, param->string); + if (ret < 0) + return ret; + break; + case Opt_sec: + ret = nfs_parse_security_flavors(fc, param); + if (ret < 0) + return ret; + break; + + case Opt_proto: + protofamily = AF_INET; + switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { + case Opt_xprt_udp6: + protofamily = AF_INET6; + /* fall through */ + case Opt_xprt_udp: + ctx->flags &= ~NFS_MOUNT_TCP; + ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; + break; + case Opt_xprt_tcp6: + protofamily = AF_INET6; + /* fall through */ + case Opt_xprt_tcp: + ctx->flags |= NFS_MOUNT_TCP; + ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; + break; + case Opt_xprt_rdma6: + protofamily = AF_INET6; + /* fall through */ + case Opt_xprt_rdma: + /* vector side protocols to TCP */ + ctx->flags |= NFS_MOUNT_TCP; + ctx->nfs_server.protocol = XPRT_TRANSPORT_RDMA; + xprt_load_transport(param->string); + break; + default: + return nfs_invalf(fc, "NFS: Unrecognized transport protocol"); + } + + ctx->protofamily = protofamily; + break; + + case Opt_mountproto: + mountfamily = AF_INET; + switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { + case Opt_xprt_udp6: + mountfamily = AF_INET6; + /* fall through */ + case Opt_xprt_udp: + ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; + break; + case Opt_xprt_tcp6: + mountfamily = AF_INET6; + /* fall through */ + case Opt_xprt_tcp: + ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; + break; + case Opt_xprt_rdma: /* not used for side protocols */ + default: + return nfs_invalf(fc, "NFS: Unrecognized transport protocol"); + } + ctx->mountfamily = mountfamily; + break; + + case Opt_addr: + len = rpc_pton(fc->net_ns, param->string, param->size, + &ctx->nfs_server.address, + sizeof(ctx->nfs_server._address)); + if (len == 0) + goto out_invalid_address; + ctx->nfs_server.addrlen = len; + break; + case Opt_clientaddr: + kfree(ctx->client_address); + ctx->client_address = param->string; + param->string = NULL; + break; + case Opt_mounthost: + kfree(ctx->mount_server.hostname); + ctx->mount_server.hostname = param->string; + param->string = NULL; + break; + case Opt_mountaddr: + len = rpc_pton(fc->net_ns, param->string, param->size, + &ctx->mount_server.address, + sizeof(ctx->mount_server._address)); + if (len == 0) + goto out_invalid_address; + ctx->mount_server.addrlen = len; + break; + case Opt_nconnect: + if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_CONNECTIONS) + goto out_of_bounds; + ctx->nfs_server.nconnect = result.uint_32; + break; + case Opt_lookupcache: + switch (result.uint_32) { + case Opt_lookupcache_all: + ctx->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE); + break; + case Opt_lookupcache_positive: + ctx->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE; + ctx->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG; + break; + case Opt_lookupcache_none: + ctx->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE; + break; + default: + goto out_invalid_value; + } + break; + case Opt_local_lock: + switch (result.uint_32) { + case Opt_local_lock_all: + ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + case Opt_local_lock_flock: + ctx->flags |= NFS_MOUNT_LOCAL_FLOCK; + break; + case Opt_local_lock_posix: + ctx->flags |= NFS_MOUNT_LOCAL_FCNTL; + break; + case Opt_local_lock_none: + ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + default: + goto out_invalid_value; + } + break; + + /* + * Special options + */ + case Opt_sloppy: + ctx->sloppy = true; + dfprintk(MOUNT, "NFS: relaxing parsing rules\n"); + break; + } + + return 0; + +out_invalid_value: + return nfs_invalf(fc, "NFS: Bad mount option value specified"); +out_invalid_address: + return nfs_invalf(fc, "NFS: Bad IP address specified"); +out_of_bounds: + return nfs_invalf(fc, "NFS: Value for '%s' out of range", param->key); +} + +/* + * Split fc->source into "hostname:export_path". + * + * The leftmost colon demarks the split between the server's hostname + * and the export path. If the hostname starts with a left square + * bracket, then it may contain colons. + * + * Note: caller frees hostname and export path, even on error. + */ +static int nfs_parse_source(struct fs_context *fc, + size_t maxnamlen, size_t maxpathlen) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + const char *dev_name = fc->source; + size_t len; + const char *end; + + if (unlikely(!dev_name || !*dev_name)) { + dfprintk(MOUNT, "NFS: device name not specified\n"); + return -EINVAL; + } + + /* Is the host name protected with square brakcets? */ + if (*dev_name == '[') { + end = strchr(++dev_name, ']'); + if (end == NULL || end[1] != ':') + goto out_bad_devname; + + len = end - dev_name; + end++; + } else { + const char *comma; + + end = strchr(dev_name, ':'); + if (end == NULL) + goto out_bad_devname; + len = end - dev_name; + + /* kill possible hostname list: not supported */ + comma = memchr(dev_name, ',', len); + if (comma) + len = comma - dev_name; + } + + if (len > maxnamlen) + goto out_hostname; + + /* N.B. caller will free nfs_server.hostname in all cases */ + ctx->nfs_server.hostname = kmemdup_nul(dev_name, len, GFP_KERNEL); + if (!ctx->nfs_server.hostname) + goto out_nomem; + len = strlen(++end); + if (len > maxpathlen) + goto out_path; + ctx->nfs_server.export_path = kmemdup_nul(end, len, GFP_KERNEL); + if (!ctx->nfs_server.export_path) + goto out_nomem; + + dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", ctx->nfs_server.export_path); + return 0; + +out_bad_devname: + return nfs_invalf(fc, "NFS: device name not in host:path format"); +out_nomem: + nfs_errorf(fc, "NFS: not enough memory to parse device name"); + return -ENOMEM; +out_hostname: + nfs_errorf(fc, "NFS: server hostname too long"); + return -ENAMETOOLONG; +out_path: + nfs_errorf(fc, "NFS: export pathname too long"); + return -ENAMETOOLONG; +} + +static inline bool is_remount_fc(struct fs_context *fc) +{ + return fc->root != NULL; +} + +/* + * Parse monolithic NFS2/NFS3 mount data + * - fills in the mount root filehandle + * + * For option strings, user space handles the following behaviors: + * + * + DNS: mapping server host name to IP address ("addr=" option) + * + * + failure mode: how to behave if a mount request can't be handled + * immediately ("fg/bg" option) + * + * + retry: how often to retry a mount request ("retry=" option) + * + * + breaking back: trying proto=udp after proto=tcp, v2 after v3, + * mountproto=tcp after mountproto=udp, and so on + */ +static int nfs23_parse_monolithic(struct fs_context *fc, + struct nfs_mount_data *data) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct nfs_fh *mntfh = ctx->mntfh; + struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; + + if (data == NULL) + goto out_no_data; + + ctx->version = NFS_DEFAULT_VERSION; + switch (data->version) { + case 1: + data->namlen = 0; /* fall through */ + case 2: + data->bsize = 0; /* fall through */ + case 3: + if (data->flags & NFS_MOUNT_VER3) + goto out_no_v3; + data->root.size = NFS2_FHSIZE; + memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); + /* Turn off security negotiation */ + extra_flags |= NFS_MOUNT_SECFLAVOUR; + /* fall through */ + case 4: + if (data->flags & NFS_MOUNT_SECFLAVOUR) + goto out_no_sec; + /* fall through */ + case 5: + memset(data->context, 0, sizeof(data->context)); + /* fall through */ + case 6: + if (data->flags & NFS_MOUNT_VER3) { + if (data->root.size > NFS3_FHSIZE || data->root.size == 0) + goto out_invalid_fh; + mntfh->size = data->root.size; + ctx->version = 3; + } else { + mntfh->size = NFS2_FHSIZE; + ctx->version = 2; + } + + + memcpy(mntfh->data, data->root.data, mntfh->size); + if (mntfh->size < sizeof(mntfh->data)) + memset(mntfh->data + mntfh->size, 0, + sizeof(mntfh->data) - mntfh->size); + + /* + * Translate to nfs_fs_context, which nfs_fill_super + * can deal with. + */ + ctx->flags = data->flags & NFS_MOUNT_FLAGMASK; + ctx->flags |= extra_flags; + ctx->rsize = data->rsize; + ctx->wsize = data->wsize; + ctx->timeo = data->timeo; + ctx->retrans = data->retrans; + ctx->acregmin = data->acregmin; + ctx->acregmax = data->acregmax; + ctx->acdirmin = data->acdirmin; + ctx->acdirmax = data->acdirmax; + ctx->need_mount = false; + + memcpy(sap, &data->addr, sizeof(data->addr)); + ctx->nfs_server.addrlen = sizeof(data->addr); + ctx->nfs_server.port = ntohs(data->addr.sin_port); + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) + goto out_no_address; + + if (!(data->flags & NFS_MOUNT_TCP)) + ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; + /* N.B. caller will free nfs_server.hostname in all cases */ + ctx->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL); + if (!ctx->nfs_server.hostname) + goto out_nomem; + + ctx->namlen = data->namlen; + ctx->bsize = data->bsize; + + if (data->flags & NFS_MOUNT_SECFLAVOUR) + ctx->selected_flavor = data->pseudoflavor; + else + ctx->selected_flavor = RPC_AUTH_UNIX; + + if (!(data->flags & NFS_MOUNT_NONLM)) + ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK| + NFS_MOUNT_LOCAL_FCNTL); + else + ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK| + NFS_MOUNT_LOCAL_FCNTL); + + /* + * The legacy version 6 binary mount data from userspace has a + * field used only to transport selinux information into the + * the kernel. To continue to support that functionality we + * have a touch of selinux knowledge here in the NFS code. The + * userspace code converted context=blah to just blah so we are + * converting back to the full string selinux understands. + */ + if (data->context[0]){ +#ifdef CONFIG_SECURITY_SELINUX + int ret; + + data->context[NFS_MAX_CONTEXT_LEN] = '\0'; + ret = vfs_parse_fs_string(fc, "context", + data->context, strlen(data->context)); + if (ret < 0) + return ret; +#else + return -EINVAL; +#endif + } + + break; + default: + goto generic; + } + + ctx->skip_reconfig_option_check = true; + return 0; + +generic: + return generic_parse_monolithic(fc, data); + +out_no_data: + if (is_remount_fc(fc)) { + ctx->skip_reconfig_option_check = true; + return 0; + } + return nfs_invalf(fc, "NFS: mount program didn't pass any mount data"); + +out_no_v3: + return nfs_invalf(fc, "NFS: nfs_mount_data version does not support v3"); + +out_no_sec: + return nfs_invalf(fc, "NFS: nfs_mount_data version supports only AUTH_SYS"); + +out_nomem: + dfprintk(MOUNT, "NFS: not enough memory to handle mount options"); + return -ENOMEM; + +out_no_address: + return nfs_invalf(fc, "NFS: mount program didn't pass remote address"); + +out_invalid_fh: + return nfs_invalf(fc, "NFS: invalid root filehandle"); +} + +#if IS_ENABLED(CONFIG_NFS_V4) +/* + * Validate NFSv4 mount options + */ +static int nfs4_parse_monolithic(struct fs_context *fc, + struct nfs4_mount_data *data) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + char *c; + + if (data == NULL) + goto out_no_data; + + ctx->version = 4; + + switch (data->version) { + case 1: + if (data->host_addrlen > sizeof(ctx->nfs_server.address)) + goto out_no_address; + if (data->host_addrlen == 0) + goto out_no_address; + ctx->nfs_server.addrlen = data->host_addrlen; + if (copy_from_user(sap, data->host_addr, data->host_addrlen)) + return -EFAULT; + if (!nfs_verify_server_address(sap)) + goto out_no_address; + ctx->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); + + if (data->auth_flavourlen) { + rpc_authflavor_t pseudoflavor; + if (data->auth_flavourlen > 1) + goto out_inval_auth; + if (copy_from_user(&pseudoflavor, + data->auth_flavours, + sizeof(pseudoflavor))) + return -EFAULT; + ctx->selected_flavor = pseudoflavor; + } else + ctx->selected_flavor = RPC_AUTH_UNIX; + + c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); + if (IS_ERR(c)) + return PTR_ERR(c); + ctx->nfs_server.hostname = c; + + c = strndup_user(data->mnt_path.data, NFS4_MAXPATHLEN); + if (IS_ERR(c)) + return PTR_ERR(c); + ctx->nfs_server.export_path = c; + dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", c); + + c = strndup_user(data->client_addr.data, 16); + if (IS_ERR(c)) + return PTR_ERR(c); + ctx->client_address = c; + + /* + * Translate to nfs_fs_context, which nfs_fill_super + * can deal with. + */ + + ctx->flags = data->flags & NFS4_MOUNT_FLAGMASK; + ctx->rsize = data->rsize; + ctx->wsize = data->wsize; + ctx->timeo = data->timeo; + ctx->retrans = data->retrans; + ctx->acregmin = data->acregmin; + ctx->acregmax = data->acregmax; + ctx->acdirmin = data->acdirmin; + ctx->acdirmax = data->acdirmax; + ctx->nfs_server.protocol = data->proto; + nfs_validate_transport_protocol(ctx); + if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; + + break; + default: + goto generic; + } + + ctx->skip_reconfig_option_check = true; + return 0; + +generic: + return generic_parse_monolithic(fc, data); + +out_no_data: + if (is_remount_fc(fc)) { + ctx->skip_reconfig_option_check = true; + return 0; + } + return nfs_invalf(fc, "NFS4: mount program didn't pass any mount data"); + +out_inval_auth: + return nfs_invalf(fc, "NFS4: Invalid number of RPC auth flavours %d", + data->auth_flavourlen); + +out_no_address: + return nfs_invalf(fc, "NFS4: mount program didn't pass remote address"); + +out_invalid_transport_udp: + return nfs_invalf(fc, "NFSv4: Unsupported transport protocol udp"); +} +#endif + +/* + * Parse a monolithic block of data from sys_mount(). + */ +static int nfs_fs_context_parse_monolithic(struct fs_context *fc, + void *data) +{ + if (fc->fs_type == &nfs_fs_type) + return nfs23_parse_monolithic(fc, data); + +#if IS_ENABLED(CONFIG_NFS_V4) + if (fc->fs_type == &nfs4_fs_type) + return nfs4_parse_monolithic(fc, data); +#endif + + return nfs_invalf(fc, "NFS: Unsupported monolithic data version"); +} + +/* + * Validate the preparsed information in the config. + */ +static int nfs_fs_context_validate(struct fs_context *fc) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct nfs_subversion *nfs_mod; + struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + int max_namelen = PAGE_SIZE; + int max_pathlen = NFS_MAXPATHLEN; + int port = 0; + int ret; + + if (!fc->source) + goto out_no_device_name; + + /* Check for sanity first. */ + if (ctx->minorversion && ctx->version != 4) + goto out_minorversion_mismatch; + + if (ctx->options & NFS_OPTION_MIGRATION && + (ctx->version != 4 || ctx->minorversion != 0)) + goto out_migration_misuse; + + /* Verify that any proto=/mountproto= options match the address + * families in the addr=/mountaddr= options. + */ + if (ctx->protofamily != AF_UNSPEC && + ctx->protofamily != ctx->nfs_server.address.sa_family) + goto out_proto_mismatch; + + if (ctx->mountfamily != AF_UNSPEC) { + if (ctx->mount_server.addrlen) { + if (ctx->mountfamily != ctx->mount_server.address.sa_family) + goto out_mountproto_mismatch; + } else { + if (ctx->mountfamily != ctx->nfs_server.address.sa_family) + goto out_mountproto_mismatch; + } + } + + if (!nfs_verify_server_address(sap)) + goto out_no_address; + + if (ctx->version == 4) { + if (IS_ENABLED(CONFIG_NFS_V4)) { + if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA) + port = NFS_RDMA_PORT; + else + port = NFS_PORT; + max_namelen = NFS4_MAXNAMLEN; + max_pathlen = NFS4_MAXPATHLEN; + nfs_validate_transport_protocol(ctx); + if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; + ctx->flags &= ~(NFS_MOUNT_NONLM | NFS_MOUNT_NOACL | + NFS_MOUNT_VER3 | NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + } else { + goto out_v4_not_compiled; + } + } else { + nfs_set_mount_transport_protocol(ctx); +#ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT + if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP) + goto out_invalid_transport_udp; +#endif + if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA) + port = NFS_RDMA_PORT; + } + + nfs_set_port(sap, &ctx->nfs_server.port, port); + + ret = nfs_parse_source(fc, max_namelen, max_pathlen); + if (ret < 0) + return ret; + + /* Load the NFS protocol module if we haven't done so yet */ + if (!ctx->nfs_mod) { + nfs_mod = get_nfs_version(ctx->version); + if (IS_ERR(nfs_mod)) { + ret = PTR_ERR(nfs_mod); + goto out_version_unavailable; + } + ctx->nfs_mod = nfs_mod; + } + return 0; + +out_no_device_name: + return nfs_invalf(fc, "NFS: Device name not specified"); +out_v4_not_compiled: + nfs_errorf(fc, "NFS: NFSv4 is not compiled into kernel"); + return -EPROTONOSUPPORT; +out_invalid_transport_udp: + return nfs_invalf(fc, "NFSv4: Unsupported transport protocol udp"); +out_no_address: + return nfs_invalf(fc, "NFS: mount program didn't pass remote address"); +out_mountproto_mismatch: + return nfs_invalf(fc, "NFS: Mount server address does not match mountproto= option"); +out_proto_mismatch: + return nfs_invalf(fc, "NFS: Server address does not match proto= option"); +out_minorversion_mismatch: + return nfs_invalf(fc, "NFS: Mount option vers=%u does not support minorversion=%u", + ctx->version, ctx->minorversion); +out_migration_misuse: + return nfs_invalf(fc, "NFS: 'Migration' not supported for this NFS version"); +out_version_unavailable: + nfs_errorf(fc, "NFS: Version unavailable"); + return ret; +} + +/* + * Create an NFS superblock by the appropriate method. + */ +static int nfs_get_tree(struct fs_context *fc) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + int err = nfs_fs_context_validate(fc); + + if (err) + return err; + if (!ctx->internal) + return ctx->nfs_mod->rpc_ops->try_get_tree(fc); + else + return nfs_get_tree_common(fc); +} + +/* + * Handle duplication of a configuration. The caller copied *src into *sc, but + * it can't deal with resource pointers in the filesystem context, so we have + * to do that. We need to clear pointers, copy data or get extra refs as + * appropriate. + */ +static int nfs_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) +{ + struct nfs_fs_context *src = nfs_fc2context(src_fc), *ctx; + + ctx = kmemdup(src, sizeof(struct nfs_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->mntfh = nfs_alloc_fhandle(); + if (!ctx->mntfh) { + kfree(ctx); + return -ENOMEM; + } + nfs_copy_fh(ctx->mntfh, src->mntfh); + + __module_get(ctx->nfs_mod->owner); + ctx->client_address = NULL; + ctx->mount_server.hostname = NULL; + ctx->nfs_server.export_path = NULL; + ctx->nfs_server.hostname = NULL; + ctx->fscache_uniq = NULL; + ctx->clone_data.fattr = NULL; + fc->fs_private = ctx; + return 0; +} + +static void nfs_fs_context_free(struct fs_context *fc) +{ + struct nfs_fs_context *ctx = nfs_fc2context(fc); + + if (ctx) { + if (ctx->server) + nfs_free_server(ctx->server); + if (ctx->nfs_mod) + put_nfs_version(ctx->nfs_mod); + kfree(ctx->client_address); + kfree(ctx->mount_server.hostname); + kfree(ctx->nfs_server.export_path); + kfree(ctx->nfs_server.hostname); + kfree(ctx->fscache_uniq); + nfs_free_fhandle(ctx->mntfh); + nfs_free_fattr(ctx->clone_data.fattr); + kfree(ctx); + } +} + +static const struct fs_context_operations nfs_fs_context_ops = { + .free = nfs_fs_context_free, + .dup = nfs_fs_context_dup, + .parse_param = nfs_fs_context_parse_param, + .parse_monolithic = nfs_fs_context_parse_monolithic, + .get_tree = nfs_get_tree, + .reconfigure = nfs_reconfigure, +}; + +/* + * Prepare superblock configuration. We use the namespaces attached to the + * context. This may be the current process's namespaces, or it may be a + * container's namespaces. + */ +static int nfs_init_fs_context(struct fs_context *fc) +{ + struct nfs_fs_context *ctx; + + ctx = kzalloc(sizeof(struct nfs_fs_context), GFP_KERNEL); + if (unlikely(!ctx)) + return -ENOMEM; + + ctx->mntfh = nfs_alloc_fhandle(); + if (unlikely(!ctx->mntfh)) { + kfree(ctx); + return -ENOMEM; + } + + ctx->protofamily = AF_UNSPEC; + ctx->mountfamily = AF_UNSPEC; + ctx->mount_server.port = NFS_UNSPEC_PORT; + + if (fc->root) { + /* reconfigure, start with the current config */ + struct nfs_server *nfss = fc->root->d_sb->s_fs_info; + struct net *net = nfss->nfs_client->cl_net; + + ctx->flags = nfss->flags; + ctx->rsize = nfss->rsize; + ctx->wsize = nfss->wsize; + ctx->retrans = nfss->client->cl_timeout->to_retries; + ctx->selected_flavor = nfss->client->cl_auth->au_flavor; + ctx->acregmin = nfss->acregmin / HZ; + ctx->acregmax = nfss->acregmax / HZ; + ctx->acdirmin = nfss->acdirmin / HZ; + ctx->acdirmax = nfss->acdirmax / HZ; + ctx->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; + ctx->nfs_server.port = nfss->port; + ctx->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; + ctx->version = nfss->nfs_client->rpc_ops->version; + ctx->minorversion = nfss->nfs_client->cl_minorversion; + + memcpy(&ctx->nfs_server.address, &nfss->nfs_client->cl_addr, + ctx->nfs_server.addrlen); + + if (fc->net_ns != net) { + put_net(fc->net_ns); + fc->net_ns = get_net(net); + } + + ctx->nfs_mod = nfss->nfs_client->cl_nfs_mod; + __module_get(ctx->nfs_mod->owner); + } else { + /* defaults */ + ctx->timeo = NFS_UNSPEC_TIMEO; + ctx->retrans = NFS_UNSPEC_RETRANS; + ctx->acregmin = NFS_DEF_ACREGMIN; + ctx->acregmax = NFS_DEF_ACREGMAX; + ctx->acdirmin = NFS_DEF_ACDIRMIN; + ctx->acdirmax = NFS_DEF_ACDIRMAX; + ctx->nfs_server.port = NFS_UNSPEC_PORT; + ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; + ctx->selected_flavor = RPC_AUTH_MAXFLAVOR; + ctx->minorversion = 0; + ctx->need_mount = true; + } + fc->fs_private = ctx; + fc->ops = &nfs_fs_context_ops; + return 0; +} + +struct file_system_type nfs_fs_type = { + .owner = THIS_MODULE, + .name = "nfs", + .init_fs_context = nfs_init_fs_context, + .parameters = nfs_fs_parameters, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; +MODULE_ALIAS_FS("nfs"); +EXPORT_SYMBOL_GPL(nfs_fs_type); + +#if IS_ENABLED(CONFIG_NFS_V4) +struct file_system_type nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .init_fs_context = nfs_init_fs_context, + .parameters = nfs_fs_parameters, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, +}; +MODULE_ALIAS_FS("nfs4"); +MODULE_ALIAS("nfs4"); +EXPORT_SYMBOL_GPL(nfs4_fs_type); +#endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7def925d3af5..52270bfac120 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -128,7 +128,7 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int return; key->nfs_client = nfss->nfs_client; - key->key.super.s_flags = sb->s_flags & NFS_MS_MASK; + key->key.super.s_flags = sb->s_flags & NFS_SB_MASK; key->key.nfs_server.flags = nfss->flags; key->key.nfs_server.rsize = nfss->rsize; key->key.nfs_server.wsize = nfss->wsize; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 878c4c5982d9..b012c2668a1f 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -64,66 +64,71 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i /* * get an NFS2/NFS3 root dentry from the root filehandle */ -struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh, - const char *devname) +int nfs_get_root(struct super_block *s, struct fs_context *fc) { - struct nfs_server *server = NFS_SB(sb); + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct nfs_server *server = NFS_SB(s); struct nfs_fsinfo fsinfo; - struct dentry *ret; + struct dentry *root; struct inode *inode; - void *name = kstrdup(devname, GFP_KERNEL); - int error; + char *name; + int error = -ENOMEM; + name = kstrdup(fc->source, GFP_KERNEL); if (!name) - return ERR_PTR(-ENOMEM); + goto out; /* get the actual root for this mount */ fsinfo.fattr = nfs_alloc_fattr(); - if (fsinfo.fattr == NULL) { - kfree(name); - return ERR_PTR(-ENOMEM); - } + if (fsinfo.fattr == NULL) + goto out_name; - error = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo); + error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo); if (error < 0) { dprintk("nfs_get_root: getattr error = %d\n", -error); - ret = ERR_PTR(error); - goto out; + nfs_errorf(fc, "NFS: Couldn't getattr on root"); + goto out_fattr; } - inode = nfs_fhget(sb, mntfh, fsinfo.fattr, NULL); + inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr, NULL); if (IS_ERR(inode)) { dprintk("nfs_get_root: get root inode failed\n"); - ret = ERR_CAST(inode); - goto out; + error = PTR_ERR(inode); + nfs_errorf(fc, "NFS: Couldn't get root inode"); + goto out_fattr; } - error = nfs_superblock_set_dummy_root(sb, inode); - if (error != 0) { - ret = ERR_PTR(error); - goto out; - } + error = nfs_superblock_set_dummy_root(s, inode); + if (error != 0) + goto out_fattr; /* root dentries normally start off anonymous and get spliced in later * if the dentry tree reaches them; however if the dentry already * exists, we'll pick it up at this point and use it as the root */ - ret = d_obtain_root(inode); - if (IS_ERR(ret)) { + root = d_obtain_root(inode); + if (IS_ERR(root)) { dprintk("nfs_get_root: get root dentry failed\n"); - goto out; + error = PTR_ERR(root); + nfs_errorf(fc, "NFS: Couldn't get root dentry"); + goto out_fattr; } - security_d_instantiate(ret, inode); - spin_lock(&ret->d_lock); - if (IS_ROOT(ret) && !ret->d_fsdata && - !(ret->d_flags & DCACHE_NFSFS_RENAMED)) { - ret->d_fsdata = name; + security_d_instantiate(root, inode); + spin_lock(&root->d_lock); + if (IS_ROOT(root) && !root->d_fsdata && + !(root->d_flags & DCACHE_NFSFS_RENAMED)) { + root->d_fsdata = name; name = NULL; } - spin_unlock(&ret->d_lock); -out: - kfree(name); + spin_unlock(&root->d_lock); + fc->root = root; + error = 0; + +out_fattr: nfs_free_fattr(fsinfo.fattr); - return ret; +out_name: + kfree(name); +out: + return error; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b0b4b9f303fd..1309e6f47f3d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1061,7 +1061,7 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct rcu_read_lock(); list_for_each_entry_rcu(pos, &nfsi->open_files, list) { - if (cred != NULL && pos->cred != cred) + if (cred != NULL && cred_fscmp(pos->cred, cred) != 0) continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; @@ -1156,7 +1156,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); - if (status == -ESTALE) { + switch (status) { + case -ETIMEDOUT: + /* A soft timeout occurred. Use cached information? */ + if (server->flags & NFS_MOUNT_SOFTREVAL) + status = 0; + break; + case -ESTALE: nfs_zap_caches(inode); if (!S_ISDIR(inode->i_mode)) set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 24a65da58aa9..f80c47d5ff27 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -4,17 +4,19 @@ */ #include "nfs4_fs.h" -#include <linux/mount.h> +#include <linux/fs_context.h> #include <linux/security.h> #include <linux/crc32.h> +#include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> #include <linux/wait_bit.h> -#define NFS_MS_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) +#define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; struct nfs_string; +struct nfs_pageio_descriptor; static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { @@ -31,17 +33,14 @@ static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) return 1; } -struct nfs_clone_mount { - const struct super_block *sb; - const struct dentry *dentry; - struct nfs_fh *fh; - struct nfs_fattr *fattr; - char *hostname; - char *mnt_path; - struct sockaddr *addr; - size_t addrlen; - rpc_authflavor_t authflavor; -}; +static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) +{ + if (!(NFS_SB(dentry->d_sb)->flags & NFS_MOUNT_SOFTREVAL)) + return false; + if (!d_is_positive(dentry) || !NFS_FH(d_inode(dentry))->size) + return false; + return true; +} /* * Note: RFC 1813 doesn't limit the number of auth flavors that @@ -82,12 +81,16 @@ struct nfs_client_initdata { /* * In-kernel mount arguments */ -struct nfs_parsed_mount_data { - int flags; +struct nfs_fs_context { + bool internal; + bool skip_reconfig_option_check; + bool need_mount; + bool sloppy; + unsigned int flags; /* NFS{,4}_MOUNT_* flags */ unsigned int rsize, wsize; unsigned int timeo, retrans; - unsigned int acregmin, acregmax, - acdirmin, acdirmax; + unsigned int acregmin, acregmax; + unsigned int acdirmin, acdirmax; unsigned int namlen; unsigned int options; unsigned int bsize; @@ -97,10 +100,14 @@ struct nfs_parsed_mount_data { unsigned int version; unsigned int minorversion; char *fscache_uniq; - bool need_mount; + unsigned short protofamily; + unsigned short mountfamily; struct { - struct sockaddr_storage address; + union { + struct sockaddr address; + struct sockaddr_storage _address; + }; size_t addrlen; char *hostname; u32 version; @@ -109,19 +116,41 @@ struct nfs_parsed_mount_data { } mount_server; struct { - struct sockaddr_storage address; + union { + struct sockaddr address; + struct sockaddr_storage _address; + }; size_t addrlen; char *hostname; char *export_path; int port; unsigned short protocol; unsigned short nconnect; + unsigned short export_path_len; } nfs_server; - void *lsm_opts; - struct net *net; + struct nfs_fh *mntfh; + struct nfs_server *server; + struct nfs_subversion *nfs_mod; + + /* Information for a cloned mount. */ + struct nfs_clone_mount { + struct super_block *sb; + struct dentry *dentry; + struct nfs_fattr *fattr; + unsigned int inherited_bsize; + } clone_data; }; +#define nfs_errorf(fc, fmt, ...) errorf(fc, fmt, ## __VA_ARGS__) +#define nfs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__) +#define nfs_warnf(fc, fmt, ...) warnf(fc, fmt, ## __VA_ARGS__) + +static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) +{ + return fc->fs_private; +} + /* mount_clnt.c */ struct nfs_mount_request { struct sockaddr *sap; @@ -137,14 +166,6 @@ struct nfs_mount_request { struct net *net; }; -struct nfs_mount_info { - void (*fill_super)(struct super_block *, struct nfs_mount_info *); - int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *); - struct nfs_parsed_mount_data *parsed; - struct nfs_clone_mount *cloned; - struct nfs_fh *mntfh; -}; - extern int nfs_mount(struct nfs_mount_request *info); extern void nfs_umount(const struct nfs_mount_request *info); @@ -170,13 +191,9 @@ extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); -extern struct nfs_server *nfs_create_server(struct nfs_mount_info *, - struct nfs_subversion *); -extern struct nfs_server *nfs4_create_server( - struct nfs_mount_info *, - struct nfs_subversion *); -extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, - struct nfs_fh *); +extern struct nfs_server *nfs_create_server(struct fs_context *); +extern struct nfs_server *nfs4_create_server(struct fs_context *); +extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, struct sockaddr *sap, size_t salen, struct net *net); @@ -227,7 +244,9 @@ static inline void nfs_fs_proc_exit(void) extern const struct svc_version nfs4_callback_version1; extern const struct svc_version nfs4_callback_version4; -struct nfs_pageio_descriptor; +/* fs_context.c */ +extern struct file_system_type nfs_fs_type; + /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); @@ -387,23 +406,10 @@ extern int nfs_wait_atomic_killable(atomic_t *p, unsigned int mode); /* super.c */ extern const struct super_operations nfs_sops; -extern struct file_system_type nfs_fs_type; -extern struct file_system_type nfs_xdev_fs_type; -#if IS_ENABLED(CONFIG_NFS_V4) -extern struct file_system_type nfs4_referral_fs_type; -#endif bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); -struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *, - struct nfs_subversion *); -int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); -int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); -struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *, - struct nfs_mount_info *, struct nfs_subversion *); -struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *); -struct dentry * nfs_xdev_mount_common(struct file_system_type *, int, - const char *, struct nfs_mount_info *); +int nfs_try_get_tree(struct fs_context *); +int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); -void nfs_fill_super(struct super_block *, struct nfs_mount_info *); extern struct rpc_stat nfs_rpcstat; @@ -430,18 +436,12 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); -struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *, - struct nfs_fh *, struct nfs_fattr *); -struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *, - struct nfs_fattr *, rpc_authflavor_t); +int nfs_submount(struct fs_context *, struct nfs_server *); +int nfs_do_submount(struct fs_context *); /* getroot.c */ -extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, - const char *); +extern int nfs_get_root(struct super_block *s, struct fs_context *fc); #if IS_ENABLED(CONFIG_NFS_V4) -extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, - const char *); - extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif @@ -460,7 +460,7 @@ int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); -int nfs_remount(struct super_block *sb, int *flags, char *raw_data); +int nfs_reconfigure(struct fs_context *); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, @@ -706,9 +706,9 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) } /* - * Convert a struct timespec into a 64-bit change attribute + * Convert a struct timespec64 into a 64-bit change attribute * - * This does approximately the same thing as timespec_to_ns(), + * This does approximately the same thing as timespec64_to_ns(), * but for calculation efficiency, we multiply the seconds by * 1024*1024*1024. */ @@ -777,3 +777,16 @@ static inline bool nfs_error_is_fatal_on_server(int err) } return nfs_error_is_fatal(err); } + +/* + * Select between a default port value and a user-specified port value. + * If a zero value is set, then autobind will be used. + */ +static inline void nfs_set_port(struct sockaddr *sap, int *port, + const unsigned short default_port) +{ + if (*port == NFS_UNSPEC_PORT) + *port = default_port; + + rpc_set_port(sap, *port); +} diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index cb7c10e9721e..35c8cb2d7637 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -29,9 +29,7 @@ */ #define encode_dirpath_sz (1 + XDR_QUADLEN(MNTPATHLEN)) #define MNT_status_sz (1) -#define MNT_fhs_status_sz (1) #define MNT_fhandle_sz XDR_QUADLEN(NFS2_FHSIZE) -#define MNT_fhandle3_sz (1 + XDR_QUADLEN(NFS3_FHSIZE)) #define MNT_authflav3_sz (1 + NFS_MAX_SECFLAVORS) /* diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 5e0e9d29f5c5..ad6077404947 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -19,6 +19,7 @@ #include <linux/vfs.h> #include <linux/sunrpc/gss_api.h> #include "internal.h" +#include "nfs.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -139,34 +140,65 @@ EXPORT_SYMBOL_GPL(nfs_path); */ struct vfsmount *nfs_d_automount(struct path *path) { - struct vfsmount *mnt; + struct nfs_fs_context *ctx; + struct fs_context *fc; + struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct nfs_server *server = NFS_SERVER(d_inode(path->dentry)); - struct nfs_fh *fh = NULL; - struct nfs_fattr *fattr = NULL; + struct nfs_client *client = server->nfs_client; + int ret; if (IS_ROOT(path->dentry)) return ERR_PTR(-ESTALE); - mnt = ERR_PTR(-ENOMEM); - fh = nfs_alloc_fhandle(); - fattr = nfs_alloc_fattr(); - if (fh == NULL || fattr == NULL) - goto out; + /* Open a new filesystem context, transferring parameters from the + * parent superblock, including the network namespace. + */ + fc = fs_context_for_submount(&nfs_fs_type, path->dentry); + if (IS_ERR(fc)) + return ERR_CAST(fc); - mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr); + ctx = nfs_fc2context(fc); + ctx->clone_data.dentry = path->dentry; + ctx->clone_data.sb = path->dentry->d_sb; + ctx->clone_data.fattr = nfs_alloc_fattr(); + if (!ctx->clone_data.fattr) + goto out_fc; + + if (fc->net_ns != client->cl_net) { + put_net(fc->net_ns); + fc->net_ns = get_net(client->cl_net); + } + + /* for submounts we want the same server; referrals will reassign */ + memcpy(&ctx->nfs_server.address, &client->cl_addr, client->cl_addrlen); + ctx->nfs_server.addrlen = client->cl_addrlen; + ctx->nfs_server.port = server->port; + + ctx->version = client->rpc_ops->version; + ctx->minorversion = client->cl_minorversion; + ctx->nfs_mod = client->cl_nfs_mod; + __module_get(ctx->nfs_mod->owner); + + ret = client->rpc_ops->submount(fc, server); + if (ret < 0) { + mnt = ERR_PTR(ret); + goto out_fc; + } + + up_write(&fc->root->d_sb->s_umount); + mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) - goto out; + goto out_fc; if (nfs_mountpoint_expiry_timeout < 0) - goto out; + goto out_fc; mntget(mnt); /* prevent immediate expiration */ mnt_set_expiry(mnt, &nfs_automount_list); schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout); -out: - nfs_free_fattr(fattr); - nfs_free_fhandle(fh); +out_fc: + put_fs_context(fc); return mnt; } @@ -213,16 +245,6 @@ void nfs_release_automount_timer(void) cancel_delayed_work(&nfs_automount_task); } -/* - * Clone a mountpoint of the appropriate type - */ -static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, - const char *devname, - struct nfs_clone_mount *mountdata) -{ - return vfs_submount(mountdata->dentry, &nfs_xdev_fs_type, devname, mountdata); -} - /** * nfs_do_submount - set up mountpoint when crossing a filesystem boundary * @dentry: parent directory @@ -231,46 +253,62 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, * @authflavor: security flavor to use when performing the mount * */ -struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr, rpc_authflavor_t authflavor) +int nfs_do_submount(struct fs_context *fc) { - struct nfs_clone_mount mountdata = { - .sb = dentry->d_sb, - .dentry = dentry, - .fh = fh, - .fattr = fattr, - .authflavor = authflavor, - }; - struct vfsmount *mnt; - char *page = (char *) __get_free_page(GFP_USER); - char *devname; - - if (page == NULL) - return ERR_PTR(-ENOMEM); - - devname = nfs_devname(dentry, page, PAGE_SIZE); - if (IS_ERR(devname)) - mnt = ERR_CAST(devname); - else - mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata); - - free_page((unsigned long)page); - return mnt; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct dentry *dentry = ctx->clone_data.dentry; + struct nfs_server *server; + char *buffer, *p; + int ret; + + /* create a new volume representation */ + server = ctx->nfs_mod->rpc_ops->clone_server(NFS_SB(ctx->clone_data.sb), + ctx->mntfh, + ctx->clone_data.fattr, + ctx->selected_flavor); + + if (IS_ERR(server)) + return PTR_ERR(server); + + ctx->server = server; + + buffer = kmalloc(4096, GFP_USER); + if (!buffer) + return -ENOMEM; + + ctx->internal = true; + ctx->clone_data.inherited_bsize = ctx->clone_data.sb->s_blocksize_bits; + + p = nfs_devname(dentry, buffer, 4096); + if (IS_ERR(p)) { + nfs_errorf(fc, "NFS: Couldn't determine submount pathname"); + ret = PTR_ERR(p); + } else { + ret = vfs_parse_fs_string(fc, "source", p, buffer + 4096 - p); + if (!ret) + ret = vfs_get_tree(fc); + } + kfree(buffer); + return ret; } EXPORT_SYMBOL_GPL(nfs_do_submount); -struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, - struct nfs_fh *fh, struct nfs_fattr *fattr) +int nfs_submount(struct fs_context *fc, struct nfs_server *server) { - int err; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct dentry *dentry = ctx->clone_data.dentry; struct dentry *parent = dget_parent(dentry); + int err; /* Look it up again to get its attributes */ - err = server->nfs_client->rpc_ops->lookup(d_inode(parent), &dentry->d_name, fh, fattr, NULL); + err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, + ctx->mntfh, ctx->clone_data.fattr, + NULL); dput(parent); if (err != 0) - return ERR_PTR(err); + return err; - return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor); + ctx->selected_flavor = server->client->cl_auth->au_flavor; + return nfs_do_submount(fc); } EXPORT_SYMBOL_GPL(nfs_submount); diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index d94c7abdf25a..f6676af37d5d 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -360,17 +360,17 @@ static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr, else *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); - if (attr->ia_valid & ATTR_ATIME_SET) { + if (attr->ia_valid & ATTR_ATIME_SET) p = xdr_encode_time(p, &attr->ia_atime); - } else if (attr->ia_valid & ATTR_ATIME) { + else if (attr->ia_valid & ATTR_ATIME) p = xdr_encode_current_server_time(p, &attr->ia_atime); - } else + else p = xdr_time_not_set(p); - if (attr->ia_valid & ATTR_MTIME_SET) { + if (attr->ia_valid & ATTR_MTIME_SET) xdr_encode_time(p, &attr->ia_mtime); - } else if (attr->ia_valid & ATTR_MTIME) { + else if (attr->ia_valid & ATTR_MTIME) xdr_encode_current_server_time(p, &attr->ia_mtime); - } else + else xdr_time_not_set(p); } diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index f82e11c4cb56..1b950b66b3bb 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -27,7 +27,7 @@ static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, #endif /* CONFIG_NFS_V3_ACL */ /* nfs3client.c */ -struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *); +struct nfs_server *nfs3_create_server(struct fs_context *); struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 223904bc40a7..5601e47360c2 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -46,10 +46,10 @@ static inline void nfs_init_server_aclclient(struct nfs_server *server) } #endif -struct nfs_server *nfs3_create_server(struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) +struct nfs_server *nfs3_create_server(struct fs_context *fc) { - struct nfs_server *server = nfs_create_server(mount_info, nfs_mod); + struct nfs_server *server = nfs_create_server(fc); + /* Create a client RPC handle for the NFS v3 ACL management interface */ if (!IS_ERR(server)) nfs_init_server_aclclient(server); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 9eb2f1a503ab..a46d1d5d16d8 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -110,10 +110,15 @@ nfs3_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_resp = fattr, }; int status; + unsigned short task_flags = 0; + + /* Is this is an attribute revalidation, subject to softreval? */ + if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) + task_flags |= RPC_TASK_TIMEOUT; dprintk("NFS call getattr\n"); nfs_fattr_init(fattr); - status = rpc_call_sync(server->client, &msg, 0); + status = rpc_call_sync(server->client, &msg, task_flags); dprintk("NFS reply getattr: %d\n", status); return status; } @@ -140,23 +145,23 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, nfs_fattr_init(fattr); status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); if (status == 0) { + nfs_setattr_update_inode(inode, sattr, fattr); if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); - nfs_setattr_update_inode(inode, sattr, fattr); } dprintk("NFS reply setattr: %d\n", status); return status; } static int -nfs3_proc_lookup(struct inode *dir, const struct qstr *name, +nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { struct nfs3_diropargs arg = { .fh = NFS_FH(dir), - .name = name->name, - .len = name->len + .name = dentry->d_name.name, + .len = dentry->d_name.len }; struct nfs3_diropres res = { .fh = fhandle, @@ -168,20 +173,25 @@ nfs3_proc_lookup(struct inode *dir, const struct qstr *name, .rpc_resp = &res, }; int status; + unsigned short task_flags = 0; - dprintk("NFS call lookup %s\n", name->name); + /* Is this is an attribute revalidation, subject to softreval? */ + if (nfs_lookup_is_soft_revalidate(dentry)) + task_flags |= RPC_TASK_TIMEOUT; + + dprintk("NFS call lookup %pd2\n", dentry); res.dir_attr = nfs_alloc_fattr(); if (res.dir_attr == NULL) return -ENOMEM; nfs_fattr_init(fattr); - status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, task_flags); nfs_refresh_inode(dir, res.dir_attr); if (status >= 0 && !(fattr->valid & NFS_ATTR_FATTR)) { msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; msg.rpc_argp = fhandle; msg.rpc_resp = fattr; - status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, task_flags); } nfs_free_fattr(res.dir_attr); dprintk("NFS reply lookup: %d\n", status); @@ -990,7 +1000,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .nlmclnt_ops = &nlmclnt_fl_close_lock_ops, .getroot = nfs3_proc_get_root, .submount = nfs_submount, - .try_mount = nfs_try_mount, + .try_get_tree = nfs_try_get_tree, .getattr = nfs3_proc_getattr, .setattr = nfs3_proc_setattr, .lookup = nfs3_proc_lookup, diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 927eb680f161..69971f6c840d 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2334,6 +2334,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, void *data) { struct nfs_commitres *result = data; + struct nfs_writeverf *verf = result->verf; enum nfs_stat status; int error; @@ -2346,7 +2347,9 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, result->op_status = status; if (status != NFS3_OK) goto out_status; - error = decode_writeverf3(xdr, &result->verf->verifier); + error = decode_writeverf3(xdr, &verf->verifier); + if (!error) + verf->committed = NFS_FILE_SYNC; out: return error; out_status: diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 1fe83e0f663e..e2ae54b35dfe 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -61,8 +61,11 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context, lock, FMODE_WRITE); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; + } res.falloc_fattr = nfs_alloc_fattr(); if (!res.falloc_fattr) @@ -287,8 +290,11 @@ static ssize_t _nfs42_proc_copy(struct file *src, } else { status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context, src_lock, FMODE_READ); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; + } } status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping, pos_src, pos_src + (loff_t)count - 1); @@ -297,8 +303,11 @@ static ssize_t _nfs42_proc_copy(struct file *src, status = nfs4_set_rw_stateid(&args->dst_stateid, dst_lock->open_context, dst_lock, FMODE_WRITE); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; + } status = nfs_sync_inode(dst_inode); if (status) @@ -334,14 +343,14 @@ static ssize_t _nfs42_proc_copy(struct file *src, status = handle_async_copy(res, dst_server, src_server, src, dst, &args->src_stateid, restart); if (status) - return status; + goto out; } if ((!res->synchronous || !args->sync) && res->write_res.verifier.committed != NFS_FILE_SYNC) { status = process_copy_commit(dst, pos_dst, res); if (status) - return status; + goto out; } truncate_pagecache_range(dst_inode, pos_dst, @@ -546,8 +555,11 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx, FMODE_READ); nfs_put_lock_context(l_ctx); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; + } status = nfs4_call_sync(src_server->client, src_server, &msg, &args->cna_seq_args, &res->cnr_seq_res, 0); @@ -618,8 +630,11 @@ static loff_t _nfs42_proc_llseek(struct file *filep, status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context, lock, FMODE_READ); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; + } status = nfs_filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); @@ -994,13 +1009,18 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context, src_lock, FMODE_READ); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; - + } status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context, dst_lock, FMODE_WRITE); - if (status) + if (status) { + if (status == -EAGAIN) + status = -NFS4ERR_BAD_STATEID; return status; + } res.dst_fattr = nfs_alloc_fattr(); if (!res.dst_fattr) diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index a7a73b1d1fec..8be1ba7c62bb 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -268,14 +268,13 @@ extern const struct dentry_operations nfs4_dentry_operations; int nfs_atomic_open(struct inode *, struct dentry *, struct file *, unsigned, umode_t); -/* super.c */ +/* fs_context.c */ extern struct file_system_type nfs4_fs_type; /* nfs4namespace.c */ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, const struct qstr *); -struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, - struct nfs_fh *, struct nfs_fattr *); +int nfs4_submount(struct fs_context *, struct nfs_server *); int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); @@ -303,8 +302,10 @@ extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struc extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, struct page *page, const struct cred *); extern int nfs4_proc_fsid_present(struct inode *, const struct cred *); -extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, const struct qstr *, - struct nfs_fh *, struct nfs_fattr *); +extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, + struct dentry *, + struct nfs_fh *, + struct nfs_fattr *); extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); extern const struct xattr_handler *nfs4_xattr_handlers[]; extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, @@ -446,9 +447,7 @@ extern void nfs4_schedule_state_renewal(struct nfs_client *); extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); extern void nfs4_kill_renewd(struct nfs_client *); extern void nfs4_renew_state(struct work_struct *); -extern void nfs4_set_lease_period(struct nfs_client *clp, - unsigned long lease, - unsigned long lastrenewed); +extern void nfs4_set_lease_period(struct nfs_client *clp, unsigned long lease); /* nfs4state.c */ @@ -526,7 +525,6 @@ extern const nfs4_stateid invalid_stateid; /* nfs4super.c */ struct nfs_mount_info; extern struct nfs_subversion nfs_v4; -struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *); extern bool nfs4_disable_idmapping; extern unsigned short max_session_slots; extern unsigned short max_session_cb_slots; @@ -536,6 +534,9 @@ extern bool recover_lost_locks; #define NFS4_CLIENT_ID_UNIQ_LEN (64) extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN]; +extern int nfs4_try_get_tree(struct fs_context *); +extern int nfs4_get_referral_tree(struct fs_context *); + /* nfs4sysctl.c */ #ifdef CONFIG_SYSCTL int nfs4_register_sysctl(void); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 460d6251c405..0cd767e5c977 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1055,66 +1055,64 @@ out: /* * Create a version 4 volume record */ -static int nfs4_init_server(struct nfs_server *server, - struct nfs_parsed_mount_data *data) +static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); struct rpc_timeout timeparms; int error; - nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, - data->timeo, data->retrans); + nfs_init_timeout_values(&timeparms, ctx->nfs_server.protocol, + ctx->timeo, ctx->retrans); /* Initialise the client representation from the mount data */ - server->flags = data->flags; - server->options = data->options; - server->auth_info = data->auth_info; + server->flags = ctx->flags; + server->options = ctx->options; + server->auth_info = ctx->auth_info; /* Use the first specified auth flavor. If this flavor isn't * allowed by the server, use the SECINFO path to try the * other specified flavors */ - if (data->auth_info.flavor_len >= 1) - data->selected_flavor = data->auth_info.flavors[0]; + if (ctx->auth_info.flavor_len >= 1) + ctx->selected_flavor = ctx->auth_info.flavors[0]; else - data->selected_flavor = RPC_AUTH_UNIX; + ctx->selected_flavor = RPC_AUTH_UNIX; /* Get a client record */ error = nfs4_set_client(server, - data->nfs_server.hostname, - (const struct sockaddr *)&data->nfs_server.address, - data->nfs_server.addrlen, - data->client_address, - data->nfs_server.protocol, - &timeparms, - data->minorversion, - data->nfs_server.nconnect, - data->net); + ctx->nfs_server.hostname, + &ctx->nfs_server.address, + ctx->nfs_server.addrlen, + ctx->client_address, + ctx->nfs_server.protocol, + &timeparms, + ctx->minorversion, + ctx->nfs_server.nconnect, + fc->net_ns); if (error < 0) return error; - if (data->rsize) - server->rsize = nfs_block_size(data->rsize, NULL); - if (data->wsize) - server->wsize = nfs_block_size(data->wsize, NULL); + if (ctx->rsize) + server->rsize = nfs_block_size(ctx->rsize, NULL); + if (ctx->wsize) + server->wsize = nfs_block_size(ctx->wsize, NULL); - server->acregmin = data->acregmin * HZ; - server->acregmax = data->acregmax * HZ; - server->acdirmin = data->acdirmin * HZ; - server->acdirmax = data->acdirmax * HZ; - server->port = data->nfs_server.port; + server->acregmin = ctx->acregmin * HZ; + server->acregmax = ctx->acregmax * HZ; + server->acdirmin = ctx->acdirmin * HZ; + server->acdirmax = ctx->acdirmax * HZ; + server->port = ctx->nfs_server.port; return nfs_init_server_rpcclient(server, &timeparms, - data->selected_flavor); + ctx->selected_flavor); } /* * Create a version 4 volume record * - keyed on server and FSID */ -/*struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data, - struct nfs_fh *mntfh)*/ -struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) +struct nfs_server *nfs4_create_server(struct fs_context *fc) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_server *server; bool auth_probe; int error; @@ -1125,14 +1123,14 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, server->cred = get_cred(current_cred()); - auth_probe = mount_info->parsed->auth_info.flavor_len < 1; + auth_probe = ctx->auth_info.flavor_len < 1; /* set up the general RPC client */ - error = nfs4_init_server(server, mount_info->parsed); + error = nfs4_init_server(server, fc); if (error < 0) goto error; - error = nfs4_server_common_setup(server, mount_info->mntfh, auth_probe); + error = nfs4_server_common_setup(server, ctx->mntfh, auth_probe); if (error < 0) goto error; @@ -1146,9 +1144,9 @@ error: /* * Create an NFS4 referral server record */ -struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, - struct nfs_fh *mntfh) +struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_client *parent_client; struct nfs_server *server, *parent_server; bool auth_probe; @@ -1158,7 +1156,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, if (!server) return ERR_PTR(-ENOMEM); - parent_server = NFS_SB(data->sb); + parent_server = NFS_SB(ctx->clone_data.sb); parent_client = parent_server->nfs_client; server->cred = get_cred(parent_server->cred); @@ -1168,10 +1166,11 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, /* Get a client representation */ #if IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) - rpc_set_port(data->addr, NFS_RDMA_PORT); - error = nfs4_set_client(server, data->hostname, - data->addr, - data->addrlen, + rpc_set_port(&ctx->nfs_server.address, NFS_RDMA_PORT); + error = nfs4_set_client(server, + ctx->nfs_server.hostname, + &ctx->nfs_server.address, + ctx->nfs_server.addrlen, parent_client->cl_ipaddr, XPRT_TRANSPORT_RDMA, parent_server->client->cl_timeout, @@ -1182,10 +1181,11 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, goto init_server; #endif /* IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) */ - rpc_set_port(data->addr, NFS_PORT); - error = nfs4_set_client(server, data->hostname, - data->addr, - data->addrlen, + rpc_set_port(&ctx->nfs_server.address, NFS_PORT); + error = nfs4_set_client(server, + ctx->nfs_server.hostname, + &ctx->nfs_server.address, + ctx->nfs_server.addrlen, parent_client->cl_ipaddr, XPRT_TRANSPORT_TCP, parent_server->client->cl_timeout, @@ -1198,13 +1198,14 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, #if IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) init_server: #endif - error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor); + error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, + ctx->selected_flavor); if (error < 0) goto error; auth_probe = parent_server->auth_info.flavor_len < 1; - error = nfs4_server_common_setup(server, mntfh, auth_probe); + error = nfs4_server_common_setup(server, ctx->mntfh, auth_probe); if (error < 0) goto error; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 620de905cba9..be4eb720d5b6 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/falloc.h> +#include <linux/mount.h> #include <linux/nfs_fs.h> #include "delegation.h" #include "internal.h" diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 2e460c33ae48..84026e7b8a5f 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -8,6 +8,7 @@ * NFSv4 namespace */ +#include <linux/module.h> #include <linux/dcache.h> #include <linux/mount.h> #include <linux/namei.h> @@ -21,37 +22,64 @@ #include <linux/inet.h> #include "internal.h" #include "nfs4_fs.h" +#include "nfs.h" #include "dns_resolve.h" #define NFSDBG_FACILITY NFSDBG_VFS /* + * Work out the length that an NFSv4 path would render to as a standard posix + * path, with a leading slash but no terminating slash. + */ +static ssize_t nfs4_pathname_len(const struct nfs4_pathname *pathname) +{ + ssize_t len = 0; + int i; + + for (i = 0; i < pathname->ncomponents; i++) { + const struct nfs4_string *component = &pathname->components[i]; + + if (component->len > NAME_MAX) + goto too_long; + len += 1 + component->len; /* Adding "/foo" */ + if (len > PATH_MAX) + goto too_long; + } + return len; + +too_long: + return -ENAMETOOLONG; +} + +/* * Convert the NFSv4 pathname components into a standard posix path. - * - * Note that the resulting string will be placed at the end of the buffer */ -static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname, - char *buffer, ssize_t buflen) +static char *nfs4_pathname_string(const struct nfs4_pathname *pathname, + unsigned short *_len) { - char *end = buffer + buflen; - int n; + ssize_t len; + char *buf, *p; + int i; + + len = nfs4_pathname_len(pathname); + if (len < 0) + return ERR_PTR(len); + *_len = len; + + p = buf = kmalloc(len + 1, GFP_KERNEL); + if (!buf) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < pathname->ncomponents; i++) { + const struct nfs4_string *component = &pathname->components[i]; - *--end = '\0'; - buflen--; - - n = pathname->ncomponents; - while (--n >= 0) { - const struct nfs4_string *component = &pathname->components[n]; - buflen -= component->len + 1; - if (buflen < 0) - goto Elong; - end -= component->len; - memcpy(end, component->data, component->len); - *--end = '/'; + *p++ = '/'; + memcpy(p, component->data, component->len); + p += component->len; } - return end; -Elong: - return ERR_PTR(-ENAMETOOLONG); + + *p = 0; + return buf; } /* @@ -100,21 +128,36 @@ static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) */ static int nfs4_validate_fspath(struct dentry *dentry, const struct nfs4_fs_locations *locations, - char *page, char *page2) + struct nfs_fs_context *ctx) { - const char *path, *fs_path; + const char *path; + char *fs_path; + unsigned short len; + char *buf; + int n; - path = nfs4_path(dentry, page, PAGE_SIZE); - if (IS_ERR(path)) + buf = kmalloc(4096, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + path = nfs4_path(dentry, buf, 4096); + if (IS_ERR(path)) { + kfree(buf); return PTR_ERR(path); + } - fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE); - if (IS_ERR(fs_path)) + fs_path = nfs4_pathname_string(&locations->fs_path, &len); + if (IS_ERR(fs_path)) { + kfree(buf); return PTR_ERR(fs_path); + } - if (strncmp(path, fs_path, strlen(fs_path)) != 0) { + n = strncmp(path, fs_path, len); + kfree(buf); + kfree(fs_path); + if (n != 0) { dprintk("%s: path %s does not begin with fsroot %s\n", - __func__, path, fs_path); + __func__, path, ctx->nfs_server.export_path); return -ENOENT; } @@ -236,55 +279,77 @@ out: return new; } -static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, - char *page, char *page2, - const struct nfs4_fs_location *location) +static int try_location(struct fs_context *fc, + const struct nfs4_fs_location *location) { - const size_t addr_bufsize = sizeof(struct sockaddr_storage); - struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client); - struct vfsmount *mnt = ERR_PTR(-ENOENT); - char *mnt_path; - unsigned int maxbuflen; - unsigned int s; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + unsigned int len, s; + char *export_path, *source, *p; + int ret = -ENOENT; + + /* Allocate a buffer big enough to hold any of the hostnames plus a + * terminating char and also a buffer big enough to hold the hostname + * plus a colon plus the path. + */ + len = 0; + for (s = 0; s < location->nservers; s++) { + const struct nfs4_string *buf = &location->servers[s]; + if (buf->len > len) + len = buf->len; + } - mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE); - if (IS_ERR(mnt_path)) - return ERR_CAST(mnt_path); - mountdata->mnt_path = mnt_path; - maxbuflen = mnt_path - 1 - page2; + kfree(ctx->nfs_server.hostname); + ctx->nfs_server.hostname = kmalloc(len + 1, GFP_KERNEL); + if (!ctx->nfs_server.hostname) + return -ENOMEM; - mountdata->addr = kmalloc(addr_bufsize, GFP_KERNEL); - if (mountdata->addr == NULL) - return ERR_PTR(-ENOMEM); + export_path = nfs4_pathname_string(&location->rootpath, + &ctx->nfs_server.export_path_len); + if (IS_ERR(export_path)) + return PTR_ERR(export_path); + + ctx->nfs_server.export_path = export_path; + + source = kmalloc(len + 1 + ctx->nfs_server.export_path_len + 1, + GFP_KERNEL); + if (!source) + return -ENOMEM; + kfree(fc->source); + fc->source = source; for (s = 0; s < location->nservers; s++) { const struct nfs4_string *buf = &location->servers[s]; - if (buf->len <= 0 || buf->len >= maxbuflen) - continue; - if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len)) continue; - mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len, - mountdata->addr, addr_bufsize, net); - if (mountdata->addrlen == 0) + ctx->nfs_server.addrlen = + nfs_parse_server_name(buf->data, buf->len, + &ctx->nfs_server.address, + sizeof(ctx->nfs_server._address), + fc->net_ns); + if (ctx->nfs_server.addrlen == 0) continue; - memcpy(page2, buf->data, buf->len); - page2[buf->len] = '\0'; - mountdata->hostname = page2; + rpc_set_port(&ctx->nfs_server.address, NFS_PORT); - snprintf(page, PAGE_SIZE, "%s:%s", - mountdata->hostname, - mountdata->mnt_path); + memcpy(ctx->nfs_server.hostname, buf->data, buf->len); + ctx->nfs_server.hostname[buf->len] = '\0'; - mnt = vfs_submount(mountdata->dentry, &nfs4_referral_fs_type, page, mountdata); - if (!IS_ERR(mnt)) - break; + p = source; + memcpy(p, buf->data, buf->len); + p += buf->len; + *p++ = ':'; + memcpy(p, ctx->nfs_server.export_path, ctx->nfs_server.export_path_len); + p += ctx->nfs_server.export_path_len; + *p = 0; + + ret = nfs4_get_referral_tree(fc); + if (ret == 0) + return 0; } - kfree(mountdata->addr); - return mnt; + + return ret; } /** @@ -293,38 +358,23 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, * @locations: array of NFSv4 server location information * */ -static struct vfsmount *nfs_follow_referral(struct dentry *dentry, - const struct nfs4_fs_locations *locations) +static int nfs_follow_referral(struct fs_context *fc, + const struct nfs4_fs_locations *locations) { - struct vfsmount *mnt = ERR_PTR(-ENOENT); - struct nfs_clone_mount mountdata = { - .sb = dentry->d_sb, - .dentry = dentry, - .authflavor = NFS_SB(dentry->d_sb)->client->cl_auth->au_flavor, - }; - char *page = NULL, *page2 = NULL; + struct nfs_fs_context *ctx = nfs_fc2context(fc); int loc, error; if (locations == NULL || locations->nlocations <= 0) - goto out; - - dprintk("%s: referral at %pd2\n", __func__, dentry); - - page = (char *) __get_free_page(GFP_USER); - if (!page) - goto out; + return -ENOENT; - page2 = (char *) __get_free_page(GFP_USER); - if (!page2) - goto out; + dprintk("%s: referral at %pd2\n", __func__, ctx->clone_data.dentry); /* Ensure fs path is a prefix of current dentry path */ - error = nfs4_validate_fspath(dentry, locations, page, page2); - if (error < 0) { - mnt = ERR_PTR(error); - goto out; - } + error = nfs4_validate_fspath(ctx->clone_data.dentry, locations, ctx); + if (error < 0) + return error; + error = -ENOENT; for (loc = 0; loc < locations->nlocations; loc++) { const struct nfs4_fs_location *location = &locations->locations[loc]; @@ -332,15 +382,12 @@ static struct vfsmount *nfs_follow_referral(struct dentry *dentry, location->rootpath.ncomponents == 0) continue; - mnt = try_location(&mountdata, page, page2, location); - if (!IS_ERR(mnt)) - break; + error = try_location(fc, location); + if (error == 0) + return 0; } -out: - free_page((unsigned long) page); - free_page((unsigned long) page2); - return mnt; + return error; } /* @@ -348,71 +395,72 @@ out: * @dentry - dentry of referral * */ -static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) +static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client) { - struct vfsmount *mnt = ERR_PTR(-ENOMEM); - struct dentry *parent; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct dentry *dentry, *parent; struct nfs4_fs_locations *fs_locations = NULL; struct page *page; - int err; + int err = -ENOMEM; /* BUG_ON(IS_ROOT(dentry)); */ page = alloc_page(GFP_KERNEL); - if (page == NULL) - return mnt; + if (!page) + return -ENOMEM; fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); - if (fs_locations == NULL) + if (!fs_locations) goto out_free; /* Get locations */ - mnt = ERR_PTR(-ENOENT); - + dentry = ctx->clone_data.dentry; parent = dget_parent(dentry); dprintk("%s: getting locations for %pd2\n", __func__, dentry); err = nfs4_proc_fs_locations(client, d_inode(parent), &dentry->d_name, fs_locations, page); dput(parent); - if (err != 0 || - fs_locations->nlocations <= 0 || + if (err != 0) + goto out_free_2; + + err = -ENOENT; + if (fs_locations->nlocations <= 0 || fs_locations->fs_path.ncomponents <= 0) - goto out_free; + goto out_free_2; - mnt = nfs_follow_referral(dentry, fs_locations); + err = nfs_follow_referral(fc, fs_locations); +out_free_2: + kfree(fs_locations); out_free: __free_page(page); - kfree(fs_locations); - return mnt; + return err; } -struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, - struct nfs_fh *fh, struct nfs_fattr *fattr) +int nfs4_submount(struct fs_context *fc, struct nfs_server *server) { - rpc_authflavor_t flavor = server->client->cl_auth->au_flavor; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct dentry *dentry = ctx->clone_data.dentry; struct dentry *parent = dget_parent(dentry); struct inode *dir = d_inode(parent); - const struct qstr *name = &dentry->d_name; struct rpc_clnt *client; - struct vfsmount *mnt; + int ret; /* Look it up again to get its attributes and sec flavor */ - client = nfs4_proc_lookup_mountpoint(dir, name, fh, fattr); + client = nfs4_proc_lookup_mountpoint(dir, dentry, ctx->mntfh, + ctx->clone_data.fattr); dput(parent); if (IS_ERR(client)) - return ERR_CAST(client); + return PTR_ERR(client); - if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { - mnt = nfs_do_refmount(client, dentry); - goto out; + ctx->selected_flavor = client->cl_auth->au_flavor; + if (ctx->clone_data.