diff options
Diffstat (limited to 'fs')
561 files changed, 32065 insertions, 14877 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 819c75233235..32619d146cbc 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -57,6 +57,8 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq) int err, len; len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); + if (len > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_write_subrequest_terminated(subreq, len ?: err, false); } @@ -79,11 +81,13 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); if (pos + total >= i_size_read(rreq->inode)) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - - if (!err) + if (!err && total) { subreq->transferred += total; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } - netfs_read_subreq_terminated(subreq, err, false); + subreq->error = err; + netfs_read_subreq_terminated(subreq); } /** diff --git a/fs/afs/Makefile b/fs/afs/Makefile index dcdc0f1bb76f..5efd7e13b304 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -11,6 +11,7 @@ kafs-y := \ cmservice.o \ dir.o \ dir_edit.o \ + dir_search.o \ dir_silly.o \ dynroot.o \ file.o \ diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c index a189ff8a5034..c0384201b8fe 100644 --- a/fs/afs/addr_prefs.c +++ b/fs/afs/addr_prefs.c @@ -413,8 +413,10 @@ int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size) do { argc = afs_split_string(&buf, argv, ARRAY_SIZE(argv)); - if (argc < 0) - return argc; + if (argc < 0) { + ret = argc; + goto done; + } if (argc < 2) goto inval; diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b488072aee87..ec3db00bd081 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -10,7 +10,7 @@ #include <linux/in.h> -#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */ +#define AFS_MAXCELLNAME 253 /* Maximum length of a cell name (DNS limited) */ #define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */ #define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */ #define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */ diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index a06296c8827d..b835e25a2c02 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -13,6 +13,7 @@ #define AFS_VL_PORT 7003 /* volume location service port */ #define VL_SERVICE 52 /* RxRPC service ID for the Volume Location service */ #define YFS_VL_SERVICE 2503 /* Service ID for AuriStor upgraded VL service */ +#define YFS_VL_MAXCELLNAME 256 /* Maximum length of a cell name in YFS protocol */ enum AFSVL_Operations { VLGETENTRYBYID = 503, /* AFS Get VLDB entry by ID */ diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 99b2c8172021..69e1dd55b160 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -41,7 +41,7 @@ static void afs_volume_init_callback(struct afs_volume *volume) list_for_each_entry(vnode, &volume->open_mmaps, cb_mmap_link) { if (vnode->cb_v_check != atomic_read(&volume->cb_v_break)) { - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); + afs_clear_cb_promise(vnode, afs_cb_promise_clear_vol_init_cb); queue_work(system_unbound_wq, &vnode->cb_work); } } @@ -79,7 +79,7 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas _enter(""); clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE) { + if (afs_clear_cb_promise(vnode, afs_cb_promise_clear_cb_break)) { vnode->cb_break++; vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break); afs_clear_permits(vnode); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index caa09875f520..cee42646736c 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -146,18 +146,20 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, return ERR_PTR(-ENOMEM); } - cell->name = kmalloc(namelen + 1, GFP_KERNEL); + cell->name = kmalloc(1 + namelen + 1, GFP_KERNEL); if (!cell->name) { kfree(cell); return ERR_PTR(-ENOMEM); } - cell->net = net; + cell->name[0] = '.'; + cell->name++; cell->name_len = namelen; for (i = 0; i < namelen; i++) cell->name[i] = tolower(name[i]); cell->name[i] = 0; + cell->net = net; refcount_set(&cell->ref, 1); atomic_set(&cell->active, 0); INIT_WORK(&cell->manager, afs_manage_cell_work); @@ -211,7 +213,7 @@ parse_failed: if (ret == -EINVAL) printk(KERN_ERR "kAFS: bad VL server IP address\n"); error: - kfree(cell->name); + kfree(cell->name - 1); kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -365,6 +367,14 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) len = cp - rootcell; } + if (len == 0 || !rootcell[0] || rootcell[0] == '.' || rootcell[len - 1] == '.') + return -EINVAL; + if (memchr(rootcell, '/', len)) + return -EINVAL; + cp = strstr(rootcell, ".."); + if (cp && cp < rootcell + len) + return -EINVAL; + /* allocate a cell record for the root cell */ new_root = afs_lookup_cell(net, rootcell, len, vllist, false); if (IS_ERR(new_root)) { @@ -502,7 +512,7 @@ static void afs_cell_destroy(struct rcu_head *rcu) afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers)); afs_unuse_cell(net, cell->alias_of, afs_cell_trace_unuse_alias); key_put(cell->anonymous_key); - kfree(cell->name); + kfree(cell->name - 1); kfree(cell); afs_dec_cells_outstanding(net); @@ -710,7 +720,8 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell) afs_proc_cell_remove(cell); mutex_lock(&net->proc_cells_lock); - hlist_del_rcu(&cell->proc_link); + if (!hlist_unhashed(&cell->proc_link)) + hlist_del_rcu(&cell->proc_link); afs_dynroot_rmdir(net, cell); mutex_unlock(&net->proc_cells_lock); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index ada363af5aab..a843c36fc471 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -13,6 +13,7 @@ #include <linux/ctype.h> #include <linux/sched.h> #include <linux/iversion.h> +#include <linux/iov_iter.h> #include <linux/task_io_accounting_ops.h> #include "internal.h" #include "afs_fs.h" @@ -42,15 +43,6 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); -static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags); -static void afs_dir_invalidate_folio(struct folio *folio, size_t offset, - size_t length); - -static bool afs_dir_dirty_folio(struct address_space *mapping, - struct folio *folio) -{ - BUG(); /* This should never happen. */ -} const struct file_operations afs_dir_file_operations = { .open = afs_dir_open, @@ -75,10 +67,7 @@ const struct inode_operations afs_dir_inode_operations = { }; const struct address_space_operations afs_dir_aops = { - .dirty_folio = afs_dir_dirty_folio, - .release_folio = afs_dir_release_folio, - .invalidate_folio = afs_dir_invalidate_folio, - .migrate_folio = filemap_migrate_folio, + .writepages = afs_single_writepages, }; const struct dentry_operations afs_fs_dentry_operations = { @@ -99,152 +88,124 @@ struct afs_lookup_one_cookie { struct afs_lookup_cookie { struct dir_context ctx; struct qstr name; - bool found; - bool one_only; unsigned short nr_fids; struct afs_fid fids[50]; }; +static void afs_dir_unuse_cookie(struct afs_vnode *dvnode, int ret) +{ + if (ret == 0) { + struct afs_vnode_cache_aux aux; + loff_t i_size = i_size_read(&dvnode->netfs.inode); + + afs_set_cache_aux(dvnode, &aux); + fscache_unuse_cookie(afs_vnode_cache(dvnode), &aux, &i_size); + } else { + fscache_unuse_cookie(afs_vnode_cache(dvnode), NULL, NULL); + } +} + /* - * Drop the refs that we're holding on the folios we were reading into. We've - * got refs on the first nr_pages pages. + * Iterate through a kmapped directory segment, dumping a summary of + * the contents. */ -static void afs_dir_read_cleanup(struct afs_read *req) +static size_t afs_dir_dump_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) { - struct address_space *mapping = req->vnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t last = req->nr_pages - 1; + do { + union afs_xdr_dir_block *block = iter_base; - XA_STATE(xas, &mapping->i_pages, 0); + pr_warn("[%05zx] %32phN\n", progress, block); + iter_base += AFS_DIR_BLOCK_SIZE; + progress += AFS_DIR_BLOCK_SIZE; + len -= AFS_DIR_BLOCK_SIZE; + } while (len > 0); - if (unlikely(!req->nr_pages)) - return; + return len; +} - rcu_read_lock(); - xas_for_each(&xas, folio, last) { - if (xas_retry(&xas, folio)) - continue; - BUG_ON(xa_is_value(folio)); - ASSERTCMP(folio->mapping, ==, mapping); +/* + * Dump the contents of a directory. + */ +static void afs_dir_dump(struct afs_vnode *dvnode) +{ + struct iov_iter iter; + unsigned long long i_size = i_size_read(&dvnode->netfs.inode); - folio_put(folio); - } + pr_warn("DIR %llx:%llx is=%llx\n", + dvnode->fid.vid, dvnode->fid.vnode, i_size); - rcu_read_unlock(); + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size); + iterate_folioq(&iter, iov_iter_count(&iter), NULL, NULL, + afs_dir_dump_step); } /* * check that a directory folio is valid */ -static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio, - loff_t i_size) +static bool afs_dir_check_block(struct afs_vnode *dvnode, size_t progress, + union afs_xdr_dir_block *block) { - union afs_xdr_dir_block *block; - size_t offset, size; - loff_t pos; + if (block->hdr.magic != AFS_DIR_MAGIC) { + pr_warn("%s(%lx): [%zx] bad magic %04x\n", + __func__, dvnode->netfs.inode.i_ino, + progress, ntohs(block->hdr.magic)); + trace_afs_dir_check_failed(dvnode, progress); + trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic); + return false; + } - /* Determine how many magic numbers there should be in this folio, but - * we must take care because the directory may change size under us. + /* Make sure each block is NUL terminated so we can reasonably + * use string functions on it. The filenames in the folio + * *should* be NUL-terminated anyway. */ - pos = folio_pos(folio); - if (i_size <= pos) - goto checked; - - size = min_t(loff_t, folio_size(folio), i_size - pos); - for (offset = 0; offset < size; offset += sizeof(*block)) { - block = kmap_local_folio(folio, offset); - if (block->hdr.magic != AFS_DIR_MAGIC) { - printk("kAFS: %s(%lx): [%llx] bad magic %zx/%zx is %04hx\n", - __func__, dvnode->netfs.inode.i_ino, - pos, offset, size, ntohs(block->hdr.magic)); - trace_afs_dir_check_failed(dvnode, pos + offset, i_size); - kunmap_local(block); - trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic); - goto error; - } - - /* Make sure each block is NUL terminated so we can reasonably - * use string functions on it. The filenames in the folio - * *should* be NUL-terminated anyway. - */ - ((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0; - - kunmap_local(block); - } -checked: + ((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0; afs_stat_v(dvnode, n_read_dir); return true; - -error: - return false; } /* - * Dump the contents of a directory. + * Iterate through a kmapped directory segment, checking the content. */ -static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) +static size_t afs_dir_check_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) { - union afs_xdr_dir_block *block; - struct address_space *mapping = dvnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t last = req->nr_pages - 1; - size_t offset, size; - - XA_STATE(xas, &mapping->i_pages, 0); - - pr_warn("DIR %llx:%llx f=%llx l=%llx al=%llx\n", - dvnode->fid.vid, dvnode->fid.vnode, - req->file_size, req->len, req->actual_len); - pr_warn("DIR %llx %x %zx %zx\n", - req->pos, req->nr_pages, - req->iter->iov_offset, iov_iter_count(req->iter)); - - xas_for_each(&xas, folio, last) { - if (xas_retry(&xas, folio)) - continue; + struct afs_vnode *dvnode = priv; - BUG_ON(folio->mapping != mapping); + if (WARN_ON_ONCE(progress % AFS_DIR_BLOCK_SIZE || + len % AFS_DIR_BLOCK_SIZE)) + return len; - size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio)); - for (offset = 0; offset < size; offset += sizeof(*block)) { - block = kmap_local_folio(folio, offset); - pr_warn("[%02lx] %32phN\n", folio->index + offset, block); - kunmap_local(block); - } - } + do { + if (!afs_dir_check_block(dvnode, progress, iter_base)) + break; + iter_base += AFS_DIR_BLOCK_SIZE; + len -= AFS_DIR_BLOCK_SIZE; + } while (len > 0); + + return len; } /* - * Check all the blocks in a directory. All the folios are held pinned. + * Check all the blocks in a directory. */ -static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) +static int afs_dir_check(struct afs_vnode *dvnode) { - struct address_space *mapping = dvnode->netfs.inode.i_mapping; - struct folio *folio; - pgoff_t last = req->nr_pages - 1; - int ret = 0; + struct iov_iter iter; + unsigned long long i_size = i_size_read(&dvnode->netfs.inode); + size_t checked = 0; - XA_STATE(xas, &mapping->i_pages, 0); - - if (unlikely(!req->nr_pages)) + if (unlikely(!i_size)) return 0; - rcu_read_lock(); - xas_for_each(&xas, folio, last) { - if (xas_retry(&xas, folio)) - continue; - - BUG_ON(folio->mapping != mapping); - - if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) { - afs_dir_dump(dvnode, req); - ret = -EIO; - break; - } + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size); + checked = iterate_folioq(&iter, iov_iter_count(&iter), dvnode, NULL, + afs_dir_check_step); + if (checked != i_size) { + afs_dir_dump(dvnode); + return -EIO; } - - rcu_read_unlock(); - return ret; + return 0; } /* @@ -264,134 +225,140 @@ static int afs_dir_open(struct inode *inode, struct file *file) } /* - * Read the directory into the pagecache in one go, scrubbing the previous - * contents. The list of folios is returned, pinning them so that they don't - * get reclaimed during the iteration. + * Read a file in a single download. */ -static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) - __acquires(&dvnode->validate_lock) +static ssize_t afs_do_read_single(struct afs_vnode *dvnode, struct file *file) { - struct address_space *mapping = dvnode->netfs.inode.i_mapping; - struct afs_read *req; + struct iov_iter iter; + ssize_t ret; loff_t i_size; - int nr_pages, i; - int ret; - loff_t remote_size = 0; - - _enter(""); + bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) && + !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags)); - req = kzalloc(sizeof(*req), GFP_KERNEL); - if (!req) - return ERR_PTR(-ENOMEM); - - refcount_set(&req->usage, 1); - req->vnode = dvnode; - req->key = key_get(key); - req->cleanup = afs_dir_read_cleanup; - -expand: i_size = i_size_read(&dvnode->netfs.inode); - if (i_size < remote_size) - i_size = remote_size; - if (i_size < 2048) { - ret = afs_bad(dvnode, afs_file_error_dir_small); - goto error; - } - if (i_size > 2048 * 1024) { - trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); - ret = -EFBIG; - goto error; + if (is_dir) { + if (i_size < AFS_DIR_BLOCK_SIZE) + return afs_bad(dvnode, afs_file_error_dir_small); + if (i_size > AFS_DIR_BLOCK_SIZE * 1024) { + trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; + } + } else { + if (i_size > AFSPATHMAX) { + trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; + } } - _enter("%llu", i_size); + /* Expand the storage. TODO: Shrink the storage too. */ + if (dvnode->directory_size < i_size) { + size_t cur_size = dvnode->directory_size; - nr_pages = (i_size + PAGE_SIZE - 1) / PAGE_SIZE; + ret = netfs_alloc_folioq_buffer(NULL, + &dvnode->directory, &cur_size, i_size, + mapping_gfp_mask(dvnode->netfs.inode.i_mapping)); + dvnode->directory_size = cur_size; + if (ret < 0) + return ret; + } - req->actual_len = i_size; /* May change */ - req->len = nr_pages * PAGE_SIZE; /* We can ask for more than there is */ - req->data_version = dvnode->status.data_version; /* May change */ - iov_iter_xarray(&req->def_iter, ITER_DEST, &dvnode->netfs.inode.i_mapping->i_pages, - 0, i_size); - req->iter = &req->def_iter; + iov_iter_folio_queue(&iter, ITER_DEST, dvnode->directory, 0, 0, dvnode->directory_size); - /* Fill in any gaps that we might find where the memory reclaimer has - * been at work and pin all the folios. If there are any gaps, we will - * need to reread the entire directory contents. + /* AFS requires us to perform the read of a directory synchronously as + * a single unit to avoid issues with the directory contents being + * changed between reads. */ - i = req->nr_pages; - while (i < nr_pages) { - struct folio *folio; - - folio = filemap_get_folio(mapping, i); - if (IS_ERR(folio)) { - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_stat_v(dvnode, n_inval); - folio = __filemap_get_folio(mapping, - i, FGP_LOCK | FGP_CREAT, - mapping->gfp_mask); - if (IS_ERR(folio)) { - ret = PTR_ERR(folio); - goto error; - } - folio_attach_private(folio, (void *)1); - folio_unlock(folio); + ret = netfs_read_single(&dvnode->netfs.inode, file, &iter); + if (ret >= 0) { + i_size = i_size_read(&dvnode->netfs.inode); + if (i_size > ret) { + /* The content has grown, so we need to expand the + * buffer. + */ + ret = -ESTALE; + } else if (is_dir) { + int ret2 = afs_dir_check(dvnode); + + if (ret2 < 0) + ret = ret2; + } else if (i_size < folioq_folio_size(dvnode->directory, 0)) { + /* NUL-terminate a symlink. */ + char *symlink = kmap_local_folio(folioq_folio(dvnode->directory, 0), 0); + + symlink[i_size] = 0; + kunmap_local(symlink); } - - req->nr_pages += folio_nr_pages(folio); - i += folio_nr_pages(folio); } - /* If we're going to reload, we need to lock all the pages to prevent - * races. - */ + return ret; +} + +ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file) +{ + ssize_t ret; + + fscache_use_cookie(afs_vnode_cache(dvnode), false); + ret = afs_do_read_single(dvnode, file); + fscache_unuse_cookie(afs_vnode_cache(dvnode), NULL, NULL); + return ret; +} + +/* + * Read the directory into a folio_queue buffer in one go, scrubbing the + * previous contents. We return -ESTALE if the caller needs to call us again. + */ +ssize_t afs_read_dir(struct afs_vnode *dvnode, struct file *file) + __acquires(&dvnode->validate_lock) +{ + ssize_t ret; + loff_t i_size; + + i_size = i_size_read(&dvnode->netfs.inode); + ret = -ERESTARTSYS; if (down_read_killable(&dvnode->validate_lock) < 0) goto error; - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - goto success; + /* We only need to reread the data if it became invalid - or if we + * haven't read it yet. + */ + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + test_bit(AFS_VNODE_DIR_READ, &dvnode->flags)) { + ret = i_size; + goto valid; + } up_read(&dvnode->validate_lock); if (down_write_killable(&dvnode->validate_lock) < 0) goto error; - if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { - trace_afs_reload_dir(dvnode); - ret = afs_fetch_data(dvnode, req); - if (ret < 0) - goto error_unlock; - - task_io_account_read(PAGE_SIZE * req->nr_pages); - - if (req->len < req->file_size) { - /* The content has grown, so we need to expand the - * buffer. - */ - up_write(&dvnode->validate_lock); - remote_size = req->file_size; - goto expand; - } + if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + afs_invalidate_cache(dvnode, 0); - /* Validate the data we just read. */ - ret = afs_dir_check(dvnode, req); + if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) || + !test_bit(AFS_VNODE_DIR_READ, &dvnode->flags)) { + trace_afs_reload_dir(dvnode); + ret = afs_read_single(dvnode, file); if (ret < 0) goto error_unlock; // TODO: Trim excess pages set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags); + set_bit(AFS_VNODE_DIR_READ, &dvnode->flags); + } else { + ret = i_size; } downgrade_write(&dvnode->validate_lock); -success: - return req; +valid: + return ret; error_unlock: up_write(&dvnode->validate_lock); error: - afs_put_read(req); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = %zd", ret); + return ret; } /* @@ -399,79 +366,69 @@ error: */ static int afs_dir_iterate_block(struct afs_vnode *dvnode, struct dir_context *ctx, - union afs_xdr_dir_block *block, - unsigned blkoff) + union afs_xdr_dir_block *block) { union afs_xdr_dirent *dire; - unsigned offset, next, curr, nr_slots; + unsigned int blknum, base, hdr, pos, next, nr_slots; size_t nlen; int tmp; - _enter("%llx,%x", ctx->pos, blkoff); + blknum = ctx->pos / AFS_DIR_BLOCK_SIZE; + base = blknum * AFS_DIR_SLOTS_PER_BLOCK; + hdr = (blknum == 0 ? AFS_DIR_RESV_BLOCKS0 : AFS_DIR_RESV_BLOCKS); + pos = DIV_ROUND_UP(ctx->pos, AFS_DIR_DIRENT_SIZE) - base; - curr = (ctx->pos - blkoff) / sizeof(union afs_xdr_dirent); + _enter("%llx,%x", ctx->pos, blknum); /* walk through the block, an entry at a time */ - for (offset = (blkoff == 0 ? AFS_DIR_RESV_BLOCKS0 : AFS_DIR_RESV_BLOCKS); - offset < AFS_DIR_SLOTS_PER_BLOCK; - offset = next - ) { + for (unsigned int slot = hdr; slot < AFS_DIR_SLOTS_PER_BLOCK; slot = next) { /* skip entries marked unused in the bitmap */ - if (!(block->hdr.bitmap[offset / 8] & - (1 << (offset % 8)))) { - _debug("ENT[%zu.%u]: unused", - blkoff / sizeof(union afs_xdr_dir_block), offset); - next = offset + 1; - if (offset >= curr) - ctx->pos = blkoff + - next * sizeof(union afs_xdr_dirent); + if (!(block->hdr.bitmap[slot / 8] & + (1 << (slot % 8)))) { + _debug("ENT[%x]: Unused", base + slot); + next = slot + 1; + if (next >= pos) + ctx->pos = (base + next) * sizeof(union afs_xdr_dirent); continue; } /* got a valid entry */ - dire = &block->dirents[offset]; + dire = &block->dirents[slot]; nlen = strnlen(dire->u.name, - sizeof(*block) - - offset * sizeof(union afs_xdr_dirent)); + (unsigned long)(block + 1) - (unsigned long)dire->u.name - 1); if (nlen > AFSNAMEMAX - 1) { - _debug("ENT[%zu]: name too long (len %u/%zu)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, nlen); + _debug("ENT[%x]: Name too long (len %zx)", + base + slot, nlen); return afs_bad(dvnode, afs_file_error_dir_name_too_long); } - _debug("ENT[%zu.%u]: %s %zu \"%s\"", - blkoff / sizeof(union afs_xdr_dir_block), offset, - (offset < curr ? "skip" : "fill"), + _debug("ENT[%x]: %s %zx \"%s\"", + base + slot, (slot < pos ? "skip" : "fill"), nlen, dire->u.name); nr_slots = afs_dir_calc_slots(nlen); - next = offset + nr_slots; + next = slot + nr_slots; if (next > AFS_DIR_SLOTS_PER_BLOCK) { - _debug("ENT[%zu.%u]:" - " %u extends beyond end dir block" - " (len %zu)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, next, nlen); + _debug("ENT[%x]: extends beyond end dir block (len %zx)", + base + slot, nlen); return afs_bad(dvnode, afs_file_error_dir_over_end); } /* Check that the name-extension dirents are all allocated */ for (tmp = 1; tmp < nr_slots; tmp++) { - unsigned int ix = offset + tmp; - if (!(block->hdr.bitmap[ix / 8] & (1 << (ix % 8)))) { - _debug("ENT[%zu.u]:" - " %u unmarked extension (%u/%u)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, tmp, nr_slots); + unsigned int xslot = slot + tmp; + + if (!(block->hdr.bitmap[xslot / 8] & (1 << (xslot % 8)))) { + _debug("ENT[%x]: Unmarked extension (%x/%x)", + base + slot, tmp, nr_slots); return afs_bad(dvnode, afs_file_error_dir_unmarked_ext); } } /* skip if starts before the current position */ - if (offset < curr) { - if (next > curr) - ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); + if (slot < pos) { + if (next > pos) + ctx->pos = (base + next) * sizeof(union afs_xdr_dirent); continue; } @@ -485,75 +442,110 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, return 0; } - ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); + ctx->pos = (base + next) * sizeof(union afs_xdr_dirent); } _leave(" = 1 [more]"); return 1; } +struct afs_dir_iteration_ctx { + struct dir_context *dir_ctx; + int error; +}; + /* - * iterate through the data blob that lists the contents of an AFS directory + * Iterate through a kmapped directory segment. */ -static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, - struct key *key, afs_dataversion_t *_dir_version) +static size_t afs_dir_iterate_step(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2) { - struct afs_vnode *dvnode = AFS_FS_I(dir); - union afs_xdr_dir_block *dblock; - struct afs_read *req; - struct folio *folio; - unsigned offset, size; + struct afs_dir_iteration_ctx *ctx = priv2; + struct afs_vnode *dvnode = priv; int ret; - _enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos); - - if (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(dir)->flags)) { - _leave(" = -ESTALE"); - return -ESTALE; + if (WARN_ON_ONCE(progress % AFS_DIR_BLOCK_SIZE || + len % AFS_DIR_BLOCK_SIZE)) { + pr_err("Mis-iteration prog=%zx len=%zx\n", + progress % AFS_DIR_BLOCK_SIZE, + len % AFS_DIR_BLOCK_SIZE); + return len; } - req = afs_read_dir(dvnode, key); - if (IS_ERR(req)) - return PTR_ERR(req); - *_dir_version = req->data_version; + do { + ret = afs_dir_iterate_block(dvnode, ctx->dir_ctx, iter_base); + if (ret != 1) + break; - /* round the file position up to the next entry boundary */ - ctx->pos += sizeof(union afs_xdr_dirent) - 1; - ctx->pos &= ~(sizeof(union afs_xdr_dirent) - 1); + ctx->dir_ctx->pos = round_up(ctx->dir_ctx->pos, AFS_DIR_BLOCK_SIZE); + iter_base += AFS_DIR_BLOCK_SIZE; + len -= AFS_DIR_BLOCK_SIZE; + } while (len > 0); - /* walk through the blocks in sequence */ - ret = 0; - while (ctx->pos < req->actual_len) { - /* Fetch the appropriate folio from the directory and re-add it - * to the LRU. We have all the pages pinned with an extra ref. - */ - folio = __filemap_get_folio(dir->i_mapping, ctx->pos / PAGE_SIZE, - FGP_ACCESSED, 0); - if (IS_ERR(folio)) { - ret = afs_bad(dvnode, afs_file_error_dir_missing_page); - break; - } + return len; +} - offset = round_down(ctx->pos, sizeof(*dblock)) - folio_pos(folio); - size = min_t(loff_t, folio_size(folio), - req->actual_len - folio_pos(folio)); +/* + * Iterate through the directory folios. + */ +static int afs_dir_iterate_contents(struct inode *dir, struct dir_context *dir_ctx) +{ + struct afs_dir_iteration_ctx ctx = { .dir_ctx = dir_ctx }; + struct afs_vnode *dvnode = AFS_FS_I(dir); + struct iov_iter iter; + unsigned long long i_size = i_size_read(dir); - do { - dblock = kmap_local_folio(folio, offset); - ret = afs_dir_iterate_block(dvnode, ctx, dblock, - folio_pos(folio) + offset); - kunmap_local(dblock); - if (ret != 1) - goto out; + /* Round the file position up to the next entry boundary */ + dir_ctx->pos = round_up(dir_ctx->pos, sizeof(union afs_xdr_dirent)); - } while (offset += sizeof(*dblock), offset < size); + if (i_size <= 0 || dir_ctx->pos >= i_size) + return 0; - ret = 0; - } + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size); + iov_iter_advance(&iter, round_down(dir_ctx->pos, AFS_DIR_BLOCK_SIZE)); + + iterate_folioq(&iter, iov_iter_count(&iter), dvnode, &ctx, + afs_dir_iterate_step); + + if (ctx.error == -ESTALE) + afs_invalidate_dir(dvnode, afs_dir_invalid_iter_stale); + return ctx.error; +} + +/* + * iterate through the data blob that lists the contents of an AFS directory + */ +static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, + struct file *file, afs_dataversion_t *_dir_version) +{ + struct afs_vnode *dvnode = AFS_FS_I(dir); + int retry_limit = 100; + int ret; + + _enter("{%lu},%llx,,", dir->i_ino, ctx->pos); + + do { + if (--retry_limit < 0) { + pr_warn("afs_read_dir(): Too many retries\n"); + ret = -ESTALE; + break; + } + ret = afs_read_dir(dvnode, file); + if (ret < 0) { + if (ret != -ESTALE) + break; + if (test_bit(AFS_VNODE_DELETED, &AFS_FS_I(dir)->flags)) { + ret = -ESTALE; + break; + } + continue; + } + *_dir_version = inode_peek_iversion_raw(dir); + + ret = afs_dir_iterate_contents(dir, ctx); + up_read(&dvnode->validate_lock); + } while (ret == -ESTALE); -out: - up_read(&dvnode->validate_lock); - afs_put_read(req); _leave(" = %d", ret); return ret; } @@ -565,8 +557,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx) { afs_dataversion_t dir_version; - return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file), - &dir_version); + return afs_dir_iterate(file_inode(file), ctx, file, &dir_version); } /* @@ -607,7 +598,7 @@ static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, * - just returns the FID the dentry name maps to if found */ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, - struct afs_fid *fid, struct key *key, + struct afs_fid *fid, afs_dataversion_t *_dir_version) { struct afs_super_info *as = dir->i_sb->s_fs_info; @@ -621,7 +612,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); /* search the directory */ - ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version); + ret = afs_dir_iterate(dir, &cookie.ctx, NULL, _dir_version); if (ret < 0) { _leave(" = %d [iter]", ret); return ret; @@ -656,19 +647,10 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, BUILD_BUG_ON(sizeof(union afs_xdr_dir_block) != 2048); BUILD_BUG_ON(sizeof(union afs_xdr_dirent) != 32); - if (cookie->found) { - if (cookie->nr_fids < 50) { - cookie->fids[cookie->nr_fids].vnode = ino; - cookie->fids[cookie->nr_fids].unique = dtype; - cookie->nr_fids++; - } - } else if (cookie->name.len == nlen && - memcmp(cookie->name.name, name, nlen) == 0) { - cookie->fids[1].vnode = ino; - cookie->fids[1].unique = dtype; - cookie->found = 1; - if (cookie->one_only) - return false; + if (cookie->nr_fids < 50) { + cookie->fids[cookie->nr_fids].vnode = ino; + cookie->fids[cookie->nr_fids].unique = dtype; + cookie->nr_fids++; } return cookie->nr_fids < 50; @@ -788,8 +770,7 @@ static bool afs_server_supports_ibulk(struct afs_vnode *dvnode) * files in one go and create inodes for them. The inode of the file we were * asked for is returned. */ -static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, - struct key *key) +static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry) { struct afs_lookup_cookie *cookie; struct afs_vnode_param *vp; @@ -797,6 +778,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct inode *inode = NULL, *ti; afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version); + bool supports_ibulk; long ret; int i; @@ -813,19 +795,19 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->nr_fids = 2; /* slot 1 is saved for the fid we actually want * and slot 0 for the directory */ - if (!afs_server_supports_ibulk(dvnode)) - cookie->one_only = true; - - /* search the directory */ - ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version); + /* Search the directory for the named entry using the hash table... */ + ret = afs_dir_search(dvnode, &dentry->d_name, &cookie->fids[1], &data_version); if (ret < 0) goto out; - dentry->d_fsdata = (void *)(unsigned long)data_version; + supports_ibulk = afs_server_supports_ibulk(dvnode); + if (supports_ibulk) { + /* ...then scan linearly from that point for entries to lookup-ahead. */ + cookie->ctx.pos = (ret + 1) * AFS_DIR_DIRENT_SIZE; + afs_dir_iterate(dir, &cookie->ctx, NULL, &data_version); + } - ret = -ENOENT; - if (!cookie->found) - goto out; + dentry->d_fsdata = (void *)(unsigned long)data_version; /* Check to see if we already have an inode for the primary fid. */ inode = ilookup5(dir->i_sb, cookie->fids[1].vnode, @@ -884,7 +866,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, * the whole operation. */ afs_op_set_error(op, -ENOTSUPP); - if (!cookie->one_only) { + if (supports_ibulk) { op->ops = &afs_inline_bulk_status_operation; afs_begin_vnode_operation(op); afs_wait_for_operation(op); @@ -926,8 +908,7 @@ out: /* * Look up an entry in a directory with @sys substitution. */ -static struct dentry *afs_lookup_atsys(struct inode *dir, struct dentry *dentry, - struct key *key) +static struct dentry *afs_lookup_atsys(struct inode *dir, struct dentry *dentry) { struct afs_sysnames *subs; struct afs_net *net = afs_i2net(dir); @@ -975,7 +956,6 @@ out_s: afs_put_sysnames(subs); kfree(buf); out_p: - key_put(key); return ret; } @@ -989,7 +969,6 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, struct afs_fid fid = {}; struct inode *inode; struct dentry *d; - struct key *key; int ret; _enter("{%llx:%llu},%p{%pd},", @@ -1007,15 +986,9 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ESTALE); } - key = afs_request_key(dvnode->volume->cell); - if (IS_ERR(key)) { - _leave(" = %ld [key]", PTR_ERR(key)); - return ERR_CAST(key); - } - - ret = afs_validate(dvnode, key); + ret = afs_validate(dvnode, NULL); if (ret < 0) { - key_put(key); + afs_dir_unuse_cookie(dvnode, ret); _leave(" = %d [val]", ret); return ERR_PTR(ret); } @@ -1025,11 +998,10 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_name.name[dentry->d_name.len - 3] == 's' && dentry->d_name.name[dentry->d_name.len - 2] == 'y' && dentry->d_name.name[dentry->d_name.len - 1] == 's') - return afs_lookup_atsys(dir, dentry, key); + return afs_lookup_atsys(dir, dentry); afs_stat_v(dvnode, n_lookup); - inode = afs_do_lookup(dir, dentry, key); - key_put(key); + inode = afs_do_lookup(dir, dentry); if (inode == ERR_PTR(-ENOENT)) inode = afs_try_auto_mntpt(dentry, dir); @@ -1155,7 +1127,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) afs_stat_v(dir, n_reval); /* search the directory for this vnode */ - ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, key, &dir_version); + ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, &dir_version); switch (ret) { case 0: /* the filename maps to something */ @@ -1282,6 +1254,7 @@ void afs_check_for_remote_deletion(struct afs_operation *op) */ static void afs_vnode_new_inode(struct afs_operation *op) { + struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode_param *vp = &op->file[1]; struct afs_vnode *vnode; struct inode *inode; @@ -1301,6 +1274,10 @@ static void afs_vnode_new_inode(struct afs_operation *op) vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); + if (S_ISDIR(inode->i_mode)) + afs_mkdir_init_dir(vnode, dvp->vnode); + else if (S_ISLNK(inode->i_mode)) + afs_init_new_symlink(vnode, op); if (!afs_op_error(op)) afs_cache_permit(vnode, op->key, vnode->cb_break, &vp->scb); d_instantiate(op->dentry, inode); @@ -1317,18 +1294,21 @@ static void afs_create_success(struct afs_operation *op) static void afs_create_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources cres = {}; struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode_param *vp = &op->file[1]; struct afs_vnode *dvnode = dvp->vnode; _enter("op=%08x", op->debug_id); + fscache_begin_write_operation(&cres, afs_vnode_cache(dvnode)); down_write(&dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) afs_edit_dir_add(dvnode, &op->dentry->d_name, &vp->fid, op->create.reason); up_write(&dvnode->validate_lock); + fscache_end_operation(&cres); } static void afs_create_put(struct afs_operation *op) @@ -1356,6 +1336,7 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); + int ret; _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); @@ -1366,6 +1347,8 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, return PTR_ERR(op); } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1375,7 +1358,9 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, op->create.reason = afs_edit_dir_for_mkdir; op->mtime = current_time(dir); op->ops = &afs_mkdir_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; } /* @@ -1388,8 +1373,8 @@ static void afs_dir_remove_subdir(struct dentry *dentry) clear_nlink(&vnode->netfs.inode); set_bit(AFS_VNODE_DELETED, &vnode->flags); - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_clear_cb_promise(vnode, afs_cb_promise_clear_rmdir); + afs_invalidate_dir(vnode, afs_dir_invalid_subdir_removed); } } @@ -1403,18 +1388,21 @@ static void afs_rmdir_success(struct afs_operation *op) static void afs_rmdir_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources cres = {}; struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode *dvnode = dvp->vnode; _enter("op=%08x", op->debug_id); afs_dir_remove_subdir(op->dentry); + fscache_begin_write_operation(&cres, afs_vnode_cache(dvnode)); down_write(&dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) afs_edit_dir_remove(dvnode, &op->dentry->d_name, afs_edit_dir_for_rmdir); up_write(&dvnode->validate_lock); + fscache_end_operation(&cres); } static void afs_rmdir_put(struct afs_operation *op) @@ -1449,6 +1437,8 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) if (IS_ERR(op)) return PTR_ERR(op); + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1472,10 +1462,18 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) op->file[1].vnode = vnode; } - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + + /* Not all systems that can host afs servers have ENOTEMPTY. */ + if (ret == -EEXIST) + ret = -ENOTEMPTY; +out: + afs_dir_unuse_cookie(dvnode, ret); + return ret; error: - return afs_put_operation(op); + ret = afs_put_operation(op); + goto out; } /* @@ -1538,16 +1536,19 @@ static void afs_unlink_success(struct afs_operation *op) static void afs_unlink_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources cres = {}; struct afs_vnode_param *dvp = &op->file[0]; struct afs_vnode *dvnode = dvp->vnode; _enter("op=%08x", op->debug_id); + fscache_begin_write_operation(&cres, afs_vnode_cache(dvnode)); down_write(&dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && dvnode->status.data_version == dvp->dv_before + dvp->dv_delta) afs_edit_dir_remove(dvnode, &op->dentry->d_name, afs_edit_dir_for_unlink); up_write(&dvnode->validate_lock); + fscache_end_operation(&cres); } static void afs_unlink_put(struct afs_operation *op) @@ -1586,6 +1587,8 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) if (IS_ERR(op)) return PTR_ERR(op); + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1632,10 +1635,10 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) afs_wait_for_operation(op); } - return afs_put_operation(op); - error: - return afs_put_operation(op); + ret = afs_put_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; } static const struct afs_operation_ops afs_create_operation = { @@ -1669,6 +1672,8 @@ static int afs_create(struct mnt_idmap *idmap, struct inode *dir, goto error; } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; op->file[0].modification = true; @@ -1679,7 +1684,9 @@ static int afs_create(struct mnt_idmap *idmap, struct inode *dir, op->create.reason = afs_edit_dir_for_create; op->mtime = current_time(dir); op->ops = &afs_create_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; error: d_drop(dentry); @@ -1744,6 +1751,8 @@ static int afs_link(struct dentry *from, struct inode *dir, goto error; } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + ret = afs_validate(vnode, op->key); if (ret < 0) goto error_op; @@ -1759,10 +1768,13 @@ static int afs_link(struct dentry *from, struct inode *dir, op->dentry_2 = from; op->ops = &afs_link_operation; op->create.reason = afs_edit_dir_for_link; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; error_op: afs_put_operation(op); + afs_dir_unuse_cookie(dvnode, ret); error: d_drop(dentry); _leave(" = %d", ret); @@ -1806,6 +1818,8 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, goto error; } + fscache_use_cookie(afs_vnode_cache(dvnode), true); + afs_op_set_vnode(op, 0, dvnode); op->file[0].dv_delta = 1; @@ -1814,7 +1828,9 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, op->create.reason = afs_edit_dir_for_symlink; op->create.symlink = content; op->mtime = current_time(dir); - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + afs_dir_unuse_cookie(dvnode, ret); + return ret; error: d_drop(dentry); @@ -1846,6 +1862,7 @@ static void afs_rename_success(struct afs_operation *op) write_seqlock(&vnode->cb_lock); new_dv = vnode->status.data_version + 1; + trace_afs_set_dv(vnode, new_dv); vnode->status.data_version = new_dv; inode_set_iversion_raw(&vnode->netfs.inode, new_dv); @@ -1855,6 +1872,7 @@ static void afs_rename_success(struct afs_operation *op) static void afs_rename_edit_dir(struct afs_operation *op) { + struct netfs_cache_resources orig_cres = {}, new_cres = {}; struct afs_vnode_param *orig_dvp = &op->file[0]; struct afs_vnode_param *new_dvp = &op->file[1]; struct afs_vnode *orig_dvnode = orig_dvp->vnode; @@ -1871,6 +1889,10 @@ static void afs_rename_edit_dir(struct afs_operation *op) op->rename.rehash = NULL; } + fscache_begin_write_operation(&orig_cres, afs_vnode_cache(orig_dvnode)); + if (new_dvnode != orig_dvnode) + fscache_begin_write_operation(&new_cres, afs_vnode_cache(new_dvnode)); + down_write(&orig_dvnode->validate_lock); if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) && orig_dvnode->status.data_version == orig_dvp->dv_before + orig_dvp->dv_delta) @@ -1920,6 +1942,9 @@ static void afs_rename_edit_dir(struct afs_operation *op) d_move(old_dentry, new_dentry); up_write(&new_dvnode->validate_lock); + fscache_end_operation(&orig_cres); + if (new_dvnode != orig_dvnode) + fscache_end_operation(&new_cres); } static void afs_rename_put(struct afs_operation *op) @@ -1972,6 +1997,10 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (IS_ERR(op)) return PTR_ERR(op); + fscache_use_cookie(afs_vnode_cache(orig_dvnode), true); + if (new_dvnode != orig_dvnode) + fscache_use_cookie(afs_vnode_cache(new_dvnode), true); + ret = afs_validate(vnode, op->key); afs_op_set_error(op, ret); if (ret < 0) @@ -2039,47 +2068,43 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, */ d_drop(old_dentry); - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); +out: + afs_dir_unuse_cookie(orig_dvnode, ret); + if (new_dvnode != orig_dvnode) + afs_dir_unuse_cookie(new_dvnode, ret); + return ret; error: - return afs_put_operation(op); -} - -/* - * Release a directory folio and clean up its private state if it's not busy - * - return true if the folio can now be released, false if not - */ -static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags) -{ - struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - - _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio->index); - - folio_detach_private(folio); - - /* The directory will need reloading. */ - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_stat_v(dvnode, n_relpg); - return true; + ret = afs_put_operation(op); + goto out; } /* - * Invalidate part or all of a folio. + * Write the file contents to the cache as a single blob. */ -static void afs_dir_invalidate_folio(struct folio *folio, size_t offset, - size_t length) +int afs_single_writepages(struct address_space *mapping, + struct writeback_control *wbc) { - struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - - _enter("{%lu},%zu,%zu", folio->index, offset, length); - - BUG_ON(!folio_test_locked(folio)); + struct afs_vnode *dvnode = AFS_FS_I(mapping->host); + struct iov_iter iter; + bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) && + !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags)); + int ret = 0; - /* The directory will need reloading. */ - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_stat_v(dvnode, n_inval); + /* Need to lock to prevent the folio queue and folios from being thrown + * away. + */ + down_read(&dvnode->validate_lock); + + if (is_dir ? + test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) : + atomic64_read(&dvnode->cb_expires_at) != AFS_NO_CB_PROMISE) { + iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, + i_size_read(&dvnode->netfs.inode)); + ret = netfs_writeback_single(mapping, wbc, &iter); + } - /* we clean up only if the entire folio is being invalidated */ - if (offset == 0 && length == folio_size(folio)) - folio_detach_private(folio); + up_read(&dvnode->validate_lock); + return ret; } diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index fe223fb78111..60a549f1d9c5 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -10,6 +10,7 @@ #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/iversion.h> +#include <linux/folio_queue.h> #include "internal.h" #include "xdr_fs.h" @@ -105,23 +106,57 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block, } /* - * Get a new directory folio. + * Get a specific block, extending the directory storage to cover it as needed. */ -static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) +static union afs_xdr_dir_block *afs_dir_get_block(struct afs_dir_iter *iter, size_t block) { - struct address_space *mapping = vnode->netfs.inode.i_mapping; + struct folio_queue *fq; + struct afs_vnode *dvnode = iter->dvnode; struct folio *folio; + size_t blpos = block * AFS_DIR_BLOCK_SIZE; + size_t blend = (block + 1) * AFS_DIR_BLOCK_SIZE, fpos = iter->fpos; + int ret; + + if (dvnode->directory_size < blend) { + size_t cur_size = dvnode->directory_size; + + ret = netfs_alloc_folioq_buffer( + NULL, &dvnode->directory, &cur_size, blend, + mapping_gfp_mask(dvnode->netfs.inode.i_mapping)); + dvnode->directory_size = cur_size; + if (ret < 0) + goto fail; + } - folio = __filemap_get_folio(mapping, index, - FGP_LOCK | FGP_ACCESSED | FGP_CREAT, - mapping->gfp_mask); - if (IS_ERR(folio)) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - return NULL; + fq = iter->fq; + if (!fq) + fq = dvnode->directory; + + /* Search the folio queue for the folio containing the block... */ + for (; fq; fq = fq->next) { + for (int s = iter->fq_slot; s < folioq_count(fq); s++) { + size_t fsize = folioq_folio_size(fq, s); + + if (blend <= fpos + fsize) { + /* ... and then return the mapped block. */ + folio = folioq_folio(fq, s); + if (WARN_ON_ONCE(folio_pos(folio) != fpos)) + goto fail; + iter->fq = fq; + iter->fq_slot = s; + iter->fpos = fpos; + return kmap_local_folio(folio, blpos - fpos); + } + fpos += fsize; + } + iter->fq_slot = 0; } - if (!folio_test_private(folio)) - folio_attach_private(folio, (void *)1); - return folio; + +fail: + iter->fq = NULL; + iter->fq_slot = 0; + afs_invalidate_dir(dvnode, afs_dir_invalid_edit_get_block); + return NULL; } /* @@ -209,9 +244,8 @@ void afs_edit_dir_add(struct afs_vnode *vnode, { union afs_xdr_dir_block *meta, *block; union afs_xdr_dirent *de; - struct folio *folio0, *folio; - unsigned int need_slots, nr_blocks, b; - pgoff_t index; + struct afs_dir_iter iter = { .dvnode = vnode }; + unsigned int nr_blocks, b, entry; loff_t i_size; int slot; @@ -220,20 +254,17 @@ void afs_edit_dir_add(struct afs_vnode *vnode, i_size = i_size_read(&vnode->netfs.inode); if (i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS || (i_size & (AFS_DIR_BLOCK_SIZE - 1))) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_add_bad_size); return; } - folio0 = afs_dir_get_folio(vnode, 0); - if (!folio0) { - _leave(" [fgp]"); + meta = afs_dir_get_block(&iter, 0); + if (!meta) return; - } /* Work out how many slots we're going to need. */ - need_slots = afs_dir_calc_slots(name->len); + iter.nr_slots = afs_dir_calc_slots(name->len); - meta = kmap_local_folio(folio0, 0); if (i_size == 0) goto new_directory; nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; @@ -245,22 +276,21 @@ void afs_edit_dir_add(struct afs_vnode *vnode, /* If the directory extended into a new folio, then we need to * tack a new folio on the end. */ - index = b / AFS_DIR_BLOCKS_PER_PAGE; if (nr_blocks >= AFS_DIR_MAX_BLOCKS) - goto error; - if (index >= folio_nr_pages(folio0)) { - folio = afs_dir_get_folio(vnode, index); - if (!folio) - goto error; - } else { - folio = folio0; - } + goto error_too_many_blocks; - block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); + /* Lower dir blocks have a counter in the header we can check. */ + if (b < AFS_DIR_BLOCKS_WITH_CTR && + meta->meta.alloc_ctrs[b] < iter.nr_slots) + continue; + + block = afs_dir_get_block(&iter, b); + if (!block) + goto error; /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - goto invalidated; + goto already_invalidated; _debug("block %u: %2u %3u %u", b, @@ -275,31 +305,23 @@ void afs_edit_dir_add(struct afs_vnode *vnode, afs_set_i_size(vnode, (b + 1) * AFS_DIR_BLOCK_SIZE); } - /* Only lower dir blocks have a counter in the header. */ - if (b >= AFS_DIR_BLOCKS_WITH_CTR || - meta->meta.alloc_ctrs[b] >= need_slots) { - /* We need to try and find one or more consecutive - * slots to hold the entry. - */ - slot = afs_find_contig_bits(block, need_slots); - if (slot >= 0) { - _debug("slot %u", slot); - goto found_space; - } + /* We need to try and find one or more consecutive slots to + * hold the entry. + */ + slot = afs_find_contig_bits(block, iter.nr_slots); + if (slot >= 0) { + _debug("slot %u", slot); + goto found_space; } kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } } /* There are no spare slots of sufficient size, yet the operation * succeeded. Download the directory again. */ trace_afs_edit_dir(vnode, why, afs_edit_dir_create_nospc, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_add_no_slots); goto out_unmap; new_directory: @@ -307,8 +329,7 @@ new_directory: i_size = AFS_DIR_BLOCK_SIZE; afs_set_i_size(vnode, i_size); slot = AFS_DIR_RESV_BLOCKS0; - folio = folio0; - block = kmap_local_folio(folio, 0); + block = afs_dir_get_block(&iter, 0); nr_blocks = 1; b = 0; @@ -326,41 +347,39 @@ found_space: de->u.name[name->len] = 0; /* Adjust the bitmap. */ - afs_set_contig_bits(block, slot, need_slots); - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } + afs_set_contig_bits(block, slot, iter.nr_slots); /* Adjust the allocation counter. */ if (b < AFS_DIR_BLOCKS_WITH_CTR) - meta->meta.alloc_ctrs[b] -= need_slots; + meta->meta.alloc_ctrs[b] -= iter.nr_slots; + + /* Adjust the hash chain. */ + entry = b * AFS_DIR_SLOTS_PER_BLOCK + slot; + iter.bucket = afs_dir_hash_name(name); + de->u.hash_next = meta->meta.hashtable[iter.bucket]; + meta->meta.hashtable[iter.bucket] = htons(entry); + kunmap_local(block); inode_inc_iversion_raw(&vnode->netfs.inode); afs_stat_v(vnode, n_dir_cr); _debug("Insert %s in %u[%u]", name->name, b, slot); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); + out_unmap: kunmap_local(meta); - folio_unlock(folio0); - folio_put(folio0); _leave(""); return; -invalidated: +already_invalidated: trace_afs_edit_dir(vnode, why, afs_edit_dir_create_inval, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } goto out_unmap; +error_too_many_blocks: + afs_invalidate_dir(vnode, afs_dir_invalid_edit_add_too_many_blocks); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_create_error, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out_unmap; } @@ -374,13 +393,14 @@ error: void afs_edit_dir_remove(struct afs_vnode *vnode, struct qstr *name, enum afs_edit_dir_reason why) { - union afs_xdr_dir_block *meta, *block; - union afs_xdr_dirent *de; - struct folio *folio0, *folio; - unsigned int need_slots, nr_blocks, b; - pgoff_t index; + union afs_xdr_dir_block *meta, *block, *pblock; + union afs_xdr_dirent *de, *pde; + struct afs_dir_iter iter = { .dvnode = vnode }; + struct afs_fid fid; + unsigned int b, slot, entry; loff_t i_size; - int slot; + __be16 next; + int found; _enter(",,{%d,%s},", name->len, name->name); @@ -388,81 +408,95 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, if (i_size < AFS_DIR_BLOCK_SIZE || i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS || (i_size & (AFS_DIR_BLOCK_SIZE - 1))) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_rem_bad_size); return; } - nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; - folio0 = afs_dir_get_folio(vnode, 0); - if (!folio0) { - _leave(" [fgp]"); + if (!afs_dir_init_iter(&iter, name)) return; - } - - /* Work out how many slots we're going to discard. */ - need_slots = afs_dir_calc_slots(name->len); - - meta = kmap_local_folio(folio0, 0); - - /* Find a block that has sufficient slots available. Each folio - * contains two or more directory blocks. - */ - for (b = 0; b < nr_blocks; b++) { - index = b / AFS_DIR_BLOCKS_PER_PAGE; - if (index >= folio_nr_pages(folio0)) { - folio = afs_dir_get_folio(vnode, index); - if (!folio) - goto error; - } else { - folio = folio0; - } - block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); - - /* Abandon the edit if we got a callback break. */ - if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - goto invalidated; - - if (b > AFS_DIR_BLOCKS_WITH_CTR || - meta->meta.alloc_ctrs[b] <= AFS_DIR_SLOTS_PER_BLOCK - 1 - need_slots) { - slot = afs_dir_scan_block(block, name, b); - if (slot >= 0) - goto found_dirent; - } + meta = afs_dir_find_block(&iter, 0); + if (!meta) + return; - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } + /* Find the entry in the blob. */ + found = afs_dir_search_bucket(&iter, name, &fid); + if (found < 0) { + /* Didn't find the dirent to clobber. Re-download. */ + trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_noent, + 0, 0, 0, 0, name->name); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_rem_wrong_name); + goto out_unmap; } - /* Didn't find the dirent to clobber. Download the directory again. */ - trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_noent, - 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - goto out_unmap; + entry = found; + b = entry / AFS_DIR_SLOTS_PER_BLOCK; + slot = entry % AFS_DIR_SLOTS_PER_BLOCK; -found_dirent: + block = afs_dir_find_block(&iter, b); + if (!block) + goto error; + if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + goto already_invalidated; + + /* Check and clear the entry. */ de = &block->dirents[slot]; + if (de->u.valid != 1) + goto error_unmap; trace_afs_edit_dir(vnode, why, afs_edit_dir_delete, b, slot, ntohl(de->u.vnode), ntohl(de->u.unique), name->name); - memset(de, 0, sizeof(*de) * need_slots); - /* Adjust the bitmap. */ - afs_clear_contig_bits(block, slot, need_slots); - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } + afs_clear_contig_bits(block, slot, iter.nr_slots); /* Adjust the allocation counter. */ if (b < AFS_DIR_BLOCKS_WITH_CTR) - meta->meta.alloc_ctrs[b] += need_slots; + meta->meta.alloc_ctrs[b] += iter.nr_slots; + + /* Clear the constituent entries. */ + next = de->u.hash_next; + memset(de, 0, sizeof(*de) * iter.nr_slots); + kunmap_local(block); + + /* Adjust the hash chain: if iter->prev_entry is 0, the hashtable head + * index is previous; otherwise it's slot number of the previous entry. + */ + if (!iter.prev_entry) { + __be16 prev_next = meta->meta.hashtable[iter.bucket]; + + if (unlikely(prev_next != htons(entry))) { + pr_warn("%llx:%llx:%x: not head of chain b=%x p=%x,%x e=%x %*s", + vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, + iter.bucket, iter.prev_entry, prev_next, entry, + name->len, name->name); + goto error; + } + meta->meta.hashtable[iter.bucket] = next; + } else { + unsigned int pb = iter.prev_entry / AFS_DIR_SLOTS_PER_BLOCK; + unsigned int ps = iter.prev_entry % AFS_DIR_SLOTS_PER_BLOCK; + __be16 prev_next; + + pblock = afs_dir_find_block(&iter, pb); + if (!pblock) + goto error; + pde = &pblock->dirents[ps]; + prev_next = pde->u.hash_next; + if (prev_next != htons(entry)) { + kunmap_local(pblock); + pr_warn("%llx:%llx:%x: not prev in chain b=%x p=%x,%x e=%x %*s", + vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, + iter.bucket, iter.prev_entry, prev_next, entry, + name->len, name->name); + goto error; + } + pde->u.hash_next = next; + kunmap_local(pblock); + } + + netfs_single_mark_inode_dirty(&vnode->netfs.inode); inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version); afs_stat_v(vnode, n_dir_rm); @@ -470,26 +504,20 @@ found_dirent: out_unmap: kunmap_local(meta); - folio_unlock(folio0); - folio_put(folio0); _leave(""); return; -invalidated: +already_invalidated: + kunmap_local(block); trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - kunmap_local(block); - if (folio != folio0) { - folio_unlock(folio); - folio_put(folio); - } goto out_unmap; +error_unmap: + kunmap_local(block); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_error, 0, 0, 0, 0, name->name); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out_unmap; } @@ -502,9 +530,8 @@ void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_d { union afs_xdr_dir_block *block; union afs_xdr_dirent *de; - struct folio *folio; + struct afs_dir_iter iter = { .dvnode = vnode }; unsigned int nr_blocks, b; - pgoff_t index; loff_t i_size; int slot; @@ -512,39 +539,35 @@ void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_d i_size = i_size_read(&vnode->netfs.inode); if (i_size < AFS_DIR_BLOCK_SIZE) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_upd_bad_size); return; } + nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; /* Find a block that has sufficient slots available. Each folio * contains two or more directory blocks. */ for (b = 0; b < nr_blocks; b++) { - index = b / AFS_DIR_BLOCKS_PER_PAGE; - folio = afs_dir_get_folio(vnode, index); - if (!folio) + block = afs_dir_get_block(&iter, b); + if (!block) goto error; - block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); - /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - goto invalidated; + goto already_invalidated; slot = afs_dir_scan_block(block, &dotdot_name, b); if (slot >= 0) goto found_dirent; kunmap_local(block); - folio_unlock(folio); - folio_put(folio); } /* Didn't find the dirent to clobber. Download the directory again. */ trace_afs_edit_dir(vnode, why, afs_edit_dir_update_nodd, 0, 0, 0, 0, ".."); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + afs_invalidate_dir(vnode, afs_dir_invalid_edit_upd_no_dd); goto out; found_dirent: @@ -556,26 +579,70 @@ found_dirent: ntohl(de->u.vnode), ntohl(de->u.unique), ".."); kunmap_local(block); - folio_unlock(folio); - folio_put(folio); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version); out: _leave(""); return; -invalidated: +already_invalidated: kunmap_local(block); - folio_unlock(folio); - folio_put(folio); trace_afs_edit_dir(vnode, why, afs_edit_dir_update_inval, 0, 0, 0, 0, ".."); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out; error: trace_afs_edit_dir(vnode, why, afs_edit_dir_update_error, 0, 0, 0, 0, ".."); - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out; } + +/* + * Initialise a new directory. We need to fill in the "." and ".." entries. + */ +void afs_mkdir_init_dir(struct afs_vnode *dvnode, struct afs_vnode *parent_dvnode) +{ + union afs_xdr_dir_block *meta; + struct afs_dir_iter iter = { .dvnode = dvnode }; + union afs_xdr_dirent *de; + unsigned int slot = AFS_DIR_RESV_BLOCKS0; + loff_t i_size; + + i_size = i_size_read(&dvnode->netfs.inode); + if (i_size != AFS_DIR_BLOCK_SIZE) { + afs_invalidate_dir(dvnode, afs_dir_invalid_edit_add_bad_size); + return; + } + + meta = afs_dir_get_block(&iter, 0); + if (!meta) + return; + + afs_edit_init_block(meta, meta, 0); + + de = &meta->dirents[slot]; + de->u.valid = 1; + de->u.vnode = htonl(dvnode->fid.vnode); + de->u.unique = htonl(dvnode->fid.unique); + memcpy(de->u.name, ".", 2); + trace_afs_edit_dir(dvnode, afs_edit_dir_for_mkdir, afs_edit_dir_mkdir, 0, slot, + dvnode->fid.vnode, dvnode->fid.unique, "."); + slot++; + + de = &meta->dirents[slot]; + de->u.valid = 1; + de->u.vnode = htonl(parent_dvnode->fid.vnode); + de->u.unique = htonl(parent_dvnode->fid.unique); + memcpy(de->u.name, "..", 3); + trace_afs_edit_dir(dvnode, afs_edit_dir_for_mkdir, afs_edit_dir_mkdir, 0, slot, + parent_dvnode->fid.vnode, parent_dvnode->fid.unique, ".."); + + afs_set_contig_bits(meta, AFS_DIR_RESV_BLOCKS0, 2); + meta->meta.alloc_ctrs[0] -= 2; + kunmap_local(meta); + + netfs_single_mark_inode_dirty(&dvnode->netfs.inode); + set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags); + set_bit(AFS_VNODE_DIR_READ, &dvnode->flags); +} diff --git a/fs/afs/dir_search.c b/fs/afs/dir_search.c new file mode 100644 index 000000000000..b25bd892db4d --- /dev/null +++ b/fs/afs/dir_search.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Search a directory's hash table. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * https://tools.ietf.org/html/draft-keiser-afs3-directory-object-00 + */ + +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/iversion.h> +#include "internal.h" +#include "afs_fs.h" +#include "xdr_fs.h" + +/* + * Calculate the name hash. + */ +unsigned int afs_dir_hash_name(const struct qstr *name) +{ + const unsigned char *p = name->name; + unsigned int hash = 0, i; + int bucket; + + for (i = 0; i < name->len; i++) + hash = (hash * 173) + p[i]; + bucket = hash & (AFS_DIR_HASHTBL_SIZE - 1); + if (hash > INT_MAX) { + bucket = AFS_DIR_HASHTBL_SIZE - bucket; + bucket &= (AFS_DIR_HASHTBL_SIZE - 1); + } + return bucket; +} + +/* + * Reset a directory iterator. + */ +static bool afs_dir_reset_iter(struct afs_dir_iter *iter) +{ + unsigned long long i_size = i_size_read(&iter->dvnode->netfs.inode); + unsigned int nblocks; + + /* Work out the maximum number of steps we can take. */ + nblocks = umin(i_size / AFS_DIR_BLOCK_SIZE, AFS_DIR_MAX_BLOCKS); + if (!nblocks) + return false; + iter->loop_check = nblocks * (AFS_DIR_SLOTS_PER_BLOCK - AFS_DIR_RESV_BLOCKS); + iter->prev_entry = 0; /* Hash head is previous */ + return true; +} + +/* + * Initialise a directory iterator for looking up a name. + */ +bool afs_dir_init_iter(struct afs_dir_iter *iter, const struct qstr *name) +{ + iter->nr_slots = afs_dir_calc_slots(name->len); + iter->bucket = afs_dir_hash_name(name); + return afs_dir_reset_iter(iter); +} + +/* + * Get a specific block. + */ +union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t block) +{ + struct folio_queue *fq = iter->fq; + struct afs_vnode *dvnode = iter->dvnode; + struct folio *folio; + size_t blpos = block * AFS_DIR_BLOCK_SIZE; + size_t blend = (block + 1) * AFS_DIR_BLOCK_SIZE, fpos = iter->fpos; + int slot = iter->fq_slot; + + _enter("%zx,%d", block, slot); + + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } + + if (dvnode->directory_size < blend) + goto fail; + + if (!fq || blpos < fpos) { + fq = dvnode->directory; + slot = 0; + fpos = 0; + } + + /* Search the folio queue for the folio containing the block... */ + for (; fq; fq = fq->next) { + for (; slot < folioq_count(fq); slot++) { + size_t fsize = folioq_folio_size(fq, slot); + + if (blend <= fpos + fsize) { + /* ... and then return the mapped block. */ + folio = folioq_folio(fq, slot); + if (WARN_ON_ONCE(folio_pos(folio) != fpos)) + goto fail; + iter->fq = fq; + iter->fq_slot = slot; + iter->fpos = fpos; + iter->block = kmap_local_folio(folio, blpos - fpos); + return iter->block; + } + fpos += fsize; + } + slot = 0; + } + +fail: + iter->fq = NULL; + iter->fq_slot = 0; + afs_invalidate_dir(dvnode, afs_dir_invalid_edit_get_block); + return NULL; +} + +/* + * Search through a directory bucket. + */ +int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, + struct afs_fid *_fid) +{ + const union afs_xdr_dir_block *meta; + unsigned int entry; + int ret = -ESTALE; + + meta = afs_dir_find_block(iter, 0); + if (!meta) + return -ESTALE; + + entry = ntohs(meta->meta.hashtable[iter->bucket & (AFS_DIR_HASHTBL_SIZE - 1)]); + _enter("%x,%x", iter->bucket, entry); + + while (entry) { + const union afs_xdr_dir_block *block; + const union afs_xdr_dirent *dire; + unsigned int blnum = entry / AFS_DIR_SLOTS_PER_BLOCK; + unsigned int slot = entry % AFS_DIR_SLOTS_PER_BLOCK; + unsigned int resv = (blnum == 0 ? AFS_DIR_RESV_BLOCKS0 : AFS_DIR_RESV_BLOCKS); + + _debug("search %x", entry); + + if (slot < resv) { + kdebug("slot out of range h=%x rs=%2x sl=%2x-%2x", + iter->bucket, resv, slot, slot + iter->nr_slots - 1); + goto bad; + } + + block = afs_dir_find_block(iter, blnum); + if (!block) + goto bad; + dire = &block->dirents[slot]; + + if (slot + iter->nr_slots <= AFS_DIR_SLOTS_PER_BLOCK && + memcmp(dire->u.name, name->name, name->len) == 0 && + dire->u.name[name->len] == '\0') { + _fid->vnode = ntohl(dire->u.vnode); + _fid->unique = ntohl(dire->u.unique); + ret = entry; + goto found; + } + + iter->prev_entry = entry; + entry = ntohs(dire->u.hash_next); + if (!--iter->loop_check) { + kdebug("dir chain loop h=%x", iter->bucket); + goto bad; + } + } + + ret = -ENOENT; +found: + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } + +bad: + if (ret == -ESTALE) + afs_invalidate_dir(iter->dvnode, afs_dir_invalid_iter_stale); + _leave(" = %d", ret); + return ret; +} + +/* + * Search the appropriate hash chain in the contents of an AFS directory. + */ +int afs_dir_search(struct afs_vnode *dvnode, struct qstr *name, + struct afs_fid *_fid, afs_dataversion_t *_dir_version) +{ + struct afs_dir_iter iter = { .dvnode = dvnode, }; + int ret, retry_limit = 3; + + _enter("{%lu},,,", dvnode->netfs.inode.i_ino); + + if (!afs_dir_init_iter(&iter, name)) + return -ENOENT; + do { + if (--retry_limit < 0) { + pr_warn("afs_read_dir(): Too many retries\n"); + ret = -ESTALE; + break; + } + ret = afs_read_dir(dvnode, NULL); + if (ret < 0) { + if (ret != -ESTALE) + break; + if (test_bit(AFS_VNODE_DELETED, &dvnode->flags)) { + ret = -ESTALE; + break; + } + continue; + } + *_dir_version = inode_peek_iversion_raw(&dvnode->netfs.inode); + + ret = afs_dir_search_bucket(&iter, name, _fid); + up_read(&dvnode->validate_lock); + if (ret == -ESTALE) + afs_dir_reset_iter(&iter); + } while (ret == -ESTALE); + + _leave(" = %d", ret); + return ret; +} diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index c4d2711e20ad..d8bf52f77d93 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -186,50 +186,6 @@ out: } /* - * Look up @cell in a dynroot directory. This is a substitution for the - * local cell name for the net namespace. - */ -static struct dentry *afs_lookup_atcell(struct dentry *dentry) -{ - struct afs_cell *cell; - struct afs_net *net = afs_d2net(dentry); - struct dentry *ret; - char *name; - int len; - - if (!net->ws_cell) - return ERR_PTR(-ENOENT); - - ret = ERR_PTR(-ENOMEM); - name = kmalloc(AFS_MAXCELLNAME + 1, GFP_KERNEL); - if (!name) - goto out_p; - - down_read(&net->cells_lock); - cell = net->ws_cell; - if (cell) { - len = cell->name_len; - memcpy(name, cell->name, len + 1); - } - up_read(&net->cells_lock); - - ret = ERR_PTR(-ENOENT); - if (!cell) - goto out_n; - - ret = lookup_one_len(name, dentry->d_parent, len); - - /* We don't want to d_add() the @cell dentry here as we don't want to - * the cached dentry to hide changes to the local cell name. - */ - -out_n: - kfree(name); -out_p: - return ret; -} - -/* * Look up an entry in a dynroot directory. */ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry, @@ -247,10 +203,6 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr return ERR_PTR(-ENAMETOOLONG); } - if (dentry->d_name.len == 5 && - memcmp(dentry->d_name.name, "@cell", 5) == 0) - return afs_lookup_atcell(dentry); - return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry); } @@ -271,7 +223,8 @@ const struct dentry_operations afs_dynroot_dentry_operations = { int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; - struct dentry *root, *subdir; + struct dentry *root, *subdir, *dsubdir; + char *dotname = cell->name - 1; int ret; if (!sb || atomic_read(&sb->s_active) == 0) @@ -286,14 +239,43 @@ int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell) goto unlock; } - /* Note that we're retaining an extra ref on the dentry */ + dsubdir = lookup_one_len(dotname, root, cell->name_len + 1); + if (IS_ERR(dsubdir)) { + ret = PTR_ERR(dsubdir); + dput(subdir); + goto unlock; + } + + /* Note that we're retaining extra refs on the dentries. */ subdir->d_fsdata = (void *)1UL; + dsubdir->d_fsdata = (void *)1UL; ret = 0; unlock: inode_unlock(root->d_inode); return ret; } +static void afs_dynroot_rm_one_dir(struct dentry *root, const char *name, size_t name_len) +{ + struct dentry *subdir; + + /* Don't want to trigger a lookup call, which will re-add the cell */ + subdir = try_lookup_one_len(name, root, name_len); + if (IS_ERR_OR_NULL(subdir)) { + _debug("lookup %ld", PTR_ERR(subdir)); + return; + } + + _debug("rmdir %pd %u", subdir, d_count(subdir)); + + if (subdir->d_fsdata) { + _debug("unpin %u", d_count(subdir)); + subdir->d_fsdata = NULL; + dput(subdir); + } + dput(subdir); +} + /* * Remove a manually added cell mount directory. * - The caller must hold net->proc_cells_lock @@ -301,32 +283,141 @@ unlock: void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; - struct dentry *root, *subdir; + char *dotname = cell->name - 1; if (!sb || atomic_read(&sb->s_active) == 0) return; - root = sb->s_root; - inode_lock(root->d_inode); + inode_lock(sb->s_root->d_inode); + afs_dynroot_rm_one_dir(sb->s_root, cell->name, cell->name_len); + afs_dynroot_rm_one_dir(sb->s_root, dotname, cell->name_len + 1); + inode_unlock(sb->s_root->d_inode); + _leave(""); +} - /* Don't want to trigger a lookup call, which will re-add the cell */ - subdir = try_lookup_one_len(cell->name, root, cell->name_len); - if (IS_ERR_OR_NULL(subdir)) { - _debug("lookup %ld", PTR_ERR(subdir)); - goto no_dentry; +static void afs_atcell_delayed_put_cell(void *arg) +{ + struct afs_cell *cell = arg; + + afs_put_cell(cell, afs_cell_trace_put_atcell); +} + +/* + * Read @cell or .@cell symlinks. + */ +static const char *afs_atcell_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_cell *cell; + struct afs_net *net = afs_i2net(inode); + const char *name; + bool dotted = vnode->fid.vnode == 3; + + if (!net->ws_cell) + return ERR_PTR(-ENOENT); + + down_read(&net->cells_lock); + + cell = net->ws_cell; + if (dotted) + name = cell->name - 1; + else + name = cell->name; + afs_get_cell(cell, afs_cell_trace_get_atcell); + set_delayed_call(done, afs_atcell_delayed_put_cell, cell); + + up_read(&net->cells_lock); + return name; +} + +static const struct inode_operations afs_atcell_inode_operations = { + .get_link = afs_atcell_get_link, +}; + +/* + * Look up @cell or .@cell in a dynroot directory. This is a substitution for + * the local cell name for the net namespace. + */ +static struct dentry *afs_dynroot_create_symlink(struct dentry *root, const char *name) +{ + struct afs_vnode *vnode; + struct afs_fid fid = { .vnode = 2, .unique = 1, }; + struct dentry *dentry; + struct inode *inode; + + if (name[0] == '.') + fid.vnode = 3; + + dentry = d_alloc_name(root, name); + if (!dentry) + return ERR_PTR(-ENOMEM); + + inode = iget5_locked(dentry->d_sb, fid.vnode, + afs_iget5_pseudo_test, afs_iget5_pseudo_set, &fid); + if (!inode) { + dput(dentry); + return ERR_PTR(-ENOMEM); } - _debug("rmdir %pd %u", subdir, d_count(subdir)); + vnode = AFS_FS_I(inode); - if (subdir->d_fsdata) { - _debug("unpin %u", d_count(subdir)); - subdir->d_fsdata = NULL; - dput(subdir); + /* there shouldn't be an existing inode */ + if (WARN_ON_ONCE(!(inode->i_state & I_NEW))) { + iput(inode); + dput(dentry); + return ERR_PTR(-EIO); } - dput(subdir); -no_dentry: + + netfs_inode_init(&vnode->netfs, NULL, false); + simple_inode_init_ts(inode); + set_nlink(inode, 1); + inode->i_size = 0; + inode->i_mode = S_IFLNK | 0555; + inode->i_op = &afs_atcell_inode_operations; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + inode->i_blocks = 0; + inode->i_generation = 0; + inode->i_flags |= S_NOATIME; + + unlock_new_inode(inode); + d_splice_alias(inode, dentry); + return dentry; +} + +/* + * Create @cell and .@cell symlinks. + */ +static int afs_dynroot_symlink(struct afs_net *net) +{ + struct super_block *sb = net->dynroot_sb; + struct dentry *root, *symlink, *dsymlink; + int ret; + + /* Let the ->lookup op do the creation */ + root = sb->s_root; + inode_lock(root->d_inode); + symlink = afs_dynroot_create_symlink(root, "@cell"); + if (IS_ERR(symlink)) { + ret = PTR_ERR(symlink); + goto unlock; + } + + dsymlink = afs_dynroot_create_symlink(root, ".@cell"); + if (IS_ERR(dsymlink)) { + ret = PTR_ERR(dsymlink); + dput(symlink); + goto unlock; + } + + /* Note that we're retaining extra refs on the dentries. */ + symlink->d_fsdata = (void *)1UL; + dsymlink->d_fsdata = (void *)1UL; + ret = 0; +unlock: inode_unlock(root->d_inode); - _leave(""); + return ret; } /* @@ -341,6 +432,10 @@ int afs_dynroot_populate(struct super_block *sb) mutex_lock(&net->proc_cells_lock); net->dynroot_sb = sb; + ret = afs_dynroot_symlink(net); + if (ret < 0) + goto error; + hlist_for_each_entry(cell, &net->proc_cells, proc_link) { ret = afs_dynroot_mkdir(net, cell); if (ret < 0) diff --git a/fs/afs/file.c b/fs/afs/file.c index 6762eff97517..fc15497608c6 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -20,7 +20,6 @@ #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); -static int afs_symlink_read_folio(struct file *file, struct folio *folio); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos, @@ -61,13 +60,6 @@ const struct address_space_operations afs_file_aops = { .writepages = afs_writepages, }; -const struct address_space_operations afs_symlink_aops = { - .read_folio = afs_symlink_read_folio, - .release_folio = netfs_release_folio, - .invalidate_folio = netfs_invalidate_folio, - .migrate_folio = filemap_migrate_folio, -}; - static const struct vm_operations_struct afs_vm_ops = { .open = afs_vm_open, .close = afs_vm_close, @@ -208,49 +200,12 @@ int afs_release(struct inode *inode, struct file *file) return ret; } -/* - * Allocate a new read record. - */ -struct afs_read *afs_alloc_read(gfp_t gfp) -{ - struct afs_read *req; - - req = kzalloc(sizeof(struct afs_read), gfp); - if (req) - refcount_set(&req->usage, 1); - - return req; -} - -/* - * Dispose of a ref to a read record. - */ -void afs_put_read(struct afs_read *req) -{ - if (refcount_dec_and_test(&req->usage)) { - if (req->cleanup) - req->cleanup(req); - key_put(req->key); - kfree(req); - } -} - static void afs_fetch_data_notify(struct afs_operation *op) { - struct afs_read *req = op->fetch.req; - struct netfs_io_subrequest *subreq = req->subreq; - int error = afs_op_error(op); - - req->error = error; - if (subreq) { - subreq->rreq->i_size = req->file_size; - if (req->pos + req->actual_len >= req->file_size) - __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - netfs_read_subreq_terminated(subreq, error, false); - req->subreq = NULL; - } else if (req->done) { - req->done(req); - } + struct netfs_io_subrequest *subreq = op->fetch.subreq; + + subreq->error = afs_op_error(op); + netfs_read_subreq_terminated(subreq); } static void afs_fetch_data_success(struct afs_operation *op) @@ -260,7 +215,7 @@ static void afs_fetch_data_success(struct afs_operation *op) _enter("op=%08x", op->debug_id); afs_vnode_commit_status(op, &op->file[0]); afs_stat_v(vnode, n_fetches); - atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes); + atomic_long_add(op->fetch.subreq->transferred, &op->net->n_fetch_bytes); afs_fetch_data_notify(op); } @@ -270,107 +225,188 @@ static void afs_fetch_data_aborted(struct afs_operation *op) afs_fetch_data_notify(op); } -static void afs_fetch_data_put(struct afs_operation *op) -{ - op->fetch.req->error = afs_op_error(op); - afs_put_read(op->fetch.req); -} - -static const struct afs_operation_ops afs_fetch_data_operation = { +const struct afs_operation_ops afs_fetch_data_operation = { .issue_afs_rpc = afs_fs_fetch_data, .issue_yfs_rpc = yfs_fs_fetch_data, .success = afs_fetch_data_success, .aborted = afs_fetch_data_aborted, .failed = afs_fetch_data_notify, - .put = afs_fetch_data_put, }; +static void afs_issue_read_call(struct afs_operation *op) +{ + op->call_responded = false; + op->call_error = 0; + op->call_abort_code = 0; + if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags)) + yfs_fs_fetch_data(op); + else + afs_fs_fetch_data(op); +} + +static void afs_end_read(struct afs_operation *op) +{ + if (op->call_responded && op->server) + set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags); + + if (!afs_op_error(op)) + afs_fetch_data_success(op); + else if (op->cumul_error.aborted) + afs_fetch_data_aborted(op); + else + afs_fetch_data_notify(op); + + afs_end_vnode_operation(op); + afs_put_operation(op); +} + +/* + * Perform I/O processing on an asynchronous call. The work item carries a ref + * to the call struct that we either need to release or to pass on. + */ +static void afs_read_receive(struct afs_call *call) +{ + struct afs_operation *op = call->op; + enum afs_call_state state; + + _enter(""); + + state = READ_ONCE(call->state); + if (state == AFS_CALL_COMPLETE) + return; + trace_afs_read_recv(op, call); + + while (state < AFS_CALL_COMPLETE && READ_ONCE(call->need_attention)) { + WRITE_ONCE(call->need_attention, false); + afs_deliver_to_call(call); + state = READ_ONCE(call->state); + } + + if (state < AFS_CALL_COMPLETE) { + netfs_read_subreq_progress(op->fetch.subreq); + if (rxrpc_kernel_check_life(call->net->socket, call->rxcall)) + return; + /* rxrpc terminated the call. */ + afs_set_call_complete(call, call->error, call->abort_code); + } + + op->call_abort_code = call->abort_code; + op->call_error = call->error; + op->call_responded = call->responded; + op->call = NULL; + call->op = NULL; + afs_put_call(call); + + /* If the call failed, then we need to crank the server rotation + * handle and try the next. + */ + if (afs_select_fileserver(op)) { + afs_issue_read_call(op); + return; + } + + afs_end_read(op); +} + +void afs_fetch_data_async_rx(struct work_struct *work) +{ + struct afs_call *call = container_of(work, struct afs_call, async_work); + + afs_read_receive(call); + afs_put_call(call); +} + +void afs_fetch_data_immediate_cancel(struct afs_call *call) +{ + if (call->async) { + afs_get_call(call, afs_call_trace_wake); + if (!queue_work(afs_async_calls, &call->async_work)) + afs_deferred_put_call(call); + flush_work(&call->async_work); + } +} + /* * Fetch file data from the volume. */ -int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) +static void afs_issue_read(struct netfs_io_subrequest *subreq) { struct afs_operation *op; + struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); + struct key *key = subreq->rreq->netfs_priv; _enter("%s{%llx:%llu.%u},%x,,,", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, - key_serial(req->key)); + key_serial(key)); - op = afs_alloc_operation(req->key, vnode->volume); + op = afs_alloc_operation(key, vnode->volume); if (IS_ERR(op)) { - if (req->subreq) - netfs_read_subreq_terminated(req->subreq, PTR_ERR(op), false); - return PTR_ERR(op); + subreq->error = PTR_ERR(op); + netfs_read_subreq_terminated(subreq); + return; } afs_op_set_vnode(op, 0, vnode); - op->fetch.req = afs_get_read(req); + op->fetch.subreq = subreq; op->ops = &afs_fetch_data_operation; - return afs_do_sync_operation(op); -} - -static void afs_read_worker(struct work_struct *work) -{ - struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work); - struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); - struct afs_read *fsreq; - - fsreq = afs_alloc_read(GFP_NOFS); - if (!fsreq) - return netfs_read_subreq_terminated(subreq, -ENOMEM, false); - - fsreq->subreq = subreq; - fsreq->pos = subreq->start + subreq->transferred; - fsreq->len = subreq->len - subreq->transferred; - fsreq->key = key_get(subreq->rreq->netfs_priv); - fsreq->vnode = vnode; - fsreq->iter = &subreq->io_iter; trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - afs_fetch_data(fsreq->vnode, fsreq); - afs_put_read(fsreq); -} - -static void afs_issue_read(struct netfs_io_subrequest *subreq) -{ - INIT_WORK(&subreq->work, afs_read_worker); - queue_work(system_long_wq, &subreq->work); -} -static int afs_symlink_read_folio(struct file *file, struct folio *folio) -{ - struct afs_vnode *vnode = AFS_FS_I(folio->mapping->host); - struct afs_read *fsreq; - int ret; + if (subreq->rreq->origin == NETFS_READAHEAD || + subreq->rreq->iocb) { + op->flags |= AFS_OPERATION_ASYNC; - fsreq = afs_alloc_read(GFP_NOFS); - if (!fsreq) - return -ENOMEM; + if (!afs_begin_vnode_operation(op)) { + subreq->error = afs_put_operation(op); + netfs_read_subreq_terminated(subreq); + return; + } - fsreq->pos = folio_pos(folio); - fsreq->len = folio_size(folio); - fsreq->vnode = vnode; - fsreq->iter = &fsreq->def_iter; - iov_iter_xarray(&fsreq->def_iter, ITER_DEST, &folio->mapping->i_pages, - fsreq->pos, fsreq->len); + if (!afs_select_fileserver(op)) { + afs_end_read(op); + return; + } - ret = afs_fetch_data(fsreq->vnode, fsreq); - if (ret == 0) - folio_mark_uptodate(folio); - folio_unlock(folio); - return ret; + afs_issue_read_call(op); + } else { + afs_do_sync_operation(op); + } } static int afs_init_request(struct netfs_io_request *rreq, struct file *file) { + struct afs_vnode *vnode = AFS_FS_I(rreq->inode); + if (file) rreq->netfs_priv = key_get(afs_file_key(file)); rreq->rsize = 256 * 1024; rreq->wsize = 256 * 1024 * 1024; + + switch (rreq->origin) { + case NETFS_READ_SINGLE: + if (!file) { + struct key *key = afs_request_key(vnode->volume->cell); + + if (IS_ERR(key)) + return PTR_ERR(key); + rreq->netfs_priv = key; + } + break; + case NETFS_WRITEBACK: + case NETFS_WRITETHROUGH: + case NETFS_UNBUFFERED_WRITE: + case NETFS_DIO_WRITE: + if (S_ISREG(rreq->inode->i_mode)) + rreq->io_streams[0].avail = true; + break; + case NETFS_WRITEBACK_SINGLE: + default: + break; + } return 0; } diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 428721bbe4f6..8418813ee043 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -49,6 +49,105 @@ struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *vo return op; } +struct afs_io_locker { + struct list_head link; + struct task_struct *task; + unsigned long have_lock; +}; + +/* + * Unlock the I/O lock on a vnode. + */ +static void afs_unlock_for_io(struct afs_vnode *vnode) +{ + struct afs_io_locker *locker; + + spin_lock(&vnode->lock); + locker = list_first_entry_or_null(&vnode->io_lock_waiters, + struct afs_io_locker, link); + if (locker) { + list_del(&locker->link); + smp_store_release(&locker->have_lock, 1); /* The unlock barrier. */ + smp_mb__after_atomic(); /* Store have_lock before task state */ + wake_up_process(locker->task); + } else { + clear_bit(AFS_VNODE_IO_LOCK, &vnode->flags); + } + spin_unlock(&vnode->lock); +} + +/* + * Lock the I/O lock on a vnode uninterruptibly. We can't use an ordinary + * mutex as lockdep will complain if we unlock it in the wrong thread. + */ +static void afs_lock_for_io(struct afs_vnode *vnode) +{ + struct afs_io_locker myself = { .task = current, }; + + spin_lock(&vnode->lock); + + if (!test_and_set_bit(AFS_VNODE_IO_LOCK, &vnode->flags)) { + spin_unlock(&vnode->lock); + return; + } + + list_add_tail(&myself.link, &vnode->io_lock_waiters); + spin_unlock(&vnode->lock); + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (smp_load_acquire(&myself.have_lock)) /* The lock barrier */ + break; + schedule(); + } + __set_current_state(TASK_RUNNING); +} + +/* + * Lock the I/O lock on a vnode interruptibly. We can't use an ordinary mutex + * as lockdep will complain if we unlock it in the wrong thread. + */ +static int afs_lock_for_io_interruptible(struct afs_vnode *vnode) +{ + struct afs_io_locker myself = { .task = current, }; + int ret = 0; + + spin_lock(&vnode->lock); + + if (!test_and_set_bit(AFS_VNODE_IO_LOCK, &vnode->flags)) { + spin_unlock(&vnode->lock); + return 0; + } + + list_add_tail(&myself.link, &vnode->io_lock_waiters); + spin_unlock(&vnode->lock); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (smp_load_acquire(&myself.have_lock) || /* The lock barrier */ + signal_pending(current)) + break; + schedule(); + } + __set_current_state(TASK_RUNNING); + + /* If we got a signal, try to transfer the lock onto the next + * waiter. + */ + if (unlikely(signal_pending(current))) { + spin_lock(&vnode->lock); + if (myself.have_lock) { + spin_unlock(&vnode->lock); + afs_unlock_for_io(vnode); + } else { + list_del(&myself.link); + spin_unlock(&vnode->lock); + } + ret = -ERESTARTSYS; + } + return ret; +} + /* * Lock the vnode(s) being operated upon. */ @@ -60,7 +159,7 @@ static bool afs_get_io_locks(struct afs_operation *op) _enter(""); if (op->flags & AFS_OPERATION_UNINTR) { - mutex_lock(&vnode->io_lock); + afs_lock_for_io(vnode); op->flags |= AFS_OPERATION_LOCK_0; _leave(" = t [1]"); return true; @@ -72,7 +171,7 @@ static bool afs_get_io_locks(struct afs_operation *op) if (vnode2 > vnode) swap(vnode, vnode2); - if (mutex_lock_interruptible(&vnode->io_lock) < 0) { + if (afs_lock_for_io_interruptible(vnode) < 0) { afs_op_set_error(op, -ERESTARTSYS); op->flags |= AFS_OPERATION_STOP; _leave(" = f [I 0]"); @@ -81,10 +180,10 @@ static bool afs_get_io_locks(struct afs_operation *op) op->flags |= AFS_OPERATION_LOCK_0; if (vnode2) { - if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) { + if (afs_lock_for_io_interruptible(vnode2) < 0) { afs_op_set_error(op, -ERESTARTSYS); op->flags |= AFS_OPERATION_STOP; - mutex_unlock(&vnode->io_lock); + afs_unlock_for_io(vnode); op->flags &= ~AFS_OPERATION_LOCK_0; _leave(" = f [I 1]"); return false; @@ -104,9 +203,9 @@ static void afs_drop_io_locks(struct afs_operation *op) _enter(""); if (op->flags & AFS_OPERATION_LOCK_1) - mutex_unlock(&vnode2->io_lock); + afs_unlock_for_io(vnode2); if (op->flags & AFS_OPERATION_LOCK_0) - mutex_unlock(&vnode->io_lock); + afs_unlock_for_io(vnode); } static void afs_prepare_vnode(struct afs_operation *op, struct afs_vnode_param *vp, @@ -157,7 +256,7 @@ bool afs_begin_vnode_operation(struct afs_operation *op) /* * Tidy up a filesystem cursor and unlock the vnode. */ -static void afs_end_vnode_operation(struct afs_operation *op) +void afs_end_vnode_operation(struct afs_operation *op) { _enter(""); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 098fa034a1cc..1d9ecd5418d8 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -301,19 +301,19 @@ void afs_fs_fetch_status(struct afs_operation *op) static int afs_deliver_fs_fetch_data(struct afs_call *call) { struct afs_operation *op = call->op; + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; const __be32 *bp; size_t count_before; int ret; _enter("{%u,%zu,%zu/%llu}", call->unmarshall, call->iov_len, iov_iter_count(call->iter), - req->actual_len); + call->remaining); switch (call->unmarshall) { case 0: - req->actual_len = 0; + call->remaining = 0; call->unmarshall++; if (call->operation_ID == FSFETCHDATA64) { afs_extract_to_tmp64(call); @@ -323,8 +323,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) } fallthrough; - /* Extract the returned data length into - * ->actual_len. This may indicate more or less data than was + /* Extract the returned data length into ->remaining. + * This may indicate more or less data than was * requested will be returned. */ case 1: @@ -333,42 +333,40 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (ret < 0) return ret; - req->actual_len = be64_to_cpu(call->tmp64); - _debug("DATA length: %llu", req->actual_len); + call->remaining = be64_to_cpu(call->tmp64); + _debug("DATA length: %llu", call->remaining); - if (req->actual_len == 0) + if (call->remaining == 0) goto no_more_data; - call->iter = req->iter; - call->iov_len = min(req->actual_len, req->len); + call->iter = &subreq->io_iter; + call->iov_len = umin(call->remaining, subreq->len - subreq->transferred); call->unmarshall++; fallthrough; /* extract the returned data */ case 2: count_before = call->iov_len; - _debug("extract data %zu/%llu", count_before, req->actual_len); + _debug("extract data %zu/%llu", count_before, call->remaining); ret = afs_extract_data(call, true); - if (req->subreq) { - req->subreq->transferred += count_before - call->iov_len; - netfs_read_subreq_progress(req->subreq, false); - } + subreq->transferred += count_before - call->iov_len; + call->remaining -= count_before - call->iov_len; if (ret < 0) return ret; call->iter = &call->def_iter; - if (req->actual_len <= req->len) + if (call->remaining) goto no_more_data; /* Discard any excess data the server gave us */ - afs_extract_discard(call, req->actual_len - req->len); + afs_extract_discard(call, call->remaining); call->unmarshall = 3; fallthrough; case 3: _debug("extract discard %zu/%llu", - iov_iter_count(call->iter), req->actual_len - req->len); + iov_iter_count(call->iter), call->remaining); ret = afs_extract_data(call, true); if (ret < 0) @@ -390,8 +388,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) xdr_decode_AFSCallBack(&bp, call, &vp->scb); xdr_decode_AFSVolSync(&bp, &op->volsync); - req->data_version = vp->scb.status.data_version; - req->file_size = vp->scb.status.size; + if (subreq->start + subreq->transferred >= vp->scb.status.size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); call->unmarshall++; fallthrough; @@ -410,14 +408,18 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) static const struct afs_call_type afs_RXFSFetchData = { .name = "FS.FetchData", .op = afs_FS_FetchData, + .async_rx = afs_fetch_data_async_rx, .deliver = afs_deliver_fs_fetch_data, + .immediate_cancel = afs_fetch_data_immediate_cancel, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSFetchData64 = { .name = "FS.FetchData64", .op = afs_FS_FetchData64, + .async_rx = afs_fetch_data_async_rx, .deliver = afs_deliver_fs_fetch_data, + .immediate_cancel = afs_fetch_data_immediate_cancel, .destructor = afs_flat_call_destructor, }; @@ -426,8 +428,8 @@ static const struct afs_call_type afs_RXFSFetchData64 = { */ static void afs_fs_fetch_data64(struct afs_operation *op) { + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; struct afs_call *call; __be32 *bp; @@ -437,16 +439,19 @@ static void afs_fs_fetch_data64(struct afs_operation *op) if (!call) return afs_op_nomem(op); + if (op->flags & AFS_OPERATION_ASYNC) + call->async = true; + /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA64); bp[1] = htonl(vp->fid.vid); bp[2] = htonl(vp->fid.vnode); bp[3] = htonl(vp->fid.unique); - bp[4] = htonl(upper_32_bits(req->pos)); - bp[5] = htonl(lower_32_bits(req->pos)); + bp[4] = htonl(upper_32_bits(subreq->start + subreq->transferred)); + bp[5] = htonl(lower_32_bits(subreq->start + subreq->transferred)); bp[6] = 0; - bp[7] = htonl(lower_32_bits(req->len)); + bp[7] = htonl(lower_32_bits(subreq->len - subreq->transferred)); call->fid = vp->fid; trace_afs_make_fs_call(call, &vp->fid); @@ -458,9 +463,9 @@ static void afs_fs_fetch_data64(struct afs_operation *op) */ void afs_fs_fetch_data(struct afs_operation *op) { + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; struct afs_call *call; - struct afs_read *req = op->fetch.req; __be32 *bp; if (test_bit(AFS_SERVER_FL_HAS_FS64, &op->server->flags)) @@ -472,16 +477,14 @@ void afs_fs_fetch_data(struct afs_operation *op) if (!call) return afs_op_nomem(op); - req->call_debug_id = call->debug_id; - /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA); bp[1] = htonl(vp->fid.vid); bp[2] = htonl(vp->fid.vnode); bp[3] = htonl(vp->fid.unique); - bp[4] = htonl(lower_32_bits(req->pos)); - bp[5] = htonl(lower_32_bits(req->len)); + bp[4] = htonl(lower_32_bits(subreq->start + subreq->transferred)); + bp[5] = htonl(lower_32_bits(subreq->len + subreq->transferred)); call->fid = vp->fid; trace_afs_make_fs_call(call, &vp->fid); @@ -1733,6 +1736,7 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { .op = afs_FS_GetCapabilities, .deliver = afs_deliver_fs_get_capabilities, .done = afs_fileserver_probe_result, + .immediate_cancel = afs_fileserver_probe_result, .destructor = afs_fs_get_capabilities_destructor, }; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index a95e77670b49..e9538e91f848 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -25,8 +25,94 @@ #include "internal.h" #include "afs_fs.h" +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op) +{ + size_t size = strlen(op->create.symlink) + 1; + size_t dsize = 0; + char *p; + + if (netfs_alloc_folioq_buffer(NULL, &vnode->directory, &dsize, size, + mapping_gfp_mask(vnode->netfs.inode.i_mapping)) < 0) + return; + + vnode->directory_size = dsize; + p = kmap_local_folio(folioq_folio(vnode->directory, 0), 0); + memcpy(p, op->create.symlink, size); + kunmap_local(p); + set_bit(AFS_VNODE_DIR_READ, &vnode->flags); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); +} + +static void afs_put_link(void *arg) +{ + struct folio *folio = virt_to_folio(arg); + + kunmap_local(arg); + folio_put(folio); +} + +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + struct folio *folio; + char *content; + ssize_t ret; + + if (!dentry) { + /* RCU pathwalk. */ + if (!test_bit(AFS_VNODE_DIR_READ, &vnode->flags) || !afs_check_validity(vnode)) + return ERR_PTR(-ECHILD); + goto good; + } + + if (test_bit(AFS_VNODE_DIR_READ, &vnode->flags)) + goto fetch; + + ret = afs_validate(vnode, NULL); + if (ret < 0) + return ERR_PTR(ret); + + if (!test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) && + test_bit(AFS_VNODE_DIR_READ, &vnode->flags)) + goto good; + +fetch: + ret = afs_read_single(vnode, NULL); + if (ret < 0) + return ERR_PTR(ret); + set_bit(AFS_VNODE_DIR_READ, &vnode->flags); + +good: + folio = folioq_folio(vnode->directory, 0); + folio_get(folio); + content = kmap_local_folio(folio, 0); + set_delayed_call(callback, afs_put_link, content); + return content; +} + +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen) +{ + DEFINE_DELAYED_CALL(done); + const char *content; + int len; + + content = afs_get_link(dentry, d_inode(dentry), &done); + if (IS_ERR(content)) { + do_delayed_call(&done); + return PTR_ERR(content); + } + + len = umin(strlen(content), buflen); + if (copy_to_user(buffer, content, len)) + len = -EFAULT; + do_delayed_call(&done); + return len; +} + static const struct inode_operations afs_symlink_inode_operations = { - .get_link = page_get_link, + .get_link = afs_get_link, + .readlink = afs_readlink, }; static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode) @@ -110,7 +196,9 @@ static int afs_inode_init_from_status(struct afs_operation *op, inode->i_op = &afs_dir_inode_operations; inode->i_fop = &afs_dir_file_operations; inode->i_mapping->a_ops = &afs_dir_aops; - mapping_set_large_folios(inode->i_mapping); + __set_bit(NETFS_ICTX_SINGLE_NO_UPLOAD, &vnode->netfs.flags); + /* Assume locally cached directory data will be valid. */ + __set_bit(AFS_VNODE_DIR_VALID, &vnode->flags); break; case AFS_FTYPE_SYMLINK: /* Symlinks with a mode of 0644 are actually mountpoints. */ @@ -122,13 +210,13 @@ static int afs_inode_init_from_status(struct afs_operation *op, inode->i_mode = S_IFDIR | 0555; inode->i_op = &afs_mntpt_inode_operations; inode->i_fop = &afs_mntpt_file_operations; - inode->i_mapping->a_ops = &afs_symlink_aops; } else { inode->i_mode = S_IFLNK | status->mode; inode->i_op = &afs_symlink_inode_operations; - inode->i_mapping->a_ops = &afs_symlink_aops; } + inode->i_mapping->a_ops = &afs_dir_aops; inode_nohighmem(inode); + mapping_set_release_always(inode->i_mapping); break; default: dump_vnode(vnode, op->file[0].vnode != vnode ? op->file[0].vnode : NULL); @@ -140,15 +228,17 @@ static int afs_inode_init_from_status(struct afs_operation *op, afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; + trace_afs_set_dv(vnode, status->data_version); inode_set_iversion_raw(&vnode->netfs.inode, status->data_version); if (!vp->scb.have_cb) { /* it's a symlink we just created (the fileserver * didn't give us a callback) */ - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); + afs_clear_cb_promise(vnode, afs_cb_promise_set_new_symlink); } else { vnode->cb_server = op->server; - atomic64_set(&vnode->cb_expires_at, vp->scb.callback.expires_at); + afs_set_cb_promise(vnode, vp->scb.callback.expires_at, + afs_cb_promise_set_new_inode); } write_sequnlock(&vnode->cb_lock); @@ -207,12 +297,17 @@ static void afs_apply_status(struct afs_operation *op, if (vp->update_ctime) inode_set_ctime_to_ts(inode, op->ctime); - if (vnode->status.data_version != status->data_version) + if (vnode->status.data_version != status->data_version) { + trace_afs_set_dv(vnode, status->data_version); data_changed = true; + } vnode->status = *status; if (vp->dv_before + vp->dv_delta != status->data_version) { + trace_afs_dv_mismatch(vnode, vp->dv_before, vp->dv_delta, + status->data_version); + if (vnode->cb_ro_snapshot == atomic_read(&vnode->volume->cb_ro_snapshot) && atomic64_read(&vnode->cb_expires_at) != AFS_NO_CB_PROMISE) pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n", @@ -223,12 +318,10 @@ static void afs_apply_status(struct afs_operation *op, op->debug_id); vnode->invalid_before = status->data_version; - if (vnode->status.type == AFS_FTYPE_DIR) { - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - afs_stat_v(vnode, n_inval); - } else { + if (vnode->status.type == AFS_FTYPE_DIR) + afs_invalidate_dir(vnode, afs_dir_invalid_dv_mismatch); + else set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); - } change_size = true; data_changed = true; unexpected_jump = true; @@ -258,6 +351,8 @@ static void afs_apply_status(struct afs_operation *op, inode_set_ctime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); } + if (op->ops == &afs_fetch_data_operation) + op->fetch.subreq->rreq->i_size = status->size; } } @@ -273,7 +368,7 @@ static void afs_apply_callback(struct afs_operation *op, if (!afs_cb_is_broken(vp->cb_break_before, vnode)) { if (op->volume->type == AFSVL_RWVOL) vnode->cb_server = op->server; - atomic64_set(&vnode->cb_expires_at, cb->expires_at); + afs_set_cb_promise(vnode, cb->expires_at, afs_cb_promise_set_apply_cb); } } @@ -435,7 +530,9 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) } __packed key; struct afs_vnode_cache_aux aux; - if (vnode->status.type != AFS_FTYPE_FILE) { + if (vnode->status.type != AFS_FTYPE_FILE && + vnode->status.type != AFS_FTYPE_DIR && + vnode->status.type != AFS_FTYPE_SYMLINK) { vnode->netfs.cache = NULL; return; } @@ -637,6 +734,7 @@ int afs_drop_inode(struct inode *inode) void afs_evict_inode(struct inode *inode) { struct afs_vnode_cache_aux aux; + struct afs_super_info *sbi = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); _enter("{%llx:%llu.%d}", @@ -648,8 +746,22 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); + if ((S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) && + (inode->i_state & I_DIRTY) && + !sbi->dyn_root) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .for_sync = true, + .range_end = LLONG_MAX, + }; + + afs_single_writepages(inode->i_mapping, &wbc); + } + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); + netfs_free_folioq_buffer(vnode->directory); afs_set_cache_aux(vnode, &aux); netfs_clear_inode_writeback(inode, &aux); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index c9d620175e80..90f407774a9a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -163,6 +163,7 @@ struct afs_call { spinlock_t state_lock; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ + unsigned long long remaining; /* How much is left to receive */ unsigned int max_lifespan; /* Maximum lifespan in secs to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ @@ -201,11 +202,17 @@ struct afs_call_type { /* clean up a call */ void (*destructor)(struct afs_call *call); + /* Async receive processing function */ + void (*async_rx)(struct work_struct *work); + /* Work function */ void (*work)(struct work_struct *work); /* Call done function (gets called immediately on success or failure) */ void (*done)(struct afs_call *call); + + /* Handle a call being immediately cancelled. */ + void (*immediate_cancel)(struct afs_call *call); }; /* @@ -233,28 +240,6 @@ static inline struct key *afs_file_key(struct file *file) } /* - * Record of an outstanding read operation on a vnode. - */ -struct afs_read { - loff_t pos; /* Where to start reading */ - loff_t len; /* How much we're asking for */ - loff_t actual_len; /* How much we're actually getting */ - loff_t file_size; /* File size returned by server */ - struct key *key; /* The key to use to reissue the read */ - struct afs_vnode *vnode; /* The file being read into. */ - struct netfs_io_subrequest *subreq; /* Fscache helper read request this belongs to */ - afs_dataversion_t data_version; /* Version number returned by server */ - refcount_t usage; - unsigned int call_debug_id; - unsigned int nr_pages; - int error; - void (*done)(struct afs_read *); - void (*cleanup)(struct afs_read *); - struct iov_iter *iter; /* Iterator representing the buffer */ - struct iov_iter def_iter; /* Default iterator */ -}; - -/* * AFS superblock private data * - there's one superblock per volume */ @@ -702,13 +687,14 @@ struct afs_vnode { struct afs_file_status status; /* AFS status info for this file */ afs_dataversion_t invalid_before; /* Child dentries are invalid before this */ struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ - struct mutex io_lock; /* Lock for serialising I/O on this mutex */ + struct list_head io_lock_waiters; /* Threads waiting for the I/O lock */ struct rw_semaphore validate_lock; /* lock for validating this vnode */ struct rw_semaphore rmdir_lock; /* Lock for rmdir vs sillyrename */ struct key *silly_key; /* Silly rename key */ spinlock_t wb_lock; /* lock for wb_keys */ spinlock_t lock; /* waitqueue/flags lock */ unsigned long flags; +#define AFS_VNODE_IO_LOCK 0 /* Set if the I/O serialisation lock is held */ #define AFS_VNODE_UNSET 1 /* set if vnode attributes not yet set */ #define AFS_VNODE_DIR_VALID 2 /* Set if dir contents are valid */ #define AFS_VNODE_ZAP_DATA 3 /* set if vnode's data should be invalidated */ @@ -719,7 +705,9 @@ struct afs_vnode { #define AFS_VNODE_NEW_CONTENT 8 /* Set if file has new content (create/trunc-0) */ #define AFS_VNODE_SILLY_DELETED 9 /* Set if file has been silly-deleted */ #define AFS_VNODE_MODIFYING 10 /* Set if we're performing a modification op */ +#define AFS_VNODE_DIR_READ 11 /* Set if we've read a dir's contents */ + struct folio_queue *directory; /* Directory contents */ struct list_head wb_keys; /* List of keys available for writeback */ struct list_head pending_locks; /* locks waiting to be granted */ struct list_head granted_locks; /* locks granted on this file */ @@ -728,6 +716,7 @@ struct afs_vnode { ktime_t locked_at; /* Time at which lock obtained */ enum afs_lock_state lock_state : 8; afs_lock_type_t lock_type : 8; + unsigned int directory_size; /* Amount of space in ->directory */ /* outstanding callback notification on this file */ struct work_struct cb_work; /* Work for mmap'd files */ @@ -907,7 +896,7 @@ struct afs_operation { bool new_negative; } rename; struct { - struct afs_read *req; + struct netfs_io_subrequest *subreq; } fetch; struct { afs_lock_type_t type; @@ -959,6 +948,7 @@ struct afs_operation { #define AFS_OPERATION_TRIED_ALL 0x0400 /* Set if we've tried all the fileservers */ #define AFS_OPERATION_RETRY_SERVER 0x0800 /* Set if we should retry the current server */ #define AFS_OPERATION_DIR_CONFLICT 0x1000 /* Set if we detected a 3rd-party dir change */ +#define AFS_OPERATION_ASYNC 0x2000 /* Set if should run asynchronously */ }; /* @@ -983,6 +973,21 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl i_size_read(&vnode->netfs.inode), flags); } +/* + * Directory iteration management. + */ +struct afs_dir_iter { + struct afs_vnode *dvnode; + union afs_xdr_dir_block *block; + struct folio_queue *fq; + unsigned int fpos; + int fq_slot; + unsigned int loop_check; + u8 nr_slots; + u8 bucket; + unsigned int prev_entry; +}; + #include <trace/events/afs.h> /*****************************************************************************/ @@ -1064,8 +1069,13 @@ extern const struct inode_operations afs_dir_inode_operations; extern const struct address_space_operations afs_dir_aops; extern const struct dentry_operations afs_fs_dentry_operations; +ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file); +ssize_t afs_read_dir(struct afs_vnode *dvnode, struct file *file) + __acquires(&dvnode->validate_lock); extern void afs_d_release(struct dentry *); extern void afs_check_for_remote_deletion(struct afs_operation *); +int afs_single_writepages(struct address_space *mapping, + struct writeback_control *wbc); /* * dir_edit.c @@ -1075,6 +1085,18 @@ extern void afs_edit_dir_add(struct afs_vnode *, struct qstr *, struct afs_fid * extern void afs_edit_dir_remove(struct afs_vnode *, struct qstr *, enum afs_edit_dir_reason); void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode, enum afs_edit_dir_reason why); +void afs_mkdir_init_dir(struct afs_vnode *dvnode, struct afs_vnode *parent_vnode); + +/* + * dir_search.c + */ +unsigned int afs_dir_hash_name(const struct qstr *name); +bool afs_dir_init_iter(struct afs_dir_iter *iter, const struct qstr *name); +union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t block); +int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, + struct afs_fid *_fid); +int afs_dir_search(struct afs_vnode *dvnode, struct qstr *name, + struct afs_fid *_fid, afs_dataversion_t *_dir_version); /* * dir_silly.c @@ -1099,24 +1121,17 @@ extern void afs_dynroot_depopulate(struct super_block *); * file.c */ extern const struct address_space_operations afs_file_aops; -extern const struct address_space_operations afs_symlink_aops; extern const struct inode_operations afs_file_inode_operations; extern const struct file_operations afs_file_operations; +extern const struct afs_operation_ops afs_fetch_data_operation; extern const struct netfs_request_ops afs_req_ops; extern int afs_cache_wb_key(struct afs_vnode *, struct afs_file *); extern void afs_put_wb_key(struct afs_wb_key *); extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); -extern int afs_fetch_data(struct afs_vnode *, struct afs_read *); -extern struct afs_read *afs_alloc_read(gfp_t); -extern void afs_put_read(struct afs_read *); - -static inline struct afs_read *afs_get_read(struct afs_read *req) -{ - refcount_inc(&req->usage); - return req; -} +void afs_fetch_data_async_rx(struct work_struct *work); +void afs_fetch_data_immediate_cancel(struct afs_call *call); /* * flock.c @@ -1168,6 +1183,7 @@ extern void afs_fs_store_acl(struct afs_operation *); extern struct afs_operation *afs_alloc_operation(struct key *, struct afs_volume *); extern int afs_put_operation(struct afs_operation *); extern bool afs_begin_vnode_operation(struct afs_operation *); +extern void afs_end_vnode_operation(struct afs_operation *op); extern void afs_wait_for_operation(struct afs_operation *); extern int afs_do_sync_operation(struct afs_operation *); @@ -1205,6 +1221,10 @@ extern void afs_fs_probe_cleanup(struct afs_net *); */ extern const struct afs_operation_ops afs_fetch_status_operation; +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op); +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback); +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen); extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *); extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); extern int afs_ilookup5_test_by_fid(struct inode *, void *); @@ -1336,6 +1356,7 @@ extern void afs_charge_preallocation(struct work_struct *); extern void afs_put_call(struct afs_call *); void afs_deferred_put_call(struct afs_call *call); void afs_make_call(struct afs_call *call, gfp_t gfp); +void afs_deliver_to_call(struct afs_call *call); void afs_wait_for_call_to_complete(struct afs_call *call); extern struct afs_call *afs_alloc_flat_call(struct afs_net *, const struct afs_call_type *, @@ -1346,6 +1367,28 @@ extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, bool); extern int afs_protocol_error(struct afs_call *, enum afs_eproto_cause); +static inline struct afs_call *afs_get_call(struct afs_call *call, + enum afs_call_trace why) +{ + int r; + + __refcount_inc(&call->ref, &r); + + trace_afs_call(call->debug_id, why, r + 1, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); + return call; +} + +static inline void afs_see_call(struct afs_call *call, enum afs_call_trace why) +{ + int r = refcount_read(&call->ref); + + trace_afs_call(call->debug_id, why, r, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); +} + static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *call, gfp_t gfp) { @@ -1712,6 +1755,38 @@ static inline int afs_bad(struct afs_vnode *vnode, enum afs_file_error where) return -EIO; } +/* + * Set the callback promise on a vnode. + */ +static inline void afs_set_cb_promise(struct afs_vnode *vnode, time64_t expires_at, + enum afs_cb_promise_trace trace) +{ + atomic64_set(&vnode->cb_expires_at, expires_at); + trace_afs_cb_promise(vnode, trace); +} + +/* + * Clear the callback promise on a vnode, returning true if it was promised. + */ +static inline bool afs_clear_cb_promise(struct afs_vnode *vnode, + enum afs_cb_promise_trace trace) +{ + trace_afs_cb_promise(vnode, trace); + return atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE; +} + +/* + * Mark a directory as being invalid. + */ +static inline void afs_invalidate_dir(struct afs_vnode *dvnode, + enum afs_dir_invalid_trace trace) +{ + if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + trace_afs_dir_invalid(dvnode, trace); + afs_stat_v(dvnode, n_inval); + } +} + /*****************************************************************************/ /* * debug tracing diff --git a/fs/afs/main.c b/fs/afs/main.c index a14f6013e316..1ae0067f772d 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -177,7 +177,7 @@ static int __init afs_init(void) afs_wq = alloc_workqueue("afs", 0, 0); if (!afs_wq) goto error_afs_wq; - afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0); + afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!afs_async_calls) goto error_async; afs_lock_manager = alloc_workqueue("kafs_lockd", WQ_MEM_RECLAIM, 0); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 297487ee8323..507c25a5b2cb 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -30,7 +30,7 @@ const struct file_operations afs_mntpt_file_operations = { const struct inode_operations afs_mntpt_inode_operations = { .lookup = afs_mntpt_lookup, - .readlink = page_readlink, + .readlink = afs_readlink, .getattr = afs_getattr, }; @@ -118,9 +118,9 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) ctx->volnamesz = sizeof(afs_root_volume) - 1; } else { /* read the contents of the AFS special symlink */ - struct page *page; + DEFINE_DELAYED_CALL(cleanup); + const char *content; loff_t size = i_size_read(d_inode(mntpt)); - char *buf; if (src_as->cell) ctx->cell = afs_use_cell(src_as->cell, afs_cell_trace_use_mntpt); @@ -128,16 +128,16 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) if (size < 2 || size > PAGE_SIZE - 1) return -EINVAL; - page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL); - if (IS_ERR(page)) - return PTR_ERR(page); + content = afs_get_link(mntpt, d_inode(mntpt), &cleanup); + if (IS_ERR(content)) { + do_delayed_call(&cleanup); + return PTR_ERR(content); + } - buf = kmap(page); ret = -EINVAL; - if (buf[size - 1] == '.') - ret = vfs_parse_fs_string(fc, "source", buf, size - 1); - kunmap(page); - put_page(page); + if (content[size - 1] == '.') + ret = vfs_parse_fs_string(fc, "source", content, size - 1); + do_delayed_call(&cleanup); if (ret < 0) return ret; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 15eab053af6d..e7614f4f30c2 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -240,7 +240,13 @@ static int afs_proc_rootcell_write(struct file *file, char *buf, size_t size) /* determine command to perform */ _debug("rootcell=%s", buf); - ret = afs_cell_init(net, buf); + ret = -EEXIST; + inode_lock(file_inode(file)); + if (!net->ws_cell) + ret = afs_cell_init(net, buf); + else + printk("busy\n"); + inode_unlock(file_inode(file)); out: _leave(" = %d", ret); diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index d612983d6f38..a1c24f589d9e 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -99,7 +99,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op, write_seqlock(&vnode->cb_lock); ASSERTCMP(cb_server, ==, vnode->cb_server); vnode->cb_server = NULL; - if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE) + if (afs_clear_cb_promise(vnode, afs_cb_promise_clear_rotate_server)) vnode->cb_break++; write_sequnlock(&vnode->cb_lock); } @@ -583,7 +583,7 @@ selected_server: if (vnode->cb_server != server) { vnode->cb_server = server; vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break); - atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE); + afs_clear_cb_promise(vnode, afs_cb_promise_clear_server_change); } retry_server: diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 9f2a3bb56ec6..886416ea1d96 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -149,7 +149,8 @@ static struct afs_call *afs_alloc_call(struct afs_net *net, call->net = net; call->debug_id = atomic_inc_return(&rxrpc_debug_id); refcount_set(&call->ref, 1); - INIT_WORK(&call->async_work, afs_process_async_call); + INIT_WORK(&call->async_work, type->async_rx ?: afs_process_async_call); + INIT_WORK(&call->work, call->type->work); INIT_WORK(&call->free_work, afs_deferred_free_worker); init_waitqueue_head(&call->waitq); spin_lock_init(&call->state_lock); @@ -235,27 +236,12 @@ void afs_deferred_put_call(struct afs_call *call) schedule_work(&call->free_work); } -static struct afs_call *afs_get_call(struct afs_call *call, - enum afs_call_trace why) -{ - int r; - - __refcount_inc(&call->ref, &r); - - trace_afs_call(call->debug_id, why, r + 1, - atomic_read(&call->net->nr_outstanding_calls), - __builtin_return_address(0)); - return call; -} - /* * Queue the call for actual work. */ static void afs_queue_call_work(struct afs_call *call) { if (call->type->work) { - INIT_WORK(&call->work, call->type->work); - afs_get_call(call, afs_call_trace_work); if (!queue_work(afs_wq, &call->work)) afs_put_call(call); @@ -430,11 +416,16 @@ void afs_make_call(struct afs_call *call, gfp_t gfp) return; error_do_abort: - if (ret != -ECONNABORTED) { + if (ret != -ECONNABORTED) rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, afs_abort_send_data_error); - } else { + if (call->async) { + afs_see_call(call, afs_call_trace_async_abort); + return; + } + + if (ret == -ECONNABORTED) { len = 0; iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0); rxrpc_kernel_recv_data(call->net->socket, rxcall, @@ -445,8 +436,10 @@ error_do_abort: call->error = ret; trace_afs_call_done(call); error_kill_call: - if (call->type->done) - call->type->done(call); + if (call->async) + afs_see_call(call, afs_call_trace_async_kill); + if (call->type->immediate_cancel) + call->type->immediate_cancel(call); /* We need to dispose of the extra ref we grabbed for an async call. * The call, however, might be queued on afs_async_calls and we need to @@ -501,7 +494,7 @@ static void afs_log_error(struct afs_call *call, s32 remote_abort) /* * deliver messages to a call */ -static void afs_deliver_to_call(struct afs_call *call) +void afs_deliver_to_call(struct afs_call *call) { enum afs_call_state state; size_t len; @@ -602,7 +595,6 @@ local_abort: abort_code = 0; call_complete: afs_set_call_complete(call, ret, remote_abort); - state = AFS_CALL_COMPLETE; goto done; } @@ -803,6 +795,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call) return -ENOTSUPP; trace_afs_cb_call(call); + call->work.func = call->type->work; /* pass responsibility for the remainer of this message off to the * cache manager op */ diff --git a/fs/afs/super.c b/fs/afs/super.c index f3ba1c3e72f5..a9bee610674e 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -663,7 +663,7 @@ static void afs_i_init_once(void *_vnode) memset(vnode, 0, sizeof(*vnode)); inode_init_once(&vnode->netfs.inode); - mutex_init(&vnode->io_lock); + INIT_LIST_HEAD(&vnode->io_lock_waiters); init_rwsem(&vnode->validate_lock); spin_lock_init(&vnode->wb_lock); spin_lock_init(&vnode->lock); @@ -696,6 +696,8 @@ static struct inode *afs_alloc_inode(struct super_block *sb) vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; + vnode->directory = NULL; + vnode->directory_size = 0; vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; diff --git a/fs/afs/validation.c b/fs/afs/validation.c index bef8af12ebe2..0ba8336c9025 100644 --- a/fs/afs/validation.c +++ b/fs/afs/validation.c @@ -120,22 +120,31 @@ bool afs_check_validity(const struct afs_vnode *vnode) { const struct afs_volume *volume = vnode->volume; + enum afs_vnode_invalid_trace trace = afs_vnode_valid_trace; + time64_t cb_expires_at = atomic64_read(&vnode->cb_expires_at); time64_t deadline = ktime_get_real_seconds() + 10; if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) return true; - if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) || - atomic64_read(&vnode->cb_expires_at) <= deadline || - volume->cb_expires_at <= deadline || - vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot) || - vnode->cb_scrub != atomic_read(&volume->cb_scrub) || - test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) { - _debug("inval"); - return false; - } - - return true; + if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break)) + trace = afs_vnode_invalid_trace_cb_v_break; + else if (cb_expires_at == AFS_NO_CB_PROMISE) + trace = afs_vnode_invalid_trace_no_cb_promise; + else if (cb_expires_at <= deadline) + trace = afs_vnode_invalid_trace_expired; + else if (volume->cb_expires_at <= deadline) + trace = afs_vnode_invalid_trace_vol_expired; + else if (vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot)) + trace = afs_vnode_invalid_trace_cb_ro_snapshot; + else if (vnode->cb_scrub != atomic_read(&volume->cb_scrub)) + trace = afs_vnode_invalid_trace_cb_scrub; + else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) + trace = afs_vnode_invalid_trace_zap_data; + else + return true; + trace_afs_vnode_invalid(vnode, trace); + return false; } /* diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 9f36e14f1c2d..f9e76b604f31 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -253,6 +253,7 @@ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; + size_t name_len; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); @@ -264,8 +265,11 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) return 0; } - master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), - NULL, false); + name_len = strlen(cell_name); + if (!name_len || name_len > AFS_MAXCELLNAME) + master = ERR_PTR(-EOPNOTSUPP); + else + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index cac75f89b64a..3a23c0b08eb6 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -370,6 +370,7 @@ static const struct afs_call_type afs_RXVLGetCapabilities = { .name = "VL.GetCapabilities", .op = afs_VL_GetCapabilities, .deliver = afs_deliver_vl_get_capabilities, + .immediate_cancel = afs_vlserver_probe_result, .done = afs_vlserver_probe_result, .destructor = afs_destroy_vl_get_capabilities, }; @@ -697,7 +698,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) return ret; namesz = ntohl(call->tmp); - if (namesz > AFS_MAXCELLNAME) + if (namesz > YFS_VL_MAXCELLNAME) return afs_protocol_error(call, afs_eproto_cellname_len); paddedsz = (namesz + 3) & ~3; call->count = namesz; diff --git a/fs/afs/write.c b/fs/afs/write.c index 34107b55f834..18b0a9f1615e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -122,7 +122,7 @@ static void afs_issue_write_worker(struct work_struct *work) if (subreq->debug_index == 3) return netfs_write_subrequest_terminated(subreq, -ENOANO, false); - if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { + if (!subreq->retry_count) { set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); return netfs_write_subrequest_terminated(subreq, -EAGAIN, false); } @@ -149,6 +149,9 @@ static void afs_issue_write_worker(struct work_struct *work) afs_wait_for_operation(op); ret = afs_put_operation(op); switch (ret) { + case 0: + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + break; case -EACCES: case -EPERM: case -ENOKEY: @@ -179,8 +182,8 @@ void afs_issue_write(struct netfs_io_subrequest *subreq) */ void afs_begin_writeback(struct netfs_io_request *wreq) { - afs_get_writeback_key(wreq); - wreq->io_streams[0].avail = true; + if (S_ISREG(wreq->inode->i_mode)) + afs_get_writeback_key(wreq); } /* @@ -193,6 +196,18 @@ void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *st list_first_entry(&stream->subrequests, struct netfs_io_subrequest, rreq_link); + switch (wreq->origin) { + case NETFS_READAHEAD: + case NETFS_READPAGE: + case NETFS_READ_GAPS: + case NETFS_READ_SINGLE: + case NETFS_READ_FOR_WRITE: + case NETFS_DIO_READ: + return; + default: + break; + } + switch (subreq->error) { case -EACCES: case -EPERM: diff --git a/fs/afs/xdr_fs.h b/fs/afs/xdr_fs.h index 8ca868164507..cc5f143d21a3 100644 --- a/fs/afs/xdr_fs.h +++ b/fs/afs/xdr_fs.h @@ -88,7 +88,7 @@ union afs_xdr_dir_block { struct { struct afs_xdr_dir_hdr hdr; - u8 alloc_ctrs[AFS_DIR_MAX_BLOCKS]; + u8 alloc_ctrs[AFS_DIR_BLOCKS_WITH_CTR]; __be16 hashtable[AFS_DIR_HASHTBL_SIZE]; } meta; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 024227aba4cd..257af259c04a 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -352,19 +352,19 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call) static int yfs_deliver_fs_fetch_data64(struct afs_call *call) { struct afs_operation *op = call->op; + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; const __be32 *bp; size_t count_before; int ret; _enter("{%u,%zu, %zu/%llu}", call->unmarshall, call->iov_len, iov_iter_count(call->iter), - req->actual_len); + call->remaining); switch (call->unmarshall) { case 0: - req->actual_len = 0; + call->remaining = 0; afs_extract_to_tmp64(call); call->unmarshall++; fallthrough; @@ -379,42 +379,39 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) if (ret < 0) return ret; - req->actual_len = be64_to_cpu(call->tmp64); - _debug("DATA length: %llu", req->actual_len); + call->remaining = be64_to_cpu(call->tmp64); + _debug("DATA length: %llu", call->remaining); - if (req->actual_len == 0) + if (call->remaining == 0) goto no_more_data; - call->iter = req->iter; - call->iov_len = min(req->actual_len, req->len); + call->iter = &subreq->io_iter; + call->iov_len = min(call->remaining, subreq->len - subreq->transferred); call->unmarshall++; fallthrough; /* extract the returned data */ case 2: count_before = call->iov_len; - _debug("extract data %zu/%llu", count_before, req->actual_len); + _debug("extract data %zu/%llu", count_before, call->remaining); ret = afs_extract_data(call, true); - if (req->subreq) { - req->subreq->transferred += count_before - call->iov_len; - netfs_read_subreq_progress(req->subreq, false); - } + subreq->transferred += count_before - call->iov_len; if (ret < 0) return ret; call->iter = &call->def_iter; - if (req->actual_len <= req->len) + if (call->remaining) goto no_more_data; /* Discard any excess data the server gave us */ - afs_extract_discard(call, req->actual_len - req->len); + afs_extract_discard(call, call->remaining); call->unmarshall = 3; fallthrough; case 3: _debug("extract discard %zu/%llu", - iov_iter_count(call->iter), req->actual_len - req->len); + iov_iter_count(call->iter), call->remaining); ret = afs_extract_data(call, true); if (ret < 0) @@ -439,8 +436,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) xdr_decode_YFSCallBack(&bp, call, &vp->scb); xdr_decode_YFSVolSync(&bp, &op->volsync); - req->data_version = vp->scb.status.data_version; - req->file_size = vp->scb.status.size; + if (subreq->start + subreq->transferred >= vp->scb.status.size) + __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); call->unmarshall++; fallthrough; @@ -459,7 +456,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) static const struct afs_call_type yfs_RXYFSFetchData64 = { .name = "YFS.FetchData64", .op = yfs_FS_FetchData64, + .async_rx = afs_fetch_data_async_rx, .deliver = yfs_deliver_fs_fetch_data64, + .immediate_cancel = afs_fetch_data_immediate_cancel, .destructor = afs_flat_call_destructor, }; @@ -468,14 +467,15 @@ static const struct afs_call_type yfs_RXYFSFetchData64 = { */ void yfs_fs_fetch_data(struct afs_operation *op) { + struct netfs_io_subrequest *subreq = op->fetch.subreq; struct afs_vnode_param *vp = &op->file[0]; - struct afs_read *req = op->fetch.req; struct afs_call *call; __be32 *bp; - _enter(",%x,{%llx:%llu},%llx,%llx", + _enter(",%x,{%llx:%llu},%llx,%zx", key_serial(op->key), vp->fid.vid, vp->fid.vnode, - req->pos, req->len); + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchData64, sizeof(__be32) * 2 + @@ -487,15 +487,16 @@ void yfs_fs_fetch_data(struct afs_operation *op) if (!call) return afs_op_nomem(op); - req->call_debug_id = call->debug_id; + if (op->flags & AFS_OPERATION_ASYNC) + call->async = true; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSFETCHDATA64); bp = xdr_encode_u32(bp, 0); /* RPC flags */ bp = xdr_encode_YFSFid(bp, &vp->fid); - bp = xdr_encode_u64(bp, req->pos); - bp = xdr_encode_u64(bp, req->len); + bp = xdr_encode_u64(bp, subreq->start + subreq->transferred); + bp = xdr_encode_u64(bp, subreq->len - subreq->transferred); yfs_check_req(call, bp); call->fid = vp->fid; @@ -666,8 +667,9 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call) static void yfs_done_fs_remove_file2(struct afs_call *call) { if (call->error == -ECONNABORTED && - call->abort_code == RX_INVALID_OPERATION) { - set_bit(AFS_SERVER_FL_NO_RM2, &call->server->flags); + (call->abort_code == RX_INVALID_OPERATION || + call->abort_code == RXGEN_OPCODE)) { + set_bit(AFS_SERVER_FL_NO_RM2, &call->op->server->flags); call->op->flags |= AFS_OPERATION_DOWNGRADE; } } diff --git a/fs/backing-file.c b/fs/backing-file.c index cbdad8b68474..763fbe9b72b2 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -176,7 +176,7 @@ ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); @@ -197,7 +197,7 @@ ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, backing_aio_cleanup(aio, ret); } out: - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->accessed) ctx->accessed(iocb->ki_filp); @@ -233,7 +233,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, */ flags &= ~IOCB_DIO_CALLER_COMP; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); @@ -264,7 +264,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, backing_aio_cleanup(aio, ret); } out: - revert_creds_light(old_cred); + revert_creds(old_cred); return ret; } @@ -281,9 +281,9 @@ ssize_t backing_file_splice_read(struct file *in, struct kiocb *iocb, if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING))) return -EIO; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); ret = vfs_splice_read(in, &iocb->ki_pos, pipe, len, flags); - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->accessed) ctx->accessed(iocb->ki_filp); @@ -310,11 +310,11 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, if (ret) return ret; - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); file_start_write(out); ret = out->f_op->splice_write(pipe, out, &iocb->ki_pos, len, flags); file_end_write(out); - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->end_write) ctx->end_write(iocb, ret); @@ -338,9 +338,9 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma, vma_set_file(vma, file); - old_cred = override_creds_light(ctx->cred); + old_cred = override_creds(ctx->cred); ret = call_mmap(vma->vm_file, vma); - revert_creds_light(old_cred); + revert_creds(old_cred); if (ctx->accessed) ctx->accessed(user_file); diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig index ab6c95b895b3..85eea7a4dea3 100644 --- a/fs/bcachefs/Kconfig +++ b/fs/bcachefs/Kconfig @@ -15,6 +15,7 @@ config BCACHEFS_FS select ZLIB_INFLATE select ZSTD_COMPRESS select ZSTD_DECOMPRESS + select CRYPTO select CRYPTO_SHA256 select CRYPTO_CHACHA20 select CRYPTO_POLY1305 @@ -90,7 +91,7 @@ config BCACHEFS_SIX_OPTIMISTIC_SPIN config BCACHEFS_PATH_TRACEPOINTS bool "Extra btree_path tracepoints" - depends on BCACHEFS_FS + depends on BCACHEFS_FS && TRACING help Enable extra tracepoints for debugging btree_path operations; we don't normally want these enabled because they happen at very high rates. diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile index 56d20e219f59..d2689388d5e8 100644 --- a/fs/bcachefs/Makefile +++ b/fs/bcachefs/Makefile @@ -82,6 +82,7 @@ bcachefs-y := \ siphash.o \ six.o \ snapshot.o \ + str_hash.o \ subvolume.o \ super.o \ super-io.o \ diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c index 87f1be9d4db4..99487727ae64 100644 --- a/fs/bcachefs/acl.c +++ b/fs/bcachefs/acl.c @@ -184,11 +184,6 @@ invalid: return ERR_PTR(-EINVAL); } -#define acl_for_each_entry(acl, acl_e) \ - for (acl_e = acl->a_entries; \ - acl_e < acl->a_entries + acl->a_count; \ - acl_e++) - /* * Convert from in-memory to filesystem representation. */ @@ -199,11 +194,11 @@ bch2_acl_to_xattr(struct btree_trans *trans, { struct bkey_i_xattr *xattr; bch_acl_header *acl_header; - const struct posix_acl_entry *acl_e; + const struct posix_acl_entry *acl_e, *pe; void *outptr; unsigned nr_short = 0, nr_long = 0, acl_len, u64s; - acl_for_each_entry(acl, acl_e) { + FOREACH_ACL_ENTRY(acl_e, acl, pe) { switch (acl_e->e_tag) { case ACL_USER: case ACL_GROUP: @@ -241,7 +236,7 @@ bch2_acl_to_xattr(struct btree_trans *trans, outptr = (void *) acl_header + sizeof(*acl_header); - acl_for_each_entry(acl, acl_e) { + FOREACH_ACL_ENTRY(acl_e, acl, pe) { bch_acl_entry *entry = outptr; entry->e_tag = cpu_to_le16(acl_e->e_tag); diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index c84a91572a1d..fc2ef33b67b3 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -198,7 +198,7 @@ static unsigned bch_alloc_v1_val_u64s(const struct bch_alloc *a) } int bch2_alloc_v1_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_alloc a = bkey_s_c_to_alloc(k); int ret = 0; @@ -213,7 +213,7 @@ fsck_err: } int bch2_alloc_v2_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_alloc_unpacked u; int ret = 0; @@ -226,7 +226,7 @@ fsck_err: } int bch2_alloc_v3_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_alloc_unpacked u; int ret = 0; @@ -239,7 +239,7 @@ fsck_err: } int bch2_alloc_v4_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bch_alloc_v4 a; int ret = 0; @@ -322,9 +322,9 @@ fsck_err: void bch2_alloc_v4_swab(struct bkey_s k) { struct bch_alloc_v4 *a = bkey_s_to_alloc_v4(k).v; - struct bch_backpointer *bp, *bps; - a->journal_seq = swab64(a->journal_seq); + a->journal_seq_nonempty = swab64(a->journal_seq_nonempty); + a->journal_seq_empty = swab64(a->journal_seq_empty); a->flags = swab32(a->flags); a->dirty_sectors = swab32(a->dirty_sectors); a->cached_sectors = swab32(a->cached_sectors); @@ -333,13 +333,6 @@ void bch2_alloc_v4_swab(struct bkey_s k) a->stripe = swab32(a->stripe); a->nr_external_backpointers = swab32(a->nr_external_backpointers); a->stripe_sectors = swab32(a->stripe_sectors); - - bps = alloc_v4_backpointers(a); - for (bp = bps; bp < bps + BCH_ALLOC_V4_NR_BACKPOINTERS(a); bp++) { - bp->bucket_offset = swab40(bp->bucket_offset); - bp->bucket_len = swab32(bp->bucket_len); - bch2_bpos_swab(&bp->pos); - } } void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) @@ -354,16 +347,17 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c prt_printf(out, "gen %u oldest_gen %u data_type ", a->gen, a->oldest_gen); bch2_prt_data_type(out, a->data_type); prt_newline(out); - prt_printf(out, "journal_seq %llu\n", a->journal_seq); - prt_printf(out, "need_discard %llu\n", BCH_ALLOC_V4_NEED_DISCARD(a)); - prt_printf(out, "need_inc_gen %llu\n", BCH_ALLOC_V4_NEED_INC_GEN(a)); - prt_printf(out, "dirty_sectors %u\n", a->dirty_sectors); - prt_printf(out, "stripe_sectors %u\n", a->stripe_sectors); - prt_printf(out, "cached_sectors %u\n", a->cached_sectors); - prt_printf(out, "stripe %u\n", a->stripe); - prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy); - prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]); - prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]); + prt_printf(out, "journal_seq_nonempty %llu\n", a->journal_seq_nonempty); + prt_printf(out, "journal_seq_empty %llu\n", a->journal_seq_empty); + prt_printf(out, "need_discard %llu\n", BCH_ALLOC_V4_NEED_DISCARD(a)); + prt_printf(out, "need_inc_gen %llu\n", BCH_ALLOC_V4_NEED_INC_GEN(a)); + prt_printf(out, "dirty_sectors %u\n", a->dirty_sectors); + prt_printf(out, "stripe_sectors %u\n", a->stripe_sectors); + prt_printf(out, "cached_sectors %u\n", a->cached_sectors); + prt_printf(out, "stripe %u\n", a->stripe); + prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy); + prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]); + prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]); if (ca) prt_printf(out, "fragmentation %llu\n", alloc_lru_idx_fragmentation(*a, ca)); @@ -392,7 +386,7 @@ void __bch2_alloc_to_v4(struct bkey_s_c k, struct bch_alloc_v4 *out) struct bkey_alloc_unpacked u = bch2_alloc_unpack(k); *out = (struct bch_alloc_v4) { - .journal_seq = u.journal_seq, + .journal_seq_nonempty = u.journal_seq, .flags = u.need_discard, .gen = u.gen, .oldest_gen = u.oldest_gen, @@ -517,7 +511,7 @@ static unsigned alloc_gen(struct bkey_s_c k, unsigned offset) } int bch2_bucket_gens_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -664,74 +658,80 @@ int bch2_alloc_read(struct bch_fs *c) /* Free space/discard btree: */ +static int __need_discard_or_freespace_err(struct btree_trans *trans, + struct bkey_s_c alloc_k, + bool set, bool discard, bool repair) +{ + struct bch_fs *c = trans->c; + enum bch_fsck_flags flags = FSCK_CAN_IGNORE|(repair ? FSCK_CAN_FIX : 0); + enum bch_sb_error_id err_id = discard + ? BCH_FSCK_ERR_need_discard_key_wrong + : BCH_FSCK_ERR_freespace_key_wrong; + enum btree_id btree = discard ? BTREE_ID_need_discard : BTREE_ID_freespace; + struct printbuf buf = PRINTBUF; + + bch2_bkey_val_to_text(&buf, c, alloc_k); + + int ret = __bch2_fsck_err(NULL, trans, flags, err_id, + "bucket incorrectly %sset in %s btree\n" + " %s", + set ? "" : "un", + bch2_btree_id_str(btree), + buf.buf); + if (ret == -BCH_ERR_fsck_ignore || + ret == -BCH_ERR_fsck_errors_not_fixed) + ret = 0; + + printbuf_exit(&buf); + return ret; +} + +#define need_discard_or_freespace_err(...) \ + fsck_err_wrap(__need_discard_or_freespace_err(__VA_ARGS__)) + +#define need_discard_or_freespace_err_on(cond, ...) \ + (unlikely(cond) ? need_discard_or_freespace_err(__VA_ARGS__) : false) + static int bch2_bucket_do_index(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c alloc_k, const struct bch_alloc_v4 *a, bool set) { - struct bch_fs *c = trans->c; - struct btree_iter iter; - struct bkey_s_c old; - struct bkey_i *k; enum btree_id btree; - enum bch_bkey_type old_type = !set ? KEY_TYPE_set : KEY_TYPE_deleted; - enum bch_bkey_type new_type = set ? KEY_TYPE_set : KEY_TYPE_deleted; - struct printbuf buf = PRINTBUF; - int ret; + struct bpos pos; if (a->data_type != BCH_DATA_free && a->data_type != BCH_DATA_need_discard) return 0; - k = bch2_trans_kmalloc_nomemzero(trans, sizeof(*k)); - if (IS_ERR(k)) - return PTR_ERR(k); - - bkey_init(&k->k); - k->k.type = new_type; - switch (a->data_type) { case BCH_DATA_free: btree = BTREE_ID_freespace; - k->k.p = alloc_freespace_pos(alloc_k.k->p, *a); - bch2_key_resize(&k->k, 1); + pos = alloc_freespace_pos(alloc_k.k->p, *a); break; case BCH_DATA_need_discard: btree = BTREE_ID_need_discard; - k->k.p = alloc_k.k->p; + pos = alloc_k.k->p; break; default: return 0; } - old = bch2_bkey_get_iter(trans, &iter, btree, - bkey_start_pos(&k->k), - BTREE_ITER_intent); - ret = bkey_err(old); + struct btree_iter iter; + struct bkey_s_c old = bch2_bkey_get_iter(trans, &iter, btree, pos, BTREE_ITER_intent); + int ret = bkey_err(old); if (ret) return ret; - if (ca->mi.freespace_initialized && - c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info && - bch2_trans_inconsistent_on(old.k->type != old_type, trans, - "incorrect key when %s %s:%llu:%llu:0 (got %s should be %s)\n" - " for %s", - set ? "setting" : "clearing", - bch2_btree_id_str(btree), - iter.pos.inode, - iter.pos.offset, - bch2_bkey_types[old.k->type], - bch2_bkey_types[old_type], - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { - ret = -EIO; - goto err; - } + need_discard_or_freespace_err_on(ca->mi.freespace_initialized && + !old.k->type != set, + trans, alloc_k, set, + btree == BTREE_ID_need_discard, false); - ret = bch2_trans_update(trans, &iter, k, 0); -err: + ret = bch2_btree_bit_mod_iter(trans, &iter, set); +fsck_err: bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); return ret; } @@ -858,7 +858,10 @@ int bch2_trigger_alloc(struct btree_trans *trans, if (flags & BTREE_TRIGGER_transactional) { alloc_data_type_set(new_a, new_a->data_type); - if (bch2_bucket_sectors_total(*new_a) > bch2_bucket_sectors_total(*old_a)) { + int is_empty_delta = (int) data_type_is_empty(new_a->data_type) - + (int) data_type_is_empty(old_a->data_type); + + if (is_empty_delta < 0) { new_a->io_time[READ] = bch2_current_io_time(c, READ); new_a->io_time[WRITE]= bch2_current_io_time(c, WRITE); SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, true); @@ -928,37 +931,55 @@ int bch2_trigger_alloc(struct btree_trans *trans, } if ((flags & BTREE_TRIGGER_atomic) && (flags & BTREE_TRIGGER_insert)) { - u64 journal_seq = trans->journal_res.seq; - u64 bucket_journal_seq = new_a->journal_seq; + u64 transaction_seq = trans->journal_res.seq; + BUG_ON(!transaction_seq); - if ((flags & BTREE_TRIGGER_insert) && - data_type_is_empty(old_a->data_type) != - data_type_is_empty(new_a->data_type) && - new.k->type == KEY_TYPE_alloc_v4) { - struct bch_alloc_v4 *v = bkey_s_to_alloc_v4(new).v; + if (log_fsck_err_on(transaction_seq && new_a->journal_seq_nonempty > transaction_seq, + trans, alloc_key_journal_seq_in_future, + "bucket journal seq in future (currently at %llu)\n%s", + journal_cur_seq(&c->journal), + (bch2_bkey_val_to_text(&buf, c, new.s_c), buf.buf))) + new_a->journal_seq_nonempty = transaction_seq; - /* - * If the btree updates referring to a bucket weren't flushed - * before the bucket became empty again, then the we don't have - * to wait on a journal flush before we can reuse the bucket: - */ - v->journal_seq = bucket_journal_seq = - data_type_is_empty(new_a->data_type) && - (journal_seq == v->journal_seq || - bch2_journal_noflush_seq(&c->journal, v->journal_seq)) - ? 0 : journal_seq; + int is_empty_delta = (int) data_type_is_empty(new_a->data_type) - + (int) data_type_is_empty(old_a->data_type); + + /* + * Record journal sequence number of empty -> nonempty transition: + * Note that there may be multiple empty -> nonempty + * transitions, data in a bucket may be overwritten while we're + * still writing to it - so be careful to only record the first: + * */ + if (is_empty_delta < 0 && + new_a->journal_seq_empty <= c->journal.flushed_seq_ondisk) { + new_a->journal_seq_nonempty = transaction_seq; + new_a->journal_seq_empty = 0; } - if (!data_type_is_empty(old_a->data_type) && - data_type_is_empty(new_a->data_type) && - bucket_journal_seq) { - ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, - c->journal.flushed_seq_ondisk, - new.k->p.inode, new.k->p.offset, - bucket_journal_seq); - if (bch2_fs_fatal_err_on(ret, c, - "setting bucket_needs_journal_commit: %s", bch2_err_str(ret))) - goto err; + /* + * Bucket becomes empty: mark it as waiting for a journal flush, + * unless updates since empty -> nonempty transition were never + * flushed - we may need to ask the journal not to flush + * intermediate sequence numbers: + */ + if (is_empty_delta > 0) { + if (new_a->journal_seq_nonempty == transaction_seq || + bch2_journal_noflush_seq(&c->journal, + new_a->journal_seq_nonempty, + transaction_seq)) { + new_a->journal_seq_nonempty = new_a->journal_seq_empty = 0; + } else { + new_a->journal_seq_empty = transaction_seq; + + ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, + c->journal.flushed_seq_ondisk, + new.k->p.inode, new.k->p.offset, + transaction_seq); + if (bch2_fs_fatal_err_on(ret, c, + "setting bucket_needs_journal_commit: %s", + bch2_err_str(ret))) + goto err; + } } if (new_a->gen != old_a->gen) { @@ -974,7 +995,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, #define eval_state(_a, expr) ({ const struct bch_alloc_v4 *a = _a; expr; }) #define statechange(expr) !eval_state(old_a, expr) && eval_state(new_a, expr) -#define bucket_flushed(a) (!a->journal_seq || a->journal_seq <= c->journal.flushed_seq_ondisk) +#define bucket_flushed(a) (a->journal_seq_empty <= c->journal.flushed_seq_ondisk) if (statechange(a->data_type == BCH_DATA_free) && bucket_flushed(new_a)) @@ -1006,6 +1027,7 @@ int bch2_trigger_alloc(struct btree_trans *trans, rcu_read_unlock(); } err: +fsck_err: printbuf_exit(&buf); bch2_dev_put(ca); return ret; @@ -1045,7 +1067,7 @@ static struct bkey_s_c bch2_get_key_or_hole(struct btree_iter *iter, struct bpos * btree node min/max is a closed interval, upto takes a half * open interval: */ - k = bch2_btree_iter_peek_upto(&iter2, end); + k = bch2_btree_iter_peek_max(&iter2, end); next = iter2.pos; bch2_trans_iter_exit(iter->trans, &iter2); @@ -1129,7 +1151,6 @@ int bch2_check_alloc_key(struct btree_trans *trans, struct bch_fs *c = trans->c; struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a; - unsigned discard_key_type, freespace_key_type; unsigned gens_offset; struct bkey_s_c k; struct printbuf buf = PRINTBUF; @@ -1149,64 +1170,30 @@ int bch2_check_alloc_key(struct btree_trans *trans, a = bch2_alloc_to_v4(alloc_k, &a_convert); - discard_key_type = a->data_type == BCH_DATA_need_discard ? KEY_TYPE_set : 0; bch2_btree_iter_set_pos(discard_iter, alloc_k.k->p); k = bch2_btree_iter_peek_slot(discard_iter); ret = bkey_err(k); if (ret) goto err; - if (fsck_err_on(k.k->type != discard_key_type, - trans, need_discard_key_wrong, - "incorrect key in need_discard btree (got %s should be %s)\n" - " %s", - bch2_bkey_types[k.k->type], - bch2_bkey_types[discard_key_type], - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { - struct bkey_i *update = - bch2_trans_kmalloc(trans, sizeof(*update)); - - ret = PTR_ERR_OR_ZERO(update); - if (ret) - goto err; - - bkey_init(&update->k); - update->k.type = discard_key_type; - update->k.p = discard_iter->pos; - - ret = bch2_trans_update(trans, discard_iter, update, 0); + bool is_discarded = a->data_type == BCH_DATA_need_discard; + if (need_discard_or_freespace_err_on(!!k.k->type != is_discarded, + trans, alloc_k, !is_discarded, true, true)) { + ret = bch2_btree_bit_mod_iter(trans, discard_iter, is_discarded); if (ret) goto err; } - freespace_key_type = a->data_type == BCH_DATA_free ? KEY_TYPE_set : 0; bch2_btree_iter_set_pos(freespace_iter, alloc_freespace_pos(alloc_k.k->p, *a)); k = bch2_btree_iter_peek_slot(freespace_iter); ret = bkey_err(k); if (ret) goto err; - if (fsck_err_on(k.k->type != freespace_key_type, - trans, freespace_key_wrong, - "incorrect key in freespace btree (got %s should be %s)\n" - " %s", - bch2_bkey_types[k.k->type], - bch2_bkey_types[freespace_key_type], - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { - struct bkey_i *update = - bch2_trans_kmalloc(trans, sizeof(*update)); - - ret = PTR_ERR_OR_ZERO(update); - if (ret) - goto err; - - bkey_init(&update->k); - update->k.type = freespace_key_type; - update->k.p = freespace_iter->pos; - bch2_key_resize(&update->k, 1); - - ret = bch2_trans_update(trans, freespace_iter, update, 0); + bool is_free = a->data_type == BCH_DATA_free; + if (need_discard_or_freespace_err_on(!!k.k->type != is_free, + trans, alloc_k, !is_free, false, true)) { + ret = bch2_btree_bit_mod_iter(trans, freespace_iter, is_free); if (ret) goto err; } @@ -1368,51 +1355,88 @@ fsck_err: return ret; } -static noinline_for_stack int bch2_check_discard_freespace_key(struct btree_trans *trans, - struct btree_iter *iter) +struct check_discard_freespace_key_async { + struct work_struct work; + struct bch_fs *c; + struct bbpos pos; +}; + +static int bch2_recheck_discard_freespace_key(struct btree_trans *trans, struct bbpos pos) +{ + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, pos.btree, pos.pos, 0); + int ret = bkey_err(k); + if (ret) + return ret; + + u8 gen; + ret = k.k->type != KEY_TYPE_set + ? bch2_check_discard_freespace_key(trans, &iter, &gen, false) + : 0; + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +static void check_discard_freespace_key_work(struct work_struct *work) +{ + struct check_discard_freespace_key_async *w = + container_of(work, struct check_discard_freespace_key_async, work); + + bch2_trans_do(w->c, bch2_recheck_discard_freespace_key(trans, w->pos)); + bch2_write_ref_put(w->c, BCH_WRITE_REF_check_discard_freespace_key); + kfree(w); +} + +int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_iter *iter, u8 *gen, + bool async_repair) { struct bch_fs *c = trans->c; - struct btree_iter alloc_iter; - struct bkey_s_c alloc_k; - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a; - u64 genbits; - struct bpos pos; enum bch_data_type state = iter->btree_id == BTREE_ID_need_discard ? BCH_DATA_need_discard : BCH_DATA_free; struct printbuf buf = PRINTBUF; - int ret; - pos = iter->pos; - pos.offset &= ~(~0ULL << 56); - genbits = iter->pos.offset & (~0ULL << 56); + struct bpos bucket = iter->pos; + bucket.offset &= ~(~0ULL << 56); + u64 genbits = iter->pos.offset & (~0ULL << 56); - alloc_k = bch2_bkey_get_iter(trans, &alloc_iter, BTREE_ID_alloc, pos, 0); - ret = bkey_err(alloc_k); + struct btree_iter alloc_iter; + struct bkey_s_c alloc_k = bch2_bkey_get_iter(trans, &alloc_iter, + BTREE_ID_alloc, bucket, + async_repair ? BTREE_ITER_cached : 0); + int ret = bkey_err(alloc_k); if (ret) return ret; - if (fsck_err_on(!bch2_dev_bucket_exists(c, pos), - trans, need_discard_freespace_key_to_invalid_dev_bucket, - "entry in %s btree for nonexistant dev:bucket %llu:%llu", - bch2_btree_id_str(iter->btree_id), pos.inode, pos.offset)) - goto delete; + if (!bch2_dev_bucket_exists(c, bucket)) { + if (fsck_err(trans, need_discard_freespace_key_to_invalid_dev_bucket, + "entry in %s btree for nonexistant dev:bucket %llu:%llu", + bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset)) + goto delete; + ret = 1; + goto out; + } - a = bch2_alloc_to_v4(alloc_k, &a_convert); + struct bch_alloc_v4 a_convert; + const struct bch_alloc_v4 *a = bch2_alloc_to_v4(alloc_k, &a_convert); + + if (a->data_type != state || + (state == BCH_DATA_free && + genbits != alloc_freespace_genbits(*a))) { + if (fsck_err(trans, need_discard_freespace_key_bad, + "%s\n incorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", + (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), + bch2_btree_id_str(iter->btree_id), + iter->pos.inode, + iter->pos.offset, + a->data_type == state, + genbits >> 56, alloc_freespace_genbits(*a) >> 56)) + goto delete; + ret = 1; + goto out; + } - if (fsck_err_on(a->data_type != state || - (state == BCH_DATA_free && - genbits != alloc_freespace_genbits(*a)), - trans, need_discard_freespace_key_bad, - "%s\n incorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), - bch2_btree_id_str(iter->btree_id), - iter->pos.inode, - iter->pos.offset, - a->data_type == state, - genbits >> 56, alloc_freespace_genbits(*a) >> 56)) - goto delete; + *gen = a->gen; out: fsck_err: bch2_set_btree_iter_dontneed(&alloc_iter); @@ -1420,11 +1444,40 @@ fsck_err: printbuf_exit(&buf); return ret; delete: - ret = bch2_btree_delete_extent_at(trans, iter, - iter->btree_id == BTREE_ID_freespace ? 