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { + ret = nfs_do_refmount(fc, client); + } else { + ret = nfs_do_submount(fc); } - if (client->cl_auth->au_flavor != flavor) - flavor = client->cl_auth->au_flavor; - mnt = nfs_do_submount(dentry, fh, fattr, flavor); -out: rpc_shutdown_client(client); - return mnt; + return ret; } /* @@ -453,7 +501,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, rpc_set_port(sap, NFS_PORT); error = -ENOMEM; - hostname = kstrndup(buf->data, buf->len, GFP_KERNEL); + hostname = kmemdup_nul(buf->data, buf->len, GFP_KERNEL); if (hostname == NULL) break; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 76d37161409a..95d07a3dc5d1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1097,11 +1097,12 @@ static int nfs4_call_sync_custom(struct rpc_task_setup *task_setup) return ret; } -static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, - struct nfs_server *server, - struct rpc_message *msg, - struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res) +static int nfs4_do_call_sync(struct rpc_clnt *clnt, + struct nfs_server *server, + struct rpc_message *msg, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + unsigned short task_flags) { struct nfs_client *clp = server->nfs_client; struct nfs4_call_sync_data data = { @@ -1113,12 +1114,23 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, .rpc_client = clnt, .rpc_message = msg, .callback_ops = clp->cl_mvops->call_sync_ops, - .callback_data = &data + .callback_data = &data, + .flags = task_flags, }; return nfs4_call_sync_custom(&task_setup); } +static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, + struct nfs_server *server, + struct rpc_message *msg, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res) +{ + return nfs4_do_call_sync(clnt, server, msg, args, res, 0); +} + + int nfs4_call_sync(struct rpc_clnt *clnt, struct nfs_server *server, struct rpc_message *msg, @@ -3187,6 +3199,11 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, exception.retry = 1; continue; } + if (status == -NFS4ERR_EXPIRED) { + nfs4_schedule_lease_recovery(server->nfs_client); + exception.retry = 1; + continue; + } if (status == -EAGAIN) { /* We must have found a delegation */ exception.retry = 1; @@ -3239,6 +3256,8 @@ static int _nfs4_do_setattr(struct inode *inode, nfs_put_lock_context(l_ctx); if (status == -EIO) return -EBADF; + else if (status == -EAGAIN) + goto zero_stateid; } else { zero_stateid: nfs4_stateid_copy(&arg->stateid, &zero_stateid); @@ -4064,11 +4083,18 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_argp = &args, .rpc_resp = &res, }; + unsigned short task_flags = 0; + + /* Is this is an attribute revalidation, subject to softreval? */ + if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) + task_flags |= RPC_TASK_TIMEOUT; nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode); nfs_fattr_init(fattr); - return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); + return nfs4_do_call_sync(server->client, server, &msg, + &args.seq_args, &res.seq_res, task_flags); } int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, @@ -4156,7 +4182,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, - const struct qstr *name, struct nfs_fh *fhandle, + struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { struct nfs_server *server = NFS_SERVER(dir); @@ -4164,7 +4190,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct nfs4_lookup_arg args = { .bitmask = server->attr_bitmask, .dir_fh = NFS_FH(dir), - .name = name, + .name = &dentry->d_name, }; struct nfs4_lookup_res res = { .server = server, @@ -4177,13 +4203,20 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, .rpc_argp = &args, .rpc_resp = &res, }; + unsigned short task_flags = 0; + + /* Is this is an attribute revalidation, subject to softreval? */ + if (nfs_lookup_is_soft_revalidate(dentry)) + task_flags |= RPC_TASK_TIMEOUT; args.bitmask = nfs4_bitmask(server, label); nfs_fattr_init(fattr); - dprintk("NFS call lookup %s\n", name->name); - status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, &res.seq_res, 0); + dprintk("NFS call lookup %pd2\n", dentry); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); + status = nfs4_do_call_sync(clnt, server, &msg, + &args.seq_args, &res.seq_res, task_flags); dprintk("NFS reply lookup: %d\n", status); return status; } @@ -4197,16 +4230,17 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) } static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, - const struct qstr *name, struct nfs_fh *fhandle, + struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { struct nfs4_exception exception = { .interruptible = true, }; struct rpc_clnt *client = *clnt; + const struct qstr *name = &dentry->d_name; int err; do { - err = _nfs4_proc_lookup(client, dir, name, fhandle, fattr, label); + err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr, label); trace_nfs4_lookup(dir, name, err); switch (err) { case -NFS4ERR_BADNAME: @@ -4241,14 +4275,14 @@ out: return err; } -static int nfs4_proc_lookup(struct inode *dir, const struct qstr *name, +static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { int status; struct rpc_clnt *client = NFS_CLIENT(dir); - status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, label); + status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, label); if (client != NFS_CLIENT(dir)) { rpc_shutdown_client(client); nfs_fixup_secinfo_attributes(fattr); @@ -4257,13 +4291,13 @@ static int nfs4_proc_lookup(struct inode *dir, const struct qstr *name, } struct rpc_clnt * -nfs4_proc_lookup_mountpoint(struct inode *dir, const struct qstr *name, +nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct rpc_clnt *client = NFS_CLIENT(dir); int status; - status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, NULL); + status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, NULL); if (status < 0) return ERR_PTR(status); return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; @@ -5019,16 +5053,13 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str struct nfs4_exception exception = { .interruptible = true, }; - unsigned long now = jiffies; int err; do { err = _nfs4_do_fsinfo(server, fhandle, fsinfo); trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err); if (err == 0) { - nfs4_set_lease_period(server->nfs_client, - fsinfo->lease_time * HZ, - now); + nfs4_set_lease_period(server->nfs_client, fsinfo->lease_time * HZ); break; } err = nfs4_handle_exception(server, err, &exception); @@ -5582,10 +5613,9 @@ out: */ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen) { - struct page *pages[NFS4ACL_MAXPAGES + 1] = {NULL, }; + struct page **pages; struct nfs_getaclargs args = { .fh = NFS_FH(inode), - .acl_pages = pages, .acl_len = buflen, }; struct nfs_getaclres res = { @@ -5596,11 +5626,19 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu .rpc_argp = &args, .rpc_resp = &res, }; - unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1; + unsigned int npages; int ret = -ENOMEM, i; + struct nfs_server *server = NFS_SERVER(inode); - if (npages > ARRAY_SIZE(pages)) - return -ERANGE; + if (buflen == 0) + buflen = server->rsize; + + npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1; + pages = kmalloc_array(npages, sizeof(struct page *), GFP_NOFS); + if (!pages) + return -ENOMEM; + + args.acl_pages = pages; for (i = 0; i < npages; i++) { pages[i] = alloc_page(GFP_KERNEL); @@ -5646,6 +5684,7 @@ out_free: __free_page(pages[i]); if (res.acl_scratch) __free_page(res.acl_scratch); + kfree(pages); return ret; } @@ -6084,6 +6123,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, .callback_data = &setclientid, .flags = RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN, }; + unsigned long now = jiffies; int status; /* nfs_client_id4 */ @@ -6116,6 +6156,9 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred); put_rpccred(setclientid.sc_cred); } + + if (status == 0) + do_renew_lease(clp, now); out: trace_nfs4_setclientid(clp, status); dprintk("NFS reply setclientid: %d\n", status); @@ -6859,7 +6902,7 @@ static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_ case -NFS4ERR_STALE_STATEID: lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED; nfs4_schedule_lease_recovery(server->nfs_client); - }; + } } static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int recovery_type) @@ -8203,6 +8246,7 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre struct rpc_task *task; struct nfs41_exchange_id_args *argp; struct nfs41_exchange_id_res *resp; + unsigned long now = jiffies; int status; task = nfs4_run_exchange_id(clp, cred, sp4_how, NULL); @@ -8223,6 +8267,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre if (status != 0) goto out; + do_renew_lease(clp, now); + clp->cl_clientid = resp->clientid; clp->cl_exchange_flags = resp->flags; clp->cl_seqid = resp->seqid; @@ -8626,7 +8672,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp, case -EACCES: case -EAGAIN: goto out; - }; + } clp->cl_seqid++; if (!status) { @@ -10001,7 +10047,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .file_ops = &nfs4_file_operations, .getroot = nfs4_proc_get_root, .submount = nfs4_submount, - .try_mount = nfs4_try_mount, + .try_get_tree = nfs4_try_get_tree, .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 6ea431b067dd..ff876dda7f06 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -138,15 +138,12 @@ nfs4_kill_renewd(struct nfs_client *clp) * * @clp: pointer to nfs_client * @lease: new value for lease period - * @lastrenewed: time at which lease was last renewed */ void nfs4_set_lease_period(struct nfs_client *clp, - unsigned long lease, - unsigned long lastrenewed) + unsigned long lease) { spin_lock(&clp->cl_lock); clp->cl_lease_time = lease; - clp->cl_last_renewal = lastrenewed; spin_unlock(&clp->cl_lock); /* Cap maximum reconnect timeout at 1/2 lease period */ diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 34552329233d..f7723d221945 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -92,17 +92,15 @@ static int nfs4_setup_state_renewal(struct nfs_client *clp) { int status; struct nfs_fsinfo fsinfo; - unsigned long now; if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { nfs4_schedule_state_renewal(clp); return 0; } - now = jiffies; status = nfs4_proc_get_lease_time(clp, &fsinfo); if (status == 0) { - nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now); + nfs4_set_lease_period(clp, fsinfo.lease_time * HZ); nfs4_schedule_state_renewal(clp); } @@ -766,6 +764,7 @@ void nfs4_put_open_state(struct nfs4_state *state) list_del(&state->open_states); spin_unlock(&inode->i_lock); spin_unlock(&owner->so_lock); + nfs4_inode_return_delegation_on_close(inode); iput(inode); nfs4_free_open_state(state); nfs4_put_state_owner(owner); @@ -1135,7 +1134,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) case -NFS4ERR_MOVED: /* Non-seqid mutating errors */ return; - }; + } /* * Note: no locking needed as we are guaranteed to be first * on the sequence list diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 2c9cbade561a..1475f932d7da 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -4,6 +4,7 @@ */ #include <linux/init.h> #include <linux/module.h> +#include <linux/mount.h> #include <linux/nfs4_mount.h> #include <linux/nfs_fs.h> #include "delegation.h" @@ -18,36 +19,6 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc); static void nfs4_evict_inode(struct inode *inode); -static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data); -static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data); -static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data); - -static struct file_system_type nfs4_remote_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs4_remote_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, -}; - -static struct file_system_type nfs4_remote_referral_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs4_remote_referral_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, -}; - -struct file_system_type nfs4_referral_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs4_referral_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, -}; static const struct super_operations nfs4_sops = { .alloc_inode = nfs_alloc_inode, @@ -61,16 +32,15 @@ static const struct super_operations nfs4_sops = { .show_devname = nfs_show_devname, .show_path = nfs_show_path, .show_stats = nfs_show_stats, - .remount_fs = nfs_remount, }; struct nfs_subversion nfs_v4 = { - .owner = THIS_MODULE, - .nfs_fs = &nfs4_fs_type, - .rpc_vers = &nfs_version4, - .rpc_ops = &nfs_v4_clientops, - .sops = &nfs4_sops, - .xattr = nfs4_xattr_handlers, + .owner = THIS_MODULE, + .nfs_fs = &nfs4_fs_type, + .rpc_vers = &nfs_version4, + .rpc_ops = &nfs_v4_clientops, + .sops = &nfs4_sops, + .xattr = nfs4_xattr_handlers, }; static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc) @@ -101,53 +71,6 @@ static void nfs4_evict_inode(struct inode *inode) nfs_clear_inode(inode); } -/* - * Get the superblock for the NFS4 root partition - */ -static struct dentry * -nfs4_remote_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *info) -{ - struct nfs_mount_info *mount_info = info; - struct nfs_server *server; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - - mount_info->set_security = nfs_set_sb_security; - - /* Get a volume representation */ - server = nfs4_create_server(mount_info, &nfs_v4); - if (IS_ERR(server)) { - mntroot = ERR_CAST(server); - goto out; - } - - mntroot = nfs_fs_mount_common(server, flags, dev_name, mount_info, &nfs_v4); - -out: - return mntroot; -} - -static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, - int flags, void *data, const char *hostname) -{ - struct vfsmount *root_mnt; - char *root_devname; - size_t len; - - len = strlen(hostname) + 5; - root_devname = kmalloc(len, GFP_KERNEL); - if (root_devname == NULL) - return ERR_PTR(-ENOMEM); - /* Does hostname needs to be enclosed in brackets? */ - if (strchr(hostname, ':')) - snprintf(root_devname, len, "[%s]:/", hostname); - else - snprintf(root_devname, len, "%s:/", hostname); - root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data); - kfree(root_devname); - return root_mnt; -} - struct nfs_referral_count { struct list_head list; const struct task_struct *task; @@ -214,111 +137,125 @@ static void nfs_referral_loop_unprotect(void) kfree(p); } -static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, - const char *export_path) +static int do_nfs4_mount(struct nfs_server *server, + struct fs_context *fc, + const char *hostname, + const char *export_path) { + struct nfs_fs_context *root_ctx; + struct fs_context *root_fc; + struct vfsmount *root_mnt; struct dentry *dentry; - int err; + size_t len; + int ret; - if (IS_ERR(root_mnt)) - return ERR_CAST(root_mnt); + struct fs_parameter param = { + .key = "source", + .type = fs_value_is_string, + .dirfd = -1, + }; - err = nfs_referral_loop_protect(); - if (err) { - mntput(root_mnt); - return ERR_PTR(err); + if (IS_ERR(server)) + return PTR_ERR(server); + + root_fc = vfs_dup_fs_context(fc); + if (IS_ERR(root_fc)) { + nfs_free_server(server); + return PTR_ERR(root_fc); } + kfree(root_fc->source); + root_fc->source = NULL; - dentry = mount_subtree(root_mnt, export_path); - nfs_referral_loop_unprotect(); + root_ctx = nfs_fc2context(root_fc); + root_ctx->internal = true; + root_ctx->server = server; + /* We leave export_path unset as it's not used to find the root. */ - return dentry; -} + len = strlen(hostname) + 5; + param.string = kmalloc(len, GFP_KERNEL); + if (param.string == NULL) { + put_fs_context(root_fc); + return -ENOMEM; + } -struct dentry *nfs4_try_mount(int flags, const char *dev_name, - struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) -{ - char *export_path; - struct vfsmount *root_mnt; - struct dentry *res; - struct nfs_parsed_mount_data *data = mount_info->parsed; + /* Does hostname needs to be enclosed in brackets? */ + if (strchr(hostname, ':')) + param.size = snprintf(param.string, len, "[%s]:/", hostname); + else + param.size = snprintf(param.string, len, "%s:/", hostname); + ret = vfs_parse_fs_param(root_fc, ¶m); + kfree(param.string); + if (ret < 0) { + put_fs_context(root_fc); + return ret; + } + root_mnt = fc_mount(root_fc); + put_fs_context(root_fc); + + if (IS_ERR(root_mnt)) + return PTR_ERR(root_mnt); - dfprintk(MOUNT, "--> nfs4_try_mount()\n"); + ret = nfs_referral_loop_protect(); + if (ret) { + mntput(root_mnt); + return ret; + } - export_path = data->nfs_server.export_path; - data->nfs_server.export_path = "/"; - root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, - data->nfs_server.hostname); - data->nfs_server.export_path = export_path; + dentry = mount_subtree(root_mnt, export_path); + nfs_referral_loop_unprotect(); - res = nfs_follow_remote_path(root_mnt, export_path); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); - dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", - PTR_ERR_OR_ZERO(res), - IS_ERR(res) ? " [error]" : ""); - return res; + fc->root = dentry; + return 0; } -static struct dentry * -nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) +int nfs4_try_get_tree(struct fs_context *fc) { - struct nfs_mount_info mount_info = { - .fill_super = nfs_fill_super, - .set_security = nfs_clone_sb_security, - .cloned = raw_data, - }; - struct nfs_server *server; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - - dprintk("--> nfs4_referral_get_sb()\n"); + struct nfs_fs_context *ctx = nfs_fc2context(fc); + int err; - mount_info.mntfh = nfs_alloc_fhandle(); - if (mount_info.cloned == NULL || mount_info.mntfh == NULL) - goto out; + dfprintk(MOUNT, "--> nfs4_try_get_tree()\n"); - /* create a new volume representation */ - server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh); - if (IS_ERR(server)) { - mntroot = ERR_CAST(server); - goto out; + /* We create a mount for the server's root, walk to the requested + * location and then create another mount for that. + */ + err= do_nfs4_mount(nfs4_create_server(fc), + fc, ctx->nfs_server.hostname, + ctx->nfs_server.export_path); + if (err) { + nfs_errorf(fc, "NFS4: Couldn't follow remote path"); + dfprintk(MOUNT, "<-- nfs4_try_get_tree() = %d [error]\n", err); + } else { + dfprintk(MOUNT, "<-- nfs4_try_get_tree() = 0\n"); } - - mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, &nfs_v4); -out: - nfs_free_fhandle(mount_info.mntfh); - return mntroot; + return err; } /* * Create an NFS4 server record on referral traversal */ -static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) +int nfs4_get_referral_tree(struct fs_context *fc) { - struct nfs_clone_mount *data = raw_data; - char *export_path; - struct vfsmount *root_mnt; - struct dentry *res; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + int err; dprintk("--> nfs4_referral_mount()\n"); - export_path = data->mnt_path; - data->mnt_path = "/"; - - root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type, - flags, data, data->hostname); - data->mnt_path = export_path; - - res = nfs_follow_remote_path(root_mnt, export_path); - dprintk("<-- nfs4_referral_mount() = %d%s\n", - PTR_ERR_OR_ZERO(res), - IS_ERR(res) ? " [error]" : ""); - return res; + /* create a new volume representation */ + err = do_nfs4_mount(nfs4_create_referral_server(fc), + fc, ctx->nfs_server.hostname, + ctx->nfs_server.export_path); + if (err) { + nfs_errorf(fc, "NFS4: Couldn't follow remote path"); + dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = %d [error]\n", err); + } else { + dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = 0\n"); + } + return err; } - static int __init init_nfs_v4(void) { int err; diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c index 1a8f376b3f73..d9ac556bebcf 100644 --- a/fs/nfs/nfs4trace.c +++ b/fs/nfs/nfs4trace.c @@ -24,4 +24,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_read_done); EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_done); EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_read_pagelist); EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_pagelist); + +EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_read_error); +EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_write_error); +EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_commit_error); #endif diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index e60b6fbd5ada..1e97e5e04cb4 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -155,6 +155,9 @@ TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); TRACE_DEFINE_ENUM(NFS4ERR_XDEV); +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); + #define show_nfsv4_errors(error) \ __print_symbolic(error, \ { NFS4_OK, "OK" }, \ @@ -305,7 +308,10 @@ TRACE_DEFINE_ENUM(NFS4ERR_XDEV); { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ - { NFS4ERR_XDEV, "XDEV" }) + { NFS4ERR_XDEV, "XDEV" }, \ + /* ***** Internal to Linux NFS client ***** */ \ + { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ + { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) #define show_open_flags(flags) \ __print_flags(flags, "|", \ @@ -352,7 +358,7 @@ DECLARE_EVENT_CLASS(nfs4_clientid_event, ), TP_fast_assign( - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __assign_str(dstaddr, clp->cl_hostname); ), @@ -432,7 +438,8 @@ TRACE_EVENT(nfs4_sequence_done, __entry->target_highest_slotid = res->sr_target_highest_slotid; __entry->status_flags = res->sr_status_flags; - __entry->error = res->sr_status; + __entry->error = res->sr_status < 0 ? + -res->sr_status : 0; ), TP_printk( "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " @@ -640,7 +647,7 @@ TRACE_EVENT(nfs4_state_mgr_failed, ), TP_fast_assign( - __entry->error = status; + __entry->error = status < 0 ? -status : 0; __entry->state = clp->cl_state; __assign_str(hostname, clp->cl_hostname); __assign_str(section, section); @@ -659,7 +666,7 @@ TRACE_EVENT(nfs4_xdr_status, TP_PROTO( const struct xdr_stream *xdr, u32 op, - int error + u32 error ), TP_ARGS(xdr, op, error), @@ -691,6 +698,41 @@ TRACE_EVENT(nfs4_xdr_status, ) ); +DECLARE_EVENT_CLASS(nfs4_cb_error_class, + TP_PROTO( + __be32 xid, + u32 cb_ident + ), + + TP_ARGS(xid, cb_ident), + + TP_STRUCT__entry( + __field(u32, xid) + __field(u32, cbident) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpu(xid); + __entry->cbident = cb_ident; + ), + + TP_printk( + "xid=0x%08x cb_ident=0x%08x", + __entry->xid, __entry->cbident + ) +); + +#define DEFINE_CB_ERROR_EVENT(name) \ + DEFINE_EVENT(nfs4_cb_error_class, nfs_cb_##name, \ + TP_PROTO( \ + __be32 xid, \ + u32 cb_ident \ + ), \ + TP_ARGS(xid, cb_ident)) + +DEFINE_CB_ERROR_EVENT(no_clp); +DEFINE_CB_ERROR_EVENT(badprinc); + DECLARE_EVENT_CLASS(nfs4_open_event, TP_PROTO( const struct nfs_open_context *ctx, @@ -849,7 +891,7 @@ TRACE_EVENT(nfs4_close, __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->fmode = (__force unsigned int)state->state; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->stateid_seq = be32_to_cpu(args->stateid.seqid); __entry->stateid_hash = @@ -914,7 +956,7 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, TP_fast_assign( const struct inode *inode = state->inode; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->cmd = cmd; __entry->type = request->fl_type; __entry->start = request->fl_start; @@ -986,7 +1028,7 @@ TRACE_EVENT(nfs4_set_lock, TP_fast_assign( const struct inode *inode = state->inode; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->cmd = cmd; __entry->type = request->fl_type; __entry->start = request->fl_start; @@ -1164,7 +1206,7 @@ TRACE_EVENT(nfs4_delegreturn_exit, TP_fast_assign( __entry->dev = res->server->s_dev; __entry->fhandle = nfs_fhandle_hash(args->fhandle); - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->stateid_seq = be32_to_cpu(args->stateid->seqid); __entry->stateid_hash = @@ -1204,7 +1246,7 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, TP_fast_assign( const struct inode *inode = state->inode; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); @@ -1306,7 +1348,7 @@ TRACE_EVENT(nfs4_lookupp, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = NFS_FILEID(inode); - __entry->error = error; + __entry->error = error < 0 ? -error : 0; ), TP_printk( @@ -1342,7 +1384,7 @@ TRACE_EVENT(nfs4_rename, __entry->dev = olddir->i_sb->s_dev; __entry->olddir = NFS_FILEID(olddir); __entry->newdir = NFS_FILEID(newdir); - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __assign_str(oldname, oldname->name); __assign_str(newname, newname->name); ), @@ -1433,7 +1475,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_event, __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->stateid_seq = be32_to_cpu(stateid->seqid); __entry->stateid_hash = @@ -1489,7 +1531,7 @@ DECLARE_EVENT_CLASS(nfs4_getattr_event, __entry->valid = fattr->valid; __entry->fhandle = nfs_fhandle_hash(fhandle); __entry->fileid = (fattr->valid & NFS_ATTR_FATTR_FILEID) ? fattr->fileid : 0; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; ), TP_printk( @@ -1536,7 +1578,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, ), TP_fast_assign( - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->fhandle = nfs_fhandle_hash(fhandle); if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); @@ -1593,7 +1635,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, ), TP_fast_assign( - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->fhandle = nfs_fhandle_hash(fhandle); if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); @@ -1694,7 +1736,8 @@ DECLARE_EVENT_CLASS(nfs4_read_event, __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) - __field(size_t, count) + __field(u32, arg_count) + __field(u32, res_count) __field(unsigned long, error) __field(int, stateid_seq) __field(u32, stateid_hash) @@ -1702,13 +1745,18 @@ DECLARE_EVENT_CLASS(nfs4_read_event, TP_fast_assign( const struct inode *inode = hdr->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; const struct nfs4_state *state = hdr->args.context->state; + __entry->dev = inode->i_sb->s_dev; - __entry->fileid = NFS_FILEID(inode); - __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); __entry->offset = hdr->args.offset; - __entry->count = hdr->args.count; + __entry->arg_count = hdr->args.count; + __entry->res_count = hdr->res.count; __entry->error = error < 0 ? -error : 0; __entry->stateid_seq = be32_to_cpu(state->stateid.seqid); @@ -1718,14 +1766,14 @@ DECLARE_EVENT_CLASS(nfs4_read_event, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu stateid=%d:0x%08x", + "offset=%lld count=%u res=%u stateid=%d:0x%08x", -__entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count, + __entry->arg_count, __entry->res_count, __entry->stateid_seq, __entry->stateid_hash ) ); @@ -1754,7 +1802,8 @@ DECLARE_EVENT_CLASS(nfs4_write_event, __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) - __field(size_t, count) + __field(u32, arg_count) + __field(u32, res_count) __field(unsigned long, error) __field(int, stateid_seq) __field(u32, stateid_hash) @@ -1762,13 +1811,18 @@ DECLARE_EVENT_CLASS(nfs4_write_event, TP_fast_assign( const struct inode *inode = hdr->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; const struct nfs4_state *state = hdr->args.context->state; + __entry->dev = inode->i_sb->s_dev; - __entry->fileid = NFS_FILEID(inode); - __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); __entry->offset = hdr->args.offset; - __entry->count = hdr->args.count; + __entry->arg_count = hdr->args.count; + __entry->res_count = hdr->res.count; __entry->error = error < 0 ? -error : 0; __entry->stateid_seq = be32_to_cpu(state->stateid.seqid); @@ -1778,14 +1832,14 @@ DECLARE_EVENT_CLASS(nfs4_write_event, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu stateid=%d:0x%08x", + "offset=%lld count=%u res=%u stateid=%d:0x%08x", -__entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count, + __entry->arg_count, __entry->res_count, __entry->stateid_seq, __entry->stateid_hash ) ); @@ -1814,24 +1868,28 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) - __field(loff_t, offset) - __field(size_t, count) __field(unsigned long, error) + __field(loff_t, offset) + __field(u32, count) ), TP_fast_assign( const struct inode *inode = data->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = data->args.fh ? + data->args.fh : &nfsi->fh; + __entry->dev = inode->i_sb->s_dev; - __entry->fileid = NFS_FILEID(inode); - __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); __entry->offset = data->args.offset; __entry->count = data->args.count; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu", + "offset=%lld count=%u", -__entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1896,7 +1954,7 @@ TRACE_EVENT(nfs4_layoutget, __entry->iomode = args->iomode; __entry->offset = args->offset; __entry->count = args->length; - __entry->error = error; + __entry->error = error < 0 ? -error : 0; __entry->stateid_seq = be32_to_cpu(state->stateid.seqid); __entry->stateid_hash = @@ -2094,6 +2152,115 @@ DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_write_done); DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_read_pagelist); DEFINE_PNFS_LAYOUT_EVENT(pnfs_mds_fallback_write_pagelist); +DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, + TP_PROTO( + const struct nfs_pgio_header *hdr + ), + + TP_ARGS(hdr), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(u32, count) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __string(dstaddr, hdr->ds_clp ? + rpc_peeraddr2str(hdr->ds_clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown") + ), + + TP_fast_assign( + const struct inode *inode = hdr->inode; + + __entry->error = hdr->res.op_status; + __entry->fhandle = nfs_fhandle_hash(hdr->args.fh); + __entry->fileid = NFS_FILEID(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->offset = hdr->args.offset; + __entry->count = hdr->args.count; + __entry->stateid_seq = + be32_to_cpu(hdr->args.stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&hdr->args.stateid); + __assign_str(dstaddr, hdr->ds_clp ? + rpc_peeraddr2str(hdr->ds_clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown"); + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s", + -__entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->count, + __entry->stateid_seq, __entry->stateid_hash, + __get_str(dstaddr) + ) +); + +#define DEFINE_NFS4_FLEXFILES_IO_EVENT(name) \ + DEFINE_EVENT(nfs4_flexfiles_io_event, name, \ + TP_PROTO( \ + const struct nfs_pgio_header *hdr \ + ), \ + TP_ARGS(hdr)) +DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_read_error); +DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_write_error); + +TRACE_EVENT(ff_layout_commit_error, + TP_PROTO( + const struct nfs_commit_data *data + ), + + TP_ARGS(data), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(u32, count) + __string(dstaddr, data->ds_clp ? + rpc_peeraddr2str(data->ds_clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown") + ), + + TP_fast_assign( + const struct inode *inode = data->inode; + + __entry->error = data->res.op_status; + __entry->fhandle = nfs_fhandle_hash(data->args.fh); + __entry->fileid = NFS_FILEID(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->offset = data->args.offset; + __entry->count = data->args.count; + __assign_str(dstaddr, data->ds_clp ? + rpc_peeraddr2str(data->ds_clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown"); + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%llu count=%u dstaddr=%s", + -__entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->count, + __get_str(dstaddr) + ) +); + + #endif /* CONFIG_NFS_V4_1 */ #endif /* _TRACE_NFS4_H */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 728d88b6a698..47817ef0aadb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1061,7 +1061,7 @@ static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *ve static __be32 * xdr_encode_nfstime4(__be32 *p, const struct timespec64 *t) { - p = xdr_encode_hyper(p, (__s64)t->tv_sec); + p = xdr_encode_hyper(p, t->tv_sec); *p++ = cpu_to_be32(t->tv_nsec); return p; } @@ -4313,11 +4313,14 @@ static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifi static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res) { + struct nfs_writeverf *verf = res->verf; int status; status = decode_op_hdr(xdr, OP_COMMIT); if (!status) - status = decode_write_verifier(xdr, &res->verf->verifier); + status = decode_write_verifier(xdr, &verf->verifier); + if (!status) + verf->committed = NFS_FILE_SYNC; return status; } diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 2a82dcce5fc1..a9588d19a5ae 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -198,7 +198,66 @@ DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); -DEFINE_NFS_INODE_EVENT_DONE(nfs_access_exit); + +TRACE_EVENT(nfs_access_exit, + TP_PROTO( + const struct inode *inode, + unsigned int mask, + unsigned int permitted, + int error + ), + + TP_ARGS(inode, mask, permitted, error), + + TP_STRUCT__entry( + __field(unsigned long, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(unsigned char, type) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, size) + __field(unsigned long, nfsi_flags) + __field(unsigned long, cache_validity) + __field(unsigned int, mask) + __field(unsigned int, permitted) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->error = error < 0 ? -error : 0; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->type = nfs_umode_to_dtype(inode->i_mode); + __entry->version = inode_peek_iversion_raw(inode); + __entry->size = i_size_read(inode); + __entry->nfsi_flags = nfsi->flags; + __entry->cache_validity = nfsi->cache_validity; + __entry->mask = mask; + __entry->permitted = permitted; + ), + + TP_printk( + "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "type=%u (%s) version=%llu size=%lld " + "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) " + "mask=0x%x permitted=0x%x", + -__entry->error, nfs_show_status(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->type, + nfs_show_file_type(__entry->type), + (unsigned long long)__entry->version, + (long long)__entry->size, + __entry->cache_validity, + nfs_show_cache_validity(__entry->cache_validity), + __entry->nfsi_flags, + nfs_show_nfsi_flags(__entry->nfsi_flags), + __entry->mask, __entry->permitted + ) +); TRACE_DEFINE_ENUM(LOOKUP_FOLLOW); TRACE_DEFINE_ENUM(LOOKUP_DIRECTORY); @@ -818,75 +877,85 @@ TRACE_EVENT(nfs_sillyrename_unlink, TRACE_EVENT(nfs_initiate_read, TP_PROTO( - const struct inode *inode, - loff_t offset, unsigned long count + const struct nfs_pgio_header *hdr ), - TP_ARGS(inode, offset, count), + TP_ARGS(hdr), TP_STRUCT__entry( - __field(loff_t, offset) - __field(unsigned long, count) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(loff_t, offset) + __field(u32, count) ), TP_fast_assign( + const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; - __entry->offset = offset; - __entry->count = count; + __entry->offset = hdr->args.offset; + __entry->count = hdr->args.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%lu", + "offset=%lld count=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - __entry->offset, __entry->count + (long long)__entry->offset, __entry->count ) ); TRACE_EVENT(nfs_readpage_done, TP_PROTO( - const struct inode *inode, - int status, loff_t offset, bool eof + const struct rpc_task *task, + const struct nfs_pgio_header *hdr ), - TP_ARGS(inode, status, offset, eof), + TP_ARGS(task, hdr), TP_STRUCT__entry( - __field(int, status) - __field(loff_t, offset) - __field(bool, eof) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(loff_t, offset) + __field(u32, arg_count) + __field(u32, res_count) + __field(bool, eof) + __field(int, status) ), TP_fast_assign( + const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); - - __entry->status = status; - __entry->offset = offset; - __entry->eof = eof; + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; + + __entry->status = task->tk_status; + __entry->offset = hdr->args.offset; + __entry->arg_count = hdr->args.count; + __entry->res_count = hdr->res.count; + __entry->eof = hdr->res.eof; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld status=%d%s", + "offset=%lld count=%u res=%u status=%d%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - __entry->offset, __entry->status, + (long long)__entry->offset, __entry->arg_count, + __entry->res_count, __entry->status, __entry->eof ? " eof" : "" ) ); @@ -903,90 +972,144 @@ TRACE_DEFINE_ENUM(NFS_FILE_SYNC); TRACE_EVENT(nfs_initiate_write, TP_PROTO( - const struct inode *inode, - loff_t offset, unsigned long count, - enum nfs3_stable_how stable + const struct nfs_pgio_header *hdr ), - TP_ARGS(inode, offset, count, stable), + TP_ARGS(hdr), TP_STRUCT__entry( - __field(loff_t, offset) - __field(unsigned long, count) - __field(enum nfs3_stable_how, stable) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(loff_t, offset) + __field(u32, count) + __field(enum nfs3_stable_how, stable) ), TP_fast_assign( + const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; - __entry->offset = offset; - __entry->count = count; - __entry->stable = stable; + __entry->offset = hdr->args.offset; + __entry->count = hdr->args.count; + __entry->stable = hdr->args.stable; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%lu stable=%s", + "offset=%lld count=%u stable=%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - __entry->offset, __entry->count, + (long long)__entry->offset, __entry->count, nfs_show_stable(__entry->stable) ) ); TRACE_EVENT(nfs_writeback_done, TP_PROTO( - const struct inode *inode, - int status, - loff_t offset, - struct nfs_writeverf *writeverf + const struct rpc_task *task, + const struct nfs_pgio_header *hdr ), - TP_ARGS(inode, status, offset, writeverf), + TP_ARGS(task, hdr), TP_STRUCT__entry( - __field(int, status) - __field(loff_t, offset) - __field(enum nfs3_stable_how, stable) - __field(unsigned long long, verifier) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(loff_t, offset) + __field(u32, arg_count) + __field(u32, res_count) + __field(int, status) + __field(enum nfs3_stable_how, stable) + __array(char, verifier, NFS4_VERIFIER_SIZE) ), TP_fast_assign( + const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); - - __entry->status = status; - __entry->offset = offset; - __entry->stable = writeverf->committed; - memcpy(&__entry->verifier, &writeverf->verifier, - sizeof(__entry->verifier)); + const struct nfs_fh *fh = hdr->args.fh ? + hdr->args.fh : &nfsi->fh; + const struct nfs_writeverf *verf = hdr->res.verf; + + __entry->status = task->tk_status; + __entry->offset = hdr->args.offset; + __entry->arg_count = hdr->args.count; + __entry->res_count = hdr->res.count; + __entry->stable = verf->committed; + memcpy(__entry->verifier, + &verf->verifier, + NFS4_VERIFIER_SIZE); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld status=%d stable=%s " - "verifier 0x%016llx", + "offset=%lld count=%u res=%u status=%d stable=%s " + "verifier=%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - __entry->offset, __entry->status, + (long long)__entry->offset, __entry->arg_count, + __entry->res_count, __entry->status, nfs_show_stable(__entry->stable), - __entry->verifier + __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) ) ); +DECLARE_EVENT_CLASS(nfs_page_error_class, + TP_PROTO( + const struct nfs_page *req, + int error + ), + + TP_ARGS(req, error), + + TP_STRUCT__entry( + __field(const void *, req) + __field(pgoff_t, index) + __field(unsigned int, offset) + __field(unsigned int, pgbase) + __field(unsigned int, bytes) + __field(int, error) + ), + + TP_fast_assign( + __entry->req = req; + __entry->index = req->wb_index; + __entry->offset = req->wb_offset; + __entry->pgbase = req->wb_pgbase; + __entry->bytes = req->wb_bytes; + __entry->error = error; + ), + + TP_printk( + "req=%p index=%lu offset=%u pgbase=%u bytes=%u error=%d", + __entry->req, __entry->index, __entry->offset, + __entry->pgbase, __entry->bytes, __entry->error + ) +); + +#define DEFINE_NFS_PAGEERR_EVENT(name) \ + DEFINE_EVENT(nfs_page_error_class, name, \ + TP_PROTO( \ + const struct nfs_page *req, \ + int error \ + ), \ + TP_ARGS(req, error)) + +DEFINE_NFS_PAGEERR_EVENT(nfs_write_error); +DEFINE_NFS_PAGEERR_EVENT(nfs_comp_error); +DEFINE_NFS_PAGEERR_EVENT(nfs_commit_error); + TRACE_EVENT(nfs_initiate_commit, TP_PROTO( const struct nfs_commit_data *data @@ -995,71 +1118,81 @@ TRACE_EVENT(nfs_initiate_commit, TP_ARGS(data), TP_STRUCT__entry( - __field(loff_t, offset) - __field(unsigned long, count) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(loff_t, offset) + __field(u32, count) ), TP_fast_assign( const struct inode *inode = data->inode; const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = data->args.fh ? + data->args.fh : &nfsi->fh; __entry->offset = data->args.offset; __entry->count = data->args.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%lu", + "offset=%lld count=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - __entry->offset, __entry->count + (long long)__entry->offset, __entry->count ) ); TRACE_EVENT(nfs_commit_done, TP_PROTO( + const struct rpc_task *task, const struct nfs_commit_data *data ), - TP_ARGS(data), + TP_ARGS(task, data), TP_STRUCT__entry( - __field(int, status) - __field(loff_t, offset) - __field(unsigned long long, verifier) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(loff_t, offset) + __field(int, status) + __field(enum nfs3_stable_how, stable) + __array(char, verifier, NFS4_VERIFIER_SIZE) ), TP_fast_assign( const struct inode *inode = data->inode; const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = data->args.fh ? + data->args.fh : &nfsi->fh; + const struct nfs_writeverf *verf = data->res.verf; - __entry->status = data->res.op_status; + __entry->status = task->tk_status; __entry->offset = data->args.offset; - memcpy(&__entry->verifier, &data->verf.verifier, - sizeof(__entry->verifier)); + __entry->stable = verf->committed; + memcpy(__entry->verifier, + &verf->verifier, + NFS4_VERIFIER_SIZE); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld status=%d verifier 0x%016llx", + "offset=%lld status=%d stable=%s verifier=%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - __entry->offset, __entry->status, - __entry->verifier + (long long)__entry->offset, __entry->status, + nfs_show_stable(__entry->stable), + __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) ) ); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index cec3070ab577..542ea8dfd1bc 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1425,7 +1425,7 @@ retry: /* lo ref dropped in pnfs_roc_release() */ layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &iomode); /* If the creds don't match, we can't compound the layoutreturn */ - if (!layoutreturn || cred != lo->plh_lc_cred) + if (!layoutreturn || cred_fscmp(cred, lo->plh_lc_cred) != 0) goto out_noroc; roc = layoutreturn; @@ -1998,8 +1998,6 @@ lookup_again: trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_INVALID_OPEN); - if (status != -EAGAIN) - goto out_unlock; spin_unlock(&ino->i_lock); nfs4_schedule_stateid_recovery(server, ctx->state); pnfs_clear_first_layoutget(lo); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index f8a38065c7e4..0fafdadc9c8d 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -79,6 +79,10 @@ enum pnfs_try_status { PNFS_TRY_AGAIN = 2, }; +/* error codes for internal use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + #ifdef CONFIG_NFS_V4_1 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" @@ -91,10 +95,6 @@ enum pnfs_try_status { #define NFS4_DEF_DS_RETRANS 5 #define PNFS_DEVICE_RETRY_TIMEOUT (120*HZ) -/* error codes for internal use */ -#define NFS4ERR_RESET_TO_MDS 12001 -#define NFS4ERR_RESET_TO_PNFS 12002 - enum { NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 82af4809b869..8b37e7f8e789 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -31,12 +31,11 @@ EXPORT_SYMBOL_GPL(pnfs_generic_rw_release); /* Fake up some data that will cause nfs_commit_release to retry the writes. */ void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data) { - struct nfs_page *first = nfs_list_entry(data->pages.next); + struct nfs_writeverf *verf = data->res.verf; data->task.tk_status = 0; - memcpy(&data->verf.verifier, &first->wb_verf, - sizeof(data->verf.verifier)); - data->verf.verifier.data[0]++; /* ensure verifier mismatch */ + memset(&verf->verifier, 0, sizeof(verf->verifier)); + verf->committed = NFS_UNSTABLE; } EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 0f7288b94633..15c865cc837f 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -108,10 +108,15 @@ nfs_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_resp = fattr, }; int status; + unsigned short task_flags = 0; + + /* Is this is an attribute revalidation, subject to softreval? */ + if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) + task_flags |= RPC_TASK_TIMEOUT; dprintk("NFS call getattr\n"); nfs_fattr_init(fattr); - status = rpc_call_sync(server->client, &msg, 0); + status = rpc_call_sync(server->client, &msg, task_flags); dprintk("NFS reply getattr: %d\n", status); return status; } @@ -147,14 +152,14 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct inode *dir, const struct qstr *name, +nfs_proc_lookup(struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { struct nfs_diropargs arg = { .fh = NFS_FH(dir), - .name = name->name, - .len = name->len + .name = dentry->d_name.name, + .len = dentry->d_name.len }; struct nfs_diropok res = { .fh = fhandle, @@ -166,10 +171,15 @@ nfs_proc_lookup(struct inode *dir, const struct qstr *name, .rpc_resp = &res, }; int status; + unsigned short task_flags = 0; + + /* Is this is an attribute revalidation, subject to softreval? */ + if (nfs_lookup_is_soft_revalidate(dentry)) + task_flags |= RPC_TASK_TIMEOUT; - dprintk("NFS call lookup %s\n", name->name); + dprintk("NFS call lookup %pd2\n", dentry); nfs_fattr_init(fattr); - status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + status = rpc_call_sync(NFS_CLIENT(dir), &msg, task_flags); dprintk("NFS reply lookup: %d\n", status); return status; } @@ -710,7 +720,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .file_ops = &nfs_file_operations, .getroot = nfs_proc_get_root, .submount = nfs_submount, - .try_mount = nfs_try_mount, + .try_get_tree = nfs_try_get_tree, .getattr = nfs_proc_getattr, .setattr = nfs_proc_setattr, .lookup = nfs_proc_lookup, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index cfe0b586eadd..34bb9add2302 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -214,7 +214,7 @@ static void nfs_initiate_read(struct nfs_pgio_header *hdr, task_setup_data->flags |= swap_flags; rpc_ops->read_setup(hdr, msg); - trace_nfs_initiate_read(inode, hdr->io_start, hdr->good_bytes); + trace_nfs_initiate_read(hdr); } static void @@ -247,8 +247,7 @@ static int nfs_readpage_done(struct rpc_task *task, return status; nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, hdr->res.count); - trace_nfs_readpage_done(inode, task->tk_status, - hdr->args.offset, hdr->res.eof); + trace_nfs_readpage_done(task, hdr); if (task->tk_status == -ESTALE) { set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); @@ -282,6 +281,8 @@ static void nfs_readpage_retry(struct rpc_task *task, argp->offset += resp->count; argp->pgbase += resp->count; argp->count -= resp->count; + resp->count = 0; + resp->eof = 0; rpc_restart_call_prepare(task); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 8d8d04bb9d64..dada09b391c6 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -69,250 +69,6 @@ #include "nfs.h" #define NFSDBG_FACILITY NFSDBG_VFS -#define NFS_TEXT_DATA 1 - -#if IS_ENABLED(CONFIG_NFS_V3) -#define NFS_DEFAULT_VERSION 3 -#else -#define NFS_DEFAULT_VERSION 2 -#endif - -#define NFS_MAX_CONNECTIONS 16 - -enum { - /* Mount options that take no arguments */ - Opt_soft, Opt_softerr, Opt_hard, - Opt_posix, Opt_noposix, - Opt_cto, Opt_nocto, - Opt_ac, Opt_noac, - Opt_lock, Opt_nolock, - Opt_udp, Opt_tcp, Opt_rdma, - Opt_acl, Opt_noacl, - Opt_rdirplus, Opt_nordirplus, - Opt_sharecache, Opt_nosharecache, - Opt_resvport, Opt_noresvport, - Opt_fscache, Opt_nofscache, - Opt_migration, Opt_nomigration, - - /* Mount options that take integer arguments */ - Opt_port, - Opt_rsize, Opt_wsize, Opt_bsize, - Opt_timeo, Opt_retrans, - Opt_acregmin, Opt_acregmax, - Opt_acdirmin, Opt_acdirmax, - Opt_actimeo, - Opt_namelen, - Opt_mountport, - Opt_mountvers, - Opt_minorversion, - - /* Mount options that take string arguments */ - Opt_nfsvers, - Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost, - Opt_addr, Opt_mountaddr, Opt_clientaddr, - Opt_nconnect, - Opt_lookupcache, - Opt_fscache_uniq, - Opt_local_lock, - - /* Special mount options */ - Opt_userspace, Opt_deprecated, Opt_sloppy, - - Opt_err -}; - -static const match_table_t nfs_mount_option_tokens = { - { Opt_userspace, "bg" }, - { Opt_userspace, "fg" }, - { Opt_userspace, "retry=%s" }, - - { Opt_sloppy, "sloppy" }, - - { Opt_soft, "soft" }, - { Opt_softerr, "softerr" }, - { Opt_hard, "hard" }, - { Opt_deprecated, "intr" }, - { Opt_deprecated, "nointr" }, - { Opt_posix, "posix" }, - { Opt_noposix, "noposix" }, - { Opt_cto, "cto" }, - { Opt_nocto, "nocto" }, - { Opt_ac, "ac" }, - { Opt_noac, "noac" }, - { Opt_lock, "lock" }, - { Opt_nolock, "nolock" }, - { Opt_udp, "udp" }, - { Opt_tcp, "tcp" }, - { Opt_rdma, "rdma" }, - { Opt_acl, "acl" }, - { Opt_noacl, "noacl" }, - { Opt_rdirplus, "rdirplus" }, - { Opt_nordirplus, "nordirplus" }, - { Opt_sharecache, "sharecache" }, - { Opt_nosharecache, "nosharecache" }, - { Opt_resvport, "resvport" }, - { Opt_noresvport, "noresvport" }, - { Opt_fscache, "fsc" }, - { Opt_nofscache, "nofsc" }, - { Opt_migration, "migration" }, - { Opt_nomigration, "nomigration" }, - - { Opt_port, "port=%s" }, - { Opt_rsize, "rsize=%s" }, - { Opt_wsize, "wsize=%s" }, - { Opt_bsize, "bsize=%s" }, - { Opt_timeo, "timeo=%s" }, - { Opt_retrans, "retrans=%s" }, - { Opt_acregmin, "acregmin=%s" }, - { Opt_acregmax, "acregmax=%s" }, - { Opt_acdirmin, "acdirmin=%s" }, - { Opt_acdirmax, "acdirmax=%s" }, - { Opt_actimeo, "actimeo=%s" }, - { Opt_namelen, "namlen=%s" }, - { Opt_mountport, "mountport=%s" }, - { Opt_mountvers, "mountvers=%s" }, - { Opt_minorversion, "minorversion=%s" }, - - { Opt_nfsvers, "nfsvers=%s" }, - { Opt_nfsvers, "vers=%s" }, - - { Opt_sec, "sec=%s" }, - { Opt_proto, "proto=%s" }, - { Opt_mountproto, "mountproto=%s" }, - { Opt_addr, "addr=%s" }, - { Opt_clientaddr, "clientaddr=%s" }, - { Opt_mounthost, "mounthost=%s" }, - { Opt_mountaddr, "mountaddr=%s" }, - - { Opt_nconnect, "nconnect=%s" }, - - { Opt_lookupcache, "lookupcache=%s" }, - { Opt_fscache_uniq, "fsc=%s" }, - { Opt_local_lock, "local_lock=%s" }, - - /* The following needs to be listed after all other options */ - { Opt_nfsvers, "v%s" }, - - { Opt_err, NULL } -}; - -enum { - Opt_xprt_udp, Opt_xprt_udp6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_rdma, - Opt_xprt_rdma6, - - Opt_xprt_err -}; - -static const match_table_t nfs_xprt_protocol_tokens = { - { Opt_xprt_udp, "udp" }, - { Opt_xprt_udp6, "udp6" }, - { Opt_xprt_tcp, "tcp" }, - { Opt_xprt_tcp6, "tcp6" }, - { Opt_xprt_rdma, "rdma" }, - { Opt_xprt_rdma6, "rdma6" }, - - { Opt_xprt_err, NULL } -}; - -enum { - Opt_sec_none, Opt_sec_sys, - Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p, - Opt_sec_lkey, Opt_sec_lkeyi, Opt_sec_lkeyp, - Opt_sec_spkm, Opt_sec_spkmi, Opt_sec_spkmp, - - Opt_sec_err -}; - -static const match_table_t nfs_secflavor_tokens = { - { Opt_sec_none, "none" }, - { Opt_sec_none, "null" }, - { Opt_sec_sys, "sys" }, - - { Opt_sec_krb5, "krb5" }, - { Opt_sec_krb5i, "krb5i" }, - { Opt_sec_krb5p, "krb5p" }, - - { Opt_sec_lkey, "lkey" }, - { Opt_sec_lkeyi, "lkeyi" }, - { Opt_sec_lkeyp, "lkeyp" }, - - { Opt_sec_spkm, "spkm3" }, - { Opt_sec_spkmi, "spkm3i" }, - { Opt_sec_spkmp, "spkm3p" }, - - { Opt_sec_err, NULL } -}; - -enum { - Opt_lookupcache_all, Opt_lookupcache_positive, - Opt_lookupcache_none, - - Opt_lookupcache_err -}; - -static match_table_t nfs_lookupcache_tokens = { - { Opt_lookupcache_all, "all" }, - { Opt_lookupcache_positive, "pos" }, - { Opt_lookupcache_positive, "positive" }, - { Opt_lookupcache_none, "none" }, - - { Opt_lookupcache_err, NULL } -}; - -enum { - Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix, - Opt_local_lock_none, - - Opt_local_lock_err -}; - -static match_table_t nfs_local_lock_tokens = { - { Opt_local_lock_all, "all" }, - { Opt_local_lock_flock, "flock" }, - { Opt_local_lock_posix, "posix" }, - { Opt_local_lock_none, "none" }, - - { Opt_local_lock_err, NULL } -}; - -enum { - Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0, - Opt_vers_4_1, Opt_vers_4_2, - - Opt_vers_err -}; - -static match_table_t nfs_vers_tokens = { - { Opt_vers_2, "2" }, - { Opt_vers_3, "3" }, - { Opt_vers_4, "4" }, - { Opt_vers_4_0, "4.0" }, - { Opt_vers_4_1, "4.1" }, - { Opt_vers_4_2, "4.2" }, - - { Opt_vers_err, NULL } -}; - -static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data); - -struct file_system_type nfs_fs_type = { - .owner = THIS_MODULE, - .name = "nfs", - .mount = nfs_fs_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, -}; -MODULE_ALIAS_FS("nfs"); -EXPORT_SYMBOL_GPL(nfs_fs_type); - -struct file_system_type nfs_xdev_fs_type = { - .owner = THIS_MODULE, - .name = "nfs", - .mount = nfs_xdev_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, -}; const struct super_operations nfs_sops = { .alloc_inode = nfs_alloc_inode, @@ -326,26 +82,10 @@ const struct super_operations nfs_sops = { .show_devname = nfs_show_devname, .show_path = nfs_show_path, .show_stats = nfs_show_stats, - .remount_fs = nfs_remount, }; EXPORT_SYMBOL_GPL(nfs_sops); #if IS_ENABLED(CONFIG_NFS_V4) -static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); -static int nfs4_validate_mount_data(void *options, - struct nfs_parsed_mount_data *args, const char *dev_name); - -struct file_system_type nfs4_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs_fs_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, -}; -MODULE_ALIAS_FS("nfs4"); -MODULE_ALIAS("nfs4"); -EXPORT_SYMBOL_GPL(nfs4_fs_type); - static int __init register_nfs4_fs(void) { return register_filesystem(&nfs4_fs_type); @@ -635,6 +375,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, } nfs_info[] = { { NFS_MOUNT_SOFT, ",soft", "" }, { NFS_MOUNT_SOFTERR, ",softerr", "" }, + { NFS_MOUNT_SOFTREVAL, ",softreval", "" }, { NFS_MOUNT_POSIX, ",posix", "" }, { NFS_MOUNT_NOCTO, ",nocto", "" }, { NFS_MOUNT_NOAC, ",noac", "" }, @@ -931,141 +672,6 @@ void nfs_umount_begin(struct super_block *sb) } EXPORT_SYMBOL_GPL(nfs_umount_begin); -static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) -{ - struct nfs_parsed_mount_data *data; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (data) { - data->timeo = NFS_UNSPEC_TIMEO; - data->retrans = NFS_UNSPEC_RETRANS; - data->acregmin = NFS_DEF_ACREGMIN; - data->acregmax = NFS_DEF_ACREGMAX; - data->acdirmin = NFS_DEF_ACDIRMIN; - data->acdirmax = NFS_DEF_ACDIRMAX; - data->mount_server.port = NFS_UNSPEC_PORT; - data->nfs_server.port = NFS_UNSPEC_PORT; - data->nfs_server.protocol = XPRT_TRANSPORT_TCP; - data->selected_flavor = RPC_AUTH_MAXFLAVOR; - data->minorversion = 0; - data->need_mount = true; - data->net = current->nsproxy->net_ns; - data->lsm_opts = NULL; - } - return data; -} - -static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data) -{ - if (data) { - kfree(data->client_address); - kfree(data->mount_server.hostname); - kfree(data->nfs_server.export_path); - kfree(data->nfs_server.hostname); - kfree(data->fscache_uniq); - security_free_mnt_opts(&data->lsm_opts); - kfree(data); - } -} - -/* - * Sanity-check a server address provided by the mount command. - * - * Address family must be initialized, and address must not be - * the ANY address for that family. - */ -static int nfs_verify_server_address(struct sockaddr *addr) -{ - switch (addr->sa_family) { - case AF_INET: { - struct sockaddr_in *sa = (struct sockaddr_in *)addr; - return sa->sin_addr.s_addr != htonl(INADDR_ANY); - } - case AF_INET6: { - struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr; - return !ipv6_addr_any(sa); - } - } - - dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); - return 0; -} - -/* - * Select between a default port value and a user-specified port value. - * If a zero value is set, then autobind will be used. - */ -static void nfs_set_port(struct sockaddr *sap, int *port, - const unsigned short default_port) -{ - if (*port == NFS_UNSPEC_PORT) - *port = default_port; - - rpc_set_port(sap, *port); -} - -/* - * Sanity check the NFS transport protocol. - * - */ -static void nfs_validate_transport_protocol(struct nfs_parsed_mount_data *mnt) -{ - switch (mnt->nfs_server.protocol) { - case XPRT_TRANSPORT_UDP: - case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_RDMA: - break; - default: - mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP; - } -} - -/* - * For text based NFSv2/v3 mounts, the mount protocol transport default - * settings should depend upon the specified NFS transport. - */ -static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) -{ - nfs_validate_transport_protocol(mnt); - - if (mnt->mount_server.protocol == XPRT_TRANSPORT_UDP || - mnt->mount_server.protocol == XPRT_TRANSPORT_TCP) - return; - switch (mnt->nfs_server.protocol) { - case XPRT_TRANSPORT_UDP: - mnt->mount_server.protocol = XPRT_TRANSPORT_UDP; - break; - case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_RDMA: - mnt->mount_server.protocol = XPRT_TRANSPORT_TCP; - } -} - -/* - * Add 'flavor' to 'auth_info' if not already present. - * Returns true if 'flavor' ends up in the list, false otherwise - */ -static bool nfs_auth_info_add(struct nfs_auth_info *auth_info, - rpc_authflavor_t flavor) -{ - unsigned int i; - unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors); - - /* make sure this flavor isn't already in the list */ - for (i = 0; i < auth_info->flavor_len; i++) { - if (flavor == auth_info->flavors[i]) - return true; - } - - if (auth_info->flavor_len + 1 >= max_flavor_len) { - dfprintk(MOUNT, "NFS: too many sec= flavors\n"); - return false; - } - - auth_info->flavors[auth_info->flavor_len++] = flavor; - return true; -} - /* * Return true if 'match' is in auth_info or auth_info is empty. * Return false otherwise. @@ -1087,633 +693,13 @@ bool nfs_auth_info_match(const struct nfs_auth_info *auth_info, EXPORT_SYMBOL_GPL(nfs_auth_info_match); /* - * Parse the value of the 'sec=' option. - */ -static int nfs_parse_security_flavors(char *value, - struct nfs_parsed_mount_data *mnt) -{ - substring_t args[MAX_OPT_ARGS]; - rpc_authflavor_t pseudoflavor; - char *p; - - dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value); - - while ((p = strsep(&value, ":")) != NULL) { - switch (match_token(p, nfs_secflavor_tokens, args)) { - case Opt_sec_none: - pseudoflavor = RPC_AUTH_NULL; - break; - case Opt_sec_sys: - pseudoflavor = RPC_AUTH_UNIX; - break; - case Opt_sec_krb5: - pseudoflavor = RPC_AUTH_GSS_KRB5; - break; - case Opt_sec_krb5i: - pseudoflavor = RPC_AUTH_GSS_KRB5I; - break; - case Opt_sec_krb5p: - pseudoflavor = RPC_AUTH_GSS_KRB5P; - break; - case Opt_sec_lkey: - pseudoflavor = RPC_AUTH_GSS_LKEY; - break; - case Opt_sec_lkeyi: - pseudoflavor = RPC_AUTH_GSS_LKEYI; - break; - case Opt_sec_lkeyp: - pseudoflavor = RPC_AUTH_GSS_LKEYP; - break; - case Opt_sec_spkm: - pseudoflavor = RPC_AUTH_GSS_SPKM; - break; - case Opt_sec_spkmi: - pseudoflavor = RPC_AUTH_GSS_SPKMI; - break; - case Opt_sec_spkmp: - pseudoflavor = RPC_AUTH_GSS_SPKMP; - break; - default: - dfprintk(MOUNT, - "NFS: sec= option '%s' not recognized\n", p); - return 0; - } - - if (!nfs_auth_info_add(&mnt->auth_info, pseudoflavor)) - return 0; - } - - return 1; -} - -static int nfs_parse_version_string(char *string, - struct nfs_parsed_mount_data *mnt, - substring_t *args) -{ - mnt->flags &= ~NFS_MOUNT_VER3; - switch (match_token(string, nfs_vers_tokens, args)) { - case Opt_vers_2: - mnt->version = 2; - break; - case Opt_vers_3: - mnt->flags |= NFS_MOUNT_VER3; - mnt->version = 3; - break; - case Opt_vers_4: - /* Backward compatibility option. In future, - * the mount program should always supply - * a NFSv4 minor version number. - */ - mnt->version = 4; - break; - case Opt_vers_4_0: - mnt->version = 4; - mnt->minorversion = 0; - break; - case Opt_vers_4_1: - mnt->version = 4; - mnt->minorversion = 1; - break; - case Opt_vers_4_2: - mnt->version = 4; - mnt->minorversion = 2; - break; - default: - return 0; - } - return 1; -} - -static int nfs_get_option_str(substring_t args[], char **option) -{ - kfree(*option); - *option = match_strdup(args); - return !