1 : 0, 0) ?: - bch2_trans_commit(trans, NULL, NULL, - BCH_TRANS_COMMIT_no_enospc); - goto out; + if (!async_repair) { + ret = bch2_btree_bit_mod_iter(trans, iter, false) ?: + bch2_trans_commit(trans, NULL, NULL, + BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_commit; + goto out; + } else { + /* + * We can't repair here when called from the allocator path: the + * commit will recurse back into the allocator + */ + struct check_discard_freespace_key_async *w = + kzalloc(sizeof(*w), GFP_KERNEL); + if (!w) + goto out; + + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_check_discard_freespace_key)) { + kfree(w); + goto out; + } + + INIT_WORK(&w->work, check_discard_freespace_key_work); + w->c = c; + w->pos = BBPOS(iter->btree_id, iter->pos); + queue_work(c->write_ref_wq, &w->work); + goto out; + } +} + +static int bch2_check_discard_freespace_key_fsck(struct btree_trans *trans, struct btree_iter *iter) +{ + u8 gen; + int ret = bch2_check_discard_freespace_key(trans, iter, &gen, false); + return ret < 0 ? ret : 0; } /* @@ -1581,7 +1634,7 @@ bkey_err: ret = for_each_btree_key(trans, iter, BTREE_ID_need_discard, POS_MIN, BTREE_ITER_prefetch, k, - bch2_check_discard_freespace_key(trans, &iter)); + bch2_check_discard_freespace_key_fsck(trans, &iter)); if (ret) goto err; @@ -1594,7 +1647,7 @@ bkey_err: break; ret = bkey_err(k) ?: - bch2_check_discard_freespace_key(trans, &iter); + bch2_check_discard_freespace_key_fsck(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { ret = 0; continue; @@ -1757,7 +1810,8 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, struct bch_dev *ca, struct btree_iter *need_discard_iter, struct bpos *discard_pos_done, - struct discard_buckets_state *s) + struct discard_buckets_state *s, + bool fastpath) { struct bch_fs *c = trans->c; struct bpos pos = need_discard_iter->pos; @@ -1793,44 +1847,23 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, if (ret) goto out; - if (bch2_bucket_sectors_total(a->v)) { - if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, - trans, "attempting to discard bucket with dirty data\n%s", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = -EIO; - goto out; - } - if (a->v.data_type != BCH_DATA_need_discard) { - if (data_type_is_empty(a->v.data_type) && - BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) { - a->v.gen++; - SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false); - goto write; + if (need_discard_or_freespace_err(trans, k, true, true, true)) { + ret = bch2_btree_bit_mod_iter(trans, need_discard_iter, false); + if (ret) + goto out; + goto commit; } - if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, - trans, "bucket incorrectly set in need_discard btree\n" - "%s", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = -EIO; goto out; } - if (a->v.journal_seq > c->journal.flushed_seq_ondisk) { - if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, - trans, "clearing need_discard but journal_seq %llu > flushed_seq %llu\n%s", - a->v.journal_seq, - c->journal.flushed_seq_ondisk, - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = -EIO; - goto out; - } - - if (discard_in_flight_add(ca, iter.pos.offset, true)) - goto out; + if (!fastpath) { + if (discard_in_flight_add(ca, iter.pos.offset, true)) + goto out; - discard_locked = true; + discard_locked = true; + } if (!bkey_eq(*discard_pos_done, iter.pos) && ca->mi.discard && !c->opts.nochanges) { @@ -1844,6 +1877,7 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, ca->mi.bucket_size, GFP_KERNEL); *discard_pos_done = iter.pos; + s->discarded++; ret = bch2_trans_relock_notrace(trans); if (ret) @@ -1851,22 +1885,25 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, } SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); -write: alloc_data_type_set(&a->v, a->v.data_type); - ret = bch2_trans_update(trans, &iter, &a->k_i, 0) ?: - bch2_trans_commit(trans, NULL, NULL, - BCH_WATERMARK_btree| - BCH_TRANS_COMMIT_no_enospc); + ret = bch2_trans_update(trans, &iter, &a->k_i, 0); + if (ret) + goto out; +commit: + ret = bch2_trans_commit(trans, NULL, NULL, + BCH_WATERMARK_btree| + BCH_TRANS_COMMIT_no_enospc); if (ret) goto out; count_event(c, bucket_discard); - s->discarded++; out: +fsck_err: if (discard_locked) discard_in_flight_remove(ca, iter.pos.offset); - s->seen++; + if (!ret) + s->seen++; bch2_trans_iter_exit(trans, &iter); printbuf_exit(&buf); return ret; @@ -1886,11 +1923,11 @@ static void bch2_do_discards_work(struct work_struct *work) * successful commit: */ ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, + for_each_btree_key_max(trans, iter, BTREE_ID_need_discard, POS(ca->dev_idx, 0), POS(ca->dev_idx, U64_MAX), 0, k, - bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s))); + bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s, false))); trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); @@ -1923,27 +1960,29 @@ void bch2_do_discards(struct bch_fs *c) bch2_dev_do_discards(ca); } -static int bch2_clear_bucket_needs_discard(struct btree_trans *trans, struct bpos bucket) +static int bch2_do_discards_fast_one(struct btree_trans *trans, + struct bch_dev *ca, + u64 bucket, + struct bpos *discard_pos_done, + struct discard_buckets_state *s) { - struct btree_iter iter; - bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, bucket, BTREE_ITER_intent); - struct bkey_s_c k = bch2_btree_iter_peek_slot(&iter); - int ret = bkey_err(k); + struct btree_iter need_discard_iter; + struct bkey_s_c discard_k = bch2_bkey_get_iter(trans, &need_discard_iter, + BTREE_ID_need_discard, POS(ca->dev_idx, bucket), 0); + int ret = bkey_err(discard_k); if (ret) - goto err; - - struct bkey_i_alloc_v4 *a = bch2_alloc_to_v4_mut(trans, k); - ret = PTR_ERR_OR_ZERO(a); - if (ret) - goto err; + return ret; - BUG_ON(a->v.dirty_sectors); - SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); - alloc_data_type_set(&a->v, a->v.data_type); + if (log_fsck_err_on(discard_k.k->type != KEY_TYPE_set, + trans, discarding_bucket_not_in_need_discard_btree, + "attempting to discard bucket %u:%llu not in need_discard btree", + ca->dev_idx, bucket)) + goto out; - ret = bch2_trans_update(trans, &iter, &a->k_i, 0); -err: - bch2_trans_iter_exit(trans, &iter); + ret = bch2_discard_one_bucket(trans, ca, &need_discard_iter, discard_pos_done, s, true); +out: +fsck_err: + bch2_trans_iter_exit(trans, &need_discard_iter); return ret; } @@ -1951,6 +1990,10 @@ static void bch2_do_discards_fast_work(struct work_struct *work) { struct bch_dev *ca = container_of(work, struct bch_dev, discard_fast_work); struct bch_fs *c = ca->fs; + struct discard_buckets_state s = {}; + struct bpos discard_pos_done = POS_MAX; + struct btree_trans *trans = bch2_trans_get(c); + int ret = 0; while (1) { bool got_bucket = false; @@ -1971,16 +2014,8 @@ static void bch2_do_discards_fast_work(struct work_struct *work) if (!got_bucket) break; - if (ca->mi.discard && !c->opts.nochanges) - blkdev_issue_discard(ca->disk_sb.bdev, - bucket_to_sector(ca, bucket), - ca->mi.bucket_size, - GFP_KERNEL); - - int ret = bch2_trans_commit_do(c, NULL, NULL, - BCH_WATERMARK_btree| - BCH_TRANS_COMMIT_no_enospc, - bch2_clear_bucket_needs_discard(trans, POS(ca->dev_idx, bucket))); + ret = lockrestart_do(trans, + bch2_do_discards_fast_one(trans, ca, bucket, &discard_pos_done, &s)); bch_err_fn(c, ret); discard_in_flight_remove(ca, bucket); @@ -1989,6 +2024,9 @@ static void bch2_do_discards_fast_work(struct work_struct *work) break; } + trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); + + bch2_trans_put(trans); percpu_ref_put(&ca->io_ref); bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); } @@ -2030,8 +2068,11 @@ static int invalidate_one_bucket(struct btree_trans *trans, return 1; if (!bch2_dev_bucket_exists(c, bucket)) { - prt_str(&buf, "lru entry points to invalid bucket"); - goto err; + if (fsck_err(trans, lru_entry_to_invalid_bucket, + "lru key points to nonexistent device:bucket %llu:%llu", + bucket.inode, bucket.offset)) + return bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false); + goto out; } if (bch2_bucket_is_open_safe(c, bucket.inode, bucket.offset)) @@ -2072,28 +2113,9 @@ static int invalidate_one_bucket(struct btree_trans *trans, trace_and_count(c, bucket_invalidate, c, bucket.inode, bucket.offset, cached_sectors); --*nr_to_invalidate; out: +fsck_err: printbuf_exit(&buf); return ret; -err: - prt_str(&buf, "\n lru key: "); - bch2_bkey_val_to_text(&buf, c, lru_k); - - prt_str(&buf, "\n lru entry: "); - bch2_lru_pos_to_text(&buf, lru_iter->pos); - - prt_str(&buf, "\n alloc key: "); - if (!a) - bch2_bpos_to_text(&buf, bucket); - else - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&a->k_i)); - - bch_err(c, "%s", buf.buf); - if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_lrus) { - bch2_inconsistent_error(c); - ret = -EINVAL; - } - - goto out; } static struct bkey_s_c next_lru_key(struct btree_trans *trans, struct btree_iter *iter, @@ -2101,7 +2123,7 @@ static struct bkey_s_c next_lru_key(struct btree_trans *trans, struct btree_iter { struct bkey_s_c k; again: - k = bch2_btree_iter_peek_upto(iter, lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX)); + k = bch2_btree_iter_peek_max(iter, lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX)); if (!k.k && !*wrapped) { bch2_btree_iter_set_pos(iter, lru_pos(ca->dev_idx, 0, 0)); *wrapped = true; diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index 163a67b97a40..de25ba4ee94b 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -8,8 +8,6 @@ #include "debug.h" #include "super.h" -enum bch_validate_flags; - /* How out of date a pointer gen is allowed to be: */ #define BUCKET_GC_GEN_MAX 96U @@ -245,10 +243,14 @@ struct bkey_i_alloc_v4 *bch2_alloc_to_v4_mut(struct btree_trans *, struct bkey_s int bch2_bucket_io_time_reset(struct btree_trans *, unsigned, size_t, int); -int bch2_alloc_v1_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int bch2_alloc_v2_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int bch2_alloc_v3_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_alloc_v1_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_alloc_v2_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_alloc_v3_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_alloc_v4_swab(struct bkey_s); void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); @@ -282,7 +284,7 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); }) int bch2_bucket_gens_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_bucket_gens_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_bucket_gens ((struct bkey_ops) { \ @@ -307,6 +309,8 @@ int bch2_alloc_key_to_dev_counters(struct btree_trans *, struct bch_dev *, int bch2_trigger_alloc(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); + +int bch2_check_discard_freespace_key(struct btree_trans *, struct btree_iter *, u8 *, bool); int bch2_check_alloc_info(struct bch_fs *); int bch2_check_alloc_to_lru_refs(struct bch_fs *); void bch2_dev_do_discards(struct bch_dev *); diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h index befdaa95c515..740238369a5a 100644 --- a/fs/bcachefs/alloc_background_format.h +++ b/fs/bcachefs/alloc_background_format.h @@ -58,7 +58,7 @@ LE32_BITMASK(BCH_ALLOC_V3_NEED_INC_GEN,struct bch_alloc_v3, flags, 1, 2) struct bch_alloc_v4 { struct bch_val v; - __u64 journal_seq; + __u64 journal_seq_nonempty; __u32 flags; __u8 gen; __u8 oldest_gen; @@ -70,7 +70,7 @@ struct bch_alloc_v4 { __u32 stripe; __u32 nr_external_backpointers; /* end of fields in original version of alloc_v4 */ - __u64 _fragmentation_lru; /* obsolete */ + __u64 journal_seq_empty; __u32 stripe_sectors; __u32 pad; } __packed __aligned(8); diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 372178c8d416..6df41c331a52 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -107,14 +107,10 @@ void __bch2_open_bucket_put(struct bch_fs *c, struct open_bucket *ob) return; } - percpu_down_read(&c->mark_lock); spin_lock(&ob->lock); - ob->valid = false; ob->data_type = 0; - spin_unlock(&ob->lock); - percpu_up_read(&c->mark_lock); spin_lock(&c->freelist_lock); bch2_open_bucket_hash_remove(c, ob); @@ -156,6 +152,14 @@ static struct open_bucket *bch2_open_bucket_alloc(struct bch_fs *c) return ob; } +static inline bool is_superblock_bucket(struct bch_fs *c, struct bch_dev *ca, u64 b) +{ + if (c->curr_recovery_pass > BCH_RECOVERY_PASS_trans_mark_dev_sbs) + return false; + + return bch2_is_superblock_bucket(ca, b); +} + static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob) { BUG_ON(c->open_buckets_partial_nr >= @@ -175,20 +179,6 @@ static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob) closure_wake_up(&c->freelist_wait); } -/* _only_ for allocating the journal on a new device: */ -long bch2_bucket_alloc_new_fs(struct bch_dev *ca) -{ - while (ca->new_fs_bucket_idx < ca->mi.nbuckets) { - u64 b = ca->new_fs_bucket_idx++; - - if (!is_superblock_bucket(ca, b) && - (!ca->buckets_nouse || !test_bit(b, ca->buckets_nouse))) - return b; - } - - return -1; -} - static inline unsigned open_buckets_reserved(enum bch_watermark watermark) { switch (watermark) { @@ -206,33 +196,40 @@ static inline unsigned open_buckets_reserved(enum bch_watermark watermark) } } -static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev *ca, - u64 bucket, - enum bch_watermark watermark, - const struct bch_alloc_v4 *a, - struct bucket_alloc_state *s, - struct closure *cl) +static inline bool may_alloc_bucket(struct bch_fs *c, + struct bpos bucket, + struct bucket_alloc_state *s) { - struct open_bucket *ob; - - if (unlikely(ca->buckets_nouse && test_bit(bucket, ca->buckets_nouse))) { - s->skipped_nouse++; - return NULL; - } - - if (bch2_bucket_is_open(c, ca->dev_idx, bucket)) { + if (bch2_bucket_is_open(c, bucket.inode, bucket.offset)) { s->skipped_open++; - return NULL; + return false; } if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, - c->journal.flushed_seq_ondisk, ca->dev_idx, bucket)) { + c->journal.flushed_seq_ondisk, bucket.inode, bucket.offset)) { s->skipped_need_journal_commit++; - return NULL; + return false; } - if (bch2_bucket_nocow_is_locked(&c->nocow_locks, POS(ca->dev_idx, bucket))) { + if (bch2_bucket_nocow_is_locked(&c->nocow_locks, bucket)) { s->skipped_nocow++; + return false; + } + + return true; +} + +static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev *ca, + u64 bucket, u8 gen, + enum bch_watermark watermark, + struct bucket_alloc_state *s, + struct closure *cl) +{ + if (unlikely(is_superblock_bucket(c, ca, bucket))) + return NULL; + + if (unlikely(ca->buckets_nouse && test_bit(bucket, ca->buckets_nouse))) { + s->skipped_nouse++; return NULL; } @@ -254,14 +251,13 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev * return NULL; } - ob = bch2_open_bucket_alloc(c); + struct open_bucket *ob = bch2_open_bucket_alloc(c); spin_lock(&ob->lock); - ob->valid = true; ob->sectors_free = ca->mi.bucket_size; ob->dev = ca->dev_idx; - ob->gen = a->gen; + ob->gen = gen; ob->bucket = bucket; spin_unlock(&ob->lock); @@ -276,111 +272,29 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c, struct bch_dev * } static struct open_bucket *try_alloc_bucket(struct btree_trans *trans, struct bch_dev *ca, - enum bch_watermark watermark, u64 free_entry, + enum bch_watermark watermark, struct bucket_alloc_state *s, - struct bkey_s_c freespace_k, + struct btree_iter *freespace_iter, struct closure *cl) { struct bch_fs *c = trans->c; - struct btree_iter iter = { NULL }; - struct bkey_s_c k; - struct open_bucket *ob; - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a; - u64 b = free_entry & ~(~0ULL << 56); - unsigned genbits = free_entry >> 56; - struct printbuf buf = PRINTBUF; - int ret; - - if (b < ca->mi.first_bucket || b >= ca->mi.nbuckets) { - prt_printf(&buf, "freespace btree has bucket outside allowed range %u-%llu\n" - " freespace key ", - ca->mi.first_bucket, ca->mi.nbuckets); - bch2_bkey_val_to_text(&buf, c, freespace_k); - bch2_trans_inconsistent(trans, "%s", buf.buf); - ob = ERR_PTR(-EIO); - goto err; - } + u64 b = freespace_iter->pos.offset & ~(~0ULL << 56); - k = bch2_bkey_get_iter(trans, &iter, - BTREE_ID_alloc, POS(ca->dev_idx, b), - BTREE_ITER_cached); - ret = bkey_err(k); - if (ret) { - ob = ERR_PTR(ret); - goto err; - } - - a = bch2_alloc_to_v4(k, &a_convert); - - if (a->data_type != BCH_DATA_free) { - if (c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_alloc_info) { - ob = NULL; - goto err; - } - - prt_printf(&buf, "non free bucket in freespace btree\n" - " freespace key "); - bch2_bkey_val_to_text(&buf, c, freespace_k); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, k); - bch2_trans_inconsistent(trans, "%s", buf.buf); - ob = ERR_PTR(-EIO); - goto err; - } - - if (genbits != (alloc_freespace_genbits(*a) >> 56) && - c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info) { - prt_printf(&buf, "bucket in freespace btree with wrong genbits (got %u should be %llu)\n" - " freespace key ", - genbits, alloc_freespace_genbits(*a) >> 56); - bch2_bkey_val_to_text(&buf, c, freespace_k); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, k); - bch2_trans_inconsistent(trans, "%s", buf.buf); - ob = ERR_PTR(-EIO); - goto err; - } - - if (c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_extents_to_backpointers) { - struct bch_backpointer bp; - struct bpos bp_pos = POS_MIN; - - ret = bch2_get_next_backpointer(trans, ca, POS(ca->dev_idx, b), -1, - &bp_pos, &bp, - BTREE_ITER_nopreserve); - if (ret) { - ob = ERR_PTR(ret); - goto err; - } + if (!may_alloc_bucket(c, POS(ca->dev_idx, b), s)) + return NULL; - if (!bkey_eq(bp_pos, POS_MAX)) { - /* - * Bucket may have data in it - we don't call - * bc2h_trans_inconnsistent() because fsck hasn't - * finished yet - */ - ob = NULL; - goto err; - } - } + u8 gen; + int ret = bch2_check_discard_freespace_key(trans, freespace_iter, &gen, true); + if (ret < 0) + return ERR_PTR(ret); + if (ret) + return NULL; - ob = __try_alloc_bucket(c, ca, b, watermark, a, s, cl); - if (!ob) - bch2_set_btree_iter_dontneed(&iter); -err: - if (iter.path) - bch2_set_btree_iter_dontneed(&iter); - bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); - return ob; + return __try_alloc_bucket(c, ca, b, gen, watermark, s, cl); } /* * This path is for before the freespace btree is initialized: - * - * If ca->new_fs_bucket_idx is nonzero, we haven't yet marked superblock & - * journal buckets - journal buckets will be < ca->new_fs_bucket_idx */ static noinline struct open_bucket * bch2_bucket_alloc_early(struct btree_trans *trans, @@ -389,10 +303,11 @@ bch2_bucket_alloc_early(struct btree_trans *trans, struct bucket_alloc_state *s, struct closure *cl) { + struct bch_fs *c = trans->c; struct btree_iter iter, citer; struct bkey_s_c k, ck; struct open_bucket *ob = NULL; - u64 first_bucket = max_t(u64, ca->mi.first_bucket, ca->new_fs_bucket_idx); + u64 first_bucket = ca->mi.first_bucket; u64 *dev_alloc_cursor = &ca->alloc_cursor[s->btree_bitmap]; u64 alloc_start = max(first_bucket, *dev_alloc_cursor); u64 alloc_cursor = alloc_start; @@ -415,10 +330,6 @@ again: if (bkey_ge(k.k->p, POS(ca->dev_idx, ca->mi.nbuckets))) break; - if (ca->new_fs_bucket_idx && - is_superblock_bucket(ca, k.k->p.offset)) - continue; - if (s->btree_bitmap != BTREE_BITMAP_ANY && s->btree_bitmap != bch2_dev_btree_bitmap_marked_sectors(ca, bucket_to_sector(ca, bucket), ca->mi.bucket_size)) { @@ -452,7 +363,10 @@ again: s->buckets_seen++; - ob = __try_alloc_bucket(trans->c, ca, k.k->p.offset, watermark, a, s, cl); + ob = may_alloc_bucket(c, k.k->p, s) + ? __try_alloc_bucket(c, ca, k.k->p.offset, a->gen, + watermark, s, cl) + : NULL; next: bch2_set_btree_iter_dontneed(&citer); bch2_trans_iter_exit(trans, &citer); @@ -489,20 +403,21 @@ static struct open_bucket *bch2_bucket_alloc_freelist(struct btree_trans *trans, u64 alloc_start = max_t(u64, ca->mi.first_bucket, READ_ONCE(*dev_alloc_cursor)); u64 alloc_cursor = alloc_start; int ret; - - BUG_ON(ca->new_fs_bucket_idx); again: - for_each_btree_key_norestart(trans, iter, BTREE_ID_freespace, - POS(ca->dev_idx, alloc_cursor), 0, k, ret) { - if (k.k->p.inode != ca->dev_idx) - break; + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_freespace, + POS(ca->dev_idx, alloc_cursor), + POS(ca->dev_idx, U64_MAX), + 0, k, ret) { + /* + * peek normally dosen't trim extents - they can span iter.pos, + * which is not what we want here: + */ + iter.k.size = iter.k.p.offset - iter.pos.offset; - for (alloc_cursor = max(alloc_cursor, bkey_start_offset(k.k)); - alloc_cursor < k.k->p.offset; - alloc_cursor++) { + while (iter.k.size) { s->buckets_seen++; - u64 bucket = alloc_cursor & ~(~0ULL << 56); + u64 bucket = iter.pos.offset & ~(~0ULL << 56); if (s->btree_bitmap != BTREE_BITMAP_ANY && s->btree_bitmap != bch2_dev_btree_bitmap_marked_sectors(ca, bucket_to_sector(ca, bucket), ca->mi.bucket_size)) { @@ -511,32 +426,36 @@ again: goto fail; bucket = sector_to_bucket(ca, - round_up(bucket_to_sector(ca, bucket) + 1, + round_up(bucket_to_sector(ca, bucket + 1), 1ULL << ca->mi.btree_bitmap_shift)); - u64 genbits = alloc_cursor >> 56; - alloc_cursor = bucket | (genbits << 56); + alloc_cursor = bucket|(iter.pos.offset & (~0ULL << 56)); - if (alloc_cursor > k.k->p.offset) - bch2_btree_iter_set_pos(&iter, POS(ca->dev_idx, alloc_cursor)); + bch2_btree_iter_set_pos(&iter, POS(ca->dev_idx, alloc_cursor)); s->skipped_mi_btree_bitmap++; - continue; + goto next; } - ob = try_alloc_bucket(trans, ca, watermark, - alloc_cursor, s, k, cl); + ob = try_alloc_bucket(trans, ca, watermark, s, &iter, cl); if (ob) { + if (!IS_ERR(ob)) + *dev_alloc_cursor = iter.pos.offset; bch2_set_btree_iter_dontneed(&iter); break; } - } + iter.k.size--; + iter.pos.offset++; + } +next: if (ob || ret) break; } fail: bch2_trans_iter_exit(trans, &iter); - if (!ob && ret) + BUG_ON(ob && ret); + + if (ret) ob = ERR_PTR(ret); if (!ob && alloc_start > ca->mi.first_bucket) { @@ -544,8 +463,6 @@ fail: goto again; } - *dev_alloc_cursor = alloc_cursor; - return ob; } @@ -595,6 +512,7 @@ static noinline void trace_bucket_alloc2(struct bch_fs *c, struct bch_dev *ca, * @watermark: how important is this allocation? * @data_type: BCH_DATA_journal, btree, user... * @cl: if not NULL, closure to be used to wait if buckets not available + * @nowait: if true, do not wait for buckets to become available * @usage: for secondarily also returning the current device usage * * Returns: an open_bucket on success, or an ERR_PTR() on failure. @@ -629,6 +547,10 @@ again: bch2_dev_do_invalidates(ca); if (!avail) { + if (watermark > BCH_WATERMARK_normal && + c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_allocations) + goto alloc; + if (cl && !waiting) { closure_wait(&c->freelist_wait, cl); waiting = true; @@ -711,9 +633,9 @@ struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *c, unsigned i; for_each_set_bit(i, devs->d, BCH_SB_MEMBERS_MAX) - ret.devs[ret.nr++] = i; + ret.data[ret.nr++] = i; - bubble_sort(ret.devs, ret.nr, dev_stripe_cmp); + bubble_sort(ret.data, ret.nr, dev_stripe_cmp); return ret; } @@ -785,18 +707,13 @@ int bch2_bucket_alloc_set_trans(struct btree_trans *trans, struct closure *cl) { struct bch_fs *c = trans->c; - struct dev_alloc_list devs_sorted = - bch2_dev_alloc_list(c, stripe, devs_may_alloc); int ret = -BCH_ERR_insufficient_devices; BUG_ON(*nr_effective >= nr_replicas); - for (unsigned i = 0; i < devs_sorted.nr; i++) { - struct bch_dev_usage usage; - struct open_bucket *ob; - - unsigned dev = devs_sorted.devs[i]; - struct bch_dev *ca = bch2_dev_tryget_noerror(c, dev); + struct dev_alloc_list devs_sorted = bch2_dev_alloc_list(c, stripe, devs_may_alloc); + darray_for_each(devs_sorted, i) { + struct bch_dev *ca = bch2_dev_tryget_noerror(c, *i); if (!ca) continue; @@ -805,8 +722,9 @@ int bch2_bucket_alloc_set_trans(struct btree_trans *trans, continue; } - ob = bch2_bucket_alloc_trans(trans, ca, watermark, data_type, - cl, flags & BCH_WRITE_ALLOC_NOWAIT, &usage); + struct bch_dev_usage usage; + struct open_bucket *ob = bch2_bucket_alloc_trans(trans, ca, watermark, data_type, + cl, flags & BCH_WRITE_ALLOC_NOWAIT, &usage); if (!IS_ERR(ob)) bch2_dev_stripe_increment_inlined(ca, stripe, &usage); bch2_dev_put(ca); @@ -850,10 +768,6 @@ static int bucket_alloc_from_stripe(struct btree_trans *trans, struct closure *cl) { struct bch_fs *c = trans->c; - struct dev_alloc_list devs_sorted; - struct ec_stripe_head *h; - struct open_bucket *ob; - unsigned i, ec_idx; int ret = 0; if (nr_replicas < 2) @@ -862,34 +776,32 @@ static int bucket_alloc_from_stripe(struct btree_trans *trans, if (ec_open_bucket(c, ptrs)) return 0; - h = bch2_ec_stripe_head_get(trans, target, 0, nr_replicas - 1, watermark, cl); + struct ec_stripe_head *h = + bch2_ec_stripe_head_get(trans, target, 0, nr_replicas - 1, watermark, cl); if (IS_ERR(h)) return PTR_ERR(h); if (!h) return 0; - devs_sorted = bch2_dev_alloc_list(c, &wp->stripe, devs_may_alloc); - - for (i = 0; i < devs_sorted.nr; i++) - for (ec_idx = 0; ec_idx < h->s->nr_data; ec_idx++) { + struct dev_alloc_list devs_sorted = bch2_dev_alloc_list(c, &wp->stripe, devs_may_alloc); + darray_for_each(devs_sorted, i) + for (unsigned ec_idx = 0; ec_idx < h->s->nr_data; ec_idx++) { if (!h->s->blocks[ec_idx]) continue; - ob = c->open_buckets + h->s->blocks[ec_idx]; - if (ob->dev == devs_sorted.devs[i] && - !test_and_set_bit(ec_idx, h->s->blocks_allocated)) - goto got_bucket; + struct open_bucket *ob = c->open_buckets + h->s->blocks[ec_idx]; + if (ob->dev == *i && !test_and_set_bit(ec_idx, h->s->blocks_allocated)) { + ob->ec_idx = ec_idx; + ob->ec = h->s; + ec_stripe_new_get(h->s, STRIPE_REF_io); + + ret = add_new_bucket(c, ptrs, devs_may_alloc, + nr_replicas, nr_effective, + have_cache, ob); + goto out; + } } - goto out_put_head; -got_bucket: - ob->ec_idx = ec_idx; - ob->ec = h->s; - ec_stripe_new_get(h->s, STRIPE_REF_io); - - ret = add_new_bucket(c, ptrs, devs_may_alloc, - nr_replicas, nr_effective, - have_cache, ob); -out_put_head: +out: bch2_ec_stripe_head_put(c, h); return ret; } diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h index 1a16fd5bd4f8..f25481a0d1a0 100644 --- a/fs/bcachefs/alloc_foreground.h +++ b/fs/bcachefs/alloc_foreground.h @@ -20,7 +20,7 @@ void bch2_reset_alloc_cursors(struct bch_fs *); struct dev_alloc_list { unsigned nr; - u8 devs[BCH_SB_MEMBERS_MAX]; + u8 data[BCH_SB_MEMBERS_MAX]; }; struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *, @@ -28,8 +28,6 @@ struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *, struct bch_devs_mask *); void bch2_dev_stripe_increment(struct bch_dev *, struct dev_stripe_state *); -long bch2_bucket_alloc_new_fs(struct bch_dev *); - static inline struct bch_dev *ob_dev(struct bch_fs *c, struct open_bucket *ob) { return bch2_dev_have_ref(c, ob->dev); diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 654a58132a4d..ebeb6a5ff9d2 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -14,42 +14,8 @@ #include <linux/mm.h> -static bool extent_matches_bp(struct bch_fs *c, - enum btree_id btree_id, unsigned level, - struct bkey_s_c k, - struct bpos bucket, - struct bch_backpointer bp) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry; - struct extent_ptr_decoded p; - - rcu_read_lock(); - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bpos bucket2; - struct bch_backpointer bp2; - - if (p.ptr.cached) - continue; - - struct bch_dev *ca = bch2_dev_rcu(c, p.ptr.dev); - if (!ca) - continue; - - bch2_extent_ptr_to_bp(c, ca, btree_id, level, k, p, entry, &bucket2, &bp2); - if (bpos_eq(bucket, bucket2) && - !memcmp(&bp, &bp2, sizeof(bp))) { - rcu_read_unlock(); - return true; - } - } - rcu_read_unlock(); - - return false; -} - int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); int ret = 0; @@ -59,67 +25,70 @@ int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k, "backpointer level bad: %u >= %u", bp.v->level, BTREE_MAX_DEPTH); - rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp.k->p.inode); - if (!ca) { - /* these will be caught by fsck */ - rcu_read_unlock(); - return 0; - } - - struct bpos bucket = bp_pos_to_bucket(ca, bp.k->p); - struct bpos bp_pos = bucket_pos_to_bp_noerror(ca, bucket, bp.v->bucket_offset); - rcu_read_unlock(); - - bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size || - !bpos_eq(bp.k->p, bp_pos), - c, backpointer_bucket_offset_wrong, - "backpointer bucket_offset wrong"); + bkey_fsck_err_on(bp.k->p.inode == BCH_SB_MEMBER_INVALID, + c, backpointer_dev_bad, + "backpointer for BCH_SB_MEMBER_INVALID"); fsck_err: return ret; } -void bch2_backpointer_to_text(struct printbuf *out, const struct bch_backpointer *bp) +void bch2_backpointer_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { - prt_printf(out, "btree=%s l=%u offset=%llu:%u len=%u pos=", - bch2_btree_id_str(bp->btree_id), - bp->level, - (u64) (bp->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT), - (u32) bp->bucket_offset & ~(~0U << MAX_EXTENT_COMPRESS_RATIO_SHIFT), - bp->bucket_len); - bch2_bpos_to_text(out, bp->pos); -} + struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); -void bch2_backpointer_k_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) -{ rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu_noerror(c, k.k->p.inode); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp.k->p.inode); if (ca) { - struct bpos bucket = bp_pos_to_bucket(ca, k.k->p); + u32 bucket_offset; + struct bpos bucket = bp_pos_to_bucket_and_offset(ca, bp.k->p, &bucket_offset); rcu_read_unlock(); - prt_str(out, "bucket="); - bch2_bpos_to_text(out, bucket); - prt_str(out, " "); + prt_printf(out, "bucket=%llu:%llu:%u ", bucket.inode, bucket.offset, bucket_offset); } else { rcu_read_unlock(); + prt_printf(out, "sector=%llu:%llu ", bp.k->p.inode, bp.k->p.offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT); } - bch2_backpointer_to_text(out, bkey_s_c_to_backpointer(k).v); + bch2_btree_id_level_to_text(out, bp.v->btree_id, bp.v->level); + prt_printf(out, " suboffset=%u len=%u gen=%u pos=", + (u32) bp.k->p.offset & ~(~0U << MAX_EXTENT_COMPRESS_RATIO_SHIFT), + bp.v->bucket_len, + bp.v->bucket_gen); + bch2_bpos_to_text(out, bp.v->pos); } void bch2_backpointer_swab(struct bkey_s k) { struct bkey_s_backpointer bp = bkey_s_to_backpointer(k); - bp.v->bucket_offset = swab40(bp.v->bucket_offset); bp.v->bucket_len = swab32(bp.v->bucket_len); bch2_bpos_swab(&bp.v->pos); } +static bool extent_matches_bp(struct bch_fs *c, + enum btree_id btree_id, unsigned level, + struct bkey_s_c k, + struct bkey_s_c_backpointer bp) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + struct bkey_i_backpointer bp2; + bch2_extent_ptr_to_bp(c, btree_id, level, k, p, entry, &bp2); + + if (bpos_eq(bp.k->p, bp2.k.p) && + !memcmp(bp.v, &bp2.v, sizeof(bp2.v))) + return true; + } + + return false; +} + static noinline int backpointer_mod_err(struct btree_trans *trans, - struct bch_backpointer bp, - struct bkey_s_c bp_k, struct bkey_s_c orig_k, + struct bkey_i_backpointer *new_bp, + struct bkey_s_c found_bp, bool insert) { struct bch_fs *c = trans->c; @@ -127,12 +96,12 @@ static noinline int backpointer_mod_err(struct btree_trans *trans, if (insert) { prt_printf(&buf, "existing backpointer found when inserting "); - bch2_backpointer_to_text(&buf, &bp); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&new_bp->k_i)); prt_newline(&buf); printbuf_indent_add(&buf, 2); prt_printf(&buf, "found "); - bch2_bkey_val_to_text(&buf, c, bp_k); + bch2_bkey_val_to_text(&buf, c, found_bp); prt_newline(&buf); prt_printf(&buf, "for "); @@ -144,11 +113,11 @@ static noinline int backpointer_mod_err(struct btree_trans *trans, printbuf_indent_add(&buf, 2); prt_printf(&buf, "searching for "); - bch2_backpointer_to_text(&buf, &bp); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&new_bp->k_i)); prt_newline(&buf); prt_printf(&buf, "got "); - bch2_bkey_val_to_text(&buf, c, bp_k); + bch2_bkey_val_to_text(&buf, c, found_bp); prt_newline(&buf); prt_printf(&buf, "for "); @@ -167,161 +136,118 @@ static noinline int backpointer_mod_err(struct btree_trans *trans, } int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *trans, - struct bch_dev *ca, - struct bpos bucket, - struct bch_backpointer bp, struct bkey_s_c orig_k, + struct bkey_i_backpointer *bp, bool insert) { struct btree_iter bp_iter; - struct bkey_s_c k; - struct bkey_i_backpointer *bp_k; - int ret; - - bp_k = bch2_trans_kmalloc_nomemzero(trans, sizeof(struct bkey_i_backpointer)); - ret = PTR_ERR_OR_ZERO(bp_k); - if (ret) - return ret; - - bkey_backpointer_init(&bp_k->k_i); - bp_k->k.p = bucket_pos_to_bp(ca, bucket, bp.bucket_offset); - bp_k->v = bp; - - if (!insert) { - bp_k->k.type = KEY_TYPE_deleted; - set_bkey_val_u64s(&bp_k->k, 0); - } - - k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, - bp_k->k.p, + struct bkey_s_c k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, + bp->k.p, BTREE_ITER_intent| BTREE_ITER_slots| BTREE_ITER_with_updates); - ret = bkey_err(k); + int ret = bkey_err(k); if (ret) - goto err; + return ret; if (insert ? k.k->type : (k.k->type != KEY_TYPE_backpointer || - memcmp(bkey_s_c_to_backpointer(k).v, &bp, sizeof(bp)))) { - ret = backpointer_mod_err(trans, bp, k, orig_k, insert); + memcmp(bkey_s_c_to_backpointer(k).v, &bp->v, sizeof(bp->v)))) { + ret = backpointer_mod_err(trans, orig_k, bp, k, insert); if (ret) goto err; } - ret = bch2_trans_update(trans, &bp_iter, &bp_k->k_i, 0); + if (!insert) { + bp->k.type = KEY_TYPE_deleted; + set_bkey_val_u64s(&bp->k, 0); + } + + ret = bch2_trans_update(trans, &bp_iter, &bp->k_i, 0); err: bch2_trans_iter_exit(trans, &bp_iter); return ret; } -/* - * Find the next backpointer >= *bp_offset: - */ -int bch2_get_next_backpointer(struct btree_trans *trans, - struct bch_dev *ca, - struct bpos bucket, int gen, - struct bpos *bp_pos, - struct bch_backpointer *bp, - unsigned iter_flags) +static int bch2_backpointer_del(struct btree_trans *trans, struct bpos pos) { - struct bpos bp_end_pos = bucket_pos_to_bp(ca, bpos_nosnap_successor(bucket), 0); - struct btree_iter alloc_iter = { NULL }, bp_iter = { NULL }; - struct bkey_s_c k; - int ret = 0; - - if (bpos_ge(*bp_pos, bp_end_pos)) - goto done; - - if (gen >= 0) { - k = bch2_bkey_get_iter(trans, &alloc_iter, BTREE_ID_alloc, - bucket, BTREE_ITER_cached|iter_flags); - ret = bkey_err(k); - if (ret) - goto out; - - if (k.k->type != KEY_TYPE_alloc_v4 || - bkey_s_c_to_alloc_v4(k).v->gen != gen) - goto done; - } - - *bp_pos = bpos_max(*bp_pos, bucket_pos_to_bp(ca, bucket, 0)); - - for_each_btree_key_norestart(trans, bp_iter, BTREE_ID_backpointers, - *bp_pos, iter_flags, k, ret) { - if (bpos_ge(k.k->p, bp_end_pos)) - break; + return (likely(!bch2_backpointers_no_use_write_buffer) + ? bch2_btree_delete_at_buffered(trans, BTREE_ID_backpointers, pos) + : bch2_btree_delete(trans, BTREE_ID_backpointers, pos, 0)) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); +} - *bp_pos = k.k->p; - *bp = *bkey_s_c_to_backpointer(k).v; - goto out; - } -done: - *bp_pos = SPOS_MAX; -out: - bch2_trans_iter_exit(trans, &bp_iter); - bch2_trans_iter_exit(trans, &alloc_iter); - return ret; +static inline int bch2_backpointers_maybe_flush(struct btree_trans *trans, + struct bkey_s_c visiting_k, + struct bkey_buf *last_flushed) +{ + return likely(!bch2_backpointers_no_use_write_buffer) + ? bch2_btree_write_buffer_maybe_flush(trans, visiting_k, last_flushed) + : 0; } -static void backpointer_not_found(struct btree_trans *trans, - struct bpos bp_pos, - struct bch_backpointer bp, - struct bkey_s_c k) +static int backpointer_target_not_found(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, + struct bkey_s_c target_k, + struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + int ret = 0; /* * If we're using the btree write buffer, the backpointer we were * looking at may have already been deleted - failure to find what it * pointed to is not an error: */ - if (likely(!bch2_backpointers_no_use_write_buffer)) - return; - - struct bpos bucket; - if (!bp_pos_to_bucket_nodev(c, bp_pos, &bucket)) - return; + ret = last_flushed + ? bch2_backpointers_maybe_flush(trans, bp.s_c, last_flushed) + : 0; + if (ret) + return ret; prt_printf(&buf, "backpointer doesn't match %s it points to:\n ", - bp.level ? "btree node" : "extent"); - prt_printf(&buf, "bucket: "); - bch2_bpos_to_text(&buf, bucket); - prt_printf(&buf, "\n "); + bp.v->level ? "btree node" : "extent"); + bch2_bkey_val_to_text(&buf, c, bp.s_c); - prt_printf(&buf, "backpointer pos: "); - bch2_bpos_to_text(&buf, bp_pos); prt_printf(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, target_k); - bch2_backpointer_to_text(&buf, &bp); - prt_printf(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, k); - if (c->curr_recovery_pass >= BCH_RECOVERY_PASS_check_extents_to_backpointers) - bch_err_ratelimited(c, "%s", buf.buf); - else - bch2_trans_inconsistent(trans, "%s", buf.buf); + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(target_k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + bkey_for_each_ptr_decode(target_k.k, ptrs, p, entry) + if (p.ptr.dev == bp.k->p.inode) { + prt_printf(&buf, "\n "); + struct bkey_i_backpointer bp2; + bch2_extent_ptr_to_bp(c, bp.v->btree_id, bp.v->level, target_k, p, entry, &bp2); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&bp2.k_i)); + } + if (fsck_err(trans, backpointer_to_missing_ptr, + "%s", buf.buf)) + ret = bch2_backpointer_del(trans, bp.k->p); +fsck_err: printbuf_exit(&buf); + return ret; } struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, struct btree_iter *iter, - struct bpos bp_pos, - struct bch_backpointer bp, - unsigned iter_flags) + unsigned iter_flags, + struct bkey_buf *last_flushed) { - if (likely(!bp.level)) { - struct bch_fs *c = trans->c; + struct bch_fs *c = trans->c; - struct bpos bucket; - if (!bp_pos_to_bucket_nodev(c, bp_pos, &bucket)) - return bkey_s_c_err(-EIO); + if (unlikely(bp.v->btree_id >= btree_id_nr_alive(c))) + return bkey_s_c_null; + if (likely(!bp.v->level)) { bch2_trans_node_iter_init(trans, iter, - bp.btree_id, - bp.pos, + bp.v->btree_id, + bp.v->pos, 0, 0, iter_flags); struct bkey_s_c k = bch2_btree_iter_peek_slot(iter); @@ -330,67 +256,64 @@ struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, return k; } - if (k.k && extent_matches_bp(c, bp.btree_id, bp.level, k, bucket, bp)) + if (k.k && + extent_matches_bp(c, bp.v->btree_id, bp.v->level, k, bp)) return k; bch2_trans_iter_exit(trans, iter); - backpointer_not_found(trans, bp_pos, bp, k); - return bkey_s_c_null; + int ret = backpointer_target_not_found(trans, bp, k, last_flushed); + return ret ? bkey_s_c_err(ret) : bkey_s_c_null; } else { - struct btree *b = bch2_backpointer_get_node(trans, iter, bp_pos, bp); + struct btree *b = bch2_backpointer_get_node(trans, bp, iter, last_flushed); + if (IS_ERR_OR_NULL(b)) + return ((struct bkey_s_c) { .k = ERR_CAST(b) }); - if (IS_ERR_OR_NULL(b)) { - bch2_trans_iter_exit(trans, iter); - return IS_ERR(b) ? bkey_s_c_err(PTR_ERR(b)) : bkey_s_c_null; - } return bkey_i_to_s_c(&b->key); } } struct btree *bch2_backpointer_get_node(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, struct btree_iter *iter, - struct bpos bp_pos, - struct bch_backpointer bp) + struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; - BUG_ON(!bp.level); - - struct bpos bucket; - if (!bp_pos_to_bucket_nodev(c, bp_pos, &bucket)) - return ERR_PTR(-EIO); + BUG_ON(!bp.v->level); bch2_trans_node_iter_init(trans, iter, - bp.btree_id, - bp.pos, + bp.v->btree_id, + bp.v->pos, 0, - bp.level - 1, + bp.v->level - 1, 0); struct btree *b = bch2_btree_iter_peek_node(iter); if (IS_ERR_OR_NULL(b)) goto err; - BUG_ON(b->c.level != bp.level - 1); + BUG_ON(b->c.level != bp.v->level - 1); - if (extent_matches_bp(c, bp.btree_id, bp.level, - bkey_i_to_s_c(&b->key), - bucket, bp)) + if (extent_matches_bp(c, bp.v->btree_id, bp.v->level, + bkey_i_to_s_c(&b->key), bp)) return b; if (btree_node_will_make_reachable(b)) { b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node); } else { - backpointer_not_found(trans, bp_pos, bp, bkey_i_to_s_c(&b->key)); - b = NULL; + int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key), last_flushed); + b = ret ? ERR_PTR(ret) : NULL; } err: bch2_trans_iter_exit(trans, iter); return b; } -static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_iter *bp_iter, - struct bkey_s_c k) +static int bch2_check_backpointer_has_valid_bucket(struct btree_trans *trans, struct bkey_s_c k, + struct bkey_buf *last_flushed) { + if (k.k->type != KEY_TYPE_backpointer) + return 0; + struct bch_fs *c = trans->c; struct btree_iter alloc_iter = { NULL }; struct bkey_s_c alloc_k; @@ -399,10 +322,14 @@ static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_ struct bpos bucket; if (!bp_pos_to_bucket_nodev_noerror(c, k.k->p, &bucket)) { + ret = bch2_backpointers_maybe_flush(trans, k, last_flushed); + if (ret) + goto out; + if (fsck_err(trans, backpointer_to_missing_device, "backpointer for missing device:\n%s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = bch2_btree_delete_at(trans, bp_iter, 0); + ret = bch2_backpointer_del(trans, k.k->p); goto out; } @@ -411,13 +338,16 @@ static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_ if (ret) goto out; - if (fsck_err_on(alloc_k.k->type != KEY_TYPE_alloc_v4, - trans, backpointer_to_missing_alloc, - "backpointer for nonexistent alloc key: %llu:%llu:0\n%s", - alloc_iter.pos.inode, alloc_iter.pos.offset, - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - ret = bch2_btree_delete_at(trans, bp_iter, 0); - goto out; + if (alloc_k.k->type != KEY_TYPE_alloc_v4) { + ret = bch2_backpointers_maybe_flush(trans, k, last_flushed); + if (ret) + goto out; + + if (fsck_err(trans, backpointer_to_missing_alloc, + "backpointer for nonexistent alloc key: %llu:%llu:0\n%s", + alloc_iter.pos.inode, alloc_iter.pos.offset, + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + ret = bch2_backpointer_del(trans, k.k->p); } out: fsck_err: @@ -429,18 +359,24 @@ fsck_err: /* verify that every backpointer has a corresponding alloc key */ int bch2_check_btree_backpointers(struct bch_fs *c) { + struct bkey_buf last_flushed; + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers, POS_MIN, 0, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - bch2_check_btree_backpointer(trans, &iter, k))); + bch2_check_backpointer_has_valid_bucket(trans, k, &last_flushed))); + + bch2_bkey_buf_exit(&last_flushed, c); bch_err_fn(c, ret); return ret; } struct extents_to_bp_state { - struct bpos bucket_start; - struct bpos bucket_end; + struct bpos bp_start; + struct bpos bp_end; struct bkey_buf last_flushed; }; @@ -501,9 +437,13 @@ found: goto err; prt_str(&buf, "extents pointing to same space, but first extent checksum bad:"); - prt_printf(&buf, "\n %s ", bch2_btree_id_str(btree)); + prt_printf(&buf, "\n "); + bch2_btree_id_to_text(&buf, btree); + prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, extent); - prt_printf(&buf, "\n %s ", bch2_btree_id_str(o_btree)); + prt_printf(&buf, "\n "); + bch2_btree_id_to_text(&buf, o_btree); + prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, extent2); struct nonce nonce = extent_nonce(extent.k->bversion, p.crc); @@ -524,41 +464,25 @@ err: static int check_bp_exists(struct btree_trans *trans, struct extents_to_bp_state *s, - struct bpos bucket, - struct bch_backpointer bp, + struct bkey_i_backpointer *bp, struct bkey_s_c orig_k) { struct bch_fs *c = trans->c; - struct btree_iter bp_iter = {}; struct btree_iter other_extent_iter = {}; struct printbuf buf = PRINTBUF; - struct bkey_s_c bp_k; - int ret = 0; - struct bch_dev *ca = bch2_dev_bucket_tryget(c, bucket); - if (!ca) { - prt_str(&buf, "extent for nonexistent device:bucket "); - bch2_bpos_to_text(&buf, bucket); - prt_str(&buf, "\n "); - bch2_bkey_val_to_text(&buf, c, orig_k); - bch_err(c, "%s", buf.buf); - ret = -BCH_ERR_fsck_repair_unimplemented; - goto err; - } - - if (bpos_lt(bucket, s->bucket_start) || - bpos_gt(bucket, s->bucket_end)) - goto out; + if (bpos_lt(bp->k.p, s->bp_start) || + bpos_gt(bp->k.p, s->bp_end)) + return 0; - bp_k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, - bucket_pos_to_bp(ca, bucket, bp.bucket_offset), - 0); - ret = bkey_err(bp_k); + struct btree_iter bp_iter; + struct bkey_s_c bp_k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, bp->k.p, 0); + int ret = bkey_err(bp_k); if (ret) goto err; if (bp_k.k->type != KEY_TYPE_backpointer || - memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) { + memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp->v, sizeof(bp->v))) { ret = bch2_btree_write_buffer_maybe_flush(trans, orig_k, &s->last_flushed); if (ret) goto err; @@ -570,7 +494,6 @@ err: fsck_err: bch2_trans_iter_exit(trans, &other_extent_iter); bch2_trans_iter_exit(trans, &bp_iter); - bch2_dev_put(ca); printbuf_exit(&buf); return ret; check_existing_bp: @@ -578,10 +501,10 @@ check_existing_bp: if (bp_k.k->type != KEY_TYPE_backpointer) goto missing; - struct bch_backpointer other_bp = *bkey_s_c_to_backpointer(bp_k).v; + struct bkey_s_c_backpointer other_bp = bkey_s_c_to_backpointer(bp_k); struct bkey_s_c other_extent = - bch2_backpointer_get_key(trans, &other_extent_iter, bp_k.k->p, other_bp, 0); + bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL); ret = bkey_err(other_extent); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) ret = 0; @@ -600,19 +523,23 @@ check_existing_bp: bch_err(c, "%s", buf.buf); if (other_extent.k->size <= orig_k.k->size) { - ret = drop_dev_and_update(trans, other_bp.btree_id, other_extent, bucket.inode); + ret = drop_dev_and_update(trans, other_bp.v->btree_id, + other_extent, bp->k.p.inode); if (ret) goto err; goto out; } else { - ret = drop_dev_and_update(trans, bp.btree_id, orig_k, bucket.inode); + ret = drop_dev_and_update(trans, bp->v.btree_id, orig_k, bp->k.p.inode); if (ret) goto err; goto missing; } } - ret = check_extent_checksum(trans, other_bp.btree_id, other_extent, bp.btree_id, orig_k, bucket.inode); + ret = check_extent_checksum(trans, + other_bp.v->btree_id, other_extent, + bp->v.btree_id, orig_k, + bp->k.p.inode); if (ret < 0) goto err; if (ret) { @@ -620,7 +547,8 @@ check_existing_bp: goto missing; } - ret = check_extent_checksum(trans, bp.btree_id, orig_k, other_bp.btree_id, other_extent, bucket.inode); + ret = check_extent_checksum(trans, bp->v.btree_id, orig_k, + other_bp.v->btree_id, other_extent, bp->k.p.inode); if (ret < 0) goto err; if (ret) { @@ -629,7 +557,7 @@ check_existing_bp: } printbuf_reset(&buf); - prt_printf(&buf, "duplicate extents pointing to same space on dev %llu\n ", bucket.inode); + prt_printf(&buf, "duplicate extents pointing to same space on dev %llu\n ", bp->k.p.inode); bch2_bkey_val_to_text(&buf, c, orig_k); prt_str(&buf, "\n "); bch2_bkey_val_to_text(&buf, c, other_extent); @@ -638,21 +566,15 @@ check_existing_bp: goto err; missing: printbuf_reset(&buf); - prt_printf(&buf, "missing backpointer for btree=%s l=%u ", - bch2_btree_id_str(bp.btree_id), bp.level); + prt_str(&buf, "missing backpointer\n for: "); bch2_bkey_val_to_text(&buf, c, orig_k); - prt_printf(&buf, "\n got: "); + prt_printf(&buf, "\n want: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&bp->k_i)); + prt_printf(&buf, "\n got: "); bch2_bkey_val_to_text(&buf, c, bp_k); - struct bkey_i_backpointer n_bp_k; - bkey_backpointer_init(&n_bp_k.k_i); - n_bp_k.k.p = bucket_pos_to_bp(ca, bucket, bp.bucket_offset); - n_bp_k.v = bp; - prt_printf(&buf, "\n want: "); - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&n_bp_k.k_i)); - if (fsck_err(trans, ptr_to_missing_backpointer, "%s", buf.buf)) - ret = bch2_bucket_backpointer_mod(trans, ca, bucket, bp, orig_k, true); + ret = bch2_bucket_backpointer_mod(trans, orig_k, bp, true); goto out; } @@ -663,31 +585,33 @@ static int check_extent_to_backpointers(struct btree_trans *trans, struct bkey_s_c k) { struct bch_fs *c = trans->c; - struct bkey_ptrs_c ptrs; + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; - int ret; - ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bpos bucket_pos = POS_MIN; - struct bch_backpointer bp; - if (p.ptr.cached) continue; + if (p.ptr.dev == BCH_SB_MEMBER_INVALID) + continue; + rcu_read_lock(); struct bch_dev *ca = bch2_dev_rcu_noerror(c, p.ptr.dev); - if (ca) - bch2_extent_ptr_to_bp(c, ca, btree, level, k, p, entry, &bucket_pos, &bp); + bool check = ca && test_bit(PTR_BUCKET_NR(ca, &p.ptr), ca->bucket_backpointer_mismatches); + bool empty = ca && test_bit(PTR_BUCKET_NR(ca, &p.ptr), ca->bucket_backpointer_empty); rcu_read_unlock(); - if (!ca) - continue; + if (check || empty) { + struct bkey_i_backpointer bp; + bch2_extent_ptr_to_bp(c, btree, level, k, p, entry, &bp); - ret = check_bp_exists(trans, s, bucket_pos, bp, k); - if (ret) - return ret; + int ret = check + ? check_bp_exists(trans, s, &bp, k) + : bch2_bucket_backpointer_mod(trans, k, &bp, true); + if (ret) + return ret; + } } return 0; @@ -896,54 +820,330 @@ static int bch2_check_extents_to_backpointers_pass(struct btree_trans *trans, return 0; } +enum alloc_sector_counter { + ALLOC_dirty, + ALLOC_cached, + ALLOC_stripe, + ALLOC_SECTORS_NR +}; + +static enum alloc_sector_counter data_type_to_alloc_counter(enum bch_data_type t) +{ + switch (t) { + case BCH_DATA_btree: + case BCH_DATA_user: + return ALLOC_dirty; + case BCH_DATA_cached: + return ALLOC_cached; + case BCH_DATA_stripe: + return ALLOC_stripe; + default: + BUG(); + } +} + +static int check_bucket_backpointers_to_extents(struct btree_trans *, struct bch_dev *, struct bpos); + +static int check_bucket_backpointer_mismatch(struct btree_trans *trans, struct bkey_s_c alloc_k, + struct bkey_buf *last_flushed) +{ + struct bch_fs *c = trans->c; + struct bch_alloc_v4 a_convert; + const struct bch_alloc_v4 *a = bch2_alloc_to_v4(alloc_k, &a_convert); + bool need_commit = false; + + if (a->data_type == BCH_DATA_sb || + a->data_type == BCH_DATA_journal || + a->data_type == BCH_DATA_parity) + return 0; + + u32 sectors[ALLOC_SECTORS_NR]; + memset(sectors, 0, sizeof(sectors)); + + struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(trans->c, alloc_k.k->p); + if (!ca) + return 0; + + struct btree_iter iter; + struct bkey_s_c bp_k; + int ret = 0; + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, alloc_k.k->p), + bucket_pos_to_bp_end(ca, alloc_k.k->p), 0, bp_k, ret) { + if (bp_k.k->type != KEY_TYPE_backpointer) + continue; + + struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(bp_k); + + if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_backpointer_bucket_gen && + (bp.v->bucket_gen != a->gen || + bp.v->pad)) { + ret = bch2_backpointer_del(trans, bp_k.k->p); + if (ret) + break; + + need_commit = true; + continue; + } + + if (bp.v->bucket_gen != a->gen) + continue; + + sectors[data_type_to_alloc_counter(bp.v->data_type)] += bp.v->bucket_len; + }; + bch2_trans_iter_exit(trans, &iter); + if (ret) + goto err; + + if (need_commit) { + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + } + + /* Cached pointers don't have backpointers: */ + + if (sectors[ALLOC_dirty] != a->dirty_sectors || + sectors[ALLOC_stripe] != a->stripe_sectors) { + if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_backpointer_bucket_gen) { + ret = bch2_backpointers_maybe_flush(trans, alloc_k, last_flushed); + if (ret) + goto err; + } + + if (sectors[ALLOC_dirty] > a->dirty_sectors || + sectors[ALLOC_stripe] > a->stripe_sectors) { + ret = check_bucket_backpointers_to_extents(trans, ca, alloc_k.k->p) ?: + -BCH_ERR_transaction_restart_nested; + goto err; + } + + if (!sectors[ALLOC_dirty] && + !sectors[ALLOC_stripe]) + __set_bit(alloc_k.k->p.offset, ca->bucket_backpointer_empty); + else + __set_bit(alloc_k.k->p.offset, ca->bucket_backpointer_mismatches); + } +err: + bch2_dev_put(ca); + return ret; +} + +static bool backpointer_node_has_missing(struct bch_fs *c, struct bkey_s_c k) +{ + switch (k.k->type) { + case KEY_TYPE_btree_ptr_v2: { + bool ret = false; + + rcu_read_lock(); + struct bpos pos = bkey_s_c_to_btree_ptr_v2(k).v->min_key; + while (pos.inode <= k.k->p.inode) { + if (pos.inode >= c->sb.nr_devices) + break; + + struct bch_dev *ca = bch2_dev_rcu_noerror(c, pos.inode); + if (!ca) + goto next; + + struct bpos bucket = bp_pos_to_bucket(ca, pos); + bucket.offset = find_next_bit(ca->bucket_backpointer_mismatches, + ca->mi.nbuckets, bucket.offset); + if (bucket.offset == ca->mi.nbuckets) + goto next; + + ret = bpos_le(bucket_pos_to_bp_end(ca, bucket), k.k->p); + if (ret) + break; +next: + pos = SPOS(pos.inode + 1, 0, 0); + } + rcu_read_unlock(); + + return ret; + } + case KEY_TYPE_btree_ptr: + return true; + default: + return false; + } +} + +static int btree_node_get_and_pin(struct btree_trans *trans, struct bkey_i *k, + enum btree_id btree, unsigned level) +{ + struct btree_iter iter; + bch2_trans_node_iter_init(trans, &iter, btree, k->k.p, 0, level, 0); + struct btree *b = bch2_btree_iter_peek_node(&iter); + int ret = PTR_ERR_OR_ZERO(b); + if (ret) + goto err; + + if (b) + bch2_node_pin(trans->c, b); +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +static int bch2_pin_backpointer_nodes_with_missing(struct btree_trans *trans, + struct bpos start, struct bpos *end) +{ + struct bch_fs *c = trans->c; + int ret = 0; + + struct bkey_buf tmp; + bch2_bkey_buf_init(&tmp); + + bch2_btree_cache_unpin(c); + + *end = SPOS_MAX; + + s64 mem_may_pin = mem_may_pin_bytes(c); + struct btree_iter iter; + bch2_trans_node_iter_init(trans, &iter, BTREE_ID_backpointers, start, + 0, 1, BTREE_ITER_prefetch); + ret = for_each_btree_key_continue(trans, iter, 0, k, ({ + if (!backpointer_node_has_missing(c, k)) + continue; + + mem_may_pin -= c->opts.btree_node_size; + if (mem_may_pin <= 0) + break; + + bch2_bkey_buf_reassemble(&tmp, c, k); + struct btree_path *path = btree_iter_path(trans, &iter); + + BUG_ON(path->level != 1); + + bch2_btree_node_prefetch(trans, path, tmp.k, path->btree_id, path->level - 1); + })); + if (ret) + return ret; + + struct bpos pinned = SPOS_MAX; + mem_may_pin = mem_may_pin_bytes(c); + bch2_trans_node_iter_init(trans, &iter, BTREE_ID_backpointers, start, + 0, 1, BTREE_ITER_prefetch); + ret = for_each_btree_key_continue(trans, iter, 0, k, ({ + if (!backpointer_node_has_missing(c, k)) + continue; + + mem_may_pin -= c->opts.btree_node_size; + if (mem_may_pin <= 0) { + *end = pinned; + break; + } + + bch2_bkey_buf_reassemble(&tmp, c, k); + struct btree_path *path = btree_iter_path(trans, &iter); + + BUG_ON(path->level != 1); + + int ret2 = btree_node_get_and_pin(trans, tmp.k, path->btree_id, path->level - 1); + + if (!ret2) + pinned = tmp.k->k.p; + + ret; + })); + if (ret) + return ret; + + return ret; +} + int bch2_check_extents_to_backpointers(struct bch_fs *c) { + int ret = 0; + + /* + * Can't allow devices to come/go/resize while we have bucket bitmaps + * allocated + */ + lockdep_assert_held(&c->state_lock); + + for_each_member_device(c, ca) { + BUG_ON(ca->bucket_backpointer_mismatches); + ca->bucket_backpointer_mismatches = kvcalloc(BITS_TO_LONGS(ca->mi.nbuckets), + sizeof(unsigned long), + GFP_KERNEL); + ca->bucket_backpointer_empty = kvcalloc(BITS_TO_LONGS(ca->mi.nbuckets), + sizeof(unsigned long), + GFP_KERNEL); + if (!ca->bucket_backpointer_mismatches || + !ca->bucket_backpointer_empty) { + bch2_dev_put(ca); + ret = -BCH_ERR_ENOMEM_backpointer_mismatches_bitmap; + goto err_free_bitmaps; + } + } + struct btree_trans *trans = bch2_trans_get(c); - struct extents_to_bp_state s = { .bucket_start = POS_MIN }; - int ret; + struct extents_to_bp_state s = { .bp_start = POS_MIN }; bch2_bkey_buf_init(&s.last_flushed); bkey_init(&s.last_flushed.k->k); + ret = for_each_btree_key(trans, iter, BTREE_ID_alloc, + POS_MIN, BTREE_ITER_prefetch, k, ({ + check_bucket_backpointer_mismatch(trans, k, &s.last_flushed); + })); + if (ret) + goto err; + + u64 nr_buckets = 0, nr_mismatches = 0, nr_empty = 0; + for_each_member_device(c, ca) { + nr_buckets += ca->mi.nbuckets; + nr_mismatches += bitmap_weight(ca->bucket_backpointer_mismatches, ca->mi.nbuckets); + nr_empty += bitmap_weight(ca->bucket_backpointer_empty, ca->mi.nbuckets); + } + + if (!nr_mismatches && !nr_empty) + goto err; + + bch_info(c, "scanning for missing backpointers in %llu/%llu buckets", + nr_mismatches + nr_empty, nr_buckets); + while (1) { - struct bbpos end; - ret = bch2_get_btree_in_memory_pos(trans, - BIT_ULL(BTREE_ID_backpointers), - BIT_ULL(BTREE_ID_backpointers), - BBPOS(BTREE_ID_backpointers, s.bucket_start), &end); + ret = bch2_pin_backpointer_nodes_with_missing(trans, s.bp_start, &s.bp_end); if (ret) break; - s.bucket_end = end.pos; - - if ( bpos_eq(s.bucket_start, POS_MIN) && - !bpos_eq(s.bucket_end, SPOS_MAX)) + if ( bpos_eq(s.bp_start, POS_MIN) && + !bpos_eq(s.bp_end, SPOS_MAX)) bch_verbose(c, "%s(): alloc info does not fit in ram, running in multiple passes with %zu nodes per pass", __func__, btree_nodes_fit_in_ram(c)); - if (!bpos_eq(s.bucket_start, POS_MIN) || - !bpos_eq(s.bucket_end, SPOS_MAX)) { + if (!bpos_eq(s.bp_start, POS_MIN) || + !bpos_eq(s.bp_end, SPOS_MAX)) { struct printbuf buf = PRINTBUF; prt_str(&buf, "check_extents_to_backpointers(): "); - bch2_bpos_to_text(&buf, s.bucket_start); + bch2_bpos_to_text(&buf, s.bp_start); prt_str(&buf, "-"); - bch2_bpos_to_text(&buf, s.bucket_end); + bch2_bpos_to_text(&buf, s.bp_end); bch_verbose(c, "%s", buf.buf); printbuf_exit(&buf); } ret = bch2_check_extents_to_backpointers_pass(trans, &s); - if (ret || bpos_eq(s.bucket_end, SPOS_MAX)) + if (ret || bpos_eq(s.bp_end, SPOS_MAX)) break; - s.bucket_start = bpos_successor(s.bucket_end); + s.bp_start = bpos_successor(s.bp_end); } +err: bch2_trans_put(trans); bch2_bkey_buf_exit(&s.last_flushed, c); - bch2_btree_cache_unpin(c); +err_free_bitmaps: + for_each_member_device(c, ca) { + kvfree(ca->bucket_backpointer_empty); + ca->bucket_backpointer_empty = NULL; + kvfree(ca->bucket_backpointer_mismatches); + ca->bucket_backpointer_mismatches = NULL; + } bch_err_fn(c, ret); return ret; @@ -959,44 +1159,43 @@ static int check_one_backpointer(struct btree_trans *trans, return 0; struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(bp_k); - struct bch_fs *c = trans->c; - struct btree_iter iter; struct bbpos pos = bp_to_bbpos(*bp.v); - struct bkey_s_c k; - struct printbuf buf = PRINTBUF; - int ret; if (bbpos_cmp(pos, start) < 0 || bbpos_cmp(pos, end) > 0) return 0; - k = bch2_backpointer_get_key(trans, &iter, bp.k->p, *bp.v, 0); - ret = bkey_err(k); + struct btree_iter iter; + struct bkey_s_c k = bch2_backpointer_get_key(trans, bp, &iter, 0, last_flushed); + int ret = bkey_err(k); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) return 0; if (ret) return ret; - if (!k.k) { - ret = bch2_btree_write_buffer_maybe_flush(trans, bp.s_c, last_flushed); - if (ret) - goto out; - - if (fsck_err(trans, backpointer_to_missing_ptr, - "backpointer for missing %s\n %s", - bp.v->level ? "btree node" : "extent", - (bch2_bkey_val_to_text(&buf, c, bp.s_c), buf.buf))) { - ret = bch2_btree_delete_at_buffered(trans, BTREE_ID_backpointers, bp.k->p); - goto out; - } - } -out: -fsck_err: bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); return ret; } +static int check_bucket_backpointers_to_extents(struct btree_trans *trans, + struct bch_dev *ca, struct bpos bucket) +{ + u32 restart_count = trans->restart_count; + struct bkey_buf last_flushed; + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + + int ret = for_each_btree_key_max(trans, iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, bucket), + bucket_pos_to_bp_end(ca, bucket), + 0, k, + check_one_backpointer(trans, BBPOS_MIN, BBPOS_MAX, k, &last_flushed) + ); + + bch2_bkey_buf_exit(&last_flushed, trans->c); + return ret ?: trans_was_restarted(trans, restart_count); +} + static int bch2_check_backpointers_to_extents_pass(struct btree_trans *trans, struct bbpos start, struct bbpos end) @@ -1009,9 +1208,8 @@ static int bch2_check_backpointers_to_extents_pass(struct btree_trans *trans, bkey_init(&last_flushed.k->k); progress_init(&progress, trans->c, BIT_ULL(BTREE_ID_backpointers)); - int ret = for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers, - POS_MIN, BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ + int ret = for_each_btree_key(trans, iter, BTREE_ID_backpointers, + POS_MIN, BTREE_ITER_prefetch, k, ({ progress_update_iter(trans, &progress, &iter, "backpointers_to_extents"); check_one_backpointer(trans, start, end, k, &last_flushed); })); diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h index 3b29fdf519dd..060dad1521ee 100644 --- a/fs/bcachefs/backpointers.h +++ b/fs/bcachefs/backpointers.h @@ -18,14 +18,14 @@ static inline u64 swab40(u64 x) ((x & 0xff00000000ULL) >> 32)); } -int bch2_backpointer_validate(struct bch_fs *, struct bkey_s_c k, enum bch_validate_flags); -void bch2_backpointer_to_text(struct printbuf *, const struct bch_backpointer *); -void bch2_backpointer_k_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); +int bch2_backpointer_validate(struct bch_fs *, struct bkey_s_c k, + struct bkey_validate_context); +void bch2_backpointer_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_backpointer_swab(struct bkey_s); #define bch2_bkey_ops_backpointer ((struct bkey_ops) { \ .key_validate = bch2_backpointer_validate, \ - .val_to_text = bch2_backpointer_k_to_text, \ + .val_to_text = bch2_backpointer_to_text, \ .swab = bch2_backpointer_swab, \ .min_val_size = 32, \ }) @@ -43,22 +43,24 @@ static inline struct bpos bp_pos_to_bucket(const struct bch_dev *ca, struct bpos return POS(bp_pos.inode, sector_to_bucket(ca, bucket_sector)); } +static inline struct bpos bp_pos_to_bucket_and_offset(const struct bch_dev *ca, struct bpos bp_pos, + u32 *bucket_offset) +{ + u64 bucket_sector = bp_pos.offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT; + + return POS(bp_pos.inode, sector_to_bucket_and_offset(ca, bucket_sector, bucket_offset)); +} + static inline bool bp_pos_to_bucket_nodev_noerror(struct bch_fs *c, struct bpos bp_pos, struct bpos *bucket) { rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, bp_pos.inode); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp_pos.inode); if (ca) *bucket = bp_pos_to_bucket(ca, bp_pos); rcu_read_unlock(); return ca != NULL; } -static inline bool bp_pos_to_bucket_nodev(struct bch_fs *c, struct bpos bp_pos, struct bpos *bucket) -{ - return !bch2_fs_inconsistent_on(!bp_pos_to_bucket_nodev_noerror(c, bp_pos, bucket), - c, "backpointer for missing device %llu", bp_pos.inode); -} - static inline struct bpos bucket_pos_to_bp_noerror(const struct bch_dev *ca, struct bpos bucket, u64 bucket_offset) @@ -80,31 +82,35 @@ static inline struct bpos bucket_pos_to_bp(const struct bch_dev *ca, return ret; } -int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *, struct bch_dev *, - struct bpos bucket, struct bch_backpointer, struct bkey_s_c, bool); +static inline struct bpos bucket_pos_to_bp_start(const struct bch_dev *ca, struct bpos bucket) +{ + return bucket_pos_to_bp(ca, bucket, 0); +} + +static inline struct bpos bucket_pos_to_bp_end(const struct bch_dev *ca, struct bpos bucket) +{ + return bpos_nosnap_predecessor(bucket_pos_to_bp(ca, bpos_nosnap_successor(bucket), 0)); +} + +int bch2_bucket_backpointer_mod_nowritebuffer(struct btree_trans *, + struct bkey_s_c, + struct bkey_i_backpointer *, + bool); static inline int bch2_bucket_backpointer_mod(struct btree_trans *trans, - struct bch_dev *ca, - struct bpos bucket, - struct bch_backpointer bp, struct bkey_s_c orig_k, + struct bkey_i_backpointer *bp, bool insert) { if (unlikely(bch2_backpointers_no_use_write_buffer)) - return bch2_bucket_backpointer_mod_nowritebuffer(trans, ca, bucket, bp, orig_k, insert); - - struct bkey_i_backpointer bp_k; - - bkey_backpointer_init(&bp_k.k_i); - bp_k.k.p = bucket_pos_to_bp(ca, bucket, bp.bucket_offset); - bp_k.v = bp; + return bch2_bucket_backpointer_mod_nowritebuffer(trans, orig_k, bp, insert); if (!insert) { - bp_k.k.type = KEY_TYPE_deleted; - set_bkey_val_u64s(&bp_k.k, 0); + bp->k.type = KEY_TYPE_deleted; + set_bkey_val_u64s(&bp->k, 0); } - return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp_k.k_i); + return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp->k_i); } static inline enum bch_data_type bch2_bkey_ptr_data_type(struct bkey_s_c k, @@ -134,44 +140,29 @@ static inline enum bch_data_type bch2_bkey_ptr_data_type(struct bkey_s_c k, } } -static inline void __bch2_extent_ptr_to_bp(struct bch_fs *c, struct bch_dev *ca, +static inline void bch2_extent_ptr_to_bp(struct bch_fs *c, enum btree_id btree_id, unsigned level, struct bkey_s_c k, struct extent_ptr_decoded p, const union bch_extent_entry *entry, - struct bpos *bucket_pos, struct bch_backpointer *bp, - u64 sectors) + struct bkey_i_backpointer *bp) { - u32 bucket_offset; - *bucket_pos = PTR_BUCKET_POS_OFFSET(ca, &p.ptr, &bucket_offset); - *bp = (struct bch_backpointer) { + bkey_backpointer_init(&bp->k_i); + bp->k.p = POS(p.ptr.dev, ((u64) p.ptr.offset << MAX_EXTENT_COMPRESS_RATIO_SHIFT) + p.crc.offset); + bp->v = (struct bch_backpointer) { .btree_id = btree_id, .level = level, .data_type = bch2_bkey_ptr_data_type(k, p, entry), - .bucket_offset = ((u64) bucket_offset << MAX_EXTENT_COMPRESS_RATIO_SHIFT) + - p.crc.offset, - .bucket_len = sectors, + .bucket_gen = p.ptr.gen, + .bucket_len = ptr_disk_sectors(level ? btree_sectors(c) : k.k->size, p), .pos = k.k->p, }; } -static inline void bch2_extent_ptr_to_bp(struct bch_fs *c, struct bch_dev *ca, - enum btree_id btree_id, unsigned level, - struct bkey_s_c k, struct extent_ptr_decoded p, - const union bch_extent_entry *entry, - struct bpos *bucket_pos, struct bch_backpointer *bp) -{ - u64 sectors = ptr_disk_sectors(level ? btree_sectors(c) : k.k->size, p); - - __bch2_extent_ptr_to_bp(c, ca, btree_id, level, k, p, entry, bucket_pos, bp, sectors); -} - -int bch2_get_next_backpointer(struct btree_trans *, struct bch_dev *ca, struct bpos, int, - struct bpos *, struct bch_backpointer *, unsigned); -struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *, struct btree_iter *, - struct bpos, struct bch_backpointer, - unsigned); -struct btree *bch2_backpointer_get_node(struct btree_trans *, struct btree_iter *, - struct bpos, struct bch_backpointer); +struct bkey_buf; +struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *, struct bkey_s_c_backpointer, + struct btree_iter *, unsigned, struct bkey_buf *); +struct btree *bch2_backpointer_get_node(struct btree_trans *, struct bkey_s_c_backpointer, + struct btree_iter *, struct bkey_buf *); int bch2_check_btree_backpointers(struct bch_fs *); int bch2_check_extents_to_backpointers(struct bch_fs *); diff --git a/fs/bcachefs/bbpos.h b/fs/bcachefs/bbpos.h index be2edced5213..63abe17f35ea 100644 --- a/fs/bcachefs/bbpos.h +++ b/fs/bcachefs/bbpos.h @@ -29,7 +29,7 @@ static inline struct bbpos bbpos_successor(struct bbpos pos) static inline void bch2_bbpos_to_text(struct printbuf *out, struct bbpos pos) { - prt_str(out, bch2_btree_id_str(pos.btree)); + bch2_btree_id_to_text(out, pos.btree); prt_char(out, ':'); bch2_bpos_to_text(out, pos.pos); } diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index e94a83b8113e..161cf2f05d2a 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -205,6 +205,7 @@ #include <linux/zstd.h> #include "bcachefs_format.h" +#include "btree_journal_iter_types.h" #include "disk_accounting_types.h" #include "errcode.h" #include "fifo.h" @@ -293,6 +294,8 @@ do { \ #define bch_info(c, fmt, ...) \ bch2_print(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__) +#define bch_info_ratelimited(c, fmt, ...) \ + bch2_print_ratelimited(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_notice(c, fmt, ...) \ bch2_print(c, KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_warn(c, fmt, ...) \ @@ -352,6 +355,12 @@ do { \ bch_info(c, fmt, ##__VA_ARGS__); \ } while (0) +#define bch_verbose_ratelimited(c, fmt, ...) \ +do { \ + if ((c)->opts.verbose) \ + bch_info_ratelimited(c, fmt, ##__VA_ARGS__); \ +} while (0) + #define pr_verbose_init(opts, fmt, ...) \ do { \ if (opt_get(opts, verbose)) \ @@ -538,20 +547,20 @@ struct bch_dev { /* * Buckets: - * Per-bucket arrays are protected by c->mark_lock, bucket_lock and - * gc_gens_lock, for device resize - holding any is sufficient for - * access: Or rcu_read_lock(), but only for dev_ptr_stale(): + * Per-bucket arrays are protected by either rcu_read_lock or + * state_lock, for device resize. */ GENRADIX(struct bucket) buckets_gc; struct bucket_gens __rcu *bucket_gens; u8 *oldest_gen; unsigned long *buckets_nouse; - struct rw_semaphore bucket_lock; + + unsigned long *bucket_backpointer_mismatches; + unsigned long *bucket_backpointer_empty; struct bch_dev_usage __percpu *usage; /* Allocator: */ - u64 new_fs_bucket_idx; u64 alloc_cursor[3]; unsigned nr_open_buckets; @@ -606,6 +615,7 @@ struct bch_dev { x(going_ro) \ x(write_disable_complete) \ x(clean_shutdown) \ + x(recovery_running) \ x(fsck_running) \ x(initial_gc_unfixed) \ x(need_delete_dead_snapshots) \ @@ -650,28 +660,6 @@ struct journal_seq_blacklist_table { } entries[]; }; -struct journal_keys { - /* must match layout in darray_types.h */ - size_t nr, size; - struct journal_key { - u64 journal_seq; - u32 journal_offset; - enum btree_id btree_id:8; - unsigned level:8; - bool allocated; - bool overwritten; - struct bkey_i *k; - } *data; - /* - * Gap buffer: instead of all the empty space in the array being at the - * end of the buffer - from @nr to @size - the empty space is at @gap. - * This means that sequential insertions are O(n) instead of O(n^2). - */ - size_t gap; - atomic_t ref; - bool initial_ref_held; -}; - struct btree_trans_buf { struct btree_trans *trans; }; @@ -680,6 +668,7 @@ struct btree_trans_buf { ((subvol_inum) { BCACHEFS_ROOT_SUBVOL, BCACHEFS_ROOT_INO }) #define BCH_WRITE_REFS() \ + x(journal) \ x(trans) \ x(write) \ x(promote) \ @@ -692,6 +681,7 @@ struct btree_trans_buf { x(dio_write) \ x(discard) \ x(discard_fast) \ + x(check_discard_freespace_key) \ x(invalidate) \ x(delete_dead_snapshots) \ x(gc_gens) \ @@ -735,6 +725,12 @@ struct bch_fs { struct percpu_ref writes; #endif /* + * Certain operations are only allowed in single threaded mode, during + * recovery, and we want to assert that this is the case: + */ + struct task_struct *recovery_task; + + /* * Analagous to c->writes, for asynchronous ops that don't necessarily * need fs to be read-write */ @@ -764,6 +760,8 @@ struct bch_fs { __uuid_t user_uuid; u16 version; + u16 version_incompat; + u16 version_incompat_allowed; u16 version_min; u16 version_upgrade_complete; @@ -834,9 +832,10 @@ struct bch_fs { struct work_struct btree_interior_update_work; struct workqueue_struct *btree_node_rewrite_worker; - - struct list_head pending_node_rewrites; - struct mutex pending_node_rewrites_lock; + struct list_head btree_node_rewrites; + struct list_head btree_node_rewrites_pending; + spinlock_t btree_node_rewrites_lock; + struct closure_waitlist btree_node_rewrites_wait; /* btree_io.c: */ spinlock_t btree_write_error_lock; @@ -967,8 +966,7 @@ struct bch_fs { struct rhashtable promote_table; mempool_t compression_bounce[2]; - mempool_t compress_workspace[BCH_COMPRESSION_TYPE_NR]; - mempool_t decompress_workspace; + mempool_t compress_workspace[BCH_COMPRESSION_OPT_NR]; size_t zstd_workspace_size; struct crypto_shash *sha256; @@ -1027,6 +1025,7 @@ struct bch_fs { struct list_head vfs_inodes_list; struct mutex vfs_inodes_lock; struct rhashtable vfs_inodes_table; + struct rhltable vfs_inodes_by_inum_table; /* VFS IO PATH - fs-io.c */ struct bio_set writepage_bioset; @@ -1048,10 +1047,12 @@ struct bch_fs { * for signaling to the toplevel code which pass we want to run now. */ enum bch_recovery_pass curr_recovery_pass; + enum bch_recovery_pass next_recovery_pass; /* bitmask of recovery passes that we actually ran */ u64 recovery_passes_complete; /* never rewinds version of curr_recovery_pass */ enum bch_recovery_pass recovery_pass_done; + spinlock_t recovery_pass_lock; struct semaphore online_fsck_mutex; /* DEBUG JUNK */ @@ -1062,9 +1063,6 @@ struct bch_fs { struct btree_node *verify_ondisk; struct mutex verify_lock; - u64 *unused_inode_hints; - unsigned inode_shard_bits; - /* * A btree node on disk could have too many bsets for an iterator to fit * on the stack - have to dynamically allocate them @@ -1086,8 +1084,6 @@ struct bch_fs { u64 counters_on_mount[BCH_COUNTER_NR]; u64 __percpu *counters; - unsigned copy_gc_enabled:1; - struct bch2_time_stats times[BCH_TIME_STAT_NR]; struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR]; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 5004f6ba997c..f70f0108401f 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -418,7 +418,8 @@ static inline void bkey_init(struct bkey *k) x(snapshot_tree, 31) \ x(logged_op_truncate, 32) \ x(logged_op_finsert, 33) \ - x(accounting, 34) + x(accounting, 34) \ + x(inode_alloc_cursor, 35) enum bch_bkey_type { #define x(name, nr) KEY_TYPE_##name = nr, @@ -463,7 +464,8 @@ struct bch_backpointer { __u8 btree_id; __u8 level; __u8 data_type; - __u64 bucket_offset:40; + __u8 bucket_gen; + __u32 pad; __u32 bucket_len; struct bpos pos; } __packed __aligned(8); @@ -499,8 +501,6 @@ struct bch_sb_field { #include "disk_groups_format.h" #include "extents_format.h" #include "ec_format.h" -#include "dirent_format.h" -#include "disk_groups_format.h" #include "inode_format.h" #include "journal_seq_blacklist_format.h" #include "logged_ops_format.h" @@ -679,7 +679,14 @@ struct bch_sb_field_ext { x(disk_accounting_v3, BCH_VERSION(1, 10)) \ x(disk_accounting_inum, BCH_VERSION(1, 11)) \ x(rebalance_work_acct_fix, BCH_VERSION(1, 12)) \ - x(inode_has_child_snapshots, BCH_VERSION(1, 13)) + x(inode_has_child_snapshots, BCH_VERSION(1, 13)) \ + x(backpointer_bucket_gen, BCH_VERSION(1, 14)) \ + x(disk_accounting_big_endian, BCH_VERSION(1, 15)) \ + x(reflink_p_may_update_opts, BCH_VERSION(1, 16)) \ + x(inode_depth, BCH_VERSION(1, 17)) \ + x(persistent_inode_cursors, BCH_VERSION(1, 18)) \ + x(autofix_errors, BCH_VERSION(1, 19)) \ + x(directory_size, BCH_VERSION(1, 20)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, @@ -844,6 +851,10 @@ LE64_BITMASK(BCH_SB_VERSION_UPGRADE_COMPLETE, struct bch_sb, flags[5], 0, 16); LE64_BITMASK(BCH_SB_ALLOCATOR_STUCK_TIMEOUT, struct bch_sb, flags[5], 16, 32); +LE64_BITMASK(BCH_SB_VERSION_INCOMPAT, struct bch_sb, flags[5], 32, 48); +LE64_BITMASK(BCH_SB_VERSION_INCOMPAT_ALLOWED, + struct bch_sb, flags[5], 48, 64); +LE64_BITMASK(BCH_SB_SHARD_INUMS_NBITS, struct bch_sb, flags[6], 0, 4); static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb) { @@ -896,21 +907,22 @@ static inline void SET_BCH_SB_BACKGROUND_COMPRESSION_TYPE(struct bch_sb *sb, __u x(new_varint, 15) \ x(journal_no_flush, 16) \ x(alloc_v2, 17) \ - x(extents_across_btree_nodes, 18) + x(extents_across_btree_nodes, 18) \ + x(incompat_version_field, 19) #define BCH_SB_FEATURES_ALWAYS \ - ((1ULL << BCH_FEATURE_new_extent_overwrite)| \ - (1ULL << BCH_FEATURE_extents_above_btree_updates)|\ - (1ULL << BCH_FEATURE_btree_updates_journalled)|\ - (1ULL << BCH_FEATURE_alloc_v2)|\ - (1ULL << BCH_FEATURE_extents_across_btree_nodes)) + (BIT_ULL(BCH_FEATURE_new_extent_overwrite)| \ + BIT_ULL(BCH_FEATURE_extents_above_btree_updates)|\ + BIT_ULL(BCH_FEATURE_btree_updates_journalled)|\ + BIT_ULL(BCH_FEATURE_alloc_v2)|\ + BIT_ULL(BCH_FEATURE_extents_across_btree_nodes)) #define BCH_SB_FEATURES_ALL \ (BCH_SB_FEATURES_ALWAYS| \ - (1ULL << BCH_FEATURE_new_siphash)| \ - (1ULL << BCH_FEATURE_btree_ptr_v2)| \ - (1ULL << BCH_FEATURE_new_varint)| \ - (1ULL << BCH_FEATURE_journal_no_flush)) + BIT_ULL(BCH_FEATURE_new_siphash)| \ + BIT_ULL(BCH_FEATURE_btree_ptr_v2)| \ + BIT_ULL(BCH_FEATURE_new_varint)| \ + BIT_ULL(BCH_FEATURE_journal_no_flush)) enum bch_sb_feature { #define x(f, n) BCH_FEATURE_##f, @@ -1032,7 +1044,7 @@ static inline _Bool bch2_csum_type_is_encryption(enum bch_csum_type type) x(crc64, 2) \ x(xxhash, 3) -enum bch_csum_opts { +enum bch_csum_opt { #define x(t, n) BCH_CSUM_OPT_##t = n, BCH_CSUM_OPTS() #undef x @@ -1221,6 +1233,15 @@ struct jset_entry_log { u8 d[]; } __packed __aligned(8); +static inline unsigned jset_entry_log_msg_bytes(struct jset_entry_log *l) +{ + unsigned b = vstruct_bytes(&l->entry) - offsetof(struct jset_entry_log, d); + + while (b && !l->d[b - 1]) + --b; + return b; +} + struct jset_entry_datetime { struct jset_entry entry; __le64 seconds; @@ -1268,14 +1289,18 @@ LE32_BITMASK(JSET_NO_FLUSH, struct jset, flags, 5, 6); /* Btree: */ enum btree_id_flags { - BTREE_ID_EXTENTS = BIT(0), - BTREE_ID_SNAPSHOTS = BIT(1), - BTREE_ID_SNAPSHOT_FIELD = BIT(2), - BTREE_ID_DATA = BIT(3), + BTREE_IS_extents = BIT(0), + BTREE_IS_snapshots = BIT(1), + BTREE_IS_snapshot_field = BIT(2), + BTREE_IS_data = BIT(3), + BTREE_IS_write_buffer = BIT(4), }; #define BCH_BTREE_IDS() \ - x(extents, 0, BTREE_ID_EXTENTS|BTREE_ID_SNAPSHOTS|BTREE_ID_DATA,\ + x(extents, 0, \ + BTREE_IS_extents| \ + BTREE_IS_snapshots| \ + BTREE_IS_data, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_error)| \ BIT_ULL(KEY_TYPE_cookie)| \ @@ -1283,17 +1308,20 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_reservation)| \ BIT_ULL(KEY_TYPE_reflink_p)| \ BIT_ULL(KEY_TYPE_inline_data)) \ - x(inodes, 1, BTREE_ID_SNAPSHOTS, \ + x(inodes, 1, \ + BTREE_IS_snapshots, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_inode)| \ BIT_ULL(KEY_TYPE_inode_v2)| \ BIT_ULL(KEY_TYPE_inode_v3)| \ BIT_ULL(KEY_TYPE_inode_generation)) \ - x(dirents, 2, BTREE_ID_SNAPSHOTS, \ + x(dirents, 2, \ + BTREE_IS_snapshots, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_hash_whiteout)| \ BIT_ULL(KEY_TYPE_dirent)) \ - x(xattrs, 3, BTREE_ID_SNAPSHOTS, \ + x(xattrs, 3, \ + BTREE_IS_snapshots, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_cookie)| \ BIT_ULL(KEY_TYPE_hash_whiteout)| \ @@ -1307,7 +1335,9 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_quota)) \ x(stripes, 6, 0, \ BIT_ULL(KEY_TYPE_stripe)) \ - x(reflink, 7, BTREE_ID_EXTENTS|BTREE_ID_DATA, \ + x(reflink, 7, \ + BTREE_IS_extents| \ + BTREE_IS_data, \ BIT_ULL(KEY_TYPE_reflink_v)| \ BIT_ULL(KEY_TYPE_indirect_inline_data)| \ BIT_ULL(KEY_TYPE_error)) \ @@ -1315,28 +1345,38 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_subvolume)) \ x(snapshots, 9, 0, \ BIT_ULL(KEY_TYPE_snapshot)) \ - x(lru, 10, 0, \ + x(lru, 10, \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_set)) \ - x(freespace, 11, BTREE_ID_EXTENTS, \ + x(freespace, 11, \ + BTREE_IS_extents, \ BIT_ULL(KEY_TYPE_set)) \ x(need_discard, 12, 0, \ BIT_ULL(KEY_TYPE_set)) \ - x(backpointers, 13, 0, \ + x(backpointers, 13, \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_backpointer)) \ x(bucket_gens, 14, 0, \ BIT_ULL(KEY_TYPE_bucket_gens)) \ x(snapshot_trees, 15, 0, \ BIT_ULL(KEY_TYPE_snapshot_tree)) \ - x(deleted_inodes, 16, BTREE_ID_SNAPSHOT_FIELD, \ + x(deleted_inodes, 16, \ + BTREE_IS_snapshot_field| \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_set)) \ x(logged_ops, 17, 0, \ BIT_ULL(KEY_TYPE_logged_op_truncate)| \ - BIT_ULL(KEY_TYPE_logged_op_finsert)) \ - x(rebalance_work, 18, BTREE_ID_SNAPSHOT_FIELD, \ + BIT_ULL(KEY_TYPE_logged_op_finsert)| \ + BIT_ULL(KEY_TYPE_inode_alloc_cursor)) \ + x(rebalance_work, 18, \ + BTREE_IS_snapshot_field| \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_set)|BIT_ULL(KEY_TYPE_cookie)) \ x(subvolume_children, 19, 0, \ BIT_ULL(KEY_TYPE_set)) \ - x(accounting, 20, BTREE_ID_SNAPSHOT_FIELD, \ + x(accounting, 20, \ + BTREE_IS_snapshot_field| \ + BTREE_IS_write_buffer, \ BIT_ULL(KEY_TYPE_accounting)) \ enum btree_id { @@ -1361,6 +1401,8 @@ static inline bool btree_id_is_alloc(enum btree_id id) case BTREE_ID_need_discard: case BTREE_ID_freespace: case BTREE_ID_bucket_gens: + case BTREE_ID_lru: + case BTREE_ID_accounting: return true; default: return false; diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index 41df24a53d97..054e2d5e8448 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -9,13 +9,6 @@ #include "util.h" #include "vstructs.h" -enum bch_validate_flags { - BCH_VALIDATE_write = BIT(0), - BCH_VALIDATE_commit = BIT(1), - BCH_VALIDATE_journal = BIT(2), - BCH_VALIDATE_silent = BIT(3), -}; - #if 0 /* diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index e7ac227ba7e8..15c93576b5c2 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -28,7 +28,7 @@ const char * const bch2_bkey_types[] = { }; static int deleted_key_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -42,7 +42,7 @@ static int deleted_key_validate(struct bch_fs *c, struct bkey_s_c k, }) static int empty_val_key_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -59,7 +59,7 @@ fsck_err: }) static int key_type_cookie_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -83,7 +83,7 @@ static void key_type_cookie_to_text(struct printbuf *out, struct bch_fs *c, }) static int key_type_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -124,7 +124,7 @@ const struct bkey_ops bch2_bkey_null_ops = { }; int bch2_bkey_val_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { if (test_bit(BCH_FS_no_invalid_checks, &c->flags)) return 0; @@ -140,7 +140,7 @@ int bch2_bkey_val_validate(struct bch_fs *c, struct bkey_s_c k, if (!ops->key_validate) return 0; - ret = ops->key_validate(c, k, flags); + ret = ops->key_validate(c, k, from); fsck_err: return ret; } @@ -161,9 +161,10 @@ const char *bch2_btree_node_type_str(enum btree_node_type type) } int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, - enum btree_node_type type, - enum bch_validate_flags flags) + struct bkey_validate_context from) { + enum btree_node_type type = __btree_node_type(from.level, from.btree); + if (test_bit(BCH_FS_no_invalid_checks, &c->flags)) return 0; @@ -177,7 +178,7 @@ int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, return 0; bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX && - (type == BKEY_TYPE_btree || (flags & BCH_VALIDATE_commit)) && + (type == BKEY_TYPE_btree || (from.flags & BCH_VALIDATE_commit)) && !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, bkey_invalid_type_for_btree, "invalid key type for btree %s (%s)", @@ -228,15 +229,15 @@ fsck_err: } int bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k, - enum btree_node_type type, - enum bch_validate_flags flags) + struct bkey_validate_context from) { - return __bch2_bkey_validate(c, k, type, flags) ?: - bch2_bkey_val_validate(c, k, flags); + return __bch2_bkey_validate(c, k, from) ?: + bch2_bkey_val_validate(c, k, from); } int bch2_bkey_in_btree_node(struct bch_fs *c, struct btree *b, - struct bkey_s_c k, enum bch_validate_flags flags) + struct bkey_s_c k, + struct bkey_validate_context from) { int ret = 0; diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h index 018fb72e32d3..bf34111cdf00 100644 --- a/fs/bcachefs/bkey_methods.h +++ b/fs/bcachefs/bkey_methods.h @@ -22,7 +22,7 @@ extern const struct bkey_ops bch2_bkey_null_ops; */ struct bkey_ops { int (*key_validate)(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags); + struct bkey_validate_context from); void (*val_to_text)(struct printbuf *, struct bch_fs *, struct bkey_s_c); void (*swab)(struct bkey_s); @@ -48,13 +48,14 @@ static inline const struct bkey_ops *bch2_bkey_type_ops(enum bch_bkey_type type) : &bch2_bkey_null_ops; } -int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); -int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type, - enum bch_validate_flags); -int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type, - enum bch_validate_flags); +int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context from); void bch2_bpos_to_text(struct printbuf *, struct bpos); void bch2_bkey_to_text(struct printbuf *, const struct bkey *); diff --git a/fs/bcachefs/bkey_types.h b/fs/bcachefs/bkey_types.h index c9ae9e42b385..b4f328f9853c 100644 --- a/fs/bcachefs/bkey_types.h +++ b/fs/bcachefs/bkey_types.h @@ -210,4 +210,32 @@ static inline struct bkey_i_##name *bkey_##name##_init(struct bkey_i *_k)\ BCH_BKEY_TYPES(); #undef x +enum bch_validate_flags { + BCH_VALIDATE_write = BIT(0), + BCH_VALIDATE_commit = BIT(1), + BCH_VALIDATE_silent = BIT(2), +}; + +#define BKEY_VALIDATE_CONTEXTS() \ + x(unknown) \ + x(superblock) \ + x(journal) \ + x(btree_root) \ + x(btree_node) \ + x(commit) + +struct bkey_validate_context { + enum { +#define x(n) BKEY_VALIDATE_##n, + BKEY_VALIDATE_CONTEXTS() +#undef x + } from:8; + enum bch_validate_flags flags:8; + u8 level; + enum btree_id btree; + bool root:1; + unsigned journal_offset; + u64 journal_seq; +}; + #endif /* _BCACHEFS_BKEY_TYPES_H */ diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 7123019ab3bc..672ca2c1d37d 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -222,7 +222,6 @@ void bch2_node_pin(struct bch_fs *c, struct btree *b) struct btree_cache *bc = &c->btree_cache; mutex_lock(&bc->lock); - BUG_ON(!__btree_node_pinned(bc, b)); if (b != btree_node_root(c, b) && !btree_node_pinned(b)) { set_btree_node_pinned(b); list_move(&b->list, &bc->live[1].list); @@ -326,7 +325,7 @@ void bch2_btree_node_update_key_early(struct btree_trans *trans, if (!IS_ERR_OR_NULL(b)) { mutex_lock(&c->btree_cache.lock); - bch2_btree_node_hash_remove(&c->btree_cache, b); + __bch2_btree_node_hash_remove(&c->btree_cache, b); bkey_copy(&b->key, new); ret = __bch2_btree_node_hash_insert(&c->btree_cache, b); @@ -1004,16 +1003,14 @@ static noinline void btree_bad_header(struct bch_fs *c, struct btree *b) return; prt_printf(&buf, - "btree node header doesn't match ptr\n" - "btree %s level %u\n" - "ptr: ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + "btree node header doesn't match ptr: "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, "\nptr: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); - prt_printf(&buf, "\nheader: btree %s level %llu\n" - "min ", - bch2_btree_id_str(BTREE_NODE_ID(b->data)), - BTREE_NODE_LEVEL(b->data)); + prt_str(&buf, "\nheader: "); + bch2_btree_id_level_to_text(&buf, BTREE_NODE_ID(b->data), BTREE_NODE_LEVEL(b->data)); + prt_str(&buf, "\nmin "); bch2_bpos_to_text(&buf, b->data->min_key); prt_printf(&buf, "\nmax "); @@ -1133,7 +1130,7 @@ retry: if (unlikely(btree_node_read_error(b))) { six_unlock_type(&b->c.lock, lock_type); - return ERR_PTR(-BCH_ERR_btree_node_read_error); + return ERR_PTR(-BCH_ERR_btree_node_read_err_cached); } EBUG_ON(b->c.btree_id != path->btree_id); @@ -1223,7 +1220,7 @@ struct btree *bch2_btree_node_get(struct btree_trans *trans, struct btree_path * if (unlikely(btree_node_read_error(b))) { six_unlock_type(&b->c.lock, lock_type); - return ERR_PTR(-BCH_ERR_btree_node_read_error); + return ERR_PTR(-BCH_ERR_btree_node_read_err_cached); } EBUG_ON(b->c.btree_id != path->btree_id); @@ -1305,7 +1302,7 @@ lock_node: if (unlikely(btree_node_read_error(b))) { six_unlock_read(&b->c.lock); - b = ERR_PTR(-BCH_ERR_btree_node_read_error); + b = ERR_PTR(-BCH_ERR_btree_node_read_err_cached); goto out; } @@ -1398,13 +1395,31 @@ void bch2_btree_id_to_text(struct printbuf *out, enum btree_id btree) prt_printf(out, "(unknown btree %u)", btree); } +void bch2_btree_id_level_to_text(struct printbuf *out, enum btree_id btree, unsigned level) +{ + prt_str(out, "btree="); + bch2_btree_id_to_text(out, btree); + prt_printf(out, " level=%u", level); +} + +void __bch2_btree_pos_to_text(struct printbuf *out, struct bch_fs *c, + enum btree_id btree, unsigned level, struct bkey_s_c k) +{ + bch2_btree_id_to_text(out, btree); + prt_printf(out, " level %u/", level); + struct btree_root *r = bch2_btree_id_root(c, btree); + if (r) + prt_printf(out, "%u", r->level); + else + prt_printf(out, "(unknown)"); + prt_printf(out, "\n "); + + bch2_bkey_val_to_text(out, c, k); +} + void bch2_btree_pos_to_text(struct printbuf *out, struct bch_fs *c, const struct btree *b) { - prt_printf(out, "%s level %u/%u\n ", - bch2_btree_id_str(b->c.btree_id), - b->c.level, - bch2_btree_id_root(c, b->c.btree_id)->level); - bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(&b->key)); + __bch2_btree_pos_to_text(out, c, b->c.btree_id, b->c.level, bkey_i_to_s_c(&b->key)); } void bch2_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struct btree *b) @@ -1478,8 +1493,12 @@ void bch2_btree_cache_to_text(struct printbuf *out, const struct btree_cache *bc prt_printf(out, "cannibalize lock:\t%p\n", bc->alloc_lock); prt_newline(out); - for (unsigned i = 0; i < ARRAY_SIZE(bc->nr_by_btree); i++) - prt_btree_cache_line(out, c, bch2_btree_id_str(i), bc->nr_by_btree[i]); + for (unsigned i = 0; i < ARRAY_SIZE(bc->nr_by_btree); i++) { + bch2_btree_id_to_text(out, i); + prt_printf(out, "\t"); + prt_human_readable_u64(out, bc->nr_by_btree[i] * c->opts.btree_node_size); + prt_printf(out, " (%zu)\n", bc->nr_by_btree[i]); + } prt_newline(out); prt_printf(out, "freed:\t%zu\n", bc->nr_freed); diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h index 66e86d1a178d..ca3c1b145330 100644 --- a/fs/bcachefs/btree_cache.h +++ b/fs/bcachefs/btree_cache.h @@ -128,19 +128,27 @@ static inline struct btree_root *bch2_btree_id_root(struct bch_fs *c, unsigned i } else { unsigned idx = id - BTREE_ID_NR; - EBUG_ON(idx >= c->btree_roots_extra.nr); + /* This can happen when we're called from btree_node_scan */ + if (idx >= c->btree_roots_extra.nr) + return NULL; + return &c->btree_roots_extra.data[idx]; } } static inline struct btree *btree_node_root(struct bch_fs *c, struct btree *b) { - return bch2_btree_id_root(c, b->c.btree_id)->b; + struct btree_root *r = bch2_btree_id_root(c, b->c.btree_id); + + return r ? r->b : NULL; } -const char *bch2_btree_id_str(enum btree_id); +const char *bch2_btree_id_str(enum btree_id); /* avoid */ void bch2_btree_id_to_text(struct printbuf *, enum btree_id); +void bch2_btree_id_level_to_text(struct printbuf *, enum btree_id, unsigned); +void __bch2_btree_pos_to_text(struct printbuf *, struct bch_fs *, + enum btree_id, unsigned, struct bkey_s_c); void bch2_btree_pos_to_text(struct printbuf *, struct bch_fs *, const struct btree *); void bch2_btree_node_to_text(struct printbuf *, struct bch_fs *, const struct btree *); void bch2_btree_cache_to_text(struct printbuf *, const struct btree_cache *); diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index 81dcf9e512c0..dd1d9b74076e 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -29,6 +29,7 @@ #include "move.h" #include "recovery_passes.h" #include "reflink.h" +#include "recovery.h" #include "replicas.h" #include "super-io.h" #include "trace.h" @@ -56,8 +57,8 @@ void bch2_gc_pos_to_text(struct printbuf *out, struct gc_pos *p) { prt_str(out, bch2_gc_phase_strs[p->phase]); prt_char(out, ' '); - bch2_btree_id_to_text(out, p->btree); - prt_printf(out, " l=%u ", p->level); + bch2_btree_id_level_to_text(out, p->btree, p->level); + prt_char(out, ' '); bch2_bpos_to_text(out, p->pos); } @@ -209,8 +210,9 @@ static int btree_check_node_boundaries(struct btree_trans *trans, struct btree * if (bpos_eq(expected_start, cur->data->min_key)) return 0; - prt_printf(&buf, " at btree %s level %u:\n parent: ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_printf(&buf, " at "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_printf(&buf, ":\n parent: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); if (prev) { @@ -277,8 +279,9 @@ static int btree_repair_node_end(struct btree_trans *trans, struct btree *b, if (bpos_eq(child->key.k.p, b->key.k.p)) return 0; - prt_printf(&buf, "at btree %s level %u:\n parent: ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_printf(&buf, " at "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_printf(&buf, ":\n parent: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n child: "); @@ -341,14 +344,14 @@ again: ret = PTR_ERR_OR_ZERO(cur); printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level - 1); + prt_char(&buf, ' '); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(cur_k.k)); if (mustfix_fsck_err_on(bch2_err_matches(ret, EIO), - trans, btree_node_unreadable, - "Topology repair: unreadable btree node at btree %s level %u:\n" + trans, btree_node_read_error, + "Topology repair: unreadable btree node at\n" " %s", - bch2_btree_id_str(b->c.btree_id), - b->c.level - 1, buf.buf)) { bch2_btree_node_evict(trans, cur_k.k); cur = NULL; @@ -357,11 +360,9 @@ again: if (ret) break; - if (!btree_id_is_alloc(b->c.btree_id)) { - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); - if (ret) - break; - } + ret = bch2_btree_lost_data(c, b->c.btree_id); + if (ret) + break; continue; } @@ -370,7 +371,7 @@ again: break; if (bch2_btree_node_is_stale(c, cur)) { - bch_info(c, "btree node %s older than nodes found by scanning", buf.buf); + bch_info(c, "btree node older than nodes found by scanning\n %s", buf.buf); six_unlock_read(&cur->c.lock); bch2_btree_node_evict(trans, cur_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, @@ -478,14 +479,13 @@ again: } printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); if (mustfix_fsck_err_on(!have_child, trans, btree_node_topology_interior_node_empty, - "empty interior btree node at btree %s level %u\n" - " %s", - bch2_btree_id_str(b->c.btree_id), - b->c.level, buf.buf)) + "empty interior btree node at %s", buf.buf)) ret = DROP_THIS_NODE; err: fsck_err: @@ -511,6 +511,7 @@ int bch2_check_topology(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct bpos pulled_from_scan = POS_MIN; + struct printbuf buf = PRINTBUF; int ret = 0; bch2_trans_srcu_unlock(trans); @@ -519,19 +520,22 @@ int bch2_check_topology(struct bch_fs *c) struct btree_root *r = bch2_btree_id_root(c, i); bool reconstructed_root = false; + printbuf_reset(&buf); + bch2_btree_id_to_text(&buf, i); + if (r->error) { - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + ret = bch2_btree_lost_data(c, i); if (ret) break; reconstruct_root: - bch_info(c, "btree root %s unreadable, must recover from scan", bch2_btree_id_str(i)); + bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf); r->alive = false; r->error = 0; if (!bch2_btree_has_scanned_nodes(c, i)) { mustfix_fsck_err(trans, btree_root_unreadable_and_scan_found_nothing, - "no nodes found for btree %s, continue?", bch2_btree_id_str(i)); + "no nodes found for btree %s, continue?", buf.buf); bch2_btree_root_alloc_fake_trans(trans, i, 0); } else { bch2_btree_root_alloc_fake_trans(trans, i, 1); @@ -560,13 +564,14 @@ reconstruct_root: if (!reconstructed_root) goto reconstruct_root; - bch_err(c, "empty btree root %s", bch2_btree_id_str(i)); + bch_err(c, "empty btree root %s", buf.buf); bch2_btree_root_alloc_fake_trans(trans, i, 0); r->alive = false; ret = 0; } } fsck_err: + printbuf_exit(&buf); bch2_trans_put(trans); return ret; } @@ -713,6 +718,7 @@ static int bch2_gc_btrees(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); enum btree_id ids[BTREE_ID_NR]; + struct printbuf buf = PRINTBUF; unsigned i; int ret = 0; @@ -727,14 +733,9 @@ static int bch2_gc_btrees(struct bch_fs *c) continue; ret = bch2_gc_btree(trans, btree, true); - - if (mustfix_fsck_err_on(bch2_err_matches(ret, EIO), - trans, btree_node_read_error, - "btree node read error for %s", - bch2_btree_id_str(btree))) - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); } -fsck_err: + + printbuf_exit(&buf); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; @@ -802,7 +803,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans, old = bch2_alloc_to_v4(k, &old_convert); gc = new = *old; - percpu_down_read(&c->mark_lock); __bucket_m_to_alloc(&gc, *gc_bucket(ca, iter->pos.offset)); old_gc = gc; @@ -813,7 +813,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans, gc.data_type = old->data_type; gc.dirty_sectors = old->dirty_sectors; } - percpu_up_read(&c->mark_lock); /* * gc.data_type doesn't yet include need_discard & need_gc_gen states - @@ -831,11 +830,9 @@ static int bch2_alloc_write_key(struct btree_trans *trans, * safe w.r.t. transaction restarts, so fixup the gc_bucket so * we don't run it twice: */ - percpu_down_read(&c->mark_lock); struct bucket *gc_m = gc_bucket(ca, iter->pos.offset); gc_m->data_type = gc.data_type; gc_m->dirty_sectors = gc.dirty_sectors; - percpu_up_read(&c->mark_lock); } if (fsck_err_on(new.data_type != gc.data_type, @@ -895,11 +892,11 @@ static int bch2_gc_alloc_done(struct bch_fs *c) for_each_member_device(c, ca) { ret = bch2_trans_run(c, - for_each_btree_key_upto_commit(trans, iter, BTREE_ID_alloc, + for_each_btree_key_max_commit(trans, iter, BTREE_ID_alloc, POS(ca->dev_idx, ca->mi.first_bucket), POS(ca->dev_idx, ca->mi.nbuckets - 1), BTREE_ITER_slots|BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_lazy_rw, + NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_alloc_write_key(trans, &iter, ca, k))); if (ret) { bch2_dev_put(ca); @@ -928,98 +925,6 @@ static int bch2_gc_alloc_start(struct bch_fs *c) return ret; } -static int bch2_gc_write_reflink_key(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k, - size_t *idx) -{ - struct bch_fs *c = trans->c; - const __le64 *refcount = bkey_refcount_c(k); - struct printbuf buf = PRINTBUF; - struct reflink_gc *r; - int ret = 0; - - if (!refcount) - return 0; - - while ((r = genradix_ptr(&c->reflink_gc_table, *idx)) && - r->offset < k.k->p.offset) - ++*idx; - - if (!r || - r->offset != k.k->p.offset || - r->size != k.k->size) { - bch_err(c, "unexpected inconsistency walking reflink table at gc finish"); - return -EINVAL; - } - - if (fsck_err_on(r->refcount != le64_to_cpu(*refcount), - trans, reflink_v_refcount_wrong, - "reflink key has wrong refcount:\n" - " %s\n" - " should be %u", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf), - r->refcount)) { - struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); - ret = PTR_ERR_OR_ZERO(new); - if (ret) - goto out; - - if (!r->refcount) - new->k.type = KEY_TYPE_deleted; - else - *bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount); - ret = bch2_trans_update(trans, iter, new, 0); - } -out: -fsck_err: - printbuf_exit(&buf); - return ret; -} - -static int bch2_gc_reflink_done(struct bch_fs *c) -{ - size_t idx = 0; - - int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, - BTREE_ID_reflink, POS_MIN, - BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - bch2_gc_write_reflink_key(trans, &iter, k, &idx))); - c->reflink_gc_nr = 0; - return ret; -} - -static int bch2_gc_reflink_start(struct bch_fs *c) -{ - c->reflink_gc_nr = 0; - - int ret = bch2_trans_run(c, - for_each_btree_key(trans, iter, BTREE_ID_reflink, POS_MIN, - BTREE_ITER_prefetch, k, ({ - const __le64 *refcount = bkey_refcount_c(k); - - if (!refcount) - continue; - - struct reflink_gc *r = genradix_ptr_alloc(&c->reflink_gc_table, - c->reflink_gc_nr++, GFP_KERNEL); - if (!r) { - ret = -BCH_ERR_ENOMEM_gc_reflink_start; - break; - } - - r->offset = k.k->p.offset; - r->size = k.k->size; - r->refcount = 0; - 0; - }))); - - bch_err_fn(c, ret); - return ret; -} - static int bch2_gc_write_stripes_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) @@ -1171,7 +1076,6 @@ static int gc_btree_gens_key(struct btree_trans *trans, if (unlikely(test_bit(BCH_FS_going_ro, &c->flags))) return -EROFS; - percpu_down_read(&c->mark_lock); rcu_read_lock(); bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev); @@ -1180,7 +1084,6 @@ static int gc_btree_gens_key(struct btree_trans *trans, if (dev_ptr_stale(ca, ptr) > 16) { rcu_read_unlock(); - percpu_up_read(&c->mark_lock); goto update; } } @@ -1195,7 +1098,6 @@ static int gc_btree_gens_key(struct btree_trans *trans, *gen = ptr->gen; } rcu_read_unlock(); - percpu_up_read(&c->mark_lock); return 0; update: u = bch2_bkey_make_mut(trans, iter, &k, 0); @@ -1224,7 +1126,6 @@ static int bch2_alloc_write_oldest_gen(struct btree_trans *trans, struct bch_dev return ret; a_mut->v.oldest_gen = ca->oldest_gen[iter->pos.offset]; - alloc_data_type_set(&a_mut->v, a_mut->v.data_type); return bch2_trans_update(trans, iter, &a_mut->k_i, 0); } @@ -1337,9 +1238,16 @@ void bch2_gc_gens_async(struct bch_fs *c) bch2_write_ref_put(c, BCH_WRITE_REF_gc_gens); } -void bch2_fs_gc_init(struct bch_fs *c) +void bch2_fs_btree_gc_exit(struct bch_fs *c) { - seqcount_init(&c->gc_pos_lock); +} +int bch2_fs_btree_gc_init(struct bch_fs *c) +{ + seqcount_init(&c->gc_pos_lock); INIT_WORK(&c->gc_gens_work, bch2_gc_gens_work); + + init_rwsem(&c->gc_lock); + mutex_init(&c->gc_gens_lock); + return 0; } diff --git a/fs/bcachefs/btree_gc.h b/fs/bcachefs/btree_gc.h index 8a47e8bd0791..9693a90a48a2 100644 --- a/fs/bcachefs/btree_gc.h +++ b/fs/bcachefs/btree_gc.h @@ -82,6 +82,8 @@ void bch2_gc_pos_to_text(struct printbuf *, struct gc_pos *); int bch2_gc_gens(struct bch_fs *); void bch2_gc_gens_async(struct bch_fs *); -void bch2_fs_gc_init(struct bch_fs *); + +void bch2_fs_btree_gc_exit(struct bch_fs *); +int bch2_fs_btree_gc_init(struct bch_fs *); #endif /* _BCACHEFS_BTREE_GC_H */ diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 839d68802e42..e371e60e3133 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -25,9 +25,8 @@ static void bch2_btree_node_header_to_text(struct printbuf *out, struct btree_node *bn) { - prt_printf(out, "btree=%s l=%u seq %llux\n", - bch2_btree_id_str(BTREE_NODE_ID(bn)), - (unsigned) BTREE_NODE_LEVEL(bn), bn->keys.seq); + bch2_btree_id_level_to_text(out, BTREE_NODE_ID(bn), BTREE_NODE_LEVEL(bn)); + prt_printf(out, " seq %llx %llu\n", bn->keys.seq, BTREE_NODE_SEQ(bn)); prt_str(out, "min: "); bch2_bpos_to_text(out, bn->min_key); prt_newline(out); @@ -490,8 +489,8 @@ void bch2_btree_init_next(struct btree_trans *trans, struct btree *b) if (b->nsets == MAX_BSETS && !btree_node_write_in_flight(b) && should_compact_all(c, b)) { - bch2_btree_node_write(c, b, SIX_LOCK_write, - BTREE_WRITE_init_next_bset); + bch2_btree_node_write_trans(trans, b, SIX_LOCK_write, + BTREE_WRITE_init_next_bset); reinit_iter = true; } @@ -832,13 +831,32 @@ fsck_err: return ret; } +static int btree_node_bkey_val_validate(struct bch_fs *c, struct btree *b, + struct bkey_s_c k, + enum bch_validate_flags flags) +{ + return bch2_bkey_val_validate(c, k, (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = flags + }); +} + static int bset_key_validate(struct bch_fs *c, struct btree *b, struct bkey_s_c k, - bool updated_range, int rw) + bool updated_range, + enum bch_validate_flags flags) { - return __bch2_bkey_validate(c, k, btree_node_type(b), 0) ?: - (!updated_range ? bch2_bkey_in_btree_node(c, b, k, 0) : 0) ?: - (rw == WRITE ? bch2_bkey_val_validate(c, k, 0) : 0); + struct bkey_validate_context from = (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = flags, + }; + return __bch2_bkey_validate(c, k, from) ?: + (!updated_range ? bch2_bkey_in_btree_node(c, b, k, from) : 0) ?: + (flags & BCH_VALIDATE_write ? btree_node_bkey_val_validate(c, b, k, flags) : 0); } static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, @@ -855,7 +873,21 @@ static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, struct bkey tmp; struct bkey_s u = __bkey_disassemble(b, k, &tmp); - return !__bch2_bkey_validate(c, u.s_c, btree_node_type(b), BCH_VALIDATE_silent); + return !__bch2_bkey_validate(c, u.s_c, + (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = BCH_VALIDATE_silent + }); +} + +static inline int btree_node_read_bkey_cmp(const struct btree *b, + const struct bkey_packed *l, + const struct bkey_packed *r) +{ + return bch2_bkey_cmp_packed(b, l, r) + ?: (int) bkey_deleted(r) - (int) bkey_deleted(l); } static int validate_bset_keys(struct bch_fs *c, struct btree *b, @@ -918,7 +950,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, BSET_BIG_ENDIAN(i), write, &b->format, k); - if (prev && bkey_iter_cmp(b, prev, k) > 0) { + if (prev && btree_node_read_bkey_cmp(b, prev, k) >= 0) { struct bkey up = bkey_unpack_key(b, prev); printbuf_reset(&buf); @@ -965,6 +997,7 @@ drop_this_key: got_good_key: le16_add_cpu(&i->u64s, -next_good_key); memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k); + set_btree_node_need_rewrite(b); } fsck_err: printbuf_exit(&buf); @@ -1038,39 +1071,51 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, while (b->written < (ptr_written ?: btree_sectors(c))) { unsigned sectors; - struct nonce nonce; bool first = !b->written; - bool csum_bad; - if (!b->written) { + if (first) { + bne = NULL; i = &b->data->keys; + } else { + bne = write_block(b); + i = &bne->keys; - btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)), - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_unknown_csum, - "unknown checksum type %llu", BSET_CSUM_TYPE(i)); - - nonce = btree_nonce(i, b->written << 9); + if (i->seq != b->data->keys.seq) + break; + } - struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data); - csum_bad = bch2_crc_cmp(b->data->csum, csum); - if (csum_bad) - bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); + struct nonce nonce = btree_nonce(i, b->written << 9); + bool good_csum_type = bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)); - btree_err_on(csum_bad, - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_bad_csum, - "%s", - (printbuf_reset(&buf), - bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), b->data->csum, csum), - buf.buf)); - - ret = bset_encrypt(c, i, b->written << 9); - if (bch2_fs_fatal_err_on(ret, c, - "decrypting btree node: %s", bch2_err_str(ret))) - goto fsck_err; + btree_err_on(!good_csum_type, + bch2_csum_type_is_encryption(BSET_CSUM_TYPE(i)) + ? -BCH_ERR_btree_node_read_err_must_retry + : -BCH_ERR_btree_node_read_err_want_retry, + c, ca, b, i, NULL, + bset_unknown_csum, + "unknown checksum type %llu", BSET_CSUM_TYPE(i)); + + if (first) { + if (good_csum_type) { + struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data); + bool csum_bad = bch2_crc_cmp(b->data->csum, csum); + if (csum_bad) + bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); + + btree_err_on(csum_bad, + -BCH_ERR_btree_node_read_err_want_retry, + c, ca, b, i, NULL, + bset_bad_csum, + "%s", + (printbuf_reset(&buf), + bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), b->data->csum, csum), + buf.buf)); + + ret = bset_encrypt(c, i, b->written << 9); + if (bch2_fs_fatal_err_on(ret, c, + "decrypting btree node: %s", bch2_err_str(ret))) + goto fsck_err; + } btree_err_on(btree_node_type_is_extents(btree_node_type(b)) && !BTREE_NODE_NEW_EXTENT_OVERWRITE(b->data), @@ -1081,37 +1126,26 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, sectors = vstruct_sectors(b->data, c->block_bits); } else { - bne = write_block(b); - i = &bne->keys; - - if (i->seq != b->data->keys.seq) - break; - - btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)), - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_unknown_csum, - "unknown checksum type %llu", BSET_CSUM_TYPE(i)); - - nonce = btree_nonce(i, b->written << 9); - struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); - csum_bad = bch2_crc_cmp(bne->csum, csum); - if (ca && csum_bad) - bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); - - btree_err_on(csum_bad, - -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, NULL, - bset_bad_csum, - "%s", - (printbuf_reset(&buf), - bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), bne->csum, csum), - buf.buf)); - - ret = bset_encrypt(c, i, b->written << 9); - if (bch2_fs_fatal_err_on(ret, c, - "decrypting btree node: %s", bch2_err_str(ret))) - goto fsck_err; + if (good_csum_type) { + struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); + bool csum_bad = bch2_crc_cmp(bne->csum, csum); + if (ca && csum_bad) + bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); + + btree_err_on(csum_bad, + -BCH_ERR_btree_node_read_err_want_retry, + c, ca, b, i, NULL, + bset_bad_csum, + "%s", + (printbuf_reset(&buf), + bch2_csum_err_msg(&buf, BSET_CSUM_TYPE(i), bne->csum, csum), + buf.buf)); + + ret = bset_encrypt(c, i, b->written << 9); + if (bch2_fs_fatal_err_on(ret, c, + "decrypting btree node: %s", bch2_err_str(ret))) + goto fsck_err; + } sectors = vstruct_sectors(bne, c->block_bits); } @@ -1216,7 +1250,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, struct bkey tmp; struct bkey_s u = __bkey_disassemble(b, k, &tmp); - ret = bch2_bkey_val_validate(c, u.s_c, READ); + ret = btree_node_bkey_val_validate(c, b, u.s_c, READ); if (ret == -BCH_ERR_fsck_delete_bkey || (bch2_inject_invalid_keys && !bversion_cmp(u.k->bversion, MAX_VERSION))) { @@ -1226,6 +1260,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k); set_btree_bset_end(b, b->set); + set_btree_node_need_rewrite(b); continue; } if (ret) @@ -1339,13 +1374,18 @@ start: rb->start_time); bio_put(&rb->bio); - if (saw_error && + if ((saw_error || + btree_node_need_rewrite(b)) && !btree_node_read_error(b) && c->curr_recovery_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes) { - printbuf_reset(&buf); - bch2_bpos_to_text(&buf, b->key.k.p); - bch_err_ratelimited(c, "%s: rewriting btree node at btree=%s level=%u %s due to error", - __func__, bch2_btree_id_str(b->c.btree_id), b->c.level, buf.buf); + if (saw_error) { + printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + bch_err_ratelimited(c, "%s: rewriting btree node at due to error\n %s", + __func__, buf.buf); + } bch2_btree_node_rewrite_async(c, b); } @@ -1933,7 +1973,12 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b, bool saw_error; int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key), - BKEY_TYPE_btree, WRITE); + (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level + 1, + .btree = b->c.btree_id, + .flags = BCH_VALIDATE_write, + }); if (ret) { bch2_fs_inconsistent(c, "invalid btree node key before write"); return ret; @@ -2300,6 +2345,34 @@ void bch2_btree_node_write(struct bch_fs *c, struct btree *b, } } +void bch2_btree_node_write_trans(struct btree_trans *trans, struct btree *b, + enum six_lock_type lock_type_held, + unsigned flags) +{ + struct bch_fs *c = trans->c; + + if (lock_type_held == SIX_LOCK_intent || + (lock_type_held == SIX_LOCK_read && + six_lock_tryupgrade(&b->c.lock))) { + __bch2_btree_node_write(c, b, flags); + + /* don't cycle lock unnecessarily: */ + if (btree_node_just_written(b) && + six_trylock_write(&b->c.lock)) { + bch2_btree_post_write_cleanup(c, b); + __bch2_btree_node_unlock_write(trans, b); + } + + if (lock_type_held == SIX_LOCK_read) + six_lock_downgrade(&b->c.lock); + } else { + __bch2_btree_node_write(c, b, flags); + if (lock_type_held == SIX_LOCK_write && + btree_node_just_written(b)) + bch2_btree_post_write_cleanup(c, b); + } +} + static bool __bch2_btree_flush_all(struct bch_fs *c, unsigned flag) { struct bucket_table *tbl; diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h index 9b01ca3de907..6f9e4a6dacf7 100644 --- a/fs/bcachefs/btree_io.h +++ b/fs/bcachefs/btree_io.h @@ -144,11 +144,13 @@ enum btree_write_flags { void __bch2_btree_node_write(struct bch_fs *, struct btree *, unsigned); void bch2_btree_node_write(struct bch_fs *, struct btree *, enum six_lock_type, unsigned); +void bch2_btree_node_write_trans(struct btree_trans *, struct btree *, + enum six_lock_type, unsigned); -static inline void btree_node_write_if_need(struct bch_fs *c, struct btree *b, +static inline void btree_node_write_if_need(struct btree_trans *trans, struct btree *b, enum six_lock_type lock_held) { - bch2_btree_node_write(c, b, lock_held, BTREE_WRITE_ONLY_IF_NEED); + bch2_btree_node_write_trans(trans, b, lock_held, BTREE_WRITE_ONLY_IF_NEED); } bool bch2_btree_flush_all_reads(struct bch_fs *); diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index eef9b89c561d..367231ab1980 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -270,8 +270,10 @@ static void bch2_btree_iter_verify_entry_exit(struct btree_iter *iter) BUG_ON(!(iter->flags & BTREE_ITER_all_snapshots) && iter->pos.snapshot != iter->snapshot); - BUG_ON(bkey_lt(iter->pos, bkey_start_pos(&iter->k)) || - bkey_gt(iter->pos, iter->k.p)); + BUG_ON(iter->flags & BTREE_ITER_all_snapshots ? !bpos_eq(iter->pos, iter->k.p) : + !(iter->flags & BTREE_ITER_is_extents) ? !bkey_eq(iter->pos, iter->k.p) : + (bkey_lt(iter->pos, bkey_start_pos(&iter->k)) || + bkey_gt(iter->pos, iter->k.p))); } static int bch2_btree_iter_verify_ret(struct btree_iter *iter, struct bkey_s_c k) @@ -327,7 +329,7 @@ out: void bch2_assert_pos_locked(struct btree_trans *trans, enum btree_id id, struct bpos pos) { - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); struct btree_path *path; struct trans_for_each_path_inorder_iter iter; @@ -697,6 +699,19 @@ void bch2_trans_node_add(struct btree_trans *trans, bch2_trans_revalidate_updates_in_node(trans, b); } +void bch2_trans_node_drop(struct btree_trans *trans, + struct btree *b) +{ + struct btree_path *path; + unsigned i, level = b->c.level; + + trans_for_each_path(trans, path, i) + if (path->l[level].b == b) { + btree_node_unlock(trans, path, level); + path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); + } +} + /* * A btree node has been modified in such a way as to invalidate iterators - fix * them: @@ -720,7 +735,7 @@ static inline int btree_path_lock_root(struct btree_trans *trans, unsigned long trace_ip) { struct bch_fs *c = trans->c; - struct btree *b, **rootp = &bch2_btree_id_root(c, path->btree_id)->b; + struct btree_root *r = bch2_btree_id_root(c, path->btree_id); enum six_lock_type lock_type; unsigned i; int ret; @@ -728,7 +743,12 @@ static inline int btree_path_lock_root(struct btree_trans *trans, EBUG_ON(path->nodes_locked); while (1) { - b = READ_ONCE(*rootp); + struct btree *b = READ_ONCE(r->b); + if (unlikely(!b)) { + BUG_ON(!r->error); + return r->error; + } + path->level = READ_ONCE(b->c.level); if (unlikely(path->level < depth_want)) { @@ -748,14 +768,12 @@ static inline int btree_path_lock_root(struct btree_trans *trans, ret = btree_node_lock(trans, path, &b->c, path->level, lock_type, trace_ip); if (unlikely(ret)) { - if (bch2_err_matches(ret, BCH_ERR_lock_fail_root_changed)) - continue; if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; BUG(); } - if (likely(b == READ_ONCE(*rootp) && + if (likely(b == READ_ONCE(r->b) && b->c.level == path->level && !race_fault())) { for (i = 0; i < path->level; i++) @@ -825,6 +843,8 @@ static int btree_path_prefetch_j(struct btree_trans *trans, struct btree_path *p bch2_bkey_buf_init(&tmp); + jiter->fail_if_too_many_whiteouts = true; + while (nr-- && !ret) { if (!bch2_btree_node_relock(trans, path, path->level)) break; @@ -1000,7 +1020,7 @@ retry_all: bch2_trans_unlock(trans); cond_resched(); - trans_set_locked(trans); + trans_set_locked(trans, false); if (unlikely(trans->memory_allocation_failure)) { struct closure cl; @@ -1267,7 +1287,7 @@ __bch2_btree_path_set_pos(struct btree_trans *trans, { int cmp = bpos_cmp(new_pos, trans->paths[path_idx].pos); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); EBUG_ON(!trans->paths[path_idx].ref); trace_btree_path_set_pos(trans, trans->paths + path_idx, &new_pos); @@ -1427,17 +1447,31 @@ void __noreturn bch2_trans_restart_error(struct btree_trans *trans, u32 restart_ (void *) trans->last_begin_ip); } -void __noreturn bch2_trans_in_restart_error(struct btree_trans *trans) +static void __noreturn bch2_trans_in_restart_error(struct btree_trans *trans) { +#ifdef CONFIG_BCACHEFS_DEBUG + struct printbuf buf = PRINTBUF; + bch2_prt_backtrace(&buf, &trans->last_restarted_trace); + panic("in transaction restart: %s, last restarted by\n%s", + bch2_err_str(trans->restarted), + buf.buf); +#else panic("in transaction restart: %s, last restarted by %pS\n", bch2_err_str(trans->restarted), (void *) trans->last_restarted_ip); +#endif } -void __noreturn bch2_trans_unlocked_error(struct btree_trans *trans) +void __noreturn bch2_trans_unlocked_or_in_restart_error(struct btree_trans *trans) { - panic("trans should be locked, unlocked by %pS\n", - (void *) trans->last_unlock_ip); + if (trans->restarted) + bch2_trans_in_restart_error(trans); + + if (!trans->locked) + panic("trans should be locked, unlocked by %pS\n", + (void *) trans->last_unlock_ip); + + BUG(); } noinline __cold @@ -1450,10 +1484,11 @@ void bch2_trans_updates_to_text(struct printbuf *buf, struct btree_trans *trans) trans_for_each_update(trans, i) { struct bkey_s_c old = { &i->old_k, i->old_v }; - prt_printf(buf, "update: btree=%s cached=%u %pS\n", - bch2_btree_id_str(i->btree_id), - i->cached, - (void *) i->ip_allocated); + prt_str(buf, "update: btree="); + bch2_btree_id_to_text(buf, i->btree_id); + prt_printf(buf, " cached=%u %pS\n", + i->cached, + (void *) i->ip_allocated); prt_printf(buf, " old "); bch2_bkey_val_to_text(buf, trans->c, old); @@ -1486,13 +1521,13 @@ static void bch2_btree_path_to_text_short(struct printbuf *out, struct btree_tra { struct btree_path *path = trans->paths + path_idx; - prt_printf(out, "path: idx %3u ref %u:%u %c %c %c btree=%s l=%u pos ", + prt_printf(out, "path: idx %3u ref %u:%u %c %c %c ", path_idx, path->ref, path->intent_ref, path->preserve ? 'P' : ' ', path->should_be_locked ? 'S' : ' ', - path->cached ? 'C' : 'B', - bch2_btree_id_str(path->btree_id), - path->level); + path->cached ? 'C' : 'B'); + bch2_btree_id_level_to_text(out, path->btree_id, path->level); + prt_str(out, " pos "); bch2_bpos_to_text(out, path->pos); if (!path->cached && btree_node_locked(path, path->level)) { @@ -1717,8 +1752,7 @@ btree_path_idx_t bch2_path_get(struct btree_trans *trans, struct trans_for_each_path_inorder_iter iter; btree_path_idx_t path_pos = 0, path_idx; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); bch2_trans_verify_locks(trans); btree_trans_sort_paths(trans); @@ -1833,7 +1867,7 @@ struct bkey_s_c bch2_btree_path_peek_slot(struct btree_path *path, struct bkey * !bkey_eq(path->pos, ck->key.pos)); *u = ck->k->k; - k = bkey_i_to_s_c(ck->k); + k = (struct bkey_s_c) { u, &ck->k->v }; } return k; @@ -1843,7 +1877,6 @@ hole: return (struct bkey_s_c) { u, NULL }; } - void bch2_set_btree_iter_dontneed(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; @@ -1870,7 +1903,7 @@ bch2_btree_iter_traverse(struct btree_iter *iter) struct btree_trans *trans = iter->trans; int ret; - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); iter->path = bch2_btree_path_set_pos(trans, iter->path, btree_iter_search_key(iter), @@ -1945,7 +1978,7 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *iter) int ret; EBUG_ON(trans->paths[iter->path].cached); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); bch2_btree_iter_verify(iter); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); @@ -2101,7 +2134,7 @@ static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans, { struct btree_path *path = btree_iter_path(trans, iter); - return bch2_journal_keys_peek_upto(trans->c, iter->btree_id, + return bch2_journal_keys_peek_max(trans->c, iter->btree_id, path->level, path->pos, end_pos, @@ -2124,21 +2157,47 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, } static noinline -struct bkey_s_c btree_trans_peek_journal(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k) +void btree_trans_peek_journal(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = bch2_btree_journal_peek(trans, iter, - k.k ? k.k->p : path_l(path)->b->key.k.p); - + k->k ? k->k->p : path_l(path)->b->key.k.p); if (next_journal) { iter->k = next_journal->k; - k = bkey_i_to_s_c(next_journal); + *k = bkey_i_to_s_c(next_journal); } +} - return k; +static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans, + struct btree_iter *iter, + struct bpos end_pos) +{ + struct btree_path *path = btree_iter_path(trans, iter); + + return bch2_journal_keys_peek_prev_min(trans->c, iter->btree_id, + path->level, + path->pos, + end_pos, + &iter->journal_idx); +} + +static noinline +void btree_trans_peek_prev_journal(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c *k) +{ + struct btree_path *path = btree_iter_path(trans, iter); + struct bkey_i *next_journal = + bch2_btree_journal_peek_prev(trans, iter, + k->k ? k->k->p : path_l(path)->b->key.k.p); + + if (next_journal) { + iter->k = next_journal->k; + *k = bkey_i_to_s_c(next_journal); + } } /* @@ -2154,8 +2213,7 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos struct bkey_s_c k; int ret; - bch2_trans_verify_not_in_restart(trans); - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if ((iter->flags & BTREE_ITER_key_cache_fill) && bpos_eq(iter->pos, pos)) @@ -2184,10 +2242,15 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path); k = bch2_btree_path_peek_slot(trans->paths + iter->key_cache_path, &u); - if (k.k && !bkey_err(k)) { - iter->k = u; - k.k = &iter->k; - } + if (!k.k) + return k; + + if ((iter->flags & BTREE_ITER_all_snapshots) && + !bpos_eq(pos, k.k->p)) + return bkey_s_c_null; + + iter->k = u; + k.k = &iter->k; return k; } @@ -2201,8 +2264,6 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp bch2_btree_iter_verify(iter); while (1) { - struct btree_path_level *l; - iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); @@ -2212,17 +2273,17 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp /* ensure that iter->k is consistent with iter->pos: */ bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); - goto out; + break; } struct btree_path *path = btree_iter_path(trans, iter); - l = path_l(path); + struct btree_path_level *l = path_l(path); if (unlikely(!l->b)) { /* No btree nodes at requested level: */ bch2_btree_iter_set_pos(iter, SPOS_MAX); k = bkey_s_c_null; - goto out; + break; } btree_path_set_should_be_locked(trans, path); @@ -2233,15 +2294,14 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp k.k && (k2 = btree_trans_peek_key_cache(iter, k.k->p)).k) { k = k2; - ret = bkey_err(k); - if (ret) { + if (bkey_err(k)) { bch2_btree_iter_set_pos(iter, iter->pos); - goto out; + break; } } if (unlikely(iter->flags & BTREE_ITER_with_journal)) - k = btree_trans_peek_journal(trans, iter, k); + btree_trans_peek_journal(trans, iter, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) @@ -2270,32 +2330,32 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bp /* End of btree: */ bch2_btree_iter_set_pos(iter, SPOS_MAX); k = bkey_s_c_null; - goto out; + break; } } -out: - bch2_btree_iter_verify(iter); + bch2_btree_iter_verify(iter); return k; } /** - * bch2_btree_iter_peek_upto() - returns first key greater than or equal to + * bch2_btree_iter_peek_max() - returns first key greater than or equal to * iterator's current position * @iter: iterator to peek from * @end: search limit: returns keys less than or equal to @end * * Returns: key if found, or an error extractable with bkey_err(). */ -struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos end) +struct bkey_s_c bch2_btree_iter_peek_max(struct btree_iter *iter, struct bpos end) { struct btree_trans *trans = iter->trans; struct bpos search_key = btree_iter_search_key(iter); struct bkey_s_c k; - struct bpos iter_pos; + struct bpos iter_pos = iter->pos; int ret; - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); + bch2_btree_iter_verify_entry_exit(iter); EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bkey_eq(end, POS_MAX)); if (iter->update_path) { @@ -2304,8 +2364,6 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e iter->update_path = 0; } - bch2_btree_iter_verify_entry_exit(iter); - while (1) { k = __bch2_btree_iter_peek(iter, search_key); if (unlikely(!k.k)) @@ -2313,75 +2371,75 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e if (unlikely(bkey_err(k))) goto out_no_locked; - /* - * We need to check against @end before FILTER_SNAPSHOTS because - * if we get to a different inode that requested we might be - * seeing keys for a different snapshot tree that will all be - * filtered out. - * - * But we can't do the full check here, because bkey_start_pos() - * isn't monotonically increasing before FILTER_SNAPSHOTS, and - * that's what we check against in extents mode: - */ - if (unlikely(!(iter->flags & BTREE_ITER_is_extents) - ? bkey_gt(k.k->p, end) - : k.k->p.inode > end.inode)) - goto end; + if (iter->flags & BTREE_ITER_filter_snapshots) { + /* + * We need to check against @end before FILTER_SNAPSHOTS because + * if we get to a different inode that requested we might be + * seeing keys for a different snapshot tree that will all be + * filtered out. + * + * But we can't do the full check here, because bkey_start_pos() + * isn't monotonically increasing before FILTER_SNAPSHOTS, and + * that's what we check against in extents mode: + */ + if (unlikely(!(iter->flags & BTREE_ITER_is_extents) + ? bkey_gt(k.k->p, end) + : k.k->p.inode > end.inode)) + goto end; + + if (iter->update_path && + !bkey_eq(trans->paths[iter->update_path].pos, k.k->p)) { + bch2_path_put_nokeep(trans, iter->update_path, + iter->flags & BTREE_ITER_intent); + iter->update_path = 0; + } - if (iter->update_path && - !bkey_eq(trans->paths[iter->update_path].pos, k.k->p)) { - bch2_path_put_nokeep(trans, iter->update_path, - iter->flags & BTREE_ITER_intent); - iter->update_path = 0; - } + if ((iter->flags & BTREE_ITER_intent) && + !(iter->flags & BTREE_ITER_is_extents) && + !iter->update_path) { + struct bpos pos = k.k->p; - if ((iter->flags & BTREE_ITER_filter_snapshots) && - (iter->flags & BTREE_ITER_intent) && - !(iter->flags & BTREE_ITER_is_extents) && - !iter->update_path) { - struct bpos pos = k.k->p; + if (pos.snapshot < iter->snapshot) { + search_key = bpos_successor(k.k->p); + continue; + } - if (pos.snapshot < iter->snapshot) { - search_key = bpos_successor(k.k->p); - continue; - } + pos.snapshot = iter->snapshot; - pos.snapshot = iter->snapshot; + /* + * advance, same as on exit for iter->path, but only up + * to snapshot + */ + __btree_path_get(trans, trans->paths + iter->path, iter->flags & BTREE_ITER_intent); + iter->update_path = iter->path; + + iter->update_path = bch2_btree_path_set_pos(trans, + iter->update_path, pos, + iter->flags & BTREE_ITER_intent, + _THIS_IP_); + ret = bch2_btree_path_traverse(trans, iter->update_path, iter->flags); + if (unlikely(ret)) { + k = bkey_s_c_err(ret); + goto out_no_locked; + } + } /* - * advance, same as on exit for iter->path, but only up - * to snapshot + * We can never have a key in a leaf node at POS_MAX, so + * we don't have to check these successor() calls: */ - __btree_path_get(trans, trans->paths + iter->path, iter->flags & BTREE_ITER_intent); - iter->update_path = iter->path; - - iter->update_path = bch2_btree_path_set_pos(trans, - iter->update_path, pos, - iter->flags & BTREE_ITER_intent, - _THIS_IP_); - ret = bch2_btree_path_traverse(trans, iter->update_path, iter->flags); - if (unlikely(ret)) { - k = bkey_s_c_err(ret); - goto out_no_locked; + if (!bch2_snapshot_is_ancestor(trans->c, + iter->snapshot, + k.k->p.snapshot)) { + search_key = bpos_successor(k.k->p); + continue; } - } - - /* - * We can never have a key in a leaf node at POS_MAX, so - * we don't have to check these successor() calls: - */ - if ((iter->flags & BTREE_ITER_filter_snapshots) && - !bch2_snapshot_is_ancestor(trans->c, - iter->snapshot, - k.k->p.snapshot)) { - search_key = bpos_successor(k.k->p); - continue; - } - if (bkey_whiteout(k.k) && - !(iter->flags & BTREE_ITER_all_snapshots)) { - search_key = bkey_successor(iter, k.k->p); - continue; + if (bkey_whiteout(k.k) && + !(iter->flags & BTREE_ITER_key_cache_fill)) { + search_key = bkey_successor(iter, k.k->p); + continue; + } } /* @@ -2451,127 +2509,204 @@ struct bkey_s_c bch2_btree_iter_next(struct btree_iter *iter) return bch2_btree_iter_peek(iter); } -/** - * bch2_btree_iter_peek_prev() - returns first key less than or equal to - * iterator's current position - * @iter: iterator to peek from - * - * Returns: key if found, or an error extractable with bkey_err(). - */ -struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter) +static struct bkey_s_c __bch2_btree_iter_peek_prev(struct btree_iter *iter, struct bpos search_key) { struct btree_trans *trans = iter->trans; - struct bpos search_key = iter->pos; - struct bkey_s_c k; - struct bkey saved_k; - const struct bch_val *saved_v; - btree_path_idx_t saved_path = 0; - int ret; - - bch2_trans_verify_not_unlocked(trans); - EBUG_ON(btree_iter_path(trans, iter)->cached || - btree_iter_path(trans, iter)->level); - - if (iter->flags & BTREE_ITER_with_journal) - return bkey_s_c_err(-BCH_ERR_btree_iter_with_journal_not_supported); + struct bkey_s_c k, k2; bch2_btree_iter_verify(iter); - bch2_btree_iter_verify_entry_exit(iter); - - if (iter->flags & BTREE_ITER_filter_snapshots) - search_key.snapshot = U32_MAX; while (1) { iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, - iter->flags & BTREE_ITER_intent, - btree_iter_ip_allocated(iter)); + iter->flags & BTREE_ITER_intent, + btree_iter_ip_allocated(iter)); - ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); + int ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (unlikely(ret)) { /* ensure that iter->k is consistent with iter->pos: */ bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); - goto out_no_locked; + break; } struct btree_path *path = btree_iter_path(trans, iter); + struct btree_path_level *l = path_l(path); + + if (unlikely(!l->b)) { + /* No btree nodes at requested level: */ + bch2_btree_iter_set_pos(iter, SPOS_MAX); + k = bkey_s_c_null; + break; + } + + btree_path_set_should_be_locked(trans, path); - k = btree_path_level_peek(trans, path, &path->l[0], &iter->k); - if (!k.k || - ((iter->flags & BTREE_ITER_is_extents) - ? bpos_ge(bkey_start_pos(k.k), search_key) - : bpos_gt(k.k->p, search_key))) - k = btree_path_level_prev(trans, path, &path->l[0], &iter->k); + k = btree_path_level_peek_all(trans->c, l, &iter->k); + if (!k.k || bpos_gt(k.k->p, search_key)) { + k = btree_path_level_prev(trans, path, l, &iter->k); + + BUG_ON(k.k && bpos_gt(k.k->p, search_key)); + } + + if (unlikely(iter->flags & BTREE_ITER_with_key_cache) && + k.k && + (k2 = btree_trans_peek_key_cache(iter, k.k->p)).k) { + k = k2; + if (bkey_err(k2)) { + bch2_btree_iter_set_pos(iter, iter->pos); + break; + } + } + + if (unlikely(iter->flags & BTREE_ITER_with_journal)) + btree_trans_peek_prev_journal(trans, iter, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) bch2_btree_trans_peek_prev_updates(trans, iter, &k); - if (likely(k.k)) { - if (iter->flags & BTREE_ITER_filter_snapshots) { - if (k.k->p.snapshot == iter->snapshot) - goto got_key; + if (likely(k.k && !bkey_deleted(k.k))) { + break; + } else if (k.k) { + search_key = bpos_predecessor(k.k->p); + } else if (likely(!bpos_eq(path->l[0].b->data->min_key, POS_MIN))) { + /* Advance to previous leaf node: */ + search_key = bpos_predecessor(path->l[0].b->data->min_key); + } else { + /* Start of btree: */ + bch2_btree_iter_set_pos(iter, POS_MIN); + k = bkey_s_c_null; + break; + } + } + + bch2_btree_iter_verify(iter); + return k; +} + +/** + * bch2_btree_iter_peek_prev_min() - returns first key less than or equal to + * iterator's current position + * @iter: iterator to peek from + * @end: search limit: returns keys greater than or equal to @end + * + * Returns: key if found, or an error extractable with bkey_err(). + */ +struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_iter *iter, struct bpos end) +{ + if ((iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots)) && + !bkey_eq(iter->pos, POS_MAX)) { + /* + * bkey_start_pos(), for extents, is not monotonically + * increasing until after filtering for snapshots: + * + * Thus, for extents we need to search forward until we find a + * real visible extents - easiest to just use peek_slot() (which + * internally uses peek() for extents) + */ + struct bkey_s_c k = bch2_btree_iter_peek_slot(iter); + if (bkey_err(k)) + return k; + + if (!bkey_deleted(k.k) && + (!(iter->flags & BTREE_ITER_is_extents) || + bkey_lt(bkey_start_pos(k.k), iter->pos))) + return k; + } + + struct btree_trans *trans = iter->trans; + struct bpos search_key = iter->pos; + struct bkey_s_c k; + btree_path_idx_t saved_path = 0; + + bch2_trans_verify_not_unlocked_or_in_restart(trans); + bch2_btree_iter_verify_entry_exit(iter); + EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN)); + + while (1) { + k = __bch2_btree_iter_peek_prev(iter, search_key); + if (unlikely(!k.k)) + goto end; + if (unlikely(bkey_err(k))) + goto out_no_locked; + if (iter->flags & BTREE_ITER_filter_snapshots) { + struct btree_path *s = saved_path ? trans->paths + saved_path : NULL; + if (s && bpos_lt(k.k->p, SPOS(s->pos.inode, s->pos.offset, iter->snapshot))) { /* - * If we have a saved candidate, and we're no - * longer at the same _key_ (not pos), return - * that candidate + * If we have a saved candidate, and we're past + * the last possible snapshot overwrite, return + * it: */ - if (saved_path && !bkey_eq(k.k->p, saved_k.p)) { - bch2_path_put_nokeep(trans, iter->path, - iter->flags & BTREE_ITER_intent); - iter->path = saved_path; + bch2_path_put_nokeep(trans, iter->path, + iter->flags & BTREE_ITER_intent); + iter->path = saved_path; + saved_path = 0; + k = bch2_btree_path_peek_slot(btree_iter_path(trans, iter), &iter->k); + break; + } + + /* + * We need to check against @end before FILTER_SNAPSHOTS because + * if we get to a different inode that requested we might be + * seeing keys for a different snapshot tree that will all be + * filtered out. + */ + if (unlikely(bkey_lt(k.k->p, end))) + goto end; + + if (!bch2_snapshot_is_ancestor(trans->c, iter->snapshot, k.k->p.snapshot)) { + search_key = bpos_predecessor(k.k->p); + continue; + } + + if (k.k->p.snapshot != iter->snapshot) { + /* + * Have a key visible in iter->snapshot, but + * might have overwrites: - save it and keep + * searching. Unless it's a whiteout - then drop + * our previous saved candidate: + */ + if (saved_path) { + bch2_path_put_nokeep(trans, saved_path, + iter->flags & BTREE_ITER_intent); saved_path = 0; - iter->k = saved_k; - k.v = saved_v; - goto got_key; } - if (bch2_snapshot_is_ancestor(trans->c, - iter->snapshot, - k.k->p.snapshot)) { - if (saved_path) - bch2_path_put_nokeep(trans, saved_path, - iter->flags & BTREE_ITER_intent); + if (!bkey_whiteout(k.k)) { saved_path = btree_path_clone(trans, iter->path, iter->flags & BTREE_ITER_intent, _THIS_IP_); - path = btree_iter_path(trans, iter); - trace_btree_path_save_pos(trans, path, trans->paths + saved_path); - saved_k = *k.k; - saved_v = k.v; + trace_btree_path_save_pos(trans, + trans->paths + iter->path, + trans->paths + saved_path); } search_key = bpos_predecessor(k.k->p); continue; } -got_key: - if (bkey_whiteout(k.k) && - !(iter->flags & BTREE_ITER_all_snapshots)) { + + if (bkey_whiteout(k.k)) { search_key = bkey_predecessor(iter, k.k->p); - if (iter->flags & BTREE_ITER_filter_snapshots) - search_key.snapshot = U32_MAX; + search_key.snapshot = U32_MAX; continue; } - - btree_path_set_should_be_locked(trans, path); - break; - } else if (likely(!bpos_eq(path->l[0].b->data->min_key, POS_MIN))) { - /* Advance to previous leaf node: */ - search_key = bpos_predecessor(path->l[0].b->data->min_key); - } else { - /* Start of btree: */ - bch2_btree_iter_set_pos(iter, POS_MIN); - k = bkey_s_c_null; - goto out_no_locked; } - } - EBUG_ON(bkey_gt(bkey_start_pos(k.k), iter->pos)); + EBUG_ON(iter->flags & BTREE_ITER_all_snapshots ? bpos_gt(k.k->p, iter->pos) : + iter->flags & BTREE_ITER_is_extents ? bkey_ge(bkey_start_pos(k.k), iter->pos) : + bkey_gt(k.k->p, iter->pos)); + + if (unlikely(iter->flags & BTREE_ITER_all_snapshots ? bpos_lt(k.k->p, end) : + iter->flags & BTREE_ITER_is_extents ? bkey_le(k.k->p, end) : + bkey_lt(k.k->p, end))) + goto end; + + break; + } /* Extents can straddle iter->pos: */ - if (bkey_lt(k.k->p, iter->pos)) - iter->pos = k.k->p; + iter->pos = bpos_min(iter->pos, k.k->p);; if (iter->flags & BTREE_ITER_filter_snapshots) iter->pos.snapshot = iter->snapshot; @@ -2581,8 +2716,11 @@ out_no_locked: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(iter); - return k; +end: + bch2_btree_iter_set_pos(iter, end); + k = bkey_s_c_null; + goto out_no_locked; } /** @@ -2607,7 +2745,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) struct bkey_s_c k; int ret; - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); bch2_btree_iter_verify(iter); bch2_btree_iter_verify_entry_exit(iter); EBUG_ON(btree_iter_path(trans, iter)->level && (iter->flags & BTREE_ITER_with_key_cache)); @@ -2632,6 +2770,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) goto out_no_locked; } + struct btree_path *path = btree_iter_path(trans, iter); + if (unlikely(!btree_path_node(path, path->level))) + return bkey_s_c_null; + if ((iter->flags & BTREE_ITER_cached) || !(iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots))) { k = bkey_s_c_null; @@ -2658,6 +2800,11 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k); if (unlikely(!k.k)) goto out_no_locked; + + if (unlikely(k.k->type == KEY_TYPE_whiteout && + (iter->flags & BTREE_ITER_filter_snapshots) && + !(iter->flags & BTREE_ITER_key_cache_fill))) + iter->k.type = KEY_TYPE_deleted; } else { struct bpos next; struct bpos end = iter->pos; @@ -2671,7 +2818,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) struct btree_iter iter2; bch2_trans_copy_iter(&iter2, iter); - k = bch2_btree_iter_peek_upto(&iter2, end); + k = bch2_btree_iter_peek_max(&iter2, end); if (k.k && !bkey_err(k)) { swap(iter->key_cache_path, iter2.key_cache_path); @@ -2682,7 +2829,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) } else { struct bpos pos = iter->pos; - k = bch2_btree_iter_peek_upto(iter, end); + k = bch2_btree_iter_peek_max(iter, end); if (unlikely(bkey_err(k))) bch2_btree_iter_set_pos(iter, pos); else @@ -2902,7 +3049,7 @@ void bch2_trans_iter_init_outlined(struct btree_trans *trans, unsigned flags) { bch2_trans_iter_init_common(trans, iter, btree_id, pos, 0, 0, - bch2_btree_iter_flags(trans, btree_id, flags), + bch2_btree_iter_flags(trans, btree_id, 0, flags), _RET_IP_); } @@ -2918,8 +3065,11 @@ void bch2_trans_node_iter_init(struct btree_trans *trans, flags |= BTREE_ITER_snapshot_field; flags |= BTREE_ITER_all_snapshots; + if (!depth && btree_id_cached(trans->c, btree_id)) + flags |= BTREE_ITER_with_key_cache; + bch2_trans_iter_init_common(trans, iter, btree_id, pos, locks_want, depth, - __bch2_btree_iter_flags(trans, btree_id, flags), + bch2_btree_iter_flags(trans, btree_id, depth, flags), _RET_IP_); iter->min_depth = depth; @@ -3122,14 +3272,14 @@ u32 bch2_trans_begin(struct btree_trans *trans) trans->last_begin_ip = _RET_IP_; - trans_set_locked(trans); + trans_set_locked(trans, false); if (trans->restarted) { bch2_btree_path_traverse_all(trans); trans->notrace_relock_fail = false; } - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); return trans->restart_count; } @@ -3228,7 +3378,7 @@ got_trans: trans->srcu_idx = srcu_read_lock(&c->btree_trans_barrier); trans->srcu_lock_time = jiffies; trans->srcu_held = true; - trans_set_locked(trans); + trans_set_locked(trans, false); closure_init_stack_release(&trans->ref); return trans; @@ -3262,6 +3412,9 @@ void bch2_trans_put(struct btree_trans *trans) { struct bch_fs *c = trans->c; + if (trans->restarted) + bch2_trans_in_restart_error(trans); + bch2_trans_unlock(trans); trans_for_each_update(trans, i) @@ -3285,6 +3438,10 @@ void bch2_trans_put(struct btree_trans *trans) closure_return_sync(&trans->ref); trans->locking_wait.task = NULL; +#ifdef CONFIG_BCACHEFS_DEBUG + darray_exit(&trans->last_restarted_trace); +#endif + unsigned long *paths_allocated = trans->paths_allocated; trans->paths_allocated = NULL; trans->paths = NULL; @@ -3338,8 +3495,9 @@ bch2_btree_bkey_cached_common_to_text(struct printbuf *out, pid = owner ? owner->pid : 0; rcu_read_unlock(); - prt_printf(out, "\t%px %c l=%u %s:", b, b->cached ? 'c' : 'b', - b->level, bch2_btree_id_str(b->btree_id)); + prt_printf(out, "\t%px %c ", b, b->cached ? 'c' : 'b'); + bch2_btree_id_to_text(out, b->btree_id); + prt_printf(out, " l=%u:", b->level); bch2_bpos_to_text(out, btree_node_pos(b)); prt_printf(out, "\t locks %u:%u:%u held by pid %u", @@ -3378,11 +3536,11 @@ void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans) if (!path->nodes_locked) continue; - prt_printf(out, " path %u %c l=%u %s:", - idx, - path->cached ? 'c' : 'b', - path->level, - bch2_btree_id_str(path->btree_id)); + prt_printf(out, " path %u %c ", + idx, + path->cached ? 