*option; -} - -static int nfs_get_option_ul(substring_t args[], unsigned long *option) -{ - int rc; - char *string; - - string = match_strdup(args); - if (string == NULL) - return -ENOMEM; - rc = kstrtoul(string, 10, option); - kfree(string); - - return rc; -} - -static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option, - unsigned long l_bound, unsigned long u_bound) -{ - int ret; - - ret = nfs_get_option_ul(args, option); - if (ret != 0) - return ret; - if (*option < l_bound || *option > u_bound) - return -ERANGE; - return 0; -} - -/* - * Error-check and convert a string of mount options from user space into - * a data structure. The whole mount string is processed; bad options are - * skipped as they are encountered. If there were no errors, return 1; - * otherwise return 0 (zero). - */ -static int nfs_parse_mount_options(char *raw, - struct nfs_parsed_mount_data *mnt) -{ - char *p, *string; - int rc, sloppy = 0, invalid_option = 0; - unsigned short protofamily = AF_UNSPEC; - unsigned short mountfamily = AF_UNSPEC; - - if (!raw) { - dfprintk(MOUNT, "NFS: mount options string was NULL.\n"); - return 1; - } - dfprintk(MOUNT, "NFS: nfs mount opts='%s'\n", raw); - - rc = security_sb_eat_lsm_opts(raw, &mnt->lsm_opts); - if (rc) - goto out_security_failure; - - while ((p = strsep(&raw, ",")) != NULL) { - substring_t args[MAX_OPT_ARGS]; - unsigned long option; - int token; - - if (!*p) - continue; - - dfprintk(MOUNT, "NFS: parsing nfs mount option '%s'\n", p); - - token = match_token(p, nfs_mount_option_tokens, args); - switch (token) { - - /* - * boolean options: foo/nofoo - */ - case Opt_soft: - mnt->flags |= NFS_MOUNT_SOFT; - mnt->flags &= ~NFS_MOUNT_SOFTERR; - break; - case Opt_softerr: - mnt->flags |= NFS_MOUNT_SOFTERR; - mnt->flags &= ~NFS_MOUNT_SOFT; - break; - case Opt_hard: - mnt->flags &= ~(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR); - break; - case Opt_posix: - mnt->flags |= NFS_MOUNT_POSIX; - break; - case Opt_noposix: - mnt->flags &= ~NFS_MOUNT_POSIX; - break; - case Opt_cto: - mnt->flags &= ~NFS_MOUNT_NOCTO; - break; - case Opt_nocto: - mnt->flags |= NFS_MOUNT_NOCTO; - break; - case Opt_ac: - mnt->flags &= ~NFS_MOUNT_NOAC; - break; - case Opt_noac: - mnt->flags |= NFS_MOUNT_NOAC; - break; - case Opt_lock: - mnt->flags &= ~NFS_MOUNT_NONLM; - mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | - NFS_MOUNT_LOCAL_FCNTL); - break; - case Opt_nolock: - mnt->flags |= NFS_MOUNT_NONLM; - mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK | - NFS_MOUNT_LOCAL_FCNTL); - break; - case Opt_udp: - mnt->flags &= ~NFS_MOUNT_TCP; - mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP; - break; - case Opt_tcp: - mnt->flags |= NFS_MOUNT_TCP; - mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP; - break; - case Opt_rdma: - mnt->flags |= NFS_MOUNT_TCP; /* for side protocols */ - mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA; - xprt_load_transport(p); - break; - case Opt_acl: - mnt->flags &= ~NFS_MOUNT_NOACL; - break; - case Opt_noacl: - mnt->flags |= NFS_MOUNT_NOACL; - break; - case Opt_rdirplus: - mnt->flags &= ~NFS_MOUNT_NORDIRPLUS; - break; - case Opt_nordirplus: - mnt->flags |= NFS_MOUNT_NORDIRPLUS; - break; - case Opt_sharecache: - mnt->flags &= ~NFS_MOUNT_UNSHARED; - break; - case Opt_nosharecache: - mnt->flags |= NFS_MOUNT_UNSHARED; - break; - case Opt_resvport: - mnt->flags &= ~NFS_MOUNT_NORESVPORT; - break; - case Opt_noresvport: - mnt->flags |= NFS_MOUNT_NORESVPORT; - break; - case Opt_fscache: - mnt->options |= NFS_OPTION_FSCACHE; - kfree(mnt->fscache_uniq); - mnt->fscache_uniq = NULL; - break; - case Opt_nofscache: - mnt->options &= ~NFS_OPTION_FSCACHE; - kfree(mnt->fscache_uniq); - mnt->fscache_uniq = NULL; - break; - case Opt_migration: - mnt->options |= NFS_OPTION_MIGRATION; - break; - case Opt_nomigration: - mnt->options &= ~NFS_OPTION_MIGRATION; - break; - - /* - * options that take numeric values - */ - case Opt_port: - if (nfs_get_option_ul(args, &option) || - option > USHRT_MAX) - goto out_invalid_value; - mnt->nfs_server.port = option; - break; - case Opt_rsize: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->rsize = option; - break; - case Opt_wsize: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->wsize = option; - break; - case Opt_bsize: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->bsize = option; - break; - case Opt_timeo: - if (nfs_get_option_ul_bound(args, &option, 1, INT_MAX)) - goto out_invalid_value; - mnt->timeo = option; - break; - case Opt_retrans: - if (nfs_get_option_ul_bound(args, &option, 0, INT_MAX)) - goto out_invalid_value; - mnt->retrans = option; - break; - case Opt_acregmin: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->acregmin = option; - break; - case Opt_acregmax: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->acregmax = option; - break; - case Opt_acdirmin: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->acdirmin = option; - break; - case Opt_acdirmax: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->acdirmax = option; - break; - case Opt_actimeo: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->acregmin = mnt->acregmax = - mnt->acdirmin = mnt->acdirmax = option; - break; - case Opt_namelen: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - mnt->namlen = option; - break; - case Opt_mountport: - if (nfs_get_option_ul(args, &option) || - option > USHRT_MAX) - goto out_invalid_value; - mnt->mount_server.port = option; - break; - case Opt_mountvers: - if (nfs_get_option_ul(args, &option) || - option < NFS_MNT_VERSION || - option > NFS_MNT3_VERSION) - goto out_invalid_value; - mnt->mount_server.version = option; - break; - case Opt_minorversion: - if (nfs_get_option_ul(args, &option)) - goto out_invalid_value; - if (option > NFS4_MAX_MINOR_VERSION) - goto out_invalid_value; - mnt->minorversion = option; - break; - - /* - * options that take text values - */ - case Opt_nfsvers: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - rc = nfs_parse_version_string(string, mnt, args); - kfree(string); - if (!rc) - goto out_invalid_value; - break; - case Opt_sec: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - rc = nfs_parse_security_flavors(string, mnt); - kfree(string); - if (!rc) { - dfprintk(MOUNT, "NFS: unrecognized " - "security flavor\n"); - return 0; - } - break; - case Opt_proto: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - token = match_token(string, - nfs_xprt_protocol_tokens, args); - - protofamily = AF_INET; - switch (token) { - case Opt_xprt_udp6: - protofamily = AF_INET6; - /* fall through */ - case Opt_xprt_udp: - mnt->flags &= ~NFS_MOUNT_TCP; - mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP; - break; - case Opt_xprt_tcp6: - protofamily = AF_INET6; - /* fall through */ - case Opt_xprt_tcp: - mnt->flags |= NFS_MOUNT_TCP; - mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP; - break; - case Opt_xprt_rdma6: - protofamily = AF_INET6; - /* fall through */ - case Opt_xprt_rdma: - /* vector side protocols to TCP */ - mnt->flags |= NFS_MOUNT_TCP; - mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA; - xprt_load_transport(string); - break; - default: - dfprintk(MOUNT, "NFS: unrecognized " - "transport protocol\n"); - kfree(string); - return 0; - } - kfree(string); - break; - case Opt_mountproto: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - token = match_token(string, - nfs_xprt_protocol_tokens, args); - kfree(string); - - mountfamily = AF_INET; - switch (token) { - case Opt_xprt_udp6: - mountfamily = AF_INET6; - /* fall through */ - case Opt_xprt_udp: - mnt->mount_server.protocol = XPRT_TRANSPORT_UDP; - break; - case Opt_xprt_tcp6: - mountfamily = AF_INET6; - /* fall through */ - case Opt_xprt_tcp: - mnt->mount_server.protocol = XPRT_TRANSPORT_TCP; - break; - case Opt_xprt_rdma: /* not used for side protocols */ - default: - dfprintk(MOUNT, "NFS: unrecognized " - "transport protocol\n"); - return 0; - } - break; - case Opt_addr: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - mnt->nfs_server.addrlen = - rpc_pton(mnt->net, string, strlen(string), - (struct sockaddr *) - &mnt->nfs_server.address, - sizeof(mnt->nfs_server.address)); - kfree(string); - if (mnt->nfs_server.addrlen == 0) - goto out_invalid_address; - break; - case Opt_clientaddr: - if (nfs_get_option_str(args, &mnt->client_address)) - goto out_nomem; - break; - case Opt_mounthost: - if (nfs_get_option_str(args, - &mnt->mount_server.hostname)) - goto out_nomem; - break; - case Opt_mountaddr: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - mnt->mount_server.addrlen = - rpc_pton(mnt->net, string, strlen(string), - (struct sockaddr *) - &mnt->mount_server.address, - sizeof(mnt->mount_server.address)); - kfree(string); - if (mnt->mount_server.addrlen == 0) - goto out_invalid_address; - break; - case Opt_nconnect: - if (nfs_get_option_ul_bound(args, &option, 1, NFS_MAX_CONNECTIONS)) - goto out_invalid_value; - mnt->nfs_server.nconnect = option; - break; - case Opt_lookupcache: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - token = match_token(string, - nfs_lookupcache_tokens, args); - kfree(string); - switch (token) { - case Opt_lookupcache_all: - mnt->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE); - break; - case Opt_lookupcache_positive: - mnt->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE; - mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG; - break; - case Opt_lookupcache_none: - mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE; - break; - default: - dfprintk(MOUNT, "NFS: invalid " - "lookupcache argument\n"); - return 0; - } - break; - case Opt_fscache_uniq: - if (nfs_get_option_str(args, &mnt->fscache_uniq)) - goto out_nomem; - mnt->options |= NFS_OPTION_FSCACHE; - break; - case Opt_local_lock: - string = match_strdup(args); - if (string == NULL) - goto out_nomem; - token = match_token(string, nfs_local_lock_tokens, - args); - kfree(string); - switch (token) { - case Opt_local_lock_all: - mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK | - NFS_MOUNT_LOCAL_FCNTL); - break; - case Opt_local_lock_flock: - mnt->flags |= NFS_MOUNT_LOCAL_FLOCK; - break; - case Opt_local_lock_posix: - mnt->flags |= NFS_MOUNT_LOCAL_FCNTL; - break; - case Opt_local_lock_none: - mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | - NFS_MOUNT_LOCAL_FCNTL); - break; - default: - dfprintk(MOUNT, "NFS: invalid " - "local_lock argument\n"); - return 0; - } - break; - - /* - * Special options - */ - case Opt_sloppy: - sloppy = 1; - dfprintk(MOUNT, "NFS: relaxing parsing rules\n"); - break; - case Opt_userspace: - case Opt_deprecated: - dfprintk(MOUNT, "NFS: ignoring mount option " - "'%s'\n", p); - break; - - default: - invalid_option = 1; - dfprintk(MOUNT, "NFS: unrecognized mount option " - "'%s'\n", p); - } - } - - if (!sloppy && invalid_option) - return 0; - - if (mnt->minorversion && mnt->version != 4) - goto out_minorversion_mismatch; - - if (mnt->options & NFS_OPTION_MIGRATION && - (mnt->version != 4 || mnt->minorversion != 0)) - goto out_migration_misuse; - - /* - * verify that any proto=/mountproto= options match the address - * families in the addr=/mountaddr= options. - */ - if (protofamily != AF_UNSPEC && - protofamily != mnt->nfs_server.address.ss_family) - goto out_proto_mismatch; - - if (mountfamily != AF_UNSPEC) { - if (mnt->mount_server.addrlen) { - if (mountfamily != mnt->mount_server.address.ss_family) - goto out_mountproto_mismatch; - } else { - if (mountfamily != mnt->nfs_server.address.ss_family) - goto out_mountproto_mismatch; - } - } - - return 1; - -out_mountproto_mismatch: - printk(KERN_INFO "NFS: mount server address does not match mountproto= " - "option\n"); - return 0; -out_proto_mismatch: - printk(KERN_INFO "NFS: server address does not match proto= option\n"); - return 0; -out_invalid_address: - printk(KERN_INFO "NFS: bad IP address specified: %s\n", p); - return 0; -out_invalid_value: - printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p); - return 0; -out_minorversion_mismatch: - printk(KERN_INFO "NFS: mount option vers=%u does not support " - "minorversion=%u\n", mnt->version, mnt->minorversion); - return 0; -out_migration_misuse: - printk(KERN_INFO - "NFS: 'migration' not supported for this NFS version\n"); - return 0; -out_nomem: - printk(KERN_INFO "NFS: not enough memory to parse option\n"); - return 0; -out_security_failure: - printk(KERN_INFO "NFS: security options invalid: %d\n", rc); - return 0; -} - -/* - * Ensure that a specified authtype in args->auth_info is supported by - * the server. Returns 0 and sets args->selected_flavor if it's ok, and + * Ensure that a specified authtype in ctx->auth_info is supported by + * the server. Returns 0 and sets ctx->selected_flavor if it's ok, and * -EACCES if not. */ -static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, - rpc_authflavor_t *server_authlist, unsigned int count) +static int nfs_verify_authflavors(struct nfs_fs_context *ctx, + rpc_authflavor_t *server_authlist, + unsigned int count) { rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; bool found_auth_null = false; @@ -1734,7 +720,7 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, for (i = 0; i < count; i++) { flavor = server_authlist[i]; - if (nfs_auth_info_match(&args->auth_info, flavor)) + if (nfs_auth_info_match(&ctx->auth_info, flavor)) goto out; if (flavor == RPC_AUTH_NULL) @@ -1742,7 +728,7 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, } if (found_auth_null) { - flavor = args->auth_info.flavors[0]; + flavor = ctx->auth_info.flavors[0]; goto out; } @@ -1751,8 +737,8 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, return -EACCES; out: - args->selected_flavor = flavor; - dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor); + ctx->selected_flavor = flavor; + dfprintk(MOUNT, "NFS: using auth flavor %u\n", ctx->selected_flavor); return 0; } @@ -1760,50 +746,51 @@ out: * Use the remote server's MOUNT service to request the NFS file handle * corresponding to the provided path. */ -static int nfs_request_mount(struct nfs_parsed_mount_data *args, +static int nfs_request_mount(struct fs_context *fc, struct nfs_fh *root_fh, rpc_authflavor_t *server_authlist, unsigned int *server_authlist_len) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_mount_request request = { .sap = (struct sockaddr *) - &args->mount_server.address, - .dirpath = args->nfs_server.export_path, - .protocol = args->mount_server.protocol, + &ctx->mount_server.address, + .dirpath = ctx->nfs_server.export_path, + .protocol = ctx->mount_server.protocol, .fh = root_fh, - .noresvport = args->flags & NFS_MOUNT_NORESVPORT, + .noresvport = ctx->flags & NFS_MOUNT_NORESVPORT, .auth_flav_len = server_authlist_len, .auth_flavs = server_authlist, - .net = args->net, + .net = fc->net_ns, }; int status; - if (args->mount_server.version == 0) { - switch (args->version) { + if (ctx->mount_server.version == 0) { + switch (ctx->version) { default: - args->mount_server.version = NFS_MNT3_VERSION; + ctx->mount_server.version = NFS_MNT3_VERSION; break; case 2: - args->mount_server.version = NFS_MNT_VERSION; + ctx->mount_server.version = NFS_MNT_VERSION; } } - request.version = args->mount_server.version; + request.version = ctx->mount_server.version; - if (args->mount_server.hostname) - request.hostname = args->mount_server.hostname; + if (ctx->mount_server.hostname) + request.hostname = ctx->mount_server.hostname; else - request.hostname = args->nfs_server.hostname; + request.hostname = ctx->nfs_server.hostname; /* * Construct the mount server's address. */ - if (args->mount_server.address.ss_family == AF_UNSPEC) { - memcpy(request.sap, &args->nfs_server.address, - args->nfs_server.addrlen); - args->mount_server.addrlen = args->nfs_server.addrlen; + if (ctx->mount_server.address.sa_family == AF_UNSPEC) { + memcpy(request.sap, &ctx->nfs_server.address, + ctx->nfs_server.addrlen); + ctx->mount_server.addrlen = ctx->nfs_server.addrlen; } - request.salen = args->mount_server.addrlen; - nfs_set_port(request.sap, &args->mount_server.port, 0); + request.salen = ctx->mount_server.addrlen; + nfs_set_port(request.sap, &ctx->mount_server.port, 0); /* * Now ask the mount server to map our export path @@ -1819,20 +806,18 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args, return 0; } -static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) +static struct nfs_server *nfs_try_mount_request(struct fs_context *fc) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); int status; unsigned int i; bool tried_auth_unix = false; bool auth_null_in_list = false; struct nfs_server *server = ERR_PTR(-EACCES); - struct nfs_parsed_mount_data *args = mount_info->parsed; rpc_authflavor_t authlist[NFS_MAX_SECFLAVORS]; unsigned int authlist_len = ARRAY_SIZE(authlist); - status = nfs_request_mount(args, mount_info->mntfh, authlist, - &authlist_len); + status = nfs_request_mount(fc, ctx->mntfh, authlist, &authlist_len); if (status) return ERR_PTR(status); @@ -1840,13 +825,13 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf * Was a sec= authflavor specified in the options? First, verify * whether the server supports it, and then just try to use it if so. */ - if (args->auth_info.flavor_len > 0) { - status = nfs_verify_authflavors(args, authlist, authlist_len); + if (ctx->auth_info.flavor_len > 0) { + status = nfs_verify_authflavors(ctx, authlist, authlist_len); dfprintk(MOUNT, "NFS: using auth flavor %u\n", - args->selected_flavor); + ctx->selected_flavor); if (status) return ERR_PTR(status); - return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); + return ctx->nfs_mod->rpc_ops->create_server(fc); } /* @@ -1872,8 +857,8 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Fallthrough */ } dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor); - args->selected_flavor = flavor; - server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); + ctx->selected_flavor = flavor; + server = ctx->nfs_mod->rpc_ops->create_server(fc); if (!IS_ERR(server)) return server; } @@ -1888,348 +873,23 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Last chance! Try AUTH_UNIX */ dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX); - args->selected_flavor = RPC_AUTH_UNIX; - return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); + ctx->selected_flavor = RPC_AUTH_UNIX; + return ctx->nfs_mod->rpc_ops->create_server(fc); } -struct dentry *nfs_try_mount(int flags, const char *dev_name, - struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) +int nfs_try_get_tree(struct fs_context *fc) { - struct nfs_server *server; + struct nfs_fs_context *ctx = nfs_fc2context(fc); - if (mount_info->parsed->need_mount) - server = nfs_try_mount_request(mount_info, nfs_mod); + if (ctx->need_mount) + ctx->server = nfs_try_mount_request(fc); else - server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); - - if (IS_ERR(server)) - return ERR_CAST(server); - - return nfs_fs_mount_common(server, flags, dev_name, mount_info, nfs_mod); -} -EXPORT_SYMBOL_GPL(nfs_try_mount); - -/* - * Split "dev_name" into "hostname:export_path". - * - * The leftmost colon demarks the split between the server's hostname - * and the export path. If the hostname starts with a left square - * bracket, then it may contain colons. - * - * Note: caller frees hostname and export path, even on error. - */ -static int nfs_parse_devname(const char *dev_name, - char **hostname, size_t maxnamlen, - char **export_path, size_t maxpathlen) -{ - size_t len; - char *end; - - if (unlikely(!dev_name || !*dev_name)) { - dfprintk(MOUNT, "NFS: device name not specified\n"); - return -EINVAL; - } - - /* Is the host name protected with square brakcets? */ - if (*dev_name == '[') { - end = strchr(++dev_name, ']'); - if (end == NULL || end[1] != ':') - goto out_bad_devname; - - len = end - dev_name; - end++; - } else { - char *comma; - - end = strchr(dev_name, ':'); - if (end == NULL) - goto out_bad_devname; - len = end - dev_name; - - /* kill possible hostname list: not supported */ - comma = strchr(dev_name, ','); - if (comma != NULL && comma < end) - len = comma - dev_name; - } - - if (len > maxnamlen) - goto out_hostname; - - /* N.B. caller will free nfs_server.hostname in all cases */ - *hostname = kstrndup(dev_name, len, GFP_KERNEL); - if (*hostname == NULL) - goto out_nomem; - len = strlen(++end); - if (len > maxpathlen) - goto out_path; - *export_path = kstrndup(end, len, GFP_KERNEL); - if (!*export_path) - goto out_nomem; - - dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", *export_path); - return 0; - -out_bad_devname: - dfprintk(MOUNT, "NFS: device name not in host:path format\n"); - return -EINVAL; + ctx->server = ctx->nfs_mod->rpc_ops->create_server(fc); -out_nomem: - dfprintk(MOUNT, "NFS: not enough memory to parse device name\n"); - return -ENOMEM; - -out_hostname: - dfprintk(MOUNT, "NFS: server hostname too long\n"); - return -ENAMETOOLONG; - -out_path: - dfprintk(MOUNT, "NFS: export pathname too long\n"); - return -ENAMETOOLONG; + return nfs_get_tree_common(fc); } +EXPORT_SYMBOL_GPL(nfs_try_get_tree); -/* - * Validate the NFS2/NFS3 mount data - * - fills in the mount root filehandle - * - * For option strings, user space handles the following behaviors: - * - * + DNS: mapping server host name to IP address ("addr=" option) - * - * + failure mode: how to behave if a mount request can't be handled - * immediately ("fg/bg" option) - * - * + retry: how often to retry a mount request ("retry=" option) - * - * + breaking back: trying proto=udp after proto=tcp, v2 after v3, - * mountproto=tcp after mountproto=udp, and so on - */ -static int nfs23_validate_mount_data(void *options, - struct nfs_parsed_mount_data *args, - struct nfs_fh *mntfh, - const char *dev_name) -{ - struct nfs_mount_data *data = (struct nfs_mount_data *)options; - struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; - int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; - - if (data == NULL) - goto out_no_data; - - args->version = NFS_DEFAULT_VERSION; - switch (data->version) { - case 1: - data->namlen = 0; /* fall through */ - case 2: - data->bsize = 0; /* fall through */ - case 3: - if (data->flags & NFS_MOUNT_VER3) - goto out_no_v3; - data->root.size = NFS2_FHSIZE; - memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); - /* Turn off security negotiation */ - extra_flags |= NFS_MOUNT_SECFLAVOUR; - /* fall through */ - case 4: - if (data->flags & NFS_MOUNT_SECFLAVOUR) - goto out_no_sec; - /* fall through */ - case 5: - memset(data->context, 0, sizeof(data->context)); - /* fall through */ - case 6: - if (data->flags & NFS_MOUNT_VER3) { - if (data->root.size > NFS3_FHSIZE || data->root.size == 0) - goto out_invalid_fh; - mntfh->size = data->root.size; - args->version = 3; - } else { - mntfh->size = NFS2_FHSIZE; - args->version = 2; - } - - - memcpy(mntfh->data, data->root.data, mntfh->size); - if (mntfh->size < sizeof(mntfh->data)) - memset(mntfh->data + mntfh->size, 0, - sizeof(mntfh->data) - mntfh->size); - - /* - * Translate to nfs_parsed_mount_data, which nfs_fill_super - * can deal with. - */ - args->flags = data->flags & NFS_MOUNT_FLAGMASK; - args->flags |= extra_flags; - args->rsize = data->rsize; - args->wsize = data->wsize; - args->timeo = data->timeo; - args->retrans = data->retrans; - args->acregmin = data->acregmin; - args->acregmax = data->acregmax; - args->acdirmin = data->acdirmin; - args->acdirmax = data->acdirmax; - args->need_mount = false; - - memcpy(sap, &data->addr, sizeof(data->addr)); - args->nfs_server.addrlen = sizeof(data->addr); - args->nfs_server.port = ntohs(data->addr.sin_port); - if (sap->sa_family != AF_INET || - !nfs_verify_server_address(sap)) - goto out_no_address; - - if (!(data->flags & NFS_MOUNT_TCP)) - args->nfs_server.protocol = XPRT_TRANSPORT_UDP; - /* N.B. caller will free nfs_server.hostname in all cases */ - args->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL); - args->namlen = data->namlen; - args->bsize = data->bsize; - - if (data->flags & NFS_MOUNT_SECFLAVOUR) - args->selected_flavor = data->pseudoflavor; - else - args->selected_flavor = RPC_AUTH_UNIX; - if (!args->nfs_server.hostname) - goto out_nomem; - - if (!(data->flags & NFS_MOUNT_NONLM)) - args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK| - NFS_MOUNT_LOCAL_FCNTL); - else - args->flags |= (NFS_MOUNT_LOCAL_FLOCK| - NFS_MOUNT_LOCAL_FCNTL); - /* - * The legacy version 6 binary mount data from userspace has a - * field used only to transport selinux information into the - * the kernel. To continue to support that functionality we - * have a touch of selinux knowledge here in the NFS code. The - * userspace code converted context=blah to just blah so we are - * converting back to the full string selinux understands. - */ - if (data->context[0]){ -#ifdef CONFIG_SECURITY_SELINUX - int rc; - data->context[NFS_MAX_CONTEXT_LEN] = '\0'; - rc = security_add_mnt_opt("context", data->context, - strlen(data->context), &args->lsm_opts); - if (rc) - return rc; -#else - return -EINVAL; -#endif - } - - break; - default: - return NFS_TEXT_DATA; - } - - return 0; - -out_no_data: - dfprintk(MOUNT, "NFS: mount program didn't pass any mount data\n"); - return -EINVAL; - -out_no_v3: - dfprintk(MOUNT, "NFS: nfs_mount_data version %d does not support v3\n", - data->version); - return -EINVAL; - -out_no_sec: - dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n"); - return -EINVAL; - -out_nomem: - dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n"); - return -ENOMEM; - -out_no_address: - dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); - return -EINVAL; - -out_invalid_fh: - dfprintk(MOUNT, "NFS: invalid root filehandle\n"); - return -EINVAL; -} - -#if IS_ENABLED(CONFIG_NFS_V4) -static int nfs_validate_mount_data(struct file_system_type *fs_type, - void *options, - struct nfs_parsed_mount_data *args, - struct nfs_fh *mntfh, - const char *dev_name) -{ - if (fs_type == &nfs_fs_type) - return nfs23_validate_mount_data(options, args, mntfh, dev_name); - return nfs4_validate_mount_data(options, args, dev_name); -} -#else -static int nfs_validate_mount_data(struct file_system_type *fs_type, - void *options, - struct nfs_parsed_mount_data *args, - struct nfs_fh *mntfh, - const char *dev_name) -{ - return nfs23_validate_mount_data(options, args, mntfh, dev_name); -} -#endif - -static int nfs_validate_text_mount_data(void *options, - struct nfs_parsed_mount_data *args, - const char *dev_name) -{ - int port = 0; - int max_namelen = PAGE_SIZE; - int max_pathlen = NFS_MAXPATHLEN; - struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; - - if (nfs_parse_mount_options((char *)options, args) == 0) - return -EINVAL; - - if (!nfs_verify_server_address(sap)) - goto out_no_address; - - if (args->version == 4) { -#if IS_ENABLED(CONFIG_NFS_V4) - if (args->nfs_server.protocol == XPRT_TRANSPORT_RDMA) - port = NFS_RDMA_PORT; - else - port = NFS_PORT; - max_namelen = NFS4_MAXNAMLEN; - max_pathlen = NFS4_MAXPATHLEN; - nfs_validate_transport_protocol(args); - if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP) - goto out_invalid_transport_udp; - nfs4_validate_mount_flags(args); -#else - goto out_v4_not_compiled; -#endif /* CONFIG_NFS_V4 */ - } else { - nfs_set_mount_transport_protocol(args); - if (args->nfs_server.protocol == XPRT_TRANSPORT_RDMA) - port = NFS_RDMA_PORT; - } - - nfs_set_port(sap, &args->nfs_server.port, port); - - return nfs_parse_devname(dev_name, - &args->nfs_server.hostname, - max_namelen, - &args->nfs_server.export_path, - max_pathlen); - -#if !IS_ENABLED(CONFIG_NFS_V4) -out_v4_not_compiled: - dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); - return -EPROTONOSUPPORT; -#else -out_invalid_transport_udp: - dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n"); - return -EINVAL; -#endif /* !CONFIG_NFS_V4 */ - -out_no_address: - dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); - return -EINVAL; -} #define NFS_REMOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \ | NFS_MOUNT_SECURE \ @@ -2246,39 +906,35 @@ out_no_address: static int nfs_compare_remount_data(struct nfs_server *nfss, - struct nfs_parsed_mount_data *data) -{ - if ((data->flags ^ nfss->flags) & NFS_REMOUNT_CMP_FLAGMASK || - data->rsize != nfss->rsize || - data->wsize != nfss->wsize || - data->version != nfss->nfs_client->rpc_ops->version || - data->minorversion != nfss->nfs_client->cl_minorversion || - data->retrans != nfss->client->cl_timeout->to_retries || - !nfs_auth_info_match(&data->auth_info, nfss->client->cl_auth->au_flavor) || - data->acregmin != nfss->acregmin / HZ || - data->acregmax != nfss->acregmax / HZ || - data->acdirmin != nfss->acdirmin / HZ || - data->acdirmax != nfss->acdirmax / HZ || - data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) || - (data->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) || - data->nfs_server.port != nfss->port || - data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen || - !rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address, + struct nfs_fs_context *ctx) +{ + if ((ctx->flags ^ nfss->flags) & NFS_REMOUNT_CMP_FLAGMASK || + ctx->rsize != nfss->rsize || + ctx->wsize != nfss->wsize || + ctx->version != nfss->nfs_client->rpc_ops->version || + ctx->minorversion != nfss->nfs_client->cl_minorversion || + ctx->retrans != nfss->client->cl_timeout->to_retries || + !nfs_auth_info_match(&ctx->auth_info, nfss->client->cl_auth->au_flavor) || + ctx->acregmin != nfss->acregmin / HZ || + ctx->acregmax != nfss->acregmax / HZ || + ctx->acdirmin != nfss->acdirmin / HZ || + ctx->acdirmax != nfss->acdirmax / HZ || + ctx->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) || + (ctx->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) || + ctx->nfs_server.port != nfss->port || + ctx->nfs_server.addrlen != nfss->nfs_client->cl_addrlen || + !rpc_cmp_addr((struct sockaddr *)&ctx->nfs_server.address, (struct sockaddr *)&nfss->nfs_client->cl_addr)) return -EINVAL; return 0; } -int -nfs_remount(struct super_block *sb, int *flags, char *raw_data) +int nfs_reconfigure(struct fs_context *fc) { - int error; + struct nfs_fs_context *ctx = nfs_fc2context(fc); + struct super_block *sb = fc->root->d_sb; struct nfs_server *nfss = sb->s_fs_info; - struct nfs_parsed_mount_data *data; - struct nfs_mount_data *options = (struct nfs_mount_data *)raw_data; - struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data; - u32 nfsvers = nfss->nfs_client->rpc_ops->version; sync_filesystem(sb); @@ -2288,92 +944,38 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) * ones were explicitly specified. Fall back to legacy behavior and * just return success. */ - if ((nfsvers == 4 && (!options4 || options4->version == 1)) || - (nfsvers <= 3 && (!options || (options->version >= 1 && - options->version <= 6)))) + if (ctx->skip_reconfig_option_check) return 0; - data = nfs_alloc_parsed_mount_data(); - if (data == NULL) - return -ENOMEM; - - /* fill out struct with values from existing mount */ - data->flags = nfss->flags; - data->rsize = nfss->rsize; - data->wsize = nfss->wsize; - data->retrans = nfss->client->cl_timeout->to_retries; - data->selected_flavor = nfss->client->cl_auth->au_flavor; - data->acregmin = nfss->acregmin / HZ; - data->acregmax = nfss->acregmax / HZ; - data->acdirmin = nfss->acdirmin / HZ; - data->acdirmax = nfss->acdirmax / HZ; - data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; - data->nfs_server.port = nfss->port; - data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; - data->version = nfsvers; - data->minorversion = nfss->nfs_client->cl_minorversion; - data->net = current->nsproxy->net_ns; - memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr, - data->nfs_server.addrlen); - - /* overwrite those values with any that were specified */ - error = -EINVAL; - if (!nfs_parse_mount_options((char *)options, data)) - goto out; - /* * noac is a special case. It implies -o sync, but that's not - * necessarily reflected in the mtab options. do_remount_sb + * necessarily reflected in the mtab options. reconfigure_super * will clear SB_SYNCHRONOUS if -o sync wasn't specified in the * remount options, so we have to explicitly reset it. */ - if (data->flags & NFS_MOUNT_NOAC) - *flags |= SB_SYNCHRONOUS; + if (ctx->flags & NFS_MOUNT_NOAC) { + fc->sb_flags |= SB_SYNCHRONOUS; + fc->sb_flags_mask |= SB_SYNCHRONOUS; + } /* compare new mount options with old ones */ - error = nfs_compare_remount_data(nfss, data); - if (!error) - error = security_sb_remount(sb, data->lsm_opts); -out: - nfs_free_parsed_mount_data(data); - return error; -} -EXPORT_SYMBOL_GPL(nfs_remount); - -/* - * Initialise the common bits of the superblock - */ -static void nfs_initialise_sb(struct super_block *sb) -{ - struct nfs_server *server = NFS_SB(sb); - - sb->s_magic = NFS_SUPER_MAGIC; - - /* We probably want something more informative here */ - snprintf(sb->s_id, sizeof(sb->s_id), - "%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev)); - - if (sb->s_blocksize == 0) - sb->s_blocksize = nfs_block_bits(server->wsize, - &sb->s_blocksize_bits); - - nfs_super_set_maxbytes(sb, server->maxfilesize); + return nfs_compare_remount_data(nfss, ctx); } +EXPORT_SYMBOL_GPL(nfs_reconfigure); /* - * Finish setting up an NFS2/3 superblock + * Finish setting up an NFS superblock */ -void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) +static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) { - struct nfs_parsed_mount_data *data = mount_info->parsed; struct nfs_server *server = NFS_SB(sb); sb->s_blocksize_bits = 0; sb->s_blocksize = 0; sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr; sb->s_op = server->nfs_client->cl_nfs_mod->sops; - if (data && data->bsize) - sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits); + if (ctx && ctx->bsize) + sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits); if (server->nfs_client->rpc_ops->version != 2) { /* The VFS shouldn't apply the umask to mode bits. We will do @@ -2393,53 +995,27 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) sb->s_time_max = S64_MAX; } - nfs_initialise_sb(sb); -} -EXPORT_SYMBOL_GPL(nfs_fill_super); - -/* - * Finish setting up a cloned NFS2/3/4 superblock - */ -static void nfs_clone_super(struct super_block *sb, - struct nfs_mount_info *mount_info) -{ - const struct super_block *old_sb = mount_info->cloned->sb; - struct nfs_server *server = NFS_SB(sb); - - sb->s_blocksize_bits = old_sb->s_blocksize_bits; - sb->s_blocksize = old_sb->s_blocksize; - sb->s_maxbytes = old_sb->s_maxbytes; - sb->s_xattr = old_sb->s_xattr; - sb->s_op = old_sb->s_op; - sb->s_export_op = old_sb->s_export_op; + sb->s_magic = NFS_SUPER_MAGIC; - if (server->nfs_client->rpc_ops->version != 2) { - /* The VFS shouldn't apply the umask to mode bits. We will do - * so ourselves when necessary. - */ - sb->s_flags |= SB_POSIXACL; - sb->s_time_gran = 1; - } else - sb->s_time_gran = 1000; + /* We probably want something more informative here */ + snprintf(sb->s_id, sizeof(sb->s_id), + "%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev)); - if (server->nfs_client->rpc_ops->version != 4) { - sb->s_time_min = 0; - sb->s_time_max = U32_MAX; - } else { - sb->s_time_min = S64_MIN; - sb->s_time_max = S64_MAX; - } + if (sb->s_blocksize == 0) + sb->s_blocksize = nfs_block_bits(server->wsize, + &sb->s_blocksize_bits); - nfs_initialise_sb(sb); + nfs_super_set_maxbytes(sb, server->maxfilesize); } -static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags) +static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, + const struct fs_context *fc) { const struct nfs_server *a = s->s_fs_info; const struct rpc_clnt *clnt_a = a->client; const struct rpc_clnt *clnt_b = b->client; - if ((s->s_flags & NFS_MS_MASK) != (flags & NFS_MS_MASK)) + if ((s->s_flags & NFS_SB_MASK) != (fc->sb_flags & NFS_SB_MASK)) goto Ebusy; if (a->nfs_client != b->nfs_client) goto Ebusy; @@ -2464,19 +1040,11 @@ Ebusy: return 0; } -struct nfs_sb_mountdata { - struct nfs_server *server; - int mntflags; -}; - -static int nfs_set_super(struct super_block *s, void *data) +static int nfs_set_super(struct super_block *s, struct fs_context *fc) { - struct nfs_sb_mountdata *sb_mntdata = data; - struct nfs_server *server = sb_mntdata->server; + struct nfs_server *server = fc->s_fs_info; int ret; - s->s_flags = sb_mntdata->mntflags; - s->s_fs_info = server; s->s_d_op = server->nfs_client->rpc_ops->dentry_ops; ret = set_anon_super(s, server); if (ret == 0) @@ -2541,11 +1109,9 @@ static int nfs_compare_userns(const struct nfs_server *old, return 1; } -static int nfs_compare_super(struct super_block *sb, void *data) +static int nfs_compare_super(struct super_block *sb, struct fs_context *fc) { - struct nfs_sb_mountdata *sb_mntdata = data; - struct nfs_server *server = sb_mntdata->server, *old = NFS_SB(sb); - int mntflags = sb_mntdata->mntflags; + struct nfs_server *server = fc->s_fs_info, *old = NFS_SB(sb); if (!nfs_compare_super_address(old, server)) return 0; @@ -2556,13 +1122,12 @@ static int nfs_compare_super(struct super_block *sb, void *data) return 0; if (!nfs_compare_userns(old, server)) return 0; - return nfs_compare_mount_options(sb, server, mntflags); + return nfs_compare_mount_options(sb, server, fc); } #ifdef CONFIG_NFS_FSCACHE static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_parsed_mount_data *parsed, - struct nfs_clone_mount *cloned) + struct nfs_fs_context *ctx) { struct nfs_server *nfss = NFS_SB(sb); char *uniq = NULL; @@ -2571,80 +1136,36 @@ static void nfs_get_cache_cookie(struct super_block *sb, nfss->fscache_key = NULL; nfss->fscache = NULL; - if (parsed) { - if (!(parsed->options & NFS_OPTION_FSCACHE)) - return; - if (parsed->fscache_uniq) { - uniq = parsed->fscache_uniq; - ulen = strlen(parsed->fscache_uniq); - } - } else if (cloned) { - struct nfs_server *mnt_s = NFS_SB(cloned->sb); + if (!ctx) + return; + + if (ctx->clone_data.sb) { + struct nfs_server *mnt_s = NFS_SB(ctx->clone_data.sb); if (!(mnt_s->options & NFS_OPTION_FSCACHE)) return; if (mnt_s->fscache_key) { uniq = mnt_s->fscache_key->key.uniquifier; ulen = mnt_s->fscache_key->key.uniq_len; } - } else + } else { + if (!(ctx->options & NFS_OPTION_FSCACHE)) + return; + if (ctx->fscache_uniq) { + uniq = ctx->fscache_uniq; + ulen = strlen(ctx->fscache_uniq); + } return; + } nfs_fscache_get_super_cookie(sb, uniq, ulen); } #else static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_parsed_mount_data *parsed, - struct nfs_clone_mount *cloned) + struct nfs_fs_context *ctx) { } #endif -int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, - struct nfs_mount_info *mount_info) -{ - int error; - unsigned long kflags = 0, kflags_out = 0; - if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) - kflags |= SECURITY_LSM_NATIVE_LABELS; - - error = security_sb_set_mnt_opts(s, mount_info->parsed->lsm_opts, - kflags, &kflags_out); - if (error) - goto err; - - if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL && - !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) - NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL; -err: - return error; -} -EXPORT_SYMBOL_GPL(nfs_set_sb_security); - -int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, - struct nfs_mount_info *mount_info) -{ - int error; - unsigned long kflags = 0, kflags_out = 0; - - /* clone any lsm security options from the parent to the new sb */ - if (d_inode(mntroot)->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) - return -ESTALE; - - if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) - kflags |= SECURITY_LSM_NATIVE_LABELS; - - error = security_sb_clone_mnt_opts(mount_info->cloned->sb, s, kflags, - &kflags_out); - if (error) - return error; - - if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL && - !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) - NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL; - return 0; -} -EXPORT_SYMBOL_GPL(nfs_clone_sb_security); - static void nfs_set_readahead(struct backing_dev_info *bdi, unsigned long iomax_pages) { @@ -2652,35 +1173,40 @@ static void nfs_set_readahead(struct backing_dev_info *bdi, bdi->io_pages = iomax_pages; } -struct dentry *nfs_fs_mount_common(struct nfs_server *server, - int flags, const char *dev_name, - struct nfs_mount_info *mount_info, - struct nfs_subversion *nfs_mod) +int nfs_get_tree_common(struct fs_context *fc) { + struct nfs_fs_context *ctx = nfs_fc2context(fc); struct super_block *s; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - int (*compare_super)(struct super_block *, void *) = nfs_compare_super; - struct nfs_sb_mountdata sb_mntdata = { - .mntflags = flags, - .server = server, - }; + int (*compare_super)(struct super_block *, struct fs_context *) = nfs_compare_super; + struct nfs_server *server = ctx->server; + unsigned long kflags = 0, kflags_out = 0; int error; + ctx->server = NULL; + if (IS_ERR(server)) + return PTR_ERR(server); + if (server->flags & NFS_MOUNT_UNSHARED) compare_super = NULL; /* -o noac implies -o sync */ if (server->flags & NFS_MOUNT_NOAC) - sb_mntdata.mntflags |= SB_SYNCHRONOUS; + fc->sb_flags |= SB_SYNCHRONOUS; - if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL) - if (mount_info->cloned->sb->s_flags & SB_SYNCHRONOUS) - sb_mntdata.mntflags |= SB_SYNCHRONOUS; + if (ctx->clone_data.sb) + if (ctx->clone_data.sb->s_flags & SB_SYNCHRONOUS) + fc->sb_flags |= SB_SYNCHRONOUS; + + if (server->caps & NFS_CAP_SECURITY_LABEL) + fc->lsm_flags |= SECURITY_LSM_NATIVE_LABELS; /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata); + fc->s_fs_info = server; + s = sget_fc(fc, compare_super, nfs_set_super); + fc->s_fs_info = NULL; if (IS_ERR(s)) { - mntroot = ERR_CAST(s); + error = PTR_ERR(s); + nfs_errorf(fc, "NFS: Couldn't get superblock"); goto out_err_nosb; } @@ -2690,88 +1216,66 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, } else { error = super_setup_bdi_name(s, "%u:%u", MAJOR(server->s_dev), MINOR(server->s_dev)); - if (error) { - mntroot = ERR_PTR(error); + if (error) goto error_splat_super; - } nfs_set_readahead(s->s_bdi, server->rpages); server->super = s; } if (!s->s_root) { + unsigned bsize = ctx->clone_data.inherited_bsize; /* initial superblock/root creation */ - mount_info->fill_super(s, mount_info); - nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); - if (!(server->flags & NFS_MOUNT_UNSHARED)) - s->s_iflags |= SB_I_MULTIROOT; + nfs_fill_super(s, ctx); + if (bsize) { + s->s_blocksize_bits = bsize; + s->s_blocksize = 1U << bsize; + } + nfs_get_cache_cookie(s, ctx); } - mntroot = nfs_get_root(s, mount_info->mntfh, dev_name); - if (IS_ERR(mntroot)) + error = nfs_get_root(s, fc); + if (error < 0) { + nfs_errorf(fc, "NFS: Couldn't get root dentry"); goto error_splat_super; + } - error = mount_info->set_security(s, mntroot, mount_info); + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) + kflags |= SECURITY_LSM_NATIVE_LABELS; + if (ctx->clone_data.sb) { + if (d_inode(fc->root)->i_fop != &nfs_dir_operations) { + error = -ESTALE; + goto error_splat_root; + } + /* clone any lsm security options from the parent to the new sb */ + error = security_sb_clone_mnt_opts(ctx->clone_data.sb, s, kflags, + &kflags_out); + } else { + error = security_sb_set_mnt_opts(s, fc->security, + kflags, &kflags_out); + } if (error) goto error_splat_root; + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL && + !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) + NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL; s->s_flags |= SB_ACTIVE; + error = 0; out: - return mntroot; + return error; out_err_nosb: nfs_free_server(server); goto out; error_splat_root: - dput(mntroot); - mntroot = ERR_PTR(error); + dput(fc->root); + fc->root = NULL; error_splat_super: deactivate_locked_super(s); goto out; } -EXPORT_SYMBOL_GPL(nfs_fs_mount_common); - -struct dentry *nfs_fs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) -{ - struct nfs_mount_info mount_info = { - .fill_super = nfs_fill_super, - .set_security = nfs_set_sb_security, - }; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - struct nfs_subversion *nfs_mod; - int error; - - mount_info.parsed = nfs_alloc_parsed_mount_data(); - mount_info.mntfh = nfs_alloc_fhandle(); - if (mount_info.parsed == NULL || mount_info.mntfh == NULL) - goto out; - - /* Validate the mount data */ - error = nfs_validate_mount_data(fs_type, raw_data, mount_info.parsed, mount_info.mntfh, dev_name); - if (error == NFS_TEXT_DATA) - error = nfs_validate_text_mount_data(raw_data, mount_info.parsed, dev_name); - if (error < 0) { - mntroot = ERR_PTR(error); - goto out; - } - - nfs_mod = get_nfs_version(mount_info.parsed->version); - if (IS_ERR(nfs_mod)) { - mntroot = ERR_CAST(nfs_mod); - goto out; - } - - mntroot = nfs_mod->rpc_ops->try_mount(flags, dev_name, &mount_info, nfs_mod); - - put_nfs_version(nfs_mod); -out: - nfs_free_parsed_mount_data(mount_info.parsed); - nfs_free_fhandle(mount_info.mntfh); - return mntroot; -} -EXPORT_SYMBOL_GPL(nfs_fs_mount); /* * Destroy an NFS2/3 superblock @@ -2790,150 +1294,8 @@ void nfs_kill_super(struct super_block *s) } EXPORT_SYMBOL_GPL(nfs_kill_super); -/* - * Clone an NFS2/3/4 server record on xdev traversal (FSID-change) - */ -static struct dentry * -nfs_xdev_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) -{ - struct nfs_clone_mount *data = raw_data; - struct nfs_mount_info mount_info = { - .fill_super = nfs_clone_super, - .set_security = nfs_clone_sb_security, - .cloned = data, - }; - struct nfs_server *server; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod; - - dprintk("--> nfs_xdev_mount()\n"); - - mount_info.mntfh = mount_info.cloned->fh; - - /* create a new volume representation */ - server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); - - if (IS_ERR(server)) - mntroot = ERR_CAST(server); - else - mntroot = nfs_fs_mount_common(server, flags, - dev_name, &mount_info, nfs_mod); - - dprintk("<-- nfs_xdev_mount() = %ld\n", - IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L); - return mntroot; -} - #if IS_ENABLED(CONFIG_NFS_V4) -static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) -{ - args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3| - NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL); -} - -/* - * Validate NFSv4 mount options - */ -static int nfs4_validate_mount_data(void *options, - struct nfs_parsed_mount_data *args, - const char *dev_name) -{ - struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; - struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; - char *c; - - if (data == NULL) - goto out_no_data; - - args->version = 4; - - switch (data->version) { - case 1: - if (data->host_addrlen > sizeof(args->nfs_server.address)) - goto out_no_address; - if (data->host_addrlen == 0) - goto out_no_address; - args->nfs_server.addrlen = data->host_addrlen; - if (copy_from_user(sap, data->host_addr, data->host_addrlen)) - return -EFAULT; - if (!nfs_verify_server_address(sap)) - goto out_no_address; - args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); - - if (data->auth_flavourlen) { - rpc_authflavor_t pseudoflavor; - if (data->auth_flavourlen > 1) - goto out_inval_auth; - if (copy_from_user(&pseudoflavor, - data->auth_flavours, - sizeof(pseudoflavor))) - return -EFAULT; - args->selected_flavor = pseudoflavor; - } else - args->selected_flavor = RPC_AUTH_UNIX; - - c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); - if (IS_ERR(c)) - return PTR_ERR(c); - args->nfs_server.hostname = c; - - c = strndup_user(data->mnt_path.data, NFS4_MAXPATHLEN); - if (IS_ERR(c)) - return PTR_ERR(c); - args->nfs_server.export_path = c; - dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", c); - - c = strndup_user(data->client_addr.data, 16); - if (IS_ERR(c)) - return PTR_ERR(c); - args->client_address = c; - - /* - * Translate to nfs_parsed_mount_data, which nfs4_fill_super - * can deal with. - */ - - args->flags = data->flags & NFS4_MOUNT_FLAGMASK; - args->rsize = data->rsize; - args->wsize = data->wsize; - args->timeo = data->timeo; - args->retrans = data->retrans; - args->acregmin = data->acregmin; - args->acregmax = data->acregmax; - args->acdirmin = data->acdirmin; - args->acdirmax = data->acdirmax; - args->nfs_server.protocol = data->proto; - nfs_validate_transport_protocol(args); - if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP) - goto out_invalid_transport_udp; - - break; - default: - return NFS_TEXT_DATA; - } - - return 0; - -out_no_data: - dfprintk(MOUNT, "NFS4: mount program didn't pass any mount data\n"); - return -EINVAL; - -out_inval_auth: - dfprintk(MOUNT, "NFS4: Invalid number of RPC auth flavours %d\n", - data->auth_flavourlen); - return -EINVAL; - -out_no_address: - dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n"); - return -EINVAL; - -out_invalid_transport_udp: - dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n"); - return -EINVAL; -} - /* * NFS v4 module parameters need to stay in the * NFS client for backwards compatibility diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 52cab65f91cf..c478b772cc49 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -243,13 +243,24 @@ out: /* A writeback failed: mark the page as bad, and invalidate the page cache */ static void nfs_set_pageerror(struct address_space *mapping) { + struct inode *inode = mapping->host; + nfs_zap_mapping(mapping->host, mapping); + /* Force file size revalidation */ + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED | + NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_SIZE; + spin_unlock(&inode->i_lock); } static void nfs_mapping_set_error(struct page *page, int error) { + struct address_space *mapping = page_file_mapping(page); + SetPageError(page); - mapping_set_error(page_file_mapping(page), error); + mapping_set_error(mapping, error); + nfs_set_pageerror(mapping); } /* @@ -592,7 +603,7 @@ release_request: static void nfs_write_error(struct nfs_page *req, int error) { - nfs_set_pageerror(page_file_mapping(req->wb_page)); + trace_nfs_write_error(req, error); nfs_mapping_set_error(req->wb_page, error); nfs_inode_remove_request(req); nfs_end_page_writeback(req); @@ -998,7 +1009,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - nfs_set_pageerror(page_file_mapping(req->wb_page)); + trace_nfs_comp_error(req, hdr->error); nfs_mapping_set_error(req->wb_page, hdr->error); goto remove_req; } @@ -1403,8 +1414,7 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, task_setup_data->priority = priority; rpc_ops->write_setup(hdr, msg, &task_setup_data->rpc_client); - trace_nfs_initiate_write(hdr->inode, hdr->io_start, hdr->good_bytes, - hdr->args.stable); + trace_nfs_initiate_write(hdr); } /* If a nfs_flush_* function fails, it should remove reqs from @head and @@ -1568,8 +1578,7 @@ static int nfs_writeback_done(struct rpc_task *task, return status; nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); - trace_nfs_writeback_done(inode, task->tk_status, - hdr->args.offset, hdr->res.verf); + trace_nfs_writeback_done(task, hdr); if (hdr->res.verf->committed < hdr->args.stable && task->tk_status >= 0) { @@ -1649,6 +1658,8 @@ static void nfs_writeback_result(struct rpc_task *task, */ argp->stable = NFS_FILE_SYNC; } + resp->count = 0; + resp->verf->committed = 0; rpc_restart_call_prepare(task); } } @@ -1824,11 +1835,12 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) /* Call the NFS version-specific code */ NFS_PROTO(data->inode)->commit_done(task, data); - trace_nfs_commit_done(data); + trace_nfs_commit_done(task, data); } static void nfs_commit_release_pages(struct nfs_commit_data *data) { + const struct nfs_writeverf *verf = data->res.verf; struct nfs_page *req; int status = data->task.tk_status; struct nfs_commit_info cinfo; @@ -1847,6 +1859,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) (long long)req_offset(req)); if (status < 0) { if (req->wb_page) { + trace_nfs_commit_error(req, status); nfs_mapping_set_error(req->wb_page, status); nfs_inode_remove_request(req); } @@ -1856,7 +1869,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* Okay, COMMIT succeeded, apparently. Check the verifier * returned by the server against all stored verfs. */ - if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) { + if (verf->committed > NFS_UNSTABLE && + !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier)) { /* We have a match */ if (req->wb_page) nfs_inode_remove_request(req); diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index f2f81561ebb6..f368f3215f88 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -134,6 +134,16 @@ config NFSD_FLEXFILELAYOUT If unsure, say N. +config NFSD_V4_2_INTER_SSC + bool "NFSv4.2 inter server to server COPY" + depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2 + help + This option enables support for NFSv4.2 inter server to + server copy where the destination server calls the NFSv4.2 + client to read the data to copy from the source server. + + If unsure, say N. + config NFSD_V4_SECURITY_LABEL bool "Provide Security Label support for NFSv4 server" depends on NFSD_V4 && SECURITY diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 32a9bf22ac08..22e77ede9f14 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -27,7 +27,6 @@ #define NFSD_FILE_HASH_SIZE (1 << NFSD_FILE_HASH_BITS) #define NFSD_LAUNDRETTE_DELAY (2 * HZ) -#define NFSD_FILE_LRU_RESCAN (0) #define NFSD_FILE_SHUTDOWN (1) #define NFSD_FILE_LRU_THRESHOLD (4096UL) #define NFSD_FILE_LRU_LIMIT (NFSD_FILE_LRU_THRESHOLD << 2) @@ -44,6 +43,17 @@ struct nfsd_fcache_bucket { static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); +struct nfsd_fcache_disposal { + struct list_head list; + struct work_struct work; + struct net *net; + spinlock_t lock; + struct list_head freeme; + struct rcu_head rcu; +}; + +static struct workqueue_struct *nfsd_filecache_wq __read_mostly; + static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; static struct nfsd_fcache_bucket *nfsd_file_hashtbl; @@ -52,32 +62,21 @@ static long nfsd_file_lru_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static atomic_long_t nfsd_filecache_count; static struct delayed_work nfsd_filecache_laundrette; +static DEFINE_SPINLOCK(laundrette_lock); +static LIST_HEAD(laundrettes); -enum nfsd_file_laundrette_ctl { - NFSD_FILE_LAUNDRETTE_NOFLUSH = 0, - NFSD_FILE_LAUNDRETTE_MAY_FLUSH -}; +static void nfsd_file_gc(void); static void -nfsd_file_schedule_laundrette(enum nfsd_file_laundrette_ctl ctl) +nfsd_file_schedule_laundrette(void) { long count = atomic_long_read(&nfsd_filecache_count); if (count == 0 || test_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags)) return; - /* Be more aggressive about scanning if over the threshold */ - if (count > NFSD_FILE_LRU_THRESHOLD) - mod_delayed_work(system_wq, &nfsd_filecache_laundrette, 0); - else - schedule_delayed_work(&nfsd_filecache_laundrette, NFSD_LAUNDRETTE_DELAY); - - if (ctl == NFSD_FILE_LAUNDRETTE_NOFLUSH) - return; - - /* ...and don't delay flushing if we're out of control */ - if (count >= NFSD_FILE_LRU_LIMIT) - flush_delayed_work(&nfsd_filecache_laundrette); + queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + NFSD_LAUNDRETTE_DELAY); } static void @@ -101,7 +100,7 @@ nfsd_file_mark_free(struct fsnotify_mark *mark) static struct nfsd_file_mark * nfsd_file_mark_get(struct nfsd_file_mark *nfm) { - if (!atomic_inc_not_zero(&nfm->nfm_ref)) + if (!refcount_inc_not_zero(&nfm->nfm_ref)) return NULL; return nfm; } @@ -109,8 +108,7 @@ nfsd_file_mark_get(struct nfsd_file_mark *nfm) static void nfsd_file_mark_put(struct nfsd_file_mark *nfm) { - if (atomic_dec_and_test(&nfm->nfm_ref)) { - + if (refcount_dec_and_test(&nfm->nfm_ref)) { fsnotify_destroy_mark(&nfm->nfm_mark, nfsd_file_fsnotify_group); fsnotify_put_mark(&nfm->nfm_mark); } @@ -133,9 +131,13 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) struct nfsd_file_mark, nfm_mark)); mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); - fsnotify_put_mark(mark); - if (likely(nfm)) + if (nfm) { + fsnotify_put_mark(mark); break; + } + /* Avoid soft lockup race with nfsd_file_mark_put() */ + fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group); + fsnotify_put_mark(mark); } else mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); @@ -145,7 +147,7 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) return NULL; fsnotify_init_mark(&new->nfm_mark, nfsd_file_fsnotify_group); new->nfm_mark.mask = FS_ATTRIB|FS_DELETE_SELF; - atomic_set(&new->nfm_ref, 1); + refcount_set(&new->nfm_ref, 1); err = fsnotify_add_inode_mark(&new->nfm_mark, inode, 0); @@ -183,7 +185,7 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, nf->nf_flags = 0; nf->nf_inode = inode; nf->nf_hashval = hashval; - atomic_set(&nf->nf_ref, 1); + refcount_set(&nf->nf_ref, 1); nf->nf_may = may & NFSD_FILE_MAY_MASK; if (may & NFSD_MAY_NOT_BREAK_LEASE) { if (may & NFSD_MAY_WRITE) @@ -192,6 +194,7 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, __set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags); } nf->nf_mark = NULL; + init_rwsem(&nf->nf_rwsem); trace_nfsd_file_alloc(nf); } return nf; @@ -238,13 +241,6 @@ nfsd_file_check_write_error(struct nfsd_file *nf) return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err)); } -static bool -nfsd_file_in_use(struct nfsd_file *nf) -{ - return nfsd_file_check_writeback(nf) || - nfsd_file_check_write_error(nf); -} - static void nfsd_file_do_unhash(struct nfsd_file *nf) { @@ -256,8 +252,6 @@ nfsd_file_do_unhash(struct nfsd_file *nf) nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id)); --nfsd_file_hashtbl[nf->nf_hashval].nfb_count; hlist_del_rcu(&nf->nf_node); - if (!list_empty(&nf->nf_lru)) - list_lru_del(&nfsd_file_lru, &nf->nf_lru); atomic_long_dec(&nfsd_filecache_count); } @@ -266,6 +260,8 @@ nfsd_file_unhash(struct nfsd_file *nf) { if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { nfsd_file_do_unhash(nf); + if (!list_empty(&nf->nf_lru)) + list_lru_del(&nfsd_file_lru, &nf->nf_lru); return true; } return false; @@ -283,42 +279,48 @@ nfsd_file_unhash_and_release_locked(struct nfsd_file *nf, struct list_head *disp if (!nfsd_file_unhash(nf)) return false; /* keep final reference for nfsd_file_lru_dispose */ - if (atomic_add_unless(&nf->nf_ref, -1, 1)) + if (refcount_dec_not_one(&nf->nf_ref)) return true; list_add(&nf->nf_lru, dispose); return true; } -static int +static void nfsd_file_put_noref(struct nfsd_file *nf) { - int count; trace_nfsd_file_put(nf); - count = atomic_dec_return(&nf->nf_ref); - if (!count) { + if (refcount_dec_and_test(&nf->nf_ref)) { WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags)); nfsd_file_free(nf); } - return count; } void nfsd_file_put(struct nfsd_file *nf) { - bool is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - bool unused = !nfsd_file_in_use(nf); + bool is_hashed; set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (nfsd_file_put_noref(nf) == 1 && is_hashed && unused) - nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_MAY_FLUSH); + if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { + nfsd_file_put_noref(nf); + return; + } + + filemap_flush(nf->nf_file->f_mapping); + is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; + nfsd_file_put_noref(nf); + if (is_hashed) + nfsd_file_schedule_laundrette(); + if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) + nfsd_file_gc(); } struct nfsd_file * nfsd_file_get(struct nfsd_file *nf) { - if (likely(atomic_inc_not_zero(&nf->nf_ref))) + if (likely(refcount_inc_not_zero(&nf->nf_ref))) return nf; return NULL; } @@ -344,7 +346,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); - if (!atomic_dec_and_test(&nf->nf_ref)) + if (!refcount_dec_and_test(&nf->nf_ref)) continue; if (nfsd_file_free(nf)) flush = true; @@ -353,6 +355,58 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) flush_delayed_fput(); } +static void +nfsd_file_list_remove_disposal(struct list_head *dst, + struct nfsd_fcache_disposal *l) +{ + spin_lock(&l->lock); + list_splice_init(&l->freeme, dst); + spin_unlock(&l->lock); +} + +static void +nfsd_file_list_add_disposal(struct list_head *files, struct net *net) +{ + struct nfsd_fcache_disposal *l; + + rcu_read_lock(); + list_for_each_entry_rcu(l, &laundrettes, list) { + if (l->net == net) { + spin_lock(&l->lock); + list_splice_tail_init(files, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); + break; + } + } + rcu_read_unlock(); +} + +static void +nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, + struct net *net) +{ + struct nfsd_file *nf, *tmp; + + list_for_each_entry_safe(nf, tmp, src, nf_lru) { + if (nf->nf_net == net) + list_move_tail(&nf->nf_lru, dst); + } +} + +static void +nfsd_file_dispose_list_delayed(struct list_head *dispose) +{ + LIST_HEAD(list); + struct nfsd_file *nf; + + while(!list_empty(dispose)) { + nf = list_first_entry(dispose, struct nfsd_file, nf_lru); + nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); + nfsd_file_list_add_disposal(&list, nf->nf_net); + } +} + /* * Note this can deadlock with nfsd_file_cache_purge. */ @@ -375,7 +429,7 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, * counter. Here we check the counter and then test and clear the flag. * That order is deliberate to ensure that we can do this locklessly. */ - if (atomic_read(&nf->nf_ref) > 1) + if (refcount_read(&nf->nf_ref) > 1) goto out_skip; /* @@ -386,31 +440,51 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, goto out_skip; if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) - goto out_rescan; + goto out_skip; if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) goto out_skip; list_lru_isolate_move(lru, &nf->nf_lru, head); return LRU_REMOVED; -out_rescan: - set_bit(NFSD_FILE_LRU_RESCAN, &nfsd_file_lru_flags); out_skip: return LRU_SKIP; } -static void -nfsd_file_lru_dispose(struct list_head *head) +static unsigned long +nfsd_file_lru_walk_list(struct shrink_control *sc) { - while(!list_empty(head)) { - struct nfsd_file *nf = list_first_entry(head, - struct nfsd_file, nf_lru); - list_del_init(&nf->nf_lru); + LIST_HEAD(head); + struct nfsd_file *nf; + unsigned long ret; + + if (sc) + ret = list_lru_shrink_walk(&nfsd_file_lru, sc, + nfsd_file_lru_cb, &head); + else + ret = list_lru_walk(&nfsd_file_lru, + nfsd_file_lru_cb, + &head, LONG_MAX); + list_for_each_entry(nf, &head, nf_lru) { spin_lock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); nfsd_file_do_unhash(nf); spin_unlock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - nfsd_file_put_noref(nf); } + nfsd_file_dispose_list_delayed(&head); + return ret; +} + +static void +nfsd_file_gc(void) +{ + nfsd_file_lru_walk_list(NULL); +} + +static void +nfsd_file_gc_worker(struct work_struct *work) +{ + nfsd_file_gc(); + nfsd_file_schedule_laundrette(); } static unsigned long @@ -422,12 +496,7 @@ nfsd_file_lru_count(struct shrinker *s, struct shrink_control *sc) static unsigned long nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) { - LIST_HEAD(head); - unsigned long ret; - - ret = list_lru_shrink_walk(&nfsd_file_lru, sc, nfsd_file_lru_cb, &head); - nfsd_file_lru_dispose(&head); - return ret; + return nfsd_file_lru_walk_list(sc); } static struct shrinker nfsd_file_shrinker = { @@ -489,7 +558,7 @@ nfsd_file_close_inode(struct inode *inode) __nfsd_file_close_inode(inode, hashval, &dispose); trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose)); - nfsd_file_dispose_list(&dispose); + nfsd_file_dispose_list_delayed(&dispose); } /** @@ -505,16 +574,11 @@ static void nfsd_file_delayed_close(struct work_struct *work) { LIST_HEAD(head); + struct nfsd_fcache_disposal *l = container_of(work, + struct nfsd_fcache_disposal, work); - list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, &head, LONG_MAX); - - if (test_and_clear_bit(NFSD_FILE_LRU_RESCAN, &nfsd_file_lru_flags)) - nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_NOFLUSH); - - if (!list_empty(&head)) { - nfsd_file_lru_dispose(&head); - flush_delayed_fput(); - } + nfsd_file_list_remove_disposal(&head, l); + nfsd_file_dispose_list(&head); } static int @@ -575,6 +639,10 @@ nfsd_file_cache_init(void) if (nfsd_file_hashtbl) return 0; + nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); + if (!nfsd_filecache_wq) + goto out; + nfsd_file_hashtbl = kcalloc(NFSD_FILE_HASH_SIZE, sizeof(*nfsd_file_hashtbl), GFP_KERNEL); if (!nfsd_file_hashtbl) { @@ -628,7 +696,7 @@ nfsd_file_cache_init(void) spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock); } - INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_delayed_close); + INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: return ret; out_notifier: @@ -644,6 +712,8 @@ out_err: nfsd_file_mark_slab = NULL; kfree(nfsd_file_hashtbl); nfsd_file_hashtbl = NULL; + destroy_workqueue(nfsd_filecache_wq); + nfsd_filecache_wq = NULL; goto out; } @@ -682,6 +752,88 @@ nfsd_file_cache_purge(struct net *net) } } +static struct nfsd_fcache_disposal * +nfsd_alloc_fcache_disposal(struct net *net) +{ + struct nfsd_fcache_disposal *l; + + l = kmalloc(sizeof(*l), GFP_KERNEL); + if (!l) + return NULL; + INIT_WORK(&l->work, nfsd_file_delayed_close); + l->net = net; + spin_lock_init(&l->lock); + INIT_LIST_HEAD(&l->freeme); + return l; +} + +static void +nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) +{ + rcu_assign_pointer(l->net, NULL); + cancel_work_sync(&l->work); + nfsd_file_dispose_list(&l->freeme); + kfree_rcu(l, rcu); +} + +static void +nfsd_add_fcache_disposal(struct nfsd_fcache_disposal *l) +{ + spin_lock(&laundrette_lock); + list_add_tail_rcu(&l->list, &laundrettes); + spin_unlock(&laundrette_lock); +} + +static void +nfsd_del_fcache_disposal(struct nfsd_fcache_disposal *l) +{ + spin_lock(&laundrette_lock); + list_del_rcu(&l->list); + spin_unlock(&laundrette_lock); +} + +static int +nfsd_alloc_fcache_disposal_net(struct net *net) +{ + struct nfsd_fcache_disposal *l; + + l = nfsd_alloc_fcache_disposal(net); + if (!l) + return -ENOMEM; + nfsd_add_fcache_disposal(l); + return 0; +} + +static void +nfsd_free_fcache_disposal_net(struct net *net) +{ + struct nfsd_fcache_disposal *l; + + rcu_read_lock(); + list_for_each_entry_rcu(l, &laundrettes, list) { + if (l->net != net) + continue; + nfsd_del_fcache_disposal(l); + rcu_read_unlock(); + nfsd_free_fcache_disposal(l); + return; + } + rcu_read_unlock(); +} + +int +nfsd_file_cache_start_net(struct net *net) +{ + return nfsd_alloc_fcache_disposal_net(net); +} + +void +nfsd_file_cache_shutdown_net(struct net *net) +{ + nfsd_file_cache_purge(net); + nfsd_free_fcache_disposal_net(net); +} + void nfsd_file_cache_shutdown(void) { @@ -706,6 +858,8 @@ nfsd_file_cache_shutdown(void) nfsd_file_mark_slab = NULL; kfree(nfsd_file_hashtbl); nfsd_file_hashtbl = NULL; + destroy_workqueue(nfsd_filecache_wq); + nfsd_filecache_wq = NULL; } static bool @@ -789,6 +943,7 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, *new; struct inode *inode; unsigned int hashval; + bool retry = true; /* FIXME: skip this if fh_dentry is already set? */ status = fh_verify(rqstp, fhp, S_IFREG, @@ -824,6 +979,11 @@ wait_for_construction: /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { + if (!retry) { + status = nfserr_jukebox; + goto out; + } + retry = false; nfsd_file_put_noref(nf); goto retry; } @@ -858,7 +1018,7 @@ out: open_file: nf = new; /* Take reference for the hashtable */ - atomic_inc(&nf->nf_ref); + refcount_inc(&nf->nf_ref); __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); list_lru_add(&nfsd_file_lru, &nf->nf_lru); @@ -867,7 +1027,8 @@ open_file: nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount, nfsd_file_hashtbl[hashval].nfb_count); spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - atomic_long_inc(&nfsd_filecache_count); + if (atomic_long_inc_return(&nfsd_filecache_count) >= NFSD_FILE_LRU_THRESHOLD) + nfsd_file_gc(); nf->nf_mark = nfsd_file_mark_find_or_create(nf); if (nf->nf_mark) diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 851d9abf54c2..7872df5a0fe3 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -19,7 +19,7 @@ */ struct nfsd_file_mark { struct fsnotify_mark nfm_mark; - atomic_t nfm_ref; + refcount_t nfm_ref; }; /* @@ -43,14 +43,17 @@ struct nfsd_file { unsigned long nf_flags; struct inode *nf_inode; unsigned int nf_hashval; - atomic_t nf_ref; + refcount_t nf_ref; unsigned char nf_may; struct nfsd_file_mark *nf_mark; + struct rw_semaphore nf_rwsem; }; int nfsd_file_cache_init(void); void nfsd_file_cache_purge(struct net *); void nfsd_file_cache_shutdown(void); +int nfsd_file_cache_start_net(struct net *net); +void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 9a4ef815fb8c..2baf32311e00 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -40,7 +40,7 @@ struct nfsd_net { struct lock_manager nfsd4_manager; bool grace_ended; - time_t boot_time; + time64_t boot_time; /* internal mount of the "nfsd" pseudofilesystem: */ struct vfsmount *nfsd_mnt; @@ -92,8 +92,8 @@ struct nfsd_net { bool in_grace; const struct nfsd4_client_tracking_ops *client_tracking_ops; - time_t nfsd4_lease; - time_t nfsd4_grace; + time64_t nfsd4_lease; + time64_t nfsd4_grace; bool somebody_reclaimed; bool track_reclaim_completes; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index cea68d8411ac..288bc76b4574 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -203,7 +203,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp) RETURN_STATUS(nfserr_io); nfserr = nfsd_write(rqstp, &resp->fh, argp->offset, rqstp->rq_vec, nvecs, &cnt, - resp->committed); + resp->committed, resp->verf); resp->count = cnt; RETURN_STATUS(nfserr); } @@ -683,7 +683,8 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) RETURN_STATUS(nfserr_inval); fh_copy(&resp->fh, &argp->fh); - nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count); + nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count, + resp->verf); RETURN_STATUS(nfserr); } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 195ab7a0fc89..aae514d40b64 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -32,14 +32,14 @@ static u32 nfs3_ftypes[] = { * XDR functions for basic NFS types */ static __be32 * -encode_time3(__be32 *p, struct timespec *time) +encode_time3(__be32 *p, struct timespec64 *time) { *p++ = htonl((u32) time->tv_sec); *p++ = htonl(time->tv_nsec); return p; } static __be32 * -decode_time3(__be32 *p, struct timespec *time) +decode_time3(__be32 *p, struct timespec64 *time) { time->tv_sec = ntohl(*p++); time->tv_nsec = ntohl(*p++); @@ -167,7 +167,6 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat) { struct user_namespace *userns = nfsd_user_namespace(rqstp); - struct timespec ts; *p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]); *p++ = htonl((u32) (stat->mode & S_IALLUGO)); *p++ = htonl((u32) stat->nlink); @@ -183,12 +182,9 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, *p++ = htonl((u32) MINOR(stat->rdev)); p = encode_fsid(p, fhp); p = xdr_encode_hyper(p, stat->ino); - ts = timespec64_to_timespec(stat->atime); - p = encode_time3(p, &ts); - ts = timespec64_to_timespec(stat->mtime); - p = encode_time3(p, &ts); - ts = timespec64_to_timespec(stat->ctime); - p = encode_time3(p, &ts); + p = encode_time3(p, &stat->atime); + p = encode_time3(p, &stat->mtime); + p = encode_time3(p, &stat->ctime); return p; } @@ -277,8 +273,8 @@ void fill_pre_wcc(struct svc_fh *fhp) stat.size = inode->i_size; } - fhp->fh_pre_mtime = timespec64_to_timespec(stat.mtime); - fhp->fh_pre_ctime = timespec64_to_timespec(stat.ctime); + fhp->fh_pre_mtime = stat.mtime; + fhp->fh_pre_ctime = stat.ctime; fhp->fh_pre_size = stat.size; fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); fhp->fh_pre_saved = true; @@ -330,7 +326,7 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); if ((args->check_guard = ntohl(*p++)) != 0) { - struct timespec time; + struct timespec64 time; p = decode_time3(p, &time); args->guardtime = time.tv_sec; } @@ -751,17 +747,13 @@ int nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_writeres *resp = rqstp->rq_resp; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - __be32 verf[2]; p = encode_wcc_data(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->count); *p++ = htonl(resp->committed); - /* unique identifier, y2038 overflow can be ignored */ - nfsd_copy_boot_verifier(verf, nn); - *p++ = verf[0]; - *p++ = verf[1]; + *p++ = resp->verf[0]; + *p++ = resp->verf[1]; } return xdr_ressize_check(rqstp, p); } @@ -1125,16 +1117,12 @@ int nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_commitres *resp = rqstp->rq_resp; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - __be32 verf[2]; p = encode_wcc_data(rqstp, p, &resp->fh); /* Write verifier */ if (resp->status == 0) { - /* unique identifier, y2038 overflow can be ignored */ - nfsd_copy_boot_verifier(verf, nn); - *p++ = verf[0]; - *p++ = verf[1]; + *p++ = resp->verf[0]; + *p++ = resp->verf[1]; } return xdr_ressize_check(rqstp, p); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 24534db87e86..c3b11a715082 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -823,7 +823,16 @@ static const struct rpc_program cb_program = { static int max_cb_time(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - return max(nn->nfsd4_lease/10, (time_t)1) * HZ; + + /* + * nfsd4_lease is set to at most one hour in __nfsd4_write_time, + * so we can use 32-bit math on it. Warn if that assumption + * ever stops being true. + */ + if (WARN_ON_ONCE(nn->nfsd4_lease > 3600)) + return 360 * HZ; + + return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ; } static struct workqueue_struct *callback_wq; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 2681c70283ce..e12409eca7cc 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -675,7 +675,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) /* Client gets 2 lease periods to return it */ cutoff = ktime_add_ns(task->tk_start, - nn->nfsd4_lease * NSEC_PER_SEC * 2); + (u64)nn->nfsd4_lease * NSEC_PER_SEC * 2); if (ktime_before(now, cutoff)) { rpc_delay(task, HZ/100); /* 10 mili-seconds */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4798667af647..0e75f7fb5fec 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -37,6 +37,7 @@ #include <linux/falloc.h> #include <linux/slab.h> #include <linux/kthread.h> +#include <linux/sunrpc/addr.h> #include "idmap.h" #include "cache.h" @@ -232,7 +233,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru if (!*resfh) return nfserr_jukebox; fh_init(*resfh, NFS4_FHSIZE); - open->op_truncate = 0; + open->op_truncate = false; if (open->op_create) { /* FIXME: check session persistence and pnfs flags. @@ -365,7 +366,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL) return nfserr_inval; - open->op_created = 0; + open->op_created = false; /* * RFC5661 18.51.3 * Before RECLAIM_COMPLETE done, server should deny new lock @@ -503,12 +504,20 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_putfh *putfh = &u->putfh; + __be32 ret; fh_put(&cstate->current_fh); cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, putfh->pf_fhlen); - return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS); + ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS); +#ifdef CONFIG_NFSD_V4_2_INTER_SSC + if (ret == nfserr_stale && putfh->no_verify) { + SET_FH_FLAG(&cstate->current_fh, NFSD4_FH_FOREIGN); + ret = 0; + } +#endif + return ret; } static __be32 @@ -530,9 +539,9 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_restorefh; fh_dup2(&cstate->current_fh, &cstate->save_fh); - if (HAS_STATE_ID(cstate, SAVED_STATE_ID_FLAG)) { + if (HAS_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG)) { memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t)); - SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG); + SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } return nfs_ok; } @@ -542,9 +551,9 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { fh_dup2(&cstate->save_fh, &cstate->current_fh); - if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG)) { + if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG)) { memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t)); - SET_STATE_ID(cstate, SAVED_STATE_ID_FLAG); + SET_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG); } return nfs_ok; } @@ -581,9 +590,9 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { struct nfsd4_commit *commit = &u->commit; - gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp)); return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset, - commit->co_count); + commit->co_count, + (__be32 *)commit->co_verf.data); } static __be32 @@ -776,7 +785,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* check stateid */ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &read->rd_stateid, RD_STATE, - &read->rd_nf); + &read->rd_nf, NULL); if (status) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; @@ -948,7 +957,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, - WR_STATE, NULL); + WR_STATE, NULL, NULL); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -975,7 +984,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr, - 0, (time_t)0); + 0, (time64_t)0); out: fh_drop_write(&cstate->current_fh); return status; @@ -999,22 +1008,22 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, trace_nfsd_write_start(rqstp, &cstate->current_fh, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, - stateid, WR_STATE, &nf); + stateid, WR_STATE, &nf, NULL); if (status) { dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; } write->wr_how_written = write->wr_stable_how; - gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp)); nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist, &write->wr_head, write->wr_buflen); WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); - status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf->nf_file, + status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf, write->wr_offset, rqstp->rq_vec, nvecs, &cnt, - write->wr_how_written); + write->wr_how_written, + (__be32 *)write->wr_verifier.data); nfsd_file_put(nf); write->wr_bytes_written = cnt; @@ -1034,14 +1043,14 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_nofilehandle; status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, - src_stateid, RD_STATE, src); + src_stateid, RD_STATE, src, NULL); if (status) { dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); goto out; } status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, - dst_stateid, WR_STATE, dst); + dst_stateid, WR_STATE, dst, NULL); if (status) { dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); goto out_put_src; @@ -1076,8 +1085,8 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - status = nfsd4_clone_file_range(src->nf_file, clone->cl_src_pos, - dst->nf_file, clone->cl_dst_pos, clone->cl_count, + status = nfsd4_clone_file_range(src, clone->cl_src_pos, + dst, clone->cl_dst_pos, clone->cl_count, EX_ISSYNC(cstate->current_fh.fh_export)); nfsd_file_put(dst); @@ -1135,6 +1144,207 @@ void nfsd4_shutdown_copy(struct nfs4_client *clp) while ((copy = nfsd4_get_copy(clp)) != NULL) nfsd4_stop_copy(copy); } +#ifdef CONFIG_NFSD_V4_2_INTER_SSC + +extern struct file *nfs42_ssc_open(struct vfsmount *ss_mnt, + struct nfs_fh *src_fh, + nfs4_stateid *stateid); +extern void nfs42_ssc_close(struct file *filep); + +extern void nfs_sb_deactive(struct super_block *sb); + +#define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys" + +/** + * Support one copy source server for now. + */ +static __be32 +nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, + struct vfsmount **mount) +{ + struct file_system_type *type; + struct vfsmount *ss_mnt; + struct nfs42_netaddr *naddr; + struct sockaddr_storage tmp_addr; + size_t tmp_addrlen, match_netid_len = 3; + char *startsep = "", *endsep = "", *match_netid = "tcp"; + char *ipaddr, *dev_name, *raw_data; + int len, raw_len; + __be32 status = nfserr_inval; + + naddr = &nss->u.nl4_addr; + tmp_addrlen = rpc_uaddr2sockaddr(SVC_NET(rqstp), naddr->addr, + naddr->addr_len, + (struct sockaddr *)&tmp_addr, + sizeof(tmp_addr)); + if (tmp_addrlen == 0) + goto out_err; + + if (tmp_addr.ss_family == AF_INET6) { + startsep = "["; + endsep = "]"; + match_netid = "tcp6"; + match_netid_len = 4; + } + + if (naddr->netid_len != match_netid_len || + strncmp(naddr->netid, match_netid, naddr->netid_len)) + goto out_err; + + /* Construct the raw data for the vfs_kern_mount call */ + len = RPC_MAX_ADDRBUFLEN + 1; + ipaddr = kzalloc(len, GFP_KERNEL); + if (!ipaddr) + goto out_err; + + rpc_ntop((struct sockaddr *)&tmp_addr, ipaddr, len); + + /* 2 for ipv6 endsep and startsep. 3 for ":/" and trailing '/0'*/ + + raw_len = strlen(NFSD42_INTERSSC_MOUNTOPS) + strlen(ipaddr); + raw_data = kzalloc(raw_len, GFP_KERNEL); + if (!raw_data) + goto out_free_ipaddr; + + snprintf(raw_data, raw_len, NFSD42_INTERSSC_MOUNTOPS, ipaddr); + + status = nfserr_nodev; + type = get_fs_type("nfs"); + if (!type) + goto out_free_rawdata; + + /* Set the server:<export> for the vfs_kern_mount call */ + dev_name = kzalloc(len + 5, GFP_KERNEL); + if (!dev_name) + goto out_free_rawdata; + snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep); + + /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */ + ss_mnt = vfs_kern_mount(type, SB_KERNMOUNT, dev_name, raw_data); + module_put(type->owner); + if (IS_ERR(ss_mnt)) + goto out_free_devname; + + status = 0; + *mount = ss_mnt; + +out_free_devname: + kfree(dev_name); +out_free_rawdata: + kfree(raw_data); +out_free_ipaddr: + kfree(ipaddr); +out_err: + return status; +} + +static void +nfsd4_interssc_disconnect(struct vfsmount *ss_mnt) +{ + nfs_sb_deactive(ss_mnt->mnt_sb); + mntput(ss_mnt); +} + +/** + * nfsd4_setup_inter_ssc + * + * Verify COPY destination stateid. + * Connect to the source server with NFSv4.1. + * Create the source struct file for nfsd_copy_range. + * Called with COPY cstate: + * SAVED_FH: source filehandle + * CURRENT_FH: destination filehandle + */ +static __be32 +nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_copy *copy, struct vfsmount **mount) +{ + struct svc_fh *s_fh = NULL; + stateid_t *s_stid = ©->cp_src_stateid; + __be32 status = nfserr_inval; + + /* Verify the destination stateid and set dst struct file*/ + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + ©->cp_dst_stateid, + WR_STATE, ©->nf_dst, NULL); + if (status) + goto out; + + status = nfsd4_interssc_connect(©->cp_src, rqstp, mount); + if (status) + goto out; + + s_fh = &cstate->save_fh; + + copy->c_fh.size = s_fh->fh_handle.fh_size; + memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size); + copy->stateid.seqid = cpu_to_be32(s_stid->si_generation); + memcpy(copy->stateid.other, (void *)&s_stid->si_opaque, + sizeof(stateid_opaque_t)); + + status = 0; +out: + return status; +} + +static void +nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, + struct nfsd_file *dst) +{ + nfs42_ssc_close(src->nf_file); + nfsd_file_put(src); + nfsd_file_put(dst); + mntput(ss_mnt); +} + +#else /* CONFIG_NFSD_V4_2_INTER_SSC */ + +static __be32 +nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_copy *copy, + struct vfsmount **mount) +{ + *mount = NULL; + return nfserr_inval; +} + +static void +nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, + struct nfsd_file *dst) +{ +} + +static void +nfsd4_interssc_disconnect(struct vfsmount *ss_mnt) +{ +} + +static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt, + struct nfs_fh *src_fh, + nfs4_stateid *stateid) +{ + return NULL; +} +#endif /* CONFIG_NFSD_V4_2_INTER_SSC */ + +static __be32 +nfsd4_setup_intra_ssc(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_copy *copy) +{ + return nfsd4_verify_copy(rqstp, cstate, ©->cp_src_stateid, + ©->nf_src, ©->cp_dst_stateid, + ©->nf_dst); +} + +static void +nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) +{ + nfsd_file_put(src); + nfsd_file_put(dst); +} static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { @@ -1200,12 +1410,16 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) status = nfs_ok; } - nfsd_file_put(copy->nf_src); - nfsd_file_put(copy->nf_dst); + if (!copy->cp_intra) /* Inter server SSC */ + nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src, + copy->nf_dst); + else + nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); + return status; } -static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) +static int dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) { dst->cp_src_pos = src->cp_src_pos; dst->cp_dst_pos = src->cp_dst_pos; @@ -1215,15 +1429,25 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) memcpy(&dst->fh, &src->fh, sizeof(src->fh)); dst->cp_clp = src->cp_clp; dst->nf_dst = nfsd_file_get(src->nf_dst); - dst->nf_src = nfsd_file_get(src->nf_src); + dst->cp_intra = src->cp_intra; + if (src->cp_intra) /* for inter, file_src doesn't exist yet */ + dst->nf_src = nfsd_file_get(src->nf_src); + memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid)); + memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server)); + memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); + memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); + dst->ss_mnt = src->ss_mnt; + + return 0; } static void cleanup_async_copy(struct nfsd4_copy *copy) { - nfs4_free_cp_state(copy); + nfs4_free_copy_state(copy); nfsd_file_put(copy->nf_dst); - nfsd_file_put(copy->nf_src); + if (copy->cp_intra) + nfsd_file_put(copy->nf_src); spin_lock(©->cp_clp->async_lock); list_del(©->copies); spin_unlock(©->cp_clp->async_lock); @@ -1235,7 +1459,24 @@ static int nfsd4_do_async_copy(void *data) struct nfsd4_copy *copy = (struct nfsd4_copy *)data; struct nfsd4_copy *cb_copy; + if (!copy->cp_intra) { /* Inter server SSC */ + copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL); + if (!copy->nf_src) { + copy->nfserr = nfserr_serverfault; + nfsd4_interssc_disconnect(copy->ss_mnt); + goto do_callback; + } + copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, + ©->stateid); + if (IS_ERR(copy->nf_src->nf_file)) { + copy->nfserr = nfserr_offload_denied; + nfsd4_interssc_disconnect(copy->ss_mnt); + goto do_callback; + } + } + copy->nfserr = nfsd4_do_copy(copy, 0); +do_callback: cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!cb_copy) goto out; @@ -1247,6 +1488,8 @@ static int nfsd4_do_async_copy(void *data) &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); nfsd4_run_cb(&cb_copy->cp_cb); out: + if (!copy->cp_intra) + kfree(copy->nf_src); cleanup_async_copy(copy); return 0; } @@ -1259,11 +1502,20 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd4_copy *async_copy = NULL; - status = nfsd4_verify_copy(rqstp, cstate, ©->cp_src_stateid, - ©->nf_src, ©->cp_dst_stateid, - ©->nf_dst); - if (status) - goto out; + if (!copy->cp_intra) { /* Inter server SSC */ + if (!inter_copy_offload_enable || copy->cp_synchronous) { + status = nfserr_notsupp; + goto out; + } + status = nfsd4_setup_inter_ssc(rqstp, cstate, copy, + ©->ss_mnt); + if (status) + return nfserr_offload_denied; + } else { + status = nfsd4_setup_intra_ssc(rqstp, cstate, copy); + if (status) + return status; + } copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, @@ -1274,15 +1526,15 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) - goto out; - if (!nfs4_init_cp_state(nn, copy)) { - kfree(async_copy); - goto out; - } + goto out_err; + if (!nfs4_init_copy_state(nn, copy)) + goto out_err; refcount_set(&async_copy->refcount, 1); memcpy(©->cp_res.cb_stateid, ©->cp_stateid, sizeof(copy->cp_stateid)); - dup_copy_fields(copy, async_copy); + status = dup_copy_fields(copy, async_copy); + if (status) + goto out_err; async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) @@ -1293,13 +1545,17 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, spin_unlock(&async_copy->cp_clp->async_lock); wake_up_process(async_copy->copy_task); status = nfs_ok; - } else + } else { status = nfsd4_do_copy(copy, 1); + } out: return status; out_err: if (async_copy) cleanup_async_copy(async_copy); + status = nfserrno(-ENOMEM); + if (!copy->cp_intra) + nfsd4_interssc_disconnect(copy->ss_mnt); goto out; } @@ -1310,7 +1566,7 @@ find_async_copy(struct nfs4_client *clp, stateid_t *stateid) spin_lock(&clp->async_lock); list_for_each_entry(copy, &clp->async_copies, copies) { - if (memcmp(©->cp_stateid, stateid, NFS4_STATEID_SIZE)) + if (memcmp(©->cp_stateid.stid, stateid, NFS4_STATEID_SIZE)) continue; refcount_inc(©->refcount); spin_unlock(&clp->async_lock); @@ -1326,16 +1582,61 @@ nfsd4_offload_cancel(struct svc_rqst *rqstp, union nfsd4_op_u *u) { struct nfsd4_offload_status *os = &u->offload_status; - __be32 status = 0; struct nfsd4_copy *copy; struct nfs4_client *clp = cstate->clp; copy = find_async_copy(clp, &os->stateid); - if (copy) + if (!copy) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + + return manage_cpntf_state(nn, &os->stateid, clp, NULL); + } else nfsd4_stop_copy(copy); - else - status = nfserr_bad_stateid; + return nfs_ok; +} + +static __be32 +nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) +{ + struct nfsd4_copy_notify *cn = &u->copy_notify; + __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfs4_stid *stid; + struct nfs4_cpntf_state *cps; + struct nfs4_client *clp = cstate->clp; + + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + &cn->cpn_src_stateid, RD_STATE, NULL, + &stid); + if (status) + return status; + + cn->cpn_sec = nn->nfsd4_lease; + cn->cpn_nsec = 0; + + status = nfserrno(-ENOMEM); + cps = nfs4_alloc_init_cpntf_state(nn, stid); + if (!cps) + goto out; + memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t)); + memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t)); + memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t)); + + /* For now, only return one server address in cpn_src, the + * address used by the client to connect to this server. + */ + cn->cpn_src.nl4_type = NL4_NETADDR; + status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr, + &cn->cpn_src.u.nl4_addr); + WARN_ON_ONCE(status); + if (status) { + nfs4_put_cpntf_state(nn, cps); + goto out; + } +out: + nfs4_put_stid(stid); return status; } @@ -1348,7 +1649,7 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, - WR_STATE, &nf); + WR_STATE, &nf, NULL); if (status != nfs_ok) { dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); return status; @@ -1407,7 +1708,7 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, - RD_STATE, &nf); + RD_STATE, &nf, NULL); if (status) { dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); return status; @@ -1912,6 +2213,45 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp, - rqstp->rq_auth_slack; } +#ifdef CONFIG_NFSD_V4_2_INTER_SSC +static void +check_if_stalefh_allowed(struct nfsd4_compoundargs *args) +{ + struct nfsd4_op *op, *current_op = NULL, *saved_op = NULL; + struct nfsd4_copy *copy; + struct nfsd4_putfh *putfh; + int i; + + /* traverse all operation and if it's a COPY compound, mark the + * source filehandle to skip verification + */ + for (i = 0; i < args->opcnt; i++) { + op = &args->ops[i]; + if (op->opnum == OP_PUTFH) + current_op = op; + else if (op->opnum == OP_SAVEFH) + saved_op = current_op; + else if (op->opnum == OP_RESTOREFH) + current_op = saved_op; + else if (op->opnum == OP_COPY) { + copy = (struct nfsd4_copy *)&op->u; + if (!saved_op) { + op->status = nfserr_nofilehandle; + return; + } + putfh = (struct nfsd4_putfh *)&saved_op->u; + if (!copy->cp_intra) + putfh->no_verify = true; + } + } +} +#else +static void +check_if_stalefh_allowed(struct nfsd4_compoundargs *args) +{ +} +#endif + /* * COMPOUND call. */ @@ -1960,6 +2300,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) resp->opcnt = 1; goto encode_op; } + check_if_stalefh_allowed(args); trace_nfsd_compound(rqstp, args->opcnt); while (!status && resp->opcnt < args->opcnt) { @@ -1975,13 +2316,14 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) op->status = nfsd4_open_omfg(rqstp, cstate, op); goto encode_op; } - - if (!current_fh->fh_dentry) { + if (!current_fh->fh_dentry && + !HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) { if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { op->status = nfserr_nofilehandle; goto encode_op; } - } else if (current_fh->fh_export->ex_fslocs.migrated && + } else if (current_fh->fh_export && + current_fh->fh_export->ex_fslocs.migrated && !(op->opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) { op->status = nfserr_moved; goto encode_op; @@ -2025,7 +2367,8 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) if (op->opdesc->op_flags & OP_CLEAR_STATEID) clear_current_stateid(cstate); - if (need_wrongsec_check(rqstp)) + if (current_fh->fh_export && + need_wrongsec_check(rqstp)) op->status = check_nfsd_access(current_fh->fh_export, rqstp); } encode_op: @@ -2292,6 +2635,21 @@ static inline u32 nfsd4_offload_status_rsize(struct svc_rqst *rqstp, 1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32); } +static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp, + struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 3 /* cnr_lease_time */ + + 1 /* We support one cnr_source_server */ + + 1 /* cnr_stateid seq */ + + op_encode_stateid_maxsz /* cnr_stateid */ + + 1 /* num cnr_source_server*/ + + 1 /* nl4_type */ + + 1 /* nl4 size */ + + XDR_QUADLEN(NFS4_OPAQUE_LIMIT) /*nl4_loc + nl4_loc_sz */) + * sizeof(__be32); +} + #ifdef CONFIG_NFSD_PNFS static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) { @@ -2716,6 +3074,12 @@ static const struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_OFFLOAD_CANCEL", .op_rsize_bop = nfsd4_only_status_rsize, }, + [OP_COPY_NOTIFY] = { + .op_func = nfsd4_copy_notify, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_COPY_NOTIFY", + .op_rsize_bop = nfsd4_copy_notify_rsize, + }, }; /** diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 2481e7662128..a8fb18609146 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -1445,7 +1445,7 @@ nfsd4_cld_grace_done_v0(struct nfsd_net *nn) } cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone; - cup->cu_u.cu_msg.cm_u.cm_gracetime = (int64_t)nn->boot_time; + cup->cu_u.cu_msg.cm_u.cm_gracetime = nn->boot_time; ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg); if (!ret) ret = cup->cu_u.cu_msg.cm_status; @@ -1782,7 +1782,7 @@ nfsd4_cltrack_client_has_session(struct nfs4_client *clp) } static char * -nfsd4_cltrack_grace_start(time_t grace_start) +nfsd4_cltrack_grace_start(time64_t grace_start) { int copied; size_t len; @@ -1795,7 +1795,7 @@ nfsd4_cltrack_grace_start(time_t grace_start) if (!result) return result; - copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%ld", + copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%lld", grace_start); if (copied >= len) { /* just return nothing if output was truncated */ @@ -2004,7 +2004,7 @@ nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn) char *legacy; char timestr[22]; /* FIXME: better way to determine max size? */ - sprintf(timestr, "%ld", nn->boot_time); + sprintf(timestr, "%lld", nn->boot_time); legacy = nfsd4_cltrack_legacy_topdir(); nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy, NULL); kfree(legacy); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 369e574c5092..65cfe9ab47be 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -80,6 +80,7 @@ static u64 current_sessionid = 1; static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); +static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); /* Locking: */ @@ -170,7 +171,7 @@ renew_client_locked(struct nfs4_client *clp) clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); list_move_tail(&clp->cl_lru, &nn->client_lru); - clp->cl_time = get_seconds(); + clp->cl_time = ktime_get_boottime_seconds(); } static void put_client_renew_locked(struct nfs4_client *clp) @@ -722,6 +723,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla /* Will be incremented before return to client: */ refcount_set(&stid->sc_count, 1); spin_lock_init(&stid->sc_lock); + INIT_LIST_HEAD(&stid->sc_cp_list); /* * It shouldn't be a problem to reuse an opaque stateid value. @@ -741,30 +743,76 @@ out_free: /* * Create a unique stateid_t to represent each COPY. */ -int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy) +static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, + unsigned char sc_type) { int new_id; + stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; + stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; + stid->sc_type = sc_type; + idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); - new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, copy, 0, 0, GFP_NOWAIT); + new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); + stid->stid.si_opaque.so_id = new_id; spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; - copy->cp_stateid.si_opaque.so_id = new_id; - copy->cp_stateid.si_opaque.so_clid.cl_boot = nn->boot_time; - copy->cp_stateid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; return 1; } -void nfs4_free_cp_state(struct nfsd4_copy *copy) +int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) +{ + return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID); +} + +struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, + struct nfs4_stid *p_stid) +{ + struct nfs4_cpntf_state *cps; + + cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL); + if (!cps) + return NULL; + cps->cpntf_time = ktime_get_boottime_seconds(); + refcount_set(&cps->cp_stateid.sc_count, 1); + if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) + goto out_free; + spin_lock(&nn->s2s_cp_lock); + list_add(&cps->cp_list, &p_stid->sc_cp_list); + spin_unlock(&nn->s2s_cp_lock); + return cps; +out_free: + kfree(cps); + return NULL; +} + +void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; + WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID); nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); - idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.si_opaque.so_id); + idr_remove(&nn->s2s_cp_stateids, + copy->cp_stateid.stid.si_opaque.so_id); + spin_unlock(&nn->s2s_cp_lock); +} + +static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid) +{ + struct nfs4_cpntf_state *cps; + struct nfsd_net *nn; + + nn = net_generic(net, nfsd_net_id); + spin_lock(&nn->s2s_cp_lock); + while (!list_empty(&stid->sc_cp_list)) { + cps = list_first_entry(&stid->sc_cp_list, + struct nfs4_cpntf_state, cp_list); + _free_cpntf_state_locked(nn, cps); + } spin_unlock(&nn->s2s_cp_lock); } @@ -806,7 +854,7 @@ static void nfs4_free_deleg(struct nfs4_stid *stid) static DEFINE_SPINLOCK(blocked_delegations_lock); static struct bloom_pair { int entries, old_entries; - time_t swap_time; + time64_t swap_time; int new; /* index into 'set' */ DECLARE_BITMAP(set[2], 256); } blocked_delegations; @@ -818,15 +866,15 @@ static int delegation_blocked(struct knfsd_fh *fh) if (bd->entries == 0) return 0; - if (seconds_since_boot() - bd->swap_time > 30) { + if (ktime_get_seconds() - bd->swap_time > 30) { spin_lock(&blocked_delegations_lock); - if (seconds_since_boot() - bd->swap_time > 30) { + if (ktime_get_seconds() - bd->swap_time > 30) { bd->entries -= bd->old_entries; bd->old_entries = bd->entries; memset(bd->set[bd->new], 0, sizeof(bd->set[0])); bd->new = 1-bd->new; - bd->swap_time = seconds_since_boot(); + bd->swap_time = ktime_get_seconds(); } spin_unlock(&blocked_delegations_lock); } @@ -856,7 +904,7 @@ static void block_delegations(struct knfsd_fh *fh) __set_bit((hash>>8)&255, bd->set[bd->new]); __set_bit((hash>>16)&255, bd->set[bd->new]); if (bd->entries == 0) - bd->swap_time = seconds_since_boot(); + bd->swap_time = ktime_get_seconds(); bd->entries += 1; spin_unlock(&blocked_delegations_lock); } @@ -915,6 +963,7 @@ nfs4_put_stid(struct nfs4_stid *s) return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + nfs4_free_cpntf_statelist(clp->net, s); spin_unlock(&clp->cl_lock); s->sc_free(s); if (fp) @@ -1862,7 +1911,7 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) */ if (clid->cl_boot == (u32)nn->boot_time) return 0; - dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n", + dprintk("NFSD stale clientid (%08x/%08x) boot_time %08llx\n", clid->cl_boot, clid->cl_id, nn->boot_time); return 1; } @@ -2215,14 +2264,14 @@ static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn) * This is opaque to client, so no need to byte-swap. Use * __force to keep sparse happy */ - verf[0] = (__force __be32)get_seconds(); + verf[0] = (__force __be32)(u32)ktime_get_real_seconds(); verf[1] = (__force __be32)nn->clverifier_counter++; memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data)); } static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn) { - clp->cl_clientid.cl_boot = nn->boot_time; + clp->cl_clientid.cl_boot = (u32)nn->boot_time; clp->cl_clientid.cl_id = nn->clientid_counter++; gen_confirm(clp, nn); } @@ -2292,7 +2341,7 @@ static int client_info_show(struct seq_file *m, void *v) clp->cl_nii_domain.len); seq_printf(m, "\nImplementation name: "); seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); - seq_printf(m, "\nImplementation time: [%ld, %ld]\n", + seq_printf(m, "\nImplementation time: [%lld, %ld]\n", clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); } drop_client(clp); @@ -2612,7 +2661,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, gen_clid(clp, nn); kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); - clp->cl_time = get_seconds(); + clp->cl_time = ktime_get_boottime_seconds(); clear_bit(0, &clp->cl_cb_slot_busy); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); @@ -2946,8 +2995,7 @@ static __be32 copy_impl_id(struct nfs4_client *clp, xdr_netobj_dup(&clp->cl_nii_name, &exid->nii_name, GFP_KERNEL); if (!clp->cl_nii_name.data) return nfserr_jukebox; - clp->cl_nii_time.tv_sec = exid->nii_time.tv_sec; - clp->cl_nii_time.tv_nsec = exid->nii_time.tv_nsec; + clp->cl_nii_time = exid->nii_time; return 0; } @@ -3373,7 +3421,7 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir) case NFS4_CDFC4_BACK_OR_BOTH: *dir = NFS4_CDFC4_BOTH; return nfs_ok; - }; + } return nfserr_inval; } @@ -4283,7 +4331,7 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) last = oo->oo_last_closed_stid; oo->oo_last_closed_stid = s; list_move_tail(&oo->oo_close_lru, &nn->close_lru); - oo->oo_time = get_seconds(); + oo->oo_time = ktime_get_boottime_seconds(); spin_unlock(&nn->client_lock); if (last) nfs4_put_stid(&last->st_stid); @@ -4378,7 +4426,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) */ spin_lock(&state_lock); if (dp->dl_time == 0) { - dp->dl_time = get_seconds(); + dp->dl_time = ktime_get_boottime_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } spin_unlock(&state_lock); @@ -4490,7 +4538,8 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4 static __be32 lookup_clientid(clientid_t *clid, struct nfsd4_compound_state *cstate, - struct nfsd_net *nn) + struct nfsd_net *nn, + bool sessions) { struct nfs4_client *found; @@ -4511,7 +4560,7 @@ static __be32 lookup_clientid(clientid_t *clid, */ WARN_ON_ONCE(cstate->session); spin_lock(&nn->client_lock); - found = find_confirmed_client(clid, false, nn); + found = find_confirmed_client(clid, sessions, nn); if (!found) { spin_unlock(&nn->client_lock); return nfserr_expired; @@ -4544,7 +4593,7 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, if (open->op_file == NULL) return nfserr_jukebox; - status = lookup_clientid(clientid, cstate, nn); + status = lookup_clientid(clientid, cstate, nn, false); if (status) return status; clp = cstate->clp; @@ -4672,7 +4721,7 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0); + return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, @@ -5133,7 +5182,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("process_renew(%08x/%08x): starting\n", clid->cl_boot, clid->cl_id); - status = lookup_clientid(clid, cstate, nn); + status = lookup_clientid(clid, cstate, nn, false); if (status) goto out; clp = cstate->clp; @@ -5184,9 +5233,8 @@ nfsd4_end_grace(struct nfsd_net *nn) */ static bool clients_still_reclaiming(struct nfsd_net *nn) { - unsigned long now = get_seconds(); - unsigned long double_grace_period_end = nn->boot_time + - 2 * nn->nfsd4_lease; + time64_t double_grace_period_end = nn->boot_time + + 2 * nn->nfsd4_lease; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == @@ -5199,12 +5247,12 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) * If we've given them *two* lease times to reclaim, and they're * still not done, give up: */ - if (time_after(now, double_grace_period_end)) + if (ktime_get_boottime_seconds() > double_grace_period_end) return false; return true; } -static time_t +static time64_t nfs4_laundromat(struct nfsd_net *nn) { struct nfs4_client *clp; @@ -5213,8 +5261,11 @@ nfs4_laundromat(struct nfsd_net *nn) struct nfs4_ol_stateid *stp; struct nfsd4_blocked_lock *nbl; struct list_head *pos, *next, reaplist; - time_t cutoff = get_seconds() - nn->nfsd4_lease; - time_t t, new_timeo = nn->nfsd4_lease; + time64_t cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease; + time64_t t, new_timeo = nn->nfsd4_lease; + struct nfs4_cpntf_state *cps; + copy_stateid_t *cps_t; + int i; dprintk("NFSD: laundromat service - starting\n"); @@ -5225,10 +5276,20 @@ nfs4_laundromat(struct nfsd_net *nn) dprintk("NFSD: end of grace period\n"); nfsd4_end_grace(nn); INIT_LIST_HEAD(&reaplist); + + spin_lock(&nn->s2s_cp_lock); + idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { + cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); + if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID && + cps->cpntf_time > cutoff) + _free_cpntf_state_locked(nn, cps); + } + spin_unlock(&nn->s2s_cp_lock); + spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); - if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) { + if (clp->cl_time > cutoff) { t = clp->cl_time - cutoff; new_timeo = min(new_timeo, t); break; @@ -5251,7 +5312,7 @@ nfs4_laundromat(struct nfsd_net *nn) spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); - if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) { + if (dp->dl_time > cutoff) { t = dp->dl_time - cutoff; new_timeo = min(new_timeo, t); break; @@ -5271,8 +5332,7 @@ nfs4_laundromat(struct nfsd_net *nn) while (!list_empty(&nn->close_lru)) { oo = list_first_entry(&nn->close_lru, struct nfs4_openowner, oo_close_lru); - if (time_after((unsigned long)oo->oo_time, - (unsigned long)cutoff)) { + if (oo->oo_time > cutoff) { t = oo->oo_time - cutoff; new_timeo = min(new_timeo, t); break; @@ -5302,8 +5362,7 @@ nfs4_laundromat(struct nfsd_net *nn) while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); - if (time_after((unsigned long)nbl->nbl_time, - (unsigned long)cutoff)) { + if (nbl->nbl_time > cutoff) { t = nbl->nbl_time - cutoff; new_timeo = min(new_timeo, t); break; @@ -5320,7 +5379,7 @@ nfs4_laundromat(struct nfsd_net *nn) free_blocked_lock(nbl); } out: - new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); + new_timeo = max_t(time64_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); return new_timeo; } @@ -5330,13 +5389,13 @@ static void laundromat_main(struct work_struct *); static void laundromat_main(struct work_struct *laundry) { - time_t t; + time64_t t; struct delayed_work *dwork = to_delayed_work(laundry); struct nfsd_net *nn = container_of(dwork, struct nfsd_net, laundromat_work); t = nfs4_laundromat(nn); - dprintk("NFSD: laundromat_main - sleeping for %ld seconds\n", t); + dprintk("NFSD: laundromat_main - sleeping for %lld seconds\n", t); queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } @@ -5521,7 +5580,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return nfserr_bad_stateid; - status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn); + status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn, + false); if (status == nfserr_stale_clientid) { if (cstate->session) return nfserr_bad_stateid; @@ -5600,6 +5660,85 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, out: return status; } +static void +_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) +{ + WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID); + if (!refcount_dec_and_test(&cps->cp_stateid.sc_count)) + return; + list_del(&cps->cp_list); + idr_remove(&nn->s2s_cp_stateids, + cps->cp_stateid.stid.si_opaque.so_id); + kfree(cps); +} +/* + * A READ from an inter server to server COPY will have a + * copy stateid. Look up the copy notify stateid from the + * idr structure and take a reference on it. + */ +__be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, + struct nfs4_client *clp, + struct nfs4_cpntf_state **cps) +{ + copy_stateid_t *cps_t; + struct nfs4_cpntf_state *state = NULL; + + if (st->si_opaque.so_clid.cl_id != nn->s2s_cp_cl_id) + return nfserr_bad_stateid; + spin_lock(&nn->s2s_cp_lock); + cps_t = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id); + if (cps_t) { + state = container_of(cps_t, struct nfs4_cpntf_state, + cp_stateid); + if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) { + state = NULL; + goto unlock; + } + if (!clp) + refcount_inc(&state->cp_stateid.sc_count); + else + _free_cpntf_state_locked(nn, state); + } +unlock: + spin_unlock(&nn->s2s_cp_lock); + if (!state) + return nfserr_bad_stateid; + if (!clp && state) + *cps = state; + return 0; +} + +static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, + struct nfs4_stid **stid) +{ + __be32 status; + struct nfs4_cpntf_state *cps = NULL; + struct nfsd4_compound_state cstate; + + status = manage_cpntf_state(nn, st, NULL, &cps); + if (status) + return status; + + cps->cpntf_time = ktime_get_boottime_seconds(); + memset(&cstate, 0, sizeof(cstate)); + status = lookup_clientid(&cps->cp_p_clid, &cstate, nn, true); + if (status) + goto out; + status = nfsd4_lookup_stateid(&cstate, &cps->cp_p_stateid, + NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, + stid, nn); + put_client_renew(cstate.clp); +out: + nfs4_put_cpntf_state(nn, cps); + return status; +} + +void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) +{ + spin_lock(&nn->s2s_cp_lock); + _free_cpntf_state_locked(nn, cps); + spin_unlock(&nn->s2s_cp_lock); +} /* * Checks for stateid operations @@ -5607,7 +5746,8 @@ out: __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct svc_fh *fhp, - stateid_t *stateid, int flags, struct nfsd_file **nfp) + stateid_t *stateid, int flags, struct nfsd_file **nfp, + struct nfs4_stid **cstid) { struct inode *ino = d_inode(fhp->fh_dentry); struct net *net = SVC_NET(rqstp); @@ -5629,6 +5769,8 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, nn); + if (status == nfserr_bad_stateid) + status = find_cpntf_state(nn, stateid, &s); if (status) return status; status = nfsd4_stid_check_stateid_generation(stateid, s, @@ -5656,8 +5798,12 @@ done: if (status == nfs_ok && nfp) status = nfs4_check_file(rqstp, fhp, s, nfp, flags); out: - if (s) - nfs4_put_stid(s); + if (s) { + if (!status && cstid) + *cstid = s; + else + nfs4_put_stid(s); + } return status; } @@ -6550,7 +6696,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } if (fl_flags & FL_SLEEP) { - nbl->nbl_time = jiffies; + nbl->nbl_time = ktime_get_boottime_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); @@ -6657,7 +6803,8 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; if (!nfsd4_has_session(cstate)) { - status = lookup_clientid(&lockt->lt_clientid, cstate, nn); + status = lookup_clientid(&lockt->lt_clientid, cstate, nn, + false); if (status) goto out; } @@ -6841,7 +6988,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); - status = lookup_clientid(clid, cstate, nn); + status = lookup_clientid(clid, cstate, nn, false); if (status) return status; @@ -6988,7 +7135,7 @@ nfs4_check_open_reclaim(clientid_t *clid, __be32 status; /* find clientid in conf_id_hashtbl */ - status = lookup_clientid(clid, cstate, nn); + status = lookup_clientid(clid, cstate, nn, false); if (status) return nfserr_reclaim_bad; @@ -7641,7 +7788,7 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]); nn->conf_name_tree = RB_ROOT; nn->unconf_name_tree = RB_ROOT; - nn->boot_time = get_seconds(); + nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); @@ -7710,7 +7857,7 @@ nfs4_state_start_net(struct net *net) nfsd4_client_tracking_init(net); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; - printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n", + printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; @@ -7786,7 +7933,8 @@ nfs4_state_shutdown(void) static void get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { - if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid)) + if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG) && + CURRENT_STATEID(stateid)) memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t)); } @@ -7795,14 +7943,14 @@ put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { if (cstate->minorversion) { memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t)); - SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG); + SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } } void clear_current_stateid(struct nfsd4_compound_state *cstate) { - CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG); + CLEAR_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } /* diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index d2dc4c0e22e8..9761512674a0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -40,6 +40,7 @@ #include <linux/utsname.h> #include <linux/pagemap.h> #include <linux/sunrpc/svcauth_gss.h> +#include <linux/sunrpc/addr.h> #include "idmap.h" #include "acl.h" @@ -1744,10 +1745,47 @@ nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) DECODE_TAIL; } +static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, + struct nl4_server *ns) +{ + DECODE_HEAD; + struct nfs42_netaddr *naddr; + + READ_BUF(4); + ns->nl4_type = be32_to_cpup(p++); + + /* currently support for 1 inter-server source server */ + switch (ns->nl4_type) { + case NL4_NETADDR: + naddr = &ns->u.nl4_addr; + + READ_BUF(4); + naddr->netid_len = be32_to_cpup(p++); + if (naddr->netid_len > RPCBIND_MAXNETIDLEN) + goto xdr_error; + + READ_BUF(naddr->netid_len + 4); /* 4 for uaddr len */ + COPYMEM(naddr->netid, naddr->netid_len); + + naddr->addr_len = be32_to_cpup(p++); + if (naddr->addr_len > RPCBIND_MAXUADDRLEN) + goto xdr_error; + + READ_BUF(naddr->addr_len); + COPYMEM(naddr->addr, naddr->addr_len); + break; + default: + goto xdr_error; + } + DECODE_TAIL; +} + static __be32 nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) { DECODE_HEAD; + struct nl4_server *ns_dummy; + int i, count; status = nfsd4_decode_stateid(argp, ©->cp_src_stateid); if (status) @@ -1762,7 +1800,32 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) p = xdr_decode_hyper(p, ©->cp_count); p++; /* ca_consecutive: we always do consecutive copies */ copy->cp_synchronous = be32_to_cpup(p++); - /* tmp = be32_to_cpup(p); Source server list not supported */ + + count = be32_to_cpup(p++); + + copy->cp_intra = false; + if (count == 0) { /* intra-server copy */ + copy->cp_intra = true; + goto intra; + } + + /* decode all the supplied server addresses but use first */ + status = nfsd4_decode_nl4_server(argp, ©->cp_src); + if (status) + return status; + + ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL); + if (ns_dummy == NULL) + return nfserrno(-ENOMEM); + for (i = 0; i < count - 1; i++) { + status = nfsd4_decode_nl4_server(argp, ns_dummy); + if (status) { + kfree(ns_dummy); + return status; + } + } + kfree(ns_dummy); +intra: DECODE_TAIL; } @@ -1775,6 +1838,18 @@ nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp, } static __be32 +nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, + struct nfsd4_copy_notify *cn) +{ + int status; + + status = nfsd4_decode_stateid(argp, &cn->cpn_src_stateid); + if (status) + return status; + return nfsd4_decode_nl4_server(argp, &cn->cpn_dst); +} + +static __be32 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) { DECODE_HEAD; @@ -1875,7 +1950,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = { /* new operations for NFSv4.2 */ [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, [OP_COPY] = (nfsd4_dec)nfsd4_decode_copy, - [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_copy_notify, [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp, @@ -2024,11 +2099,11 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, */ static __be32 *encode_time_delta(__be32 *p, struct inode *inode) { - struct timespec ts; + struct timespec64 ts; u32 ns; ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran); - ts = ns_to_timespec(ns); + ts = ns_to_timespec64(ns); p = xdr_encode_hyper(p, ts.tv_sec); *p++ = cpu_to_be32(ts.tv_nsec); @@ -4244,6 +4319,46 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp, } static __be32 +nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns) +{ + struct xdr_stream *xdr = &resp->xdr; + struct nfs42_netaddr *addr; + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + *p++ = cpu_to_be32(ns->nl4_type); + + switch (ns->nl4_type) { + case NL4_NETADDR: + addr = &ns->u.nl4_addr; + + /* netid_len, netid, uaddr_len, uaddr (port included + * in RPCBIND_MAXUADDRLEN) + */ + p = xdr_reserve_space(xdr, + 4 /* netid len */ + + (XDR_QUADLEN(addr->netid_len) * 4) + + 4 /* uaddr len */ + + (XDR_QUADLEN(addr->addr_len) * 4)); + if (!p) + return nfserr_resource; + + *p++ = cpu_to_be32(addr->netid_len); + p = xdr_encode_opaque_fixed(p, addr->netid, + addr->netid_len); + *p++ = cpu_to_be32(addr->addr_len); + p = xdr_encode_opaque_fixed(p, addr->addr, + addr->addr_len); + break; + default: + WARN_ON_ONCE(ns->nl4_type != NL4_NETADDR); + return nfserr_inval; + } + + return 0; +} + +static __be32 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_copy *copy) { @@ -4277,6 +4392,40 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 +nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_copy_notify *cn) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + /* 8 sec, 4 nsec */ + p = xdr_reserve_space(xdr, 12); + if (!p) + return nfserr_resource; + + /* cnr_lease_time */ + p = xdr_encode_hyper(p, cn->cpn_sec); + *p++ = cpu_to_be32(cn->cpn_nsec); + + /* cnr_stateid */ + nfserr = nfsd4_encode_stateid(xdr, &cn->cpn_cnr_stateid); + if (nfserr) + return nfserr; + + /* cnr_src.nl_nsvr */ + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + + *p++ = cpu_to_be32(1); + + return nfsd42_encode_nl4_server(resp, &cn->cpn_src); +} + +static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_seek *seek) { @@ -4373,7 +4522,7 @@ static const nfsd4_enc nfsd4_enc_ops[] = { /* NFSv4.2 operations */ [OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, [OP_COPY] = (nfsd4_enc)nfsd4_encode_copy, - [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_noop, + [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_copy_notify, [OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, [OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop, @@ -4500,8 +4649,6 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) __be32 *p; struct nfs4_replay *rp = op->replay; - BUG_ON(!rp); - p = xdr_reserve_space(xdr, 8 + rp->rp_buflen); if (!p) { WARN_ON_ONCE(1); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 11b42c523f04..e109a1007704 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -157,11 +157,11 @@ static int exports_proc_open(struct inode *inode, struct file *file) return exports_net_open(current->nsproxy->net_ns, file); } -static const struct file_operations exports_proc_operations = { - .open = exports_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int exports_nfsd_open(struct inode *inode, struct file *file) @@ -956,7 +956,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size) #ifdef CONFIG_NFSD_V4 static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, - time_t *time, struct nfsd_net *nn) + time64_t *time, struct nfsd_net *nn) { char *mesg = buf; int rv, i; @@ -984,11 +984,11 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, *time = i; } - return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n", *time); + return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%lld\n", *time); } static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, - time_t *time, struct nfsd_net *nn) + time64_t *time, struct nfsd_net *nn) { ssize_t rv; @@ -1431,8 +1431,7 @@ static int create_proc_exports_entry(void) entry = proc_mkdir("fs/nfs", NULL); if (!entry) return -ENOMEM; - entry = proc_create("exports", 0, entry, - &exports_proc_operations); + entry = proc_create("exports", 0, entry, &exports_proc_ops); if (!entry) { remove_proc_entry("fs/nfs", NULL); return -ENOMEM; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 57b93d95fa5c..2ab5569126b8 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -19,6 +19,7 @@ #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/msg_prot.h> +#include <linux/sunrpc/addr.h> #include <uapi/linux/nfsd/debug.h> @@ -142,7 +143,6 @@ int nfs4_state_start(void); int nfs4_state_start_net(struct net *net); void nfs4_state_shutdown(void); void nfs4_state_shutdown_net(struct net *net); -void nfs4_reset_lease(time_t leasetime); int nfs4_reset_recoverydir(char *recdir); char * nfs4_recoverydir(void); bool nfsd4_spo_must_allow(struct svc_rqst *rqstp); @@ -153,7 +153,6 @@ static inline int nfs4_state_start(void) { return 0; } static inline int nfs4_state_start_net(struct net *net) { return 0; } static inline void nfs4_state_shutdown(void) { } static inline void nfs4_state_shutdown_net(struct net *net) { } -static inline void nfs4_reset_lease(time_t leasetime) { } static inline int nfs4_reset_recoverydir(char *recdir) { return 0; } static inline char * nfs4_recoverydir(void) {return NULL; } static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) @@ -387,6 +386,37 @@ void nfsd_lockd_shutdown(void); extern const u32 nfsd_suppattrs[3][3]; +static inline __be32 nfsd4_set_netaddr(struct sockaddr *addr, + struct nfs42_netaddr *netaddr) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)addr; + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; + unsigned int port; + size_t ret_addr, ret_port; + + switch (addr->sa_family) { + case AF_INET: + port = ntohs(sin->sin_port); + sprintf(netaddr->netid, "tcp"); + netaddr->netid_len = 3; + break; + case AF_INET6: + port = ntohs(sin6->sin6_port); + sprintf(netaddr->netid, "tcp6"); + netaddr->netid_len = 4; + break; + default: + return nfserr_inval; + } + ret_addr = rpc_ntop(addr, netaddr->addr, sizeof(netaddr->addr)); + ret_port = snprintf(netaddr->addr + ret_addr, + RPCBIND_MAXUADDRLEN + 1 - ret_addr, + ".