'c' : 'b'); + bch2_btree_id_to_text(out, path->btree_id); + prt_printf(out, " l=%u:", path->level); bch2_bpos_to_text(out, path->pos); prt_newline(out); @@ -3488,7 +3646,7 @@ int bch2_fs_btree_iter_init(struct bch_fs *c) #ifdef CONFIG_LOCKDEP fs_reclaim_acquire(GFP_KERNEL); struct btree_trans *trans = bch2_trans_get(c); - trans_set_locked(trans); + trans_set_locked(trans, false); bch2_trans_put(trans); fs_reclaim_release(GFP_KERNEL); #endif diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index 0bda054f80d7..b9538e6e6d65 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -23,6 +23,7 @@ static inline void __btree_path_get(struct btree_trans *trans, struct btree_path { unsigned idx = path - trans->paths; + EBUG_ON(idx >= trans->nr_paths); EBUG_ON(!test_bit(idx, trans->paths_allocated)); if (unlikely(path->ref == U8_MAX)) { bch2_dump_trans_paths_updates(trans); @@ -36,6 +37,7 @@ static inline void __btree_path_get(struct btree_trans *trans, struct btree_path static inline bool __btree_path_put(struct btree_trans *trans, struct btree_path *path, bool intent) { + EBUG_ON(path - trans->paths >= trans->nr_paths); EBUG_ON(!test_bit(path - trans->paths, trans->paths_allocated)); EBUG_ON(!path->ref); EBUG_ON(!path->intent_ref && intent); @@ -234,12 +236,12 @@ int __must_check bch2_btree_path_traverse_one(struct btree_trans *, btree_path_idx_t, unsigned, unsigned long); -static inline void bch2_trans_verify_not_unlocked(struct btree_trans *); +static inline void bch2_trans_verify_not_unlocked_or_in_restart(struct btree_trans *); static inline int __must_check bch2_btree_path_traverse(struct btree_trans *trans, btree_path_idx_t path, unsigned flags) { - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (trans->paths[path].uptodate < BTREE_ITER_NEED_RELOCK) return 0; @@ -324,38 +326,33 @@ static inline void bch2_trans_verify_not_restarted(struct btree_trans *trans, bch2_trans_restart_error(trans, restart_count); } -void __noreturn bch2_trans_in_restart_error(struct btree_trans *); +void __noreturn bch2_trans_unlocked_or_in_restart_error(struct btree_trans *); -static inline void bch2_trans_verify_not_in_restart(struct btree_trans *trans) +static inline void bch2_trans_verify_not_unlocked_or_in_restart(struct btree_trans *trans) { - if (trans->restarted) - bch2_trans_in_restart_error(trans); -} - -void __noreturn bch2_trans_unlocked_error(struct btree_trans *); - -static inline void bch2_trans_verify_not_unlocked(struct btree_trans *trans) -{ - if (!trans->locked) - bch2_trans_unlocked_error(trans); + if (trans->restarted || !trans->locked) + bch2_trans_unlocked_or_in_restart_error(trans); } __always_inline -static int btree_trans_restart_nounlock(struct btree_trans *trans, int err) +static int btree_trans_restart_ip(struct btree_trans *trans, int err, unsigned long ip) { BUG_ON(err <= 0); BUG_ON(!bch2_err_matches(-err, BCH_ERR_transaction_restart)); trans->restarted = err; - trans->last_restarted_ip = _THIS_IP_; + trans->last_restarted_ip = ip; +#ifdef CONFIG_BCACHEFS_DEBUG + darray_exit(&trans->last_restarted_trace); + bch2_save_backtrace(&trans->last_restarted_trace, current, 0, GFP_NOWAIT); +#endif return -err; } __always_inline static int btree_trans_restart(struct btree_trans *trans, int err) { - btree_trans_restart_nounlock(trans, err); - return -err; + return btree_trans_restart_ip(trans, err, _THIS_IP_); } bool bch2_btree_node_upgrade(struct btree_trans *, @@ -375,6 +372,7 @@ static inline void bch2_btree_path_downgrade(struct btree_trans *trans, void bch2_trans_downgrade(struct btree_trans *); void bch2_trans_node_add(struct btree_trans *trans, struct btree_path *, struct btree *); +void bch2_trans_node_drop(struct btree_trans *trans, struct btree *); void bch2_trans_node_reinit_iter(struct btree_trans *, struct btree *); int __must_check __bch2_btree_iter_traverse(struct btree_iter *iter); @@ -384,15 +382,21 @@ struct btree *bch2_btree_iter_peek_node(struct btree_iter *); struct btree *bch2_btree_iter_peek_node_and_restart(struct btree_iter *); struct btree *bch2_btree_iter_next_node(struct btree_iter *); -struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *, struct bpos); +struct bkey_s_c bch2_btree_iter_peek_max(struct btree_iter *, struct bpos); struct bkey_s_c bch2_btree_iter_next(struct btree_iter *); static inline struct bkey_s_c bch2_btree_iter_peek(struct btree_iter *iter) { - return bch2_btree_iter_peek_upto(iter, SPOS_MAX); + return bch2_btree_iter_peek_max(iter, SPOS_MAX); +} + +struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_iter *, struct bpos); + +static inline struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter) +{ + return bch2_btree_iter_peek_prev_min(iter, POS_MIN); } -struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *); struct bkey_s_c bch2_btree_iter_prev(struct btree_iter *); struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *); @@ -443,10 +447,17 @@ static inline void bch2_btree_iter_set_snapshot(struct btree_iter *iter, u32 sna void bch2_trans_iter_exit(struct btree_trans *, struct btree_iter *); -static inline unsigned __bch2_btree_iter_flags(struct btree_trans *trans, - unsigned btree_id, - unsigned flags) +static inline unsigned bch2_btree_iter_flags(struct btree_trans *trans, + unsigned btree_id, + unsigned level, + unsigned flags) { + if (level || !btree_id_cached(trans->c, btree_id)) { + flags &= ~BTREE_ITER_cached; + flags &= ~BTREE_ITER_with_key_cache; + } else if (!(flags & BTREE_ITER_cached)) + flags |= BTREE_ITER_with_key_cache; + if (!(flags & (BTREE_ITER_all_snapshots|BTREE_ITER_not_extents)) && btree_id_is_extents(btree_id)) flags |= BTREE_ITER_is_extents; @@ -465,19 +476,6 @@ static inline unsigned __bch2_btree_iter_flags(struct btree_trans *trans, return flags; } -static inline unsigned bch2_btree_iter_flags(struct btree_trans *trans, - unsigned btree_id, - unsigned flags) -{ - if (!btree_id_cached(trans->c, btree_id)) { - flags &= ~BTREE_ITER_cached; - flags &= ~BTREE_ITER_with_key_cache; - } else if (!(flags & BTREE_ITER_cached)) - flags |= BTREE_ITER_with_key_cache; - - return __bch2_btree_iter_flags(trans, btree_id, flags); -} - static inline void bch2_trans_iter_init_common(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, @@ -514,7 +512,7 @@ static inline void bch2_trans_iter_init(struct btree_trans *trans, if (__builtin_constant_p(btree_id) && __builtin_constant_p(flags)) bch2_trans_iter_init_common(trans, iter, btree_id, pos, 0, 0, - bch2_btree_iter_flags(trans, btree_id, flags), + bch2_btree_iter_flags(trans, btree_id, 0, flags), _THIS_IP_); else bch2_trans_iter_init_outlined(trans, iter, btree_id, pos, flags); @@ -593,13 +591,18 @@ static inline struct bkey_s_c bch2_bkey_get_iter(struct btree_trans *trans, bkey_s_c_to_##_type(__bch2_bkey_get_iter(_trans, _iter, \ _btree_id, _pos, _flags, KEY_TYPE_##_type)) +static inline void __bkey_val_copy(void *dst_v, unsigned dst_size, struct bkey_s_c src_k) +{ + unsigned b = min_t(unsigned, dst_size, bkey_val_bytes(src_k.k)); + memcpy(dst_v, src_k.v, b); + if (unlikely(b < dst_size)) + memset(dst_v + b, 0, dst_size - b); +} + #define bkey_val_copy(_dst_v, _src_k) \ do { \ - unsigned b = min_t(unsigned, sizeof(*_dst_v), \ - bkey_val_bytes(_src_k.k)); \ - memcpy(_dst_v, _src_k.v, b); \ - if (b < sizeof(*_dst_v)) \ - memset((void *) (_dst_v) + b, 0, sizeof(*_dst_v) - b); \ + BUILD_BUG_ON(!__typecheck(*_dst_v, *_src_k.v)); \ + __bkey_val_copy(_dst_v, sizeof(*_dst_v), _src_k.s_c); \ } while (0) static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans, @@ -608,17 +611,10 @@ static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans, unsigned val_size, void *val) { struct btree_iter iter; - struct bkey_s_c k; - int ret; - - k = __bch2_bkey_get_iter(trans, &iter, btree_id, pos, flags, type); - ret = bkey_err(k); + struct bkey_s_c k = __bch2_bkey_get_iter(trans, &iter, btree_id, pos, flags, type); + int ret = bkey_err(k); if (!ret) { - unsigned b = min_t(unsigned, bkey_val_bytes(k.k), val_size); - - memcpy(val, k.v, b); - if (unlikely(b < sizeof(*val))) - memset((void *) val + b, 0, sizeof(*val) - b); + __bkey_val_copy(val, val_size, k); bch2_trans_iter_exit(trans, &iter); } @@ -677,12 +673,12 @@ static inline struct bkey_s_c bch2_btree_iter_peek_type(struct btree_iter *iter, bch2_btree_iter_peek(iter); } -static inline struct bkey_s_c bch2_btree_iter_peek_upto_type(struct btree_iter *iter, +static inline struct bkey_s_c bch2_btree_iter_peek_max_type(struct btree_iter *iter, struct bpos end, unsigned flags) { if (!(flags & BTREE_ITER_slots)) - return bch2_btree_iter_peek_upto(iter, end); + return bch2_btree_iter_peek_max(iter, end); if (bkey_gt(iter->pos, end)) return bkey_s_c_null; @@ -746,7 +742,7 @@ transaction_restart: \ _ret2 ?: trans_was_restarted(_trans, _restart_count); \ }) -#define for_each_btree_key_upto_continue(_trans, _iter, \ +#define for_each_btree_key_max_continue(_trans, _iter, \ _end, _flags, _k, _do) \ ({ \ struct bkey_s_c _k; \ @@ -754,7 +750,7 @@ transaction_restart: \ \ do { \ _ret3 = lockrestart_do(_trans, ({ \ - (_k) = bch2_btree_iter_peek_upto_type(&(_iter), \ + (_k) = bch2_btree_iter_peek_max_type(&(_iter), \ _end, (_flags)); \ if (!(_k).k) \ break; \ @@ -768,9 +764,9 @@ transaction_restart: \ }) #define for_each_btree_key_continue(_trans, _iter, _flags, _k, _do) \ - for_each_btree_key_upto_continue(_trans, _iter, SPOS_MAX, _flags, _k, _do) + for_each_btree_key_max_continue(_trans, _iter, SPOS_MAX, _flags, _k, _do) -#define for_each_btree_key_upto(_trans, _iter, _btree_id, \ +#define for_each_btree_key_max(_trans, _iter, _btree_id, \ _start, _end, _flags, _k, _do) \ ({ \ bch2_trans_begin(trans); \ @@ -779,12 +775,12 @@ transaction_restart: \ bch2_trans_iter_init((_trans), &(_iter), (_btree_id), \ (_start), (_flags)); \ \ - for_each_btree_key_upto_continue(_trans, _iter, _end, _flags, _k, _do);\ + for_each_btree_key_max_continue(_trans, _iter, _end, _flags, _k, _do);\ }) #define for_each_btree_key(_trans, _iter, _btree_id, \ _start, _flags, _k, _do) \ - for_each_btree_key_upto(_trans, _iter, _btree_id, _start, \ + for_each_btree_key_max(_trans, _iter, _btree_id, _start, \ SPOS_MAX, _flags, _k, _do) #define for_each_btree_key_reverse(_trans, _iter, _btree_id, \ @@ -828,33 +824,33 @@ transaction_restart: \ (_do) ?: bch2_trans_commit(_trans, (_disk_res),\ (_journal_seq), (_commit_flags))) -#define for_each_btree_key_upto_commit(_trans, _iter, _btree_id, \ +#define for_each_btree_key_max_commit(_trans, _iter, _btree_id, \ _start, _end, _iter_flags, _k, \ _disk_res, _journal_seq, _commit_flags,\ _do) \ - for_each_btree_key_upto(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\ + for_each_btree_key_max(_trans, _iter, _btree_id, _start, _end, _iter_flags, _k,\ (_do) ?: bch2_trans_commit(_trans, (_disk_res),\ (_journal_seq), (_commit_flags))) struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *); -#define for_each_btree_key_upto_norestart(_trans, _iter, _btree_id, \ +#define for_each_btree_key_max_norestart(_trans, _iter, _btree_id, \ _start, _end, _flags, _k, _ret) \ for (bch2_trans_iter_init((_trans), &(_iter), (_btree_id), \ (_start), (_flags)); \ - (_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, _flags),\ + (_k) = bch2_btree_iter_peek_max_type(&(_iter), _end, _flags),\ !((_ret) = bkey_err(_k)) && (_k).k; \ bch2_btree_iter_advance(&(_iter))) -#define for_each_btree_key_upto_continue_norestart(_iter, _end, _flags, _k, _ret)\ +#define for_each_btree_key_max_continue_norestart(_iter, _end, _flags, _k, _ret)\ for (; \ - (_k) = bch2_btree_iter_peek_upto_type(&(_iter), _end, _flags), \ + (_k) = bch2_btree_iter_peek_max_type(&(_iter), _end, _flags), \ !((_ret) = bkey_err(_k)) && (_k).k; \ bch2_btree_iter_advance(&(_iter))) #define for_each_btree_key_norestart(_trans, _iter, _btree_id, \ _start, _flags, _k, _ret) \ - for_each_btree_key_upto_norestart(_trans, _iter, _btree_id, _start,\ + for_each_btree_key_max_norestart(_trans, _iter, _btree_id, _start,\ SPOS_MAX, _flags, _k, _ret) #define for_each_btree_key_reverse_norestart(_trans, _iter, _btree_id, \ @@ -866,7 +862,7 @@ struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *); bch2_btree_iter_rewind(&(_iter))) #define for_each_btree_key_continue_norestart(_iter, _flags, _k, _ret) \ - for_each_btree_key_upto_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret) + for_each_btree_key_max_continue_norestart(_iter, SPOS_MAX, _flags, _k, _ret) /* * This should not be used in a fastpath, without first trying _do in diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index c1657182c275..6d25e3f85ce8 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -16,6 +16,17 @@ * operations for the regular btree iter code to use: */ +static inline size_t pos_to_idx(struct journal_keys *keys, size_t pos) +{ + size_t gap_size = keys->size - keys->nr; + + BUG_ON(pos >= keys->gap && pos < keys->gap + gap_size); + + if (pos >= keys->gap) + pos -= gap_size; + return pos; +} + static inline size_t idx_to_pos(struct journal_keys *keys, size_t idx) { size_t gap_size = keys->size - keys->nr; @@ -61,7 +72,7 @@ static size_t bch2_journal_key_search(struct journal_keys *keys, } /* Returns first non-overwritten key >= search key: */ -struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *c, enum btree_id btree_id, +struct bkey_i *bch2_journal_keys_peek_max(struct bch_fs *c, enum btree_id btree_id, unsigned level, struct bpos pos, struct bpos end_pos, size_t *idx) { @@ -84,27 +95,92 @@ search: } } + struct bkey_i *ret = NULL; + rcu_read_lock(); /* for overwritten_ranges */ + while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) { if (__journal_key_cmp(btree_id, level, end_pos, k) < 0) - return NULL; + break; if (k->overwritten) { - (*idx)++; + if (k->overwritten_range) + *idx = rcu_dereference(k->overwritten_range)->end; + else + *idx += 1; continue; } - if (__journal_key_cmp(btree_id, level, pos, k) <= 0) - return k->k; + if (__journal_key_cmp(btree_id, level, pos, k) <= 0) { + ret = k->k; + break; + } (*idx)++; iters++; if (iters == 10) { *idx = 0; + rcu_read_unlock(); goto search; } } - return NULL; + rcu_read_unlock(); + return ret; +} + +struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *c, enum btree_id btree_id, + unsigned level, struct bpos pos, + struct bpos end_pos, size_t *idx) +{ + struct journal_keys *keys = &c->journal_keys; + unsigned iters = 0; + struct journal_key *k; + + BUG_ON(*idx > keys->nr); +search: + if (!*idx) + *idx = __bch2_journal_key_search(keys, btree_id, level, pos); + + while (*idx && + __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) { + (*idx)++; + iters++; + if (iters == 10) { + *idx = 0; + goto search; + } + } + + struct bkey_i *ret = NULL; + rcu_read_lock(); /* for overwritten_ranges */ + + while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) { + if (__journal_key_cmp(btree_id, level, end_pos, k) > 0) + break; + + if (k->overwritten) { + if (k->overwritten_range) + *idx = rcu_dereference(k->overwritten_range)->start - 1; + else + *idx -= 1; + continue; + } + + if (__journal_key_cmp(btree_id, level, pos, k) >= 0) { + ret = k->k; + break; + } + + --(*idx); + iters++; + if (iters == 10) { + *idx = 0; + goto search; + } + } + + rcu_read_unlock(); + return ret; } struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *c, enum btree_id btree_id, @@ -112,11 +188,12 @@ struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *c, enum btree_id btree { size_t idx = 0; - return bch2_journal_keys_peek_upto(c, btree_id, level, pos, pos, &idx); + return bch2_journal_keys_peek_max(c, btree_id, level, pos, pos, &idx); } static void journal_iter_verify(struct journal_iter *iter) { +#ifdef CONFIG_BCACHEFS_DEBUG struct journal_keys *keys = iter->keys; size_t gap_size = keys->size - keys->nr; @@ -126,10 +203,10 @@ static void journal_iter_verify(struct journal_iter *iter) if (iter->idx < keys->size) { struct journal_key *k = keys->data + iter->idx; - int cmp = cmp_int(k->btree_id, iter->btree_id) ?: - cmp_int(k->level, iter->level); - BUG_ON(cmp < 0); + int cmp = __journal_key_btree_cmp(iter->btree_id, iter->level, k); + BUG_ON(cmp > 0); } +#endif } static void journal_iters_fix(struct bch_fs *c) @@ -182,7 +259,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id, * Ensure these keys are done last by journal replay, to unblock * journal reclaim: */ - .journal_seq = U32_MAX, + .journal_seq = U64_MAX, }; struct journal_keys *keys = &c->journal_keys; size_t idx = bch2_journal_key_search(keys, id, level, k->k.p); @@ -290,6 +367,68 @@ bool bch2_key_deleted_in_journal(struct btree_trans *trans, enum btree_id btree, bkey_deleted(&keys->data[idx].k->k)); } +static void __bch2_journal_key_overwritten(struct journal_keys *keys, size_t pos) +{ + struct journal_key *k = keys->data + pos; + size_t idx = pos_to_idx(keys, pos); + + k->overwritten = true; + + struct journal_key *prev = idx > 0 ? keys->data + idx_to_pos(keys, idx - 1) : NULL; + struct journal_key *next = idx + 1 < keys->nr ? keys->data + idx_to_pos(keys, idx + 1) : NULL; + + bool prev_overwritten = prev && prev->overwritten; + bool next_overwritten = next && next->overwritten; + + struct journal_key_range_overwritten *prev_range = + prev_overwritten ? prev->overwritten_range : NULL; + struct journal_key_range_overwritten *next_range = + next_overwritten ? next->overwritten_range : NULL; + + BUG_ON(prev_range && prev_range->end != idx); + BUG_ON(next_range && next_range->start != idx + 1); + + if (prev_range && next_range) { + prev_range->end = next_range->end; + + keys->data[pos].overwritten_range = prev_range; + for (size_t i = next_range->start; i < next_range->end; i++) { + struct journal_key *ip = keys->data + idx_to_pos(keys, i); + BUG_ON(ip->overwritten_range != next_range); + ip->overwritten_range = prev_range; + } + + kfree_rcu_mightsleep(next_range); + } else if (prev_range) { + prev_range->end++; + k->overwritten_range = prev_range; + if (next_overwritten) { + prev_range->end++; + next->overwritten_range = prev_range; + } + } else if (next_range) { + next_range->start--; + k->overwritten_range = next_range; + if (prev_overwritten) { + next_range->start--; + prev->overwritten_range = next_range; + } + } else if (prev_overwritten || next_overwritten) { + struct journal_key_range_overwritten *r = kmalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return; + + r->start = idx - (size_t) prev_overwritten; + r->end = idx + 1 + (size_t) next_overwritten; + + rcu_assign_pointer(k->overwritten_range, r); + if (prev_overwritten) + prev->overwritten_range = r; + if (next_overwritten) + next->overwritten_range = r; + } +} + void bch2_journal_key_overwritten(struct bch_fs *c, enum btree_id btree, unsigned level, struct bpos pos) { @@ -299,8 +438,12 @@ void bch2_journal_key_overwritten(struct bch_fs *c, enum btree_id btree, if (idx < keys->size && keys->data[idx].btree_id == btree && keys->data[idx].level == level && - bpos_eq(keys->data[idx].k->k.p, pos)) - keys->data[idx].overwritten = true; + bpos_eq(keys->data[idx].k->k.p, pos) && + !keys->data[idx].overwritten) { + mutex_lock(&keys->overwrite_lock); + __bch2_journal_key_overwritten(keys, idx); + mutex_unlock(&keys->overwrite_lock); + } } static void bch2_journal_iter_advance(struct journal_iter *iter) @@ -314,24 +457,32 @@ static void bch2_journal_iter_advance(struct journal_iter *iter) static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter) { + struct bkey_s_c ret = bkey_s_c_null; + journal_iter_verify(iter); + rcu_read_lock(); while (iter->idx < iter->keys->size) { struct journal_key *k = iter->keys->data + iter->idx; - int cmp = cmp_int(k->btree_id, iter->btree_id) ?: - cmp_int(k->level, iter->level); - if (cmp > 0) + int cmp = __journal_key_btree_cmp(iter->btree_id, iter->level, k); + if (cmp < 0) break; BUG_ON(cmp); - if (!k->overwritten) - return bkey_i_to_s_c(k->k); + if (!k->overwritten) { + ret = bkey_i_to_s_c(k->k); + break; + } - bch2_journal_iter_advance(iter); + if (k->overwritten_range) + iter->idx = idx_to_pos(iter->keys, rcu_dereference(k->overwritten_range)->end); + else + bch2_journal_iter_advance(iter); } + rcu_read_unlock(); - return bkey_s_c_null; + return ret; } static void bch2_journal_iter_exit(struct journal_iter *iter) @@ -382,6 +533,7 @@ static void btree_and_journal_iter_prefetch(struct btree_and_journal_iter *_iter : (level > 1 ? 1 : 16); iter.prefetch = false; + iter.fail_if_too_many_whiteouts = true; bch2_bkey_buf_init(&tmp); while (nr--) { @@ -400,6 +552,7 @@ static void btree_and_journal_iter_prefetch(struct btree_and_journal_iter *_iter struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *iter) { struct bkey_s_c btree_k, journal_k = bkey_s_c_null, ret; + size_t iters = 0; if (iter->prefetch && iter->journal.level) btree_and_journal_iter_prefetch(iter); @@ -407,6 +560,11 @@ again: if (iter->at_end) return bkey_s_c_null; + iters++; + + if (iters > 20 && iter->fail_if_too_many_whiteouts) + return bkey_s_c_null; + while ((btree_k = bch2_journal_iter_peek_btree(iter)).k && bpos_lt(btree_k.k->p, iter->pos)) bch2_journal_iter_advance_btree(iter); @@ -481,16 +639,6 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans, /* sort and dedup all keys in the journal: */ -void bch2_journal_entries_free(struct bch_fs *c) -{ - struct journal_replay **i; - struct genradix_iter iter; - - genradix_for_each(&c->journal_entries, iter, i) - kvfree(*i); - genradix_free(&c->journal_entries); -} - /* * When keys compare equal, oldest compares first: */ @@ -515,15 +663,26 @@ void bch2_journal_keys_put(struct bch_fs *c) move_gap(keys, keys->nr); - darray_for_each(*keys, i) + darray_for_each(*keys, i) { + if (i->overwritten_range && + (i == &darray_last(*keys) || + i->overwritten_range != i[1].overwritten_range)) + kfree(i->overwritten_range); + if (i->allocated) kfree(i->k); + } kvfree(keys->data); keys->data = NULL; keys->nr = keys->gap = keys->size = 0; - bch2_journal_entries_free(c); + struct journal_replay **i; + struct genradix_iter iter; + + genradix_for_each(&c->journal_entries, iter, i) + kvfree(*i); + genradix_free(&c->journal_entries); } static void __journal_keys_sort(struct journal_keys *keys) @@ -628,8 +787,20 @@ void bch2_journal_keys_dump(struct bch_fs *c) darray_for_each(*keys, i) { printbuf_reset(&buf); + prt_printf(&buf, "btree="); + bch2_btree_id_to_text(&buf, i->btree_id); + prt_printf(&buf, " l=%u ", i->level); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(i->k)); - pr_err("%s l=%u %s", bch2_btree_id_str(i->btree_id), i->level, buf.buf); + pr_err("%s", buf.buf); } printbuf_exit(&buf); } + +void bch2_fs_journal_keys_init(struct bch_fs *c) +{ + struct journal_keys *keys = &c->journal_keys; + + atomic_set(&keys->ref, 1); + keys->initial_ref_held = true; + mutex_init(&keys->overwrite_lock); +} diff --git a/fs/bcachefs/btree_journal_iter.h b/fs/bcachefs/btree_journal_iter.h index 1653de9d609b..2a3082919b8d 100644 --- a/fs/bcachefs/btree_journal_iter.h +++ b/fs/bcachefs/btree_journal_iter.h @@ -26,16 +26,24 @@ struct btree_and_journal_iter { struct bpos pos; bool at_end; bool prefetch; + bool fail_if_too_many_whiteouts; }; +static inline int __journal_key_btree_cmp(enum btree_id l_btree_id, + unsigned l_level, + const struct journal_key *r) +{ + return -cmp_int(l_level, r->level) ?: + cmp_int(l_btree_id, r->btree_id); +} + static inline int __journal_key_cmp(enum btree_id l_btree_id, unsigned l_level, struct bpos l_pos, const struct journal_key *r) { - return (cmp_int(l_btree_id, r->btree_id) ?: - cmp_int(l_level, r->level) ?: - bpos_cmp(l_pos, r->k->k.p)); + return __journal_key_btree_cmp(l_btree_id, l_level, r) ?: + bpos_cmp(l_pos, r->k->k.p); } static inline int journal_key_cmp(const struct journal_key *l, const struct journal_key *r) @@ -43,7 +51,9 @@ static inline int journal_key_cmp(const struct journal_key *l, const struct jour return __journal_key_cmp(l->btree_id, l->level, l->k->k.p, r); } -struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *, enum btree_id, +struct bkey_i *bch2_journal_keys_peek_max(struct bch_fs *, enum btree_id, + unsigned, struct bpos, struct bpos, size_t *); +struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos, size_t *); struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *, enum btree_id, unsigned, struct bpos); @@ -79,8 +89,6 @@ static inline void bch2_journal_keys_put_initial(struct bch_fs *c) c->journal_keys.initial_ref_held = false; } -void bch2_journal_entries_free(struct bch_fs *); - int bch2_journal_keys_sort(struct bch_fs *); void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id, @@ -89,4 +97,6 @@ void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id, void bch2_journal_keys_dump(struct bch_fs *); +void bch2_fs_journal_keys_init(struct bch_fs *); + #endif /* _BCACHEFS_BTREE_JOURNAL_ITER_H */ diff --git a/fs/bcachefs/btree_journal_iter_types.h b/fs/bcachefs/btree_journal_iter_types.h new file mode 100644 index 000000000000..8b773823704f --- /dev/null +++ b/fs/bcachefs/btree_journal_iter_types.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_BTREE_JOURNAL_ITER_TYPES_H +#define _BCACHEFS_BTREE_JOURNAL_ITER_TYPES_H + +struct journal_key_range_overwritten { + size_t start, end; +}; + +struct journal_key { + u64 journal_seq; + u32 journal_offset; + enum btree_id btree_id:8; + unsigned level:8; + bool allocated; + bool overwritten; + struct journal_key_range_overwritten __rcu * + overwritten_range; + struct bkey_i *k; +}; + +struct journal_keys { + /* must match layout in darray_types.h */ + size_t nr, size; + struct journal_key *data; + /* + * Gap buffer: instead of all the empty space in the array being at the + * end of the buffer - from @nr to @size - the empty space is at @gap. + * This means that sequential insertions are O(n) instead of O(n^2). + */ + size_t gap; + atomic_t ref; + bool initial_ref_held; + struct mutex overwrite_lock; +}; + +#endif /* _BCACHEFS_BTREE_JOURNAL_ITER_TYPES_H */ diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 244610b1d0b5..3b62296c3100 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -197,7 +197,9 @@ out: return ck; } -static int btree_key_cache_create(struct btree_trans *trans, struct btree_path *path, +static int btree_key_cache_create(struct btree_trans *trans, + struct btree_path *path, + struct btree_path *ck_path, struct bkey_s_c k) { struct bch_fs *c = trans->c; @@ -217,7 +219,7 @@ static int btree_key_cache_create(struct btree_trans *trans, struct btree_path * key_u64s = min(256U, (key_u64s * 3) / 2); key_u64s = roundup_pow_of_two(key_u64s); - struct bkey_cached *ck = bkey_cached_alloc(trans, path, key_u64s); + struct bkey_cached *ck = bkey_cached_alloc(trans, ck_path, key_u64s); int ret = PTR_ERR_OR_ZERO(ck); if (ret) return ret; @@ -226,19 +228,19 @@ static int btree_key_cache_create(struct btree_trans *trans, struct btree_path * ck = bkey_cached_reuse(bc); if (unlikely(!ck)) { bch_err(c, "error allocating memory for key cache item, btree %s", - bch2_btree_id_str(path->btree_id)); + bch2_btree_id_str(ck_path->btree_id)); return -BCH_ERR_ENOMEM_btree_key_cache_create; } } ck->c.level = 0; - ck->c.btree_id = path->btree_id; - ck->key.btree_id = path->btree_id; - ck->key.pos = path->pos; + ck->c.btree_id = ck_path->btree_id; + ck->key.btree_id = ck_path->btree_id; + ck->key.pos = ck_path->pos; ck->flags = 1U << BKEY_CACHED_ACCESSED; if (unlikely(key_u64s > ck->u64s)) { - mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); + mark_btree_node_locked_noreset(ck_path, 0, BTREE_NODE_UNLOCKED); struct bkey_i *new_k = allocate_dropping_locks(trans, ret, kmalloc(key_u64s * sizeof(u64), _gfp)); @@ -258,22 +260,29 @@ static int btree_key_cache_create(struct btree_trans *trans, struct btree_path * bkey_reassemble(ck->k, k); + ret = bch2_btree_node_lock_write(trans, path, &path_l(path)->b->c); + if (unlikely(ret)) + goto err; + ret = rhashtable_lookup_insert_fast(&bc->table, &ck->hash, bch2_btree_key_cache_params); + + bch2_btree_node_unlock_write(trans, path, path_l(path)->b); + if (unlikely(ret)) /* raced with another fill? */ goto err; atomic_long_inc(&bc->nr_keys); six_unlock_write(&ck->c.lock); - enum six_lock_type lock_want = __btree_lock_want(path, 0); + enum six_lock_type lock_want = __btree_lock_want(ck_path, 0); if (lock_want == SIX_LOCK_read) six_lock_downgrade(&ck->c.lock); - btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want); - path->uptodate = BTREE_ITER_UPTODATE; + btree_path_cached_set(trans, ck_path, ck, (enum btree_node_locked_type) lock_want); + ck_path->uptodate = BTREE_ITER_UPTODATE; return 0; err: bkey_cached_free(bc, ck); - mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); + mark_btree_node_locked_noreset(ck_path, 0, BTREE_NODE_UNLOCKED); return ret; } @@ -282,10 +291,8 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, struct btree_path *ck_path, unsigned flags) { - if (flags & BTREE_ITER_cached_nofill) { - ck_path->uptodate = BTREE_ITER_UPTODATE; + if (flags & BTREE_ITER_cached_nofill) return 0; - } struct bch_fs *c = trans->c; struct btree_iter iter; @@ -293,6 +300,7 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, int ret; bch2_trans_iter_init(trans, &iter, ck_path->btree_id, ck_path->pos, + BTREE_ITER_intent| BTREE_ITER_key_cache_fill| BTREE_ITER_cached_nofill); iter.flags &= ~BTREE_ITER_with_journal; @@ -306,9 +314,19 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, if (unlikely(ret)) goto out; - ret = btree_key_cache_create(trans, ck_path, k); + ret = btree_key_cache_create(trans, btree_iter_path(trans, &iter), ck_path, k); if (ret) goto err; + + if (trace_key_cache_fill_enabled()) { + struct printbuf buf = PRINTBUF; + + bch2_bpos_to_text(&buf, ck_path->pos); + prt_char(&buf, ' '); + bch2_bkey_val_to_text(&buf, trans->c, k); + trace_key_cache_fill(trans, buf.buf); + printbuf_exit(&buf); + } out: /* We're not likely to need this iterator again: */ bch2_set_btree_iter_dontneed(&iter); @@ -424,8 +442,15 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans, !test_bit(JOURNAL_space_low, &c->journal.flags)) commit_flags |= BCH_TRANS_COMMIT_no_journal_res; - ret = bch2_btree_iter_traverse(&b_iter) ?: - bch2_trans_update(trans, &b_iter, ck->k, + struct bkey_s_c btree_k = bch2_btree_iter_peek_slot(&b_iter); + ret = bkey_err(btree_k); + if (ret) + goto err; + + /* * Check that we're not violating cache coherency rules: */ + BUG_ON(bkey_deleted(btree_k.k)); + + ret = bch2_trans_update(trans, &b_iter, ck->k, BTREE_UPDATE_key_cache_reclaim| BTREE_UPDATE_internal_snapshot_node| BTREE_TRIGGER_norun) ?: @@ -433,7 +458,7 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans, BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc| commit_flags); - +err: bch2_fs_fatal_err_on(ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart) && !bch2_err_matches(ret, BCH_ERR_journal_reclaim_would_deadlock) && @@ -586,8 +611,18 @@ void bch2_btree_key_cache_drop(struct btree_trans *trans, bkey_cached_free(bc, ck); mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED); - btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); - path->should_be_locked = false; + + struct btree_path *path2; + unsigned i; + trans_for_each_path(trans, path2, i) + if (path2->l[0].b == (void *) ck) { + __bch2_btree_path_unlock(trans, path2); + path2->l[0].b = ERR_PTR(-BCH_ERR_no_btree_node_drop); + path2->should_be_locked = false; + btree_path_set_dirty(path2, BTREE_ITER_NEED_TRAVERSE); + } + + bch2_trans_verify_locks(trans); } static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c index efe2a007b482..10b805a60f52 100644 --- a/fs/bcachefs/btree_locking.c +++ b/fs/bcachefs/btree_locking.c @@ -109,6 +109,12 @@ static noinline void lock_graph_pop_all(struct lock_graph *g) lock_graph_up(g); } +static noinline void lock_graph_pop_from(struct lock_graph *g, struct trans_waiting_for_lock *i) +{ + while (g->g + g->nr > i) + lock_graph_up(g); +} + static void __lock_graph_down(struct lock_graph *g, struct btree_trans *trans) { g->g[g->nr++] = (struct trans_waiting_for_lock) { @@ -124,15 +130,20 @@ static void lock_graph_down(struct lock_graph *g, struct btree_trans *trans) __lock_graph_down(g, trans); } -static bool lock_graph_remove_non_waiters(struct lock_graph *g) +static bool lock_graph_remove_non_waiters(struct lock_graph *g, + struct trans_waiting_for_lock *from) { struct trans_waiting_for_lock *i; - for (i = g->g + 1; i < g->g + g->nr; i++) + if (from->trans->locking != from->node_want) { + lock_graph_pop_from(g, from); + return true; + } + + for (i = from + 1; i < g->g + g->nr; i++) if (i->trans->locking != i->node_want || i->trans->locking_wait.start_time != i[-1].lock_start_time) { - while (g->g + g->nr > i) - lock_graph_up(g); + lock_graph_pop_from(g, i); return true; } @@ -179,13 +190,14 @@ static int btree_trans_abort_preference(struct btree_trans *trans) return 3; } -static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle) +static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle, + struct trans_waiting_for_lock *from) { struct trans_waiting_for_lock *i, *abort = NULL; unsigned best = 0, pref; int ret; - if (lock_graph_remove_non_waiters(g)) + if (lock_graph_remove_non_waiters(g, from)) return 0; /* Only checking, for debugfs: */ @@ -195,7 +207,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle) goto out; } - for (i = g->g; i < g->g + g->nr; i++) { + for (i = from; i < g->g + g->nr; i++) { pref = btree_trans_abort_preference(i->trans); if (pref > best) { abort = i; @@ -229,8 +241,9 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle) ret = abort_lock(g, abort); out: if (ret) - while (g->nr) - lock_graph_up(g); + lock_graph_pop_all(g); + else + lock_graph_pop_from(g, abort); return ret; } @@ -243,7 +256,7 @@ static int lock_graph_descend(struct lock_graph *g, struct btree_trans *trans, for (i = g->g; i < g->g + g->nr; i++) if (i->trans == trans) { closure_put(&trans->ref); - return break_cycle(g, cycle); + return break_cycle(g, cycle, i); } if (g->nr == ARRAY_SIZE(g->g)) { @@ -252,8 +265,7 @@ static int lock_graph_descend(struct lock_graph *g, struct btree_trans *trans, if (orig_trans->lock_may_not_fail) return 0; - while (g->nr) - lock_graph_up(g); + lock_graph_pop_all(g); if (cycle) return 0; @@ -281,7 +293,7 @@ int bch2_check_for_deadlock(struct btree_trans *trans, struct printbuf *cycle) g.nr = 0; - if (trans->lock_must_abort) { + if (trans->lock_must_abort && !trans->lock_may_not_fail) { if (cycle) return -1; @@ -336,7 +348,7 @@ next: * structures - which means it can't be blocked * waiting on a lock: */ - if (!lock_graph_remove_non_waiters(&g)) { + if (!lock_graph_remove_non_waiters(&g, g.g)) { /* * If lock_graph_remove_non_waiters() * didn't do anything, it must be @@ -512,7 +524,6 @@ bool bch2_btree_node_upgrade(struct btree_trans *trans, struct btree_path *path, unsigned level) { struct btree *b = path->l[level].b; - struct six_lock_count count = bch2_btree_node_lock_counts(trans, path, &b->c, level); if (!is_btree_node(path, level)) return false; @@ -536,24 +547,11 @@ bool bch2_btree_node_upgrade(struct btree_trans *trans, if (race_fault()) return false; - if (btree_node_locked(path, level)) { - bool ret; - - six_lock_readers_add(&b->c.lock, -count.n[SIX_LOCK_read]); - ret = six_lock_tryupgrade(&b->c.lock); - six_lock_readers_add(&b->c.lock, count.n[SIX_LOCK_read]); - - if (ret) - goto success; - } else { - if (six_relock_type(&b->c.lock, SIX_LOCK_intent, path->l[level].lock_seq)) - goto success; - } + if (btree_node_locked(path, level) + ? six_lock_tryupgrade(&b->c.lock) + : six_relock_type(&b->c.lock, SIX_LOCK_intent, path->l[level].lock_seq)) + goto success; - /* - * Do we already have an intent lock via another path? If so, just bump - * lock count: - */ if (btree_node_lock_seq_matches(path, b, level) && btree_node_lock_increment(trans, &b->c, level, BTREE_NODE_INTENT_LOCKED)) { btree_node_unlock(trans, path, level); @@ -782,7 +780,7 @@ static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace) return bch2_trans_relock_fail(trans, path, &f, trace); } - trans_set_locked(trans); + trans_set_locked(trans, true); out: bch2_trans_verify_locks(trans); return 0; @@ -818,6 +816,17 @@ void bch2_trans_unlock_long(struct btree_trans *trans) bch2_trans_srcu_unlock(trans); } +void bch2_trans_unlock_write(struct btree_trans *trans) +{ + struct btree_path *path; + unsigned i; + + trans_for_each_path(trans, path, i) + for (unsigned l = 0; l < BTREE_MAX_DEPTH; l++) + if (btree_node_write_locked(path, l)) + bch2_btree_node_unlock_write(trans, path, path->l[l].b); +} + int __bch2_trans_mutex_lock(struct btree_trans *trans, struct mutex *lock) { @@ -856,6 +865,9 @@ void bch2_btree_path_verify_locks(struct btree_path *path) (want == BTREE_NODE_UNLOCKED || have != BTREE_NODE_WRITE_LOCKED) && want != have); + + BUG_ON(btree_node_locked(path, l) && + path->l[l].lock_seq != six_lock_seq(&path->l[l].b->c.lock)); } } diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h index 7c07f9fa9add..b54ef48eb8cc 100644 --- a/fs/bcachefs/btree_locking.h +++ b/fs/bcachefs/btree_locking.h @@ -16,6 +16,7 @@ void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags); void bch2_trans_unlock_noassert(struct btree_trans *); +void bch2_trans_unlock_write(struct btree_trans *); static inline bool is_btree_node(struct btree_path *path, unsigned l) { @@ -75,13 +76,6 @@ static inline void mark_btree_node_locked_noreset(struct btree_path *path, path->nodes_locked |= (type + 1) << (level << 1); } -static inline void mark_btree_node_unlocked(struct btree_path *path, - unsigned level) -{ - EBUG_ON(btree_node_write_locked(path, level)); - mark_btree_node_locked_noreset(path, level, BTREE_NODE_UNLOCKED); -} - static inline void mark_btree_node_locked(struct btree_trans *trans, struct btree_path *path, unsigned level, @@ -124,19 +118,25 @@ static void btree_trans_lock_hold_time_update(struct btree_trans *trans, /* unlock: */ +void bch2_btree_node_unlock_write(struct btree_trans *, + struct btree_path *, struct btree *); + static inline void btree_node_unlock(struct btree_trans *trans, struct btree_path *path, unsigned level) { int lock_type = btree_node_locked_type(path, level); EBUG_ON(level >= BTREE_MAX_DEPTH); - EBUG_ON(lock_type == BTREE_NODE_WRITE_LOCKED); if (lock_type != BTREE_NODE_UNLOCKED) { + if (unlikely(lock_type == BTREE_NODE_WRITE_LOCKED)) { + bch2_btree_node_unlock_write(trans, path, path->l[level].b); + lock_type = BTREE_NODE_INTENT_LOCKED; + } six_unlock_type(&path->l[level].b->c.lock, lock_type); btree_trans_lock_hold_time_update(trans, path, level); + mark_btree_node_locked_noreset(path, level, BTREE_NODE_UNLOCKED); } - mark_btree_node_unlocked(path, level); } static inline int btree_path_lowest_level_locked(struct btree_path *path) @@ -163,35 +163,39 @@ static inline void __bch2_btree_path_unlock(struct btree_trans *trans, * succeed: */ static inline void +__bch2_btree_node_unlock_write(struct btree_trans *trans, struct btree *b) +{ + if (!b->c.lock.write_lock_recurse) { + struct btree_path *linked; + unsigned i; + + trans_for_each_path_with_node(trans, b, linked, i) + linked->l[b->c.level].lock_seq++; + } + + six_unlock_write(&b->c.lock); +} + +static inline void bch2_btree_node_unlock_write_inlined(struct btree_trans *trans, struct btree_path *path, struct btree *b) { - struct btree_path *linked; - unsigned i; - EBUG_ON(path->l[b->c.level].b != b); EBUG_ON(path->l[b->c.level].lock_seq != six_lock_seq(&b->c.lock)); EBUG_ON(btree_node_locked_type(path, b->c.level) != SIX_LOCK_write); mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); - - trans_for_each_path_with_node(trans, b, linked, i) - linked->l[b->c.level].lock_seq++; - - six_unlock_write(&b->c.lock); + __bch2_btree_node_unlock_write(trans, b); } -void bch2_btree_node_unlock_write(struct btree_trans *, - struct btree_path *, struct btree *); - int bch2_six_check_for_deadlock(struct six_lock *lock, void *p); /* lock: */ -static inline void trans_set_locked(struct btree_trans *trans) +static inline void trans_set_locked(struct btree_trans *trans, bool try) { if (!trans->locked) { - lock_acquire_exclusive(&trans->dep_map, 0, 0, NULL, _THIS_IP_); + lock_acquire_exclusive(&trans->dep_map, 0, try, NULL, _THIS_IP_); trans->locked = true; trans->last_unlock_ip = 0; @@ -282,7 +286,7 @@ static inline int btree_node_lock(struct btree_trans *trans, int ret = 0; EBUG_ON(level >= BTREE_MAX_DEPTH); - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (likely(six_trylock_type(&b->lock, type)) || btree_node_lock_increment(trans, b, level, (enum btree_node_locked_type) type) || diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 30131c3bdd97..a7f06deee13c 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -12,6 +12,7 @@ #include "recovery_passes.h" #include <linux/kthread.h> +#include <linux/min_heap.h> #include <linux/sort.h> struct find_btree_nodes_worker { @@ -22,17 +23,15 @@ struct find_btree_nodes_worker { static void found_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struct found_btree_node *n) { - prt_printf(out, "%s l=%u seq=%u journal_seq=%llu cookie=%llx ", - bch2_btree_id_str(n->btree_id), n->level, n->seq, - n->journal_seq, n->cookie); + bch2_btree_id_level_to_text(out, n->btree_id, n->level); + prt_printf(out, " seq=%u journal_seq=%llu cookie=%llx ", + n->seq, n->journal_seq, n->cookie); bch2_bpos_to_text(out, n->min_key); prt_str(out, "-"); bch2_bpos_to_text(out, n->max_key); if (n->range_updated) prt_str(out, " range updated"); - if (n->overwritten) - prt_str(out, " overwritten"); for (unsigned i = 0; i < n->nr_ptrs; i++) { prt_char(out, ' '); @@ -140,6 +139,24 @@ static int found_btree_node_cmp_pos(const void *_l, const void *_r) -found_btree_node_cmp_time(l, r); } +static inline bool found_btree_node_cmp_pos_less(const void *l, const void *r, void *arg) +{ + return found_btree_node_cmp_pos(l, r) < 0; +} + +static inline void found_btree_node_swap(void *_l, void *_r, void *arg) +{ + struct found_btree_node *l = _l; + struct found_btree_node *r = _r; + + swap(*l, *r); +} + +static const struct min_heap_callbacks found_btree_node_heap_cbs = { + .less = found_btree_node_cmp_pos_less, + .swp = found_btree_node_swap, +}; + static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, struct bio *bio, struct btree_node *bn, u64 offset) { @@ -159,6 +176,9 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, return; if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) { + if (!c->chacha20) + return; + struct nonce nonce = btree_nonce(&bn->keys, 0); unsigned bytes = (void *) &bn->keys - (void *) &bn->flags; @@ -292,55 +312,48 @@ err: return f->ret ?: ret; } -static void bubble_up(struct found_btree_node *n, struct found_btree_node *end) +static bool nodes_overlap(const struct found_btree_node *l, + const struct found_btree_node *r) { - while (n + 1 < end && - found_btree_node_cmp_pos(n, n + 1) > 0) { - swap(n[0], n[1]); - n++; - } + return (l->btree_id == r->btree_id && + l->level == r->level && + bpos_gt(l->max_key, r->min_key)); } static int handle_overwrites(struct bch_fs *c, - struct found_btree_node *start, - struct found_btree_node *end) + struct found_btree_node *l, + found_btree_nodes *nodes_heap) { - struct found_btree_node *n; -again: - for (n = start + 1; - n < end && - n->btree_id == start->btree_id && - n->level == start->level && - bpos_lt(n->min_key, start->max_key); - n++) { - int cmp = found_btree_node_cmp_time(start, n); + struct found_btree_node *r; + + while ((r = min_heap_peek(nodes_heap)) && + nodes_overlap(l, r)) { + int cmp = found_btree_node_cmp_time(l, r); if (cmp > 0) { - if (bpos_cmp(start->max_key, n->max_key) >= 0) - n->overwritten = true; + if (bpos_cmp(l->max_key, r->max_key) >= 0) + min_heap_pop(nodes_heap, &found_btree_node_heap_cbs, NULL); else { - n->range_updated = true; - n->min_key = bpos_successor(start->max_key); - n->range_updated = true; - bubble_up(n, end); - goto again; + r->range_updated = true; + r->min_key = bpos_successor(l->max_key); + r->range_updated = true; + min_heap_sift_down(nodes_heap, 0, &found_btree_node_heap_cbs, NULL); } } else if (cmp < 0) { - BUG_ON(bpos_cmp(n->min_key, start->min_key) <= 0); + BUG_ON(bpos_eq(l->min_key, r->min_key)); - start->max_key = bpos_predecessor(n->min_key); - start->range_updated = true; - } else if (n->level) { - n->overwritten = true; + l->max_key = bpos_predecessor(r->min_key); + l->range_updated = true; + } else if (r->level) { + min_heap_pop(nodes_heap, &found_btree_node_heap_cbs, NULL); } else { - if (bpos_cmp(start->max_key, n->max_key) >= 0) - n->overwritten = true; + if (bpos_cmp(l->max_key, r->max_key) >= 0) + min_heap_pop(nodes_heap, &found_btree_node_heap_cbs, NULL); else { - n->range_updated = true; - n->min_key = bpos_successor(start->max_key); - n->range_updated = true; - bubble_up(n, end); - goto again; + r->range_updated = true; + r->min_key = bpos_successor(l->max_key); + r->range_updated = true; + min_heap_sift_down(nodes_heap, 0, &found_btree_node_heap_cbs, NULL); } } } @@ -352,6 +365,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c) { struct find_btree_nodes *f = &c->found_btree_nodes; struct printbuf buf = PRINTBUF; + found_btree_nodes nodes_heap = {}; size_t dst; int ret = 0; @@ -406,29 +420,57 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c) bch2_print_string_as_lines(KERN_INFO, buf.buf); } - dst = 0; - darray_for_each(f->nodes, i) { - if (i->overwritten) - continue; + swap(nodes_heap, f->nodes); + + { + /* darray must have same layout as a heap */ + min_heap_char real_heap; + BUILD_BUG_ON(sizeof(nodes_heap.nr) != sizeof(real_heap.nr)); + BUILD_BUG_ON(sizeof(nodes_heap.size) != sizeof(real_heap.size)); + BUILD_BUG_ON(offsetof(found_btree_nodes, nr) != offsetof(min_heap_char, nr)); + BUILD_BUG_ON(offsetof(found_btree_nodes, size) != offsetof(min_heap_char, size)); + } + + min_heapify_all(&nodes_heap, &found_btree_node_heap_cbs, NULL); - ret = handle_overwrites(c, i, &darray_top(f->nodes)); + if (nodes_heap.nr) { + ret = darray_push(&f->nodes, *min_heap_peek(&nodes_heap)); if (ret) goto err; - BUG_ON(i->overwritten); - f->nodes.data[dst++] = *i; + min_heap_pop(&nodes_heap, &found_btree_node_heap_cbs, NULL); } - f->nodes.nr = dst; - if (c->opts.verbose) { + while (true) { + ret = handle_overwrites(c, &darray_last(f->nodes), &nodes_heap); + if (ret) + goto err; + + if (!nodes_heap.nr) + break; + + ret = darray_push(&f->nodes, *min_heap_peek(&nodes_heap)); + if (ret) + goto err; + + min_heap_pop(&nodes_heap, &found_btree_node_heap_cbs, NULL); + } + + for (struct found_btree_node *n = f->nodes.data; n < &darray_last(f->nodes); n++) + BUG_ON(nodes_overlap(n, n + 1)); + + if (0 && c->opts.verbose) { printbuf_reset(&buf); prt_printf(&buf, "%s: nodes found after overwrites:\n", __func__); found_btree_nodes_to_text(&buf, c, f->nodes); bch2_print_string_as_lines(KERN_INFO, buf.buf); + } else { + bch_info(c, "btree node scan found %zu nodes after overwrites", f->nodes.nr); } eytzinger0_sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL); err: + darray_exit(&nodes_heap); printbuf_exit(&buf); return ret; } @@ -499,7 +541,9 @@ int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, if (c->opts.verbose) { struct printbuf buf = PRINTBUF; - prt_printf(&buf, "recovering %s l=%u ", bch2_btree_id_str(btree), level); + prt_str(&buf, "recovery "); + bch2_btree_id_level_to_text(&buf, btree, level); + prt_str(&buf, " "); bch2_bpos_to_text(&buf, node_min); prt_str(&buf, " - "); bch2_bpos_to_text(&buf, node_max); @@ -533,7 +577,12 @@ int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, bch_verbose(c, "%s(): recovering %s", __func__, buf.buf); printbuf_exit(&buf); - BUG_ON(bch2_bkey_validate(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0)); + BUG_ON(bch2_bkey_validate(c, bkey_i_to_s_c(&tmp.k), + (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = level + 1, + .btree = btree, + })); ret = bch2_journal_key_insert(c, btree, level + 1, &tmp.k); if (ret) diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h index b6c36c45d0be..2811b6857c97 100644 --- a/fs/bcachefs/btree_node_scan_types.h +++ b/fs/bcachefs/btree_node_scan_types.h @@ -6,7 +6,6 @@ struct found_btree_node { bool range_updated:1; - bool overwritten:1; u8 btree_id; u8 level; unsigned sectors_written; diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 9bf471fa4361..6b79b672e0b1 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -133,7 +133,7 @@ static inline int bch2_trans_lock_write(struct btree_trans *trans) return 0; } -static inline void bch2_trans_unlock_write(struct btree_trans *trans) +static inline void bch2_trans_unlock_updates_write(struct btree_trans *trans) { if (likely(trans->write_locked)) { trans_for_each_update(trans, i) @@ -249,7 +249,7 @@ static int __btree_node_flush(struct journal *j, struct journal_entry_pin *pin, new |= 1 << BTREE_NODE_need_write; } while (!try_cmpxchg(&b->flags, &old, new)); - btree_node_write_if_need(c, b, SIX_LOCK_read); + btree_node_write_if_need(trans, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); bch2_trans_put(trans); @@ -384,7 +384,7 @@ btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags, struct bkey_i *new_k; int ret; - bch2_trans_unlock_write(trans); + bch2_trans_unlock_updates_write(trans); bch2_trans_unlock(trans); new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL); @@ -479,8 +479,7 @@ static int run_one_mem_trigger(struct btree_trans *trans, old, flags); } -static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_entry *i, - bool overwrite) +static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_entry *i) { verify_update_old_key(trans, i); @@ -507,10 +506,10 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ return bch2_key_trigger(trans, i->btree_id, i->level, old, bkey_i_to_s(i->k), BTREE_TRIGGER_insert| BTREE_TRIGGER_overwrite|flags) ?: 1; - } else if (overwrite && !i->overwrite_trigger_run) { + } else if (!i->overwrite_trigger_run) { i->overwrite_trigger_run = true; return bch2_key_trigger_old(trans, i->btree_id, i->level, old, flags) ?: 1; - } else if (!overwrite && !i->insert_trigger_run) { + } else if (!i->insert_trigger_run) { i->insert_trigger_run = true; return bch2_key_trigger_new(trans, i->btree_id, i->level, bkey_i_to_s(i->k), flags) ?: 1; } else { @@ -519,39 +518,45 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ } static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, - unsigned btree_id_start) + unsigned *btree_id_updates_start) { - for (int overwrite = 1; overwrite >= 0; --overwrite) { - bool trans_trigger_run; + bool trans_trigger_run; - /* - * Running triggers will append more updates to the list of updates as - * we're walking it: - */ - do { - trans_trigger_run = false; - - for (unsigned i = btree_id_start; - i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; - i++) { - if (trans->updates[i].btree_id != btree_id) - continue; + /* + * Running triggers will append more updates to the list of updates as + * we're walking it: + */ + do { + trans_trigger_run = false; - int ret = run_one_trans_trigger(trans, trans->updates + i, overwrite); - if (ret < 0) - return ret; - if (ret) - trans_trigger_run = true; + for (unsigned i = *btree_id_updates_start; + i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; + i++) { + if (trans->updates[i].btree_id < btree_id) { + *btree_id_updates_start = i; + continue; } - } while (trans_trigger_run); - } + + int ret = run_one_trans_trigger(trans, trans->updates + i); + if (ret < 0) + return ret; + if (ret) + trans_trigger_run = true; + } + } while (trans_trigger_run); + + trans_for_each_update(trans, i) + BUG_ON(!(i->flags & BTREE_TRIGGER_norun) && + i->btree_id == btree_id && + btree_node_type_has_trans_triggers(i->bkey_type) && + (!i->insert_trigger_run || !i->overwrite_trigger_run)); return 0; } static int bch2_trans_commit_run_triggers(struct btree_trans *trans) { - unsigned btree_id = 0, btree_id_start = 0; + unsigned btree_id = 0, btree_id_updates_start = 0; int ret = 0; /* @@ -565,27 +570,15 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans) if (btree_id == BTREE_ID_alloc) continue; - while (btree_id_start < trans->nr_updates && - trans->updates[btree_id_start].btree_id < btree_id) - btree_id_start++; - - ret = run_btree_triggers(trans, btree_id, btree_id_start); + ret = run_btree_triggers(trans, btree_id, &btree_id_updates_start); if (ret) return ret; } - for (unsigned idx = 0; idx < trans->nr_updates; idx++) { - struct btree_insert_entry *i = trans->updates + idx; - - if (i->btree_id > BTREE_ID_alloc) - break; - if (i->btree_id == BTREE_ID_alloc) { - ret = run_btree_triggers(trans, BTREE_ID_alloc, idx); - if (ret) - return ret; - break; - } - } + btree_id_updates_start = 0; + ret = run_btree_triggers(trans, BTREE_ID_alloc, &btree_id_updates_start); + if (ret) + return ret; #ifdef CONFIG_BCACHEFS_DEBUG trans_for_each_update(trans, i) @@ -609,14 +602,6 @@ static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans) return 0; } -static struct bversion journal_pos_to_bversion(struct journal_res *res, unsigned offset) -{ - return (struct bversion) { - .hi = res->seq >> 32, - .lo = (res->seq << 32) | (res->offset + offset), - }; -} - static inline int bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct btree_insert_entry **stopped_at, @@ -627,12 +612,11 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, unsigned u64s = 0; int ret = 0; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (race_fault()) { trace_and_count(c, trans_restart_fault_inject, trans, trace_ip); - return btree_trans_restart_nounlock(trans, BCH_ERR_transaction_restart_fault_inject); + return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject); } /* @@ -701,25 +685,14 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct jset_entry *entry = trans->journal_entries; percpu_down_read(&c->mark_lock); - for (entry = trans->journal_entries; entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); entry = vstruct_next(entry)) if (entry->type == BCH_JSET_ENTRY_write_buffer_keys && entry->start->k.type == KEY_TYPE_accounting) { - BUG_ON(!trans->journal_res.ref); - - struct bkey_i_accounting *a = bkey_i_to_accounting(entry->start); - - a->k.bversion = journal_pos_to_bversion(&trans->journal_res, - (u64 *) entry - (u64 *) trans->journal_entries); - BUG_ON(bversion_zero(a->k.bversion)); - - if (likely(!(flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { - ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal); - if (ret) - goto revert_fs_usage; - } + ret = bch2_accounting_trans_commit_hook(trans, bkey_i_to_accounting(entry->start), flags); + if (ret) + goto revert_fs_usage; } percpu_up_read(&c->mark_lock); @@ -739,33 +712,17 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, goto fatal_err; } - trans_for_each_update(trans, i) { - enum bch_validate_flags invalid_flags = 0; + struct bkey_validate_context validate_context = { .from = BKEY_VALIDATE_commit }; - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), - i->bkey_type, invalid_flags); - if (unlikely(ret)){ - bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", - trans->fn, (void *) i->ip_allocated); - goto fatal_err; - } - btree_insert_entry_checks(trans, i); - } + if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) + validate_context.flags = BCH_VALIDATE_write|BCH_VALIDATE_commit; for (struct jset_entry *i = trans->journal_entries; i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); i = vstruct_next(i)) { - enum bch_validate_flags invalid_flags = 0; - - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - ret = bch2_journal_entry_validate(c, NULL, i, bcachefs_metadata_version_current, - CPU_BIG_ENDIAN, invalid_flags); + CPU_BIG_ENDIAN, validate_context); if (unlikely(ret)) { bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", trans->fn); @@ -773,6 +730,19 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, } } + trans_for_each_update(trans, i) { + validate_context.level = i->level; + validate_context.btree = i->btree_id; + + ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), validate_context); + if (unlikely(ret)){ + bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", + trans->fn, (void *) i->ip_allocated); + goto fatal_err; + } + btree_insert_entry_checks(trans, i); + } + if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) { struct journal *j = &c->journal; struct jset_entry *entry; @@ -833,13 +803,9 @@ revert_fs_usage: entry2 != entry; entry2 = vstruct_next(entry2)) if (entry2->type == BCH_JSET_ENTRY_write_buffer_keys && - entry2->start->k.type == KEY_TYPE_accounting) { - struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start); - - bch2_accounting_neg(a); - bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); - bch2_accounting_neg(a); - } + entry2->start->k.type == KEY_TYPE_accounting) + bch2_accounting_trans_commit_revert(trans, + bkey_i_to_accounting(entry2->start), flags); percpu_up_read(&c->mark_lock); return ret; } @@ -902,7 +868,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags if (!ret && unlikely(trans->journal_replay_not_finished)) bch2_drop_overwrites_from_journal(trans); - bch2_trans_unlock_write(trans); + bch2_trans_unlock_updates_write(trans); if (!ret && trans->journal_pin) bch2_journal_pin_add(&c->journal, trans->journal_res.seq, @@ -994,24 +960,6 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, return ret; } -static noinline int -bch2_trans_commit_get_rw_cold(struct btree_trans *trans, unsigned flags) -{ - struct bch_fs *c = trans->c; - int ret; - - if (likely(!(flags & BCH_TRANS_COMMIT_lazy_rw)) || - test_bit(BCH_FS_started, &c->flags)) - return -BCH_ERR_erofs_trans_commit; - - ret = drop_locks_do(trans, bch2_fs_read_write_early(c)); - if (ret) - return ret; - - bch2_write_ref_get(c, BCH_WRITE_REF_trans); - return 0; -} - /* * This is for updates done in the early part of fsck - btree_gc - before we've * gone RW. we only add the new key to the list of keys for journal replay to @@ -1022,6 +970,8 @@ do_bch2_trans_commit_to_journal_replay(struct btree_trans *trans) { struct bch_fs *c = trans->c; + BUG_ON(current != c->recovery_task); + trans_for_each_update(trans, i) { int ret = bch2_journal_key_insert(c, i->btree_id, i->level, i->k); if (ret) @@ -1047,8 +997,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) struct bch_fs *c = trans->c; int ret = 0; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (!trans->nr_updates && !trans->journal_entries_u64s) @@ -1058,16 +1007,13 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) if (ret) goto out_reset; - if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { - ret = do_bch2_trans_commit_to_journal_replay(trans); - goto out_reset; - } - if (!(flags & BCH_TRANS_COMMIT_no_check_rw) && unlikely(!bch2_write_ref_tryget(c, BCH_WRITE_REF_trans))) { - ret = bch2_trans_commit_get_rw_cold(trans, flags); - if (ret) - goto out_reset; + if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) + ret = do_bch2_trans_commit_to_journal_replay(trans); + else + ret = -BCH_ERR_erofs_trans_commit; + goto out_reset; } EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); @@ -1112,8 +1058,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) } retry: errored_at = NULL; - bch2_trans_verify_not_unlocked(trans); - bch2_trans_verify_not_in_restart(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) memset(&trans->journal_res, 0, sizeof(trans->journal_res)); memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta)); diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index 4568a41fefaf..a6f251eb4164 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -513,6 +513,9 @@ struct btree_trans { u64 last_begin_time; unsigned long last_begin_ip; unsigned long last_restarted_ip; +#ifdef CONFIG_BCACHEFS_DEBUG + bch_stacktrace last_restarted_trace; +#endif unsigned long last_unlock_ip; unsigned long srcu_lock_time; @@ -787,53 +790,64 @@ static inline bool btree_node_type_has_triggers(enum btree_node_type type) return BIT_ULL(type) & BTREE_NODE_TYPE_HAS_TRIGGERS; } -static inline bool btree_node_type_is_extents(enum btree_node_type type) +static inline bool btree_id_is_extents(enum btree_id btree) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_EXTENTS)) << (nr + 1)) +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_extents)) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(type) & mask; + return BIT_ULL(btree) & mask; } -static inline bool btree_id_is_extents(enum btree_id btree) +static inline bool btree_node_type_is_extents(enum btree_node_type type) { - return btree_node_type_is_extents(__btree_node_type(0, btree)); + return type != BKEY_TYPE_btree && btree_id_is_extents(type - 1); +} + +static inline bool btree_type_has_snapshots(enum btree_id btree) +{ + const u64 mask = 0 +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_snapshots)) << nr) + BCH_BTREE_IDS() +#undef x + ; + + return BIT_ULL(btree) & mask; } -static inline bool btree_type_has_snapshots(enum btree_id id) +static inline bool btree_type_has_snapshot_field(enum btree_id btree) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_SNAPSHOTS)) << nr) +#define x(name, nr, flags, ...) |((!!((flags) & (BTREE_IS_snapshot_field|BTREE_IS_snapshots))) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(id) & mask; + return BIT_ULL(btree) & mask; } -static inline bool btree_type_has_snapshot_field(enum btree_id id) +static inline bool btree_type_has_ptrs(enum btree_id btree) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & (BTREE_ID_SNAPSHOT_FIELD|BTREE_ID_SNAPSHOTS))) << nr) +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_data)) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(id) & mask; + return BIT_ULL(btree) & mask; } -static inline bool btree_type_has_ptrs(enum btree_id id) +static inline bool btree_type_uses_write_buffer(enum btree_id btree) { const u64 mask = 0 -#define x(name, nr, flags, ...) |((!!((flags) & BTREE_ID_DATA)) << nr) +#define x(name, nr, flags, ...) |((!!((flags) & BTREE_IS_write_buffer)) << nr) BCH_BTREE_IDS() #undef x ; - return BIT_ULL(id) & mask; + return BIT_ULL(btree) & mask; } struct btree_root { diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index 5d809e8bd170..13d794f201a5 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -144,7 +144,7 @@ int __bch2_insert_snapshot_whiteouts(struct btree_trans *trans, !(ret = bkey_err(old_k)) && bkey_eq(old_pos, old_k.k->p)) { struct bpos whiteout_pos = - SPOS(new_pos.inode, new_pos.offset, old_k.k->p.snapshot);; + SPOS(new_pos.inode, new_pos.offset, old_k.k->p.snapshot); if (!bch2_snapshot_is_ancestor(c, old_k.k->p.snapshot, old_pos.snapshot) || snapshot_list_has_ancestor(c, &s, old_k.k->p.snapshot)) @@ -296,7 +296,7 @@ static int bch2_trans_update_extent(struct btree_trans *trans, BTREE_ITER_intent| BTREE_ITER_with_updates| BTREE_ITER_not_extents); - k = bch2_btree_iter_peek_upto(&iter, POS(insert->k.p.inode, U64_MAX)); + k = bch2_btree_iter_peek_max(&iter, POS(insert->k.p.inode, U64_MAX)); if ((ret = bkey_err(k))) goto err; if (!k.k) @@ -323,7 +323,7 @@ static int bch2_trans_update_extent(struct btree_trans *trans, goto out; next: bch2_btree_iter_advance(&iter); - k = bch2_btree_iter_peek_upto(&iter, POS(insert->k.p.inode, U64_MAX)); + k = bch2_btree_iter_peek_max(&iter, POS(insert->k.p.inode, U64_MAX)); if ((ret = bkey_err(k))) goto err; if (!k.k) @@ -588,12 +588,9 @@ struct jset_entry *__bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsi int bch2_bkey_get_empty_slot(struct btree_trans *trans, struct btree_iter *iter, enum btree_id btree, struct bpos end) { - struct bkey_s_c k; - int ret = 0; - - bch2_trans_iter_init(trans, iter, btree, POS_MAX, BTREE_ITER_intent); - k = bch2_btree_iter_prev(iter); - ret = bkey_err(k); + bch2_trans_iter_init(trans, iter, btree, end, BTREE_ITER_intent); + struct bkey_s_c k = bch2_btree_iter_peek_prev(iter); + int ret = bkey_err(k); if (ret) goto err; @@ -672,27 +669,19 @@ int bch2_btree_insert(struct bch_fs *c, enum btree_id id, struct bkey_i *k, bch2_btree_insert_trans(trans, id, k, iter_flags)); } -int bch2_btree_delete_extent_at(struct btree_trans *trans, struct btree_iter *iter, - unsigned len, unsigned update_flags) +int bch2_btree_delete_at(struct btree_trans *trans, + struct btree_iter *iter, unsigned update_flags) { - struct bkey_i *k; - - k = bch2_trans_kmalloc(trans, sizeof(*k)); - if (IS_ERR(k)) - return PTR_ERR(k); + struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k)); + int ret = PTR_ERR_OR_ZERO(k); + if (ret) + return ret; bkey_init(&k->k); k->k.p = iter->pos; - bch2_key_resize(&k->k, len); return bch2_trans_update(trans, iter, k, update_flags); } -int bch2_btree_delete_at(struct btree_trans *trans, - struct btree_iter *iter, unsigned update_flags) -{ - return bch2_btree_delete_extent_at(trans, iter, 0, update_flags); -} - int bch2_btree_delete(struct btree_trans *trans, enum btree_id btree, struct bpos pos, unsigned update_flags) @@ -721,7 +710,7 @@ int bch2_btree_delete_range_trans(struct btree_trans *trans, enum btree_id id, int ret = 0; bch2_trans_iter_init(trans, &iter, id, start, BTREE_ITER_intent); - while ((k = bch2_btree_iter_peek_upto(&iter, end)).k) { + while ((k = bch2_btree_iter_peek_max(&iter, end)).k) { struct disk_reservation disk_res = bch2_disk_reservation_init(trans->c, 0); struct bkey_i delete; @@ -794,8 +783,7 @@ int bch2_btree_delete_range(struct bch_fs *c, enum btree_id id, return ret; } -int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree, - struct bpos pos, bool set) +int bch2_btree_bit_mod_iter(struct btree_trans *trans, struct btree_iter *iter, bool set) { struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k)); int ret = PTR_ERR_OR_ZERO(k); @@ -804,13 +792,21 @@ int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree, bkey_init(&k->k); k->k.type = set ? KEY_TYPE_set : KEY_TYPE_deleted; - k->k.p = pos; + k->k.p = iter->pos; + if (iter->flags & BTREE_ITER_is_extents) + bch2_key_resize(&k->k, 1); + return bch2_trans_update(trans, iter, k, 0); +} + +int bch2_btree_bit_mod(struct btree_trans *trans, enum btree_id btree, + struct bpos pos, bool set) +{ struct btree_iter iter; bch2_trans_iter_init(trans, &iter, btree, pos, BTREE_ITER_intent); - ret = bch2_btree_iter_traverse(&iter) ?: - bch2_trans_update(trans, &iter, k, 0); + int ret = bch2_btree_iter_traverse(&iter) ?: + bch2_btree_bit_mod_iter(trans, &iter, set); bch2_trans_iter_exit(trans, &iter); return ret; } @@ -827,10 +823,17 @@ int bch2_btree_bit_mod_buffered(struct btree_trans *trans, enum btree_id btree, return bch2_trans_update_buffered(trans, btree, &k); } -static int __bch2_trans_log_msg(struct btree_trans *trans, struct printbuf *buf, unsigned u64s) +int bch2_trans_log_msg(struct btree_trans *trans, struct printbuf *buf) { + unsigned u64s = DIV_ROUND_UP(buf->pos, sizeof(u64)); + prt_chars(buf, '\0', u64s * sizeof(u64) - buf->pos); + + int ret = buf->allocation_failure ? -BCH_ERR_ENOMEM_trans_log_msg : 0; + if (ret) + return ret; + struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, jset_u64s(u64s)); - int ret = PTR_ERR_OR_ZERO(e); + ret = PTR_ERR_OR_ZERO(e); if (ret) return ret; @@ -865,9 +868,8 @@ __bch2_fs_log_msg(struct bch_fs *c, unsigned commit_flags, const char *fmt, memcpy(l->d, buf.buf, buf.pos); c->journal.early_journal_entries.nr += jset_u64s(u64s); } else { - ret = bch2_trans_commit_do(c, NULL, NULL, - BCH_TRANS_COMMIT_lazy_rw|commit_flags, - __bch2_trans_log_msg(trans, &buf, u64s)); + ret = bch2_trans_commit_do(c, NULL, NULL, commit_flags, + bch2_trans_log_msg(trans, &buf)); } err: printbuf_exit(&buf); diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 70b3c989fac2..8f22ef9a7651 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -24,7 +24,6 @@ void bch2_btree_insert_key_leaf(struct btree_trans *, struct btree_path *, #define BCH_TRANS_COMMIT_FLAGS() \ x(no_enospc, "don't check for enospc") \ x(no_check_rw, "don't attempt to take a ref on c->writes") \ - x(lazy_rw, "go read-write if we haven't yet - only for use in recovery") \ x(no_journal_res, "don't take a journal reservation, instead " \ "pin journal entry referred to by trans->journal_res.seq") \ x(journal_reclaim, "operation required for journal reclaim; may return error" \ @@ -47,8 +46,6 @@ enum bch_trans_commit_flags { void bch2_trans_commit_flags_to_text(struct printbuf *, enum bch_trans_commit_flags); -int bch2_btree_delete_extent_at(struct btree_trans *, struct btree_iter *, - unsigned, unsigned); int bch2_btree_delete_at(struct btree_trans *, struct btree_iter *, unsigned); int bch2_btree_delete(struct btree_trans *, enum btree_id, struct bpos, unsigned); @@ -66,6 +63,7 @@ int bch2_btree_delete_range_trans(struct btree_trans *, enum btree_id, int bch2_btree_delete_range(struct bch_fs *, enum btree_id, struct bpos, struct bpos, unsigned, u64 *); +int bch2_btree_bit_mod_iter(struct btree_trans *, struct btree_iter *, bool); int bch2_btree_bit_mod(struct btree_trans *, enum btree_id, struct bpos, bool); int bch2_btree_bit_mod_buffered(struct btree_trans *, enum btree_id, struct bpos, bool); @@ -161,6 +159,7 @@ void bch2_trans_commit_hook(struct btree_trans *, struct btree_trans_commit_hook *); int __bch2_trans_commit(struct btree_trans *, unsigned); +int bch2_trans_log_msg(struct btree_trans *, struct printbuf *); __printf(2, 3) int bch2_fs_log_msg(struct bch_fs *, const char *, ...); __printf(2, 3) int bch2_journal_log_msg(struct bch_fs *, const char *, ...); @@ -244,7 +243,8 @@ static inline struct bkey_i *bch2_bkey_make_mut_noupdate(struct btree_trans *tra KEY_TYPE_##_type, sizeof(struct bkey_i_##_type))) static inline struct bkey_i *__bch2_bkey_make_mut(struct btree_trans *trans, struct btree_iter *iter, - struct bkey_s_c *k, unsigned flags, + struct bkey_s_c *k, + enum btree_iter_update_trigger_flags flags, unsigned type, unsigned min_bytes) { struct bkey_i *mut = __bch2_bkey_make_mut_noupdate(trans, *k, type, min_bytes); @@ -261,8 +261,9 @@ static inline struct bkey_i *__bch2_bkey_make_mut(struct btree_trans *trans, str return mut; } -static inline struct bkey_i *bch2_bkey_make_mut(struct btree_trans *trans, struct btree_iter *iter, - struct bkey_s_c *k, unsigned flags) +static inline struct bkey_i *bch2_bkey_make_mut(struct btree_trans *trans, + struct btree_iter *iter, struct bkey_s_c *k, + enum btree_iter_update_trigger_flags flags) { return __bch2_bkey_make_mut(trans, iter, k, flags, 0, 0); } @@ -274,7 +275,8 @@ static inline struct bkey_i *bch2_bkey_make_mut(struct btree_trans *trans, struc static inline struct bkey_i *__bch2_bkey_get_mut_noupdate(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags, unsigned type, unsigned min_bytes) + enum btree_iter_update_trigger_flags flags, + unsigned type, unsigned min_bytes) { struct bkey_s_c k = __bch2_bkey_get_iter(trans, iter, btree_id, pos, flags|BTREE_ITER_intent, type); @@ -289,7 +291,7 @@ static inline struct bkey_i *__bch2_bkey_get_mut_noupdate(struct btree_trans *tr static inline struct bkey_i *bch2_bkey_get_mut_noupdate(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags) + enum btree_iter_update_trigger_flags flags) { return __bch2_bkey_get_mut_noupdate(trans, iter, btree_id, pos, flags, 0, 0); } @@ -297,7 +299,8 @@ static inline struct bkey_i *bch2_bkey_get_mut_noupdate(struct btree_trans *tran static inline struct bkey_i *__bch2_bkey_get_mut(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags, unsigned type, unsigned min_bytes) + enum btree_iter_update_trigger_flags flags, + unsigned type, unsigned min_bytes) { struct bkey_i *mut = __bch2_bkey_get_mut_noupdate(trans, iter, btree_id, pos, flags|BTREE_ITER_intent, type, min_bytes); @@ -318,7 +321,8 @@ static inline struct bkey_i *__bch2_bkey_get_mut(struct btree_trans *trans, static inline struct bkey_i *bch2_bkey_get_mut_minsize(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags, unsigned min_bytes) + enum btree_iter_update_trigger_flags flags, + unsigned min_bytes) { return __bch2_bkey_get_mut(trans, iter, btree_id, pos, flags, 0, min_bytes); } @@ -326,7 +330,7 @@ static inline struct bkey_i *bch2_bkey_get_mut_minsize(struct btree_trans *trans static inline struct bkey_i *bch2_bkey_get_mut(struct btree_trans *trans, struct btree_iter *iter, unsigned btree_id, struct bpos pos, - unsigned flags) + enum btree_iter_update_trigger_flags flags) { return __bch2_bkey_get_mut(trans, iter, btree_id, pos, flags, 0, 0); } @@ -337,7 +341,8 @@ static inline struct bkey_i *bch2_bkey_get_mut(struct btree_trans *trans, KEY_TYPE_##_type, sizeof(struct bkey_i_##_type))) static inline struct bkey_i *__bch2_bkey_alloc(struct btree_trans *trans, struct btree_iter *iter, - unsigned flags, unsigned type, unsigned val_size) + enum btree_iter_update_trigger_flags flags, + unsigned type, unsigned val_size) { struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k) + val_size); int ret; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index d596ef93239f..f4aeadbe53c1 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -58,11 +58,15 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, b->data->min_key)); + bch2_bkey_buf_init(&prev); + bkey_init(&prev.k->k); + bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); + if (b == btree_node_root(c, b)) { if (!bpos_eq(b->data->min_key, POS_MIN)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->min_key); - need_fsck_err(trans, btree_root_bad_min_key, + log_fsck_err(trans, btree_root_bad_min_key, "btree root with incorrect min_key: %s", buf.buf); goto topology_repair; } @@ -70,18 +74,14 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) if (!bpos_eq(b->data->max_key, SPOS_MAX)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->max_key); - need_fsck_err(trans, btree_root_bad_max_key, + log_fsck_err(trans, btree_root_bad_max_key, "btree root with incorrect max_key: %s", buf.buf); goto topology_repair; } } if (!b->c.level) - return 0; - - bch2_bkey_buf_init(&prev); - bkey_init(&prev.k->k); - bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); + goto out; while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { if (k.k->type != KEY_TYPE_btree_ptr_v2) @@ -97,16 +97,16 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) bch2_topology_error(c); printbuf_reset(&buf); - prt_str(&buf, "end of prev node doesn't match start of next node\n"), - prt_printf(&buf, " in btree %s level %u node ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_str(&buf, "end of prev node doesn't match start of next node\n in "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n prev "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); prt_str(&buf, "\n next "); bch2_bkey_val_to_text(&buf, c, k); - need_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf); + log_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf); goto topology_repair; } @@ -118,25 +118,25 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) bch2_topology_error(c); printbuf_reset(&buf); - prt_str(&buf, "empty interior node\n"); - prt_printf(&buf, " in btree %s level %u node ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_str(&buf, "empty interior node\n in "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); - need_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf); + log_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf); goto topology_repair; } else if (!bpos_eq(prev.k->k.p, b->key.k.p)) { bch2_topology_error(c); printbuf_reset(&buf); - prt_str(&buf, "last child node doesn't end at end of parent node\n"); - prt_printf(&buf, " in btree %s level %u node ", - bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_str(&buf, "last child node doesn't end at end of parent node\n in "); + bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); + prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n last key "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); - need_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf); + log_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf); goto topology_repair; } out: @@ -146,13 +146,7 @@ fsck_err: printbuf_exit(&buf); return ret; topology_repair: - if ((c->opts.recovery_passes & BIT_ULL(BCH_RECOVERY_PASS_check_topology)) && - c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology) { - bch2_inconsistent_error(c); - ret = -BCH_ERR_btree_need_topology_repair; - } else { - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); - } + ret = bch2_topology_error(c); goto out; } @@ -244,7 +238,6 @@ static void bch2_btree_node_free_inmem(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; - unsigned i, level = b->c.level; bch2_btree_node_lock_write_nofail(trans, path, &b->c); @@ -255,13 +248,9 @@ static void bch2_btree_node_free_inmem(struct btree_trans *trans, mutex_unlock(&c->btree_cache.lock); six_unlock_write(&b->c.lock); - mark_btree_node_locked_noreset(path, level, BTREE_NODE_INTENT_LOCKED); + mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); - trans_for_each_path(trans, path, i) - if (path->l[level].b == b) { - btree_node_unlock(trans, path, level); - path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); - } + bch2_trans_node_drop(trans, b); } static void bch2_btree_node_free_never_used(struct btree_update *as, @@ -270,8 +259,6 @@ static void bch2_btree_node_free_never_used(struct btree_update *as, { struct bch_fs *c = as->c; struct prealloc_nodes *p = &as->prealloc_nodes[b->c.lock.readers != NULL]; - struct btree_path *path; - unsigned i, level = b->c.level; BUG_ON(!list_empty(&b->write_blocked)); BUG_ON(b->will_make_reachable != (1UL|(unsigned long) as)); @@ -293,11 +280,7 @@ static void bch2_btree_node_free_never_used(struct btree_update *as, six_unlock_intent(&b->c.lock); - trans_for_each_path(trans, path, i) - if (path->l[level].b == b) { - btree_node_unlock(trans, path, level); - path->l[level].b = ERR_PTR(-BCH_ERR_no_btree_node_init); - } + bch2_trans_node_drop(trans, b); } static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, @@ -809,7 +792,7 @@ err: mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); six_unlock_write(&b->c.lock); - btree_node_write_if_need(c, b, SIX_LOCK_intent); + btree_node_write_if_need(trans, b, SIX_LOCK_intent); btree_node_unlock(trans, path, b->c.level); bch2_path_put(trans, path_idx, true); } @@ -830,7 +813,7 @@ err: b = as->new_nodes[i]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); - btree_node_write_if_need(c, b, SIX_LOCK_read); + btree_node_write_if_need(trans, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); } @@ -1366,9 +1349,14 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as, if (unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags))) bch2_journal_key_overwritten(c, b->c.btree_id, b->c.level, insert->k.p); - if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), - btree_node_type(b), BCH_VALIDATE_write) ?: - bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), BCH_VALIDATE_write)) { + struct bkey_validate_context from = (struct bkey_validate_context) { + .from = BKEY_VALIDATE_btree_node, + .level = b->c.level, + .btree = b->c.btree_id, + .flags = BCH_VALIDATE_commit, + }; + if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), from) ?: + bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), from)) { bch2_fs_inconsistent(c, "%s: inserting invalid bkey", __func__); dump_stack(); } @@ -1418,15 +1406,26 @@ bch2_btree_insert_keys_interior(struct btree_update *as, (bkey_cmp_left_packed(b, k, &insert->k.p) >= 0)) ; - while (!bch2_keylist_empty(keys)) { - insert = bch2_keylist_front(keys); + for (; + insert != keys->top && bpos_le(insert->k.p, b->key.k.p); + insert = bkey_next(insert)) + bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert); - if (bpos_gt(insert->k.p, b->key.k.p)) - break; + if (bch2_btree_node_check_topology(trans, b)) { + struct printbuf buf = PRINTBUF; - bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert); - bch2_keylist_pop_front(keys); + for (struct bkey_i *k = keys->keys; + k != insert; + k = bkey_next(k)) { + bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k)); + prt_newline(&buf); + } + + panic("%s(): check_topology error: inserted keys\n%s", __func__, buf.buf); } + + memmove_u64s_down(keys->keys, insert, keys->top_p - insert->_data); + keys->top_p -= insert->_data - keys->keys_p; } static bool key_deleted_in_insert(struct keylist *insert_keys, struct bpos pos) @@ -1575,8 +1574,6 @@ static void btree_split_insert_keys(struct btree_update *as, bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p); bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); - - BUG_ON(bch2_btree_node_check_topology(trans, b)); } } @@ -1599,8 +1596,6 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, if (ret) return ret; - bch2_btree_interior_update_will_free_node(as, b); - if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) { struct btree *n[2]; @@ -1699,16 +1694,18 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, if (ret) goto err; + bch2_btree_interior_update_will_free_node(as, b); + if (n3) { bch2_btree_update_get_open_buckets(as, n3); - bch2_btree_node_write(c, n3, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n3, SIX_LOCK_intent, 0); } if (n2) { bch2_btree_update_get_open_buckets(as, n2); - bch2_btree_node_write(c, n2, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n2, SIX_LOCK_intent, 0); } bch2_btree_update_get_open_buckets(as, n1); - bch2_btree_node_write(c, n1, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n1, SIX_LOCK_intent, 0); /* * The old node must be freed (in memory) _before_ unlocking the new @@ -1827,8 +1824,6 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t btree_update_updated_node(as, b); bch2_btree_node_unlock_write(trans, path, b); - - BUG_ON(bch2_btree_node_check_topology(trans, b)); return 0; split: /* @@ -1905,7 +1900,7 @@ static void __btree_increase_depth(struct btree_update *as, struct btree_trans * BUG_ON(ret); bch2_btree_update_get_open_buckets(as, n); - bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_trans_node_add(trans, path, n); six_unlock_intent(&n->c.lock); @@ -1953,8 +1948,7 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, u64 start_time = local_clock(); int ret = 0; - bch2_trans_verify_not_in_restart(trans); - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); BUG_ON(!trans->paths[path].should_be_locked); BUG_ON(!btree_node_locked(&trans->paths[path], level)); @@ -2058,9 +2052,6 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, trace_and_count(c, btree_node_merge, trans, b); - bch2_btree_interior_update_will_free_node(as, b); - bch2_btree_interior_update_will_free_node(as, m); - n = bch2_btree_node_alloc(as, trans, b->c.level); SET_BTREE_NODE_SEQ(n->data, @@ -2096,10 +2087,13 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, if (ret) goto err_free_update; + bch2_btree_interior_update_will_free_node(as, b); + bch2_btree_interior_update_will_free_node(as, m); + bch2_trans_verify_paths(trans); bch2_btree_update_get_open_buckets(as, n); - bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, trans->paths + path, b); bch2_btree_node_free_inmem(trans, trans->paths + sib_path, m); @@ -2150,8 +2144,6 @@ int bch2_btree_node_rewrite(struct btree_trans *trans, if (ret) goto out; - bch2_btree_interior_update_will_free_node(as, b); - n = bch2_btree_node_alloc_replacement(as, trans, b); bch2_btree_build_aux_trees(n); @@ -2175,8 +2167,10 @@ int bch2_btree_node_rewrite(struct btree_trans *trans, if (ret) goto err; + bch2_btree_interior_update_will_free_node(as, b); + bch2_btree_update_get_open_buckets(as, n); - bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); + bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, btree_iter_path(trans, iter), b); @@ -2201,42 +2195,50 @@ struct async_btree_rewrite { struct list_head list; enum btree_id btree_id; unsigned level; - struct bpos pos; - __le64 seq; + struct bkey_buf key; }; static int async_btree_node_rewrite_trans(struct btree_trans *trans, struct async_btree_rewrite *a) { - struct bch_fs *c = trans->c; struct btree_iter iter; - struct btree *b; - int ret; - - bch2_trans_node_iter_init(trans, &iter, a->btree_id, a->pos, + bch2_trans_node_iter_init(trans, &iter, + a->btree_id, a->key.k->k.p, BTREE_MAX_DEPTH, a->level, 0); - b = bch2_btree_iter_peek_node(&iter); - ret = PTR_ERR_OR_ZERO(b); + struct btree *b = bch2_btree_iter_peek_node(&iter); + int ret = PTR_ERR_OR_ZERO(b); if (ret) goto out; - if (!b || b->data->keys.seq != a->seq) { + bool found = b && btree_ptr_hash_val(&b->key) == btree_ptr_hash_val(a->key.k); + ret = found + ? bch2_btree_node_rewrite(trans, &iter, b, 0) + : -ENOENT; + +#if 0 + /* Tracepoint... */ + if (!ret || ret == -ENOENT) { + struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; - if (b) - bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); - else - prt_str(&buf, "(null"); - bch_info(c, "%s: node to rewrite not found:, searching for seq %llu, got\n%s", - __func__, a->seq, buf.buf); + if (!ret) { + prt_printf(&buf, "rewrite node:\n "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(a->key.k)); + } else { + prt_printf(&buf, "node to rewrite not found:\n want: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(a->key.k)); + prt_printf(&buf, "\n got: "); + if (b) + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + else + prt_str(&buf, "(null)"); + } + bch_info(c, "%s", buf.buf); printbuf_exit(&buf); - goto out; } - - ret = bch2_btree_node_rewrite(trans, &iter, b, 0); +#endif out: bch2_trans_iter_exit(trans, &iter); - return ret; } @@ -2247,81 +2249,97 @@ static void async_btree_node_rewrite_work(struct work_struct *work) struct bch_fs *c = a->c; int ret = bch2_trans_do(c, async_btree_node_rewrite_trans(trans, a)); - bch_err_fn_ratelimited(c, ret); + if (ret != -ENOENT) + bch_err_fn_ratelimited(c, ret); + + spin_lock(&c->btree_node_rewrites_lock); + list_del(&a->list); + spin_unlock(&c->btree_node_rewrites_lock); + + closure_wake_up(&c->btree_node_rewrites_wait); + + bch2_bkey_buf_exit(&a->key, c); bch2_write_ref_put(c, BCH_WRITE_REF_node_rewrite); kfree(a); } void bch2_btree_node_rewrite_async(struct bch_fs *c, struct btree *b) { - struct async_btree_rewrite *a; - int ret; - - a = kmalloc(sizeof(*a), GFP_NOFS); - if (!a) { - bch_err(c, "%s: error allocating memory", __func__); + struct async_btree_rewrite *a = kmalloc(sizeof(*a), GFP_NOFS); + if (!a) return; - } a->c = c; a->btree_id = b->c.btree_id; a->level = b->c.level; - a->pos = b->key.k.p; - a->seq = b->data->keys.seq; INIT_WORK(&a->work, async_btree_node_rewrite_work); - if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { - mutex_lock(&c->pending_node_rewrites_lock); - list_add(&a->list, &c->pending_node_rewrites); - mutex_unlock(&c->pending_node_rewrites_lock); - return; - } + bch2_bkey_buf_init(&a->key); + bch2_bkey_buf_copy(&a->key, c, &b->key); - if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) { - if (test_bit(BCH_FS_started, &c->flags)) { - bch_err(c, "%s: error getting c->writes ref", __func__); - kfree(a); - return; - } + bool now = false, pending = false; - ret = bch2_fs_read_write_early(c); - bch_err_msg(c, ret, "going read-write"); - if (ret) { - kfree(a); - return; - } + spin_lock(&c->btree_node_rewrites_lock); + if (c->curr_recovery_pass > BCH_RECOVERY_PASS_journal_replay && + bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) { + list_add(&a->list, &c->btree_node_rewrites); + now = true; + } else if (!test_bit(BCH_FS_may_go_rw, &c->flags)) { + list_add(&a->list, &c->btree_node_rewrites_pending); + pending = true; + } + spin_unlock(&c->btree_node_rewrites_lock); - bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); + if (now) { + queue_work(c->btree_node_rewrite_worker, &a->work); + } else if (pending) { + /* bch2_do_pending_node_rewrites will execute */ + } else { + bch2_bkey_buf_exit(&a->key, c); + kfree(a); } +} - queue_work(c->btree_node_rewrite_worker, &a->work); +void bch2_async_btree_node_rewrites_flush(struct bch_fs *c) +{ + closure_wait_event(&c->btree_node_rewrites_wait, + list_empty(&c->btree_node_rewrites)); } void bch2_do_pending_node_rewrites(struct bch_fs *c) { - struct async_btree_rewrite *a, *n; - - mutex_lock(&c->pending_node_rewrites_lock); - list_for_each_entry_safe(a, n, &c->pending_node_rewrites, list) { - list_del(&a->list); + while (1) { + spin_lock(&c->btree_node_rewrites_lock); + struct async_btree_rewrite *a = + list_pop_entry(&c->btree_node_rewrites_pending, + struct async_btree_rewrite, list); + if (a) + list_add(&a->list, &c->btree_node_rewrites); + spin_unlock(&c->btree_node_rewrites_lock); + + if (!a) + break; bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); queue_work(c->btree_node_rewrite_worker, &a->work); } - mutex_unlock(&c->pending_node_rewrites_lock); } void bch2_free_pending_node_rewrites(struct bch_fs *c) { - struct async_btree_rewrite *a, *n; + while (1) { + spin_lock(&c->btree_node_rewrites_lock); + struct async_btree_rewrite *a = + list_pop_entry(&c->btree_node_rewrites_pending, + struct async_btree_rewrite, list); + spin_unlock(&c->btree_node_rewrites_lock); - mutex_lock(&c->pending_node_rewrites_lock); - list_for_each_entry_safe(a, n, &c->pending_node_rewrites, list) { - list_del(&a->list); + if (!a) + break; + bch2_bkey_buf_exit(&a->key, c); kfree(a); } - mutex_unlock(&c->pending_node_rewrites_lock); } static int __bch2_btree_node_update_key(struct btree_trans *trans, @@ -2575,8 +2593,9 @@ static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update prt_printf(out, "%ps: ", (void *) as->ip_started); bch2_trans_commit_flags_to_text(out, as->flags); - prt_printf(out, " btree=%s l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", - bch2_btree_id_str(as->btree_id), + prt_str(out, " "); + bch2_btree_id_to_text(out, as->btree_id); + prt_printf(out, " l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", as->update_level_start, as->update_level_end, bch2_btree_update_modes[as->mode], @@ -2677,6 +2696,9 @@ void bch2_btree_reserve_cache_to_text(struct printbuf *out, struct bch_fs *c) void bch2_fs_btree_interior_update_exit(struct bch_fs *c) { + WARN_ON(!list_empty(&c->btree_node_rewrites)); + WARN_ON(!list_empty(&c->btree_node_rewrites_pending)); + if (c->btree_node_rewrite_worker) destroy_workqueue(c->btree_node_rewrite_worker); if (c->btree_interior_update_worker) @@ -2692,8 +2714,9 @@ void bch2_fs_btree_interior_update_init_early(struct bch_fs *c) mutex_init(&c->btree_interior_update_lock); INIT_WORK(&c->btree_interior_update_work, btree_interior_update_work); - INIT_LIST_HEAD(&c->pending_node_rewrites); - mutex_init(&c->pending_node_rewrites_lock); + INIT_LIST_HEAD(&c->btree_node_rewrites); + INIT_LIST_HEAD(&c->btree_node_rewrites_pending); + spin_lock_init(&c->btree_node_rewrites_lock); } int bch2_fs_btree_interior_update_init(struct bch_fs *c) diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index 10f400957f21..7930ffea3075 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -159,7 +159,7 @@ static inline int bch2_foreground_maybe_merge(struct btree_trans *trans, unsigned level, unsigned flags) { - bch2_trans_verify_not_unlocked(trans); + bch2_trans_verify_not_unlocked_or_in_restart(trans); return bch2_foreground_maybe_merge_sibling(trans, path, level, flags, btree_prev_sib) ?: @@ -334,6 +334,7 @@ void bch2_journal_entry_to_btree_root(struct bch_fs *, struct jset_entry *); struct jset_entry *bch2_btree_roots_to_journal_entries(struct bch_fs *, struct jset_entry *, unsigned long); +void bch2_async_btree_node_rewrites_flush(struct bch_fs *); void bch2_do_pending_node_rewrites(struct bch_fs *); void bch2_free_pending_node_rewrites(struct bch_fs *); diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index 1639c60dffa0..b56c4987b8c9 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -19,8 +19,6 @@ static int bch2_btree_write_buffer_journal_flush(struct journal *, struct journal_entry_pin *, u64); -static int bch2_journal_keys_to_write_buffer(struct bch_fs *, struct journal_buf *); - static inline bool __wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_key_ref *r) { return (cmp_int(l->hi, r->hi) ?: @@ -314,6 +312,8 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) darray_for_each(wb->sorted, i) { struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx]; + BUG_ON(!btree_type_uses_write_buffer(k->btree)); + for (struct wb_key_ref *n = i + 1; n < min(i + 4, &darray_top(wb->sorted)); n++) prefetch(&wb->flushing.keys.data[n->idx]); @@ -481,21 +481,55 @@ err: return ret; } -static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 seq) +static int bch2_journal_keys_to_write_buffer(struct bch_fs *c, struct journal_buf *buf) +{ + struct journal_keys_to_wb dst; + int ret = 0; + + bch2_journal_keys_to_write_buffer_start(c, &dst, le64_to_cpu(buf->data->seq)); + + for_each_jset_entry_type(entry, buf->data, BCH_JSET_ENTRY_write_buffer_keys) { + jset_entry_for_each_key(entry, k) { + ret = bch2_journal_key_to_wb(c, &dst, entry->btree_id, k); + if (ret) + goto out; + } + + entry->type = BCH_JSET_ENTRY_btree_keys; + } +out: + ret = bch2_journal_keys_to_write_buffer_end(c, &dst) ?: ret; + return ret; +} + +static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 max_seq) { struct journal *j = &c->journal; struct journal_buf *buf; + bool blocked; int ret = 0; - while (!ret && (buf = bch2_next_write_buffer_flush_journal_buf(j, seq))) { + while (!ret && (buf = bch2_next_write_buffer_flush_journal_buf(j, max_seq, &blocked))) { ret = bch2_journal_keys_to_write_buffer(c, buf); + + if (!blocked && !ret) { + spin_lock(&j->lock); + buf->need_flush_to_write_buffer = false; + spin_unlock(&j->lock); + } + mutex_unlock(&j->buf_lock); + + if (blocked) { + bch2_journal_unblock(j); + break; + } } return ret; } -static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, +static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 max_seq, bool *did_work) { struct bch_fs *c = trans->c; @@ -505,7 +539,7 @@ static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, do { bch2_trans_unlock(trans); - fetch_from_journal_err = fetch_wb_keys_from_journal(c, seq); + fetch_from_journal_err = fetch_wb_keys_from_journal(c, max_seq); *did_work |= wb->inc.keys.nr || wb->flushing.keys.nr; @@ -518,8 +552,8 @@ static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, mutex_unlock(&wb->flushing.lock); } while (!ret && (fetch_from_journal_err || - (wb->inc.pin.seq && wb->inc.pin.seq <= seq) || - (wb->flushing.pin.seq && wb->flushing.pin.seq <= seq))); + (wb->inc.pin.seq && wb->inc.pin.seq <= max_seq) || + (wb->flushing.pin.seq && wb->flushing.pin.seq <= max_seq))); return ret; } @@ -600,6 +634,14 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans, bch2_bkey_buf_init(&tmp); if (!bkey_and_val_eq(referring_k, bkey_i_to_s_c(last_flushed->k))) { + if (trace_write_buffer_maybe_flush_enabled()) { + struct printbuf buf = PRINTBUF; + + bch2_bkey_val_to_text(&buf, c, referring_k); + trace_write_buffer_maybe_flush(trans, _RET_IP_, buf.buf); + printbuf_exit(&buf); + } + bch2_bkey_buf_reassemble(&tmp, c, referring_k); if (bkey_is_btree_ptr(referring_k.k)) { @@ -771,31 +813,6 @@ int bch2_journal_keys_to_write_buffer_end(struct bch_fs *c, struct journal_keys_ return ret; } -static int bch2_journal_keys_to_write_buffer(struct bch_fs *c, struct journal_buf *buf) -{ - struct journal_keys_to_wb dst; - int ret = 0; - - bch2_journal_keys_to_write_buffer_start(c, &dst, le64_to_cpu(buf->data->seq)); - - for_each_jset_entry_type(entry, buf->data, BCH_JSET_ENTRY_write_buffer_keys) { - jset_entry_for_each_key(entry, k) { - ret = bch2_journal_key_to_wb(c, &dst, entry->btree_id, k); - if (ret) - goto out; - } - - entry->type = BCH_JSET_ENTRY_btree_keys; - } - - spin_lock(&c->journal.lock); - buf->need_flush_to_write_buffer = false; - spin_unlock(&c->journal.lock); -out: - ret = bch2_journal_keys_to_write_buffer_end(c, &dst) ?: ret; - return ret; -} - static int wb_keys_resize(struct btree_write_buffer_keys *wb, size_t new_size) { if (wb->keys.size >= new_size) diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index ec7d9a59bea9..345b117a4a4a 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -18,7 +18,9 @@ #include "error.h" #include "inode.h" #include "movinggc.h" +#include "rebalance.h" #include "recovery.h" +#include "recovery_passes.h" #include "reflink.h" #include "replicas.h" #include "subvolume.h" @@ -260,8 +262,6 @@ int bch2_check_fix_ptrs(struct btree_trans *trans, struct printbuf buf = PRINTBUF; int ret = 0; - percpu_down_read(&c->mark_lock); - bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) { ret = bch2_check_fix_ptr(trans, k, p, entry_c, &do_update); if (ret) @@ -362,7 +362,6 @@ found: bch_info(c, "new key %s", buf.buf); } - percpu_up_read(&c->mark_lock); struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, new->k.p, 0, level, BTREE_ITER_intent|BTREE_ITER_all_snapshots); @@ -371,8 +370,6 @@ found: BTREE_UPDATE_internal_snapshot_node| BTREE_TRIGGER_norun); bch2_trans_iter_exit(trans, &iter); - percpu_down_read(&c->mark_lock); - if (ret) goto err; @@ -380,7 +377,6 @@ found: bch2_btree_node_update_key_early(trans, btree, level - 1, k, new); } err: - percpu_up_read(&c->mark_lock); printbuf_exit(&buf); return ret; } @@ -401,8 +397,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, BUG_ON(!sectors); if (gen_after(ptr->gen, b_gen)) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - ptr_gen_newer_than_bucket_gen, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, ptr_gen_newer_than_bucket_gen, "bucket %u:%zu gen %u data type %s: ptr gen %u newer than bucket gen\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -415,8 +411,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if (gen_cmp(b_gen, ptr->gen) > BUCKET_GC_GEN_MAX) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - ptr_too_stale, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, ptr_too_stale, "bucket %u:%zu gen %u data type %s: ptr gen %u too stale\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -435,8 +431,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if (b_gen != ptr->gen) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - stale_dirty_ptr, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, stale_dirty_ptr, "bucket %u:%zu gen %u (mem gen %u) data type %s: stale dirty ptr (gen %u)\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -451,8 +447,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if (bucket_data_type_mismatch(bucket_data_type, ptr_data_type)) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - ptr_bucket_data_type_mismatch, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, ptr_bucket_data_type_mismatch, "bucket %u:%zu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -466,8 +462,8 @@ int bch2_bucket_ref_update(struct btree_trans *trans, struct bch_dev *ca, } if ((u64) *bucket_sectors + sectors > U32_MAX) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - bucket_sector_count_overflow, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, bucket_sector_count_overflow, "bucket %u:%zu gen %u data type %s sector count overflow: %u + %lli > U32_MAX\n" "while marking %s", ptr->dev, bucket_nr, b_gen, @@ -485,7 +481,9 @@ out: printbuf_exit(&buf); return ret; err: +fsck_err: bch2_dump_trans_updates(trans); + bch2_inconsistent_error(c); ret = -BCH_ERR_bucket_ref_update; goto out; } @@ -543,7 +541,8 @@ static int __mark_pointer(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c k, const struct extent_ptr_decoded *p, s64 sectors, enum bch_data_type ptr_data_type, - struct bch_alloc_v4 *a) + struct bch_alloc_v4 *a, + bool insert) { u32 *dst_sectors = p->has_ec ? &a->stripe_sectors : !p->ptr.cached ? &a->dirty_sectors : @@ -553,8 +552,8 @@ static int __mark_pointer(struct btree_trans *trans, struct bch_dev *ca, if (ret) return ret; - - alloc_data_type_set(a, ptr_data_type); + if (insert) + alloc_data_type_set(a, ptr_data_type); return 0; } @@ -570,8 +569,10 @@ static int bch2_trigger_pointer(struct btree_trans *trans, struct printbuf buf = PRINTBUF; int ret = 0; - u64 abs_sectors = ptr_disk_sectors(level ? btree_sectors(c) : k.k->size, p); - *sectors = insert ? abs_sectors : -abs_sectors; + struct bkey_i_backpointer bp; + bch2_extent_ptr_to_bp(c, btree_id, level, k, p, entry, &bp); + + *sectors = insert ? bp.v.bucket_len : -(s64) bp.v.bucket_len; struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (unlikely(!ca)) { @@ -580,41 +581,36 @@ static int bch2_trigger_pointer(struct btree_trans *trans, goto err; } - struct bpos bucket; - struct bch_backpointer bp; - __bch2_extent_ptr_to_bp(trans->c, ca, btree_id, level, k, p, entry, &bucket, &bp, abs_sectors); + struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr); if (flags & BTREE_TRIGGER_transactional) { struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, bucket, 0); ret = PTR_ERR_OR_ZERO(a) ?: - __mark_pointer(trans, ca, k, &p, *sectors, bp.data_type, &a->v); + __mark_pointer(trans, ca, k, &p, *sectors, bp.v.data_type, &a->v, insert); if (ret) goto err; if (!p.ptr.cached) { - ret = bch2_bucket_backpointer_mod(trans, ca, bucket, bp, k, insert); + ret = bch2_bucket_backpointer_mod(trans, k, &bp, insert); if (ret) goto err; } } if (flags & BTREE_TRIGGER_gc) { - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", p.ptr.dev, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = -BCH_ERR_trigger_pointer; - goto err_unlock; + goto err; } bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g), new = old; - ret = __mark_pointer(trans, ca, k, &p, *sectors, bp.data_type, &new); + ret = __mark_pointer(trans, ca, k, &p, *sectors, bp.v.data_type, &new, insert); alloc_to_bucket(g, new); bucket_unlock(g); -err_unlock: - percpu_up_read(&c->mark_lock); if (!ret) ret = bch2_alloc_key_to_dev_counters(trans, ca, &old, &new, flags); @@ -951,6 +947,7 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, enum bch_data_type type, unsigned sectors) { + struct bch_fs *c = trans->c; struct btree_iter iter; int ret = 0; @@ -960,8 +957,8 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, return PTR_ERR(a); if (a->v.data_type && type && a->v.data_type != type) { - bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, - bucket_metadata_type_mismatch, + bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_allocations); + log_fsck_err(trans, bucket_metadata_type_mismatch, "bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n" "while marking %s", iter.pos.inode, iter.pos.offset, a->v.gen, @@ -979,6 +976,7 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans, ret = bch2_trans_update(trans, &iter, &a->k_i, 0); } err: +fsck_err: bch2_trans_iter_exit(trans, &iter); return ret; } @@ -990,11 +988,10 @@ static int bch2_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev * struct bch_fs *c = trans->c; int ret = 0; - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, b); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u when marking metadata type %s", ca->dev_idx, bch2_data_type_str(data_type))) - goto err_unlock; + goto err; bucket_lock(g); struct bch_alloc_v4 old = bucket_m_to_alloc(*g); @@ -1004,26 +1001,24 @@ static int bch2_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev * "different types of data in same bucket: %s, %s", bch2_data_type_str(g->data_type), bch2_data_type_str(data_type))) - goto err; + goto err_unlock; if (bch2_fs_inconsistent_on((u64) g->dirty_sectors + sectors > ca->mi.bucket_size, c, "bucket %u:%llu gen %u data type %s sector count overflow: %u + %u > bucket size", ca->dev_idx, b, g->gen, bch2_data_type_str(g->data_type ?: data_type), g->dirty_sectors, sectors)) - goto err; + goto err_unlock; g->data_type = data_type; g->dirty_sectors += sectors; struct bch_alloc_v4 new = bucket_m_to_alloc(*g); bucket_unlock(g); - percpu_up_read(&c->mark_lock); ret = bch2_alloc_key_to_dev_counters(trans, ca, &old, &new, flags); return ret; -err: - bucket_unlock(g); err_unlock: - percpu_up_read(&c->mark_lock); + bucket_unlock(g); +err: return -BCH_ERR_metadata_bucket_inconsistency; } @@ -1155,6 +1150,31 @@ int bch2_trans_mark_dev_sbs(struct bch_fs *c) return bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_transactional); } +bool bch2_is_superblock_bucket(struct bch_dev *ca, u64 b) +{ + struct bch_sb_layout *layout = &ca->disk_sb.sb->layout; + u64 b_offset = bucket_to_sector(ca, b); + u64 b_end = bucket_to_sector(ca, b + 1); + unsigned i; + + if (!b) + return true; + + for (i = 0; i < layout->nr_superblocks; i++) { + u64 offset = le64_to_cpu(layout->sb_offset[i]); + u64 end = offset + (1 << layout->sb_max_size_bits); + + if (!(offset >= b_end || end <= b_offset)) + return true; + } + + for (i = 0; i < ca->journal.nr; i++) + if (b == ca->journal.buckets[i]) + return true; + + return false; +} + /* Disk reservations: */ #define SECTORS_CACHE 1024 @@ -1238,7 +1258,7 @@ int bch2_buckets_nouse_alloc(struct bch_fs *c) for_each_member_device(c, ca) { BUG_ON(ca->buckets_nouse); - ca->buckets_nouse = kvmalloc(BITS_TO_LONGS(ca->mi.nbuckets) * + ca->buckets_nouse = bch2_kvmalloc(BITS_TO_LONGS(ca->mi.nbuckets) * sizeof(unsigned long), GFP_KERNEL|__GFP_ZERO); if (!ca->buckets_nouse) { @@ -1264,10 +1284,15 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) bool resize = ca->bucket_gens != NULL; int ret; - BUG_ON(resize && ca->buckets_nouse); + if (resize) + lockdep_assert_held(&c->state_lock); + + if (resize && ca->buckets_nouse) + return -BCH_ERR_no_resize_with_buckets_nouse; - if (!(bucket_gens = kvmalloc(sizeof(struct bucket_gens) + nbuckets, - GFP_KERNEL|__GFP_ZERO))) { + bucket_gens = bch2_kvmalloc(struct_size(bucket_gens, b, nbuckets), + GFP_KERNEL|__GFP_ZERO); + if (!bucket_gens) { ret = -BCH_ERR_ENOMEM_bucket_gens; goto err; } @@ -1277,19 +1302,16 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) bucket_gens->nbuckets_minus_first = bucket_gens->nbuckets - bucket_gens->first_bucket; - if (resize) { - down_write(&ca->bucket_lock); - percpu_down_write(&c->mark_lock); - } - old_bucket_gens = rcu_dereference_protected(ca->bucket_gens, 1); if (resize) { - size_t n = min(bucket_gens->nbuckets, old_bucket_gens->nbuckets); - + bucket_gens->nbuckets = min(bucket_gens->nbuckets, + old_bucket_gens->nbuckets); + bucket_gens->nbuckets_minus_first = + bucket_gens->nbuckets - bucket_gens->first_bucket; memcpy(bucket_gens->b, old_bucket_gens->b, - n); + bucket_gens->nbuckets); } rcu_assign_pointer(ca->bucket_gens, bucket_gens); @@ -1297,11 +1319,6 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) nbuckets = ca->mi.nbuckets; - if (resize) { - percpu_up_write(&c->mark_lock); - up_write(&ca->bucket_lock); - } - ret = 0; err: if (bucket_gens) diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index ccc78bfe2fd4..a9acdd6c0c86 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -82,16 +82,15 @@ static inline void bucket_lock(struct bucket *b) static inline struct bucket *gc_bucket(struct bch_dev *ca, size_t b) { - return genradix_ptr(&ca->buckets_gc, b); + return bucket_valid(ca, b) + ? genradix_ptr(&ca->buckets_gc, b) + : NULL; } static inline struct bucket_gens *bucket_gens(struct bch_dev *ca) { return rcu_dereference_check(ca->bucket_gens, - !ca->fs || - percpu_rwsem_is_held(&ca->fs->mark_lock) || - lockdep_is_held(&ca->fs->state_lock) || - lockdep_is_held(&ca->bucket_lock)); + lockdep_is_held(&ca->fs->state_lock)); } static inline u8 *bucket_gen(struct bch_dev *ca, size_t b) @@ -308,26 +307,7 @@ int bch2_trans_mark_dev_sbs_flags(struct bch_fs *, enum btree_iter_update_trigger_flags); int bch2_trans_mark_dev_sbs(struct bch_fs *); -static inline bool is_superblock_bucket(struct bch_dev *ca, u64 b) -{ - struct bch_sb_layout *layout = &ca->disk_sb.sb->layout; - u64 b_offset = bucket_to_sector(ca, b); - u64 b_end = bucket_to_sector(ca, b + 1); - unsigned i; - - if (!b) - return true; - - for (i = 0; i < layout->nr_superblocks; i++) { - u64 offset = le64_to_cpu(layout->sb_offset[i]); - u64 end = offset + (1 << layout->sb_max_size_bits); - - if (!(offset >= b_end || end <= b_offset)) - return true; - } - - return false; -} +bool bch2_is_superblock_bucket(struct bch_dev *, u64); static inline const char *bch2_data_type_str(enum bch_data_type type) { diff --git a/fs/bcachefs/buckets_types.h b/fs/bcachefs/buckets_types.h index 28bd09a253c8..7174047b8e92 100644 --- a/fs/bcachefs/buckets_types.h +++ b/fs/bcachefs/buckets_types.h @@ -24,7 +24,7 @@ struct bucket_gens { u16 first_bucket; size_t nbuckets; size_t nbuckets_minus_first; - u8 b[]; + u8 b[] __counted_by(nbuckets); }; struct bch_dev_usage { diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index 2182b555c112..46e9e32105a9 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -6,11 +6,11 @@ #include "buckets.h" #include "chardev.h" #include "disk_accounting.h" +#include "fsck.h" #include "journal.h" #include "move.h" #include "recovery_passes.h" #include "replicas.h" -#include "super.h" #include "super-io.h" #include "thread_with_file.h" @@ -127,130 +127,6 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg } #endif -struct fsck_thread { - struct thread_with_stdio thr; - struct bch_fs *c; - struct bch_opts opts; -}; - -static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) -{ - struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); - kfree(thr); -} - -static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) -{ - struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); - struct bch_fs *c = thr->c; - - int ret = PTR_ERR_OR_ZERO(c); - if (ret) - return ret; - - ret = bch2_fs_start(thr->c); - if (ret) - goto err; - - if (test_bit(BCH_FS_errors_fixed, &c->flags)) { - bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); - ret |= 1; - } - if (test_bit(BCH_FS_error, &c->flags)) { - bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); - ret |= 4; - } -err: - bch2_fs_stop(c); - return ret; -} - -static const struct thread_with_stdio_ops bch2_offline_fsck_ops = { - .exit = bch2_fsck_thread_exit, - .fn = bch2_fsck_offline_thread_fn, -}; - -static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg) -{ - struct bch_ioctl_fsck_offline arg; - struct fsck_thread *thr = NULL; - darray_str(devs) = {}; - long ret = 0; - - if (copy_from_user(&arg, user_arg, sizeof(arg))) - return -EFAULT; - - if (arg.flags) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - for (size_t i = 0; i < arg.nr_devs; i++) { - u64 dev_u64; - ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); - if (ret) - goto err; - - char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); - ret = PTR_ERR_OR_ZERO(dev_str); - if (ret) - goto err; - - ret = darray_push(&devs, dev_str); - if (ret) { - kfree(dev_str); - goto err; - } - } - - thr = kzalloc(sizeof(*thr), GFP_KERNEL); - if (!thr) { - ret = -ENOMEM; - goto err; - } - - thr->opts = bch2_opts_empty(); - - if (arg.opts) { - char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); - ret = PTR_ERR_OR_ZERO(optstr) ?: - bch2_parse_mount_opts(NULL, &thr->opts, NULL, optstr); - if (!IS_ERR(optstr)) - kfree(optstr); - - if (ret) - goto err; - } - - opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); - opt_set(thr->opts, read_only, 1); - opt_set(thr->opts, ratelimit_errors, 0); - - /* We need request_key() to be called before we punt to kthread: */ - opt_set(thr->opts, nostart, true); - - bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); - - thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts); - - if (!IS_ERR(thr->c) && - thr->c->opts.errors == BCH_ON_ERROR_panic) - thr->c->opts.errors = BCH_ON_ERROR_ro; - - ret = __bch2_run_thread_with_stdio(&thr->thr); -out: - darray_for_each(devs, i) - kfree(*i); - darray_exit(&devs); - return ret; -err: - if (thr) - bch2_fsck_thread_exit(&thr->thr); - pr_err("ret %s", bch2_err_str(ret)); - goto out; -} - static long bch2_global_ioctl(unsigned cmd, void __user *arg) { long ret; @@ -775,99 +651,6 @@ static long bch2_ioctl_disk_resize_journal(struct bch_fs *c, return ret; } -static int bch2_fsck_online_thread_fn(struct thread_with_stdio *stdio) -{ - struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); - struct bch_fs *c = thr->c; - - c->stdio_filter = current; - c->stdio = &thr->thr.stdio; - - /* - * XXX: can we figure out a way to do this without mucking with c->opts? - */ - unsigned old_fix_errors = c->opts.fix_errors; - if (opt_defined(thr->opts, fix_errors)) - c->opts.fix_errors = thr->opts.fix_errors; - else - c->opts.fix_errors = FSCK_FIX_ask; - - c->opts.fsck = true; - set_bit(BCH_FS_fsck_running, &c->flags); - - c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info; - int ret = bch2_run_online_recovery_passes(c); - - clear_bit(BCH_FS_fsck_running, &c->flags); - bch_err_fn(c, ret); - - c->stdio = NULL; - c->stdio_filter = NULL; - c->opts.fix_errors = old_fix_errors; - - up(&c->online_fsck_mutex); - bch2_ro_ref_put(c); - return ret; -} - -static const struct thread_with_stdio_ops bch2_online_fsck_ops = { - .exit = bch2_fsck_thread_exit, - .fn = bch2_fsck_online_thread_fn, -}; - -static long bch2_ioctl_fsck_online(struct bch_fs *c, - struct bch_ioctl_fsck_online arg) -{ - struct fsck_thread *thr = NULL; - long ret = 0; - - if (arg.flags) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (!bch2_ro_ref_tryget(c)) - return -EROFS; - - if (down_trylock(&c->online_fsck_mutex)) { - bch2_ro_ref_put(c); - return -EAGAIN; - } - - thr = kzalloc(sizeof(*thr), GFP_KERNEL); - if (!thr) { - ret = -ENOMEM; - goto err; - } - - thr->c = c; - thr->opts = bch2_opts_empty(); - - if (arg.opts) { - char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); - - ret = PTR_ERR_OR_ZERO(optstr) ?: - bch2_parse_mount_opts(c, &thr->opts, NULL, optstr); - if (!IS_ERR(optstr)) - kfree(optstr); - - if (ret) - goto err; - } - - ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_online_fsck_ops); -err: - if (ret < 0) { - bch_err_fn(c, ret); - if (thr) - bch2_fsck_thread_exit(&thr->thr); - up(&c->online_fsck_mutex); - bch2_ro_ref_put(c); - } - return ret; -} - #define BCH_IOCTL(_name, _argtype) \ do { \ _argtype i; \ diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c index ce8fc677bef9..23a383577d4c 100644 --- a/fs/bcachefs/checksum.c +++ b/fs/bcachefs/checksum.c @@ -2,6 +2,7 @@ #include "bcachefs.h" #include "checksum.h" #include "errcode.h" +#include "error.h" #include "super.h" #include "super-io.h" @@ -252,6 +253,10 @@ int bch2_encrypt(struct bch_fs *c, unsigned type, if (!bch2_csum_type_is_encryption(type)) return 0; + if (bch2_fs_inconsistent_on(!c->chacha20, + c, "attempting to encrypt without encryption key")) + return -BCH_ERR_no_encryption_key; + return do_encrypt(c->chacha20, nonce, data, len); } @@ -337,8 +342,9 @@ int __bch2_encrypt_bio(struct bch_fs *c, unsigned type, size_t sgl_len = 0; int ret = 0; - if (!bch2_csum_type_is_encryption(type)) - return 0; + if (bch2_fs_inconsistent_on(!c->chacha20, + c, "attempting to encrypt without encryption key")) + return -BCH_ERR_no_encryption_key; darray_init(&sgl); diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h index e40499fde9a4..43b9d71f2f2b 100644 --- a/fs/bcachefs/checksum.h +++ b/fs/bcachefs/checksum.h @@ -109,7 +109,7 @@ int bch2_enable_encryption(struct bch_fs *, bool); void bch2_fs_encryption_exit(struct bch_fs *); int bch2_fs_encryption_init(struct bch_fs *); -static inline enum bch_csum_type bch2_csum_opt_to_type(enum bch_csum_opts type, +static inline enum bch_csum_type bch2_csum_opt_to_type(enum bch_csum_opt type, bool data) { switch (type) { diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c index 1410365a8891..f99ff1819597 100644 --- a/fs/bcachefs/compress.c +++ b/fs/bcachefs/compress.c @@ -2,13 +2,33 @@ #include "bcachefs.h" #include "checksum.h" #include "compress.h" +#include "error.h" #include "extents.h" +#include "opts.h" #include "super-io.h" #include <linux/lz4.h> #include <linux/zlib.h> #include <linux/zstd.h> +static inline enum bch_compression_opts bch2_compression_type_to_opt(enum bch_compression_type type) +{ + switch (type) { + case BCH_COMPRESSION_TYPE_none: + case BCH_COMPRESSION_TYPE_incompressible: + return BCH_COMPRESSION_OPT_none; + case BCH_COMPRESSION_TYPE_lz4_old: + case BCH_COMPRESSION_TYPE_lz4: + return BCH_COMPRESSION_OPT_lz4; + case BCH_COMPRESSION_TYPE_gzip: + return BCH_COMPRESSION_OPT_gzip; + case BCH_COMPRESSION_TYPE_zstd: + return BCH_COMPRESSION_OPT_zstd; + default: + BUG(); + } +} + /* Bounce buffer: */ struct bbuf { void *b; @@ -158,6 +178,19 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, void *workspace; int ret; + enum bch_compression_opts opt = bch2_compression_type_to_opt(crc.compression_type); + mempool_t *workspace_pool = &c->compress_workspace[opt]; + if (unlikely(!mempool_initialized(workspace_pool))) { + if (fsck_err(c, compression_type_not_marked_in_sb, + "compression type %s set but not marked in superblock", + __bch2_compression_types[crc.compression_type])) + ret = bch2_check_set_has_compressed_data(c, opt); + else + ret = -BCH_ERR_compression_workspace_not_initialized; + if (ret) + goto out; + } + src_data = bio_map_or_bounce(c, src, READ); switch (crc.compression_type) { @@ -176,13 +209,13 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, .avail_out = dst_len, }; - workspace = mempool_alloc(&c->decompress_workspace, GFP_NOFS); + workspace = mempool_alloc(workspace_pool, GFP_NOFS); zlib_set_workspace(&strm, workspace); zlib_inflateInit2(&strm, -MAX_WBITS); ret = zlib_inflate(&strm, Z_FINISH); - mempool_free(workspace, &c->decompress_workspace); + mempool_free(workspace, workspace_pool); if (ret != Z_STREAM_END) goto err; @@ -195,14 +228,14 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, if (real_src_len > src_len - 4) goto err; - workspace = mempool_alloc(&c->decompress_workspace, GFP_NOFS); + workspace = mempool_alloc(workspace_pool, GFP_NOFS); ctx = zstd_init_dctx(workspace, zstd_dctx_workspace_bound()); ret = zstd_decompress_dctx(ctx, dst_data, dst_len, src_data.b + 4, real_src_len); - mempool_free(workspace, &c->decompress_workspace); + mempool_free(workspace, workspace_pool); if (ret != dst_len) goto err; @@ -212,6 +245,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src, BUG(); } ret = 0; +fsck_err: out: bio_unmap_or_unbounce(c, src_data); return ret; @@ -394,8 +428,21 @@ static unsigned __bio_compress(struct bch_fs *c, unsigned pad; int ret = 0; - BUG_ON(compression_type >= BCH_COMPRESSION_TYPE_NR); - BUG_ON(!mempool_initialized(&c->compress_workspace[compression_type])); + /* bch2_compression_decode catches unknown compression types: */ + BUG_ON(compression.type >= BCH_COMPRESSION_OPT_NR); + + mempool_t *workspace_pool = &c->compress_workspace[compression.type]; + if (unlikely(!mempool_initialized(workspace_pool))) { + if (fsck_err(c, compression_opt_not_marked_in_sb, + "compression opt %s set but not marked in superblock", + bch2_compression_opts[compression.type])) { + ret = bch2_check_set_has_compressed_data(c, compression.type); + if (ret) /* memory allocation failure, don't compress */ + return 0; + } else { + return 0; + } + } /* If it's only one block, don't bother trying to compress: */ if (src->bi_iter.bi_size <= c->opts.block_size) @@ -404,7 +451,7 @@ static unsigned __bio_compress(struct bch_fs *c, dst_data = bio_map_or_bounce(c, dst, WRITE); src_data = bio_map_or_bounce(c, src, READ); - workspace = mempool_alloc(&c->compress_workspace[compression_type], GFP_NOFS); + workspace = mempool_alloc(workspace_pool, GFP_NOFS); *src_len = src->bi_iter.bi_size; *dst_len = dst->bi_iter.bi_size; @@ -447,7 +494,7 @@ static unsigned __bio_compress(struct bch_fs *c, *src_len = round_down(*src_len, block_bytes(c)); } - mempool_free(workspace, &c->compress_workspace[compression_type]); + mempool_free(workspace, workspace_pool); if (ret) goto err; @@ -477,6 +524,9 @@ out: err: ret = BCH_COMPRESSION_TYPE_incompressible; goto out; +fsck_err: + ret = 0; + goto out; } unsigned bch2_bio_compress(struct bch_fs *c, @@ -559,7 +609,6 @@ void bch2_fs_compress_exit(struct bch_fs *c) { unsigned i; - mempool_exit(&c->decompress_workspace); for (i = 0; i < ARRAY_SIZE(c->compress_workspace); i++) mempool_exit(&c->compress_workspace[i]); mempool_exit(&c->compression_bounce[WRITE]); @@ -568,7 +617,6 @@ void bch2_fs_compress_exit(struct bch_fs *c) static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) { - size_t decompress_workspace_size = 0; ZSTD_parameters params = zstd_get_params(zstd_max_clevel(), c->opts.encoded_extent_max); @@ -576,19 +624,17 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) struct { unsigned feature; - enum bch_compression_type type; + enum bch_compression_opts type; size_t compress_workspace; - size_t decompress_workspace; } compression_types[] = { - { BCH_FEATURE_lz4, BCH_COMPRESSION_TYPE_lz4, - max_t(size_t, LZ4_MEM_COMPRESS, LZ4HC_MEM_COMPRESS), - 0 }, - { BCH_FEATURE_gzip, BCH_COMPRESSION_TYPE_gzip, - zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL), - zlib_inflate_workspacesize(), }, - { BCH_FEATURE_zstd, BCH_COMPRESSION_TYPE_zstd, - c->zstd_workspace_size, - zstd_dctx_workspace_bound() }, + { BCH_FEATURE_lz4, BCH_COMPRESSION_OPT_lz4, + max_t(size_t, LZ4_MEM_COMPRESS, LZ4HC_MEM_COMPRESS) }, + { BCH_FEATURE_gzip, BCH_COMPRESSION_OPT_gzip, + max(zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL), + zlib_inflate_workspacesize()) }, + { BCH_FEATURE_zstd, BCH_COMPRESSION_OPT_zstd, + max(c->zstd_workspace_size, + zstd_dctx_workspace_bound()) }, }, *i; bool have_compressed = false; @@ -613,9 +659,6 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) for (i = compression_types; i < compression_types + ARRAY_SIZE(compression_types); i++) { - decompress_workspace_size = - max(decompress_workspace_size, i->decompress_workspace); - if (!(features & (1 << i->feature))) continue; @@ -628,11 +671,6 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features) return -BCH_ERR_ENOMEM_compression_workspace_init; } - if (!mempool_initialized(&c->decompress_workspace) && - mempool_init_kvmalloc_pool(&c->decompress_workspace, - 1, decompress_workspace_size)) - return -BCH_ERR_ENOMEM_decompression_workspace_init; - return 0; } diff --git a/fs/bcachefs/darray.h b/fs/bcachefs/darray.h index 8f4c3f0665c4..c6151495985f 100644 --- a/fs/bcachefs/darray.h +++ b/fs/bcachefs/darray.h @@ -83,7 +83,7 @@ int __bch2_darray_resize_noprof(darray_char *, size_t, size_t, gfp_t); for (typeof(&(_d).data[0]) _i = (_d).data; _i < (_d).data + (_d).nr; _i++) #define darray_for_each_reverse(_d, _i) \ - for (typeof(&(_d).data[0]) _i = (_d).data + (_d).nr - 1; _i >= (_d).data; --_i) + for (typeof(&(_d).data[0]) _i = (_d).data + (_d).nr - 1; _i >= (_d).data && (_d).nr; --_i) #define darray_init(_d) \ do { \ diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 8e75a852b358..585214931e05 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -110,11 +110,8 @@ static void trace_move_extent_fail2(struct data_update *m, { struct bch_fs *c = m->op.c; struct bkey_s_c old = bkey_i_to_s_c(m->k.k); - const union bch_extent_entry *entry; - struct bch_extent_ptr *ptr; - struct extent_ptr_decoded p; struct printbuf buf = PRINTBUF; - unsigned i, rewrites_found = 0; + unsigned rewrites_found = 0; if (!trace_move_extent_fail_enabled()) return; @@ -122,27 +119,25 @@ static void trace_move_extent_fail2(struct data_update *m, prt_str(&buf, msg); if (insert) { - i = 0; + const union bch_extent_entry *entry; + struct bch_extent_ptr *ptr; + struct extent_ptr_decoded p; + + unsigned ptr_bit = 1; bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs_c(old), p, entry) { - if (((1U << i) & m->data_opts.rewrite_ptrs) && + if ((ptr_bit & m->data_opts.rewrite_ptrs) && (ptr = bch2_extent_has_ptr(old, p, bkey_i_to_s(insert))) && !ptr->cached) - rewrites_found |= 1U << i; - i++; + rewrites_found |= ptr_bit; + ptr_bit <<= 1; } } - prt_printf(&buf, "\nrewrite ptrs: %u%u%u%u", - (m->data_opts.rewrite_ptrs & (1 << 0)) != 0, - (m->data_opts.rewrite_ptrs & (1 << 1)) != 0, - (m->data_opts.rewrite_ptrs & (1 << 2)) != 0, - (m->data_opts.rewrite_ptrs & (1 << 3)) != 0); + prt_str(&buf, "rewrites found:\t"); + bch2_prt_u64_base2(&buf, rewrites_found); + prt_newline(&buf); - prt_printf(&buf, "\nrewrites found: %u%u%u%u", - (rewrites_found & (1 << 0)) != 0, - (rewrites_found & (1 << 1)) != 0, - (rewrites_found & (1 << 2)) != 0, - (rewrites_found & (1 << 3)) != 0); + bch2_data_update_opts_to_text(&buf, c, &m->op.opts, &m->data_opts); prt_str(&buf, "\nold: "); bch2_bkey_val_to_text(&buf, c, old); @@ -194,7 +189,7 @@ static int __bch2_data_update_index_update(struct btree_trans *trans, struct bpos next_pos; bool should_check_enospc; s64 i_sectors_delta = 0, disk_sectors_delta = 0; - unsigned rewrites_found = 0, durability, i; + unsigned rewrites_found = 0, durability, ptr_bit; bch2_trans_begin(trans); @@ -231,16 +226,16 @@ static int __bch2_data_update_index_update(struct btree_trans *trans, * * Fist, drop rewrite_ptrs from @new: */ - i = 0; + ptr_bit = 1; bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs_c(old), p, entry_c) { - if (((1U << i) & m->data_opts.rewrite_ptrs) && + if ((ptr_bit & m->data_opts.rewrite_ptrs) && (ptr = bch2_extent_has_ptr(old, p, bkey_i_to_s(insert))) && !ptr->cached) { bch2_extent_ptr_set_cached(c, &m->op.opts, bkey_i_to_s(insert), ptr); - rewrites_found |= 1U << i; + rewrites_found |= ptr_bit; } - i++; + ptr_bit <<= 1; } if (m->data_opts.rewrite_ptrs && @@ -323,8 +318,11 @@ restart_drop_extra_replicas: * it's been hard to reproduce, so this should give us some more * information when it does occur: */ - int invalid = bch2_bkey_validate(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), - BCH_VALIDATE_commit); + int invalid = bch2_bkey_validate(c, bkey_i_to_s_c(insert), + (struct bkey_validate_context) { + .btree = m->btree_id, + .flags = BCH_VALIDATE_commit, + }); if (invalid) { struct printbuf buf = PRINTBUF; @@ -362,7 +360,7 @@ restart_drop_extra_replicas: k.k->p, bkey_start_pos(&insert->k)) ?: bch2_insert_snapshot_whiteouts(trans, m->btree_id, k.k->p, insert->k.p) ?: - bch2_bkey_set_needs_rebalance(c, insert, &op->opts) ?: + bch2_bkey_set_needs_rebalance(c, &op->opts, insert) ?: bch2_trans_update(trans, &iter, insert, BTREE_UPDATE_internal_snapshot_node) ?: bch2_trans_commit(trans, &op->res, @@ -540,7 +538,7 @@ void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c, prt_newline(out); prt_str(out, "compression:\t"); - bch2_compression_opt_to_text(out, background_compression(*io_opts)); + bch2_compression_opt_to_text(out, io_opts->background_compression); prt_newline(out); prt_str(out, "opts.replicas:\t"); @@ -614,7 +612,7 @@ int bch2_data_update_init(struct btree_trans *trans, struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; - unsigned i, reserve_sectors = k.k->size * data_opts.extra_replicas; + unsigned reserve_sectors = k.k->size * data_opts.extra_replicas; int ret = 0; /* @@ -622,7 +620,7 @@ int bch2_data_update_init(struct btree_trans *trans, * and we have to check for this because we go rw before repairing the * snapshots table - just skip it, we can move it later. */ - if (unlikely(k.k->p.snapshot && !bch2_snapshot_equiv(c, k.k->p.snapshot))) + if (unlikely(k.k->p.snapshot && !bch2_snapshot_exists(c, k.k->p.snapshot))) return -BCH_ERR_data_update_done; if (!bkey_get_dev_refs(c, k)) @@ -652,22 +650,22 @@ int bch2_data_update_init(struct btree_trans *trans, BCH_WRITE_DATA_ENCODED| BCH_WRITE_MOVE| m->data_opts.write_flags; - m->op.compression_opt = background_compression(io_opts); + m->op.compression_opt = io_opts.background_compression; m->op.watermark = m->data_opts.btree_insert_flags & BCH_WATERMARK_MASK; unsigned durability_have = 0, durability_removing = 0; - i = 0; + unsigned ptr_bit = 1; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { if (!p.ptr.cached) { rcu_read_lock(); - if (BIT(i) & m->data_opts.rewrite_ptrs) { + if (ptr_bit & m->data_opts.rewrite_ptrs) { if (crc_is_compressed(p.crc)) reserve_sectors += k.k->size; m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p); durability_removing += bch2_extent_ptr_desired_durability(c, &p); - } else if (!(BIT(i) & m->data_opts.kill_ptrs)) { + } else if (!(ptr_bit & m->data_opts.kill_ptrs)) { bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev); durability_have += bch2_extent_ptr_durability(c, &p); } @@ -687,7 +685,7 @@ int bch2_data_update_init(struct btree_trans *trans, if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) m->op.incompressible = true; - i++; + ptr_bit <<= 1; } unsigned durability_required = max(0, (int) (io_opts.data_replicas - durability_have)); @@ -750,14 +748,14 @@ out: void bch2_data_update_opts_normalize(struct bkey_s_c k, struct data_update_opts *opts) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - unsigned i = 0; + unsigned ptr_bit = 1; bkey_for_each_ptr(ptrs, ptr) { - if ((opts->rewrite_ptrs & (1U << i)) && ptr->cached) { - opts->kill_ptrs |= 1U << i; - opts->rewrite_ptrs ^= 1U << i; + if ((opts->rewrite_ptrs & ptr_bit) && ptr->cached) { + opts->kill_ptrs |= ptr_bit; + opts->rewrite_ptrs ^= ptr_bit; } - i++; + ptr_bit <<= 1; } } diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index 45aec1afdb0e..b5de52a50d10 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -472,7 +472,9 @@ static void bch2_cached_btree_node_to_text(struct printbuf *out, struct bch_fs * if (!out->nr_tabstops) printbuf_tabstop_push(out, 32); - prt_printf(out, "%px btree=%s l=%u\n", b, bch2_btree_id_str(b->c.btree_id), b->c.level); + prt_printf(out, "%px ", b); + bch2_btree_id_level_to_text(out, b->c.btree_id, b->c.level); + prt_printf(out, "\n"); printbuf_indent_add(out, 2); diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index faffc98d5605..600eee936f13 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -101,7 +101,7 @@ const struct bch_hash_desc bch2_dirent_hash_desc = { }; int bch2_dirent_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); struct qstr d_name = bch2_dirent_get_name(d); @@ -120,7 +120,7 @@ int bch2_dirent_validate(struct bch_fs *c, struct bkey_s_c k, * Check new keys don't exceed the max length * (older keys may be larger.) */ - bkey_fsck_err_on((flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, + bkey_fsck_err_on((from.flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, c, dirent_name_too_long, "dirent name too big (%u > %u)", d_name.len, BCH_NAME_MAX); @@ -266,7 +266,7 @@ int bch2_dirent_read_target(struct btree_trans *trans, subvol_inum dir, } else { target->subvol = le32_to_cpu(d.v->d_child_subvol); - ret = bch2_subvolume_get(trans, target->subvol, true, BTREE_ITER_cached, &s); + ret = bch2_subvolume_get(trans, target->subvol, true, &s); target->inum = le64_to_cpu(s.inode); } @@ -500,7 +500,7 @@ int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 subvol, u32 struct bkey_s_c k; int ret; - for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents, + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, SPOS(dir, 0, snapshot), POS(dir, U64_MAX), 0, k, ret) if (k.k->type == KEY_TYPE_dirent) { @@ -549,7 +549,7 @@ int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx) bch2_bkey_buf_init(&sk); int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_dirents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_dirents, POS(inum.inum, ctx->pos), POS(inum.inum, U64_MAX), inum.subvol, 0, k, ({ diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index 53ad99666022..a633f83c1ac7 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -4,10 +4,10 @@ #include "str_hash.h" -enum bch_validate_flags; extern const struct bch_hash_desc bch2_dirent_hash_desc; -int bch2_dirent_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_dirent_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_dirent_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_dirent ((struct bkey_ops) { \ @@ -31,6 +31,11 @@ static inline unsigned dirent_val_u64s(unsigned len) sizeof(u64)); } +static inline unsigned int dirent_occupied_size(const struct qstr *name) +{ + return (BKEY_U64s + dirent_val_u64s(name->len)) * sizeof(u64); +} + int bch2_dirent_read_target(struct btree_trans *, subvol_inum, struct bkey_s_c_dirent, subvol_inum *); diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index 07eb8fa1b026..b32e91ba8be8 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -79,6 +79,8 @@ static inline void accounting_key_init(struct bkey_i *k, struct disk_accounting_ memcpy_u64s_small(acc->v.d, d, nr); } +static int bch2_accounting_update_sb_one(struct bch_fs *, struct bpos); + int bch2_disk_accounting_mod(struct btree_trans *trans, struct disk_accounting_pos *k, s64 *d, unsigned nr, bool gc) @@ -96,9 +98,16 @@ int bch2_disk_accounting_mod(struct btree_trans *trans, accounting_key_init(&k_i.k, k, d, nr); - return likely(!gc) - ? bch2_trans_update_buffered(trans, BTREE_ID_accounting, &k_i.k) - : bch2_accounting_mem_add(trans, bkey_i_to_s_c_accounting(&k_i.k), true); + if (unlikely(gc)) { + int ret = bch2_accounting_mem_add(trans, bkey_i_to_s_c_accounting(&k_i.k), true); + if (ret == -BCH_ERR_btree_insert_need_mark_replicas) + ret = drop_locks_do(trans, + bch2_accounting_update_sb_one(trans->c, disk_accounting_pos_to_bpos(k))) ?: + bch2_accounting_mem_add(trans, bkey_i_to_s_c_accounting(&k_i.k), true); + return ret; + } else { + return bch2_trans_update_buffered(trans, BTREE_ID_accounting, &k_i.k); + } } int bch2_mod_dev_cached_sectors(struct btree_trans *trans, @@ -127,14 +136,15 @@ static inline bool is_zero(char *start, char *end) #define field_end(p, member) (((void *) (&p.member)) + sizeof(p.member)) int bch2_accounting_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, k.k->p); void *end = &acc_k + 1; int ret = 0; - bkey_fsck_err_on(bversion_zero(k.k->bversion), + bkey_fsck_err_on((from.flags & BCH_VALIDATE_commit) && + bversion_zero(k.k->bversion), c, accounting_key_version_0, "accounting key with version=0"); @@ -217,7 +227,8 @@ void bch2_accounting_key_to_text(struct printbuf *out, struct disk_accounting_po prt_printf(out, "id=%u", k->snapshot.id); break; case BCH_DISK_ACCOUNTING_btree: - prt_printf(out, "btree=%s", bch2_btree_id_str(k->btree.id)); + prt_str(out, "btree="); + bch2_btree_id_to_text(out, k->btree.id); break; } } @@ -243,10 +254,10 @@ void bch2_accounting_swab(struct bkey_s k) } static inline void __accounting_to_replicas(struct bch_replicas_entry_v1 *r, - struct disk_accounting_pos acc) + struct disk_accounting_pos *acc) { - unsafe_memcpy(r, &acc.replicas, - replicas_entry_bytes(&acc.replicas), + unsafe_memcpy(r, &acc->replicas, + replicas_entry_bytes(&acc->replicas), "variable length struct"); } @@ -257,7 +268,7 @@ static inline bool accounting_to_replicas(struct bch_replicas_entry_v1 *r, struc switch (acc_k.type) { case BCH_DISK_ACCOUNTING_replicas: - __accounting_to_replicas(r, acc_k); + __accounting_to_replicas(r, &acc_k); return true; default: return false; @@ -322,6 +333,14 @@ static int __bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accoun eytzinger0_sort(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), accounting_pos_cmp, NULL); + + if (trace_accounting_mem_insert_enabled()) { + struct printbuf buf = PRINTBUF; + + bch2_accounting_to_text(&buf, c, a.s_c); + trace_accounting_mem_insert(c, buf.buf); + printbuf_exit(&buf); + } return 0; err: free_percpu(n.v[1]); @@ -461,32 +480,6 @@ int bch2_fs_accounting_read(struct bch_fs *c, darray_char *out_buf, unsigned acc return ret; } -void bch2_fs_accounting_to_text(struct printbuf *out, struct bch_fs *c) -{ - struct bch_accounting_mem *acc = &c->accounting; - - percpu_down_read(&c->mark_lock); - out->atomic++; - - eytzinger0_for_each(i, acc->k.nr) { - struct disk_accounting_pos acc_k; - bpos_to_disk_accounting_pos(&acc_k, acc->k.data[i].pos); - - bch2_accounting_key_to_text(out, &acc_k); - - u64 v[BCH_ACCOUNTING_MAX_COUNTERS]; - bch2_accounting_mem_read_counters(acc, i, v, ARRAY_SIZE(v), false); - - prt_str(out, ":"); - for (unsigned j = 0; j < acc->k.data[i].nr_counters; j++) - prt_printf(out, " %llu", v[j]); - prt_newline(out); - } - - --out->atomic; - percpu_up_read(&c->mark_lock); -} - static void bch2_accounting_free_counters(struct bch_accounting_mem *acc, bool gc) { darray_for_each(acc->k, e) { @@ -625,7 +618,7 @@ static int bch2_disk_accounting_validate_late(struct btree_trans *trans, switch (acc.type) { case BCH_DISK_ACCOUNTING_replicas: { struct bch_replicas_padded r; - __accounting_to_replicas(&r.e, acc); + __accounting_to_replicas(&r.e, &acc); for (unsigned i = 0; i < r.e.nr_devs; i++) if (r.e.devs[i] != BCH_SB_MEMBER_INVALID && @@ -699,11 +692,45 @@ int bch2_accounting_read(struct bch_fs *c) struct btree_trans *trans = bch2_trans_get(c); struct printbuf buf = PRINTBUF; - int ret = for_each_btree_key(trans, iter, - BTREE_ID_accounting, POS_MIN, + /* + * We might run more than once if we rewind to start topology repair or + * btree node scan - and those might cause us to get different results, + * so we can't just skip if we've already run. + * + * Instead, zero out any accounting we have: + */ + percpu_down_write(&c->mark_lock); + darray_for_each(acc->k, e) + percpu_memset(e->v[0], 0, sizeof(u64) * e->nr_counters); + for_each_member_device(c, ca) + percpu_memset(ca->usage, 0, sizeof(*ca->usage)); + percpu_memset(c->usage, 0, sizeof(*c->usage)); + percpu_up_write(&c->mark_lock); + + struct btree_iter iter; + bch2_trans_iter_init(trans, &iter, BTREE_ID_accounting, POS_MIN, + BTREE_ITER_prefetch|BTREE_ITER_all_snapshots); + iter.flags &= ~BTREE_ITER_with_journal; + int ret = for_each_btree_key_continue(trans, iter, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({ struct bkey u; struct bkey_s_c k = bch2_btree_path_peek_slot_exact(btree_iter_path(trans, &iter), &u); + + if (k.k->type != KEY_TYPE_accounting) + continue; + + struct disk_accounting_pos acc_k; + bpos_to_disk_accounting_pos(&acc_k, k.k->p); + + if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) + break; + + if (!bch2_accounting_is_mem(acc_k)) { + struct disk_accounting_pos next = { .type = acc_k.type + 1 }; + bch2_btree_iter_set_pos(&iter, disk_accounting_pos_to_bpos(&next)); + continue; + } + accounting_read_key(trans, k); })); if (ret) @@ -715,6 +742,12 @@ int bch2_accounting_read(struct bch_fs *c) darray_for_each(*keys, i) { if (i->k->k.type == KEY_TYPE_accounting) { + struct disk_accounting_pos acc_k; + bpos_to_disk_accounting_pos(&acc_k, i->k->k.p); + + if (!bch2_accounting_is_mem(acc_k)) + continue; + struct bkey_s_c k = bkey_i_to_s_c(i->k); unsigned idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), @@ -748,15 +781,16 @@ int bch2_accounting_read(struct bch_fs *c) keys->gap = keys->nr = dst - keys->data; percpu_down_write(&c->mark_lock); - unsigned i = 0; - while (i < acc->k.nr) { - unsigned idx = inorder_to_eytzinger0(i, acc->k.nr); + darray_for_each_reverse(acc->k, i) { struct disk_accounting_pos acc_k; - bpos_to_disk_accounting_pos(&acc_k, acc->k.data[idx].pos); + bpos_to_disk_accounting_pos(&acc_k, i->pos); u64 v[BCH_ACCOUNTING_MAX_COUNTERS]; - bch2_accounting_mem_read_counters(acc, idx, v, ARRAY_SIZE(v), false); + memset(v, 0, sizeof(v)); + + for (unsigned j = 0; j < i->nr_counters; j++) + v[j] = percpu_u64_get(i->v[0] + j); /* * If the entry counters are zeroed, it should be treated as @@ -765,26 +799,25 @@ int bch2_accounting_read(struct bch_fs *c) * Remove it, so that if it's re-added it gets re-marked in the * superblock: */ - ret = bch2_is_zero(v, sizeof(v[0]) * acc->k.data[idx].nr_counters) + ret = bch2_is_zero(v, sizeof(v[0]) * i->nr_counters) ? -BCH_ERR_remove_disk_accounting_entry - : bch2_disk_accounting_validate_late(trans, acc_k, - v, acc->k.data[idx].nr_counters); + : bch2_disk_accounting_validate_late(trans, acc_k, v, i->nr_counters); if (ret == -BCH_ERR_remove_disk_accounting_entry) { - free_percpu(acc->k.data[idx].v[0]); - free_percpu(acc->k.data[idx].v[1]); - darray_remove_item(&acc->k, &acc->k.data[idx]); - eytzinger0_sort(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), - accounting_pos_cmp, NULL); + free_percpu(i->v[0]); + free_percpu(i->v[1]); + darray_remove_item(&acc->k, i); ret = 0; continue; } if (ret) goto fsck_err; - i++; } + eytzinger0_sort(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), + accounting_pos_cmp, NULL); + preempt_disable(); struct bch_fs_usage_base *usage = this_cpu_ptr(c->usage); @@ -804,7 +837,7 @@ int bch2_accounting_read(struct bch_fs *c) break; case BCH_DISK_ACCOUNTING_dev_data_type: rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, k.dev_data_type.dev); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, k.dev_data_type.dev); if (ca) { struct bch_dev_usage_type __percpu *d = &ca->usage->d[k.dev_data_type.data_type]; percpu_u64_set(&d->buckets, v[0]); @@ -881,10 +914,13 @@ void bch2_verify_accounting_clean(struct bch_fs *c) bpos_to_disk_accounting_pos(&acc_k, k.k->p); if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR) - continue; + break; - if (acc_k.type == BCH_DISK_ACCOUNTING_inum) + if (!bch2_accounting_is_mem(acc_k)) { + struct disk_accounting_pos next = { .type = acc_k.type + 1 }; + bch2_btree_iter_set_pos(&iter, disk_accounting_pos_to_bpos(&next)); continue; + } bch2_accounting_mem_read(c, k.k->p, v, nr); @@ -910,7 +946,7 @@ void bch2_verify_accounting_clean(struct bch_fs *c) break; case BCH_DISK_ACCOUNTING_dev_data_type: { rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev); if (!ca) { rcu_read_unlock(); continue; diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index 4ea6c8a092bc..5360cbb3ec29 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -2,6 +2,7 @@ #ifndef _BCACHEFS_DISK_ACCOUNTING_H #define _BCACHEFS_DISK_ACCOUNTING_H +#include "btree_update.h" #include "eytzinger.h" #include "sb-members.h" @@ -62,27 +63,32 @@ static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage static inline void bpos_to_disk_accounting_pos(struct disk_accounting_pos *acc, struct bpos p) { - acc->_pad = p; + BUILD_BUG_ON(sizeof(*acc) != sizeof(p)); + #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - bch2_bpos_swab(&acc->_pad); + acc->_pad = p; +#else + memcpy_swab(acc, &p, sizeof(p)); #endif } -static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *k) +static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *acc) { - struct bpos ret = k->_pad; - + struct bpos p; #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - bch2_bpos_swab(&ret); + p = acc->_pad; +#else + memcpy_swab(&p, acc, sizeof(p)); #endif - return ret; + return p; } int bch2_disk_accounting_mod(struct btree_trans *, struct disk_accounting_pos *, s64 *, unsigned, bool); int bch2_mod_dev_cached_sectors(struct btree_trans *, unsigned, s64, bool); -int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_accounting_key_to_text(struct printbuf *, struct disk_accounting_pos *); void bch2_accounting_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_accounting_swab(struct bkey_s); @@ -112,6 +118,12 @@ enum bch_accounting_mode { int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode); void bch2_accounting_mem_gc(struct bch_fs *); +static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc) +{ + return acc.type < BCH_DISK_ACCOUNTING_TYPE_NR && + acc.type != BCH_DISK_ACCOUNTING_inum; +} + /* * Update in memory counters so they match the btree update we're doing; called * from transaction commit path @@ -126,9 +138,10 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, bpos_to_disk_accounting_pos(&acc_k, a.k->p); bool gc = mode == BCH_ACCOUNTING_gc; - EBUG_ON(gc && !acc->gc_running); + if (gc && !acc->gc_running) + return 0; - if (acc_k.type == BCH_DISK_ACCOUNTING_inum) + if (!bch2_accounting_is_mem(acc_k)) return 0; if (mode == BCH_ACCOUNTING_normal) { @@ -141,7 +154,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, break; case BCH_DISK_ACCOUNTING_dev_data_type: rcu_read_lock(); - struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev); + struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev); if (ca) { this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]); this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]); @@ -204,9 +217,45 @@ static inline void bch2_accounting_mem_read(struct bch_fs *c, struct bpos p, bch2_accounting_mem_read_counters(acc, idx, v, nr, false); } +static inline struct bversion journal_pos_to_bversion(struct journal_res *res, unsigned offset) +{ + EBUG_ON(!res->ref); + + return (struct bversion) { + .hi = res->seq >> 32, + .lo = (res->seq << 32) | (res->offset + offset), + }; +} + +static inline int bch2_accounting_trans_commit_hook(struct btree_trans *trans, + struct bkey_i_accounting *a, + unsigned commit_flags) +{ + a->k.bversion = journal_pos_to_bversion(&trans->journal_res, + (u64 *) a - (u64 *) trans->journal_entries); + + EBUG_ON(bversion_zero(a->k.bversion)); + + return likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply)) + ? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal) + : 0; +} + +static inline void bch2_accounting_trans_commit_revert(struct btree_trans *trans, + struct bkey_i_accounting *a_i, + unsigned commit_flags) +{ + if (likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { + struct bkey_s_accounting a = accounting_i_to_s(a_i); + + bch2_accounting_neg(a); + bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); + bch2_accounting_neg(a); + } +} + int bch2_fs_replicas_usage_read(struct bch_fs *, darray_char *); int bch2_fs_accounting_read(struct bch_fs *, darray_char *, unsigned); -void bch2_fs_accounting_to_text(struct printbuf *, struct bch_fs *); int bch2_gc_accounting_start(struct bch_fs *); int bch2_gc_accounting_done(struct bch_fs *); diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 6094afb0c6be..d2a5e76e6479 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -26,6 +26,7 @@ #include "util.h" #include <linux/sort.h> +#include <linux/string_choices.h> #ifdef __KERNEL__ @@ -109,7 +110,7 @@ struct ec_bio { /* Stripes btree keys: */ int bch2_stripe_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { const struct bch_stripe *s = bkey_s_c_to_stripe(k).v; int ret = 0; @@ -129,7 +130,7 @@ int bch2_stripe_validate(struct bch_fs *c, struct bkey_s_c k, "invalid csum granularity (%u >= 64)", s->csum_granularity_bits); - ret = bch2_bkey_ptrs_validate(c, k, flags); + ret = bch2_bkey_ptrs_validate(c, k, from); fsck_err: return ret; } @@ -304,13 +305,12 @@ static int mark_stripe_bucket(struct btree_trans *trans, } if (flags & BTREE_TRIGGER_gc) { - percpu_down_read(&c->mark_lock); struct bucket *g = gc_bucket(ca, bucket.offset); if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n %s", ptr->dev, (bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) { ret = -BCH_ERR_mark_stripe; - goto err_unlock; + goto err; } bucket_lock(g); @@ -318,8 +318,7 @@ static int mark_stripe_bucket(struct btree_trans *trans, ret = __mark_stripe_bucket(trans, ca, s, ptr_idx, deleting, bucket, &new, flags); alloc_to_bucket(g, new); bucket_unlock(g); -err_unlock: - percpu_up_read(&c->mark_lock); + if (!ret) ret = bch2_alloc_key_to_dev_counters(trans, ca, &old, &new, flags); } @@ -732,7 +731,7 @@ static void ec_block_endio(struct bio *bio) ? BCH_MEMBER_ERROR_write : BCH_MEMBER_ERROR_read, "erasure coding %s error: %s", - bio_data_dir(bio) ? "write" : "read", + str_write_read(bio_data_dir(bio)), bch2_blk_status_to_str(bio->bi_status))) clear_bit(ec_bio->idx, ec_bio->buf->valid); @@ -909,7 +908,7 @@ err: bch2_bkey_val_to_text(&msgbuf, c, orig_k); bch_err_ratelimited(c, "error doing reconstruct read: %s\n %s", msg, msgbuf.buf); - printbuf_exit(&msgbuf);; + printbuf_exit(&msgbuf); ret = -BCH_ERR_stripe_reconstruct; goto out; } @@ -1266,11 +1265,11 @@ static int ec_stripe_update_extent(struct btree_trans *trans, struct bch_dev *ca, struct bpos bucket, u8 gen, struct ec_stripe_buf *s, - struct bpos *bp_pos) + struct bkey_s_c_backpointer bp, + struct bkey_buf *last_flushed) { struct bch_stripe *v = &bkey_i_to_stripe(&s->key)->v; struct bch_fs *c = trans->c; - struct bch_backpointer bp; struct btree_iter iter; struct bkey_s_c k; const struct bch_extent_ptr *ptr_c; @@ -1279,33 +1278,26 @@ static int ec_stripe_update_extent(struct btree_trans *trans, struct bkey_i *n; int ret, dev, block; - ret = bch2_get_next_backpointer(trans, ca, bucket, gen, - bp_pos, &bp, BTREE_ITER_cached); - if (ret) - return ret; - if (bpos_eq(*bp_pos, SPOS_MAX)) - return 0; - - if (bp.level) { + if (bp.v->level) { struct printbuf buf = PRINTBUF; struct btree_iter node_iter; struct btree *b; - b = bch2_backpointer_get_node(trans, &node_iter, *bp_pos, bp); + b = bch2_backpointer_get_node(trans, bp, &node_iter, last_flushed); bch2_trans_iter_exit(trans, &node_iter); if (!b) return 0; prt_printf(&buf, "found btree node in erasure coded bucket: b=%px\n", b); - bch2_backpointer_to_text(&buf, &bp); + bch2_bkey_val_to_text(&buf, c, bp.s_c); bch2_fs_inconsistent(c, "%s", buf.buf); printbuf_exit(&buf); return -EIO; } - k = bch2_backpointer_get_key(trans, &iter, *bp_pos, bp, BTREE_ITER_intent); + k = bch2_backpointer_get_key(trans, bp, &iter, BTREE_ITER_intent, last_flushed); ret = bkey_err(k); if (ret) return ret; @@ -1364,7 +1356,6 @@ static int ec_stripe_update_bucket(struct btree_trans *trans, struct ec_stripe_b struct bch_fs *c = trans->c; struct bch_stripe *v = &bkey_i_to_stripe(&s->key)->v; struct bch_extent_ptr ptr = v->ptrs[block]; - struct bpos bp_pos = POS_MIN; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, ptr.dev); @@ -1373,19 +1364,27 @@ static int ec_stripe_update_bucket(struct btree_trans *trans, struct ec_stripe_b struct bpos bucket_pos = PTR_BUCKET_POS(ca, &ptr); - while (1) { - ret = commit_do(trans, NULL, NULL, - BCH_TRANS_COMMIT_no_check_rw| - BCH_TRANS_COMMIT_no_enospc, - ec_stripe_update_extent(trans, ca, bucket_pos, ptr.gen, s, &bp_pos)); - if (ret) - break; - if (bkey_eq(bp_pos, POS_MAX)) + struct bkey_buf last_flushed; + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); + + ret = for_each_btree_key_max_commit(trans, bp_iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, bucket_pos), + bucket_pos_to_bp_end(ca, bucket_pos), 0, bp_k, + NULL, NULL, + BCH_TRANS_COMMIT_no_check_rw| + BCH_TRANS_COMMIT_no_enospc, ({ + if (bkey_ge(bp_k.k->p, bucket_pos_to_bp(ca, bpos_nosnap_successor(bucket_pos), 0))) break; - bp_pos = bpos_nosnap_successor(bp_pos); - } + if (bp_k.k->type != KEY_TYPE_backpointer) + continue; + ec_stripe_update_extent(trans, ca, bucket_pos, ptr.gen, s, + bkey_s_c_to_backpointer(bp_k), &last_flushed); + })); + + bch2_bkey_buf_exit(&last_flushed, c); bch2_dev_put(ca); return ret; } @@ -1707,7 +1706,7 @@ static void ec_stripe_key_init(struct bch_fs *c, set_bkey_val_u64s(&s->k, u64s); } -static int ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) +static struct ec_stripe_new *ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) { struct ec_stripe_new *s; @@ -1715,7 +1714,7 @@ static int ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) - return -BCH_ERR_ENOMEM_ec_new_stripe_alloc; + return NULL; mutex_init(&s->lock); closure_init(&s->iodone, NULL); @@ -1730,10 +1729,7 @@ static int ec_new_stripe_alloc(struct bch_fs *c, struct ec_stripe_head *h) ec_stripe_key_init(c, &s->new_stripe.key, s->nr_data, s->nr_parity, h->blocksize, h->disk_label); - - h->s = s; - h->nr_created++; - return 0; + return s; } static void ec_stripe_head_devs_update(struct bch_fs *c, struct ec_stripe_head *h) @@ -1878,25 +1874,26 @@ err: return h; } -static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_head *h, +static int new_stripe_alloc_buckets(struct btree_trans *trans, + struct ec_stripe_head *h, struct ec_stripe_new *s, enum bch_watermark watermark, struct closure *cl) { struct bch_fs *c = trans->c; struct bch_devs_mask devs = h->devs; struct open_bucket *ob; struct open_buckets buckets; - struct bch_stripe *v = &bkey_i_to_stripe(&h->s->new_stripe.key)->v; + struct bch_stripe *v = &bkey_i_to_stripe(&s->new_stripe.key)->v; unsigned i, j, nr_have_parity = 0, nr_have_data = 0; bool have_cache = true; int ret = 0; - BUG_ON(v->nr_blocks != h->s->nr_data + h->s->nr_parity); - BUG_ON(v->nr_redundant != h->s->nr_parity); + BUG_ON(v->nr_blocks != s->nr_data + s->nr_parity); + BUG_ON(v->nr_redundant != s->nr_parity); /* * We bypass the sector allocator which normally does this: */ bitmap_and(devs.d, devs.d, c->rw_devs[BCH_DATA_user].d, BCH_SB_MEMBERS_MAX); - for_each_set_bit(i, h->s->blocks_gotten, v->nr_blocks) { + for_each_set_bit(i, s->blocks_gotten, v->nr_blocks) { /* * Note: we don't yet repair invalid blocks (failed/removed * devices) when reusing stripes - we still need a codepath to @@ -1906,21 +1903,21 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ if (v->ptrs[i].dev != BCH_SB_MEMBER_INVALID) __clear_bit(v->ptrs[i].dev, devs.d); - if (i < h->s->nr_data) + if (i < s->nr_data) nr_have_data++; else nr_have_parity++; } - BUG_ON(nr_have_data > h->s->nr_data); - BUG_ON(nr_have_parity > h->s->nr_parity); + BUG_ON(nr_have_data > s->nr_data); + BUG_ON(nr_have_parity > s->nr_parity); buckets.nr = 0; - if (nr_have_parity < h->s->nr_parity) { + if (nr_have_parity < s->nr_parity) { ret = bch2_bucket_alloc_set_trans(trans, &buckets, &h->parity_stripe, &devs, - h->s->nr_parity, + s->nr_parity, &nr_have_parity, &have_cache, 0, BCH_DATA_parity, @@ -1928,14 +1925,14 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ cl); open_bucket_for_each(c, &buckets, ob, i) { - j = find_next_zero_bit(h->s->blocks_gotten, - h->s->nr_data + h->s->nr_parity, - h->s->nr_data); - BUG_ON(j >= h->s->nr_data + h->s->nr_parity); + j = find_next_zero_bit(s->blocks_gotten, + s->nr_data + s->nr_parity, + s->nr_data); + BUG_ON(j >= s->nr_data + s->nr_parity); - h->s->blocks[j] = buckets.v[i]; + s->blocks[j] = buckets.v[i]; v->ptrs[j] = bch2_ob_ptr(c, ob); - __set_bit(j, h->s->blocks_gotten); + __set_bit(j, s->blocks_gotten); } if (ret) @@ -1943,11 +1940,11 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ } buckets.nr = 0; - if (nr_have_data < h->s->nr_data) { + if (nr_have_data < s->nr_data) { ret = bch2_bucket_alloc_set_trans(trans, &buckets, &h->block_stripe, &devs, - h->s->nr_data, + s->nr_data, &nr_have_data, &have_cache, 0, BCH_DATA_user, @@ -1955,13 +1952,13 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ cl); open_bucket_for_each(c, &buckets, ob, i) { - j = find_next_zero_bit(h->s->blocks_gotten, - h->s->nr_data, 0); - BUG_ON(j >= h->s->nr_data); + j = find_next_zero_bit(s->blocks_gotten, + s->nr_data, 0); + BUG_ON(j >= s->nr_data); - h->s->blocks[j] = buckets.v[i]; + s->blocks[j] = buckets.v[i]; v->ptrs[j] = bch2_ob_ptr(c, ob); - __set_bit(j, h->s->blocks_gotten); + __set_bit(j, s->blocks_gotten); } if (ret) @@ -2007,73 +2004,78 @@ static s64 get_existing_stripe(struct bch_fs *c, return ret; } -static int __bch2_ec_stripe_head_reuse(struct btree_trans *trans, struct ec_stripe_head *h) +static int init_new_stripe_from_existing(struct bch_fs *c, struct ec_stripe_new *s) { - struct bch_fs *c = trans->c; - struct bch_stripe *new_v = &bkey_i_to_stripe(&h->s->new_stripe.key)->v; - struct bch_stripe *existing_v; + struct bch_stripe *new_v = &bkey_i_to_stripe(&s->new_stripe.key)->v; + struct bch_stripe *existing_v = &bkey_i_to_stripe(&s->existing_stripe.key)->v; unsigned i; - s64 idx; - int ret; - - /* - * If we can't allocate a new stripe, and there's no stripes with empty - * blocks for us to reuse, that means we have to wait on copygc: - */ - idx = get_existing_stripe(c, h); - if (idx < 0) - return -BCH_ERR_stripe_alloc_blocked; - - ret = get_stripe_key_trans(trans, idx, &h->s->existing_stripe); - bch2_fs_fatal_err_on(ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart), c, - "reading stripe key: %s", bch2_err_str(ret)); - if (ret) { - bch2_stripe_close(c, h->s); - return ret; - } - existing_v = &bkey_i_to_stripe(&h->s->existing_stripe.key)->v; - - BUG_ON(existing_v->nr_redundant != h->s->nr_parity); - h->s->nr_data = existing_v->nr_blocks - + BUG_ON(existing_v->nr_redundant != s->nr_parity); + s->nr_data = existing_v->nr_blocks - existing_v->nr_redundant; - ret = ec_stripe_buf_init(&h->s->existing_stripe, 0, h->blocksize); + int ret = ec_stripe_buf_init(&s->existing_stripe, 0, le16_to_cpu(existing_v->sectors)); if (ret) { - bch2_stripe_close(c, h->s); + bch2_stripe_close(c, s); return ret; } - BUG_ON(h->s->existing_stripe.size != h->blocksize); - BUG_ON(h->s->existing_stripe.size != le16_to_cpu(existing_v->sectors)); + BUG_ON(s->existing_stripe.size != le16_to_cpu(existing_v->sectors)); /* * Free buckets we initially allocated - they might conflict with * blocks from the stripe we're reusing: */ - for_each_set_bit(i, h->s->blocks_gotten, new_v->nr_blocks) { - bch2_open_bucket_put(c, c->open_buckets + h->s->blocks[i]); - h->s->blocks[i] = 0; + for_each_set_bit(i, s->blocks_gotten, new_v->nr_blocks) { + bch2_open_bucket_put(c, c->open_buckets + s->blocks[i]); + s->blocks[i] = 0; } - memset(h->s->blocks_gotten, 0, sizeof(h->s->blocks_gotten)); - memset(h->s->blocks_allocated, 0, sizeof(h->s->blocks_allocated)); + memset(s->blocks_gotten, 0, sizeof(s->blocks_gotten)); + memset(s->blocks_allocated, 0, sizeof(s->blocks_allocated)); - for (i = 0; i < existing_v->nr_blocks; i++) { + for (unsigned i = 0; i < existing_v->nr_blocks; i++) { if (stripe_blockcount_get(existing_v, i)) { - __set_bit(i, h->s->blocks_gotten); - __set_bit(i, h->s->blocks_allocated); + __set_bit(i, s->blocks_gotten); + __set_bit(i, s->blocks_allocated); } - ec_block_io(c, &h->s->existing_stripe, READ, i, &h->s->iodone); + ec_block_io(c, &s->existing_stripe, READ, i, &s->iodone); } - bkey_copy(&h->s->new_stripe.key, &h->s->existing_stripe.key); - h->s->have_existing_stripe = true; + bkey_copy(&s->new_stripe.key, &s->existing_stripe.key); + s->have_existing_stripe = true; return 0; } -static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_stripe_head *h) +static int __bch2_ec_stripe_head_reuse(struct btree_trans *trans, struct ec_stripe_head *h, + struct ec_stripe_new *s) +{ + struct bch_fs *c = trans->c; + s64 idx; + int ret; + + /* + * If we can't allocate a new stripe, and there's no stripes with empty + * blocks for us to reuse, that means we have to wait on copygc: + */ + idx = get_existing_stripe(c, h); + if (idx < 0) + return -BCH_ERR_stripe_alloc_blocked; + + ret = get_stripe_key_trans(trans, idx, &s->existing_stripe); + bch2_fs_fatal_err_on(ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart), c, + "reading stripe key: %s", bch2_err_str(ret)); + if (ret) { + bch2_stripe_close(c, s); + return ret; + } + + return init_new_stripe_from_existing(c, s); +} + +static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_stripe_head *h, + struct ec_stripe_new *s) { struct bch_fs *c = trans->c; struct btree_iter iter; @@ -2082,15 +2084,19 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st struct bpos start_pos = bpos_max(min_pos, POS(0, c->ec_stripe_hint)); int ret; - if (!h->s->res.sectors) { - ret = bch2_disk_reservation_get(c, &h->s->res, + if (!s->res.sectors) { + ret = bch2_disk_reservation_get(c, &s->res, h->blocksize, - h->s->nr_parity, + s->nr_parity, BCH_DISK_RESERVATION_NOFAIL); if (ret) return ret; } + /* + * Allocate stripe slot + * XXX: we're going to need a bitrange btree of free stripes + */ for_each_btree_key_norestart(trans, iter, BTREE_ID_stripes, start_pos, BTREE_ITER_slots|BTREE_ITER_intent, k, ret) { if (bkey_gt(k.k->p, POS(0, U32_MAX))) { @@ -2105,7 +2111,7 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st } if (bkey_deleted(k.k) && - bch2_try_open_stripe(c, h->s, k.k->p.offset)) + bch2_try_open_stripe(c, s, k.k->p.offset)) break; } @@ -2116,16 +2122,16 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st ret = ec_stripe_mem_alloc(trans, &iter); if (ret) { - bch2_stripe_close(c, h->s); + bch2_stripe_close(c, s); goto err; } - h->s->new_stripe.key.k.p = iter.pos; + s->new_stripe.key.k.p = iter.pos; out: bch2_trans_iter_exit(trans, &iter); return ret; err: - bch2_disk_reservation_put(c, &h->s->res); + bch2_disk_reservation_put(c, &s->res); goto out; } @@ -2156,22 +2162,27 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans, return h; if (!h->s) { - ret = ec_new_stripe_alloc(c, h); - if (ret) { + h->s = ec_new_stripe_alloc(c, h); + if (!h->s) { + ret = -BCH_ERR_ENOMEM_ec_new_stripe_alloc; bch_err(c, "failed to allocate new stripe"); goto err; } + + h->nr_created++; } - if (h->s->allocated) + struct ec_stripe_new *s = h->s; + + if (s->allocated) goto allocated; - if (h->s->have_existing_stripe) + if (s->have_existing_stripe) goto alloc_existing; /* First, try to allocate a full stripe: */ - ret = new_stripe_alloc_buckets(trans, h, BCH_WATERMARK_stripe, NULL) ?: - __bch2_ec_stripe_head_reserve(trans, h); + ret = new_stripe_alloc_buckets(trans, h, s, BCH_WATERMARK_stripe, NULL) ?: + __bch2_ec_stripe_head_reserve(trans, h, s); if (!ret) goto allocate_buf; if (bch2_err_matches(ret, BCH_ERR_transaction_restart) || @@ -2183,15 +2194,15 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans, * existing stripe: */ while (1) { - ret = __bch2_ec_stripe_head_reuse(trans, h); + ret = __bch2_ec_stripe_head_reuse(trans, h, s); if (!ret) break; if (waiting || !cl || ret != -BCH_ERR_stripe_alloc_blocked) goto err; if (watermark == BCH_WATERMARK_copygc) { - ret = new_stripe_alloc_buckets(trans, h, watermark, NULL) ?: - __bch2_ec_stripe_head_reserve(trans, h); + ret = new_stripe_alloc_buckets(trans, h, s, watermark, NULL) ?: + __bch2_ec_stripe_head_reserve(trans, h, s); if (ret) goto err; goto allocate_buf; @@ -2209,19 +2220,19 @@ alloc_existing: * Retry allocating buckets, with the watermark for this * particular write: */ - ret = new_stripe_alloc_buckets(trans, h, watermark, cl); + ret = new_stripe_alloc_buckets(trans, h, s, watermark, cl); if (ret) goto err; allocate_buf: - ret = ec_stripe_buf_init(&h->s->new_stripe, 0, h->blocksize); + ret = ec_stripe_buf_init(&s->new_stripe, 0, h->blocksize); if (ret) goto err; - h->s->allocated = true; + s->allocated = true; allocated: - BUG_ON(!h->s->idx); - BUG_ON(!h->s->new_stripe.data[0]); + BUG_ON(!s->idx); + BUG_ON(!s->new_stripe.data[0]); BUG_ON(trans->restarted); return h; err: @@ -2286,7 +2297,7 @@ err: int bch2_dev_remove_stripes(struct bch_fs *c, unsigned dev_idx) { return bch2_trans_run(c, - for_each_btree_key_upto_commit(trans, iter, + for_each_btree_key_max_commit(trans, iter, BTREE_ID_alloc, POS(dev_idx, 0), POS(dev_idx, U64_MAX), BTREE_ITER_intent, k, NULL, NULL, 0, ({ @@ -2449,11 +2460,9 @@ void bch2_fs_ec_exit(struct bch_fs *c) while (1) { mutex_lock(&c->ec_stripe_head_lock); - h = list_first_entry_or_null(&c->ec_stripe_head_list, - struct ec_stripe_head, list); - if (h) - list_del(&h->list); + h = list_pop_entry(&c->ec_stripe_head_list, struct ec_stripe_head, list); mutex_unlock(&c->ec_stripe_head_lock); + if (!h) break; diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index 43326370b410..583ca6a226da 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -6,9 +6,8 @@ #include "buckets_types.h" #include "extents_types.h" -enum bch_validate_flags; - -int bch2_stripe_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_stripe_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_stripe_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned, diff --git a/fs/bcachefs/ec_format.h b/fs/bcachefs/ec_format.h index 64ef52e00078..b9770f24f213 100644 --- a/fs/bcachefs/ec_format.h +++ b/fs/bcachefs/ec_format.h @@ -20,6 +20,23 @@ struct bch_stripe { */ __u8 disk_label; + /* + * Variable length sections: + * - Pointers + * - Checksums + * 2D array of [stripe block/device][csum block], with checksum block + * size given by csum_granularity_bits + * - Block sector counts: per-block array of u16s + * + * XXX: + * Either checksums should have come last, or we should have included a + * checksum_size field (the size in bytes of the checksum itself, not + * the blocksize the checksum covers). + * + * Currently we aren't able to access the block sector counts if the + * checksum type is unknown. + */ + struct bch_extent_ptr ptrs[]; } __packed __aligned(8); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 9c4fe5cdbfb7..4590cd0c7c90 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -54,7 +54,8 @@ x(ENOMEM, ENOMEM_compression_bounce_read_init) \ x(ENOMEM, ENOMEM_compression_bounce_write_init) \ x(ENOMEM, ENOMEM_compression_workspace_init) \ - x(ENOMEM, ENOMEM_decompression_workspace_init) \ + x(ENOMEM, ENOMEM_backpointer_mismatches_bitmap) \ + x(EIO, compression_workspace_not_initialized) \ x(ENOMEM, ENOMEM_bucket_gens) \ x(ENOMEM, ENOMEM_buckets_nouse) \ x(ENOMEM, ENOMEM_usage_init) \ @@ -116,6 +117,8 @@ x(ENOENT, ENOENT_dirent_doesnt_match_inode) \ x(ENOENT, ENOENT_dev_not_found) \ x(ENOENT, ENOENT_dev_idx_not_found) \ + x(ENOENT, ENOENT_inode_no_backpointer) \ + x(ENOENT, ENOENT_no_snapshot_tree_subvol) \ x(ENOTEMPTY, ENOTEMPTY_dir_not_empty) \ x(ENOTEMPTY, ENOTEMPTY_subvol_not_empty) \ x(EEXIST, EEXIST_str_hash_set) \ @@ -148,6 +151,7 @@ x(BCH_ERR_transaction_restart, transaction_restart_split_race) \ x(BCH_ERR_transaction_restart, transaction_restart_write_buffer_flush) \ x(BCH_ERR_transaction_restart, transaction_restart_nested) \ + x(BCH_ERR_transaction_restart, transaction_restart_commit) \ x(0, no_btree_node) \ x(BCH_ERR_no_btree_node, no_btree_node_relock) \ x(BCH_ERR_no_btree_node, no_btree_node_upgrade) \ @@ -164,7 +168,6 @@ x(BCH_ERR_btree_insert_fail, btree_insert_need_journal_res) \ x(BCH_ERR_btree_insert_fail, btree_insert_need_journal_reclaim) \ x(0, backpointer_to_overwritten_btree_node) \ - x(0, lock_fail_root_changed) \ x(0, journal_reclaim_would_deadlock) \ x(EINVAL, fsck) \ x(BCH_ERR_fsck, fsck_fix) \ @@ -173,7 +176,9 @@ x(BCH_ERR_fsck, fsck_errors_not_fixed) \ x(BCH_ERR_fsck, fsck_repair_unimplemented) \ x(BCH_ERR_fsck, fsck_repair_impossible) \ - x(0, restart_recovery) \ + x(EINVAL, restart_recovery) \ + x(EINVAL, not_in_recovery) \ + x(EINVAL, cannot_rewind_recovery) \ x(0, data_update_done) \ x(EINVAL, device_state_not_allowed) \ x(EINVAL, member_info_missing) \ @@ -192,7 +197,9 @@ x(EINVAL, opt_parse_error) \ x(EINVAL, remove_with_metadata_missing_unimplemented)\ x(EINVAL, remove_would_lose_data) \ - x(EINVAL, btree_iter_with_journal_not_supported) \ + x(EINVAL, no_resize_with_buckets_nouse) \ + x(EINVAL, inode_unpack_error) \ + x(EINVAL, varint_decode_error) \ x(EROFS, erofs_trans_commit) \ x(EROFS, erofs_no_writes) \ x(EROFS, erofs_journal_err) \ @@ -241,7 +248,10 @@ x(BCH_ERR_invalid_sb, invalid_sb_downgrade) \ x(BCH_ERR_invalid, invalid_bkey) \ x(BCH_ERR_operation_blocked, nocow_lock_blocked) \ + x(EIO, journal_shutdown) \ + x(EIO, journal_flush_err) \ x(EIO, btree_node_read_err) \ + x(BCH_ERR_btree_node_read_err, btree_node_read_err_cached) \ x(EIO, sb_not_downgraded) \ x(EIO, btree_node_write_all_failed) \ x(EIO, btree_node_read_error) \ @@ -257,6 +267,8 @@ x(EIO, no_device_to_read_from) \ x(EIO, missing_indirect_extent) \ x(EIO, invalidate_stripe_to_dev) \ + x(EIO, no_encryption_key) \ + x(EIO, insufficient_journal_devices) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_fixable) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_want_retry) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_must_retry) \ @@ -305,6 +317,7 @@ static inline long bch2_err_class(long err) #define BLK_STS_REMOVED ((__force blk_status_t)128) +#include <linux/blk_types.h> const char *bch2_blk_status_to_str(blk_status_t); #endif /* _BCACHFES_ERRCODE_H */ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index b679def8fb98..038da6a61f6b 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "btree_cache.h" #include "btree_iter.h" #include "error.h" +#include "fs-common.h" #include "journal.h" #include "recovery_passes.h" #include "super.h" @@ -33,7 +35,7 @@ bool bch2_inconsistent_error(struct bch_fs *c) int bch2_topology_error(struct bch_fs *c) { set_bit(BCH_FS_topology_error, &c->flags); - if (!test_bit(BCH_FS_fsck_running, &c->flags)) { + if (!test_bit(BCH_FS_recovery_running, &c->flags)) { bch2_inconsistent_error(c); return -BCH_ERR_btree_need_topology_repair; } else { @@ -218,6 +220,30 @@ static const u8 fsck_flags_extra[] = { #undef x }; +static int do_fsck_ask_yn(struct bch_fs *c, + struct btree_trans *trans, + struct printbuf *question, + const char *action) +{ + prt_str(question, ", "); + prt_str(question, action); + + if (bch2_fs_stdio_redirect(c)) + bch2_print(c, "%s", question->buf); + else + bch2_print_string_as_lines(KERN_ERR, question->buf); + + int ask = bch2_fsck_ask_yn(c, trans); + + if (trans) { + int ret = bch2_trans_relock(trans); + if (ret) + return ret; + } + + return ask; +} + int __bch2_fsck_err(struct bch_fs *c, struct btree_trans *trans, enum bch_fsck_flags flags, @@ -226,7 +252,7 @@ int __bch2_fsck_err(struct bch_fs *c, { struct fsck_err_state *s = NULL; va_list args; - bool print = true, suppressing = false, inconsistent = false; + bool print = true, suppressing = false, inconsistent = false, exiting = false; struct printbuf buf = PRINTBUF, *out = &buf; int ret = -BCH_ERR_fsck_ignore; const char *action_orig = "fix?", *action = action_orig; @@ -256,9 +282,10 @@ int __bch2_fsck_err(struct bch_fs *c, !trans && bch2_current_has_btree_trans(c)); - if ((flags & FSCK_CAN_FIX) && - test_bit(err, c->sb.errors_silent)) - return -BCH_ERR_fsck_fix; + if (test_bit(err, c->sb.errors_silent)) + return flags & FSCK_CAN_FIX + ? -BCH_ERR_fsck_fix + : -BCH_ERR_fsck_ignore; bch2_sb_error_count(c, err); @@ -289,16 +316,14 @@ int __bch2_fsck_err(struct bch_fs *c, */ if (s->last_msg && !strcmp(buf.buf, s->last_msg)) { ret = s->ret; - mutex_unlock(&c->fsck_error_msgs_lock); - goto err; + goto err_unlock; } kfree(s->last_msg); s->last_msg = kstrdup(buf.buf, GFP_KERNEL); if (!s->last_msg) { - mutex_unlock(&c->fsck_error_msgs_lock); ret = -ENOMEM; - goto err; + goto err_unlock; } if (c->opts.ratelimit_errors && @@ -318,13 +343,19 @@ int __bch2_fsck_err(struct bch_fs *c, prt_printf(out, bch2_log_msg(c, "")); #endif - if ((flags & FSCK_CAN_FIX) && - (flags & FSCK_AUTOFIX) && + if ((flags & FSCK_AUTOFIX) && (c->opts.errors == BCH_ON_ERROR_continue || c->opts.errors == BCH_ON_ERROR_fix_safe)) { prt_str(out, ", "); - prt_actioning(out, action); - ret = -BCH_ERR_fsck_fix; + if (flags & FSCK_CAN_FIX) { + prt_actioning(out, action); + ret = -BCH_ERR_fsck_fix; + } else { + prt_str(out, ", continuing"); + ret = -BCH_ERR_fsck_ignore; + } + + goto print; } else if (!test_bit(BCH_FS_fsck_running, &c->flags)) { if (c->opts.errors != BCH_ON_ERROR_continue || !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) { @@ -348,31 +379,18 @@ int __bch2_fsck_err(struct bch_fs *c, : c->opts.fix_errors; if (fix == FSCK_FIX_ask) { - prt_str(out, ", "); - prt_str(out, action); - - if (bch2_fs_stdio_redirect(c)) - bch2_print(c, "%s", out->buf); - else - bch2_print_string_as_lines(KERN_ERR, out->buf); print = false; - int ask = bch2_fsck_ask_yn(c, trans); - - if (trans) { - ret = bch2_trans_relock(trans); - if (ret) { - mutex_unlock(&c->fsck_error_msgs_lock); - goto err; - } - } + ret = do_fsck_ask_yn(c, trans, out, action); + if (ret < 0) + goto err_unlock; - if (ask >= YN_ALLNO && s) - s->fix = ask == YN_ALLNO + if (ret >= YN_ALLNO && s) + s->fix = ret == YN_ALLNO ? FSCK_FIX_no : FSCK_FIX_yes; - ret = ask & 1 + ret = ret & 1 ? -BCH_ERR_fsck_fix : -BCH_ERR_fsck_ignore; } else if (fix == FSCK_FIX_yes || @@ -385,9 +403,7 @@ int __bch2_fsck_err(struct bch_fs *c, prt_str(out, ", not "); prt_actioning(out, action); } - } else if (flags & FSCK_NEED_FSCK) { - prt_str(out, " (run fsck to correct)"); - } else { + } else if (!(flags & FSCK_CAN_IGNORE)) { prt_str(out, " (repair unimplemented)"); } @@ -396,14 +412,13 @@ int __bch2_fsck_err(struct bch_fs *c, !(flags & FSCK_CAN_IGNORE))) ret = -BCH_ERR_fsck_errors_not_fixed; - bool exiting = - test_bit(BCH_FS_fsck_running, &c->flags) && - (ret != -BCH_ERR_fsck_fix && - ret != -BCH_ERR_fsck_ignore); - - if (exiting) + if (test_bit(BCH_FS_fsck_running, &c->flags) && + (ret != -BCH_ERR_fsck_fix && + ret != -BCH_ERR_fsck_ignore)) { + exiting = true; print = true; - + } +print: if (print) { if (bch2_fs_stdio_redirect(c)) bch2_print(c, "%s\n", out->buf); @@ -419,17 +434,24 @@ int __bch2_fsck_err(struct bch_fs *c, if (s) s->ret = ret; - mutex_unlock(&c->fsck_error_msgs_lock); - if (inconsistent) bch2_inconsistent_error(c); - if (ret == -BCH_ERR_fsck_fix) { - set_bit(BCH_FS_errors_fixed, &c->flags); - } else { - set_bit(BCH_FS_errors_not_fixed, &c->flags); - set_bit(BCH_FS_error, &c->flags); + /* + * We don't yet track whether the filesystem currently has errors, for + * log_fsck_err()s: that would require us to track for every error type + * which recovery pass corrects it, to get the fsck exit status correct: + */ + if (flags & FSCK_CAN_FIX) { + if (ret == -BCH_ERR_fsck_fix) { + set_bit(BCH_FS_errors_fixed, &c->flags); + } else { + set_bit(BCH_FS_errors_not_fixed, &c->flags); + set_bit(BCH_FS_error, &c->flags); + } } +err_unlock: + mutex_unlock(&c->fsck_error_msgs_lock); err: if (action != action_orig) kfree(action); @@ -437,28 +459,52 @@ err: return ret; } +static const char * const bch2_bkey_validate_contexts[] = { +#define x(n) #n, + BKEY_VALIDATE_CONTEXTS() +#undef x + NULL +}; + int __bch2_bkey_fsck_err(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags validate_flags, + struct bkey_validate_context from, enum bch_sb_error_id err, const char *fmt, ...) { - if (validate_flags & BCH_VALIDATE_silent) + if (from.flags & BCH_VALIDATE_silent) return -BCH_ERR_fsck_delete_bkey; unsigned fsck_flags = 0; - if (!(validate_flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit))) + if (!(from.flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit))) { + if (test_bit(err, c->sb.errors_silent)) + return -BCH_ERR_fsck_delete_bkey; + fsck_flags |= FSCK_AUTOFIX|FSCK_CAN_FIX; + } + if (!WARN_ON(err >= ARRAY_SIZE(fsck_flags_extra))) + fsck_flags |= fsck_flags_extra[err]; struct printbuf buf = PRINTBUF; - va_list args; + prt_printf(&buf, "invalid bkey in %s", + bch2_bkey_validate_contexts[from.from]); + + if (from.from == BKEY_VALIDATE_journal) + prt_printf(&buf, " journal seq=%llu offset=%u", + from.journal_seq, from.journal_offset); + + prt_str(&buf, " btree="); + bch2_btree_id_to_text(&buf, from.btree); + prt_printf(&buf, " level=%u: ", from.level); - prt_str(&buf, "invalid bkey "); bch2_bkey_val_to_text(&buf, c, k); prt_str(&buf, "\n "); + + va_list args; va_start(args, fmt); prt_vprintf(&buf, fmt, args); va_end(args); + prt_str(&buf, ": delete?"); int ret = __bch2_fsck_err(c, NULL, fsck_flags, err, "%s", buf.buf); @@ -483,3 +529,36 @@ void bch2_flush_fsck_errs(struct bch_fs *c) mutex_unlock(&c->fsck_error_msgs_lock); } + +int bch2_inum_err_msg_trans(struct btree_trans *trans, struct printbuf *out, subvol_inum inum) +{ + u32 restart_count = trans->restart_count; + int ret = 0; + + /* XXX: we don't yet attempt to print paths when we don't know the subvol */ + if (inum.subvol) + ret = lockrestart_do(trans, bch2_inum_to_path(trans, inum, out)); + if (!inum.subvol || ret) + prt_printf(out, "inum %llu:%llu", inum.subvol, inum.inum); + + return trans_was_restarted(trans, restart_count); +} + +int bch2_inum_offset_err_msg_trans(struct btree_trans *trans, struct printbuf *out, + subvol_inum inum, u64 offset) +{ + int ret = bch2_inum_err_msg_trans(trans, out, inum); + prt_printf(out, " offset %llu: ", offset); + return ret; +} + +void bch2_inum_err_msg(struct bch_fs *c, struct printbuf *out, subvol_inum inum) +{ + bch2_trans_run(c, bch2_inum_err_msg_trans(trans, out, inum)); +} + +void bch2_inum_offset_err_msg(struct bch_fs *c, struct printbuf *out, + subvol_inum inum, u64 offset) +{ + bch2_trans_run(c, bch2_inum_offset_err_msg_trans(trans, out, inum, offset)); +} diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index 6551ada926b6..7acf2a27ca28 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -45,32 +45,11 @@ int bch2_topology_error(struct bch_fs *); bch2_inconsistent_error(c); \ }) -#define bch2_fs_inconsistent_on(cond, c, ...) \ +#define bch2_fs_inconsistent_on(cond, ...) \ ({ \ bool _ret = unlikely(!!(cond)); \ - \ - if (_ret) \ - bch2_fs_inconsistent(c, __VA_ARGS__); \ - _ret; \ -}) - -/* - * Later we might want to mark only the particular device inconsistent, not the - * entire filesystem: - */ - -#define bch2_dev_inconsistent(ca, ...) \ -do { \ - bch_err(ca, __VA_ARGS__); \ - bch2_inconsistent_error((ca)->fs); \ -} while (0) - -#define bch2_dev_inconsistent_on(cond, ca, ...) \ -({ \ - bool _ret = unlikely(!!(cond)); \ - \ if (_ret) \ - bch2_dev_inconsistent(ca, __VA_ARGS__); \ + bch2_fs_inconsistent(__VA_ARGS__); \ _ret; \ }) @@ -123,9 +102,9 @@ int __bch2_fsck_err(struct bch_fs *, struct btree_trans *, void bch2_flush_fsck_errs(struct bch_fs *); -#define __fsck_err(c, _flags, _err_type, ...) \ +#define fsck_err_wrap(_do) \ ({ \ - int _ret = bch2_fsck_err(c, _flags, _err_type, __VA_ARGS__); \ + int _ret = _do; \ if (_ret != -BCH_ERR_fsck_fix && \ _ret != -BCH_ERR_fsck_ignore) { \ ret = _ret; \ @@ -135,6 +114,8 @@ void bch2_flush_fsck_errs(struct bch_fs *); _ret == -BCH_ERR_fsck_fix; \ }) +#define __fsck_err(...) fsck_err_wrap(bch2_fsck_err(__VA_ARGS__)) + /* These macros return true if error should be fixed: */ /* XXX: mark in superblock that filesystem contains errors, if we ignore: */ @@ -149,12 +130,6 @@ void bch2_flush_fsck_errs(struct bch_fs *); (unlikely(cond) ? __fsck_err(c, _flags, _err_type, __VA_ARGS__) : false);\ }) -#define need_fsck_err_on(cond, c, _err_type, ...) \ - __fsck_err_on(cond, c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, _err_type, __VA_ARGS__) - -#define need_fsck_err(c, _err_type, ...) \ - __fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK, _err_type, __VA_ARGS__) - #define mustfix_fsck_err(c, _err_type, ...) \ __fsck_err(c, FSCK_CAN_FIX, _err_type, __VA_ARGS__) @@ -167,11 +142,22 @@ void bch2_flush_fsck_errs(struct bch_fs *); #define fsck_err_on(cond, c, _err_type, ...) \ __fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) +#define log_fsck_err(c, _err_type, ...) \ + __fsck_err(c, FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) + +#define log_fsck_err_on(cond, ...) \ +({ \ + bool _ret = unlikely(!!(cond)); \ + if (_ret) \ + log_fsck_err(__VA_ARGS__); \ + _ret; \ +}) + enum bch_validate_flags; __printf(5, 6) int __bch2_bkey_fsck_err(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags, + struct bkey_validate_context from, enum bch_sb_error_id, const char *, ...); @@ -181,7 +167,7 @@ int __bch2_bkey_fsck_err(struct bch_fs *, */ #define bkey_fsck_err(c, _err_type, _err_msg, ...) \ do { \ - int _ret = __bch2_bkey_fsck_err(c, k, flags, \ + int _ret = __bch2_bkey_fsck_err(c, k, from, \ BCH_FSCK_ERR_##_err_type, \ _err_msg, ##__VA_ARGS__); \ if (_ret != -BCH_ERR_fsck_fix && \ @@ -252,4 +238,10 @@ void bch2_io_error(struct bch_dev *, enum bch_member_error_type); _ret; \ }) +int bch2_inum_err_msg_trans(struct btree_trans *, struct printbuf *, subvol_inum); +int bch2_inum_offset_err_msg_trans(struct btree_trans *, struct printbuf *, subvol_inum, u64); + +void bch2_inum_err_msg(struct bch_fs *, struct printbuf *, subvol_inum); +void bch2_inum_offset_err_msg(struct bch_fs *, struct printbuf *, subvol_inum, u64); + #endif /* _BCACHEFS_ERROR_H */ diff --git a/fs/bcachefs/extent_update.c b/fs/bcachefs/extent_update.c index 5f4fecb358da..6aac579a692a 100644 --- a/fs/bcachefs/extent_update.c +++ b/fs/bcachefs/extent_update.c @@ -64,7 +64,7 @@ static int count_iters_for_insert(struct btree_trans *trans, break; case KEY_TYPE_reflink_p: { struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); - u64 idx = le64_to_cpu(p.v->idx); + u64 idx = REFLINK_P_IDX(p.v); unsigned sectors = bpos_min(*end, p.k->p).offset - bkey_start_offset(p.k); struct btree_iter iter; @@ -128,7 +128,7 @@ int bch2_extent_atomic_end(struct btree_trans *trans, bch2_trans_copy_iter(©, iter); - for_each_btree_key_upto_continue_norestart(copy, insert->k.p, 0, k, ret) { + for_each_btree_key_max_continue_norestart(copy, insert->k.p, 0, k, ret) { unsigned offset = 0; if (bkey_gt(bkey_start_pos(&insert->k), bkey_start_pos(k.k))) diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 37e3d69bec06..05d5f71a7ca9 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -21,6 +21,7 @@ #include "extents.h" #include "inode.h" #include "journal.h" +#include "rebalance.h" #include "replicas.h" #include "super.h" #include "super-io.h" @@ -88,6 +89,14 @@ static inline bool ptr_better(struct bch_fs *c, u64 l1 = dev_latency(c, p1.ptr.dev); u64 l2 = dev_latency(c, p2.ptr.dev); + /* + * Square the latencies, to bias more in favor of the faster + * device - we never want to stop issuing reads to the slower + * device altogether, so that we can update our latency numbers: + */ + l1 *= l1; + l2 *= l2; + /* Pick at random, biased in favor of the faster device: */ return bch2_rand_range(l1 + l2) > l1; @@ -169,7 +178,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k, /* KEY_TYPE_btree_ptr: */ int bch2_btree_ptr_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -177,7 +186,7 @@ int bch2_btree_ptr_validate(struct bch_fs *c, struct bkey_s_c k, c, btree_ptr_val_too_big, "value too big (%zu > %u)", bkey_val_u64s(k.k), BCH_REPLICAS_MAX); - ret = bch2_bkey_ptrs_validate(c, k, flags); + ret = bch2_bkey_ptrs_validate(c, k, from); fsck_err: return ret; } @@ -189,7 +198,7 @@ void bch2_btree_ptr_to_text(struct printbuf *out, struct bch_fs *c, } int bch2_btree_ptr_v2_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); int ret = 0; @@ -203,12 +212,13 @@ int bch2_btree_ptr_v2_validate(struct bch_fs *c, struct bkey_s_c k, c, btree_ptr_v2_min_key_bad, "min_key > key"); - if (flags & BCH_VALIDATE_write) + if ((from.flags & BCH_VALIDATE_write) && + c->sb.version_min >= bcachefs_metadata_version_btree_ptr_sectors_written) bkey_fsck_err_on(!bp.v->sectors_written, c, btree_ptr_v2_written_0, "sectors_written == 0"); - ret = bch2_bkey_ptrs_validate(c, k, flags); + ret = bch2_bkey_ptrs_validate(c, k, from); fsck_err: return ret; } @@ -395,7 +405,7 @@ bool bch2_extent_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r) /* KEY_TYPE_reservation: */ int bch2_reservation_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_reservation r = bkey_s_c_to_reservation(k); int ret = 0; @@ -1120,6 +1130,57 @@ void bch2_extent_crc_unpacked_to_text(struct printbuf *out, struct bch_extent_cr bch2_prt_compression_type(out, crc->compression_type); } +static void bch2_extent_rebalance_to_text(struct printbuf *out, struct bch_fs *c, + const struct bch_extent_rebalance *r) +{ + prt_str(out, "rebalance:"); + + prt_printf(out, " replicas=%u", r->data_replicas); + if (r->data_replicas_from_inode) + prt_str(out, " (inode)"); + + prt_str(out, " checksum="); + bch2_prt_csum_opt(out, r->data_checksum); + if (r->data_checksum_from_inode) + prt_str(out, " (inode)"); + + if (r->background_compression || r->background_compression_from_inode) { + prt_str(out, " background_compression="); + bch2_compression_opt_to_text(out, r->background_compression); + + if (r->background_compression_from_inode) + prt_str(out, " (inode)"); + } + + if (r->background_target || r->background_target_from_inode) { + prt_str(out, " background_target="); + if (c) + bch2_target_to_text(out, c, r->background_target); + else + prt_printf(out, "%u", r->background_target); + + if (r->background_target_from_inode) + prt_str(out, " (inode)"); + } + + if (r->promote_target || r->promote_target_from_inode) { + prt_str(out, " promote_target="); + if (c) + bch2_target_to_text(out, c, r->promote_target); + else + prt_printf(out, "%u", r->promote_target); + + if (r->promote_target_from_inode) + prt_str(out, " (inode)"); + } + + if (r->erasure_code || r->erasure_code_from_inode) { + prt_printf(out, " ec=%u", r->erasure_code); + if (r->erasure_code_from_inode) + prt_str(out, " (inode)"); + } +} + void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { @@ -1155,18 +1216,10 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, (u64) ec->idx, ec->block); break; } - case BCH_EXTENT_ENTRY_rebalance: { - const struct bch_extent_rebalance *r = &entry->rebalance; - - prt_str(out, "rebalance: target "); - if (c) - bch2_target_to_text(out, c, r->target); - else - prt_printf(out, "%u", r->target); - prt_str(out, " compression "); - bch2_compression_opt_to_text(out, r->compression); + case BCH_EXTENT_ENTRY_rebalance: + bch2_extent_rebalance_to_text(out, c, &entry->rebalance); break; - } + default: prt_printf(out, "(invalid extent entry %.16llx)", *((u64 *) entry)); return; @@ -1178,13 +1231,19 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, static int extent_ptr_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags, + struct bkey_validate_context from, const struct bch_extent_ptr *ptr, unsigned size_ondisk, bool metadata) { int ret = 0; + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + bkey_for_each_ptr(ptrs, ptr2) + bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, + c, ptr_to_duplicate_device, + "multiple pointers to same device (%u)", ptr->dev); + /* bad pointers are repaired by check_fix_ptrs(): */ rcu_read_lock(); struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev); @@ -1199,13 +1258,6 @@ static int extent_ptr_validate(struct bch_fs *c, unsigned bucket_size = ca->mi.bucket_size; rcu_read_unlock(); - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - bkey_for_each_ptr(ptrs, ptr2) - bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, - c, ptr_to_duplicate_device, - "multiple pointers to same device (%u)", ptr->dev); - - bkey_fsck_err_on(bucket >= nbuckets, c, ptr_after_last_bucket, "pointer past last bucket (%llu > %llu)", bucket, nbuckets); @@ -1221,7 +1273,7 @@ fsck_err: } int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; @@ -1248,7 +1300,7 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, switch (extent_entry_type(entry)) { case BCH_EXTENT_ENTRY_ptr: - ret = extent_ptr_validate(c, k, flags, &entry->ptr, size_ondisk, false); + ret = extent_ptr_validate(c, k, from, &entry->ptr, size_ondisk, false); if (ret) return ret; @@ -1270,9 +1322,6 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, case BCH_EXTENT_ENTRY_crc128: crc = bch2_extent_crc_unpack(k.k, entry_to_crc(entry)); - bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, - c, ptr_crc_uncompressed_size_too_small, - "checksum offset + key size > uncompressed size"); bkey_fsck_err_on(!bch2_checksum_type_valid(c, crc.csum_type), c, ptr_crc_csum_type_unknown, "invalid checksum type"); @@ -1280,6 +1329,19 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, c, ptr_crc_compression_type_unknown, "invalid compression type"); + bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, + c, ptr_crc_uncompressed_size_too_small, + "checksum offset + key size > uncompressed size"); + bkey_fsck_err_on(crc_is_encoded(crc) && + (crc.uncompressed_size > c->opts.encoded_extent_max >> 9) && + (from.flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), + c, ptr_crc_uncompressed_size_too_big, + "too large encoded extent"); + bkey_fsck_err_on(!crc_is_compressed(crc) && + crc.compressed_size != crc.uncompressed_size, + c, ptr_crc_uncompressed_size_mismatch, + "not compressed but compressed != uncompressed size"); + if (bch2_csum_type_is_encryption(crc.csum_type)) { if (nonce == UINT_MAX) nonce = crc.offset + crc.nonce; @@ -1293,12 +1355,6 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k, "redundant crc entry"); crc_since_last_ptr = true; - bkey_fsck_err_on(crc_is_encoded(crc) && - (crc.uncompressed_size > c->opts.encoded_extent_max >> 9) && - (flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), - c, ptr_crc_uncompressed_size_too_big, - "too large encoded extent"); - size_ondisk = crc.compressed_size; break; case BCH_EXTENT_ENTRY_stripe_ptr: @@ -1391,166 +1447,6 @@ void bch2_ptr_swab(struct bkey_s k) } } -const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c k) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry; - - bkey_extent_entry_for_each(ptrs, entry) - if (__extent_entry_type(entry) == BCH_EXTENT_ENTRY_rebalance) - return &entry->rebalance; - - return NULL; -} - -unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k, - unsigned target, unsigned compression) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - unsigned rewrite_ptrs = 0; - - if (compression) { - unsigned compression_type = bch2_compression_opt_to_type(compression); - const union bch_extent_entry *entry; - struct extent_ptr_decoded p; - unsigned i = 0; - - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || - p.ptr.unwritten) { - rewrite_ptrs = 0; - goto incompressible; - } - - if (!p.ptr.cached && p.crc.compression_type != compression_type) - rewrite_ptrs |= 1U << i; - i++; - } - } -incompressible: - if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) { - unsigned i = 0; - - bkey_for_each_ptr(ptrs, ptr) { - if (!ptr->cached && !bch2_dev_in_target(c, ptr->dev, target)) - rewrite_ptrs |= 1U << i; - i++; - } - } - - return rewrite_ptrs; -} - -bool bch2_bkey_needs_rebalance(struct bch_fs *c, struct bkey_s_c k) -{ - const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); - - /* - * If it's an indirect extent, we don't delete the rebalance entry when - * done so that we know what options were applied - check if it still - * needs work done: - */ - if (r && - k.k->type == KEY_TYPE_reflink_v && - !bch2_bkey_ptrs_need_rebalance(c, k, r->target, r->compression)) - r = NULL; - - return r != NULL; -} - -static u64 __bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k, - unsigned target, unsigned compression) -{ - struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - const union bch_extent_entry *entry; - struct extent_ptr_decoded p; - u64 sectors = 0; - - if (compression) { - unsigned compression_type = bch2_compression_opt_to_type(compression); - - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || - p.ptr.unwritten) { - sectors = 0; - goto incompressible; - } - - if (!p.ptr.cached && p.crc.compression_type != compression_type) - sectors += p.crc.compressed_size; - } - } -incompressible: - if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) { - bkey_for_each_ptr_decode(k.k, ptrs, p, entry) - if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, target)) - sectors += p.crc.compressed_size; - } - - return sectors; -} - -u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k) -{ - const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); - - return r ? __bch2_bkey_sectors_need_rebalance(c, k, r->target, r->compression) : 0; -} - -int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bkey_i *_k, - struct bch_io_opts *opts) -{ - struct bkey_s k = bkey_i_to_s(_k); - struct bch_extent_rebalance *r; - unsigned target = opts->background_target; - unsigned compression = background_compression(*opts); - bool needs_rebalance; - - if (!bkey_extent_is_direct_data(k.k)) - return 0; - - /* get existing rebalance entry: */ - r = (struct bch_extent_rebalance *) bch2_bkey_rebalance_opts(k.s_c); - if (r) { - if (k.k->type == KEY_TYPE_reflink_v) { - /* - * indirect extents: existing options take precedence, - * so that we don't move extents back and forth if - * they're referenced by different inodes with different - * options: - */ - if (r->target) - target = r->target; - if (r->compression) - compression = r->compression; - } - - r->target = target; - r->compression = compression; - } - - needs_rebalance = bch2_bkey_ptrs_need_rebalance(c, k.s_c, target, compression); - - if (needs_rebalance && !r) { - union bch_extent_entry *new = bkey_val_end(k); - - new->rebalance.type = 1U << BCH_EXTENT_ENTRY_rebalance; - new->rebalance.compression = compression; - new->rebalance.target = target; - new->rebalance.unused = 0; - k.k->u64s += extent_entry_u64s(new); - } else if (!needs_rebalance && r && k.k->type != KEY_TYPE_reflink_v) { - /* - * For indirect extents, don't delete the rebalance entry when - * we're finished so that we know we specifically moved it or - * compressed it to its current location/compression type - */ - extent_entry_drop(k, (union bch_extent_entry *) r); - } - - return 0; -} - /* Generic extent code: */ int bch2_cut_front_s(struct bpos where, struct bkey_s k) @@ -1610,7 +1506,7 @@ int bch2_cut_front_s(struct bpos where, struct bkey_s k) case KEY_TYPE_reflink_p: { struct bkey_s_reflink_p p = bkey_s_to_reflink_p(k); - le64_add_cpu(&p.v->idx, sub); + SET_REFLINK_P_IDX(p.v, REFLINK_P_IDX(p.v) + sub); break; } case KEY_TYPE_inline_data: diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index bcffcf60aaaf..620b284aa34f 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -8,7 +8,6 @@ struct bch_fs; struct btree_trans; -enum bch_validate_flags; /* extent entries: */ @@ -410,12 +409,12 @@ int bch2_bkey_pick_read_device(struct bch_fs *, struct bkey_s_c, /* KEY_TYPE_btree_ptr: */ int bch2_btree_ptr_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_btree_ptr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_btree_ptr_v2_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_btree_ptr_v2_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned, int, struct bkey_s); @@ -452,7 +451,7 @@ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); /* KEY_TYPE_reservation: */ int bch2_reservation_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_reservation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); @@ -696,7 +695,7 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_bkey_ptrs_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1, struct bch_extent_ptr ptr2) @@ -710,15 +709,6 @@ static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1, void bch2_ptr_swab(struct bkey_s); -const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c); -unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c, - unsigned, unsigned); -bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c); -u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); - -int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *, - struct bch_io_opts *); - /* Generic extent code: */ enum bch_extent_overlap { diff --git a/fs/bcachefs/extents_format.h b/fs/bcachefs/extents_format.h index 3bd2fdbb0817..c198dfc376d6 100644 --- a/fs/bcachefs/extents_format.h +++ b/fs/bcachefs/extents_format.h @@ -201,19 +201,8 @@ struct bch_extent_stripe_ptr { #endif }; -struct bch_extent_rebalance { -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u64 type:6, - unused:34, - compression:8, /* enum bch_compression_opt */ - target:16; -#elif defined (__BIG_ENDIAN_BITFIELD) - __u64 target:16, - compression:8, - unused:34, - type:6; -#endif -}; +/* bch_extent_rebalance: */ +#include "rebalance_format.h" union bch_extent_entry { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ || __BITS_PER_LONG == 64 diff --git a/fs/bcachefs/fs-common.c b/fs/bcachefs/fs-common.c index 7e10a9ddcfd9..d70d9f634cea 100644 --- a/fs/bcachefs/fs-common.c +++ b/fs/bcachefs/fs-common.c @@ -69,9 +69,7 @@ int bch2_create_trans(struct btree_trans *trans, if (!snapshot_src.inum) { /* Inode wasn't specified, just snapshot: */ struct bch_subvolume s; - - ret = bch2_subvolume_get(trans, snapshot_src.subvol, true, - BTREE_ITER_cached, &s); + ret = bch2_subvolume_get(trans, snapshot_src.subvol, true, &s); if (ret) goto err; @@ -154,6 +152,7 @@ int bch2_create_trans(struct btree_trans *trans, if (is_subdir_for_nlink(new_inode)) dir_u->bi_nlink++; dir_u->bi_mtime = dir_u->bi_ctime = now; + dir_u->bi_size += dirent_occupied_size(name); ret = bch2_inode_write(trans, &dir_iter, dir_u); if (ret) @@ -172,6 +171,10 @@ int bch2_create_trans(struct btree_trans *trans, new_inode->bi_dir_offset = dir_offset; } + if (S_ISDIR(mode) && + !new_inode->bi_subvol) + new_inode->bi_depth = dir_u->bi_depth + 1; + inode_iter.flags &= ~BTREE_ITER_all_snapshots; bch2_btree_iter_set_snapshot(&inode_iter, snapshot); @@ -218,6 +221,7 @@ int bch2_link_trans(struct btree_trans *trans, } dir_u->bi_mtime = dir_u->bi_ctime = now; + dir_u->bi_size += dirent_occupied_size(name); dir_hash = bch2_hash_info_init(c, dir_u); @@ -320,6 +324,7 @@ int bch2_unlink_trans(struct btree_trans *trans, dir_u->bi_mtime = dir_u->bi_ctime = inode_u->bi_ctime = now; dir_u->bi_nlink -= is_subdir_for_nlink(inode_u); + dir_u->bi_size -= dirent_occupied_size(name); ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc, &dir_hash, &dirent_iter, @@ -458,6 +463,14 @@ int bch2_rename_trans(struct btree_trans *trans, goto err; } + if (mode == BCH_RENAME) { + src_dir_u->bi_size -= dirent_occupied_size(src_name); + dst_dir_u->bi_size += dirent_occupied_size(dst_name); + } + + if (mode == BCH_RENAME_OVERWRITE) + src_dir_u->bi_size -= dirent_occupied_size(src_name); + if (src_inode_u->bi_parent_subvol) src_inode_u->bi_parent_subvol = dst_dir.subvol; @@ -512,6 +525,15 @@ int bch2_rename_trans(struct btree_trans *trans, dst_dir_u->bi_nlink++; } + if (S_ISDIR(src_inode_u->bi_mode) && + !src_inode_u->bi_subvol) + src_inode_u->bi_depth = dst_dir_u->bi_depth + 1; + + if (mode == BCH_RENAME_EXCHANGE && + S_ISDIR(dst_inode_u->bi_mode) && + !dst_inode_u->bi_subvol) + dst_inode_u->bi_depth = src_dir_u->bi_depth + 1; + if (dst_inum.inum && is_subdir_for_nlink(dst_inode_u)) { dst_dir_u->bi_nlink--; src_dir_u->bi_nlink += mode == BCH_RENAME_EXCHANGE; @@ -548,3 +570,94 @@ err: bch2_trans_iter_exit(trans, &src_dir_iter); return ret; } + +static inline void prt_bytes_reversed(struct printbuf *out, const void *b, unsigned n) +{ + bch2_printbuf_make_room(out, n); + + unsigned can_print = min(n, printbuf_remaining(out)); + + b += n; + + for (unsigned i = 0; i < can_print; i++) + out->buf[out->pos++] = *((char *) --b); + + printbuf_nul_terminate(out); +} + +static inline void prt_str_reversed(struct printbuf *out, const char *s) +{ + prt_bytes_reversed(out, s, strlen(s)); +} + +static inline void reverse_bytes(void *b, size_t n) +{ + char *e = b + n, *s = b; + + while (s < e) { + --e; + swap(*s, *e); + s++; + } +} + +/* XXX: we don't yet attempt to print paths when we don't know the subvol */ +int bch2_inum_to_path(struct btree_trans *trans, subvol_inum inum, struct printbuf *path) +{ + unsigned orig_pos = path->pos; + int ret = 0; + + while (!(inum.subvol == BCACHEFS_ROOT_SUBVOL && + inum.inum == BCACHEFS_ROOT_INO)) { + struct bch_inode_unpacked inode; + ret = bch2_inode_find_by_inum_trans(trans, inum, &inode); + if (ret) + goto disconnected; + + if (!inode.bi_dir && !inode.bi_dir_offset) { + ret = -BCH_ERR_ENOENT_inode_no_backpointer; + goto disconnected; + } + + inum.subvol = inode.bi_parent_subvol ?: inum.subvol; + inum.inum = inode.bi_dir; + + u32 snapshot; + ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); + if (ret) + goto disconnected; + + struct btree_iter d_iter; + struct bkey_s_c_dirent d = bch2_bkey_get_iter_typed(trans, &d_iter, + BTREE_ID_dirents, SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot), + 0, dirent); + ret = bkey_err(d.s_c); + if (ret) + goto disconnected; + + struct qstr dirent_name = bch2_dirent_get_name(d); + prt_bytes_reversed(path, dirent_name.name, dirent_name.len); + + prt_char(path, '/'); + + bch2_trans_iter_exit(trans, &d_iter); + } + + if (orig_pos == path->pos) + prt_char(path, '/'); +out: + ret = path->allocation_failure ? -ENOMEM : 0; + if (ret) + goto err; + + reverse_bytes(path->buf + orig_pos, path->pos - orig_pos); + return 0; +err: + return ret; +disconnected: + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + goto err; + + prt_str_reversed(path, "(disconnected)"); + goto out; +} diff --git a/fs/bcachefs/fs-common.h b/fs/bcachefs/fs-common.h index c934e807b380..2b59210bb5e8 100644 --- a/fs/bcachefs/fs-common.h +++ b/fs/bcachefs/fs-common.h @@ -42,4 +42,6 @@ int bch2_rename_trans(struct btree_trans *, bool bch2_reinherit_attrs(struct bch_inode_unpacked *, struct bch_inode_unpacked *); +int bch2_inum_to_path(struct btree_trans *, subvol_inum, struct printbuf *); + #endif /* _BCACHEFS_FS_COMMON_H */ diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index 95972809e76d..ab1d5db2fa56 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -164,7 +164,8 @@ static void bchfs_read(struct btree_trans *trans, BTREE_ITER_slots); while (1) { struct bkey_s_c k; - unsigned bytes, sectors, offset_into_extent; + unsigned bytes, sectors; + s64 offset_into_extent; enum btree_id data_btree = BTREE_ID_extents; bch2_trans_begin(trans); @@ -197,7 +198,7 @@ static void bchfs_read(struct btree_trans *trans, k = bkey_i_to_s_c(sk.k); - sectors = min(sectors, k.k->size - offset_into_extent); + sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent); if (readpages_iter) { ret = readpage_bio_extend(trans, readpages_iter, &rbio->bio, sectors, @@ -230,10 +231,12 @@ err: bch2_trans_iter_exit(trans, &iter); if (ret) { - bch_err_inum_offset_ratelimited(c, - iter.pos.inode, - iter.pos.offset << 9, - "read error %i from btree lookup", ret); + struct printbuf buf = PRINTBUF; + bch2_inum_offset_err_msg_trans(trans, &buf, inum, iter.pos.offset << 9); + prt_printf(&buf, "read error %i from btree lookup", ret); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + rbio->bio.bi_status = BLK_STS_IOERR; bio_endio(&rbio->bio); } @@ -248,6 +251,7 @@ void bch2_readahead(struct readahead_control *ractl) struct bch_io_opts opts; struct folio *folio; struct readpages_iter readpages_iter; + struct blk_plug plug; bch2_inode_opts_get(&opts, c, &inode->ei_inode); @@ -255,6 +259,16 @@ void bch2_readahead(struct readahead_control *ractl) if (ret) return; + /* + * Besides being a general performance optimization, plugging helps with + * avoiding btree transaction srcu warnings - submitting a bio can + * block, and we don't want todo that with the transaction locked. + * + * However, plugged bios are submitted when we schedule; we ideally + * would have our own scheduler hook to call unlock_long() before + * scheduling. + */ + blk_start_plug(&plug); bch2_pagecache_add_get(inode); struct btree_trans *trans = bch2_trans_get(c); @@ -281,7 +295,7 @@ void bch2_readahead(struct readahead_control *ractl) bch2_trans_put(trans); bch2_pagecache_add_put(inode); - + blk_finish_plug(&plug); darray_exit(&readpages_iter.folios); } @@ -296,9 +310,13 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping) struct bch_fs *c = inode->v.i_sb->s_fs_info; struct bch_read_bio *rbio; struct bch_io_opts opts; + struct blk_plug plug; int ret; DECLARE_COMPLETION_ONSTACK(done); + BUG_ON(folio_test_uptodate(folio)); + BUG_ON(folio_test_dirty(folio)); + if (!bch2_folio_create(folio, GFP_KERNEL)) return -ENOMEM; @@ -313,7 +331,9 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping) rbio->bio.bi_iter.bi_sector = folio_sector(folio); BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0)); + blk_start_plug(&plug); bch2_trans_run(c, (bchfs_read(trans, rbio, inode_inum(inode), NULL), 0)); + blk_finish_plug(&plug); wait_for_completion(&done); ret = blk_status_to_errno(rbio->bio.bi_status); @@ -605,15 +625,6 @@ do_io: BUG_ON(!bio_add_folio(&w->io->op.wbio.bio, folio, sectors << 9, offset << 9)); - /* Check for writing past i_size: */ - WARN_ONCE((bio_end_sector(&w->io->op.wbio.bio) << 9) > - round_up(i_size, block_bytes(c)) && - !test_bit(BCH_FS_emergency_ro, &c->flags), - "writing past i_size: %llu > %llu (unrounded %llu)\n", - bio_end_sector(&w->io->op.wbio.bio) << 9, - round_up(i_size, block_bytes(c)), - i_size); - w->io->op.res.sectors += reserved_sectors; w->io->op.i_sectors_delta -= dirty_sectors; w->io->op.new_i_size = i_size; @@ -669,7 +680,7 @@ int bch2_write_begin(struct file *file, struct address_space *mapping, folio = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN | fgf_set_order(len), mapping_gfp_mask(mapping)); - if (IS_ERR_OR_NULL(folio)) + if (IS_ERR(folio)) goto err_unlock; offset = pos - folio_pos(folio); diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index 6d3a05ae5da8..2089c36b5866 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -70,6 +70,7 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter) struct bch_io_opts opts; struct dio_read *dio; struct bio *bio; + struct blk_plug plug; loff_t offset = req->ki_pos; bool sync = is_sync_kiocb(req); size_t shorten; @@ -128,6 +129,8 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter) */ dio->should_dirty = iter_is_iovec(iter); + blk_start_plug(&plug); + goto start; while (iter->count) { bio = bio_alloc_bioset(NULL, @@ -160,6 +163,8 @@ start: bch2_read(c, rbio_init(bio, opts), inode_inum(inode)); } + blk_finish_plug(&plug); + iter->count += shorten; if (sync) { diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c index 1d4910ea0f1d..e072900e6a5b 100644 --- a/fs/bcachefs/fs-io-pagecache.c +++ b/fs/bcachefs/fs-io-pagecache.c @@ -29,7 +29,7 @@ int bch2_filemap_get_contig_folios_d(struct address_space *mapping, break; f = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, fgp_flags, gfp); - if (IS_ERR_OR_NULL(f)) + if (IS_ERR(f)) break; BUG_ON(fs->nr && folio_pos(f) != pos); @@ -199,7 +199,7 @@ int bch2_folio_set(struct bch_fs *c, subvol_inum inum, unsigned folio_idx = 0; return bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inum.inum, offset), POS(inum.inum, U64_MAX), inum.subvol, BTREE_ITER_slots, k, ({ diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c index 2456c41b215e..94bf34b9b65f 100644 --- a/fs/bcachefs/fs-io.c +++ b/fs/bcachefs/fs-io.c @@ -167,6 +167,34 @@ void __bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode, /* fsync: */ +static int bch2_get_inode_journal_seq_trans(struct btree_trans *trans, subvol_inum inum, + u64 *seq) +{ + struct printbuf buf = PRINTBUF; + struct bch_inode_unpacked u; + struct btree_iter iter; + int ret = bch2_inode_peek(trans, &iter, &u, inum, 0); + if (ret) + return ret; + + u64 cur_seq = journal_cur_seq(&trans->c->journal); + *seq = min(cur_seq, u.bi_journal_seq); + + if (fsck_err_on(u.bi_journal_seq > cur_seq, + trans, inode_journal_seq_in_future, + "inode journal seq in future (currently at %llu)\n%s", + cur_seq, + (bch2_inode_unpacked_to_text(&buf, &u), + buf.buf))) { + u.bi_journal_seq = cur_seq; + ret = bch2_inode_write(trans, &iter, &u); + } +fsck_err: + bch2_trans_iter_exit(trans, &iter); + printbuf_exit(&buf); + return ret; +} + /* * inode->ei_inode.bi_journal_seq won't be up to date since it's set in an * insert trigger: look up the btree inode instead @@ -180,9 +208,10 @@ static int bch2_flush_inode(struct bch_fs *c, if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) return -EROFS; - struct bch_inode_unpacked u; - int ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u) ?: - bch2_journal_flush_seq(&c->journal, u.bi_journal_seq, TASK_INTERRUPTIBLE) ?: + u64 seq; + int ret = bch2_trans_commit_do(c, NULL, NULL, 0, + bch2_get_inode_journal_seq_trans(trans, inode_inum(inode), &seq)) ?: + bch2_journal_flush_seq(&c->journal, seq, TASK_INTERRUPTIBLE) ?: bch2_inode_flush_nocow_writes(c, inode); bch2_write_ref_put(c, BCH_WRITE_REF_fsync); return ret; @@ -222,7 +251,7 @@ static inline int range_has_data(struct bch_fs *c, u32 subvol, struct bpos end) { return bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, start, end, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, start, end, subvol, 0, k, ({ bkey_extent_is_data(k.k) && !bkey_extent_is_unwritten(k); }))); @@ -256,7 +285,7 @@ static int __bch2_truncate_folio(struct bch_inode_info *inode, folio = __filemap_get_folio(mapping, index, FGP_LOCK|FGP_CREAT, GFP_KERNEL); - if (IS_ERR_OR_NULL(folio)) { + if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } @@ -806,7 +835,7 @@ static int quota_reserve_range(struct bch_inode_info *inode, u64 sectors = end - start; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inode->v.i_ino, start), POS(inode->v.i_ino, end - 1), @@ -877,11 +906,18 @@ loff_t bch2_remap_file_range(struct file *file_src, loff_t pos_src, bch2_mark_pagecache_unallocated(src, pos_src >> 9, (pos_src + aligned_len) >> 9); + /* + * XXX: we'd like to be telling bch2_remap_range() if we have + * permission to write to the source file, and thus if io path option + * changes should be propagated through the copy, but we need mnt_idmap + * from the pathwalk, awkward + */ ret = bch2_remap_range(c, inode_inum(dst), pos_dst >> 9, inode_inum(src), pos_src >> 9, aligned_len >> 9, - pos_dst + len, &i_sectors_delta); + pos_dst + len, &i_sectors_delta, + false); if (ret < 0) goto err; @@ -922,7 +958,7 @@ static loff_t bch2_seek_data(struct file *file, u64 offset) return -ENXIO; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inode->v.i_ino, offset >> 9), POS(inode->v.i_ino, U64_MAX), inum.subvol, 0, k, ({ @@ -958,7 +994,7 @@ static loff_t bch2_seek_hole(struct file *file, u64 offset) return -ENXIO; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_extents, POS(inode->v.i_ino, offset >> 9), POS(inode->v.i_ino, U64_MAX), inum.subvol, BTREE_ITER_slots, k, ({ diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index 405cf08bda34..15725b4ce393 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -406,7 +406,7 @@ static long bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp, sync_inodes_sb(c->vfs_sb); up_read(&c->vfs_sb->s_umount); } -retry: + if (arg.src_ptr) { error = user_path_at(arg.dirfd, (const char __user *)(unsigned long)arg.src_ptr, @@ -486,11 +486,6 @@ err3: err2: if (arg.src_ptr) path_put(&src_path); - - if (retry_estale(error, lookup_flags)) { - lookup_flags |= LOOKUP_REVAL; - goto retry; - } err1: return error; } diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index a41d0d8a2f7b..90ade8f648d9 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -23,6 +23,7 @@ #include "journal.h" #include "keylist.h" #include "quota.h" +#include "rebalance.h" #include "snapshot.h" #include "super.h" #include "xattr.h" @@ -38,6 +39,7 @@ #include <linux/posix_acl.h> #include <linux/random.h> #include <linux/seq_file.h> +#include <linux/siphash.h> #include <linux/statfs.h> #include <linux/string.h> #include <linux/xattr.h> @@ -65,6 +67,9 @@ void bch2_inode_update_after_write(struct btree_trans *trans, i_gid_write(&inode->v, bi->bi_gid); inode->v.i_mode = bi->bi_mode; + if (fields & ATTR_SIZE) + i_size_write(&inode->v, bi->bi_size); + if (fields & ATTR_ATIME) inode_set_atime_to_ts(&inode->v, bch2_time_to_timespec(c, bi->bi_atime)); if (fields & ATTR_MTIME) @@ -89,10 +94,25 @@ int __must_check bch2_write_inode(struct bch_fs *c, retry: bch2_trans_begin(trans); - ret = bch2_inode_peek(trans, &iter, &inode_u, inode_inum(inode), - BTREE_ITER_intent) ?: - (set ? set(trans, inode, &inode_u, p) : 0) ?: - bch2_inode_write(trans, &iter, &inode_u) ?: + ret = bch2_inode_peek(trans, &iter, &inode_u, inode_inum(inode), BTREE_ITER_intent); + if (ret) + goto err; + + struct bch_extent_rebalance old_r = bch2_inode_rebalance_opts_get(c, &inode_u); + + ret = (set ? set(trans, inode, &inode_u, p) : 0); + if (ret) + goto err; + + struct bch_extent_rebalance new_r = bch2_inode_rebalance_opts_get(c, &inode_u); + + if (memcmp(&old_r, &new_r, sizeof(new_r))) { + ret = bch2_set_rebalance_needs_scan_trans(trans, inode_u.bi_inum); + if (ret) + goto err; + } + + ret = bch2_inode_write(trans, &iter, &inode_u) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); /* @@ -101,7 +121,7 @@ retry: */ if (!ret) bch2_inode_update_after_write(trans, inode, &inode_u, fields); - +err: bch2_trans_iter_exit(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) @@ -160,8 +180,9 @@ static bool subvol_inum_eq(subvol_inum a, subvol_inum b) static u32 bch2_vfs_inode_hash_fn(const void *data, u32 len, u32 seed) { const subvol_inum *inum = data; + siphash_key_t k = { .key[0] = seed }; - return jhash(&inum->inum, sizeof(inum->inum), seed); + return siphash_2u64(inum->subvol, inum->inum, &k); } static u32 bch2_vfs_inode_obj_hash_fn(const void *data, u32 len, u32 seed) @@ -190,11 +211,18 @@ static const struct rhashtable_params bch2_vfs_inodes_params = { .automatic_shrinking = true, }; +static const struct rhashtable_params bch2_vfs_inodes_by_inum_params = { + .head_offset = offsetof(struct bch_inode_info, by_inum_hash), + .key_offset = offsetof(struct bch_inode_info, ei_inum.inum), + .key_len = sizeof(u64), + .automatic_shrinking = true, +}; + int bch2_inode_or_descendents_is_open(struct btree_trans *trans, struct bpos p) { struct bch_fs *c = trans->c; - struct rhashtable *ht = &c->vfs_inodes_table; - subvol_inum inum = (subvol_inum) { .inum = p.offset }; + struct rhltable *ht = &c->vfs_inodes_by_inum_table; + u64 inum = p.offset; DARRAY(u32) subvols; int ret = 0; @@ -219,15 +247,15 @@ restart_from_top: struct rhash_lock_head __rcu *const *bkt; struct rhash_head *he; unsigned int hash; - struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + struct bucket_table *tbl = rht_dereference_rcu(ht->ht.tbl, &ht->ht); restart: - hash = rht_key_hashfn(ht, tbl, &inum, bch2_vfs_inodes_params); + hash = rht_key_hashfn(&ht->ht, tbl, &inum, bch2_vfs_inodes_by_inum_params); bkt = rht_bucket(tbl, hash); do { struct bch_inode_info *inode; rht_for_each_entry_rcu_from(inode, he, rht_ptr_rcu(bkt), tbl, hash, hash) { - if (inode->ei_inum.inum == inum.inum) { + if (inode->ei_inum.inum == inum) { ret = darray_push_gfp(&subvols, inode->ei_inum.subvol, GFP_NOWAIT|__GFP_NOWARN); if (ret) { @@ -248,7 +276,7 @@ restart: /* Ensure we see any new tables. */ smp_rmb(); - tbl = rht_dereference_rcu(tbl->future_tbl, ht); + tbl = rht_dereference_rcu(tbl->future_tbl, &ht->ht); if (unlikely(tbl)) goto restart; rcu_read_unlock(); @@ -327,7 +355,11 @@ static void bch2_inode_hash_remove(struct bch_fs *c, struct bch_inode_info *inod spin_unlock(&inode->v.i_lock); if (remove) { - int ret = rhashtable_remove_fast(&c->vfs_inodes_table, + int ret = rhltable_remove(&c->vfs_inodes_by_inum_table, + &inode->by_inum_hash, bch2_vfs_inodes_by_inum_params); + BUG_ON(ret); + + ret = rhashtable_remove_fast(&c->vfs_inodes_table, &inode->hash, bch2_vfs_inodes_params); BUG_ON(ret); inode->v.i_hash.pprev = NULL; @@ -372,6 +404,11 @@ retry: discard_new_inode(&inode->v); return old; } else { + int ret = rhltable_insert(&c->vfs_inodes_by_inum_table, + &inode->by_inum_hash, + bch2_vfs_inodes_by_inum_params); + BUG_ON(ret); + inode_fake_hash(&inode->v); inode_sb_list_add(&inode->v); @@ -465,7 +502,7 @@ struct inode *bch2_vfs_inode_get(struct bch_fs *c, subvol_inum inum) struct bch_inode_unpacked inode_u; struct bch_subvolume subvol; int ret = lockrestart_do(trans, - bch2_subvolume_get(trans, inum.subvol, true, 0, &subvol) ?: + bch2_subvolume_get(trans, inum.subvol, true, &subvol) ?: bch2_inode_find_by_inum_trans(trans, inum, &inode_u)) ?: PTR_ERR_OR_ZERO(inode = bch2_inode_hash_init_insert(trans, inum, &inode_u, &subvol)); bch2_trans_put(trans); @@ -535,8 +572,7 @@ retry: inum.subvol = inode_u.bi_subvol ?: dir->ei_inum.subvol; inum.inum = inode_u.bi_inum; - ret = bch2_subvolume_get(trans, inum.subvol, true, - BTREE_ITER_with_updates, &subvol) ?: + ret = bch2_subvolume_get(trans, inum.subvol, true, &subvol) ?: bch2_trans_commit(trans, NULL, &journal_seq, 0); if (unlikely(ret)) { bch2_quota_acct(c, bch_qid(&inode_u), Q_INO, -1, @@ -549,7 +585,7 @@ err_before_quota: if (!(flags & BCH_CREATE_TMPFILE)) { bch2_inode_update_after_write(trans, dir, &dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); mutex_unlock(&dir->ei_update_lock); } @@ -617,7 +653,7 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans, struct bch_subvolume subvol; struct bch_inode_unpacked inode_u; - ret = bch2_subvolume_get(trans, inum.subvol, true, 0, &subvol) ?: + ret = bch2_subvolume_get(trans, inum.subvol, true, &subvol) ?: bch2_inode_find_by_inum_nowarn_trans(trans, inum, &inode_u) ?: PTR_ERR_OR_ZERO(inode = bch2_inode_hash_init_insert(trans, inum, &inode_u, &subvol)); @@ -628,7 +664,7 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans, goto err; /* regular files may have hardlinks: */ - if (bch2_fs_inconsistent_on(bch2_inode_should_have_bp(&inode_u) && + if (bch2_fs_inconsistent_on(bch2_inode_should_have_single_bp(&inode_u) && !bkey_eq(k.k->p, POS(inode_u.bi_dir, inode_u.bi_dir_offset)), c, "dirent points to inode that does not point back:\n %s", @@ -706,7 +742,7 @@ static int __bch2_link(struct bch_fs *c, if (likely(!ret)) { bch2_inode_update_after_write(trans, dir, &dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); bch2_inode_update_after_write(trans, inode, &inode_u, ATTR_CTIME); } @@ -759,7 +795,7 @@ int __bch2_unlink(struct inode *vdir, struct dentry *dentry, goto err; bch2_inode_update_after_write(trans, dir, &dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); bch2_inode_update_after_write(trans, inode, &inode_u, ATTR_MTIME); @@ -937,11 +973,11 @@ err_tx_restart: dst_inode->v.i_ino != dst_inode_u.bi_inum); bch2_inode_update_after_write(trans, src_dir, &src_dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); if (src_dir != dst_dir) bch2_inode_update_after_write(trans, dst_dir, &dst_dir_u, - ATTR_MTIME|ATTR_CTIME); + ATTR_MTIME|ATTR_CTIME|ATTR_SIZE); bch2_inode_update_after_write(trans, src_inode, &src_inode_u, ATTR_CTIME); @@ -1245,7 +1281,6 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, struct btree_iter iter; struct bkey_s_c k; struct bkey_buf cur, prev; - unsigned offset_into_extent, sectors; bool have_extent = false; int ret = 0; @@ -1278,7 +1313,7 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, bch2_btree_iter_set_snapshot(&iter, snapshot); - k = bch2_btree_iter_peek_upto(&iter, end); + k = bch2_btree_iter_peek_max(&iter, end); ret = bkey_err(k); if (ret) continue; @@ -1292,9 +1327,8 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, continue; } - offset_into_extent = iter.pos.offset - - bkey_start_offset(k.k); - sectors = k.k->size - offset_into_extent; + s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); + unsigned sectors = k.k->size - offset_into_extent; bch2_bkey_buf_reassemble(&cur, c, k); @@ -1306,7 +1340,7 @@ static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info, k = bkey_i_to_s_c(cur.k); bch2_bkey_buf_realloc(&prev, c, k.k->u64s); - sectors = min(sectors, k.k->size - offset_into_extent); + sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent); bch2_cut_front(POS(k.k->p.inode, bkey_start_offset(k.k) + @@ -1736,7 +1770,6 @@ static void bch2_vfs_inode_init(struct btree_trans *trans, bch2_inode_update_after_write(trans, inode, bi, ~0); inode->v.i_blocks = bi->bi_sectors; - inode->v.i_ino = bi->bi_inum; inode->v.i_rdev = bi->bi_dev; inode->v.i_generation = bi->bi_generation; inode->v.i_size = bi->bi_size; @@ -2200,7 +2233,8 @@ got_sb: sb->s_time_gran = c->sb.nsec_per_time_unit; sb->s_time_min = div_s64(S64_MIN, c->sb.time_units_per_sec) + 1; sb->s_time_max = div_s64(S64_MAX, c->sb.time_units_per_sec); - sb->s_uuid = c->sb.user_uuid; + super_set_uuid(sb, c->sb.user_uuid.b, sizeof(c->sb.user_uuid)); + super_set_sysfs_name_uuid(sb); sb->s_shrink->seeks = 0; c->vfs_sb = sb; strscpy(sb->s_id, c->name, sizeof(sb->s_id)); @@ -2345,13 +2379,16 @@ static int bch2_init_fs_context(struct fs_context *fc) void bch2_fs_vfs_exit(struct bch_fs *c) { + if (c->vfs_inodes_by_inum_table.ht.tbl) + rhltable_destroy(&c->vfs_inodes_by_inum_table); if (c->vfs_inodes_table.tbl) rhashtable_destroy(&c->vfs_inodes_table); } int bch2_fs_vfs_init(struct bch_fs *c) { - return rhashtable_init(&c->vfs_inodes_table, &bch2_vfs_inodes_params); + return rhashtable_init(&c->vfs_inodes_table, &bch2_vfs_inodes_params) ?: + rhltable_init(&c->vfs_inodes_by_inum_table, &bch2_vfs_inodes_by_inum_params); } static struct file_system_type bcache_fs_type = { diff --git a/fs/bcachefs/fs.h b/fs/bcachefs/fs.h index 59f9f7ae728d..dd2198541455 100644 --- a/fs/bcachefs/fs.h +++ b/fs/bcachefs/fs.h @@ -14,6 +14,7 @@ struct bch_inode_info { struct inode v; struct rhash_head hash; + struct rhlist_head by_inum_hash; subvol_inum ei_inum; struct list_head ei_vfs_inode_list; diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 75c8a97a6954..8fcf7c8e5ede 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "bcachefs_ioctl.h" #include "bkey_buf.h" #include "btree_cache.h" #include "btree_update.h" @@ -16,6 +17,7 @@ #include "recovery_passes.h" #include "snapshot.h" #include "super.h" +#include "thread_with_file.h" #include "xattr.h" #include <linux/bsearch.h> @@ -73,7 +75,7 @@ static s64 bch2_count_inode_sectors(struct btree_trans *trans, u64 inum, { u64 sectors = 0; - int ret = for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + int ret = for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ @@ -90,7 +92,7 @@ static s64 bch2_count_subdirs(struct btree_trans *trans, u64 inum, { u64 subdirs = 0; - int ret = for_each_btree_key_upto(trans, iter, BTREE_ID_dirents, + int ret = for_each_btree_key_max(trans, iter, BTREE_ID_dirents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ @@ -107,7 +109,7 @@ static int subvol_lookup(struct btree_trans *trans, u32 subvol, u32 *snapshot, u64 *inum) { struct bch_subvolume s; - int ret = bch2_subvolume_get(trans, subvol, false, 0, &s); + int ret = bch2_subvolume_get(trans, subvol, false, &s); *snapshot = le32_to_cpu(s.snapshot); *inum = le64_to_cpu(s.inode); @@ -170,7 +172,7 @@ static int lookup_dirent_in_snapshot(struct btree_trans *trans, if (ret) return ret; - struct bkey_s_c_dirent d = bkey_s_c_to_dirent(bch2_btree_iter_peek_slot(&iter)); + struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); *target = le64_to_cpu(d.v->d_inum); *type = d.v->d_type; bch2_trans_iter_exit(trans, &iter); @@ -203,6 +205,36 @@ err: return ret; } +/* + * Find any subvolume associated with a tree of snapshots + * We can't rely on master_subvol - it might have been deleted. + */ +static int find_snapshot_tree_subvol(struct btree_trans *trans, + u32 tree_id, u32 *subvol) +{ + struct btree_iter iter; + struct bkey_s_c k; + int ret; + + for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshots, POS_MIN, 0, k, ret) { + if (k.k->type != KEY_TYPE_snapshot) + continue; + + struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(k); + if (le32_to_cpu(s.v->tree) != tree_id) + continue; + + if (s.v->subvol) { + *subvol = le32_to_cpu(s.v->subvol); + goto found; + } + } + ret = -BCH_ERR_ENOENT_no_snapshot_tree_subvol; +found: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + /* Get lost+found, create if it doesn't exist: */ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, struct bch_inode_unpacked *lostfound, @@ -210,6 +242,7 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, { struct bch_fs *c = trans->c; struct qstr lostfound_str = QSTR("lost+found"); + struct btree_iter lostfound_iter = { NULL }; u64 inum = 0; unsigned d_type = 0; int ret; @@ -220,20 +253,24 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, if (ret) return ret; - subvol_inum root_inum = { .subvol = le32_to_cpu(st.master_subvol) }; + u32 subvolid; + ret = find_snapshot_tree_subvol(trans, + bch2_snapshot_tree(c, snapshot), &subvolid); + bch_err_msg(c, ret, "finding subvol associated with snapshot tree %u", + bch2_snapshot_tree(c, snapshot)); + if (ret) + return ret; struct bch_subvolume subvol; - ret = bch2_subvolume_get(trans, le32_to_cpu(st.master_subvol), - false, 0, &subvol); - bch_err_msg(c, ret, "looking up root subvol %u for snapshot %u", - le32_to_cpu(st.master_subvol), snapshot); + ret = bch2_subvolume_get(trans, subvolid, false, &subvol); + bch_err_msg(c, ret, "looking up subvol %u for snapshot %u", subvolid, snapshot); if (ret) return ret; if (!subvol.inode) { struct btree_iter iter; struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &iter, - BTREE_ID_subvolumes, POS(0, le32_to_cpu(st.master_subvol)), + BTREE_ID_subvolumes, POS(0, subvolid), 0, subvolume); ret = PTR_ERR_OR_ZERO(subvol); if (ret) @@ -243,13 +280,16 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, bch2_trans_iter_exit(trans, &iter); } - root_inum.inum = le64_to_cpu(subvol.inode); + subvol_inum root_inum = { + .subvol = subvolid, + .inum = le64_to_cpu(subvol.inode) + }; struct bch_inode_unpacked root_inode; struct bch_hash_info root_hash_info; ret = lookup_inode(trans, root_inum.inum, snapshot, &root_inode); bch_err_msg(c, ret, "looking up root inode %llu for subvol %u", - root_inum.inum, le32_to_cpu(st.master_subvol)); + root_inum.inum, subvolid); if (ret) return ret; @@ -288,11 +328,16 @@ create_lostfound: * XXX: we could have a nicer log message here if we had a nice way to * walk backpointers to print a path */ - bch_notice(c, "creating lost+found in subvol %llu snapshot %u", - root_inum.subvol, le32_to_cpu(st.root_snapshot)); + struct printbuf path = PRINTBUF; + ret = bch2_inum_to_path(trans, root_inum, &path); + if (ret) + goto err; + + bch_notice(c, "creating %s/lost+found in subvol %llu snapshot %u", + path.buf, root_inum.subvol, snapshot); + printbuf_exit(&path); u64 now = bch2_current_time(c); - struct btree_iter lostfound_iter = { NULL }; u64 cpu = raw_smp_processor_id(); bch2_inode_init_early(c, lostfound); @@ -451,7 +496,9 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * continue; struct bch_inode_unpacked child_inode; - bch2_inode_unpack(k, &child_inode); + ret = bch2_inode_unpack(k, &child_inode); + if (ret) + break; if (!inode_should_reattach(&child_inode)) { ret = maybe_delete_dirent(trans, @@ -482,6 +529,13 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * return ret; } +static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, + struct btree_iter *iter, + struct bpos pos) +{ + return bch2_bkey_get_iter_typed(trans, iter, BTREE_ID_dirents, pos, 0, dirent); +} + static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { @@ -490,13 +544,11 @@ static int remove_backpointer(struct btree_trans *trans, struct bch_fs *c = trans->c; struct btree_iter iter; - struct bkey_s_c_dirent d = - bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_dirents, - SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot), 0, - dirent); - int ret = bkey_err(d) ?: - dirent_points_to_inode(c, d, inode) ?: - __remove_dirent(trans, d.k->p); + struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter, + SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot)); + int ret = bkey_err(d) ?: + dirent_points_to_inode(c, d, inode) ?: + __remove_dirent(trans, d.k->p); bch2_trans_iter_exit(trans, &iter); return ret; } @@ -613,7 +665,7 @@ static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32 struct btree_iter iter = {}; bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(inum, U64_MAX, snapshot), 0); - struct bkey_s_c k = bch2_btree_iter_peek_prev(&iter); + struct bkey_s_c k = bch2_btree_iter_peek_prev_min(&iter, POS(inum, 0)); bch2_trans_iter_exit(trans, &iter); int ret = bkey_err(k); if (ret) @@ -780,11 +832,13 @@ struct inode_walker { struct bpos last_pos; DARRAY(struct inode_walker_entry) inodes; + snapshot_id_list deletes; }; static void inode_walker_exit(struct inode_walker *w) { darray_exit(&w->inodes); + darray_exit(&w->deletes); } static struct inode_walker inode_walker_init(void) @@ -797,9 +851,8 @@ static int add_inode(struct bch_fs *c, struct inode_walker *w, { struct bch_inode_unpacked u; - BUG_ON(bch2_inode_unpack(inode, &u)); - - return darray_push(&w->inodes, ((struct inode_walker_entry) { + return bch2_inode_unpack(inode, &u) ?: + darray_push(&w->inodes, ((struct inode_walker_entry) { .inode = u, .snapshot = inode.k->p.snapshot, })); @@ -909,8 +962,9 @@ static int get_visible_inodes(struct btree_trans *trans, int ret; w->inodes.nr = 0; + w->deletes.nr = 0; - for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, POS(0, inum), + for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, s->pos.snapshot), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inum) break; @@ -918,10 +972,13 @@ static int get_visible_inodes(struct btree_trans *trans, if (!ref_visible(c, s, s->pos.snapshot, k.k->p.snapshot)) continue; - if (bkey_is_inode(k.k)) - add_inode(c, w, k); + if (snapshot_list_has_ancestor(c, &w->deletes, k.k->p.snapshot)) + continue; - if (k.k->p.snapshot >= s->pos.snapshot) + ret = bkey_is_inode(k.k) + ? add_inode(c, w, k) + : snapshot_list_add(c, &w->deletes, k.k->p.snapshot); + if (ret) break; } bch2_trans_iter_exit(trans, &iter); @@ -929,69 +986,16 @@ static int get_visible_inodes(struct btree_trans *trans, return ret; } -static int dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dirent d) -{ - if (d.v->d_type == DT_SUBVOL) { - u32 snap; - u64 inum; - int ret = subvol_lookup(trans, le32_to_cpu(d.v->d_child_subvol), &snap, &inum); - if (ret && !bch2_err_matches(ret, ENOENT)) - return ret; - return !ret; - } else { - struct btree_iter iter; - struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, - SPOS(0, le64_to_cpu(d.v->d_inum), d.k->p.snapshot), 0); - int ret = bkey_err(k); - if (ret) - return ret; - - ret = bkey_is_inode(k.k); - bch2_trans_iter_exit(trans, &iter); - return ret; - } -} - /* * Prefer to delete the first one, since that will be the one at the wrong * offset: * return value: 0 -> delete k1, 1 -> delete k2 */ -static int hash_pick_winner(struct btree_trans *trans, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_s_c k1, - struct bkey_s_c k2) -{ - if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) && - !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k))) - return 0; - - switch (desc.btree_id) { - case BTREE_ID_dirents: { - int ret = dirent_has_target(trans, bkey_s_c_to_dirent(k1)); - if (ret < 0) - return ret; - if (!ret) - return 0; - - ret = dirent_has_target(trans, bkey_s_c_to_dirent(k2)); - if (ret < 0) - return ret; - if (!ret) - return 1; - return 2; - } - default: - return 0; - } -} - -static int fsck_update_backpointers(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_i *new) +int bch2_fsck_update_backpointers(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_i *new) { if (new->k.type != KEY_TYPE_dirent) return 0; @@ -1019,160 +1023,6 @@ err: return ret; } -static int fsck_rename_dirent(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_s_c_dirent old) -{ - struct qstr old_name = bch2_dirent_get_name(old); - struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32); - int ret = PTR_ERR_OR_ZERO(new); - if (ret) - return ret; - - bkey_dirent_init(&new->k_i); - dirent_copy_target(new, old); - new->k.p = old.k->p; - - for (unsigned i = 0; i < 1000; i++) { - unsigned len = sprintf(new->v.d_name, "%.*s.fsck_renamed-%u", - old_name.len, old_name.name, i); - unsigned u64s = BKEY_U64s + dirent_val_u64s(len); - - if (u64s > U8_MAX) - return -EINVAL; - - new->k.u64s = u64s; - - ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info, - (subvol_inum) { 0, old.k->p.inode }, - old.k->p.snapshot, &new->k_i, - BTREE_UPDATE_internal_snapshot_node); - if (!bch2_err_matches(ret, EEXIST)) - break; - } - - if (ret) - return ret; - - return fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i); -} - -static int hash_check_key(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct btree_iter *k_iter, struct bkey_s_c hash_k) -{ - struct bch_fs *c = trans->c; - struct btree_iter iter = { NULL }; - struct printbuf buf = PRINTBUF; - struct bkey_s_c k; - u64 hash; - int ret = 0; - - if (hash_k.k->type != desc.key_type) - return 0; - - hash = desc.hash_bkey(hash_info, hash_k); - - if (likely(hash == hash_k.k->p.offset)) - return 0; - - if (hash_k.k->p.offset < hash) - goto bad_hash; - - for_each_btree_key_norestart(trans, iter, desc.btree_id, - SPOS(hash_k.k->p.inode, hash, hash_k.k->p.snapshot), - BTREE_ITER_slots, k, ret) { - if (bkey_eq(k.k->p, hash_k.k->p)) - break; - - if (k.k->type == desc.key_type && - !desc.cmp_bkey(k, hash_k)) - goto duplicate_entries; - - if (bkey_deleted(k.k)) { - bch2_trans_iter_exit(trans, &iter); - goto bad_hash; - } - } -out: - bch2_trans_iter_exit(trans, &iter); - printbuf_exit(&buf); - return ret; -bad_hash: - if (fsck_err(trans, hash_table_key_wrong_offset, - "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n %s", - bch2_btree_id_str(desc.btree_id), hash_k.k->p.inode, hash_k.k->p.offset, hash, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf))) { - struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, hash_k); - if (IS_ERR(new)) - return PTR_ERR(new); - - k = bch2_hash_set_or_get_in_snapshot(trans, &iter, desc, hash_info, - (subvol_inum) { 0, hash_k.k->p.inode }, - hash_k.k->p.snapshot, new, - STR_HASH_must_create| - BTREE_ITER_with_updates| - BTREE_UPDATE_internal_snapshot_node); - ret = bkey_err(k); - if (ret) - goto out; - if (k.k) - goto duplicate_entries; - - ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter, - BTREE_UPDATE_internal_snapshot_node) ?: - fsck_update_backpointers(trans, s, desc, hash_info, new) ?: - bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: - -BCH_ERR_transaction_restart_nested; - goto out; - } -fsck_err: - goto out; -duplicate_entries: - ret = hash_pick_winner(trans, desc, hash_info, hash_k, k); - if (ret < 0) - goto out; - - if (!fsck_err(trans, hash_table_key_duplicate, - "duplicate hash table keys%s:\n%s", - ret != 2 ? "" : ", both point to valid inodes", - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, hash_k), - prt_newline(&buf), - bch2_bkey_val_to_text(&buf, c, k), - buf.buf))) - goto out; - - switch (ret) { - case 0: - ret = bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0); - break; - case 1: - ret = bch2_hash_delete_at(trans, desc, hash_info, &iter, 0); - break; - case 2: - ret = fsck_rename_dirent(trans, s, desc, hash_info, bkey_s_c_to_dirent(hash_k)) ?: - bch2_hash_delete_at(trans, desc, hash_info, k_iter, 0); - goto out; - } - - ret = bch2_trans_commit(trans, NULL, NULL, 0) ?: - -BCH_ERR_transaction_restart_nested; - goto out; -} - -static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, - struct btree_iter *iter, - struct bpos pos) -{ - return bch2_bkey_get_iter_typed(trans, iter, BTREE_ID_dirents, pos, 0, dirent); -} - static struct bkey_s_c_dirent inode_get_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, @@ -1260,12 +1110,43 @@ static int get_snapshot_root_inode(struct btree_trans *trans, goto err; BUG(); found_root: - BUG_ON(bch2_inode_unpack(k, root)); + ret = bch2_inode_unpack(k, root); err: bch2_trans_iter_exit(trans, &iter); return ret; } +static int check_directory_size(struct btree_trans *trans, + struct bch_inode_unpacked *inode_u, + struct bkey_s_c inode_k, bool *write_inode) +{ + struct btree_iter iter; + struct bkey_s_c k; + u64 new_size = 0; + int ret; + + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, + SPOS(inode_k.k->p.offset, 0, inode_k.k->p.snapshot), + POS(inode_k.k->p.offset, U64_MAX), + 0, k, ret) { + if (k.k->type != KEY_TYPE_dirent) + continue; + + struct bkey_s_c_dirent dirent = bkey_s_c_to_dirent(k); + struct qstr name = bch2_dirent_get_name(dirent); + + new_size += dirent_occupied_size(&name); + } + bch2_trans_iter_exit(trans, &iter); + + if (!ret && inode_u->bi_size != new_size) { + inode_u->bi_size = new_size; + *write_inode = true; + } + + return ret; +} + static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, @@ -1291,7 +1172,9 @@ static int check_inode(struct btree_trans *trans, if (!bkey_is_inode(k.k)) return 0; - BUG_ON(bch2_inode_unpack(k, &u)); + ret = bch2_inode_unpack(k, &u); + if (ret) + goto err; if (snapshot_root->bi_inum != u.bi_inum) { ret = get_snapshot_root_inode(trans, snapshot_root, u.bi_inum); @@ -1302,7 +1185,7 @@ static int check_inode(struct btree_trans *trans, if (fsck_err_on(u.bi_hash_seed != snapshot_root->bi_hash_seed || INODE_STR_HASH(&u) != INODE_STR_HASH(snapshot_root), trans, inode_snapshot_mismatch, - "inodes in different snapshots don't match")) { + "inode hash info in different snapshots don't match")) { u.bi_hash_seed = snapshot_root->bi_hash_seed; SET_INODE_STR_HASH(&u, INODE_STR_HASH(snapshot_root)); do_update = true; @@ -1392,7 +1275,7 @@ static int check_inode(struct btree_trans *trans, if (fsck_err_on(!ret, trans, inode_unlinked_and_not_open, - "inode %llu%u unlinked and not open", + "inode %llu:%u unlinked and not open", u.bi_inum, u.bi_snapshot)) { ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); bch_err_msg(c, ret, "in fsck deleting inode"); @@ -1415,7 +1298,7 @@ static int check_inode(struct btree_trans *trans, if (u.bi_subvol) { struct bch_subvolume s; - ret = bch2_subvolume_get(trans, u.bi_subvol, false, 0, &s); + ret = bch2_subvolume_get(trans, u.bi_subvol, false, &s); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; @@ -1441,6 +1324,27 @@ static int check_inode(struct btree_trans *trans, do_update = true; } } + + if (fsck_err_on(u.bi_journal_seq > journal_cur_seq(&c->journal), + trans, inode_journal_seq_in_future, + "inode journal seq in future (currently at %llu)\n%s", + journal_cur_seq(&c->journal), + (printbuf_reset(&buf), + bch2_inode_unpacked_to_text(&buf, &u), + buf.buf))) { + u.bi_journal_seq = journal_cur_seq(&c->journal); + do_update = true; + } + + if (S_ISDIR(u.bi_mode)) { + ret = check_directory_size(trans, &u, k, &do_update); + + fsck_err_on(ret, + trans, directory_size_mismatch, + "directory inode %llu:%u with the mismatch directory size", + u.bi_inum, k.k->p.snapshot); + ret = 0; + } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); @@ -1502,7 +1406,9 @@ static int find_oldest_inode_needs_reattach(struct btree_trans *trans, break; struct bch_inode_unpacked parent_inode; - bch2_inode_unpack(k, &parent_inode); + ret = bch2_inode_unpack(k, &parent_inode); + if (ret) + break; if (!inode_should_reattach(&parent_inode)) break; @@ -1525,7 +1431,9 @@ static int check_unreachable_inode(struct btree_trans *trans, return 0; struct bch_inode_unpacked inode; - BUG_ON(bch2_inode_unpack(k, &inode)); + ret = bch2_inode_unpack(k, &inode); + if (ret) + return ret; if (!inode_should_reattach(&inode)) return 0; @@ -1649,7 +1557,7 @@ static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_wal if (i->count != count2) { bch_err_ratelimited(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu", w->last_pos.inode, i->snapshot, i->count, count2); - return -BCH_ERR_internal_fsck_err; + i->count = count2; } if (fsck_err_on(!(i->inode.bi_flags & BCH_INODE_i_sectors_dirty), @@ -1753,7 +1661,7 @@ static int overlapping_extents_found(struct btree_trans *trans, bch2_trans_iter_init(trans, &iter1, btree, pos1, BTREE_ITER_all_snapshots| BTREE_ITER_not_extents); - k1 = bch2_btree_iter_peek_upto(&iter1, POS(pos1.inode, U64_MAX)); + k1 = bch2_btree_iter_peek_max(&iter1, POS(pos1.inode, U64_MAX)); ret = bkey_err(k1); if (ret) goto err; @@ -1778,7 +1686,7 @@ static int overlapping_extents_found(struct btree_trans *trans, while (1) { bch2_btree_iter_advance(&iter2); - k2 = bch2_btree_iter_peek_upto(&iter2, POS(pos1.inode, U64_MAX)); + k2 = bch2_btree_iter_peek_max(&iter2, POS(pos1.inode, U64_MAX)); ret = bkey_err(k2); if (ret) goto err; @@ -2156,7 +2064,7 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, return __bch2_fsck_write_inode(trans, target); } - if (bch2_inode_should_have_bp(target) && + if (bch2_inode_should_have_single_bp(target) && !fsck_err(trans, inode_wrong_backpointer, "dirent points to inode that does not point back:\n %s", (bch2_bkey_val_to_text(&buf, c, d.s_c), @@ -2480,7 +2388,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, *hash_info = bch2_hash_info_init(c, &i->inode); dir->first_this_inode = false; - ret = hash_check_key(trans, s, bch2_dirent_hash_desc, hash_info, iter, k); + ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, k); if (ret < 0) goto err; if (ret) { @@ -2519,6 +2427,30 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; } + + darray_for_each(target->deletes, i) + if (fsck_err_on(!snapshot_list_has_id(&s->ids, *i), + trans, dirent_to_overwritten_inode, + "dirent points to inode overwritten in snapshot %u:\n%s", + *i, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), + buf.buf))) { + struct btree_iter delete_iter; + bch2_trans_iter_init(trans, &delete_iter, + BTREE_ID_dirents, + SPOS(k.k->p.inode, k.k->p.offset, *i), + BTREE_ITER_intent); + ret = bch2_btree_iter_traverse(&delete_iter) ?: + bch2_hash_delete_at(trans, bch2_dirent_hash_desc, + hash_info, + &delete_iter, + BTREE_UPDATE_internal_snapshot_node); + bch2_trans_iter_exit(trans, &delete_iter); + if (ret) + goto err; + + } } ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); @@ -2594,7 +2526,7 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter, *hash_info = bch2_hash_info_init(c, &i->inode); inode->first_this_inode = false; - ret = hash_check_key(trans, NULL, bch2_xattr_hash_desc, hash_info, iter, k); + ret = bch2_str_hash_check_key(trans, NULL, &bch2_xattr_hash_desc, hash_info, iter, k); bch_err_fn(c, ret); return ret; } @@ -2774,6 +2706,48 @@ struct pathbuf_entry { typedef DARRAY(struct pathbuf_entry) pathbuf; +static int bch2_bi_depth_renumber_one(struct btree_trans *trans, struct pathbuf_entry *p, + u32 new_depth) +{ + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + SPOS(0, p->inum, p->snapshot), 0); + + struct bch_inode_unpacked inode; + int ret = bkey_err(k) ?: + !bkey_is_inode(k.k) ? -BCH_ERR_ENOENT_inode + : bch2_inode_unpack(k, &inode); + if (ret) + goto err; + + if (inode.bi_depth != new_depth) { + inode.bi_depth = new_depth; + ret = __bch2_fsck_write_inode(trans, &inode) ?: + bch2_trans_commit(trans, NULL, NULL, 0); + } +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 new_bi_depth) +{ + u32 restart_count = trans->restart_count; + int ret = 0; + + darray_for_each_reverse(*path, i) { + ret = nested_lockrestart_do(trans, + bch2_bi_depth_renumber_one(trans, i, new_bi_depth)); + bch_err_fn(trans->c, ret); + if (ret) + break; + + new_bi_depth++; + } + + return ret ?: trans_was_restarted(trans, restart_count); +} + static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot) { darray_for_each(*p, i) @@ -2783,21 +2757,21 @@ static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot) return false; } -static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c inode_k) +static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) { struct bch_fs *c = trans->c; struct btree_iter inode_iter = {}; - struct bch_inode_unpacked inode; + pathbuf path = {}; struct printbuf buf = PRINTBUF; u32 snapshot = inode_k.k->p.snapshot; + bool redo_bi_depth = false; + u32 min_bi_depth = U32_MAX; int ret = 0; - p->nr = 0; - - BUG_ON(bch2_inode_unpack(inode_k, &inode)); - - if (!S_ISDIR(inode.bi_mode)) - return 0; + struct bch_inode_unpacked inode; + ret = bch2_inode_unpack(inode_k, &inode); + if (ret) + return ret; while (!inode.bi_subvol) { struct btree_iter dirent_iter; @@ -2807,7 +2781,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino d = inode_get_dirent(trans, &dirent_iter, &inode, &parent_snapshot); ret = bkey_err(d.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) - break; + goto out; if (!ret && (ret = dirent_points_to_inode(c, d, &inode))) bch2_trans_iter_exit(trans, &dirent_iter); @@ -2822,7 +2796,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino bch2_trans_iter_exit(trans, &dirent_iter); - ret = darray_push(p, ((struct pathbuf_entry) { + ret = darray_push(&path, ((struct pathbuf_entry) { .inum = inode.bi_inum, .snapshot = snapshot, })); @@ -2834,22 +2808,32 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino bch2_trans_iter_exit(trans, &inode_iter); inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, inode.bi_dir, snapshot), 0); + + struct bch_inode_unpacked parent_inode; ret = bkey_err(inode_k) ?: !bkey_is_inode(inode_k.k) ? -BCH_ERR_ENOENT_inode - : bch2_inode_unpack(inode_k, &inode); + : bch2_inode_unpack(inode_k, &parent_inode); if (ret) { /* Should have been caught in dirents pass */ bch_err_msg(c, ret, "error looking up parent directory"); - break; + goto out; } + min_bi_depth = parent_inode.bi_depth; + + if (parent_inode.bi_depth < inode.bi_depth && + min_bi_depth < U16_MAX) + break; + + inode = parent_inode; snapshot = inode_k.k->p.snapshot; + redo_bi_depth = true; - if (path_is_dup(p, inode.bi_inum, snapshot)) { + if (path_is_dup(&path, inode.bi_inum, snapshot)) { /* XXX print path */ bch_err(c, "directory structure loop"); - darray_for_each(*p, i) + darray_for_each(path, i) pr_err("%llu:%u", i->inum, i->snapshot); pr_err("%llu:%u", inode.bi_inum, snapshot); @@ -2862,12 +2846,20 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); } - break; + + goto out; } } + + if (inode.bi_subvol) + min_bi_depth = 0; + + if (redo_bi_depth) + ret = bch2_bi_depth_renumber(trans, &path, min_bi_depth); out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); + darray_exit(&path); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; @@ -2879,24 +2871,20 @@ fsck_err: */ int bch2_check_directory_structure(struct bch_fs *c) { - pathbuf path = { 0, }; - int ret; - - ret = bch2_trans_run(c, + int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ - if (!bkey_is_inode(k.k)) + if (!S_ISDIR(bkey_inode_mode(k))) continue; if (bch2_inode_flags(k) & BCH_INODE_unlinked) continue; - check_path(trans, &path, k); + check_path_loop(trans, k); }))); - darray_exit(&path); bch_err_fn(c, ret); return ret; @@ -2994,7 +2982,9 @@ static int check_nlinks_find_hardlinks(struct bch_fs *c, /* Should never fail, checked by bch2_inode_invalid: */ struct bch_inode_unpacked u; - BUG_ON(bch2_inode_unpack(k, &u)); + _ret3 = bch2_inode_unpack(k, &u); + if (_ret3) + break; /* * Backpointer and directory structure checks are sufficient for @@ -3072,7 +3062,9 @@ static int check_nlinks_update_inode(struct btree_trans *trans, struct btree_ite if (!bkey_is_inode(k.k)) return 0; - BUG_ON(bch2_inode_unpack(k, &u)); + ret = bch2_inode_unpack(k, &u); + if (ret) + return ret; if (S_ISDIR(u.bi_mode)) return 0; @@ -3194,3 +3186,223 @@ int bch2_fix_reflink_p(struct bch_fs *c) bch_err_fn(c, ret); return ret; } + +#ifndef NO_BCACHEFS_CHARDEV + +struct fsck_thread { + struct thread_with_stdio thr; + struct bch_fs *c; + struct bch_opts opts; +}; + +static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) +{ + struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); + kfree(thr); +} + +static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) +{ + struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); + struct bch_fs *c = thr->c; + + int ret = PTR_ERR_OR_ZERO(c); + if (ret) + return ret; + + ret = bch2_fs_start(thr->c); + if (ret) + goto err; + + if (test_bit(BCH_FS_errors_fixed, &c->flags)) { + bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); + ret |= 1; + } + if (test_bit(BCH_FS_error, &c->flags)) { + bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); + ret |= 4; + } +err: + bch2_fs_stop(c); + return ret; +} + +static const struct thread_with_stdio_ops bch2_offline_fsck_ops = { + .exit = bch2_fsck_thread_exit, + .fn = bch2_fsck_offline_thread_fn, +}; + +long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg) +{ + struct bch_ioctl_fsck_offline arg; + struct fsck_thread *thr = NULL; + darray_str(devs) = {}; + long ret = 0; + + if (copy_from_user(&arg, user_arg, sizeof(arg))) + return -EFAULT; + + if (arg.flags) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + for (size_t i = 0; i < arg.nr_devs; i++) { + u64 dev_u64; + ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); + if (ret) + goto err; + + char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); + ret = PTR_ERR_OR_ZERO(dev_str); + if (ret) + goto err; + + ret = darray_push(&devs, dev_str); + if (ret) { + kfree(dev_str); + goto err; + } + } + + thr = kzalloc(sizeof(*thr), GFP_KERNEL); + if (!thr) { + ret = -ENOMEM; + goto err; + } + + thr->opts = bch2_opts_empty(); + + if (arg.opts) { + char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); + ret = PTR_ERR_OR_ZERO(optstr) ?: + bch2_parse_mount_opts(NULL, &thr->opts, NULL, optstr); + if (!IS_ERR(optstr)) + kfree(optstr); + + if (ret) + goto err; + } + + opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); + opt_set(thr->opts, read_only, 1); + opt_set(thr->opts, ratelimit_errors, 0); + + /* We need request_key() to be called before we punt to kthread: */ + opt_set(thr->opts, nostart, true); + + bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); + + thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts); + + if (!IS_ERR(thr->c) && + thr->c->opts.errors == BCH_ON_ERROR_panic) + thr->c->opts.errors = BCH_ON_ERROR_ro; + + ret = __bch2_run_thread_with_stdio(&thr->thr); +out: + darray_for_each(devs, i) + kfree(*i); + darray_exit(&devs); + return ret; +err: + if (thr) + bch2_fsck_thread_exit(&thr->thr); + pr_err("ret %s", bch2_err_str(ret)); + goto out; +} + +static int bch2_fsck_online_thread_fn(struct thread_with_stdio *stdio) +{ + struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); + struct bch_fs *c = thr->c; + + c->stdio_filter = current; + c->stdio = &thr->thr.stdio; + + /* + * XXX: can we figure out a way to do this without mucking with c->opts? + */ + unsigned old_fix_errors = c->opts.fix_errors; + if (opt_defined(thr->opts, fix_errors)) + c->opts.fix_errors = thr->opts.fix_errors; + else + c->opts.fix_errors = FSCK_FIX_ask; + + c->opts.fsck = true; + set_bit(BCH_FS_fsck_running, &c->flags); + + c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info; + int ret = bch2_run_online_recovery_passes(c); + + clear_bit(BCH_FS_fsck_running, &c->flags); + bch_err_fn(c, ret); + + c->stdio = NULL; + c->stdio_filter = NULL; + c->opts.fix_errors = old_fix_errors; + + up(&c->online_fsck_mutex); + bch2_ro_ref_put(c); + return ret; +} + +static const struct thread_with_stdio_ops bch2_online_fsck_ops = { + .exit = bch2_fsck_thread_exit, + .fn = bch2_fsck_online_thread_fn, +}; + +long bch2_ioctl_fsck_online(struct bch_fs *c, struct bch_ioctl_fsck_online arg) +{ + struct fsck_thread *thr = NULL; + long ret = 0; + + if (arg.flags) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!bch2_ro_ref_tryget(c)) + return -EROFS; + + if (down_trylock(&c->online_fsck_mutex)) { + bch2_ro_ref_put(c); + return -EAGAIN; + } + + thr = kzalloc(sizeof(*thr), GFP_KERNEL); + if (!thr) { + ret = -ENOMEM; + goto err; + } + + thr->c = c; + thr->opts = bch2_opts_empty(); + + if (arg.opts) { + char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); + + ret = PTR_ERR_OR_ZERO(optstr) ?: + bch2_parse_mount_opts(c, &thr->opts, NULL, optstr); + if (!IS_ERR(optstr)) + kfree(optstr); + + if (ret) + goto err; + } + + ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_online_fsck_ops); +err: + if (ret < 0) { + bch_err_fn(c, ret); + if (thr) + bch2_fsck_thread_exit(&thr->thr); + up(&c->online_fsck_mutex); + bch2_ro_ref_put(c); + } + return ret; +} + +#endif /* NO_BCACHEFS_CHARDEV */ diff --git a/fs/bcachefs/fsck.h b/fs/bcachefs/fsck.h index 1cca31011530..574948278cd4 100644 --- a/fs/bcachefs/fsck.h +++ b/fs/bcachefs/fsck.h @@ -2,6 +2,14 @@ #ifndef _BCACHEFS_FSCK_H #define _BCACHEFS_FSCK_H +#include "str_hash.h" + +int bch2_fsck_update_backpointers(struct btree_trans *, + struct snapshots_seen *, + const struct bch_hash_desc, + struct bch_hash_info *, + struct bkey_i *); + int bch2_check_inodes(struct bch_fs *); int bch2_check_extents(struct bch_fs *); int bch2_check_indirect_extents(struct bch_fs *); @@ -14,4 +22,7 @@ int bch2_check_directory_structure(struct bch_fs *); int bch2_check_nlinks(struct bch_fs *); int bch2_fix_reflink_p(struct bch_fs *); +long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *); +long bch2_ioctl_fsck_online(struct bch_fs *, struct bch_ioctl_fsck_online); + #endif /* _BCACHEFS_FSCK_H */ diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 039cb7a22244..04ec05206f8c 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -14,6 +14,7 @@ #include "extent_update.h" #include "fs.h" #include "inode.h" +#include "opts.h" #include "str_hash.h" #include "snapshot.h" #include "subvolume.h" @@ -47,10 +48,10 @@ static int inode_decode_field(const u8 *in, const u8 *end, u8 *p; if (in >= end) - return -1; + return -BCH_ERR_inode_unpack_error; if (!*in) - return -1; + return -BCH_ERR_inode_unpack_error; /* * position of highest set bit indicates number of bytes: @@ -60,7 +61,7 @@ static int inode_decode_field(const u8 *in, const u8 *end, bytes = byte_table[shift - 1]; if (in + bytes > end) - return -1; + return -BCH_ERR_inode_unpack_error; p = (u8 *) be + 16 - bytes; memcpy(p, in, bytes); @@ -176,7 +177,7 @@ static noinline int bch2_inode_unpack_v1(struct bkey_s_c_inode inode, return ret; \ \ if (field_bits > sizeof(unpacked->_name) * 8) \ - return -1; \ + return -BCH_ERR_inode_unpack_error; \ \ unpacked->_name = field[1]; \ in += ret; @@ -217,7 +218,7 @@ static int bch2_inode_unpack_v2(struct bch_inode_unpacked *unpacked, \ unpacked->_name = v[0]; \ if (v[1] || v[0] != unpacked->_name) \ - return -1; \ + return -BCH_ERR_inode_unpack_error; \ fieldnr++; BCH_INODE_FIELDS_v2() @@ -268,7 +269,7 @@ static int bch2_inode_unpack_v3(struct bkey_s_c k, \ unpacked->_name = v[0]; \ if (v[1] || v[0] != unpacked->_name) \ - return -1; \ + return -BCH_ERR_inode_unpack_error; \ fieldnr++; BCH_INODE_FIELDS_v3() @@ -428,7 +429,7 @@ struct bkey_i *bch2_inode_to_v3(struct btree_trans *trans, struct bkey_i *k) } static int __bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bch_inode_unpacked unpacked; int ret = 0; @@ -468,7 +469,7 @@ fsck_err: } int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_inode inode = bkey_s_c_to_inode(k); int ret = 0; @@ -478,13 +479,13 @@ int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, "invalid str hash type (%llu >= %u)", INODEv1_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_validate(c, k, flags); + ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_inode_v2 inode = bkey_s_c_to_inode_v2(k); int ret = 0; @@ -494,13 +495,13 @@ int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k, "invalid str hash type (%llu >= %u)", INODEv2_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_validate(c, k, flags); + ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_inode_v3 inode = bkey_s_c_to_inode_v3(k); int ret = 0; @@ -518,7 +519,7 @@ int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k, "invalid str hash type (%llu >= %u)", INODEv3_STR_HASH(inode.v), BCH_STR_HASH_NR); - ret = __bch2_inode_validate(c, k, flags); + ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } @@ -617,7 +618,7 @@ bch2_bkey_get_iter_snapshot_parent(struct btree_trans *trans, struct btree_iter struct bkey_s_c k; int ret = 0; - for_each_btree_key_upto_norestart(trans, *iter, btree, + for_each_btree_key_max_norestart(trans, *iter, btree, bpos_successor(pos), SPOS(pos.inode, pos.offset, U32_MAX), flags|BTREE_ITER_all_snapshots, k, ret) @@ -652,7 +653,7 @@ int __bch2_inode_has_child_snapshots(struct btree_trans *trans, struct bpos pos) struct bkey_s_c k; int ret = 0; - for_each_btree_key_upto_norestart(trans, iter, + for_each_btree_key_max_norestart(trans, iter, BTREE_ID_inodes, POS(0, pos.offset), bpos_predecessor(pos), BTREE_ITER_all_snapshots| BTREE_ITER_with_updates, k, ret) @@ -779,7 +780,7 @@ int bch2_trigger_inode(struct btree_trans *trans, } int bch2_inode_generation_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -798,6 +799,28 @@ void bch2_inode_generation_to_text(struct printbuf *out, struct bch_fs *c, prt_printf(out, "generation: %u", le32_to_cpu(gen.v->bi_generation)); } +int bch2_inode_alloc_cursor_validate(struct bch_fs *c, struct bkey_s_c k, + struct bkey_validate_context from) +{ + int ret = 0; + + bkey_fsck_err_on(k.k->p.inode != LOGGED_OPS_INUM_inode_cursors, + c, inode_alloc_cursor_inode_bad, + "k.p.inode bad"); +fsck_err: + return ret; +} + +void bch2_inode_alloc_cursor_to_text(struct printbuf *out, struct bch_fs *c, + struct bkey_s_c k) +{ + struct bkey_s_c_inode_alloc_cursor i = bkey_s_c_to_inode_alloc_cursor(k); + + prt_printf(out, "idx %llu generation %llu", + le64_to_cpu(i.v->idx), + le64_to_cpu(i.v->gen)); +} + void bch2_inode_init_early(struct bch_fs *c, struct bch_inode_unpacked *inode_u) { @@ -858,43 +881,78 @@ static inline u32 bkey_generation(struct bkey_s_c k) } } -/* - * This just finds an empty slot: - */ -int bch2_inode_create(struct btree_trans *trans, - struct btree_iter *iter, - struct bch_inode_unpacked *inode_u, - u32 snapshot, u64 cpu) +static struct bkey_i_inode_alloc_cursor * +bch2_inode_alloc_cursor_get(struct btree_trans *trans, u64 cpu, u64 *min, u64 *max) { struct bch_fs *c = trans->c; - struct bkey_s_c k; - u64 min, max, start, pos, *hint; - int ret = 0; - unsigned bits = (c->opts.inodes_32bit ? 31 : 63); - if (c->opts.shard_inode_numbers) { - bits -= c->inode_shard_bits; + u64 cursor_idx = c->opts.inodes_32bit ? 0 : cpu + 1; - min = (cpu << bits); - max = (cpu << bits) | ~(ULLONG_MAX << bits); + cursor_idx &= ~(~0ULL << c->opts.shard_inode_numbers_bits); - min = max_t(u64, min, BLOCKDEV_INODE_MAX); - hint = c->unused_inode_hints + cpu; + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, + BTREE_ID_logged_ops, + POS(LOGGED_OPS_INUM_inode_cursors, cursor_idx), + BTREE_ITER_cached); + int ret = bkey_err(k); + if (ret) + return ERR_PTR(ret); + + struct bkey_i_inode_alloc_cursor *cursor = + k.k->type == KEY_TYPE_inode_alloc_cursor + ? bch2_bkey_make_mut_typed(trans, &iter, &k, 0, inode_alloc_cursor) + : bch2_bkey_alloc(trans, &iter, 0, inode_alloc_cursor); + ret = PTR_ERR_OR_ZERO(cursor); + if (ret) + goto err; + + if (c->opts.inodes_32bit) { + *min = BLOCKDEV_INODE_MAX; + *max = INT_MAX; } else { - min = BLOCKDEV_INODE_MAX; - max = ~(ULLONG_MAX << bits); - hint = c->unused_inode_hints; + cursor->v.bits = c->opts.shard_inode_numbers_bits; + + unsigned bits = 63 - c->opts.shard_inode_numbers_bits; + + *min = max(cpu << bits, (u64) INT_MAX + 1); + *max = (cpu << bits) | ~(ULLONG_MAX << bits); } - start = READ_ONCE(*hint); + if (le64_to_cpu(cursor->v.idx) < *min) + cursor->v.idx = cpu_to_le64(*min); - if (start >= max || start < min) - start = min; + if (le64_to_cpu(cursor->v.idx) >= *max) { + cursor->v.idx = cpu_to_le64(*min); + le32_add_cpu(&cursor->v.gen, 1); + } +err: + bch2_trans_iter_exit(trans, &iter); + return ret ? ERR_PTR(ret) : cursor; +} + +/* + * This just finds an empty slot: + */ +int bch2_inode_create(struct btree_trans *trans, + struct btree_iter *iter, + struct bch_inode_unpacked *inode_u, + u32 snapshot, u64 cpu) +{ + u64 min, max; + struct bkey_i_inode_alloc_cursor *cursor = + bch2_inode_alloc_cursor_get(trans, cpu, &min, &max); + int ret = PTR_ERR_OR_ZERO(cursor); + if (ret) + return ret; + + u64 start = le64_to_cpu(cursor->v.idx); + u64 pos = start; - pos = start; bch2_trans_iter_init(trans, iter, BTREE_ID_inodes, POS(0, pos), BTREE_ITER_all_snapshots| BTREE_ITER_intent); + struct bkey_s_c k; again: while ((k = bch2_btree_iter_peek(iter)).k && !(ret = bkey_err(k)) && @@ -924,6 +982,7 @@ again: /* Retry from start */ pos = start = min; bch2_btree_iter_set_pos(iter, POS(0, pos)); + le32_add_cpu(&cursor->v.gen, 1); goto again; found_slot: bch2_btree_iter_set_pos(iter, SPOS(0, pos, snapshot)); @@ -934,9 +993,9 @@ found_slot: return ret; } - *hint = k.k->p.offset; inode_u->bi_inum = k.k->p.offset; - inode_u->bi_generation = bkey_generation(k); + inode_u->bi_generation = le64_to_cpu(cursor->v.gen); + cursor->v.idx = cpu_to_le64(k.k->p.offset + 1); return 0; } @@ -966,7 +1025,7 @@ static int bch2_inode_delete_keys(struct btree_trans *trans, bch2_btree_iter_set_snapshot(&iter, snapshot); - k = bch2_btree_iter_peek_upto(&iter, end); + k = bch2_btree_iter_peek_max(&iter, end); ret = bkey_err(k); if (ret) goto err; @@ -998,8 +1057,6 @@ int bch2_inode_rm(struct bch_fs *c, subvol_inum inum) { struct btree_trans *trans = bch2_trans_get(c); struct btree_iter iter = { NULL }; - struct bkey_i_inode_generation delete; - struct bch_inode_unpacked inode_u; struct bkey_s_c k; u32 snapshot; int ret; @@ -1039,13 +1096,7 @@ retry: goto err; } - bch2_inode_unpack(k, &inode_u); - - bkey_inode_generation_init(&delete.k_i); - delete.k.p = iter.pos; - delete.v.bi_generation = cpu_to_le32(inode_u.bi_generation + 1); - - ret = bch2_trans_update(trans, &iter, &delete.k_i, 0) ?: + ret = bch2_btree_delete_at(trans, &iter, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); err: @@ -1141,12 +1192,17 @@ struct bch_opts bch2_inode_opts_to_opts(struct bch_inode_unpacked *inode) void bch2_inode_opts_get(struct bch_io_opts *opts, struct bch_fs *c, struct bch_inode_unpacked *inode) { -#define x(_name, _bits) opts->_name = inode_opt_get(c, inode, _name); +#define x(_name, _bits) \ + if ((inode)->bi_##_name) { \ + opts->_name = inode->bi_##_name - 1; \ + opts->_name##_from_inode = true; \ + } else { \ + opts->_name = c->opts._name; \ + } BCH_INODE_OPTS() #undef x - if (opts->nocow) - opts->compression = opts->background_compression = opts->data_checksum = opts->erasure_code = 0; + bch2_io_opts_fixups(opts); } int bch2_inum_opts_get(struct btree_trans *trans, subvol_inum inum, struct bch_io_opts *opts) @@ -1380,7 +1436,8 @@ again: NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ ret = may_delete_deleted_inode(trans, &iter, k.k->p, &need_another_pass); if (ret > 0) { - bch_verbose(c, "deleting unlinked inode %llu:%u", k.k->p.offset, k.k->p.snapshot); + bch_verbose_ratelimited(c, "deleting unlinked inode %llu:%u", + k.k->p.offset, k.k->p.snapshot); ret = bch2_inode_rm_snapshot(trans, k.k->p.offset, k.k->p.snapshot); /* diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index eab82b5eb897..d2e134528f0e 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -7,15 +7,14 @@ #include "opts.h" #include "snapshot.h" -enum bch_validate_flags; extern const char * const bch2_inode_opts[]; int bch2_inode_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); int bch2_inode_v2_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); int bch2_inode_v3_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_inode_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int __bch2_inode_has_child_snapshots(struct btree_trans *, struct bpos); @@ -60,7 +59,7 @@ static inline bool bkey_is_inode(const struct bkey *k) } int bch2_inode_generation_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_inode_generation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_inode_generation ((struct bkey_ops) { \ @@ -69,6 +68,16 @@ void bch2_inode_generation_to_text(struct printbuf *, struct bch_fs *, struct bk .min_val_size = 8, \ }) +int bch2_inode_alloc_cursor_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); +void bch2_inode_alloc_cursor_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); + +#define bch2_bkey_ops_inode_alloc_cursor ((struct bkey_ops) { \ + .key_validate = bch2_inode_alloc_cursor_validate, \ + .val_to_text = bch2_inode_alloc_cursor_to_text, \ + .min_val_size = 16, \ +}) + #if 0 typedef struct { u64 lo; @@ -220,6 +229,20 @@ static inline u32 bch2_inode_flags(struct bkey_s_c k) } } +static inline unsigned bkey_inode_mode(struct bkey_s_c k) +{ + switch (k.k->type) { + case KEY_TYPE_inode: + return le16_to_cpu(bkey_s_c_to_inode(k).v->bi_mode); + case KEY_TYPE_inode_v2: + return le16_to_cpu(bkey_s_c_to_inode_v2(k).v->bi_mode); + case KEY_TYPE_inode_v3: + return INODEv3_MODE(bkey_s_c_to_inode_v3(k).v); + default: + return 0; + } +} + /* i_nlink: */ static inline unsigned nlink_bias(umode_t mode) @@ -249,7 +272,7 @@ static inline void bch2_inode_nlink_set(struct bch_inode_unpacked *bi, int bch2_inode_nlink_inc(struct bch_inode_unpacked *); void bch2_inode_nlink_dec(struct btree_trans *, struct bch_inode_unpacked *); -static inline bool bch2_inode_should_have_bp(struct bch_inode_unpacked *inode) +static inline bool bch2_inode_should_have_single_bp(struct bch_inode_unpacked *inode) { bool inode_has_bp = inode->bi_dir || inode->bi_dir_offset; @@ -262,6 +285,14 @@ void bch2_inode_opts_get(struct bch_io_opts *, struct bch_fs *, struct bch_inode_unpacked *); int bch2_inum_opts_get(struct btree_trans*, subvol_inum, struct bch_io_opts *); +static inline struct bch_extent_rebalance +bch2_inode_rebalance_opts_get(struct bch_fs *c, struct bch_inode_unpacked *inode) +{ + struct bch_io_opts io_opts; + bch2_inode_opts_get(&io_opts, c, inode); + return io_opts_to_rebalance_opts(&io_opts); +} + int bch2_inode_rm_snapshot(struct btree_trans *, u64, u32); int bch2_delete_dead_inodes(struct bch_fs *); diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h index 7928d0c6954f..b99a5bf1a75e 100644 --- a/fs/bcachefs/inode_format.h +++ b/fs/bcachefs/inode_format.h @@ -101,7 +101,9 @@ struct bch_inode_generation { x(bi_dir_offset, 64) \ x(bi_subvol, 32) \ x(bi_parent_subvol, 32) \ - x(bi_nocow, 8) + x(bi_nocow, 8) \ + x(bi_depth, 32) \ + x(bi_inodes_32bit, 8) /* subset of BCH_INODE_FIELDS */ #define BCH_INODE_OPTS() \ @@ -114,7 +116,8 @@ struct bch_inode_generation { x(foreground_target, 16) \ x(background_target, 16) \ x(erasure_code, 16) \ - x(nocow, 8) + x(nocow, 8) \ + x(inodes_32bit, 8) enum inode_opt_id { #define x(name, ...) \ @@ -164,4 +167,12 @@ LE64_BITMASK(INODEv3_FIELDS_START, struct bch_inode_v3, bi_flags, 31, 36); LE64_BITMASK(INODEv3_MODE, struct bch_inode_v3, bi_flags, 36, 52); +struct bch_inode_alloc_cursor { + struct bch_val v; + __u8 bits; + __u8 pad; + __le32 gen; + __le64 idx; +}; + #endif /* _BCACHEFS_INODE_FORMAT_H */ diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index f283051758d6..5353979117b0 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -113,11 +113,13 @@ int bch2_extent_fallocate(struct btree_trans *trans, err: if (!ret && sectors_allocated) bch2_increment_clock(c, sectors_allocated, WRITE); - if (should_print_err(ret)) - bch_err_inum_offset_ratelimited(c, - inum.inum, - iter->pos.offset << 9, - "%s(): error: %s", __func__, bch2_err_str(ret)); + if (should_print_err(ret)) { + struct printbuf buf = PRINTBUF; + bch2_inum_offset_err_msg_trans(trans, &buf, inum, iter->pos.offset << 9); + prt_printf(&buf, "fallocate error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } err_noprint: bch2_open_buckets_put(c, &open_buckets); bch2_disk_reservation_put(c, &disk_res); @@ -164,9 +166,9 @@ int bch2_fpunch_at(struct btree_trans *trans, struct btree_iter *iter, bch2_btree_iter_set_snapshot(iter, snapshot); /* - * peek_upto() doesn't have ideal semantics for extents: + * peek_max() doesn't have ideal semantics for extents: */ - k = bch2_btree_iter_peek_upto(iter, end_pos); + k = bch2_btree_iter_peek_max(iter, end_pos); if (!k.k) break; @@ -426,8 +428,8 @@ case LOGGED_OP_FINSERT_shift_extents: bch2_btree_iter_set_pos(&iter, SPOS(inum.inum, pos, snapshot)); k = insert - ? bch2_btree_iter_peek_prev(&iter) - : bch2_btree_iter_peek_upto(&iter, POS(inum.inum, U64_MAX)); + ? bch2_btree_iter_peek_prev_min(&iter, POS(inum.inum, 0)) + : bch2_btree_iter_peek_max(&iter, POS(inum.inum, U64_MAX)); if ((ret = bkey_err(k))) goto btree_err; @@ -461,7 +463,7 @@ case LOGGED_OP_FINSERT_shift_extents: op->v.pos = cpu_to_le64(insert ? bkey_start_offset(&delete.k) : delete.k.p.offset); - ret = bch2_bkey_set_needs_rebalance(c, copy, &opts) ?: + ret = bch2_bkey_set_needs_rebalance(c, &opts, copy) ?: bch2_btree_insert_trans(trans, BTREE_ID_extents, &delete, 0) ?: bch2_btree_insert_trans(trans, BTREE_ID_extents, copy, 0) ?: bch2_logged_op_update(trans, &op->k_i) ?: diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index b3b934a87c6d..8c7b2d3d779d 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -21,6 +21,7 @@ #include "io_read.h" #include "io_misc.h" #include "io_write.h" +#include "reflink.h" #include "subvolume.h" #include "trace.h" @@ -90,13 +91,18 @@ static const struct rhashtable_params bch_promote_params = { .automatic_shrinking = true, }; +static inline bool have_io_error(struct bch_io_failures *failed) +{ + return failed && failed->nr; +} + static inline int should_promote(struct bch_fs *c, struct bkey_s_c k, struct bpos pos, struct bch_io_opts opts, unsigned flags, struct bch_io_failures *failed) { - if (!failed) { + if (!have_io_error(failed)) { BUG_ON(!opts.promote_target); if (!(flags & BCH_READ_MAY_PROMOTE)) @@ -223,7 +229,7 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans, struct data_update_opts update_opts = {}; - if (!failed) { + if (!have_io_error(failed)) { update_opts.target = opts.promote_target; update_opts.extra_replicas = 1; update_opts.write_flags = BCH_WRITE_ALLOC_NOWAIT|BCH_WRITE_CACHED; @@ -231,11 +237,11 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans, update_opts.target = opts.foreground_target; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); - unsigned i = 0; + unsigned ptr_bit = 1; bkey_for_each_ptr(ptrs, ptr) { if (bch2_dev_io_failures(failed, ptr->dev)) - update_opts.rewrite_ptrs |= BIT(i); - i++; + update_opts.rewrite_ptrs |= ptr_bit; + ptr_bit <<= 1; } } @@ -285,7 +291,7 @@ static struct promote_op *promote_alloc(struct btree_trans *trans, * if failed != NULL we're not actually doing a promote, we're * recovering from an io/checksum error */ - bool promote_full = (failed || + bool promote_full = (have_io_error(failed) || *read_full || READ_ONCE(c->opts.promote_whole_extents)); /* data might have to be decompressed in the write path: */ @@ -321,6 +327,20 @@ nopromote: /* Read */ +static int bch2_read_err_msg_trans(struct btree_trans *trans, struct printbuf *out, + struct bch_read_bio *rbio, struct bpos read_pos) +{ + return bch2_inum_offset_err_msg_trans(trans, out, + (subvol_inum) { rbio->subvol, read_pos.inode }, + read_pos.offset << 9); +} + +static void bch2_read_err_msg(struct bch_fs *c, struct printbuf *out, + struct bch_read_bio *rbio, struct bpos read_pos) +{ + bch2_trans_run(c, bch2_read_err_msg_trans(trans, out, rbio, read_pos)); +} + #define READ_RETRY_AVOID 1 #define READ_RETRY 2 #define READ_ERR 3 @@ -499,6 +519,29 @@ static void bch2_rbio_error(struct bch_read_bio *rbio, int retry, } } +static void bch2_read_io_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bio *bio = &rbio->bio; + struct bch_fs *c = rbio->c; + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_printf(&buf, "data read error: %s", bch2_blk_status_to_str(bio->bi_status)); + + if (ca) { + bch2_io_error(ca, BCH_MEMBER_ERROR_read); + bch_err_ratelimited(ca, "%s", buf.buf); + } else { + bch_err_ratelimited(c, "%s", buf.buf); + } + + printbuf_exit(&buf); + bch2_rbio_error(rbio, READ_RETRY_AVOID, bio->bi_status); +} + static int __bch2_rbio_narrow_crcs(struct btree_trans *trans, struct bch_read_bio *rbio) { @@ -562,6 +605,73 @@ static noinline void bch2_rbio_narrow_crcs(struct bch_read_bio *rbio) __bch2_rbio_narrow_crcs(trans, rbio)); } +static void bch2_read_csum_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bch_fs *c = rbio->c; + struct bio *src = &rbio->bio; + struct bch_extent_crc_unpacked crc = rbio->pick.crc; + struct nonce nonce = extent_nonce(rbio->version, crc); + struct bch_csum csum = bch2_checksum_bio(c, crc.csum_type, nonce, src); + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_str(&buf, "data "); + bch2_csum_err_msg(&buf, crc.csum_type, rbio->pick.crc.csum, csum); + + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + if (ca) { + bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); + bch_err_ratelimited(ca, "%s", buf.buf); + } else { + bch_err_ratelimited(c, "%s", buf.buf); + } + + bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR); + printbuf_exit(&buf); +} + +static void bch2_read_decompress_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bch_fs *c = rbio->c; + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_str(&buf, "decompression error"); + + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + if (ca) + bch_err_ratelimited(ca, "%s", buf.buf); + else + bch_err_ratelimited(c, "%s", buf.buf); + + bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + printbuf_exit(&buf); +} + +static void bch2_read_decrypt_err(struct work_struct *work) +{ + struct bch_read_bio *rbio = + container_of(work, struct bch_read_bio, work); + struct bch_fs *c = rbio->c; + struct printbuf buf = PRINTBUF; + + bch2_read_err_msg(c, &buf, rbio, rbio->read_pos); + prt_str(&buf, "decrypt error"); + + struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; + if (ca) + bch_err_ratelimited(ca, "%s", buf.buf); + else + bch_err_ratelimited(c, "%s", buf.buf); + + bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + printbuf_exit(&buf); +} + /* Inner part that may run in process context */ static void __bch2_read_endio(struct work_struct *work) { @@ -668,33 +778,13 @@ csum_err: goto out; } - struct printbuf buf = PRINTBUF; - buf.atomic++; - prt_str(&buf, "data "); - bch2_csum_err_msg(&buf, crc.csum_type, rbio->pick.crc.csum, csum); - - struct bch_dev *ca = rbio->have_ioref ? bch2_dev_have_ref(c, rbio->pick.ptr.dev) : NULL; - if (ca) { - bch_err_inum_offset_ratelimited(ca, - rbio->read_pos.inode, - rbio->read_pos.offset << 9, - "data %s", buf.buf); - bch2_io_error(ca, BCH_MEMBER_ERROR_checksum); - } - printbuf_exit(&buf); - bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR); + bch2_rbio_punt(rbio, bch2_read_csum_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); goto out; decompression_err: - bch_err_inum_offset_ratelimited(c, rbio->read_pos.inode, - rbio->read_pos.offset << 9, - "decompression error"); - bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + bch2_rbio_punt(rbio, bch2_read_decompress_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); goto out; decrypt_err: - bch_err_inum_offset_ratelimited(c, rbio->read_pos.inode, - rbio->read_pos.offset << 9, - "decrypt error"); - bch2_rbio_error(rbio, READ_ERR, BLK_STS_IOERR); + bch2_rbio_punt(rbio, bch2_read_decrypt_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); goto out; } @@ -715,16 +805,8 @@ static void bch2_read_endio(struct bio *bio) if (!rbio->split) rbio->bio.bi_end_io = rbio->end_io; - if (bio->bi_status) { - if (ca) { - bch_err_inum_offset_ratelimited(ca, - rbio->read_pos.inode, - rbio->read_pos.offset, - "data read error: %s", - bch2_blk_status_to_str(bio->bi_status)); - bch2_io_error(ca, BCH_MEMBER_ERROR_read); - } - bch2_rbio_error(rbio, READ_RETRY_AVOID, bio->bi_status); + if (unlikely(bio->bi_status)) { + bch2_rbio_punt(rbio, bch2_read_io_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq); return; } @@ -750,45 +832,6 @@ static void bch2_read_endio(struct bio *bio) bch2_rbio_punt(rbio, __bch2_read_endio, context, wq); } -int __bch2_read_indirect_extent(struct btree_trans *trans, - unsigned *offset_into_extent, - struct bkey_buf *orig_k) -{ - struct btree_iter iter; - struct bkey_s_c k; - u64 reflink_offset; - int ret; - - reflink_offset = le64_to_cpu(bkey_i_to_reflink_p(orig_k->k)->v.idx) + - *offset_into_extent; - - k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_reflink, - POS(0, reflink_offset), 0); - ret = bkey_err(k); - if (ret) - goto err; - - if (k.k->type != KEY_TYPE_reflink_v && - k.k->type != KEY_TYPE_indirect_inline_data) { - bch_err_inum_offset_ratelimited(trans->c, - orig_k->k->k.p.inode, - orig_k->k->k.p.offset << 9, - "%llu len %u points to nonexistent indirect extent %llu", - orig_k->k->k.p.offset, - orig_k->k->k.size, - reflink_offset); - bch2_inconsistent_error(trans->c); - ret = -BCH_ERR_missing_indirect_extent; - goto err; - } - - *offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); - bch2_bkey_buf_reassemble(orig_k, trans->c, k); -err: - bch2_trans_iter_exit(trans, &iter); - return ret; -} - static noinline void read_from_stale_dirty_pointer(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c k, @@ -868,15 +911,24 @@ retry_pick: if (!pick_ret) goto hole; - if (pick_ret < 0) { + if (unlikely(pick_ret < 0)) { + struct printbuf buf = PRINTBUF; + bch2_read_err_msg_trans(trans, &buf, orig, read_pos); + prt_printf(&buf, "no device to read from: %s\n ", bch2_err_str(pick_ret)); + bch2_bkey_val_to_text(&buf, c, k); + + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + goto err; + } + + if (unlikely(bch2_csum_type_is_encryption(pick.crc.csum_type)) && !c->chacha20) { struct printbuf buf = PRINTBUF; + bch2_read_err_msg_trans(trans, &buf, orig, read_pos); + prt_printf(&buf, "attempting to read encrypted data without encryption key\n "); bch2_bkey_val_to_text(&buf, c, k); - bch_err_inum_offset_ratelimited(c, - read_pos.inode, read_pos.offset << 9, - "no device to read from: %s\n %s", - bch2_err_str(pick_ret), - buf.buf); + bch_err_ratelimited(c, "%s", buf.buf); printbuf_exit(&buf); goto err; } @@ -942,7 +994,7 @@ retry_pick: bounce = true; } - if (orig->opts.promote_target)// || failed) + if (orig->opts.promote_target || have_io_error(failed)) promote = promote_alloc(trans, iter, k, &pick, orig->opts, flags, &rbio, &bounce, &read_full, failed); @@ -1062,11 +1114,15 @@ get_bio: } if (!rbio->pick.idx) { - if (!rbio->have_ioref) { - bch_err_inum_offset_ratelimited(c, - read_pos.inode, - read_pos.offset << 9, - "no device to read from"); + if (unlikely(!rbio->have_ioref)) { + struct printbuf buf = PRINTBUF; + bch2_read_err_msg_trans(trans, &buf, rbio, read_pos); + prt_printf(&buf, "no device to read from:\n "); + bch2_bkey_val_to_text(&buf, c, k); + + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + bch2_rbio_error(rbio, READ_RETRY_AVOID, BLK_STS_IOERR); goto out; } @@ -1164,7 +1220,6 @@ void __bch2_read(struct bch_fs *c, struct bch_read_bio *rbio, BTREE_ITER_slots); while (1) { - unsigned bytes, sectors, offset_into_extent; enum btree_id data_btree = BTREE_ID_extents; bch2_trans_begin(trans); @@ -1184,9 +1239,9 @@ void __bch2_read(struct bch_fs *c, struct bch_read_bio *rbio, if (ret) goto err; - offset_into_extent = iter.pos.offset - + s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); - sectors = k.k->size - offset_into_extent; + unsigned sectors = k.k->size - offset_into_extent; bch2_bkey_buf_reassemble(&sk, c, k); @@ -1201,9 +1256,9 @@ void __bch2_read(struct bch_fs *c, struct bch_read_bio *rbio, * With indirect extents, the amount of data to read is the min * of the original extent and the indirect extent: */ - sectors = min(sectors, k.k->size - offset_into_extent); + sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent); - bytes = min(sectors, bvec_iter_sectors(bvec_iter)) << 9; + unsigned bytes = min(sectors, bvec_iter_sectors(bvec_iter)) << 9; swap(bvec_iter.bi_size, bytes); if (bvec_iter.bi_size == bytes) @@ -1229,16 +1284,20 @@ err: } bch2_trans_iter_exit(trans, &iter); - bch2_trans_put(trans); - bch2_bkey_buf_exit(&sk, c); if (ret) { - bch_err_inum_offset_ratelimited(c, inum.inum, - bvec_iter.bi_sector << 9, - "read error %i from btree lookup", ret); + struct printbuf buf = PRINTBUF; + bch2_inum_offset_err_msg_trans(trans, &buf, inum, bvec_iter.bi_sector << 9); + prt_printf(&buf, "read error %i from btree lookup", ret); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + rbio->bio.bi_status = BLK_STS_IOERR; bch2_rbio_done(rbio); } + + bch2_trans_put(trans); + bch2_bkey_buf_exit(&sk, c); } void bch2_fs_io_read_exit(struct bch_fs *c) diff --git a/fs/bcachefs/io_read.h b/fs/bcachefs/io_read.h index d9c18bb7d403..a82e8a94ccb6 100644 --- a/fs/bcachefs/io_read.h +++ b/fs/bcachefs/io_read.h @@ -3,6 +3,7 @@ #define _BCACHEFS_IO_READ_H #include "bkey_buf.h" +#include "reflink.h" struct bch_read_bio { struct bch_fs *c; @@ -79,19 +80,32 @@ struct bch_devs_mask; struct cache_promote_op; struct extent_ptr_decoded; -int __bch2_read_indirect_extent(struct btree_trans *, unsigned *, - struct bkey_buf *); - static inline int bch2_read_indirect_extent(struct btree_trans *trans, enum btree_id *data_btree, - unsigned *offset_into_extent, - struct bkey_buf *k) + s64 *offset_into_extent, + struct bkey_buf *extent) { - if (k->k->k.type != KEY_TYPE_reflink_p) + if (extent->k->k.type != KEY_TYPE_reflink_p) return 0; *data_btree = BTREE_ID_reflink; - return __bch2_read_indirect_extent(trans, offset_into_extent, k); + struct btree_iter iter; + struct bkey_s_c k = bch2_lookup_indirect_extent(trans, &iter, + offset_into_extent, + bkey_i_to_s_c_reflink_p(extent->k), + true, 0); + int ret = bkey_err(k); + if (ret) + return ret; + + if (bkey_deleted(k.k)) { + bch2_trans_iter_exit(trans, &iter); + return -BCH_ERR_missing_indirect_extent; + } + + bch2_bkey_buf_reassemble(extent, trans->c, k); + bch2_trans_iter_exit(trans, &iter); + return 0; } enum bch_read_flags { diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index 96720adcfee0..3e71860f66b9 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -164,7 +164,7 @@ int bch2_sum_sector_overwrites(struct btree_trans *trans, bch2_trans_copy_iter(&iter, extent_iter); - for_each_btree_key_upto_continue_norestart(iter, + for_each_btree_key_max_continue_norestart(iter, new->k.p, BTREE_ITER_slots, old, ret) { s64 sectors = min(new->k.p.offset, old.k->p.offset) - max(bkey_start_offset(&new->k), @@ -216,6 +216,7 @@ static inline int bch2_extent_update_i_size_sectors(struct btree_trans *trans, SPOS(0, extent_iter->pos.inode, extent_iter->snapshot), + BTREE_ITER_intent| BTREE_ITER_cached); int ret = bkey_err(k); if (unlikely(ret)) @@ -369,7 +370,7 @@ static int bch2_write_index_default(struct bch_write_op *op) bkey_start_pos(&sk.k->k), BTREE_ITER_slots|BTREE_ITER_intent); - ret = bch2_bkey_set_needs_rebalance(c, sk.k, &op->opts) ?: + ret = bch2_bkey_set_needs_rebalance(c, &op->opts, sk.k) ?: bch2_extent_update(trans, inum, &iter, sk.k, &op->res, op->new_i_size, &op->i_sectors_delta, @@ -395,6 +396,21 @@ static int bch2_write_index_default(struct bch_write_op *op) /* Writes */ +static void __bch2_write_op_error(struct printbuf *out, struct bch_write_op *op, + u64 offset) +{ + bch2_inum_offset_err_msg(op->c, out, + (subvol_inum) { op->subvol, op->pos.inode, }, + offset << 9); + prt_printf(out, "write error%s: ", + op->flags & BCH_WRITE_MOVE ? "(internal move)" : ""); +} + +static void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op) +{ + __bch2_write_op_error(out, op, op->pos.offset); +} + void bch2_submit_wbio_replicas(struct bch_write_bio *wbio, struct bch_fs *c, enum bch_data_type type, const struct bkey_i *k, @@ -531,14 +547,14 @@ static void __bch2_write_index(struct bch_write_op *op) op->written += sectors_start - keylist_sectors(keys); - if (ret && !bch2_err_matches(ret, EROFS)) { + if (unlikely(ret && !bch2_err_matches(ret, EROFS))) { struct bkey_i *insert = bch2_keylist_front(&op->insert_keys); - bch_err_inum_offset_ratelimited(c, - insert->k.p.inode, insert->k.p.offset << 9, - "%s write error while doing btree update: %s", - op->flags & BCH_WRITE_MOVE ? "move" : "user", - bch2_err_str(ret)); + struct printbuf buf = PRINTBUF; + __bch2_write_op_error(&buf, op, bkey_start_offset(&insert->k)); + prt_printf(&buf, "btree update error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); } if (ret) @@ -621,9 +637,7 @@ void bch2_write_point_do_index_updates(struct work_struct *work) while (1) { spin_lock_irq(&wp->writes_lock); - op = list_first_entry_or_null(&wp->writes, struct bch_write_op, wp_list); - if (op) - list_del(&op->wp_list); + op = list_pop_entry(&wp->writes, struct bch_write_op, wp_list); wp_update_state(wp, op != NULL); spin_unlock_irq(&wp->writes_lock); @@ -1080,11 +1094,14 @@ do_write: *_dst = dst; return more; csum_err: - bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s write error: error verifying existing checksum while rewriting existing data (memory corruption?)", - op->flags & BCH_WRITE_MOVE ? "move" : "user"); + { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "error verifying existing checksum while rewriting existing data (memory corruption?)"); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } + ret = -EIO; err: if (to_wbio(dst)->bounce) @@ -1165,7 +1182,7 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op) struct btree_trans *trans = bch2_trans_get(c); for_each_keylist_key(&op->insert_keys, orig) { - int ret = for_each_btree_key_upto_commit(trans, iter, BTREE_ID_extents, + int ret = for_each_btree_key_max_commit(trans, iter, BTREE_ID_extents, bkey_start_pos(&orig->k), orig->k.p, BTREE_ITER_intent, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ @@ -1175,11 +1192,11 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op) if (ret && !bch2_err_matches(ret, EROFS)) { struct bkey_i *insert = bch2_keylist_front(&op->insert_keys); - bch_err_inum_offset_ratelimited(c, - insert->k.p.inode, insert->k.p.offset << 9, - "%s write error while doing btree update: %s", - op->flags & BCH_WRITE_MOVE ? "move" : "user", - bch2_err_str(ret)); + struct printbuf buf = PRINTBUF; + __bch2_write_op_error(&buf, op, bkey_start_offset(&insert->k)); + prt_printf(&buf, "btree update error: %s", bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); } if (ret) { @@ -1339,17 +1356,19 @@ err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) goto retry; + bch2_trans_put(trans); + darray_exit(&buckets); + if (ret) { - bch_err_inum_offset_ratelimited(c, - op->pos.inode, op->pos.offset << 9, - "%s: btree lookup error %s", __func__, bch2_err_str(ret)); + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "%s(): btree lookup error: %s", __func__, bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); op->error = ret; op->flags |= BCH_WRITE_SUBMITTED; } - bch2_trans_put(trans); - darray_exit(&buckets); - /* fallback to cow write path? */ if (!(op->flags & BCH_WRITE_SUBMITTED)) { closure_sync(&op->cl); @@ -1462,14 +1481,14 @@ err: if (ret <= 0) { op->flags |= BCH_WRITE_SUBMITTED; - if (ret < 0) { - if (!(op->flags & BCH_WRITE_ALLOC_NOWAIT)) - bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s(): %s error: %s", __func__, - op->flags & BCH_WRITE_MOVE ? "move" : "user", - bch2_err_str(ret)); + if (unlikely(ret < 0)) { + if (!(op->flags & BCH_WRITE_ALLOC_NOWAIT)) { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "%s(): %s", __func__, bch2_err_str(ret)); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } op->error = ret; break; } @@ -1595,12 +1614,11 @@ CLOSURE_CALLBACK(bch2_write) bch2_keylist_init(&op->insert_keys, op->inline_keys); wbio_init(bio)->put_bio = false; - if (bio->bi_iter.bi_size & (c->opts.block_size - 1)) { - bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s write error: misaligned write", - op->flags & BCH_WRITE_MOVE ? "move" : "user"); + if (unlikely(bio->bi_iter.bi_size & (c->opts.block_size - 1))) { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "misaligned write"); + printbuf_exit(&buf); op->error = -EIO; goto err; } diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 2dc0d60c1745..2cd20114b74b 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -217,6 +217,12 @@ void bch2_journal_buf_put_final(struct journal *j, u64 seq) if (__bch2_journal_pin_put(j, seq)) bch2_journal_reclaim_fast(j); bch2_journal_do_writes(j); + + /* + * for __bch2_next_write_buffer_flush_journal_buf(), when quiescing an + * open journal entry + */ + wake_up(&j->wait); } /* @@ -251,6 +257,9 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool t if (!__journal_entry_is_open(old)) return; + if (old.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL) + old.cur_entry_offset = j->cur_entry_offset_if_blocked; + /* Close out old buffer: */ buf->data->u64s = cpu_to_le32(old.cur_entry_offset); @@ -373,6 +382,10 @@ static int journal_entry_open(struct journal *j) if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf)) return JOURNAL_ERR_max_in_flight; + if (bch2_fs_fatal_err_on(journal_cur_seq(j) >= JOURNAL_SEQ_MAX, + c, "cannot start: journal seq overflow")) + return JOURNAL_ERR_insufficient_devices; /* -EROFS */ + BUG_ON(!j->cur_entry_sectors); buf->expires = @@ -664,7 +677,7 @@ out: * @seq: seq to flush * @parent: closure object to wait with * Returns: 1 if @seq has already been flushed, 0 if @seq is being flushed, - * -EIO if @seq will never be flushed + * -BCH_ERR_journal_flush_err if @seq will never be flushed * * Like bch2_journal_wait_on_seq, except that it triggers a write immediately if * necessary @@ -687,7 +700,7 @@ int bch2_journal_flush_seq_async(struct journal *j, u64 seq, /* Recheck under lock: */ if (j->err_seq && seq >= j->err_seq) { - ret = -EIO; + ret = -BCH_ERR_journal_flush_err; goto out; } @@ -794,10 +807,11 @@ int bch2_journal_flush(struct journal *j) } /* - * bch2_journal_noflush_seq - tell the journal not to issue any flushes before + * bch2_journal_noflush_seq - ask the journal not to issue any flushes in the + * range [start, end) * @seq */ -bool bch2_journal_noflush_seq(struct journal *j, u64 seq) +bool bch2_journal_noflush_seq(struct journal *j, u64 start, u64 end) { struct bch_fs *c = container_of(j, struct bch_fs, journal); u64 unwritten_seq; @@ -806,15 +820,15 @@ bool bch2_journal_noflush_seq(struct journal *j, u64 seq) if (!