%u.%u", port >> 8, port & 0xff); + WARN_ON(ret_port >= RPCBIND_MAXUADDRLEN + 1 - ret_addr); + netaddr->addr_len = ret_addr + ret_port; + return 0; +} + static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2) { return !((bm1[0] & ~bm2[0]) || diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 755e256a9103..56cfbc361561 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -35,15 +35,15 @@ typedef struct svc_fh { bool fh_locked; /* inode locked by us */ bool fh_want_write; /* remount protection taken */ - + int fh_flags; /* FH flags */ #ifdef CONFIG_NFSD_V3 bool fh_post_saved; /* post-op attrs saved */ bool fh_pre_saved; /* pre-op attrs saved */ /* Pre-op attributes saved during fh_lock */ __u64 fh_pre_size; /* size before operation */ - struct timespec fh_pre_mtime; /* mtime before oper */ - struct timespec fh_pre_ctime; /* ctime before oper */ + struct timespec64 fh_pre_mtime; /* mtime before oper */ + struct timespec64 fh_pre_ctime; /* ctime before oper */ /* * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode) * to find out if it is valid. @@ -56,6 +56,9 @@ typedef struct svc_fh { #endif /* CONFIG_NFSD_V3 */ } svc_fh; +#define NFSD4_FH_FOREIGN (1<<0) +#define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f)) +#define HAS_FH_FLAG(c, f) ((c)->fh_flags & (f)) enum nfsd_fsid { FSID_DEV = 0, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index c83ddac22f38..543bbe0a556e 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -94,7 +94,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) * Solaris, at least, doesn't seem to care what the time * request is. We require it be within 30 minutes of now. */ - time_t delta = iap->ia_atime.tv_sec - get_seconds(); + time64_t delta = iap->ia_atime.tv_sec - ktime_get_real_seconds(); nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); if (nfserr) @@ -113,7 +113,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) } } - nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0); + nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0); done: return nfsd_return_attrs(nfserr, resp); } @@ -226,7 +226,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) return nfserr_io; nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), argp->offset, rqstp->rq_vec, nvecs, - &cnt, NFS_DATA_SYNC); + &cnt, NFS_DATA_SYNC, NULL); return nfsd_return_attrs(nfserr, resp); } @@ -380,7 +380,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ attr->ia_valid &= ATTR_SIZE; if (attr->ia_valid) - nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time_t)0); + nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time64_t)0); } out_unlock: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index e8bee8ff30c5..3b77b904212d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -31,6 +31,12 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC +bool inter_copy_offload_enable; +EXPORT_SYMBOL_GPL(inter_copy_offload_enable); +module_param(inter_copy_offload_enable, bool, 0644); +MODULE_PARM_DESC(inter_copy_offload_enable, + "Enable inter server to server copy offload. Default: false"); + extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) @@ -391,20 +397,25 @@ static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cre ret = lockd_up(net, cred); if (ret) goto out_socks; - nn->lockd_up = 1; + nn->lockd_up = true; } - ret = nfs4_state_start_net(net); + ret = nfsd_file_cache_start_net(net); if (ret) goto out_lockd; + ret = nfs4_state_start_net(net); + if (ret) + goto out_filecache; nn->nfsd_net_up = true; return 0; +out_filecache: + nfsd_file_cache_shutdown_net(net); out_lockd: if (nn->lockd_up) { lockd_down(net); - nn->lockd_up = 0; + nn->lockd_up = false; } out_socks: nfsd_shutdown_generic(); @@ -415,11 +426,11 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfsd_file_cache_purge(net); + nfsd_file_cache_shutdown_net(net); nfs4_state_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); - nn->lockd_up = 0; + nn->lockd_up = false; } nn->nfsd_net_up = false; nfsd_shutdown_generic(); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index d61b83b9654c..68d3f30ee760 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -56,6 +56,14 @@ typedef struct { stateid_opaque_t si_opaque; } stateid_t; +typedef struct { + stateid_t stid; +#define NFS4_COPY_STID 1 +#define NFS4_COPYNOTIFY_STID 2 + unsigned char sc_type; + refcount_t sc_count; +} copy_stateid_t; + #define STATEID_FMT "(%08x/%08x/%08x/%08x)" #define STATEID_VAL(s) \ (s)->si_opaque.so_clid.cl_boot, \ @@ -96,6 +104,7 @@ struct nfs4_stid { #define NFS4_REVOKED_DELEG_STID 16 #define NFS4_CLOSED_DELEG_STID 32 #define NFS4_LAYOUT_STID 64 + struct list_head sc_cp_list; unsigned char sc_type; stateid_t sc_stateid; spinlock_t sc_lock; @@ -104,6 +113,17 @@ struct nfs4_stid { void (*sc_free)(struct nfs4_stid *); }; +/* Keep a list of stateids issued by the COPY_NOTIFY, associate it with the + * parent OPEN/LOCK/DELEG stateid. + */ +struct nfs4_cpntf_state { + copy_stateid_t cp_stateid; + struct list_head cp_list; /* per parent nfs4_stid */ + stateid_t cp_p_stateid; /* copy of parent's stateid */ + clientid_t cp_p_clid; /* copy of parent's clid */ + time64_t cpntf_time; /* last time stateid used */ +}; + /* * Represents a delegation stateid. The nfs4_client holds references to these * and they are put when it is being destroyed or when the delegation is @@ -132,7 +152,7 @@ struct nfs4_delegation { struct list_head dl_recall_lru; /* delegation recalled */ struct nfs4_clnt_odstate *dl_clnt_odstate; u32 dl_type; - time_t dl_time; + time64_t dl_time; /* For recall: */ int dl_retries; struct nfsd4_callback dl_recall; @@ -310,7 +330,7 @@ struct nfs4_client { #endif struct xdr_netobj cl_name; /* id generated by client */ nfs4_verifier cl_verifier; /* generated by client */ - time_t cl_time; /* time of last lease renewal */ + time64_t cl_time; /* time of last lease renewal */ struct sockaddr_storage cl_addr; /* client ipaddress */ bool cl_mach_cred; /* SP4_MACH_CRED in force */ struct svc_cred cl_cred; /* setclientid principal */ @@ -320,7 +340,7 @@ struct nfs4_client { /* NFSv4.1 client implementation id: */ struct xdr_netobj cl_nii_domain; struct xdr_netobj cl_nii_name; - struct timespec cl_nii_time; + struct timespec64 cl_nii_time; /* for v4.0 and v4.1 callbacks: */ struct nfs4_cb_conn cl_cb_conn; @@ -449,7 +469,7 @@ struct nfs4_openowner { */ struct list_head oo_close_lru; struct nfs4_ol_stateid *oo_last_closed_stid; - time_t oo_time; /* time of placement on so_close_lru */ + time64_t oo_time; /* time of placement on so_close_lru */ #define NFS4_OO_CONFIRMED 1 unsigned char oo_flags; }; @@ -606,7 +626,7 @@ static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b) struct nfsd4_blocked_lock { struct list_head nbl_list; struct list_head nbl_lru; - unsigned long nbl_time; + time64_t nbl_time; struct file_lock nbl_lock; struct knfsd_fh nbl_fh; struct nfsd4_callback nbl_cb; @@ -618,14 +638,17 @@ struct nfsd4_copy; extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct svc_fh *fhp, - stateid_t *stateid, int flags, struct nfsd_file **filp); + stateid_t *stateid, int flags, struct nfsd_file **filp, + struct nfs4_stid **cstid); __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, void (*sc_free)(struct nfs4_stid *)); -int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy); -void nfs4_free_cp_state(struct nfsd4_copy *copy); +int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy); +void nfs4_free_copy_state(struct nfsd4_copy *copy); +struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, + struct nfs4_stid *p_stid); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); @@ -655,6 +678,11 @@ void put_nfs4_file(struct nfs4_file *fi); extern void nfs4_put_copy(struct nfsd4_copy *copy); extern struct nfsd4_copy * find_async_copy(struct nfs4_client *clp, stateid_t *staetid); +extern void nfs4_put_cpntf_state(struct nfsd_net *nn, + struct nfs4_cpntf_state *cps); +extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, + struct nfs4_client *clp, + struct nfs4_cpntf_state **cps); static inline void get_nfs4_file(struct nfs4_file *fi) { refcount_inc(&fi->fi_ref); diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 9bce3b913189..b1bc582b0493 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -84,17 +84,17 @@ static int nfsd_proc_open(struct inode *inode, struct file *file) return single_open(file, nfsd_proc_show, NULL); } -static const struct file_operations nfsd_proc_fops = { - .open = nfsd_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops nfsd_proc_ops = { + .proc_open = nfsd_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; void nfsd_stat_init(void) { - svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_fops); + svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops); } void diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index ffc78a0e28b2..06dd0d337049 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -166,6 +166,12 @@ DEFINE_STATEID_EVENT(layout_recall_done); DEFINE_STATEID_EVENT(layout_recall_fail); DEFINE_STATEID_EVENT(layout_recall_release); +TRACE_DEFINE_ENUM(NFSD_FILE_HASHED); +TRACE_DEFINE_ENUM(NFSD_FILE_PENDING); +TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ); +TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_WRITE); +TRACE_DEFINE_ENUM(NFSD_FILE_REFERENCED); + #define show_nf_flags(val) \ __print_flags(val, "|", \ { 1 << NFSD_FILE_HASHED, "HASHED" }, \ @@ -195,7 +201,7 @@ DECLARE_EVENT_CLASS(nfsd_file_class, TP_fast_assign( __entry->nf_hashval = nf->nf_hashval; __entry->nf_inode = nf->nf_inode; - __entry->nf_ref = atomic_read(&nf->nf_ref); + __entry->nf_ref = refcount_read(&nf->nf_ref); __entry->nf_flags = nf->nf_flags; __entry->nf_may = nf->nf_may; __entry->nf_file = nf->nf_file; @@ -228,7 +234,7 @@ TRACE_EVENT(nfsd_file_acquire, TP_ARGS(rqstp, hash, inode, may_flags, nf, status), TP_STRUCT__entry( - __field(__be32, xid) + __field(u32, xid) __field(unsigned int, hash) __field(void *, inode) __field(unsigned int, may_flags) @@ -236,27 +242,27 @@ TRACE_EVENT(nfsd_file_acquire, __field(unsigned long, nf_flags) __field(unsigned char, nf_may) __field(struct file *, nf_file) - __field(__be32, status) + __field(u32, status) ), TP_fast_assign( - __entry->xid = rqstp->rq_xid; + __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->hash = hash; __entry->inode = inode; __entry->may_flags = may_flags; - __entry->nf_ref = nf ? atomic_read(&nf->nf_ref) : 0; + __entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0; __entry->nf_flags = nf ? nf->nf_flags : 0; __entry->nf_may = nf ? nf->nf_may : 0; __entry->nf_file = nf ? nf->nf_file : NULL; - __entry->status = status; + __entry->status = be32_to_cpu(status); ), TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u", - be32_to_cpu(__entry->xid), __entry->hash, __entry->inode, + __entry->xid, __entry->hash, __entry->inode, show_nf_may(__entry->may_flags), __entry->nf_ref, show_nf_flags(__entry->nf_flags), show_nf_may(__entry->nf_may), __entry->nf_file, - be32_to_cpu(__entry->status)) + __entry->status) ); DECLARE_EVENT_CLASS(nfsd_file_search_class, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c0dc491537a6..0aa02eb18bd3 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -280,19 +280,25 @@ out: * Commit metadata changes to stable storage. */ static int -commit_metadata(struct svc_fh *fhp) +commit_inode_metadata(struct inode *inode) { - struct inode *inode = d_inode(fhp->fh_dentry); const struct export_operations *export_ops = inode->i_sb->s_export_op; - if (!EX_ISSYNC(fhp->fh_export)) - return 0; - if (export_ops->commit_metadata) return export_ops->commit_metadata(inode); return sync_inode_metadata(inode, 1); } +static int +commit_metadata(struct svc_fh *fhp) +{ + struct inode *inode = d_inode(fhp->fh_dentry); + + if (!EX_ISSYNC(fhp->fh_export)) + return 0; + return commit_inode_metadata(inode); +} + /* * Go over the attributes and take care of the small differences between * NFS semantics and what Linux expects. @@ -358,7 +364,7 @@ out_nfserrno: */ __be32 nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, - int check_guard, time_t guardtime) + int check_guard, time64_t guardtime) { struct dentry *dentry; struct inode *inode; @@ -524,23 +530,39 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif -__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, - u64 dst_pos, u64 count, bool sync) +__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, + struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync) { + struct file *src = nf_src->nf_file; + struct file *dst = nf_dst->nf_file; loff_t cloned; + __be32 ret = 0; + down_write(&nf_dst->nf_rwsem); cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); - if (cloned < 0) - return nfserrno(cloned); - if (count && cloned != count) - return nfserrno(-EINVAL); + if (cloned < 0) { + ret = nfserrno(cloned); + goto out_err; + } + if (count && cloned != count) { + ret = nfserrno(-EINVAL); + goto out_err; + } if (sync) { loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX; int status = vfs_fsync_range(dst, dst_pos, dst_end, 0); - if (status < 0) - return nfserrno(status); + + if (!status) + status = commit_inode_metadata(file_inode(src)); + if (status < 0) { + nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net, + nfsd_net_id)); + ret = nfserrno(status); + } } - return 0; +out_err: + up_write(&nf_dst->nf_rwsem); + return ret; } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, @@ -938,10 +960,12 @@ static int wait_for_concurrent_writes(struct file *file) } __be32 -nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, +nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, loff_t offset, struct kvec *vec, int vlen, - unsigned long *cnt, int stable) + unsigned long *cnt, int stable, + __be32 *verf) { + struct file *file = nf->nf_file; struct svc_export *exp; struct iov_iter iter; __be32 nfserr; @@ -972,9 +996,28 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, flags |= RWF_SYNC; iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); - host_err = vfs_iter_write(file, &iter, &pos, flags); - if (host_err < 0) + if (flags & RWF_SYNC) { + down_write(&nf->nf_rwsem); + host_err = vfs_iter_write(file, &iter, &pos, flags); + if (host_err < 0) + nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), + nfsd_net_id)); + up_write(&nf->nf_rwsem); + } else { + down_read(&nf->nf_rwsem); + if (verf) + nfsd_copy_boot_verifier(verf, + net_generic(SVC_NET(rqstp), + nfsd_net_id)); + host_err = vfs_iter_write(file, &iter, &pos, flags); + up_read(&nf->nf_rwsem); + } + if (host_err < 0) { + nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), + nfsd_net_id)); goto out_nfserr; + } + *cnt = host_err; nfsdstats.io_write += *cnt; fsnotify_modify(file); @@ -1036,7 +1079,8 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, */ __be32 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, - struct kvec *vec, int vlen, unsigned long *cnt, int stable) + struct kvec *vec, int vlen, unsigned long *cnt, int stable, + __be32 *verf) { struct nfsd_file *nf; __be32 err; @@ -1047,8 +1091,8 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, if (err) goto out; - err = nfsd_vfs_write(rqstp, fhp, nf->nf_file, offset, vec, - vlen, cnt, stable); + err = nfsd_vfs_write(rqstp, fhp, nf, offset, vec, + vlen, cnt, stable, verf); nfsd_file_put(nf); out: trace_nfsd_write_done(rqstp, fhp, offset, *cnt); @@ -1067,7 +1111,7 @@ out: */ __be32 nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, unsigned long count) + loff_t offset, unsigned long count, __be32 *verf) { struct nfsd_file *nf; loff_t end = LLONG_MAX; @@ -1086,10 +1130,14 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, if (err) goto out; if (EX_ISSYNC(fhp->fh_export)) { - int err2 = vfs_fsync_range(nf->nf_file, offset, end, 0); + int err2; + down_write(&nf->nf_rwsem); + err2 = vfs_fsync_range(nf->nf_file, offset, end, 0); switch (err2) { case 0: + nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net, + nfsd_net_id)); break; case -EINVAL: err = nfserr_notsupp; @@ -1099,7 +1147,10 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id)); } - } + up_write(&nf->nf_rwsem); + } else + nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net, + nfsd_net_id)); nfsd_file_put(nf); out: @@ -1123,7 +1174,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) iap->ia_valid &= ~(ATTR_UID|ATTR_GID); if (iap->ia_valid) - return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); + return nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0); /* Callers expect file metadata to be committed here */ return nfserrno(commit_metadata(resfhp)); } @@ -1386,7 +1437,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, && d_inode(dchild)->i_atime.tv_sec == v_atime && d_inode(dchild)->i_size == 0 ) { if (created) - *created = 1; + *created = true; break; } /* fall through */ @@ -1395,7 +1446,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, && d_inode(dchild)->i_atime.tv_sec == v_atime && d_inode(dchild)->i_size == 0 ) { if (created) - *created = 1; + *created = true; goto set_attr; } /* fall through */ @@ -1412,7 +1463,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } if (created) - *created = 1; + *created = true; nfsd_check_ignore_resizing(iap); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index cc110a10bfe8..3eb660ad80d1 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -34,6 +34,8 @@ #define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) #define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) +struct nfsd_file; + /* * Callback function for readdir */ @@ -48,15 +50,16 @@ __be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, const char *, unsigned int, struct svc_export **, struct dentry **); __be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, - struct iattr *, int, time_t); + struct iattr *, int, time64_t); int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, struct xdr_netobj *); __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); -__be32 nfsd4_clone_file_range(struct file *, u64, struct file *, - u64, u64, bool); +__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, + struct nfsd_file *nf_dst, u64 dst_pos, + u64 count, bool sync); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, @@ -71,7 +74,7 @@ __be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *, struct svc_fh *res, int createmode, u32 *verifier, bool *truncp, bool *created); __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, - loff_t, unsigned long); + loff_t, unsigned long, __be32 *verf); #endif /* CONFIG_NFSD_V3 */ int nfsd_open_break_lease(struct inode *, int); __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, @@ -91,11 +94,12 @@ __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, loff_t, struct kvec *, int, unsigned long *, u32 *eof); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t, - struct kvec *, int, unsigned long *, int); + struct kvec *, int, unsigned long *, + int stable, __be32 *verf); __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct file *file, loff_t offset, + struct nfsd_file *nf, loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt, - int stable); + int stable, __be32 *verf); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 99ff9f403ff1..4155fd71714c 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -14,7 +14,7 @@ struct nfsd3_sattrargs { struct svc_fh fh; struct iattr attrs; int check_guard; - time_t guardtime; + time64_t guardtime; }; struct nfsd3_diropargs { @@ -159,6 +159,7 @@ struct nfsd3_writeres { struct svc_fh fh; unsigned long count; int committed; + __be32 verf[2]; }; struct nfsd3_renameres { @@ -223,6 +224,7 @@ struct nfsd3_pathconfres { struct nfsd3_commitres { __be32 status; struct svc_fh fh; + __be32 verf[2]; }; struct nfsd3_getaclres { diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index f4737d66ee98..db63d39b1507 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -46,9 +46,9 @@ #define CURRENT_STATE_ID_FLAG (1<<0) #define SAVED_STATE_ID_FLAG (1<<1) -#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f)) -#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f)) -#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f)) +#define SET_CSTATE_FLAG(c, f) ((c)->sid_flags |= (f)) +#define HAS_CSTATE_FLAG(c, f) ((c)->sid_flags & (f)) +#define CLEAR_CSTATE_FLAG(c, f) ((c)->sid_flags &= ~(f)) struct nfsd4_compound_state { struct svc_fh current_fh; @@ -221,6 +221,7 @@ struct nfsd4_lookup { struct nfsd4_putfh { u32 pf_fhlen; /* request */ char *pf_fhval; /* request */ + bool no_verify; /* represents foreigh fh */ }; struct nfsd4_open { @@ -518,11 +519,13 @@ struct nfsd42_write_res { struct nfsd4_copy { /* request */ - stateid_t cp_src_stateid; - stateid_t cp_dst_stateid; - u64 cp_src_pos; - u64 cp_dst_pos; - u64 cp_count; + stateid_t cp_src_stateid; + stateid_t cp_dst_stateid; + u64 cp_src_pos; + u64 cp_dst_pos; + u64 cp_count; + struct nl4_server cp_src; + bool cp_intra; /* both */ bool cp_synchronous; @@ -540,13 +543,18 @@ struct nfsd4_copy { struct nfsd_file *nf_src; struct nfsd_file *nf_dst; - stateid_t cp_stateid; + copy_stateid_t cp_stateid; struct list_head copies; struct task_struct *copy_task; refcount_t refcount; bool stopped; + + struct vfsmount *ss_mnt; + struct nfs_fh c_fh; + nfs4_stateid stateid; }; +extern bool inter_copy_offload_enable; struct nfsd4_seek { /* request */ @@ -568,6 +576,18 @@ struct nfsd4_offload_status { u32 status; }; +struct nfsd4_copy_notify { + /* request */ + stateid_t cpn_src_stateid; + struct nl4_server cpn_dst; + + /* response */ + stateid_t cpn_cnr_stateid; + u64 cpn_sec; + u32 cpn_nsec; + struct nl4_server cpn_src; +}; + struct nfsd4_op { int opnum; const struct nfsd4_operation * opdesc; @@ -627,6 +647,7 @@ struct nfsd4_op { struct nfsd4_clone clone; struct nfsd4_copy copy; struct nfsd4_offload_status offload_status; + struct nfsd4_copy_notify copy_notify; struct nfsd4_seek seek; } u; struct nfs4_replay * replay; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 6c7388430ad3..d4359a1df3d5 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2899,18 +2899,12 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) ia_valid |= ATTR_MTIME | ATTR_CTIME; } } - if (ia_valid & ATTR_ATIME) { - vi->i_atime = timestamp_truncate(attr->ia_atime, - vi); - } - if (ia_valid & ATTR_MTIME) { - vi->i_mtime = timestamp_truncate(attr->ia_mtime, - vi); - } - if (ia_valid & ATTR_CTIME) { - vi->i_ctime = timestamp_truncate(attr->ia_ctime, - vi); - } + if (ia_valid & ATTR_ATIME) + vi->i_atime = attr->ia_atime; + if (ia_valid & ATTR_MTIME) + vi->i_mtime = attr->ia_mtime; + if (ia_valid & ATTR_CTIME) + vi->i_ctime = attr->ia_ctime; mark_inode_dirty(vi); out: return err; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9876db52913a..6cd5e4924e4d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2101,17 +2101,15 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, struct buffer_head **di_bh, int meta_level, - int overwrite_io, int write_sem, int wait) { int ret = 0; if (wait) - ret = ocfs2_inode_lock(inode, NULL, meta_level); + ret = ocfs2_inode_lock(inode, di_bh, meta_level); else - ret = ocfs2_try_inode_lock(inode, - overwrite_io ? NULL : di_bh, meta_level); + ret = ocfs2_try_inode_lock(inode, di_bh, meta_level); if (ret < 0) goto out; @@ -2136,6 +2134,7 @@ static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, out_unlock: brelse(*di_bh); + *di_bh = NULL; ocfs2_inode_unlock(inode, meta_level); out: return ret; @@ -2177,7 +2176,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file, ret = ocfs2_inode_lock_for_extent_tree(inode, &di_bh, meta_level, - overwrite_io, write_sem, wait); if (ret < 0) { @@ -2233,13 +2231,13 @@ static int ocfs2_prepare_inode_for_write(struct file *file, &di_bh, meta_level, write_sem); + meta_level = 1; + write_sem = 1; ret = ocfs2_inode_lock_for_extent_tree(inode, &di_bh, meta_level, - overwrite_io, - 1, + write_sem, wait); - write_sem = 1; if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 4180c3ef0a68..939df99d2dec 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -696,7 +696,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode, ac, cl); - if (IS_ERR(bg_bh) && (PTR_ERR(bg_bh) == -ENOSPC)) + if (PTR_ERR(bg_bh) == -ENOSPC) bg_bh = ocfs2_block_group_alloc_discontig(handle, alloc_inode, ac, cl); diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 25543a966c48..29eaa4544372 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -273,6 +273,7 @@ static void *help_start(struct seq_file *m, loff_t *pos) static void *help_next(struct seq_file *m, void *v, loff_t *pos) { + (*pos)++; gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_next: start\n"); return NULL; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 6220642fe113..9fc47c2e078d 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -24,7 +24,7 @@ static int ovl_ccup_set(const char *buf, const struct kernel_param *param) { - pr_warn("overlayfs: \"check_copy_up\" module option is obsolete\n"); + pr_warn("\"check_copy_up\" module option is obsolete\n"); return 0; } @@ -123,6 +123,9 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) loff_t old_pos = 0; loff_t new_pos = 0; loff_t cloned; + loff_t data_pos = -1; + loff_t hole_len; + bool skip_hole = false; int error = 0; if (len == 0) @@ -144,7 +147,11 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) goto out; /* Couldn't clone, so now we try to copy the data */ - /* FIXME: copy up sparse files efficiently */ + /* Check if lower fs supports seek operation */ + if (old_file->f_mode & FMODE_LSEEK && + old_file->f_op->llseek) + skip_hole = true; + while (len) { size_t this_len = OVL_COPY_UP_CHUNK_SIZE; long bytes; @@ -157,6 +164,36 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) break; } + /* + * Fill zero for hole will cost unnecessary disk space + * and meanwhile slow down the copy-up speed, so we do + * an optimization for hole during copy-up, it relies + * on SEEK_DATA implementation in lower fs so if lower + * fs does not support it, copy-up will behave as before. + * + * Detail logic of hole detection as below: + * When we detect next data position is larger than current + * position we will skip that hole, otherwise we copy + * data in the size of OVL_COPY_UP_CHUNK_SIZE. Actually, + * it may not recognize all kind of holes and sometimes + * only skips partial of hole area. However, it will be + * enough for most of the use cases. + */ + + if (skip_hole && data_pos < old_pos) { + data_pos = vfs_llseek(old_file, old_pos, SEEK_DATA); + if (data_pos > old_pos) { + hole_len = data_pos - old_pos; + len -= hole_len; + old_pos = new_pos = data_pos; + continue; + } else if (data_pos == -ENXIO) { + break; + } else if (data_pos < 0) { + skip_hole = false; + } + } + bytes = do_splice_direct(old_file, &old_pos, new_file, &new_pos, this_len, SPLICE_F_MOVE); @@ -480,7 +517,7 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp) } inode_lock(temp->d_inode); - if (c->metacopy) + if (S_ISREG(c->stat.mode)) err = ovl_set_size(temp, &c->stat); if (!err) err = ovl_set_attr(temp, &c->stat); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 29abdb1d3b5c..8e57d5372b8f 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -35,7 +35,7 @@ int ovl_cleanup(struct inode *wdir, struct dentry *wdentry) dput(wdentry); if (err) { - pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n", + pr_err("cleanup of '%pd2' failed (%i)\n", wdentry, err); } @@ -53,7 +53,7 @@ static struct dentry *ovl_lookup_temp(struct dentry *workdir) temp = lookup_one_len(name, workdir, strlen(name)); if (!IS_ERR(temp) && temp->d_inode) { - pr_err("overlayfs: workdir/%s already exists\n", name); + pr_err("workdir/%s already exists\n", name); dput(temp); temp = ERR_PTR(-EIO); } @@ -134,7 +134,7 @@ static int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, d = lookup_one_len(dentry->d_name.name, dentry->d_parent, dentry->d_name.len); if (IS_ERR(d)) { - pr_warn("overlayfs: failed lookup after mkdir (%pd2, err=%i).\n", + pr_warn("failed lookup after mkdir (%pd2, err=%i).\n", dentry, err); return PTR_ERR(d); } @@ -267,7 +267,7 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, d_instantiate(dentry, inode); if (inode != oip.newinode) { - pr_warn_ratelimited("overlayfs: newly created inode found in cache (%pd2)\n", + pr_warn_ratelimited("newly created inode found in cache (%pd2)\n", dentry); } @@ -1009,7 +1009,7 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) spin_unlock(&dentry->d_lock); } else { kfree(redirect); - pr_warn_ratelimited("overlayfs: failed to set redirect (%i)\n", + pr_warn_ratelimited("failed to set redirect (%i)\n", err); /* Fall back to userspace copy-up */ err = -EXDEV; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 70e55588aedc..6f54d70cef27 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -30,7 +30,7 @@ static int ovl_encode_maybe_copy_up(struct dentry *dentry) } if (err) { - pr_warn_ratelimited("overlayfs: failed to copy up on encode (%pd2, err=%i)\n", + pr_warn_ratelimited("failed to copy up on encode (%pd2, err=%i)\n", dentry, err); } @@ -244,7 +244,7 @@ out: return err; fail: - pr_warn_ratelimited("overlayfs: failed to encode file handle (%pd2, err=%i, buflen=%d, len=%d, type=%d)\n", + pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i, buflen=%d, len=%d, type=%d)\n", dentry, err, buflen, fh ? (int)fh->fb.len : 0, fh ? fh->fb.type : 0); goto out; @@ -358,7 +358,7 @@ static struct dentry *ovl_dentry_real_at(struct dentry *dentry, int idx) */ static struct dentry *ovl_lookup_real_one(struct dentry *connected, struct dentry *real, - struct ovl_layer *layer) + const struct ovl_layer *layer) { struct inode *dir = d_inode(connected); struct dentry *this, *parent = NULL; @@ -406,7 +406,7 @@ out: return this; fail: - pr_warn_ratelimited("overlayfs: failed to lookup one by real (%pd2, layer=%d, connected=%pd2, err=%i)\n", + pr_warn_ratelimited("failed to lookup one by real (%pd2, layer=%d, connected=%pd2, err=%i)\n", real, layer->idx, connected, err); this = ERR_PTR(err); goto out; @@ -414,17 +414,16 @@ fail: static struct dentry *ovl_lookup_real(struct super_block *sb, struct dentry *real, - struct ovl_layer *layer); + const struct ovl_layer *layer); /* * Lookup an indexed or hashed overlay dentry by real inode. */ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, struct dentry *real, - struct ovl_layer *layer) + const struct ovl_layer *layer) { struct ovl_fs *ofs = sb->s_fs_info; - struct ovl_layer upper_layer = { .mnt = ofs->upper_mnt }; struct dentry *index = NULL; struct dentry *this = NULL; struct inode *inode; @@ -466,7 +465,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, * recursive call walks back from indexed upper to the topmost * connected/hashed upper parent (or up to root). */ - this = ovl_lookup_real(sb, upper, &upper_layer); + this = ovl_lookup_real(sb, upper, &ofs->layers[0]); dput(upper); } @@ -487,7 +486,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, */ static struct dentry *ovl_lookup_real_ancestor(struct super_block *sb, struct dentry *real, - struct ovl_layer *layer) + const struct ovl_layer *layer) { struct dentry *next, *parent = NULL; struct dentry *ancestor = ERR_PTR(-EIO); @@ -540,7 +539,7 @@ static struct dentry *ovl_lookup_real_ancestor(struct super_block *sb, */ static struct dentry *ovl_lookup_real(struct super_block *sb, struct dentry *real, - struct ovl_layer *layer) + const struct ovl_layer *layer) { struct dentry *connected; int err = 0; @@ -631,7 +630,7 @@ static struct dentry *ovl_lookup_real(struct super_block *sb, return connected; fail: - pr_warn_ratelimited("overlayfs: failed to lookup by real (%pd2, layer=%d, connected=%pd2, err=%i)\n", + pr_warn_ratelimited("failed to lookup by real (%pd2, layer=%d, connected=%pd2, err=%i)\n", real, layer->idx, connected, err); dput(connected); return ERR_PTR(err); @@ -646,8 +645,7 @@ static struct dentry *ovl_get_dentry(struct super_block *sb, struct dentry *index) { struct ovl_fs *ofs = sb->s_fs_info; - struct ovl_layer upper_layer = { .mnt = ofs->upper_mnt }; - struct ovl_layer *layer = upper ? &upper_layer : lowerpath->layer; + const struct ovl_layer *layer = upper ? &ofs->layers[0] : lowerpath->layer; struct dentry *real = upper ?: (index ?: lowerpath->dentry); /* @@ -822,7 +820,7 @@ out: return dentry; out_err: - pr_warn_ratelimited("overlayfs: failed to decode file handle (len=%d, type=%d, flags=%x, err=%i)\n", + pr_warn_ratelimited("failed to decode file handle (len=%d, type=%d, flags=%x, err=%i)\n", fh_len, fh_type, flags, err); dentry = ERR_PTR(err); goto out; @@ -831,7 +829,7 @@ out_err: static struct dentry *ovl_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { - pr_warn_ratelimited("overlayfs: connectable file handles not supported; use 'no_subtree_check' exportfs option.\n"); + pr_warn_ratelimited("connectable file handles not supported; use 'no_subtree_check' exportfs option.\n"); return ERR_PTR(-EACCES); } diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index e235a635d9ec..a5317216de73 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -9,8 +9,19 @@ #include <linux/xattr.h> #include <linux/uio.h> #include <linux/uaccess.h> +#include <linux/splice.h> +#include <linux/mm.h> +#include <linux/fs.h> #include "overlayfs.h" +struct ovl_aio_req { + struct kiocb iocb; + struct kiocb *orig_iocb; + struct fd fd; +}; + +static struct kmem_cache *ovl_aio_request_cachep; + static char ovl_whatisit(struct inode *inode, struct inode *realinode) { if (realinode != ovl_inode_upper(inode)) @@ -146,7 +157,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) struct inode *inode = file_inode(file); struct fd real; const struct cred *old_cred; - ssize_t ret; + loff_t ret; /* * The two special cases below do not need to involve real fs, @@ -171,7 +182,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) * limitations that are more strict than ->s_maxbytes for specific * files, so we use the real file to perform seeks. */ - inode_lock(inode); + ovl_inode_lock(inode); real.file->f_pos = file->f_pos; old_cred = ovl_override_creds(inode->i_sb); @@ -179,7 +190,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) revert_creds(old_cred); file->f_pos = real.file->f_pos; - inode_unlock(inode); + ovl_inode_unlock(inode); fdput(real); @@ -225,6 +236,33 @@ static rwf_t ovl_iocb_to_rwf(struct kiocb *iocb) return flags; } +static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) +{ + struct kiocb *iocb = &aio_req->iocb; + struct kiocb *orig_iocb = aio_req->orig_iocb; + + if (iocb->ki_flags & IOCB_WRITE) { + struct inode *inode = file_inode(orig_iocb->ki_filp); + + file_end_write(iocb->ki_filp); + ovl_copyattr(ovl_inode_real(inode), inode); + } + + orig_iocb->ki_pos = iocb->ki_pos; + fdput(aio_req->fd); + kmem_cache_free(ovl_aio_request_cachep, aio_req); +} + +static void ovl_aio_rw_complete(struct kiocb *iocb, long res, long res2) +{ + struct ovl_aio_req *aio_req = container_of(iocb, + struct ovl_aio_req, iocb); + struct kiocb *orig_iocb = aio_req->orig_iocb; + + ovl_aio_cleanup_handler(aio_req); + orig_iocb->ki_complete(orig_iocb, res, res2); +} + static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; @@ -240,10 +278,28 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) return ret; old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, - ovl_iocb_to_rwf(iocb)); + if (is_sync_kiocb(iocb)) { + ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, + ovl_iocb_to_rwf(iocb)); + } else { + struct ovl_aio_req *aio_req; + + ret = -ENOMEM; + aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL); + if (!aio_req) + goto out; + + aio_req->fd = real; + real.flags = 0; + aio_req->orig_iocb = iocb; + kiocb_clone(&aio_req->iocb, iocb, real.file); + aio_req->iocb.ki_complete = ovl_aio_rw_complete; + ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter); + if (ret != -EIOCBQUEUED) + ovl_aio_cleanup_handler(aio_req); + } +out: revert_creds(old_cred); - ovl_file_accessed(file); fdput(real); @@ -274,15 +330,33 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); - file_start_write(real.file); - ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, - ovl_iocb_to_rwf(iocb)); - file_end_write(real.file); + if (is_sync_kiocb(iocb)) { + file_start_write(real.file); + ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, + ovl_iocb_to_rwf(iocb)); + file_end_write(real.file); + /* Update size */ + ovl_copyattr(ovl_inode_real(inode), inode); + } else { + struct ovl_aio_req *aio_req; + + ret = -ENOMEM; + aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL); + if (!aio_req) + goto out; + + file_start_write(real.file); + aio_req->fd = real; + real.flags = 0; + aio_req->orig_iocb = iocb; + kiocb_clone(&aio_req->iocb, iocb, real.file); + aio_req->iocb.ki_complete = ovl_aio_rw_complete; + ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter); + if (ret != -EIOCBQUEUED) + ovl_aio_cleanup_handler(aio_req); + } +out: revert_creds(old_cred); - - /* Update size */ - ovl_copyattr(ovl_inode_real(inode), inode); - fdput(real); out_unlock: @@ -291,6 +365,48 @@ out_unlock: return ret; } +static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t ret; + struct fd real; + const struct cred *old_cred; + + ret = ovl_real_fdget(in, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(in)->i_sb); + ret = generic_file_splice_read(real.file, ppos, pipe, len, flags); + revert_creds(old_cred); + + ovl_file_accessed(in); + fdput(real); + return ret; +} + +static ssize_t +ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) +{ + struct fd real; + const struct cred *old_cred; + ssize_t ret; + + ret = ovl_real_fdget(out, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(out)->i_sb); + ret = iter_file_splice_write(pipe, real.file, ppos, len, flags); + revert_creds(old_cred); + + ovl_file_accessed(out); + fdput(real); + return ret; +} + static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct fd real; @@ -647,7 +763,25 @@ const struct file_operations ovl_file_operations = { .fadvise = ovl_fadvise, .unlocked_ioctl = ovl_ioctl, .compat_ioctl = ovl_compat_ioctl, + .splice_read = ovl_splice_read, + .splice_write = ovl_splice_write, .copy_file_range = ovl_copy_file_range, .remap_file_range = ovl_remap_file_range, }; + +int __init ovl_aio_request_cache_init(void) +{ + ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req", + sizeof(struct ovl_aio_req), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!ovl_aio_request_cachep) + return -ENOMEM; + + return 0; +} + +void ovl_aio_request_cache_destroy(void) +{ + kmem_cache_destroy(ovl_aio_request_cachep); +} diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b045cf1826fc..79e8994e3bc1 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -75,10 +75,9 @@ out: return err; } -static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, - struct ovl_layer *lower_layer) +static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) { - bool samefs = ovl_same_sb(dentry->d_sb); + bool samefs = ovl_same_fs(dentry->d_sb); unsigned int xinobits = ovl_xino_bits(dentry->d_sb); if (samefs) { @@ -100,12 +99,10 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, * persistent for a given layer configuration. */ if (stat->ino >> shift) { - pr_warn_ratelimited("overlayfs: inode number too big (%pd2, ino=%llu, xinobits=%d)\n", + pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n", dentry, stat->ino, xinobits); } else { - if (lower_layer) - stat->ino |= ((u64)lower_layer->fsid) << shift; - + stat->ino |= ((u64)fsid) << shift; stat->dev = dentry->d_sb->s_dev; return 0; } @@ -124,15 +121,14 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, */ stat->dev = dentry->d_sb->s_dev; stat->ino = dentry->d_inode->i_ino; - } else if (lower_layer && lower_layer->fsid) { + } else { /* * For non-samefs setup, if we cannot map all layers st_ino * to a unified address space, we need to make sure that st_dev - * is unique per lower fs. Upper layer uses real st_dev and - * lower layers use the unique anonymous bdev assigned to the - * lower fs. + * is unique per underlying fs, so we use the unique anonymous + * bdev assigned to the underlying fs. */ - stat->dev = lower_layer->fs->pseudo_dev; + stat->dev = OVL_FS(dentry->d_sb)->fs[fsid].pseudo_dev; } return 0; @@ -146,8 +142,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat, struct path realpath; const struct cred *old_cred; bool is_dir = S_ISDIR(dentry->d_inode->i_mode); - bool samefs = ovl_same_sb(dentry->d_sb); - struct ovl_layer *lower_layer = NULL; + int fsid = 0; int err; bool metacopy_blocks = false; @@ -168,9 +163,9 @@ int ovl_getattr(const struct path *path, struct kstat *stat, * If lower filesystem supports NFS file handles, this also guaranties * persistent st_ino across mount cycle. */ - if (!is_dir || samefs || ovl_xino_bits(dentry->d_sb)) { + if (!is_dir || ovl_same_dev(dentry->d_sb)) { if (!OVL_TYPE_UPPER(type)) { - lower_layer = ovl_layer_lower(dentry); + fsid = ovl_layer_lower(dentry)->fsid; } else if (OVL_TYPE_ORIGIN(type)) { struct kstat lowerstat; u32 lowermask = STATX_INO | STATX_BLOCKS | @@ -200,14 +195,8 @@ int ovl_getattr(const struct path *path, struct kstat *stat, if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) || (!ovl_verify_lower(dentry->d_sb) && (is_dir || lowerstat.nlink == 1))) { - lower_layer = ovl_layer_lower(dentry); - /* - * Cannot use origin st_dev;st_ino because - * origin inode content may differ from overlay - * inode content. - */ - if (samefs || lower_layer->fsid) - stat->ino = lowerstat.ino; + fsid = ovl_layer_lower(dentry)->fsid; + stat->ino = lowerstat.ino; } /* @@ -241,7 +230,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat, } } - err = ovl_map_dev_ino(dentry, stat, lower_layer); + err = ovl_map_dev_ino(dentry, stat, fsid); if (err) goto out; @@ -527,6 +516,27 @@ static const struct address_space_operations ovl_aops = { * [...] &ovl_i_mutex_dir_key[depth] (stack_depth=2) * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1) * [...] &type->i_mutex_dir_key (stack_depth=0) + * + * Locking order w.r.t ovl_want_write() is important for nested overlayfs. + * + * This chain is valid: + * - inode->i_rwsem (inode_lock[2]) + * - upper_mnt->mnt_sb->s_writers (ovl_want_write[0]) + * - OVL_I(inode)->lock (ovl_inode_lock[2]) + * - OVL_I(lowerinode)->lock (ovl_inode_lock[1]) + * + * And this chain is valid: + * - inode->i_rwsem (inode_lock[2]) + * - OVL_I(inode)->lock (ovl_inode_lock[2]) + * - lowerinode->i_rwsem (inode_lock[1]) + * - OVL_I(lowerinode)->lock (ovl_inode_lock[1]) + * + * But lowerinode->i_rwsem SHOULD NOT be acquired while ovl_want_write() is + * held, because it is in reverse order of the non-nested case using the same + * upper fs: + * - inode->i_rwsem (inode_lock[1]) + * - upper_mnt->mnt_sb->s_writers (ovl_want_write[0]) + * - OVL_I(inode)->lock (ovl_inode_lock[1]) */ #define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH @@ -565,7 +575,7 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real * upper inode i_ino on ovl_inode_init() or ovl_inode_update(). */ - if (ovl_same_sb(inode->i_sb) || xinobits) { + if (ovl_same_dev(inode->i_sb)) { inode->i_ino = ino; if (xinobits && fsid && !(ino >> (64 - xinobits))) inode->i_ino |= (unsigned long)fsid << (64 - xinobits); @@ -698,7 +708,7 @@ unsigned int ovl_get_nlink(struct dentry *lowerdentry, return nlink; fail: - pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n", + pr_warn_ratelimited("failed to get index nlink (%pd2, err=%i)\n", upperdentry, err); return fallback; } @@ -969,7 +979,7 @@ out: return inode; out_err: - pr_warn_ratelimited("overlayfs: failed to get inode (%i)\n", err); + pr_warn_ratelimited("failed to get inode (%i)\n", err); inode = ERR_PTR(err); goto out; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 76ff66339173..ed9e129fae04 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -141,10 +141,10 @@ out: return NULL; fail: - pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res); + pr_warn_ratelimited("failed to get origin (%i)\n", res); goto out; invalid: - pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh); + pr_warn_ratelimited("invalid origin (%*phN)\n", res, fh); goto out; } @@ -322,16 +322,16 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, struct dentry *origin = NULL; int i; - for (i = 0; i < ofs->numlower; i++) { + for (i = 1; i < ofs->numlayer; i++) { /* * If lower fs uuid is not unique among lower fs we cannot match * fh->uuid to layer. */ - if (ofs->lower_layers[i].fsid && - ofs->lower_layers[i].fs->bad_uuid) + if (ofs->layers[i].fsid && + ofs->layers[i].fs->bad_uuid) continue; - origin = ovl_decode_real_fh(fh, ofs->lower_layers[i].mnt, + origin = ovl_decode_real_fh(fh, ofs->layers[i].mnt, connected); if (origin) break; @@ -354,13 +354,13 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, } **stackp = (struct ovl_path){ .dentry = origin, - .layer = &ofs->lower_layers[i] + .layer = &ofs->layers[i] }; return 0; invalid: - pr_warn_ratelimited("overlayfs: invalid origin (%pd2, ftype=%x, origin ftype=%x).\n", + pr_warn_ratelimited("invalid origin (%pd2, ftype=%x, origin ftype=%x).\n", upperdentry, d_inode(upperdentry)->i_mode & S_IFMT, d_inode(origin)->i_mode & S_IFMT); dput(origin); @@ -449,7 +449,7 @@ out: fail: inode = d_inode(real); - pr_warn_ratelimited("overlayfs: failed to verify %s (%pd2, ino=%lu, err=%i)\n", + pr_warn_ratelimited("failed to verify %s (%pd2, ino=%lu, err=%i)\n", is_upper ? "upper" : "origin", real, inode ? inode->i_ino : 0, err); goto out; @@ -475,7 +475,7 @@ struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index) return upper ?: ERR_PTR(-ESTALE); if (!d_is_dir(upper)) { - pr_warn_ratelimited("overlayfs: invalid index upper (%pd2, upper=%pd2).\n", + pr_warn_ratelimited("invalid index upper (%pd2, upper=%pd2).\n", index, upper); dput(upper); return ERR_PTR(-EIO); @@ -589,12 +589,12 @@ out: return err; fail: - pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n", + pr_warn_ratelimited("failed to verify index (%pd2, ftype=%x, err=%i)\n", index, d_inode(index)->i_mode & S_IFMT, err); goto out; orphan: - pr_warn_ratelimited("overlayfs: orphan index entry (%pd2, ftype=%x, nlink=%u)\n", + pr_warn_ratelimited("orphan index entry (%pd2, ftype=%x, nlink=%u)\n", index, d_inode(index)->i_mode & S_IFMT, d_inode(index)->i_nlink); err = -ENOENT; @@ -696,7 +696,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, index = NULL; goto out; } - pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n" + pr_warn_ratelimited("failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n" "overlayfs: mount with '-o index=off' to disable inodes index.\n", d_inode(origin)->i_ino, name.len, name.name, err); @@ -723,13 +723,13 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, * unlinked, which means that finding a lower origin on lookup * whose index is a whiteout should be treated as an error. */ - pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n", + pr_warn_ratelimited("bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n", index, d_inode(index)->i_mode & S_IFMT, d_inode(origin)->i_mode & S_IFMT); goto fail; } else if (is_dir && verify) { if (!upper) { - pr_warn_ratelimited("overlayfs: suspected uncovered redirected dir found (origin=%pd2, index=%pd2).\n", + pr_warn_ratelimited("suspected uncovered redirected dir found (origin=%pd2, index=%pd2).\n", origin, index); goto fail; } @@ -738,7 +738,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, err = ovl_verify_upper(index, upper, false); if (err) { if (err == -ESTALE) { - pr_warn_ratelimited("overlayfs: suspected multiply redirected dir found (upper=%pd2, origin=%pd2, index=%pd2).\n", + pr_warn_ratelimited("suspected multiply redirected dir found (upper=%pd2, origin=%pd2, index=%pd2).\n", upper, origin, index); } goto fail; @@ -885,7 +885,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (!d.stop && poe->numlower) { err = -ENOMEM; - stack = kcalloc(ofs->numlower, sizeof(struct ovl_path), + stack = kcalloc(ofs->numlayer - 1, sizeof(struct ovl_path), GFP_KERNEL); if (!stack) goto out_put_upper; @@ -967,7 +967,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, */ err = -EPERM; if (d.redirect && !ofs->config.redirect_follow) { - pr_warn_ratelimited("overlayfs: refusing to follow redirect for (%pd2)\n", + pr_warn_ratelimited("refusing to follow redirect for (%pd2)\n", dentry); goto out_put; } @@ -994,7 +994,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, err = -EPERM; if (!ofs->config.metacopy) { - pr_warn_ratelimited("overlay: refusing to follow metacopy origin for (%pd2)\n", + pr_warn_ratelimited("refusing to follow metacopy origin for (%pd2)\n", dentry); goto out_put; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index f283b1d69a9e..3623d28aa4fa 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -9,6 +9,9 @@ #include <linux/fs.h> #include "ovl_entry.h" +#undef pr_fmt +#define pr_fmt(fmt) "overlayfs: " fmt + enum ovl_path_type { __OVL_PATH_UPPER = (1 << 0), __OVL_PATH_MERGE = (1 << 1), @@ -221,7 +224,6 @@ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); -struct super_block *ovl_same_sb(struct super_block *sb); int ovl_can_decode_fh(struct super_block *sb); struct dentry *ovl_indexdir(struct super_block *sb); bool ovl_index_all(struct super_block *sb); @@ -237,7 +239,7 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); struct dentry *ovl_dentry_upper(struct dentry *dentry); struct dentry *ovl_dentry_lower(struct dentry *dentry); struct dentry *ovl_dentry_lowerdata(struct dentry *dentry); -struct ovl_layer *ovl_layer_lower(struct dentry *dentry); +const struct ovl_layer *ovl_layer_lower(struct dentry *dentry); struct dentry *ovl_dentry_real(struct dentry *dentry); struct dentry *ovl_i_dentry_upper(struct inode *inode); struct inode *ovl_inode_upper(struct inode *inode); @@ -299,11 +301,21 @@ static inline bool ovl_is_impuredir(struct dentry *dentry) return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE); } -static inline unsigned int ovl_xino_bits(struct super_block *sb) +/* All layers on same fs? */ +static inline bool ovl_same_fs(struct super_block *sb) +{ + return OVL_FS(sb)->xino_mode == 0; +} + +/* All overlay inodes have same st_dev? */ +static inline bool ovl_same_dev(struct super_block *sb) { - struct ovl_fs *ofs = sb->s_fs_info; + return OVL_FS(sb)->xino_mode >= 0; +} - return ofs->xino_bits; +static inline unsigned int ovl_xino_bits(struct super_block *sb) +{ + return ovl_same_dev(sb) ? OVL_FS(sb)->xino_mode : 0; } static inline int ovl_inode_lock(struct inode *inode) @@ -438,6 +450,8 @@ struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr); /* file.c */ extern const struct file_operations ovl_file_operations; +int __init ovl_aio_request_cache_init(void); +void ovl_aio_request_cache_destroy(void); /* copy_up.c */ int ovl_copy_up(struct dentry *dentry); diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 28348c44ea5b..89015ea822e7 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -24,6 +24,8 @@ struct ovl_sb { dev_t pseudo_dev; /* Unusable (conflicting) uuid */ bool bad_uuid; + /* Used as a lower layer (but maybe also as upper) */ + bool is_lower; }; struct ovl_layer { @@ -38,18 +40,18 @@ struct ovl_layer { }; struct ovl_path { - struct ovl_layer *layer; + const struct ovl_layer *layer; struct dentry *dentry; }; /* private information held for overlayfs's superblock */ struct ovl_fs { struct vfsmount *upper_mnt; - unsigned int numlower; - /* Number of unique lower sb that differ from upper sb */ - unsigned int numlowerfs; - struct ovl_layer *lower_layers; - struct ovl_sb *lower_fs; + unsigned int numlayer; + /* Number of unique fs among layers including upper fs */ + unsigned int numfs; + const struct ovl_layer *layers; + struct ovl_sb *fs; /* workbasedir is the path at workdir= mount option */ struct dentry *workbasedir; /* workdir is the 'work' directory under workbasedir */ @@ -71,10 +73,15 @@ struct ovl_fs { struct inode *workbasedir_trap; struct inode *workdir_trap; struct inode *indexdir_trap; - /* Inode numbers in all layers do not use the high xino_bits */ - unsigned int xino_bits; + /* -1: disabled, 0: same fs, 1..32: number of unused ino bits */ + int xino_mode; }; +static inline struct ovl_fs *OVL_FS(struct super_block *sb) +{ + return (struct ovl_fs *)sb->s_fs_info; +} + /* private information held for every overlayfs dentry */ struct ovl_entry { union { diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 47a91c9733a5..40ac9ce2465a 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -441,7 +441,7 @@ static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid, const char *name, int namelen) { if (ino >> (64 - xinobits)) { - pr_warn_ratelimited("overlayfs: d_ino too big (%.*s, ino=%llu, xinobits=%d)\n", + pr_warn_ratelimited("d_ino too big (%.