(c->sb.features & (1ULL << BCH_FEATURE_journal_no_flush))) return false; - if (seq <= c->journal.flushed_seq_ondisk) + if (c->journal.flushed_seq_ondisk >= start) return false; spin_lock(&j->lock); - if (seq <= c->journal.flushed_seq_ondisk) + if (c->journal.flushed_seq_ondisk >= start) goto out; for (unwritten_seq = journal_last_unwritten_seq(j); - unwritten_seq < seq; + unwritten_seq < end; unwritten_seq++) { struct journal_buf *buf = journal_seq_to_buf(j, unwritten_seq); @@ -831,19 +845,14 @@ out: return ret; } -int bch2_journal_meta(struct journal *j) +static int __bch2_journal_meta(struct journal *j) { - struct journal_buf *buf; - struct journal_res res; - int ret; - - memset(&res, 0, sizeof(res)); - - ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0); + struct journal_res res = {}; + int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0); if (ret) return ret; - buf = j->buf + (res.seq & JOURNAL_BUF_MASK); + struct journal_buf *buf = j->buf + (res.seq & JOURNAL_BUF_MASK); buf->must_flush = true; if (!buf->flush_time) { @@ -856,27 +865,70 @@ int bch2_journal_meta(struct journal *j) return bch2_journal_flush_seq(j, res.seq, TASK_UNINTERRUPTIBLE); } +int bch2_journal_meta(struct journal *j) +{ + struct bch_fs *c = container_of(j, struct bch_fs, journal); + + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_journal)) + return -EROFS; + + int ret = __bch2_journal_meta(j); + bch2_write_ref_put(c, BCH_WRITE_REF_journal); + return ret; +} + /* block/unlock the journal: */ void bch2_journal_unblock(struct journal *j) { spin_lock(&j->lock); - j->blocked--; + if (!--j->blocked && + j->cur_entry_offset_if_blocked < JOURNAL_ENTRY_CLOSED_VAL && + j->reservations.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL) { + union journal_res_state old, new; + + old.v = atomic64_read(&j->reservations.counter); + do { + new.v = old.v; + new.cur_entry_offset = j->cur_entry_offset_if_blocked; + } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); + } spin_unlock(&j->lock); journal_wake(j); } +static void __bch2_journal_block(struct journal *j) +{ + if (!j->blocked++) { + union journal_res_state old, new; + + old.v = atomic64_read(&j->reservations.counter); + do { + j->cur_entry_offset_if_blocked = old.cur_entry_offset; + + if (j->cur_entry_offset_if_blocked >= JOURNAL_ENTRY_CLOSED_VAL) + break; + + new.v = old.v; + new.cur_entry_offset = JOURNAL_ENTRY_BLOCKED_VAL; + } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); + + journal_cur_buf(j)->data->u64s = cpu_to_le32(old.cur_entry_offset); + } +} + void bch2_journal_block(struct journal *j) { spin_lock(&j->lock); - j->blocked++; + __bch2_journal_block(j); spin_unlock(&j->lock); journal_quiesce(j); } -static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq) +static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct journal *j, + u64 max_seq, bool *blocked) { struct journal_buf *ret = NULL; @@ -893,13 +945,17 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou struct journal_buf *buf = j->buf + idx; if (buf->need_flush_to_write_buffer) { - if (seq == journal_cur_seq(j)) - __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true); - union journal_res_state s; s.v = atomic64_read_acquire(&j->reservations.counter); - ret = journal_state_count(s, idx) + unsigned open = seq == journal_cur_seq(j) && __journal_entry_is_open(s); + + if (open && !*blocked) { + __bch2_journal_block(j); + *blocked = true; + } + + ret = journal_state_count(s, idx) > open ? ERR_PTR(-EAGAIN) : buf; break; @@ -912,11 +968,17 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou return ret; } -struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq) +struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, + u64 max_seq, bool *blocked) { struct journal_buf *ret; + *blocked = false; + + wait_event(j->wait, (ret = __bch2_next_write_buffer_flush_journal_buf(j, + max_seq, blocked)) != ERR_PTR(-EAGAIN)); + if (IS_ERR_OR_NULL(ret) && *blocked) + bch2_journal_unblock(j); - wait_event(j->wait, (ret = __bch2_next_write_buffer_flush_journal_buf(j, max_seq)) != ERR_PTR(-EAGAIN)); return ret; } @@ -945,19 +1007,17 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, } for (nr_got = 0; nr_got < nr_want; nr_got++) { - if (new_fs) { - bu[nr_got] = bch2_bucket_alloc_new_fs(ca); - if (bu[nr_got] < 0) { - ret = -BCH_ERR_ENOSPC_bucket_alloc; - break; - } - } else { - ob[nr_got] = bch2_bucket_alloc(c, ca, BCH_WATERMARK_normal, - BCH_DATA_journal, cl); - ret = PTR_ERR_OR_ZERO(ob[nr_got]); - if (ret) - break; + enum bch_watermark watermark = new_fs + ? BCH_WATERMARK_btree + : BCH_WATERMARK_normal; + ob[nr_got] = bch2_bucket_alloc(c, ca, watermark, + BCH_DATA_journal, cl); + ret = PTR_ERR_OR_ZERO(ob[nr_got]); + if (ret) + break; + + if (!new_fs) { ret = bch2_trans_run(c, bch2_trans_mark_metadata_bucket(trans, ca, ob[nr_got]->bucket, BCH_DATA_journal, @@ -967,9 +1027,9 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, bch_err_msg(c, ret, "marking new journal buckets"); break; } - - bu[nr_got] = ob[nr_got]->bucket; } + + bu[nr_got] = ob[nr_got]->bucket; } if (!nr_got) @@ -1009,8 +1069,7 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr, if (ret) goto err_unblock; - if (!new_fs) - bch2_write_super(c); + bch2_write_super(c); /* Commit: */ if (c) @@ -1044,9 +1103,8 @@ err_unblock: bu[i], BCH_DATA_free, 0, BTREE_TRIGGER_transactional)); err_free: - if (!new_fs) - for (i = 0; i < nr_got; i++) - bch2_open_bucket_put(c, ob[i]); + for (i = 0; i < nr_got; i++) + bch2_open_bucket_put(c, ob[i]); kfree(new_bucket_seq); kfree(new_buckets); @@ -1193,7 +1251,7 @@ void bch2_fs_journal_stop(struct journal *j) * Always write a new journal entry, to make sure the clock hands are up * to date (and match the superblock) */ - bch2_journal_meta(j); + __bch2_journal_meta(j); journal_quiesce(j); cancel_delayed_work_sync(&j->write_work); @@ -1217,6 +1275,11 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) bool had_entries = false; u64 last_seq = cur_seq, nr, seq; + if (cur_seq >= JOURNAL_SEQ_MAX) { + bch_err(c, "cannot start: journal seq overflow"); + return -EINVAL; + } + genradix_for_each_reverse(&c->journal_entries, iter, _i) { i = *_i; @@ -1474,6 +1537,9 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) case JOURNAL_ENTRY_CLOSED_VAL: prt_printf(out, "closed\n"); break; + case JOURNAL_ENTRY_BLOCKED_VAL: + prt_printf(out, "blocked\n"); + break; default: prt_printf(out, "%u/%u\n", s.cur_entry_offset, j->cur_entry_u64s); break; @@ -1499,6 +1565,9 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) printbuf_indent_sub(out, 2); for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) { + if (!ca->mi.durability) + continue; + struct journal_device *ja = &ca->journal; if (!test_bit(ca->dev_idx, c->rw_devs[BCH_DATA_journal].d)) @@ -1508,6 +1577,7 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) continue; prt_printf(out, "dev %u:\n", ca->dev_idx); + prt_printf(out, "durability %u:\n", ca->mi.durability); printbuf_indent_add(out, 2); prt_printf(out, "nr\t%u\n", ja->nr); prt_printf(out, "bucket size\t%u\n", ca->mi.bucket_size); @@ -1519,6 +1589,8 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) printbuf_indent_sub(out, 2); } + prt_printf(out, "replicas want %u need %u\n", c->opts.metadata_replicas, c->opts.metadata_replicas_required); + rcu_read_unlock(); --out->atomic; diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 2762be6f9814..cb0df0663946 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -285,7 +285,8 @@ static inline void bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq spin_lock(&j->lock); bch2_journal_buf_put_final(j, seq); spin_unlock(&j->lock); - } + } else if (unlikely(s.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL)) + wake_up(&j->wait); } /* @@ -403,7 +404,7 @@ void bch2_journal_flush_async(struct journal *, struct closure *); int bch2_journal_flush_seq(struct journal *, u64, unsigned); int bch2_journal_flush(struct journal *); -bool bch2_journal_noflush_seq(struct journal *, u64); +bool bch2_journal_noflush_seq(struct journal *, u64, u64); int bch2_journal_meta(struct journal *); void bch2_journal_halt(struct journal *); @@ -411,7 +412,7 @@ void bch2_journal_halt(struct journal *); static inline int bch2_journal_error(struct journal *j) { return j->reservations.cur_entry_offset == JOURNAL_ENTRY_ERROR_VAL - ? -EIO : 0; + ? -BCH_ERR_journal_shutdown : 0; } struct bch_dev; @@ -424,7 +425,7 @@ static inline void bch2_journal_set_replay_done(struct journal *j) void bch2_journal_unblock(struct journal *); void bch2_journal_block(struct journal *); -struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq); +struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u64, bool *); void __bch2_journal_debug_to_text(struct printbuf *, struct journal *); void bch2_journal_debug_to_text(struct printbuf *, struct journal *); diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index fb35dd336331..7f2efe85a805 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -17,6 +17,8 @@ #include "sb-clean.h" #include "trace.h" +#include <linux/string_choices.h> + void bch2_journal_pos_from_member_info_set(struct bch_fs *c) { lockdep_assert_held(&c->sb_lock); @@ -299,7 +301,7 @@ static void journal_entry_err_msg(struct printbuf *out, journal_entry_err_msg(&_buf, version, jset, entry); \ prt_printf(&_buf, msg, ##__VA_ARGS__); \ \ - switch (flags & BCH_VALIDATE_write) { \ + switch (from.flags & BCH_VALIDATE_write) { \ case READ: \ mustfix_fsck_err(c, _err, "%s", _buf.buf); \ break; \ @@ -325,11 +327,11 @@ static void journal_entry_err_msg(struct printbuf *out, static int journal_validate_key(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, - unsigned level, enum btree_id btree_id, struct bkey_i *k, - unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from, + unsigned version, int big_endian) { + enum bch_validate_flags flags = from.flags; int write = flags & BCH_VALIDATE_write; void *next = vstruct_next(entry); int ret = 0; @@ -364,11 +366,10 @@ static int journal_validate_key(struct bch_fs *c, } if (!write) - bch2_bkey_compat(level, btree_id, version, big_endian, + bch2_bkey_compat(from.level, from.btree, version, big_endian, write, NULL, bkey_to_packed(k)); - ret = bch2_bkey_validate(c, bkey_i_to_s_c(k), - __btree_node_type(level, btree_id), write); + ret = bch2_bkey_validate(c, bkey_i_to_s_c(k), from); if (ret == -BCH_ERR_fsck_delete_bkey) { le16_add_cpu(&entry->u64s, -((u16) k->k.u64s)); memmove(k, bkey_next(k), next - (void *) bkey_next(k)); @@ -379,7 +380,7 @@ static int journal_validate_key(struct bch_fs *c, goto fsck_err; if (write) - bch2_bkey_compat(level, btree_id, version, big_endian, + bch2_bkey_compat(from.level, from.btree, version, big_endian, write, NULL, bkey_to_packed(k)); fsck_err: return ret; @@ -389,16 +390,15 @@ static int journal_entry_btree_keys_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_i *k = entry->start; + from.level = entry->level; + from.btree = entry->btree_id; + while (k != vstruct_last(entry)) { - int ret = journal_validate_key(c, jset, entry, - entry->level, - entry->btree_id, - k, version, big_endian, - flags|BCH_VALIDATE_journal); + int ret = journal_validate_key(c, jset, entry, k, from, version, big_endian); if (ret == FSCK_DELETED_KEY) continue; else if (ret) @@ -421,7 +421,8 @@ static void journal_entry_btree_keys_to_text(struct printbuf *out, struct bch_fs bch2_prt_jset_entry_type(out, entry->type); prt_str(out, ": "); } - prt_printf(out, "btree=%s l=%u ", bch2_btree_id_str(entry->btree_id), entry->level); + bch2_btree_id_level_to_text(out, entry->btree_id, entry->level); + prt_char(out, ' '); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(k)); first = false; } @@ -431,11 +432,15 @@ static int journal_entry_btree_root_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_i *k = entry->start; int ret = 0; + from.root = true; + from.level = entry->level + 1; + from.btree = entry->btree_id; + if (journal_entry_err_on(!entry->u64s || le16_to_cpu(entry->u64s) != k->k.u64s, c, version, jset, entry, @@ -452,8 +457,7 @@ static int journal_entry_btree_root_validate(struct bch_fs *c, return 0; } - ret = journal_validate_key(c, jset, entry, 1, entry->btree_id, k, - version, big_endian, flags); + ret = journal_validate_key(c, jset, entry, k, from, version, big_endian); if (ret == FSCK_DELETED_KEY) ret = 0; fsck_err: @@ -470,7 +474,7 @@ static int journal_entry_prio_ptrs_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { /* obsolete, don't care: */ return 0; @@ -485,7 +489,7 @@ static int journal_entry_blacklist_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -512,7 +516,7 @@ static int journal_entry_blacklist_v2_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_blacklist_v2 *bl_entry; int ret = 0; @@ -554,7 +558,7 @@ static int journal_entry_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_usage *u = container_of(entry, struct jset_entry_usage, entry); @@ -588,7 +592,7 @@ static int journal_entry_data_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_data_usage *u = container_of(entry, struct jset_entry_data_usage, entry); @@ -632,7 +636,7 @@ static int journal_entry_clock_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_clock *clock = container_of(entry, struct jset_entry_clock, entry); @@ -665,14 +669,14 @@ static void journal_entry_clock_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry_clock *clock = container_of(entry, struct jset_entry_clock, entry); - prt_printf(out, "%s=%llu", clock->rw ? "write" : "read", le64_to_cpu(clock->time)); + prt_printf(out, "%s=%llu", str_write_read(clock->rw), le64_to_cpu(clock->time)); } static int journal_entry_dev_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct jset_entry_dev_usage *u = container_of(entry, struct jset_entry_dev_usage, entry); @@ -729,7 +733,7 @@ static int journal_entry_log_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return 0; } @@ -738,19 +742,19 @@ static void journal_entry_log_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_log *l = container_of(entry, struct jset_entry_log, entry); - unsigned bytes = vstruct_bytes(entry) - offsetof(struct jset_entry_log, d); - prt_printf(out, "%.*s", bytes, l->d); + prt_printf(out, "%.*s", jset_entry_log_msg_bytes(l), l->d); } static int journal_entry_overwrite_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { + from.flags = 0; return journal_entry_btree_keys_validate(c, jset, entry, - version, big_endian, READ); + version, big_endian, from); } static void journal_entry_overwrite_to_text(struct printbuf *out, struct bch_fs *c, @@ -763,10 +767,10 @@ static int journal_entry_write_buffer_keys_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return journal_entry_btree_keys_validate(c, jset, entry, - version, big_endian, READ); + version, big_endian, from); } static void journal_entry_write_buffer_keys_to_text(struct printbuf *out, struct bch_fs *c, @@ -779,7 +783,7 @@ static int journal_entry_datetime_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { unsigned bytes = vstruct_bytes(entry); unsigned expected = 16; @@ -809,7 +813,7 @@ static void journal_entry_datetime_to_text(struct printbuf *out, struct bch_fs * struct jset_entry_ops { int (*validate)(struct bch_fs *, struct jset *, struct jset_entry *, unsigned, int, - enum bch_validate_flags); + struct bkey_validate_context); void (*to_text)(struct printbuf *, struct bch_fs *, struct jset_entry *); }; @@ -827,11 +831,11 @@ int bch2_journal_entry_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, - enum bch_validate_flags flags) + struct bkey_validate_context from) { return entry->type < BCH_JSET_ENTRY_NR ? bch2_jset_entry_ops[entry->type].validate(c, jset, entry, - version, big_endian, flags) + version, big_endian, from) : 0; } @@ -849,10 +853,18 @@ void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c, static int jset_validate_entries(struct bch_fs *c, struct jset *jset, enum bch_validate_flags flags) { + struct bkey_validate_context from = { + .flags = flags, + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(jset->seq), + }; + unsigned version = le32_to_cpu(jset->version); int ret = 0; vstruct_for_each(jset, entry) { + from.journal_offset = (u64 *) entry - jset->_data; + if (journal_entry_err_on(vstruct_next(entry) > vstruct_last(jset), c, version, jset, entry, journal_entry_past_jset_end, @@ -861,8 +873,8 @@ static int jset_validate_entries(struct bch_fs *c, struct jset *jset, break; } - ret = bch2_journal_entry_validate(c, jset, entry, - version, JSET_BIG_ENDIAN(jset), flags); + ret = bch2_journal_entry_validate(c, jset, entry, version, + JSET_BIG_ENDIAN(jset), from); if (ret) break; } @@ -875,13 +887,17 @@ static int jset_validate(struct bch_fs *c, struct jset *jset, u64 sector, enum bch_validate_flags flags) { - unsigned version; + struct bkey_validate_context from = { + .flags = flags, + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(jset->seq), + }; int ret = 0; if (le64_to_cpu(jset->magic) != jset_magic(c)) return JOURNAL_ENTRY_NONE; - version = le32_to_cpu(jset->version); + unsigned version = le32_to_cpu(jset->version); if (journal_entry_err_on(!bch2_version_compatible(version), c, version, jset, NULL, jset_unsupported_version, @@ -926,15 +942,16 @@ static int jset_validate_early(struct bch_fs *c, unsigned bucket_sectors_left, unsigned sectors_read) { - size_t bytes = vstruct_bytes(jset); - unsigned version; - enum bch_validate_flags flags = BCH_VALIDATE_journal; + struct bkey_validate_context from = { + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(jset->seq), + }; int ret = 0; if (le64_to_cpu(jset->magic) != jset_magic(c)) return JOURNAL_ENTRY_NONE; - version = le32_to_cpu(jset->version); + unsigned version = le32_to_cpu(jset->version); if (journal_entry_err_on(!bch2_version_compatible(version), c, version, jset, NULL, jset_unsupported_version, @@ -947,6 +964,7 @@ static int jset_validate_early(struct bch_fs *c, return -EINVAL; } + size_t bytes = vstruct_bytes(jset); if (bytes > (sectors_read << 9) && sectors_read < bucket_sectors_left) return JOURNAL_ENTRY_REREAD; @@ -1231,8 +1249,6 @@ int bch2_journal_read(struct bch_fs *c, * those entries will be blacklisted: */ genradix_for_each_reverse(&c->journal_entries, radix_iter, _i) { - enum bch_validate_flags flags = BCH_VALIDATE_journal; - i = *_i; if (journal_replay_ignore(i)) @@ -1252,6 +1268,10 @@ int bch2_journal_read(struct bch_fs *c, continue; } + struct bkey_validate_context from = { + .from = BKEY_VALIDATE_journal, + .journal_seq = le64_to_cpu(i->j.seq), + }; if (journal_entry_err_on(le64_to_cpu(i->j.last_seq) > le64_to_cpu(i->j.seq), c, le32_to_cpu(i->j.version), &i->j, NULL, jset_last_seq_newer_than_seq, @@ -1411,27 +1431,50 @@ fsck_err: /* journal write: */ +static void journal_advance_devs_to_next_bucket(struct journal *j, + struct dev_alloc_list *devs, + unsigned sectors, u64 seq) +{ + struct bch_fs *c = container_of(j, struct bch_fs, journal); + + darray_for_each(*devs, i) { + struct bch_dev *ca = rcu_dereference(c->devs[*i]); + if (!ca) + continue; + + struct journal_device *ja = &ca->journal; + + if (sectors > ja->sectors_free && + sectors <= ca->mi.bucket_size && + bch2_journal_dev_buckets_available(j, ja, + journal_space_discarded)) { + ja->cur_idx = (ja->cur_idx + 1) % ja->nr; + ja->sectors_free = ca->mi.bucket_size; + + /* + * ja->bucket_seq[ja->cur_idx] must always have + * something sensible: + */ + ja->bucket_seq[ja->cur_idx] = le64_to_cpu(seq); + } + } +} + static void __journal_write_alloc(struct journal *j, struct journal_buf *w, - struct dev_alloc_list *devs_sorted, + struct dev_alloc_list *devs, unsigned sectors, unsigned *replicas, unsigned replicas_want) { struct bch_fs *c = container_of(j, struct bch_fs, journal); - struct journal_device *ja; - struct bch_dev *ca; - unsigned i; - if (*replicas >= replicas_want) - return; - - for (i = 0; i < devs_sorted->nr; i++) { - ca = rcu_dereference(c->devs[devs_sorted->devs[i]]); + darray_for_each(*devs, i) { + struct bch_dev *ca = rcu_dereference(c->devs[*i]); if (!ca) continue; - ja = &ca->journal; + struct journal_device *ja = &ca->journal; /* * Check that we can use this device, and aren't already using @@ -1477,65 +1520,53 @@ static int journal_write_alloc(struct journal *j, struct journal_buf *w) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_devs_mask devs; - struct journal_device *ja; - struct bch_dev *ca; struct dev_alloc_list devs_sorted; unsigned sectors = vstruct_sectors(w->data, c->block_bits); unsigned target = c->opts.metadata_target ?: c->opts.foreground_target; - unsigned i, replicas = 0, replicas_want = + unsigned replicas = 0, replicas_want = READ_ONCE(c->opts.metadata_replicas); unsigned replicas_need = min_t(unsigned, replicas_want, READ_ONCE(c->opts.metadata_replicas_required)); + bool advance_done = false; rcu_read_lock(); -retry: - devs = target_rw_devs(c, BCH_DATA_journal, target); - devs_sorted = bch2_dev_alloc_list(c, &j->wp.stripe, &devs); + /* We might run more than once if we have to stop and do discards: */ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(&w->key)); + bkey_for_each_ptr(ptrs, p) { + struct bch_dev *ca = bch2_dev_rcu_noerror(c, p->dev); + if (ca) + replicas += ca->mi.durability; + } - __journal_write_alloc(j, w, &devs_sorted, - sectors, &replicas, replicas_want); +retry_target: + devs = target_rw_devs(c, BCH_DATA_journal, target); + devs_sorted = bch2_dev_alloc_list(c, &j->wp.stripe, &devs); +retry_alloc: + __journal_write_alloc(j, w, &devs_sorted, sectors, &replicas, replicas_want); - if (replicas >= replicas_want) + if (likely(replicas >= replicas_want)) goto done; - for (i = 0; i < devs_sorted.nr; i++) { - ca = rcu_dereference(c->devs[devs_sorted.devs[i]]); - if (!ca) - continue; - - ja = &ca->journal; - - if (sectors > ja->sectors_free && - sectors <= ca->mi.bucket_size && - bch2_journal_dev_buckets_available(j, ja, - journal_space_discarded)) { - ja->cur_idx = (ja->cur_idx + 1) % ja->nr; - ja->sectors_free = ca->mi.bucket_size; - - /* - * ja->bucket_seq[ja->cur_idx] must always have - * something sensible: - */ - ja->bucket_seq[ja->cur_idx] = le64_to_cpu(w->data->seq); - } + if (!advance_done) { + journal_advance_devs_to_next_bucket(j, &devs_sorted, sectors, w->data->seq); + advance_done = true; + goto retry_alloc; } - __journal_write_alloc(j, w, &devs_sorted, - sectors, &replicas, replicas_want); - if (replicas < replicas_want && target) { /* Retry from all devices: */ target = 0; - goto retry; + advance_done = false; + goto retry_target; } done: rcu_read_unlock(); BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX); - return replicas >= replicas_need ? 0 : -EROFS; + return replicas >= replicas_need ? 0 : -BCH_ERR_insufficient_journal_devices; } static void journal_buf_realloc(struct journal *j, struct journal_buf *buf) @@ -2023,19 +2054,21 @@ CLOSURE_CALLBACK(bch2_journal_write) bch2_journal_do_discards(j); } - if (ret) { + if (ret && !bch2_journal_error(j)) { struct printbuf buf = PRINTBUF; buf.atomic++; - prt_printf(&buf, bch2_fmt(c, "Unable to allocate journal write at seq %llu: %s"), + prt_printf(&buf, bch2_fmt(c, "Unable to allocate journal write at seq %llu for %zu sectors: %s"), le64_to_cpu(w->data->seq), + vstruct_sectors(w->data, c->block_bits), bch2_err_str(ret)); __bch2_journal_debug_to_text(&buf, j); spin_unlock(&j->lock); bch2_print_string_as_lines(KERN_ERR, buf.buf); printbuf_exit(&buf); - goto err; } + if (ret) + goto err; /* * write is allocated, no longer need to account for it in diff --git a/fs/bcachefs/journal_io.h b/fs/bcachefs/journal_io.h index 2ca9cde30ea8..12b39fcb4424 100644 --- a/fs/bcachefs/journal_io.h +++ b/fs/bcachefs/journal_io.h @@ -63,7 +63,7 @@ static inline struct jset_entry *__jset_entry_type_next(struct jset *jset, int bch2_journal_entry_validate(struct bch_fs *, struct jset *, struct jset_entry *, unsigned, int, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_journal_entry_to_text(struct printbuf *, struct bch_fs *, struct jset_entry *); diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index ace291f175dd..3c8242606da7 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -38,6 +38,9 @@ unsigned bch2_journal_dev_buckets_available(struct journal *j, struct journal_device *ja, enum journal_space_from from) { + if (!ja->nr) + return 0; + unsigned available = (journal_space_from(ja, from) - ja->cur_idx - 1 + ja->nr) % ja->nr; @@ -137,14 +140,18 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne struct bch_fs *c = container_of(j, struct bch_fs, journal); unsigned pos, nr_devs = 0; struct journal_space space, dev_space[BCH_SB_MEMBERS_MAX]; + unsigned min_bucket_size = U32_MAX; BUG_ON(nr_devs_want > ARRAY_SIZE(dev_space)); rcu_read_lock(); for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) { - if (!ca->journal.nr) + if (!ca->journal.nr || + !ca->mi.durability) continue; + min_bucket_size = min(min_bucket_size, ca->mi.bucket_size); + space = journal_dev_space_available(j, ca, from); if (!space.next_entry) continue; @@ -164,7 +171,9 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne * We sorted largest to smallest, and we want the smallest out of the * @nr_devs_want largest devices: */ - return dev_space[nr_devs_want - 1]; + space = dev_space[nr_devs_want - 1]; + space.next_entry = min(space.next_entry, min_bucket_size); + return space; } void bch2_journal_space_available(struct journal *j) @@ -758,10 +767,12 @@ static int bch2_journal_reclaim_thread(void *arg) journal_empty = fifo_empty(&j->pin); spin_unlock(&j->lock); + long timeout = j->next_reclaim - jiffies; + if (journal_empty) schedule(); - else if (time_after(j->next_reclaim, jiffies)) - schedule_timeout(j->next_reclaim - jiffies); + else if (timeout > 0) + schedule_timeout(timeout); else break; } diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h index 19183fcf7ad7..e9bd716fbb71 100644 --- a/fs/bcachefs/journal_types.h +++ b/fs/bcachefs/journal_types.h @@ -9,6 +9,9 @@ #include "super_types.h" #include "fifo.h" +/* btree write buffer steals 8 bits for its own purposes: */ +#define JOURNAL_SEQ_MAX ((1ULL << 56) - 1) + #define JOURNAL_BUF_BITS 2 #define JOURNAL_BUF_NR (1U << JOURNAL_BUF_BITS) #define JOURNAL_BUF_MASK (JOURNAL_BUF_NR - 1) @@ -112,6 +115,7 @@ union journal_res_state { */ #define JOURNAL_ENTRY_OFFSET_MAX ((1U << 20) - 1) +#define JOURNAL_ENTRY_BLOCKED_VAL (JOURNAL_ENTRY_OFFSET_MAX - 2) #define JOURNAL_ENTRY_CLOSED_VAL (JOURNAL_ENTRY_OFFSET_MAX - 1) #define JOURNAL_ENTRY_ERROR_VAL (JOURNAL_ENTRY_OFFSET_MAX) @@ -193,6 +197,7 @@ struct journal { * insufficient devices: */ enum journal_errors cur_entry_error; + unsigned cur_entry_offset_if_blocked; unsigned buf_size_want; /* diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c index 60e00702d1a4..75f27ec26f85 100644 --- a/fs/bcachefs/logged_ops.c +++ b/fs/bcachefs/logged_ops.c @@ -63,8 +63,10 @@ fsck_err: int bch2_resume_logged_ops(struct bch_fs *c) { int ret = bch2_trans_run(c, - for_each_btree_key(trans, iter, - BTREE_ID_logged_ops, POS_MIN, + for_each_btree_key_max(trans, iter, + BTREE_ID_logged_ops, + POS(LOGGED_OPS_INUM_logged_ops, 0), + POS(LOGGED_OPS_INUM_logged_ops, U64_MAX), BTREE_ITER_prefetch, k, resume_logged_op(trans, &iter, k))); bch_err_fn(c, ret); @@ -74,9 +76,8 @@ int bch2_resume_logged_ops(struct bch_fs *c) static int __bch2_logged_op_start(struct btree_trans *trans, struct bkey_i *k) { struct btree_iter iter; - int ret; - - ret = bch2_bkey_get_empty_slot(trans, &iter, BTREE_ID_logged_ops, POS_MAX); + int ret = bch2_bkey_get_empty_slot(trans, &iter, + BTREE_ID_logged_ops, POS(LOGGED_OPS_INUM_logged_ops, U64_MAX)); if (ret) return ret; diff --git a/fs/bcachefs/logged_ops_format.h b/fs/bcachefs/logged_ops_format.h index 6a4bf7129dba..cfb67c95d4c8 100644 --- a/fs/bcachefs/logged_ops_format.h +++ b/fs/bcachefs/logged_ops_format.h @@ -2,6 +2,11 @@ #ifndef _BCACHEFS_LOGGED_OPS_FORMAT_H #define _BCACHEFS_LOGGED_OPS_FORMAT_H +enum logged_ops_inums { + LOGGED_OPS_INUM_logged_ops, + LOGGED_OPS_INUM_inode_cursors, +}; + struct bch_logged_op_truncate { struct bch_val v; __le32 subvol; diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c index 10857eccdeaf..ce794d55818f 100644 --- a/fs/bcachefs/lru.c +++ b/fs/bcachefs/lru.c @@ -12,7 +12,7 @@ /* KEY_TYPE_lru is obsolete: */ int bch2_lru_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -192,7 +192,7 @@ int bch2_check_lrus(struct bch_fs *c) int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_lru, POS_MIN, BTREE_ITER_prefetch, k, - NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw, + NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_check_lru_key(trans, &iter, k, &last_flushed))); bch2_bkey_buf_exit(&last_flushed, c); diff --git a/fs/bcachefs/lru.h b/fs/bcachefs/lru.h index e6a7d8241bb8..f31a6cf1514c 100644 --- a/fs/bcachefs/lru.h +++ b/fs/bcachefs/lru.h @@ -33,7 +33,7 @@ static inline enum bch_lru_type lru_type(struct bkey_s_c l) return BCH_LRU_read; } -int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); void bch2_lru_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_lru_pos_to_text(struct printbuf *, struct bpos); diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c index 0ef4a86850bb..160b4374160a 100644 --- a/fs/bcachefs/move.c +++ b/fs/bcachefs/move.c @@ -21,6 +21,8 @@ #include "journal_reclaim.h" #include "keylist.h" #include "move.h" +#include "rebalance.h" +#include "reflink.h" #include "replicas.h" #include "snapshot.h" #include "super-io.h" @@ -196,6 +198,13 @@ void bch2_moving_ctxt_exit(struct moving_context *ctxt) list_del(&ctxt->list); mutex_unlock(&c->moving_context_lock); + /* + * Generally, releasing a transaction within a transaction restart means + * an unhandled transaction restart: but this can happen legitimately + * within the move code, e.g. when bch2_move_ratelimit() tells us to + * exit before we've retried + */ + bch2_trans_begin(ctxt->trans); bch2_trans_put(ctxt->trans); memset(ctxt, 0, sizeof(*ctxt)); } @@ -292,8 +301,8 @@ int bch2_move_extent(struct moving_context *ctxt, io->write_sectors = k.k->size; bio_init(&io->write.op.wbio.bio, NULL, io->bi_inline_vecs, pages, 0); - bio_set_prio(&io->write.op.wbio.bio, - IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); + io->write.op.wbio.bio.bi_ioprio = + IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); if (bch2_bio_alloc_pages(&io->write.op.wbio.bio, sectors << 9, GFP_KERNEL)) @@ -303,7 +312,7 @@ int bch2_move_extent(struct moving_context *ctxt, io->rbio.opts = io_opts; bio_init(&io->rbio.bio, NULL, io->bi_inline_vecs, pages, 0); io->rbio.bio.bi_vcnt = pages; - bio_set_prio(&io->rbio.bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); + io->rbio.bio.bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); io->rbio.bio.bi_iter.bi_size = sectors << 9; io->rbio.bio.bi_opf = REQ_OP_READ; @@ -379,34 +388,42 @@ err: return ret; } -struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, +static struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, struct per_snapshot_io_opts *io_opts, + struct bpos extent_pos, /* extent_iter, extent_k may be in reflink btree */ + struct btree_iter *extent_iter, struct bkey_s_c extent_k) { struct bch_fs *c = trans->c; u32 restart_count = trans->restart_count; + struct bch_io_opts *opts_ret = &io_opts->fs_io_opts; int ret = 0; - if (io_opts->cur_inum != extent_k.k->p.inode) { + if (extent_k.k->type == KEY_TYPE_reflink_v) + goto out; + + if (io_opts->cur_inum != extent_pos.inode) { io_opts->d.nr = 0; - ret = for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_k.k->p.inode), + ret = for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_pos.inode), BTREE_ITER_all_snapshots, k, ({ - if (k.k->p.offset != extent_k.k->p.inode) + if (k.k->p.offset != extent_pos.inode) break; if (!bkey_is_inode(k.k)) continue; struct bch_inode_unpacked inode; - BUG_ON(bch2_inode_unpack(k, &inode)); + _ret3 = bch2_inode_unpack(k, &inode); + if (_ret3) + break; struct snapshot_io_opts_entry e = { .snapshot = k.k->p.snapshot }; bch2_inode_opts_get(&e.io_opts, trans->c, &inode); darray_push(&io_opts->d, e); })); - io_opts->cur_inum = extent_k.k->p.inode; + io_opts->cur_inum = extent_pos.inode; } ret = ret ?: trans_was_restarted(trans, restart_count); @@ -415,43 +432,46 @@ struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, if (extent_k.k->p.snapshot) darray_for_each(io_opts->d, i) - if (bch2_snapshot_is_ancestor(c, extent_k.k->p.snapshot, i->snapshot)) - return &i->io_opts; - - return &io_opts->fs_io_opts; + if (bch2_snapshot_is_ancestor(c, extent_k.k->p.snapshot, i->snapshot)) { + opts_ret = &i->io_opts; + break; + } +out: + ret = bch2_get_update_rebalance_opts(trans, opts_ret, extent_iter, extent_k); + if (ret) + return ERR_PTR(ret); + return opts_ret; } int bch2_move_get_io_opts_one(struct btree_trans *trans, struct bch_io_opts *io_opts, + struct btree_iter *extent_iter, struct bkey_s_c extent_k) { - struct btree_iter iter; - struct bkey_s_c k; - int ret; + struct bch_fs *c = trans->c; + + *io_opts = bch2_opts_to_inode_opts(c->opts); /* reflink btree? */ - if (!extent_k.k->p.inode) { - *io_opts = bch2_opts_to_inode_opts(trans->c->opts); - return 0; - } + if (!extent_k.k->p.inode) + goto out; - k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + struct btree_iter inode_iter; + struct bkey_s_c inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, extent_k.k->p.inode, extent_k.k->p.snapshot), BTREE_ITER_cached); - ret = bkey_err(k); + int ret = bkey_err(inode_k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; - if (!ret && bkey_is_inode(k.k)) { + if (!ret && bkey_is_inode(inode_k.k)) { struct bch_inode_unpacked inode; - bch2_inode_unpack(k, &inode); - bch2_inode_opts_get(io_opts, trans->c, &inode); - } else { - *io_opts = bch2_opts_to_inode_opts(trans->c->opts); + bch2_inode_unpack(inode_k, &inode); + bch2_inode_opts_get(io_opts, c, &inode); } - - bch2_trans_iter_exit(trans, &iter); - return 0; + bch2_trans_iter_exit(trans, &inode_iter); +out: + return bch2_get_update_rebalance_opts(trans, io_opts, extent_iter, extent_k); } int bch2_move_ratelimit(struct moving_context *ctxt) @@ -509,9 +529,15 @@ static int bch2_move_data_btree(struct moving_context *ctxt, struct per_snapshot_io_opts snapshot_io_opts; struct bch_io_opts *io_opts; struct bkey_buf sk; - struct btree_iter iter; + struct btree_iter iter, reflink_iter = {}; struct bkey_s_c k; struct data_update_opts data_opts; + /* + * If we're moving a single file, also process reflinked data it points + * to (this includes propagating changed io_opts from the inode to the + * extent): + */ + bool walk_indirect = start.inode == end.inode; int ret = 0, ret2; per_snapshot_io_opts_init(&snapshot_io_opts, c); @@ -531,6 +557,8 @@ static int bch2_move_data_btree(struct moving_context *ctxt, bch2_ratelimit_reset(ctxt->rate); while (!bch2_move_ratelimit(ctxt)) { + struct btree_iter *extent_iter = &iter; + bch2_trans_begin(trans); k = bch2_btree_iter_peek(&iter); @@ -549,10 +577,36 @@ static int bch2_move_data_btree(struct moving_context *ctxt, if (ctxt->stats) ctxt->stats->pos = BBPOS(iter.btree_id, iter.pos); + if (walk_indirect && + k.k->type == KEY_TYPE_reflink_p && + REFLINK_P_MAY_UPDATE_OPTIONS(bkey_s_c_to_reflink_p(k).v)) { + struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); + s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k); + + bch2_trans_iter_exit(trans, &reflink_iter); + k = bch2_lookup_indirect_extent(trans, &reflink_iter, &offset_into_extent, p, true, 0); + ret = bkey_err(k); + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + continue; + if (ret) + break; + + if (bkey_deleted(k.k)) + goto next_nondata; + + /* + * XXX: reflink pointers may point to multiple indirect + * extents, so don't advance past the entire reflink + * pointer - need to fixup iter->k + */ + extent_iter = &reflink_iter; + } + if (!bkey_extent_is_direct_data(k.k)) goto next_nondata; - io_opts = bch2_move_get_io_opts(trans, &snapshot_io_opts, k); + io_opts = bch2_move_get_io_opts(trans, &snapshot_io_opts, + iter.pos, extent_iter, k); ret = PTR_ERR_OR_ZERO(io_opts); if (ret) continue; @@ -568,7 +622,7 @@ static int bch2_move_data_btree(struct moving_context *ctxt, bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); - ret2 = bch2_move_extent(ctxt, NULL, &iter, k, *io_opts, data_opts); + ret2 = bch2_move_extent(ctxt, NULL, extent_iter, k, *io_opts, data_opts); if (ret2) { if (bch2_err_matches(ret2, BCH_ERR_transaction_restart)) continue; @@ -589,6 +643,7 @@ next_nondata: bch2_btree_iter_advance(&iter); } + bch2_trans_iter_exit(trans, &reflink_iter); bch2_trans_iter_exit(trans, &iter); bch2_bkey_buf_exit(&sk, c); per_snapshot_io_opts_exit(&snapshot_io_opts); @@ -654,16 +709,12 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, struct bch_fs *c = trans->c; bool is_kthread = current->flags & PF_KTHREAD; struct bch_io_opts io_opts = bch2_opts_to_inode_opts(c->opts); - struct btree_iter iter; + struct btree_iter iter = {}, bp_iter = {}; struct bkey_buf sk; - struct bch_backpointer bp; - struct bch_alloc_v4 a_convert; - const struct bch_alloc_v4 *a; struct bkey_s_c k; struct data_update_opts data_opts; - unsigned dirty_sectors, bucket_size; - u64 fragmentation; - struct bpos bp_pos = POS_MIN; + unsigned sectors_moved = 0; + struct bkey_buf last_flushed; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, bucket.inode); @@ -672,6 +723,8 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, trace_bucket_evacuate(c, &bucket); + bch2_bkey_buf_init(&last_flushed); + bkey_init(&last_flushed.k->k); bch2_bkey_buf_init(&sk); /* @@ -679,21 +732,13 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, */ bch2_trans_begin(trans); - bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, - bucket, BTREE_ITER_cached); - ret = lockrestart_do(trans, - bkey_err(k = bch2_btree_iter_peek_slot(&iter))); - bch2_trans_iter_exit(trans, &iter); + bch2_trans_iter_init(trans, &bp_iter, BTREE_ID_backpointers, + bucket_pos_to_bp_start(ca, bucket), 0); bch_err_msg(c, ret, "looking up alloc key"); if (ret) goto err; - a = bch2_alloc_to_v4(k, &a_convert); - dirty_sectors = bch2_bucket_sectors_dirty(*a); - bucket_size = ca->mi.bucket_size; - fragmentation = alloc_lru_idx_fragmentation(*a, ca); - ret = bch2_btree_write_buffer_tryflush(trans); bch_err_msg(c, ret, "flushing btree write buffer"); if (ret) @@ -705,18 +750,23 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, bch2_trans_begin(trans); - ret = bch2_get_next_backpointer(trans, ca, bucket, gen, - &bp_pos, &bp, - BTREE_ITER_cached); + k = bch2_btree_iter_peek(&bp_iter); + ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) goto err; - if (bkey_eq(bp_pos, POS_MAX)) + + if (!k.k || bkey_gt(k.k->p, bucket_pos_to_bp_end(ca, bucket))) break; - if (!bp.level) { - k = bch2_backpointer_get_key(trans, &iter, bp_pos, bp, 0); + if (k.k->type != KEY_TYPE_backpointer) + goto next; + + struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); + + if (!bp.v->level) { + k = bch2_backpointer_get_key(trans, bp, &iter, 0, &last_flushed); ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; @@ -728,7 +778,7 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); - ret = bch2_move_get_io_opts_one(trans, &io_opts, k); + ret = bch2_move_get_io_opts_one(trans, &io_opts, &iter, k); if (ret) { bch2_trans_iter_exit(trans, &iter); continue; @@ -738,14 +788,18 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, data_opts.target = io_opts.background_target; data_opts.rewrite_ptrs = 0; + unsigned sectors = bp.v->bucket_len; /* move_extent will drop locks */ unsigned i = 0; - bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) { - if (ptr->dev == bucket.inode) { - data_opts.rewrite_ptrs |= 1U << i; - if (ptr->cached) { + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + bkey_for_each_ptr_decode(k.k, bch2_bkey_ptrs_c(k), p, entry) { + if (p.ptr.dev == bucket.inode) { + if (p.ptr.cached) { bch2_trans_iter_exit(trans, &iter); goto next; } + data_opts.rewrite_ptrs |= 1U << i; + break; } i++; } @@ -765,14 +819,15 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, goto err; if (ctxt->stats) - atomic64_add(k.k->size, &ctxt->stats->sectors_seen); + atomic64_add(sectors, &ctxt->stats->sectors_seen); + sectors_moved += sectors; } else { struct btree *b; - b = bch2_backpointer_get_node(trans, &iter, bp_pos, bp); + b = bch2_backpointer_get_node(trans, bp, &iter, &last_flushed); ret = PTR_ERR_OR_ZERO(b); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) - continue; + goto next; if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) @@ -796,15 +851,18 @@ int bch2_evacuate_bucket(struct moving_context *ctxt, atomic64_add(sectors, &ctxt->stats->sectors_seen); atomic64_add(sectors, &ctxt->stats->sectors_moved); } + sectors_moved += btree_sectors(c); } next: - bp_pos = bpos_nosnap_successor(bp_pos); + bch2_btree_iter_advance(&bp_iter); } - trace_evacuate_bucket(c, &bucket, dirty_sectors, bucket_size, fragmentation, ret); + trace_evacuate_bucket(c, &bucket, sectors_moved, ca->mi.bucket_size, ret); err: + bch2_trans_iter_exit(trans, &bp_iter); bch2_dev_put(ca); bch2_bkey_buf_exit(&sk, c); + bch2_bkey_buf_exit(&last_flushed, c); return ret; } diff --git a/fs/bcachefs/move.h b/fs/bcachefs/move.h index 9baf3093a678..51e0505a8156 100644 --- a/fs/bcachefs/move.h +++ b/fs/bcachefs/move.h @@ -110,9 +110,8 @@ static inline void per_snapshot_io_opts_exit(struct per_snapshot_io_opts *io_opt darray_exit(&io_opts->d); } -struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *, - struct per_snapshot_io_opts *, struct bkey_s_c); -int bch2_move_get_io_opts_one(struct btree_trans *, struct bch_io_opts *, struct bkey_s_c); +int bch2_move_get_io_opts_one(struct btree_trans *, struct bch_io_opts *, + struct btree_iter *, struct bkey_s_c); int bch2_scan_old_btree_nodes(struct bch_fs *, struct bch_move_stats *); diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index d658be90f737..85c361e78ba5 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -167,7 +167,7 @@ static int bch2_copygc_get_buckets(struct moving_context *ctxt, bch2_trans_begin(trans); - ret = for_each_btree_key_upto(trans, iter, BTREE_ID_lru, + ret = for_each_btree_key_max(trans, iter, BTREE_ID_lru, lru_pos(BCH_LRU_FRAGMENTATION_START, 0, 0), lru_pos(BCH_LRU_FRAGMENTATION_START, U64_MAX, LRU_TIME_MAX), 0, k, ({ @@ -350,9 +350,9 @@ static int bch2_copygc_thread(void *arg) bch2_trans_unlock_long(ctxt.trans); cond_resched(); - if (!c->copy_gc_enabled) { + if (!c->opts.copygc_enabled) { move_buckets_wait(&ctxt, buckets, true); - kthread_wait_freezable(c->copy_gc_enabled || + kthread_wait_freezable(c->opts.copygc_enabled || kthread_should_stop()); } diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c index 0e2ee262fbd4..6772faf385a5 100644 --- a/fs/bcachefs/opts.c +++ b/fs/bcachefs/opts.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> +#include <linux/fs_parser.h> #include "bcachefs.h" #include "compress.h" @@ -48,12 +49,12 @@ static const char * const __bch2_csum_types[] = { NULL }; -const char * const bch2_csum_opts[] = { +const char * const __bch2_csum_opts[] = { BCH_CSUM_OPTS() NULL }; -static const char * const __bch2_compression_types[] = { +const char * const __bch2_compression_types[] = { BCH_COMPRESSION_TYPES() NULL }; @@ -113,6 +114,7 @@ void bch2_prt_##name(struct printbuf *out, type t) \ PRT_STR_OPT_BOUNDSCHECKED(jset_entry_type, enum bch_jset_entry_type); PRT_STR_OPT_BOUNDSCHECKED(fs_usage_type, enum bch_fs_usage_type); PRT_STR_OPT_BOUNDSCHECKED(data_type, enum bch_data_type); +PRT_STR_OPT_BOUNDSCHECKED(csum_opt, enum bch_csum_opt); PRT_STR_OPT_BOUNDSCHECKED(csum_type, enum bch_csum_type); PRT_STR_OPT_BOUNDSCHECKED(compression_type, enum bch_compression_type); PRT_STR_OPT_BOUNDSCHECKED(str_hash_type, enum bch_str_hash_type); @@ -333,17 +335,18 @@ int bch2_opt_parse(struct bch_fs *c, switch (opt->type) { case BCH_OPT_BOOL: if (val) { - ret = kstrtou64(val, 10, res); + ret = lookup_constant(bool_names, val, -BCH_ERR_option_not_bool); + if (ret != -BCH_ERR_option_not_bool) { + *res = ret; + } else { + if (err) + prt_printf(err, "%s: must be bool", opt->attr.name); + return ret; + } } else { - ret = 0; *res = 1; } - if (ret < 0 || (*res != 0 && *res != 1)) { - if (err) - prt_printf(err, "%s: must be bool", opt->attr.name); - return ret < 0 ? ret : -BCH_ERR_option_not_bool; - } break; case BCH_OPT_UINT: if (!val) { @@ -710,11 +713,14 @@ void bch2_opt_set_sb(struct bch_fs *c, struct bch_dev *ca, struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts src) { - return (struct bch_io_opts) { + struct bch_io_opts opts = { #define x(_name, _bits) ._name = src._name, BCH_INODE_OPTS() #undef x }; + + bch2_io_opts_fixups(&opts); + return opts; } bool bch2_opt_is_inode_opt(enum bch_opt_id id) diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 23dda014e331..e763d52e0f38 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -16,7 +16,8 @@ extern const char * const bch2_version_upgrade_opts[]; extern const char * const bch2_sb_features[]; extern const char * const bch2_sb_compat[]; extern const char * const __bch2_btree_ids[]; -extern const char * const bch2_csum_opts[]; +extern const char * const __bch2_csum_opts[]; +extern const char * const __bch2_compression_types[]; extern const char * const bch2_compression_opts[]; extern const char * const __bch2_str_hash_types[]; extern const char * const bch2_str_hash_opts[]; @@ -27,6 +28,7 @@ extern const char * const bch2_d_types[]; void bch2_prt_jset_entry_type(struct printbuf *, enum bch_jset_entry_type); void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type); void bch2_prt_data_type(struct printbuf *, enum bch_data_type); +void bch2_prt_csum_opt(struct printbuf *, enum bch_csum_opt); void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type); void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type); void bch2_prt_str_hash_type(struct printbuf *, enum bch_str_hash_type); @@ -171,12 +173,12 @@ enum fsck_err_opts { "size", "Maximum size of checksummed/compressed extents")\ x(metadata_checksum, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ - OPT_STR(bch2_csum_opts), \ + OPT_STR(__bch2_csum_opts), \ BCH_SB_META_CSUM_TYPE, BCH_CSUM_OPT_crc32c, \ NULL, NULL) \ x(data_checksum, u8, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ - OPT_STR(bch2_csum_opts), \ + OPT_STR(__bch2_csum_opts), \ BCH_SB_DATA_CSUM_TYPE, BCH_CSUM_OPT_crc32c, \ NULL, NULL) \ x(compression, u8, \ @@ -220,14 +222,14 @@ enum fsck_err_opts { BCH_SB_ERASURE_CODE, false, \ NULL, "Enable erasure coding (DO NOT USE YET)") \ x(inodes_32bit, u8, \ - OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ + OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_INODE_32BIT, true, \ NULL, "Constrain inode numbers to 32 bits") \ - x(shard_inode_numbers, u8, \ - OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ - OPT_BOOL(), \ - BCH_SB_SHARD_INUMS, true, \ + x(shard_inode_numbers_bits, u8, \ + OPT_FS|OPT_FORMAT, \ + OPT_UINT(0, 8), \ + BCH_SB_SHARD_INUMS_NBITS, 0, \ NULL, "Shard new inode numbers by CPU id") \ x(inodes_use_key_cache, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ @@ -473,6 +475,18 @@ enum fsck_err_opts { BCH2_NO_SB_OPT, true, \ NULL, "Enable nocow mode: enables runtime locking in\n"\ "data move path needed if nocow will ever be in use\n")\ + x(copygc_enabled, u8, \ + OPT_FS|OPT_MOUNT, \ + OPT_BOOL(), \ + BCH2_NO_SB_OPT, true, \ + NULL, "Enable copygc: disable for debugging, or to\n"\ + "quiet the system when doing performance testing\n")\ + x(rebalance_enabled, u8, \ + OPT_FS|OPT_MOUNT, \ + OPT_BOOL(), \ + BCH2_NO_SB_OPT, true, \ + NULL, "Enable rebalance: disable for debugging, or to\n"\ + "quiet the system when doing performance testing\n")\ x(no_data_io, u8, \ OPT_MOUNT, \ OPT_BOOL(), \ @@ -488,7 +502,7 @@ enum fsck_err_opts { OPT_DEVICE, \ OPT_UINT(0, S64_MAX), \ BCH2_NO_SB_OPT, 0, \ - "size", "Size of filesystem on device") \ + "size", "Specifies the bucket size; must be greater than the btree node size")\ x(durability, u8, \ OPT_DEVICE|OPT_SB_FIELD_ONE_BIAS, \ OPT_UINT(0, BCH_REPLICAS_MAX), \ @@ -624,14 +638,39 @@ struct bch_io_opts { #define x(_name, _bits) u##_bits _name; BCH_INODE_OPTS() #undef x +#define x(_name, _bits) u64 _name##_from_inode:1; + BCH_INODE_OPTS() +#undef x }; -static inline unsigned background_compression(struct bch_io_opts opts) +static inline void bch2_io_opts_fixups(struct bch_io_opts *opts) { - return opts.background_compression ?: opts.compression; + if (!opts->background_target) + opts->background_target = opts->foreground_target; + if (!opts->background_compression) + opts->background_compression = opts->compression; + if (opts->nocow) { + opts->compression = opts->background_compression = 0; + opts->data_checksum = 0; + opts->erasure_code = 0; + } } struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts); bool bch2_opt_is_inode_opt(enum bch_opt_id); +/* rebalance opts: */ + +static inline struct bch_extent_rebalance io_opts_to_rebalance_opts(struct bch_io_opts *opts) +{ + return (struct bch_extent_rebalance) { + .type = BIT(BCH_EXTENT_ENTRY_rebalance), +#define x(_name) \ + ._name = opts->_name, \ + ._name##_from_inode = opts->_name##_from_inode, + BCH_REBALANCE_OPTS() +#undef x + }; +}; + #endif /* _BCACHEFS_OPTS_H */ diff --git a/fs/bcachefs/printbuf.h b/fs/bcachefs/printbuf.h index 1d570387b77f..d0dd398baa2b 100644 --- a/fs/bcachefs/printbuf.h +++ b/fs/bcachefs/printbuf.h @@ -251,16 +251,23 @@ static inline void prt_hex_byte_upper(struct printbuf *out, u8 byte) printbuf_nul_terminate_reserved(out); } +static inline void printbuf_reset_keep_tabstops(struct printbuf *buf) +{ + buf->pos = 0; + buf->allocation_failure = 0; + buf->last_newline = 0; + buf->last_field = 0; + buf->indent = 0; + buf->cur_tabstop = 0; +} + /** * printbuf_reset - re-use a printbuf without freeing and re-initializing it: */ static inline void printbuf_reset(struct printbuf *buf) { - buf->pos = 0; - buf->allocation_failure = 0; - buf->indent = 0; + printbuf_reset_keep_tabstops(buf); buf->nr_tabstops = 0; - buf->cur_tabstop = 0; } /** diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c index 74f45a8162ad..8b857fc33244 100644 --- a/fs/bcachefs/quota.c +++ b/fs/bcachefs/quota.c @@ -60,7 +60,7 @@ const struct bch_sb_field_ops bch_sb_field_ops_quota = { }; int bch2_quota_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; diff --git a/fs/bcachefs/quota.h b/fs/bcachefs/quota.h index a62abcc5332a..1551800ff44c 100644 --- a/fs/bcachefs/quota.h +++ b/fs/bcachefs/quota.h @@ -5,10 +5,10 @@ #include "inode.h" #include "quota_types.h" -enum bch_validate_flags; extern const struct bch_sb_field_ops bch_sb_field_ops_quota; -int bch2_quota_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_quota_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_quota_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_quota ((struct bkey_ops) { \ diff --git a/fs/bcachefs/rcu_pending.c b/fs/bcachefs/rcu_pending.c index 40a20192eee8..bef2aa1b8bcd 100644 --- a/fs/bcachefs/rcu_pending.c +++ b/fs/bcachefs/rcu_pending.c @@ -25,21 +25,37 @@ enum rcu_pending_special { #define RCU_PENDING_KVFREE_FN ((rcu_pending_process_fn) (ulong) RCU_PENDING_KVFREE) #define RCU_PENDING_CALL_RCU_FN ((rcu_pending_process_fn) (ulong) RCU_PENDING_CALL_RCU) -static inline unsigned long __get_state_synchronize_rcu(struct srcu_struct *ssp) +#ifdef __KERNEL__ +typedef unsigned long rcu_gp_poll_state_t; + +static inline bool rcu_gp_poll_cookie_eq(rcu_gp_poll_state_t l, rcu_gp_poll_state_t r) +{ + return l == r; +} +#else +typedef struct urcu_gp_poll_state rcu_gp_poll_state_t; + +static inline bool rcu_gp_poll_cookie_eq(rcu_gp_poll_state_t l, rcu_gp_poll_state_t r) +{ + return l.grace_period_id == r.grace_period_id; +} +#endif + +static inline rcu_gp_poll_state_t __get_state_synchronize_rcu(struct srcu_struct *ssp) { return ssp ? get_state_synchronize_srcu(ssp) : get_state_synchronize_rcu(); } -static inline unsigned long __start_poll_synchronize_rcu(struct srcu_struct *ssp) +static inline rcu_gp_poll_state_t __start_poll_synchronize_rcu(struct srcu_struct *ssp) { return ssp ? start_poll_synchronize_srcu(ssp) : start_poll_synchronize_rcu(); } -static inline bool __poll_state_synchronize_rcu(struct srcu_struct *ssp, unsigned long cookie) +static inline bool __poll_state_synchronize_rcu(struct srcu_struct *ssp, rcu_gp_poll_state_t cookie) { return ssp ? poll_state_synchronize_srcu(ssp, cookie) @@ -71,13 +87,13 @@ struct rcu_pending_seq { GENRADIX(struct rcu_head *) objs; size_t nr; struct rcu_head **cursor; - unsigned long seq; + rcu_gp_poll_state_t seq; }; struct rcu_pending_list { struct rcu_head *head; struct rcu_head *tail; - unsigned long seq; + rcu_gp_poll_state_t seq; }; struct rcu_pending_pcpu { @@ -316,10 +332,10 @@ static void rcu_pending_rcu_cb(struct rcu_head *rcu) } static __always_inline struct rcu_pending_seq * -get_object_radix(struct rcu_pending_pcpu *p, unsigned long seq) +get_object_radix(struct rcu_pending_pcpu *p, rcu_gp_poll_state_t seq) { darray_for_each_reverse(p->objs, objs) - if (objs->seq == seq) + if (rcu_gp_poll_cookie_eq(objs->seq, seq)) return objs; if (darray_push_gfp(&p->objs, ((struct rcu_pending_seq) { .seq = seq }), GFP_ATOMIC)) @@ -329,7 +345,7 @@ get_object_radix(struct rcu_pending_pcpu *p, unsigned long seq) } static noinline bool -rcu_pending_enqueue_list(struct rcu_pending_pcpu *p, unsigned long seq, +rcu_pending_enqueue_list(struct rcu_pending_pcpu *p, rcu_gp_poll_state_t seq, struct rcu_head *head, void *ptr, unsigned long *flags) { @@ -364,7 +380,7 @@ rcu_pending_enqueue_list(struct rcu_pending_pcpu *p, unsigned long seq, again: for (struct rcu_pending_list *i = p->lists; i < p->lists + NUM_ACTIVE_RCU_POLL_OLDSTATE; i++) { - if (i->seq == seq) { + if (rcu_gp_poll_cookie_eq(i->seq, seq)) { rcu_pending_list_add(i, head); return false; } @@ -408,7 +424,7 @@ __rcu_pending_enqueue(struct rcu_pending *pending, struct rcu_head *head, struct rcu_pending_pcpu *p; struct rcu_pending_seq *objs; struct genradix_node *new_node = NULL; - unsigned long seq, flags; + unsigned long flags; bool start_gp = false; BUG_ON((ptr != NULL) != (pending->process == RCU_PENDING_KVFREE_FN)); @@ -416,7 +432,7 @@ __rcu_pending_enqueue(struct rcu_pending *pending, struct rcu_head *head, local_irq_save(flags); p = this_cpu_ptr(pending->p); spin_lock(&p->lock); - seq = __get_state_synchronize_rcu(pending->srcu); + rcu_gp_poll_state_t seq = __get_state_synchronize_rcu(pending->srcu); restart: if (may_sleep && unlikely(process_finished_items(pending, p, flags))) diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c index cd6647374353..4adc74cd3f70 100644 --- a/fs/bcachefs/rebalance.c +++ b/fs/bcachefs/rebalance.c @@ -24,6 +24,192 @@ #include <linux/kthread.h> #include <linux/sched/cputime.h> +/* bch_extent_rebalance: */ + +static const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + + bkey_extent_entry_for_each(ptrs, entry) + if (__extent_entry_type(entry) == BCH_EXTENT_ENTRY_rebalance) + return &entry->rebalance; + + return NULL; +} + +static inline unsigned bch2_bkey_ptrs_need_compress(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_s_c k, + struct bkey_ptrs_c ptrs) +{ + if (!opts->background_compression) + return 0; + + unsigned compression_type = bch2_compression_opt_to_type(opts->background_compression); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + unsigned ptr_bit = 1; + unsigned rewrite_ptrs = 0; + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) + return 0; + + if (!p.ptr.cached && p.crc.compression_type != compression_type) + rewrite_ptrs |= ptr_bit; + ptr_bit <<= 1; + } + + return rewrite_ptrs; +} + +static inline unsigned bch2_bkey_ptrs_need_move(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_ptrs_c ptrs) +{ + if (!opts->background_target || + !bch2_target_accepts_data(c, BCH_DATA_user, opts->background_target)) + return 0; + + unsigned ptr_bit = 1; + unsigned rewrite_ptrs = 0; + + bkey_for_each_ptr(ptrs, ptr) { + if (!ptr->cached && !bch2_dev_in_target(c, ptr->dev, opts->background_target)) + rewrite_ptrs |= ptr_bit; + ptr_bit <<= 1; + } + + return rewrite_ptrs; +} + +static unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_s_c k) +{ + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + return bch2_bkey_ptrs_need_compress(c, opts, k, ptrs) | + bch2_bkey_ptrs_need_move(c, opts, ptrs); +} + +u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k) +{ + const struct bch_extent_rebalance *opts = bch2_bkey_rebalance_opts(k); + if (!opts) + return 0; + + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + u64 sectors = 0; + + if (opts->background_compression) { + unsigned compression_type = bch2_compression_opt_to_type(opts->background_compression); + + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) { + sectors = 0; + goto incompressible; + } + + if (!p.ptr.cached && p.crc.compression_type != compression_type) + sectors += p.crc.compressed_size; + } + } +incompressible: + if (opts->background_target && + bch2_target_accepts_data(c, BCH_DATA_user, opts->background_target)) { + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) + if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, opts->background_target)) + sectors += p.crc.compressed_size; + } + + return sectors; +} + +static bool bch2_bkey_rebalance_needs_update(struct bch_fs *c, struct bch_io_opts *opts, + struct bkey_s_c k) +{ + if (!bkey_extent_is_direct_data(k.k)) + return 0; + + const struct bch_extent_rebalance *old = bch2_bkey_rebalance_opts(k); + + if (k.k->type == KEY_TYPE_reflink_v || bch2_bkey_ptrs_need_rebalance(c, opts, k)) { + struct bch_extent_rebalance new = io_opts_to_rebalance_opts(opts); + return old == NULL || memcmp(old, &new, sizeof(new)); + } else { + return old != NULL; + } +} + +int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bch_io_opts *opts, + struct bkey_i *_k) +{ + if (!bkey_extent_is_direct_data(&_k->k)) + return 0; + + struct bkey_s k = bkey_i_to_s(_k); + struct bch_extent_rebalance *old = + (struct bch_extent_rebalance *) bch2_bkey_rebalance_opts(k.s_c); + + if (k.k->type == KEY_TYPE_reflink_v || bch2_bkey_ptrs_need_rebalance(c, opts, k.s_c)) { + if (!old) { + old = bkey_val_end(k); + k.k->u64s += sizeof(*old) / sizeof(u64); + } + + *old = io_opts_to_rebalance_opts(opts); + } else { + if (old) + extent_entry_drop(k, (union bch_extent_entry *) old); + } + + return 0; +} + +int bch2_get_update_rebalance_opts(struct btree_trans *trans, + struct bch_io_opts *io_opts, + struct btree_iter *iter, + struct bkey_s_c k) +{ + BUG_ON(iter->flags & BTREE_ITER_is_extents); + BUG_ON(iter->flags & BTREE_ITER_filter_snapshots); + + const struct bch_extent_rebalance *r = k.k->type == KEY_TYPE_reflink_v + ? bch2_bkey_rebalance_opts(k) : NULL; + if (r) { +#define x(_name) \ + if (r->_name##_from_inode) { \ + io_opts->_name = r->_name; \ + io_opts->_name##_from_inode = true; \ + } + BCH_REBALANCE_OPTS() +#undef x + } + + if (!bch2_bkey_rebalance_needs_update(trans->c, io_opts, k)) + return 0; + + struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(k.k) + 8); + int ret = PTR_ERR_OR_ZERO(n); + if (ret) + return ret; + + bkey_reassemble(n, k); + + /* On successfull transaction commit, @k was invalidated: */ + + return bch2_bkey_set_needs_rebalance(trans->c, io_opts, n) ?: + bch2_trans_update(trans, iter, n, BTREE_UPDATE_internal_snapshot_node) ?: + bch2_trans_commit(trans, NULL, NULL, 0) ?: + -BCH_ERR_transaction_restart_nested; +} + #define REBALANCE_WORK_SCAN_OFFSET (U64_MAX - 1) static const char * const bch2_rebalance_state_strs[] = { @@ -33,7 +219,7 @@ static const char * const bch2_rebalance_state_strs[] = { #undef x }; -static int __bch2_set_rebalance_needs_scan(struct btree_trans *trans, u64 inum) +int bch2_set_rebalance_needs_scan_trans(struct btree_trans *trans, u64 inum) { struct btree_iter iter; struct bkey_s_c k; @@ -71,9 +257,8 @@ err: int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum) { int ret = bch2_trans_commit_do(c, NULL, NULL, - BCH_TRANS_COMMIT_no_enospc| - BCH_TRANS_COMMIT_lazy_rw, - __bch2_set_rebalance_needs_scan(trans, inum)); + BCH_TRANS_COMMIT_no_enospc, + bch2_set_rebalance_needs_scan_trans(trans, inum)); rebalance_wakeup(c); return ret; } @@ -121,6 +306,9 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { + if (!bch2_bkey_rebalance_opts(k)) + return 0; + struct bkey_i *n = bch2_bkey_make_mut(trans, iter, &k, 0); int ret = PTR_ERR_OR_ZERO(n); if (ret) @@ -134,31 +322,27 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans, static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans, struct bpos work_pos, struct btree_iter *extent_iter, + struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { struct bch_fs *c = trans->c; - struct bkey_s_c k; bch2_trans_iter_exit(trans, extent_iter); bch2_trans_iter_init(trans, extent_iter, work_pos.inode ? BTREE_ID_extents : BTREE_ID_reflink, work_pos, BTREE_ITER_all_snapshots); - k = bch2_btree_iter_peek_slot(extent_iter); + struct bkey_s_c k = bch2_btree_iter_peek_slot(extent_iter); if (bkey_err(k)) return k; - const struct bch_extent_rebalance *r = k.k ? bch2_bkey_rebalance_opts(k) : NULL; - if (!r) { - /* raced due to btree write buffer, nothing to do */ - return bkey_s_c_null; - } + int ret = bch2_move_get_io_opts_one(trans, io_opts, extent_iter, k); + if (ret) + return bkey_s_c_err(ret); memset(data_opts, 0, sizeof(*data_opts)); - - data_opts->rewrite_ptrs = - bch2_bkey_ptrs_need_rebalance(c, k, r->target, r->compression); - data_opts->target = r->target; + data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, io_opts, k); + data_opts->target = io_opts->background_target; data_opts->write_flags |= BCH_WRITE_ONLY_SPECIFIED_DEVS; if (!data_opts->rewrite_ptrs) { @@ -178,12 +362,28 @@ static struct bkey_s_c next_rebalance_extent(struct btree_trans *trans, if (trace_rebalance_extent_enabled()) { struct printbuf buf = PRINTBUF; - prt_str(&buf, "target="); - bch2_target_to_text(&buf, c, r->target); - prt_str(&buf, " compression="); - bch2_compression_opt_to_text(&buf, r->compression); - prt_str(&buf, " "); bch2_bkey_val_to_text(&buf, c, k); + prt_newline(&buf); + + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + + unsigned p = bch2_bkey_ptrs_need_compress(c, io_opts, k, ptrs); + if (p) { + prt_str(&buf, "compression="); + bch2_compression_opt_to_text(&buf, io_opts->background_compression); + prt_str(&buf, " "); + bch2_prt_u64_base2(&buf, p); + prt_newline(&buf); + } + + p = bch2_bkey_ptrs_need_move(c, io_opts, ptrs); + if (p) { + prt_str(&buf, "move="); + bch2_target_to_text(&buf, c, io_opts->background_target); + prt_str(&buf, " "); + bch2_prt_u64_base2(&buf, p); + prt_newline(&buf); + } trace_rebalance_extent(c, buf.buf); printbuf_exit(&buf); @@ -212,14 +412,10 @@ static int do_rebalance_extent(struct moving_context *ctxt, bch2_bkey_buf_init(&sk); ret = bkey_err(k = next_rebalance_extent(trans, work_pos, - extent_iter, &data_opts)); + extent_iter, &io_opts, &data_opts)); if (ret || !k.k) goto out; - ret = bch2_move_get_io_opts_one(trans, &io_opts, k); - if (ret) - goto out; - atomic64_add(k.k->size, &ctxt->stats->sectors_seen); /* @@ -253,20 +449,8 @@ static bool rebalance_pred(struct bch_fs *c, void *arg, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { - unsigned target, compression; - - if (k.k->p.inode) { - target = io_opts->background_target; - compression = background_compression(*io_opts); - } else { - const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k); - - target = r ? r->target : io_opts->background_target; - compression = r ? r->compression : background_compression(*io_opts); - } - - data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, k, target, compression); - data_opts->target = target; + data_opts->rewrite_ptrs = bch2_bkey_ptrs_need_rebalance(c, io_opts, k); + data_opts->target = io_opts->background_target; data_opts->write_flags |= BCH_WRITE_ONLY_SPECIFIED_DEVS; return data_opts->rewrite_ptrs != 0; } @@ -338,9 +522,9 @@ static int do_rebalance(struct moving_context *ctxt) BTREE_ITER_all_snapshots); while (!bch2_move_ratelimit(ctxt)) { - if (!r->enabled) { + if (!c->opts.rebalance_enabled) { bch2_moving_ctxt_flush_all(ctxt); - kthread_wait_freezable(r->enabled || + kthread_wait_freezable(c->opts.rebalance_enabled || kthread_should_stop()); } diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h index 28a52638f16c..0a0821ab895d 100644 --- a/fs/bcachefs/rebalance.h +++ b/fs/bcachefs/rebalance.h @@ -2,8 +2,18 @@ #ifndef _BCACHEFS_REBALANCE_H #define _BCACHEFS_REBALANCE_H +#include "compress.h" +#include "disk_groups.h" #include "rebalance_types.h" +u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); +int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bch_io_opts *, struct bkey_i *); +int bch2_get_update_rebalance_opts(struct btree_trans *, + struct bch_io_opts *, + struct btree_iter *, + struct bkey_s_c); + +int bch2_set_rebalance_needs_scan_trans(struct btree_trans *, u64); int bch2_set_rebalance_needs_scan(struct bch_fs *, u64 inum); int bch2_set_fs_needs_rebalance(struct bch_fs *); diff --git a/fs/bcachefs/rebalance_format.h b/fs/bcachefs/rebalance_format.h new file mode 100644 index 000000000000..ff9a1342a22b --- /dev/null +++ b/fs/bcachefs/rebalance_format.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_REBALANCE_FORMAT_H +#define _BCACHEFS_REBALANCE_FORMAT_H + +struct bch_extent_rebalance { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 type:6, + unused:3, + + promote_target_from_inode:1, + erasure_code_from_inode:1, + data_checksum_from_inode:1, + background_compression_from_inode:1, + data_replicas_from_inode:1, + background_target_from_inode:1, + + promote_target:16, + erasure_code:1, + data_checksum:4, + data_replicas:4, + background_compression:8, /* enum bch_compression_opt */ + background_target:16; +#elif defined (__BIG_ENDIAN_BITFIELD) + __u64 background_target:16, + background_compression:8, + data_replicas:4, + data_checksum:4, + erasure_code:1, + promote_target:16, + + background_target_from_inode:1, + data_replicas_from_inode:1, + background_compression_from_inode:1, + data_checksum_from_inode:1, + erasure_code_from_inode:1, + promote_target_from_inode:1, + + unused:3, + type:6; +#endif +}; + +/* subset of BCH_INODE_OPTS */ +#define BCH_REBALANCE_OPTS() \ + x(data_checksum) \ + x(background_compression) \ + x(data_replicas) \ + x(promote_target) \ + x(background_target) \ + x(erasure_code) + +#endif /* _BCACHEFS_REBALANCE_FORMAT_H */ + diff --git a/fs/bcachefs/rebalance_types.h b/fs/bcachefs/rebalance_types.h index 0fffb536c1d0..fe5098c17dfc 100644 --- a/fs/bcachefs/rebalance_types.h +++ b/fs/bcachefs/rebalance_types.h @@ -30,8 +30,6 @@ struct bch_fs_rebalance { struct bbpos scan_start; struct bbpos scan_end; struct bch_move_stats scan_stats; - - unsigned enabled:1; }; #endif /* _BCACHEFS_REBALANCE_TYPES_H */ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 3c7f941dde39..98825437381c 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -34,21 +34,83 @@ #define QSTR(n) { { { .len = strlen(n) } }, .name = n } -void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) +int bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) { - if (btree >= BTREE_ID_NR_MAX) - return; - u64 b = BIT_ULL(btree); + int ret = 0; + + mutex_lock(&c->sb_lock); + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); if (!(c->sb.btrees_lost_data & b)) { - bch_err(c, "flagging btree %s lost data", bch2_btree_id_str(btree)); + struct printbuf buf = PRINTBUF; + bch2_btree_id_to_text(&buf, btree); + bch_err(c, "flagging btree %s lost data", buf.buf); + printbuf_exit(&buf); + ext->btrees_lost_data |= cpu_to_le64(b); + } - mutex_lock(&c->sb_lock); - bch2_sb_field_get(c->disk_sb.sb, ext)->btrees_lost_data |= cpu_to_le64(b); - bch2_write_super(c); - mutex_unlock(&c->sb_lock); + /* Once we have runtime self healing for topology errors we won't need this: */ + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_topology) ?: ret; + + /* Btree node accounting will be off: */ + __set_bit_le64(BCH_FSCK_ERR_accounting_mismatch, ext->errors_silent); + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_allocations) ?: ret; + +#ifdef CONFIG_BCACHEFS_DEBUG + /* + * These are much more minor, and don't need to be corrected right away, + * but in debug mode we want the next fsck run to be clean: + */ + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_lrus) ?: ret; + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_backpointers_to_extents) ?: ret; +#endif + + switch (btree) { + case BTREE_ID_alloc: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + + __set_bit_le64(BCH_FSCK_ERR_alloc_key_data_type_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_gen_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_cached_sectors_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_redundancy_wrong, ext->errors_silent); + goto out; + case BTREE_ID_backpointers: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_btree_backpointers) ?: ret; + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_extents_to_backpointers) ?: ret; + goto out; + case BTREE_ID_need_discard: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_freespace: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_bucket_gens: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_lru: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_alloc_info) ?: ret; + goto out; + case BTREE_ID_accounting: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_check_allocations) ?: ret; + goto out; + default: + ret = bch2_run_explicit_recovery_pass_persistent_locked(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?: ret; + goto out; } +out: + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + + return ret; +} + +static void kill_btree(struct bch_fs *c, enum btree_id btree) +{ + bch2_btree_id_root(c, btree)->alive = false; + bch2_shoot_down_journal_keys(c, btree, 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); } /* for -o reconstruct_alloc: */ @@ -79,6 +141,8 @@ static void bch2_reconstruct_alloc(struct bch_fs *c) __set_bit_le64(BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_fs_usage_replicas_wrong, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_to_missing_lru_entry, ext->errors_silent); + __set_bit_le64(BCH_FSCK_ERR_alloc_key_data_type_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_alloc_key_gen_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong, ext->errors_silent); @@ -99,16 +163,9 @@ static void bch2_reconstruct_alloc(struct bch_fs *c) bch2_write_super(c); mutex_unlock(&c->sb_lock); - bch2_shoot_down_journal_keys(c, BTREE_ID_alloc, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_backpointers, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_need_discard, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_freespace, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - bch2_shoot_down_journal_keys(c, BTREE_ID_bucket_gens, - 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + for (unsigned i = 0; i < btree_id_nr_alive(c); i++) + if (btree_id_is_alloc(i)) + kill_btree(c, i); } /* @@ -354,10 +411,13 @@ int bch2_journal_replay(struct bch_fs *c) ? BCH_TRANS_COMMIT_no_journal_res|BCH_WATERMARK_reclaim : 0), bch2_journal_replay_key(trans, k)); - bch_err_msg(c, ret, "while replaying key at btree %s level %u:", - bch2_btree_id_str(k->btree_id), k->level); - if (ret) + if (ret) { + struct printbuf buf = PRINTBUF; + bch2_btree_id_level_to_text(&buf, k->btree_id, k->level); + bch_err_msg(c, ret, "while replaying key at %s:", buf.buf); + printbuf_exit(&buf); goto err; + } BUG_ON(k->btree_id != BTREE_ID_accounting && !k->overwritten); } @@ -403,7 +463,9 @@ static int journal_replay_entry_early(struct bch_fs *c, switch (entry->type) { case BCH_JSET_ENTRY_btree_root: { - struct btree_root *r; + + if (unlikely(!entry->u64s)) + return 0; if (fsck_err_on(entry->btree_id >= BTREE_ID_NR_MAX, c, invalid_btree_id, @@ -417,15 +479,11 @@ static int journal_replay_entry_early(struct bch_fs *c, return ret; } - r = bch2_btree_id_root(c, entry->btree_id); + struct btree_root *r = bch2_btree_id_root(c, entry->btree_id); - if (entry->u64s) { - r->level = entry->level; - bkey_copy(&r->key, (struct bkey_i *) entry->start); - r->error = 0; - } else { - r->error = -BCH_ERR_btree_node_read_error; - } + r->level = entry->level; + bkey_copy(&r->key, (struct bkey_i *) entry->start); + r->error = 0; r->alive = true; break; } @@ -505,6 +563,7 @@ static int journal_replay_early(struct bch_fs *c, static int read_btree_roots(struct bch_fs *c) { + struct printbuf buf = PRINTBUF; int ret = 0; for (unsigned i = 0; i < btree_id_nr_alive(c); i++) { @@ -513,33 +572,22 @@ static int read_btree_roots(struct bch_fs *c) if (!r->alive) continue; - if (btree_id_is_alloc(i) && c->opts.reconstruct_alloc) - continue; + printbuf_reset(&buf); + bch2_btree_id_level_to_text(&buf, i, r->level); if (mustfix_fsck_err_on((ret = r->error), c, btree_root_bkey_invalid, "invalid btree root %s", - bch2_btree_id_str(i)) || + buf.buf) || mustfix_fsck_err_on((ret = r->error = bch2_btree_root_read(c, i, &r->key, r->level)), c, btree_root_read_error, - "error reading btree root %s l=%u: %s", - bch2_btree_id_str(i), r->level, bch2_err_str(ret))) { - if (btree_id_is_alloc(i)) { - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_allocations); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_lrus); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_to_lru_refs); - c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info); + "error reading btree root %s: %s", + buf.buf, bch2_err_str(ret))) { + if (btree_id_is_alloc(i)) r->error = 0; - } else if (!(c->opts.recovery_passes & BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes))) { - bch_info(c, "will run btree node scan"); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes); - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); - } - ret = 0; - bch2_btree_lost_data(c, i); + ret = bch2_btree_lost_data(c, i); + BUG_ON(ret); } } @@ -553,6 +601,7 @@ static int read_btree_roots(struct bch_fs *c) } } fsck_err: + printbuf_exit(&buf); return ret; } @@ -563,6 +612,7 @@ static bool check_version_upgrade(struct bch_fs *c) bch2_latest_compatible_version(c->sb.version)); unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version; unsigned new_version = 0; + bool ret = false; if (old_version < bcachefs_metadata_required_upgrade_below) { if (c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible || @@ -618,14 +668,32 @@ static bool check_version_upgrade(struct bch_fs *c) } bch_info(c, "%s", buf.buf); + printbuf_exit(&buf); - bch2_sb_upgrade(c, new_version); + ret = true; + } + if (new_version > c->sb.version_incompat && + c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "Now allowing incompatible features up to "); + bch2_version_to_text(&buf, new_version); + prt_str(&buf, ", previously allowed up to "); + bch2_version_to_text(&buf, c->sb.version_incompat_allowed); + prt_newline(&buf); + + bch_info(c, "%s", buf.buf); printbuf_exit(&buf); - return true; + + ret = true; } - return false; + if (ret) + bch2_sb_upgrade(c, new_version, + c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible); + + return ret; } int bch2_fs_recovery(struct bch_fs *c) @@ -660,8 +728,13 @@ int bch2_fs_recovery(struct bch_fs *c) goto err; } - if (c->opts.norecovery) - c->opts.recovery_pass_last = BCH_RECOVERY_PASS_journal_replay - 1; + if (c->opts.norecovery) { + c->opts.recovery_pass_last = c->opts.recovery_pass_last + ? min(c->opts.recovery_pass_last, BCH_RECOVERY_PASS_snapshots_read) + : BCH_RECOVERY_PASS_snapshots_read; + c->opts.nochanges = true; + c->opts.read_only = true; + } mutex_lock(&c->sb_lock); struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); @@ -708,17 +781,20 @@ int bch2_fs_recovery(struct bch_fs *c) c->opts.recovery_passes |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + if (c->sb.version_upgrade_complete < bcachefs_metadata_version_autofix_errors) { + SET_BCH_SB_ERROR_ACTION(c->disk_sb.sb, BCH_ON_ERROR_fix_safe); + write_sb = true; + } + if (write_sb) bch2_write_super(c); mutex_unlock(&c->sb_lock); - if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) - c->opts.recovery_passes |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); - if (c->opts.fsck) set_bit(BCH_FS_fsck_running, &c->flags); if (c->sb.clean) set_bit(BCH_FS_clean_recovery, &c->flags); + set_bit(BCH_FS_recovery_running, &c->flags); ret = bch2_blacklist_table_initialize(c); if (ret) { @@ -807,15 +883,15 @@ use_clean: c->journal_replay_seq_start = last_seq; c->journal_replay_seq_end = blacklist_seq - 1; - if (c->opts.reconstruct_alloc) - bch2_reconstruct_alloc(c); - zero_out_btree_mem_ptr(&c->journal_keys); ret = journal_replay_early(c, clean); if (ret) goto err; + if (c->opts.reconstruct_alloc) + bch2_reconstruct_alloc(c); + /* * After an unclean shutdown, skip then next few journal sequence * numbers as they may have been referenced by btree writes that @@ -870,16 +946,17 @@ use_clean: */ set_bit(BCH_FS_may_go_rw, &c->flags); clear_bit(BCH_FS_fsck_running, &c->flags); + clear_bit(BCH_FS_recovery_running, &c->flags); /* in case we don't run journal replay, i.e. norecovery mode */ set_bit(BCH_FS_accounting_replay_done, &c->flags); + bch2_async_btree_node_rewrites_flush(c); + /* fsync if we fixed errors */ - if (test_bit(BCH_FS_errors_fixed, &c->flags) && - bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) { + if (test_bit(BCH_FS_errors_fixed, &c->flags)) { bch2_journal_flush_all_pins(&c->journal); bch2_journal_meta(&c->journal); - bch2_write_ref_put(c, BCH_WRITE_REF_fsync); } /* If we fixed errors, verify that fs is actually clean now: */ @@ -1021,7 +1098,7 @@ int bch2_fs_initialize(struct bch_fs *c) bch2_check_version_downgrade(c); if (c->opts.version_upgrade != BCH_VERSION_UPGRADE_none) { - bch2_sb_upgrade(c, bcachefs_metadata_version_current); + bch2_sb_upgrade(c, bcachefs_metadata_version_current, false); SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); bch2_write_super(c); } @@ -1035,7 +1112,6 @@ int bch2_fs_initialize(struct bch_fs *c) bch2_write_super(c); mutex_unlock(&c->sb_lock); - c->curr_recovery_pass = BCH_RECOVERY_PASS_NR; set_bit(BCH_FS_btree_running, &c->flags); set_bit(BCH_FS_may_go_rw, &c->flags); @@ -1076,9 +1152,6 @@ int bch2_fs_initialize(struct bch_fs *c) if (ret) goto err; - for_each_online_member(c, ca) - ca->new_fs_bucket_idx = 0; - ret = bch2_fs_freespace_init(c); if (ret) goto err; @@ -1137,6 +1210,7 @@ int bch2_fs_initialize(struct bch_fs *c) bch2_write_super(c); mutex_unlock(&c->sb_lock); + c->curr_recovery_pass = BCH_RECOVERY_PASS_NR; return 0; err: bch_err_fn(c, ret); diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h index 4bf818de1f2f..b0d55754b21b 100644 --- a/fs/bcachefs/recovery.h +++ b/fs/bcachefs/recovery.h @@ -2,7 +2,7 @@ #ifndef _BCACHEFS_RECOVERY_H #define _BCACHEFS_RECOVERY_H -void bch2_btree_lost_data(struct bch_fs *, enum btree_id); +int bch2_btree_lost_data(struct bch_fs *, enum btree_id); int bch2_journal_replay(struct bch_fs *); diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index dff589ddc984..0b3c951c32da 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -46,7 +46,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c) set_bit(BCH_FS_may_go_rw, &c->flags); - if (keys->nr || c->opts.fsck || !c->sb.clean || c->opts.recovery_passes) + if (keys->nr || !c->opts.read_only || c->opts.fsck || !c->sb.clean || c->opts.recovery_passes) return bch2_fs_read_write_early(c); return 0; } @@ -100,20 +100,34 @@ u64 bch2_recovery_passes_from_stable(u64 v) /* * For when we need to rewind recovery passes and run a pass we skipped: */ -int bch2_run_explicit_recovery_pass(struct bch_fs *c, - enum bch_recovery_pass pass) +static int __bch2_run_explicit_recovery_pass(struct bch_fs *c, + enum bch_recovery_pass pass) { - if (c->opts.recovery_passes & BIT_ULL(pass)) + if (c->curr_recovery_pass == ARRAY_SIZE(recovery_pass_fns)) + return -BCH_ERR_not_in_recovery; + + if (c->recovery_passes_complete & BIT_ULL(pass)) return 0; - bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", - bch2_recovery_passes[pass], pass, - bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); + bool print = !(c->opts.recovery_passes & BIT_ULL(pass)); + + if (pass < BCH_RECOVERY_PASS_set_may_go_rw && + c->curr_recovery_pass >= BCH_RECOVERY_PASS_set_may_go_rw) { + if (print) + bch_info(c, "need recovery pass %s (%u), but already rw", + bch2_recovery_passes[pass], pass); + return -BCH_ERR_cannot_rewind_recovery; + } + + if (print) + bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", + bch2_recovery_passes[pass], pass, + bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); c->opts.recovery_passes |= BIT_ULL(pass); - if (c->curr_recovery_pass >= pass) { - c->curr_recovery_pass = pass; + if (c->curr_recovery_pass > pass) { + c->next_recovery_pass = pass; c->recovery_passes_complete &= (1ULL << pass) >> 1; return -BCH_ERR_restart_recovery; } else { @@ -121,6 +135,27 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *c, } } +int bch2_run_explicit_recovery_pass(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + unsigned long flags; + spin_lock_irqsave(&c->recovery_pass_lock, flags); + int ret = __bch2_run_explicit_recovery_pass(c, pass); + spin_unlock_irqrestore(&c->recovery_pass_lock, flags); + return ret; +} + +int bch2_run_explicit_recovery_pass_persistent_locked(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + lockdep_assert_held(&c->sb_lock); + + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + __set_bit_le64(bch2_recovery_pass_to_stable(pass), ext->recovery_passes_required); + + return bch2_run_explicit_recovery_pass(c, pass); +} + int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *c, enum bch_recovery_pass pass) { @@ -233,31 +268,48 @@ int bch2_run_recovery_passes(struct bch_fs *c) */ c->opts.recovery_passes_exclude &= ~BCH_RECOVERY_PASS_set_may_go_rw; - while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) { - if (c->opts.recovery_pass_last && - c->curr_recovery_pass > c->opts.recovery_pass_last) - break; - - if (should_run_recovery_pass(c, c->curr_recovery_pass)) { - unsigned pass = c->curr_recovery_pass; + while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) { + c->next_recovery_pass = c->curr_recovery_pass + 1; - ret = bch2_run_recovery_pass(c, c->curr_recovery_pass) ?: - bch2_journal_flush(&c->journal); - if (bch2_err_matches(ret, BCH_ERR_restart_recovery) || - (ret && c->curr_recovery_pass < pass)) - continue; - if (ret) - break; + spin_lock_irq(&c->recovery_pass_lock); + unsigned pass = c->curr_recovery_pass; - c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass); + if (c->opts.recovery_pass_last && + c->curr_recovery_pass > c->opts.recovery_pass_last) { + spin_unlock_irq(&c->recovery_pass_lock); + break; } - c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass); - - if (!test_bit(BCH_FS_error, &c->flags)) - bch2_clear_recovery_pass_required(c, c->curr_recovery_pass); - - c->curr_recovery_pass++; + if (!should_run_recovery_pass(c, pass)) { + c->curr_recovery_pass++; + c->recovery_pass_done = max(c->recovery_pass_done, pass); + spin_unlock_irq(&c->recovery_pass_lock); + continue; + } + spin_unlock_irq(&c->recovery_pass_lock); + + ret = bch2_run_recovery_pass(c, pass) ?: + bch2_journal_flush(&c->journal); + + if (!ret && !test_bit(BCH_FS_error, &c->flags)) + bch2_clear_recovery_pass_required(c, pass); + + spin_lock_irq(&c->recovery_pass_lock); + if (c->next_recovery_pass < c->curr_recovery_pass) { + /* + * bch2_run_explicit_recovery_pass() was called: we + * can't always catch -BCH_ERR_restart_recovery because + * it may have been called from another thread (btree + * node read completion) + */ + ret = 0; + c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass); + } else { + c->recovery_passes_complete |= BIT_ULL(pass); + c->recovery_pass_done = max(c->recovery_pass_done, pass); + } + c->curr_recovery_pass = c->next_recovery_pass; + spin_unlock_irq(&c->recovery_pass_lock); } return ret; diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h index 99b464e127b8..7d7339c8fa29 100644 --- a/fs/bcachefs/recovery_passes.h +++ b/fs/bcachefs/recovery_passes.h @@ -9,6 +9,7 @@ u64 bch2_recovery_passes_from_stable(u64 v); u64 bch2_fsck_recovery_passes(void); int bch2_run_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass); +int bch2_run_explicit_recovery_pass_persistent_locked(struct bch_fs *, enum bch_recovery_pass); int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *, enum bch_recovery_pass); int bch2_run_online_recovery_passes(struct bch_fs *); diff --git a/fs/bcachefs/recovery_passes_types.h b/fs/bcachefs/recovery_passes_types.h index 94dc20ca2065..418557960ed6 100644 --- a/fs/bcachefs/recovery_passes_types.h +++ b/fs/bcachefs/recovery_passes_types.h @@ -8,53 +8,59 @@ #define PASS_ALWAYS BIT(3) #define PASS_ONLINE BIT(4) +#ifdef CONFIG_BCACHEFS_DEBUG +#define PASS_FSCK_DEBUG BIT(1) +#else +#define PASS_FSCK_DEBUG 0 +#endif + /* * Passes may be reordered, but the second field is a persistent identifier and * must never change: */ -#define BCH_RECOVERY_PASSES() \ - x(recovery_pass_empty, 41, PASS_SILENT) \ - x(scan_for_btree_nodes, 37, 0) \ - x(check_topology, 4, 0) \ - x(accounting_read, 39, PASS_ALWAYS) \ - x(alloc_read, 0, PASS_ALWAYS) \ - x(stripes_read, 1, PASS_ALWAYS) \ - x(initialize_subvolumes, 2, 0) \ - x(snapshots_read, 3, PASS_ALWAYS) \ - x(check_allocations, 5, PASS_FSCK) \ - x(trans_mark_dev_sbs, 6, PASS_ALWAYS|PASS_SILENT) \ - x(fs_journal_alloc, 7, PASS_ALWAYS|PASS_SILENT) \ - x(set_may_go_rw, 8, PASS_ALWAYS|PASS_SILENT) \ - x(journal_replay, 9, PASS_ALWAYS) \ - x(check_alloc_info, 10, PASS_ONLINE|PASS_FSCK) \ - x(check_lrus, 11, PASS_ONLINE|PASS_FSCK) \ - x(check_btree_backpointers, 12, PASS_ONLINE|PASS_FSCK) \ - x(check_backpointers_to_extents, 13, PASS_ONLINE|PASS_FSCK) \ - x(check_extents_to_backpointers, 14, PASS_ONLINE|PASS_FSCK) \ - x(check_alloc_to_lru_refs, 15, PASS_ONLINE|PASS_FSCK) \ - x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ - x(bucket_gens_init, 17, 0) \ - x(reconstruct_snapshots, 38, 0) \ - x(check_snapshot_trees, 18, PASS_ONLINE|PASS_FSCK) \ - x(check_snapshots, 19, PASS_ONLINE|PASS_FSCK) \ - x(check_subvols, 20, PASS_ONLINE|PASS_FSCK) \ - x(check_subvol_children, 35, PASS_ONLINE|PASS_FSCK) \ - x(delete_dead_snapshots, 21, PASS_ONLINE|PASS_FSCK) \ - x(fs_upgrade_for_subvolumes, 22, 0) \ - x(check_inodes, 24, PASS_FSCK) \ - x(check_extents, 25, PASS_FSCK) \ - x(check_indirect_extents, 26, PASS_FSCK) \ - x(check_dirents, 27, PASS_FSCK) \ - x(check_xattrs, 28, PASS_FSCK) \ - x(check_root, 29, PASS_ONLINE|PASS_FSCK) \ - x(check_unreachable_inodes, 40, PASS_ONLINE|PASS_FSCK) \ - x(check_subvolume_structure, 36, PASS_ONLINE|PASS_FSCK) \ - x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ - x(check_nlinks, 31, PASS_FSCK) \ - x(resume_logged_ops, 23, PASS_ALWAYS) \ - x(delete_dead_inodes, 32, PASS_ALWAYS) \ - x(fix_reflink_p, 33, 0) \ - x(set_fs_needs_rebalance, 34, 0) \ +#define BCH_RECOVERY_PASSES() \ + x(recovery_pass_empty, 41, PASS_SILENT) \ + x(scan_for_btree_nodes, 37, 0) \ + x(check_topology, 4, 0) \ + x(accounting_read, 39, PASS_ALWAYS) \ + x(alloc_read, 0, PASS_ALWAYS) \ + x(stripes_read, 1, PASS_ALWAYS) \ + x(initialize_subvolumes, 2, 0) \ + x(snapshots_read, 3, PASS_ALWAYS) \ + x(check_allocations, 5, PASS_FSCK) \ + x(trans_mark_dev_sbs, 6, PASS_ALWAYS|PASS_SILENT) \ + x(fs_journal_alloc, 7, PASS_ALWAYS|PASS_SILENT) \ + x(set_may_go_rw, 8, PASS_ALWAYS|PASS_SILENT) \ + x(journal_replay, 9, PASS_ALWAYS) \ + x(check_alloc_info, 10, PASS_ONLINE|PASS_FSCK) \ + x(check_lrus, 11, PASS_ONLINE|PASS_FSCK) \ + x(check_btree_backpointers, 12, PASS_ONLINE|PASS_FSCK) \ + x(check_backpointers_to_extents, 13, PASS_ONLINE|PASS_FSCK_DEBUG) \ + x(check_extents_to_backpointers, 14, PASS_ONLINE|PASS_FSCK) \ + x(check_alloc_to_lru_refs, 15, PASS_ONLINE|PASS_FSCK) \ + x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ + x(bucket_gens_init, 17, 0) \ + x(reconstruct_snapshots, 38, 0) \ + x(check_snapshot_trees, 18, PASS_ONLINE|PASS_FSCK) \ + x(check_snapshots, 19, PASS_ONLINE|PASS_FSCK) \ + x(check_subvols, 20, PASS_ONLINE|PASS_FSCK) \ + x(check_subvol_children, 35, PASS_ONLINE|PASS_FSCK) \ + x(delete_dead_snapshots, 21, PASS_ONLINE|PASS_FSCK) \ + x(fs_upgrade_for_subvolumes, 22, 0) \ + x(check_inodes, 24, PASS_FSCK) \ + x(check_extents, 25, PASS_FSCK) \ + x(check_indirect_extents, 26, PASS_ONLINE|PASS_FSCK) \ + x(check_dirents, 27, PASS_FSCK) \ + x(check_xattrs, 28, PASS_FSCK) \ + x(check_root, 29, PASS_ONLINE|PASS_FSCK) \ + x(check_unreachable_inodes, 40, PASS_FSCK) \ + x(check_subvolume_structure, 36, PASS_ONLINE|PASS_FSCK) \ + x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ + x(check_nlinks, 31, PASS_FSCK) \ + x(resume_logged_ops, 23, PASS_ALWAYS) \ + x(delete_dead_inodes, 32, PASS_ALWAYS) \ + x(fix_reflink_p, 33, 0) \ + x(set_fs_needs_rebalance, 34, 0) /* We normally enumerate recovery passes in the order we run them: */ enum bch_recovery_pass { diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index f457925fa362..93ba4f4e47ca 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -15,6 +15,17 @@ #include <linux/sched/signal.h> +static inline bool bkey_extent_is_reflink_data(const struct bkey *k) +{ + switch (k->type) { + case KEY_TYPE_reflink_v: + case KEY_TYPE_indirect_inline_data: + return true; + default: + return false; + } +} + static inline unsigned bkey_type_to_indirect(const struct bkey *k) { switch (k->type) { @@ -30,15 +41,15 @@ static inline unsigned bkey_type_to_indirect(const struct bkey *k) /* reflink pointers */ int bch2_reflink_p_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); int ret = 0; - bkey_fsck_err_on(le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad), + bkey_fsck_err_on(REFLINK_P_IDX(p.v) < le32_to_cpu(p.v->front_pad), c, reflink_p_front_pad_bad, "idx < front_pad (%llu < %u)", - le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad)); + REFLINK_P_IDX(p.v), le32_to_cpu(p.v->front_pad)); fsck_err: return ret; } @@ -49,7 +60,7 @@ void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); prt_printf(out, "idx %llu front_pad %u back_pad %u", - le64_to_cpu(p.v->idx), + REFLINK_P_IDX(p.v), le32_to_cpu(p.v->front_pad), le32_to_cpu(p.v->back_pad)); } @@ -65,49 +76,250 @@ bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r */ return false; - if (le64_to_cpu(l.v->idx) + l.k->size != le64_to_cpu(r.v->idx)) + if (REFLINK_P_IDX(l.v) + l.k->size != REFLINK_P_IDX(r.v)) + return false; + + if (REFLINK_P_ERROR(l.v) != REFLINK_P_ERROR(r.v)) return false; bch2_key_resize(l.k, l.k->size + r.k->size); return true; } +/* indirect extents */ + +int bch2_reflink_v_validate(struct bch_fs *c, struct bkey_s_c k, + struct bkey_validate_context from) +{ + int ret = 0; + + bkey_fsck_err_on(bkey_gt(k.k->p, POS(0, REFLINK_P_IDX_MAX)), + c, reflink_v_pos_bad, + "indirect extent above maximum position 0:%llu", + REFLINK_P_IDX_MAX); + + ret = bch2_bkey_ptrs_validate(c, k, from); +fsck_err: + return ret; +} + +void bch2_reflink_v_to_text(struct printbuf *out, struct bch_fs *c, + struct bkey_s_c k) +{ + struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(k); + + prt_printf(out, "refcount: %llu ", le64_to_cpu(r.v->refcount)); + + bch2_bkey_ptrs_to_text(out, c, k); +} + +#if 0 +Currently disabled, needs to be debugged: + +bool bch2_reflink_v_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r) +{ + struct bkey_s_reflink_v l = bkey_s_to_reflink_v(_l); + struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(_r); + + return l.v->refcount == r.v->refcount && bch2_extent_merge(c, _l, _r); +} +#endif + +/* indirect inline data */ + +int bch2_indirect_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, + struct bkey_validate_context from) +{ + return 0; +} + +void bch2_indirect_inline_data_to_text(struct printbuf *out, + struct bch_fs *c, struct bkey_s_c k) +{ + struct bkey_s_c_indirect_inline_data d = bkey_s_c_to_indirect_inline_data(k); + unsigned datalen = bkey_inline_data_bytes(k.k); + + prt_printf(out, "refcount %llu datalen %u: %*phN", + le64_to_cpu(d.v->refcount), datalen, + min(datalen, 32U), d.v->data); +} + +/* lookup */ + +static int bch2_indirect_extent_not_missing(struct btree_trans *trans, struct bkey_s_c_reflink_p p, + bool should_commit) +{ + struct bkey_i_reflink_p *new = bch2_bkey_make_mut_noupdate_typed(trans, p.s_c, reflink_p); + int ret = PTR_ERR_OR_ZERO(new); + if (ret) + return ret; + + SET_REFLINK_P_ERROR(&new->v, false); + ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, &new->k_i, BTREE_TRIGGER_norun); + if (ret) + return ret; + + if (!should_commit) + return 0; + + return bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; +} + +static int bch2_indirect_extent_missing_error(struct btree_trans *trans, + struct bkey_s_c_reflink_p p, + u64 missing_start, u64 missing_end, + bool should_commit) +{ + if (REFLINK_P_ERROR(p.v)) + return -BCH_ERR_missing_indirect_extent; + + struct bch_fs *c = trans->c; + u64 live_start = REFLINK_P_IDX(p.v); + u64 live_end = REFLINK_P_IDX(p.v) + p.k->size; + u64 refd_start = live_start - le32_to_cpu(p.v->front_pad); + u64 refd_end = live_end + le32_to_cpu(p.v->back_pad); + struct printbuf buf = PRINTBUF; + int ret = 0; + + BUG_ON(missing_start < refd_start); + BUG_ON(missing_end > refd_end); + + if (fsck_err(trans, reflink_p_to_missing_reflink_v, + "pointer to missing indirect extent\n" + " %s\n" + " missing range %llu-%llu", + (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf), + missing_start, missing_end)) { + struct bkey_i_reflink_p *new = bch2_bkey_make_mut_noupdate_typed(trans, p.s_c, reflink_p); + ret = PTR_ERR_OR_ZERO(new); + if (ret) + goto err; + + /* + * Is the missing range not actually needed? + * + * p.v->idx refers to the data that we actually want, but if the + * indirect extent we point to was bigger, front_pad and back_pad + * indicate the range we took a reference on. + */ + + if (missing_end <= live_start) { + new->v.front_pad = cpu_to_le32(live_start - missing_end); + } else if (missing_start >= live_end) { + new->v.back_pad = cpu_to_le32(missing_start - live_end); + } else { + struct bpos new_start = bkey_start_pos(&new->k); + struct bpos new_end = new->k.p; + + if (missing_start > live_start) + new_start.offset += missing_start - live_start; + if (missing_end < live_end) + new_end.offset -= live_end - missing_end; + + bch2_cut_front(new_start, &new->k_i); + bch2_cut_back(new_end, &new->k_i); + + SET_REFLINK_P_ERROR(&new->v, true); + } + + ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, &new->k_i, BTREE_TRIGGER_norun); + if (ret) + goto err; + + if (should_commit) + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; + } +err: +fsck_err: + printbuf_exit(&buf); + return ret; +} + +/* + * This is used from the read path, which doesn't expect to have to do a + * transaction commit, and from triggers, which should not be doing a commit: + */ +struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, + struct btree_iter *iter, + s64 *offset_into_extent, + struct bkey_s_c_reflink_p p, + bool should_commit, + unsigned iter_flags) +{ + BUG_ON(*offset_into_extent < -((s64) le32_to_cpu(p.v->front_pad))); + BUG_ON(*offset_into_extent >= p.k->size + le32_to_cpu(p.v->back_pad)); + + u64 reflink_offset = REFLINK_P_IDX(p.v) + *offset_into_extent; + + struct bkey_s_c k = bch2_bkey_get_iter(trans, iter, BTREE_ID_reflink, + POS(0, reflink_offset), iter_flags); + if (bkey_err(k)) + return k; + + if (unlikely(!bkey_extent_is_reflink_data(k.k))) { + bch2_trans_iter_exit(trans, iter); + + unsigned size = min((u64) k.k->size, + REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - + reflink_offset); + bch2_key_resize(&iter->k, size); + + int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, + k.k->p.offset, should_commit); + if (ret) + return bkey_s_c_err(ret); + } else if (unlikely(REFLINK_P_ERROR(p.v))) { + bch2_trans_iter_exit(trans, iter); + + int ret = bch2_indirect_extent_not_missing(trans, p, should_commit); + if (ret) + return bkey_s_c_err(ret); + } + + *offset_into_extent = reflink_offset - bkey_start_offset(k.k); + return k; +} + +/* reflink pointer trigger */ + static int trans_trigger_reflink_p_segment(struct btree_trans *trans, struct bkey_s_c_reflink_p p, u64 *idx, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; - struct btree_iter iter; - struct bkey_i *k; - __le64 *refcount; - int add = !(flags & BTREE_TRIGGER_overwrite) ? 1 : -1; struct printbuf buf = PRINTBUF; - int ret; - k = bch2_bkey_get_mut_noupdate(trans, &iter, - BTREE_ID_reflink, POS(0, *idx), - BTREE_ITER_with_updates); - ret = PTR_ERR_OR_ZERO(k); + s64 offset_into_extent = *idx - REFLINK_P_IDX(p.v); + struct btree_iter iter; + struct bkey_s_c k = bch2_lookup_indirect_extent(trans, &iter, &offset_into_extent, p, false, + BTREE_ITER_intent| + BTREE_ITER_with_updates); + int ret = bkey_err(k); if (ret) - goto err; + return ret; - refcount = bkey_refcount(bkey_i_to_s(k)); - if (!refcount) { - bch2_bkey_val_to_text(&buf, c, p.s_c); - bch2_trans_inconsistent(trans, - "nonexistent indirect extent at %llu while marking\n %s", - *idx, buf.buf); - ret = -EIO; - goto err; + if (bkey_deleted(k.k)) { + if (!(flags & BTREE_TRIGGER_overwrite)) + ret = -BCH_ERR_missing_indirect_extent; + goto next; } + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); + ret = PTR_ERR_OR_ZERO(new); + if (ret) + goto err; + + __le64 *refcount = bkey_refcount(bkey_i_to_s(new)); if (!*refcount && (flags & BTREE_TRIGGER_overwrite)) { bch2_bkey_val_to_text(&buf, c, p.s_c); - bch2_trans_inconsistent(trans, - "indirect extent refcount underflow at %llu while marking\n %s", - *idx, buf.buf); - ret = -EIO; - goto err; + prt_printf(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, k); + log_fsck_err(trans, reflink_refcount_underflow, + "indirect extent refcount underflow while marking\n %s", + buf.buf); + goto next; } if (flags & BTREE_TRIGGER_insert) { @@ -115,25 +327,26 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans, u64 pad; pad = max_t(s64, le32_to_cpu(v->front_pad), - le64_to_cpu(v->idx) - bkey_start_offset(&k->k)); + REFLINK_P_IDX(v) - bkey_start_offset(&new->k)); BUG_ON(pad > U32_MAX); v->front_pad = cpu_to_le32(pad); pad = max_t(s64, le32_to_cpu(v->back_pad), - k->k.p.offset - p.k->size - le64_to_cpu(v->idx)); + new->k.p.offset - p.k->size - REFLINK_P_IDX(v)); BUG_ON(pad > U32_MAX); v->back_pad = cpu_to_le32(pad); } - le64_add_cpu(refcount, add); + le64_add_cpu(refcount, !(flags & BTREE_TRIGGER_overwrite) ? 1 : -1); bch2_btree_iter_set_pos_to_extent_start(&iter); - ret = bch2_trans_update(trans, &iter, k, 0); + ret = bch2_trans_update(trans, &iter, new, 0); if (ret) goto err; - - *idx = k->k.p.offset; +next: + *idx = k.k->p.offset; err: +fsck_err: bch2_trans_iter_exit(trans, &iter); printbuf_exit(&buf); return ret; @@ -147,9 +360,7 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans, struct bch_fs *c = trans->c; struct reflink_gc *r; int add = !(flags & BTREE_TRIGGER_overwrite) ? 1 : -1; - u64 start = le64_to_cpu(p.v->idx); - u64 end = le64_to_cpu(p.v->idx) + p.k->size; - u64 next_idx = end + le32_to_cpu(p.v->back_pad); + u64 next_idx = REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad); s64 ret = 0; struct printbuf buf = PRINTBUF; @@ -168,36 +379,14 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans, *idx = r->offset; return 0; not_found: - BUG_ON(!(flags & BTREE_TRIGGER_check_repair)); - - if (fsck_err(trans, reflink_p_to_missing_reflink_v, - "pointer to missing indirect extent\n" - " %s\n" - " missing range %llu-%llu", - (bch2_bkey_val_to_text(&buf, c, p.s_c), buf.buf), - *idx, next_idx)) { - struct bkey_i *update = bch2_bkey_make_mut_noupdate(trans, p.s_c); - ret = PTR_ERR_OR_ZERO(update); + if (flags & BTREE_TRIGGER_check_repair) { + ret = bch2_indirect_extent_missing_error(trans, p, *idx, next_idx, false); if (ret) goto err; - - if (next_idx <= start) { - bkey_i_to_reflink_p(update)->v.front_pad = cpu_to_le32(start - next_idx); - } else if (*idx >= end) { - bkey_i_to_reflink_p(update)->v.back_pad = cpu_to_le32(*idx - end); - } else { - bkey_error_init(update); - update->k.p = p.k->p; - update->k.size = p.k->size; - set_bkey_val_u64s(&update->k, 0); - } - - ret = bch2_btree_insert_trans(trans, BTREE_ID_extents, update, BTREE_TRIGGER_norun); } *idx = next_idx; err: -fsck_err: printbuf_exit(&buf); return ret; } @@ -210,8 +399,8 @@ static int __trigger_reflink_p(struct btree_trans *trans, struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); int ret = 0; - u64 idx = le64_to_cpu(p.v->idx) - le32_to_cpu(p.v->front_pad); - u64 end = le64_to_cpu(p.v->idx) + p.k->size + le32_to_cpu(p.v->back_pad); + u64 idx = REFLINK_P_IDX(p.v) - le32_to_cpu(p.v->front_pad); + u64 end = REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad); if (flags & BTREE_TRIGGER_transactional) { while (idx < end && !ret) @@ -253,35 +442,7 @@ int bch2_trigger_reflink_p(struct btree_trans *trans, return trigger_run_overwrite_then_insert(__trigger_reflink_p, trans, btree_id, level, old, new, flags); } -/* indirect extents */ - -int bch2_reflink_v_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) -{ - return bch2_bkey_ptrs_validate(c, k, flags); -} - -void bch2_reflink_v_to_text(struct printbuf *out, struct bch_fs *c, - struct bkey_s_c k) -{ - struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(k); - - prt_printf(out, "refcount: %llu ", le64_to_cpu(r.v->refcount)); - - bch2_bkey_ptrs_to_text(out, c, k); -} - -#if 0 -Currently disabled, needs to be debugged: - -bool bch2_reflink_v_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r) -{ - struct bkey_s_reflink_v l = bkey_s_to_reflink_v(_l); - struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(_r); - - return l.v->refcount == r.v->refcount && bch2_extent_merge(c, _l, _r); -} -#endif +/* indirect extent trigger */ static inline void check_indirect_extent_deleting(struct bkey_s new, @@ -307,25 +468,6 @@ int bch2_trigger_reflink_v(struct btree_trans *trans, return bch2_trigger_extent(trans, btree_id, level, old, new, flags); } -/* indirect inline data */ - -int bch2_indirect_inline_data_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) -{ - return 0; -} - -void bch2_indirect_inline_data_to_text(struct printbuf *out, - struct bch_fs *c, struct bkey_s_c k) -{ - struct bkey_s_c_indirect_inline_data d = bkey_s_c_to_indirect_inline_data(k); - unsigned datalen = bkey_inline_data_bytes(k.k); - - prt_printf(out, "refcount %llu datalen %u: %*phN", - le64_to_cpu(d.v->refcount), datalen, - min(datalen, 32U), d.v->data); -} - int bch2_trigger_indirect_inline_data(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c old, struct bkey_s new, @@ -336,9 +478,12 @@ int bch2_trigger_indirect_inline_data(struct btree_trans *trans, return 0; } +/* create */ + static int bch2_make_extent_indirect(struct btree_trans *trans, struct btree_iter *extent_iter, - struct bkey_i *orig) + struct bkey_i *orig, + bool reflink_p_may_update_opts_field) { struct bch_fs *c = trans->c; struct btree_iter reflink_iter = { NULL }; @@ -358,6 +503,14 @@ static int bch2_make_extent_indirect(struct btree_trans *trans, if (ret) goto err; + /* + * XXX: we're assuming that 56 bits will be enough for the life of the + * filesystem: we need to implement wraparound, with a cursor in the + * logged ops btree: + */ + if (bkey_ge(reflink_iter.pos, POS(0, REFLINK_P_IDX_MAX - orig->k.size))) + return -ENOSPC; + r_v = bch2_trans_kmalloc(trans, sizeof(__le64) + bkey_bytes(&orig->k)); ret = PTR_ERR_OR_ZERO(r_v); if (ret) @@ -394,7 +547,10 @@ static int bch2_make_extent_indirect(struct btree_trans *trans, memset(&r_p->v, 0, sizeof(r_p->v)); #endif - r_p->v.idx = cpu_to_le64(bkey_start_offset(&r_v->k)); + SET_REFLINK_P_IDX(&r_p->v, bkey_start_offset(&r_v->k)); + + if (reflink_p_may_update_opts_field) + SET_REFLINK_P_MAY_UPDATE_OPTIONS(&r_p->v, true); ret = bch2_trans_update(trans, extent_iter, &r_p->k_i, BTREE_UPDATE_internal_snapshot_node); @@ -409,7 +565,7 @@ static struct bkey_s_c get_next_src(struct btree_iter *iter, struct bpos end) struct bkey_s_c k; int ret; - for_each_btree_key_upto_continue_norestart(*iter, end, 0, k, ret) { + for_each_btree_key_max_continue_norestart(*iter, end, 0, k, ret) { if (bkey_extent_is_unwritten(k)) continue; @@ -426,7 +582,8 @@ s64 bch2_remap_range(struct bch_fs *c, subvol_inum dst_inum, u64 dst_offset, subvol_inum src_inum, u64 src_offset, u64 remap_sectors, - u64 new_i_size, s64 *i_sectors_delta) + u64 new_i_size, s64 *i_sectors_delta, + bool may_change_src_io_path_opts) { struct btree_trans *trans; struct btree_iter dst_iter, src_iter; @@ -439,6 +596,8 @@ s64 bch2_remap_range(struct bch_fs *c, struct bpos src_want; u64 dst_done = 0; u32 dst_snapshot, src_snapshot; + bool reflink_p_may_update_opts_field = + bch2_request_incompat_feature(c, bcachefs_metadata_version_reflink_p_may_update_opts); int ret = 0, ret2 = 0; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_reflink)) @@ -520,7 +679,8 @@ s64 bch2_remap_range(struct bch_fs *c, src_k = bkey_i_to_s_c(new_src.k); ret = bch2_make_extent_indirect(trans, &src_iter, - new_src.k); + new_src.k, + reflink_p_may_update_opts_field); if (ret) continue; @@ -533,11 +693,15 @@ s64 bch2_remap_range(struct bch_fs *c, struct bkey_i_reflink_p *dst_p = bkey_reflink_p_init(new_dst.k); - u64 offset = le64_to_cpu(src_p.v->idx) + + u64 offset = REFLINK_P_IDX(src_p.v) + (src_want.offset - bkey_start_offset(src_k.k)); - dst_p->v.idx = cpu_to_le64(offset); + SET_REFLINK_P_IDX(&dst_p->v, offset); + + if (reflink_p_may_update_opts_field && + may_change_src_io_path_opts) + SET_REFLINK_P_MAY_UPDATE_OPTIONS(&dst_p->v, true); } else { BUG(); } @@ -547,7 +711,7 @@ s64 bch2_remap_range(struct bch_fs *c, min(src_k.k->p.offset - src_want.offset, dst_end.offset - dst_iter.pos.offset)); - ret = bch2_bkey_set_needs_rebalance(c, new_dst.k, &opts) ?: + ret = bch2_bkey_set_needs_rebalance(c, &opts, new_dst.k) ?: bch2_extent_update(trans, dst_inum, &dst_iter, new_dst.k, &disk_res, new_i_size, i_sectors_delta, @@ -591,3 +755,97 @@ err: return dst_done ?: ret ?: ret2; } + +/* fsck */ + +static int bch2_gc_write_reflink_key(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c k, + size_t *idx) +{ + struct bch_fs *c = trans->c; + const __le64 *refcount = bkey_refcount_c(k); + struct printbuf buf = PRINTBUF; + struct reflink_gc *r; + int ret = 0; + + if (!refcount) + return 0; + + while ((r = genradix_ptr(&c->reflink_gc_table, *idx)) && + r->offset < k.k->p.offset) + ++*idx; + + if (!r || + r->offset != k.k->p.offset || + r->size != k.k->size) { + bch_err(c, "unexpected inconsistency walking reflink table at gc finish"); + return -EINVAL; + } + + if (fsck_err_on(r->refcount != le64_to_cpu(*refcount), + trans, reflink_v_refcount_wrong, + "reflink key has wrong refcount:\n" + " %s\n" + " should be %u", + (bch2_bkey_val_to_text(&buf, c, k), buf.buf), + r->refcount)) { + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); + ret = PTR_ERR_OR_ZERO(new); + if (ret) + goto out; + + if (!r->refcount) + new->k.type = KEY_TYPE_deleted; + else + *bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount); + ret = bch2_trans_update(trans, iter, new, 0); + } +out: +fsck_err: + printbuf_exit(&buf); + return ret; +} + +int bch2_gc_reflink_done(struct bch_fs *c) +{ + size_t idx = 0; + + int ret = bch2_trans_run(c, + for_each_btree_key_commit(trans, iter, + BTREE_ID_reflink, POS_MIN, + BTREE_ITER_prefetch, k, + NULL, NULL, BCH_TRANS_COMMIT_no_enospc, + bch2_gc_write_reflink_key(trans, &iter, k, &idx))); + c->reflink_gc_nr = 0; + return ret; +} + +int bch2_gc_reflink_start(struct bch_fs *c) +{ + c->reflink_gc_nr = 0; + + int ret = bch2_trans_run(c, + for_each_btree_key(trans, iter, BTREE_ID_reflink, POS_MIN, + BTREE_ITER_prefetch, k, ({ + const __le64 *refcount = bkey_refcount_c(k); + + if (!refcount) + continue; + + struct reflink_gc *r = genradix_ptr_alloc(&c->reflink_gc_table, + c->reflink_gc_nr++, GFP_KERNEL); + if (!r) { + ret = -BCH_ERR_ENOMEM_gc_reflink_start; + break; + } + + r->offset = k.k->p.offset; + r->size = k.k->size; + r->refcount = 0; + 0; + }))); + + bch_err_fn(c, ret); + return ret; +} diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h index 51afe11d8ed6..1632780bdf18 100644 --- a/fs/bcachefs/reflink.h +++ b/fs/bcachefs/reflink.h @@ -2,9 +2,8 @@ #ifndef _BCACHEFS_REFLINK_H #define _BCACHEFS_REFLINK_H -enum bch_validate_flags; - -int bch2_reflink_p_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_reflink_p_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reflink_p_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned, @@ -19,7 +18,8 @@ int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned, .min_val_size = 16, \ }) -int bch2_reflink_v_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_reflink_v_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, @@ -34,7 +34,7 @@ int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned, }) int bch2_indirect_inline_data_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); void bch2_indirect_inline_data_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_trigger_indirect_inline_data(struct btree_trans *, @@ -73,7 +73,15 @@ static inline __le64 *bkey_refcount(struct bkey_s k) } } +struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *, struct btree_iter *, + s64 *, struct bkey_s_c_reflink_p, + bool, unsigned); + s64 bch2_remap_range(struct bch_fs *, subvol_inum, u64, - subvol_inum, u64, u64, u64, s64 *); + subvol_inum, u64, u64, u64, s64 *, + bool); + +int bch2_gc_reflink_done(struct bch_fs *); +int bch2_gc_reflink_start(struct bch_fs *); #endif /* _BCACHEFS_REFLINK_H */ diff --git a/fs/bcachefs/reflink_format.h b/fs/bcachefs/reflink_format.h index 6772eebb1fc6..92995e4f898e 100644 --- a/fs/bcachefs/reflink_format.h +++ b/fs/bcachefs/reflink_format.h @@ -4,7 +4,7 @@ struct bch_reflink_p { struct bch_val v; - __le64 idx; + __le64 idx_flags; /* * A reflink pointer might point to an indirect extent which is then * later split (by copygc or rebalance). If we only pointed to part of @@ -17,6 +17,11 @@ struct bch_reflink_p { __le32 back_pad; } __packed __aligned(8); +LE64_BITMASK(REFLINK_P_IDX, struct bch_reflink_p, idx_flags, 0, 56); +LE64_BITMASK(REFLINK_P_ERROR, struct bch_reflink_p, idx_flags, 56, 57); +LE64_BITMASK(REFLINK_P_MAY_UPDATE_OPTIONS, + struct bch_reflink_p, idx_flags, 57, 58); + struct bch_reflink_v { struct bch_val v; __le64 refcount; diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index 005275281804..59c8770e4a0e 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -23,6 +23,10 @@ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *clean, int write) { + struct bkey_validate_context from = { + .flags = write, + .from = BKEY_VALIDATE_superblock, + }; struct jset_entry *entry; int ret; @@ -40,7 +44,7 @@ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *cle ret = bch2_journal_entry_validate(c, NULL, entry, le16_to_cpu(c->disk_sb.sb->version), BCH_SB_BIG_ENDIAN(c->disk_sb.sb), - write); + from); if (ret) return ret; } diff --git a/fs/bcachefs/sb-counters_format.h b/fs/bcachefs/sb-counters_format.h index 62ea478215d0..fdcf598f08b1 100644 --- a/fs/bcachefs/sb-counters_format.h +++ b/fs/bcachefs/sb-counters_format.h @@ -2,86 +2,91 @@ #ifndef _BCACHEFS_SB_COUNTERS_FORMAT_H #define _BCACHEFS_SB_COUNTERS_FORMAT_H -#define BCH_PERSISTENT_COUNTERS() \ - x(io_read, 0) \ - x(io_write, 1) \ - x(io_move, 2) \ - x(bucket_invalidate, 3) \ - x(bucket_discard, 4) \ - x(bucket_alloc, 5) \ - x(bucket_alloc_fail, 6) \ - x(btree_cache_scan, 7) \ - x(btree_cache_reap, 8) \ - x(btree_cache_cannibalize, 9) \ - x(btree_cache_cannibalize_lock, 10) \ - x(btree_cache_cannibalize_lock_fail, 11) \ - x(btree_cache_cannibalize_unlock, 12) \ - x(btree_node_write, 13) \ - x(btree_node_read, 14) \ - x(btree_node_compact, 15) \ - x(btree_node_merge, 16) \ - x(btree_node_split, 17) \ - x(btree_node_rewrite, 18) \ - x(btree_node_alloc, 19) \ - x(btree_node_free, 20) \ - x(btree_node_set_root, 21) \ - x(btree_path_relock_fail, 22) \ - x(btree_path_upgrade_fail, 23) \ - x(btree_reserve_get_fail, 24) \ - x(journal_entry_full, 25) \ - x(journal_full, 26) \ - x(journal_reclaim_finish, 27) \ - x(journal_reclaim_start, 28) \ - x(journal_write, 29) \ - x(read_promote, 30) \ - x(read_bounce, 31) \ - x(read_split, 33) \ - x(read_retry, 32) \ - x(read_reuse_race, 34) \ - x(move_extent_read, 35) \ - x(move_extent_write, 36) \ - x(move_extent_finish, 37) \ - x(move_extent_fail, 38) \ - x(move_extent_start_fail, 39) \ - x(copygc, 40) \ - x(copygc_wait, 41) \ - x(gc_gens_end, 42) \ - x(gc_gens_start, 43) \ - x(trans_blocked_journal_reclaim, 44) \ - x(trans_restart_btree_node_reused, 45) \ - x(trans_restart_btree_node_split, 46) \ - x(trans_restart_fault_inject, 47) \ - x(trans_restart_iter_upgrade, 48) \ - x(trans_restart_journal_preres_get, 49) \ - x(trans_restart_journal_reclaim, 50) \ - x(trans_restart_journal_res_get, 51) \ - x(trans_restart_key_cache_key_realloced, 52) \ - x(trans_restart_key_cache_raced, 53) \ - x(trans_restart_mark_replicas, 54) \ - x(trans_restart_mem_realloced, 55) \ - x(trans_restart_memory_allocation_failure, 56) \ - x(trans_restart_relock, 57) \ - x(trans_restart_relock_after_fill, 58) \ - x(trans_restart_relock_key_cache_fill, 59) \ - x(trans_restart_relock_next_node, 60) \ - x(trans_restart_relock_parent_for_fill, 61) \ - x(trans_restart_relock_path, 62) \ - x(trans_restart_relock_path_intent, 63) \ - x(trans_restart_too_many_iters, 64) \ - x(trans_restart_traverse, 65) \ - x(trans_restart_upgrade, 66) \ - x(trans_restart_would_deadlock, 67) \ - x(trans_restart_would_deadlock_write, 68) \ - x(trans_restart_injected, 69) \ - x(trans_restart_key_cache_upgrade, 70) \ - x(trans_traverse_all, 71) \ - x(transaction_commit, 72) \ - x(write_super, 73) \ - x(trans_restart_would_deadlock_recursion_limit, 74) \ - x(trans_restart_write_buffer_flush, 75) \ - x(trans_restart_split_race, 76) \ - x(write_buffer_flush_slowpath, 77) \ - x(write_buffer_flush_sync, 78) +enum counters_flags { + TYPE_COUNTER = BIT(0), /* event counters */ + TYPE_SECTORS = BIT(1), /* amount counters, the unit is sectors */ +}; + +#define BCH_PERSISTENT_COUNTERS() \ + x(io_read, 0, TYPE_SECTORS) \ + x(io_write, 1, TYPE_SECTORS) \ + x(io_move, 2, TYPE_SECTORS) \ + x(bucket_invalidate, 3, TYPE_COUNTER) \ + x(bucket_discard, 4, TYPE_COUNTER) \ + x(bucket_alloc, 5, TYPE_COUNTER) \ + x(bucket_alloc_fail, 6, TYPE_COUNTER) \ + x(btree_cache_scan, 7, TYPE_COUNTER) \ + x(btree_cache_reap, 8, TYPE_COUNTER) \ + x(btree_cache_cannibalize, 9, TYPE_COUNTER) \ + x(btree_cache_cannibalize_lock, 10, TYPE_COUNTER) \ + x(btree_cache_cannibalize_lock_fail, 11, TYPE_COUNTER) \ + x(btree_cache_cannibalize_unlock, 12, TYPE_COUNTER) \ + x(btree_node_write, 13, TYPE_COUNTER) \ + x(btree_node_read, 14, TYPE_COUNTER) \ + x(btree_node_compact, 15, TYPE_COUNTER) \ + x(btree_node_merge, 16, TYPE_COUNTER) \ + x(btree_node_split, 17, TYPE_COUNTER) \ + x(btree_node_rewrite, 18, TYPE_COUNTER) \ + x(btree_node_alloc, 19, TYPE_COUNTER) \ + x(btree_node_free, 20, TYPE_COUNTER) \ + x(btree_node_set_root, 21, TYPE_COUNTER) \ + x(btree_path_relock_fail, 22, TYPE_COUNTER) \ + x(btree_path_upgrade_fail, 23, TYPE_COUNTER) \ + x(btree_reserve_get_fail, 24, TYPE_COUNTER) \ + x(journal_entry_full, 25, TYPE_COUNTER) \ + x(journal_full, 26, TYPE_COUNTER) \ + x(journal_reclaim_finish, 27, TYPE_COUNTER) \ + x(journal_reclaim_start, 28, TYPE_COUNTER) \ + x(journal_write, 29, TYPE_COUNTER) \ + x(read_promote, 30, TYPE_COUNTER) \ + x(read_bounce, 31, TYPE_COUNTER) \ + x(read_split, 33, TYPE_COUNTER) \ + x(read_retry, 32, TYPE_COUNTER) \ + x(read_reuse_race, 34, TYPE_COUNTER) \ + x(move_extent_read, 35, TYPE_SECTORS) \ + x(move_extent_write, 36, TYPE_SECTORS) \ + x(move_extent_finish, 37, TYPE_SECTORS) \ + x(move_extent_fail, 38, TYPE_COUNTER) \ + x(move_extent_start_fail, 39, TYPE_COUNTER) \ + x(copygc, 40, TYPE_COUNTER) \ + x(copygc_wait, 41, TYPE_COUNTER) \ + x(gc_gens_end, 42, TYPE_COUNTER) \ + x(gc_gens_start, 43, TYPE_COUNTER) \ + x(trans_blocked_journal_reclaim, 44, TYPE_COUNTER) \ + x(trans_restart_btree_node_reused, 45, TYPE_COUNTER) \ + x(trans_restart_btree_node_split, 46, TYPE_COUNTER) \ + x(trans_restart_fault_inject, 47, TYPE_COUNTER) \ + x(trans_restart_iter_upgrade, 48, TYPE_COUNTER) \ + x(trans_restart_journal_preres_get, 49, TYPE_COUNTER) \ + x(trans_restart_journal_reclaim, 50, TYPE_COUNTER) \ + x(trans_restart_journal_res_get, 51, TYPE_COUNTER) \ + x(trans_restart_key_cache_key_realloced, 52, TYPE_COUNTER) \ + x(trans_restart_key_cache_raced, 53, TYPE_COUNTER) \ + x(trans_restart_mark_replicas, 54, TYPE_COUNTER) \ + x(trans_restart_mem_realloced, 55, TYPE_COUNTER) \ + x(trans_restart_memory_allocation_failure, 56, TYPE_COUNTER) \ + x(trans_restart_relock, 57, TYPE_COUNTER) \ + x(trans_restart_relock_after_fill, 58, TYPE_COUNTER) \ + x(trans_restart_relock_key_cache_fill, 59, TYPE_COUNTER) \ + x(trans_restart_relock_next_node, 60, TYPE_COUNTER) \ + x(trans_restart_relock_parent_for_fill, 61, TYPE_COUNTER) \ + x(trans_restart_relock_path, 62, TYPE_COUNTER) \ + x(trans_restart_relock_path_intent, 63, TYPE_COUNTER) \ + x(trans_restart_too_many_iters, 64, TYPE_COUNTER) \ + x(trans_restart_traverse, 65, TYPE_COUNTER) \ + x(trans_restart_upgrade, 66, TYPE_COUNTER) \ + x(trans_restart_would_deadlock, 67, TYPE_COUNTER) \ + x(trans_restart_would_deadlock_write, 68, TYPE_COUNTER) \ + x(trans_restart_injected, 69, TYPE_COUNTER) \ + x(trans_restart_key_cache_upgrade, 70, TYPE_COUNTER) \ + x(trans_traverse_all, 71, TYPE_COUNTER) \ + x(transaction_commit, 72, TYPE_COUNTER) \ + x(write_super, 73, TYPE_COUNTER) \ + x(trans_restart_would_deadlock_recursion_limit, 74, TYPE_COUNTER) \ + x(trans_restart_write_buffer_flush, 75, TYPE_COUNTER) \ + x(trans_restart_split_race, 76, TYPE_COUNTER) \ + x(write_buffer_flush_slowpath, 77, TYPE_COUNTER) \ + x(write_buffer_flush_sync, 78, TYPE_COUNTER) enum bch_persistent_counters { #define x(t, n, ...) BCH_COUNTER_##t, diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 8767c33c2b51..14f6b6a5fb38 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -81,7 +81,19 @@ BCH_FSCK_ERR_accounting_mismatch) \ x(inode_has_child_snapshots, \ BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ - BCH_FSCK_ERR_inode_has_child_snapshots_wrong) + BCH_FSCK_ERR_inode_has_child_snapshots_wrong) \ + x(backpointer_bucket_gen, \ + BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ + BCH_FSCK_ERR_backpointer_to_missing_ptr, \ + BCH_FSCK_ERR_ptr_to_missing_backpointer) \ + x(disk_accounting_big_endian, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch, \ + BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ + BCH_FSCK_ERR_accounting_key_junk_at_end) \ + x(directory_size, \ + BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ + BCH_FSCK_ERR_directory_size_mismatch) \ #define DOWNGRADE_TABLE() \ x(bucket_stripe_sectors, \ @@ -117,7 +129,19 @@ BCH_FSCK_ERR_bkey_version_in_future) \ x(rebalance_work_acct_fix, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ - BCH_FSCK_ERR_accounting_mismatch) + BCH_FSCK_ERR_accounting_mismatch, \ + BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ + BCH_FSCK_ERR_accounting_key_junk_at_end) \ + x(backpointer_bucket_gen, \ + BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ + BCH_FSCK_ERR_backpointer_bucket_offset_wrong, \ + BCH_FSCK_ERR_backpointer_to_missing_ptr, \ + BCH_FSCK_ERR_ptr_to_missing_backpointer) \ + x(disk_accounting_big_endian, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_accounting_mismatch, \ + BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ + BCH_FSCK_ERR_accounting_key_junk_at_end) struct upgrade_downgrade_entry { u64 recovery_passes; diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index 9feb6739f77a..0b4fe899209b 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -5,9 +5,8 @@ enum bch_fsck_flags { FSCK_CAN_FIX = 1 << 0, FSCK_CAN_IGNORE = 1 << 1, - FSCK_NEED_FSCK = 1 << 2, - FSCK_NO_RATELIMIT = 1 << 3, - FSCK_AUTOFIX = 1 << 4, + FSCK_NO_RATELIMIT = 1 << 2, + FSCK_AUTOFIX = 1 << 3, }; #define BCH_SB_ERRS() \ @@ -59,7 +58,7 @@ enum bch_fsck_flags { x(bset_empty, 45, 0) \ x(bset_bad_seq, 46, 0) \ x(bset_blacklisted_journal_seq, 47, 0) \ - x(first_bset_blacklisted_journal_seq, 48, 0) \ + x(first_bset_blacklisted_journal_seq, 48, FSCK_AUTOFIX) \ x(btree_node_bad_btree, 49, 0) \ x(btree_node_bad_level, 50, 0) \ x(btree_node_bad_min_key, 51, 0) \ @@ -68,17 +67,17 @@ enum bch_fsck_flags { x(btree_node_bkey_past_bset_end, 54, 0) \ x(btree_node_bkey_bad_format, 55, 0) \ x(btree_node_bad_bkey, 56, 0) \ - x(btree_node_bkey_out_of_order, 57, 0) \ - x(btree_root_bkey_invalid, 58, 0) \ - x(btree_root_read_error, 59, 0) \ + x(btree_node_bkey_out_of_order, 57, FSCK_AUTOFIX) \ + x(btree_root_bkey_invalid, 58, FSCK_AUTOFIX) \ + x(btree_root_read_error, 59, FSCK_AUTOFIX) \ x(btree_root_bad_min_key, 60, 0) \ x(btree_root_bad_max_key, 61, 0) \ - x(btree_node_read_error, 62, 0) \ - x(btree_node_topology_bad_min_key, 63, 0) \ - x(btree_node_topology_bad_max_key, 64, 0) \ - x(btree_node_topology_overwritten_by_prev_node, 65, 0) \ - x(btree_node_topology_overwritten_by_next_node, 66, 0) \ - x(btree_node_topology_interior_node_empty, 67, 0) \ + x(btree_node_read_error, 62, FSCK_AUTOFIX) \ + x(btree_node_topology_bad_min_key, 63, FSCK_AUTOFIX) \ + x(btree_node_topology_bad_max_key, 64, FSCK_AUTOFIX) \ + x(btree_node_topology_overwritten_by_prev_node, 65, FSCK_AUTOFIX) \ + x(btree_node_topology_overwritten_by_next_node, 66, FSCK_AUTOFIX) \ + x(btree_node_topology_interior_node_empty, 67, FSCK_AUTOFIX) \ x(fs_usage_hidden_wrong, 68, FSCK_AUTOFIX) \ x(fs_usage_btree_wrong, 69, FSCK_AUTOFIX) \ x(fs_usage_data_wrong, 70, FSCK_AUTOFIX) \ @@ -123,11 +122,12 @@ enum bch_fsck_flags { x(alloc_key_cached_sectors_wrong, 109, FSCK_AUTOFIX) \ x(alloc_key_stripe_wrong, 110, FSCK_AUTOFIX) \ x(alloc_key_stripe_redundancy_wrong, 111, FSCK_AUTOFIX) \ + x(alloc_key_journal_seq_in_future, 298, FSCK_AUTOFIX) \ x(bucket_sector_count_overflow, 112, 0) \ x(bucket_metadata_type_mismatch, 113, 0) \ - x(need_discard_key_wrong, 114, 0) \ - x(freespace_key_wrong, 115, 0) \ - x(freespace_hole_missing, 116, 0) \ + x(need_discard_key_wrong, 114, FSCK_AUTOFIX) \ + x(freespace_key_wrong, 115, FSCK_AUTOFIX) \ + x(freespace_hole_missing, 116, FSCK_AUTOFIX) \ x(bucket_gens_val_size_bad, 117, 0) \ x(bucket_gens_key_wrong, 118, FSCK_AUTOFIX) \ x(bucket_gens_hole_wrong, 119, FSCK_AUTOFIX) \ @@ -139,9 +139,10 @@ enum bch_fsck_flags { x(discarding_bucket_not_in_need_discard_btree, 291, 0) \ x(backpointer_bucket_offset_wrong, 125, 0) \ x(backpointer_level_bad, 294, 0) \ - x(backpointer_to_missing_device, 126, 0) \ - x(backpointer_to_missing_alloc, 127, 0) \ - x(backpointer_to_missing_ptr, 128, 0) \ + x(backpointer_dev_bad, 297, 0) \ + x(backpointer_to_missing_device, 126, FSCK_AUTOFIX) \ + x(backpointer_to_missing_alloc, 127, FSCK_AUTOFIX) \ + x(backpointer_to_missing_ptr, 128, FSCK_AUTOFIX) \ x(lru_entry_at_time_0, 129, FSCK_AUTOFIX) \ x(lru_entry_to_invalid_bucket, 130, FSCK_AUTOFIX) \ x(lru_entry_bad, 131, FSCK_AUTOFIX) \ @@ -167,14 +168,15 @@ enum bch_fsck_flags { x(ptr_to_incorrect_stripe, 151, 0) \ x(ptr_gen_newer_than_bucket_gen, 152, 0) \ x(ptr_too_stale, 153, 0) \ - x(stale_dirty_ptr, 154, 0) \ + x(stale_dirty_ptr, 154, FSCK_AUTOFIX) \ x(ptr_bucket_data_type_mismatch, 155, 0) \ x(ptr_cached_and_erasure_coded, 156, 0) \ x(ptr_crc_uncompressed_size_too_small, 157, 0) \ + x(ptr_crc_uncompressed_size_too_big, 161, 0) \ + x(ptr_crc_uncompressed_size_mismatch, 300, 0) \ x(ptr_crc_csum_type_unknown, 158, 0) \ x(ptr_crc_compression_type_unknown, 159, 0) \ x(ptr_crc_redundant, 160, 0) \ - x(ptr_crc_uncompressed_size_too_big, 161, 0) \ x(ptr_crc_nonce_mismatch, 162, 0) \ x(ptr_stripe_redundant, 163, 0) \ x(reservation_key_nr_replicas_invalid, 164, 0) \ @@ -209,6 +211,7 @@ enum bch_fsck_flags { x(bkey_in_missing_snapshot, 190, 0) \ x(inode_pos_inode_nonzero, 191, 0) \ x(inode_pos_blockdev_range, 192, 0) \ + x(inode_alloc_cursor_inode_bad, 301, 0) \ x(inode_unpack_error, 193, 0) \ x(inode_str_hash_invalid, 194, 0) \ x(inode_v3_fields_start_bad, 195, 0) \ @@ -232,6 +235,7 @@ enum bch_fsck_flags { x(inode_wrong_nlink, 209, FSCK_AUTOFIX) \ x(inode_has_child_snapshots_wrong, 287, 0) \ x(inode_unreachable, 210, FSCK_AUTOFIX) \ + x(inode_journal_seq_in_future, 299, FSCK_AUTOFIX) \ x(deleted_inode_but_clean, 211, FSCK_AUTOFIX) \ x(deleted_inode_missing, 212, FSCK_AUTOFIX) \ x(deleted_inode_is_dir, 213, FSCK_AUTOFIX) \ @@ -252,6 +256,7 @@ enum bch_fsck_flags { x(dirent_in_missing_dir_inode, 227, 0) \ x(dirent_in_non_dir_inode, 228, 0) \ x(dirent_to_missing_inode, 229, 0) \ + x(dirent_to_overwritten_inode, 302, 0) \ x(dirent_to_missing_subvol, 230, 0) \ x(dirent_to_itself, 231, 0) \ x(quota_type_invalid, 232, 0) \ @@ -288,7 +293,7 @@ enum bch_fsck_flags { x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \ x(snapshot_node_missing, 264, 0) \ x(dup_backpointer_to_bad_csum_extent, 265, 0) \ - x(btree_bitmap_not_marked, 266, 0) \ + x(btree_bitmap_not_marked, 266, FSCK_AUTOFIX) \ x(sb_clean_entry_overrun, 267, 0) \ x(btree_ptr_v2_written_0, 268, 0) \ x(subvol_snapshot_bad, 269, 0) \ @@ -306,7 +311,10 @@ enum bch_fsck_flags { x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \ x(accounting_key_version_0, 282, FSCK_AUTOFIX) \ x(logged_op_but_clean, 283, FSCK_AUTOFIX) \ - x(MAX, 295, 0) + x(compression_opt_not_marked_in_sb, 295, FSCK_AUTOFIX) \ + x(compression_type_not_marked_in_sb, 296, FSCK_AUTOFIX) \ + x(directory_size_mismatch, 303, FSCK_AUTOFIX) \ + x(MAX, 304, 0) enum bch_sb_error_id { #define x(t, n, ...) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index 617d07e53b20..7e7c66a1e1a6 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -491,8 +491,12 @@ static int six_lock_slowpath(struct six_lock *lock, enum six_lock_type type, list_del(&wait->list); raw_spin_unlock(&lock->wait_lock); - if (unlikely(acquired)) + if (unlikely(acquired)) { do_six_unlock_type(lock, type); + } else if (type == SIX_LOCK_write) { + six_clear_bitmask(lock, SIX_LOCK_HELD_write); + six_lock_wakeup(lock, atomic_read(&lock->state), SIX_LOCK_read); + } break; } @@ -501,10 +505,6 @@ static int six_lock_slowpath(struct six_lock *lock, enum six_lock_type type, __set_current_state(TASK_RUNNING); out: - if (ret && type == SIX_LOCK_write) { - six_clear_bitmask(lock, SIX_LOCK_HELD_write); - six_lock_wakeup(lock, atomic_read(&lock->state), SIX_LOCK_read); - } trace_contention_end(lock, 0); return ret; @@ -616,8 +616,6 @@ void six_unlock_ip(struct six_lock *lock, enum six_lock_type type, unsigned long if (type != SIX_LOCK_write) six_release(&lock->dep_map, ip); - else - lock->seq++; if (type == SIX_LOCK_intent && lock->intent_lock_recurse) { @@ -625,6 +623,15 @@ void six_unlock_ip(struct six_lock *lock, enum six_lock_type type, unsigned long return; } + if (type == SIX_LOCK_write && + lock->write_lock_recurse) { + --lock->write_lock_recurse; + return; + } + + if (type == SIX_LOCK_write) + lock->seq++; + do_six_unlock_type(lock, type); } EXPORT_SYMBOL_GPL(six_unlock_ip); @@ -735,13 +742,13 @@ void six_lock_increment(struct six_lock *lock, enum six_lock_type type) atomic_add(l[type].lock_val, &lock->state); } break; + case SIX_LOCK_write: + lock->write_lock_recurse++; + fallthrough; case SIX_LOCK_intent: EBUG_ON(!(atomic_read(&lock->state) & SIX_LOCK_HELD_intent)); lock->intent_lock_recurse++; break; - case SIX_LOCK_write: - BUG(); - break; } } EXPORT_SYMBOL_GPL(six_lock_increment); diff --git a/fs/bcachefs/six.h b/fs/bcachefs/six.h index 68d46fd7f391..c142e06b7a3a 100644 --- a/fs/bcachefs/six.h +++ b/fs/bcachefs/six.h @@ -137,6 +137,7 @@ struct six_lock { atomic_t state; u32 seq; unsigned intent_lock_recurse; + unsigned write_lock_recurse; struct task_struct *owner; unsigned __percpu *readers; raw_spinlock_t wait_lock; diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index ae57638506c3..c54091a28909 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -2,6 +2,7 @@ #include "bcachefs.h" #include "bkey_buf.h" +#include "btree_cache.h" #include "btree_key_cache.h" #include "btree_update.h" #include "buckets.h" @@ -32,7 +33,7 @@ void bch2_snapshot_tree_to_text(struct printbuf *out, struct bch_fs *c, } int bch2_snapshot_tree_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { int ret = 0; @@ -225,7 +226,7 @@ void bch2_snapshot_to_text(struct printbuf *out, struct bch_fs *c, } int bch2_snapshot_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_snapshot s; u32 i, id; @@ -279,23 +280,6 @@ fsck_err: return ret; } -static void __set_is_ancestor_bitmap(struct bch_fs *c, u32 id) -{ - struct snapshot_t *t = snapshot_t_mut(c, id); - u32 parent = id; - - while ((parent = bch2_snapshot_parent_early(c, parent)) && - parent - id - 1 < IS_ANCESTOR_BITMAP) - __set_bit(parent - id - 1, t->is_ancestor); -} - -static void set_is_ancestor_bitmap(struct bch_fs *c, u32 id) -{ - mutex_lock(&c->snapshot_table_lock); - __set_is_ancestor_bitmap(c, id); - mutex_unlock(&c->snapshot_table_lock); -} - static int __bch2_mark_snapshot(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_s_c old, struct bkey_s_c new, @@ -317,6 +301,7 @@ static int __bch2_mark_snapshot(struct btree_trans *trans, if (new.k->type == KEY_TYPE_snapshot) { struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(new); + t->live = true; t->parent = le32_to_cpu(s.v->parent); t->children[0] = le32_to_cpu(s.v->children[0]); t->children[1] = le32_to_cpu(s.v->children[1]); @@ -335,7 +320,11 @@ static int __bch2_mark_snapshot(struct btree_trans *trans, t->skip[2] = 0; } - __set_is_ancestor_bitmap(c, id); + u32 parent = id; + + while ((parent = bch2_snapshot_parent_early(c, parent)) && + parent - id - 1 < IS_ANCESTOR_BITMAP) + __set_bit(parent - id - 1, t->is_ancestor); if (BCH_SNAPSHOT_DELETED(s.v)) { set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags); @@ -365,70 +354,6 @@ int bch2_snapshot_lookup(struct btree_trans *trans, u32 id, BTREE_ITER_with_updates, snapshot, s); } -static int bch2_snapshot_live(struct btree_trans *trans, u32 id) -{ - struct bch_snapshot v; - int ret; - - if (!id) - return 0; - - ret = bch2_snapshot_lookup(trans, id, &v); - if (bch2_err_matches(ret, ENOENT)) - bch_err(trans->c, "snapshot node %u not found", id); - if (ret) - return ret; - - return !BCH_SNAPSHOT_DELETED(&v); -} - -/* - * If @k is a snapshot with just one live child, it's part of a linear chain, - * which we consider to be an equivalence class: and then after snapshot - * deletion cleanup, there should only be a single key at a given position in - * this equivalence class. - * - * This sets the equivalence class of @k to be the child's equivalence class, if - * it's part of such a linear chain: this correctly sets equivalence classes on - * startup if we run leaf to root (i.e. in natural key order). - */ -static int bch2_snapshot_set_equiv(struct btree_trans *trans, struct bkey_s_c k) -{ - struct bch_fs *c = trans->c; - unsigned i, nr_live = 0, live_idx = 0; - struct bkey_s_c_snapshot snap; - u32 id = k.k->p.offset, child[2]; - - if (k.k->type != KEY_TYPE_snapshot) - return 0; - - snap = bkey_s_c_to_snapshot(k); - - child[0] = le32_to_cpu(snap.v->children[0]); - child[1] = le32_to_cpu(snap.v->children[1]); - - for (i = 0; i < 2; i++) { - int ret = bch2_snapshot_live(trans, child[i]); - - if (ret < 0) - return ret; - - if (ret) - live_idx = i; - nr_live += ret; - } - - mutex_lock(&c->snapshot_table_lock); - - snapshot_t_mut(c, id)->equiv = nr_live == 1 - ? snapshot_t_mut(c, child[live_idx])->equiv - : id; - - mutex_unlock(&c->snapshot_table_lock); - - return 0; -} - /* fsck: */ static u32 bch2_snapshot_child(struct bch_fs *c, u32 id, unsigned child) @@ -506,7 +431,6 @@ static int bch2_snapshot_tree_master_subvol(struct btree_trans *trans, break; } } - bch2_trans_iter_exit(trans, &iter); if (!ret && !found) { @@ -536,6 +460,7 @@ static int check_snapshot_tree(struct btree_trans *trans, struct bch_snapshot s; struct bch_subvolume subvol; struct printbuf buf = PRINTBUF; + struct btree_iter snapshot_iter = {}; u32 root_id; int ret; @@ -545,22 +470,35 @@ static int check_snapshot_tree(struct btree_trans *trans, st = bkey_s_c_to_snapshot_tree(k); root_id = le32_to_cpu(st.v->root_snapshot); - ret = bch2_snapshot_lookup(trans, root_id, &s); + struct bkey_s_c_snapshot snapshot_k = + bch2_bkey_get_iter_typed(trans, &snapshot_iter, BTREE_ID_snapshots, + POS(0, root_id), 0, snapshot); + ret = bkey_err(snapshot_k); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; + if (!ret) + bkey_val_copy(&s, snapshot_k); + if (fsck_err_on(ret || root_id != bch2_snapshot_root(c, root_id) || st.k->p.offset != le32_to_cpu(s.tree), trans, snapshot_tree_to_missing_snapshot, "snapshot tree points to missing/incorrect snapshot:\n %s", - (bch2_bkey_val_to_text(&buf, c, st.s_c), buf.buf))) { + (bch2_bkey_val_to_text(&buf, c, st.s_c), + prt_newline(&buf), + ret + ? prt_printf(&buf, "(%s)", bch2_err_str(ret)) + : bch2_bkey_val_to_text(&buf, c, snapshot_k.s_c), + buf.buf))) { ret = bch2_btree_delete_at(trans, iter, 0); goto err; } - ret = bch2_subvolume_get(trans, le32_to_cpu(st.v->master_subvol), - false, 0, &subvol); + if (!st.v->master_subvol) + goto out; + + ret = bch2_subvolume_get(trans, le32_to_cpu(st.v->master_subvol), false, &subvol); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; @@ -603,8 +541,10 @@ static int check_snapshot_tree(struct btree_trans *trans, u->v.master_subvol = cpu_to_le32(subvol_id); st = snapshot_tree_i_to_s_c(u); } +out: err: fsck_err: + bch2_trans_iter_exit(trans, &snapshot_iter); printbuf_exit(&buf); return ret; } @@ -799,7 +739,7 @@ static int check_snapshot(struct btree_trans *trans, if (should_have_subvol) { id = le32_to_cpu(s.subvol); - ret = bch2_subvolume_get(trans, id, 0, false, &subvol); + ret = bch2_subvolume_get(trans, id, false, &subvol); if (bch2_err_matches(ret, ENOENT)) bch_err(c, "snapshot points to nonexistent subvolume:\n %s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf)); @@ -902,7 +842,7 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) { struct bch_fs *c = trans->c; - if (bch2_snapshot_equiv(c, id)) + if (bch2_snapshot_exists(c, id)) return 0; /* Do we need to reconstruct the snapshot_tree entry as well? */ @@ -951,8 +891,7 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) return bch2_btree_insert_trans(trans, BTREE_ID_snapshots, &snapshot->k_i, 0) ?: bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, - bkey_s_c_null, bkey_i_to_s(&snapshot->k_i), 0) ?: - bch2_snapshot_set_equiv(trans, bkey_i_to_s_c(&snapshot->k_i)); + bkey_s_c_null, bkey_i_to_s(&snapshot->k_i), 0); } /* Figure out which snapshot nodes belong in the same tree: */ @@ -1050,7 +989,7 @@ int bch2_reconstruct_snapshots(struct bch_fs *c) snapshot_id_list_to_text(&buf, t); darray_for_each(*t, id) { - if (fsck_err_on(!bch2_snapshot_equiv(c, *id), + if (fsck_err_on(!bch2_snapshot_exists(c, *id), trans, snapshot_node_missing, "snapshot node %u from tree %s missing, recreate?", *id, buf.buf)) { if (t->nr > 1) { @@ -1083,10 +1022,12 @@ int bch2_check_key_has_snapshot(struct btree_trans *trans, struct printbuf buf = PRINTBUF; int ret = 0; - if (fsck_err_on(!bch2_snapshot_equiv(c, k.k->p.snapshot), + if (fsck_err_on(!bch2_snapshot_exists(c, k.k->p.snapshot), trans, bkey_in_missing_snapshot, "key in missing snapshot %s, delete?", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + (bch2_btree_id_to_text(&buf, iter->btree_id), + prt_char(&buf, ' '), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node) ?: 1; fsck_err: @@ -1100,13 +1041,11 @@ fsck_err: int bch2_snapshot_node_set_deleted(struct btree_trans *trans, u32 id) { struct btree_iter iter; - struct bkey_i_snapshot *s; - int ret = 0; - - s = bch2_bkey_get_mut_typed(trans, &iter, + struct bkey_i_snapshot *s = + bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_snapshots, POS(0, id), 0, snapshot); - ret = PTR_ERR_OR_ZERO(s); + int ret = PTR_ERR_OR_ZERO(s); if (unlikely(ret)) { bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing snapshot %u", id); @@ -1294,10 +1233,6 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree, goto err; new_snapids[i] = iter.pos.offset; - - mutex_lock(&c->snapshot_table_lock); - snapshot_t_mut(c, new_snapids[i])->equiv = new_snapids[i]; - mutex_unlock(&c->snapshot_table_lock); } err: bch2_trans_iter_exit(trans, &iter); @@ -1403,129 +1338,153 @@ int bch2_snapshot_node_create(struct btree_trans *trans, u32 parent, * that key to snapshot leaf nodes, where we can mutate it */ -static int delete_dead_snapshots_process_key(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k, - snapshot_id_list *deleted, - snapshot_id_list *equiv_seen, - struct bpos *last_pos) +struct snapshot_interior_delete { + u32 id; + u32 live_child; +}; +typedef DARRAY(struct snapshot_interior_delete) interior_delete_list; + +static inline u32 interior_delete_has_id(interior_delete_list *l, u32 id) { - int ret = bch2_check_key_has_snapshot(trans, iter, k); - if (ret) - return ret < 0 ? ret : 0; + darray_for_each(*l, i) + if (i->id == id) + return i->live_child; + return 0; +} - struct bch_fs *c = trans->c; - u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot); - if (!equiv) /* key for invalid snapshot node, but we chose not to delete */ +static unsigned __live_child(struct snapshot_table *t, u32 id, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) +{ + struct snapshot_t *s = __snapshot_t(t, id); + if (!s) return 0; - if (!bkey_eq(k.k->p, *last_pos)) - equiv_seen->nr = 0; + for (unsigned i = 0; i < ARRAY_SIZE(s->children); i++) + if (s->children[i] && + !snapshot_list_has_id(delete_leaves, s->children[i]) && + !interior_delete_has_id(delete_interior, s->children[i])) + return s->children[i]; - if (snapshot_list_has_id(deleted, k.k->p.snapshot)) - return bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node); + for (unsigned i = 0; i < ARRAY_SIZE(s->children); i++) { + u32 live_child = s->children[i] + ? __live_child(t, s->children[i], delete_leaves, delete_interior) + : 0; + if (live_child) + return live_child; + } - if (!bpos_eq(*last_pos, k.k->p) && - snapshot_list_has_id(equiv_seen, equiv)) - return bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node); + return 0; +} - *last_pos = k.k->p; +static unsigned live_child(struct bch_fs *c, u32 id, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) +{ + rcu_read_lock(); + u32 ret = __live_child(rcu_dereference(c->snapshots), id, + delete_leaves, delete_interior); + rcu_read_unlock(); + return ret; +} - ret = snapshot_list_add_nodup(c, equiv_seen, equiv); - if (ret) - return ret; +static int delete_dead_snapshots_process_key(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c k, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) +{ + if (snapshot_list_has_id(delete_leaves, k.k->p.snapshot)) + return bch2_btree_delete_at(trans, iter, + BTREE_UPDATE_internal_snapshot_node); - /* - * When we have a linear chain of snapshot nodes, we consider - * those to form an equivalence class: we're going to collapse - * them all down to a single node, and keep the leaf-most node - - * which has the same id as the equivalence class id. - * - * If there are multiple keys in different snapshots at the same - * position, we're only going to keep the one in the newest - * snapshot (we delete the others above) - the rest have been - * overwritten and are redundant, and for the key we're going to keep we - * need to move it to the equivalance class ID if it's not there - * already. - */ - if (equiv != k.k->p.snapshot) { + u32 live_child = interior_delete_has_id(delete_interior, k.k->p.snapshot); + if (live_child) { struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); int ret = PTR_ERR_OR_ZERO(new); if (ret) return ret; - new->k.p.snapshot = equiv; - - struct btree_iter new_iter; - bch2_trans_iter_init(trans, &new_iter, iter->btree_id, new->k.p, - BTREE_ITER_all_snapshots| - BTREE_ITER_cached| - BTREE_ITER_intent); + new->k.p.snapshot = live_child; - ret = bch2_btree_iter_traverse(&new_iter) ?: - bch2_trans_update(trans, &new_iter, new, - BTREE_UPDATE_internal_snapshot_node) ?: - bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node); - bch2_trans_iter_exit(trans, &new_iter); + struct btree_iter dst_iter; + struct bkey_s_c dst_k = bch2_bkey_get_iter(trans, &dst_iter, + iter->btree_id, new->k.p, + BTREE_ITER_all_snapshots| + BTREE_ITER_intent); + ret = bkey_err(dst_k); if (ret) return ret; + + ret = (bkey_deleted(dst_k.k) + ? bch2_trans_update(trans, &dst_iter, new, + BTREE_UPDATE_internal_snapshot_node) + : 0) ?: + bch2_btree_delete_at(trans, iter, + BTREE_UPDATE_internal_snapshot_node); + bch2_trans_iter_exit(trans, &dst_iter); + return ret; } return 0; } -static int bch2_snapshot_needs_delete(struct btree_trans *trans, struct bkey_s_c k) +/* + * For a given snapshot, if it doesn't have a subvolume that points to it, and + * it doesn't have child snapshot nodes - it's now redundant and we can mark it + * as deleted. + */ +static int check_should_delete_snapshot(struct btree_trans *trans, struct bkey_s_c k, + snapshot_id_list *delete_leaves, + interior_delete_list *delete_interior) { - struct bkey_s_c_snapshot snap; - u32 children[2]; - int ret; - if (k.k->type != KEY_TYPE_snapshot) return 0; - snap = bkey_s_c_to_snapshot(k); - if (BCH_SNAPSHOT_DELETED(snap.v) || - BCH_SNAPSHOT_SUBVOL(snap.v)) + struct bch_fs *c = trans->c; + struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(k); + unsigned live_children = 0; + + if (BCH_SNAPSHOT_SUBVOL(s.v)) return 0; - children[0] = le32_to_cpu(snap.v->children[0]); - children[1] = le32_to_cpu(snap.v->children[1]); + for (unsigned i = 0; i < 2; i++) { + u32 child = le32_to_cpu(s.v->children[i]); - ret = bch2_snapshot_live(trans, children[0]) ?: - bch2_snapshot_live(trans, children[1]); - if (ret < 0) - return ret; - return !ret; -} + live_children += child && + !snapshot_list_has_id(delete_leaves, child); + } -/* - * For a given snapshot, if it doesn't have a subvolume that points to it, and - * it doesn't have child snapshot nodes - it's now redundant and we can mark it - * as deleted. - */ -static int bch2_delete_redundant_snapshot(struct btree_trans *trans, struct bkey_s_c k) -{ - int ret = bch2_snapshot_needs_delete(trans, k); + if (live_children == 0) { + return snapshot_list_add(c, delete_leaves, s.k->p.offset); + } else if (live_children == 1) { + struct snapshot_interior_delete d = { + .id = s.k->p.offset, + .live_child = live_child(c, s.k->p.offset, delete_leaves, delete_interior), + }; + + if (!d.live_child) { + bch_err(c, "error finding live child of snapshot %u", d.id); + return -EINVAL; + } - return ret <= 0 - ? ret - : bch2_snapshot_node_set_deleted(trans, k.k->p.offset); + return darray_push(delete_interior, d); + } else { + return 0; + } } static inline u32 bch2_snapshot_nth_parent_skip(struct bch_fs *c, u32 id, u32 n, - snapshot_id_list *skip) + interior_delete_list *skip) { rcu_read_lock(); - while (snapshot_list_has_id(skip, id)) + while (interior_delete_has_id(skip, id)) id = __bch2_snapshot_parent(c, id); while (n--) { do { id = __bch2_snapshot_parent(c, id); - } while (snapshot_list_has_id(skip, id)); + } while (interior_delete_has_id(skip, id)); } rcu_read_unlock(); @@ -1534,7 +1493,7 @@ static inline u32 bch2_snapshot_nth_parent_skip(struct bch_fs *c, u32 id, u32 n, static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, - snapshot_id_list *deleted) + interior_delete_list *deleted) { struct bch_fs *c = trans->c; u32 nr_deleted_ancestors = 0; @@ -1544,7 +1503,7 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, if (k.k->type != KEY_TYPE_snapshot) return 0; - if (snapshot_list_has_id(deleted, k.k->p.offset)) + if (interior_delete_has_id(deleted, k.k->p.offset)) return 0; s = bch2_bkey_make_mut_noupdate_typed(trans, k, snapshot); @@ -1553,7 +1512,7 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, return ret; darray_for_each(*deleted, i) - nr_deleted_ancestors += bch2_snapshot_is_ancestor(c, s->k.p.offset, *i); + nr_deleted_ancestors += bch2_snapshot_is_ancestor(c, s->k.p.offset, i->id); if (!nr_deleted_ancestors) return 0; @@ -1571,7 +1530,7 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, for (unsigned j = 0; j < ARRAY_SIZE(s->v.skip); j++) { u32 id = le32_to_cpu(s->v.skip[j]); - if (snapshot_list_has_id(deleted, id)) { + if (interior_delete_has_id(deleted, id)) { id = bch2_snapshot_nth_parent_skip(c, parent, depth > 1 @@ -1590,51 +1549,45 @@ static int bch2_fix_child_of_deleted_snapshot(struct btree_trans *trans, int bch2_delete_dead_snapshots(struct bch_fs *c) { - struct btree_trans *trans; - snapshot_id_list deleted = { 0 }; - snapshot_id_list deleted_interior = { 0 }; - int ret = 0; - if (!test_and_clear_bit(BCH_FS_need_delete_dead_snapshots, &c->flags)) return 0; - trans = bch2_trans_get(c); + struct btree_trans *trans = bch2_trans_get(c); + snapshot_id_list delete_leaves = {}; + interior_delete_list delete_interior = {}; + int ret = 0; /* * For every snapshot node: If we have no live children and it's not * pointed to by a subvolume, delete it: */ - ret = for_each_btree_key_commit(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, - NULL, NULL, 0, - bch2_delete_redundant_snapshot(trans, k)); - bch_err_msg(c, ret, "deleting redundant snapshots"); + ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, POS_MIN, 0, k, + check_should_delete_snapshot(trans, k, &delete_leaves, &delete_interior)); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "walking snapshots"); if (ret) goto err; - ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, - bch2_snapshot_set_equiv(trans, k)); - bch_err_msg(c, ret, "in bch2_snapshots_set_equiv"); - if (ret) + if (!delete_leaves.nr && !delete_interior.nr) goto err; - ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, ({ - if (k.k->type != KEY_TYPE_snapshot) - continue; + { + struct printbuf buf = PRINTBUF; + prt_printf(&buf, "deleting leaves"); + darray_for_each(delete_leaves, i) + prt_printf(&buf, " %u", *i); - BCH_SNAPSHOT_DELETED(bkey_s_c_to_snapshot(k).v) - ? snapshot_list_add(c, &deleted, k.k->p.offset) - : 0; - })); - bch_err_msg(c, ret, "walking snapshots"); - if (ret) - goto err; + prt_printf(&buf, " interior"); + darray_for_each(delete_interior, i) + prt_printf(&buf, " %u->%u", i->id, i->live_child); + + ret = commit_do(trans, NULL, NULL, 0, bch2_trans_log_msg(trans, &buf)); + printbuf_exit(&buf); + if (ret) + goto err; + } for (unsigned btree = 0; btree < BTREE_ID_NR; btree++) { - struct bpos last_pos = POS_MIN; - snapshot_id_list equiv_seen = { 0 }; struct disk_reservation res = { 0 }; if (!btree_type_has_snapshots(btree)) @@ -1644,33 +1597,26 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) btree, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, &res, NULL, BCH_TRANS_COMMIT_no_enospc, - delete_dead_snapshots_process_key(trans, &iter, k, &deleted, - &equiv_seen, &last_pos)); + delete_dead_snapshots_process_key(trans, &iter, k, + &delete_leaves, + &delete_interior)); bch2_disk_reservation_put(c, &res); - darray_exit(&equiv_seen); - bch_err_msg(c, ret, "deleting keys from dying snapshots"); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "deleting keys from dying snapshots"); if (ret) goto err; } - bch2_trans_unlock(trans); - down_write(&c->snapshot_create_lock); - - ret = for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, ({ - u32 snapshot = k.k->p.offset; - u32 equiv = bch2_snapshot_equiv(c, snapshot); - - equiv != snapshot - ? snapshot_list_add(c, &deleted_interior, snapshot) - : 0; - })); - - bch_err_msg(c, ret, "walking snapshots"); - if (ret) - goto err_create_lock; + darray_for_each(delete_leaves, i) { + ret = commit_do(trans, NULL, NULL, 0, + bch2_snapshot_node_delete(trans, *i)); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "deleting snapshot %u", *i); + if (ret) + goto err; + } /* * Fixing children of deleted snapshots can't be done completely @@ -1680,32 +1626,24 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) ret = for_each_btree_key_commit(trans, iter, BTREE_ID_snapshots, POS_MIN, BTREE_ITER_intent, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, - bch2_fix_child_of_deleted_snapshot(trans, &iter, k, &deleted_interior)); + bch2_fix_child_of_deleted_snapshot(trans, &iter, k, &delete_interior)); if (ret) - goto err_create_lock; - - darray_for_each(deleted, i) { - ret = commit_do(trans, NULL, NULL, 0, - bch2_snapshot_node_delete(trans, *i)); - bch_err_msg(c, ret, "deleting snapshot %u", *i); - if (ret) - goto err_create_lock; - } + goto err; - darray_for_each(deleted_interior, i) { + darray_for_each(delete_interior, i) { ret = commit_do(trans, NULL, NULL, 0, - bch2_snapshot_node_delete(trans, *i)); - bch_err_msg(c, ret, "deleting snapshot %u", *i); + bch2_snapshot_node_delete(trans, i->id)); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "deleting snapshot %u", i->id); if (ret) - goto err_create_lock; + goto err; } -err_create_lock: - up_write(&c->snapshot_create_lock); err: - darray_exit(&deleted_interior); - darray_exit(&deleted); + darray_exit(&delete_interior); + darray_exit(&delete_leaves); bch2_trans_put(trans); - bch_err_fn(c, ret); + if (!bch2_err_matches(ret, EROFS)) + bch_err_fn(c, ret); return ret; } @@ -1721,8 +1659,12 @@ void bch2_delete_dead_snapshots_work(struct work_struct *work) void bch2_delete_dead_snapshots_async(struct bch_fs *c) { - if (bch2_write_ref_tryget(c, BCH_WRITE_REF_delete_dead_snapshots) && - !queue_work(c->write_ref_wq, &c->snapshot_delete_work)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_delete_dead_snapshots)) + return; + + BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags)); + + if (!queue_work(c->write_ref_wq, &c->snapshot_delete_work)) bch2_write_ref_put(c, BCH_WRITE_REF_delete_dead_snapshots); } @@ -1735,18 +1677,10 @@ int __bch2_key_has_snapshot_overwrites(struct btree_trans *trans, struct bkey_s_c k; int ret; - bch2_trans_iter_init(trans, &iter, id, pos, - BTREE_ITER_not_extents| - BTREE_ITER_all_snapshots); - while (1) { - k = bch2_btree_iter_prev(&iter); - ret = bkey_err(k); - if (ret) - break; - - if (!k.k) - break; - + for_each_btree_key_reverse_norestart(trans, iter, id, bpos_predecessor(pos), + BTREE_ITER_not_extents| + BTREE_ITER_all_snapshots, + k, ret) { if (!bkey_eq(pos, k.k->p)) break; @@ -1760,37 +1694,36 @@ int __bch2_key_has_snapshot_overwrites(struct btree_trans *trans, return ret; } -static int bch2_check_snapshot_needs_deletion(struct btree_trans *trans, struct bkey_s_c k) +static bool interior_snapshot_needs_delete(struct bkey_s_c_snapshot snap) { - struct bch_fs *c = trans->c; - struct bkey_s_c_snapshot snap; - int ret = 0; + /* If there's one child, it's redundant and keys will be moved to the child */ + return !!snap.v->children[0] + !!snap.v->children[1] == 1; +} +static int bch2_check_snapshot_needs_deletion(struct btree_trans *trans, struct bkey_s_c k) +{ if (k.k->type != KEY_TYPE_snapshot) return 0; - snap = bkey_s_c_to_snapshot(k); + struct bkey_s_c_snapshot snap = bkey_s_c_to_snapshot(k); if (BCH_SNAPSHOT_DELETED(snap.v) || - bch2_snapshot_equiv(c, k.k->p.offset) != k.k->p.offset || - (ret = bch2_snapshot_needs_delete(trans, k)) > 0) { - set_bit(BCH_FS_need_delete_dead_snapshots, &c->flags); - return 0; - } + interior_snapshot_needs_delete(snap)) + set_bit(BCH_FS_need_delete_dead_snapshots, &trans->c->flags); - return ret; + return 0; } int bch2_snapshots_read(struct bch_fs *c) { + /* + * Initializing the is_ancestor bitmaps requires ancestors to already be + * initialized - so mark in reverse: + */ int ret = bch2_trans_run(c, - for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, + for_each_btree_key_reverse(trans, iter, BTREE_ID_snapshots, + POS_MAX, 0, k, __bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, bkey_s_c_null, k, 0) ?: - bch2_snapshot_set_equiv(trans, k) ?: - bch2_check_snapshot_needs_deletion(trans, k)) ?: - for_each_btree_key(trans, iter, BTREE_ID_snapshots, - POS_MIN, 0, k, - (set_is_ancestor_bitmap(c, k.k->p.offset), 0))); + bch2_check_snapshot_needs_deletion(trans, k))); bch_err_fn(c, ret); /* diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h index 29c94716293e..00373cf32e7b 100644 --- a/fs/bcachefs/snapshot.h +++ b/fs/bcachefs/snapshot.h @@ -2,11 +2,9 @@ #ifndef _BCACHEFS_SNAPSHOT_H #define _BCACHEFS_SNAPSHOT_H -enum bch_validate_flags; - void bch2_snapshot_tree_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_snapshot_tree_validate(struct bch_fs *, struct bkey_s_c, - enum bch_validate_flags); + struct bkey_validate_context); #define bch2_bkey_ops_snapshot_tree ((struct bkey_ops) { \ .key_validate = bch2_snapshot_tree_validate, \ @@ -19,7 +17,8 @@ struct bkey_i_snapshot_tree *__bch2_snapshot_tree_create(struct btree_trans *); int bch2_snapshot_tree_lookup(struct btree_trans *, u32, struct bch_snapshot_tree *); void bch2_snapshot_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); -int bch2_snapshot_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_snapshot_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); @@ -120,19 +119,19 @@ static inline u32 bch2_snapshot_root(struct bch_fs *c, u32 id) return id; } -static inline u32 __bch2_snapshot_equiv(struct bch_fs *c, u32 id) +static inline bool __bch2_snapshot_exists(struct bch_fs *c, u32 id) { const struct snapshot_t *s = snapshot_t(c, id); - return s ? s->equiv : 0; + return s ? s->live : 0; } -static inline u32 bch2_snapshot_equiv(struct bch_fs *c, u32 id) +static inline bool bch2_snapshot_exists(struct bch_fs *c, u32 id) { rcu_read_lock(); - id = __bch2_snapshot_equiv(c, id); + bool ret = __bch2_snapshot_exists(c, id); rcu_read_unlock(); - return id; + return ret; } static inline int bch2_snapshot_is_internal_node(struct bch_fs *c, u32 id) diff --git a/fs/bcachefs/str_hash.c b/fs/bcachefs/str_hash.c new file mode 100644 index 000000000000..8c2c5539de2e --- /dev/null +++ b/fs/bcachefs/str_hash.