*s, ino=%llu, xinobits=%d)\n", namelen, name, ino, xinobits); return ino; } @@ -469,7 +469,7 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p) int xinobits = ovl_xino_bits(dir->d_sb); int err = 0; - if (!ovl_same_sb(dir->d_sb) && !xinobits) + if (!ovl_same_dev(dir->d_sb)) goto out; if (p->name[0] == '.') { @@ -504,7 +504,13 @@ get: if (err) goto fail; - WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev); + /* + * Directory inode is always on overlay st_dev. + * Non-dir with ovl_same_dev() could be on pseudo st_dev in case + * of xino bits overflow. + */ + WARN_ON_ONCE(S_ISDIR(stat.mode) && + dir->d_sb->s_dev != stat.dev); ino = stat.ino; } else if (xinobits && !OVL_TYPE_UPPER(type)) { ino = ovl_remap_lower_ino(ino, xinobits, @@ -518,7 +524,7 @@ out: return err; fail: - pr_warn_ratelimited("overlayfs: failed to look up (%s) for ino (%i)\n", + pr_warn_ratelimited("failed to look up (%s) for ino (%i)\n", p->name, err); goto out; } @@ -685,7 +691,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) int err; struct ovl_dir_file *od = file->private_data; struct dentry *dir = file->f_path.dentry; - struct ovl_layer *lower_layer = ovl_layer_lower(dir); + const struct ovl_layer *lower_layer = ovl_layer_lower(dir); struct ovl_readdir_translate rdt = { .ctx.actor = ovl_fill_real, .orig_ctx = ctx, @@ -738,7 +744,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) * entries. */ if (ovl_xino_bits(dentry->d_sb) || - (ovl_same_sb(dentry->d_sb) && + (ovl_same_fs(dentry->d_sb) && (ovl_is_impure_dir(file) || OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) { return ovl_iterate_real(file, ctx); @@ -965,7 +971,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) dentry = lookup_one_len(p->name, upper, p->len); if (IS_ERR(dentry)) { - pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n", + pr_err("lookup '%s/%.*s' failed (%i)\n", upper->d_name.name, p->len, p->name, (int) PTR_ERR(dentry)); continue; @@ -1147,6 +1153,6 @@ next: out: ovl_cache_free(&list); if (err) - pr_err("overlayfs: failed index dir cleanup (%i)\n", err); + pr_err("failed index dir cleanup (%i)\n", err); return err; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 7621ff176d15..319fe0d355b0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -224,14 +224,14 @@ static void ovl_free_fs(struct ovl_fs *ofs) if (ofs->upperdir_locked) ovl_inuse_unlock(ofs->upper_mnt->mnt_root); mntput(ofs->upper_mnt); - for (i = 0; i < ofs->numlower; i++) { - iput(ofs->lower_layers[i].trap); - mntput(ofs->lower_layers[i].mnt); + for (i = 1; i < ofs->numlayer; i++) { + iput(ofs->layers[i].trap); + mntput(ofs->layers[i].mnt); } - for (i = 0; i < ofs->numlowerfs; i++) - free_anon_bdev(ofs->lower_fs[i].pseudo_dev); - kfree(ofs->lower_layers); - kfree(ofs->lower_fs); + kfree(ofs->layers); + for (i = 0; i < ofs->numfs; i++) + free_anon_bdev(ofs->fs[i].pseudo_dev); + kfree(ofs->fs); kfree(ofs->config.lowerdir); kfree(ofs->config.upperdir); @@ -358,7 +358,7 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) if (ofs->config.nfs_export != ovl_nfs_export_def) seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ? "on" : "off"); - if (ofs->config.xino != ovl_xino_def()) + if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(sb)) seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]); if (ofs->config.metacopy != ovl_metacopy_def) seq_printf(m, ",metacopy=%s", @@ -462,7 +462,7 @@ static int ovl_parse_redirect_mode(struct ovl_config *config, const char *mode) if (ovl_redirect_always_follow) config->redirect_follow = true; } else if (strcmp(mode, "nofollow") != 0) { - pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n", + pr_err("bad mount option \"redirect_dir=%s\"\n", mode); return -EINVAL; } @@ -560,14 +560,15 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) break; default: - pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p); + pr_err("unrecognized mount option \"%s\" or missing value\n", + p); return -EINVAL; } } /* Workdir is useless in non-upper mount */ if (!config->upperdir && config->workdir) { - pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n", + pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n", config->workdir); kfree(config->workdir); config->workdir = NULL; @@ -587,7 +588,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) /* Resolve metacopy -> redirect_dir dependency */ if (config->metacopy && !config->redirect_dir) { if (metacopy_opt && redirect_opt) { - pr_err("overlayfs: conflicting options: metacopy=on,redirect_dir=%s\n", + pr_err("conflicting options: metacopy=on,redirect_dir=%s\n", config->redirect_mode); return -EINVAL; } @@ -596,7 +597,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) * There was an explicit redirect_dir=... that resulted * in this conflict. */ - pr_info("overlayfs: disabling metacopy due to redirect_dir=%s\n", + pr_info("disabling metacopy due to redirect_dir=%s\n", config->redirect_mode); config->metacopy = false; } else { @@ -692,7 +693,7 @@ out_unlock: out_dput: dput(work); out_err: - pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n", + pr_warn("failed to create directory %s/%s (errno: %i); mounting read-only\n", ofs->config.workdir, name, -err); work = NULL; goto out_unlock; @@ -716,21 +717,21 @@ static int ovl_mount_dir_noesc(const char *name, struct path *path) int err = -EINVAL; if (!*name) { - pr_err("overlayfs: empty lowerdir\n"); + pr_err("empty lowerdir\n"); goto out; } err = kern_path(name, LOOKUP_FOLLOW, path); if (err) { - pr_err("overlayfs: failed to resolve '%s': %i\n", name, err); + pr_err("failed to resolve '%s': %i\n", name, err); goto out; } err = -EINVAL; if (ovl_dentry_weird(path->dentry)) { - pr_err("overlayfs: filesystem on '%s' not supported\n", name); + pr_err("filesystem on '%s' not supported\n", name); goto out_put; } if (!d_is_dir(path->dentry)) { - pr_err("overlayfs: '%s' not a directory\n", name); + pr_err("'%s' not a directory\n", name); goto out_put; } return 0; @@ -752,7 +753,7 @@ static int ovl_mount_dir(const char *name, struct path *path) if (!err) if (ovl_dentry_remote(path->dentry)) { - pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n", + pr_err("filesystem on '%s' not supported as upperdir\n", tmp); path_put_init(path); err = -EINVAL; @@ -769,7 +770,7 @@ static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs, int err = vfs_statfs(path, &statfs); if (err) - pr_err("overlayfs: statfs failed on '%s'\n", name); + pr_err("statfs failed on '%s'\n", name); else ofs->namelen = max(ofs->namelen, statfs.f_namelen); @@ -804,13 +805,13 @@ static int ovl_lower_dir(const char *name, struct path *path, (ofs->config.index && ofs->config.upperdir)) && !fh_type) { ofs->config.index = false; ofs->config.nfs_export = false; - pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n", + pr_warn("fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n", name); } /* Check if lower fs has 32bit inode numbers */ if (fh_type != FILEID_INO32_GEN) - ofs->xino_bits = 0; + ofs->xino_mode = -1; return 0; @@ -996,7 +997,7 @@ static int ovl_setup_trap(struct super_block *sb, struct dentry *dir, err = PTR_ERR_OR_ZERO(trap); if (err) { if (err == -ELOOP) - pr_err("overlayfs: conflicting %s path\n", name); + pr_err("conflicting %s path\n", name); return err; } @@ -1013,11 +1014,11 @@ static int ovl_setup_trap(struct super_block *sb, struct dentry *dir, static int ovl_report_in_use(struct ovl_fs *ofs, const char *name) { if (ofs->config.index) { - pr_err("overlayfs: %s is in-use as upperdir/workdir of another mount, mount with '-o index=off' to override exclusive upperdir protection.\n", + pr_err("%s is in-use as upperdir/workdir of another mount, mount with '-o index=off' to override exclusive upperdir protection.\n", name); return -EBUSY; } else { - pr_warn("overlayfs: %s is in-use as upperdir/workdir of another mount, accessing files from both mounts will result in undefined behavior.\n", + pr_warn("%s is in-use as upperdir/workdir of another mount, accessing files from both mounts will result in undefined behavior.\n", name); return 0; } @@ -1035,7 +1036,7 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs, /* Upper fs should not be r/o */ if (sb_rdonly(upperpath->mnt->mnt_sb)) { - pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n"); + pr_err("upper fs is r/o, try multi-lower layers mount\n"); err = -EINVAL; goto out; } @@ -1052,7 +1053,7 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs, upper_mnt = clone_private_mount(upperpath); err = PTR_ERR(upper_mnt); if (IS_ERR(upper_mnt)) { - pr_err("overlayfs: failed to clone upperpath\n"); + pr_err("failed to clone upperpath\n"); goto out; } @@ -1108,7 +1109,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, * kernel upgrade. So warn instead of erroring out. */ if (!err) - pr_warn("overlayfs: upper fs needs to support d_type.\n"); + pr_warn("upper fs needs to support d_type.\n"); /* Check if upper/work fs supports O_TMPFILE */ temp = ovl_do_tmpfile(ofs->workdir, S_IFREG | 0); @@ -1116,7 +1117,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, if (ofs->tmpfile) dput(temp); else - pr_warn("overlayfs: upper fs does not support tmpfile.\n"); + pr_warn("upper fs does not support tmpfile.\n"); /* * Check if upper/work fs supports trusted.overlay.* xattr @@ -1126,7 +1127,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, ofs->noxattr = true; ofs->config.index = false; ofs->config.metacopy = false; - pr_warn("overlayfs: upper fs does not support xattr, falling back to index=off and metacopy=off.\n"); + pr_warn("upper fs does not support xattr, falling back to index=off and metacopy=off.\n"); err = 0; } else { vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE); @@ -1136,16 +1137,16 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, fh_type = ovl_can_decode_fh(ofs->workdir->d_sb); if (ofs->config.index && !fh_type) { ofs->config.index = false; - pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n"); + pr_warn("upper fs does not support file handles, falling back to index=off.\n"); } /* Check if upper fs has 32bit inode numbers */ if (fh_type != FILEID_INO32_GEN) - ofs->xino_bits = 0; + ofs->xino_mode = -1; /* NFS export of r/w mount depends on index */ if (ofs->config.nfs_export && !ofs->config.index) { - pr_warn("overlayfs: NFS export requires \"index=on\", falling back to nfs_export=off.\n"); + pr_warn("NFS export requires \"index=on\", falling back to nfs_export=off.\n"); ofs->config.nfs_export = false; } out: @@ -1165,11 +1166,11 @@ static int ovl_get_workdir(struct super_block *sb, struct ovl_fs *ofs, err = -EINVAL; if (upperpath->mnt != workpath.mnt) { - pr_err("overlayfs: workdir and upperdir must reside under the same mount\n"); + pr_err("workdir and upperdir must reside under the same mount\n"); goto out; } if (!ovl_workdir_ok(workpath.dentry, upperpath->dentry)) { - pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); + pr_err("workdir and upperdir must be separate subtrees\n"); goto out; } @@ -1210,7 +1211,7 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, err = ovl_verify_origin(upperpath->dentry, oe->lowerstack[0].dentry, true); if (err) { - pr_err("overlayfs: failed to verify upper root origin\n"); + pr_err("failed to verify upper root origin\n"); goto out; } @@ -1233,18 +1234,18 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, err = ovl_verify_set_fh(ofs->indexdir, OVL_XATTR_ORIGIN, upperpath->dentry, true, false); if (err) - pr_err("overlayfs: failed to verify index dir 'origin' xattr\n"); + pr_err("failed to verify index dir 'origin' xattr\n"); } err = ovl_verify_upper(ofs->indexdir, upperpath->dentry, true); if (err) - pr_err("overlayfs: failed to verify index dir 'upper' xattr\n"); + pr_err("failed to verify index dir 'upper' xattr\n"); /* Cleanup bad/stale/orphan index entries */ if (!err) err = ovl_indexdir_cleanup(ofs); } if (err || !ofs->indexdir) - pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n"); + pr_warn("try deleting index dir or mounting with '-o index=off' to disable inodes index.\n"); out: mnt_drop_write(mnt); @@ -1258,7 +1259,7 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) if (!ofs->config.nfs_export && !ofs->upper_mnt) return true; - for (i = 0; i < ofs->numlowerfs; i++) { + for (i = 0; i < ofs->numfs; i++) { /* * We use uuid to associate an overlay lower file handle with a * lower layer, so we can accept lower fs with null uuid as long @@ -1266,8 +1267,9 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) * if we detect multiple lower fs with the same uuid, we * disable lower file handle decoding on all of them. */ - if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) { - ofs->lower_fs[i].bad_uuid = true; + if (ofs->fs[i].is_lower && + uuid_equal(&ofs->fs[i].sb->s_uuid, uuid)) { + ofs->fs[i].bad_uuid = true; return false; } } @@ -1283,13 +1285,9 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) int err; bool bad_uuid = false; - /* fsid 0 is reserved for upper fs even with non upper overlay */ - if (ofs->upper_mnt && ofs->upper_mnt->mnt_sb == sb) - return 0; - - for (i = 0; i < ofs->numlowerfs; i++) { - if (ofs->lower_fs[i].sb == sb) - return i + 1; + for (i = 0; i < ofs->numfs; i++) { + if (ofs->fs[i].sb == sb) + return i; } if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) { @@ -1297,7 +1295,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) if (ofs->config.index || ofs->config.nfs_export) { ofs->config.index = false; ofs->config.nfs_export = false; - pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", + pr_warn("%s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", uuid_is_null(&sb->s_uuid) ? "null" : "conflicting", path->dentry); @@ -1306,35 +1304,59 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) err = get_anon_bdev(&dev); if (err) { - pr_err("overlayfs: failed to get anonymous bdev for lowerpath\n"); + pr_err("failed to get anonymous bdev for lowerpath\n"); return err; } - ofs->lower_fs[ofs->numlowerfs].sb = sb; - ofs->lower_fs[ofs->numlowerfs].pseudo_dev = dev; - ofs->lower_fs[ofs->numlowerfs].bad_uuid = bad_uuid; - ofs->numlowerfs++; + ofs->fs[ofs->numfs].sb = sb; + ofs->fs[ofs->numfs].pseudo_dev = dev; + ofs->fs[ofs->numfs].bad_uuid = bad_uuid; - return ofs->numlowerfs; + return ofs->numfs++; } -static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, - struct path *stack, unsigned int numlower) +static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, + struct path *stack, unsigned int numlower) { int err; unsigned int i; + struct ovl_layer *layers; err = -ENOMEM; - ofs->lower_layers = kcalloc(numlower, sizeof(struct ovl_layer), - GFP_KERNEL); - if (ofs->lower_layers == NULL) + layers = kcalloc(numlower + 1, sizeof(struct ovl_layer), GFP_KERNEL); + if (!layers) goto out; + ofs->layers = layers; - ofs->lower_fs = kcalloc(numlower, sizeof(struct ovl_sb), - GFP_KERNEL); - if (ofs->lower_fs == NULL) + ofs->fs = kcalloc(numlower + 1, sizeof(struct ovl_sb), GFP_KERNEL); + if (ofs->fs == NULL) goto out; + /* idx/fsid 0 are reserved for upper fs even with lower only overlay */ + ofs->numfs++; + + layers[0].mnt = ofs->upper_mnt; + layers[0].idx = 0; + layers[0].fsid = 0; + ofs->numlayer = 1; + + /* + * All lower layers that share the same fs as upper layer, use the same + * pseudo_dev as upper layer. Allocate fs[0].pseudo_dev even for lower + * only overlay to simplify ovl_fs_free(). + * is_lower will be set if upper fs is shared with a lower layer. + */ + err = get_anon_bdev(&ofs->fs[0].pseudo_dev); + if (err) { + pr_err("failed to get anonymous bdev for upper fs\n"); + goto out; + } + + if (ofs->upper_mnt) { + ofs->fs[0].sb = ofs->upper_mnt->mnt_sb; + ofs->fs[0].is_lower = false; + } + for (i = 0; i < numlower; i++) { struct vfsmount *mnt; struct inode *trap; @@ -1357,7 +1379,7 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, mnt = clone_private_mount(&stack[i]); err = PTR_ERR(mnt); if (IS_ERR(mnt)) { - pr_err("overlayfs: failed to clone lowerpath\n"); + pr_err("failed to clone lowerpath\n"); iput(trap); goto out; } @@ -1368,15 +1390,13 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, */ mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME; - ofs->lower_layers[ofs->numlower].trap = trap; - ofs->lower_layers[ofs->numlower].mnt = mnt; - ofs->lower_layers[ofs->numlower].idx = i + 1; - ofs->lower_layers[ofs->numlower].fsid = fsid; - if (fsid) { - ofs->lower_layers[ofs->numlower].fs = - &ofs->lower_fs[fsid - 1]; - } - ofs->numlower++; + layers[ofs->numlayer].trap = trap; + layers[ofs->numlayer].mnt = mnt; + layers[ofs->numlayer].idx = ofs->numlayer; + layers[ofs->numlayer].fsid = fsid; + layers[ofs->numlayer].fs = &ofs->fs[fsid]; + ofs->numlayer++; + ofs->fs[fsid].is_lower = true; } /* @@ -1387,22 +1407,23 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, * bits reserved for fsid, it emits a warning and uses the original * inode number. */ - if (!ofs->numlowerfs || (ofs->numlowerfs == 1 && !ofs->upper_mnt)) { - ofs->xino_bits = 0; - ofs->config.xino = OVL_XINO_OFF; - } else if (ofs->config.xino == OVL_XINO_ON && !ofs->xino_bits) { + if (ofs->numfs - !ofs->upper_mnt == 1) { + if (ofs->config.xino == OVL_XINO_ON) + pr_info("\"xino=on\" is useless with all layers on same fs, ignore.\n"); + ofs->xino_mode = 0; + } else if (ofs->config.xino == OVL_XINO_ON && ofs->xino_mode < 0) { /* - * This is a roundup of number of bits needed for numlowerfs+1 - * (i.e. ilog2(numlowerfs+1 - 1) + 1). fsid 0 is reserved for - * upper fs even with non upper overlay. + * This is a roundup of number of bits needed for encoding + * fsid, where fsid 0 is reserved for upper fs even with + * lower only overlay. */ BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31); - ofs->xino_bits = ilog2(ofs->numlowerfs) + 1; + ofs->xino_mode = ilog2(ofs->numfs - 1) + 1; } - if (ofs->xino_bits) { - pr_info("overlayfs: \"xino\" feature enabled using %d upper inode bits.\n", - ofs->xino_bits); + if (ofs->xino_mode > 0) { + pr_info("\"xino\" feature enabled using %d upper inode bits.\n", + ofs->xino_mode); } err = 0; @@ -1428,15 +1449,15 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, err = -EINVAL; stacklen = ovl_split_lowerdirs(lowertmp); if (stacklen > OVL_MAX_STACK) { - pr_err("overlayfs: too many lower directories, limit is %d\n", + pr_err("too many lower directories, limit is %d\n", OVL_MAX_STACK); goto out_err; } else if (!ofs->config.upperdir && stacklen == 1) { - pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n"); + pr_err("at least 2 lowerdir are needed while upperdir nonexistent\n"); goto out_err; } else if (!ofs->config.upperdir && ofs->config.nfs_export && ofs->config.redirect_follow) { - pr_warn("overlayfs: NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n"); + pr_warn("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n"); ofs->config.nfs_export = false; } @@ -1459,11 +1480,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, err = -EINVAL; sb->s_stack_depth++; if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { - pr_err("overlayfs: maximum fs stacking depth exceeded\n"); + pr_err("maximum fs stacking depth exceeded\n"); goto out_err; } - err = ovl_get_lower_layers(sb, ofs, stack, numlower); + err = ovl_get_layers(sb, ofs, stack, numlower); if (err) goto out_err; @@ -1474,7 +1495,7 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, for (i = 0; i < numlower; i++) { oe->lowerstack[i].dentry = dget(stack[i].dentry); - oe->lowerstack[i].layer = &ofs->lower_layers[i]; + oe->lowerstack[i].layer = &ofs->layers[i+1]; } if (remote) @@ -1515,7 +1536,7 @@ static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs, while (!err && parent != next) { if (ovl_lookup_trap_inode(sb, parent)) { err = -ELOOP; - pr_err("overlayfs: overlapping %s path\n", name); + pr_err("overlapping %s path\n", name); } else if (ovl_is_inuse(parent)) { err = ovl_report_in_use(ofs, name); } @@ -1555,9 +1576,9 @@ static int ovl_check_overlapping_layers(struct super_block *sb, return err; } - for (i = 0; i < ofs->numlower; i++) { + for (i = 1; i < ofs->numlayer; i++) { err = ovl_check_layer(sb, ofs, - ofs->lower_layers[i].mnt->mnt_root, + ofs->layers[i].mnt->mnt_root, "lowerdir"); if (err) return err; @@ -1595,7 +1616,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) err = -EINVAL; if (!ofs->config.lowerdir) { if (!silent) - pr_err("overlayfs: missing 'lowerdir'\n"); + pr_err("missing 'lowerdir'\n"); goto out_err; } @@ -1603,14 +1624,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = MAX_LFS_FILESIZE; /* Assume underlaying fs uses 32bit inodes unless proven otherwise */ if (ofs->config.xino != OVL_XINO_OFF) - ofs->xino_bits = BITS_PER_LONG - 32; + ofs->xino_mode = BITS_PER_LONG - 32; /* alloc/destroy_inode needed for setting up traps in inode cache */ sb->s_op = &ovl_super_operations; if (ofs->config.upperdir) { if (!ofs->config.workdir) { - pr_err("overlayfs: missing 'workdir'\n"); + pr_err("missing 'workdir'\n"); goto out_err; } @@ -1660,13 +1681,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!ofs->indexdir) { ofs->config.index = false; if (ofs->upper_mnt && ofs->config.nfs_export) { - pr_warn("overlayfs: NFS export requires an index dir, falling back to nfs_export=off.\n"); + pr_warn("NFS export requires an index dir, falling back to nfs_export=off.\n"); ofs->config.nfs_export = false; } } if (ofs->config.metacopy && ofs->config.nfs_export) { - pr_warn("overlayfs: NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n"); + pr_warn("NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n"); ofs->config.nfs_export = false; } @@ -1749,9 +1770,15 @@ static int __init ovl_init(void) if (ovl_inode_cachep == NULL) return -ENOMEM; - err = register_filesystem(&ovl_fs_type); - if (err) - kmem_cache_destroy(ovl_inode_cachep); + err = ovl_aio_request_cache_init(); + if (!err) { + err = register_filesystem(&ovl_fs_type); + if (!err) + return 0; + + ovl_aio_request_cache_destroy(); + } + kmem_cache_destroy(ovl_inode_cachep); return err; } @@ -1766,7 +1793,7 @@ static void __exit ovl_exit(void) */ rcu_barrier(); kmem_cache_destroy(ovl_inode_cachep); - + ovl_aio_request_cache_destroy(); } module_init(ovl_init); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index f5678a3f8350..ea005085803f 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -40,18 +40,6 @@ const struct cred *ovl_override_creds(struct super_block *sb) return override_creds(ofs->creator_cred); } -struct super_block *ovl_same_sb(struct super_block *sb) -{ - struct ovl_fs *ofs = sb->s_fs_info; - - if (!ofs->numlowerfs) - return ofs->upper_mnt->mnt_sb; - else if (ofs->numlowerfs == 1 && !ofs->upper_mnt) - return ofs->lower_fs[0].sb; - else - return NULL; -} - /* * Check if underlying fs supports file handles and try to determine encoding * type, in order to deduce maximum inode number used by fs. @@ -198,7 +186,7 @@ struct dentry *ovl_dentry_lower(struct dentry *dentry) return oe->numlower ? oe->lowerstack[0].dentry : NULL; } -struct ovl_layer *ovl_layer_lower(struct dentry *dentry) +const struct ovl_layer *ovl_layer_lower(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; @@ -576,7 +564,7 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry, err = ovl_do_setxattr(upperdentry, name, value, size, 0); if (err == -EOPNOTSUPP) { - pr_warn("overlayfs: cannot set %s xattr on upper\n", name); + pr_warn("cannot set %s xattr on upper\n", name); ofs->noxattr = true; return xerr; } @@ -700,7 +688,7 @@ static void ovl_cleanup_index(struct dentry *dentry) inode = d_inode(upperdentry); if (!S_ISDIR(inode->i_mode) && inode->i_nlink != 1) { - pr_warn_ratelimited("overlayfs: cleanup linked index (%pd2, ino=%lu, nlink=%u)\n", + pr_warn_ratelimited("cleanup linked index (%pd2, ino=%lu, nlink=%u)\n", upperdentry, inode->i_ino, inode->i_nlink); /* * We either have a bug with persistent union nlink or a lower @@ -739,7 +727,7 @@ out: return; fail: - pr_err("overlayfs: cleanup index of '%pd2' failed (%i)\n", dentry, err); + pr_err("cleanup index of '%pd2' failed (%i)\n", dentry, err); goto out; } @@ -830,7 +818,7 @@ int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) err_unlock: unlock_rename(workdir, upperdir); err: - pr_err("overlayfs: failed to lock workdir+upperdir\n"); + pr_err("failed to lock workdir+upperdir\n"); return -EIO; } @@ -852,7 +840,7 @@ int ovl_check_metacopy_xattr(struct dentry *dentry) return 1; out: - pr_warn_ratelimited("overlayfs: failed to get metacopy (%i)\n", res); + pr_warn_ratelimited("failed to get metacopy (%i)\n", res); return res; } @@ -899,7 +887,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value, return res; fail: - pr_warn_ratelimited("overlayfs: failed to get xattr %s: err=%zi)\n", + pr_warn_ratelimited("failed to get xattr %s: err=%zi)\n", name, res); kfree(buf); return res; @@ -931,7 +919,7 @@ char *ovl_get_redirect_xattr(struct dentry *dentry, int padding) return buf; invalid: - pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf); + pr_warn_ratelimited("invalid redirect (%s)\n", buf); res = -EINVAL; kfree(buf); return ERR_PTR(res); diff --git a/fs/pipe.c b/fs/pipe.c index 57502c3c0fba..5a34d6c22d4c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -108,16 +108,19 @@ void pipe_double_lock(struct pipe_inode_info *pipe1, /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe) { - DEFINE_WAIT(wait); + DEFINE_WAIT(rdwait); + DEFINE_WAIT(wrwait); /* * Pipes are system-local resources, so sleeping on them * is considered a noninteractive wait: */ - prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); + prepare_to_wait(&pipe->wr_wait, &wrwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); - finish_wait(&pipe->wait, &wait); + finish_wait(&pipe->rd_wait, &rdwait); + finish_wait(&pipe->wr_wait, &wrwait); pipe_lock(pipe); } @@ -286,7 +289,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; - bool was_full; + bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ @@ -344,10 +347,10 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (!buf->len) { pipe_buf_release(pipe, buf); - spin_lock_irq(&pipe->wait.lock); + spin_lock_irq(&pipe->rd_wait.lock); tail++; pipe->tail = tail; - spin_unlock_irq(&pipe->wait.lock); + spin_unlock_irq(&pipe->rd_wait.lock); } total_len -= chars; if (!total_len) @@ -384,7 +387,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) * no data. */ if (unlikely(was_full)) { - wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM); + wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } @@ -394,18 +397,23 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ - if (wait_event_interruptible(pipe->wait, pipe_readable(pipe)) < 0) + if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; __pipe_lock(pipe); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); + wake_next_reader = true; } + if (pipe_empty(pipe->head, pipe->tail)) + wake_next_reader = false; __pipe_unlock(pipe); if (was_full) { - wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM); + wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } + if (wake_next_reader) + wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); if (ret > 0) file_accessed(filp); return ret; @@ -437,6 +445,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; + bool wake_next_writer = false; /* Null write succeeds. */ if (unlikely(total_len == 0)) @@ -515,16 +524,16 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * it, either the reader will consume it or it'll still * be there for the next write. */ - spin_lock_irq(&pipe->wait.lock); + spin_lock_irq(&pipe->rd_wait.lock); head = pipe->head; if (pipe_full(head, pipe->tail, pipe->max_usage)) { - spin_unlock_irq(&pipe->wait.lock); + spin_unlock_irq(&pipe->rd_wait.lock); continue; } pipe->head = head + 1; - spin_unlock_irq(&pipe->wait.lock); + spin_unlock_irq(&pipe->rd_wait.lock); /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; @@ -576,14 +585,17 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) */ __pipe_unlock(pipe); if (was_empty) { - wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); + wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } - wait_event_interruptible(pipe->wait, pipe_writable(pipe)); + wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); __pipe_lock(pipe); was_empty = pipe_empty(pipe->head, pipe->tail); + wake_next_writer = true; } out: + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + wake_next_writer = false; __pipe_unlock(pipe); /* @@ -596,9 +608,11 @@ out: * wake up pending jobs */ if (was_empty) { - wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); + wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } + if (wake_next_writer) + wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) @@ -642,12 +656,15 @@ pipe_poll(struct file *filp, poll_table *wait) unsigned int head, tail; /* - * Reading only -- no need for acquiring the semaphore. + * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ - poll_wait(filp, &pipe->wait, wait); + if (filp->f_mode & FMODE_READ) + poll_wait(filp, &pipe->rd_wait, wait); + if (filp->f_mode & FMODE_WRITE) + poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, @@ -706,7 +723,8 @@ pipe_release(struct inode *inode, struct file *file) pipe->writers--; if (pipe->readers || pipe->writers) { - wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM | EPOLLERR | EPOLLHUP); + wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLHUP); + wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM | EPOLLERR | EPOLLHUP); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } @@ -789,7 +807,8 @@ struct pipe_inode_info *alloc_pipe_info(void) GFP_KERNEL_ACCOUNT); if (pipe->bufs) { - init_waitqueue_head(&pipe->wait); + init_waitqueue_head(&pipe->rd_wait); + init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; @@ -1007,7 +1026,8 @@ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) static void wake_up_partner(struct pipe_inode_info *pipe) { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible(&pipe->rd_wait); + wake_up_interruptible(&pipe->wr_wait); } static int fifo_open(struct inode *inode, struct file *filp) @@ -1118,13 +1138,13 @@ static int fifo_open(struct inode *inode, struct file *filp) err_rd: if (!--pipe->readers) - wake_up_interruptible(&pipe->wait); + wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) - wake_up_interruptible(&pipe->wait); + wake_up_interruptible(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; @@ -1251,7 +1271,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; - wake_up_interruptible_all(&pipe->wait); + wake_up_interruptible_all(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->wr_wait); return pipe->max_usage * PAGE_SIZE; out_revert_acct: diff --git a/fs/proc/Makefile b/fs/proc/Makefile index ead487e80510..bd08616ed8ba 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -33,3 +33,4 @@ proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o +proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c new file mode 100644 index 000000000000..9955d75c0585 --- /dev/null +++ b/fs/proc/bootconfig.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * /proc/bootconfig - Extra boot configuration + */ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/printk.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/bootconfig.h> +#include <linux/slab.h> + +static char *saved_boot_config; + +static int boot_config_proc_show(struct seq_file *m, void *v) +{ + if (saved_boot_config) + seq_puts(m, saved_boot_config); + return 0; +} + +/* Rest size of buffer */ +#define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0) + +/* Return the needed total length if @size is 0 */ +static int __init copy_xbc_key_value_list(char *dst, size_t size) +{ + struct xbc_node *leaf, *vnode; + const char *val; + char *key, *end = dst + size; + int ret = 0; + + key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL); + + xbc_for_each_key_value(leaf, val) { + ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX); + if (ret < 0) + break; + ret = snprintf(dst, rest(dst, end), "%s = ", key); + if (ret < 0) + break; + dst += ret; + vnode = xbc_node_get_child(leaf); + if (vnode && xbc_node_is_array(vnode)) { + xbc_array_for_each_value(vnode, val) { + ret = snprintf(dst, rest(dst, end), "\"%s\"%s", + val, vnode->next ? ", " : "\n"); + if (ret < 0) + goto out; + dst += ret; + } + } else { + ret = snprintf(dst, rest(dst, end), "\"%s\"\n", val); + if (ret < 0) + break; + dst += ret; + } + } +out: + kfree(key); + + return ret < 0 ? ret : dst - (end - size); +} + +static int __init proc_boot_config_init(void) +{ + int len; + + len = copy_xbc_key_value_list(NULL, 0); + if (len < 0) + return len; + + if (len > 0) { + saved_boot_config = kzalloc(len + 1, GFP_KERNEL); + if (!saved_boot_config) + return -ENOMEM; + + len = copy_xbc_key_value_list(saved_boot_config, len + 1); + if (len < 0) { + kfree(saved_boot_config); + return len; + } + } + + proc_create_single("bootconfig", 0, NULL, boot_config_proc_show); + + return 0; +} +fs_initcall(proc_boot_config_init); diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index 96f1087e372c..c1dea9b8222e 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -16,16 +16,16 @@ static int cpuinfo_open(struct inode *inode, struct file *file) return seq_open(file, &cpuinfo_op); } -static const struct file_operations proc_cpuinfo_operations = { - .open = cpuinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops cpuinfo_proc_ops = { + .proc_open = cpuinfo_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int __init proc_cpuinfo_init(void) { - proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); + proc_create("cpuinfo", 0, NULL, &cpuinfo_proc_ops); return 0; } fs_initcall(proc_cpuinfo_init); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 074e9585c699..3faed94e4b65 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -473,7 +473,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent = __proc_create(&parent, name, S_IFDIR | mode, 2); if (ent) { ent->data = data; - ent->proc_fops = &proc_dir_operations; + ent->proc_dir_ops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; ent = proc_register(parent, ent); } @@ -503,7 +503,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent = __proc_create(&parent, name, mode, 2); if (ent) { ent->data = NULL; - ent->proc_fops = NULL; + ent->proc_dir_ops = NULL; ent->proc_iops = NULL; ent = proc_register(parent, ent); } @@ -533,25 +533,23 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops, void *data) + const struct proc_ops *proc_ops, void *data) { struct proc_dir_entry *p; - BUG_ON(proc_fops == NULL); - p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; - p->proc_fops = proc_fops; + p->proc_ops = proc_ops; return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops) + const struct proc_ops *proc_ops) { - return proc_create_data(name, mode, parent, proc_fops, NULL); + return proc_create_data(name, mode, parent, proc_ops, NULL); } EXPORT_SYMBOL(proc_create); @@ -573,11 +571,11 @@ static int proc_seq_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations proc_seq_fops = { - .open = proc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = proc_seq_release, +static const struct proc_ops proc_seq_ops = { + .proc_open = proc_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = proc_seq_release, }; struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, @@ -589,7 +587,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; - p->proc_fops = &proc_seq_fops; + p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); @@ -603,11 +601,11 @@ static int proc_single_open(struct inode *inode, struct file *file) return single_open(file, de->single_show, de->data); } -static const struct file_operations proc_single_fops = { - .open = proc_single_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops proc_single_ops = { + .proc_open = proc_single_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, @@ -619,7 +617,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; - p->proc_fops = &proc_single_fops; + p->proc_ops = &proc_single_ops; p->single_show = show; return proc_register(parent, p); } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index dbe43a50caf2..6da18316d209 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -163,7 +163,7 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; - pde->proc_fops->release(file_inode(file), file); + pde->proc_ops->proc_release(file_inode(file), file); spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); @@ -200,12 +200,12 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) struct proc_dir_entry *pde = PDE(file_inode(file)); loff_t rv = -EINVAL; if (use_pde(pde)) { - typeof_member(struct file_operations, llseek) llseek; + typeof_member(struct proc_ops, proc_lseek) lseek; - llseek = pde->proc_fops->llseek; - if (!llseek) - llseek = default_llseek; - rv = llseek(file, offset, whence); + lseek = pde->proc_ops->proc_lseek; + if (!lseek) + lseek = default_llseek; + rv = lseek(file, offset, whence); unuse_pde(pde); } return rv; @@ -216,9 +216,9 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, read) read; + typeof_member(struct proc_ops, proc_read) read; - read = pde->proc_fops->read; + read = pde->proc_ops->proc_read; if (read) rv = read(file, buf, count, ppos); unuse_pde(pde); @@ -231,9 +231,9 @@ static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, write) write; + typeof_member(struct proc_ops, proc_write) write; - write = pde->proc_fops->write; + write = pde->proc_ops->proc_write; if (write) rv = write(file, buf, count, ppos); unuse_pde(pde); @@ -246,9 +246,9 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) struct proc_dir_entry *pde = PDE(file_inode(file)); __poll_t rv = DEFAULT_POLLMASK; if (use_pde(pde)) { - typeof_member(struct file_operations, poll) poll; + typeof_member(struct proc_ops, proc_poll) poll; - poll = pde->proc_fops->poll; + poll = pde->proc_ops->proc_poll; if (poll) rv = poll(file, pts); unuse_pde(pde); @@ -261,9 +261,9 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (use_pde(pde)) { - typeof_member(struct file_operations, unlocked_ioctl) ioctl; + typeof_member(struct proc_ops, proc_ioctl) ioctl; - ioctl = pde->proc_fops->unlocked_ioctl; + ioctl = pde->proc_ops->proc_ioctl; if (ioctl) rv = ioctl(file, cmd, arg); unuse_pde(pde); @@ -277,9 +277,9 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (use_pde(pde)) { - typeof_member(struct file_operations, compat_ioctl) compat_ioctl; + typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl; - compat_ioctl = pde->proc_fops->compat_ioctl; + compat_ioctl = pde->proc_ops->proc_compat_ioctl; if (compat_ioctl) rv = compat_ioctl(file, cmd, arg); unuse_pde(pde); @@ -293,9 +293,9 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) struct proc_dir_entry *pde = PDE(file_inode(file)); int rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, mmap) mmap; + typeof_member(struct proc_ops, proc_mmap) mmap; - mmap = pde->proc_fops->mmap; + mmap = pde->proc_ops->proc_mmap; if (mmap) rv = mmap(file, vma); unuse_pde(pde); @@ -312,9 +312,9 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, get_unmapped_area) get_area; + typeof_member(struct proc_ops, proc_get_unmapped_area) get_area; - get_area = pde->proc_fops->get_unmapped_area; + get_area = pde->proc_ops->proc_get_unmapped_area; #ifdef CONFIG_MMU if (!get_area) get_area = current->mm->get_unmapped_area; @@ -333,8 +333,8 @@ static int proc_reg_open(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); int rv = 0; - typeof_member(struct file_operations, open) open; - typeof_member(struct file_operations, release) release; + typeof_member(struct proc_ops, proc_open) open; + typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; /* @@ -351,7 +351,7 @@ static int proc_reg_open(struct inode *inode, struct file *file) if (!use_pde(pde)) return -ENOENT; - release = pde->proc_fops->release; + release = pde->proc_ops->proc_release; if (release) { pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); if (!pdeo) { @@ -360,7 +360,7 @@ static int proc_reg_open(struct inode *inode, struct file *file) } } - open = pde->proc_fops->open; + open = pde->proc_ops->proc_open; if (open) rv = open(inode, file); @@ -468,21 +468,23 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) inode->i_size = de->size; if (de->nlink) set_nlink(inode, de->nlink); - WARN_ON(!de->proc_iops); - inode->i_op = de->proc_iops; - if (de->proc_fops) { - if (S_ISREG(inode->i_mode)) { + + if (S_ISREG(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT - if (!de->proc_fops->compat_ioctl) - inode->i_fop = - &proc_reg_file_ops_no_compat; - else -#endif - inode->i_fop = &proc_reg_file_ops; - } else { - inode->i_fop = de->proc_fops; + if (!de->proc_ops->proc_compat_ioctl) { + inode->i_fop = &proc_reg_file_ops_no_compat; } - } +#endif + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = de->proc_dir_ops; + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = NULL; + } else + BUG(); } else pde_put(de); return inode; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 0f3b557c9b77..41587276798e 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -39,7 +39,10 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; struct completion *pde_unload_completion; const struct inode_operations *proc_iops; - const struct file_operations *proc_fops; + union { + const struct proc_ops *proc_ops; + const struct file_operations *proc_dir_ops; + }; const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e2ed8e08cc7a..8ba492d44e68 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -574,11 +574,11 @@ static int release_kcore(struct inode *inode, struct file *file) return 0; } -static const struct file_operations proc_kcore_operations = { - .read = read_kcore, - .open = open_kcore, - .release = release_kcore, - .llseek = default_llseek, +static const struct proc_ops kcore_proc_ops = { + .proc_read = read_kcore, + .proc_open = open_kcore, + .proc_release = release_kcore, + .proc_lseek = default_llseek, }; /* just remember that we have to update kcore */ @@ -637,8 +637,7 @@ static void __init add_modules_range(void) static int __init proc_kcore_init(void) { - proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, - &proc_kcore_operations); + proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &kcore_proc_ops); if (!proc_root_kcore) { pr_err("couldn't create /proc/kcore\n"); return 0; /* Always returns 0. */ diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index 4f4a2abb225e..ec1b7d2fb773 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -49,17 +49,17 @@ static __poll_t kmsg_poll(struct file *file, poll_table *wait) } -static const struct file_operations proc_kmsg_operations = { - .read = kmsg_read, - .poll = kmsg_poll, - .open = kmsg_open, - .release = kmsg_release, - .llseek = generic_file_llseek, +static const struct proc_ops kmsg_proc_ops = { + .proc_read = kmsg_read, + .proc_poll = kmsg_poll, + .proc_open = kmsg_open, + .proc_release = kmsg_release, + .proc_lseek = generic_file_llseek, }; static int __init proc_kmsg_init(void) { - proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); + proc_create("kmsg", S_IRUSR, NULL, &kmsg_proc_ops); return 0; } fs_initcall(proc_kmsg_init); diff --git a/fs/proc/page.c b/fs/proc/page.c index 7c952ee732e6..f909243d4a66 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -21,6 +21,21 @@ #define KPMMASK (KPMSIZE - 1) #define KPMBITS (KPMSIZE * BITS_PER_BYTE) +static inline unsigned long get_max_dump_pfn(void) +{ +#ifdef CONFIG_SPARSEMEM + /* + * The memmap of early sections is completely populated and marked + * online even if max_pfn does not fall on a section boundary - + * pfn_to_online_page() will succeed on all pages. Allow inspecting + * these memmaps. + */ + return round_up(max_pfn, PAGES_PER_SECTION); +#else + return max_pfn; +#endif +} + /* /proc/kpagecount - an array exposing page counts * * Each entry is a u64 representing the corresponding @@ -29,6 +44,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; struct page *ppage; unsigned long src = *ppos; @@ -37,9 +53,11 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, u64 pcount; pfn = src / KPMSIZE; - count = min_t(size_t, count, (max_pfn * KPMSIZE) - src); if (src & KPMMASK || count & KPMMASK) return -EINVAL; + if (src >= max_dump_pfn * KPMSIZE) + return 0; + count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src); while (count > 0) { /* @@ -71,9 +89,9 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return ret; } -static const struct file_operations proc_kpagecount_operations = { - .llseek = mem_lseek, - .read = kpagecount_read, +static const struct proc_ops kpagecount_proc_ops = { + .proc_lseek = mem_lseek, + .proc_read = kpagecount_read, }; /* /proc/kpageflags - an array exposing page flags @@ -206,6 +224,7 @@ u64 stable_page_flags(struct page *page) static ssize_t kpageflags_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; struct page *ppage; unsigned long src = *ppos; @@ -213,9 +232,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, ssize_t ret = 0; pfn = src / KPMSIZE; - count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); if (src & KPMMASK || count & KPMMASK) return -EINVAL; + if (src >= max_dump_pfn * KPMSIZE) + return 0; + count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src); while (count > 0) { /* @@ -242,15 +263,16 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return ret; } -static const struct file_operations proc_kpageflags_operations = { - .llseek = mem_lseek, - .read = kpageflags_read, +static const struct proc_ops kpageflags_proc_ops = { + .proc_lseek = mem_lseek, + .proc_read = kpageflags_read, }; #ifdef CONFIG_MEMCG static ssize_t kpagecgroup_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; struct page *ppage; unsigned long src = *ppos; @@ -259,9 +281,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, u64 ino; pfn = src / KPMSIZE; - count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); if (src & KPMMASK || count & KPMMASK) return -EINVAL; + if (src >= max_dump_pfn * KPMSIZE) + return 0; + count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src); while (count > 0) { /* @@ -293,18 +317,18 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, return ret; } -static const struct file_operations proc_kpagecgroup_operations = { - .llseek = mem_lseek, - .read = kpagecgroup_read, +static const struct proc_ops kpagecgroup_proc_ops = { + .proc_lseek = mem_lseek, + .proc_read = kpagecgroup_read, }; #endif /* CONFIG_MEMCG */ static int __init proc_page_init(void) { - proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations); - proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations); + proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops); + proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops); #ifdef CONFIG_MEMCG - proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations); + proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops); #endif return 0; } diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 76ae278df1c4..4888c5224442 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -90,12 +90,12 @@ static int seq_release_net(struct inode *ino, struct file *f) return 0; } -static const struct file_operations proc_net_seq_fops = { - .open = seq_open_net, - .read = seq_read, - .write = proc_simple_write, - .llseek = seq_lseek, - .release = seq_release_net, +static const struct proc_ops proc_net_seq_ops = { + .proc_open = seq_open_net, + .proc_read = seq_read, + .proc_write = proc_simple_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release_net, }; struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, @@ -108,7 +108,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_seq_fops; + p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); @@ -152,7 +152,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_seq_fops; + p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; p->write = write; @@ -183,12 +183,12 @@ static int single_release_net(struct inode *ino, struct file *f) return single_release(ino, f); } -static const struct file_operations proc_net_single_fops = { - .open = single_open_net, - .read = seq_read, - .write = proc_simple_write, - .llseek = seq_lseek, - .release = single_release_net, +static const struct proc_ops proc_net_single_ops = { + .proc_open = single_open_net, + .proc_read = seq_read, + .proc_write = proc_simple_write, + .proc_lseek = seq_lseek, + .proc_release = single_release_net, }; struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, @@ -201,7 +201,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_single_fops; + p->proc_ops = &proc_net_single_ops; p->single_show = show; return proc_register(parent, p); } @@ -244,7 +244,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_single_fops; + p->proc_ops = &proc_net_single_ops; p->single_show = show; p->write = write; return proc_register(parent, p); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d80989b6c344..c75bb4632ed1 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1720,7 +1720,7 @@ int __init proc_sys_init(void) proc_sys_root = proc_mkdir("sys", NULL); proc_sys_root->proc_iops = &proc_sys_dir_operations; - proc_sys_root->proc_fops = &proc_sys_dir_file_operations; + proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; return sysctl_init(); diff --git a/fs/proc/root.c b/fs/proc/root.c index 0b7c8dffc9ae..608233dfd29c 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -41,24 +41,19 @@ enum proc_param { Opt_hidepid, }; -static const struct fs_parameter_spec proc_param_specs[] = { +static const struct fs_parameter_spec proc_fs_parameters[] = { fsparam_u32("gid", Opt_gid), fsparam_u32("hidepid", Opt_hidepid), {} }; -static const struct fs_parameter_description proc_fs_parameters = { - .name = "proc", - .specs = proc_param_specs, -}; - static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; struct fs_parse_result result; int opt; - opt = fs_parse(fc, &proc_fs_parameters, param, &result); + opt = fs_parse(fc, proc_fs_parameters, param, &result); if (opt < 0) return opt; @@ -71,7 +66,7 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->hidepid = result.uint_32; if (ctx->hidepid < HIDEPID_OFF || ctx->hidepid > HIDEPID_INVISIBLE) - return invalf(fc, "proc: hidepid value must be between 0 and 2.\n"); + return invalfc(fc, "hidepid value must be between 0 and 2.\n"); break; default: @@ -207,7 +202,7 @@ static void proc_kill_sb(struct super_block *sb) static struct file_system_type proc_fs_type = { .name = "proc", .init_fs_context = proc_init_fs_context, - .parameters = &proc_fs_parameters, + .parameters = proc_fs_parameters, .kill_sb = proc_kill_sb, .fs_flags = FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM, }; @@ -292,7 +287,7 @@ struct proc_dir_entry proc_root = { .nlink = 2, .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, - .proc_fops = &proc_root_operations, + .proc_dir_ops = &proc_root_operations, .parent = &proc_root, .subdir = RB_ROOT, .name = "/proc", diff --git a/fs/proc/stat.c b/fs/proc/stat.c index fd931d3e77be..0449edf460f5 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -223,16 +223,16 @@ static int stat_open(struct inode *inode, struct file *file) return single_open_size(file, show_stat, NULL, size); } -static const struct file_operations proc_stat_operations = { - .open = stat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops stat_proc_ops = { + .proc_open = stat_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static int __init proc_stat_init(void) { - proc_create("stat", 0, NULL, &proc_stat_operations); + proc_create("stat", 0, NULL, &stat_proc_ops); return 0; } fs_initcall(proc_stat_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9442631fd4af..3ba9ae83bff5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -505,7 +505,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, #ifdef CONFIG_SHMEM static int smaps_pte_hole(unsigned long addr, unsigned long end, - struct mm_walk *walk) + __always_unused int depth, struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; @@ -1282,7 +1282,7 @@ static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme, } static int pagemap_pte_hole(unsigned long start, unsigned long end, - struct mm_walk *walk) + __always_unused int depth, struct mm_walk *walk) { struct pagemapread *pm = walk->private; unsigned long addr = start; diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 7b13988796e1..7dc800cce354 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -667,10 +667,10 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) } #endif -static const struct file_operations proc_vmcore_operations = { - .read = read_vmcore, - .llseek = default_llseek, - .mmap = mmap_vmcore, +static const struct proc_ops vmcore_proc_ops = { + .proc_read = read_vmcore, + .proc_lseek = default_llseek, + .proc_mmap = mmap_vmcore, }; static struct vmcore* __init get_new_element(void) @@ -1555,7 +1555,7 @@ static int __init vmcore_init(void) elfcorehdr_free(elfcorehdr_addr); elfcorehdr_addr = ELFCORE_ADDR_ERR; - proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations); + proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &vmcore_proc_ops); if (proc_vmcore) proc_vmcore->size = vmcore_size; return 0; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index d82636e8eb65..ee179a81b3da 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -181,23 +181,18 @@ enum ramfs_param { Opt_mode, }; -static const struct fs_parameter_spec ramfs_param_specs[] = { +const struct fs_parameter_spec ramfs_fs_parameters[] = { fsparam_u32oct("mode", Opt_mode), {} }; -const struct fs_parameter_description ramfs_fs_parameters = { - .name = "ramfs", - .specs = ramfs_param_specs, -}; - static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct ramfs_fs_info *fsi = fc->s_fs_info; int opt; - opt = fs_parse(fc, &ramfs_fs_parameters, param, &result); + opt = fs_parse(fc, ramfs_fs_parameters, param, &result); if (opt < 0) { /* * We might like to report bad mount options here; @@ -278,7 +273,7 @@ static void ramfs_kill_sb(struct super_block *sb) static struct file_system_type ramfs_fs_type = { .name = "ramfs", .init_fs_context = ramfs_init_fs_context, - .parameters = &ramfs_fs_parameters, + .parameters = ramfs_fs_parameters, .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; diff --git a/fs/read_write.c b/fs/read_write.c index 7458fccc59e1..59d819c5b92e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -939,6 +939,34 @@ out: return ret; } +ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, + struct iov_iter *iter) +{ + size_t tot_len; + ssize_t ret = 0; + + if (!file->f_op->read_iter) + return -EINVAL; + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_READ)) + return -EINVAL; + + tot_len = iov_iter_count(iter); + if (!tot_len) + goto out; + ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); + if (ret < 0) + return ret; + + ret = call_read_iter(file, iocb, iter); +out: + if (ret >= 0) + fsnotify_access(file); + return ret; +} +EXPORT_SYMBOL(vfs_iocb_iter_read); + ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { @@ -975,6 +1003,34 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, return ret; } +ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, + struct iov_iter *iter) +{ + size_t tot_len; + ssize_t ret = 0; + + if (!file->f_op->write_iter) + return -EINVAL; + if (!(file->f_mode & FMODE_WRITE)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_WRITE)) + return -EINVAL; + + tot_len = iov_iter_count(iter); + if (!tot_len) + return 0; + ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); + if (ret < 0) + return ret; + + ret = call_write_iter(file, iocb, iter); + if (ret > 0) + fsnotify_modify(file); + + return ret; +} +EXPORT_SYMBOL(vfs_iocb_iter_write); + ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { diff --git a/fs/splice.c b/fs/splice.c index 3009652a41c8..d671936d0aad 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -165,8 +165,8 @@ static const struct pipe_buf_operations user_page_pipe_buf_ops = { static void wakeup_pipe_readers(struct pipe_inode_info *pipe) { smp_mb(); - if (waitqueue_active(&pipe->wait)) - wake_up_interruptible(&pipe->wait); + if (waitqueue_active(&pipe->rd_wait)) + wake_up_interruptible(&pipe->rd_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } @@ -462,8 +462,8 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, static void wakeup_pipe_writers(struct pipe_inode_info *pipe) { smp_mb(); - if (waitqueue_active(&pipe->wait)) - wake_up_interruptible(&pipe->wait); + if (waitqueue_active(&pipe->wr_wait)) + wake_up_interruptible(&pipe->wr_wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index d41c21fef138..c4ab045926b7 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -449,7 +449,7 @@ int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, } link = kernfs_create_link(kobj->sd, target_name, entry); - if (IS_ERR(link) && PTR_ERR(link) == -EEXIST) + if (PTR_ERR(link) == -EEXIST) sysfs_warn_dup(kobj->sd, target_name); kernfs_put(entry); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 0caa151cae4e..0ee8c6dfb036 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -330,7 +330,10 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) parent = tracefs_mount->mnt_root; inode_lock(parent->d_inode); - dentry = lookup_one_len(name, parent, strlen(name)); + if (unlikely(IS_DEADDIR(parent->d_inode))) + dentry = ERR_PTR(-ENOENT); + else + dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry) && dentry->d_inode) { dput(dentry); dentry = ERR_PTR(-EEXIST); @@ -499,122 +502,27 @@ __init struct dentry *tracefs_create_instance_dir(const char *name, return dentry; } -static int __tracefs_remove(struct dentry *dentry, struct dentry *parent) +static void remove_one(struct dentry *victim) { - int ret = 0; - - if (simple_positive(dentry)) { - if (dentry->d_inode) { - dget(dentry); - switch (dentry->d_inode->i_mode & S_IFMT) { - case S_IFDIR: - ret = simple_rmdir(parent->d_inode, dentry); - if (!ret) - fsnotify_rmdir(parent->d_inode, dentry); - break; - default: - simple_unlink(parent->d_inode, dentry); - fsnotify_unlink(parent->d_inode, dentry); - break; - } - if (!ret) - d_delete(dentry); - dput(dentry); - } - } - return ret; -} - -/** - * tracefs_remove - removes a file or directory from the tracefs filesystem - * @dentry: a pointer to a the dentry of the file or directory to be - * removed. - * - * This function removes a file or directory in tracefs that was previously - * created with a call to another tracefs function (like - * tracefs_create_file() or variants thereof.) - */ -void tracefs_remove(struct dentry *dentry) -{ - struct dentry *parent; - int ret; - - if (IS_ERR_OR_NULL(dentry)) - return; - - parent = dentry->d_parent; - inode_lock(parent->d_inode); - ret = __tracefs_remove(dentry, parent); - inode_unlock(parent->d_inode); - if (!ret) - simple_release_fs(&tracefs_mount, &tracefs_mount_count); + simple_release_fs(&tracefs_mount, &tracefs_mount_count); } /** - * tracefs_remove_recursive - recursively removes a directory + * tracefs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. * * This function recursively removes a directory tree in tracefs that * was previously created with a call to another tracefs function * (like tracefs_create_file() or variants thereof.) */ -void tracefs_remove_recursive(struct dentry *dentry) +void tracefs_remove(struct dentry *dentry) { - struct dentry *child, *parent; - if (IS_ERR_OR_NULL(dentry)) return; - parent = dentry; - down: - inode_lock(parent->d_inode); - loop: - /* - * The parent->d_subdirs is protected by the d_lock. Outside that - * lock, the child can be unlinked and set to be freed which can - * use the d_u.d_child as the rcu head and corrupt this list. - */ - spin_lock(&parent->d_lock); - list_for_each_entry(child, &parent->d_subdirs, d_child) { - if (!simple_positive(child)) - continue; - - /* perhaps simple_empty(child) makes more sense */ - if (!list_empty(&child->d_subdirs)) { - spin_unlock(&parent->d_lock); - inode_unlock(parent->d_inode); - parent = child; - goto down; - } - - spin_unlock(&parent->d_lock); - - if (!__tracefs_remove(child, parent)) - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - - /* - * The parent->d_lock protects agaist child from unlinking - * from d_subdirs. When releasing the parent->d_lock we can - * no longer trust that the next pointer is valid. - * Restart the loop. We'll skip this one with the - * simple_positive() check. - */ - goto loop; - } - spin_unlock(&parent->d_lock); - - inode_unlock(parent->d_inode); - child = parent; - parent = parent->d_parent; - inode_lock(parent->d_inode); - - if (child != dentry) - /* go up */ - goto loop; - - if (!