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "bcachefs.h" +#include "btree_cache.h" +#include "btree_update.h" +#include "dirent.h" +#include "fsck.h" +#include "str_hash.h" +#include "subvolume.h" + +static int bch2_dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dirent d) +{ + if (d.v->d_type == DT_SUBVOL) { + struct bch_subvolume subvol; + int ret = bch2_subvolume_get(trans, le32_to_cpu(d.v->d_child_subvol), + false, &subvol); + if (ret && !bch2_err_matches(ret, ENOENT)) + return ret; + return !ret; + } else { + struct btree_iter iter; + struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + SPOS(0, le64_to_cpu(d.v->d_inum), d.k->p.snapshot), 0); + int ret = bkey_err(k); + if (ret) + return ret; + + ret = bkey_is_inode(k.k); + bch2_trans_iter_exit(trans, &iter); + return ret; + } +} + +static int fsck_rename_dirent(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_s_c_dirent old) +{ + struct qstr old_name = bch2_dirent_get_name(old); + struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32); + int ret = PTR_ERR_OR_ZERO(new); + if (ret) + return ret; + + bkey_dirent_init(&new->k_i); + dirent_copy_target(new, old); + new->k.p = old.k->p; + + for (unsigned i = 0; i < 1000; i++) { + unsigned len = sprintf(new->v.d_name, "%.*s.fsck_renamed-%u", + old_name.len, old_name.name, i); + unsigned u64s = BKEY_U64s + dirent_val_u64s(len); + + if (u64s > U8_MAX) + return -EINVAL; + + new->k.u64s = u64s; + + ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info, + (subvol_inum) { 0, old.k->p.inode }, + old.k->p.snapshot, &new->k_i, + BTREE_UPDATE_internal_snapshot_node); + if (!bch2_err_matches(ret, EEXIST)) + break; + } + + if (ret) + return ret; + + return bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i); +} + +static int hash_pick_winner(struct btree_trans *trans, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_s_c k1, + struct bkey_s_c k2) +{ + if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) && + !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k))) + return 0; + + switch (desc.btree_id) { + case BTREE_ID_dirents: { + int ret = bch2_dirent_has_target(trans, bkey_s_c_to_dirent(k1)); + if (ret < 0) + return ret; + if (!ret) + return 0; + + ret = bch2_dirent_has_target(trans, bkey_s_c_to_dirent(k2)); + if (ret < 0) + return ret; + if (!ret) + return 1; + return 2; + } + default: + return 0; + } +} + +static int repair_inode_hash_info(struct btree_trans *trans, + struct bch_inode_unpacked *snapshot_root) +{ + struct btree_iter iter; + struct bkey_s_c k; + int ret = 0; + + for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, + SPOS(0, snapshot_root->bi_inum, snapshot_root->bi_snapshot - 1), + BTREE_ITER_all_snapshots, k, ret) { + if (k.k->p.offset != snapshot_root->bi_inum) + break; + if (!bkey_is_inode(k.k)) + continue; + + struct bch_inode_unpacked inode; + ret = bch2_inode_unpack(k, &inode); + if (ret) + break; + + if (fsck_err_on(inode.bi_hash_seed != snapshot_root->bi_hash_seed || + INODE_STR_HASH(&inode) != INODE_STR_HASH(snapshot_root), + trans, inode_snapshot_mismatch, + "inode hash info in different snapshots don't match")) { + inode.bi_hash_seed = snapshot_root->bi_hash_seed; + SET_INODE_STR_HASH(&inode, INODE_STR_HASH(snapshot_root)); + ret = __bch2_fsck_write_inode(trans, &inode) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; + break; + } + } +fsck_err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +/* + * All versions of the same inode in different snapshots must have the same hash + * seed/type: verify that the hash info we're using matches the root + */ +static int check_inode_hash_info_matches_root(struct btree_trans *trans, u64 inum, + struct bch_hash_info *hash_info) +{ + struct bch_fs *c = trans->c; + struct btree_iter iter; + struct bkey_s_c k; + int ret = 0; + + for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, U32_MAX), + BTREE_ITER_all_snapshots, k, ret) { + if (k.k->p.offset != inum) + break; + if (bkey_is_inode(k.k)) + goto found; + } + bch_err(c, "%s(): inum %llu not found", __func__, inum); + ret = -BCH_ERR_fsck_repair_unimplemented; + goto err; +found:; + struct bch_inode_unpacked inode; + ret = bch2_inode_unpack(k, &inode); + if (ret) + goto err; + + struct bch_hash_info hash2 = bch2_hash_info_init(c, &inode); + if (hash_info->type != hash2.type || + memcmp(&hash_info->siphash_key, &hash2.siphash_key, sizeof(hash2.siphash_key))) { + ret = repair_inode_hash_info(trans, &inode); + if (!ret) { + bch_err(c, "inode hash info mismatch with root, but mismatch not found\n" + "%u %llx %llx\n" + "%u %llx %llx", + hash_info->type, + hash_info->siphash_key.k0, + hash_info->siphash_key.k1, + hash2.type, + hash2.siphash_key.k0, + hash2.siphash_key.k1); + ret = -BCH_ERR_fsck_repair_unimplemented; + } + } +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +int __bch2_str_hash_check_key(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc *desc, + struct bch_hash_info *hash_info, + struct btree_iter *k_iter, struct bkey_s_c hash_k) +{ + struct bch_fs *c = trans->c; + struct btree_iter iter = { NULL }; + struct printbuf buf = PRINTBUF; + struct bkey_s_c k; + int ret = 0; + + u64 hash = desc->hash_bkey(hash_info, hash_k); + if (hash_k.k->p.offset < hash) + goto bad_hash; + + for_each_btree_key_norestart(trans, iter, desc->btree_id, + SPOS(hash_k.k->p.inode, hash, hash_k.k->p.snapshot), + BTREE_ITER_slots, k, ret) { + if (bkey_eq(k.k->p, hash_k.k->p)) + break; + + if (k.k->type == desc->key_type && + !desc->cmp_bkey(k, hash_k)) + goto duplicate_entries; + + if (bkey_deleted(k.k)) { + bch2_trans_iter_exit(trans, &iter); + goto bad_hash; + } + } +out: + bch2_trans_iter_exit(trans, &iter); + printbuf_exit(&buf); + return ret; +bad_hash: + /* + * Before doing any repair, check hash_info itself: + */ + ret = check_inode_hash_info_matches_root(trans, hash_k.k->p.inode, hash_info); + if (ret) + goto out; + + if (fsck_err(trans, hash_table_key_wrong_offset, + "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n %s", + bch2_btree_id_str(desc->btree_id), hash_k.k->p.inode, hash_k.k->p.offset, hash, + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf))) { + struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, hash_k); + if (IS_ERR(new)) + return PTR_ERR(new); + + k = bch2_hash_set_or_get_in_snapshot(trans, &iter, *desc, hash_info, + (subvol_inum) { 0, hash_k.k->p.inode }, + hash_k.k->p.snapshot, new, + STR_HASH_must_create| + BTREE_ITER_with_updates| + BTREE_UPDATE_internal_snapshot_node); + ret = bkey_err(k); + if (ret) + goto out; + if (k.k) + goto duplicate_entries; + + ret = bch2_hash_delete_at(trans, *desc, hash_info, k_iter, + BTREE_UPDATE_internal_snapshot_node) ?: + bch2_fsck_update_backpointers(trans, s, *desc, hash_info, new) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: + -BCH_ERR_transaction_restart_nested; + goto out; + } +fsck_err: + goto out; +duplicate_entries: + ret = hash_pick_winner(trans, *desc, hash_info, hash_k, k); + if (ret < 0) + goto out; + + if (!fsck_err(trans, hash_table_key_duplicate, + "duplicate hash table keys%s:\n%s", + ret != 2 ? "" : ", both point to valid inodes", + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, hash_k), + prt_newline(&buf), + bch2_bkey_val_to_text(&buf, c, k), + buf.buf))) + goto out; + + switch (ret) { + case 0: + ret = bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0); + break; + case 1: + ret = bch2_hash_delete_at(trans, *desc, hash_info, &iter, 0); + break; + case 2: + ret = fsck_rename_dirent(trans, s, *desc, hash_info, bkey_s_c_to_dirent(hash_k)) ?: + bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0); + goto out; + } + + ret = bch2_trans_commit(trans, NULL, NULL, 0) ?: + -BCH_ERR_transaction_restart_nested; + goto out; +} diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h index ec2b1feea520..55a4ac7bf220 100644 --- a/fs/bcachefs/str_hash.h +++ b/fs/bcachefs/str_hash.h @@ -160,7 +160,7 @@ bch2_hash_lookup_in_snapshot(struct btree_trans *trans, struct bkey_s_c k; int ret; - for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, + for_each_btree_key_max_norestart(trans, *iter, desc.btree_id, SPOS(inum.inum, desc.hash_key(info, key), snapshot), POS(inum.inum, U64_MAX), BTREE_ITER_slots|flags, k, ret) { @@ -210,7 +210,7 @@ bch2_hash_hole(struct btree_trans *trans, if (ret) return ret; - for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, + for_each_btree_key_max_norestart(trans, *iter, desc.btree_id, SPOS(inum.inum, desc.hash_key(info, key), snapshot), POS(inum.inum, U64_MAX), BTREE_ITER_slots|BTREE_ITER_intent, k, ret) @@ -265,7 +265,7 @@ struct bkey_s_c bch2_hash_set_or_get_in_snapshot(struct btree_trans *trans, bool found = false; int ret; - for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, + for_each_btree_key_max_norestart(trans, *iter, desc.btree_id, SPOS(insert->k.p.inode, desc.hash_bkey(info, bkey_i_to_s_c(insert)), snapshot), @@ -393,4 +393,26 @@ int bch2_hash_delete(struct btree_trans *trans, return ret; } +struct snapshots_seen; +int __bch2_str_hash_check_key(struct btree_trans *, + struct snapshots_seen *, + const struct bch_hash_desc *, + struct bch_hash_info *, + struct btree_iter *, struct bkey_s_c); + +static inline int bch2_str_hash_check_key(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc *desc, + struct bch_hash_info *hash_info, + struct btree_iter *k_iter, struct bkey_s_c hash_k) +{ + if (hash_k.k->type != desc->key_type) + return 0; + + if (likely(desc->hash_bkey(hash_info, hash_k) == hash_k.k->p.offset)) + return 0; + + return __bch2_str_hash_check_key(trans, s, desc, hash_info, k_iter, hash_k); +} + #endif /* _BCACHEFS_STR_HASH_H */ diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index 80e5efaff524..e3d0475232e5 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -207,7 +207,7 @@ int bch2_check_subvol_children(struct bch_fs *c) /* Subvolumes: */ int bch2_subvolume_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_subvolume subvol = bkey_s_c_to_subvolume(k); int ret = 0; @@ -286,11 +286,11 @@ int bch2_subvol_has_children(struct btree_trans *trans, u32 subvol) static __always_inline int bch2_subvolume_get_inlined(struct btree_trans *trans, unsigned subvol, bool inconsistent_if_not_found, - int iter_flags, struct bch_subvolume *s) { int ret = bch2_bkey_get_val_typed(trans, BTREE_ID_subvolumes, POS(0, subvol), - iter_flags, subvolume, s); + BTREE_ITER_cached| + BTREE_ITER_with_updates, subvolume, s); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT) && inconsistent_if_not_found, trans->c, "missing subvolume %u", subvol); @@ -299,16 +299,15 @@ bch2_subvolume_get_inlined(struct btree_trans *trans, unsigned subvol, int bch2_subvolume_get(struct btree_trans *trans, unsigned subvol, bool inconsistent_if_not_found, - int iter_flags, struct bch_subvolume *s) { - return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, iter_flags, s); + return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, s); } int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol) { struct bch_subvolume s; - int ret = bch2_subvolume_get_inlined(trans, subvol, true, 0, &s); + int ret = bch2_subvolume_get_inlined(trans, subvol, true, &s); if (ret) return ret; @@ -328,7 +327,7 @@ int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot, struct bch_snapshot snap; return bch2_snapshot_lookup(trans, snapshot, &snap) ?: - bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, 0, subvol); + bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, subvol); } int __bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, @@ -396,8 +395,7 @@ static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_d struct bch_subvolume s; return lockrestart_do(trans, - bch2_subvolume_get(trans, subvolid_to_delete, true, - BTREE_ITER_cached, &s)) ?: + bch2_subvolume_get(trans, subvolid_to_delete, true, &s)) ?: for_each_btree_key_commit(trans, iter, BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, @@ -411,26 +409,56 @@ static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_d */ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid) { - struct btree_iter iter; - struct bkey_s_c_subvolume subvol; - u32 snapid; - int ret = 0; + struct btree_iter subvol_iter = {}, snapshot_iter = {}, snapshot_tree_iter = {}; - subvol = bch2_bkey_get_iter_typed(trans, &iter, + struct bkey_s_c_subvolume subvol = + bch2_bkey_get_iter_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, subvolid), BTREE_ITER_cached|BTREE_ITER_intent, subvolume); - ret = bkey_err(subvol); + int ret = bkey_err(subvol); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing subvolume %u", subvolid); if (ret) - return ret; + goto err; - snapid = le32_to_cpu(subvol.v->snapshot); + u32 snapid = le32_to_cpu(subvol.v->snapshot); + + struct bkey_s_c_snapshot snapshot = + bch2_bkey_get_iter_typed(trans, &snapshot_iter, + BTREE_ID_snapshots, POS(0, snapid), + 0, snapshot); + ret = bkey_err(subvol); + bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, + "missing snapshot %u", snapid); + if (ret) + goto err; + + u32 treeid = le32_to_cpu(snapshot.v->tree); - ret = bch2_btree_delete_at(trans, &iter, 0) ?: + struct bkey_s_c_snapshot_tree snapshot_tree = + bch2_bkey_get_iter_typed(trans, &snapshot_tree_iter, + BTREE_ID_snapshot_trees, POS(0, treeid), + 0, snapshot_tree); + + if (le32_to_cpu(snapshot_tree.v->master_subvol) == subvolid) { + struct bkey_i_snapshot_tree *snapshot_tree_mut = + bch2_bkey_make_mut_typed(trans, &snapshot_tree_iter, + &snapshot_tree.s_c, + 0, snapshot_tree); + ret = PTR_ERR_OR_ZERO(snapshot_tree_mut); + if (ret) + goto err; + + snapshot_tree_mut->v.master_subvol = 0; + } + + ret = bch2_btree_delete_at(trans, &subvol_iter, 0) ?: bch2_snapshot_node_set_deleted(trans, snapid); - bch2_trans_iter_exit(trans, &iter); +err: + bch2_trans_iter_exit(trans, &snapshot_tree_iter); + bch2_trans_iter_exit(trans, &snapshot_iter); + bch2_trans_iter_exit(trans, &subvol_iter); return ret; } @@ -675,7 +703,7 @@ err: /* set bi_subvol on root inode */ int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) { - int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw, + int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, __bch2_fs_upgrade_for_subvolumes(trans)); bch_err_fn(c, ret); return ret; diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index f897d106e142..910f6196700e 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -5,12 +5,11 @@ #include "darray.h" #include "subvolume_types.h" -enum bch_validate_flags; - int bch2_check_subvols(struct bch_fs *); int bch2_check_subvol_children(struct bch_fs *); -int bch2_subvolume_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_subvolume_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_subvolume_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, @@ -25,7 +24,7 @@ int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned, int bch2_subvol_has_children(struct btree_trans *, u32); int bch2_subvolume_get(struct btree_trans *, unsigned, - bool, int, struct bch_subvolume *); + bool, struct bch_subvolume *); int __bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *, bool); int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *); @@ -34,7 +33,7 @@ int bch2_subvol_is_ro_trans(struct btree_trans *, u32); int bch2_subvol_is_ro(struct bch_fs *, u32); static inline struct bkey_s_c -bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos end, +bch2_btree_iter_peek_in_subvolume_max_type(struct btree_iter *iter, struct bpos end, u32 subvolid, unsigned flags) { u32 snapshot; @@ -43,10 +42,10 @@ bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos return bkey_s_c_err(ret); bch2_btree_iter_set_snapshot(iter, snapshot); - return bch2_btree_iter_peek_upto_type(iter, end, flags); + return bch2_btree_iter_peek_max_type(iter, end, flags); } -#define for_each_btree_key_in_subvolume_upto_continue(_trans, _iter, \ +#define for_each_btree_key_in_subvolume_max_continue(_trans, _iter, \ _end, _subvolid, _flags, _k, _do) \ ({ \ struct bkey_s_c _k; \ @@ -54,7 +53,7 @@ bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos \ do { \ _ret3 = lockrestart_do(_trans, ({ \ - (_k) = bch2_btree_iter_peek_in_subvolume_upto_type(&(_iter), \ + (_k) = bch2_btree_iter_peek_in_subvolume_max_type(&(_iter), \ _end, _subvolid, (_flags)); \ if (!(_k).k) \ break; \ @@ -67,14 +66,14 @@ bch2_btree_iter_peek_in_subvolume_upto_type(struct btree_iter *iter, struct bpos _ret3; \ }) -#define for_each_btree_key_in_subvolume_upto(_trans, _iter, _btree_id, \ +#define for_each_btree_key_in_subvolume_max(_trans, _iter, _btree_id, \ _start, _end, _subvolid, _flags, _k, _do) \ ({ \ struct btree_iter _iter; \ bch2_trans_iter_init((_trans), &(_iter), (_btree_id), \ (_start), (_flags)); \ \ - for_each_btree_key_in_subvolume_upto_continue(_trans, _iter, \ + for_each_btree_key_in_subvolume_max_continue(_trans, _iter, \ _end, _subvolid, _flags, _k, _do); \ }) diff --git a/fs/bcachefs/subvolume_types.h b/fs/bcachefs/subvolume_types.h index f2ec4277c2a5..1549d6daf7af 100644 --- a/fs/bcachefs/subvolume_types.h +++ b/fs/bcachefs/subvolume_types.h @@ -9,13 +9,13 @@ typedef DARRAY(u32) snapshot_id_list; #define IS_ANCESTOR_BITMAP 128 struct snapshot_t { + bool live; u32 parent; u32 skip[3]; u32 depth; u32 children[2]; u32 subvol; /* Nonzero only if a subvolume points to this node: */ u32 tree; - u32 equiv; unsigned long is_ancestor[BITS_TO_LONGS(IS_ANCESTOR_BITMAP)]; }; diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 7c71594f6a8b..8037ccbacf6a 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -23,6 +23,7 @@ #include <linux/backing-dev.h> #include <linux/sort.h> +#include <linux/string_choices.h> static const struct blk_holder_ops bch2_sb_handle_bdev_ops = { }; @@ -41,7 +42,7 @@ static const struct bch2_metadata_version bch2_metadata_versions[] = { #undef x }; -void bch2_version_to_text(struct printbuf *out, unsigned v) +void bch2_version_to_text(struct printbuf *out, enum bcachefs_metadata_version v) { const char *str = "(unknown version)"; @@ -54,7 +55,7 @@ void bch2_version_to_text(struct printbuf *out, unsigned v) prt_printf(out, "%u.%u: %s", BCH_VERSION_MAJOR(v), BCH_VERSION_MINOR(v), str); } -unsigned bch2_latest_compatible_version(unsigned v) +enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version v) { if (!BCH_VERSION_MAJOR(v)) return v; @@ -68,6 +69,16 @@ unsigned bch2_latest_compatible_version(unsigned v) return v; } +void bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version) +{ + mutex_lock(&c->sb_lock); + SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb, + max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version)); + c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); +} + const char * const bch2_sb_fields[] = { #define x(name, nr) #name, BCH_SB_FIELDS() @@ -368,6 +379,12 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, return -BCH_ERR_invalid_sb_features; } + if (BCH_VERSION_MAJOR(le16_to_cpu(sb->version)) > BCH_VERSION_MAJOR(bcachefs_metadata_version_current) || + BCH_SB_VERSION_INCOMPAT(sb) > bcachefs_metadata_version_current) { + prt_printf(out, "Filesystem has incompatible version"); + return -BCH_ERR_invalid_sb_features; + } + block_size = le16_to_cpu(sb->block_size); if (block_size > PAGE_SECTORS) { @@ -406,6 +423,21 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, return -BCH_ERR_invalid_sb_time_precision; } + /* old versions didn't know to downgrade this field */ + if (BCH_SB_VERSION_INCOMPAT_ALLOWED(sb) > le16_to_cpu(sb->version)) + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(sb, le16_to_cpu(sb->version)); + + if (BCH_SB_VERSION_INCOMPAT(sb) > BCH_SB_VERSION_INCOMPAT_ALLOWED(sb)) { + prt_printf(out, "Invalid version_incompat "); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT(sb)); + prt_str(out, " > incompat_allowed "); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT_ALLOWED(sb)); + if (flags & BCH_VALIDATE_write) + return -BCH_ERR_invalid_sb_version; + else + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(sb, BCH_SB_VERSION_INCOMPAT(sb)); + } + if (!flags) { /* * Been seeing a bug where these are getting inexplicably @@ -428,6 +460,11 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, SET_BCH_SB_PROMOTE_WHOLE_EXTENTS(sb, true); } +#ifdef __KERNEL__ + if (!BCH_SB_SHARD_INUMS_NBITS(sb)) + SET_BCH_SB_SHARD_INUMS_NBITS(sb, ilog2(roundup_pow_of_two(num_online_cpus()))); +#endif + for (opt_id = 0; opt_id < bch2_opts_nr; opt_id++) { const struct bch_option *opt = bch2_opt_table + opt_id; @@ -519,6 +556,9 @@ static void bch2_sb_update(struct bch_fs *c) c->sb.uuid = src->uuid; c->sb.user_uuid = src->user_uuid; c->sb.version = le16_to_cpu(src->version); + c->sb.version_incompat = BCH_SB_VERSION_INCOMPAT(src); + c->sb.version_incompat_allowed + = BCH_SB_VERSION_INCOMPAT_ALLOWED(src); c->sb.version_min = le16_to_cpu(src->version_min); c->sb.version_upgrade_complete = BCH_SB_VERSION_UPGRADE_COMPLETE(src); c->sb.nr_devices = src->nr_devices; @@ -676,7 +716,8 @@ reread: } enum bch_csum_type csum_type = BCH_SB_CSUM_TYPE(sb->sb); - if (csum_type >= BCH_CSUM_NR) { + if (csum_type >= BCH_CSUM_NR || + bch2_csum_type_is_encryption(csum_type)) { prt_printf(err, "unknown checksum type %llu", BCH_SB_CSUM_TYPE(sb->sb)); return -BCH_ERR_invalid_sb_csum_type; } @@ -878,7 +919,7 @@ static void write_super_endio(struct bio *bio) ? BCH_MEMBER_ERROR_write : BCH_MEMBER_ERROR_read, "superblock %s error: %s", - bio_data_dir(bio) ? "write" : "read", + str_write_read(bio_data_dir(bio)), bch2_blk_status_to_str(bio->bi_status))) ca->sb_write_error = 1; @@ -891,14 +932,15 @@ static void read_back_super(struct bch_fs *c, struct bch_dev *ca) struct bch_sb *sb = ca->disk_sb.sb; struct bio *bio = ca->disk_sb.bio; + memset(ca->sb_read_scratch, 0, BCH_SB_READ_SCRATCH_BUF_SIZE); + bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ|REQ_SYNC|REQ_META); bio->bi_iter.bi_sector = le64_to_cpu(sb->layout.sb_offset[0]); bio->bi_end_io = write_super_endio; bio->bi_private = ca; - bch2_bio_map(bio, ca->sb_read_scratch, PAGE_SIZE); + bch2_bio_map(bio, ca->sb_read_scratch, BCH_SB_READ_SCRATCH_BUF_SIZE); - this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_sb], - bio_sectors(bio)); + this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_sb], bio_sectors(bio)); percpu_ref_get(&ca->io_ref); closure_bio_submit(bio, &c->sb_write); @@ -1042,9 +1084,16 @@ int bch2_write_super(struct bch_fs *c) ": Superblock write was silently dropped! (seq %llu expected %llu)", le64_to_cpu(ca->sb_read_scratch->seq), ca->disk_sb.seq); - bch2_fs_fatal_error(c, "%s", buf.buf); + + if (c->opts.errors != BCH_ON_ERROR_continue && + c->opts.errors != BCH_ON_ERROR_fix_safe) { + ret = -BCH_ERR_erofs_sb_err; + bch2_fs_fatal_error(c, "%s", buf.buf); + } else { + bch_err(c, "%s", buf.buf); + } + printbuf_exit(&buf); - ret = -BCH_ERR_erofs_sb_err; } if (le64_to_cpu(ca->sb_read_scratch->seq) > ca->disk_sb.seq) { @@ -1149,6 +1198,8 @@ bool bch2_check_version_downgrade(struct bch_fs *c) */ if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); + if (BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb) > bcachefs_metadata_version_current) + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb, bcachefs_metadata_version_current); if (c->sb.version > bcachefs_metadata_version_current) c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current); if (c->sb.version_min > bcachefs_metadata_version_current) @@ -1157,7 +1208,7 @@ bool bch2_check_version_downgrade(struct bch_fs *c) return ret; } -void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) +void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version, bool incompat) { lockdep_assert_held(&c->sb_lock); @@ -1167,6 +1218,10 @@ void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) c->disk_sb.sb->version = cpu_to_le16(new_version); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL); + + if (incompat) + SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb, + max(BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb), new_version)); } static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f, @@ -1331,6 +1386,14 @@ void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb, bch2_version_to_text(out, le16_to_cpu(sb->version)); prt_newline(out); + prt_printf(out, "Incompatible features allowed:\t"); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT_ALLOWED(sb)); + prt_newline(out); + + prt_printf(out, "Incompatible features in use:\t"); + bch2_version_to_text(out, BCH_SB_VERSION_INCOMPAT(sb)); + prt_newline(out); + prt_printf(out, "Version upgrade complete:\t"); bch2_version_to_text(out, BCH_SB_VERSION_UPGRADE_COMPLETE(sb)); prt_newline(out); diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h index fadd364e2802..f1ab4f943720 100644 --- a/fs/bcachefs/super-io.h +++ b/fs/bcachefs/super-io.h @@ -10,14 +10,29 @@ #include <asm/byteorder.h> +#define BCH_SB_READ_SCRATCH_BUF_SIZE 4096 + static inline bool bch2_version_compatible(u16 version) { return BCH_VERSION_MAJOR(version) <= BCH_VERSION_MAJOR(bcachefs_metadata_version_current) && version >= bcachefs_metadata_version_min; } -void bch2_version_to_text(struct printbuf *, unsigned); -unsigned bch2_latest_compatible_version(unsigned); +void bch2_version_to_text(struct printbuf *, enum bcachefs_metadata_version); +enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version); + +void bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version); + +static inline bool bch2_request_incompat_feature(struct bch_fs *c, + enum bcachefs_metadata_version version) +{ + if (unlikely(version > c->sb.version_incompat)) { + if (version > c->sb.version_incompat_allowed) + return false; + bch2_set_version_incompat(c, version); + } + return true; +} static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f) { @@ -92,7 +107,7 @@ static inline void bch2_check_set_feature(struct bch_fs *c, unsigned feat) } bool bch2_check_version_downgrade(struct bch_fs *); -void bch2_sb_upgrade(struct bch_fs *, unsigned); +void bch2_sb_upgrade(struct bch_fs *, unsigned, bool); void __bch2_sb_field_to_text(struct printbuf *, struct bch_sb *, struct bch_sb_field *); diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index a6ed9a0bf1c7..d97ea7bd1171 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -290,7 +290,7 @@ static void __bch2_fs_read_only(struct bch_fs *c) bch2_fs_journal_stop(&c->journal); - bch_info(c, "%sshutdown complete, journal seq %llu", + bch_info(c, "%sclean shutdown complete, journal seq %llu", test_bit(BCH_FS_clean_shutdown, &c->flags) ? "" : "un", c->journal.seq_ondisk); @@ -441,6 +441,8 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early) { int ret; + BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags)); + if (test_bit(BCH_FS_initial_gc_unfixed, &c->flags)) { bch_err(c, "cannot go rw, unfixed btree errors"); return -BCH_ERR_erofs_unfixed_errors; @@ -561,6 +563,7 @@ static void __bch2_fs_free(struct bch_fs *c) bch2_io_clock_exit(&c->io_clock[WRITE]); bch2_io_clock_exit(&c->io_clock[READ]); bch2_fs_compress_exit(c); + bch2_fs_btree_gc_exit(c); bch2_journal_keys_put_initial(c); bch2_find_btree_nodes_exit(&c->found_btree_nodes); BUG_ON(atomic_read(&c->journal_keys.ref)); @@ -584,7 +587,6 @@ static void __bch2_fs_free(struct bch_fs *c) #endif kfree(rcu_dereference_protected(c->disk_groups, 1)); kfree(c->journal_seq_blacklist_table); - kfree(c->unused_inode_hints); if (c->write_ref_wq) destroy_workqueue(c->write_ref_wq); @@ -766,21 +768,17 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) refcount_set(&c->ro_ref, 1); init_waitqueue_head(&c->ro_ref_wait); + spin_lock_init(&c->recovery_pass_lock); sema_init(&c->online_fsck_mutex, 1); - init_rwsem(&c->gc_lock); - mutex_init(&c->gc_gens_lock); - atomic_set(&c->journal_keys.ref, 1); - c->journal_keys.initial_ref_held = true; - for (i = 0; i < BCH_TIME_STAT_NR; i++) bch2_time_stats_init(&c->times[i]); - bch2_fs_gc_init(c); bch2_fs_copygc_init(c); bch2_fs_btree_key_cache_init_early(&c->btree_key_cache); bch2_fs_btree_iter_init_early(c); bch2_fs_btree_interior_update_init_early(c); + bch2_fs_journal_keys_init(c); bch2_fs_allocator_background_init(c); bch2_fs_allocator_foreground_init(c); bch2_fs_rebalance_init(c); @@ -809,9 +807,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) INIT_LIST_HEAD(&c->vfs_inodes_list); mutex_init(&c->vfs_inodes_lock); - c->copy_gc_enabled = 1; - c->rebalance.enabled = 1; - c->journal.flush_write_time = &c->times[BCH_TIME_journal_flush_write]; c->journal.noflush_write_time = &c->times[BCH_TIME_journal_noflush_write]; c->journal.flush_seq_time = &c->times[BCH_TIME_journal_flush_seq]; @@ -873,8 +868,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) (btree_blocks(c) + 1) * 2 * sizeof(struct sort_iter_set); - c->inode_shard_bits = ilog2(roundup_pow_of_two(num_possible_cpus())); - if (!(c->btree_update_wq = alloc_workqueue("bcachefs", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_UNBOUND, 512)) || !(c->btree_io_complete_wq = alloc_workqueue("bcachefs_btree_io", @@ -901,9 +894,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) !(c->online_reserved = alloc_percpu(u64)) || mempool_init_kvmalloc_pool(&c->btree_bounce_pool, 1, c->opts.btree_node_size) || - mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048) || - !(c->unused_inode_hints = kcalloc(1U << c->inode_shard_bits, - sizeof(u64), GFP_KERNEL))) { + mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048)) { ret = -BCH_ERR_ENOMEM_fs_other_alloc; goto err; } @@ -917,6 +908,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) bch2_fs_btree_cache_init(c) ?: bch2_fs_btree_key_cache_init(&c->btree_key_cache) ?: bch2_fs_btree_interior_update_init(c) ?: + bch2_fs_btree_gc_init(c) ?: bch2_fs_buckets_waiting_for_journal_init(c) ?: bch2_fs_btree_write_buffer_init(c) ?: bch2_fs_subvolumes_init(c) ?: @@ -1033,9 +1025,12 @@ int bch2_fs_start(struct bch_fs *c) bch2_dev_allocator_add(c, ca); bch2_recalc_capacity(c); + c->recovery_task = current; ret = BCH_SB_INITIALIZED(c->disk_sb.sb) ? bch2_fs_recovery(c) : bch2_fs_initialize(c); + c->recovery_task = NULL; + if (ret) goto err; @@ -1120,12 +1115,12 @@ static int bch2_dev_in_fs(struct bch_sb_handle *fs, prt_bdevname(&buf, fs->bdev); prt_char(&buf, ' '); - bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time));; + bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time)); prt_newline(&buf); prt_bdevname(&buf, sb->bdev); prt_char(&buf, ' '); - bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time));; + bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time)); prt_newline(&buf); if (!opts->no_splitbrain_check) @@ -1198,7 +1193,7 @@ static void bch2_dev_free(struct bch_dev *ca) free_percpu(ca->io_done); bch2_dev_buckets_free(ca); - free_page((unsigned long) ca->sb_read_scratch); + kfree(ca->sb_read_scratch); bch2_time_stats_quantiles_exit(&ca->io_latency[WRITE]); bch2_time_stats_quantiles_exit(&ca->io_latency[READ]); @@ -1309,8 +1304,6 @@ static struct bch_dev *__bch2_dev_alloc(struct bch_fs *c, init_completion(&ca->ref_completion); init_completion(&ca->io_ref_completion); - init_rwsem(&ca->bucket_lock); - INIT_WORK(&ca->io_error_work, bch2_io_error_work); bch2_time_stats_quantiles_init(&ca->io_latency[READ]); @@ -1337,7 +1330,7 @@ static struct bch_dev *__bch2_dev_alloc(struct bch_fs *c, if (percpu_ref_init(&ca->io_ref, bch2_dev_io_ref_complete, PERCPU_REF_INIT_DEAD, GFP_KERNEL) || - !(ca->sb_read_scratch = (void *) __get_free_page(GFP_KERNEL)) || + !(ca->sb_read_scratch = kmalloc(BCH_SB_READ_SCRATCH_BUF_SIZE, GFP_KERNEL)) || bch2_dev_buckets_alloc(c, ca) || !(ca->io_done = alloc_percpu(*ca->io_done))) goto err; @@ -1366,7 +1359,6 @@ static int bch2_dev_alloc(struct bch_fs *c, unsigned dev_idx) { struct bch_member member = bch2_sb_member_get(c->disk_sb.sb, dev_idx); struct bch_dev *ca = NULL; - int ret = 0; if (bch2_fs_init_fault("dev_alloc")) goto err; @@ -1378,10 +1370,8 @@ static int bch2_dev_alloc(struct bch_fs *c, unsigned dev_idx) ca->fs = c; bch2_dev_attach(c, ca, dev_idx); - return ret; + return 0; err: - if (ca) - bch2_dev_free(ca); return -BCH_ERR_ENOMEM_dev_alloc; } @@ -1751,11 +1741,6 @@ int bch2_dev_add(struct bch_fs *c, const char *path) if (ret) goto err; - ret = bch2_dev_journal_alloc(ca, true); - bch_err_msg(c, ret, "allocating journal"); - if (ret) - goto err; - down_write(&c->state_lock); mutex_lock(&c->sb_lock); @@ -1806,11 +1791,14 @@ int bch2_dev_add(struct bch_fs *c, const char *path) if (ret) goto err_late; - ca->new_fs_bucket_idx = 0; - if (ca->mi.state == BCH_MEMBER_STATE_rw) __bch2_dev_read_write(c, ca); + ret = bch2_dev_journal_alloc(ca, false); + bch_err_msg(c, ret, "allocating journal"); + if (ret) + goto err_late; + up_write(&c->state_lock); return 0; diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h index dada09331d2e..fa6d52216510 100644 --- a/fs/bcachefs/super.h +++ b/fs/bcachefs/super.h @@ -34,16 +34,6 @@ void bch2_fs_read_only(struct bch_fs *); int bch2_fs_read_write(struct bch_fs *); int bch2_fs_read_write_early(struct bch_fs *); -/* - * Only for use in the recovery/fsck path: - */ -static inline void bch2_fs_lazy_rw(struct bch_fs *c) -{ - if (!test_bit(BCH_FS_rw, &c->flags) && - !test_bit(BCH_FS_was_rw, &c->flags)) - bch2_fs_read_write_early(c); -} - void __bch2_fs_stop(struct bch_fs *); void bch2_fs_free(struct bch_fs *); void bch2_fs_stop(struct bch_fs *); diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index 03e59f86f360..a7eb1f511484 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -146,7 +146,7 @@ write_attribute(trigger_journal_writes); write_attribute(trigger_btree_cache_shrink); write_attribute(trigger_btree_key_cache_shrink); write_attribute(trigger_freelist_wakeup); -rw_attribute(gc_gens_pos); +read_attribute(gc_gens_pos); read_attribute(uuid); read_attribute(minor); @@ -203,7 +203,6 @@ read_attribute(disk_groups); read_attribute(has_data); read_attribute(alloc_debug); -read_attribute(accounting); read_attribute(usage_base); #define x(t, n, ...) read_attribute(t); @@ -211,12 +210,11 @@ BCH_PERSISTENT_COUNTERS() #undef x rw_attribute(discard); +read_attribute(state); rw_attribute(label); -rw_attribute(copy_gc_enabled); read_attribute(copy_gc_wait); -rw_attribute(rebalance_enabled); sysfs_pd_controller_attribute(rebalance); read_attribute(rebalance_status); @@ -237,11 +235,6 @@ write_attribute(perf_test); BCH_TIME_STATS() #undef x -static struct attribute sysfs_state_rw = { - .name = "state", - .mode = 0444, -}; - static size_t bch2_btree_cache_size(struct bch_fs *c) { struct btree_cache *bc = &c->btree_cache; @@ -302,7 +295,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c static void bch2_gc_gens_pos_to_text(struct printbuf *out, struct bch_fs *c) { - prt_printf(out, "%s: ", bch2_btree_id_str(c->gc_gens_btree)); + bch2_btree_id_to_text(out, c->gc_gens_btree); + prt_printf(out, ": "); bch2_bpos_to_text(out, c->gc_gens_pos); prt_printf(out, "\n"); } @@ -339,9 +333,6 @@ SHOW(bch2_fs) if (attr == &sysfs_gc_gens_pos) bch2_gc_gens_pos_to_text(out, c); - sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled); - - sysfs_printf(rebalance_enabled, "%i", c->rebalance.enabled); sysfs_pd_controller_show(rebalance, &c->rebalance.pd); /* XXX */ if (attr == &sysfs_copy_gc_wait) @@ -405,9 +396,6 @@ SHOW(bch2_fs) if (attr == &sysfs_alloc_debug) bch2_fs_alloc_debug_to_text(out, c); - if (attr == &sysfs_accounting) - bch2_fs_accounting_to_text(out, c); - if (attr == &sysfs_usage_base) bch2_fs_usage_base_to_text(out, c); @@ -418,23 +406,6 @@ STORE(bch2_fs) { struct bch_fs *c = container_of(kobj, struct bch_fs, kobj); - if (attr == &sysfs_copy_gc_enabled) { - ssize_t ret = strtoul_safe(buf, c->copy_gc_enabled) - ?: (ssize_t) size; - - if (c->copygc_thread) - wake_up_process(c->copygc_thread); - return ret; - } - - if (attr == &sysfs_rebalance_enabled) { - ssize_t ret = strtoul_safe(buf, c->rebalance.enabled) - ?: (ssize_t) size; - - rebalance_wakeup(c); - return ret; - } - sysfs_pd_controller_store(rebalance, &c->rebalance.pd); /* Debugging: */ @@ -534,15 +505,22 @@ SHOW(bch2_fs_counters) printbuf_tabstop_push(out, 32); - #define x(t, ...) \ + #define x(t, n, f, ...) \ if (attr == &sysfs_##t) { \ counter = percpu_u64_get(&c->counters[BCH_COUNTER_##t]);\ counter_since_mount = counter - c->counters_on_mount[BCH_COUNTER_##t];\ + if (f & TYPE_SECTORS) { \ + counter <<= 9; \ + counter_since_mount <<= 9; \ + } \ + \ prt_printf(out, "since mount:\t"); \ + (f & TYPE_COUNTER) ? prt_u64(out, counter_since_mount) :\ prt_human_readable_u64(out, counter_since_mount); \ prt_newline(out); \ \ prt_printf(out, "since filesystem creation:\t"); \ + (f & TYPE_COUNTER) ? prt_u64(out, counter) : \ prt_human_readable_u64(out, counter); \ prt_newline(out); \ } @@ -610,10 +588,8 @@ struct attribute *bch2_fs_internal_files[] = { &sysfs_gc_gens_pos, - &sysfs_copy_gc_enabled, &sysfs_copy_gc_wait, - &sysfs_rebalance_enabled, sysfs_pd_controller_files(rebalance), &sysfs_moving_ctxts, @@ -622,7 +598,6 @@ struct attribute *bch2_fs_internal_files[] = { &sysfs_disk_groups, &sysfs_alloc_debug, - &sysfs_accounting, &sysfs_usage_base, NULL }; @@ -682,6 +657,13 @@ STORE(bch2_fs_opts_dir) (id == Opt_compression && !c->opts.background_compression))) bch2_set_rebalance_needs_scan(c, 0); + if (v && id == Opt_rebalance_enabled) + rebalance_wakeup(c); + + if (v && id == Opt_copygc_enabled && + c->copygc_thread) + wake_up_process(c->copygc_thread); + ret = size; err: bch2_write_ref_put(c, BCH_WRITE_REF_sysfs); @@ -790,7 +772,7 @@ SHOW(bch2_dev) prt_char(out, '\n'); } - if (attr == &sysfs_state_rw) { + if (attr == &sysfs_state) { prt_string_option(out, bch2_member_states, ca->mi.state); prt_char(out, '\n'); } @@ -870,7 +852,7 @@ struct attribute *bch2_dev_files[] = { /* settings: */ &sysfs_discard, - &sysfs_state_rw, + &sysfs_state, &sysfs_label, &sysfs_has_data, diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c index fb5c1543e52f..6c6469814637 100644 --- a/fs/bcachefs/tests.c +++ b/fs/bcachefs/tests.c @@ -131,7 +131,7 @@ static int test_iterate(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(k.k->p.offset != i++); @@ -186,7 +186,7 @@ static int test_iterate_extents(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(bkey_start_offset(k.k) != i); @@ -242,7 +242,7 @@ static int test_iterate_slots(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(k.k->p.offset != i); @@ -259,7 +259,7 @@ static int test_iterate_slots(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), BTREE_ITER_slots, k, ({ if (i >= nr * 2) @@ -302,7 +302,7 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, ({ BUG_ON(bkey_start_offset(k.k) != i + 8); @@ -320,7 +320,7 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr) i = 0; ret = bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_extents, + for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), BTREE_ITER_slots, k, ({ if (i == nr) @@ -349,10 +349,10 @@ static int test_peek_end(struct bch_fs *c, u64 nr) bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), 0); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); bch2_trans_iter_exit(trans, &iter); @@ -369,10 +369,10 @@ static int test_peek_end_extents(struct bch_fs *c, u64 nr) bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(0, 0, U32_MAX), 0); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k); bch2_trans_iter_exit(trans, &iter); @@ -488,7 +488,7 @@ static int test_snapshot_filter(struct bch_fs *c, u32 snapid_lo, u32 snapid_hi) trans = bch2_trans_get(c); bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, SPOS(0, 0, snapid_lo), 0); - lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)))); + lockrestart_do(trans, bkey_err(k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)))); BUG_ON(k.k->p.snapshot != U32_MAX); @@ -672,7 +672,7 @@ static int __do_delete(struct btree_trans *trans, struct bpos pos) bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, pos, BTREE_ITER_intent); - k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)); + k = bch2_btree_iter_peek_max(&iter, POS(0, U64_MAX)); ret = bkey_err(k); if (ret) goto err; @@ -726,7 +726,7 @@ static int seq_insert(struct bch_fs *c, u64 nr) static int seq_lookup(struct bch_fs *c, u64 nr) { return bch2_trans_run(c, - for_each_btree_key_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_max(trans, iter, BTREE_ID_xattrs, SPOS(0, 0, U32_MAX), POS(0, U64_MAX), 0, k, 0)); diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index 5597b9d6297f..9d40b7d4ea29 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -199,6 +199,30 @@ DECLARE_EVENT_CLASS(bio, (unsigned long long)__entry->sector, __entry->nr_sector) ); +/* disk_accounting.c */ + +TRACE_EVENT(accounting_mem_insert, + TP_PROTO(struct bch_fs *c, const char *acc), + TP_ARGS(c, acc), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(unsigned, new_nr ) + __string(acc, acc ) + ), + + TP_fast_assign( + __entry->dev = c->dev; + __entry->new_nr = c->accounting.k.nr; + __assign_str(acc); + ), + + TP_printk("%d,%d entries %u added %s", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->new_nr, + __get_str(acc)) +); + /* fs.c: */ TRACE_EVENT(bch2_sync_fs, TP_PROTO(struct super_block *sb, int wait), @@ -848,8 +872,8 @@ TRACE_EVENT(move_data, TRACE_EVENT(evacuate_bucket, TP_PROTO(struct bch_fs *c, struct bpos *bucket, unsigned sectors, unsigned bucket_size, - u64 fragmentation, int ret), - TP_ARGS(c, bucket, sectors, bucket_size, fragmentation, ret), + int ret), + TP_ARGS(c, bucket, sectors, bucket_size, ret), TP_STRUCT__entry( __field(dev_t, dev ) @@ -857,7 +881,6 @@ TRACE_EVENT(evacuate_bucket, __field(u64, bucket ) __field(u32, sectors ) __field(u32, bucket_size ) - __field(u64, fragmentation ) __field(int, ret ) ), @@ -867,15 +890,14 @@ TRACE_EVENT(evacuate_bucket, __entry->bucket = bucket->offset; __entry->sectors = sectors; __entry->bucket_size = bucket_size; - __entry->fragmentation = fragmentation; __entry->ret = ret; ), - TP_printk("%d,%d %llu:%llu sectors %u/%u fragmentation %llu ret %i", + TP_printk("%d,%d %llu:%llu sectors %u/%u ret %i", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->member, __entry->bucket, __entry->sectors, __entry->bucket_size, - __entry->fragmentation, __entry->ret) + __entry->ret) ); TRACE_EVENT(copygc, @@ -1316,6 +1338,12 @@ TRACE_EVENT(trans_restart_key_cache_key_realloced, __entry->new_u64s) ); +DEFINE_EVENT(transaction_event, trans_restart_write_buffer_flush, + TP_PROTO(struct btree_trans *trans, + unsigned long caller_ip), + TP_ARGS(trans, caller_ip) +); + TRACE_EVENT(path_downgrade, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, @@ -1352,10 +1380,21 @@ TRACE_EVENT(path_downgrade, __entry->pos_snapshot) ); -DEFINE_EVENT(transaction_event, trans_restart_write_buffer_flush, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip), - TP_ARGS(trans, caller_ip) +TRACE_EVENT(key_cache_fill, + TP_PROTO(struct btree_trans *trans, const char *key), + TP_ARGS(trans, key), + + TP_STRUCT__entry( + __array(char, trans_fn, 32 ) + __string(key, key ) + ), + + TP_fast_assign( + strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); + __assign_str(key); + ), + + TP_printk("%s %s", __entry->trans_fn, __get_str(key)) ); TRACE_EVENT(write_buffer_flush, @@ -1414,6 +1453,24 @@ TRACE_EVENT(write_buffer_flush_slowpath, TP_printk("%zu/%zu", __entry->slowpath, __entry->total) ); +TRACE_EVENT(write_buffer_maybe_flush, + TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, const char *key), + TP_ARGS(trans, caller_ip, key), + + TP_STRUCT__entry( + __array(char, trans_fn, 32 ) + __field(unsigned long, caller_ip ) + __string(key, key ) + ), + + TP_fast_assign( + strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); + __assign_str(key); + ), + + TP_printk("%s %pS %s", __entry->trans_fn, (void *) __entry->caller_ip, __get_str(key)) +); + DEFINE_EVENT(fs_str, rebalance_extent, TP_PROTO(struct bch_fs *c, const char *str), TP_ARGS(c, str) diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index fb02c1c36004..1a1720116071 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -55,6 +55,16 @@ static inline size_t buf_pages(void *p, size_t len) PAGE_SIZE); } +static inline void *bch2_kvmalloc(size_t n, gfp_t flags) +{ + void *p = unlikely(n >= INT_MAX) + ? vmalloc(n) + : kvmalloc(n, flags & ~__GFP_ZERO); + if (p && (flags & __GFP_ZERO)) + memset(p, 0, n); + return p; +} + #define init_heap(heap, _size, gfp) \ ({ \ (heap)->nr = 0; \ @@ -317,6 +327,19 @@ do { \ _ptr ? container_of(_ptr, type, member) : NULL; \ }) +static inline struct list_head *list_pop(struct list_head *head) +{ + if (list_empty(head)) + return NULL; + + struct list_head *ret = head->next; + list_del_init(ret); + return ret; +} + +#define list_pop_entry(head, type, member) \ + container_of_or_null(list_pop(head), type, member) + /* Does linear interpolation between powers of two */ static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits) { @@ -696,4 +719,13 @@ static inline bool test_bit_le64(size_t bit, __le64 *addr) return (addr[bit / 64] & cpu_to_le64(BIT_ULL(bit % 64))) != 0; } +static inline void memcpy_swab(void *_dst, void *_src, size_t len) +{ + u8 *dst = _dst + len; + u8 *src = _src; + + while (len--) + *--dst = *src++; +} + #endif /* _BCACHEFS_UTIL_H */ diff --git a/fs/bcachefs/varint.c b/fs/bcachefs/varint.c index 6a78553d9b0c..6620ecae26af 100644 --- a/fs/bcachefs/varint.c +++ b/fs/bcachefs/varint.c @@ -9,6 +9,7 @@ #include <valgrind/memcheck.h> #endif +#include "errcode.h" #include "varint.h" /** @@ -53,7 +54,7 @@ int bch2_varint_decode(const u8 *in, const u8 *end, u64 *out) u64 v; if (unlikely(in + bytes > end)) - return -1; + return -BCH_ERR_varint_decode_error; if (likely(bytes < 9)) { __le64 v_le = 0; @@ -115,7 +116,7 @@ int bch2_varint_decode_fast(const u8 *in, const u8 *end, u64 *out) unsigned bytes = ffz(*in) + 1; if (unlikely(in + bytes > end)) - return -1; + return -BCH_ERR_varint_decode_error; if (likely(bytes < 9)) { v >>= bytes; diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index 952aca400faf..aed7c6984173 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -71,7 +71,7 @@ const struct bch_hash_desc bch2_xattr_hash_desc = { }; int bch2_xattr_validate(struct bch_fs *c, struct bkey_s_c k, - enum bch_validate_flags flags) + struct bkey_validate_context from) { struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k); unsigned val_u64s = xattr_val_u64s(xattr.v->x_name_len, @@ -309,7 +309,7 @@ ssize_t bch2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) u64 offset = 0, inum = inode->ei_inode.bi_inum; int ret = bch2_trans_run(c, - for_each_btree_key_in_subvolume_upto(trans, iter, BTREE_ID_xattrs, + for_each_btree_key_in_subvolume_max(trans, iter, BTREE_ID_xattrs, POS(inum, offset), POS(inum, U64_MAX), inode->ei_inum.subvol, 0, k, ({ @@ -565,13 +565,6 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler, ret = bch2_write_inode(c, inode, inode_opt_set_fn, &s, 0); err: mutex_unlock(&inode->ei_update_lock); - - if (value && - (opt_id == Opt_background_target || - opt_id == Opt_background_compression || - (opt_id == Opt_compression && !inode_opt_get(c, &inode->ei_inode, background_compression)))) - bch2_set_rebalance_needs_scan(c, inode->ei_inode.bi_inum); - err_class_exit: return bch2_err_class(ret); } @@ -609,7 +602,7 @@ static const struct xattr_handler bch_xattr_bcachefs_effective_handler = { #endif /* NO_BCACHEFS_FS */ -const struct xattr_handler *bch2_xattr_handlers[] = { +const struct xattr_handler * const bch2_xattr_handlers[] = { &bch_xattr_user_handler, &bch_xattr_trusted_handler, &bch_xattr_security_handler, diff --git a/fs/bcachefs/xattr.h b/fs/bcachefs/xattr.h index c188a5ad64ce..132fbbd15a66 100644 --- a/fs/bcachefs/xattr.h +++ b/fs/bcachefs/xattr.h @@ -6,7 +6,8 @@ extern const struct bch_hash_desc bch2_xattr_hash_desc; -int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); +int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, + struct bkey_validate_context); void bch2_xattr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_xattr ((struct bkey_ops) { \ @@ -44,6 +45,6 @@ int bch2_xattr_set(struct btree_trans *, subvol_inum, ssize_t bch2_xattr_list(struct dentry *, char *, size_t); -extern const struct xattr_handler *bch2_xattr_handlers[]; +extern const struct xattr_handler * const bch2_xattr_handlers[]; #endif /* _BCACHEFS_XATTR_H */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 106f0e8af177..8054f44d39cf 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1257,7 +1257,7 @@ out_free_interp: } reloc_func_desc = interp_load_addr; - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); kfree(interp_elf_ex); @@ -1354,7 +1354,7 @@ out_free_dentry: kfree(interp_elf_ex); kfree(interp_elf_phdata); out_free_file: - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); if (interpreter) fput(interpreter); out_free_ph: diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index f1a7c4875c4a..c13ee8180b17 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -394,7 +394,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) goto error; } - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); interpreter = NULL; } @@ -467,7 +467,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) error: if (interpreter) { - allow_write_access(interpreter); + exe_file_allow_write_access(interpreter); fput(interpreter); } kfree(interpreter_name); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 390808ce935d..b5b5ca1a44f7 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -478,7 +478,7 @@ static int load_flat_file(struct linux_binprm *bprm, * 28 bits (256 MB) is way more than reasonable in this case. * If some top bits are set we have probable binary corruption. */ - if ((text_len | data_len | bss_len | stack_len | full_data) >> 28) { + if ((text_len | data_len | bss_len | stack_len | relocs | full_data) >> 28) { pr_err("bad header\n"); ret = -ENOEXEC; goto err; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 6a3a16f91051..5a7ebd160724 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -1001,7 +1001,7 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc) /* * If it turns out that most user namespaces actually want to * register their own binary type handler and therefore all - * create their own separate binfm_misc mounts we should + * create their own separate binfmt_misc mounts we should * consider turning this into a kmem cache. */ misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 3cfc440c636c..2d5f0482678b 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -44,4 +44,4 @@ btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \ tests/extent-buffer-tests.o tests/btrfs-tests.o \ tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o \ tests/free-space-tree-tests.o tests/extent-map-tests.o \ - tests/raid-stripe-tree-tests.o + tests/raid-stripe-tree-tests.o tests/delayed-refs-tests.o diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 361a866c1995..a4c51600a408 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -18,7 +18,7 @@ enum { }; #define NO_THRESHOLD (-1) -#define DFT_THRESHOLD (32) +#define DEFAULT_THRESHOLD (32) struct btrfs_workqueue { struct workqueue_struct *normal_wq; @@ -94,9 +94,9 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, ret->limit_active = limit_active; if (thresh == 0) - thresh = DFT_THRESHOLD; + thresh = DEFAULT_THRESHOLD; /* For low threshold, disabling threshold is a better choice */ - if (thresh < DFT_THRESHOLD) { + if (thresh < DEFAULT_THRESHOLD) { ret->current_active = limit_active; ret->thresh = NO_THRESHOLD; } else { diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 04f53ca548e1..3d3923cfc357 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -250,6 +250,21 @@ static int prelim_ref_compare(const struct prelim_ref *ref1, return 0; } +static int prelim_ref_rb_add_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct prelim_ref *ref_new = + rb_entry(new, struct prelim_ref, rbnode); + const struct prelim_ref *ref_exist = + rb_entry(exist, struct prelim_ref, rbnode); + + /* + * prelim_ref_compare() expects the first parameter as the existing one, + * different from the rb_find_add_cached() order. + */ + return prelim_ref_compare(ref_exist, ref_new); +} + static void update_share_count(struct share_check *sc, int oldcount, int newcount, const struct prelim_ref *newref) { @@ -278,55 +293,39 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, struct share_check *sc) { struct rb_root_cached *root; - struct rb_node **p; - struct rb_node *parent = NULL; - struct prelim_ref *ref; - int result; - bool leftmost = true; + struct rb_node *exist; root = &preftree->root; - p = &root->rb_root.rb_node; + exist = rb_find_add_cached(&newref->rbnode, root, prelim_ref_rb_add_cmp); + if (exist) { + struct prelim_ref *ref = rb_entry(exist, struct prelim_ref, rbnode); + /* Identical refs, merge them and free @newref */ + struct extent_inode_elem *eie = ref->inode_list; - while (*p) { - parent = *p; - ref = rb_entry(parent, struct prelim_ref, rbnode); - result = prelim_ref_compare(ref, newref); - if (result < 0) { - p = &(*p)->rb_left; - } else if (result > 0) { - p = &(*p)->rb_right; - leftmost = false; - } else { - /* Identical refs, merge them and free @newref */ - struct extent_inode_elem *eie = ref->inode_list; - - while (eie && eie->next) - eie = eie->next; + while (eie && eie->next) + eie = eie->next; - if (!eie) - ref->inode_list = newref->inode_list; - else - eie->next = newref->inode_list; - trace_btrfs_prelim_ref_merge(fs_info, ref, newref, - preftree->count); - /* - * A delayed ref can have newref->count < 0. - * The ref->count is updated to follow any - * BTRFS_[ADD|DROP]_DELAYED_REF actions. - */ - update_share_count(sc, ref->count, - ref->count + newref->count, newref); - ref->count += newref->count; - free_pref(newref); - return; - } + if (!eie) + ref->inode_list = newref->inode_list; + else + eie->next = newref->inode_list; + trace_btrfs_prelim_ref_merge(fs_info, ref, newref, + preftree->count); + /* + * A delayed ref can have newref->count < 0. + * The ref->count is updated to follow any + * BTRFS_[ADD|DROP]_DELAYED_REF actions. + */ + update_share_count(sc, ref->count, + ref->count + newref->count, newref); + ref->count += newref->count; + free_pref(newref); + return; } update_share_count(sc, 0, newref->count, newref); preftree->count++; trace_btrfs_prelim_ref_insert(fs_info, newref, NULL, preftree->count); - rb_link_node(&newref->rbnode, parent, p); - rb_insert_color_cached(&newref->rbnode, root, leftmost); } /* @@ -3022,9 +3021,6 @@ void btrfs_backref_init_cache(struct btrfs_fs_info *fs_info, cache->rb_root = RB_ROOT; for (i = 0; i < BTRFS_MAX_LEVEL; i++) INIT_LIST_HEAD(&cache->pending[i]); - INIT_LIST_HEAD(&cache->changed); - INIT_LIST_HEAD(&cache->detached); - INIT_LIST_HEAD(&cache->leaves); INIT_LIST_HEAD(&cache->pending_edge); INIT_LIST_HEAD(&cache->useless_node); cache->fs_info = fs_info; @@ -3132,29 +3128,17 @@ void btrfs_backref_drop_node(struct btrfs_backref_cache *tree, void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { - struct btrfs_backref_node *upper; struct btrfs_backref_edge *edge; if (!node) return; - BUG_ON(!node->lowest && !node->detached); while (!list_empty(&node->upper)) { edge = list_entry(node->upper.next, struct btrfs_backref_edge, list[LOWER]); - upper = edge->node[UPPER]; list_del(&edge->list[LOWER]); list_del(&edge->list[UPPER]); btrfs_backref_free_edge(cache, edge); - - /* - * Add the node to leaf node list if no other child block - * cached. - */ - if (list_empty(&upper->lower)) { - list_add_tail(&upper->lower, &cache->leaves); - upper->lowest = 1; - } } btrfs_backref_drop_node(cache, node); @@ -3166,33 +3150,13 @@ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, void btrfs_backref_release_cache(struct btrfs_backref_cache *cache) { struct btrfs_backref_node *node; - int i; - - while (!list_empty(&cache->detached)) { - node = list_entry(cache->detached.next, - struct btrfs_backref_node, list); - btrfs_backref_cleanup_node(cache, node); - } - while (!list_empty(&cache->leaves)) { - node = list_entry(cache->leaves.next, - struct btrfs_backref_node, lower); + while ((node = rb_entry_safe(rb_first(&cache->rb_root), + struct btrfs_backref_node, rb_node))) btrfs_backref_cleanup_node(cache, node); - } - for (i = 0; i < BTRFS_MAX_LEVEL; i++) { - while (!list_empty(&cache->pending[i])) { - node = list_first_entry(&cache->pending[i], - struct btrfs_backref_node, - list); - btrfs_backref_cleanup_node(cache, node); - } - } ASSERT(list_empty(&cache->pending_edge)); ASSERT(list_empty(&cache->useless_node)); - ASSERT(list_empty(&cache->changed)); - ASSERT(list_empty(&cache->detached)); - ASSERT(RB_EMPTY_ROOT(&cache->rb_root)); ASSERT(!cache->nr_nodes); ASSERT(!cache->nr_edges); } @@ -3316,8 +3280,12 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, root = btrfs_get_fs_root(fs_info, ref_key->offset, false); if (IS_ERR(root)) return PTR_ERR(root); - if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) - cur->cowonly = 1; + + /* We shouldn't be using backref cache for non-shareable roots. */ + if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { + btrfs_put_root(root); + return -EUCLEAN; + } if (btrfs_root_level(&root->root_item) == cur->level) { /* Tree root */ @@ -3403,8 +3371,15 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, goto out; } upper->owner = btrfs_header_owner(eb); - if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) - upper->cowonly = 1; + + /* We shouldn't be using backref cache for non shareable roots. */ + if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { + btrfs_put_root(root); + btrfs_backref_free_edge(cache, edge); + btrfs_backref_free_node(cache, upper); + ret = -EUCLEAN; + goto out; + } /* * If we know the block isn't shared we can avoid @@ -3595,15 +3570,9 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, ASSERT(start->checked); - /* Insert this node to cache if it's not COW-only */ - if (!start->cowonly) { - rb_node = rb_simple_insert(&cache->rb_root, start->bytenr, - &start->rb_node); - if (rb_node) - btrfs_backref_panic(cache->fs_info, start->bytenr, - -EEXIST); - list_add_tail(&start->lower, &cache->leaves); - } + rb_node = rb_simple_insert(&cache->rb_root, start->bytenr, &start->rb_node); + if (rb_node) + btrfs_backref_panic(cache->fs_info, start->bytenr, -EEXIST); /* * Use breadth first search to iterate all related edges. @@ -3642,11 +3611,6 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, * parents have already been linked. */ if (!RB_EMPTY_NODE(&upper->rb_node)) { - if (upper->lowest) { - list_del_init(&upper->lower); - upper->lowest = 0; - } - list_add_tail(&edge->list[UPPER], &upper->lower); continue; } @@ -3657,23 +3621,13 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, return -EUCLEAN; } - /* Sanity check, COW-only node has non-COW-only parent */ - if (start->cowonly != upper->cowonly) { - ASSERT(0); + rb_node = rb_simple_insert(&cache->rb_root, upper->bytenr, + &upper->rb_node); + if (unlikely(rb_node)) { + btrfs_backref_panic(cache->fs_info, upper->bytenr, -EEXIST); return -EUCLEAN; } - /* Only cache non-COW-only (subvolume trees) tree blocks */ - if (!upper->cowonly) { - rb_node = rb_simple_insert(&cache->rb_root, upper->bytenr, - &upper->rb_node); - if (rb_node) { - btrfs_backref_panic(cache->fs_info, - upper->bytenr, -EEXIST); - return -EUCLEAN; - } - } - list_add_tail(&edge->list[UPPER], &upper->lower); /* diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index e8c22cccb5c1..74e614031274 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -318,6 +318,12 @@ struct btrfs_backref_node { u64 bytenr; }; /* Use rb_simple_node for search/insert */ + /* + * This is a sanity check, whenever we COW a block we will update + * new_bytenr with it's current location, and we will check this in + * various places to validate that the cache makes sense, it shouldn't + * be used for anything else. + */ u64 new_bytenr; /* Objectid of tree block owner, can be not uptodate */ u64 owner; @@ -335,10 +341,6 @@ struct btrfs_backref_node { struct extent_buffer *eb; /* Level of the tree block */ unsigned int level:8; - /* Is the block in a non-shareable tree */ - unsigned int cowonly:1; - /* 1 if no child node is in the cache */ - unsigned int lowest:1; /* Is the extent buffer locked */ unsigned int locked:1; /* Has the block been processed */ @@ -391,12 +393,6 @@ struct btrfs_backref_cache { * level blocks may not reflect the new location */ struct list_head pending[BTRFS_MAX_LEVEL]; - /* List of backref nodes with no child node */ - struct list_head leaves; - /* List of blocks that have been COWed in current transaction */ - struct list_head changed; - /* List of detached backref node. */ - struct list_head detached; u64 last_trans; diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 1f216d07eff6..bc2555c44a12 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -81,6 +81,9 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS, &btrfs_clone_bioset); + if (IS_ERR(bio)) + return ERR_CAST(bio); + bbio = btrfs_bio(bio); btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); bbio->inode = orig_bbio->inode; @@ -355,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -398,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -412,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -450,6 +453,14 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio) (unsigned long)dev->bdev->bd_dev, btrfs_dev_name(dev), dev->devid, bio->bi_iter.bi_size); + /* + * Track reads if tracking is enabled; ignore I/O operations before the + * filesystem is fully initialized. + */ + if (dev->fs_devices->collect_fs_stats && bio_op(bio) == REQ_OP_READ && dev->fs_info) + percpu_counter_add(&dev->fs_info->stats_read_blocks, + bio->bi_iter.bi_size >> dev->fs_info->sectorsize_bits); + if (bio->bi_opf & REQ_BTRFS_CGROUP_PUNT) blkcg_punt_bio_submit(bio); else @@ -649,8 +660,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } @@ -678,7 +695,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) &bioc, &smap, &mirror_num); if (error) { ret = errno_to_blk_status(error); - goto fail; + btrfs_bio_counter_dec(fs_info); + goto end_bbio; } map_length = min(map_length, length); @@ -686,7 +704,15 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) map_length = btrfs_append_map_length(bbio, map_length); if (map_length < length) { - bbio = btrfs_split_bio(fs_info, bbio, map_length); + struct btrfs_bio *split; + + split = btrfs_split_bio(fs_info, bbio, map_length); + if (IS_ERR(split)) { + ret = errno_to_blk_status(PTR_ERR(split)); + btrfs_bio_counter_dec(fs_info); + goto end_bbio; + } + bbio = split; bio = &bbio->bio; } @@ -707,8 +733,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) bio->bi_opf |= REQ_OP_ZONE_APPEND; } - if (is_data_bbio(bbio) && bioc && - btrfs_need_stripe_tree_update(bioc->fs_info, bioc->map_type)) { + if (is_data_bbio(bbio) && bioc && bioc->use_rst) { /* * No locking for the list update, as we only add to * the list in the I/O submission path, and list @@ -760,6 +785,7 @@ fail: btrfs_bio_end_io(remaining, ret); } +end_bbio: btrfs_bio_end_io(bbio, ret); /* Do not submit another chunk */ return true; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 4427c1b835e8..c0a8f7d92acc 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -173,43 +173,41 @@ void btrfs_put_block_group(struct btrfs_block_group *cache) } } +static int btrfs_bg_start_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct btrfs_block_group *new_bg = + rb_entry(new, struct btrfs_block_group, cache_node); + const struct btrfs_block_group *exist_bg = + rb_entry(exist, struct btrfs_block_group, cache_node); + + if (new_bg->start < exist_bg->start) + return -1; + if (new_bg->start > exist_bg->start) + return 1; + return 0; +} + /* * This adds the block group to the fs_info rb tree for the block group cache */ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, struct btrfs_block_group *block_group) { - struct rb_node **p; - struct rb_node *parent = NULL; - struct btrfs_block_group *cache; - bool leftmost = true; + struct rb_node *exist; + int ret = 0; ASSERT(block_group->length != 0); write_lock(&info->block_group_cache_lock); - p = &info->block_group_cache_tree.rb_root.rb_node; - - while (*p) { - parent = *p; - cache = rb_entry(parent, struct btrfs_block_group, cache_node); - if (block_group->start < cache->start) { - p = &(*p)->rb_left; - } else if (block_group->start > cache->start) { - p = &(*p)->rb_right; - leftmost = false; - } else { - write_unlock(&info->block_group_cache_lock); - return -EEXIST; - } - } - - rb_link_node(&block_group->cache_node, parent, p); - rb_insert_color_cached(&block_group->cache_node, - &info->block_group_cache_tree, leftmost); + exist = rb_find_add_cached(&block_group->cache_node, + &info->block_group_cache_tree, btrfs_bg_start_cmp); + if (exist) + ret = -EEXIST; write_unlock(&info->block_group_cache_lock); - return 0; + return ret; } /* @@ -1223,7 +1221,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, block_group->space_info->total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); - btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info, + btrfs_space_info_update_bytes_zone_unusable(block_group->space_info, -block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; @@ -1396,8 +1394,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes to readonly */ sinfo->bytes_readonly += cache->zone_unusable; - btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, - -cache->zone_unusable); + btrfs_space_info_update_bytes_zone_unusable(sinfo, -cache->zone_unusable); cache->zone_unusable = 0; } cache->ro++; @@ -1645,8 +1642,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&space_info->lock); spin_lock(&block_group->lock); - btrfs_space_info_update_bytes_pinned(fs_info, space_info, - -block_group->pinned); + btrfs_space_info_update_bytes_pinned(space_info, -block_group->pinned); space_info->bytes_readonly += block_group->pinned; block_group->pinned = 0; @@ -2672,7 +2668,6 @@ static int insert_dev_extent(struct btrfs_trans_handle *trans, btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset); btrfs_set_dev_extent_length(leaf, extent, num_bytes); - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -3060,8 +3055,7 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) (cache->alloc_offset - cache->used - cache->pinned - cache->reserved) + (cache->length - cache->zone_capacity); - btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, - cache->zone_unusable); + btrfs_space_info_update_bytes_zone_unusable(sinfo, cache->zone_unusable); sinfo->bytes_readonly -= cache->zone_unusable; } num_bytes = cache->length - cache->reserved - @@ -3123,7 +3117,6 @@ static int update_block_group_item(struct btrfs_trans_handle *trans, cache->global_root_id); btrfs_set_stack_block_group_flags(&bgi, cache->flags); write_extent_buffer(leaf, &bgi, bi, sizeof(bgi)); - btrfs_mark_buffer_dirty(trans, leaf); fail: btrfs_release_path(path); /* @@ -3699,7 +3692,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; - btrfs_space_info_update_bytes_pinned(info, space_info, num_bytes); + btrfs_space_info_update_bytes_pinned(space_info, num_bytes); space_info->bytes_used -= num_bytes; space_info->disk_used -= num_bytes * factor; if (READ_ONCE(space_info->periodic_reclaim)) @@ -3781,8 +3774,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache, space_info->bytes_reserved += num_bytes; trace_btrfs_space_reservation(cache->fs_info, "space_info", space_info->flags, num_bytes, 1); - btrfs_space_info_update_bytes_may_use(cache->fs_info, - space_info, -ram_bytes); + btrfs_space_info_update_bytes_may_use(space_info, -ram_bytes); if (delalloc) cache->delalloc_bytes += num_bytes; diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index a07b9594dc70..3f3608299c0b 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -150,9 +150,7 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info, spin_unlock(&dest->lock); } if (num_bytes) - btrfs_space_info_free_bytes_may_use(fs_info, - space_info, - num_bytes); + btrfs_space_info_free_bytes_may_use(space_info, num_bytes); } if (qgroup_to_release_ret) *qgroup_to_release_ret = qgroup_to_release; @@ -383,13 +381,11 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info) if (block_rsv->reserved < block_rsv->size) { num_bytes = block_rsv->size - block_rsv->reserved; - btrfs_space_info_update_bytes_may_use(fs_info, sinfo, - num_bytes); + btrfs_space_info_update_bytes_may_use(sinfo, num_bytes); block_rsv->reserved = block_rsv->size; } else if (block_rsv->reserved > block_rsv->size) { num_bytes = block_rsv->reserved - block_rsv->size; - btrfs_space_info_update_bytes_may_use(fs_info, sinfo, - -num_bytes); + btrfs_space_info_update_bytes_may_use(sinfo, -num_bytes); block_rsv->reserved = block_rsv->size; btrfs_try_granting_tickets(fs_info, sinfo); } diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index aa1f55cd81b7..b2fa33911c28 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -526,7 +526,7 @@ bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev, u32 bio_offset, struct bio_vec *bv); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, struct btrfs_file_extent *file_extent, - bool nowait, bool strict); + bool nowait); void btrfs_del_delalloc_inode(struct btrfs_inode *inode); struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 693dc27ffb89..92071ca0655f 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -37,19 +37,6 @@ static int push_node_left(struct btrfs_trans_handle *trans, static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); - -static const struct btrfs_csums { - u16 size; - const char name[10]; - const char driver[12]; -} btrfs_csums[] = { - [BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" }, - [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" }, - [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" }, - [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b", - .driver = "blake2b-256" }, -}; - /* * The leaf data grows from end-to-front in the node. this returns the address * of the start of the last item, which is the stop of the leaf data stack. @@ -148,44 +135,6 @@ static inline void copy_leaf_items(const struct extent_buffer *dst, nr_items * sizeof(struct btrfs_item)); } -/* This exists for btrfs-progs usages. */ -u16 btrfs_csum_type_size(u16 type) -{ - return btrfs_csums[type].size; -} - -int btrfs_super_csum_size(const struct btrfs_super_block *s) -{ - u16 t = btrfs_super_csum_type(s); - /* - * csum type is validated at mount time - */ - return btrfs_csum_type_size(t); -} - -const char *btrfs_super_csum_name(u16 csum_type) -{ - /* csum type is validated at mount time */ - return btrfs_csums[csum_type].name; -} - -/* - * Return driver name if defined, otherwise the name that's also a valid driver - * name - */ -const char *btrfs_super_csum_driver(u16 csum_type) -{ - /* csum type is validated at mount time */ - return btrfs_csums[csum_type].driver[0] ? - btrfs_csums[csum_type].driver : - btrfs_csums[csum_type].name; -} - -size_t __attribute_const__ btrfs_get_num_csums(void) -{ - return ARRAY_SIZE(btrfs_csums); -} - struct btrfs_path *btrfs_alloc_path(void) { might_sleep(); @@ -226,22 +175,6 @@ noinline void btrfs_release_path(struct btrfs_path *p) } /* - * We want the transaction abort to print stack trace only for errors where the - * cause could be a bug, eg. due to ENOSPC, and not for common errors that are - * caused by external factors. - */ -bool __cold abort_should_print_stack(int error) -{ - switch (error) { - case -EIO: - case -EROFS: - case -ENOMEM: - return false; - } - return true; -} - -/* * safely gets a reference on the root node of a tree. A lock * is not taken, so a concurrent writer may put a different node * at the root of the tree. See btrfs_lock_root_node for the @@ -654,6 +587,8 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, goto error_unlock_cow; } } + + trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); @@ -710,7 +645,6 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; - int ret; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); @@ -751,12 +685,8 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); - ret = btrfs_force_cow_block(trans, root, buf, parent, parent_slot, - cow_ret, search_start, 0, nest); - - trace_btrfs_cow_block(root, buf, *cow_ret); - - return ret; + return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, + cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); @@ -3903,6 +3833,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY && + key.type != BTRFS_RAID_STRIPE_KEY && key.type != BTRFS_EXTENT_CSUM_KEY); if (btrfs_leaf_free_space(leaf) >= ins_len) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c70..1096a80a64e7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -7,7 +7,6 @@ #define BTRFS_CTREE_H #include "linux/cleanup.h" -#include <linux/pagemap.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/mutex.h> @@ -371,6 +370,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ @@ -487,20 +505,6 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item); } -#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \ - ((bytes) >> (fs_info)->sectorsize_bits) - -static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) -{ - return mapping_gfp_constraint(mapping, ~__GFP_FS); -} - -void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); -int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, - u64 num_bytes, u64 *actual_bytes); -int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range); - -/* ctree.c */ int __init btrfs_ctree_init(void); void __cold btrfs_ctree_exit(void); @@ -737,18 +741,4 @@ static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root) return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID; } -u16 btrfs_csum_type_size(u16 type); -int btrfs_super_csum_size(const struct btrfs_super_block *s); -const char *btrfs_super_csum_name(u16 csum_type); -const char *btrfs_super_csum_driver(u16 csum_type); -size_t __attribute_const__ btrfs_get_num_csums(void); - -/* - * We use folio flag owner_2 to indicate there is an ordered extent with - * unfinished IO. - */ -#define folio_test_ordered(folio) folio_test_owner_2(folio) -#define folio_set_ordered(folio) folio_set_owner_2(folio) -#define folio_clear_ordered(folio) folio_clear_owner_2(folio) - #endif diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 7aa8a395d838..88e900e5a43d 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -176,7 +176,7 @@ void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info, ASSERT(IS_ALIGNED(len, fs_info->sectorsize)); data_sinfo = fs_info->data_sinfo; - btrfs_space_info_free_bytes_may_use(fs_info, data_sinfo, len); + btrfs_space_info_free_bytes_may_use(data_sinfo, len); } /* diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 508bdbae29a0..0b4933c6a889 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -366,40 +366,35 @@ static struct btrfs_delayed_item *__btrfs_lookup_delayed_item( return NULL; } +static int btrfs_delayed_item_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct btrfs_delayed_item *new_item = + rb_entry(new, struct btrfs_delayed_item, rb_node); + const struct btrfs_delayed_item *exist_item = + rb_entry(exist, struct btrfs_delayed_item, rb_node); + + if (new_item->index < exist_item->index) + return -1; + if (new_item->index > exist_item->index) + return 1; + return 0; +} + static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node, struct btrfs_delayed_item *ins) { - struct rb_node **p, *node; - struct rb_node *parent_node = NULL; struct rb_root_cached *root; - struct btrfs_delayed_item *item; - bool leftmost = true; + struct rb_node *exist; if (ins->type == BTRFS_DELAYED_INSERTION_ITEM) root = &delayed_node->ins_root; else root = &delayed_node->del_root; - p = &root->rb_root.rb_node; - node = &ins->rb_node; - - while (*p) { - parent_node = *p; - item = rb_entry(parent_node, struct btrfs_delayed_item, - rb_node); - - if (item->index < ins->index) { - p = &(*p)->rb_right; - leftmost = false; - } else if (item->index > ins->index) { - p = &(*p)->rb_left; - } else { - return -EEXIST; - } - } - - rb_link_node(node, parent_node, p); - rb_insert_color_cached(node, root, leftmost); + exist = rb_find_add_cached(&ins->rb_node, root, btrfs_delayed_item_cmp); + if (exist) + return -EEXIST; if (ins->type == BTRFS_DELAYED_INSERTION_ITEM && ins->index >= delayed_node->index_cnt) @@ -1038,7 +1033,6 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans, struct btrfs_inode_item); write_extent_buffer(leaf, &node->inode_item, (unsigned long)inode_item, sizeof(struct btrfs_inode_item)); - btrfs_mark_buffer_dirty(trans, leaf); if (!test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags)) goto out; @@ -1561,8 +1555,7 @@ release_node: return ret; } -static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_node *node, +static int btrfs_delete_delayed_insertion_item(struct btrfs_delayed_node *node, u64 index) { struct btrfs_delayed_item *item; @@ -1620,7 +1613,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, if (IS_ERR(node)) return PTR_ERR(node); - ret = btrfs_delete_delayed_insertion_item(trans->fs_info, node, index); + ret = btrfs_delete_delayed_insertion_item(node, index); if (!ret) goto end; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 0d878dbbabba..98c5b61dabe8 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -93,6 +93,9 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) u64 num_bytes; u64 reserved_bytes; + if (btrfs_is_testing(fs_info)) + return; + num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, trans->delayed_ref_updates); num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info, trans->delayed_ref_csum_deletions); @@ -254,7 +257,7 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); if (to_free > 0) - btrfs_space_info_free_bytes_may_use(fs_info, space_info, to_free); + btrfs_space_info_free_bytes_may_use(space_info, to_free); if (refilled_bytes > 0) trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, @@ -265,8 +268,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, /* * compare two delayed data backrefs with same bytenr and type */ -static int comp_data_refs(struct btrfs_delayed_ref_node *ref1, - struct btrfs_delayed_ref_node *ref2) +static int comp_data_refs(const struct btrfs_delayed_ref_node *ref1, + const struct btrfs_delayed_ref_node *ref2) { if (ref1->data_ref.objectid < ref2->data_ref.objectid) return -1; @@ -279,8 +282,8 @@ static int comp_data_refs(struct btrfs_delayed_ref_node *ref1, return 0; } -static int comp_refs(struct btrfs_delayed_ref_node *ref1, - struct btrfs_delayed_ref_node *ref2, +static int comp_refs(const struct btrfs_delayed_ref_node *ref1, + const struct btrfs_delayed_ref_node *ref2, bool check_seq) { int ret = 0; @@ -314,34 +317,25 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1, return 0; } +static int cmp_refs_node(const struct rb_node *new, const struct rb_node *exist) +{ + const struct btrfs_delayed_ref_node *new_node = + rb_entry(new, struct btrfs_delayed_ref_node, ref_node); + const struct btrfs_delayed_ref_node *exist_node = + rb_entry(exist, struct btrfs_delayed_ref_node, ref_node); + + return comp_refs(new_node, exist_node, true); +} + static struct btrfs_delayed_ref_node* tree_insert(struct rb_root_cached *root, struct btrfs_delayed_ref_node *ins) { - struct rb_node **p = &root->rb_root.rb_node; struct rb_node *node = &ins->ref_node; - struct rb_node *parent_node = NULL; - struct btrfs_delayed_ref_node *entry; - bool leftmost = true; - - while (*p) { - int comp; - - parent_node = *p; - entry = rb_entry(parent_node, struct btrfs_delayed_ref_node, - ref_node); - comp = comp_refs(ins, entry, true); - if (comp < 0) { - p = &(*p)->rb_left; - } else if (comp > 0) { - p = &(*p)->rb_right; - leftmost = false; - } else { - return entry; - } - } + struct rb_node *exist; - rb_link_node(node, parent_node, p); - rb_insert_color_cached(node, root, leftmost); + exist = rb_find_add_cached(node, root, cmp_refs_node); + if (exist) + return rb_entry(exist, struct btrfs_delayed_ref_node, ref_node); return NULL; } @@ -555,6 +549,32 @@ void btrfs_delete_ref_head(const struct btrfs_fs_info *fs_info, delayed_refs->num_heads_ready--; } +struct btrfs_delayed_ref_node *btrfs_select_delayed_ref(struct btrfs_delayed_ref_head *head) +{ + struct btrfs_delayed_ref_node *ref; + + lockdep_assert_held(&head->mutex); + lockdep_assert_held(&head->lock); + + if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) + return NULL; + + /* + * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first. + * This is to prevent a ref count from going down to zero, which deletes + * the extent item from the extent tree, when there still are references + * to add, which would fail because they would not find the extent item. + */ + if (!list_empty(&head->ref_add_list)) + return list_first_entry(&head->ref_add_list, + struct btrfs_delayed_ref_node, add_list); + + ref = rb_entry(rb_first_cached(&head->ref_tree), + struct btrfs_delayed_ref_node, ref_node); + ASSERT(list_empty(&ref->add_list)); + return ref; +} + /* * Helper to insert the ref_node to the tail or merge with tail. * @@ -1234,6 +1254,7 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) { struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; + bool testing = btrfs_is_testing(fs_info); spin_lock(&delayed_refs->lock); while (true) { @@ -1263,7 +1284,7 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) spin_unlock(&delayed_refs->lock); mutex_unlock(&head->mutex); - if (pin_bytes) { + if (!testing && pin_bytes) { struct btrfs_block_group *bg; bg = btrfs_lookup_block_group(fs_info, head->bytenr); @@ -1281,8 +1302,7 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) spin_lock(&bg->space_info->lock); spin_lock(&bg->lock); bg->pinned += head->num_bytes; - btrfs_space_info_update_bytes_pinned(fs_info, - bg->space_info, + btrfs_space_info_update_bytes_pinned(bg->space_info, head->num_bytes); bg->reserved -= head->num_bytes; bg->space_info->bytes_reserved -= head->num_bytes; @@ -1295,12 +1315,15 @@ void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) btrfs_error_unpin_extent_range(fs_info, head->bytenr, head->bytenr + head->num_bytes - 1); } - btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); + if (!testing) + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); } - btrfs_qgroup_destroy_extent_records(trans); + + if (!testing) + btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 611fb3388f82..a35067cebb97 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -402,6 +402,7 @@ struct btrfs_delayed_ref_head *btrfs_select_ref_head( struct btrfs_delayed_ref_root *delayed_refs); void btrfs_unselect_ref_head(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); +struct btrfs_delayed_ref_node *btrfs_select_delayed_ref(struct btrfs_delayed_ref_head *head); int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index ac8e97ed13f7..f86fbea0b3de 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -440,9 +440,6 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans) dev_replace->cursor_right); dev_replace->item_needs_writeback = 0; up_write(&dev_replace->rwsem); - - btrfs_mark_buffer_dirty(trans, eb); - out: btrfs_free_path(path); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 1ea5d8fcfbf7..ccf91de29f80 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -92,7 +92,6 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, name, name_ptr, name_len); write_extent_buffer(leaf, data, data_ptr, data_len); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); return ret; } @@ -152,7 +151,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, name_ptr = (unsigned long)(dir_item + 1); write_extent_buffer(leaf, name->name, name_ptr, name->len); - btrfs_mark_buffer_dirty(trans, leaf); second_insert: /* FIXME, use some real flag for selecting the extra index */ diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index a7c3e221378d..8567af46e16f 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -248,8 +248,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, len = min(len, em->len - (start - em->start)); block_start = extent_map_block_start(em) + (start - em->start); - if (can_nocow_extent(inode, start, &len, - &file_extent, false, false) == 1) { + if (can_nocow_extent(inode, start, &len, &file_extent, false) == 1) { bg = btrfs_inc_nocow_writers(fs_info, block_start); if (bg) can_nocow = true; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 814320948645..f09db62e61a1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -226,7 +226,7 @@ int btrfs_read_extent_buffer(struct extent_buffer *eb, while (1) { clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); - ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num, check); + ret = read_extent_buffer_pages(eb, mirror_num, check); if (!ret) break; @@ -1258,6 +1258,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { struct percpu_counter *em_counter = &fs_info->evictable_extent_maps; + percpu_counter_destroy(&fs_info->stats_read_blocks); percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); percpu_counter_destroy(&fs_info->ordered_bytes); @@ -2327,6 +2328,71 @@ out: return ret; } +static int validate_sys_chunk_array(const struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *sb) +{ + unsigned int cur = 0; /* Offset inside the sys chunk array */ + /* + * At sb read time, fs_info is not fully initialized. Thus we have + * to use super block sectorsize, which should have been validated. + */ + const u32 sectorsize = btrfs_super_sectorsize(sb); + u32 sys_array_size = btrfs_super_sys_array_size(sb); + + if (sys_array_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { + btrfs_err(fs_info, "system chunk array too big %u > %u", + sys_array_size, BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); + return -EUCLEAN; + } + + while (cur < sys_array_size) { + struct btrfs_disk_key *disk_key; + struct btrfs_chunk *chunk; + struct btrfs_key key; + u64 type; + u16 num_stripes; + u32 len; + int ret; + + disk_key = (struct btrfs_disk_key *)(sb->sys_chunk_array + cur); + len = sizeof(*disk_key); + + if (cur + len > sys_array_size) + goto short_read; + cur += len; + + btrfs_disk_key_to_cpu(&key, disk_key); + if (key.type != BTRFS_CHUNK_ITEM_KEY) { + btrfs_err(fs_info, + "unexpected item type %u in sys_array at offset %u", + key.type, cur); + return -EUCLEAN; + } + chunk = (struct btrfs_chunk *)(sb->sys_chunk_array + cur); + num_stripes = btrfs_stack_chunk_num_stripes(chunk); + if (cur + btrfs_chunk_item_size(num_stripes) > sys_array_size) + goto short_read; + type = btrfs_stack_chunk_type(chunk); + if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) { + btrfs_err(fs_info, + "invalid chunk type %llu in sys_array at offset %u", + type, cur); + return -EUCLEAN; + } + ret = btrfs_check_chunk_valid(fs_info, NULL, chunk, key.offset, + sectorsize); + if (ret < 0) + return ret; + cur += btrfs_chunk_item_size(num_stripes); + } + return 0; +short_read: + btrfs_err(fs_info, + "super block sys chunk array short read, cur=%u sys_array_size=%u", + cur, sys_array_size); + return -EUCLEAN; +} + /* * Real super block validation * NOTE: super csum type and incompat features will not be checked here. @@ -2495,6 +2561,8 @@ int btrfs_validate_super(const struct btrfs_fs_info *fs_info, ret = -EINVAL; } + ret = validate_sys_chunk_array(fs_info, sb); + /* * Obvious sys_chunk_array corruptions, it must hold at least one key * and one chunk @@ -2856,6 +2924,10 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block if (ret) return ret; + ret = percpu_counter_init(&fs_info->stats_read_blocks, 0, GFP_KERNEL); + if (ret) + return ret; + fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -3321,6 +3393,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->sectors_per_page = (PAGE_SIZE >> fs_info->sectorsize_bits); fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; + fs_info->fs_devices->fs_info = fs_info; /* * Handle the space caching options appropriately now that we have the @@ -4262,6 +4335,15 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) * already the cleaner, but below we run all pending delayed iputs. */ btrfs_flush_workqueue(fs_info->fixup_workers); + /* + * Similar case here, we have to wait for delalloc workers before we + * proceed below and stop the cleaner kthread, otherwise we trigger a + * use-after-tree on the cleaner kthread task_struct when a delalloc + * worker running submit_compressed_extents() adds a delayed iput, which + * does a wake up on the cleaner kthread, which was already freed below + * when we call kthread_stop(). + */ + btrfs_flush_workqueue(fs_info->delalloc_workers); /* * After we parked the cleaner kthread, ordered extents may have diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index a7051e2570c1..587842991b24 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -96,9 +96,6 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info); /* * This function is used to grab the root, and avoid it is freed when we * access it. But it doesn't ensure that the tree is not dropped. - * - * If you want to ensure the whole tree is safe, you should use - * fs_info->subvol_srcu */ static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0..3014a1a23efd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -570,7 +570,6 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref, num_refs); } } - btrfs_mark_buffer_dirty(trans, leaf); ret = 0; fail: btrfs_release_path(path); @@ -618,7 +617,6 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref1, num_refs); else if (key.type == BTRFS_SHARED_DATA_REF_KEY) btrfs_set_shared_data_ref_count(leaf, ref2, num_refs); - btrfs_mark_buffer_dirty(trans, leaf); } return ret; } @@ -1050,7 +1048,6 @@ void setup_inline_extent_backref(struct btrfs_trans_handle *trans, } else { btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid); } - btrfs_mark_buffer_dirty(trans, leaf); } static int lookup_extent_backref(struct btrfs_trans_handle *trans, @@ -1195,7 +1192,6 @@ static noinline_for_stack int update_inline_extent_backref( item_size -= size; btrfs_truncate_item(trans, path, item_size, 1); } - btrfs_mark_buffer_dirty(trans, leaf); return 0; } @@ -1260,12 +1256,12 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, { int j, ret = 0; u64 bytes_left, end; - u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT); + u64 aligned_start = ALIGN(start, SECTOR_SIZE); /* Adjust the range to be aligned to 512B sectors if necessary. */ if (start != aligned_start) { len -= aligned_start - start; - len = round_down(len, 1 << SECTOR_SHIFT); + len = round_down(len, SECTOR_SIZE); start = aligned_start; } @@ -1527,7 +1523,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (extent_op) __run_delayed_extent_op(extent_op, leaf, item); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* now insert the actual backref */ @@ -1711,8 +1706,6 @@ again: ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); __run_delayed_extent_op(extent_op, leaf, ei); - - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -1803,30 +1796,6 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, return ret; } -static inline struct btrfs_delayed_ref_node * -select_delayed_ref(struct btrfs_delayed_ref_head *head) -{ - struct btrfs_delayed_ref_node *ref; - - if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) - return NULL; - - /* - * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first. - * This is to prevent a ref count from going down to zero, which deletes - * the extent item from the extent tree, when there still are references - * to add, which would fail because they would not find the extent item. - */ - if (!list_empty(&head->ref_add_list)) - return list_first_entry(&head->ref_add_list, - struct btrfs_delayed_ref_node, add_list); - - ref = rb_entry(rb_first_cached(&head->ref_tree), - struct btrfs_delayed_ref_node, ref_node); - ASSERT(list_empty(&ref->add_list)); - return ref; -} - static struct btrfs_delayed_extent_op *cleanup_extent_op( struct btrfs_delayed_ref_head *head) { @@ -1959,7 +1928,7 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, lockdep_assert_held(&locked_ref->mutex); lockdep_assert_held(&locked_ref->lock); - while ((ref = select_delayed_ref(locked_ref))) { + while ((ref = btrfs_select_delayed_ref(locked_ref))) { if (ref->seq && btrfs_check_delayed_seq(fs_info, ref->seq)) { spin_unlock(&locked_ref->lock); @@ -2230,10 +2199,11 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, return ret; } -static noinline int check_delayed_ref(struct btrfs_root *root, +static noinline int check_delayed_ref(struct btrfs_inode *inode, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr) + u64 offset, u64 bytenr) { + struct btrfs_root *root = inode->root; struct btrfs_delayed_ref_head *head; struct btrfs_delayed_ref_node *ref; struct btrfs_delayed_ref_root *delayed_refs; @@ -2307,7 +2277,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root, * then we have a cross reference. */ if (ref->ref_root != btrfs_root_id(root) || - ref_owner != objectid || ref_offset != offset) { + ref_owner != btrfs_ino(inode) || ref_offset != offset) { ret = 1; break; } @@ -2318,11 +2288,53 @@ static noinline int check_delayed_ref(struct btrfs_root *root, return ret; } -static noinline int check_committed_ref(struct btrfs_root *root, +/* + * Check if there are references for a data extent other than the one belonging + * to the given inode and offset. + * + * @inode: The only inode we expect to find associated with the data extent. + * @path: A path to use for searching the extent tree. + * @offset: The only offset we expect to find associated with the data extent. + * @bytenr: The logical address of the data extent. + * + * When the extent does not have any other references other than the one we + * expect to find, we always return a value of 0 with the path having a locked + * leaf that contains the extent's extent item - this is necessary to ensure + * we don't race with a task running delayed references, and our caller must + * have such a path when calling check_delayed_ref() - it must lock a delayed + * ref head while holding the leaf locked. In case the extent item is not found + * in the extent tree, we return -ENOENT with the path having the leaf (locked) + * where the extent item should be, in order to prevent races with another task + * running delayed references, so that we don't miss any reference when calling + * check_delayed_ref(). + * + * Note: this may return false positives, and this is because we want to be + * quick here as we're called in write paths (when flushing delalloc and + * in the direct IO write path). For example we can have an extent with + * a single reference but that reference is not inlined, or we may have + * many references in the extent tree but we also have delayed references + * that cancel all the reference except the one for our inode and offset, + * but it would be expensive to do such checks and complex due to all + * locking to avoid races between the checks and flushing delayed refs, + * plus non-inline references may be located on leaves other than the one + * that contains the extent item in the extent tree. The important thing + * here is to not return false negatives and that the false positives are + * not very common. + * + * Returns: 0 if there are no cross references and with the path having a locked + * leaf from the extent tree that contains the extent's extent item. + * + * 1 if there are cross references (false positives can happen). + * + * < 0 in case of an error. In case of -ENOENT the leaf in the extent + * tree where the extent item should be located at is read locked and + * accessible in the given path. + */ +static noinline int check_committed_ref(struct btrfs_inode *inode, struct btrfs_path *path, - u64 objectid, u64 offset, u64 bytenr, - bool strict) + u64 offset, u64 bytenr) { + struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *extent_root = btrfs_extent_root(fs_info, bytenr); struct extent_buffer *leaf; @@ -2341,35 +2353,32 @@ static noinline int check_committed_ref(struct btrfs_root *root, ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) - goto out; + return ret; if (ret == 0) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } - ret = -ENOENT; if (path->slots[0] == 0) - goto out; + return -ENOENT; path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_ITEM_KEY) - goto out; + return -ENOENT; - ret = 1; item_size = btrfs_item_size(leaf, path->slots[0]); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); expected_size = sizeof(*ei) + btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY); /* No inline refs; we need to bail before checking for owner ref. */ if (item_size == sizeof(*ei)) - goto out; + return 1; /* Check for an owner ref; skip over it to the real inline refs. */ iref = (struct btrfs_extent_inline_ref *)(ei + 1); @@ -2377,56 +2386,69 @@ static noinline int check_committed_ref(struct btrfs_root *root, if (btrfs_fs_incompat(fs_info, SIMPLE_QUOTA) && type == BTRFS_EXTENT_OWNER_REF_KEY) { expected_size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY); iref = (struct btrfs_extent_inline_ref *)(iref + 1); + type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); } /* If extent item has more than 1 inline ref then it's shared */ if (item_size != expected_size) - goto out; - - /* - * If extent created before last snapshot => it's shared unless the - * snapshot has been deleted. Use the heuristic if strict is false. - */ - if (!strict && - (btrfs_extent_generation(leaf, ei) <= - btrfs_root_last_snapshot(&root->root_item))) - goto out; + return 1; /* If this extent has SHARED_DATA_REF then it's shared */ - type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); if (type != BTRFS_EXTENT_DATA_REF_KEY) - goto out; + return 1; ref = (struct btrfs_extent_data_ref *)(&iref->offset); if (btrfs_extent_refs(leaf, ei) != btrfs_extent_data_ref_count(leaf, ref) || btrfs_extent_data_ref_root(leaf, ref) != btrfs_root_id(root) || - btrfs_extent_data_ref_objectid(leaf, ref) != objectid || + btrfs_extent_data_ref_objectid(leaf, ref) != btrfs_ino(inode) || btrfs_extent_data_ref_offset(leaf, ref) != offset) - goto out; + return 1; - ret = 0; -out: - return ret; + return 0; } -int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, - u64 bytenr, bool strict, struct btrfs_path *path) +int btrfs_cross_ref_exist(struct btrfs_inode *inode, u64 offset, + u64 bytenr, struct btrfs_path *path) { int ret; do { - ret = check_committed_ref(root, path, objectid, - offset, bytenr, strict); + ret = check_committed_ref(inode, path, offset, bytenr); if (ret && ret != -ENOENT) goto out; - ret = check_delayed_ref(root, path, objectid, offset, bytenr); + /* + * The path must have a locked leaf from the extent tree where + * the extent item for our extent is located, in case it exists, + * or where it should be located in case it doesn't exist yet + * because it's new and its delayed ref was not yet flushed. + * We need to lock the delayed ref head at check_delayed_ref(), + * if one exists, while holding the leaf locked in order to not + * race with delayed ref flushing, missing references and + * incorrectly reporting that the extent is not shared. + */ + if (IS_ENABLED(CONFIG_BTRFS_ASSERT)) { + struct extent_buffer *leaf = path->nodes[0]; + + ASSERT(leaf != NULL); + btrfs_assert_tree_read_locked(leaf); + + if (ret != -ENOENT) { + struct btrfs_key key; + + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + ASSERT(key.objectid == bytenr); + ASSERT(key.type == BTRFS_EXTENT_ITEM_KEY); + } + } + + ret = check_delayed_ref(inode, path, offset, bytenr); } while (ret == -EAGAIN && !path->nowait); out: btrfs_release_path(path); - if (btrfs_is_data_reloc_root(root)) + if (btrfs_is_data_reloc_root(inode->root)) WARN_ON(ret > 0); return ret; } @@ -2571,13 +2593,10 @@ static int pin_down_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache, u64 bytenr, u64 num_bytes, int reserved) { - struct btrfs_fs_info *fs_info = cache->fs_info; - spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->pinned += num_bytes; - btrfs_space_info_update_bytes_pinned(fs_info, cache->space_info, - num_bytes); + btrfs_space_info_update_bytes_pinned(cache->space_info, num_bytes); if (reserved) { cache->reserved -= num_bytes; cache->space_info->bytes_reserved -= num_bytes; @@ -2724,15 +2743,15 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, { struct btrfs_block_group *cache = NULL; struct btrfs_space_info *space_info; - struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; struct btrfs_free_cluster *cluster = NULL; - u64 len; u64 total_unpinned = 0; u64 empty_cluster = 0; bool readonly; int ret = 0; while (start <= end) { + u64 len; + readonly = false; if (!cache || start >= cache->start + cache->length) { @@ -2778,37 +2797,19 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, spin_lock(&space_info->lock); spin_lock(&cache->lock); cache->pinned -= len; - btrfs_space_info_update_bytes_pinned(fs_info, space_info, -len); + btrfs_space_info_update_bytes_pinned(space_info, -len); space_info->max_extent_size = 0; if (cache->ro) { space_info->bytes_readonly += len; readonly = true; } else if (btrfs_is_zoned(fs_info)) { /* Need reset before reusing in a zoned block group */ - btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info, - len); + btrfs_space_info_update_bytes_zone_unusable(space_info, len); readonly = true; } spin_unlock(&cache->lock); - if (!readonly && return_free_space && - global_rsv->space_info == space_info) { - spin_lock(&global_rsv->lock); - if (!global_rsv->full) { - u64 to_add = min(len, global_rsv->size - - global_rsv->reserved); - - global_rsv->reserved += to_add; - btrfs_space_info_update_bytes_may_use(fs_info, - space_info, to_add); - if (global_rsv->reserved >= global_rsv->size) - global_rsv->full = 1; - len -= to_add; - } - spin_unlock(&global_rsv->lock); - } - /* Add to any tickets we may have */ - if (!readonly && return_free_space && len) - btrfs_try_granting_tickets(fs_info, space_info); + if (!readonly && return_free_space) + btrfs_return_free_space(space_info, len); spin_unlock(&space_info->lock); } @@ -3259,7 +3260,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, } } else { btrfs_set_extent_refs(leaf, ei, refs); - btrfs_mark_buffer_dirty(trans, leaf); } if (found_extent) { ret = remove_extent_backref(trans, extent_root, path, @@ -4827,7 +4827,6 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref, ref_mod); } - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_free_path(path); return alloc_reserved_extent(trans, ins->objectid, ins->offset); @@ -4902,7 +4901,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, btrfs_set_extent_inline_ref_offset(leaf, iref, node->ref_root); } - btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); return alloc_reserved_extent(trans, node->bytenr, fs_info->nodesize); @@ -5285,7 +5283,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5338,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5681,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h index 2ad51130c037..cfa52264f678 100644 --- a/fs/btrfs/extent-tree.h +++ b/fs/btrfs/extent-tree.h @@ -116,8 +116,7 @@ int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num, int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, const struct extent_buffer *eb); int btrfs_exclude_logged_extents(struct extent_buffer *eb); -int btrfs_cross_ref_exist(struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr, bool strict, +int btrfs_cross_ref_exist(struct btrfs_inode *inode, u64 offset, u64 bytenr, struct btrfs_path *path); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -163,5 +162,9 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, struct extent_buffer *parent); +void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); +int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, + u64 num_bytes, u64 *actual_bytes); +int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range); #endif diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index b923d0cec61c..d9f856358704 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -198,9 +198,8 @@ static void __process_folios_contig(struct address_space *mapping, u64 end, unsigned long page_ops) { struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); - pgoff_t start_index = start >> PAGE_SHIFT; + pgoff_t index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; - pgoff_t index = start_index; struct folio_batch fbatch; int i; @@ -221,7 +220,7 @@ static void __process_folios_contig(struct address_space *mapping, } } -static noinline void __unlock_for_delalloc(const struct inode *inode, +static noinline void unlock_delalloc_folio(const struct inode *inode, const struct folio *locked_folio, u64 start, u64 end) { @@ -242,9 +241,8 @@ static noinline int lock_delalloc_folios(struct inode *inode, { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct address_space *mapping = inode->i_mapping; - pgoff_t start_index = start >> PAGE_SHIFT; + pgoff_t index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; - pgoff_t index = start_index; u64 processed_end = start; struct folio_batch fbatch; @@ -288,8 +286,7 @@ static noinline int lock_delalloc_folios(struct inode *inode, out: folio_batch_release(&fbatch); if (processed_end > start) - __unlock_for_delalloc(inode, locked_folio, start, - processed_end); + unlock_delalloc_folio(inode, locked_folio, start, processed_end); return -EAGAIN; } @@ -390,7 +387,7 @@ again: unlock_extent(tree, delalloc_start, delalloc_end, &cached_state); if (!ret) { - __unlock_for_delalloc(inode, locked_folio, delalloc_start, + unlock_delalloc_folio(inode, locked_folio, delalloc_start, delalloc_end); cond_resched(); goto again; @@ -710,6 +707,7 @@ static void alloc_new_bio(struct btrfs_inode *inode, bbio = btrfs_bio_alloc(BIO_MAX_VECS, bio_ctrl->opf, fs_info, bio_ctrl->end_io_func, NULL); bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; + bbio->bio.bi_write_hint = inode->vfs_inode.i_write_hint; bbio->inode = inode; bbio->file_offset = file_offset; bio_ctrl->bbio = bbio; @@ -862,11 +860,6 @@ static int attach_extent_buffer_folio(struct extent_buffer *eb, return ret; } -int set_page_extent_mapped(struct page *page) -{ - return set_folio_extent_mapped(page_folio(page)); -} - int set_folio_extent_mapped(struct folio *folio) { struct btrfs_fs_info *fs_info; @@ -901,9 +894,9 @@ void clear_folio_extent_mapped(struct folio *folio) folio_detach_private(folio); } -static struct extent_map *__get_extent_map(struct inode *inode, - struct folio *folio, u64 start, - u64 len, struct extent_map **em_cached) +static struct extent_map *get_extent_map(struct btrfs_inode *inode, + struct folio *folio, u64 start, + u64 len, struct extent_map **em_cached) { struct extent_map *em; struct extent_state *cached_state = NULL; @@ -922,14 +915,14 @@ static struct extent_map *__get_extent_map(struct inode *inode, *em_cached = NULL; } - btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), start, start + len - 1, &cached_state); - em = btrfs_get_extent(BTRFS_I(inode), folio, start, len); + btrfs_lock_and_flush_ordered_range(inode, start, start + len - 1, &cached_state); + em = btrfs_get_extent(inode, folio, start, len); if (!IS_ERR(em)) { BUG_ON(*em_cached); refcount_inc(&em->refs); *em_cached = em; } - unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len - 1, &cached_state); + unlock_extent(&inode->io_tree, start, start + len - 1, &cached_state); return em; } @@ -985,8 +978,7 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, end_folio_read(folio, true, cur, iosize); break; } - em = __get_extent_map(inode, folio, cur, end - cur + 1, - em_cached); + em = get_extent_map(BTRFS_I(inode), folio, cur, end - cur + 1, em_cached); if (IS_ERR(em)) { end_folio_read(folio, false, cur, end + 1 - cur); return PTR_ERR(em); @@ -1142,14 +1134,19 @@ static bool find_next_delalloc_bitmap(struct folio *folio, } /* - * helper for extent_writepage(), doing all of the delayed allocation setup. + * Do all of the delayed allocation setup. * - * This returns 1 if btrfs_run_delalloc_range function did all the work required - * to write the page (copy into inline extent). In this case the IO has - * been started and the page is already unlocked. + * Return >0 if all the dirty blocks are submitted async (compression) or inlined. + * The @folio should no longer be touched (treat it as already unlocked). * - * This returns 0 if all went well (page still locked) - * This returns < 0 if there were errors (page still locked) + * Return 0 if there is still dirty block that needs to be submitted through + * extent_writepage_io(). + * bio_ctrl->submit_bitmap will indicate which blocks of the folio should be + * submitted, and @folio is still kept locked. + * + * Return <0 if there is any error hit. + * Any allocated ordered extent range covering this folio will be marked + * finished (IOERR), and @folio is still kept locked. */ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, struct folio *folio, @@ -1167,6 +1164,16 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, * last delalloc end. */ u64 last_delalloc_end = 0; + /* + * The range end (exclusive) of the last successfully finished delalloc + * range. + * Any range covered by ordered extent must either be manually marked + * finished (error handling), or has IO submitted (and finish the + * ordered extent normally). + * + * This records the end of ordered extent cleanup if we hit an error. + */ + u64 last_finished_delalloc_end = page_start; u64 delalloc_start = page_start; u64 delalloc_end = page_end; u64 delalloc_to_write = 0; @@ -1235,11 +1242,28 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, found_len = last_delalloc_end + 1 - found_start; if (ret >= 0) { + /* + * Some delalloc range may be created by previous folios. + * Thus we still need to clean up this range during error + * handling. + */ + last_finished_delalloc_end = found_start; /* No errors hit so far, run the current delalloc range. */ ret = btrfs_run_delalloc_range(inode, folio, found_start, found_start + found_len - 1, wbc); + if (ret >= 0) + last_finished_delalloc_end = found_start + found_len; + if (unlikely(ret < 0)) + btrfs_err_rl(fs_info, +"failed to run delalloc range, root=%lld ino=%llu folio=%llu submit_bitmap=%*pbl start=%llu len=%u: %d", + btrfs_root_id(inode->root), + btrfs_ino(inode), + folio_pos(folio), + fs_info->sectors_per_page, + &bio_ctrl->submit_bitmap, + found_start, found_len, ret); } else { /* * We've hit an error during previous delalloc range, @@ -1247,7 +1271,7 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, */ unlock_extent(&inode->io_tree, found_start, found_start + found_len - 1, NULL); - __unlock_for_delalloc(&inode->vfs_inode, folio, + unlock_delalloc_folio(&inode->vfs_inode, folio, found_start, found_start + found_len - 1); } @@ -1274,8 +1298,22 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, delalloc_start = found_start + found_len; } - if (ret < 0) + /* + * It's possible we had some ordered extents created before we hit + * an error, cleanup non-async successfully created delalloc ranges. + */ + if (unlikely(ret < 0)) { + unsigned int bitmap_size = min( + (last_finished_delalloc_end - page_start) >> + fs_info->sectorsize_bits, + fs_info->sectors_per_page); + + for_each_set_bit(bit, &bio_ctrl->submit_bitmap, bitmap_size) + btrfs_mark_ordered_io_finished(inode, folio, + page_start + (bit << fs_info->sectorsize_bits), + fs_info->sectorsize, false); return ret; + } out: if (last_delalloc_end) delalloc_end = last_delalloc_end; @@ -1335,7 +1373,7 @@ static int submit_one_sector(struct btrfs_inode *inode, em = btrfs_get_extent(inode, NULL, filepos, sectorsize); if (IS_ERR(em)) - return PTR_ERR_OR_ZERO(em); + return PTR_ERR(em); extent_offset = filepos - em->start; em_end = extent_map_end(em); @@ -1391,6 +1429,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned long range_bitmap = 0; bool submitted_io = false; + bool error = false; const u64 folio_start = folio_pos(folio); u64 cur; int bit; @@ -1433,11 +1472,26 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, break; } ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); - if (ret < 0) - goto out; + if (unlikely(ret < 0)) { + /* + * bio_ctrl may contain a bio crossing several folios. + * Submit it immediately so that the bio has a chance + * to finish normally, other than marked as error. + */ + submit_one_bio(bio_ctrl); + /* + * Failed to grab the extent map which should be very rare. + * Since there is no bio submitted to finish the ordered + * extent, we have to manually finish this sector. + */ + btrfs_mark_ordered_io_finished(inode, folio, cur, + fs_info->sectorsize, false); + error = true; + continue; + } submitted_io = true; } -out: + /* * If we didn't submitted any sector (>= i_size), folio dirty get * cleared but PAGECACHE_TAG_DIRTY is not cleared (only cleared @@ -1445,8 +1499,11 @@ out: * * Here we set writeback and clear for the range. If the full folio * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag. + * + * If we hit any error, the corresponding sector will still be dirty + * thus no need to clear PAGECACHE_TAG_DIRTY. */ - if (!submitted_io) { + if (!submitted_io && !error) { btrfs_folio_set_writeback(fs_info, folio, start, len); btrfs_folio_clear_writeback(fs_info, folio, start, len); } @@ -1464,15 +1521,14 @@ out: */ static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl) { - struct inode *inode = folio->mapping->host; - struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); - const u64 page_start = folio_pos(folio); + struct btrfs_inode *inode = BTRFS_I(folio->mapping->host); + struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret; size_t pg_offset; - loff_t i_size = i_size_read(inode); + loff_t i_size = i_size_read(&inode->vfs_inode); unsigned long end_index = i_size >> PAGE_SHIFT; - trace_extent_writepage(folio, inode, bio_ctrl->wbc); + trace_extent_writepage(folio, &inode->vfs_inode, bio_ctrl->wbc); WARN_ON(!folio_test_locked(folio)); @@ -1496,26 +1552,28 @@ static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl if (ret < 0) goto done; - ret = writepage_delalloc(BTRFS_I(inode), folio, bio_ctrl); + ret = writepage_delalloc(inode, folio, bio_ctrl); if (ret == 1) return 0; if (ret) goto done; - ret = extent_writepage_io(BTRFS_I(inode), folio, folio_pos(folio), + ret = extent_writepage_io(inode, folio, folio_pos(folio), PAGE_SIZE, bio_ctrl, i_size); if (ret == 1) return 0; + if (ret < 0) + btrfs_err_rl(fs_info, +"failed to submit blocks, root=%lld inode=%llu folio=%llu submit_bitmap=%*pbl: %d", + btrfs_root_id(inode->root), btrfs_ino(inode), + folio_pos(folio), fs_info->sectors_per_page, + &bio_ctrl->submit_bitmap, ret); bio_ctrl->wbc->nr_to_write--; done: - if (ret) { - btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio, - page_start, PAGE_SIZE, !ret); + if (ret < 0) mapping_set_error(folio->mapping, ret); - } - /* * Only unlock ranges that are submitted. As there can be some async * submitted ranges inside the folio. @@ -1525,12 +1583,6 @@ done: return ret; } -void wait_on_extent_buffer_writeback(struct extent_buffer *eb) -{ - wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, - TASK_UNINTERRUPTIBLE); -} - /* * Lock extent buffer status and pages for writeback. * @@ -1671,11 +1723,10 @@ static void end_bbio_meta_write(struct btrfs_bio *bbio) { struct extent_buffer *eb = bbio->private; struct btrfs_fs_info *fs_info = eb->fs_info; - bool uptodate = !bbio->bio.bi_status; struct folio_iter fi; u32 bio_offset = 0; - if (!uptodate) + if (bbio->bio.bi_status != BLK_STS_OK) set_btree_ioerr(eb); bio_for_each_folio_all(fi, &bbio->bio) { @@ -2292,11 +2343,8 @@ void extent_write_locked_range(struct inode *inode, const struct folio *locked_f if (ret == 1) goto next_page; - if (ret) { - btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio, - cur, cur_len, !ret); + if (ret) mapping_set_error(mapping, ret); - } btrfs_folio_end_lock(fs_info, folio, cur, cur_len); if (ret < 0) found_error = true; @@ -2495,11 +2543,6 @@ next: return try_release_extent_state(io_tree, folio); } -static void __free_extent_buffer(struct extent_buffer *eb) -{ - kmem_cache_free(extent_buffer_cache, eb); -} - static int extent_buffer_under_io(const struct extent_buffer *eb) { return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || @@ -2580,8 +2623,8 @@ static void detach_extent_buffer_folio(const struct extent_buffer *eb, struct fo spin_unlock(&folio->mapping->i_private_lock); } -/* Release all pages attached to the extent buffer */ -static void btrfs_release_extent_buffer_pages(const struct extent_buffer *eb) +/* Release all folios attached to the extent buffer */ +static void btrfs_release_extent_buffer_folios(const struct extent_buffer *eb) { ASSERT(!extent_buffer_under_io(eb)); @@ -2603,9 +2646,9 @@ static void btrfs_release_extent_buffer_pages(const struct extent_buffer *eb) */ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) { - btrfs_release_extent_buffer_pages(eb); + btrfs_release_extent_buffer_folios(eb); btrfs_leak_debug_del_eb(eb); - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); } static struct extent_buffer * @@ -2703,7 +2746,7 @@ err: folio_put(eb->folios[i]); } } - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); return NULL; } @@ -2830,13 +2873,12 @@ free_eb: } #endif -static struct extent_buffer *grab_extent_buffer( - struct btrfs_fs_info *fs_info, struct page *page) +static struct extent_buffer *grab_extent_buffer(struct btrfs_fs_info *fs_info, + struct folio *folio) { - struct folio *folio = page_folio(page); struct extent_buffer *exists; - lockdep_assert_held(&page->mapping->i_private_lock); + lockdep_assert_held(&folio->mapping->i_private_lock); /* * For subpage case, we completely rely on radix tree to ensure we @@ -2851,7 +2893,7 @@ static struct extent_buffer *grab_extent_buffer( return NULL; /* - * We could have already allocated an eb for this page and attached one + * We could have already allocated an eb for this folio and attached one * so lets see if we can get a ref on the existing eb, and if we can we * know it's good and we can just return that one, else we know we can * just overwrite folio private. @@ -2860,16 +2902,19 @@ static struct extent_buffer *grab_extent_buffer( if (atomic_inc_not_zero(&exists->refs)) return exists; - WARN_ON(PageDirty(page)); + WARN_ON(folio_test_dirty(folio)); folio_detach_private(folio); return NULL; } -static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) +/* + * Validate alignment constraints of eb at logical address @start. + */ +static bool check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) { if (!IS_ALIGNED(start, fs_info->sectorsize)) { btrfs_err(fs_info, "bad tree block start %llu", start); - return -EINVAL; + return true; } if (fs_info->nodesize < PAGE_SIZE && @@ -2877,14 +2922,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) btrfs_err(fs_info, "tree block crosses page boundary, start %llu nodesize %u", start, fs_info->nodesize); - return -EINVAL; + return true; } if (fs_info->nodesize >= PAGE_SIZE && !PAGE_ALIGNED(start)) { btrfs_err(fs_info, "tree block is not page aligned, start %llu nodesize %u", start, fs_info->nodesize); - return -EINVAL; + return true; } if (!IS_ALIGNED(start, fs_info->nodesize) && !test_and_set_bit(BTRFS_FS_UNALIGNED_TREE_BLOCK, &fs_info->flags)) { @@ -2892,10 +2937,9 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) "tree block not nodesize aligned, start %llu nodesize %u, can be resolved by a full metadata balance", start, fs_info->nodesize); } - return 0; + return false; } - /* * Return 0 if eb->folios[i] is attached to btree inode successfully. * Return >0 if there is already another extent buffer for the range, @@ -2951,8 +2995,7 @@ finish: } else if (existing_folio) { struct extent_buffer *existing_eb; - existing_eb = grab_extent_buffer(fs_info, - folio_page(existing_folio, 0)); + existing_eb = grab_extent_buffer(fs_info, existing_folio); if (existing_eb) { /* The extent buffer still exists, we can use it directly. */ *found_eb_ret = existing_eb; @@ -3149,7 +3192,7 @@ again: * live buffer and won't free them prematurely. */ for (int i = 0; i < num_folios; i++) - unlock_page(folio_page(eb->folios[i], 0)); + folio_unlock(eb->folios[i]); return eb; out: @@ -3173,7 +3216,7 @@ out: for (int i = 0; i < attached; i++) { ASSERT(eb->folios[i]); detach_extent_buffer_folio(eb, eb->folios[i]); - unlock_page(folio_page(eb->folios[i], 0)); + folio_unlock(eb->folios[i]); folio_put(eb->folios[i]); eb->folios[i] = NULL; } @@ -3195,7 +3238,7 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head) struct extent_buffer *eb = container_of(head, struct extent_buffer, rcu_head); - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); } static int release_extent_buffer(struct extent_buffer *eb) @@ -3219,11 +3262,11 @@ static int release_extent_buffer(struct extent_buffer *eb) } btrfs_leak_debug_del_eb(eb); - /* Should be safe to release our pages at this point */ - btrfs_release_extent_buffer_pages(eb); + /* Should be safe to release folios at this point. */ + btrfs_release_extent_buffer_folios(eb); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) { - __free_extent_buffer(eb); + kmem_cache_free(extent_buffer_cache, eb); return 1; } #endif @@ -3382,12 +3425,12 @@ void set_extent_buffer_dirty(struct extent_buffer *eb) * the above race. */ if (subpage) - lock_page(folio_page(eb->folios[0], 0)); + folio_lock(eb->folios[0]); for (int i = 0; i < num_folios; i++) btrfs_folio_set_dirty(eb->fs_info, eb->folios[i], eb->start, eb->len); if (subpage) - unlock_page(folio_page(eb->folios[0], 0)); + folio_unlock(eb->folios[0]); percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes, eb->len, eb->fs_info->dirty_metadata_batch); @@ -3497,8 +3540,8 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio) bio_put(&bbio->bio); } -int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, - const struct btrfs_tree_parent_check *check) +int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, + const struct btrfs_tree_parent_check *check) { struct btrfs_bio *bbio; bool ret; @@ -3516,7 +3559,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, /* Someone else is already reading the buffer, just wait for it. */ if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags)) - goto done; + return 0; /* * Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above @@ -3556,14 +3599,21 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, } } btrfs_submit_bbio(bbio, mirror_num); + return 0; +} -done: - if (wait == WAIT_COMPLETE) { - wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE); - if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) - return -EIO; - } +int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num, + const struct btrfs_tree_parent_check *check) +{ + int ret; + ret = read_extent_buffer_pages_nowait(eb, mirror_num, check); + if (ret < 0) + return ret; + + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE); + if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) + return -EIO; return 0; } @@ -4294,7 +4344,7 @@ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, return; } - ret = read_extent_buffer_pages(eb, WAIT_NONE, 0, &check); + ret = read_extent_buffer_pages_nowait(eb, 0, &check); if (ret < 0) free_extent_buffer_stale(eb); else diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 8a36117ed453..6c5328bfabc2 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -248,7 +248,6 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); void btrfs_readahead(struct readahead_control *rac); int set_folio_extent_mapped(struct folio *folio); -int set_page_extent_mapped(struct page *page); void clear_folio_extent_mapped(struct folio *folio); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, @@ -262,12 +261,17 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, u64 start); void free_extent_buffer(struct extent_buffer *eb); void free_extent_buffer_stale(struct extent_buffer *eb); -#define WAIT_NONE 0 -#define WAIT_COMPLETE 1 -#define WAIT_PAGE_LOCK 2 -int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, +int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *parent_check); -void wait_on_extent_buffer_writeback(struct extent_buffer *eb); +int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, + const struct btrfs_tree_parent_check *parent_check); + +static inline void wait_on_extent_buffer_writeback(struct extent_buffer *eb) +{ + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, + TASK_UNINTERRUPTIBLE); +} + void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 owner_root, u64 gen, int level); void btrfs_readahead_node_child(struct extent_buffer *node, int slot); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 886749b39672..d04a3b47b1fb 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -190,8 +190,6 @@ int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_compression(leaf, item, 0); btrfs_set_file_extent_encryption(leaf, item, 0); btrfs_set_file_extent_other_encoding(leaf, item, 0); - - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -1259,7 +1257,6 @@ found: ins_size /= csum_size; total_bytes += ins_size * fs_info->sectorsize; - btrfs_mark_buffer_dirty(trans, path->nodes[0]); if (total_bytes < sums->len) { btrfs_release_path(path); cond_resched(); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 588c353d2969..36f51c311bb1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -36,52 +36,7 @@ #include "ioctl.h" #include "file.h" #include "super.h" - -/* - * Helper to fault in page and copy. This should go away and be replaced with - * calls into generic code. - */ -static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, - struct folio *folio, struct iov_iter *i) -{ - size_t copied = 0; - size_t total_copied = 0; - int offset = offset_in_page(pos); - - while (write_bytes > 0) { - size_t count = min_t(size_t, PAGE_SIZE - offset, write_bytes); - /* - * Copy data from userspace to the current page - */ - copied = copy_folio_from_iter_atomic(folio, offset, count, i); - - /* Flush processor's dcache for this page */ - flush_dcache_folio(folio); - - /* - * if we get a partial write, we can end up with - * partially up to date page. These add - * a lot of complexity, so make sure they don't - * happen by forcing this copy to be retried. - * - * The rest of the btrfs_file_write code will fall - * back to page at a time copies after we return 0. - */ - if (unlikely(copied < count)) { - if (!folio_test_uptodate(folio)) { - iov_iter_revert(i, copied); - copied = 0; - } - if (!copied) - break; - } - - write_bytes -= copied; - total_copied += copied; - offset += copied; - } - return total_copied; -} +#include "print-tree.h" /* * Unlock folio after btrfs_file_write() is done with it. @@ -106,7 +61,7 @@ static void btrfs_drop_folio(struct btrfs_fs_info *fs_info, struct folio *folio, } /* - * After btrfs_copy_from_user(), update the following things for delalloc: + * After copy_folio_from_iter_atomic(), update the following things for delalloc: * - Mark newly dirtied folio as DELALLOC in the io tree. * Used to advise which range is to be written back. * - Mark modified folio as Uptodate/Dirty and not needing COW fixup @@ -224,7 +179,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, if (args->drop_cache) btrfs_drop_extent_map_range(inode, args->start, args->end - 1, false); - if (args->start >= inode->disk_i_size && !args->replace_extent) + if (data_race(args->start >= inode->disk_i_size) && !args->replace_extent) modify_tree = 0; update_refs = (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID); @@ -245,7 +200,11 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { - BUG_ON(del_nr > 0); + if (WARN_ON(del_nr > 0)) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } ret = btrfs_next_leaf(root, path); if (ret < 0) break; @@ -321,7 +280,11 @@ next_slot: * | -------- extent -------- | */ if (args->start > key.offset && args->end < extent_end) { - BUG_ON(del_nr > 0); + if (WARN_ON(del_nr > 0)) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; @@ -351,7 +314,6 @@ next_slot: btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - args->start); - btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) { struct btrfs_ref ref = { @@ -397,7 +359,6 @@ next_slot: btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - args->end); - btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) args->bytes_found += args->end - key.offset; break; @@ -409,7 +370,11 @@ next_slot: * | -------- extent -------- | */ if (args->start > key.offset && args->end >= extent_end) { - BUG_ON(del_nr > 0); + if (WARN_ON(del_nr > 0)) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; @@ -417,7 +382,6 @@ next_slot: btrfs_set_file_extent_num_bytes(leaf, fi, args->start - key.offset); - btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) args->bytes_found += extent_end - args->start; if (args->end == extent_end) @@ -437,7 +401,11 @@ delete_extent_item: del_slot = path->slots[0]; del_nr = 1; } else { - BUG_ON(del_slot + del_nr != path->slots[0]); + if (WARN_ON(del_slot + del_nr != path->slots[0])) { + btrfs_print_leaf(leaf); + ret = -EINVAL; + break; + } del_nr++; } @@ -668,7 +636,6 @@ again: trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, end - other_start); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } } @@ -697,7 +664,6 @@ again: other_end - start); btrfs_set_file_extent_offset(leaf, fi, start - orig_offset); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } } @@ -731,7 +697,6 @@ again: btrfs_set_file_extent_offset(leaf, fi, split - orig_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - split); - btrfs_mark_buffer_dirty(trans, leaf); ref.action = BTRFS_ADD_DELAYED_REF; ref.bytenr = bytenr; @@ -810,7 +775,6 @@ again: btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); } else { fi = btrfs_item_ptr(leaf, del_slot - 1, struct btrfs_file_extent_item); @@ -819,7 +783,6 @@ again: btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - key.offset); - btrfs_mark_buffer_dirty(trans, leaf); ret = btrfs_del_items(trans, root, path, del_slot, del_nr); if (ret < 0) { @@ -911,6 +874,7 @@ again: ret = PTR_ERR(folio); return ret; } + folio_wait_writeback(folio); /* Only support page sized folio yet. */ ASSERT(folio_order(folio) == 0); ret = set_folio_extent_mapped(folio); @@ -1051,7 +1015,7 @@ int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, &cached_state); } ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, - NULL, nowait, false); + NULL, nowait); if (ret <= 0) btrfs_drew_write_unlock(&root->snapshot_lock); else @@ -1251,7 +1215,23 @@ again: break; } - copied = btrfs_copy_from_user(pos, write_bytes, folio, i); + copied = copy_folio_from_iter_atomic(folio, + offset_in_folio(folio, pos), write_bytes, i); + flush_dcache_folio(folio); + + /* + * If we get a partial write, we can end up with partially + * uptodate page. Although if sector size < page size we can + * handle it, but if it's not sector aligned it can cause + * a lot of complexity, so make sure they don't happen by + * forcing retry this copy. + */ + if (unlikely(copied < write_bytes)) { + if (!folio_test_uptodate(folio)) { + iov_iter_revert(i, copied); + copied = 0; + } + } num_sectors = BTRFS_BYTES_TO_BLKS(fs_info, reserve_bytes); dirty_sectors = round_up(copied + sector_offset, @@ -2028,7 +2008,6 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } @@ -2045,7 +2024,6 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); goto out; } btrfs_release_path(path); @@ -2193,7 +2171,6 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, extent, replace_len); if (extent_info->is_new_extent) btrfs_set_file_extent_generation(leaf, extent, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index cfa52ef40b06..d42b6f882f57 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -12,7 +12,7 @@ #include <linux/error-injection.h> #include <linux/sched/mm.h> #include <linux/string_choices.h> -#include "ctree.h" +#include "extent-tree.h" #include "fs.h" #include "messages.h" #include "misc.h" @@ -198,7 +198,6 @@ static int __create_free_space_inode(struct btrfs_root *root, btrfs_set_inode_nlink(leaf, inode_item, 1); btrfs_set_inode_transid(leaf, inode_item, trans->transid); btrfs_set_inode_block_group(leaf, inode_item, offset); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); key.objectid = BTRFS_FREE_SPACE_OBJECTID; @@ -216,7 +215,6 @@ static int __create_free_space_inode(struct btrfs_root *root, struct btrfs_free_space_header); memzero_extent_buffer(leaf, (unsigned long)header, sizeof(*header)); btrfs_set_free_space_key(leaf, header, &disk_key); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; @@ -463,7 +461,7 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) return -ENOMEM; } - ret = set_page_extent_mapped(page); + ret = set_folio_extent_mapped(page_folio(page)); if (ret < 0) { unlock_page(page); put_page(page); @@ -1189,7 +1187,6 @@ update_cache_item(struct btrfs_trans_handle *trans, btrfs_set_free_space_entries(leaf, header, entries); btrfs_set_free_space_bitmaps(leaf, header, bitmaps); btrfs_set_free_space_generation(leaf, header, trans->transid); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 7ba50e133921..cae540ec15ed 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -89,7 +89,6 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans, struct btrfs_free_space_info); btrfs_set_free_space_extent_count(leaf, info, 0); btrfs_set_free_space_flags(leaf, info, 0); - btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -287,7 +286,6 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, flags |= BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); if (extent_count != expected_extent_count) { @@ -324,7 +322,6 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, bitmap_cursor, ptr, data_size); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); i += extent_size; @@ -430,7 +427,6 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); nrbits = block_group->length >> block_group->fs_info->sectorsize_bits; @@ -495,7 +491,6 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans, extent_count += new_extents; btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) && @@ -1350,6 +1345,12 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_end_transaction(trans); return ret; } + if (btrfs_should_end_transaction(trans)) { + btrfs_end_transaction(trans); + trans = btrfs_start_transaction(free_space_root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + } node = rb_next(node); } diff --git a/fs/btrfs/fs.c b/fs/btrfs/fs.c index 31c1648bc0b4..09cfb43580cb 100644 --- a/fs/btrfs/fs.c +++ b/fs/btrfs/fs.c @@ -4,6 +4,136 @@ #include "ctree.h" #include "fs.h" #include "accessors.h" +#include "volumes.h" + +static const struct btrfs_csums { + u16 size; + const char name[10]; + const char driver[12]; +} btrfs_csums[] = { + [BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" }, + [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" }, + [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" }, + [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b", + .driver = "blake2b-256" }, +}; + +/* This exists for btrfs-progs usages. */ +u16 btrfs_csum_type_size(u16 type) +{ + return btrfs_csums[type].size; +} + +int btrfs_super_csum_size(const struct btrfs_super_block *s) +{ + u16 t = btrfs_super_csum_type(s); + + /* csum type is validated at mount time. */ + return btrfs_csum_type_size(t); +} + +const char *btrfs_super_csum_name(u16 csum_type) +{ + /* csum type is validated at mount time. */ + return btrfs_csums[csum_type].name; +} + +/* + * Return driver name if defined, otherwise the name that's also a valid driver + * name. + */ +const char *btrfs_super_csum_driver(u16 csum_type) +{ + /* csum type is validated at mount time */ + return btrfs_csums[csum_type].driver[0] ? + btrfs_csums[csum_type].driver : + btrfs_csums[csum_type].name; +} + +size_t __attribute_const__ btrfs_get_num_csums(void) +{ + return ARRAY_SIZE(btrfs_csums); +} + +/* + * Start exclusive operation @type, return true on success. + */ +bool btrfs_exclop_start(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type) +{ + bool ret = false; + + spin_lock(&fs_info->super_lock); + if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) { + fs_info->exclusive_operation = type; + ret = true; + } + spin_unlock(&fs_info->super_lock); + + return ret; +} + +/* + * Conditionally allow to enter the exclusive operation in case it's compatible + * with the running one. This must be paired with btrfs_exclop_start_unlock() + * and btrfs_exclop_finish(). + * + * Compatibility: + * - the same type is already running + * - when trying to add a device and balance has been paused + * - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller + * must check the condition first that would allow none -> @type + */ +bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation type) +{ + spin_lock(&fs_info->super_lock); + if (fs_info->exclusive_operation == type || + (fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED && + type == BTRFS_EXCLOP_DEV_ADD)) + return true; + + spin_unlock(&fs_info->super_lock); + return false; +} + +void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info) +{ + spin_unlock(&fs_info->super_lock); +} + +void btrfs_exclop_finish(struct btrfs_fs_info *fs_info) +{ + spin_lock(&fs_info->super_lock); + WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE); + spin_unlock(&fs_info->super_lock); + sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation"); +} + +void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, + enum btrfs_exclusive_operation op) +{ + switch (op) { + case BTRFS_EXCLOP_BALANCE_PAUSED: + spin_lock(&fs_info->super_lock); + ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || + fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || + fs_info->exclusive_operation == BTRFS_EXCLOP_NONE || + fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); + fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED; + spin_unlock(&fs_info->super_lock); + break; + case BTRFS_EXCLOP_BALANCE: + spin_lock(&fs_info->super_lock); + ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); + fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE; + spin_unlock(&fs_info->super_lock); + break; + default: + btrfs_warn(fs_info, + "invalid exclop balance operation %d requested", op); + } +} void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag, const char *name) diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 79a1a3d6f04d..b572d6b9730b 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -14,10 +14,10 @@ #include <linux/lockdep.h> #include <linux/spinlock.h> #include <linux/mutex.h> -#include <linux/rwlock_types.h> #include <linux/rwsem.h> #include <linux/semaphore.h> #include <linux/list.h> +#include <linux/pagemap.h> #include <linux/radix-tree.h> #include <linux/workqueue.h> #include <linux/wait.h> @@ -627,6 +627,9 @@ struct btrfs_fs_info { struct kobject *qgroups_kobj; struct kobject *discard_kobj; + /* Track the number of blocks (sectors) read by the filesystem. */ + struct percpu_counter stats_read_blocks; + /* Used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; @@ -887,6 +890,11 @@ struct btrfs_fs_info { #define inode_to_fs_info(_inode) (BTRFS_I(_Generic((_inode), \ struct inode *: (_inode)))->root->fs_info) +static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) +{ + return mapping_gfp_constraint(mapping, ~__GFP_FS); +} + static inline u64 btrfs_get_fs_generation(const struct btrfs_fs_info *fs_info) { return READ_ONCE(fs_info->generation); @@ -953,6 +961,8 @@ static inline u64 btrfs_calc_metadata_size(const struct btrfs_fs_info *fs_info, #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \ sizeof(struct btrfs_item)) +#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) ((bytes) >> (fs_info)->sectorsize_bits) + static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info) { return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && fs_info->zone_size > 0; @@ -982,6 +992,17 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args); +u16 btrfs_csum_type_size(u16 type); +int btrfs_super_csum_size(const struct btrfs_super_block *s); +const char *btrfs_super_csum_name(u16 csum_type); +const char *btrfs_super_csum_driver(u16 csum_type); +size_t __attribute_const__ btrfs_get_num_csums(void); + +static inline bool btrfs_is_empty_uuid(const u8 *uuid) +{ + return uuid_is_null((const uuid_t *)uuid); +} + /* Compatibility and incompatibility defines */ void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag, const char *name); @@ -1058,6 +1079,14 @@ static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info) (unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, \ &(fs_info)->fs_state))) +/* + * We use folio flag owner_2 to indicate there is an ordered extent with + * unfinished IO. + */ +#define folio_test_ordered(folio) folio_test_owner_2(folio) +#define folio_set_ordered(folio) folio_set_owner_2(folio) +#define folio_clear_ordered(folio) folio_clear_owner_2(folio) + #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS #define EXPORT_FOR_TESTS diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 29572dfaf878..448aa1a682d6 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -298,8 +298,6 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, ptr = (unsigned long)&extref->name; write_extent_buffer(path->nodes[0], name->name, ptr, name->len); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); - out: btrfs_free_path(path); return ret; @@ -363,8 +361,6 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ptr = (unsigned long)(ref + 1); } write_extent_buffer(path->nodes[0], name->name, ptr, name->len); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); - out: btrfs_free_path(path); @@ -590,7 +586,6 @@ search_again: num_dec = (orig_num_bytes - extent_num_bytes); if (extent_start != 0) control->sub_bytes += num_dec; - btrfs_mark_buffer_dirty(trans, leaf); } else { extent_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index fa648ab6fe80..fe2c810335ff 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -393,34 +393,13 @@ void btrfs_inode_unlock(struct btrfs_inode *inode, unsigned int ilock_flags) * extent (btrfs_finish_ordered_io()). */ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, - struct folio *locked_folio, u64 offset, u64 bytes) { unsigned long index = offset >> PAGE_SHIFT; unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; - u64 page_start = 0, page_end = 0; struct folio *folio; - if (locked_folio) { - page_start = folio_pos(locked_folio); - page_end = page_start + folio_size(locked_folio) - 1; - } - while (index <= end_index) { - /* - * For locked page, we will call btrfs_mark_ordered_io_finished - * through btrfs_mark_ordered_io_finished() on it - * in run_delalloc_range() for the error handling, which will - * clear page Ordered and run the ordered extent accounting. - * - * Here we can't just clear the Ordered bit, or - * btrfs_mark_ordered_io_finished() would skip the accounting - * for the page range, and the ordered extent will never finish. - */ - if (locked_folio && index == (page_start >> PAGE_SHIFT)) { - index++; - continue; - } folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); index++; if (IS_ERR(folio)) @@ -436,23 +415,6 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, folio_put(folio); } - if (locked_folio) { - /* The locked page covers the full range, nothing needs to be done */ - if (bytes + offset <= page_start + folio_size(locked_folio)) - return; - /* - * In case this page belongs to the delalloc range being - * instantiated then skip it, since the first page of a range is - * going to be properly cleaned up by the caller of - * run_delalloc_range - */ - if (page_start >= offset && page_end <= (offset + bytes - 1)) { - bytes = offset + bytes - folio_pos(locked_folio) - - folio_size(locked_folio); - offset = folio_pos(locked_folio) + folio_size(locked_folio); - } - } - return btrfs_mark_ordered_io_finished(inode, NULL, offset, bytes, false); } @@ -564,7 +526,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, kunmap_local(kaddr); folio_put(folio); } - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* @@ -1129,19 +1090,14 @@ static void submit_uncompressed_range(struct btrfs_inode *inode, &wbc, false); wbc_detach_inode(&wbc); if (ret < 0) { - btrfs_cleanup_ordered_extents(inode, locked_folio, - start, end - start + 1); - if (locked_folio) { - const u64 page_start = folio_pos(locked_folio); - - folio_start_writeback(locked_folio); - folio_end_writeback(locked_folio); - btrfs_mark_ordered_io_finished(inode, locked_folio, - page_start, PAGE_SIZE, - !ret); - mapping_set_error(locked_folio->mapping, ret); - folio_unlock(locked_folio); - } + btrfs_cleanup_ordered_extents(inode, start, end - start + 1); + if (locked_folio) + btrfs_folio_end_lock(inode->root->fs_info, locked_folio, + start, async_extent->ram_size); + btrfs_err_rl(inode->root->fs_info, + "%s failed, root=%llu inode=%llu start=%llu len=%llu: %d", + __func__, btrfs_root_id(inode->root), + btrfs_ino(inode), start, async_extent->ram_size, ret); } } @@ -1373,6 +1329,17 @@ static noinline int cow_file_range(struct btrfs_inode *inode, alloc_hint = btrfs_get_extent_allocation_hint(inode, start, num_bytes); /* + * We're not doing compressed IO, don't unlock the first page (which + * the caller expects to stay locked), don't clear any dirty bits and + * don't set any writeback bits. + * + * Do set the Ordered (Private2) bit so we know this page was properly + * setup for writepage. + */ + page_ops = (keep_locked ? 