__tracefs_remove(child, parent)) - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - inode_unlock(parent->d_inode); + simple_pin_fs(&trace_fs_type, &tracefs_mount, &tracefs_mount_count); + simple_recursive_removal(dentry, remove_one); + simple_release_fs(&tracefs_mount, &tracefs_mount_count); } /** diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index bc4dec5b1633..743928efffc1 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1080,18 +1080,12 @@ static void do_attr_changes(struct inode *inode, const struct iattr *attr) inode->i_uid = attr->ia_uid; if (attr->ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; - if (attr->ia_valid & ATTR_ATIME) { - inode->i_atime = timestamp_truncate(attr->ia_atime, - inode); - } - if (attr->ia_valid & ATTR_MTIME) { - inode->i_mtime = timestamp_truncate(attr->ia_mtime, - inode); - } - if (attr->ia_valid & ATTR_CTIME) { - inode->i_ctime = timestamp_truncate(attr->ia_ctime, - inode); - } + if (attr->ia_valid & ATTR_ATIME) + inode->i_atime = attr->ia_atime; + if (attr->ia_valid & ATTR_MTIME) + inode->i_mtime = attr->ia_mtime; + if (attr->ia_valid & ATTR_CTIME) + inode->i_ctime = attr->ia_ctime; if (attr->ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 17c90dff7266..4b4b65b48c57 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -84,7 +84,6 @@ static int create_default_filesystem(struct ubifs_info *c) int idx_node_size; long long tmp64, main_bytes; __le64 tmp_le64; - __le32 tmp_le32; struct timespec64 ts; u8 hash[UBIFS_HASH_ARR_SZ]; u8 hash_lpt[UBIFS_HASH_ARR_SZ]; @@ -291,16 +290,14 @@ static int create_default_filesystem(struct ubifs_info *c) ino->creat_sqnum = cpu_to_le64(++c->max_sqnum); ino->nlink = cpu_to_le32(2); - ktime_get_real_ts64(&ts); - ts = timespec64_trunc(ts, DEFAULT_TIME_GRAN); + ktime_get_coarse_real_ts64(&ts); tmp_le64 = cpu_to_le64(ts.tv_sec); ino->atime_sec = tmp_le64; ino->ctime_sec = tmp_le64; ino->mtime_sec = tmp_le64; - tmp_le32 = cpu_to_le32(ts.tv_nsec); - ino->atime_nsec = tmp_le32; - ino->ctime_nsec = tmp_le32; - ino->mtime_nsec = tmp_le32; + ino->atime_nsec = 0; + ino->ctime_nsec = 0; + ino->mtime_nsec = 0; ino->mode = cpu_to_le32(S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO); ino->size = cpu_to_le64(UBIFS_INO_NODE_SZ); diff --git a/fs/utimes.c b/fs/utimes.c index c952b6b3d8a0..1d17ce98cb80 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -36,14 +36,14 @@ static int utimes_common(const struct path *path, struct timespec64 *times) if (times[0].tv_nsec == UTIME_OMIT) newattrs.ia_valid &= ~ATTR_ATIME; else if (times[0].tv_nsec != UTIME_NOW) { - newattrs.ia_atime = timestamp_truncate(times[0], inode); + newattrs.ia_atime = times[0]; newattrs.ia_valid |= ATTR_ATIME_SET; } if (times[1].tv_nsec == UTIME_OMIT) newattrs.ia_valid &= ~ATTR_MTIME; else if (times[1].tv_nsec != UTIME_NOW) { - newattrs.ia_mtime = timestamp_truncate(times[1], inode); + newattrs.ia_mtime = times[1]; newattrs.ia_valid |= ATTR_MTIME_SET; } /* diff --git a/fs/vboxsf/Kconfig b/fs/vboxsf/Kconfig new file mode 100644 index 000000000000..b84586ae08b3 --- /dev/null +++ b/fs/vboxsf/Kconfig @@ -0,0 +1,10 @@ +config VBOXSF_FS + tristate "VirtualBox guest shared folder (vboxsf) support" + depends on X86 && VBOXGUEST + select NLS + help + VirtualBox hosts can share folders with guests, this driver + implements the Linux-guest side of this allowing folders exported + by the host to be mounted under Linux. + + If you want to use shared folders in VirtualBox guests, answer Y or M. diff --git a/fs/vboxsf/Makefile b/fs/vboxsf/Makefile new file mode 100644 index 000000000000..9e4328e79623 --- /dev/null +++ b/fs/vboxsf/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: MIT + +obj-$(CONFIG_VBOXSF_FS) += vboxsf.o + +vboxsf-y := dir.o file.o utils.o vboxsf_wrappers.o super.o diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c new file mode 100644 index 000000000000..dd147b490982 --- /dev/null +++ b/fs/vboxsf/dir.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Directory inode and file operations + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include <linux/namei.h> +#include <linux/vbox_utils.h> +#include "vfsmod.h" + +static int vboxsf_dir_open(struct inode *inode, struct file *file) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); + struct shfl_createparms params = {}; + struct vboxsf_dir_info *sf_d; + int err; + + sf_d = vboxsf_dir_info_alloc(); + if (!sf_d) + return -ENOMEM; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_DIRECTORY | SHFL_CF_ACT_OPEN_IF_EXISTS | + SHFL_CF_ACT_FAIL_IF_NEW | SHFL_CF_ACCESS_READ; + + err = vboxsf_create_at_dentry(file_dentry(file), ¶ms); + if (err) + goto err_free_dir_info; + + if (params.result != SHFL_FILE_EXISTS) { + err = -ENOENT; + goto err_close; + } + + err = vboxsf_dir_read_all(sbi, sf_d, params.handle); + if (err) + goto err_close; + + vboxsf_close(sbi->root, params.handle); + file->private_data = sf_d; + return 0; + +err_close: + vboxsf_close(sbi->root, params.handle); +err_free_dir_info: + vboxsf_dir_info_free(sf_d); + return err; +} + +static int vboxsf_dir_release(struct inode *inode, struct file *file) +{ + if (file->private_data) + vboxsf_dir_info_free(file->private_data); + + return 0; +} + +static unsigned int vboxsf_get_d_type(u32 mode) +{ + unsigned int d_type; + + switch (mode & SHFL_TYPE_MASK) { + case SHFL_TYPE_FIFO: + d_type = DT_FIFO; + break; + case SHFL_TYPE_DEV_CHAR: + d_type = DT_CHR; + break; + case SHFL_TYPE_DIRECTORY: + d_type = DT_DIR; + break; + case SHFL_TYPE_DEV_BLOCK: + d_type = DT_BLK; + break; + case SHFL_TYPE_FILE: + d_type = DT_REG; + break; + case SHFL_TYPE_SYMLINK: + d_type = DT_LNK; + break; + case SHFL_TYPE_SOCKET: + d_type = DT_SOCK; + break; + case SHFL_TYPE_WHITEOUT: + d_type = DT_WHT; + break; + default: + d_type = DT_UNKNOWN; + break; + } + return d_type; +} + +static bool vboxsf_dir_emit(struct file *dir, struct dir_context *ctx) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(file_inode(dir)->i_sb); + struct vboxsf_dir_info *sf_d = dir->private_data; + struct shfl_dirinfo *info; + struct vboxsf_dir_buf *b; + unsigned int d_type; + loff_t i, cur = 0; + ino_t fake_ino; + void *end; + int err; + + list_for_each_entry(b, &sf_d->info_list, head) { +try_next_entry: + if (ctx->pos >= cur + b->entries) { + cur += b->entries; + continue; + } + + /* + * Note the vboxsf_dir_info objects we are iterating over here + * are variable sized, so the info pointer may end up being + * unaligned. This is how we get the data from the host. + * Since vboxsf is only supported on x86 machines this is not + * a problem. + */ + for (i = 0, info = b->buf; i < ctx->pos - cur; i++) { + end = &info->name.string.utf8[info->name.size]; + /* Only happens if the host gives us corrupt data */ + if (WARN_ON(end > (b->buf + b->used))) + return false; + info = end; + } + + end = &info->name.string.utf8[info->name.size]; + if (WARN_ON(end > (b->buf + b->used))) + return false; + + /* Info now points to the right entry, emit it. */ + d_type = vboxsf_get_d_type(info->info.attr.mode); + + /* + * On 32 bit systems pos is 64 signed, while ino is 32 bit + * unsigned so fake_ino may overflow, check for this. + */ + if ((ino_t)(ctx->pos + 1) != (u64)(ctx->pos + 1)) { + vbg_err("vboxsf: fake ino overflow, truncating dir\n"); + return false; + } + fake_ino = ctx->pos + 1; + + if (sbi->nls) { + char d_name[NAME_MAX]; + + err = vboxsf_nlscpy(sbi, d_name, NAME_MAX, + info->name.string.utf8, + info->name.length); + if (err) { + /* skip erroneous entry and proceed */ + ctx->pos += 1; + goto try_next_entry; + } + + return dir_emit(ctx, d_name, strlen(d_name), + fake_ino, d_type); + } + + return dir_emit(ctx, info->name.string.utf8, info->name.length, + fake_ino, d_type); + } + + return false; +} + +static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx) +{ + bool emitted; + + do { + emitted = vboxsf_dir_emit(dir, ctx); + if (emitted) + ctx->pos += 1; + } while (emitted); + + return 0; +} + +const struct file_operations vboxsf_dir_fops = { + .open = vboxsf_dir_open, + .iterate = vboxsf_dir_iterate, + .release = vboxsf_dir_release, + .read = generic_read_dir, + .llseek = generic_file_llseek, +}; + +/* + * This is called during name resolution/lookup to check if the @dentry in + * the cache is still valid. the job is handled by vboxsf_inode_revalidate. + */ +static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (d_really_is_positive(dentry)) + return vboxsf_inode_revalidate(dentry) == 0; + else + return vboxsf_stat_dentry(dentry, NULL) == -ENOENT; +} + +const struct dentry_operations vboxsf_dentry_ops = { + .d_revalidate = vboxsf_dentry_revalidate +}; + +/* iops */ + +static struct dentry *vboxsf_dir_lookup(struct inode *parent, + struct dentry *dentry, + unsigned int flags) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct shfl_fsobjinfo fsinfo; + struct inode *inode; + int err; + + dentry->d_time = jiffies; + + err = vboxsf_stat_dentry(dentry, &fsinfo); + if (err) { + inode = (err == -ENOENT) ? NULL : ERR_PTR(err); + } else { + inode = vboxsf_new_inode(parent->i_sb); + if (!IS_ERR(inode)) + vboxsf_init_inode(sbi, inode, &fsinfo); + } + + return d_splice_alias(inode, dentry); +} + +static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry, + struct shfl_fsobjinfo *info) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct vboxsf_inode *sf_i; + struct inode *inode; + + inode = vboxsf_new_inode(parent->i_sb); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + sf_i = VBOXSF_I(inode); + /* The host may have given us different attr then requested */ + sf_i->force_restat = 1; + vboxsf_init_inode(sbi, inode, info); + + d_instantiate(dentry, inode); + + return 0; +} + +static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, + umode_t mode, int is_dir) +{ + struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct shfl_createparms params = {}; + int err; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | + SHFL_CF_ACT_FAIL_IF_EXISTS | + SHFL_CF_ACCESS_READWRITE | + (is_dir ? SHFL_CF_DIRECTORY : 0); + params.info.attr.mode = (mode & 0777) | + (is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE); + params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING; + + err = vboxsf_create_at_dentry(dentry, ¶ms); + if (err) + return err; + + if (params.result != SHFL_FILE_CREATED) + return -EPERM; + + vboxsf_close(sbi->root, params.handle); + + err = vboxsf_dir_instantiate(parent, dentry, ¶ms.info); + if (err) + return err; + + /* parent directory access/change time changed */ + sf_parent_i->force_restat = 1; + + return 0; +} + +static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry, + umode_t mode, bool excl) +{ + return vboxsf_dir_create(parent, dentry, mode, 0); +} + +static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry, + umode_t mode) +{ + return vboxsf_dir_create(parent, dentry, mode, 1); +} + +static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); + struct inode *inode = d_inode(dentry); + struct shfl_string *path; + u32 flags; + int err; + + if (S_ISDIR(inode->i_mode)) + flags = SHFL_REMOVE_DIR; + else + flags = SHFL_REMOVE_FILE; + + if (S_ISLNK(inode->i_mode)) + flags |= SHFL_REMOVE_SYMLINK; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + err = vboxsf_remove(sbi->root, path, flags); + __putname(path); + if (err) + return err; + + /* parent directory access/change time changed */ + sf_parent_i->force_restat = 1; + + return 0; +} + +static int vboxsf_dir_rename(struct inode *old_parent, + struct dentry *old_dentry, + struct inode *new_parent, + struct dentry *new_dentry, + unsigned int flags) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(old_parent->i_sb); + struct vboxsf_inode *sf_old_parent_i = VBOXSF_I(old_parent); + struct vboxsf_inode *sf_new_parent_i = VBOXSF_I(new_parent); + u32 shfl_flags = SHFL_RENAME_FILE | SHFL_RENAME_REPLACE_IF_EXISTS; + struct shfl_string *old_path, *new_path; + int err; + + if (flags) + return -EINVAL; + + old_path = vboxsf_path_from_dentry(sbi, old_dentry); + if (IS_ERR(old_path)) + return PTR_ERR(old_path); + + new_path = vboxsf_path_from_dentry(sbi, new_dentry); + if (IS_ERR(new_path)) { + err = PTR_ERR(new_path); + goto err_put_old_path; + } + + if (d_inode(old_dentry)->i_mode & S_IFDIR) + shfl_flags = 0; + + err = vboxsf_rename(sbi->root, old_path, new_path, shfl_flags); + if (err == 0) { + /* parent directories access/change time changed */ + sf_new_parent_i->force_restat = 1; + sf_old_parent_i->force_restat = 1; + } + + __putname(new_path); +err_put_old_path: + __putname(old_path); + return err; +} + +static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry, + const char *symname) +{ + struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + int symname_size = strlen(symname) + 1; + struct shfl_string *path, *ssymname; + struct shfl_fsobjinfo info; + int err; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + ssymname = kmalloc(SHFLSTRING_HEADER_SIZE + symname_size, GFP_KERNEL); + if (!ssymname) { + __putname(path); + return -ENOMEM; + } + ssymname->length = symname_size - 1; + ssymname->size = symname_size; + memcpy(ssymname->string.utf8, symname, symname_size); + + err = vboxsf_symlink(sbi->root, path, ssymname, &info); + kfree(ssymname); + __putname(path); + if (err) { + /* -EROFS means symlinks are note support -> -EPERM */ + return (err == -EROFS) ? -EPERM : err; + } + + err = vboxsf_dir_instantiate(parent, dentry, &info); + if (err) + return err; + + /* parent directory access/change time changed */ + sf_parent_i->force_restat = 1; + return 0; +} + +const struct inode_operations vboxsf_dir_iops = { + .lookup = vboxsf_dir_lookup, + .create = vboxsf_dir_mkfile, + .mkdir = vboxsf_dir_mkdir, + .rmdir = vboxsf_dir_unlink, + .unlink = vboxsf_dir_unlink, + .rename = vboxsf_dir_rename, + .symlink = vboxsf_dir_symlink, + .getattr = vboxsf_getattr, + .setattr = vboxsf_setattr, +}; diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c new file mode 100644 index 000000000000..c4ab5996d97a --- /dev/null +++ b/fs/vboxsf/file.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Regular file inode and file ops. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include <linux/mm.h> +#include <linux/page-flags.h> +#include <linux/pagemap.h> +#include <linux/highmem.h> +#include <linux/sizes.h> +#include "vfsmod.h" + +struct vboxsf_handle { + u64 handle; + u32 root; + u32 access_flags; + struct kref refcount; + struct list_head head; +}; + +static int vboxsf_file_open(struct inode *inode, struct file *file) +{ + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct shfl_createparms params = {}; + struct vboxsf_handle *sf_handle; + u32 access_flags = 0; + int err; + + sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL); + if (!sf_handle) + return -ENOMEM; + + /* + * We check the value of params.handle afterwards to find out if + * the call succeeded or failed, as the API does not seem to cleanly + * distinguish error and informational messages. + * + * Furthermore, we must set params.handle to SHFL_HANDLE_NIL to + * make the shared folders host service use our mode parameter. + */ + params.handle = SHFL_HANDLE_NIL; + if (file->f_flags & O_CREAT) { + params.create_flags |= SHFL_CF_ACT_CREATE_IF_NEW; + /* + * We ignore O_EXCL, as the Linux kernel seems to call create + * beforehand itself, so O_EXCL should always fail. + */ + if (file->f_flags & O_TRUNC) + params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS; + else + params.create_flags |= SHFL_CF_ACT_OPEN_IF_EXISTS; + } else { + params.create_flags |= SHFL_CF_ACT_FAIL_IF_NEW; + if (file->f_flags & O_TRUNC) + params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS; + } + + switch (file->f_flags & O_ACCMODE) { + case O_RDONLY: + access_flags |= SHFL_CF_ACCESS_READ; + break; + + case O_WRONLY: + access_flags |= SHFL_CF_ACCESS_WRITE; + break; + + case O_RDWR: + access_flags |= SHFL_CF_ACCESS_READWRITE; + break; + + default: + WARN_ON(1); + } + + if (file->f_flags & O_APPEND) + access_flags |= SHFL_CF_ACCESS_APPEND; + + params.create_flags |= access_flags; + params.info.attr.mode = inode->i_mode; + + err = vboxsf_create_at_dentry(file_dentry(file), ¶ms); + if (err == 0 && params.handle == SHFL_HANDLE_NIL) + err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT; + if (err) { + kfree(sf_handle); + return err; + } + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + + /* init our handle struct and add it to the inode's handles list */ + sf_handle->handle = params.handle; + sf_handle->root = VBOXSF_SBI(inode->i_sb)->root; + sf_handle->access_flags = access_flags; + kref_init(&sf_handle->refcount); + + mutex_lock(&sf_i->handle_list_mutex); + list_add(&sf_handle->head, &sf_i->handle_list); + mutex_unlock(&sf_i->handle_list_mutex); + + file->private_data = sf_handle; + return 0; +} + +static void vboxsf_handle_release(struct kref *refcount) +{ + struct vboxsf_handle *sf_handle = + container_of(refcount, struct vboxsf_handle, refcount); + + vboxsf_close(sf_handle->root, sf_handle->handle); + kfree(sf_handle); +} + +static int vboxsf_file_release(struct inode *inode, struct file *file) +{ + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct vboxsf_handle *sf_handle = file->private_data; + + /* + * When a file is closed on our (the guest) side, we want any subsequent + * accesses done on the host side to see all changes done from our side. + */ + filemap_write_and_wait(inode->i_mapping); + + mutex_lock(&sf_i->handle_list_mutex); + list_del(&sf_handle->head); + mutex_unlock(&sf_i->handle_list_mutex); + + kref_put(&sf_handle->refcount, vboxsf_handle_release); + return 0; +} + +/* + * Write back dirty pages now, because there may not be any suitable + * open files later + */ +static void vboxsf_vma_close(struct vm_area_struct *vma) +{ + filemap_write_and_wait(vma->vm_file->f_mapping); +} + +static const struct vm_operations_struct vboxsf_file_vm_ops = { + .close = vboxsf_vma_close, + .fault = filemap_fault, + .map_pages = filemap_map_pages, +}; + +static int vboxsf_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err; + + err = generic_file_mmap(file, vma); + if (!err) + vma->vm_ops = &vboxsf_file_vm_ops; + + return err; +} + +/* + * Note that since we are accessing files on the host's filesystem, files + * may always be changed underneath us by the host! + * + * The vboxsf API between the guest and the host does not offer any functions + * to deal with this. There is no inode-generation to check for changes, no + * events / callback on changes and no way to lock files. + * + * To avoid returning stale data when a file gets *opened* on our (the guest) + * side, we do a "stat" on the host side, then compare the mtime with the + * last known mtime and invalidate the page-cache if they differ. + * This is done from vboxsf_inode_revalidate(). + * + * When reads are done through the read_iter fop, it is possible to do + * further cache revalidation then, there are 3 options to deal with this: + * + * 1) Rely solely on the revalidation done at open time + * 2) Do another "stat" and compare mtime again. Unfortunately the vboxsf + * host API does not allow stat on handles, so we would need to use + * file->f_path.dentry and the stat will then fail if the file was unlinked + * or renamed (and there is no thing like NFS' silly-rename). So we get: + * 2a) "stat" and compare mtime, on stat failure invalidate the cache + * 2b) "stat" and compare mtime, on stat failure do nothing + * 3) Simply always call invalidate_inode_pages2_range on the range of the read + * + * Currently we are keeping things KISS and using option 1. this allows + * directly using generic_file_read_iter without wrapping it. + * + * This means that only data written on the host side before open() on + * the guest side is guaranteed to be seen by the guest. If necessary + * we may provide other read-cache strategies in the future and make this + * configurable through a mount option. + */ +const struct file_operations vboxsf_reg_fops = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .mmap = vboxsf_file_mmap, + .open = vboxsf_file_open, + .release = vboxsf_file_release, + .fsync = noop_fsync, + .splice_read = generic_file_splice_read, +}; + +const struct inode_operations vboxsf_reg_iops = { + .getattr = vboxsf_getattr, + .setattr = vboxsf_setattr +}; + +static int vboxsf_readpage(struct file *file, struct page *page) +{ + struct vboxsf_handle *sf_handle = file->private_data; + loff_t off = page_offset(page); + u32 nread = PAGE_SIZE; + u8 *buf; + int err; + + buf = kmap(page); + + err = vboxsf_read(sf_handle->root, sf_handle->handle, off, &nread, buf); + if (err == 0) { + memset(&buf[nread], 0, PAGE_SIZE - nread); + flush_dcache_page(page); + SetPageUptodate(page); + } else { + SetPageError(page); + } + + kunmap(page); + unlock_page(page); + return err; +} + +static struct vboxsf_handle *vboxsf_get_write_handle(struct vboxsf_inode *sf_i) +{ + struct vboxsf_handle *h, *sf_handle = NULL; + + mutex_lock(&sf_i->handle_list_mutex); + list_for_each_entry(h, &sf_i->handle_list, head) { + if (h->access_flags == SHFL_CF_ACCESS_WRITE || + h->access_flags == SHFL_CF_ACCESS_READWRITE) { + kref_get(&h->refcount); + sf_handle = h; + break; + } + } + mutex_unlock(&sf_i->handle_list_mutex); + + return sf_handle; +} + +static int vboxsf_writepage(struct page *page, struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct vboxsf_handle *sf_handle; + loff_t off = page_offset(page); + loff_t size = i_size_read(inode); + u32 nwrite = PAGE_SIZE; + u8 *buf; + int err; + + if (off + PAGE_SIZE > size) + nwrite = size & ~PAGE_MASK; + + sf_handle = vboxsf_get_write_handle(sf_i); + if (!sf_handle) + return -EBADF; + + buf = kmap(page); + err = vboxsf_write(sf_handle->root, sf_handle->handle, + off, &nwrite, buf); + kunmap(page); + + kref_put(&sf_handle->refcount, vboxsf_handle_release); + + if (err == 0) { + ClearPageError(page); + /* mtime changed */ + sf_i->force_restat = 1; + } else { + ClearPageUptodate(page); + } + + unlock_page(page); + return err; +} + +static int vboxsf_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + struct vboxsf_handle *sf_handle = file->private_data; + unsigned int from = pos & ~PAGE_MASK; + u32 nwritten = len; + u8 *buf; + int err; + + /* zero the stale part of the page if we did a short copy */ + if (!PageUptodate(page) && copied < len) + zero_user(page, from + copied, len - copied); + + buf = kmap(page); + err = vboxsf_write(sf_handle->root, sf_handle->handle, + pos, &nwritten, buf + from); + kunmap(page); + + if (err) { + nwritten = 0; + goto out; + } + + /* mtime changed */ + VBOXSF_I(inode)->force_restat = 1; + + if (!PageUptodate(page) && nwritten == PAGE_SIZE) + SetPageUptodate(page); + + pos += nwritten; + if (pos > inode->i_size) + i_size_write(inode, pos); + +out: + unlock_page(page); + put_page(page); + + return nwritten; +} + +/* + * Note simple_write_begin does not read the page from disk on partial writes + * this is ok since vboxsf_write_end only writes the written parts of the + * page and it does not call SetPageUptodate for partial writes. + */ +const struct address_space_operations vboxsf_reg_aops = { + .readpage = vboxsf_readpage, + .writepage = vboxsf_writepage, + .set_page_dirty = __set_page_dirty_nobuffers, + .write_begin = simple_write_begin, + .write_end = vboxsf_write_end, +}; + +static const char *vboxsf_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); + struct shfl_string *path; + char *link; + int err; + + if (!dentry) + return ERR_PTR(-ECHILD); + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return ERR_CAST(path); + + link = kzalloc(PATH_MAX, GFP_KERNEL); + if (!link) { + __putname(path); + return ERR_PTR(-ENOMEM); + } + + err = vboxsf_readlink(sbi->root, path, PATH_MAX, link); + __putname(path); + if (err) { + kfree(link); + return ERR_PTR(err); + } + + set_delayed_call(done, kfree_link, link); + return link; +} + +const struct inode_operations vboxsf_lnk_iops = { + .get_link = vboxsf_get_link +}; diff --git a/fs/vboxsf/shfl_hostintf.h b/fs/vboxsf/shfl_hostintf.h new file mode 100644 index 000000000000..aca829062c12 --- /dev/null +++ b/fs/vboxsf/shfl_hostintf.h @@ -0,0 +1,901 @@ +/* SPDX-License-Identifier: MIT */ +/* + * VirtualBox Shared Folders: host interface definition. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#ifndef SHFL_HOSTINTF_H +#define SHFL_HOSTINTF_H + +#include <linux/vbox_vmmdev_types.h> + +/* The max in/out buffer size for a FN_READ or FN_WRITE call */ +#define SHFL_MAX_RW_COUNT (16 * SZ_1M) + +/* + * Structures shared between guest and the service + * can be relocated and use offsets to point to variable + * length parts. + * + * Shared folders protocol works with handles. + * Before doing any action on a file system object, + * one have to obtain the object handle via a SHFL_FN_CREATE + * request. A handle must be closed with SHFL_FN_CLOSE. + */ + +enum { + SHFL_FN_QUERY_MAPPINGS = 1, /* Query mappings changes. */ + SHFL_FN_QUERY_MAP_NAME = 2, /* Query map name. */ + SHFL_FN_CREATE = 3, /* Open/create object. */ + SHFL_FN_CLOSE = 4, /* Close object handle. */ + SHFL_FN_READ = 5, /* Read object content. */ + SHFL_FN_WRITE = 6, /* Write new object content. */ + SHFL_FN_LOCK = 7, /* Lock/unlock a range in the object. */ + SHFL_FN_LIST = 8, /* List object content. */ + SHFL_FN_INFORMATION = 9, /* Query/set object information. */ + /* Note function number 10 is not used! */ + SHFL_FN_REMOVE = 11, /* Remove object */ + SHFL_FN_MAP_FOLDER_OLD = 12, /* Map folder (legacy) */ + SHFL_FN_UNMAP_FOLDER = 13, /* Unmap folder */ + SHFL_FN_RENAME = 14, /* Rename object */ + SHFL_FN_FLUSH = 15, /* Flush file */ + SHFL_FN_SET_UTF8 = 16, /* Select UTF8 filename encoding */ + SHFL_FN_MAP_FOLDER = 17, /* Map folder */ + SHFL_FN_READLINK = 18, /* Read symlink dest (as of VBox 4.0) */ + SHFL_FN_SYMLINK = 19, /* Create symlink (as of VBox 4.0) */ + SHFL_FN_SET_SYMLINKS = 20, /* Ask host to show symlinks (4.0+) */ +}; + +/* Root handles for a mapping are of type u32, Root handles are unique. */ +#define SHFL_ROOT_NIL UINT_MAX + +/* Shared folders handle for an opened object are of type u64. */ +#define SHFL_HANDLE_NIL ULLONG_MAX + +/* Hardcoded maximum length (in chars) of a shared folder name. */ +#define SHFL_MAX_LEN (256) +/* Hardcoded maximum number of shared folder mapping available to the guest. */ +#define SHFL_MAX_MAPPINGS (64) + +/** Shared folder string buffer structure. */ +struct shfl_string { + /** Allocated size of the string member in bytes. */ + u16 size; + + /** Length of string without trailing nul in bytes. */ + u16 length; + + /** UTF-8 or UTF-16 string. Nul terminated. */ + union { + u8 utf8[2]; + u16 utf16[1]; + u16 ucs2[1]; /* misnomer, use utf16. */ + } string; +}; +VMMDEV_ASSERT_SIZE(shfl_string, 6); + +/* The size of shfl_string w/o the string part. */ +#define SHFLSTRING_HEADER_SIZE 4 + +/* Calculate size of the string. */ +static inline u32 shfl_string_buf_size(const struct shfl_string *string) +{ + return string ? SHFLSTRING_HEADER_SIZE + string->size : 0; +} + +/* Set user id on execution (S_ISUID). */ +#define SHFL_UNIX_ISUID 0004000U +/* Set group id on execution (S_ISGID). */ +#define SHFL_UNIX_ISGID 0002000U +/* Sticky bit (S_ISVTX / S_ISTXT). */ +#define SHFL_UNIX_ISTXT 0001000U + +/* Owner readable (S_IRUSR). */ +#define SHFL_UNIX_IRUSR 0000400U +/* Owner writable (S_IWUSR). */ +#define SHFL_UNIX_IWUSR 0000200U +/* Owner executable (S_IXUSR). */ +#define SHFL_UNIX_IXUSR 0000100U + +/* Group readable (S_IRGRP). */ +#define SHFL_UNIX_IRGRP 0000040U +/* Group writable (S_IWGRP). */ +#define SHFL_UNIX_IWGRP 0000020U +/* Group executable (S_IXGRP). */ +#define SHFL_UNIX_IXGRP 0000010U + +/* Other readable (S_IROTH). */ +#define SHFL_UNIX_IROTH 0000004U +/* Other writable (S_IWOTH). */ +#define SHFL_UNIX_IWOTH 0000002U +/* Other executable (S_IXOTH). */ +#define SHFL_UNIX_IXOTH 0000001U + +/* Named pipe (fifo) (S_IFIFO). */ +#define SHFL_TYPE_FIFO 0010000U +/* Character device (S_IFCHR). */ +#define SHFL_TYPE_DEV_CHAR 0020000U +/* Directory (S_IFDIR). */ +#define SHFL_TYPE_DIRECTORY 0040000U +/* Block device (S_IFBLK). */ +#define SHFL_TYPE_DEV_BLOCK 0060000U +/* Regular file (S_IFREG). */ +#define SHFL_TYPE_FILE 0100000U +/* Symbolic link (S_IFLNK). */ +#define SHFL_TYPE_SYMLINK 0120000U +/* Socket (S_IFSOCK). */ +#define SHFL_TYPE_SOCKET 0140000U +/* Whiteout (S_IFWHT). */ +#define SHFL_TYPE_WHITEOUT 0160000U +/* Type mask (S_IFMT). */ +#define SHFL_TYPE_MASK 0170000U + +/* Checks the mode flags indicate a directory (S_ISDIR). */ +#define SHFL_IS_DIRECTORY(m) (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_DIRECTORY) +/* Checks the mode flags indicate a symbolic link (S_ISLNK). */ +#define SHFL_IS_SYMLINK(m) (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_SYMLINK) + +/** The available additional information in a shfl_fsobjattr object. */ +enum shfl_fsobjattr_add { + /** No additional information is available / requested. */ + SHFLFSOBJATTRADD_NOTHING = 1, + /** + * The additional unix attributes (shfl_fsobjattr::u::unix_attr) are + * available / requested. + */ + SHFLFSOBJATTRADD_UNIX, + /** + * The additional extended attribute size (shfl_fsobjattr::u::size) is + * available / requested. + */ + SHFLFSOBJATTRADD_EASIZE, + /** + * The last valid item (inclusive). + * The valid range is SHFLFSOBJATTRADD_NOTHING thru + * SHFLFSOBJATTRADD_LAST. + */ + SHFLFSOBJATTRADD_LAST = SHFLFSOBJATTRADD_EASIZE, + + /** The usual 32-bit hack. */ + SHFLFSOBJATTRADD_32BIT_SIZE_HACK = 0x7fffffff +}; + +/** + * Additional unix Attributes, these are available when + * shfl_fsobjattr.additional == SHFLFSOBJATTRADD_UNIX. + */ +struct shfl_fsobjattr_unix { + /** + * The user owning the filesystem object (st_uid). + * This field is ~0U if not supported. + */ + u32 uid; + + /** + * The group the filesystem object is assigned (st_gid). + * This field is ~0U if not supported. + */ + u32 gid; + + /** + * Number of hard links to this filesystem object (st_nlink). + * This field is 1 if the filesystem doesn't support hardlinking or + * the information isn't available. + */ + u32 hardlinks; + + /** + * The device number of the device which this filesystem object resides + * on (st_dev). This field is 0 if this information is not available. + */ + u32 inode_id_device; + + /** + * The unique identifier (within the filesystem) of this filesystem + * object (st_ino). Together with inode_id_device, this field can be + * used as a OS wide unique id, when both their values are not 0. + * This field is 0 if the information is not available. + */ + u64 inode_id; + + /** + * User flags (st_flags). + * This field is 0 if this information is not available. + */ + u32 flags; + + /** + * The current generation number (st_gen). + * This field is 0 if this information is not available. + */ + u32 generation_id; + + /** + * The device number of a char. or block device type object (st_rdev). + * This field is 0 if the file isn't a char. or block device or when + * the OS doesn't use the major+minor device idenfication scheme. + */ + u32 device; +} __packed; + +/** Extended attribute size. */ +struct shfl_fsobjattr_easize { + /** Size of EAs. */ + s64 cb; +} __packed; + +/** Shared folder filesystem object attributes. */ +struct shfl_fsobjattr { + /** Mode flags (st_mode). SHFL_UNIX_*, SHFL_TYPE_*, and SHFL_DOS_*. */ + u32 mode; + + /** The additional attributes available. */ + enum shfl_fsobjattr_add additional; + + /** + * Additional attributes. + * + * Unless explicitly specified to an API, the API can provide additional + * data as it is provided by the underlying OS. + */ + union { + struct shfl_fsobjattr_unix unix_attr; + struct shfl_fsobjattr_easize size; + } __packed u; +} __packed; +VMMDEV_ASSERT_SIZE(shfl_fsobjattr, 44); + +struct shfl_timespec { + s64 ns_relative_to_unix_epoch; +}; + +/** Filesystem object information structure. */ +struct shfl_fsobjinfo { + /** + * Logical size (st_size). + * For normal files this is the size of the file. + * For symbolic links, this is the length of the path name contained + * in the symbolic link. + * For other objects this fields needs to be specified. + */ + s64 size; + + /** Disk allocation size (st_blocks * DEV_BSIZE). */ + s64 allocated; + + /** Time of last access (st_atime). */ + struct shfl_timespec access_time; + + /** Time of last data modification (st_mtime). */ + struct shfl_timespec modification_time; + + /** + * Time of last status change (st_ctime). + * If not available this is set to modification_time. + */ + struct shfl_timespec change_time; + + /** + * Time of file birth (st_birthtime). + * If not available this is set to change_time. + */ + struct shfl_timespec birth_time; + + /** Attributes. */ + struct shfl_fsobjattr attr; + +} __packed; +VMMDEV_ASSERT_SIZE(shfl_fsobjinfo, 92); + +/** + * result of an open/create request. + * Along with handle value the result code + * identifies what has happened while + * trying to open the object. + */ +enum shfl_create_result { + SHFL_NO_RESULT, + /** Specified path does not exist. */ + SHFL_PATH_NOT_FOUND, + /** Path to file exists, but the last component does not. */ + SHFL_FILE_NOT_FOUND, + /** File already exists and either has been opened or not. */ + SHFL_FILE_EXISTS, + /** New file was created. */ + SHFL_FILE_CREATED, + /** Existing file was replaced or overwritten. */ + SHFL_FILE_REPLACED +}; + +/* No flags. Initialization value. */ +#define SHFL_CF_NONE (0x00000000) + +/* + * Only lookup the object, do not return a handle. When this is set all other + * flags are ignored. + */ +#define SHFL_CF_LOOKUP (0x00000001) + +/* + * Open parent directory of specified object. + * Useful for the corresponding Windows FSD flag + * and for opening paths like \\dir\\*.* to search the 'dir'. + */ +#define SHFL_CF_OPEN_TARGET_DIRECTORY (0x00000002) + +/* Create/open a directory. */ +#define SHFL_CF_DIRECTORY (0x00000004) + +/* + * Open/create action to do if object exists + * and if the object does not exists. + * REPLACE file means atomically DELETE and CREATE. + * OVERWRITE file means truncating the file to 0 and + * setting new size. + * When opening an existing directory REPLACE and OVERWRITE + * actions are considered invalid, and cause returning + * FILE_EXISTS with NIL handle. + */ +#define SHFL_CF_ACT_MASK_IF_EXISTS (0x000000f0) +#define SHFL_CF_ACT_MASK_IF_NEW (0x00000f00) + +/* What to do if object exists. */ +#define SHFL_CF_ACT_OPEN_IF_EXISTS (0x00000000) +#define SHFL_CF_ACT_FAIL_IF_EXISTS (0x00000010) +#define SHFL_CF_ACT_REPLACE_IF_EXISTS (0x00000020) +#define SHFL_CF_ACT_OVERWRITE_IF_EXISTS (0x00000030) + +/* What to do if object does not exist. */ +#define SHFL_CF_ACT_CREATE_IF_NEW (0x00000000) +#define SHFL_CF_ACT_FAIL_IF_NEW (0x00000100) + +/* Read/write requested access for the object. */ +#define SHFL_CF_ACCESS_MASK_RW (0x00003000) + +/* No access requested. */ +#define SHFL_CF_ACCESS_NONE (0x00000000) +/* Read access requested. */ +#define SHFL_CF_ACCESS_READ (0x00001000) +/* Write access requested. */ +#define SHFL_CF_ACCESS_WRITE (0x00002000) +/* Read/Write access requested. */ +#define SHFL_CF_ACCESS_READWRITE (0x00003000) + +/* Requested share access for the object. */ +#define SHFL_CF_ACCESS_MASK_DENY (0x0000c000) + +/* Allow any access. */ +#define SHFL_CF_ACCESS_DENYNONE (0x00000000) +/* Do not allow read. */ +#define SHFL_CF_ACCESS_DENYREAD (0x00004000) +/* Do not allow write. */ +#define SHFL_CF_ACCESS_DENYWRITE (0x00008000) +/* Do not allow access. */ +#define SHFL_CF_ACCESS_DENYALL (0x0000c000) + +/* Requested access to attributes of the object. */ +#define SHFL_CF_ACCESS_MASK_ATTR (0x00030000) + +/* No access requested. */ +#define SHFL_CF_ACCESS_ATTR_NONE (0x00000000) +/* Read access requested. */ +#define SHFL_CF_ACCESS_ATTR_READ (0x00010000) +/* Write access requested. */ +#define SHFL_CF_ACCESS_ATTR_WRITE (0x00020000) +/* Read/Write access requested. */ +#define SHFL_CF_ACCESS_ATTR_READWRITE (0x00030000) + +/* + * The file is opened in append mode. + * Ignored if SHFL_CF_ACCESS_WRITE is not set. + */ +#define SHFL_CF_ACCESS_APPEND (0x00040000) + +/** Create parameters buffer struct for SHFL_FN_CREATE call */ +struct shfl_createparms { + /** Returned handle of opened object. */ + u64 handle; + + /** Returned result of the operation */ + enum shfl_create_result result; + + /** SHFL_CF_* */ + u32 create_flags; + + /** + * Attributes of object to create and + * returned actual attributes of opened/created object. + */ + struct shfl_fsobjinfo info; +} __packed; + +/** Shared Folder directory information */ +struct shfl_dirinfo { + /** Full information about the object. */ + struct shfl_fsobjinfo info; + /** + * The length of the short field (number of UTF16 chars). + * It is 16-bit for reasons of alignment. + */ + u16 short_name_len; + /** + * The short name for 8.3 compatibility. + * Empty string if not available. + */ + u16 short_name[14]; + struct shfl_string name; +}; + +/** Shared folder filesystem properties. */ +struct shfl_fsproperties { + /** + * The maximum size of a filesystem object name. + * This does not include the '\\0'. + */ + u32 max_component_len; + + /** + * True if the filesystem is remote. + * False if the filesystem is local. + */ + bool remote; + + /** + * True if the filesystem is case sensitive. + * False if the filesystem is case insensitive. + */ + bool case_sensitive; + + /** + * True if the filesystem is mounted read only. + * False if the filesystem is mounted read write. + */ + bool read_only; + + /** + * True if the filesystem can encode unicode object names. + * False if it can't. + */ + bool supports_unicode; + + /** + * True if the filesystem is compresses. + * False if it isn't or we don't know. + */ + bool compressed; + + /** + * True if the filesystem compresses of individual files. + * False if it doesn't or we don't know. + */ + bool file_compression; +}; +VMMDEV_ASSERT_SIZE(shfl_fsproperties, 12); + +struct shfl_volinfo { + s64 total_allocation_bytes; + s64 available_allocation_bytes; + u32 bytes_per_allocation_unit; + u32 bytes_per_sector; + u32 serial; + struct shfl_fsproperties properties; +}; + + +/** SHFL_FN_MAP_FOLDER Parameters structure. */ +struct shfl_map_folder { + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, out: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: UTF16 + * Path delimiter + */ + struct vmmdev_hgcm_function_parameter delimiter; + + /** + * pointer, in: SHFLROOT (u32) + * Case senstive flag + */ + struct vmmdev_hgcm_function_parameter case_sensitive; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_MAP_FOLDER (4) + + +/** SHFL_FN_UNMAP_FOLDER Parameters structure. */ +struct shfl_unmap_folder { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_UNMAP_FOLDER (1) + + +/** SHFL_FN_CREATE Parameters structure. */ +struct shfl_create { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, in/out: + * Points to struct shfl_createparms buffer. + */ + struct vmmdev_hgcm_function_parameter parms; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_CREATE (3) + + +/** SHFL_FN_CLOSE Parameters structure. */ +struct shfl_close { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to close. + */ + struct vmmdev_hgcm_function_parameter handle; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_CLOSE (2) + + +/** SHFL_FN_READ Parameters structure. */ +struct shfl_read { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to read from. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value64, in: + * Offset to read from. + */ + struct vmmdev_hgcm_function_parameter offset; + + /** + * value64, in/out: + * Bytes to read/How many were read. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, out: + * Buffer to place data to. + */ + struct vmmdev_hgcm_function_parameter buffer; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_READ (5) + + +/** SHFL_FN_WRITE Parameters structure. */ +struct shfl_write { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to write to. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value64, in: + * Offset to write to. + */ + struct vmmdev_hgcm_function_parameter offset; + + /** + * value64, in/out: + * Bytes to write/How many were written. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, in: + * Data to write. + */ + struct vmmdev_hgcm_function_parameter buffer; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_WRITE (5) + + +/* + * SHFL_FN_LIST + * Listing information includes variable length RTDIRENTRY[EX] structures. + */ + +#define SHFL_LIST_NONE 0 +#define SHFL_LIST_RETURN_ONE 1 + +/** SHFL_FN_LIST Parameters structure. */ +struct shfl_list { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to be listed. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value32, in: + * List flags SHFL_LIST_*. + */ + struct vmmdev_hgcm_function_parameter flags; + + /** + * value32, in/out: + * Bytes to be used for listing information/How many bytes were used. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, in/optional + * Points to struct shfl_string buffer that specifies a search path. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, out: + * Buffer to place listing information to. (struct shfl_dirinfo) + */ + struct vmmdev_hgcm_function_parameter buffer; + + /** + * value32, in/out: + * Indicates a key where the listing must be resumed. + * in: 0 means start from begin of object. + * out: 0 means listing completed. + */ + struct vmmdev_hgcm_function_parameter resume_point; + + /** + * pointer, out: + * Number of files returned + */ + struct vmmdev_hgcm_function_parameter file_count; +}; + +/* Number of parameters */ +#define SHFL_CPARMS_LIST (8) + + +/** SHFL_FN_READLINK Parameters structure. */ +struct shfl_readLink { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * pointer, out: + * Buffer to place data to. + */ + struct vmmdev_hgcm_function_parameter buffer; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_READLINK (3) + + +/* SHFL_FN_INFORMATION */ + +/* Mask of Set/Get bit. */ +#define SHFL_INFO_MODE_MASK (0x1) +/* Get information */ +#define SHFL_INFO_GET (0x0) +/* Set information */ +#define SHFL_INFO_SET (0x1) + +/* Get name of the object. */ +#define SHFL_INFO_NAME (0x2) +/* Set size of object (extend/trucate); only applies to file objects */ +#define SHFL_INFO_SIZE (0x4) +/* Get/Set file object info. */ +#define SHFL_INFO_FILE (0x8) +/* Get volume information. */ +#define SHFL_INFO_VOLUME (0x10) + +/** SHFL_FN_INFORMATION Parameters structure. */ +struct shfl_information { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * value64, in: + * SHFLHANDLE (u64) of object to be listed. + */ + struct vmmdev_hgcm_function_parameter handle; + + /** + * value32, in: + * SHFL_INFO_* + */ + struct vmmdev_hgcm_function_parameter flags; + + /** + * value32, in/out: + * Bytes to be used for information/How many bytes were used. + */ + struct vmmdev_hgcm_function_parameter cb; + + /** + * pointer, in/out: + * Information to be set/get (shfl_fsobjinfo or shfl_string). Do not + * forget to set the shfl_fsobjinfo::attr::additional for a get + * operation as well. + */ + struct vmmdev_hgcm_function_parameter info; + +}; + +/* Number of parameters */ +#define SHFL_CPARMS_INFORMATION (5) + + +/* SHFL_FN_REMOVE */ + +#define SHFL_REMOVE_FILE (0x1) +#define SHFL_REMOVE_DIR (0x2) +#define SHFL_REMOVE_SYMLINK (0x4) + +/** SHFL_FN_REMOVE Parameters structure. */ +struct shfl_remove { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string buffer. + */ + struct vmmdev_hgcm_function_parameter path; + + /** + * value32, in: + * remove flags (file/directory) + */ + struct vmmdev_hgcm_function_parameter flags; + +}; + +#define SHFL_CPARMS_REMOVE (3) + + +/* SHFL_FN_RENAME */ + +#define SHFL_RENAME_FILE (0x1) +#define SHFL_RENAME_DIR (0x2) +#define SHFL_RENAME_REPLACE_IF_EXISTS (0x4) + +/** SHFL_FN_RENAME Parameters structure. */ +struct shfl_rename { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string src. + */ + struct vmmdev_hgcm_function_parameter src; + + /** + * pointer, in: + * Points to struct shfl_string dest. + */ + struct vmmdev_hgcm_function_parameter dest; + + /** + * value32, in: + * rename flags (file/directory) + */ + struct vmmdev_hgcm_function_parameter flags; + +}; + +#define SHFL_CPARMS_RENAME (4) + + +/** SHFL_FN_SYMLINK Parameters structure. */ +struct shfl_symlink { + /** + * pointer, in: SHFLROOT (u32) + * Root handle of the mapping which name is queried. + */ + struct vmmdev_hgcm_function_parameter root; + + /** + * pointer, in: + * Points to struct shfl_string of path for the new symlink. + */ + struct vmmdev_hgcm_function_parameter new_path; + + /** + * pointer, in: + * Points to struct shfl_string of destination for symlink. + */ + struct vmmdev_hgcm_function_parameter old_path; + + /** + * pointer, out: + * Information about created symlink. + */ + struct vmmdev_hgcm_function_parameter info; + +}; + +#define SHFL_CPARMS_SYMLINK (4) + +#endif diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c new file mode 100644 index 000000000000..675e26989376 --- /dev/null +++ b/fs/vboxsf/super.c @@ -0,0 +1,491 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Virtual File System. + * + * Module initialization/finalization + * File system registration/deregistration + * Superblock reading + * Few utility functions + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include <linux/idr.h> +#include <linux/fs_parser.h> +#include <linux/magic.h> +#include <linux/module.h> +#include <linux/nls.h> +#include <linux/statfs.h> +#include <linux/vbox_utils.h> +#include "vfsmod.h" + +#define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */ + +#define VBSF_MOUNT_SIGNATURE_BYTE_0 ('\000') +#define VBSF_MOUNT_SIGNATURE_BYTE_1 ('\377') +#define VBSF_MOUNT_SIGNATURE_BYTE_2 ('\376') +#define VBSF_MOUNT_SIGNATURE_BYTE_3 ('\375') + +static int follow_symlinks; +module_param(follow_symlinks, int, 0444); +MODULE_PARM_DESC(follow_symlinks, + "Let host resolve symlinks rather than showing them"); + +static DEFINE_IDA(vboxsf_bdi_ida); +static DEFINE_MUTEX(vboxsf_setup_mutex); +static bool vboxsf_setup_done; +static struct super_operations vboxsf_super_ops; /* forward declaration */ +static struct kmem_cache *vboxsf_inode_cachep; + +static char * const vboxsf_default_nls = CONFIG_NLS_DEFAULT; + +enum { opt_nls, opt_uid, opt_gid, opt_ttl, opt_dmode, opt_fmode, + opt_dmask, opt_fmask }; + +static const struct fs_parameter_spec vboxsf_fs_parameters[] = { + fsparam_string ("nls", opt_nls), + fsparam_u32 ("uid", opt_uid), + fsparam_u32 ("gid", opt_gid), + fsparam_u32 ("ttl", opt_ttl), + fsparam_u32oct ("dmode", opt_dmode), + fsparam_u32oct ("fmode", opt_fmode), + fsparam_u32oct ("dmask", opt_dmask), + fsparam_u32oct ("fmask", opt_fmask), + {} +}; + +static int vboxsf_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct vboxsf_fs_context *ctx = fc->fs_private; + struct fs_parse_result result; + kuid_t uid; + kgid_t gid; + int opt; + + opt = fs_parse(fc, vboxsf_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case opt_nls: + if (ctx->nls_name || fc->purpose != FS_CONTEXT_FOR_MOUNT) { + vbg_err("vboxsf: Cannot reconfigure nls option\n"); + return -EINVAL; + } + ctx->nls_name = param->string; + param->string = NULL; + break; + case opt_uid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + return -EINVAL; + ctx->o.uid = uid; + break; + case opt_gid: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + return -EINVAL; + ctx->o.gid = gid; + break; + case opt_ttl: + ctx->o.ttl = msecs_to_jiffies(result.uint_32); + break; + case opt_dmode: + if (result.uint_32 & ~0777) + return -EINVAL; + ctx->o.dmode = result.uint_32; + ctx->o.dmode_set = true; + break; + case opt_fmode: + if (result.uint_32 & ~0777) + return -EINVAL; + ctx->o.fmode = result.uint_32; + ctx->o.fmode_set = true; + break; + case opt_dmask: + if (result.uint_32 & ~07777) + return -EINVAL; + ctx->o.dmask = result.uint_32; + break; + case opt_fmask: + if (result.uint_32 & ~07777) + return -EINVAL; + ctx->o.fmask = result.uint_32; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct vboxsf_fs_context *ctx = fc->fs_private; + struct shfl_string *folder_name, root_path; + struct vboxsf_sbi *sbi; + struct dentry *droot; + struct inode *iroot; + char *nls_name; + size_t size; + int err; + + if (!fc->source) + return -EINVAL; + + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + + sbi->o = ctx->o; + idr_init(&sbi->ino_idr); + spin_lock_init(&sbi->ino_idr_lock); + sbi->next_generation = 1; + sbi->bdi_id = -1; + + /* Load nls if not utf8 */ + nls_name = ctx->nls_name ? ctx->nls_name : vboxsf_default_nls; + if (strcmp(nls_name, "utf8") != 0) { + if (nls_name == vboxsf_default_nls) + sbi->nls = load_nls_default(); + else + sbi->nls = load_nls(nls_name); + + if (!sbi->nls) { + vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); + err = -EINVAL; + goto fail_free; + } + } + + sbi->bdi_id = ida_simple_get(&vboxsf_bdi_ida, 0, 0, GFP_KERNEL); + if (sbi->bdi_id < 0) { + err = sbi->bdi_id; + goto fail_free; + } + + err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id); + if (err) + goto fail_free; + + /* Turn source into a shfl_string and map the folder */ + size = strlen(fc->source) + 1; + folder_name = kmalloc(SHFLSTRING_HEADER_SIZE + size, GFP_KERNEL); + if (!folder_name) { + err = -ENOMEM; + goto fail_free; + } + folder_name->size = size; + folder_name->length = size - 1; + strlcpy(folder_name->string.utf8, fc->source, size); + err = vboxsf_map_folder(folder_name, &sbi->root); + kfree(folder_name); + if (err) { + vbg_err("vboxsf: Host rejected mount of '%s' with error %d\n", + fc->source, err); + goto fail_free; + } + + root_path.length = 1; + root_path.size = 2; + root_path.string.utf8[0] = '/'; + root_path.string.utf8[1] = 0; + err = vboxsf_stat(sbi, &root_path, &sbi->root_info); + if (err) + goto fail_unmap; + + sb->s_magic = VBOXSF_SUPER_MAGIC; + sb->s_blocksize = 1024; + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_op = &vboxsf_super_ops; + sb->s_d_op = &vboxsf_dentry_ops; + + iroot = iget_locked(sb, 0); + if (!iroot) { + err = -ENOMEM; + goto fail_unmap; + } + vboxsf_init_inode(sbi, iroot, &sbi->root_info); + unlock_new_inode(iroot); + + droot = d_make_root(iroot); + if (!droot) { + err = -ENOMEM; + goto fail_unmap; + } + + sb->s_root = droot; + sb->s_fs_info = sbi; + return 0; + +fail_unmap: + vboxsf_unmap_folder(sbi->root); +fail_free: + if (sbi->bdi_id >= 0) + ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); + if (sbi->nls) + unload_nls(sbi->nls); + idr_destroy(&sbi->ino_idr); + kfree(sbi); + return err; +} + +static void vboxsf_inode_init_once(void *data) +{ + struct vboxsf_inode *sf_i = data; + + mutex_init(&sf_i->handle_list_mutex); + inode_init_once(&sf_i->vfs_inode); +} + +static struct inode *vboxsf_alloc_inode(struct super_block *sb) +{ + struct vboxsf_inode *sf_i; + + sf_i = kmem_cache_alloc(vboxsf_inode_cachep, GFP_NOFS); + if (!sf_i) + return NULL; + + sf_i->force_restat = 0; + INIT_LIST_HEAD(&sf_i->handle_list); + + return &sf_i->vfs_inode; +} + +static void vboxsf_free_inode(struct inode *inode) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); + unsigned long flags; + + spin_lock_irqsave(&sbi->ino_idr_lock, flags); + idr_remove(&sbi->ino_idr, inode->i_ino); + spin_unlock_irqrestore(&sbi->ino_idr_lock, flags); + kmem_cache_free(vboxsf_inode_cachep, VBOXSF_I(inode)); +} + +static void vboxsf_put_super(struct super_block *sb) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(sb); + + vboxsf_unmap_folder(sbi->root); + if (sbi->bdi_id >= 0) + ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); + if (sbi->nls) + unload_nls(sbi->nls); + + /* + * vboxsf_free_inode uses the idr, make sure all delayed rcu free + * inodes are flushed. + */ + rcu_barrier(); + idr_destroy(&sbi->ino_idr); + kfree(sbi); +} + +static int vboxsf_statfs(struct dentry *dentry, struct kstatfs *stat) +{ + struct super_block *sb = dentry->d_sb; + struct shfl_volinfo shfl_volinfo; + struct vboxsf_sbi *sbi; + u32 buf_len; + int err; + + sbi = VBOXSF_SBI(sb); + buf_len = sizeof(shfl_volinfo); + err = vboxsf_fsinfo(sbi->root, 0, SHFL_INFO_GET | SHFL_INFO_VOLUME, + &buf_len, &shfl_volinfo); + if (err) + return err; + + stat->f_type = VBOXSF_SUPER_MAGIC; + stat->f_bsize = shfl_volinfo.bytes_per_allocation_unit; + + do_div(shfl_volinfo.total_allocation_bytes, + shfl_volinfo.bytes_per_allocation_unit); + stat->f_blocks = shfl_volinfo.total_allocation_bytes; + + do_div(shfl_volinfo.available_allocation_bytes, + shfl_volinfo.bytes_per_allocation_unit); + stat->f_bfree = shfl_volinfo.available_allocation_bytes; + stat->f_bavail = shfl_volinfo.available_allocation_bytes; + + stat->f_files = 1000; + /* + * Don't return 0 here since the guest may then think that it is not + * possible to create any more files. + */ + stat->f_ffree = 1000000; + stat->f_fsid.val[0] = 0; + stat->f_fsid.val[1] = 0; + stat->f_namelen = 255; + return 0; +} + +static struct super_operations vboxsf_super_ops = { + .alloc_inode = vboxsf_alloc_inode, + .free_inode = vboxsf_free_inode, + .put_super = vboxsf_put_super, + .statfs = vboxsf_statfs, +}; + +static int vboxsf_setup(void) +{ + int err; + + mutex_lock(&vboxsf_setup_mutex); + + if (vboxsf_setup_done) + goto success; + + vboxsf_inode_cachep = + kmem_cache_create("vboxsf_inode_cache", + sizeof(struct vboxsf_inode), 0, + (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | + SLAB_ACCOUNT), + vboxsf_inode_init_once); + if (!vboxsf_inode_cachep) { + err = -ENOMEM; + goto fail_nomem; + } + + err = vboxsf_connect(); + if (err) { + vbg_err("vboxsf: err %d connecting to guest PCI-device\n", err); + vbg_err("vboxsf: make sure you are inside a VirtualBox VM\n"); + vbg_err("vboxsf: and check dmesg for vboxguest errors\n"); + goto fail_free_cache; + } + + err = vboxsf_set_utf8(); + if (err) { + vbg_err("vboxsf_setutf8 error %d\n", err); + goto fail_disconnect; + } + + if (!follow_symlinks) { + err = vboxsf_set_symlinks(); + if (err) + vbg_warn("vboxsf: Unable to show symlinks: %d\n", err); + } + + vboxsf_setup_done = true; +success: + mutex_unlock(&vboxsf_setup_mutex); + return 0; + +fail_disconnect: + vboxsf_disconnect(); +fail_free_cache: + kmem_cache_destroy(vboxsf_inode_cachep); +fail_nomem: + mutex_unlock(&vboxsf_setup_mutex); + return err; +} + +static int vboxsf_parse_monolithic(struct fs_context *fc, void *data) +{ + char *options = data; + + if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 && + options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 && + options[2] == VBSF_MOUNT_SIGNATURE_BYTE_2 && + options[3] == VBSF_MOUNT_SIGNATURE_BYTE_3) { + vbg_err("vboxsf: Old binary mount data not supported, remove obsolete mount.vboxsf and/or update your VBoxService.\n"); + return -EINVAL; + } + + return generic_parse_monolithic(fc, data); +} + +static int vboxsf_get_tree(struct fs_context *fc) +{ + int err; + + err = vboxsf_setup(); + if (err) + return err; + + return get_tree_nodev(fc, vboxsf_fill_super); +} + +static int vboxsf_reconfigure(struct fs_context *fc) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(fc->root->d_sb); + struct vboxsf_fs_context *ctx = fc->fs_private; + struct inode *iroot = fc->root->d_sb->s_root->d_inode; + + /* Apply changed options to the root inode */ + sbi->o = ctx->o; + vboxsf_init_inode(sbi, iroot, &sbi->root_info); + + return 0; +} + +static void vboxsf_free_fc(struct fs_context *fc) +{ + struct vboxsf_fs_context *ctx = fc->fs_private; + + kfree(ctx->nls_name); + kfree(ctx); +} + +static const struct fs_context_operations vboxsf_context_ops = { + .free = vboxsf_free_fc, + .parse_param = vboxsf_parse_param, + .parse_monolithic = vboxsf_parse_monolithic, + .get_tree = vboxsf_get_tree, + .reconfigure = vboxsf_reconfigure, +}; + +static int vboxsf_init_fs_context(struct fs_context *fc) +{ + struct vboxsf_fs_context *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + current_uid_gid(&ctx->o.uid, &ctx->o.gid); + + fc->fs_private = ctx; + fc->ops = &vboxsf_context_ops; + return 0; +} + +static struct file_system_type vboxsf_fs_type = { + .owner = THIS_MODULE, + .name = "vboxsf", + .init_fs_context = vboxsf_init_fs_context, + .kill_sb = kill_anon_super +}; + +/* Module initialization/finalization handlers */ +static int __init vboxsf_init(void) +{ + return register_filesystem(&vboxsf_fs_type); +} + +static void __exit vboxsf_fini(void) +{ + unregister_filesystem(&vboxsf_fs_type); + + mutex_lock(&vboxsf_setup_mutex); + if (vboxsf_setup_done) { + vboxsf_disconnect(); + /* + * Make sure all delayed rcu free inodes are flushed + * before we destroy the cache. + */ + rcu_barrier(); + kmem_cache_destroy(vboxsf_inode_cachep); + } + mutex_unlock(&vboxsf_setup_mutex); +} + +module_init(vboxsf_init); +module_exit(vboxsf_fini); + +MODULE_DESCRIPTION("Oracle VM VirtualBox Module for Host File System Access"); +MODULE_AUTHOR("Oracle Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_FS("vboxsf"); diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c new file mode 100644 index 000000000000..96bd160da48b --- /dev/null +++ b/fs/vboxsf/utils.c @@ -0,0 +1,551 @@ +// SPDX-License-Identifier: MIT +/* + * VirtualBox Guest Shared Folders support: Utility functions. + * Mainly conversion from/to VirtualBox/Linux data structures. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include <linux/namei.h> +#include <linux/nls.h> +#include <linux/sizes.h> +#include <linux/vfs.h> +#include "vfsmod.h" + +struct inode *vboxsf_new_inode(struct super_block *sb) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(sb); + struct inode *inode; + unsigned long flags; + int cursor, ret; + u32 gen; + + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + idr_preload(GFP_KERNEL); + spin_lock_irqsave(&sbi->ino_idr_lock, flags); + cursor = idr_get_cursor(&sbi->ino_idr); + ret = idr_alloc_cyclic(&sbi->ino_idr, inode, 1, 0, GFP_ATOMIC); + if (ret >= 0 && ret < cursor) + sbi->next_generation++; + gen = sbi->next_generation; + spin_unlock_irqrestore(&sbi->ino_idr_lock, flags); + idr_preload_end(); + + if (ret < 0) { + iput(inode); + return ERR_PTR(ret); + } + + inode->i_ino = ret; + inode->i_generation = gen; + return inode; +} + +/* set [inode] attributes based on [info], uid/gid based on [sbi] */ +void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, + const struct shfl_fsobjinfo *info) +{ + const struct shfl_fsobjattr *attr; + s64 allocated; + int mode; + + attr = &info->attr; + +#define mode_set(r) ((attr->mode & (SHFL_UNIX_##r)) ? (S_##r) : 0) + + mode = mode_set(IRUSR); + mode |= mode_set(IWUSR); + mode |= mode_set(IXUSR); + + mode |= mode_set(IRGRP); + mode |= mode_set(IWGRP); + mode |= mode_set(IXGRP); + + mode |= mode_set(IROTH); + mode |= mode_set(IWOTH); + mode |= mode_set(IXOTH); + +#undef mode_set + + /* We use the host-side values for these */ + inode->i_flags |= S_NOATIME | S_NOCMTIME; + inode->i_mapping->a_ops = &vboxsf_reg_aops; + + if (SHFL_IS_DIRECTORY(attr->mode)) { + inode->i_mode = sbi->o.dmode_set ? sbi->o.dmode : mode; + inode->i_mode &= ~sbi->o.dmask; + inode->i_mode |= S_IFDIR; + inode->i_op = &vboxsf_dir_iops; + inode->i_fop = &vboxsf_dir_fops; + /* + * XXX: this probably should be set to the number of entries + * in the directory plus two (. ..) + */ + set_nlink(inode, 1); + } else if (SHFL_IS_SYMLINK(attr->mode)) { + inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode; + inode->i_mode &= ~sbi->o.fmask; + inode->i_mode |= S_IFLNK; + inode->i_op = &vboxsf_lnk_iops; + set_nlink(inode, 1); + } else { + inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode; + inode->i_mode &= ~sbi->o.fmask; + inode->i_mode |= S_IFREG; + inode->i_op = &vboxsf_reg_iops; + inode->i_fop = &vboxsf_reg_fops; + set_nlink(inode, 1); + } + + inode->i_uid = sbi->o.uid; + inode->i_gid = sbi->o.gid; + + inode->i_size = info->size; + inode->i_blkbits = 12; + /* i_blocks always in units of 512 bytes! */ + allocated = info->allocated + 511; + do_div(allocated, 512); + inode->i_blocks = allocated; + + inode->i_atime = ns_to_timespec64( + info->access_time.ns_relative_to_unix_epoch); + inode->i_ctime = ns_to_timespec64( + info->change_time.ns_relative_to_unix_epoch); + inode->i_mtime = ns_to_timespec64( + info->modification_time.ns_relative_to_unix_epoch); +} + +int vboxsf_create_at_dentry(struct dentry *dentry, + struct shfl_createparms *params) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); + struct shfl_string *path; + int err; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + err = vboxsf_create(sbi->root, path, params); + __putname(path); + + return err; +} + +int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path, + struct shfl_fsobjinfo *info) +{ + struct shfl_createparms params = {}; + int err; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_LOOKUP | SHFL_CF_ACT_FAIL_IF_NEW; + + err = vboxsf_create(sbi->root, path, ¶ms); + if (err) + return err; + + if (params.result != SHFL_FILE_EXISTS) + return -ENOENT; + + if (info) + *info = params.info; + + return 0; +} + +int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); + struct shfl_string *path; + int err; + + path = vboxsf_path_from_dentry(sbi, dentry); + if (IS_ERR(path)) + return PTR_ERR(path); + + err = vboxsf_stat(sbi, path, info); + __putname(path); + return err; +} + +int vboxsf_inode_revalidate(struct dentry *dentry) +{ + struct vboxsf_sbi *sbi; + struct vboxsf_inode *sf_i; + struct shfl_fsobjinfo info; + struct timespec64 prev_mtime; + struct inode *inode; + int err; + + if (!dentry || !d_really_is_positive(dentry)) + return -EINVAL; + + inode = d_inode(dentry); + prev_mtime = inode->i_mtime; + sf_i = VBOXSF_I(inode); + sbi = VBOXSF_SBI(dentry->d_sb); + if (!sf_i->force_restat) { + if (time_before(jiffies, dentry->d_time + sbi->o.ttl)) + return 0; + } + + err = vboxsf_stat_dentry(dentry, &info); + if (err) + return err; + + dentry->d_time = jiffies; + sf_i->force_restat = 0; + vboxsf_init_inode(sbi, inode, &info); + + /* + * If the file was changed on the host side we need to invalidate the + * page-cache for it. Note this also gets triggered by our own writes, + * this is unavoidable. + */ + if (timespec64_compare(&inode->i_mtime, &prev_mtime) > 0) + invalidate_inode_pages2(inode->i_mapping); + + return 0; +} + +int vboxsf_getattr(const struct path *path, struct kstat *kstat, + u32 request_mask, unsigned int flags) +{ + int err; + struct dentry *dentry = path->dentry; + struct inode *inode = d_inode(dentry); + struct vboxsf_inode *sf_i = VBOXSF_I(inode); + + switch (flags & AT_STATX_SYNC_TYPE) { + case AT_STATX_DONT_SYNC: + err = 0; + break; + case AT_STATX_FORCE_SYNC: + sf_i->force_restat = 1; + /* fall-through */ + default: + err = vboxsf_inode_revalidate(dentry); + } + if (err) + return err; + + generic_fillattr(d_inode(dentry), kstat); + return 0; +} + +int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry)); + struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb); + struct shfl_createparms params = {}; + struct shfl_fsobjinfo info = {}; + u32 buf_len; + int err; + + params.handle = SHFL_HANDLE_NIL; + params.create_flags = SHFL_CF_ACT_OPEN_IF_EXISTS | + SHFL_CF_ACT_FAIL_IF_NEW | + SHFL_CF_ACCESS_ATTR_WRITE; + + /* this is at least required for Posix hosts */ + if (iattr->ia_valid & ATTR_SIZE) + params.create_flags |= SHFL_CF_ACCESS_WRITE; + + err = vboxsf_create_at_dentry(dentry, ¶ms); + if (err || params.result != SHFL_FILE_EXISTS) + return err ? err : -ENOENT; + +#define mode_set(r) ((iattr->ia_mode & (S_##r)) ? SHFL_UNIX_##r : 0) + + /* + * Setting the file size and setting the other attributes has to + * be handled separately. + */ + if (iattr->ia_valid & (ATTR_MODE | ATTR_ATIME | ATTR_MTIME)) { + if (iattr->ia_valid & ATTR_MODE) { + info.attr.mode = mode_set(IRUSR); + info.attr.mode |= mode_set(IWUSR); + info.attr.mode |= mode_set(IXUSR); + info.attr.mode |= mode_set(IRGRP); + info.attr.mode |= mode_set(IWGRP); + info.attr.mode |= mode_set(IXGRP); + info.attr.mode |= mode_set(IROTH); + info.attr.mode |= mode_set(IWOTH); + info.attr.mode |= mode_set(IXOTH); + + if (iattr->ia_mode & S_IFDIR) + info.attr.mode |= SHFL_TYPE_DIRECTORY; + else + info.attr.mode |= SHFL_TYPE_FILE; + } + + if (iattr->ia_valid & ATTR_ATIME) + info.access_time.ns_relative_to_unix_epoch = + timespec64_to_ns(&iattr->ia_atime); + + if (iattr->ia_valid & ATTR_MTIME) + info.modification_time.ns_relative_to_unix_epoch = + timespec64_to_ns(&iattr->ia_mtime); + + /* + * Ignore ctime (inode change time) as it can't be set + * from userland anyway. + */ + + buf_len = sizeof(info); + err = vboxsf_fsinfo(sbi->root, params.handle, + SHFL_INFO_SET | SHFL_INFO_FILE, &buf_len, + &info); + if (err) { + vboxsf_close(sbi->root, params.handle); + return err; + } + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + } + +#undef mode_set + + if (iattr->ia_valid & ATTR_SIZE) { + memset(&info, 0, sizeof(info)); + info.size = iattr->ia_size; + buf_len = sizeof(info); + err = vboxsf_fsinfo(sbi->root, params.handle, + SHFL_INFO_SET | SHFL_INFO_SIZE, &buf_len, + &info); + if (err) { + vboxsf_close(sbi->root, params.handle); + return err; + } + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + } + + vboxsf_close(sbi->root, params.handle); + + /* Update the inode with what the host has actually given us. */ + if (sf_i->force_restat) + vboxsf_inode_revalidate(dentry); + + return 0; +} + +/* + * [dentry] contains string encoded in coding system that corresponds + * to [sbi]->nls, we must convert it to UTF8 here. + * Returns a shfl_string allocated through __getname (must be freed using + * __putname), or an ERR_PTR on error. + */ +struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi, + struct dentry *dentry) +{ + struct shfl_string *shfl_path; + int path_len, out_len, nb; + char *buf, *path; + wchar_t uni; + u8 *out; + + buf = __getname(); + if (!buf) + return ERR_PTR(-ENOMEM); + + path = dentry_path_raw(dentry, buf, PATH_MAX); + if (IS_ERR(path)) { + __putname(buf); + return ERR_CAST(path); + } + path_len = strlen(path); + + if (sbi->nls) { + shfl_path = __getname(); + if (!shfl_path) { + __putname(buf); + return ERR_PTR(-ENOMEM); + } + + out = shfl_path->string.utf8; + out_len = PATH_MAX - SHFLSTRING_HEADER_SIZE - 1; + + while (path_len) { + nb = sbi->nls->char2uni(path, path_len, &uni); + if (nb < 0) { + __putname(shfl_path); + __putname(buf); + return ERR_PTR(-EINVAL); + } + path += nb; + path_len -= nb; + + nb = utf32_to_utf8(uni, out, out_len); + if (nb < 0) { + __putname(shfl_path); + __putname(buf); + return ERR_PTR(-ENAMETOOLONG); + } + out += nb; + out_len -= nb; + } + *out = 0; + shfl_path->length = out - shfl_path->string.utf8; + shfl_path->size = shfl_path->length + 1; + __putname(buf); + } else { + if ((SHFLSTRING_HEADER_SIZE + path_len + 1) > PATH_MAX) { + __putname(buf); + return ERR_PTR(-ENAMETOOLONG); + } + /* + * dentry_path stores the name at the end of buf, but the + * shfl_string string we return must be properly aligned. + */ + shfl_path = (struct shfl_string *)buf; + memmove(shfl_path->string.utf8, path, path_len); + shfl_path->string.utf8[path_len] = 0; + shfl_path->length = path_len; + shfl_path->size = path_len + 1; + } + + return shfl_path; +} + +int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, + const unsigned char *utf8_name, size_t utf8_len) +{ + const char *in; + char *out; + size_t out_len; + size_t out_bound_len; + size_t in_bound_len; + + in = utf8_name; + in_bound_len = utf8_len; + + out = name; + out_len = 0; + /* Reserve space for terminating 0 */ + out_bound_len = name_bound_len - 1; + + while (in_bound_len) { + int nb; + unicode_t uni; + + nb = utf8_to_utf32(in, in_bound_len, &uni); + if (nb < 0) + return -EINVAL; + + in += nb; + in_bound_len -= nb; + + nb = sbi->nls->uni2char(uni, out, out_bound_len); + if (nb < 0) + return nb; + + out += nb; + out_bound_len -= nb; + out_len += nb; + } + + *out = 0; + + return 0; +} + +static struct vboxsf_dir_buf *vboxsf_dir_buf_alloc(struct list_head *list) +{ + struct vboxsf_dir_buf *b; + + b = kmalloc(sizeof(*b), GFP_KERNEL); + if (!b) + return NULL; + + b->buf = kmalloc(DIR_BUFFER_SIZE, GFP_KERNEL); + if (!b->buf) { + kfree(b); + return NULL; + } + + b->entries = 0; + b->used = 0; + b->free = DIR_BUFFER_SIZE; + list_add(&b->head, list); + + return b; +} + +static void vboxsf_dir_buf_free(struct vboxsf_dir_buf *b) +{ + list_del(&b->head); + kfree(b->buf); + kfree(b); +} + +struct vboxsf_dir_info *vboxsf_dir_info_alloc(void) +{ + struct vboxsf_dir_info *p; + + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return NULL; + + INIT_LIST_HEAD(&p->info_list); + return p; +} + +void vboxsf_dir_info_free(struct vboxsf_dir_info *p) +{ + struct list_head *list, *pos, *tmp; + + list = &p->info_list; + list_for_each_safe(pos, tmp, list) { + struct vboxsf_dir_buf *b; + + b = list_entry(pos, struct vboxsf_dir_buf, head); + vboxsf_dir_buf_free(b); + } + kfree(p); +} + +int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d, + u64 handle) +{ + struct vboxsf_dir_buf *b; + u32 entries, size; + int err = 0; + void *buf; + + /* vboxsf_dirinfo returns 1 on end of dir */ + while (err == 0) { + b = vboxsf_dir_buf_alloc(&sf_d->info_list); + if (!b) { + err = -ENOMEM; + break; + } + + buf = b->buf; + size = b->free; + + err = vboxsf_dirinfo(sbi->root, handle, NULL, 0, 0, + &size, buf, &entries); + if (err < 0) + break; + + b->entries += entries; + b->free -= size; + b->used += size; + } + + if (b && b->used == 0) + vboxsf_dir_buf_free(b); + + /* -EILSEQ means the host could not translate a filename, ignore */ + if (err > 0 || err == -EILSEQ) + err = 0; + + return err; +} diff --git a/fs/vboxsf/vboxsf_wrappers.c b/fs/vboxsf/vboxsf_wrappers.c new file mode 100644 index 000000000000..bfc78a097dae --- /dev/null +++ b/fs/vboxsf/vboxsf_wrappers.c @@ -0,0 +1,371 @@ +// SPDX-License-Identifier: MIT +/* + * Wrapper functions for the shfl host calls. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/vbox_err.h> +#include <linux/vbox_utils.h> +#include "vfsmod.h" + +#define SHFL_REQUEST \ + (VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV_OTHER | \ + VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN) + +static u32 vboxsf_client_id; + +int vboxsf_connect(void) +{ + struct vbg_dev *gdev; + struct vmmdev_hgcm_service_location loc; + int err, vbox_status; + + loc.type = VMMDEV_HGCM_LOC_LOCALHOST_EXISTING; + strcpy(loc.u.localhost.service_name, "VBoxSharedFolders"); + + gdev = vbg_get_gdev(); + if (IS_ERR(gdev)) + return -ENODEV; /* No guest-device */ + + err = vbg_hgcm_connect(gdev, SHFL_REQUEST, &loc, + &vboxsf_client_id, &vbox_status); + vbg_put_gdev(gdev); + + return err ? err : vbg_status_code_to_errno(vbox_status); +} + +void vboxsf_disconnect(void) +{ + struct vbg_dev *gdev; + int vbox_status; + + gdev = vbg_get_gdev(); + if (IS_ERR(gdev)) + return; /* guest-device is gone, already disconnected */ + + vbg_hgcm_disconnect(gdev, SHFL_REQUEST, vboxsf_client_id, &vbox_status); + vbg_put_gdev(gdev); +} + +static int vboxsf_call(u32 function, void *parms, u32 parm_count, int *status) +{ + struct vbg_dev *gdev; + int err, vbox_status; + + gdev = vbg_get_gdev(); + if (IS_ERR(gdev)) + return -ESHUTDOWN; /* guest-dev removed underneath us */ + + err = vbg_hgcm_call(gdev, SHFL_REQUEST, vboxsf_client_id, function, + U32_MAX, parms, parm_count, &vbox_status); + vbg_put_gdev(gdev); + + if (err < 0) + return err; + + if (status) + *status = vbox_status; + + return vbg_status_code_to_errno(vbox_status); +} + +int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root) +{ + struct shfl_map_folder parms; + int err, status; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.path.u.pointer.size = shfl_string_buf_size(folder_name); + parms.path.u.pointer.u.linear_addr = (uintptr_t)folder_name; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = 0; + + parms.delimiter.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.delimiter.u.value32 = '/'; + + parms.case_sensitive.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.case_sensitive.u.value32 = 1; + + err = vboxsf_call(SHFL_FN_MAP_FOLDER, &parms, SHFL_CPARMS_MAP_FOLDER, + &status); + if (err == -ENOSYS && status == VERR_NOT_IMPLEMENTED) + vbg_err("%s: Error host is too old\n", __func__); + + *root = parms.root.u.value32; + return err; +} + +int vboxsf_unmap_folder(u32 root) +{ + struct shfl_unmap_folder parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + return vboxsf_call(SHFL_FN_UNMAP_FOLDER, &parms, + SHFL_CPARMS_UNMAP_FOLDER, NULL); +} + +/** + * vboxsf_create - Create a new file or folder + * @root: Root of the shared folder in which to create the file + * @parsed_path: The path of the file or folder relative to the shared folder + * @param: create_parms Parameters for file/folder creation. + * + * Create a new file or folder or open an existing one in a shared folder. + * Note this function always returns 0 / success unless an exceptional condition + * occurs - out of memory, invalid arguments, etc. If the file or folder could + * not be opened or created, create_parms->handle will be set to + * SHFL_HANDLE_NIL on return. In this case the value in create_parms->result + * provides information as to why (e.g. SHFL_FILE_EXISTS), create_parms->result + * is also set on success as additional information. + * + * Returns: + * 0 or negative errno value. + */ +int vboxsf_create(u32 root, struct shfl_string *parsed_path, + struct shfl_createparms *create_parms) +{ + struct shfl_create parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + + parms.parms.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.parms.u.pointer.size = sizeof(struct shfl_createparms); + parms.parms.u.pointer.u.linear_addr = (uintptr_t)create_parms; + + return vboxsf_call(SHFL_FN_CREATE, &parms, SHFL_CPARMS_CREATE, NULL); +} + +int vboxsf_close(u32 root, u64 handle) +{ + struct shfl_close parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + + return vboxsf_call(SHFL_FN_CLOSE, &parms, SHFL_CPARMS_CLOSE, NULL); +} + +int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags) +{ + struct shfl_remove parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + + return vboxsf_call(SHFL_FN_REMOVE, &parms, SHFL_CPARMS_REMOVE, NULL); +} + +int vboxsf_rename(u32 root, struct shfl_string *src_path, + struct shfl_string *dest_path, u32 flags) +{ + struct shfl_rename parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.src.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.src.u.pointer.size = shfl_string_buf_size(src_path); + parms.src.u.pointer.u.linear_addr = (uintptr_t)src_path; + + parms.dest.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.dest.u.pointer.size = shfl_string_buf_size(dest_path); + parms.dest.u.pointer.u.linear_addr = (uintptr_t)dest_path; + + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + + return vboxsf_call(SHFL_FN_RENAME, &parms, SHFL_CPARMS_RENAME, NULL); +} + +int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf) +{ + struct shfl_read parms; + int err; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.offset.u.value64 = offset; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.buffer.u.pointer.size = *buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + err = vboxsf_call(SHFL_FN_READ, &parms, SHFL_CPARMS_READ, NULL); + + *buf_len = parms.cb.u.value32; + return err; +} + +int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf) +{ + struct shfl_write parms; + int err; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.offset.u.value64 = offset; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.buffer.u.pointer.size = *buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + err = vboxsf_call(SHFL_FN_WRITE, &parms, SHFL_CPARMS_WRITE, NULL); + + *buf_len = parms.cb.u.value32; + return err; +} + +/* Returns 0 on success, 1 on end-of-dir, negative errno otherwise */ +int vboxsf_dirinfo(u32 root, u64 handle, + struct shfl_string *parsed_path, u32 flags, u32 index, + u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count) +{ + struct shfl_list parms; + int err, status; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + if (parsed_path) { + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + } else { + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_IN; + parms.path.u.pointer.size = 0; + parms.path.u.pointer.u.linear_addr = 0; + } + + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.buffer.u.pointer.size = *buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + parms.resume_point.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.resume_point.u.value32 = index; + parms.file_count.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.file_count.u.value32 = 0; /* out parameter only */ + + err = vboxsf_call(SHFL_FN_LIST, &parms, SHFL_CPARMS_LIST, &status); + if (err == -ENODATA && status == VERR_NO_MORE_FILES) + err = 1; + + *buf_len = parms.cb.u.value32; + *file_count = parms.file_count.u.value32; + return err; +} + +int vboxsf_fsinfo(u32 root, u64 handle, u32 flags, + u32 *buf_len, void *buf) +{ + struct shfl_information parms; + int err; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT; + parms.handle.u.value64 = handle; + parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.flags.u.value32 = flags; + parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.cb.u.value32 = *buf_len; + parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL; + parms.info.u.pointer.size = *buf_len; + parms.info.u.pointer.u.linear_addr = (uintptr_t)buf; + + err = vboxsf_call(SHFL_FN_INFORMATION, &parms, SHFL_CPARMS_INFORMATION, + NULL); + + *buf_len = parms.cb.u.value32; + return err; +} + +int vboxsf_readlink(u32 root, struct shfl_string *parsed_path, + u32 buf_len, u8 *buf) +{ + struct shfl_readLink parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.path.u.pointer.size = shfl_string_buf_size(parsed_path); + parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path; + + parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.buffer.u.pointer.size = buf_len; + parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf; + + return vboxsf_call(SHFL_FN_READLINK, &parms, SHFL_CPARMS_READLINK, + NULL); +} + +int vboxsf_symlink(u32 root, struct shfl_string *new_path, + struct shfl_string *old_path, struct shfl_fsobjinfo *buf) +{ + struct shfl_symlink parms; + + parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT; + parms.root.u.value32 = root; + + parms.new_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.new_path.u.pointer.size = shfl_string_buf_size(new_path); + parms.new_path.u.pointer.u.linear_addr = (uintptr_t)new_path; + + parms.old_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN; + parms.old_path.u.pointer.size = shfl_string_buf_size(old_path); + parms.old_path.u.pointer.u.linear_addr = (uintptr_t)old_path; + + parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT; + parms.info.u.pointer.size = sizeof(struct shfl_fsobjinfo); + parms.info.u.pointer.u.linear_addr = (uintptr_t)buf; + + return vboxsf_call(SHFL_FN_SYMLINK, &parms, SHFL_CPARMS_SYMLINK, NULL); +} + +int vboxsf_set_utf8(void) +{ + return vboxsf_call(SHFL_FN_SET_UTF8, NULL, 0, NULL); +} + +int vboxsf_set_symlinks(void) +{ + return vboxsf_call(SHFL_FN_SET_SYMLINKS, NULL, 0, NULL); +} diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h new file mode 100644 index 000000000000..18f95b00fc33 --- /dev/null +++ b/fs/vboxsf/vfsmod.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: MIT */ +/* + * VirtualBox Guest Shared Folders support: module header. + * + * Copyright (C) 2006-2018 Oracle Corporation + */ + +#ifndef VFSMOD_H +#define VFSMOD_H + +#include <linux/backing-dev.h> +#include <linux/idr.h> +#include "shfl_hostintf.h" + +#define DIR_BUFFER_SIZE SZ_16K + +/* The cast is to prevent assignment of void * to pointers of arbitrary type */ +#define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info) +#define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode) + +struct vboxsf_options { + unsigned long ttl; + kuid_t uid; + kgid_t gid; + bool dmode_set; + bool fmode_set; + umode_t dmode; + umode_t fmode; + umode_t dmask; + umode_t fmask; +}; + +struct vboxsf_fs_context { + struct vboxsf_options o; + char *nls_name; +}; + +/* per-shared folder information */ +struct vboxsf_sbi { + struct vboxsf_options o; + struct shfl_fsobjinfo root_info; + struct idr ino_idr; + spinlock_t ino_idr_lock; /* This protects ino_idr */ + struct nls_table *nls; + u32 next_generation; + u32 root; + int bdi_id; +}; + +/* per-inode information */ +struct vboxsf_inode { + /* some information was changed, update data on next revalidate */ + int force_restat; + /* list of open handles for this inode + lock protecting it */ + struct list_head handle_list; + /* This mutex protects handle_list accesses */ + struct mutex handle_list_mutex; + /* The VFS inode struct */ + struct inode vfs_inode; +}; + +struct vboxsf_dir_info { + struct list_head info_list; +}; + +struct vboxsf_dir_buf { + size_t entries; + size_t free; + size_t used; + void *buf; + struct list_head head; +}; + +/* globals */ +extern const struct inode_operations vboxsf_dir_iops; +extern const struct inode_operations vboxsf_lnk_iops; +extern const struct inode_operations vboxsf_reg_iops; +extern const struct file_operations vboxsf_dir_fops; +extern const struct file_operations vboxsf_reg_fops; +extern const struct address_space_operations vboxsf_reg_aops; +extern const struct dentry_operations vboxsf_dentry_ops; + +/* from utils.c */ +struct inode *vboxsf_new_inode(struct super_block *sb); +void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, + const struct shfl_fsobjinfo *info); +int vboxsf_create_at_dentry(struct dentry *dentry, + struct shfl_createparms *params); +int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path, + struct shfl_fsobjinfo *info); +int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info); +int vboxsf_inode_revalidate(struct dentry *dentry); +int vboxsf_getattr(const struct path *path, struct kstat *kstat, + u32 request_mask, unsigned int query_flags); +int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr); +struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi, + struct dentry *dentry); +int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, + const unsigned char *utf8_name, size_t utf8_len); +struct vboxsf_dir_info *vboxsf_dir_info_alloc(void); +void vboxsf_dir_info_free(struct vboxsf_dir_info *p); +int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d, + u64 handle); + +/* from vboxsf_wrappers.c */ +int vboxsf_connect(void); +void vboxsf_disconnect(void); + +int vboxsf_create(u32 root, struct shfl_string *parsed_path, + struct shfl_createparms *create_parms); + +int vboxsf_close(u32 root, u64 handle); +int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags); +int vboxsf_rename(u32 root, struct shfl_string *src_path, + struct shfl_string *dest_path, u32 flags); + +int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf); +int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf); + +int vboxsf_dirinfo(u32 root, u64 handle, + struct shfl_string *parsed_path, u32 flags, u32 index, + u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count); +int vboxsf_fsinfo(u32 root, u64 handle, u32 flags, + u32 *buf_len, void *buf); + +int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root); +int vboxsf_unmap_folder(u32 root); + +int vboxsf_readlink(u32 root, struct shfl_string *parsed_path, + u32 buf_len, u8 *buf); +int vboxsf_symlink(u32 root, struct shfl_string *new_path, + struct shfl_string *old_path, struct shfl_fsobjinfo *buf); + +int vboxsf_set_utf8(void); +int vboxsf_set_symlinks(void); + +#endif diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 14fbdf22b7e7..08d6beb54f8c 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -23,25 +23,28 @@ #include "xfs_ag_resv.h" #include "xfs_health.h" -static struct xfs_buf * +static int xfs_get_aghdr_buf( struct xfs_mount *mp, xfs_daddr_t blkno, size_t numblks, + struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { struct xfs_buf *bp; + int error; - bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0); - if (!bp) - return NULL; + error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0, &bp); + if (error) + return error; xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); bp->b_bn = blkno; bp->b_maps[0].bm_bn = blkno; bp->b_ops = ops; - return bp; + *bpp = bp; + return 0; } static inline bool is_log_ag(struct xfs_mount *mp, struct aghdr_init_data *id) @@ -340,13 +343,13 @@ xfs_ag_init_hdr( struct aghdr_init_data *id, aghdr_init_work_f work, const struct xfs_buf_ops *ops) - { struct xfs_buf *bp; + int error; - bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, ops); - if (!bp) - return -ENOMEM; + error = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, &bp, ops); + if (error) + return error; (*work)(mp, bp, id); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index fc93fd88ec89..d8053bc96c4d 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1070,11 +1070,11 @@ xfs_alloc_ag_vextent_small( if (args->datatype & XFS_ALLOC_USERDATA) { struct xfs_buf *bp; - bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno); - if (XFS_IS_CORRUPT(args->mp, !bp)) { - error = -EFSCORRUPTED; + error = xfs_trans_get_buf(args->tp, args->mp->m_ddev_targp, + XFS_AGB_TO_DADDR(args->mp, args->agno, fbno), + args->mp->m_bsize, 0, &bp); + if (error) goto error; - } xfs_trans_binval(args->tp, bp); } *fbnop = args->agbno = fbno; @@ -2347,9 +2347,11 @@ xfs_free_agfl_block( if (error) return error; - bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno); - if (XFS_IS_CORRUPT(tp->t_mountp, !bp)) - return -EFSCORRUPTED; + error = xfs_trans_get_buf(tp, tp->t_mountp->m_ddev_targp, + XFS_AGB_TO_DADDR(tp->t_mountp, agno, agbno), + tp->t_mountp->m_bsize, 0, &bp); + if (error) + return error; xfs_trans_binval(tp, bp); return 0; @@ -2500,12 +2502,11 @@ xfs_alloc_fix_freelist( if (!pag->pagf_init) { error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); - if (error) + if (error) { + /* Couldn't lock the AGF so skip this AG. */ + if (error == -EAGAIN) + error = 0; goto out_no_agbp; - if (!pag->pagf_init) { - ASSERT(flags & XFS_ALLOC_FLAG_TRYLOCK); - ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); - goto out_agbp_relse; } } @@ -2531,11 +2532,10 @@ xfs_alloc_fix_freelist( */ if (!agbp) { error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); - if (error) - goto out_no_agbp; - if (!agbp) { - ASSERT(flags & XFS_ALLOC_FLAG_TRYLOCK); - ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); + if (error) { + /* Couldn't lock the AGF so skip this AG. */ + if (error == -EAGAIN) + error = 0; goto out_no_agbp; } } @@ -2766,11 +2766,10 @@ xfs_alloc_pagf_init( xfs_buf_t *bp; int error; - if ((error = xfs_alloc_read_agf(mp, tp, agno, flags, &bp))) - return error; - if (bp) + error = xfs_alloc_read_agf(mp, tp, agno, flags, &bp); + if (!error) xfs_trans_brelse(tp, bp); - return 0; + return error; } /* @@ -2956,14 +2955,11 @@ xfs_read_agf( trace_xfs_read_agf(mp, agno); ASSERT(agno != NULLAGNUMBER); - error = xfs_trans_read_buf( - mp, tp, mp->m_ddev_targp, + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), flags, bpp, &xfs_agf_buf_ops); if (error) return error; - if (!*bpp) - return 0; ASSERT(!(*bpp)->b_error); xfs_buf_set_ref(*bpp, XFS_AGF_REF); @@ -2987,14 +2983,15 @@ xfs_alloc_read_agf( trace_xfs_alloc_read_agf(mp, agno); + /* We don't support trylock when freeing. */ + ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) != + (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)); ASSERT(agno != NULLAGNUMBER); error = xfs_read_agf(mp, tp, agno, (flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0, bpp); if (error) return error; - if (!*bpp) - return 0; ASSERT(!(*bpp)->b_error); agf = XFS_BUF_TO_AGF(*bpp); diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index a266d05df146..8b7f74b3bea2 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -418,20 +418,10 @@ xfs_attr_rmtval_get( (map[i].br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock); dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); - bp = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, 0, - &xfs_attr3_rmt_buf_ops); - if (!bp) - return -ENOMEM; - error = bp->b_error; - if (error) { - xfs_buf_ioerror_alert(bp, __func__); - xfs_buf_relse(bp); - - /* bad CRC means corrupted metadata */ - if (error == -EFSBADCRC) - error = -EFSCORRUPTED; + error = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, + 0, &bp, &xfs_attr3_rmt_buf_ops); + if (error) return error; - } error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino, &offset, &valuelen, @@ -555,9 +545,9 @@ xfs_attr_rmtval_set( dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock), dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); - bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt); - if (!bp) - return -ENOMEM; + error = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, &bp); + if (error) + return error; bp->b_ops = &xfs_attr3_rmt_buf_ops; xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset, diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 4c2e046fbfad..9a6d7a84689a 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -730,11 +730,11 @@ xfs_bmap_extents_to_btree( cur->bc_private.b.allocated++; ip->i_d.di_nblocks++; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); - abp = xfs_btree_get_bufl(mp, tp, args.fsbno); - if (XFS_IS_CORRUPT(mp, !abp)) { - error = -EFSCORRUPTED; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, args.fsbno), + mp->m_bsize, 0, &abp); + if (error) goto out_unreserve_dquot; - } /* * Fill in the child block. @@ -878,7 +878,11 @@ xfs_bmap_local_to_extents( ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(args.len == 1); tp->t_firstblock = args.fsbno; - bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno); + error = xfs_trans_get_buf(tp, args.mp->m_ddev_targp, + XFS_FSB_TO_DADDR(args.mp, args.fsbno), + args.mp->m_bsize, 0, &bp); + if (error) + goto done; /* * Initialize the block, copy the data and log the remote buffer. @@ -3307,11 +3311,12 @@ xfs_bmap_longest_free_extent( pag = xfs_perag_get(mp, ag); if (!pag->pagf_init) { error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK); - if (error) - goto out; - - if (!pag->pagf_init) { - *notinit = 1; + if (error) { + /* Couldn't lock the AGF, so skip this AG. */ + if (error == -EAGAIN) { + *notinit = 1; + error = 0; + } goto out; } } diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index b22c7e928eb1..fd300dc93ca4 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -679,42 +679,6 @@ xfs_btree_get_block( } /* - * Get a buffer for the block, return it with no data read. - * Long-form addressing. - */ -xfs_buf_t * /* buffer for fsbno */ -xfs_btree_get_bufl( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_fsblock_t fsbno) /* file system block number */ -{ - xfs_daddr_t d; /* real disk block address */ - - ASSERT(fsbno != NULLFSBLOCK); - d = XFS_FSB_TO_DADDR(mp, fsbno); - return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, 0); -} - -/* - * Get a buffer for the block, return it with no data read. - * Short-form addressing. - */ -xfs_buf_t * /* buffer for agno/agbno */ -xfs_btree_get_bufs( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - xfs_agblock_t agbno) /* allocation group block number */ -{ - xfs_daddr_t d; /* real disk block address */ - - ASSERT(agno != NULLAGNUMBER); - ASSERT(agbno != NULLAGBLOCK); - d = XFS_AGB_TO_DADDR(mp, agno, agbno); - return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, 0); -} - -/* * Change the cursor to point to the first record at the given level. * Other levels are unaffected. */ @@ -1270,11 +1234,10 @@ xfs_btree_get_buf_block( error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; - *bpp = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, - mp->m_bsize, 0); - - if (!*bpp) - return -ENOMEM; + error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize, + 0, bpp); + if (error) + return error; (*bpp)->b_ops = cur->bc_ops->buf_ops; *block = XFS_BUF_TO_BLOCK(*bpp); diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index fb9b2121c628..3eff7c321d43 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -297,27 +297,6 @@ xfs_btree_dup_cursor( xfs_btree_cur_t **ncur);/* output cursor */ /* - * Get a buffer for the block, return it with no data read. - * Long-form addressing. - */ -struct xfs_buf * /* buffer for fsbno */ -xfs_btree_get_bufl( - struct xfs_mount *mp, /* file system mount point */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_fsblock_t fsbno); /* file system block number */ - -/* - * Get a buffer for the block, return it with no data read. - * Short-form addressing. - */ -struct xfs_buf * /* buffer for agno/agbno */ -xfs_btree_get_bufs( - struct xfs_mount *mp, /* file system mount point */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - xfs_agblock_t agbno); /* allocation group block number */ - -/* * Compute first and last byte offsets for the fields given. * Interprets the offsets table, which contains struct field offsets. */ diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 8c3eafe280ed..875e04f82541 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2591,13 +2591,9 @@ xfs_da_get_buf( if (error || nmap == 0) goto out_free; - bp = xfs_trans_get_buf_map(tp, mp->m_ddev_targp, mapp, nmap, 0); - error = bp ? bp->b_error : -EIO; - if (error) { - if (bp) - xfs_trans_brelse(tp, bp); + error = xfs_trans_get_buf_map(tp, mp->m_ddev_targp, mapp, nmap, 0, &bp); + if (error) goto out_free; - } *bpp = bp; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 5b759af4d165..bf161e930f1d 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -276,6 +276,7 @@ xfs_ialloc_inode_init( int i, j; xfs_daddr_t d; xfs_ino_t ino = 0; + int error; /* * Loop over the new block(s), filling in the inodes. For small block @@ -327,12 +328,11 @@ xfs_ialloc_inode_init( */ d = XFS_AGB_TO_DADDR(mp, agno, agbno + (j * M_IGEO(mp)->blocks_per_cluster)); - fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, - mp->m_bsize * - M_IGEO(mp)->blocks_per_cluster, - XBF_UNMAPPED); - if (!fbuf) - return -ENOMEM; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, + mp->m_bsize * M_IGEO(mp)->blocks_per_cluster, + XBF_UNMAPPED, &fbuf); + if (error) + return error; /* Initialize the inode buffers and log them appropriately. */ fbuf->b_ops = &xfs_inode_buf_ops; diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index d7d702ee4d1a..6e1665f2cb67 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1177,8 +1177,6 @@ xfs_refcount_finish_one( XFS_ALLOC_FLAG_FREEING, &agbp); if (error) return error; - if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) - return -EFSCORRUPTED; rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno); if (!rcur) { @@ -1718,10 +1716,6 @@ xfs_refcount_recover_cow_leftovers( error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (error) goto out_trans; - if (!agbp) { - error = -ENOMEM; - goto out_trans; - } cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno); /* Find all the leftover CoW staging extents. */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 0ac69751fe85..2f60fc3c99a0 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -985,9 +985,9 @@ xfs_update_secondary_sbs( for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) { struct xfs_buf *bp; - bp = xfs_buf_get(mp->m_ddev_targp, + error = xfs_buf_get(mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_DADDR), - XFS_FSS_TO_BB(mp, 1)); + XFS_FSS_TO_BB(mp, 1), &bp); /* * If we get an error reading or writing alternate superblocks, * continue. xfs_repair chooses the "best" superblock based @@ -995,12 +995,12 @@ xfs_update_secondary_sbs( * superblocks un-updated than updated, and xfs_repair may * pick them over the properly-updated primary. */ - if (!bp) { + if (error) { xfs_warn(mp, "error allocating secondary superblock for ag %d", agno); if (!saved_error) - saved_error = -ENOMEM; + saved_error = error; continue; } @@ -1185,13 +1185,14 @@ xfs_sb_get_secondary( struct xfs_buf **bpp) { struct xfs_buf *bp; + int error; ASSERT(agno != 0 && agno != NULLAGNUMBER); - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)), - XFS_FSS_TO_BB(mp, 1), 0); - if (!bp) - return -ENOMEM; + XFS_FSS_TO_BB(mp, 1), 0, &bp); + if (error) + return error; bp->b_ops = &xfs_sb_buf_ops; xfs_buf_oneshot(bp); *bpp = bp; diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 7a1a38b636a9..d5e6db9af434 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -659,8 +659,6 @@ xrep_agfl( error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp); if (error) return error; - if (!agf_bp) - return -ENOMEM; /* * Make sure we have the AGFL buffer, as scrub might have decided it @@ -735,8 +733,6 @@ xrep_agi_find_btrees( error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp); if (error) return error; - if (!agf_bp) - return -ENOMEM; /* Find the btree roots. */ error = xrep_find_ag_btree_roots(sc, agf_bp, fab, NULL); diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 7251c66a82c9..ec2064ed3c30 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -83,9 +83,6 @@ xchk_fscount_warmup( error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &agf_bp); if (error) break; - error = -ENOMEM; - if (!agf_bp || !agi_bp) - break; /* * These are supposed to be initialized by the header read diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index b70a88bc975e..e489d7a8446a 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -341,13 +341,17 @@ xrep_init_btblock( struct xfs_trans *tp = sc->tp; struct xfs_mount *mp = sc->mp; struct xfs_buf *bp; + int error; trace_xrep_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb), XFS_FSB_TO_AGBNO(mp, fsb), btnum); ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno); - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, fsb), - XFS_FSB_TO_BB(mp, 1), 0); + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, fsb), XFS_FSB_TO_BB(mp, 1), 0, + &bp); + if (error) + return error; xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.agno); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF); @@ -542,8 +546,6 @@ xrep_reap_block( error = xfs_alloc_read_agf(sc->mp, sc->tp, agno, 0, &agf_bp); if (error) return error; - if (!agf_bp) - return -ENOMEM; } else { agf_bp = sc->sa.agf_bp; } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 8fbb841cd6fe..bbfa6ba84dcd 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -205,11 +205,12 @@ xfs_attr3_node_inactive( /* * Remove the subsidiary block from the cache and from the log. */ - child_bp = xfs_trans_get_buf(*trans, mp->m_ddev_targp, + error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, child_blkno, - XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0); - if (!child_bp) - return -EIO; + XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, + &child_bp); + if (error) + return error; error = bp->b_error; if (error) { xfs_trans_brelse(*trans, child_bp); @@ -298,10 +299,10 @@ xfs_attr3_root_inactive( /* * Invalidate the incore copy of the root block. */ - bp = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno, - XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0); - if (!bp) - return -EIO; + error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno, + XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp); + if (error) + return error; error = bp->b_error; if (error) { xfs_trans_brelse(*trans, bp); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index a0229c368e78..217e4f82a44a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -198,20 +198,22 @@ xfs_buf_free_maps( } } -static struct xfs_buf * +static int _xfs_buf_alloc( struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, - xfs_buf_flags_t flags) + xfs_buf_flags_t flags, + struct xfs_buf **bpp) { struct xfs_buf *bp; int error; int i; + *bpp = NULL; bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS); if (unlikely(!bp)) - return NULL; + return -ENOMEM; /* * We don't want certain flags to appear in b_flags unless they are @@ -239,7 +241,7 @@ _xfs_buf_alloc( error = xfs_buf_get_maps(bp, nmaps); if (error) { kmem_cache_free(xfs_buf_zone, bp); - return NULL; + return error; } bp->b_bn = map[0].bm_bn; @@ -256,7 +258,8 @@ _xfs_buf_alloc( XFS_STATS_INC(bp->b_mount, xb_create); trace_xfs_buf_init(bp, _RET_IP_); - return bp; + *bpp = bp; + return 0; } /* @@ -682,53 +685,39 @@ xfs_buf_incore( * cache hits, as metadata intensive workloads will see 3 orders of magnitude * more hits than misses. */ -struct xfs_buf * +int xfs_buf_get_map( struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, - xfs_buf_flags_t flags) + xfs_buf_flags_t flags, + struct xfs_buf **bpp) { struct xfs_buf *bp; struct xfs_buf *new_bp; int error = 0; + *bpp = NULL; error = xfs_buf_find(target, map, nmaps, flags, NULL, &bp); - - switch (error) { - case 0: - /* cache hit */ + if (!error) goto found; - case -EAGAIN: - /* cache hit, trylock failure, caller handles failure */ - ASSERT(flags & XBF_TRYLOCK); - return NULL; - case -ENOENT: - /* cache miss, go for insert */ - break; - case -EFSCORRUPTED: - default: - /* - * None of the higher layers understand failure types - * yet, so return NULL to signal a fatal lookup error. - */ - return NULL; - } + if (error != -ENOENT) + return error; - new_bp = _xfs_buf_alloc(target, map, nmaps, flags); - if (unlikely(!new_bp)) - return NULL; + error = _xfs_buf_alloc(target, map, nmaps, flags, &new_bp); + if (error) + return error; error = xfs_buf_allocate_memory(new_bp, flags); if (error) { xfs_buf_free(new_bp); - return NULL; + return error; } error = xfs_buf_find(target, map, nmaps, flags, new_bp, &bp); if (error) { xfs_buf_free(new_bp); - return NULL; + return error; } if (bp != new_bp) @@ -741,7 +730,7 @@ found: xfs_warn(target->bt_mount, "%s: failed to map pagesn", __func__); xfs_buf_relse(bp); - return NULL; + return error; } } @@ -754,7 +743,8 @@ found: XFS_STATS_INC(target->bt_mount, xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); - return bp; + *bpp = bp; + return 0; } STATIC int @@ -806,46 +796,77 @@ xfs_buf_reverify( return bp->b_error; } -xfs_buf_t * +int xfs_buf_read_map( struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, xfs_buf_flags_t flags, - const struct xfs_buf_ops *ops) + struct xfs_buf **bpp, + const struct xfs_buf_ops *ops, + xfs_failaddr_t fa) { struct xfs_buf *bp; + int error; flags |= XBF_READ; + *bpp = NULL; - bp = xfs_buf_get_map(target, map, nmaps, flags); - if (!bp) - return NULL; + error = xfs_buf_get_map(target, map, nmaps, flags, &bp); + if (error) + return error; trace_xfs_buf_read(bp, flags, _RET_IP_); if (!(bp->b_flags & XBF_DONE)) { + /* Initiate the buffer read and wait. */ XFS_STATS_INC(target->bt_mount, xb_get_read); bp->b_ops = ops; - _xfs_buf_read(bp, flags); - return bp; + error = _xfs_buf_read(bp, flags); + + /* Readahead iodone already dropped the buffer, so exit. */ + if (flags & XBF_ASYNC) + return 0; + } else { + /* Buffer already read; all we need to do is check it. */ + error = xfs_buf_reverify(bp, ops); + + /* Readahead already finished; drop the buffer and exit. */ + if (flags & XBF_ASYNC) { + xfs_buf_relse(bp); + return 0; + } + + /* We do not want read in the flags */ + bp->b_flags &= ~XBF_READ; + ASSERT(bp->b_ops != NULL || ops == NULL); } - xfs_buf_reverify(bp, ops); + /* + * If we've had a read error, then the contents of the buffer are + * invalid and should not be used. To ensure that a followup read tries + * to pull the buffer from disk again, we clear the XBF_DONE flag and + * mark the buffer stale. This ensures that anyone who has a current + * reference to the buffer will interpret it's contents correctly and + * future cache lookups will also treat it as an empty, uninitialised + * buffer. + */ + if (error) { + if (!XFS_FORCED_SHUTDOWN(target->bt_mount)) + xfs_buf_ioerror_alert(bp, fa); - if (flags & XBF_ASYNC) { - /* - * Read ahead call which is already satisfied, - * drop the buffer - */ + bp->b_flags &= ~XBF_DONE; + xfs_buf_stale(bp); xfs_buf_relse(bp); - return NULL; + + /* bad CRC means corrupted metadata */ + if (error == -EFSBADCRC) + error = -EFSCORRUPTED; + return error; } - /* We do not want read in the flags */ - bp->b_flags &= ~XBF_READ; - ASSERT(bp->b_ops != NULL || ops == NULL); - return bp; + *bpp = bp; + return 0; } /* @@ -859,11 +880,14 @@ xfs_buf_readahead_map( int nmaps, const struct xfs_buf_ops *ops) { + struct xfs_buf *bp; + if (bdi_read_congested(target->bt_bdev->bd_bdi)) return; xfs_buf_read_map(target, map, nmaps, - XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD, ops); + XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD, &bp, ops, + __this_address); } /* @@ -880,12 +904,13 @@ xfs_buf_read_uncached( const struct xfs_buf_ops *ops) { struct xfs_buf *bp; + int error; *bpp = NULL; - bp = xfs_buf_get_uncached(target, numblks, flags); - if (!bp) - return -ENOMEM; + error = xfs_buf_get_uncached(target, numblks, flags, &bp); + if (error) + return error; /* set up the buffer for a read IO */ ASSERT(bp->b_map_count == 1); @@ -896,7 +921,7 @@ xfs_buf_read_uncached( xfs_buf_submit(bp); if (bp->b_error) { - int error = bp->b_error; + error = bp->b_error; xfs_buf_relse(bp); return error; } @@ -905,20 +930,23 @@ xfs_buf_read_uncached( return 0; } -xfs_buf_t * +int xfs_buf_get_uncached( struct xfs_buftarg *target, size_t numblks, - int flags) + int flags, + struct xfs_buf **bpp) { unsigned long page_count; int error, i; struct xfs_buf *bp; DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks); + *bpp = NULL; + /* flags might contain irrelevant bits, pass only what we care about */ - bp = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT); - if (unlikely(bp == NULL)) + error = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT, &bp); + if (error) goto fail; page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT; @@ -928,8 +956,10 @@ xfs_buf_get_uncached( for (i = 0; i < page_count; i++) { bp->b_pages[i] = alloc_page(xb_to_gfp(flags)); - if (!bp->b_pages[i]) + if (!bp->b_pages[i]) { + error = -ENOMEM; goto fail_free_mem; + } } bp->b_flags |= _XBF_PAGES; @@ -941,7 +971,8 @@ xfs_buf_get_uncached( } trace_xfs_buf_get_uncached(bp, _RET_IP_); - return bp; + *bpp = bp; + return 0; fail_free_mem: while (--i >= 0) @@ -951,7 +982,7 @@ xfs_buf_get_uncached( xfs_buf_free_maps(bp); kmem_cache_free(xfs_buf_zone, bp); fail: - return NULL; + return error; } /* @@ -1205,10 +1236,10 @@ __xfs_buf_ioerror( void xfs_buf_ioerror_alert( struct xfs_buf *bp, - const char *func) + xfs_failaddr_t func) { xfs_alert(bp->b_mount, -"metadata I/O error in \"%s\" at daddr 0x%llx len %d error %d", +"metadata I/O error in \"%pS\" at daddr 0x%llx len %d error %d", func, (uint64_t)XFS_BUF_ADDR(bp), bp->b_length, -bp->b_error); } diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 56e081dd1d96..d79a1fe5d738 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -192,37 +192,40 @@ struct xfs_buf *xfs_buf_incore(struct xfs_buftarg *target, xfs_daddr_t blkno, size_t numblks, xfs_buf_flags_t flags); -struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target, - struct xfs_buf_map *map, int nmaps, - xfs_buf_flags_t flags); -struct xfs_buf *xfs_buf_read_map(struct xfs_buftarg *target, - struct xfs_buf_map *map, int nmaps, - xfs_buf_flags_t flags, - const struct xfs_buf_ops *ops); +int xfs_buf_get_map(struct xfs_buftarg *target, struct xfs_buf_map *map, + int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp); +int xfs_buf_read_map(struct xfs_buftarg *target, struct xfs_buf_map *map, + int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp, + const struct xfs_buf_ops *ops, xfs_failaddr_t fa); void xfs_buf_readahead_map(struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, const struct xfs_buf_ops *ops); -static inline struct xfs_buf * +static inline int xfs_buf_get( struct xfs_buftarg *target, xfs_daddr_t blkno, - size_t numblks) + size_t numblks, + struct xfs_buf **bpp) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); - return xfs_buf_get_map(target, &map, 1, 0); + + return xfs_buf_get_map(target, &map, 1, 0, bpp); } -static inline struct xfs_buf * +static inline int xfs_buf_read( struct xfs_buftarg *target, xfs_daddr_t blkno, size_t numblks, xfs_buf_flags_t flags, + struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); - return xfs_buf_read_map(target, &map, 1, flags, ops); + + return xfs_buf_read_map(target, &map, 1, flags, bpp, ops, + __builtin_return_address(0)); } static inline void @@ -236,8 +239,8 @@ xfs_buf_readahead( return xfs_buf_readahead_map(target, &map, 1, ops); } -struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, - int flags); +int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags, + struct xfs_buf **bpp); int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, int flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops); @@ -259,7 +262,7 @@ extern void xfs_buf_ioend(struct xfs_buf *bp); extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error, xfs_failaddr_t failaddr); #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address) -extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func); +extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa); extern int __xfs_buf_submit(struct xfs_buf *bp, bool); static inline int xfs_buf_submit(struct xfs_buf *bp) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 5be8973a452c..663810e6cd59 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -1113,7 +1113,7 @@ xfs_buf_iodone_callback_error( if (bp->b_target != lasttarg || time_after(jiffies, (lasttime + 5*HZ))) { lasttime = jiffies; - xfs_buf_ioerror_alert(bp, __func__); + xfs_buf_ioerror_alert(bp, __this_address); } lasttarg = bp->b_target; diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index cae613620175..0b8350e84d28 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -45,7 +45,7 @@ xfs_trim_extents( xfs_log_force(mp, XFS_LOG_SYNC); error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); - if (error || !agbp) + if (error) goto out_put_perag; cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT); diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 9cfd3209f52b..d223e1ae90a6 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -320,10 +320,10 @@ xfs_dquot_disk_alloc( dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock); /* now we can just get the buffer (there's nothing to read yet) */ - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, 0); - if (!bp) - return -ENOMEM; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen, 0, &bp); + if (error) + return error; bp->b_ops = &xfs_dquot_buf_ops; /* diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index 5f12b5d8527a..1a88025e68a3 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -159,16 +159,15 @@ xfs_filestream_pick_ag( if (!pag->pagf_init) { err = xfs_alloc_pagf_init(mp, NULL, ag, trylock); - if (err && !trylock) { + if (err) { xfs_perag_put(pag); - return err; + if (err != -EAGAIN) + return err; + /* Couldn't lock the AGF, skip this AG. */ + continue; } } - /* Might fail sometimes during the 1st pass with trylock set. */ - if (!pag->pagf_init) - goto next_ag; - /* Keep track of the AG with the most free blocks. */ if (pag->pagf_freeblks > maxfree) { maxfree = pag->pagf_freeblks; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 1979a0055763..c5077e6326c7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2546,6 +2546,7 @@ xfs_ifree_cluster( struct xfs_perag *pag; struct xfs_ino_geometry *igeo = M_IGEO(mp); xfs_ino_t inum; + int error; inum = xic->first_ino; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum)); @@ -2574,12 +2575,11 @@ xfs_ifree_cluster( * complete before we get a lock on it, and hence we may fail * to mark all the active inodes on the buffer stale. */ - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * igeo->blocks_per_cluster, - XBF_UNMAPPED); - - if (!bp) - return -ENOMEM; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, + mp->m_bsize * igeo->blocks_per_cluster, + XBF_UNMAPPED, &bp); + if (error) + return error; /* * This buffer may not have been correctly initialised as we diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 0d683fb96396..25cfc85dbaa7 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -294,7 +294,7 @@ xlog_recover_iodone( * this during recovery. One strike! */ if (!XFS_FORCED_SHUTDOWN(bp->b_mount)) { - xfs_buf_ioerror_alert(bp, __func__); + xfs_buf_ioerror_alert(bp, __this_address); xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); } } @@ -2745,15 +2745,10 @@ xlog_recover_buffer_pass2( if (buf_f->blf_flags & XFS_BLF_INODE_BUF) buf_flags |= XBF_UNMAPPED; - bp = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, - buf_flags, NULL); - if (!bp) - return -ENOMEM; - error = bp->b_error; - if (error) { - xfs_buf_ioerror_alert(bp, "xlog_recover_do..(read#1)"); - goto out_release; - } + error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, + buf_flags, &bp, NULL); + if (error) + return error; /* * Recover the buffer only if we get an LSN from it and it's less than @@ -2950,17 +2945,10 @@ xlog_recover_inode_pass2( } trace_xfs_log_recover_inode_recover(log, in_f); - bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, 0, - &xfs_inode_buf_ops); - if (!bp) { - error = -ENOMEM; + error = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, + 0, &bp, &xfs_inode_buf_ops); + if (error) goto error; - } - error = bp->b_error; - if (error) { - xfs_buf_ioerror_alert(bp, "xlog_recover_do..(read#2)"); - goto out_release; - } ASSERT(in_f->ilf_fields & XFS_ILOG_CORE); dip = xfs_buf_offset(bp, in_f->ilf_boffset); @@ -5639,7 +5627,7 @@ xlog_do_recover( error = xfs_buf_submit(bp); if (error) { if (!XFS_FORCED_SHUTDOWN(mp)) { - xfs_buf_ioerror_alert(bp, __func__); + xfs_buf_ioerror_alert(bp, __this_address); ASSERT(0); } xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index e723b267a247..b0ce04ffd3cd 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -143,8 +143,6 @@ xfs_reflink_find_shared( error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (error) return error; - if (!agbp) - return -ENOMEM; cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index d42b5a2047e0..6209e7b6b895 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -826,12 +826,10 @@ xfs_growfs_rt_alloc( * Get a buffer for the block. */ d = XFS_FSB_TO_DADDR(mp, fsbno); - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, - mp->m_bsize, 0); - if (bp == NULL) { - error = -EIO; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, + mp->m_bsize, 0, &bp); + if (error) goto out_trans_cancel; - } memset(bp->b_addr, 0, mp->m_sb.sb_blocksize); xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1); /* diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 760901783944..2094386af8ac 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -62,7 +62,7 @@ enum { Opt_discard, Opt_nodiscard, Opt_dax, }; -static const struct fs_parameter_spec xfs_param_specs[] = { +static const struct fs_parameter_spec xfs_fs_parameters[] = { fsparam_u32("logbufs", Opt_logbufs), fsparam_string("logbsize", Opt_logbsize), fsparam_string("logdev", Opt_logdev), @@ -106,11 +106,6 @@ static const struct fs_parameter_spec xfs_param_specs[] = { {} }; -static const struct fs_parameter_description xfs_fs_parameters = { - .name = "xfs", - .specs = xfs_param_specs, -}; - struct proc_xfs_info { uint64_t flag; char *str; @@ -1120,7 +1115,7 @@ xfs_fc_parse_param( int size = 0; int opt; - opt = fs_parse(fc, &xfs_fs_parameters, param, &result); + opt = fs_parse(fc, xfs_fs_parameters, param, &result); if (opt < 0) return opt; @@ -1782,7 +1777,7 @@ static struct file_system_type xfs_fs_type = { .owner = THIS_MODULE, .name = "xfs", .init_fs_context = xfs_init_fs_context, - .parameters = &xfs_fs_parameters, + .parameters = xfs_fs_parameters, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index a25502bc2071..d762d42ed0ff 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -53,20 +53,10 @@ xfs_readlink_bmap_ilocked( d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); - bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0, - &xfs_symlink_buf_ops); - if (!bp) - return -ENOMEM; - error = bp->b_error; - if (error) { - xfs_buf_ioerror_alert(bp, __func__); - xfs_buf_relse(bp); - - /* bad CRC means corrupted metadata */ - if (error == -EFSBADCRC) - error = -EFSCORRUPTED; - goto out; - } + error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0, + &bp, &xfs_symlink_buf_ops); + if (error) + return error; byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt); if (pathlen < byte_cnt) byte_cnt = pathlen; @@ -290,12 +280,10 @@ xfs_symlink( d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, - BTOBB(byte_cnt), 0); - if (!bp) { - error = -ENOMEM; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, + BTOBB(byte_cnt), 0, &bp); + if (error) goto out_trans_cancel; - } bp->b_ops = &xfs_symlink_buf_ops; byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt); @@ -433,13 +421,12 @@ xfs_inactive_symlink_rmt( * Invalidate the block(s). No validation is done. */ for (i = 0; i < nmaps; i++) { - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, - XFS_FSB_TO_DADDR(mp, mval[i].br_startblock), - XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0); - if (!bp) { - error = -ENOMEM; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, mval[i].br_startblock), + XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0, + &bp); + if (error) goto error_trans_cancel; - } xfs_trans_binval(tp, bp); } /* diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 64d7f171ebd3..752c7fef9de7 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -169,21 +169,21 @@ int xfs_trans_alloc_empty(struct xfs_mount *mp, struct xfs_trans **tpp); void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t); -struct xfs_buf *xfs_trans_get_buf_map(struct xfs_trans *tp, - struct xfs_buftarg *target, - struct xfs_buf_map *map, int nmaps, - uint flags); +int xfs_trans_get_buf_map(struct xfs_trans *tp, struct xfs_buftarg *target, + struct xfs_buf_map *map, int nmaps, xfs_buf_flags_t flags, + struct xfs_buf **bpp); -static inline struct xfs_buf * +static inline int xfs_trans_get_buf( struct xfs_trans *tp, struct xfs_buftarg *target, xfs_daddr_t blkno, int numblks, - uint flags) + uint flags, + struct xfs_buf **bpp) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); - return xfs_trans_get_buf_map(tp, target, &map, 1, flags); + return xfs_trans_get_buf_map(tp, target, &map, 1, flags, bpp); } int xfs_trans_read_buf_map(struct xfs_mount *mp, diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index b5b3a78ef31c..08174ffa2118 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -112,19 +112,22 @@ xfs_trans_bjoin( * If the transaction pointer is NULL, make this just a normal * get_buf() call. */ -struct xfs_buf * +int xfs_trans_get_buf_map( struct xfs_trans *tp, struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, - xfs_buf_flags_t flags) + xfs_buf_flags_t flags, + struct xfs_buf **bpp) { xfs_buf_t *bp; struct xfs_buf_log_item *bip; + int error; + *bpp = NULL; if (!tp) - return xfs_buf_get_map(target, map, nmaps, flags); + return xfs_buf_get_map(target, map, nmaps, flags, bpp); /* * If we find the buffer in the cache with this transaction @@ -146,19 +149,20 @@ xfs_trans_get_buf_map( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_recur++; trace_xfs_trans_get_buf_recur(bip); - return bp; + *bpp = bp; + return 0; } - bp = xfs_buf_get_map(target, map, nmaps, flags); - if (bp == NULL) { - return NULL; - } + error = xfs_buf_get_map(target, map, nmaps, flags, &bp); + if (error) + return error; ASSERT(!bp->b_error); _xfs_trans_bjoin(tp, bp, 1); trace_xfs_trans_get_buf(bp->b_log_item); - return bp; + *bpp = bp; + return 0; } /* @@ -276,7 +280,7 @@ xfs_trans_read_buf_map( ASSERT(bp->b_ops != NULL); error = xfs_buf_reverify(bp, ops); if (error) { - xfs_buf_ioerror_alert(bp, __func__); + xfs_buf_ioerror_alert(bp, __return_address); if (tp->t_flags & XFS_TRANS_DIRTY) xfs_force_shutdown(tp->t_mountp, @@ -298,36 +302,17 @@ xfs_trans_read_buf_map( return 0; } - bp = xfs_buf_read_map(target, map, nmaps, flags, ops); - if (!bp) { - if (!(flags & XBF_TRYLOCK)) - return -ENOMEM; - return tp ? 0 : -EAGAIN; - } - - /* - * If we've had a read error, then the contents of the buffer are - * invalid and should not be used. To ensure that a followup read tries - * to pull the buffer from disk again, we clear the XBF_DONE flag and - * mark the buffer stale. This ensures that anyone who has a current - * reference to the buffer will interpret it's contents correctly and - * future cache lookups will also treat it as an empty, uninitialised - * buffer. - */ - if (bp->b_error) { - error = bp->b_error; - if (!XFS_FORCED_SHUTDOWN(mp)) - xfs_buf_ioerror_alert(bp, __func__); - bp->b_flags &= ~XBF_DONE; - xfs_buf_stale(bp); - + error = xfs_buf_read_map(target, map, nmaps, flags, &bp, ops, + __return_address); + switch (error) { + case 0: + break; + default: if (tp && (tp->t_flags & XFS_TRANS_DIRTY)) xfs_force_shutdown(tp->t_mountp, SHUTDOWN_META_IO_ERROR); - xfs_buf_relse(bp); - - /* bad CRC means corrupted metadata */ - if (error == -EFSBADCRC) - error = -EFSCORRUPTED; + /* fall through */ + case -ENOMEM: + case -EAGAIN: return error; } |