0 : PAGE_UNLOCK); + page_ops |= PAGE_SET_ORDERED; + + /* * Relocation relies on the relocated extents to have exactly the same * size as the original extents. Normally writeback for relocation data * extents follows a NOCOW path because relocation preallocates the @@ -1431,6 +1398,10 @@ static noinline int cow_file_range(struct btrfs_inode *inode, file_extent.offset = 0; file_extent.compression = BTRFS_COMPRESS_NONE; + /* + * Locked range will be released either during error clean up or + * after the whole range is finished. + */ lock_extent(&inode->io_tree, start, start + cur_alloc_size - 1, &cached); @@ -1476,21 +1447,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, btrfs_dec_block_group_reservations(fs_info, ins.objectid); - /* - * We're not doing compressed IO, don't unlock the first page - * (which the caller expects to stay locked), don't clear any - * dirty bits and don't set any writeback bits - * - * Do set the Ordered flag so we know this page was - * properly setup for writepage. - */ - page_ops = (keep_locked ? 0 : PAGE_UNLOCK); - page_ops |= PAGE_SET_ORDERED; - - extent_clear_unlock_delalloc(inode, start, start + cur_alloc_size - 1, - locked_folio, &cached, - EXTENT_LOCKED | EXTENT_DELALLOC, - page_ops); if (num_bytes < cur_alloc_size) num_bytes = 0; else @@ -1507,6 +1463,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode, if (ret) goto out_unlock; } + extent_clear_unlock_delalloc(inode, orig_start, end, locked_folio, &cached, + EXTENT_LOCKED | EXTENT_DELALLOC, page_ops); done: if (done_offset) *done_offset = end; @@ -1527,35 +1485,30 @@ out_unlock: * We process each region below. */ - clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; - page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; - /* * For the range (1). We have already instantiated the ordered extents * for this region. They are cleaned up by * btrfs_cleanup_ordered_extents() in e.g, - * btrfs_run_delalloc_range(). EXTENT_LOCKED | EXTENT_DELALLOC are - * already cleared in the above loop. And, EXTENT_DELALLOC_NEW | - * EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV are handled by the cleanup - * function. + * btrfs_run_delalloc_range(). + * EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV + * are also handled by the cleanup function. * - * However, in case of @keep_locked, we still need to unlock the pages - * (except @locked_folio) to ensure all the pages are unlocked. + * So here we only clear EXTENT_LOCKED and EXTENT_DELALLOC flag, and + * finish the writeback of the involved folios, which will be never submitted. */ - if (keep_locked && orig_start < start) { + if (orig_start < start) { + clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; + if (!locked_folio) mapping_set_error(inode->vfs_inode.i_mapping, ret); extent_clear_unlock_delalloc(inode, orig_start, start - 1, - locked_folio, NULL, 0, page_ops); + locked_folio, NULL, clear_bits, page_ops); } - /* - * At this point we're unlocked, we want to make sure we're only - * clearing these flags under the extent lock, so lock the rest of the - * range and clear everything up. - */ - lock_extent(&inode->io_tree, start, end, NULL); + clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; /* * For the range (2). If we reserved an extent for our delalloc range @@ -1589,6 +1542,10 @@ out_unlock: btrfs_qgroup_free_data(inode, NULL, start + cur_alloc_size, end - start - cur_alloc_size + 1, NULL); } + btrfs_err_rl(fs_info, + "%s failed, root=%llu inode=%llu start=%llu len=%llu: %d", + __func__, btrfs_root_id(inode->root), + btrfs_ino(inode), orig_start, end + 1 - orig_start, ret); return ret; } @@ -1809,7 +1766,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, bytes = range_bytes; spin_lock(&sinfo->lock); - btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes); + btrfs_space_info_update_bytes_may_use(sinfo, bytes); spin_unlock(&sinfo->lock); if (count > 0) @@ -1837,7 +1794,6 @@ struct can_nocow_file_extent_args { /* End file offset (inclusive) of the range we want to NOCOW. */ u64 end; bool writeback_path; - bool strict; /* * Free the path passed to can_nocow_file_extent() once it's not needed * anymore. @@ -1892,8 +1848,7 @@ static int can_nocow_file_extent(struct btrfs_path *path, * for its subvolume was created, then this implies the extent is shared, * hence we must COW. */ - if (!args->strict && - btrfs_file_extent_generation(leaf, fi) <= + if (btrfs_file_extent_generation(leaf, fi) <= btrfs_root_last_snapshot(&root->root_item)) goto out; @@ -1922,9 +1877,8 @@ static int can_nocow_file_extent(struct btrfs_path *path, */ btrfs_release_path(path); - ret = btrfs_cross_ref_exist(root, btrfs_ino(inode), - key->offset - args->file_extent.offset, - args->file_extent.disk_bytenr, args->strict, path); + ret = btrfs_cross_ref_exist(inode, key->offset - args->file_extent.offset, + args->file_extent.disk_bytenr, path); WARN_ON_ONCE(ret > 0 && is_freespace_inode); if (ret != 0) goto out; @@ -1971,6 +1925,53 @@ static int can_nocow_file_extent(struct btrfs_path *path, } /* + * Cleanup the dirty folios which will never be submitted due to error. + * + * When running a delalloc range, we may need to split the ranges (due to + * fragmentation or NOCOW). If we hit an error in the later part, we will error + * out and previously successfully executed range will never be submitted, thus + * we have to cleanup those folios by clearing their dirty flag, starting and + * finishing the writeback. + */ +static void cleanup_dirty_folios(struct btrfs_inode *inode, + struct folio *locked_folio, + u64 start, u64 end, int error) +{ + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct address_space *mapping = inode->vfs_inode.i_mapping; + pgoff_t start_index = start >> PAGE_SHIFT; + pgoff_t end_index = end >> PAGE_SHIFT; + u32 len; + + ASSERT(end + 1 - start < U32_MAX); + ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && + IS_ALIGNED(end + 1, fs_info->sectorsize)); + len = end + 1 - start; + + /* + * Handle the locked folio first. + * The btrfs_folio_clamp_*() helpers can handle range out of the folio case. + */ + btrfs_folio_clamp_finish_io(fs_info, locked_folio, start, len); + + for (pgoff_t index = start_index; index <= end_index; index++) { + struct folio *folio; + + /* Already handled at the beginning. */ + if (index == locked_folio->index) + continue; + folio = __filemap_get_folio(mapping, index, FGP_LOCK, GFP_NOFS); + /* Cache already dropped, no need to do any cleanup. */ + if (IS_ERR(folio)) + continue; + btrfs_folio_clamp_finish_io(fs_info, locked_folio, start, len); + folio_unlock(folio); + folio_put(folio); + } + mapping_set_error(mapping, error); +} + +/* * when nowcow writeback call back. This checks for snapshots or COW copies * of the extents that exist in the file, and COWs the file as required. * @@ -1985,6 +1986,11 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, struct btrfs_root *root = inode->root; struct btrfs_path *path; u64 cow_start = (u64)-1; + /* + * If not 0, represents the inclusive end of the last fallback_to_cow() + * range. Only for error handling. + */ + u64 cow_end = 0; u64 cur_offset = start; int ret; bool check_prev = true; @@ -2145,6 +2151,7 @@ must_cow: found_key.offset - 1); cow_start = (u64)-1; if (ret) { + cow_end = found_key.offset - 1; btrfs_dec_nocow_writers(nocow_bg); goto error; } @@ -2218,11 +2225,12 @@ must_cow: cow_start = cur_offset; if (cow_start != (u64)-1) { - cur_offset = end; ret = fallback_to_cow(inode, locked_folio, cow_start, end); cow_start = (u64)-1; - if (ret) + if (ret) { + cow_end = end; goto error; + } } btrfs_free_path(path); @@ -2230,12 +2238,41 @@ must_cow: error: /* + * There are several error cases: + * + * 1) Failed without falling back to COW + * start cur_offset end + * |/////////////| | + * + * For range [start, cur_offset) the folios are already unlocked (except + * @locked_folio), EXTENT_DELALLOC already removed. + * Only need to clear the dirty flag as they will never be submitted. + * Ordered extent and extent maps are handled by + * btrfs_mark_ordered_io_finished() inside run_delalloc_range(). + * + * 2) Failed with error from fallback_to_cow() + * start cur_offset cow_end end + * |/////////////|-----------| | + * + * For range [start, cur_offset) it's the same as case 1). + * But for range [cur_offset, cow_end), the folios have dirty flag + * cleared and unlocked, EXTENT_DEALLLOC cleared by cow_file_range(). + * + * Thus we should not call extent_clear_unlock_delalloc() on range + * [cur_offset, cow_end), as the folios are already unlocked. + * + * So clear the folio dirty flags for [start, cur_offset) first. + */ + if (cur_offset > start) + cleanup_dirty_folios(inode, locked_folio, start, cur_offset - 1, ret); + + /* * If an error happened while a COW region is outstanding, cur_offset - * needs to be reset to cow_start to ensure the COW region is unlocked - * as well. + * needs to be reset to @cow_end + 1 to skip the COW range, as + * cow_file_range() will do the proper cleanup at error. */ - if (cow_start != (u64)-1) - cur_offset = cow_start; + if (cow_end) + cur_offset = cow_end + 1; /* * We need to lock the extent here because we're clearing DELALLOC and @@ -2255,6 +2292,10 @@ error: btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL); } btrfs_free_path(path); + btrfs_err_rl(fs_info, + "%s failed, root=%llu inode=%llu start=%llu len=%llu: %d", + __func__, btrfs_root_id(inode->root), + btrfs_ino(inode), start, end + 1 - start, ret); return ret; } @@ -2305,8 +2346,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct folio *locked_fol out: if (ret < 0) - btrfs_cleanup_ordered_extents(inode, locked_folio, start, - end - start + 1); + btrfs_cleanup_ordered_extents(inode, start, end - start + 1); return ret; } @@ -2921,7 +2961,6 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(struct btrfs_file_extent_item)); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* @@ -4085,7 +4124,6 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, struct btrfs_inode_item); fill_inode_item(trans, leaf, inode_item, &inode->vfs_inode); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_set_inode_last_trans(trans, inode); ret = 0; failed: @@ -6380,7 +6418,6 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, } } - btrfs_mark_buffer_dirty(trans, path->nodes[0]); /* * We don't need the path anymore, plus inheriting properties, adding * ACLs, security xattrs, orphan item or adding the link, will result in @@ -7011,8 +7048,6 @@ static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr) * @orig_start: (optional) Return the original file offset of the file extent * @orig_len: (optional) Return the original on-disk length of the file extent * @ram_bytes: (optional) Return the ram_bytes of the file extent - * @strict: if true, omit optimizations that might force us into unnecessary - * cow. e.g., don't trust generation number. * * Return: * >0 and update @len if we can do nocow write @@ -7024,7 +7059,7 @@ static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr) */ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, struct btrfs_file_extent *file_extent, - bool nowait, bool strict) + bool nowait) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct can_nocow_file_extent_args nocow_args = { 0 }; @@ -7077,7 +7112,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, nocow_args.start = offset; nocow_args.end = offset + *len - 1; - nocow_args.strict = strict; nocow_args.free_path = true; ret = can_nocow_file_extent(path, &key, BTRFS_I(inode), &nocow_args); @@ -8027,31 +8061,45 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* src is a subvolume */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } else { /* src is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(old_dentry->d_inode), old_name, &old_rename_ctx); - if (!ret) - ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); - } - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } + ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } /* dest is a subvolume */ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, BTRFS_I(new_dir), new_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } else { /* dest is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(new_dentry->d_inode), new_name, &new_rename_ctx); - if (!ret) - ret = btrfs_update_inode(trans, BTRFS_I(new_inode)); - } - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } + ret = btrfs_update_inode(trans, BTRFS_I(new_inode)); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), @@ -8287,16 +8335,23 @@ static int btrfs_rename(struct mnt_idmap *idmap, if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } else { ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), &old_fname.disk_name, &rename_ctx); - if (!ret) - ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); - } - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } + ret = btrfs_update_inode(trans, BTRFS_I(old_inode)); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } if (new_inode) { @@ -8304,18 +8359,27 @@ static int btrfs_rename(struct mnt_idmap *idmap, if (unlikely(btrfs_ino(BTRFS_I(new_inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { ret = btrfs_unlink_subvol(trans, BTRFS_I(new_dir), new_dentry); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } BUG_ON(new_inode->i_nlink == 0); } else { ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(d_inode(new_dentry)), &new_fname.disk_name); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } - if (!ret && new_inode->i_nlink == 0) + if (new_inode->i_nlink == 0) { ret = btrfs_orphan_add(trans, BTRFS_I(d_inode(new_dentry))); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_fail; + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_fail; + } } } @@ -8655,7 +8719,6 @@ static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir, ptr = btrfs_file_extent_inline_start(ei); write_extent_buffer(leaf, symname, ptr, name_len); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); d_instantiate_new(dentry, inode); @@ -9078,9 +9141,9 @@ out: } struct btrfs_encoded_read_private { - wait_queue_head_t wait; + struct completion done; void *uring_ctx; - atomic_t pending; + refcount_t pending_refs; blk_status_t status; }; @@ -9099,14 +9162,14 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio) */ WRITE_ONCE(priv->status, bbio->bio.bi_status); } - if (atomic_dec_and_test(&priv->pending)) { + if (refcount_dec_and_test(&priv->pending_refs)) { int err = blk_status_to_errno(READ_ONCE(priv->status)); if (priv->uring_ctx) { btrfs_uring_read_extent_endio(priv->uring_ctx, err); kfree(priv); } else { - wake_up(&priv->wait); + complete(&priv->done); } } bio_put(&bbio->bio); @@ -9126,8 +9189,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, if (!priv) return -ENOMEM; - init_waitqueue_head(&priv->wait); - atomic_set(&priv->pending, 1); + init_completion(&priv->done); + refcount_set(&priv->pending_refs, 1); priv->status = 0; priv->uring_ctx = uring_ctx; @@ -9140,7 +9203,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE); if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) { - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, @@ -9155,11 +9218,11 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, disk_io_size -= bytes; } while (disk_io_size); - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); if (uring_ctx) { - if (atomic_dec_return(&priv->pending) == 0) { + if (refcount_dec_and_test(&priv->pending_refs)) { ret = blk_status_to_errno(READ_ONCE(priv->status)); btrfs_uring_read_extent_endio(uring_ctx, ret); kfree(priv); @@ -9168,8 +9231,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, return -EIOCBQUEUED; } else { - if (atomic_dec_return(&priv->pending) != 0) - io_wait_event(priv->wait, !atomic_read(&priv->pending)); + if (!refcount_dec_and_test(&priv->pending_refs)) + wait_for_completion_io(&priv->done); /* See btrfs_encoded_read_endio() for ordering. */ ret = blk_status_to_errno(READ_ONCE(priv->status)); kfree(priv); @@ -9799,15 +9862,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; + + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); /* * If the swap file was just created, make sure delalloc is done. If the @@ -9816,22 +9889,32 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; + } + + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; } /* @@ -9846,7 +9929,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9860,7 +9944,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9876,11 +9961,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (btrfs_root_dead(root)) { spin_unlock(&root->root_item_lock); + btrfs_drew_write_unlock(&root->snapshot_lock); btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -9888,24 +9975,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9917,23 +10019,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } + + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9968,7 +10092,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10009,20 +10132,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - start += len; + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + + cond_resched(); } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10035,6 +10161,10 @@ out: btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3af8bb0c8d75..6c18bad53cd3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -403,86 +403,6 @@ update_flags: return ret; } -/* - * Start exclusive operation @type, return true on success - */ -bool btrfs_exclop_start(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation type) -{ - bool ret = false; - - spin_lock(&fs_info->super_lock); - if (fs_info->exclusive_operation == BTRFS_EXCLOP_NONE) { - fs_info->exclusive_operation = type; - ret = true; - } - spin_unlock(&fs_info->super_lock); - - return ret; -} - -/* - * Conditionally allow to enter the exclusive operation in case it's compatible - * with the running one. This must be paired with btrfs_exclop_start_unlock and - * btrfs_exclop_finish. - * - * Compatibility: - * - the same type is already running - * - when trying to add a device and balance has been paused - * - not BTRFS_EXCLOP_NONE - this is intentionally incompatible and the caller - * must check the condition first that would allow none -> @type - */ -bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation type) -{ - spin_lock(&fs_info->super_lock); - if (fs_info->exclusive_operation == type || - (fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED && - type == BTRFS_EXCLOP_DEV_ADD)) - return true; - - spin_unlock(&fs_info->super_lock); - return false; -} - -void btrfs_exclop_start_unlock(struct btrfs_fs_info *fs_info) -{ - spin_unlock(&fs_info->super_lock); -} - -void btrfs_exclop_finish(struct btrfs_fs_info *fs_info) -{ - spin_lock(&fs_info->super_lock); - WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE); - spin_unlock(&fs_info->super_lock); - sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation"); -} - -void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, - enum btrfs_exclusive_operation op) -{ - switch (op) { - case BTRFS_EXCLOP_BALANCE_PAUSED: - spin_lock(&fs_info->super_lock); - ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || - fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || - fs_info->exclusive_operation == BTRFS_EXCLOP_NONE || - fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); - fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED; - spin_unlock(&fs_info->super_lock); - break; - case BTRFS_EXCLOP_BALANCE: - spin_lock(&fs_info->super_lock); - ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); - fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE; - spin_unlock(&fs_info->super_lock); - break; - default: - btrfs_warn(fs_info, - "invalid exclop balance operation %d requested", op); - } -} - static int btrfs_ioctl_getversion(struct inode *inode, int __user *arg) { return put_user(inode->i_generation, arg); @@ -551,17 +471,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, return ret; } -int __pure btrfs_is_empty_uuid(const u8 *uuid) -{ - int i; - - for (i = 0; i < BTRFS_UUID_SIZE; i++) { - if (uuid[i]) - return 0; - } - return 1; -} - /* * Calculate the number of transaction items to reserve for creating a subvolume * or snapshot, not including the inode, directory entries, or parent directory. @@ -2635,6 +2544,15 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) goto out; } + /* + * Don't allow defrag on pre-content watched files, as it could + * populate the page cache with 0's via readahead. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + ret = -EINVAL; + goto out; + } + if (argp) { if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; @@ -3007,7 +2925,6 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key); btrfs_set_dir_item_key(path->nodes[0], di, &disk_key); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); btrfs_set_fs_incompat(fs_info, DEFAULT_SUBVOL); @@ -4878,25 +4795,29 @@ out_fail: return ret; } +struct btrfs_uring_encoded_data { + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov; + struct iov_iter iter; +}; + static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags) { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags); size_t copy_end; - struct btrfs_ioctl_encoded_io_args args = { 0 }; int ret; u64 disk_bytenr, disk_io_size; struct file *file; struct btrfs_inode *inode; struct btrfs_fs_info *fs_info; struct extent_io_tree *io_tree; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; loff_t pos; struct kiocb kiocb; struct extent_state *cached_state = NULL; u64 start, lockend; void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; if (!capable(CAP_SYS_ADMIN)) { ret = -EPERM; @@ -4910,43 +4831,64 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue if (issue_flags & IO_URING_F_COMPAT) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); - if (copy_from_user(&args32, sqe_addr, copy_end)) { - ret = -EFAULT; - goto out_acct; - } - args.iov = compat_ptr(args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags; #else return -ENOTTY; #endif } else { copy_end = copy_end_kernel; - if (copy_from_user(&args, sqe_addr, copy_end)) { - ret = -EFAULT; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; goto out_acct; } - } - if (args.flags != 0) - return -EINVAL; + io_uring_cmd_get_async_data(cmd)->op_data = data; - ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), - &iov, &iter); - if (ret < 0) - goto out_acct; + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; - if (iov_iter_count(&iter) == 0) { - ret = 0; - goto out_free; + if (copy_from_user(&args32, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + + if (data->args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + data->iov = data->iovstack; + ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_free; + } } - pos = args.offset; - ret = rw_verify_area(READ, file, &pos, args.len); + pos = data->args.offset; + ret = rw_verify_area(READ, file, &pos, data->args.len); if (ret < 0) goto out_free; @@ -4959,15 +4901,16 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start = ALIGN_DOWN(pos, fs_info->sectorsize); lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; - ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state, + ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state, &disk_bytenr, &disk_io_size); if (ret < 0 && ret != -EIOCBQUEUED) goto out_free; file_accessed(file); - if (copy_to_user(sqe_addr + copy_end, (const char *)&args + copy_end_kernel, - sizeof(args) - copy_end_kernel)) { + if (copy_to_user(sqe_addr + copy_end, + (const char *)&data->args + copy_end_kernel, + sizeof(data->args) - copy_end_kernel)) { if (ret == -EIOCBQUEUED) { unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); @@ -4977,40 +4920,22 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue } if (ret == -EIOCBQUEUED) { - u64 count; - - /* - * If we've optimized things by storing the iovecs on the stack, - * undo this. - */ - if (!iov) { - iov = kmalloc(sizeof(struct iovec) * args.iovcnt, GFP_NOFS); - if (!iov) { - unlock_extent(io_tree, start, lockend, &cached_state); - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); - ret = -ENOMEM; - goto out_acct; - } - - memcpy(iov, iovstack, sizeof(struct iovec) * args.iovcnt); - } - - count = min_t(u64, iov_iter_count(&iter), disk_io_size); + u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size); /* Match ioctl by not returning past EOF if uncompressed. */ - if (!args.compression) - count = min_t(u64, count, args.len); + if (!data->args.compression) + count = min_t(u64, count, data->args.len); - ret = btrfs_uring_read_extent(&kiocb, &iter, start, lockend, - cached_state, disk_bytenr, - disk_io_size, count, - args.compression, iov, cmd); + ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend, + cached_state, disk_bytenr, disk_io_size, + count, data->args.compression, + data->iov, cmd); goto out_acct; } out_free: - kfree(iov); + kfree(data->iov); out_acct: if (ret > 0) @@ -5020,6 +4945,128 @@ out_acct: return ret; } +static int btrfs_uring_encoded_write(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + loff_t pos; + struct kiocb kiocb; + struct file *file; + ssize_t ret; + void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; + + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_acct; + } + + file = cmd->file; + sqe_addr = u64_to_user_ptr(READ_ONCE(cmd->sqe->addr)); + + if (!(file->f_mode & FMODE_WRITE)) { + ret = -EBADF; + goto out_acct; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; + goto out_acct; + } + + io_uring_cmd_get_async_data(cmd)->op_data = data; + + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; + + if (copy_from_user(&args32, sqe_addr, sizeof(args32))) { + ret = -EFAULT; + goto out_acct; + } + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; + data->args.len = args32.len; + data->args.unencoded_len = args32.unencoded_len; + data->args.unencoded_offset = args32.unencoded_offset; + data->args.compression = args32.compression; + data->args.encryption = args32.encryption; + memcpy(data->args.reserved, args32.reserved, + sizeof(data->args.reserved)); +#else + ret = -ENOTTY; + goto out_acct; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, sizeof(data->args))) { + ret = -EFAULT; + goto out_acct; + } + } + + ret = -EINVAL; + if (data->args.flags != 0) + goto out_acct; + if (memchr_inv(data->args.reserved, 0, sizeof(data->args.reserved))) + goto out_acct; + if (data->args.compression == BTRFS_ENCODED_IO_COMPRESSION_NONE && + data->args.encryption == BTRFS_ENCODED_IO_ENCRYPTION_NONE) + goto out_acct; + if (data->args.compression >= BTRFS_ENCODED_IO_COMPRESSION_TYPES || + data->args.encryption >= BTRFS_ENCODED_IO_ENCRYPTION_TYPES) + goto out_acct; + if (data->args.unencoded_offset > data->args.unencoded_len) + goto out_acct; + if (data->args.len > data->args.unencoded_len - data->args.unencoded_offset) + goto out_acct; + + data->iov = data->iovstack; + ret = import_iovec(ITER_SOURCE, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_iov; + } + } + + if (issue_flags & IO_URING_F_NONBLOCK) { + ret = -EAGAIN; + goto out_acct; + } + + pos = data->args.offset; + ret = rw_verify_area(WRITE, file, &pos, data->args.len); + if (ret < 0) + goto out_iov; + + init_sync_kiocb(&kiocb, file); + ret = kiocb_set_rw_flags(&kiocb, 0, WRITE); + if (ret) + goto out_iov; + kiocb.ki_pos = pos; + + file_start_write(file); + + ret = btrfs_do_write_iter(&kiocb, &data->iter, &data->args); + if (ret > 0) + fsnotify_modify(file); + + file_end_write(file); +out_iov: + kfree(data->iov); +out_acct: + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { switch (cmd->cmd_op) { @@ -5028,6 +5075,12 @@ int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) case BTRFS_IOC_ENCODED_READ_32: #endif return btrfs_uring_encoded_read(cmd, issue_flags); + + case BTRFS_IOC_ENCODED_WRITE: +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + case BTRFS_IOC_ENCODED_WRITE_32: +#endif + return btrfs_uring_encoded_write(cmd, issue_flags); } return -EINVAL; @@ -5300,6 +5353,8 @@ long btrfs_ioctl(struct file *file, unsigned int return fsverity_ioctl_enable(file, (const void __user *)argp); case FS_IOC_MEASURE_VERITY: return fsverity_ioctl_measure(file, argp); + case FS_IOC_READ_VERITY_METADATA: + return fsverity_ioctl_read_metadata(file, argp); case BTRFS_IOC_ENCODED_READ: return btrfs_ioctl_encoded_read(file, argp, false); case BTRFS_IOC_ENCODED_WRITE: diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 2b760c8778f8..ce915fcda43b 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -19,7 +19,6 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int btrfs_ioctl_get_supported_features(void __user *arg); void btrfs_sync_inode_flags_to_i_flags(struct inode *inode); -int __pure btrfs_is_empty_uuid(const u8 *uuid); void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_balance_args *bargs); int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index 35036b151bf5..c69e57ff804b 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -199,8 +199,13 @@ static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb) { lockdep_assert_held_write(&eb->lock); } +static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb) +{ + lockdep_assert_held_read(&eb->lock); +} #else static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb) { } +static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { } #endif void btrfs_unlock_up_safe(struct btrfs_path *path, int level); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a6f92836c9b1..b90fabe302e6 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -673,9 +673,6 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, key.offset = dst; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, 0); - - btrfs_mark_buffer_dirty(trans, path->nodes[0]); - btrfs_free_path(path); return ret; } @@ -752,8 +749,6 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_excl(leaf, qgroup_info, 0); btrfs_set_qgroup_info_excl_cmpr(leaf, qgroup_info, 0); - btrfs_mark_buffer_dirty(trans, leaf); - btrfs_release_path(path); key.type = BTRFS_QGROUP_LIMIT_KEY; @@ -771,8 +766,6 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_rsv_rfer(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_rsv_excl(leaf, qgroup_limit, 0); - btrfs_mark_buffer_dirty(trans, leaf); - ret = 0; out: btrfs_free_path(path); @@ -859,9 +852,6 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, qgroup->max_excl); btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, qgroup->rsv_rfer); btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, qgroup->rsv_excl); - - btrfs_mark_buffer_dirty(trans, l); - out: btrfs_free_path(path); return ret; @@ -905,9 +895,6 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_rfer_cmpr(l, qgroup_info, qgroup->rfer_cmpr); btrfs_set_qgroup_info_excl(l, qgroup_info, qgroup->excl); btrfs_set_qgroup_info_excl_cmpr(l, qgroup_info, qgroup->excl_cmpr); - - btrfs_mark_buffer_dirty(trans, l); - out: btrfs_free_path(path); return ret; @@ -947,9 +934,6 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) btrfs_set_qgroup_status_generation(l, ptr, trans->transid); btrfs_set_qgroup_status_rescan(l, ptr, fs_info->qgroup_rescan_progress.objectid); - - btrfs_mark_buffer_dirty(trans, l); - out: btrfs_free_path(path); return ret; @@ -1121,6 +1105,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -1129,8 +1114,6 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_rescan(leaf, ptr, 0); - btrfs_mark_buffer_dirty(trans, leaf); - key.objectid = 0; key.type = BTRFS_ROOT_REF_KEY; key.offset = 0; @@ -1254,8 +1237,6 @@ out_add_root: spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (simple) - btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ @@ -1839,9 +1820,19 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) * Thus its reserved space should all be zero, no matter if qgroup * is consistent or the mode. */ - WARN_ON(qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] || - qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] || - qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]); + if (qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + btrfs_warn_rl(fs_info, +"to be deleted qgroup %u/%llu has non-zero numbers, data %llu meta prealloc %llu meta pertrans %llu", + btrfs_qgroup_level(qgroup->qgroupid), + btrfs_qgroup_subvolid(qgroup->qgroupid), + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA], + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC], + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]); + + } /* * The same for rfer/excl numbers, but that's only if our qgroup is * consistent and if it's in regular qgroup mode. @@ -1850,8 +1841,9 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) */ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL && !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)) { - if (WARN_ON(qgroup->rfer || qgroup->excl || - qgroup->rfer_cmpr || qgroup->excl_cmpr)) { + if (qgroup->rfer || qgroup->excl || + qgroup->rfer_cmpr || qgroup->excl_cmpr) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); btrfs_warn_rl(fs_info, "to be deleted qgroup %u/%llu has non-zero numbers, rfer %llu rfer_cmpr %llu excl %llu excl_cmpr %llu", btrfs_qgroup_level(qgroup->qgroupid), diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index 9ffc79f250fb..1834011ccc49 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -13,12 +13,13 @@ #include "volumes.h" #include "print-tree.h" -static void btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, +static int btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_key *oldkey, u64 newlen, u64 frontpad) { - struct btrfs_stripe_extent *extent; + struct btrfs_root *stripe_root = trans->fs_info->stripe_root; + struct btrfs_stripe_extent *extent, *newitem; struct extent_buffer *leaf; int slot; size_t item_size; @@ -27,23 +28,39 @@ static void btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans, .type = BTRFS_RAID_STRIPE_KEY, .offset = newlen, }; + int ret; + ASSERT(newlen > 0); ASSERT(oldkey->type == BTRFS_RAID_STRIPE_KEY); leaf = path->nodes[0]; slot = path->slots[0]; item_size = btrfs_item_size(leaf, slot); + + newitem = kzalloc(item_size, GFP_NOFS); + if (!newitem) + return -ENOMEM; + extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent); for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) { struct btrfs_raid_stride *stride = &extent->strides[i]; u64 phys; - phys = btrfs_raid_stride_physical(leaf, stride); - btrfs_set_raid_stride_physical(leaf, stride, phys + frontpad); + phys = btrfs_raid_stride_physical(leaf, stride) + frontpad; + btrfs_set_stack_raid_stride_physical(&newitem->strides[i], phys); } - btrfs_set_item_key_safe(trans, path, &newkey); + ret = btrfs_del_item(trans, stripe_root, path); + if (ret) + goto out; + + btrfs_release_path(path); + ret = btrfs_insert_item(trans, stripe_root, &newkey, newitem, item_size); + +out: + kfree(newitem); + return ret; } int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 length) @@ -59,9 +76,22 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le int slot; int ret; - if (!stripe_root) + if (!btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE) || !stripe_root) return 0; + if (!btrfs_is_testing(fs_info)) { + struct btrfs_chunk_map *map; + bool use_rst; + + map = btrfs_find_chunk_map(fs_info, start, length); + if (!map) + return -EINVAL; + use_rst = btrfs_need_stripe_tree_update(fs_info, map->type); + btrfs_free_chunk_map(map); + if (!use_rst) + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -85,6 +115,37 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le found_end = found_start + key.offset; ret = 0; + /* + * The stripe extent starts before the range we want to delete, + * but the range spans more than one stripe extent: + * + * |--- RAID Stripe Extent ---||--- RAID Stripe Extent ---| + * |--- keep ---|--- drop ---| + * + * This means we have to get the previous item, truncate its + * length and then restart the search. + */ + if (found_start > start) { + if (slot == 0) { + ret = btrfs_previous_item(stripe_root, path, start, + BTRFS_RAID_STRIPE_KEY); + if (ret) { + if (ret > 0) + ret = -ENOENT; + break; + } + } else { + path->slots[0]--; + } + + leaf = path->nodes[0]; + slot = path->slots[0]; + btrfs_item_key_to_cpu(leaf, &key, slot); + found_start = key.objectid; + found_end = found_start + key.offset; + ASSERT(found_start <= start); + } + if (key.type != BTRFS_RAID_STRIPE_KEY) break; @@ -96,6 +157,54 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le found_start, found_end); /* + * The stripe extent starts before the range we want to delete + * and ends after the range we want to delete, i.e. we're + * punching a hole in the stripe extent: + * + * |--- RAID Stripe Extent ---| + * | keep |--- drop ---| keep | + * + * This means we need to a) truncate the existing item and b) + * create a second item for the remaining range. + */ + if (found_start < start && found_end > end) { + size_t item_size; + u64 diff_start = start - found_start; + u64 diff_end = found_end - end; + struct btrfs_stripe_extent *extent; + struct btrfs_key newkey = { + .objectid = end, + .type = BTRFS_RAID_STRIPE_KEY, + .offset = diff_end, + }; + + /* The "right" item. */ + ret = btrfs_duplicate_item(trans, stripe_root, path, &newkey); + if (ret) + break; + + item_size = btrfs_item_size(leaf, path->slots[0]); + extent = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_stripe_extent); + + for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) { + struct btrfs_raid_stride *stride = &extent->strides[i]; + u64 phys; + + phys = btrfs_raid_stride_physical(leaf, stride); + phys += diff_start + length; + btrfs_set_raid_stride_physical(leaf, stride, phys); + } + + /* The "left" item. */ + path->slots[0]--; + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + btrfs_partially_delete_raid_extent(trans, path, &key, + diff_start, 0); + break; + } + + /* * The stripe extent starts before the range we want to delete: * * |--- RAID Stripe Extent ---| @@ -105,11 +214,18 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le * length to the new size and then re-insert the item. */ if (found_start < start) { - u64 diff = start - found_start; + u64 diff_start = start - found_start; btrfs_partially_delete_raid_extent(trans, path, &key, - diff, 0); - break; + diff_start, 0); + + start += (key.offset - diff_start); + length -= (key.offset - diff_start); + if (length == 0) + break; + + btrfs_release_path(path); + continue; } /* @@ -122,13 +238,16 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le * length to the new size and then re-insert the item. */ if (found_end > end) { - u64 diff = found_end - end; + u64 diff_end = found_end - end; btrfs_partially_delete_raid_extent(trans, path, &key, - diff, diff); + key.offset - length, + length); + ASSERT(key.offset - diff_end == length); break; } + /* Finally we can delete the whole item, no more special cases. */ ret = btrfs_del_item(trans, stripe_root, path); if (ret) break; @@ -169,7 +288,6 @@ static int update_raid_extent_item(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, stripe_extent, btrfs_item_ptr_offset(leaf, slot), item_size); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); return ret; @@ -199,12 +317,8 @@ int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, for (int i = 0; i < num_stripes; i++) { u64 devid = bioc->stripes[i].dev->devid; u64 physical = bioc->stripes[i].physical; - u64 length = bioc->stripes[i].length; struct btrfs_raid_stride *raid_stride = &stripe_extent->strides[i]; - if (length == 0) - length = bioc->size; - btrfs_set_stack_raid_stride_devid(raid_stride, devid); btrfs_set_stack_raid_stride_physical(raid_stride, physical); } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index bf267bdfa8f8..af0969b70b53 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -342,12 +342,6 @@ static bool handle_useless_nodes(struct reloc_control *rc, if (cur == node) ret = true; - /* The node is the lowest node */ - if (cur->lowest) { - list_del_init(&cur->lower); - cur->lowest = 0; - } - /* Cleanup the lower edges */ while (!list_empty(&cur->lower)) { struct btrfs_backref_edge *edge; @@ -373,7 +367,6 @@ static bool handle_useless_nodes(struct reloc_control *rc, * cache to avoid unnecessary backref lookup. */ if (cur->level > 0) { - list_add(&cur->list, &cache->detached); cur->detached = 1; } else { rb_erase(&cur->rb_node, &cache->rb_root); @@ -426,7 +419,6 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( goto out; } - node->lowest = 1; cur = node; /* Breadth-first search to build backref cache */ @@ -470,92 +462,6 @@ out: } /* - * helper to add backref node for the newly created snapshot. - * the backref node is created by cloning backref node that - * corresponds to root of source tree - */ -static int clone_backref_node(struct btrfs_trans_handle *trans, - struct reloc_control *rc, - const struct btrfs_root *src, - struct btrfs_root *dest) -{ - struct btrfs_root *reloc_root = src->reloc_root; - struct btrfs_backref_cache *cache = &rc->backref_cache; - struct btrfs_backref_node *node = NULL; - struct btrfs_backref_node *new_node; - struct btrfs_backref_edge *edge; - struct btrfs_backref_edge *new_edge; - struct rb_node *rb_node; - - rb_node = rb_simple_search(&cache->rb_root, src->commit_root->start); - if (rb_node) { - node = rb_entry(rb_node, struct btrfs_backref_node, rb_node); - if (node->detached) - node = NULL; - else - BUG_ON(node->new_bytenr != reloc_root->node->start); - } - - if (!node) { - rb_node = rb_simple_search(&cache->rb_root, - reloc_root->commit_root->start); - if (rb_node) { - node = rb_entry(rb_node, struct btrfs_backref_node, - rb_node); - BUG_ON(node->detached); - } - } - - if (!node) - return 0; - - new_node = btrfs_backref_alloc_node(cache, dest->node->start, - node->level); - if (!new_node) - return -ENOMEM; - - new_node->lowest = node->lowest; - new_node->checked = 1; - new_node->root = btrfs_grab_root(dest); - ASSERT(new_node->root); - - if (!node->lowest) { - list_for_each_entry(edge, &node->lower, list[UPPER]) { - new_edge = btrfs_backref_alloc_edge(cache); - if (!new_edge) - goto fail; - - btrfs_backref_link_edge(new_edge, edge->node[LOWER], - new_node, LINK_UPPER); - } - } else { - list_add_tail(&new_node->lower, &cache->leaves); - } - - rb_node = rb_simple_insert(&cache->rb_root, new_node->bytenr, - &new_node->rb_node); - if (rb_node) - btrfs_backref_panic(trans->fs_info, new_node->bytenr, -EEXIST); - - if (!new_node->lowest) { - list_for_each_entry(new_edge, &new_node->lower, list[UPPER]) { - list_add_tail(&new_edge->list[LOWER], - &new_edge->node[LOWER]->upper); - } - } - return 0; -fail: - while (!list_empty(&new_node->lower)) { - new_edge = list_entry(new_node->lower.next, - struct btrfs_backref_edge, list[UPPER]); - list_del(&new_edge->list[UPPER]); - btrfs_backref_free_edge(cache, new_edge); - } - btrfs_backref_free_node(cache, new_node); - return -ENOMEM; -} - -/* * helper to add 'address of tree root -> reloc tree' mapping */ static int __add_reloc_root(struct btrfs_root *root) @@ -950,7 +856,6 @@ int replace_file_extents(struct btrfs_trans_handle *trans, u32 i; int ret = 0; int first = 1; - int dirty = 0; if (rc->stage != UPDATE_DATA_PTRS) return 0; @@ -1030,7 +935,6 @@ int replace_file_extents(struct btrfs_trans_handle *trans, } btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr); - dirty = 1; key.offset -= btrfs_file_extent_offset(leaf, fi); ref.action = BTRFS_ADD_DELAYED_REF; @@ -1061,8 +965,6 @@ int replace_file_extents(struct btrfs_trans_handle *trans, break; } } - if (dirty) - btrfs_mark_buffer_dirty(trans, leaf); if (inode) btrfs_add_delayed_iput(inode); return ret; @@ -1255,13 +1157,11 @@ again: */ btrfs_set_node_blockptr(parent, slot, new_bytenr); btrfs_set_node_ptr_generation(parent, slot, new_ptr_gen); - btrfs_mark_buffer_dirty(trans, parent); btrfs_set_node_blockptr(path->nodes[level], path->slots[level], old_bytenr); btrfs_set_node_ptr_generation(path->nodes[level], path->slots[level], old_ptr_gen); - btrfs_mark_buffer_dirty(trans, path->nodes[level]); ref.action = BTRFS_ADD_DELAYED_REF; ref.bytenr = old_bytenr; @@ -2058,100 +1958,72 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans, int index = 0; int ret; - next = node; - while (1) { - cond_resched(); - next = walk_up_backref(next, edges, &index); - root = next->root; + next = walk_up_backref(node, edges, &index); + root = next->root; - /* - * If there is no root, then our references for this block are - * incomplete, as we should be able to walk all the way up to a - * block that is owned by a root. - * - * This path is only for SHAREABLE roots, so if we come upon a - * non-SHAREABLE root then we have backrefs that resolve - * improperly. - * - * Both of these cases indicate file system corruption, or a bug - * in the backref walking code. - */ - if (!root) { - ASSERT(0); - btrfs_err(trans->fs_info, - "bytenr %llu doesn't have a backref path ending in a root", - node->bytenr); - return ERR_PTR(-EUCLEAN); - } - if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) { - ASSERT(0); - btrfs_err(trans->fs_info, - "bytenr %llu has multiple refs with one ending in a non-shareable root", - node->bytenr); - return ERR_PTR(-EUCLEAN); - } - - if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { - ret = record_reloc_root_in_trans(trans, root); - if (ret) - return ERR_PTR(ret); - break; - } + /* + * If there is no root, then our references for this block are + * incomplete, as we should be able to walk all the way up to a block + * that is owned by a root. + * + * This path is only for SHAREABLE roots, so if we come upon a + * non-SHAREABLE root then we have backrefs that resolve improperly. + * + * Both of these cases indicate file system corruption, or a bug in the + * backref walking code. + */ + if (unlikely(!root)) { + btrfs_err(trans->fs_info, + "bytenr %llu doesn't have a backref path ending in a root", + node->bytenr); + return ERR_PTR(-EUCLEAN); + } + if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { + btrfs_err(trans->fs_info, + "bytenr %llu has multiple refs with one ending in a non-shareable root", + node->bytenr); + return ERR_PTR(-EUCLEAN); + } - ret = btrfs_record_root_in_trans(trans, root); + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { + ret = record_reloc_root_in_trans(trans, root); if (ret) return ERR_PTR(ret); - root = root->reloc_root; - - /* - * We could have raced with another thread which failed, so - * root->reloc_root may not be set, return ENOENT in this case. - */ - if (!root) - return ERR_PTR(-ENOENT); + goto found; + } - if (next->new_bytenr != root->node->start) { - /* - * We just created the reloc root, so we shouldn't have - * ->new_bytenr set and this shouldn't be in the changed - * list. If it is then we have multiple roots pointing - * at the same bytenr which indicates corruption, or - * we've made a mistake in the backref walking code. - */ - ASSERT(next->new_bytenr == 0); - ASSERT(list_empty(&next->list)); - if (next->new_bytenr || !list_empty(&next->list)) { - btrfs_err(trans->fs_info, - "bytenr %llu possibly has multiple roots pointing at the same bytenr %llu", - node->bytenr, next->bytenr); - return ERR_PTR(-EUCLEAN); - } + ret = btrfs_record_root_in_trans(trans, root); + if (ret) + return ERR_PTR(ret); + root = root->reloc_root; - next->new_bytenr = root->node->start; - btrfs_put_root(next->root); - next->root = btrfs_grab_root(root); - ASSERT(next->root); - list_add_tail(&next->list, - &rc->backref_cache.changed); - mark_block_processed(rc, next); - break; - } + /* + * We could have raced with another thread which failed, so + * root->reloc_root may not be set, return ENOENT in this case. + */ + if (!root) + return ERR_PTR(-ENOENT); - WARN_ON(1); - root = NULL; - next = walk_down_backref(edges, &index); - if (!next || next->level <= node->level) - break; - } - if (!root) { + if (next->new_bytenr) { /* - * This can happen if there's fs corruption or if there's a bug - * in the backref lookup code. + * We just created the reloc root, so we shouldn't have + * ->new_bytenr set yet. If it is then we have multiple roots + * pointing at the same bytenr which indicates corruption, or + * we've made a mistake in the backref walking code. */ - ASSERT(0); - return ERR_PTR(-ENOENT); + ASSERT(next->new_bytenr == 0); + btrfs_err(trans->fs_info, + "bytenr %llu possibly has multiple roots pointing at the same bytenr %llu", + node->bytenr, next->bytenr); + return ERR_PTR(-EUCLEAN); } + next->new_bytenr = root->node->start; + btrfs_put_root(next->root); + next->root = btrfs_grab_root(root); + ASSERT(next->root); + mark_block_processed(rc, next); +found: next = node; /* setup backref node path for btrfs_reloc_cow_block */ while (1) { @@ -2247,17 +2119,11 @@ static noinline_for_stack u64 calcu_metadata_size(struct reloc_control *rc, return num_bytes; } -static int reserve_metadata_space(struct btrfs_trans_handle *trans, - struct reloc_control *rc, - struct btrfs_backref_node *node) +static int refill_metadata_space(struct btrfs_trans_handle *trans, + struct reloc_control *rc, u64 num_bytes) { - struct btrfs_root *root = rc->extent_root; - struct btrfs_fs_info *fs_info = root->fs_info; - u64 num_bytes; + struct btrfs_fs_info *fs_info = trans->fs_info; int ret; - u64 tmp; - - num_bytes = calcu_metadata_size(rc, node) * 2; trans->block_rsv = rc->block_rsv; rc->reserved_bytes += num_bytes; @@ -2270,7 +2136,8 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans, ret = btrfs_block_rsv_refill(fs_info, rc->block_rsv, num_bytes, BTRFS_RESERVE_FLUSH_LIMIT); if (ret) { - tmp = fs_info->nodesize * RELOCATION_RESERVED_NODES; + u64 tmp = fs_info->nodesize * RELOCATION_RESERVED_NODES; + while (tmp <= rc->reserved_bytes) tmp <<= 1; /* @@ -2288,6 +2155,16 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans, return 0; } +static int reserve_metadata_space(struct btrfs_trans_handle *trans, + struct reloc_control *rc, + struct btrfs_backref_node *node) +{ + u64 num_bytes; + + num_bytes = calcu_metadata_size(rc, node) * 2; + return refill_metadata_space(trans, rc, num_bytes); +} + /* * relocate a block tree, and then update pointers in upper level * blocks that reference the block to point to the new location. @@ -2442,7 +2319,7 @@ next: if (!ret && node->pending) { btrfs_backref_drop_node_buffer(node); - list_move_tail(&node->list, &rc->backref_cache.changed); + list_del_init(&node->list); node->pending = 0; } @@ -2605,8 +2482,7 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, /* * This block was the root block of a root, and this is * the first time we're processing the block and thus it - * should not have had the ->new_bytenr modified and - * should have not been included on the changed list. + * should not have had the ->new_bytenr modified. * * However in the case of corruption we could have * multiple refs pointing to the same block improperly, @@ -2616,8 +2492,7 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, * normal user in the case of corruption. */ ASSERT(node->new_bytenr == 0); - ASSERT(list_empty(&node->list)); - if (node->new_bytenr || !list_empty(&node->list)) { + if (node->new_bytenr) { btrfs_err(root->fs_info, "bytenr %llu has improper references to it", node->bytenr); @@ -2640,17 +2515,12 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, btrfs_put_root(node->root); node->root = btrfs_grab_root(root); ASSERT(node->root); - list_add_tail(&node->list, &rc->backref_cache.changed); } else { - path->lowest_level = node->level; - if (root == root->fs_info->chunk_root) - btrfs_reserve_chunk_metadata(trans, false); - ret = btrfs_search_slot(trans, root, key, path, 0, 1); - btrfs_release_path(path); - if (root == root->fs_info->chunk_root) - btrfs_trans_release_chunk_metadata(trans); - if (ret > 0) - ret = 0; + btrfs_err(root->fs_info, + "bytenr %llu resolved to a non-shareable root", + node->bytenr); + ret = -EUCLEAN; + goto out; } if (!ret) update_processed_blocks(rc, node); @@ -2658,11 +2528,50 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans, ret = do_relocation(trans, rc, node, key, path, 1); } out: - if (ret || node->level == 0 || node->cowonly) + if (ret || node->level == 0) btrfs_backref_cleanup_node(&rc->backref_cache, node); return ret; } +static int relocate_cowonly_block(struct btrfs_trans_handle *trans, + struct reloc_control *rc, struct tree_block *block, + struct btrfs_path *path) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *root; + u64 num_bytes; + int nr_levels; + int ret; + + root = btrfs_get_fs_root(fs_info, block->owner, true); + if (IS_ERR(root)) + return PTR_ERR(root); + + nr_levels = max(btrfs_header_level(root->node) - block->level, 0) + 1; + + num_bytes = fs_info->nodesize * nr_levels; + ret = refill_metadata_space(trans, rc, num_bytes); + if (ret) { + btrfs_put_root(root); + return ret; + } + path->lowest_level = block->level; + if (root == root->fs_info->chunk_root) + btrfs_reserve_chunk_metadata(trans, false); + + ret = btrfs_search_slot(trans, root, &block->key, path, 0, 1); + path->lowest_level = 0; + btrfs_release_path(path); + + if (root == root->fs_info->chunk_root) + btrfs_trans_release_chunk_metadata(trans); + if (ret > 0) + ret = 0; + btrfs_put_root(root); + + return ret; +} + /* * relocate a list of blocks */ @@ -2702,6 +2611,20 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Do tree relocation */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { + /* + * For COWonly blocks, or the data reloc tree, we only need to + * COW down to the block, there's no need to generate a backref + * tree. + */ + if (block->owner && + (!is_fstree(block->owner) || + block->owner == BTRFS_DATA_RELOC_TREE_OBJECTID)) { + ret = relocate_cowonly_block(trans, rc, block, path); + if (ret) + break; + continue; + } + node = build_backref_tree(trans, rc, &block->key, block->level, block->bytenr); if (IS_ERR(node)) { @@ -2902,6 +2825,7 @@ static int relocate_one_folio(struct reloc_control *rc, const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags); ASSERT(index <= last_index); +again: folio = filemap_lock_folio(inode->i_mapping, index); if (IS_ERR(folio)) { @@ -2937,11 +2861,16 @@ static int relocate_one_folio(struct reloc_control *rc, ret = -EIO; goto release_folio; } + if (folio->mapping != inode->i_mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } /* * We could have lost folio private when we dropped the lock to read the - * folio above, make sure we set_page_extent_mapped here so we have any + * folio above, make sure we set_folio_extent_mapped() here so we have any * of the subpage blocksize stuff we need in place. */ ret = set_folio_extent_mapped(folio); @@ -3793,7 +3722,6 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC); - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -4399,8 +4327,18 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, WARN_ON(!first_cow && level == 0); node = rc->backref_cache.path[level]; - BUG_ON(node->bytenr != buf->start && - node->new_bytenr != buf->start); + + /* + * If node->bytenr != buf->start and node->new_bytenr != + * buf->start then we've got the wrong backref node for what we + * expected to see here and the cache is incorrect. + */ + if (unlikely(node->bytenr != buf->start && node->new_bytenr != buf->start)) { + btrfs_err(fs_info, +"bytenr %llu was found but our backref cache was expecting %llu or %llu", + buf->start, node->bytenr, node->new_bytenr); + return -EUCLEAN; + } btrfs_backref_drop_node_buffer(node); atomic_inc(&cow->refs); @@ -4500,10 +4438,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans, return ret; } new_root->reloc_root = btrfs_grab_root(reloc_root); - - if (rc->create_reloc_tree) - ret = clone_backref_node(trans, rc, root, reloc_root); - return ret; + return 0; } /* diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 33962671a96c..e22e6b06927a 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -197,7 +197,6 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_set_root_generation_v2(item, btrfs_root_generation(item)); write_extent_buffer(l, item, ptr, sizeof(*item)); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); out: btrfs_free_path(path); return ret; @@ -447,7 +446,6 @@ again: btrfs_set_root_ref_name_len(leaf, ref, name->len); ptr = (unsigned long)(ref + 1); write_extent_buffer(leaf, name->name, ptr, name->len); - btrfs_mark_buffer_dirty(trans, leaf); if (key.type == BTRFS_ROOT_BACKREF_KEY) { btrfs_release_path(path); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 204c928beaf9..531312efee8d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1541,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, u64 extent_gen; int ret; + if (unlikely(!extent_root)) { + btrfs_err(fs_info, "no valid extent root for scrub"); + return -EUCLEAN; + } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * stripe->nr_sectors); scrub_stripe_reset_bitmaps(stripe); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7254279c3cc9..f437138fefbc 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5280,6 +5280,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) unsigned cur_len = min_t(unsigned, len, PAGE_SIZE - pg_offset); +again: folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { page_cache_sync_readahead(mapping, @@ -5312,6 +5313,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) ret = -EIO; break; } + if (folio->mapping != mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } memcpy_from_folio(sctx->send_buf + sctx->send_size, folio, @@ -7253,7 +7259,7 @@ static int changed_cb(struct btrfs_path *left_path, enum btrfs_compare_tree_result result, struct send_ctx *sctx) { - int ret = 0; + int ret; /* * We can not hold the commit root semaphore here. This is because in @@ -7313,7 +7319,6 @@ static int changed_cb(struct btrfs_path *left_path, return 0; } result = BTRFS_COMPARE_TREE_CHANGED; - ret = 0; } sctx->left_path = left_path; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 255e85f78313..a341d087567a 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -14,6 +14,7 @@ #include "fs.h" #include "accessors.h" #include "extent-tree.h" +#include "zoned.h" /* * HOW DOES SPACE RESERVATION WORK @@ -127,6 +128,14 @@ * churn a lot and we can avoid making some extent tree modifications if we * are able to delay for as long as possible. * + * RESET_ZONES + * This state works only for the zoned mode. On the zoned mode, we cannot + * reuse once allocated then freed region until we reset the zone, due to + * the sequential write zone requirement. The RESET_ZONES state resets the + * zones of an unused block group and let us reuse the space. The reusing + * is faster than removing the block group and allocating another block + * group on the zones. + * * ALLOC_CHUNK * We will skip this the first time through space reservation, because of * overcommit and we don't want to have a lot of useless metadata space when @@ -316,7 +325,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; found->bytes_readonly += block_group->bytes_super; - btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable); + btrfs_space_info_update_bytes_zone_unusable(found, block_group->zone_unusable); if (block_group->length > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -489,9 +498,7 @@ again: if ((used + ticket->bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) { - btrfs_space_info_update_bytes_may_use(fs_info, - space_info, - ticket->bytes); + btrfs_space_info_update_bytes_may_use(space_info, ticket->bytes); remove_ticket(space_info, ticket); ticket->bytes = 0; space_info->tickets_id++; @@ -834,6 +841,9 @@ static void flush_space(struct btrfs_fs_info *fs_info, */ ret = btrfs_commit_current_transaction(root); break; + case RESET_ZONES: + ret = btrfs_reset_unused_block_groups(space_info, num_bytes); + break; default: ret = -ENOSPC; break; @@ -1086,9 +1096,14 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) enum btrfs_flush_state flush_state; int commit_cycles = 0; u64 last_tickets_id; + enum btrfs_flush_state final_state; fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work); space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + if (btrfs_is_zoned(fs_info)) + final_state = RESET_ZONES; + else + final_state = COMMIT_TRANS; spin_lock(&space_info->lock); to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info); @@ -1141,7 +1156,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles) flush_state++; - if (flush_state > COMMIT_TRANS) { + if (flush_state > final_state) { commit_cycles++; if (commit_cycles > 2) { if (maybe_fail_all_tickets(fs_info, space_info)) { @@ -1155,7 +1170,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) } } spin_unlock(&space_info->lock); - } while (flush_state <= COMMIT_TRANS); + } while (flush_state <= final_state); } /* @@ -1286,6 +1301,10 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * This is where we reclaim all of the pinned space generated by running the * iputs * + * RESET_ZONES + * This state works only for the zoned mode. We scan the unused block group + * list and reset the zones and reuse the block group. + * * ALLOC_CHUNK_FORCE * For data we start with alloc chunk force, however we could have been full * before, and then the transaction commit could have freed new block groups, @@ -1295,6 +1314,7 @@ static const enum btrfs_flush_state data_flush_states[] = { FLUSH_DELALLOC_FULL, RUN_DELAYED_IPUTS, COMMIT_TRANS, + RESET_ZONES, ALLOC_CHUNK_FORCE, }; @@ -1386,6 +1406,7 @@ void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) static const enum btrfs_flush_state priority_flush_states[] = { FLUSH_DELAYED_ITEMS_NR, FLUSH_DELAYED_ITEMS, + RESET_ZONES, ALLOC_CHUNK, }; @@ -1399,6 +1420,7 @@ static const enum btrfs_flush_state evict_flush_states[] = { FLUSH_DELALLOC_FULL, ALLOC_CHUNK, COMMIT_TRANS, + RESET_ZONES, }; static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, @@ -1690,8 +1712,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, if (!pending_tickets && ((used + orig_bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { - btrfs_space_info_update_bytes_may_use(fs_info, space_info, - orig_bytes); + btrfs_space_info_update_bytes_may_use(space_info, orig_bytes); ret = 0; } @@ -1703,8 +1724,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, if (ret && unlikely(flush == BTRFS_RESERVE_FLUSH_EMERGENCY)) { used = btrfs_space_info_used(space_info, false); if (used + orig_bytes <= space_info->total_bytes) { - btrfs_space_info_update_bytes_may_use(fs_info, space_info, - orig_bytes); + btrfs_space_info_update_bytes_may_use(space_info, orig_bytes); ret = 0; } } @@ -2082,3 +2102,32 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info) do_reclaim_sweep(space_info, raid); } } + +void btrfs_return_free_space(struct btrfs_space_info *space_info, u64 len) +{ + struct btrfs_fs_info *fs_info = space_info->fs_info; + struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; + + lockdep_assert_held(&space_info->lock); + + /* Prioritize the global reservation to receive the freed space. */ + if (global_rsv->space_info != space_info) + goto grant; + + spin_lock(&global_rsv->lock); + if (!global_rsv->full) { + u64 to_add = min(len, global_rsv->size - global_rsv->reserved); + + global_rsv->reserved += to_add; + btrfs_space_info_update_bytes_may_use(space_info, to_add); + if (global_rsv->reserved >= global_rsv->size) + global_rsv->full = 1; + len -= to_add; + } + spin_unlock(&global_rsv->lock); + +grant: + /* Add to any tickets we may have. */ + if (len) + btrfs_try_granting_tickets(fs_info, space_info); +} diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index efbecc0c5258..a96efdb5e681 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -79,6 +79,10 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_EMERGENCY, }; +/* + * Please be aware that the order of enum values will be the order of the reclaim + * process in btrfs_async_reclaim_metadata_space(). + */ enum btrfs_flush_state { FLUSH_DELAYED_ITEMS_NR = 1, FLUSH_DELAYED_ITEMS = 2, @@ -91,6 +95,7 @@ enum btrfs_flush_state { ALLOC_CHUNK_FORCE = 9, RUN_DELAYED_IPUTS = 10, COMMIT_TRANS = 11, + RESET_ZONES = 12, }; struct btrfs_space_info { @@ -229,10 +234,10 @@ static inline bool btrfs_mixed_space_info(const struct btrfs_space_info *space_i */ #define DECLARE_SPACE_INFO_UPDATE(name, trace_name) \ static inline void \ -btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ - struct btrfs_space_info *sinfo, \ +btrfs_space_info_update_##name(struct btrfs_space_info *sinfo, \ s64 bytes) \ { \ + struct btrfs_fs_info *fs_info = sinfo->fs_info; \ const u64 abs_bytes = (bytes < 0) ? -bytes : bytes; \ lockdep_assert_held(&sinfo->lock); \ trace_update_##name(fs_info, sinfo, sinfo->name, bytes); \ @@ -275,13 +280,12 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( - struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes) { spin_lock(&space_info->lock); - btrfs_space_info_update_bytes_may_use(fs_info, space_info, -num_bytes); - btrfs_try_granting_tickets(fs_info, space_info); + btrfs_space_info_update_bytes_may_use(space_info, -num_bytes); + btrfs_try_granting_tickets(space_info->fs_info, space_info); spin_unlock(&space_info->lock); } int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, @@ -295,5 +299,6 @@ void btrfs_set_periodic_reclaim_ready(struct btrfs_space_info *space_info, bool bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info); int btrfs_calc_reclaim_threshold(const struct btrfs_space_info *space_info); void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info); +void btrfs_return_free_space(struct btrfs_space_info *space_info, u64 len); #endif /* BTRFS_SPACE_INFO_H */ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 8c68059ac1b0..722acf768396 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -635,6 +635,28 @@ IMPLEMENT_BTRFS_PAGE_OPS(ordered, folio_set_ordered, folio_clear_ordered, IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked, folio_test_checked); +#define GET_SUBPAGE_BITMAP(subpage, fs_info, name, dst) \ +{ \ + const int sectors_per_page = fs_info->sectors_per_page; \ + \ + ASSERT(sectors_per_page < BITS_PER_LONG); \ + *dst = bitmap_read(subpage->bitmaps, \ + sectors_per_page * btrfs_bitmap_nr_##name, \ + sectors_per_page); \ +} + +#define SUBPAGE_DUMP_BITMAP(fs_info, folio, name, start, len) \ +{ \ + const struct btrfs_subpage *subpage = folio_get_private(folio); \ + unsigned long bitmap; \ + \ + GET_SUBPAGE_BITMAP(subpage, fs_info, name, &bitmap); \ + btrfs_warn(fs_info, \ + "dumpping bitmap start=%llu len=%u folio=%llu " #name "_bitmap=%*pbl", \ + start, len, folio_pos(folio), \ + fs_info->sectors_per_page, &bitmap); \ +} + /* * Make sure not only the page dirty bit is cleared, but also subpage dirty bit * is cleared. @@ -660,6 +682,10 @@ void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, subpage = folio_get_private(folio); ASSERT(subpage); spin_lock_irqsave(&subpage->lock, flags); + if (unlikely(!bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits))) { + SUBPAGE_DUMP_BITMAP(fs_info, folio, dirty, start, len); + ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); + } ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); spin_unlock_irqrestore(&subpage->lock, flags); } @@ -689,23 +715,16 @@ void btrfs_folio_set_lock(const struct btrfs_fs_info *fs_info, nbits = len >> fs_info->sectorsize_bits; spin_lock_irqsave(&subpage->lock, flags); /* Target range should not yet be locked. */ - ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); + if (unlikely(!bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits))) { + SUBPAGE_DUMP_BITMAP(fs_info, folio, locked, start, len); + ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); + } bitmap_set(subpage->bitmaps, start_bit, nbits); ret = atomic_add_return(nbits, &subpage->nr_locked); ASSERT(ret <= fs_info->sectors_per_page); spin_unlock_irqrestore(&subpage->lock, flags); } -#define GET_SUBPAGE_BITMAP(subpage, fs_info, name, dst) \ -{ \ - const int sectors_per_page = fs_info->sectors_per_page; \ - \ - ASSERT(sectors_per_page < BITS_PER_LONG); \ - *dst = bitmap_read(subpage->bitmaps, \ - sectors_per_page * btrfs_bitmap_nr_##name, \ - sectors_per_page); \ -} - void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { @@ -716,6 +735,7 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, unsigned long writeback_bitmap; unsigned long ordered_bitmap; unsigned long checked_bitmap; + unsigned long locked_bitmap; unsigned long flags; ASSERT(folio_test_private(folio) && folio_get_private(folio)); @@ -728,15 +748,16 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, GET_SUBPAGE_BITMAP(subpage, fs_info, writeback, &writeback_bitmap); GET_SUBPAGE_BITMAP(subpage, fs_info, ordered, &ordered_bitmap); GET_SUBPAGE_BITMAP(subpage, fs_info, checked, &checked_bitmap); - GET_SUBPAGE_BITMAP(subpage, fs_info, locked, &checked_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, locked, &locked_bitmap); spin_unlock_irqrestore(&subpage->lock, flags); dump_page(folio_page(folio, 0), "btrfs subpage dump"); btrfs_warn(fs_info, -"start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl dirty=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", +"start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl dirty=%*pbl locked=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", start, len, folio_pos(folio), sectors_per_page, &uptodate_bitmap, sectors_per_page, &dirty_bitmap, + sectors_per_page, &locked_bitmap, sectors_per_page, &writeback_bitmap, sectors_per_page, &ordered_bitmap, sectors_per_page, &checked_bitmap); diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h index 428fa9389fd4..44fff1f4eac4 100644 --- a/fs/btrfs/subpage.h +++ b/fs/btrfs/subpage.h @@ -137,6 +137,19 @@ DECLARE_BTRFS_SUBPAGE_OPS(writeback); DECLARE_BTRFS_SUBPAGE_OPS(ordered); DECLARE_BTRFS_SUBPAGE_OPS(checked); +/* + * Helper for error cleanup, where a folio will have its dirty flag cleared, + * with writeback started and finished. + */ +static inline void btrfs_folio_clamp_finish_io(struct btrfs_fs_info *fs_info, + struct folio *locked_folio, + u64 start, u32 len) +{ + btrfs_folio_clamp_clear_dirty(fs_info, locked_folio, start, len); + btrfs_folio_clamp_set_writeback(fs_info, locked_folio, start, len); + btrfs_folio_clamp_clear_writeback(fs_info, locked_folio, start, len); +} + bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 97a85d180b61..dc4fee519ca6 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -961,7 +961,7 @@ static int btrfs_fill_super(struct super_block *sb, #endif sb->s_xattr = btrfs_xattr_handlers; sb->s_time_gran = 1; - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; err = super_setup_bdi(sb); if (err) { @@ -971,7 +971,7 @@ static int btrfs_fill_super(struct super_block *sb, err = open_ctree(sb, fs_devices); if (err) { - btrfs_err(fs_info, "open_ctree failed"); + btrfs_err(fs_info, "open_ctree failed: %d", err); return err; } @@ -1885,18 +1885,21 @@ static int btrfs_get_tree_super(struct fs_context *fc) if (sb->s_root) { btrfs_close_devices(fs_devices); - if ((fc->sb_flags ^ sb->s_flags) & SB_RDONLY) - ret = -EBUSY; + /* + * At this stage we may have RO flag mismatch between + * fc->sb_flags and sb->s_flags. Caller should detect such + * mismatch and reconfigure with sb->s_umount rwsem held if + * needed. + */ } else { snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); shrinker_debugfs_rename(sb->s_shrink, "sb-btrfs:%s", sb->s_id); btrfs_sb(sb)->bdev_holder = &btrfs_fs_type; ret = btrfs_fill_super(sb, fs_devices); - } - - if (ret) { - deactivate_locked_super(sb); - return ret; + if (ret) { + deactivate_locked_super(sb); + return ret; + } } btrfs_clear_oneshot_options(fs_info); @@ -1982,39 +1985,18 @@ error: * btrfs or not, setting the whole super block RO. To make per-subvolume mounting * work with different options work we need to keep backward compatibility. */ -static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc) +static int btrfs_reconfigure_for_mount(struct fs_context *fc, struct vfsmount *mnt) { - struct vfsmount *mnt; - int ret; - const bool ro2rw = !(fc->sb_flags & SB_RDONLY); - - /* - * We got an EBUSY because our SB_RDONLY flag didn't match the existing - * super block, so invert our setting here and retry the mount so we - * can get our vfsmount. - */ - if (ro2rw) - fc->sb_flags |= SB_RDONLY; - else - fc->sb_flags &= ~SB_RDONLY; - - mnt = fc_mount(fc); - if (IS_ERR(mnt)) - return mnt; + int ret = 0; - if (!ro2rw) - return mnt; + if (fc->sb_flags & SB_RDONLY) + return ret; - /* We need to convert to rw, call reconfigure. */ - fc->sb_flags &= ~SB_RDONLY; down_write(&mnt->mnt_sb->s_umount); - ret = btrfs_reconfigure(fc); + if (!(fc->sb_flags & SB_RDONLY) && (mnt->mnt_sb->s_flags & SB_RDONLY)) + ret = btrfs_reconfigure(fc); up_write(&mnt->mnt_sb->s_umount); - if (ret) { - mntput(mnt); - return ERR_PTR(ret); - } - return mnt; + return ret; } static int btrfs_get_tree_subvol(struct fs_context *fc) @@ -2024,6 +2006,7 @@ static int btrfs_get_tree_subvol(struct fs_context *fc) struct fs_context *dup_fc; struct dentry *dentry; struct vfsmount *mnt; + int ret = 0; /* * Setup a dummy root and fs_info for test/set super. This is because @@ -2066,11 +2049,16 @@ static int btrfs_get_tree_subvol(struct fs_context *fc) fc->security = NULL; mnt = fc_mount(dup_fc); - if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) - mnt = btrfs_reconfigure_for_mount(dup_fc); - put_fs_context(dup_fc); - if (IS_ERR(mnt)) + if (IS_ERR(mnt)) { + put_fs_context(dup_fc); return PTR_ERR(mnt); + } + ret = btrfs_reconfigure_for_mount(dup_fc, mnt); + put_fs_context(dup_fc); + if (ret) { + mntput(mnt); + return ret; + } /* * This free's ->subvol_name, because if it isn't set we have to @@ -2458,6 +2446,9 @@ static __cold void btrfs_interface_exit(void) static int __init btrfs_print_mod_info(void) { static const char options[] = "" +#ifdef CONFIG_BTRFS_EXPERIMENTAL + ", experimental=on" +#endif #ifdef CONFIG_BTRFS_DEBUG ", debug=on" #endif @@ -2478,7 +2469,17 @@ static int __init btrfs_print_mod_info(void) ", fsverity=no" #endif ; + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + if (btrfs_get_mod_read_policy() == NULL) + pr_info("Btrfs loaded%s\n", options); + else + pr_info("Btrfs loaded%s, read_policy=%s\n", + options, btrfs_get_mod_read_policy()); +#else pr_info("Btrfs loaded%s\n", options); +#endif + return 0; } @@ -2536,6 +2537,11 @@ static const struct init_sequence mod_init_seq[] = { }, { .init_func = extent_map_init, .exit_func = extent_map_exit, +#ifdef CONFIG_BTRFS_EXPERIMENTAL + }, { + .init_func = btrfs_read_policy_init, + .exit_func = NULL, +#endif }, { .init_func = ordered_data_init, .exit_func = ordered_data_exit, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index fdcbf650ac31..53b846d99ece 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); + return sysfs_emit(buf, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); @@ -1305,7 +1305,73 @@ static ssize_t btrfs_temp_fsid_show(struct kobject *kobj, } BTRFS_ATTR(, temp_fsid, btrfs_temp_fsid_show); -static const char * const btrfs_read_policy_name[] = { "pid" }; +static const char *btrfs_read_policy_name[] = { + "pid", +#ifdef CONFIG_BTRFS_EXPERIMENTAL + "round-robin", + "devid", +#endif +}; + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + +/* Global module configuration parameters. */ +static char *read_policy; +char *btrfs_get_mod_read_policy(void) +{ + return read_policy; +} + +/* Set perms to 0, disable /sys/module/btrfs/parameter/read_policy interface. */ +module_param(read_policy, charp, 0); +MODULE_PARM_DESC(read_policy, +"Global read policy: pid (default), round-robin[:<min_contig_read>], devid[:<devid>]"); +#endif + +int btrfs_read_policy_to_enum(const char *str, s64 *value_ret) +{ + char param[32] = { 0 }; + char __maybe_unused *value_str; + + if (!str || strlen(str) == 0) + return 0; + + strncpy(param, str, sizeof(param) - 1); + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + /* Separate value from input in policy:value format. */ + value_str = strchr(param, ':'); + if (value_str) { + int ret; + + *value_str = 0; + value_str++; + if (!value_ret) + return -EINVAL; + ret = kstrtos64(value_str, 10, value_ret); + if (ret) + return -EINVAL; + if (*value_ret < 0) + return -ERANGE; + } +#endif + + return sysfs_match_string(btrfs_read_policy_name, param); +} + +#ifdef CONFIG_BTRFS_EXPERIMENTAL +int __init btrfs_read_policy_init(void) +{ + s64 value; + + if (btrfs_read_policy_to_enum(read_policy, &value) == -EINVAL) { + btrfs_err(NULL, "invalid read policy or value %s", read_policy); + return -EINVAL; + } + + return 0; +} +#endif static ssize_t btrfs_read_policy_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) @@ -1316,14 +1382,25 @@ static ssize_t btrfs_read_policy_show(struct kobject *kobj, int i; for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { - if (policy == i) - ret += sysfs_emit_at(buf, ret, "%s[%s]", - (ret == 0 ? "" : " "), - btrfs_read_policy_name[i]); - else - ret += sysfs_emit_at(buf, ret, "%s%s", - (ret == 0 ? "" : " "), - btrfs_read_policy_name[i]); + if (ret != 0) + ret += sysfs_emit_at(buf, ret, " "); + + if (i == policy) + ret += sysfs_emit_at(buf, ret, "["); + + ret += sysfs_emit_at(buf, ret, "%s", btrfs_read_policy_name[i]); + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + if (i == BTRFS_READ_POLICY_RR) + ret += sysfs_emit_at(buf, ret, ":%u", + READ_ONCE(fs_devices->rr_min_contig_read)); + + if (i == BTRFS_READ_POLICY_DEVID) + ret += sysfs_emit_at(buf, ret, ":%llu", + READ_ONCE(fs_devices->read_devid)); +#endif + if (i == policy) + ret += sysfs_emit_at(buf, ret, "]"); } ret += sysfs_emit_at(buf, ret, "\n"); @@ -1336,21 +1413,80 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj, const char *buf, size_t len) { struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); - int i; + int index; + s64 value = -1; - for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { - if (sysfs_streq(buf, btrfs_read_policy_name[i])) { - if (i != READ_ONCE(fs_devices->read_policy)) { - WRITE_ONCE(fs_devices->read_policy, i); - btrfs_info(fs_devices->fs_info, - "read policy set to '%s'", - btrfs_read_policy_name[i]); + index = btrfs_read_policy_to_enum(buf, &value); + if (index < 0) + return -EINVAL; + +#ifdef CONFIG_BTRFS_EXPERIMENTAL + /* If moving from RR then disable collecting fs stats. */ + if (fs_devices->read_policy == BTRFS_READ_POLICY_RR && index != BTRFS_READ_POLICY_RR) + fs_devices->collect_fs_stats = false; + + if (index == BTRFS_READ_POLICY_RR) { + if (value != -1) { + const u32 sectorsize = fs_devices->fs_info->sectorsize; + + if (!IS_ALIGNED(value, sectorsize)) { + u64 temp_value = round_up(value, sectorsize); + + btrfs_debug(fs_devices->fs_info, +"read_policy: min contig read %lld should be multiple of sectorsize %u, rounded to %llu", + value, sectorsize, temp_value); + value = temp_value; } - return len; + } else { + value = BTRFS_DEFAULT_RR_MIN_CONTIG_READ; + } + + if (index != READ_ONCE(fs_devices->read_policy) || + value != READ_ONCE(fs_devices->rr_min_contig_read)) { + WRITE_ONCE(fs_devices->read_policy, index); + WRITE_ONCE(fs_devices->rr_min_contig_read, value); + + btrfs_info(fs_devices->fs_info, "read policy set to '%s:%lld'", + btrfs_read_policy_name[index], value); + } + + fs_devices->collect_fs_stats = true; + + return len; + } + + if (index == BTRFS_READ_POLICY_DEVID) { + if (value != -1) { + BTRFS_DEV_LOOKUP_ARGS(args); + + /* Validate input devid. */ + args.devid = value; + if (btrfs_find_device(fs_devices, &args) == NULL) + return -EINVAL; + } else { + /* Set default devid to the devid of the latest device. */ + value = fs_devices->latest_dev->devid; } + + if (index != READ_ONCE(fs_devices->read_policy) || + value != READ_ONCE(fs_devices->read_devid)) { + WRITE_ONCE(fs_devices->read_policy, index); + WRITE_ONCE(fs_devices->read_devid, value); + + btrfs_info(fs_devices->fs_info, "read policy set to '%s:%llu'", + btrfs_read_policy_name[index], value); + } + + return len; + } +#endif + if (index != READ_ONCE(fs_devices->read_policy)) { + WRITE_ONCE(fs_devices->read_policy, index); + btrfs_info(fs_devices->fs_info, "read policy set to '%s'", + btrfs_read_policy_name[index]); } - return -EINVAL; + return len; } BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store); diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index e6a284c59809..3fc5c6f90dc4 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -47,5 +47,11 @@ void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info); int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info); void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup); +int btrfs_read_policy_to_enum(const char *str, s64 *value); + +#ifdef CONFIG_BTRFS_EXPERIMENTAL +int __init btrfs_read_policy_init(void); +char *btrfs_get_mod_read_policy(void); +#endif #endif diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index e607b5d52fb1..5eff8d7d2360 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -30,6 +30,7 @@ const char *test_error[] = { [TEST_ALLOC_EXTENT_MAP] = "cannot allocate extent map", [TEST_ALLOC_CHUNK_MAP] = "cannot allocate chunk map", [TEST_ALLOC_IO_CONTEXT] = "cannot allocate io context", + [TEST_ALLOC_TRANSACTION] = "cannot allocate transaction", }; static const struct super_operations btrfs_test_super_ops = { @@ -142,6 +143,11 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; fs_info->sectorsize_bits = ilog2(sectorsize); + + /* CRC32C csum size. */ + fs_info->csum_size = 4; + fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / + fs_info->csum_size; set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state); test_mnt->mnt_sb->s_fs_info = fs_info; @@ -247,6 +253,15 @@ void btrfs_free_dummy_block_group(struct btrfs_block_group *cache) kfree(cache); } +void btrfs_init_dummy_transaction(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) +{ + memset(trans, 0, sizeof(*trans)); + trans->fs_info = fs_info; + xa_init(&trans->delayed_refs.head_refs); + xa_init(&trans->delayed_refs.dirty_extents); + spin_lock_init(&trans->delayed_refs.lock); +} + void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { @@ -295,6 +310,9 @@ int btrfs_run_sanity_tests(void) ret = btrfs_test_raid_stripe_tree(sectorsize, nodesize); if (ret) goto out; + ret = btrfs_test_delayed_refs(sectorsize, nodesize); + if (ret) + goto out; } } ret = btrfs_test_extent_map(); diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h index b524ecf2f452..4307bdaa6749 100644 --- a/fs/btrfs/tests/btrfs-tests.h +++ b/fs/btrfs/tests/btrfs-tests.h @@ -6,6 +6,8 @@ #ifndef BTRFS_TESTS_H #define BTRFS_TESTS_H +#include <linux/types.h> + #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_run_sanity_tests(void); @@ -25,12 +27,14 @@ enum { TEST_ALLOC_EXTENT_MAP, TEST_ALLOC_CHUNK_MAP, TEST_ALLOC_IO_CONTEXT, + TEST_ALLOC_TRANSACTION, }; extern const char *test_error[]; struct btrfs_root; struct btrfs_trans_handle; +struct btrfs_transaction; int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize); int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize); @@ -40,6 +44,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize); int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize); int btrfs_test_raid_stripe_tree(u32 sectorsize, u32 nodesize); int btrfs_test_extent_map(void); +int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize); struct inode *btrfs_new_test_inode(void); struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize); void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info); @@ -49,6 +54,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long lengt void btrfs_free_dummy_block_group(struct btrfs_block_group *cache); void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); +void btrfs_init_dummy_transaction(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info); struct btrfs_device *btrfs_alloc_dummy_device(struct btrfs_fs_info *fs_info); #else static inline int btrfs_run_sanity_tests(void) diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c new file mode 100644 index 000000000000..6558508c2ddf --- /dev/null +++ b/fs/btrfs/tests/delayed-refs-tests.c @@ -0,0 +1,1015 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/sizes.h> +#include "btrfs-tests.h" +#include "../transaction.h" +#include "../delayed-ref.h" +#include "../extent-tree.h" + +#define FAKE_ROOT_OBJECTID 256 +#define FAKE_BYTENR 0 +#define FAKE_LEVEL 1 +#define FAKE_INO 256 +#define FAKE_FILE_OFFSET 0 +#define FAKE_PARENT SZ_1M + +struct ref_head_check { + u64 bytenr; + u64 num_bytes; + int ref_mod; + int total_ref_mod; + int must_insert; +}; + +struct ref_node_check { + u64 bytenr; + u64 num_bytes; + int ref_mod; + enum btrfs_delayed_ref_action action; + u8 type; + u64 parent; + u64 root; + u64 owner; + u64 offset; +}; + +static enum btrfs_ref_type ref_type_from_disk_ref_type(u8 type) +{ + if ((type == BTRFS_TREE_BLOCK_REF_KEY) || + (type == BTRFS_SHARED_BLOCK_REF_KEY)) + return BTRFS_REF_METADATA; + return BTRFS_REF_DATA; +} + +static void delete_delayed_ref_head(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_head *head) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + + spin_lock(&delayed_refs->lock); + spin_lock(&head->lock); + btrfs_delete_ref_head(fs_info, delayed_refs, head); + spin_unlock(&head->lock); + spin_unlock(&delayed_refs->lock); + + btrfs_delayed_ref_unlock(head); + btrfs_put_delayed_ref_head(head); +} + +static void delete_delayed_ref_node(struct btrfs_delayed_ref_head *head, + struct btrfs_delayed_ref_node *node) +{ + rb_erase_cached(&node->ref_node, &head->ref_tree); + RB_CLEAR_NODE(&node->ref_node); + if (!list_empty(&node->add_list)) + list_del_init(&node->add_list); + btrfs_put_delayed_ref(node); +} + +static int validate_ref_head(struct btrfs_delayed_ref_head *head, + struct ref_head_check *check) +{ + if (head->bytenr != check->bytenr) { + test_err("invalid bytenr have: %llu want: %llu", head->bytenr, + check->bytenr); + return -EINVAL; + } + + if (head->num_bytes != check->num_bytes) { + test_err("invalid num_bytes have: %llu want: %llu", + head->num_bytes, check->num_bytes); + return -EINVAL; + } + + if (head->ref_mod != check->ref_mod) { + test_err("invalid ref_mod have: %d want: %d", head->ref_mod, + check->ref_mod); + return -EINVAL; + } + + if (head->total_ref_mod != check->total_ref_mod) { + test_err("invalid total_ref_mod have: %d want: %d", + head->total_ref_mod, check->total_ref_mod); + return -EINVAL; + } + + if (head->must_insert_reserved != check->must_insert) { + test_err("invalid must_insert have: %d want: %d", + head->must_insert_reserved, check->must_insert); + return -EINVAL; + } + + return 0; +} + +static int validate_ref_node(struct btrfs_delayed_ref_node *node, + struct ref_node_check *check) +{ + if (node->bytenr != check->bytenr) { + test_err("invalid bytenr have: %llu want: %llu", node->bytenr, + check->bytenr); + return -EINVAL; + } + + if (node->num_bytes != check->num_bytes) { + test_err("invalid num_bytes have: %llu want: %llu", + node->num_bytes, check->num_bytes); + return -EINVAL; + } + + if (node->ref_mod != check->ref_mod) { + test_err("invalid ref_mod have: %d want: %d", node->ref_mod, + check->ref_mod); + return -EINVAL; + } + + if (node->action != check->action) { + test_err("invalid action have: %d want: %d", node->action, + check->action); + return -EINVAL; + } + + if (node->parent != check->parent) { + test_err("invalid parent have: %llu want: %llu", node->parent, + check->parent); + return -EINVAL; + } + + if (node->ref_root != check->root) { + test_err("invalid root have: %llu want: %llu", node->ref_root, + check->root); + return -EINVAL; + } + + if (node->type != check->type) { + test_err("invalid type have: %d want: %d", node->type, + check->type); + return -EINVAL; + } + + if (btrfs_delayed_ref_owner(node) != check->owner) { + test_err("invalid owner have: %llu want: %llu", + btrfs_delayed_ref_owner(node), check->owner); + return -EINVAL; + } + + if (btrfs_delayed_ref_offset(node) != check->offset) { + test_err("invalid offset have: %llu want: %llu", + btrfs_delayed_ref_offset(node), check->offset); + return -EINVAL; + } + + return 0; +} + +static int simple_test(struct btrfs_trans_handle *trans, + struct ref_head_check *head_check, + struct ref_node_check *node_check) +{ + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_head *head; + struct btrfs_delayed_ref_node *node; + struct btrfs_ref ref = { + .type = ref_type_from_disk_ref_type(node_check->type), + .action = node_check->action, + .parent = node_check->parent, + .ref_root = node_check->root, + .bytenr = node_check->bytenr, + .num_bytes = fs_info->nodesize, + }; + int ret; + + if (ref.type == BTRFS_REF_METADATA) + btrfs_init_tree_ref(&ref, node_check->owner, node_check->root, + false); + else + btrfs_init_data_ref(&ref, node_check->owner, node_check->offset, + node_check->root, true); + + if (ref.type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + return ret; + } + + head = btrfs_select_ref_head(fs_info, delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + return -EINVAL; + } + + ret = -EINVAL; + if (validate_ref_head(head, head_check)) + goto out; + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, node_check)) + goto out; + ret = 0; +out: + btrfs_unselect_ref_head(delayed_refs, head); + btrfs_destroy_delayed_refs(trans->transaction); + return ret; +} + +/* + * These are simple tests, make sure that our btrfs_ref's get turned into the + * appropriate btrfs_delayed_ref_node based on their settings and action. + */ +static int simple_tests(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct ref_head_check head_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 1, + .total_ref_mod = 1, + }; + struct ref_node_check node_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 1, + .action = BTRFS_ADD_DELAYED_REF, + .type = BTRFS_TREE_BLOCK_REF_KEY, + .parent = 0, + .root = FAKE_ROOT_OBJECTID, + .owner = FAKE_LEVEL, + .offset = 0, + }; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add tree block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_EXTENT_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add extent data failed"); + return -EINVAL; + } + + node_check.parent = FAKE_PARENT; + node_check.type = BTRFS_SHARED_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + node_check.offset = 0; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add shared block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_SHARED_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single add shared data failed"); + return -EINVAL; + } + + head_check.ref_mod = -1; + head_check.total_ref_mod = -1; + node_check.action = BTRFS_DROP_DELAYED_REF; + node_check.type = BTRFS_TREE_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + node_check.offset = 0; + node_check.parent = 0; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop tree block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_EXTENT_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop extent data failed"); + return -EINVAL; + } + + node_check.parent = FAKE_PARENT; + node_check.type = BTRFS_SHARED_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + node_check.offset = 0; + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop shared block failed"); + return -EINVAL; + } + + node_check.type = BTRFS_SHARED_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + if (simple_test(trans, &head_check, &node_check)) { + test_err("single drop shared data failed"); + return -EINVAL; + } + + return 0; +} + +/* + * Merge tests, validate that we do delayed ref merging properly, the ref counts + * all end up properly, and delayed refs are deleted once they're no longer + * needed. + */ +static int merge_tests(struct btrfs_trans_handle *trans, + enum btrfs_ref_type type) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_head *head = NULL; + struct btrfs_delayed_ref_node *node; + struct btrfs_ref ref = { + .type = type, + .action = BTRFS_ADD_DELAYED_REF, + .parent = 0, + .ref_root = FAKE_ROOT_OBJECTID, + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + }; + struct ref_head_check head_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 0, + .total_ref_mod = 0, + }; + struct ref_node_check node_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 2, + .action = BTRFS_ADD_DELAYED_REF, + .parent = 0, + .root = FAKE_ROOT_OBJECTID, + }; + int ret; + + /* + * First add a ref and then drop it, make sure we get a head ref with a + * 0 total ref mod and no nodes. + */ + if (type == BTRFS_REF_METADATA) { + node_check.type = BTRFS_TREE_BLOCK_REF_KEY; + node_check.owner = FAKE_LEVEL; + btrfs_init_tree_ref(&ref, FAKE_LEVEL, FAKE_ROOT_OBJECTID, false); + } else { + node_check.type = BTRFS_EXTENT_DATA_REF_KEY; + node_check.owner = FAKE_INO; + node_check.offset = FAKE_FILE_OFFSET; + btrfs_init_data_ref(&ref, FAKE_INO, FAKE_FILE_OFFSET, + FAKE_ROOT_OBJECTID, true); + } + + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + return ret; + } + + ref.action = BTRFS_DROP_DELAYED_REF; + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + goto out; + } + + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("single add and drop failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + + delete_delayed_ref_head(trans, head); + head = NULL; + + /* + * Add a ref, then add another ref, make sure we get a head ref with a + * 2 total ref mod and 1 node. + */ + ref.action = BTRFS_ADD_DELAYED_REF; + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + goto out; + } + + head_check.ref_mod = 2; + head_check.total_ref_mod = 2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("double add failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + delete_delayed_ref_head(trans, head); + head = NULL; + + /* Add two drop refs, make sure they are merged properly. */ + ref.action = BTRFS_DROP_DELAYED_REF; + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + goto out; + } + + head_check.ref_mod = -2; + head_check.total_ref_mod = -2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("double drop failed"); + goto out; + } + + node_check.action = BTRFS_DROP_DELAYED_REF; + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + delete_delayed_ref_head(trans, head); + head = NULL; + + /* Add multiple refs, then drop until we go negative again. */ + ref.action = BTRFS_ADD_DELAYED_REF; + for (int i = 0; i < 10; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + ref.action = BTRFS_DROP_DELAYED_REF; + for (int i = 0; i < 12; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + goto out; + } + + head_check.ref_mod = -2; + head_check.total_ref_mod = -2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("double drop failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + + delete_delayed_ref_head(trans, head); + head = NULL; + + /* Drop multiple refs, then add until we go positive again. */ + ref.action = BTRFS_DROP_DELAYED_REF; + for (int i = 0; i < 10; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + ref.action = BTRFS_ADD_DELAYED_REF; + for (int i = 0; i < 12; i++) { + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + goto out; + } + + head_check.ref_mod = 2; + head_check.total_ref_mod = 2; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("add and drop to positive failed"); + goto out; + } + + node_check.action = BTRFS_ADD_DELAYED_REF; + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + delete_delayed_ref_head(trans, head); + head = NULL; + + /* + * Add a bunch of refs with different roots and parents, then drop them + * all, make sure everything is properly merged. + */ + ref.action = BTRFS_ADD_DELAYED_REF; + for (int i = 0; i < 50; i++) { + if (!(i % 2)) { + ref.parent = 0; + ref.ref_root = FAKE_ROOT_OBJECTID + i; + } else { + ref.parent = FAKE_PARENT + (i * fs_info->nodesize); + } + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + ref.action = BTRFS_DROP_DELAYED_REF; + for (int i = 0; i < 50; i++) { + if (!(i % 2)) { + ref.parent = 0; + ref.ref_root = FAKE_ROOT_OBJECTID + i; + } else { + ref.parent = FAKE_PARENT + (i * fs_info->nodesize); + } + if (type == BTRFS_REF_METADATA) + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + else + ret = btrfs_add_delayed_data_ref(trans, &ref, 0); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + } + + head = btrfs_select_ref_head(fs_info, &trans->transaction->delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + goto out; + } + + head_check.ref_mod = 0; + head_check.total_ref_mod = 0; + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("add and drop multiple failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (node) { + test_err("found node when none should exist"); + goto out; + } + ret = 0; +out: + if (!IS_ERR_OR_NULL(head)) + btrfs_unselect_ref_head(&trans->transaction->delayed_refs, head); + btrfs_destroy_delayed_refs(trans->transaction); + return ret; +} + +/* + * Basic test to validate we always get the add operations first followed by any + * delete operations. + */ +static int select_delayed_refs_test(struct btrfs_trans_handle *trans) +{ + struct btrfs_delayed_ref_root *delayed_refs = + &trans->transaction->delayed_refs; + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_delayed_ref_head *head = NULL; + struct btrfs_delayed_ref_node *node; + struct btrfs_ref ref = { + .type = BTRFS_REF_METADATA, + .action = BTRFS_DROP_DELAYED_REF, + .parent = 0, + .ref_root = FAKE_ROOT_OBJECTID, + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + }; + struct ref_head_check head_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 0, + .total_ref_mod = 0, + }; + struct ref_node_check node_check = { + .bytenr = FAKE_BYTENR, + .num_bytes = fs_info->nodesize, + .ref_mod = 1, + .action = BTRFS_ADD_DELAYED_REF, + .type = BTRFS_TREE_BLOCK_REF_KEY, + .parent = 0, + .owner = FAKE_LEVEL, + .offset = 0, + }; + int ret; + + /* Add the drop first. */ + btrfs_init_tree_ref(&ref, FAKE_LEVEL, FAKE_ROOT_OBJECTID, false); + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + return ret; + } + + /* + * Now add the add, and make it a different root so it's logically later + * in the rb tree. + */ + ref.action = BTRFS_ADD_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID + 1; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + head = NULL; + goto out; + } + + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("head check failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.root = FAKE_ROOT_OBJECTID + 1; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.action = BTRFS_DROP_DELAYED_REF; + node_check.root = FAKE_ROOT_OBJECTID; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + delete_delayed_ref_head(trans, head); + head = NULL; + + /* + * Now we're going to do the same thing, but we're going to have an add + * that gets deleted because of a merge, and make sure we still have + * another add in place. + */ + ref.action = BTRFS_DROP_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + ref.action = BTRFS_ADD_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID + 1; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + ref.action = BTRFS_DROP_DELAYED_REF; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + ref.action = BTRFS_ADD_DELAYED_REF; + ref.ref_root = FAKE_ROOT_OBJECTID + 2; + ret = btrfs_add_delayed_tree_ref(trans, &ref, NULL); + if (ret) { + test_err("failed ref action %d", ret); + goto out; + } + + head = btrfs_select_ref_head(fs_info, delayed_refs); + if (IS_ERR_OR_NULL(head)) { + if (IS_ERR(head)) + test_err("failed to select delayed ref head: %ld", + PTR_ERR(head)); + else + test_err("failed to find delayed ref head"); + ret = -EINVAL; + head = NULL; + goto out; + } + + ret = -EINVAL; + if (validate_ref_head(head, &head_check)) { + test_err("head check failed"); + goto out; + } + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.action = BTRFS_ADD_DELAYED_REF; + node_check.root = FAKE_ROOT_OBJECTID + 2; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + + spin_lock(&head->lock); + node = btrfs_select_delayed_ref(head); + spin_unlock(&head->lock); + if (!node) { + test_err("failed to select delayed ref"); + goto out; + } + + node_check.action = BTRFS_DROP_DELAYED_REF; + node_check.root = FAKE_ROOT_OBJECTID; + if (validate_ref_node(node, &node_check)) { + test_err("node check failed"); + goto out; + } + delete_delayed_ref_node(head, node); + ret = 0; +out: + if (head) + btrfs_unselect_ref_head(delayed_refs, head); + btrfs_destroy_delayed_refs(trans->transaction); + return ret; +} + +int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize) +{ + struct btrfs_transaction *transaction; + struct btrfs_trans_handle trans; + struct btrfs_fs_info *fs_info; + int ret; + + test_msg("running delayed refs tests"); + + fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); + if (!fs_info) { + test_std_err(TEST_ALLOC_FS_INFO); + return -ENOMEM; + } + transaction = kmalloc(sizeof(*transaction), GFP_KERNEL); + if (!transaction) { + test_std_err(TEST_ALLOC_TRANSACTION); + ret = -ENOMEM; + goto out_free_fs_info; + } + btrfs_init_dummy_trans(&trans, fs_info); + btrfs_init_dummy_transaction(transaction, fs_info); + trans.transaction = transaction; + + ret = simple_tests(&trans); + if (!ret) { + test_msg("running delayed refs merg tests on metadata refs"); + ret = merge_tests(&trans, BTRFS_REF_METADATA); + } + + if (!ret) { + test_msg("running delayed refs merg tests on data refs"); + ret = merge_tests(&trans, BTRFS_REF_DATA); + } + + if (!ret) + ret = select_delayed_refs_test(&trans); + +out_free_fs_info: + btrfs_free_dummy_fs_info(fs_info); + return ret; +} diff --git a/fs/btrfs/tests/raid-stripe-tree-tests.c b/fs/btrfs/tests/raid-stripe-tree-tests.c index 30f17eb7b6a8..a7bc58a5c1e2 100644 --- a/fs/btrfs/tests/raid-stripe-tree-tests.c +++ b/fs/btrfs/tests/raid-stripe-tree-tests.c @@ -14,6 +14,8 @@ #define RST_TEST_NUM_DEVICES (2) #define RST_TEST_RAID1_TYPE (BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_RAID1) +#define SZ_48K (SZ_32K + SZ_16K) + typedef int (*test_func_t)(struct btrfs_trans_handle *trans); static struct btrfs_device *btrfs_device_by_devid(struct btrfs_fs_devices *fs_devices, @@ -30,6 +32,613 @@ static struct btrfs_device *btrfs_device_by_devid(struct btrfs_fs_devices *fs_de } /* + * Test creating a range of three extents and then punch a hole in the middle, + * deleting all of the middle extents and partially deleting the "book ends". + */ +static int test_punch_hole_3extents(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 len1 = SZ_1M; + u64 logical2 = logical1 + len1; + u64 len2 = SZ_1M; + u64 logical3 = logical2 + len2; + u64 len3 = SZ_1M; + u64 hole_start = logical1 + SZ_256K; + u64 hole_len = SZ_2M; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + + /* Prepare for the test, 1st create 3 x 1M extents. */ + bioc->map_type = map_type; + bioc->size = len1; + + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical2; + bioc->size = len2; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical2 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical3; + bioc->size = len3; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical3 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + /* + * Delete a range starting at logical1 + 256K and 2M in length. Extent + * 1 is truncated to 256k length, extent 2 is completely dropped and + * extent 3 is moved 256K to the right. + */ + ret = btrfs_delete_raid_extent(trans, hole_start, hole_len); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + hole_start, hole_start + hole_len); + goto out; + } + + /* Get the first extent and check its size. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len1, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu, got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len1 != SZ_256K) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_256K, len1); + ret = -EINVAL; + goto out; + } + + /* Get the second extent and check it's absent. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical2, &len2, map_type, + 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded should fail", + logical2, logical2 + len2); + ret = -EINVAL; + goto out; + } + + /* Get the third extent and check its size. */ + logical3 += SZ_256K; + ret = btrfs_get_raid_extent_offset(fs_info, logical3, &len3, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical3, logical3 + len3); + goto out; + } + + if (io_stripe.physical != logical3) { + test_err("invalid physical address, expected %llu, got %llu", + logical3 + SZ_256K, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len3 != SZ_1M - SZ_256K) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_1M - SZ_256K, len3); + ret = -EINVAL; + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical1, len1); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical3, len3); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + +out: + btrfs_put_bioc(bioc); + return ret; +} + +static int test_delete_two_extents(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 len1 = SZ_1M; + u64 logical2 = logical1 + len1; + u64 len2 = SZ_1M; + u64 logical3 = logical2 + len2; + u64 len3 = SZ_1M; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + + /* Prepare for the test, 1st create 3 x 1M extents. */ + bioc->map_type = map_type; + bioc->size = len1; + + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical2; + bioc->size = len2; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical2 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical3; + bioc->size = len3; + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical3 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + /* + * Delete a range starting at logical1 and 2M in length. Extents 1 + * and 2 are dropped and extent 3 is kept as is. + */ + ret = btrfs_delete_raid_extent(trans, logical1, len1 + len2); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1, logical1 + len1 + len2); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len1, map_type, + 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", + logical1, len1); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical2, &len2, map_type, + 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", + logical2, len2); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical3, &len3, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical3, len3); + goto out; + } + + if (io_stripe.physical != logical3) { + test_err("invalid physical address, expected %llu, got %llu", + logical3, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len3 != SZ_1M) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_1M, len3); + ret = -EINVAL; + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical3, len3); +out: + btrfs_put_bioc(bioc); + return ret; +} + +/* Test punching a hole into a single RAID stripe-extent. */ +static int test_punch_hole(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 hole_start = logical1 + SZ_32K; + u64 hole_len = SZ_64K; + u64 logical2 = hole_start + hole_len; + u64 len = SZ_1M; + u64 len1 = SZ_32K; + u64 len2 = len - len1 - hole_len; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + bioc->map_type = map_type; + bioc->size = len; + + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len, map_type, 0, + &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", logical1, + logical1 + len); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len != SZ_1M) { + test_err("invalid stripe length, expected %llu got %llu", + (u64)SZ_1M, len); + ret = -EINVAL; + goto out; + } + + ret = btrfs_delete_raid_extent(trans, hole_start, hole_len); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + hole_start, hole_start + hole_len); + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len1, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical1, logical1 + len1); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu, got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len1 != SZ_32K) { + test_err("invalid stripe length, expected %llu, got %llu", + (u64)SZ_32K, len1); + ret = -EINVAL; + goto out; + } + + ret = btrfs_get_raid_extent_offset(fs_info, logical2, &len2, map_type, + 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", logical2, + logical2 + len2); + goto out; + } + + if (io_stripe.physical != logical2) { + test_err("invalid physical address, expected %llu, got %llu", + logical2, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len2 != len - len1 - hole_len) { + test_err("invalid length, expected %llu, got %llu", + len - len1 - hole_len, len2); + ret = -EINVAL; + goto out; + } + + /* Check for the absence of the hole. */ + ret = btrfs_get_raid_extent_offset(fs_info, hole_start, &hole_len, + map_type, 0, &io_stripe); + if (ret != -ENODATA) { + ret = -EINVAL; + test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", + hole_start, hole_start + SZ_64K); + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical1, len1); + if (ret) + goto out; + + ret = btrfs_delete_raid_extent(trans, logical2, len2); +out: + btrfs_put_bioc(bioc); + return ret; +} + +/* + * Test a 1M RST write that spans two adjacent RST items on disk and then + * delete a portion starting in the first item and spanning into the second + * item. This is similar to test_front_delete(), but spanning multiple items. + */ +static int test_front_delete_prev_item(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_io_context *bioc; + struct btrfs_io_stripe io_stripe = { 0 }; + u64 map_type = RST_TEST_RAID1_TYPE; + u64 logical1 = SZ_1M; + u64 logical2 = SZ_2M; + u64 len = SZ_1M; + int ret; + + bioc = alloc_btrfs_io_context(fs_info, logical1, RST_TEST_NUM_DEVICES); + if (!bioc) { + test_std_err(TEST_ALLOC_IO_CONTEXT); + ret = -ENOMEM; + goto out; + } + + io_stripe.dev = btrfs_device_by_devid(fs_info->fs_devices, 0); + bioc->map_type = map_type; + bioc->size = len; + + /* Insert RAID extent 1. */ + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical1 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + bioc->logical = logical2; + /* Insert RAID extent 2, directly adjacent to it. */ + for (int i = 0; i < RST_TEST_NUM_DEVICES; i++) { + struct btrfs_io_stripe *stripe = &bioc->stripes[i]; + + stripe->dev = btrfs_device_by_devid(fs_info->fs_devices, i); + if (!stripe->dev) { + test_err("cannot find device with devid %d", i); + ret = -EINVAL; + goto out; + } + + stripe->physical = logical2 + i * SZ_1G; + } + + ret = btrfs_insert_one_raid_extent(trans, bioc); + if (ret) { + test_err("inserting RAID extent failed: %d", ret); + goto out; + } + + ret = btrfs_delete_raid_extent(trans, logical1 + SZ_512K, SZ_1M); + if (ret) { + test_err("deleting RAID extent [%llu, %llu] failed", + logical1 + SZ_512K, (u64)SZ_1M); + goto out; + } + + /* Verify item 1 is truncated to 512K. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical1, &len, map_type, 0, + &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", logical1, + logical1 + len); + goto out; + } + + if (io_stripe.physical != logical1) { + test_err("invalid physical address, expected %llu got %llu", + logical1, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len != SZ_512K) { + test_err("invalid stripe length, expected %llu got %llu", + (u64)SZ_512K, len); + ret = -EINVAL; + goto out; + } + + /* Verify item 2's start is moved by 512K. */ + ret = btrfs_get_raid_extent_offset(fs_info, logical2 + SZ_512K, &len, + map_type, 0, &io_stripe); + if (ret) { + test_err("lookup of RAID extent [%llu, %llu] failed", + logical2 + SZ_512K, logical2 + len); + goto out; + } + + if (io_stripe.physical != logical2 + SZ_512K) { + test_err("invalid physical address, expected %llu got %llu", + logical2 + SZ_512K, io_stripe.physical); + ret = -EINVAL; + goto out; + } + + if (len != SZ_512K) { + test_err("invalid stripe length, expected %llu got %llu", + (u64)SZ_512K, len); + ret = -EINVAL; + goto out; + } + + /* Verify there's a hole at [1M+512K, 2M+512K] . */ + len = SZ_1M; + ret = btrfs_get_raid_extent_offset(fs_info, logical1 + SZ_512K, &len, + map_type, 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID [%llu, %llu] succeeded, should fail", + logical1 + SZ_512K, logical1 + SZ_512K + len); + goto out; + } + + /* Clean up after us. */ + ret = btrfs_delete_raid_extent(trans, logical1, SZ_512K); + if (ret) + goto out; + + ret = btrfs_delete_raid_extent(trans, logical2 + SZ_512K, SZ_512K); + +out: + btrfs_put_bioc(bioc); + return ret; +} + +/* * Test a 64K RST write on a 2 disk RAID1 at a logical address of 1M and then * delete the 1st 32K, making the new start address 1M+32K. */ @@ -94,45 +703,45 @@ static int test_front_delete(struct btrfs_trans_handle *trans) goto out; } - ret = btrfs_delete_raid_extent(trans, logical, SZ_32K); + ret = btrfs_delete_raid_extent(trans, logical, SZ_16K); if (ret) { test_err("deleting RAID extent [%llu, %llu] failed", logical, - logical + SZ_32K); + logical + SZ_16K); goto out; } - len = SZ_32K; - ret = btrfs_get_raid_extent_offset(fs_info, logical + SZ_32K, &len, + len -= SZ_16K; + ret = btrfs_get_raid_extent_offset(fs_info, logical + SZ_16K, &len, map_type, 0, &io_stripe); if (ret) { test_err("lookup of RAID extent [%llu, %llu] failed", - logical + SZ_32K, logical + SZ_32K + len); + logical + SZ_16K, logical + SZ_64K); goto out; } - if (io_stripe.physical != logical + SZ_32K) { + if (io_stripe.physical != logical + SZ_16K) { test_err("invalid physical address, expected %llu, got %llu", - logical + SZ_32K, io_stripe.physical); + logical + SZ_16K, io_stripe.physical); ret = -EINVAL; goto out; } - if (len != SZ_32K) { + if (len != SZ_48K) { test_err("invalid stripe length, expected %llu, got %llu", - (u64)SZ_32K, len); + (u64)SZ_48K, len); ret = -EINVAL; goto out; } ret = btrfs_get_raid_extent_offset(fs_info, logical, &len, map_type, 0, &io_stripe); - if (!ret) { + if (ret != -ENODATA) { ret = -EINVAL; test_err("lookup of RAID extent [%llu, %llu] succeeded, should fail", - logical, logical + SZ_32K); + logical, logical + SZ_16K); goto out; } - ret = btrfs_delete_raid_extent(trans, logical + SZ_32K, SZ_32K); + ret = btrfs_delete_raid_extent(trans, logical + SZ_16K, SZ_48K); out: btrfs_put_bioc(bioc); return ret; @@ -209,14 +818,14 @@ static int test_tail_delete(struct btrfs_trans_handle *trans) goto out; } - ret = btrfs_delete_raid_extent(trans, logical + SZ_32K, SZ_32K); + ret = btrfs_delete_raid_extent(trans, logical + SZ_48K, SZ_16K); if (ret) { test_err("deleting RAID extent [%llu, %llu] failed", - logical + SZ_32K, logical + SZ_64K); + logical + SZ_48K, logical + SZ_64K); goto out; } - len = SZ_32K; + len = SZ_48K; ret = btrfs_get_raid_extent_offset(fs_info, logical, &len, map_type, 0, &io_stripe); if (ret) { test_err("lookup of RAID extent [%llu, %llu] failed", logical, @@ -231,9 +840,19 @@ static int test_tail_delete(struct btrfs_trans_handle *trans) goto out; } - if (len != SZ_32K) { + if (len != SZ_48K) { test_err("invalid stripe length, expected %llu, got %llu", - (u64)SZ_32K, len); + (u64)SZ_48K, len); + ret = -EINVAL; + goto out; + } + + len = SZ_16K; + ret = btrfs_get_raid_extent_offset(fs_info, logical + SZ_48K, &len, + map_type, 0, &io_stripe); + if (ret != -ENODATA) { + test_err("lookup of RAID extent [%llu, %llu] succeeded should fail", + logical + SZ_48K, logical + SZ_64K); ret = -EINVAL; goto out; } @@ -456,6 +1075,10 @@ static const test_func_t tests[] = { test_create_update_delete, test_tail_delete, test_front_delete, + test_front_delete_prev_item, + test_punch_hole, + test_punch_hole_3extents, + test_delete_two_extents, }; static int run_test(test_func_t test, u32 sectorsize, u32 nodesize) @@ -478,8 +1101,8 @@ static int run_test(test_func_t test, u32 sectorsize, u32 nodesize) ret = PTR_ERR(root); goto out; } - btrfs_set_super_compat_ro_flags(root->fs_info->super_copy, - BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE); + btrfs_set_super_incompat_flags(root->fs_info->super_copy, + BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE); root->root_key.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID; root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = 0; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index dc0b837efd5d..15312013f2a3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -795,8 +795,7 @@ alloc_fail: if (num_bytes) btrfs_block_rsv_release(fs_info, trans_rsv, num_bytes, NULL); if (delayed_refs_bytes) - btrfs_space_info_free_bytes_may_use(fs_info, trans_rsv->space_info, - delayed_refs_bytes); + btrfs_space_info_free_bytes_may_use(trans_rsv->space_info, delayed_refs_bytes); reserve_fail: btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); return ERR_PTR(ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 184fa5c0062a..9f7c777af635 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -227,7 +227,21 @@ static inline void btrfs_clear_skip_qgroup(struct btrfs_trans_handle *trans) delayed_refs->qgroup_to_skip = 0; } -bool __cold abort_should_print_stack(int error); +/* + * We want the transaction abort to print stack trace only for errors where the + * cause could be a bug, eg. due to ENOSPC, and not for common errors that are + * caused by external factors. + */ +static inline bool btrfs_abort_should_print_stack(int error) +{ + switch (error) { + case -EIO: + case -EROFS: + case -ENOMEM: + return false; + } + return true; +} /* * Call btrfs_abort_transaction as early as possible when an error condition is @@ -240,7 +254,7 @@ do { \ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ &((trans)->fs_info->fs_state))) { \ __first = true; \ - if (WARN(abort_should_print_stack(error), \ + if (WARN(btrfs_abort_should_print_stack(error), \ KERN_ERR \ "BTRFS: Transaction aborted (error %d)\n", \ (error))) { \ diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40e..43979891f7c8 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -764,22 +764,19 @@ static int check_block_group_item(struct extent_buffer *leaf, return 0; } -__printf(4, 5) +__printf(5, 6) __cold -static void chunk_err(const struct extent_buffer *leaf, +static void chunk_err(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, const struct btrfs_chunk *chunk, u64 logical, const char *fmt, ...) { - const struct btrfs_fs_info *fs_info = leaf->fs_info; - bool is_sb; + bool is_sb = !leaf; struct va_format vaf; va_list args; int i; int slot = -1; - /* Only superblock eb is able to have such small offset */ - is_sb = (leaf->start == BTRFS_SUPER_INFO_OFFSET); - if (!is_sb) { /* * Get the slot number by iterating through all slots, this @@ -812,13 +809,17 @@ static void chunk_err(const struct extent_buffer *leaf, /* * The common chunk check which could also work on super block sys chunk array. * + * If @leaf is NULL, then @chunk must be an on-stack chunk item. + * (For superblock sys_chunk array, and fs_info->sectorsize is unreliable) + * * Return -EUCLEAN if anything is corrupted. * Return 0 if everything is OK. */ -int btrfs_check_chunk_valid(struct extent_buffer *leaf, - struct btrfs_chunk *chunk, u64 logical) +int btrfs_check_chunk_valid(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, + const struct btrfs_chunk *chunk, u64 logical, + u32 sectorsize) { - struct btrfs_fs_info *fs_info = leaf->fs_info; u64 length; u64 chunk_end; u64 stripe_len; @@ -826,63 +827,73 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, u16 sub_stripes; u64 type; u64 features; + u32 chunk_sector_size; bool mixed = false; int raid_index; int nparity; int ncopies; - length = btrfs_chunk_length(leaf, chunk); - stripe_len = btrfs_chunk_stripe_len(leaf, chunk); - num_stripes = btrfs_chunk_num_stripes(leaf, chunk); - sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); - type = btrfs_chunk_type(leaf, chunk); + if (leaf) { + length = btrfs_chunk_length(leaf, chunk); + stripe_len = btrfs_chunk_stripe_len(leaf, chunk); + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); + type = btrfs_chunk_type(leaf, chunk); + chunk_sector_size = btrfs_chunk_sector_size(leaf, chunk); + } else { + length = btrfs_stack_chunk_length(chunk); + stripe_len = btrfs_stack_chunk_stripe_len(chunk); + num_stripes = btrfs_stack_chunk_num_stripes(chunk); + sub_stripes = btrfs_stack_chunk_sub_stripes(chunk); + type = btrfs_stack_chunk_type(chunk); + chunk_sector_size = btrfs_stack_chunk_sector_size(chunk); + } raid_index = btrfs_bg_flags_to_raid_index(type); ncopies = btrfs_raid_array[raid_index].ncopies; nparity = btrfs_raid_array[raid_index].nparity; if (unlikely(!num_stripes)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk num_stripes, have %u", num_stripes); return -EUCLEAN; } if (unlikely(num_stripes < ncopies)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk num_stripes < ncopies, have %u < %d", num_stripes, ncopies); return -EUCLEAN; } if (unlikely(nparity && num_stripes == nparity)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk num_stripes == nparity, have %u == %d", num_stripes, nparity); return -EUCLEAN; } - if (unlikely(!IS_ALIGNED(logical, fs_info->sectorsize))) { - chunk_err(leaf, chunk, logical, + if (unlikely(!IS_ALIGNED(logical, sectorsize))) { + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk logical, have %llu should aligned to %u", - logical, fs_info->sectorsize); + logical, sectorsize); return -EUCLEAN; } - if (unlikely(btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize)) { - chunk_err(leaf, chunk, logical, + if (unlikely(chunk_sector_size != sectorsize)) { + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk sectorsize, have %u expect %u", - btrfs_chunk_sector_size(leaf, chunk), - fs_info->sectorsize); + chunk_sector_size, sectorsize); return -EUCLEAN; } - if (unlikely(!length || !IS_ALIGNED(length, fs_info->sectorsize))) { - chunk_err(leaf, chunk, logical, + if (unlikely(!length || !IS_ALIGNED(length, sectorsize))) { + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk length, have %llu", length); return -EUCLEAN; } if (unlikely(check_add_overflow(logical, length, &chunk_end))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk logical start and length, have logical start %llu length %llu", logical, length); return -EUCLEAN; } if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk stripe length: %llu", stripe_len); return -EUCLEAN; @@ -896,30 +907,29 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, * Thus it should be a good way to catch obvious bitflips. */ if (unlikely(length >= btrfs_stripe_nr_to_offset(U32_MAX))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "chunk length too large: have %llu limit %llu", length, btrfs_stripe_nr_to_offset(U32_MAX)); return -EUCLEAN; } if (unlikely(type & ~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "unrecognized chunk type: 0x%llx", ~(BTRFS_BLOCK_GROUP_TYPE_MASK | - BTRFS_BLOCK_GROUP_PROFILE_MASK) & - btrfs_chunk_type(leaf, chunk)); + BTRFS_BLOCK_GROUP_PROFILE_MASK) & type); return -EUCLEAN; } if (unlikely(!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set", type & BTRFS_BLOCK_GROUP_PROFILE_MASK); return -EUCLEAN; } if (unlikely((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0)) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "missing chunk type flag, have 0x%llx one bit must be set in 0x%llx", type, BTRFS_BLOCK_GROUP_TYPE_MASK); return -EUCLEAN; @@ -928,7 +938,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, if (unlikely((type & BTRFS_BLOCK_GROUP_SYSTEM) && (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "system chunk with data or metadata type: 0x%llx", type); return -EUCLEAN; @@ -941,7 +951,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, if (!mixed) { if (unlikely((type & BTRFS_BLOCK_GROUP_METADATA) && (type & BTRFS_BLOCK_GROUP_DATA))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "mixed chunk type in non-mixed mode: 0x%llx", type); return -EUCLEAN; } @@ -963,7 +973,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, num_stripes != btrfs_raid_array[BTRFS_RAID_DUP].dev_stripes) || ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != btrfs_raid_array[BTRFS_RAID_SINGLE].dev_stripes))) { - chunk_err(leaf, chunk, logical, + chunk_err(fs_info, leaf, chunk, logical, "invalid num_stripes:sub_stripes %u:%u for profile %llu", num_stripes, sub_stripes, type & BTRFS_BLOCK_GROUP_PROFILE_MASK); @@ -983,14 +993,15 @@ static int check_leaf_chunk_item(struct extent_buffer *leaf, struct btrfs_chunk *chunk, struct btrfs_key *key, int slot) { + struct btrfs_fs_info *fs_info = leaf->fs_info; int num_stripes; if (unlikely(btrfs_item_size(leaf, slot) < sizeof(struct btrfs_chunk))) { - chunk_err(leaf, chunk, key->offset, + chunk_err(fs_info, leaf, chunk, key->offset, "invalid chunk item size: have %u expect [%zu, %u)", btrfs_item_size(leaf, slot), sizeof(struct btrfs_chunk), - BTRFS_LEAF_DATA_SIZE(leaf->fs_info)); + BTRFS_LEAF_DATA_SIZE(fs_info)); return -EUCLEAN; } @@ -1001,14 +1012,15 @@ static int check_leaf_chunk_item(struct extent_buffer *leaf, if (unlikely(btrfs_chunk_item_size(num_stripes) != btrfs_item_size(leaf, slot))) { - chunk_err(leaf, chunk, key->offset, + chunk_err(fs_info, leaf, chunk, key->offset, "invalid chunk item size: have %u expect %lu", btrfs_item_size(leaf, slot), btrfs_chunk_item_size(num_stripes)); return -EUCLEAN; } out: - return btrfs_check_chunk_valid(leaf, chunk, key->offset); + return btrfs_check_chunk_valid(fs_info, leaf, chunk, key->offset, + fs_info->sectorsize); } __printf(3, 4) @@ -1527,6 +1539,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1556,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1633,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1721,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index db67f96cbe4b..eb201f4ec3c7 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -10,6 +10,7 @@ #include <uapi/linux/btrfs_tree.h> struct extent_buffer; +struct btrfs_fs_info; struct btrfs_chunk; struct btrfs_key; @@ -66,8 +67,10 @@ enum btrfs_tree_block_status __btrfs_check_node(struct extent_buffer *node); int btrfs_check_leaf(struct extent_buffer *leaf); int btrfs_check_node(struct extent_buffer *node); -int btrfs_check_chunk_valid(struct extent_buffer *leaf, - struct btrfs_chunk *chunk, u64 logical); +int btrfs_check_chunk_valid(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, + const struct btrfs_chunk *chunk, u64 logical, + u32 sectorsize); int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner); int btrfs_verify_level_key(struct extent_buffer *eb, const struct btrfs_tree_parent_check *check); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c8d6587688b3..955d1677e865 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -590,7 +590,6 @@ insert: } } no_copy: - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } @@ -3588,7 +3587,6 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, last_offset = max(last_offset, curr_end); } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); - btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } @@ -4566,7 +4564,6 @@ copy_item: dst_index++; } - btrfs_mark_buffer_dirty(trans, dst_path->nodes[0]); btrfs_release_path(dst_path); out: kfree(ins_data); @@ -4776,7 +4773,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, &fi, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(fi)); - btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index aca2861f2187..17b5e81123a1 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -140,8 +140,6 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ ret = 0; subid_le = cpu_to_le64(subid_cpu); write_extent_buffer(eb, &subid_le, offset, sizeof(subid_le)); - btrfs_mark_buffer_dirty(trans, eb); - out: btrfs_free_path(path); return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1cccaf9c2b0d..0a0776489055 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -13,8 +13,8 @@ #include <linux/list_sort.h> #include <linux/namei.h> #include "misc.h" -#include "ctree.h" #include "disk-io.h" +#include "extent-tree.h" #include "transaction.h" #include "volumes.h" #include "raid56.h" @@ -48,6 +48,7 @@ struct btrfs_io_geometry { u64 raid56_full_stripe_start; int max_errors; enum btrfs_map_op op; + bool use_rst; }; const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { @@ -797,6 +798,10 @@ static int get_canonical_dev_path(const char *dev_path, char *canonical) if (ret) goto out; resolved_path = d_path(&path, path_buf, PATH_MAX); + if (IS_ERR(resolved_path)) { + ret = PTR_ERR(resolved_path); + goto out; + } ret = strscpy(canonical, resolved_path, PATH_MAX); out: kfree(path_buf); @@ -1298,6 +1303,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device; struct btrfs_device *latest_dev = NULL; struct btrfs_device *tmp_device; + s64 __maybe_unused value = 0; int ret = 0; list_for_each_entry_safe(device, tmp_device, &fs_devices->devices, @@ -1327,7 +1333,23 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, fs_devices->latest_dev = latest_dev; fs_devices->total_rw_bytes = 0; fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_REGULAR; +#ifdef CONFIG_BTRFS_EXPERIMENTAL + fs_devices->rr_min_contig_read = BTRFS_DEFAULT_RR_MIN_CONTIG_READ; + fs_devices->read_devid = latest_dev->devid; + fs_devices->read_policy = btrfs_read_policy_to_enum(btrfs_get_mod_read_policy(), + &value); + if (fs_devices->read_policy == BTRFS_READ_POLICY_RR) + fs_devices->collect_fs_stats = true; + + if (value) { + if (fs_devices->read_policy == BTRFS_READ_POLICY_RR) + fs_devices->rr_min_contig_read = value; + if (fs_devices->read_policy == BTRFS_READ_POLICY_DEVID) + fs_devices->read_devid = value; + } +#else fs_devices->read_policy = BTRFS_READ_POLICY_PID; +#endif return 0; } @@ -2045,7 +2067,6 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans, ptr = btrfs_device_fsid(dev_item); write_extent_buffer(leaf, trans->fs_info->fs_devices->metadata_uuid, ptr, BTRFS_FSID_SIZE); - btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -2741,11 +2762,9 @@ next_slot: device = btrfs_find_device(fs_info->fs_devices, &args); BUG_ON(!device); /* Logic error */ - if (device->fs_devices->seeding) { + if (device->fs_devices->seeding) btrfs_set_device_generation(leaf, dev_item, device->generation); - btrfs_mark_buffer_dirty(trans, leaf); - } path->slots[0]++; goto next_slot; @@ -3038,8 +3057,6 @@ static noinline int btrfs_update_device(struct btrfs_trans_handle *trans, btrfs_device_get_disk_total_bytes(device)); btrfs_set_device_bytes_used(leaf, dev_item, btrfs_device_get_bytes_used(device)); - btrfs_mark_buffer_dirty(trans, leaf); - out: btrfs_free_path(path); return ret; @@ -3748,10 +3765,7 @@ static int insert_balance_item(struct btrfs_fs_info *fs_info, btrfs_set_balance_meta(leaf, item, &disk_bargs); btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->sys); btrfs_set_balance_sys(leaf, item, &disk_bargs); - btrfs_set_balance_flags(leaf, item, bctl->flags); - - btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); err = btrfs_commit_transaction(trans); @@ -5513,33 +5527,34 @@ void btrfs_remove_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_ma btrfs_free_chunk_map(map); } +static int btrfs_chunk_map_cmp(const struct rb_node *new, + const struct rb_node *exist) +{ + const struct btrfs_chunk_map *new_map = + rb_entry(new, struct btrfs_chunk_map, rb_node); + const struct btrfs_chunk_map *exist_map = + rb_entry(exist, struct btrfs_chunk_map, rb_node); + + if (new_map->start == exist_map->start) + return 0; + if (new_map->start < exist_map->start) + return -1; + return 1; +} + EXPORT_FOR_TESTS int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map) { - struct rb_node **p; - struct rb_node *parent = NULL; - bool leftmost = true; + struct rb_node *exist; write_lock(&fs_info->mapping_tree_lock); - p = &fs_info->mapping_tree.rb_root.rb_node; - while (*p) { - struct btrfs_chunk_map *entry; - - parent = *p; - entry = rb_entry(parent, struct btrfs_chunk_map, rb_node); - - if (map->start < entry->start) { - p = &(*p)->rb_left; - } else if (map->start > entry->start) { - p = &(*p)->rb_right; - leftmost = false; - } else { - write_unlock(&fs_info->mapping_tree_lock); - return -EEXIST; - } + exist = rb_find_add_cached(&map->rb_node, &fs_info->mapping_tree, + btrfs_chunk_map_cmp); + + if (exist) { + write_unlock(&fs_info->mapping_tree_lock); + return -EEXIST; } - rb_link_node(&map->rb_node, parent, p); - rb_insert_color_cached(&map->rb_node, &fs_info->mapping_tree, leftmost); chunk_map_device_set_bits(map, CHUNK_ALLOCATED); chunk_map_device_clear_bits(map, CHUNK_TRIMMED); write_unlock(&fs_info->mapping_tree_lock); @@ -5959,6 +5974,76 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, return len; } +#ifdef CONFIG_BTRFS_EXPERIMENTAL +static int btrfs_read_preferred(struct btrfs_chunk_map *map, int first, int num_stripes) +{ + for (int index = first; index < first + num_stripes; index++) { + const struct btrfs_device *device = map->stripes[index].dev; + + if (device->devid == READ_ONCE(device->fs_devices->read_devid)) + return index; + } + + /* If no read-preferred device is set use the first stripe. */ + return first; +} + +struct stripe_mirror { + u64 devid; + int num; +}; + +static int btrfs_cmp_devid(const void *a, const void *b) +{ + const struct stripe_mirror *s1 = (const struct stripe_mirror *)a; + const struct stripe_mirror *s2 = (const struct stripe_mirror *)b; + + if (s1->devid < s2->devid) + return -1; + if (s1->devid > s2->devid) + return 1; + return 0; +} + +/* + * Select a stripe for reading using the round-robin algorithm. + * + * 1. Compute the read cycle as the total sectors read divided by the minimum + * sectors per device. + * 2. Determine the stripe number for the current read by taking the modulus + * of the read cycle with the total number of stripes: + * + * stripe index = (total sectors / min sectors per dev) % num stripes + * + * The calculated stripe index is then used to select the corresponding device + * from the list of devices, which is ordered by devid. + */ +static int btrfs_read_rr(const struct btrfs_chunk_map *map, int first, int num_stripes) +{ + struct stripe_mirror stripes[BTRFS_RAID1_MAX_MIRRORS] = { 0 }; + struct btrfs_device *device = map->stripes[first].dev; + struct btrfs_fs_info *fs_info = device->fs_devices->fs_info; + unsigned int read_cycle; + unsigned int total_reads; + unsigned int min_reads_per_dev; + + total_reads = percpu_counter_sum(&fs_info->stats_read_blocks); + min_reads_per_dev = READ_ONCE(fs_info->fs_devices->rr_min_contig_read) >> + fs_info->sectorsize_bits; + + for (int index = 0, i = first; i < first + num_stripes; i++) { + stripes[index].devid = map->stripes[i].dev->devid; + stripes[index].num = i; + index++; + } + sort(stripes, num_stripes, sizeof(struct stripe_mirror), + btrfs_cmp_devid, NULL); + + read_cycle = total_reads / min_reads_per_dev; + return stripes[read_cycle % num_stripes].num; +} +#endif + static int find_live_mirror(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map, int first, int dev_replace_is_ongoing) @@ -5988,6 +6073,14 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, case BTRFS_READ_POLICY_PID: preferred_mirror = first + (current->pid % num_stripes); break; +#ifdef CONFIG_BTRFS_EXPERIMENTAL + case BTRFS_READ_POLICY_RR: + preferred_mirror = btrfs_read_rr(map, first, num_stripes); + break; + case BTRFS_READ_POLICY_DEVID: + preferred_mirror = btrfs_read_preferred(map, first, num_stripes); + break; +#endif } if (dev_replace_is_ongoing && @@ -6346,8 +6439,7 @@ static int set_io_stripe(struct btrfs_fs_info *fs_info, u64 logical, { dst->dev = map->stripes[io_geom->stripe_index].dev; - if (io_geom->op == BTRFS_MAP_READ && - btrfs_need_stripe_tree_update(fs_info, map->type)) + if (io_geom->op == BTRFS_MAP_READ && io_geom->use_rst) return btrfs_get_raid_extent_offset(fs_info, logical, length, map->type, io_geom->stripe_index, dst); @@ -6362,7 +6454,7 @@ static bool is_single_device_io(struct btrfs_fs_info *fs_info, const struct btrfs_io_stripe *smap, const struct btrfs_chunk_map *map, int num_alloc_stripes, - enum btrfs_map_op op, int mirror_num) + struct btrfs_io_geometry *io_geom) { if (!smap) return false; @@ -6370,10 +6462,10 @@ static bool is_single_device_io(struct btrfs_fs_info *fs_info, if (num_alloc_stripes != 1) return false; - if (btrfs_need_stripe_tree_update(fs_info, map->type) && op != BTRFS_MAP_READ) + if (io_geom->use_rst && io_geom->op != BTRFS_MAP_READ) return false; - if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && mirror_num > 1) + if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && io_geom->mirror_num > 1) return false; return true; @@ -6579,6 +6671,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom.raid56_full_stripe_start = (u64)-1; max_len = btrfs_max_io_len(map, map_offset, &io_geom); *length = min_t(u64, map->chunk_len - map_offset, max_len); + io_geom.use_rst = btrfs_need_stripe_tree_update(fs_info, map->type); if (dev_replace->replace_task != current) down_read(&dev_replace->rwsem); @@ -6647,8 +6740,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, * physical block information on the stack instead of allocating an * I/O context structure. */ - if (is_single_device_io(fs_info, smap, map, num_alloc_stripes, op, - io_geom.mirror_num)) { + if (is_single_device_io(fs_info, smap, map, num_alloc_stripes, &io_geom)) { ret = set_io_stripe(fs_info, logical, length, smap, map, &io_geom); if (mirror_num_ret) *mirror_num_ret = io_geom.mirror_num; @@ -6662,6 +6754,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, goto out; } bioc->map_type = map->type; + bioc->use_rst = io_geom.use_rst; /* * For RAID56 full map, we need to make sure the stripes[] follows the @@ -7002,16 +7095,6 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, warn_32bit_meta_chunk(fs_info, logical, length, type); #endif - /* - * Only need to verify chunk item if we're reading from sys chunk array, - * as chunk item in tree block is already verified by tree-checker. - */ - if (leaf->start == BTRFS_SUPER_INFO_OFFSET) { - ret = btrfs_check_chunk_valid(leaf, chunk, logical); - if (ret) - return ret; - } - map = btrfs_find_chunk_map(fs_info, logical, 1); /* already mapped? */ @@ -7269,16 +7352,11 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) { struct btrfs_super_block *super_copy = fs_info->super_copy; struct extent_buffer *sb; - struct btrfs_disk_key *disk_key; - struct btrfs_chunk *chunk; u8 *array_ptr; unsigned long sb_array_offset; int ret = 0; - u32 num_stripes; u32 array_size; - u32 len = 0; u32 cur_offset; - u64 type; struct btrfs_key key; ASSERT(BTRFS_SUPER_INFO_SIZE <= fs_info->nodesize); @@ -7301,10 +7379,15 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) cur_offset = 0; while (cur_offset < array_size) { - disk_key = (struct btrfs_disk_key *)array_ptr; - len = sizeof(*disk_key); - if (cur_offset + len > array_size) - goto out_short_read; + struct btrfs_chunk *chunk; + struct btrfs_disk_key *disk_key = (struct btrfs_disk_key *)array_ptr; + u32 len = sizeof(*disk_key); + + /* + * The sys_chunk_array has been already verified at super block + * read time. Only do ASSERT()s for basic checks. + */ + ASSERT(cur_offset + len <= array_size); btrfs_disk_key_to_cpu(&key, disk_key); @@ -7312,44 +7395,14 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) sb_array_offset += len; cur_offset += len; - if (key.type != BTRFS_CHUNK_ITEM_KEY) { - btrfs_err(fs_info, - "unexpected item type %u in sys_array at offset %u", - (u32)key.type, cur_offset); - ret = -EIO; - break; - } + ASSERT(key.type == BTRFS_CHUNK_ITEM_KEY); chunk = (struct btrfs_chunk *)sb_array_offset; - /* - * At least one btrfs_chunk with one stripe must be present, - * exact stripe count check comes afterwards - */ - len = btrfs_chunk_item_size(1); - if (cur_offset + len > array_size) - goto out_short_read; + ASSERT(btrfs_chunk_type(sb, chunk) & BTRFS_BLOCK_GROUP_SYSTEM); - num_stripes = btrfs_chunk_num_stripes(sb, chunk); - if (!num_stripes) { - btrfs_err(fs_info, - "invalid number of stripes %u in sys_array at offset %u", - num_stripes, cur_offset); - ret = -EIO; - break; - } + len = btrfs_chunk_item_size(btrfs_chunk_num_stripes(sb, chunk)); - type = btrfs_chunk_type(sb, chunk); - if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) { - btrfs_err(fs_info, - "invalid chunk type %llu in sys_array at offset %u", - type, cur_offset); - ret = -EIO; - break; - } - - len = btrfs_chunk_item_size(num_stripes); - if (cur_offset + len > array_size) - goto out_short_read; + ASSERT(cur_offset + len <= array_size); ret = read_one_chunk(&key, sb, chunk); if (ret) @@ -7362,13 +7415,6 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) clear_extent_buffer_uptodate(sb); free_extent_buffer_stale(sb); return ret; - -out_short_read: - btrfs_err(fs_info, "sys_array too short to read %u bytes at offset %u", - len, cur_offset); - clear_extent_buffer_uptodate(sb); - free_extent_buffer_stale(sb); - return -EIO; } /* @@ -7568,8 +7614,6 @@ int btrfs_init_devices_late(struct btrfs_fs_info *fs_info) struct btrfs_device *device; int ret = 0; - fs_devices->fs_info = fs_info; - mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry(device, &fs_devices->devices, dev_list) device->fs_info = fs_info; @@ -7745,8 +7789,6 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) btrfs_set_dev_stats_value(eb, ptr, i, btrfs_dev_stat_read(device, i)); - btrfs_mark_buffer_dirty(trans, eb); - out: btrfs_free_path(path); return ret; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 3a416b1bc24c..120f65e21eeb 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -296,6 +296,9 @@ enum btrfs_chunk_allocation_policy { BTRFS_CHUNK_ALLOC_ZONED, }; +#define BTRFS_DEFAULT_RR_MIN_CONTIG_READ (SZ_256K) +/* Keep in sync with raid_attr table, current maximum is RAID1C4. */ +#define BTRFS_RAID1_MAX_MIRRORS (4) /* * Read policies for mirrored block group profiles, read picks the stripe based * on these policies. @@ -303,6 +306,12 @@ enum btrfs_chunk_allocation_policy { enum btrfs_read_policy { /* Use process PID to choose the stripe */ BTRFS_READ_POLICY_PID, +#ifdef CONFIG_BTRFS_EXPERIMENTAL + /* Balancing RAID1 reads across all striped devices (round-robin). */ + BTRFS_READ_POLICY_RR, + /* Read from a specific device. */ + BTRFS_READ_POLICY_DEVID, +#endif BTRFS_NR_READ_POLICY, }; @@ -417,6 +426,8 @@ struct btrfs_fs_devices { bool seeding; /* The mount needs to use a randomly generated fsid. */ bool temp_fsid; + /* Enable/disable the filesystem stats tracking. */ + bool collect_fs_stats; struct btrfs_fs_info *fs_info; /* sysfs kobjects */ @@ -431,6 +442,15 @@ struct btrfs_fs_devices { enum btrfs_read_policy read_policy; #ifdef CONFIG_BTRFS_EXPERIMENTAL + /* + * Minimum contiguous reads before switching to next device, the unit + * is one block/sectorsize. + */ + u32 rr_min_contig_read; + + /* Device to be used for reading in case of RAID1. */ + u64 read_devid; + /* Checksum mode - offload it or do it synchronously. */ enum btrfs_offload_csum_mode offload_csum_mode; #endif @@ -485,6 +505,7 @@ struct btrfs_io_context { struct bio *orig_bio; atomic_t error; u16 max_errors; + bool use_rst; u64 logical; u64 size; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index bc18710d1dcf..3e0edbcf73e1 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -204,7 +204,6 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, btrfs_set_dir_data_len(leaf, di, size); data_ptr = ((unsigned long)(di + 1)) + name_len; write_extent_buffer(leaf, value, data_ptr, size); - btrfs_mark_buffer_dirty(trans, leaf); } else { /* * Insert, and we had space for the xattr, so path->slots[0] is diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index ddf0d5a448a7..c9e92c6941ec 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -174,10 +174,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, copy_page(workspace->buf + i * PAGE_SIZE, data_in); start += PAGE_SIZE; - workspace->strm.avail_in = - (in_buf_folios << PAGE_SHIFT); } workspace->strm.next_in = workspace->buf; + workspace->strm.avail_in = min(bytes_left, + in_buf_folios << PAGE_SHIFT); } else { unsigned int pg_off; unsigned int cur_len; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 11ed523e528e..73e0aa9fc08a 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -748,8 +748,9 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) (u64)lim->max_segments << PAGE_SHIFT), fs_info->sectorsize); fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; - if (fs_info->max_zone_append_size < fs_info->max_extent_size) - fs_info->max_extent_size = fs_info->max_zone_append_size; + + fs_info->max_extent_size = min_not_zero(fs_info->max_extent_size, + fs_info->max_zone_append_size); /* * Check mount options here, because we might change fs_info->zoned @@ -2651,3 +2652,127 @@ void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info) } spin_unlock(&fs_info->zone_active_bgs_lock); } + +/* + * Reset the zones of unused block groups from @space_info->bytes_zone_unusable. + * + * @space_info: the space to work on + * @num_bytes: targeting reclaim bytes + * + * This one resets the zones of a block group, so we can reuse the region + * without removing the block group. On the other hand, btrfs_delete_unused_bgs() + * just removes a block group and frees up the underlying zones. So, we still + * need to allocate a new block group to reuse the zones. + * + * Resetting is faster than deleting/recreating a block group. It is similar + * to freeing the logical space on the regular mode. However, we cannot change + * the block group's profile with this operation. + */ +int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, u64 num_bytes) +{ + struct btrfs_fs_info *fs_info = space_info->fs_info; + const sector_t zone_size_sectors = fs_info->zone_size >> SECTOR_SHIFT; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + while (num_bytes > 0) { + struct btrfs_chunk_map *map; + struct btrfs_block_group *bg = NULL; + bool found = false; + u64 reclaimed = 0; + + /* + * Here, we choose a fully zone_unusable block group. It's + * technically possible to reset a partly zone_unusable block + * group, which still has some free space left. However, + * handling that needs to cope with the allocation side, which + * makes the logic more complex. So, let's handle the easy case + * for now. + */ + spin_lock(&fs_info->unused_bgs_lock); + list_for_each_entry(bg, &fs_info->unused_bgs, bg_list) { + if ((bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) != space_info->flags) + continue; + + /* + * Use trylock to avoid locking order violation. In + * btrfs_reclaim_bgs_work(), the lock order is + * &bg->lock -> &fs_info->unused_bgs_lock. We skip a + * block group if we cannot take its lock. + */ + if (!spin_trylock(&bg->lock)) + continue; + if (btrfs_is_block_group_used(bg) || bg->zone_unusable < bg->length) { + spin_unlock(&bg->lock); + continue; + } + spin_unlock(&bg->lock); + found = true; + break; + } + if (!found) { + spin_unlock(&fs_info->unused_bgs_lock); + return 0; + } + + list_del_init(&bg->bg_list); + btrfs_put_block_group(bg); + spin_unlock(&fs_info->unused_bgs_lock); + + /* + * Since the block group is fully zone_unusable and we cannot + * allocate from this block group anymore, we don't need to set + * this block group read-only. + */ + + down_read(&fs_info->dev_replace.rwsem); + map = bg->physical_map; + for (int i = 0; i < map->num_stripes; i++) { + struct btrfs_io_stripe *stripe = &map->stripes[i]; + unsigned int nofs_flags; + int ret; + + nofs_flags = memalloc_nofs_save(); + ret = blkdev_zone_mgmt(stripe->dev->bdev, REQ_OP_ZONE_RESET, + stripe->physical >> SECTOR_SHIFT, + zone_size_sectors); + memalloc_nofs_restore(nofs_flags); + + if (ret) { + up_read(&fs_info->dev_replace.rwsem); + return ret; + } + } + up_read(&fs_info->dev_replace.rwsem); + + spin_lock(&space_info->lock); + spin_lock(&bg->lock); + ASSERT(!btrfs_is_block_group_used(bg)); + if (bg->ro) { + spin_unlock(&bg->lock); + spin_unlock(&space_info->lock); + continue; + } + + reclaimed = bg->alloc_offset; + bg->zone_unusable = bg->length - bg->zone_capacity; + bg->alloc_offset = 0; + /* + * This holds because we currently reset fully used then freed + * block group. + */ + ASSERT(reclaimed == bg->zone_capacity); + bg->free_space_ctl->free_space += reclaimed; + space_info->bytes_zone_unusable -= reclaimed; + spin_unlock(&bg->lock); + btrfs_return_free_space(space_info, reclaimed); + spin_unlock(&space_info->lock); + + if (num_bytes <= reclaimed) + break; + num_bytes -= reclaimed; + } + + return 0; +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 7612e6572605..9672bf4c3335 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -96,6 +96,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info); int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, bool do_finish); void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info); +int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, u64 num_bytes); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) @@ -265,6 +266,12 @@ static inline int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info, static inline void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info) { } +static inline int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, + u64 num_bytes) +{ + return 0; +} + #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 89b11336a836..1806bff8e59b 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -15,6 +15,7 @@ #include <linux/namei.h> #include <linux/poll.h> #include <linux/mount.h> +#include <linux/security.h> #include <linux/statfs.h> #include <linux/ctype.h> #include <linux/string.h> @@ -576,7 +577,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) */ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) { - char *secctx; + int err; _enter(",%s", args); @@ -585,16 +586,16 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) return -EINVAL; } - if (cache->secctx) { + if (cache->have_secid) { pr_err("Second security context specified\n"); return -EINVAL; } - secctx = kstrdup(args, GFP_KERNEL); - if (!secctx) - return -ENOMEM; + err = security_secctx_to_secid(args, strlen(args), &cache->secid); + if (err) + return err; - cache->secctx = secctx; + cache->have_secid = true; return 0; } @@ -820,7 +821,6 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) put_cred(cache->cache_cred); kfree(cache->rootdirname); - kfree(cache->secctx); kfree(cache->tag); _leave(""); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 7b99bd98de75..38c236e38cef 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -122,7 +122,6 @@ struct cachefiles_cache { #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ #define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ - char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ @@ -130,6 +129,8 @@ struct cachefiles_cache { struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; u32 msg_id_next; + u32 secid; /* LSM security id */ + bool have_secid; /* whether "secid" was set */ }; static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 6a821a959b59..92058ae43488 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -13,6 +13,7 @@ #include <linux/falloc.h> #include <linux/sched/mm.h> #include <trace/events/fscache.h> +#include <trace/events/netfs.h> #include "internal.h" struct cachefiles_kiocb { @@ -366,6 +367,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres, if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) { if (term_func) term_func(term_func_priv, -ENOBUFS, false); + trace_netfs_sreq(term_func_priv, netfs_sreq_trace_cache_nowrite); return -ENOBUFS; } @@ -695,6 +697,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) iov_iter_truncate(&subreq->io_iter, len); } + trace_netfs_sreq(subreq, netfs_sreq_trace_cache_prepare); cachefiles_begin_secure(cache, &saved_cred); ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres), &start, &len, len, true); @@ -704,6 +707,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq) return; } + trace_netfs_sreq(subreq, netfs_sreq_trace_cache_write); cachefiles_write(&subreq->rreq->cache_resources, subreq->start, &subreq->io_iter, netfs_write_subrequest_terminated, subreq); diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index fe777164f1d8..fc6611886b3b 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -18,7 +18,7 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) struct cred *new; int ret; - _enter("{%s}", cache->secctx); + _enter("{%u}", cache->have_secid ? cache->secid : 0); new = prepare_kernel_cred(current); if (!new) { @@ -26,8 +26,8 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) goto error; } - if (cache->secctx) { - ret = set_security_override_from_ctx(new, cache->secctx); + if (cache->have_secid) { + ret = set_security_override(new, cache->secid); if (ret < 0) { put_cred(new); pr_err("Security denies permission to nominate security context: error %d\n", diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 7c6f260a3be5..52383b1d0ba6 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -77,6 +77,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, file_inode(file), ret, cachefiles_trace_setxattr_error); trace_cachefiles_coherency(object, file_inode(file)->i_ino, + be64_to_cpup((__be64 *)buf->data), buf->content, cachefiles_coherency_set_fail); if (ret != -ENOMEM) @@ -85,6 +86,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) "Failed to set xattr with error %d", ret); } else { trace_cachefiles_coherency(object, file_inode(file)->i_ino, + be64_to_cpup((__be64 *)buf->data), buf->content, cachefiles_coherency_set_ok); } @@ -126,7 +128,10 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file object, "Failed to read aux with error %zd", xlen); why = cachefiles_coherency_check_xattr; - } else if (buf->type != CACHEFILES_COOKIE_TYPE_DATA) { + goto out; + } + + if (buf->type != CACHEFILES_COOKIE_TYPE_DATA) { why = cachefiles_coherency_check_type; } else if (memcmp(buf->data, p, len) != 0) { why = cachefiles_coherency_check_aux; @@ -141,7 +146,9 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file ret = 0; } +out: trace_cachefiles_coherency(object, file_inode(file)->i_ino, + be64_to_cpup((__be64 *)buf->data), buf->content, why); kfree(buf); return ret; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 85936f6d2bf7..f5224a566b69 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -223,10 +223,13 @@ static void finish_netfs_read(struct ceph_osd_request *req) subreq->len, i_size_read(req->r_inode)); /* no object means success but no data */ - if (err == -ENOENT) + if (err == -ENOENT) { + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); err = 0; - else if (err == -EBLOCKLISTED) + } else if (err == -EBLOCKLISTED) { fsc->blocklisted = true; + } if (err >= 0) { if (sparse && err > 0) @@ -242,6 +245,8 @@ static void finish_netfs_read(struct ceph_osd_request *req) if (err > subreq->len) err = subreq->len; } + if (err > 0) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); } if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { @@ -253,8 +258,9 @@ static void finish_netfs_read(struct ceph_osd_request *req) subreq->transferred = err; err = 0; } + subreq->error = err; trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress); - netfs_read_subreq_terminated(subreq, err, false); + netfs_read_subreq_terminated(subreq); iput(req->r_inode); ceph_dec_osd_stopping_blocker(fsc->mdsc); } @@ -314,7 +320,9 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) ceph_mdsc_put_request(req); out: - netfs_read_subreq_terminated(subreq, err, false); + subreq->error = err; + trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress); + netfs_read_subreq_terminated(subreq); return true; } @@ -426,8 +434,10 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) ceph_osdc_start_request(req->r_osdc, req); out: ceph_osdc_put_request(req); - if (err) - netfs_read_subreq_terminated(subreq, err, false); + if (err) { + subreq->error = err; + netfs_read_subreq_terminated(subreq); + } doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err); } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4b8d59ebda00..851d70200c6b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, if (ceph_inode_is_shutdown(inode)) return -EIO; - if (!len) + if (!len || !i_size) return 0; /* * flush any page cache pages in this range. this @@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, int num_pages; size_t page_off; bool more; - int idx; + int idx = 0; size_t left; struct ceph_osd_req_op *op; u64 read_off = off; @@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, len = read_off + read_len - off; more = len < iov_iter_count(to); + op = &req->r_ops[0]; + if (sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + num_pages = calc_pages_for(read_off, read_len); page_off = offset_in_page(off); pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); @@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, osd_req_op_extent_osd_data_pages(req, 0, pages, read_len, offset_in_page(read_off), - false, false); - - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } + false, true); ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); @@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, else if (ret == -ENOENT) ret = 0; - if (ret > 0 && IS_ENCRYPTED(inode)) { + if (ret < 0) { + ceph_osdc_put_request(req); + if (ret == -EBLOCKLISTED) + fsc->blocklisted = true; + break; + } + + if (IS_ENCRYPTED(inode)) { int fret; fret = ceph_fscrypt_decrypt_extents(inode, pages, @@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret = min_t(ssize_t, fret, len); } - ceph_osdc_put_request(req); - /* Short read but not EOF? Zero out the remainder. */ - if (ret >= 0 && ret < len && (off + ret < i_size)) { + if (ret < len && (off + ret < i_size)) { int zlen = min(len - ret, i_size - off - ret); int zoff = page_off + ret; @@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret += zlen; } - idx = 0; - if (ret <= 0) - left = 0; - else if (off + ret > i_size) - left = i_size - off; + if (off + ret > i_size) + left = (i_size > off) ? i_size - off : 0; else left = ret; + while (left > 0) { size_t plen, copied; @@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } } - ceph_release_page_vector(pages, num_pages); - if (ret < 0) { - if (ret == -EBLOCKLISTED) - fsc->blocklisted = true; - break; - } + ceph_osdc_put_request(req); if (off >= i_size || !more) break; @@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } + op = &req->r_ops[0]; + if (!write && sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, size); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages); if (len < 0) { ceph_osdc_put_request(req); @@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (len != size) osd_req_op_extent_update(req, 0, len); + osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); + /* * To simplify error handling, allow AIO when IO within i_size * or IO can be satisfied by single OSD request. @@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, req->r_mtime = mtime; } - osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, size); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } - if (aio_req) { aio_req->total_len += len; aio_req->num_reqs++; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 219a2cc2bf3c..785fe489ef4b 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2800,12 +2800,11 @@ retry: if (pos < 0) { /* - * A rename didn't occur, but somehow we didn't end up where - * we thought we would. Throw a warning and try again. + * The path is longer than PATH_MAX and this function + * cannot ever succeed. Creating paths that long is + * possible with Ceph, but Linux cannot use them. */ - pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n", - pos); - goto retry; + return ERR_PTR(-ENAMETOOLONG); } *pbase = base; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index de03cd6eb86e..4344e1f11806 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, switch (token) { case Opt_snapdirname: + if (strlen(param->string) > NAME_MAX) + return invalfc(fc, "snapdirname too long"); kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index af14ec382246..7fa1e7be50e4 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1132,8 +1132,7 @@ struct ceph_acl_sec_ctx { void *acl; #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL - void *sec_ctx; - u32 sec_ctxlen; + struct lsm_context lsmctx; #endif #ifdef CONFIG_FS_ENCRYPTION struct ceph_fscrypt_auth *fscrypt_auth; diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 1a9f12204666..537165db4519 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1383,8 +1383,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, int err; err = security_dentry_init_security(dentry, mode, &dentry->d_name, - &name, &as_ctx->sec_ctx, - &as_ctx->sec_ctxlen); + &name, &as_ctx->lsmctx); if (err < 0) { WARN_ON_ONCE(err != -EOPNOTSUPP); err = 0; /* do nothing */ @@ -1409,7 +1408,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, */ name_len = strlen(name); err = ceph_pagelist_reserve(pagelist, - 4 * 2 + name_len + as_ctx->sec_ctxlen); + 4 * 2 + name_len + as_ctx->lsmctx.len); if (err) goto out; @@ -1432,8 +1431,9 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, ceph_pagelist_encode_32(pagelist, name_len); ceph_pagelist_append(pagelist, name, name_len); - ceph_pagelist_encode_32(pagelist, as_ctx->sec_ctxlen); - ceph_pagelist_append(pagelist, as_ctx->sec_ctx, as_ctx->sec_ctxlen); + ceph_pagelist_encode_32(pagelist, as_ctx->lsmctx.len); + ceph_pagelist_append(pagelist, as_ctx->lsmctx.context, + as_ctx->lsmctx.len); err = 0; out: @@ -1451,7 +1451,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) posix_acl_release(as_ctx->default_acl); #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL - security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen); + security_release_secctx(&as_ctx->lsmctx); #endif #ifdef CONFIG_FS_ENCRYPTION kfree(as_ctx->fscrypt_auth); diff --git a/fs/dcache.c b/fs/dcache.c index b4d5e9e1e43d..1a01d7a6a7a9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1681,9 +1681,8 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ - dentry->d_lockref.count = 1; dentry->d_flags = 0; - spin_lock_init(&dentry->d_lock); + lockref_init(&dentry->d_lockref, 1); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 47dc96dfe386..16e198a26339 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -64,22 +64,13 @@ const struct file_operations *debugfs_real_fops(const struct file *filp) } EXPORT_SYMBOL_GPL(debugfs_real_fops); -/** - * debugfs_file_get - mark the beginning of file data access - * @dentry: the dentry object whose data is being accessed. - * - * Up to a matching call to debugfs_file_put(), any successive call - * into the file removing functions debugfs_remove() and - * debugfs_remove_recursive() will block. Since associated private - * file data may only get freed after a successful return of any of - * the removal functions, you may safely access it after a successful - * call to debugfs_file_get() without worrying about lifetime issues. - * - * If -%EIO is returned, the file has already been removed and thus, - * it is not safe to access any of its data. If, on the other hand, - * it is allowed to access the file data, zero is returned. - */ -int debugfs_file_get(struct dentry *dentry) +enum dbgfs_get_mode { + DBGFS_GET_ALREADY, + DBGFS_GET_REGULAR, + DBGFS_GET_SHORT, +}; + +static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) { struct debugfs_fsdata *fsd; void *d_fsd; @@ -96,15 +87,17 @@ int debugfs_file_get(struct dentry *dentry) if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; } else { + if (WARN_ON(mode == DBGFS_GET_ALREADY)) + return -EINVAL; + fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; - if ((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT) { + if (mode == DBGFS_GET_SHORT) { fsd->real_fops = NULL; fsd->short_fops = (void *)((unsigned long)d_fsd & - ~(DEBUGFS_FSDATA_IS_REAL_FOPS_BIT | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); } else { fsd->real_fops = (void *)((unsigned long)d_fsd & ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); @@ -138,6 +131,26 @@ int debugfs_file_get(struct dentry *dentry) return 0; } + +/** + * debugfs_file_get - mark the beginning of file data access + * @dentry: the dentry object whose data is being accessed. + * + * Up to a matching call to debugfs_file_put(), any successive call + * into the file removing functions debugfs_remove() and + * debugfs_remove_recursive() will block. Since associated private + * file data may only get freed after a successful return of any of + * the removal functions, you may safely access it after a successful + * call to debugfs_file_get() without worrying about lifetime issues. + * + * If -%EIO is returned, the file has already been removed and thus, + * it is not safe to access any of its data. If, on the other hand, + * it is allowed to access the file data, zero is returned. + */ +int debugfs_file_get(struct dentry *dentry) +{ + return __debugfs_file_get(dentry, DBGFS_GET_ALREADY); +} EXPORT_SYMBOL_GPL(debugfs_file_get); /** @@ -267,7 +280,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) const struct file_operations *real_fops = NULL; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR); if (r) return r == -EIO ? -ENOENT : r; @@ -424,7 +437,8 @@ static void __full_proxy_fops_init(struct file_operations *proxy_fops, proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; } -static int full_proxy_open(struct inode *inode, struct file *filp) +static int full_proxy_open(struct inode *inode, struct file *filp, + enum dbgfs_get_mode mode) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops; @@ -432,7 +446,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) struct debugfs_fsdata *fsd; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, mode); if (r) return r == -EIO ? -ENOENT : r; @@ -491,8 +505,22 @@ out: return r; } +static int full_proxy_open_regular(struct inode *inode, struct file *filp) +{ + return full_proxy_open(inode, filp, DBGFS_GET_REGULAR); +} + const struct file_operations debugfs_full_proxy_file_operations = { - .open = full_proxy_open, + .open = full_proxy_open_regular, +}; + +static int full_proxy_open_short(struct inode *inode, struct file *filp) +{ + return full_proxy_open(inode, filp, DBGFS_GET_SHORT); +} + +const struct file_operations debugfs_full_short_proxy_file_operations = { + .open = full_proxy_open_short, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 38a9c7eb97e6..e752009de929 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -229,7 +229,7 @@ static void debugfs_release_dentry(struct dentry *dentry) return; /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ - if (fsd && fsd->real_fops) { + if (fsd && (fsd->real_fops || fsd->short_fops)) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } @@ -455,8 +455,7 @@ struct dentry *debugfs_create_file_full(const char *name, umode_t mode, const struct file_operations *fops) { if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) return ERR_PTR(-EINVAL); return __debugfs_create_file(name, mode, parent, data, @@ -471,15 +470,13 @@ struct dentry *debugfs_create_file_short(const char *name, umode_t mode, const struct debugfs_short_fops *fops) { if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) return ERR_PTR(-EINVAL); return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_proxy_file_operations : + fops ? &debugfs_full_short_proxy_file_operations : &debugfs_noop_file_operations, - (const void *)((unsigned long)fops | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index a3edfa4f0d8e..bbae4a228ef4 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -15,6 +15,7 @@ struct file_operations; extern const struct file_operations debugfs_noop_file_operations; extern const struct file_operations debugfs_open_proxy_file_operations; extern const struct file_operations debugfs_full_proxy_file_operations; +extern const struct file_operations debugfs_full_short_proxy_file_operations; struct debugfs_fsdata { const struct file_operations *real_fops; @@ -40,11 +41,6 @@ struct debugfs_fsdata { * pointer gets its lowest bit set. */ #define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0) -/* - * A dentry's ->d_fsdata, when pointing to real fops, is with - * short fops instead of full fops. - */ -#define DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT BIT(1) /* Access BITS */ #define DEBUGFS_ALLOW_API BIT(0) diff --git a/fs/dlm/config.c b/fs/dlm/config.c index b2f21aa00719..cf9ba6fd7a28 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -935,7 +935,7 @@ int dlm_comm_seq(int nodeid, uint32_t *seq, bool locked) mutex_unlock(&clusters_root.subsys.su_mutex); } if (!cm) - return -EEXIST; + return -ENOENT; *seq = cm->seq; put_comm(cm); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index fc1d710166e9..c8ff88f1cdcf 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -824,9 +824,12 @@ static int find_rsb_dir(struct dlm_ls *ls, const void *name, int len, r->res_first_lkid = 0; } - /* A dir record will not be on the scan list. */ - if (r->res_dir_nodeid != our_nodeid) - del_scan(ls, r); + /* we always deactivate scan timer for the rsb, when + * we move it out of the inactive state as rsb state + * can be changed and scan timers are only for inactive + * rsbs. + */ + del_scan(ls, r); list_move(&r->res_slow_list, &ls->ls_slow_active); rsb_clear_flag(r, RSB_INACTIVE); kref_init(&r->res_ref); /* ref is now used in active state */ @@ -989,10 +992,10 @@ static int find_rsb_nodir(struct dlm_ls *ls, const void *name, int len, r->res_nodeid = 0; } + del_scan(ls, r); list_move(&r->res_slow_list, &ls->ls_slow_active); rsb_clear_flag(r, RSB_INACTIVE); kref_init(&r->res_ref); - del_scan(ls, r); write_unlock_bh(&ls->ls_rsbtbl_lock); goto out; @@ -1337,9 +1340,13 @@ static int _dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, const char *na __dlm_master_lookup(ls, r, our_nodeid, from_nodeid, true, flags, r_nodeid, result); - /* A dir record rsb should never be on scan list. */ - /* Try to fix this with del_scan? */ - WARN_ON(!list_empty(&r->res_scan_list)); + /* A dir record rsb should never be on scan list. + * Except when we are the dir and master node. + * This function should only be called by the dir + * node. + */ + WARN_ON(!list_empty(&r->res_scan_list) && + r->res_master_nodeid != our_nodeid); write_unlock_bh(&ls->ls_rsbtbl_lock); @@ -1430,16 +1437,23 @@ static void deactivate_rsb(struct kref *kref) list_move(&r->res_slow_list, &ls->ls_slow_inactive); /* - * When the rsb becomes unused: - * - If it's not a dir record for a remote master rsb, - * then it is put on the scan list to be freed. - * - If it's a dir record for a remote master rsb, - * then it is kept in the inactive state until - * receive_remove() from the master node. + * When the rsb becomes unused, there are two possibilities: + * 1. Leave the inactive rsb in place (don't remove it). + * 2. Add it to the scan list to be removed. + * + * 1 is done when the rsb is acting as the dir record + * for a remotely mastered rsb. The rsb must be left + * in place as an inactive rsb to act as the dir record. + * + * 2 is done when a) the rsb is not the master and not the + * dir record, b) when the rsb is both the master and the + * dir record, c) when the rsb is master but not dir record. + * + * (If no directory is used, the rsb can always be removed.) */ - if (!dlm_no_directory(ls) && - (r->res_master_nodeid != our_nodeid) && - (dlm_dir_nodeid(r) != our_nodeid)) + if (dlm_no_directory(ls) || + (r->res_master_nodeid == our_nodeid || + dlm_dir_nodeid(r) != our_nodeid)) add_scan(ls, r); if (r->res_lvbptr) { diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index df40c3fd1070..d28141829c05 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -462,7 +462,8 @@ static bool dlm_lowcomms_con_has_addr(const struct connection *con, int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr) { struct connection *con; - bool ret, idx; + bool ret; + int idx; idx = srcu_read_lock(&connections_srcu); con = nodeid2con(nodeid, GFP_NOFS); diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 586446e02ef7..ec23da8405ff 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -51,7 +51,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, * * VariableName-12345678-1234-1234-1234-1234567891bc */ -bool efivarfs_valid_name(const char *str, int len) +static bool efivarfs_valid_name(const char *str, int len) { const char *s = str + len - EFI_VARIABLE_GUID_LEN; diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index d71d2e08422f..74f0602a9e01 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -60,7 +60,6 @@ bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; -extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, const struct inode *dir, int mode, dev_t dev, bool is_removable); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index a929f1b613be..beba15673be8 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -144,9 +144,6 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr) const unsigned char *s = qstr->name; unsigned int len = qstr->len; - if (!efivarfs_valid_name(s, len)) - return -EINVAL; - while (len-- > EFI_VARIABLE_GUID_LEN) hash = partial_name_hash(*s++, hash); diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 1c49f8962021..0cd6b5c4df98 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..33f8539dda4a 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918..686d835eb533 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315e..f5956474bfde 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f147505487..33a128252687 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -320,7 +320,7 @@ static void erofs_destroy_percpu_workers(void) static struct kthread_worker *erofs_init_percpu_worker(int cpu) { struct kthread_worker *worker = - kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu); + kthread_run_worker_on_cpu(cpu, 0, "erofs_worker/%u"); if (IS_ERR(worker)) return worker; @@ -747,8 +747,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) if (IS_ERR(pcl)) return PTR_ERR(pcl); - spin_lock_init(&pcl->lockref.lock); - pcl->lockref.count = 1; /* one ref for this request */ + lockref_init(&pcl->lockref, 1); /* one ref for this request */ pcl->algorithmformat = map->m_algorithmformat; pcl->length = 0; pcl->partial = true; @@ -1792,9 +1791,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa..0dd65cefce33 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); diff --git a/fs/exec.c b/fs/exec.c index 98cb7ba9983c..18f25c23b09f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -892,7 +892,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) .lookup_flags = LOOKUP_FOLLOW, }; - if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) + if ((flags & + ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH | AT_EXECVE_CHECK)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; @@ -912,7 +913,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) path_noexec(&file->f_path)) return ERR_PTR(-EACCES); - err = deny_write_access(file); + err = exe_file_deny_write_access(file); if (err) return ERR_PTR(err); @@ -927,7 +928,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) * Returns ERR_PTR on failure or allocated struct file on success. * * As this is a wrapper for the internal do_open_execat(), callers - * must call allow_write_access() before fput() on release. Also see + * must call exe_file_allow_write_access() before fput() on release. Also see * do_close_execat(). */ struct file *open_exec(const char *name) @@ -1194,16 +1195,16 @@ static int unshare_sighand(struct task_struct *me) } /* - * These functions flushes out all traces of the currently running executable - * so that a new one can be started + * This is unlocked -- the string will always be NUL-terminated, but + * may show overlapping contents if racing concurrent reads. */ - void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { - task_lock(tsk); + size_t len = min(strlen(buf), sizeof(tsk->comm) - 1); + trace_task_rename(tsk, buf); - strscpy_pad(tsk->comm, buf, sizeof(tsk->comm)); - task_unlock(tsk); + memcpy(tsk->comm, buf, len); + memset(&tsk->comm[len], 0, sizeof(tsk->comm) - len); perf_event_comm(tsk, exec); } @@ -1341,7 +1342,28 @@ int begin_new_exec(struct linux_binprm * bprm) set_dumpable(current->mm, SUID_DUMP_USER); perf_event_exec(); - __set_task_comm(me, kbasename(bprm->filename), true); + + /* + * If the original filename was empty, alloc_bprm() made up a path + * that will probably not be useful to admins running ps or similar. + * Let's fix it up to be something reasonable. + */ + if (bprm->comm_from_dentry) { + /* + * Hold RCU lock to keep the name from being freed behind our back. + * Use acquire semantics to make sure the terminating NUL from + * __d_alloc() is seen. + * + * Note, we're deliberately sloppy here. We don't need to care about + * detecting a concurrent rename and just want a terminated name. + */ + rcu_read_lock(); + __set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name), + true); + rcu_read_unlock(); + } else { + __set_task_comm(me, kbasename(bprm->filename), true); + } /* An exec changes our domain. We are no longer part of the thread group */ @@ -1471,7 +1493,7 @@ static void do_close_execat(struct file *file) { if (!file) return; - allow_write_access(file); + exe_file_allow_write_access(file); fput(file); } @@ -1517,11 +1539,13 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { - if (filename->name[0] == '\0') + if (filename->name[0] == '\0') { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); - else + bprm->comm_from_dentry = 1; + } else { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); + } if (!bprm->fdpath) goto out_free; @@ -1541,6 +1565,21 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl } bprm->interp = bprm->filename; + /* + * At this point, security_file_open() has already been called (with + * __FMODE_EXEC) and access control checks for AT_EXECVE_CHECK will + * stop just after the security_bprm_creds_for_exec() call in + * bprm_execve(). Indeed, the kernel should not try to parse the + * content of the file with exec_binprm() nor change the calling + * thread, which means that the following security functions will not + * be called: + * - security_bprm_check() + * - security_bprm_creds_from_file() + * - security_bprm_committing_creds() + * - security_bprm_committed_creds() + */ + bprm->is_check = !!(flags & AT_EXECVE_CHECK); + retval = bprm_mm_init(bprm); if (!retval) return bprm; @@ -1719,13 +1758,11 @@ int remove_arg_zero(struct linux_binprm *bprm) } EXPORT_SYMBOL(remove_arg_zero); -#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ static int search_binary_handler(struct linux_binprm *bprm) { - bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; @@ -1737,8 +1774,6 @@ static int search_binary_handler(struct linux_binprm *bprm) if (retval) return retval; - retval = -ENOENT; - retry: read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) @@ -1756,17 +1791,7 @@ static int search_binary_handler(struct linux_binprm *bprm) } read_unlock(&binfmt_lock); - if (need_retry) { - if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && - printable(bprm->buf[2]) && printable(bprm->buf[3])) - return retval; - if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) - return retval; - need_retry = false; - goto retry; - } - - return retval; + return -ENOEXEC; } /* binfmt handlers will call back into begin_new_exec() on success. */ @@ -1797,7 +1822,7 @@ static int exec_binprm(struct linux_binprm *bprm) bprm->file = bprm->interpreter; bprm->interpreter = NULL; - allow_write_access(exec); + exe_file_allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); @@ -1836,7 +1861,7 @@ static int bprm_execve(struct linux_binprm *bprm) /* Set the unchanging part of bprm->cred */ retval = security_bprm_creds_for_exec(bprm); - if (retval) + if (retval || bprm->is_check) goto out; retval = exec_binprm(bprm); @@ -1904,9 +1929,6 @@ static int do_execveat_common(int fd, struct filename *filename, } retval = count(argv, MAX_ARG_STRINGS); - if (retval == 0) - pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", - current->comm, bprm->filename); if (retval < 0) goto out_free; bprm->argc = retval; @@ -1944,6 +1966,9 @@ static int do_execveat_common(int fd, struct filename *filename, if (retval < 0) goto out_free; bprm->argc = 1; + + pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", + current->comm, bprm->filename); } retval = bprm_execve(bprm); diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index fe0a9b8a0cd0..3103b932b674 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -122,7 +122,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent type = exfat_get_entry_type(ep); if (type == TYPE_UNUSED) { brelse(bh); - break; + goto out; } if (type != TYPE_FILE && type != TYPE_DIR) { @@ -170,6 +170,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent } } +out: dir_entry->namebuf.lfn[0] = '\0'; *cpos = EXFAT_DEN_TO_B(dentry); return 0; diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 773c320d68f3..9e5492ac409b 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -216,6 +216,16 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain if (err) goto dec_used_clus; + + if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { + /* + * The cluster chain includes a loop, scan the + * bitmap to get the number of used clusters. + */ + exfat_count_used_clusters(sb, &sbi->used_clusters); + + return 0; + } } while (clu != EXFAT_EOF_CLUSTER); } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index fb38769c3e39..05b51e721783 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -545,6 +545,7 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) while (pos < new_valid_size) { u32 len; struct folio *folio; + unsigned long off; len = PAGE_SIZE - (pos & (PAGE_SIZE - 1)); if (pos + len > new_valid_size) @@ -554,6 +555,9 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) if (err) goto out; + off = offset_in_folio(folio, pos); + folio_zero_new_buffers(folio, off, off + len); + err = ops->write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; @@ -563,6 +567,8 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) cond_resched(); } + return 0; + out: return err; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 97d2774760fe..099f80645072 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -330,8 +330,8 @@ static int exfat_find_empty_entry(struct inode *inode, while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir, num_entries, es)) < 0) { - if (dentry == -EIO) - break; + if (dentry != -ENOSPC) + return dentry; if (exfat_check_max_dentries(inode)) return -ENOSPC; diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index e20d59221fc0..c9ca41d91a6c 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -31,8 +31,7 @@ config EXT4_FS select BUFFER_HEAD select JBD2 select CRC16 - select CRYPTO - select CRYPTO_CRC32C + select CRC32 select FS_IOMAP select FS_ENCRYPTION_ALGS if FS_ENCRYPTION help diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 74f2071189b2..4e7de7eaa374 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -33,7 +33,7 @@ #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> #include <linux/ratelimit.h> -#include <crypto/hash.h> +#include <linux/crc32c.h> #include <linux/falloc.h> #include <linux/percpu-rwsem.h> #include <linux/fiemap.h> @@ -1662,9 +1662,6 @@ struct ext4_sb_info { /* record the last minlen when FITRIM is called. */ unsigned long s_last_trim_minblks; - /* Reference to checksum algorithm driver via cryptoapi */ - struct crypto_shash *s_chksum_driver; - /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_csum_seed; @@ -2463,19 +2460,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[4]; - } desc; - - BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); - - desc.shash.tfm = sbi->s_chksum_driver; - *(u32 *)desc.ctx = crc; - - BUG_ON(crypto_shash_update(&desc.shash, address, length)); - - return *(u32 *)desc.ctx; + return crc32c(crc, address, length); } #ifdef __KERNEL__ @@ -3276,11 +3261,7 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_metadata_csum(struct super_block *sb) { - WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && - !EXT4_SB(sb)->s_chksum_driver); - - return ext4_has_feature_metadata_csum(sb) && - (EXT4_SB(sb)->s_chksum_driver != NULL); + return ext4_has_feature_metadata_csum(sb); } static inline int ext4_has_group_desc_csum(struct super_block *sb) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3bd96c3d4cd0..a5205149adba 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -756,6 +756,9 @@ retry: return VM_FAULT_SIGBUS; } } else { + result = filemap_fsnotify_fault(vmf); + if (unlikely(result)) + return result; filemap_invalidate_lock_shared(mapping); } result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 89aade6f45f6..7c54ae5fcbd4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5006,10 +5006,11 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_ENCRYPTED(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; } else if (ext4_inode_is_fast_symlink(inode)) { - inode->i_link = (char *)ei->i_data; inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); + inode_set_cached_link(inode, (char *)ei->i_data, + inode->i_size); } else { inode->i_op = &ext4_symlink_inode_operations; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index bcf2737078b8..536d56d15072 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3418,7 +3418,6 @@ retry: inode->i_op = &ext4_symlink_inode_operations; } else { inode->i_op = &ext4_fast_symlink_inode_operations; - inode->i_link = (char *)&EXT4_I(inode)->i_data; } } @@ -3434,6 +3433,9 @@ retry: disk_link.len); inode->i_size = disk_link.len - 1; EXT4_I(inode)->i_disksize = inode->i_size; + if (!IS_ENCRYPTED(inode)) + inode_set_cached_link(inode, (char *)&EXT4_I(inode)->i_data, + inode->i_size); } err = ext4_add_nondir(handle, dentry, &inode); if (handle) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 785809f33ff4..a50e5c31b937 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1380,8 +1380,6 @@ static void ext4_put_super(struct super_block *sb) */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); @@ -4634,15 +4632,6 @@ static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_blo ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); - /* Load the checksum driver */ - sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(sbi->s_chksum_driver)) { - int ret = PTR_ERR(sbi->s_chksum_driver); - ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); - sbi->s_chksum_driver = NULL; - return ret; - } - /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " @@ -5312,6 +5301,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; + /* HSM events are allowed by default. */ + sb->s_iflags |= SB_I_ALLOW_HSM; + err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; @@ -5687,9 +5679,6 @@ failed_mount3: del_timer_sync(&sbi->s_err_report); ext4_group_desc_free(sbi); failed_mount: - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); - #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif @@ -7494,6 +7483,5 @@ static void __exit ext4_exit_fs(void) MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32c"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index 68a1e23e1557..5916a02fb46d 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -4,8 +4,7 @@ config F2FS_FS depends on BLOCK select BUFFER_HEAD select NLS - select CRYPTO - select CRYPTO_CRC32 + select CRC32 select F2FS_FS_XATTR if FS_ENCRYPTION select FS_ENCRYPTION_ALGS if FS_ENCRYPTION select FS_IOMAP diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6f2cbf4c5740..fd7e9cb6f893 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -24,7 +24,6 @@ #include <linux/quotaops.h> #include <linux/part_stat.h> #include <linux/rw_hint.h> -#include <crypto/hash.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> @@ -1768,9 +1767,6 @@ struct f2fs_sb_info { u64 sectors_written_start; u64 kbytes_written; - /* Reference to checksum algorithm driver via cryptoapi */ - struct crypto_shash *s_chksum_driver; - /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_chksum_seed; @@ -1948,21 +1944,7 @@ static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[4]; - } desc; - int err; - - BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); - - desc.shash.tfm = sbi->s_chksum_driver; - *(u32 *)desc.ctx = crc; - - err = crypto_shash_update(&desc.shash, address, length); - BUG_ON(err); - - return *(u32 *)desc.ctx; + return crc32(crc, address, length); } static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index fc7d463dee15..19b67828ae32 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1694,8 +1694,6 @@ static void f2fs_put_super(struct super_block *sb) kvfree(sbi->ckpt); - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->raw_super); f2fs_destroy_page_array_cache(sbi); @@ -4466,15 +4464,6 @@ try_onemore: } mutex_init(&sbi->flush_lock); - /* Load the checksum driver */ - sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0); - if (IS_ERR(sbi->s_chksum_driver)) { - f2fs_err(sbi, "Cannot load crc32 driver."); - err = PTR_ERR(sbi->s_chksum_driver); - sbi->s_chksum_driver = NULL; - goto free_sbi; - } - /* set a block size */ if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { f2fs_err(sbi, "unable to set blocksize"); @@ -4919,8 +4908,6 @@ free_options: free_sb_buf: kfree(raw_super); free_sbi: - if (sbi->s_chksum_driver) - crypto_free_shash(sbi->s_chksum_driver); kfree(sbi); sb->s_fs_info = NULL; @@ -5127,5 +5114,3 @@ module_exit(exit_f2fs_fs) MODULE_AUTHOR("Samsung Electronics's Praesto Team"); MODULE_DESCRIPTION("Flash Friendly File System"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32"); - diff --git a/fs/fcntl.c b/fs/fcntl.c index 49884fa3c81d..5598e4d57422 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -1158,10 +1158,10 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != + BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | - __FMODE_EXEC | __FMODE_NONOTIFY)); + __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, diff --git a/fs/fhandle.c b/fs/fhandle.c index ec9145047dfc..3e092ae6d142 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -187,17 +187,6 @@ static int get_path_from_fd(int fd, struct path *root) return 0; } -enum handle_to_path_flags { - HANDLE_CHECK_PERMS = (1 << 0), - HANDLE_CHECK_SUBTREE = (1 << 1), -}; - -struct handle_to_path_ctx { - struct path root; - enum handle_to_path_flags flags; - unsigned int fh_flags; -}; - static int vfs_dentry_acceptable(void *context, struct dentry *dentry) { struct handle_to_path_ctx *ctx = context; @@ -261,50 +250,55 @@ static int do_handle_to_path(struct file_handle *handle, struct path *path, { int handle_dwords; struct vfsmount *mnt = ctx->root.mnt; + struct dentry *dentry; /* change the handle size to multiple of sizeof(u32) */ handle_dwords = handle->handle_bytes >> 2; - path->dentry = exportfs_decode_fh_raw(mnt, - (struct fid *)handle->f_handle, - handle_dwords, handle->handle_type, - ctx->fh_flags, - vfs_dentry_acceptable, ctx); - if (IS_ERR_OR_NULL(path->dentry)) { - if (path->dentry == ERR_PTR(-ENOMEM)) + dentry = exportfs_decode_fh_raw(mnt, (struct fid *)handle->f_handle, + handle_dwords, handle->handle_type, + ctx->fh_flags, vfs_dentry_acceptable, + ctx); + if (IS_ERR_OR_NULL(dentry)) { + if (dentry == ERR_PTR(-ENOMEM)) return -ENOMEM; return -ESTALE; } + path->dentry = dentry; path->mnt = mntget(mnt); return 0; } -/* - * Allow relaxed permissions of file handles if the caller has the - * ability to mount the filesystem or create a bind-mount of the - * provided @mountdirfd. - * - * In both cases the caller may be able to get an unobstructed way to - * the encoded file handle. If the caller is only able to create a - * bind-mount we need to verify that there are no locked mounts on top - * of it that could prevent us from getting to the encoded file. - * - * In principle, locked mounts can prevent the caller from mounting the - * filesystem but that only applies to procfs and sysfs neither of which - * support decoding file handles. - */ -static inline bool may_decode_fh(struct handle_to_path_ctx *ctx, - unsigned int o_flags) +static inline int may_decode_fh(struct handle_to_path_ctx *ctx, + unsigned int o_flags) { struct path *root = &ctx->root; + if (capable(CAP_DAC_READ_SEARCH)) + return 0; + /* - * Restrict to O_DIRECTORY to provide a deterministic API that avoids a - * confusing api in the face of disconnected non-dir dentries. + * Allow relaxed permissions of file handles if the caller has + * the ability to mount the filesystem or create a bind-mount of + * the provided @mountdirfd. + * + * In both cases the caller may be able to get an unobstructed + * way to the encoded file handle. If the caller is only able to + * create a bind-mount we need to verify that there are no + * locked mounts on top of it that could prevent us from getting + * to the encoded file. + * + * In principle, locked mounts can prevent the caller from + * mounting the filesystem but that only applies to procfs and + * sysfs neither of which support decoding file handles. + * + * Restrict to O_DIRECTORY to provide a deterministic API that + * avoids a confusing api in the face of disconnected non-dir + * dentries. * * There's only one dentry for each directory inode (VFS rule)... */ if (!(o_flags & O_DIRECTORY)) - return false; + return -EPERM; if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN)) ctx->flags = HANDLE_CHECK_PERMS; @@ -314,14 +308,14 @@ static inline bool may_decode_fh(struct handle_to_path_ctx *ctx, !has_locked_children(real_mount(root->mnt), root->dentry)) ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE; else - return false; + return -EPERM; /* Are we able to override DAC permissions? */ if (!ns_capable(current_user_ns(), CAP_DAC_READ_SEARCH)) - return false; + return -EPERM; ctx->fh_flags = EXPORT_FH_DIR_ONLY; - return true; + return 0; } static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, @@ -331,15 +325,19 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, struct file_handle f_handle; struct file_handle *handle = NULL; struct handle_to_path_ctx ctx = {}; + const struct export_operations *eops; retval = get_path_from_fd(mountdirfd, &ctx.root); if (retval) goto out_err; - if (!capable(CAP_DAC_READ_SEARCH) && !may_decode_fh(&ctx, o_flags)) { - retval = -EPERM; + eops = ctx.root.mnt->mnt_sb->s_export_op; + if (eops && eops->permission) + retval = eops->permission(&ctx, o_flags); + else + retval = may_decode_fh(&ctx, o_flags); + if (retval) goto out_path; - } if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) { retval = -EFAULT; @@ -398,29 +396,28 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh, int open_flag) { long retval = 0; - struct path path; + struct path path __free(path_put) = {}; struct file *file; - int fd; + const struct export_operations *eops; retval = handle_to_path(mountdirfd, ufh, &path, open_flag); if (retval) return retval; - fd = get_unused_fd_flags(open_flag); - if (fd < 0) { - path_put(&path); + CLASS(get_unused_fd, fd)(O_CLOEXEC); + if (fd < 0) return fd; - } - file = file_open_root(&path, "", open_flag, 0); - if (IS_ERR(file)) { - put_unused_fd(fd); - retval = PTR_ERR(file); - } else { - retval = fd; - fd_install(fd, file); - } - path_put(&path); - return retval; + + eops = path.mnt->mnt_sb->s_export_op; + if (eops->open) + file = eops->open(&path, open_flag); + else + file = file_open_root(&path, "", open_flag, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + + fd_install(fd, file); + return take_fd(fd); } /** diff --git a/fs/file.c b/fs/file.c index fb1011cf6b4a..d868cdb95d1e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,7 @@ #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> +#include <linux/init_task.h> #include "internal.h" @@ -278,10 +279,6 @@ repeat: if (nr < fdt->max_fds) return 0; - /* Can we expand? */ - if (nr >= sysctl_nr_open) - return -EMFILE; - if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); @@ -289,6 +286,10 @@ repeat: goto repeat; } + /* Can we expand? */ + if (unlikely(nr >= sysctl_nr_open)) + return -EMFILE; + /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); @@ -1230,17 +1231,9 @@ __releases(&files->file_lock) /* * We need to detect attempts to do dup2() over allocated but still - * not finished descriptor. NB: OpenBSD avoids that at the price of - * extra work in their equivalent of fget() - they insert struct - * file immediately after grabbing descriptor, mark it larval if - * more work (e.g. actual opening) is needed and make sure that - * fget() treats larval files as absent. Potentially interesting, - * but while extra work in fget() is trivial, locking implications - * and amount of surgery on open()-related paths in VFS are not. - * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" - * deadlocks in rather amusing ways, AFAICS. All of that is out of - * scope of POSIX or SUS, since neither considers shared descriptor - * tables and this condition does not arise without those. + * not finished descriptor. + * + * POSIX is silent on the issue, we return -EBUSY. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); diff --git a/fs/file_table.c b/fs/file_table.c index 976736be47cb..a32171d2b83f 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -128,7 +128,7 @@ static struct ctl_table fs_stat_sysctls[] = { .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, @@ -478,6 +478,8 @@ static void ____fput(struct callback_head *work) __fput(container_of(work, struct file, f_task_work)); } +static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); + /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we @@ -491,11 +493,10 @@ static void ____fput(struct callback_head *work) void flush_delayed_fput(void) { delayed_fput(NULL); + flush_delayed_work(&delayed_fput_work); } EXPORT_SYMBOL_GPL(flush_delayed_fput); -static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); - void fput(struct file *file) { if (file_ref_put(&file->f_ref)) { diff --git a/fs/fs_context.c b/fs/fs_context.c index 98589aae5208..582d33e81117 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -493,7 +493,7 @@ static void put_fc_log(struct fs_context *fc) if (log) { if (refcount_dec_and_test(&log->usage)) { fc->log.log = NULL; - for (i = 0; i <= 7; i++) + for (i = 0; i < ARRAY_SIZE(log->buffer) ; i++) if (log->need_free & (1 << i)) kfree(log->buffer[i]); kfree(log); diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 16fa61ef56bf..e635a81e17d9 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -13,7 +13,7 @@ #include <linux/namei.h> #include "internal.h" -static const struct constant_table bool_names[] = { +const struct constant_table bool_names[] = { { "0", false }, { "1", true }, { "false", false }, @@ -22,6 +22,7 @@ static const struct constant_table bool_names[] = { { "yes", true }, { }, }; +EXPORT_SYMBOL(bool_names); static const struct constant_table * __lookup_constant(const struct constant_table *tbl, const char *name) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 494ac372ace0..bf057cf7098d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -467,29 +467,29 @@ static int get_security_context(struct dentry *entry, umode_t mode, { struct fuse_secctx *fctx; struct fuse_secctx_header *header; - void *ctx = NULL, *ptr; - u32 ctxlen, total_len = sizeof(*header); + struct lsm_context lsmctx = { }; + void *ptr; + u32 total_len = sizeof(*header); int err, nr_ctx = 0; - const char *name; + const char *name = NULL; size_t namelen; err = security_dentry_init_security(entry, mode, &entry->d_name, - &name, &ctx, &ctxlen); - if (err) { - if (err != -EOPNOTSUPP) - goto out_err; - /* No LSM is supporting this security hook. Ignore error */ - ctxlen = 0; - ctx = NULL; - } + &name, &lsmctx); - if (ctxlen) { + /* If no LSM is supporting this security hook ignore error */ + if (err && err != -EOPNOTSUPP) + goto out_err; + + if (lsmctx.len) { nr_ctx = 1; namelen = strlen(name) + 1; err = -EIO; - if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX)) + if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || + lsmctx.len > S32_MAX)) goto out_err; - total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen); + total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + + lsmctx.len); } err = -ENOMEM; @@ -502,19 +502,20 @@ static int get_security_context(struct dentry *entry, umode_t mode, ptr += sizeof(*header); if (nr_ctx) { fctx = ptr; - fctx->size = ctxlen; + fctx->size = lsmctx.len; ptr += sizeof(*fctx); strcpy(ptr, name); ptr += namelen; - memcpy(ptr, ctx, ctxlen); + memcpy(ptr, lsmctx.context, lsmctx.len); } ext->size = total_len; ext->value = header; err = 0; out_err: - kfree(ctx); + if (nr_ctx) + security_release_secctx(&lsmctx); return err; } @@ -1681,6 +1682,8 @@ static int fuse_dir_open(struct inode *inode, struct file *file) */ if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE)) nonseekable_open(inode, file); + if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 88d0946b5bc9..7d92a5479998 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1541,8 +1541,10 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, */ struct page **pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (nbytes < *nbytesp && nr_pages < max_pages) { unsigned nfolios, i; @@ -1557,18 +1559,22 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, nbytes += ret; - ret += start; - /* Currently, all folios in FUSE are one page */ - nfolios = DIV_ROUND_UP(ret, PAGE_SIZE); + nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE); + + for (i = 0; i < nfolios; i++) { + struct folio *folio = page_folio(pages[i]); + unsigned int offset = start + + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT); + unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start); - ap->descs[ap->num_folios].offset = start; - fuse_folio_descs_length_init(ap->descs, ap->num_folios, nfolios); - for (i = 0; i < nfolios; i++) - ap->folios[i + ap->num_folios] = page_folio(pages[i]); + ap->descs[ap->num_folios].offset = offset; + ap->descs[ap->num_folios].length = len; + ap->folios[ap->num_folios] = folio; + start = 0; + ret -= len; + ap->num_folios++; + } - ap->num_folios += nfolios; - ap->descs[ap->num_folios - 1].length -= - (PAGE_SIZE - ret) & (PAGE_SIZE - 1); nr_pages += nfolios; } kfree(pages); @@ -1584,6 +1590,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, else ap->args.out_pages = true; +out: *nbytesp = nbytes; return ret < 0 ? ret : 0; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 1e73cf87ff88..c9bb3be21d2b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -251,6 +251,7 @@ static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask) error = filemap_fdatawait(inode->i_mapping); if (error) goto out; + truncate_inode_pages(inode->i_mapping, 0); if (new_flags & GFS2_DIF_JDATA) gfs2_ordered_del_inode(ip); } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 72b48f6f5561..58bc5013ca49 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -236,8 +236,7 @@ static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, str return NULL; qd->qd_sbd = sdp; - qd->qd_lockref.count = 0; - spin_lock_init(&qd->qd_lockref.lock); + lockref_init(&qd->qd_lockref, 0); qd->qd_id = qid; qd->qd_slot = -1; INIT_LIST_HEAD(&qd->qd_lru); diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index f462d9cb3087..988f38dc5b2c 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -44,8 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, int ret; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ - if (capable(CAP_SYS_RESOURCE) || - sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF || + capable(CAP_SYS_RESOURCE)) return 0; ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 3bee9b5dba5e..fe09c2093a93 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -349,11 +349,13 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc) goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { - if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { + if (fd.entrylength != sizeof(rec.dir)) { res = -EIO; goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); + if (rec.type != HFS_CDR_DIR) + res = -EIO; } if (res) goto bail_hfs_find; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 90f883d6b8fd..fc1ae5132127 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -825,7 +825,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, error = PTR_ERR(folio); goto out; } - folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size)); + folio_zero_user(folio, addr); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 955f19e27e47..d303e6c8900c 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1138,7 +1138,7 @@ static void iomap_write_delalloc_scan(struct inode *inode, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_next_index(folio) << PAGE_SHIFT; + start_byte = folio_pos(folio) + folio_size(folio); folio_unlock(folio); folio_put(folio); } @@ -1774,7 +1774,8 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos) */ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, loff_t pos, unsigned len) + struct inode *inode, loff_t pos, loff_t end_pos, + unsigned len) { struct iomap_folio_state *ifs = folio->private; size_t poff = offset_in_folio(folio, pos); @@ -1793,15 +1794,60 @@ new_ioend: if (ifs) atomic_add(len, &ifs->write_bytes_pending); + + /* + * Clamp io_offset and io_size to the incore EOF so that ondisk + * file size updates in the ioend completion are byte-accurate. + * This avoids recovering files with zeroed tail regions when + * writeback races with appending writes: + * + * Thread 1: Thread 2: + * ------------ ----------- + * write [A, A+B] + * update inode size to A+B + * submit I/O [A, A+BS] + * write [A+B, A+B+C] + * update inode size to A+B+C + * <I/O completes, updates disk size to min(A+B+C, A+BS)> + * <power failure> + * + * After reboot: + * 1) with A+B+C < A+BS, the file has zero padding in range + * [A+B, A+B+C] + * + * |< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000| + * ^ ^ ^ + * A A+B A+B+C + * (EOF) + * + * 2) with A+B+C > A+BS, the file has zero padding in range + * [A+B, A+BS] + * + * |< Block Size (BS) >|< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000|00000000000000000000000000| + * ^ ^ ^ ^ + * A A+B A+BS A+B+C + * (EOF) + * + * D = Valid Data + * 0 = Zero Padding + * + * Note that this defeats the ability to chain the ioends of + * appending writes. + */ wpc->ioend->io_size += len; + if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) + wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + wbc_account_cgroup_owner(wbc, folio, len); return 0; } static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, u64 pos, unsigned dirty_len, - unsigned *count) + struct inode *inode, u64 pos, u64 end_pos, + unsigned dirty_len, unsigned *count) { int error; @@ -1826,7 +1872,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, break; default: error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos, - map_len); + end_pos, map_len); if (!error) (*count)++; break; @@ -1897,11 +1943,11 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, * remaining memory is zeroed when mapped, and writes to that * region are not written out to the file. * - * Also adjust the writeback range to skip all blocks entirely - * beyond i_size. + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); - *end_pos = round_up(isize, i_blocksize(inode)); + *end_pos = isize; } return true; @@ -1914,6 +1960,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct inode *inode = folio->mapping->host; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; unsigned count = 0; int error = 0; u32 rlen; @@ -1955,9 +2002,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, /* * Walk through the folio to find dirty areas to write back. */ - while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) { + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writepage_map_blocks(wpc, wbc, folio, inode, - pos, rlen, &count); + pos, end_pos, rlen, &count); if (error) break; pos += rlen; diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c index 34d5baa5d88a..5f3b6da0e022 100644 --- a/fs/isofs/compress.c +++ b/fs/isofs/compress.c @@ -301,7 +301,6 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount, */ static int zisofs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; int err; @@ -311,16 +310,15 @@ static int zisofs_read_folio(struct file *file, struct folio *folio) PAGE_SHIFT <= zisofs_block_shift ? (1 << (zisofs_block_shift - PAGE_SHIFT)) : 0; struct page **pages; - pgoff_t index = page->index, end_index; + pgoff_t index = folio->index, end_index; end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; /* - * If this page is wholly outside i_size we just return zero; + * If this folio is wholly outside i_size we just return zero; * do_generic_file_read() will handle this for us */ if (index >= end_index) { - SetPageUptodate(page); - unlock_page(page); + folio_end_read(folio, true); return 0; } @@ -338,10 +336,10 @@ static int zisofs_read_folio(struct file *file, struct folio *folio) pages = kcalloc(max_t(unsigned int, zisofs_pages_per_cblock, 1), sizeof(*pages), GFP_KERNEL); if (!pages) { - unlock_page(page); + folio_unlock(folio); return -ENOMEM; } - pages[full_page] = page; + pages[full_page] = &folio->page; for (i = 0; i < pcount; i++, index++) { if (i != full_page) diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig index 4ad2c67f93f1..9c19e1512101 100644 --- a/fs/jbd2/Kconfig +++ b/fs/jbd2/Kconfig @@ -2,8 +2,6 @@ config JBD2 tristate select CRC32 - select CRYPTO - select CRYPTO_CRC32C help This is a generic journaling layer for block devices that support both 32-bit and 64-bit block numbers. It is currently used by diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 9153ff3a08e7..e8e80761ac73 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -772,9 +772,9 @@ start_journal_io: /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue - * the commit record + * the commit record and update the journal tail sequence. */ - if (commit_transaction->t_need_data_flush && + if ((commit_transaction->t_need_data_flush || update_tail) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(journal->j_fs_dev); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 7e49d912b091..d8084b31b361 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1369,20 +1369,12 @@ static int journal_check_superblock(journal_t *journal) return err; } - /* Load the checksum driver */ if (jbd2_journal_has_csum_v2or3_feature(journal)) { if (sb->s_checksum_type != JBD2_CRC32C_CHKSUM) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); return err; } - journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); - err = PTR_ERR(journal->j_chksum_driver); - journal->j_chksum_driver = NULL; - return err; - } /* Check superblock checksum */ if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { printk(KERN_ERR "JBD2: journal checksum error\n"); @@ -1608,8 +1600,6 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: percpu_counter_destroy(&journal->j_checkpoint_jh_count); - if (journal->j_chksum_driver) - crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); journal_fail_superblock(journal); @@ -2191,8 +2181,6 @@ int jbd2_journal_destroy(journal_t *journal) iput(journal->j_inode); if (journal->j_revoke) jbd2_journal_destroy_revoke(journal); - if (journal->j_chksum_driver) - crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); @@ -2337,27 +2325,15 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, } } - /* Load the checksum driver if necessary */ - if ((journal->j_chksum_driver == NULL) && - INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { - journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); - journal->j_chksum_driver = NULL; - return 0; - } - /* Precompute checksum seed for all metadata */ - journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, - sizeof(sb->s_uuid)); - } - lock_buffer(journal->j_sb_buffer); - /* If enabling v3 checksums, update superblock */ + /* If enabling v3 checksums, update superblock and precompute seed */ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); } /* If enabling v1 checksums, downgrade superblock */ diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 4556e4689024..ce63d5fde9c3 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -654,7 +654,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(descriptor); BUFFER_TRACE(descriptor, "write"); set_buffer_dirty(descriptor); - write_dirty_buffer(descriptor, REQ_SYNC); + write_dirty_buffer(descriptor, JBD2_JOURNAL_REQ_FLAGS); } #endif diff --git a/fs/libfs.c b/fs/libfs.c index 748ac5923154..5b6120b19e99 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -245,9 +245,16 @@ const struct inode_operations simple_dir_inode_operations = { }; EXPORT_SYMBOL(simple_dir_inode_operations); -/* 0 is '.', 1 is '..', so always start with offset 2 or more */ +/* simple_offset_add() never assigns these to a dentry */ enum { - DIR_OFFSET_MIN = 2, + DIR_OFFSET_FIRST = 2, /* Find first real entry */ + DIR_OFFSET_EOD = S32_MAX, +}; + +/* simple_offset_add() allocation range */ +enum { + DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, + DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; static void offset_set(struct dentry *dentry, long offset) @@ -291,9 +298,10 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) return -EBUSY; ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, - LONG_MAX, &octx->next_offset, GFP_KERNEL); - if (ret < 0) - return ret; + DIR_OFFSET_MAX, &octx->next_offset, + GFP_KERNEL); + if (unlikely(ret < 0)) + return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; @@ -330,38 +338,6 @@ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) } /** - * simple_offset_empty - Check if a dentry can be unlinked - * @dentry: dentry to be tested - * - * Returns 0 if @dentry is a non-empty directory; otherwise returns 1. - */ -int simple_offset_empty(struct dentry *dentry) -{ - struct inode *inode = d_inode(dentry); - struct offset_ctx *octx; - struct dentry *child; - unsigned long index; - int ret = 1; - - if (!inode || !S_ISDIR(inode->i_mode)) - return ret; - - index = DIR_OFFSET_MIN; - octx = inode->i_op->get_offset_ctx(inode); - mt_for_each(&octx->mt, child, index, LONG_MAX) { - spin_lock(&child->d_lock); - if (simple_positive(child)) { - spin_unlock(&child->d_lock); - ret = 0; - break; - } - spin_unlock(&child->d_lock); - } - - return ret; -} - -/** * simple_offset_rename - handle directory offsets for rename * @old_dir: parent directory of source entry * @old_dentry: dentry of source entry @@ -454,14 +430,6 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } -static int offset_dir_open(struct inode *inode, struct file *file) -{ - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - - file->private_data = (void *)ctx->next_offset; - return 0; -} - /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -475,9 +443,6 @@ static int offset_dir_open(struct inode *inode, struct file *file) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { - struct inode *inode = file->f_inode; - struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); - switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -490,62 +455,89 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) return -EINVAL; } - /* In this case, ->private_data is protected by f_pos_lock */ - if (!offset) - file->private_data = (void *)ctx->next_offset; return vfs_setpos(file, offset, LONG_MAX); } -static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset) +static struct dentry *find_positive_dentry(struct dentry *parent, + struct dentry *dentry, + bool next) { - MA_STATE(mas, &octx->mt, offset, offset); + struct dentry *found = NULL; + + spin_lock(&parent->d_lock); + if (next) + dentry = d_next_sibling(dentry); + else if (!dentry) + dentry = d_first_child(parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (!simple_positive(dentry)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(dentry)) + found = dget_dlock(dentry); + spin_unlock(&dentry->d_lock); + if (likely(found)) + break; + } + spin_unlock(&parent->d_lock); + return found; +} + +static noinline_for_stack struct dentry * +offset_dir_lookup(struct dentry *parent, loff_t offset) +{ + struct inode *inode = d_inode(parent); + struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; - rcu_read_lock(); - child = mas_find(&mas, LONG_MAX); - if (!child) - goto out; - spin_lock(&child->d_lock); - if (simple_positive(child)) - found = dget_dlock(child); - spin_unlock(&child->d_lock); -out: - rcu_read_unlock(); + MA_STATE(mas, &octx->mt, offset, offset); + + if (offset == DIR_OFFSET_FIRST) + found = find_positive_dentry(parent, NULL, false); + else { + rcu_read_lock(); + child = mas_find(&mas, DIR_OFFSET_MAX); + found = find_positive_dentry(parent, child, false); + rcu_read_unlock(); + } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); - long offset = dentry2offset(dentry); - return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, - inode->i_ino, fs_umode_to_dtype(inode->i_mode)); + return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, + inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) +static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { - struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); + struct dentry *dir = file->f_path.dentry; struct dentry *dentry; + dentry = offset_dir_lookup(dir, ctx->pos); + if (!dentry) + goto out_eod; while (true) { - dentry = offset_find_next(octx, ctx->pos); - if (!dentry) - return; - - if (dentry2offset(dentry) >= last_index) { - dput(dentry); - return; - } + struct dentry *next; - if (!offset_dir_emit(ctx, dentry)) { - dput(dentry); - return; - } + ctx->pos = dentry2offset(dentry); + if (!offset_dir_emit(ctx, dentry)) + break; - ctx->pos = dentry2offset(dentry) + 1; + next = find_positive_dentry(dir, dentry, true); dput(dentry); + + if (!next) + goto out_eod; + dentry = next; } + dput(dentry); + return; + +out_eod: + ctx->pos = DIR_OFFSET_EOD; } /** @@ -565,6 +557,8 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon * * On return, @ctx->pos contains an offset that will read the next entry * in this directory when offset_readdir() is called again with @ctx. + * Caller places this value in the d_off field of the last entry in the + * user's buffer. * * Return values: * %0 - Complete @@ -572,19 +566,17 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; - long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - - offset_iterate_dir(d_inode(dir), ctx, last_index); + if (ctx->pos != DIR_OFFSET_EOD) + offset_iterate_dir(file, ctx); return 0; } const struct file_operations simple_offset_dir_operations = { - .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, @@ -673,6 +665,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; + s->s_export_op = ctx->eops; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); diff --git a/fs/mount.h b/fs/mount.h index 185fc56afc13..ffb613cdfeee 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -8,15 +8,23 @@ struct mnt_namespace { struct ns_common ns; struct mount * root; - struct rb_root mounts; /* Protected by namespace_sem */ + struct { + struct rb_root mounts; /* Protected by namespace_sem */ + struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ + struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ + }; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ - wait_queue_head_t poll; + union { + wait_queue_head_t poll; + struct rcu_head mnt_ns_rcu; + }; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ + struct list_head mnt_ns_list; /* entry in the sequential list of mounts namespace */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; @@ -38,6 +46,7 @@ struct mount { struct dentry *mnt_mountpoint; struct vfsmount mnt; union { + struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; @@ -51,10 +60,7 @@ struct mount { struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ - union { - struct rb_node mnt_node; /* Under ns->mounts */ - struct list_head mnt_list; - }; + struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ @@ -145,24 +151,28 @@ static inline bool is_anon_ns(struct mnt_namespace *ns) return ns->seq == 0; } +static inline bool mnt_ns_attached(const struct mount *mnt) +{ + return !RB_EMPTY_NODE(&mnt->mnt_node); +} + static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { - WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); - mnt->mnt.mnt_flags &= ~MNT_ONRB; - rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); + struct mnt_namespace *ns = mnt->mnt_ns; + WARN_ON(!mnt_ns_attached(mnt)); + if (ns->mnt_last_node == &mnt->mnt_node) + ns->mnt_last_node = rb_prev(&mnt->mnt_node); + if (ns->mnt_first_node == &mnt->mnt_node) + ns->mnt_first_node = rb_next(&mnt->mnt_node); + rb_erase(&mnt->mnt_node, &ns->mounts); + RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); -struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); -static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns) -{ - return __lookup_next_mnt_ns(mntns, false); -} -static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns) -{ - return __lookup_next_mnt_ns(mntns, true); -} +struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, + bool previous); + static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); diff --git a/fs/namei.c b/fs/namei.c index 9d30c7aa9aa6..e56c29a22d26 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -5272,19 +5272,16 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna getname(newname), 0); } -int readlink_copy(char __user *buffer, int buflen, const char *link) +int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen) { - int len = PTR_ERR(link); - if (IS_ERR(link)) - goto out; + int copylen; - len = strlen(link); - if (len > (unsigned) buflen) - len = buflen; - if (copy_to_user(buffer, link, len)) - len = -EFAULT; -out: - return len; + copylen = linklen; + if (unlikely(copylen > (unsigned) buflen)) + copylen = buflen; + if (copy_to_user(buffer, link, copylen)) + copylen = -EFAULT; + return copylen; } /** @@ -5304,6 +5301,9 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) const char *link; int res; + if (inode->i_opflags & IOP_CACHED_LINK) + return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen); + if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); @@ -5322,7 +5322,7 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) if (IS_ERR(link)) return PTR_ERR(link); } - res = readlink_copy(buffer, buflen, link); + res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } @@ -5391,10 +5391,14 @@ EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { + const char *link; + int res; + DEFINE_DELAYED_CALL(done); - int res = readlink_copy(buffer, buflen, - page_get_link(dentry, d_inode(dentry), - &done)); + link = page_get_link(dentry, d_inode(dentry), &done); + res = PTR_ERR(link); + if (!IS_ERR(link)) + res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } diff --git a/fs/namespace.c b/fs/namespace.c index 23e81c2a1e3f..4013fbac354a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -32,7 +32,7 @@ #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> -#include <linux/nospec.h> +#include <linux/pidfs.h> #include "pnode.h" #include "internal.h" @@ -66,12 +66,12 @@ static int __init set_mphash_entries(char *str) __setup("mphash_entries=", set_mphash_entries); static u64 event; -static DEFINE_IDA(mnt_id_ida); +static DEFINE_XARRAY_FLAGS(mnt_id_xa, XA_FLAGS_ALLOC); static DEFINE_IDA(mnt_group_ida); /* Don't allow confusion with old 32bit mount ID */ #define MNT_UNIQUE_ID_OFFSET (1ULL << 31) -static atomic64_t mnt_id_ctr = ATOMIC64_INIT(MNT_UNIQUE_ID_OFFSET); +static u64 mnt_id_ctr = MNT_UNIQUE_ID_OFFSET; static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; @@ -79,8 +79,10 @@ static struct kmem_cache *mnt_cache __ro_after_init; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ -static DEFINE_RWLOCK(mnt_ns_tree_lock); +static DEFINE_SEQLOCK(mnt_ns_tree_lock); + static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */ +static LIST_HEAD(mnt_ns_list); /* protected by mnt_ns_tree_lock */ struct mount_kattr { unsigned int attr_set; @@ -106,17 +108,6 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); -static int mnt_ns_cmp(u64 seq, const struct mnt_namespace *ns) -{ - u64 seq_b = ns->seq; - - if (seq < seq_b) - return -1; - if (seq > seq_b) - return 1; - return 0; -} - static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) { if (!node) @@ -124,25 +115,52 @@ static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) return rb_entry(node, struct mnt_namespace, mnt_ns_tree_node); } -static bool mnt_ns_less(struct rb_node *a, const struct rb_node *b) +static int mnt_ns_cmp(struct rb_node *a, const struct rb_node *b) { struct mnt_namespace *ns_a = node_to_mnt_ns(a); struct mnt_namespace *ns_b = node_to_mnt_ns(b); u64 seq_a = ns_a->seq; + u64 seq_b = ns_b->seq; - return mnt_ns_cmp(seq_a, ns_b) < 0; + if (seq_a < seq_b) + return -1; + if (seq_a > seq_b) + return 1; + return 0; +} + +static inline void mnt_ns_tree_write_lock(void) +{ + write_seqlock(&mnt_ns_tree_lock); +} + +static inline void mnt_ns_tree_write_unlock(void) +{ + write_sequnlock(&mnt_ns_tree_lock); } static void mnt_ns_tree_add(struct mnt_namespace *ns) { - guard(write_lock)(&mnt_ns_tree_lock); - rb_add(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_less); + struct rb_node *node, *prev; + + mnt_ns_tree_write_lock(); + node = rb_find_add_rcu(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_cmp); + /* + * If there's no previous entry simply add it after the + * head and if there is add it after the previous entry. + */ + prev = rb_prev(&ns->mnt_ns_tree_node); + if (!prev) + list_add_rcu(&ns->mnt_ns_list, &mnt_ns_list); + else + list_add_rcu(&ns->mnt_ns_list, &node_to_mnt_ns(prev)->mnt_ns_list); + mnt_ns_tree_write_unlock(); + + WARN_ON_ONCE(node); } static void mnt_ns_release(struct mnt_namespace *ns) { - lockdep_assert_not_held(&mnt_ns_tree_lock); - /* keep alive for {list,stat}mount() */ if (refcount_dec_and_test(&ns->passive)) { put_user_ns(ns->user_ns); @@ -151,41 +169,34 @@ static void mnt_ns_release(struct mnt_namespace *ns) } DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) +static void mnt_ns_release_rcu(struct rcu_head *rcu) +{ + mnt_ns_release(container_of(rcu, struct mnt_namespace, mnt_ns_rcu)); +} + static void mnt_ns_tree_remove(struct mnt_namespace *ns) { /* remove from global mount namespace list */ if (!is_anon_ns(ns)) { - guard(write_lock)(&mnt_ns_tree_lock); + mnt_ns_tree_write_lock(); rb_erase(&ns->mnt_ns_tree_node, &mnt_ns_tree); + list_bidir_del_rcu(&ns->mnt_ns_list); + mnt_ns_tree_write_unlock(); } - mnt_ns_release(ns); + call_rcu(&ns->mnt_ns_rcu, mnt_ns_release_rcu); } -/* - * Returns the mount namespace which either has the specified id, or has the - * next smallest id afer the specified one. - */ -static struct mnt_namespace *mnt_ns_find_id_at(u64 mnt_ns_id) +static int mnt_ns_find(const void *key, const struct rb_node *node) { - struct rb_node *node = mnt_ns_tree.rb_node; - struct mnt_namespace *ret = NULL; - - lockdep_assert_held(&mnt_ns_tree_lock); + const u64 mnt_ns_id = *(u64 *)key; + const struct mnt_namespace *ns = node_to_mnt_ns(node); - while (node) { - struct mnt_namespace *n = node_to_mnt_ns(node); - - if (mnt_ns_id <= n->seq) { - ret = node_to_mnt_ns(node); - if (mnt_ns_id == n->seq) - break; - node = node->rb_left; - } else { - node = node->rb_right; - } - } - return ret; + if (mnt_ns_id < ns->seq) + return -1; + if (mnt_ns_id > ns->seq) + return 1; + return 0; } /* @@ -195,18 +206,37 @@ static struct mnt_namespace *mnt_ns_find_id_at(u64 mnt_ns_id) * namespace the @namespace_sem must first be acquired. If the namespace has * already shut down before acquiring @namespace_sem, {list,stat}mount() will * see that the mount rbtree of the namespace is empty. + * + * Note the lookup is lockless protected by a sequence counter. We only + * need to guard against false negatives as false positives aren't + * possible. So if we didn't find a mount namespace and the sequence + * counter has changed we need to retry. If the sequence counter is + * still the same we know the search actually failed. */ static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id) { - struct mnt_namespace *ns; + struct mnt_namespace *ns; + struct rb_node *node; + unsigned int seq; - guard(read_lock)(&mnt_ns_tree_lock); - ns = mnt_ns_find_id_at(mnt_ns_id); - if (!ns || ns->seq != mnt_ns_id) - return NULL; + guard(rcu)(); + do { + seq = read_seqbegin(&mnt_ns_tree_lock); + node = rb_find_rcu(&mnt_ns_id, &mnt_ns_tree, mnt_ns_find); + if (node) + break; + } while (read_seqretry(&mnt_ns_tree_lock, seq)); - refcount_inc(&ns->passive); - return ns; + if (!node) + return NULL; + + /* + * The last reference count is put with RCU delay so we can + * unconditonally acquire a reference here. + */ + ns = node_to_mnt_ns(node); + refcount_inc(&ns->passive); + return ns; } static inline void lock_mount_hash(void) @@ -236,18 +266,19 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry) static int mnt_alloc_id(struct mount *mnt) { - int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); + int res; - if (res < 0) - return res; - mnt->mnt_id = res; - mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); - return 0; + xa_lock(&mnt_id_xa); + res = __xa_alloc(&mnt_id_xa, &mnt->mnt_id, mnt, XA_LIMIT(1, INT_MAX), GFP_KERNEL); + if (!res) + mnt->mnt_id_unique = ++mnt_id_ctr; + xa_unlock(&mnt_id_xa); + return res; } static void mnt_free_id(struct mount *mnt) { - ida_free(&mnt_id_ida, mnt->mnt_id); + xa_erase(&mnt_id_xa, mnt->mnt_id); } /* @@ -344,6 +375,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + RB_CLEAR_NODE(&mnt->mnt_node); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; @@ -1123,19 +1155,27 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) { struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; + bool mnt_first_node = true, mnt_last_node = true; - WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); + WARN_ON(mnt_ns_attached(mnt)); mnt->mnt_ns = ns; while (*link) { parent = *link; - if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) + if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) { link = &parent->rb_left; - else + mnt_last_node = false; + } else { link = &parent->rb_right; + mnt_first_node = false; + } } + + if (mnt_last_node) + ns->mnt_last_node = &mnt->mnt_node; + if (mnt_first_node) + ns->mnt_first_node = &mnt->mnt_node; rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); - mnt->mnt.mnt_flags |= MNT_ONRB; } /* @@ -1305,7 +1345,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags; - mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); + mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); @@ -1763,7 +1803,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; - if (p->mnt.mnt_flags & MNT_ONRB) + if (mnt_ns_attached(p)) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); @@ -1912,16 +1952,14 @@ static int do_umount(struct mount *mnt, int flags) event++; if (flags & MNT_DETACH) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } @@ -2055,9 +2093,15 @@ SYSCALL_DEFINE1(oldumount, char __user *, name) static bool is_mnt_ns_file(struct dentry *dentry) { + struct ns_common *ns; + /* Is this a proxy for a mount namespace? */ - return dentry->d_op == &ns_dentry_operations && - dentry->d_fsdata == &mntns_operations; + if (dentry->d_op != &ns_dentry_operations) + return false; + + ns = d_inode(dentry)->i_private; + + return ns->ops == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) @@ -2065,30 +2109,34 @@ struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) return &mnt->ns; } -struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool previous) +struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool previous) { - guard(read_lock)(&mnt_ns_tree_lock); + guard(rcu)(); + for (;;) { - struct rb_node *node; + struct list_head *list; if (previous) - node = rb_prev(&mntns->mnt_ns_tree_node); + list = rcu_dereference(list_bidir_prev_rcu(&mntns->mnt_ns_list)); else - node = rb_next(&mntns->mnt_ns_tree_node); - if (!node) + list = rcu_dereference(list_next_rcu(&mntns->mnt_ns_list)); + if (list_is_head(list, &mnt_ns_list)) return ERR_PTR(-ENOENT); - mntns = node_to_mnt_ns(node); - node = &mntns->mnt_ns_tree_node; + mntns = list_entry_rcu(list, struct mnt_namespace, mnt_ns_list); + /* + * The last passive reference count is put with RCU + * delay so accessing the mount namespace is not just + * safe but all relevant members are still valid. + */ if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN)) continue; /* - * Holding mnt_ns_tree_lock prevents the mount namespace from - * being freed but it may well be on it's deathbed. We want an - * active reference, not just a passive one here as we're - * persisting the mount namespace. + * We need an active reference count as we're persisting + * the mount namespace and it might already be on its + * deathbed. */ if (!refcount_inc_not_zero(&mntns->ns.count)) continue; @@ -2732,8 +2780,13 @@ static struct mount *__do_loopback(struct path *old_path, int recurse) if (IS_MNT_UNBINDABLE(old)) return mnt; - if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) - return mnt; + if (!check_mnt(old)) { + const struct dentry_operations *d_op = old_path->dentry->d_op; + + if (d_op != &ns_dentry_operations && + d_op != &pidfs_dentry_operations) + return mnt; + } if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; @@ -3835,7 +3888,7 @@ int path_mount(const char *dev_name, struct path *path, data_page); } -long do_mount(const char *dev_name, const char __user *dir_name, +int do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; @@ -3905,6 +3958,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a refcount_set(&new_ns->ns.count, 1); refcount_set(&new_ns->passive, 1); new_ns->mounts = RB_ROOT; + INIT_LIST_HEAD(&new_ns->mnt_ns_list); RB_CLEAR_NODE(&new_ns->mnt_ns_tree_node); init_waitqueue_head(&new_ns->poll); new_ns->user_ns = get_user_ns(user_ns); @@ -3984,7 +4038,6 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(skip_mnt_tree(p), old); } - mnt_ns_tree_add(new_ns); namespace_unlock(); if (rootmnt) @@ -3992,6 +4045,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, if (pwdmnt) mntput(pwdmnt); + mnt_ns_tree_add(new_ns); return new_ns; } @@ -5038,6 +5092,10 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) if (sb->s_op->show_options) { size_t start = seq->count; + err = security_sb_show_options(seq, sb); + if (err) + return err; + err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; @@ -5525,9 +5583,9 @@ static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id, if (!last_mnt_id) { if (reverse) - first = node_to_mount(rb_last(&ns->mounts)); + first = node_to_mount(ns->mnt_last_node); else - first = node_to_mount(rb_first(&ns->mounts)); + first = node_to_mount(ns->mnt_first_node); } else { if (reverse) first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index d08b0bfb6756..b43188d64bd8 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -13,8 +13,11 @@ netfs-y := \ read_collect.o \ read_pgpriv2.o \ read_retry.o \ + read_single.o \ + rolling_buffer.o \ write_collect.o \ - write_issue.o + write_issue.o \ + write_retry.o netfs-$(CONFIG_NETFS_STATS) += stats.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7ac34550c403..f761d44b3436 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -64,37 +64,6 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in } /* - * Decant the list of folios to read into a rolling buffer. - */ -static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq, - struct folio_queue *folioq, - struct folio_batch *put_batch) -{ - unsigned int order, nr; - size_t size = 0; - - nr = __readahead_batch(rreq->ractl, (struct page **)folioq->vec.folios, - ARRAY_SIZE(folioq->vec.folios)); - folioq->vec.nr = nr; - for (int i = 0; i < nr; i++) { - struct folio *folio = folioq_folio(folioq, i); - - trace_netfs_folio(folio, netfs_folio_trace_read); - order = folio_order(folio); - folioq->orders[i] = order; - size += PAGE_SIZE << order; - - if (!folio_batch_add(put_batch, folio)) - folio_batch_release(put_batch); - } - - for (int i = nr; i < folioq_nr_slots(folioq); i++) - folioq_clear(folioq, i); - - return size; -} - -/* * netfs_prepare_read_iterator - Prepare the subreq iterator for I/O * @subreq: The subrequest to be set up * @@ -128,19 +97,12 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) folio_batch_init(&put_batch); while (rreq->submitted < subreq->start + rsize) { - struct folio_queue *tail = rreq->buffer_tail, *new; - size_t added; - - new = kmalloc(sizeof(*new), GFP_NOFS); - if (!new) - return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(new); - new->prev = tail; - tail->next = new; - rreq->buffer_tail = new; - added = netfs_load_buffer_from_ra(rreq, new, &put_batch); - rreq->iter.count += added; + ssize_t added; + + added = rolling_buffer_load_from_ra(&rreq->buffer, rreq->ractl, + &put_batch); + if (added < 0) + return added; rreq->submitted += added; } folio_batch_release(&put_batch); @@ -148,7 +110,7 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { - size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, rreq->io_streams[0].sreq_max_segs); if (limit < rsize) { @@ -157,20 +119,10 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) } } - subreq->io_iter = rreq->iter; - - if (iov_iter_is_folioq(&subreq->io_iter)) { - if (subreq->io_iter.folioq_slot >= folioq_nr_slots(subreq->io_iter.folioq)) { - subreq->io_iter.folioq = subreq->io_iter.folioq->next; - subreq->io_iter.folioq_slot = 0; - } - subreq->curr_folioq = (struct folio_queue *)subreq->io_iter.folioq; - subreq->curr_folioq_slot = subreq->io_iter.folioq_slot; - subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; - } + subreq->io_iter = rreq->buffer.iter; iov_iter_truncate(&subreq->io_iter, subreq->len); - iov_iter_advance(&rreq->iter, subreq->len); + rolling_buffer_advance(&rreq->buffer, subreq->len); return subreq->len; } @@ -179,25 +131,14 @@ static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_request *rr loff_t i_size) { struct netfs_cache_resources *cres = &rreq->cache_resources; + enum netfs_io_source source; if (!cres->ops) return NETFS_DOWNLOAD_FROM_SERVER; - return cres->ops->prepare_read(subreq, i_size); -} - -static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_subrequest *subreq = priv; - - if (transferred_or_error < 0) { - netfs_read_subreq_terminated(subreq, transferred_or_error, was_async); - return; - } + source = cres->ops->prepare_read(subreq, i_size); + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + return source; - if (transferred_or_error > 0) - subreq->transferred += transferred_or_error; - netfs_read_subreq_terminated(subreq, 0, was_async); } /* @@ -214,6 +155,47 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } +static void netfs_issue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_io_stream *stream = &rreq->io_streams[0]; + + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + + /* We add to the end of the list whilst the collector may be walking + * the list. The collector only goes nextwards and uses the lock to + * remove entries off of the front. + */ + spin_lock(&rreq->lock); + list_add_tail(&subreq->rreq_link, &stream->subrequests); + if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { + stream->front = subreq; + if (!stream->active) { + stream->collected_to = stream->front->start; + /* Store list pointers before active flag */ + smp_store_release(&stream->active, true); + } + } + + spin_unlock(&rreq->lock); + + switch (subreq->source) { + case NETFS_DOWNLOAD_FROM_SERVER: + rreq->netfs_ops->issue_read(subreq); + break; + case NETFS_READ_FROM_CACHE: + netfs_read_cache_to_pagecache(rreq, subreq); + break; + default: + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + subreq->error = 0; + iov_iter_zero(subreq->len, &subreq->io_iter); + subreq->transferred = subreq->len; + netfs_read_subreq_terminated(subreq); + break; + } +} + /* * Perform a read to the pagecache from a series of sources of different types, * slicing up the region to be read according to available cache blocks and @@ -226,11 +208,9 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) ssize_t size = rreq->len; int ret = 0; - atomic_inc(&rreq->nr_outstanding); - do { struct netfs_io_subrequest *subreq; - enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER; + enum netfs_io_source source = NETFS_SOURCE_UNKNOWN; ssize_t slice; subreq = netfs_alloc_subrequest(rreq); @@ -242,20 +222,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) subreq->start = start; subreq->len = size; - atomic_inc(&rreq->nr_outstanding); - spin_lock_bh(&rreq->lock); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - subreq->prev_donated = rreq->prev_donated; - rreq->prev_donated = 0; - trace_netfs_sreq(subreq, netfs_sreq_trace_added); - spin_unlock_bh(&rreq->lock); - source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); subreq->source = source; if (source == NETFS_DOWNLOAD_FROM_SERVER) { unsigned long long zp = umin(ictx->zero_point, rreq->i_size); size_t len = subreq->len; + if (unlikely(rreq->origin == NETFS_READ_SINGLE)) + zp = rreq->i_size; if (subreq->start >= zp) { subreq->source = source = NETFS_FILL_WITH_ZEROES; goto fill_with_zeroes; @@ -276,24 +250,17 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); + subreq->error = ret; + /* Not queued - release both refs. */ + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_cancel); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); break; } trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); } - - slice = netfs_prepare_read_iterator(subreq); - if (slice < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); - ret = slice; - break; - } - - rreq->netfs_ops->issue_read(subreq); - goto done; + goto issue; } fill_with_zeroes: @@ -301,82 +268,50 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) subreq->source = NETFS_FILL_WITH_ZEROES; trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_stat(&netfs_n_rh_zero); - slice = netfs_prepare_read_iterator(subreq); - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_read_subreq_terminated(subreq, 0, false); - goto done; + goto issue; } if (source == NETFS_READ_FROM_CACHE) { trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - slice = netfs_prepare_read_iterator(subreq); - netfs_read_cache_to_pagecache(rreq, subreq); - goto done; + goto issue; } pr_err("Unexpected read source %u\n", source); WARN_ON_ONCE(1); break; - done: + issue: + slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) { + ret = slice; + subreq->error = ret; + trace_netfs_sreq(subreq, netfs_sreq_trace_cancel); + /* Not queued - release both refs. */ + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + } size -= slice; start += slice; + if (size <= 0) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + + netfs_issue_read(rreq, subreq); cond_resched(); } while (size > 0); - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, false); + if (unlikely(size > 0)) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + netfs_wake_read_collector(rreq); + } /* Defer error return as we may need to wait for outstanding I/O. */ cmpxchg(&rreq->error, 0, ret); } -/* - * Wait for the read operation to complete, successfully or otherwise. - */ -static int netfs_wait_for_read(struct netfs_io_request *rreq) -{ - int ret; - - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); - wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; - } - - return ret; -} - -/* - * Set up the initial folioq of buffer folios in the rolling buffer and set the - * iterator to refer to it. - */ -static int netfs_prime_buffer(struct netfs_io_request *rreq) -{ - struct folio_queue *folioq; - struct folio_batch put_batch; - size_t added; - - folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); - if (!folioq) - return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(folioq); - rreq->buffer = folioq; - rreq->buffer_tail = folioq; - rreq->submitted = rreq->start; - iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0); - - folio_batch_init(&put_batch); - added = netfs_load_buffer_from_ra(rreq, folioq, &put_batch); - folio_batch_release(&put_batch); - rreq->iter.count += added; - rreq->submitted += added; - return 0; -} - /** * netfs_readahead - Helper to manage a read request * @ractl: The description of the readahead request @@ -405,6 +340,8 @@ void netfs_readahead(struct readahead_control *ractl) if (IS_ERR(rreq)) return; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags); + ret = netfs_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; @@ -416,7 +353,8 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); rreq->ractl = ractl; - if (netfs_prime_buffer(rreq) < 0) + rreq->submitted = rreq->start; + if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0) goto cleanup_free; netfs_read_to_pagecache(rreq); @@ -432,23 +370,18 @@ EXPORT_SYMBOL(netfs_readahead); /* * Create a rolling buffer with a single occupying folio. */ -static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio) +static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio, + unsigned int rollbuf_flags) { - struct folio_queue *folioq; + ssize_t added; - folioq = kmalloc(sizeof(*folioq), GFP_KERNEL); - if (!folioq) + if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0) return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(folioq); - folioq_append(folioq, folio); - BUG_ON(folioq_folio(folioq, 0) != folio); - BUG_ON(folioq_folio_order(folioq, 0) != folio_order(folio)); - rreq->buffer = folioq; - rreq->buffer_tail = folioq; - rreq->submitted = rreq->start + rreq->len; - iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, rreq->len); + added = rolling_buffer_append(&rreq->buffer, folio, rollbuf_flags); + if (added < 0) + return added; + rreq->submitted = rreq->start + added; rreq->ractl = (struct readahead_control *)1UL; return 0; } @@ -516,7 +449,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) } if (to < flen) bvec_set_folio(&bvec[i++], folio, flen - to, to); - iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len); + iov_iter_bvec(&rreq->buffer.iter, ITER_DEST, bvec, i, rreq->len); rreq->submitted = rreq->start + flen; netfs_read_to_pagecache(rreq); @@ -525,7 +458,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) folio_put(sink); ret = netfs_wait_for_read(rreq); - if (ret == 0) { + if (ret >= 0) { flush_dcache_folio(folio); folio_mark_uptodate(folio); } @@ -584,7 +517,7 @@ int netfs_read_folio(struct file *file, struct folio *folio) trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); /* Set up the output buffer */ - ret = netfs_create_singular_buffer(rreq, folio); + ret = netfs_create_singular_buffer(rreq, folio, 0); if (ret < 0) goto discard; @@ -741,7 +674,7 @@ retry: trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); /* Set up the output buffer */ - ret = netfs_create_singular_buffer(rreq, folio); + ret = netfs_create_singular_buffer(rreq, folio, 0); if (ret < 0) goto error_put; @@ -806,15 +739,14 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write); /* Set up the output buffer */ - ret = netfs_create_singular_buffer(rreq, folio); + ret = netfs_create_singular_buffer(rreq, folio, NETFS_ROLLBUF_PAGECACHE_MARK); if (ret < 0) goto error_put; - folioq_mark2(rreq->buffer, 0); netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, false, netfs_rreq_trace_put_return); - return ret; + return ret < 0 ? ret : 0; error_put: netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index b1a66a6e6bc2..0bf3c2f5a710 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -25,7 +25,7 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { - size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize, + size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, rreq->io_streams[0].sreq_max_segs); if (limit < rsize) { @@ -36,9 +36,9 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - subreq->io_iter = rreq->iter; + subreq->io_iter = rreq->buffer.iter; iov_iter_truncate(&subreq->io_iter, subreq->len); - iov_iter_advance(&rreq->iter, subreq->len); + iov_iter_advance(&rreq->buffer.iter, subreq->len); } /* @@ -47,12 +47,11 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) */ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) { + struct netfs_io_stream *stream = &rreq->io_streams[0]; unsigned long long start = rreq->start; ssize_t size = rreq->len; int ret = 0; - atomic_set(&rreq->nr_outstanding, 1); - do { struct netfs_io_subrequest *subreq; ssize_t slice; @@ -67,19 +66,25 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) subreq->start = start; subreq->len = size; - atomic_inc(&rreq->nr_outstanding); - spin_lock_bh(&rreq->lock); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - subreq->prev_donated = rreq->prev_donated; - rreq->prev_donated = 0; + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + + spin_lock(&rreq->lock); + list_add_tail(&subreq->rreq_link, &stream->subrequests); + if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { + stream->front = subreq; + if (!stream->active) { + stream->collected_to = stream->front->start; + /* Store list pointers before active flag */ + smp_store_release(&stream->active, true); + } + } trace_netfs_sreq(subreq, netfs_sreq_trace_added); - spin_unlock_bh(&rreq->lock); + spin_unlock(&rreq->lock); netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); break; } @@ -87,20 +92,32 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) netfs_prepare_dio_read_iterator(subreq); slice = subreq->len; - rreq->netfs_ops->issue_read(subreq); - size -= slice; start += slice; rreq->submitted += slice; + if (size <= 0) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + + rreq->netfs_ops->issue_read(subreq); + if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + netfs_wait_for_pause(rreq); + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) + break; if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) break; cond_resched(); } while (size > 0); - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, false); + if (unlikely(size > 0)) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + netfs_wake_read_collector(rreq); + } + return ret; } @@ -133,21 +150,10 @@ static int netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) goto out; } - if (sync) { - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); - wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len && - rreq->origin != NETFS_DIO_READ) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; - } - } else { + if (sync) + ret = netfs_wait_for_read(rreq); + else ret = -EIOCBQUEUED; - } - out: _leave(" = %d", ret); return ret; @@ -199,15 +205,15 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i * the request. */ if (user_backed_iter(iter)) { - ret = netfs_extract_user_iter(iter, rreq->len, &rreq->iter, 0); + ret = netfs_extract_user_iter(iter, rreq->len, &rreq->buffer.iter, 0); if (ret < 0) goto out; - rreq->direct_bv = (struct bio_vec *)rreq->iter.bvec; + rreq->direct_bv = (struct bio_vec *)rreq->buffer.iter.bvec; rreq->direct_bv_count = ret; rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); - rreq->len = iov_iter_count(&rreq->iter); + rreq->len = iov_iter_count(&rreq->buffer.iter); } else { - rreq->iter = *iter; + rreq->buffer.iter = *iter; rreq->len = orig_count; rreq->direct_bv_unpin = false; iov_iter_advance(iter, orig_count); @@ -215,8 +221,10 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i // TODO: Set up bounce buffer if needed - if (!sync) + if (!sync) { rreq->iocb = iocb; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags); + } ret = netfs_unbuffered_read(rreq, sync); if (ret < 0) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 88f2adfab75e..42ce53cc216e 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -67,20 +67,23 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * * allocate a sufficiently large bvec array and may shorten the * request. */ - if (async || user_backed_iter(iter)) { - n = netfs_extract_user_iter(iter, len, &wreq->iter, 0); + if (user_backed_iter(iter)) { + n = netfs_extract_user_iter(iter, len, &wreq->buffer.iter, 0); if (n < 0) { ret = n; goto out; } - wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec; + wreq->direct_bv = (struct bio_vec *)wreq->buffer.iter.bvec; wreq->direct_bv_count = n; wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); } else { - wreq->iter = *iter; + /* If this is a kernel-generated async DIO request, + * assume that any resources the iterator points to + * (eg. a bio_vec array) will persist till the end of + * the op. + */ + wreq->buffer.iter = *iter; } - - wreq->io_iter = wreq->iter; } __set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags); @@ -92,7 +95,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); if (async) wreq->iocb = iocb; - wreq->len = iov_iter_count(&wreq->io_iter); + wreq->len = iov_iter_count(&wreq->buffer.iter); wreq->cleanup = netfs_cleanup_dio_write; ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len); if (ret < 0) { @@ -104,7 +107,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - smp_rmb(); /* Read error/transferred after RIP flag */ ret = wreq->error; if (ret == 0) { ret = wreq->transferred; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index c562aec3b483..eb76f98c894b 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -23,6 +23,7 @@ /* * buffered_read.c */ +void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); @@ -58,11 +59,8 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} /* * misc.c */ -struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq); -int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, - bool needs_put); -struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq); -void netfs_clear_buffer(struct netfs_io_request *rreq); +struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq, + enum netfs_folioq_trace trace); void netfs_reset_iter(struct netfs_io_subrequest *subreq); /* @@ -84,20 +82,27 @@ static inline void netfs_see_request(struct netfs_io_request *rreq, trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what); } +static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what) +{ + trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), what); +} + /* * read_collect.c */ -void netfs_read_termination_worker(struct work_struct *work); -void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async); +void netfs_read_collection_worker(struct work_struct *work); +void netfs_wake_read_collector(struct netfs_io_request *rreq); +void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async); +ssize_t netfs_wait_for_read(struct netfs_io_request *rreq); +void netfs_wait_for_pause(struct netfs_io_request *rreq); /* * read_pgpriv2.c */ -void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, - struct netfs_io_request *rreq, - struct folio_queue *folioq, - int slot); -void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq); +void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio); +void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq); bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq); /* @@ -113,6 +118,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq); extern atomic_t netfs_n_rh_dio_read; extern atomic_t netfs_n_rh_readahead; extern atomic_t netfs_n_rh_read_folio; +extern atomic_t netfs_n_rh_read_single; extern atomic_t netfs_n_rh_rreq; extern atomic_t netfs_n_rh_sreq; extern atomic_t netfs_n_rh_download; @@ -181,9 +187,9 @@ void netfs_reissue_write(struct netfs_io_stream *stream, struct iov_iter *source); void netfs_issue_write(struct netfs_io_request *wreq, struct netfs_io_stream *stream); -int netfs_advance_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start, size_t len, bool to_eof); +size_t netfs_advance_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start, size_t len, bool to_eof); struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len); int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc, struct folio *folio, size_t copied, bool to_page_end, @@ -193,6 +199,11 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len); /* + * write_retry.c + */ +void netfs_retry_writes(struct netfs_io_request *wreq); + +/* * Miscellaneous functions. */ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx) diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 6c7be1377ee0..4e3e62040831 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -37,9 +37,11 @@ static const char *netfs_origins[nr__netfs_io_origin] = { [NETFS_READAHEAD] = "RA", [NETFS_READPAGE] = "RP", [NETFS_READ_GAPS] = "RG", + [NETFS_READ_SINGLE] = "R1", [NETFS_READ_FOR_WRITE] = "RW", [NETFS_DIO_READ] = "DR", [NETFS_WRITEBACK] = "WB", + [NETFS_WRITEBACK_SINGLE] = "W1", [NETFS_WRITETHROUGH] = "WT", [NETFS_UNBUFFERED_WRITE] = "UW", [NETFS_DIO_WRITE] = "DW", @@ -69,7 +71,7 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v) refcount_read(&rreq->ref), rreq->flags, rreq->error, - atomic_read(&rreq->nr_outstanding), + 0, rreq->start, rreq->submitted, rreq->len); seq_putc(m, '\n'); return 0; @@ -116,7 +118,7 @@ static int __init netfs_init(void) goto error_reqpool; netfs_subrequest_slab = kmem_cache_create("netfs_subrequest", - sizeof(struct netfs_io_subrequest), 0, + sizeof(struct netfs_io_subrequest) + 16, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!netfs_subrequest_slab) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 78fe5796b2b2..7099aa07737a 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -8,113 +8,101 @@ #include <linux/swap.h> #include "internal.h" -/* - * Make sure there's space in the rolling queue. +/** + * netfs_alloc_folioq_buffer - Allocate buffer space into a folio queue + * @mapping: Address space to set on the folio (or NULL). + * @_buffer: Pointer to the folio queue to add to (may point to a NULL; updated). + * @_cur_size: Current size of the buffer (updated). + * @size: Target size of the buffer. + * @gfp: The allocation constraints. */ -struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq) +int netfs_alloc_folioq_buffer(struct address_space *mapping, + struct folio_queue **_buffer, + size_t *_cur_size, ssize_t size, gfp_t gfp) { - struct folio_queue *tail = rreq->buffer_tail, *prev; - unsigned int prev_nr_slots = 0; - - if (WARN_ON_ONCE(!rreq->buffer && tail) || - WARN_ON_ONCE(rreq->buffer && !tail)) - return ERR_PTR(-EIO); - - prev = tail; - if (prev) { - if (!folioq_full(tail)) - return tail; - prev_nr_slots = folioq_nr_slots(tail); - } - - tail = kmalloc(sizeof(*tail), GFP_NOFS); - if (!tail) - return ERR_PTR(-ENOMEM); - netfs_stat(&netfs_n_folioq); - folioq_init(tail); - tail->prev = prev; - if (prev) - /* [!] NOTE: After we set prev->next, the consumer is entirely - * at liberty to delete prev. - */ - WRITE_ONCE(prev->next, tail); - - rreq->buffer_tail = tail; - if (!rreq->buffer) { - rreq->buffer = tail; - iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); - } else { - /* Make sure we don't leave the master iterator pointing to a - * block that might get immediately consumed. - */ - if (rreq->io_iter.folioq == prev && - rreq->io_iter.folioq_slot == prev_nr_slots) { - rreq->io_iter.folioq = tail; - rreq->io_iter.folioq_slot = 0; + struct folio_queue *tail = *_buffer, *p; + + size = round_up(size, PAGE_SIZE); + if (*_cur_size >= size) + return 0; + + if (tail) + while (tail->next) + tail = tail->next; + + do { + struct folio *folio; + int order = 0, slot; + + if (!tail || folioq_full(tail)) { + p = netfs_folioq_alloc(0, GFP_NOFS, netfs_trace_folioq_alloc_buffer); + if (!p) + return -ENOMEM; + if (tail) { + tail->next = p; + p->prev = tail; + } else { + *_buffer = p; + } + tail = p; } - } - rreq->buffer_tail_slot = 0; - return tail; -} -/* - * Append a folio to the rolling queue. - */ -int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, - bool needs_put) -{ - struct folio_queue *tail; - unsigned int slot, order = folio_order(folio); + if (size - *_cur_size > PAGE_SIZE) + order = umin(ilog2(size - *_cur_size) - PAGE_SHIFT, + MAX_PAGECACHE_ORDER); - tail = netfs_buffer_make_space(rreq); - if (IS_ERR(tail)) - return PTR_ERR(tail); + folio = folio_alloc(gfp, order); + if (!folio && order > 0) + folio = folio_alloc(gfp, 0); + if (!folio) + return -ENOMEM; - rreq->io_iter.count += PAGE_SIZE << order; + folio->mapping = mapping; + folio->index = *_cur_size / PAGE_SIZE; + trace_netfs_folio(folio, netfs_folio_trace_alloc_buffer); + slot = folioq_append_mark(tail, folio); + *_cur_size += folioq_folio_size(tail, slot); + } while (*_cur_size < size); - slot = folioq_append(tail, folio); - /* Store the counter after setting the slot. */ - smp_store_release(&rreq->buffer_tail_slot, slot); return 0; } +EXPORT_SYMBOL(netfs_alloc_folioq_buffer); -/* - * Delete the head of a rolling queue. +/** + * netfs_free_folioq_buffer - Free a folio queue. + * @fq: The start of the folio queue to free + * + * Free up a chain of folio_queues and, if marked, the marked folios they point + * to. */ -struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq) +void netfs_free_folioq_buffer(struct folio_queue *fq) { - struct folio_queue *head = wreq->buffer, *next = head->next; - - if (next) - next->prev = NULL; - netfs_stat_d(&netfs_n_folioq); - kfree(head); - wreq->buffer = next; - return next; -} + struct folio_queue *next; + struct folio_batch fbatch; -/* - * Clear out a rolling queue. - */ -void netfs_clear_buffer(struct netfs_io_request *rreq) -{ - struct folio_queue *p; + folio_batch_init(&fbatch); + + for (; fq; fq = next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + struct folio *folio = folioq_folio(fq, slot); - while ((p = rreq->buffer)) { - rreq->buffer = p->next; - for (int slot = 0; slot < folioq_count(p); slot++) { - struct folio *folio = folioq_folio(p, slot); - if (!folio) + if (!folio || + !folioq_is_marked(fq, slot)) continue; - if (folioq_is_marked(p, slot)) { - trace_netfs_folio(folio, netfs_folio_trace_put); - folio_put(folio); - } + + trace_netfs_folio(folio, netfs_folio_trace_put); + if (folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); } + netfs_stat_d(&netfs_n_folioq); - kfree(p); + next = fq->next; + kfree(fq); } + + folio_batch_release(&fbatch); } +EXPORT_SYMBOL(netfs_free_folioq_buffer); /* * Reset the subrequest iterator to refer just to the region remaining to be diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 31e388ec6e48..dc6b41ef18b0 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -48,17 +48,20 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, spin_lock_init(&rreq->lock); INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); - INIT_LIST_HEAD(&rreq->subrequests); + init_waitqueue_head(&rreq->waitq); refcount_set(&rreq->ref, 1); if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || origin == NETFS_READ_GAPS || + origin == NETFS_READ_SINGLE || origin == NETFS_READ_FOR_WRITE || - origin == NETFS_DIO_READ) - INIT_WORK(&rreq->work, netfs_read_termination_worker); - else + origin == NETFS_DIO_READ) { + INIT_WORK(&rreq->work, netfs_read_collection_worker); + rreq->io_streams[0].avail = true; + } else { INIT_WORK(&rreq->work, netfs_write_collection_worker); + } __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); if (file && file->f_flags & O_NONBLOCK) @@ -92,14 +95,6 @@ void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async) struct netfs_io_stream *stream; int s; - while (!list_empty(&rreq->subrequests)) { - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, was_async, - netfs_sreq_trace_put_clear); - } - for (s = 0; s < ARRAY_SIZE(rreq->io_streams); s++) { stream = &rreq->io_streams[s]; while (!list_empty(&stream->subrequests)) { @@ -143,7 +138,7 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } - netfs_clear_buffer(rreq); + rolling_buffer_clear(&rreq->buffer); if (atomic_dec_and_test(&ictx->io_count)) wake_up_var(&ictx->io_count); diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3cbb289535a8..f65affa5a9e4 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -14,6 +14,14 @@ #include <linux/task_io_accounting_ops.h> #include "internal.h" +/* Notes made in the collector */ +#define HIT_PENDING 0x01 /* A front op was still pending */ +#define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ +#define BUFFERED 0x08 /* The pagecache needs cleaning up */ +#define NEED_RETRY 0x10 /* A front op requests retrying */ +#define COPY_TO_CACHE 0x40 /* Need to copy subrequest to cache */ +#define ABANDON_SREQ 0x80 /* Need to abandon untransferred part of subrequest */ + /* * Clear the unread part of an I/O request. */ @@ -31,14 +39,18 @@ static void netfs_clear_unread(struct netfs_io_subrequest *subreq) * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it * dirty and let writeback handle it. */ -static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, - struct netfs_io_request *rreq, +static void netfs_unlock_read_folio(struct netfs_io_request *rreq, struct folio_queue *folioq, int slot) { struct netfs_folio *finfo; struct folio *folio = folioq_folio(folioq, slot); + if (unlikely(folio_pos(folio) < rreq->abandon_to)) { + trace_netfs_folio(folio, netfs_folio_trace_abandon); + goto just_unlock; + } + flush_dcache_folio(folio); folio_mark_uptodate(folio); @@ -53,7 +65,7 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, kfree(finfo); } - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) { if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); @@ -62,12 +74,15 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } else { trace_netfs_folio(folio, netfs_folio_trace_read_done); } + + folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) - netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) + netfs_pgpriv2_copy_to_cache(rreq, folio); } +just_unlock: if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { if (folio->index == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { @@ -82,234 +97,244 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } /* - * Unlock any folios that are now completely read. Returns true if the - * subrequest is removed from the list. + * Unlock any folios we've finished with. */ -static bool netfs_consume_read_data(struct netfs_io_subrequest *subreq, bool was_async) +static void netfs_read_unlock_folios(struct netfs_io_request *rreq, + unsigned int *notes) { - struct netfs_io_subrequest *prev, *next; - struct netfs_io_request *rreq = subreq->rreq; - struct folio_queue *folioq = subreq->curr_folioq; - size_t avail, prev_donated, next_donated, fsize, part, excess; - loff_t fpos, start; - loff_t fend; - int slot = subreq->curr_folioq_slot; - - if (WARN(subreq->transferred > subreq->len, - "Subreq overread: R%x[%x] %zu > %zu", - rreq->debug_id, subreq->debug_index, - subreq->transferred, subreq->len)) - subreq->transferred = subreq->len; - -next_folio: - fsize = PAGE_SIZE << subreq->curr_folio_order; - fpos = round_down(subreq->start + subreq->consumed, fsize); - fend = fpos + fsize; - - if (WARN_ON_ONCE(!folioq) || - WARN_ON_ONCE(!folioq_folio(folioq, slot)) || - WARN_ON_ONCE(folioq_folio(folioq, slot)->index != fpos / PAGE_SIZE)) { - pr_err("R=%08x[%x] s=%llx-%llx ctl=%zx/%zx/%zx sl=%u\n", - rreq->debug_id, subreq->debug_index, - subreq->start, subreq->start + subreq->transferred - 1, - subreq->consumed, subreq->transferred, subreq->len, - slot); - if (folioq) { - struct folio *folio = folioq_folio(folioq, slot); - - pr_err("folioq: orders=%02x%02x%02x%02x\n", - folioq->orders[0], folioq->orders[1], - folioq->orders[2], folioq->orders[3]); - if (folio) - pr_err("folio: %llx-%llx ix=%llx o=%u qo=%u\n", - fpos, fend - 1, folio_pos(folio), folio_order(folio), - folioq_folio_order(folioq, slot)); - } - } + struct folio_queue *folioq = rreq->buffer.tail; + unsigned long long collected_to = rreq->collected_to; + unsigned int slot = rreq->buffer.first_tail_slot; -donation_changed: - /* Try to consume the current folio if we've hit or passed the end of - * it. There's a possibility that this subreq doesn't start at the - * beginning of the folio, in which case we need to donate to/from the - * preceding subreq. - * - * We also need to include any potential donation back from the - * following subreq. - */ - prev_donated = READ_ONCE(subreq->prev_donated); - next_donated = READ_ONCE(subreq->next_donated); - if (prev_donated || next_donated) { - spin_lock_bh(&rreq->lock); - prev_donated = subreq->prev_donated; - next_donated = subreq->next_donated; - subreq->start -= prev_donated; - subreq->len += prev_donated; - subreq->transferred += prev_donated; - prev_donated = subreq->prev_donated = 0; - if (subreq->transferred == subreq->len) { - subreq->len += next_donated; - subreq->transferred += next_donated; - next_donated = subreq->next_donated = 0; + if (rreq->cleaned_to >= rreq->collected_to) + return; + + // TODO: Begin decryption + + if (slot >= folioq_nr_slots(folioq)) { + folioq = rolling_buffer_delete_spent(&rreq->buffer); + if (!folioq) { + rreq->front_folio_order = 0; + return; } - trace_netfs_sreq(subreq, netfs_sreq_trace_add_donations); - spin_unlock_bh(&rreq->lock); + slot = 0; } - avail = subreq->transferred; - if (avail == subreq->len) - avail += next_donated; - start = subreq->start; - if (subreq->consumed == 0) { - start -= prev_donated; - avail += prev_donated; - } else { - start += subreq->consumed; - avail -= subreq->consumed; - } - part = umin(avail, fsize); - - trace_netfs_progress(subreq, start, avail, part); - - if (start + avail >= fend) { - if (fpos == start) { - /* Flush, unlock and mark for caching any folio we've just read. */ - subreq->consumed = fend - subreq->start; - netfs_unlock_read_folio(subreq, rreq, folioq, slot); - folioq_mark2(folioq, slot); - if (subreq->consumed >= subreq->len) - goto remove_subreq; - } else if (fpos < start) { - excess = fend - subreq->start; - - spin_lock_bh(&rreq->lock); - /* If we complete first on a folio split with the - * preceding subreq, donate to that subreq - otherwise - * we get the responsibility. - */ - if (subreq->prev_donated != prev_donated) { - spin_unlock_bh(&rreq->lock); - goto donation_changed; - } + for (;;) { + struct folio *folio; + unsigned long long fpos, fend; + unsigned int order; + size_t fsize; - if (list_is_first(&subreq->rreq_link, &rreq->subrequests)) { - spin_unlock_bh(&rreq->lock); - pr_err("Can't donate prior to front\n"); - goto bad; - } + if (*notes & COPY_TO_CACHE) + set_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - prev = list_prev_entry(subreq, rreq_link); - WRITE_ONCE(prev->next_donated, prev->next_donated + excess); - subreq->start += excess; - subreq->len -= excess; - subreq->transferred -= excess; - trace_netfs_donate(rreq, subreq, prev, excess, - netfs_trace_donate_tail_to_prev); - trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); - - if (subreq->consumed >= subreq->len) - goto remove_subreq_locked; - spin_unlock_bh(&rreq->lock); - } else { - pr_err("fpos > start\n"); - goto bad; - } + folio = folioq_folio(folioq, slot); + if (WARN_ONCE(!folio_test_locked(folio), + "R=%08x: folio %lx is not locked\n", + rreq->debug_id, folio->index)) + trace_netfs_folio(folio, netfs_folio_trace_not_locked); + + order = folioq_folio_order(folioq, slot); + rreq->front_folio_order = order; + fsize = PAGE_SIZE << order; + fpos = folio_pos(folio); + fend = umin(fpos + fsize, rreq->i_size); + + trace_netfs_collect_folio(rreq, folio, fend, collected_to); - /* Advance the rolling buffer to the next folio. */ + /* Unlock any folio we've transferred all of. */ + if (collected_to < fend) + break; + + netfs_unlock_read_folio(rreq, folioq, slot); + WRITE_ONCE(rreq->cleaned_to, fpos + fsize); + *notes |= MADE_PROGRESS; + + clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); + + /* Clean up the head folioq. If we clear an entire folioq, then + * we can get rid of it provided it's not also the tail folioq + * being filled by the issuer. + */ + folioq_clear(folioq, slot); slot++; if (slot >= folioq_nr_slots(folioq)) { + folioq = rolling_buffer_delete_spent(&rreq->buffer); + if (!folioq) + goto done; slot = 0; - folioq = folioq->next; - subreq->curr_folioq = folioq; + trace_netfs_folioq(folioq, netfs_trace_folioq_read_progress); } - subreq->curr_folioq_slot = slot; - if (folioq && folioq_folio(folioq, slot)) - subreq->curr_folio_order = folioq->orders[slot]; - if (!was_async) - cond_resched(); - goto next_folio; + + if (fpos + fsize >= collected_to) + break; } - /* Deal with partial progress. */ - if (subreq->transferred < subreq->len) - return false; + rreq->buffer.tail = folioq; +done: + rreq->buffer.first_tail_slot = slot; +} - /* Donate the remaining downloaded data to one of the neighbouring - * subrequests. Note that we may race with them doing the same thing. +/* + * Collect and assess the results of various read subrequests. We may need to + * retry some of the results. + * + * Note that we have a sequence of subrequests, which may be drawing on + * different sources and may or may not be the same size or starting position + * and may not even correspond in boundary alignment. + */ +static void netfs_collect_read_results(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *front, *remove; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + unsigned int notes; + + _enter("%llx-%llx", rreq->start, rreq->start + rreq->len); + trace_netfs_rreq(rreq, netfs_rreq_trace_collect); + trace_netfs_collect(rreq); + +reassess: + if (rreq->origin == NETFS_READAHEAD || + rreq->origin == NETFS_READPAGE || + rreq->origin == NETFS_READ_FOR_WRITE) + notes = BUFFERED; + else + notes = 0; + + /* Remove completed subrequests from the front of the stream and + * advance the completion point. We stop when we hit something that's + * in progress. The issuer thread may be adding stuff to the tail + * whilst we're doing this. */ - spin_lock_bh(&rreq->lock); + front = READ_ONCE(stream->front); + while (front) { + size_t transferred; - if (subreq->prev_donated != prev_donated || - subreq->next_donated != next_donated) { - spin_unlock_bh(&rreq->lock); - cond_resched(); - goto donation_changed; - } + trace_netfs_collect_sreq(rreq, front); + _debug("sreq [%x] %llx %zx/%zx", + front->debug_index, front->start, front->transferred, front->len); - /* Deal with the trickiest case: that this subreq is in the middle of a - * folio, not touching either edge, but finishes first. In such a - * case, we donate to the previous subreq, if there is one, so that the - * donation is only handled when that completes - and remove this - * subreq from the list. - * - * If the previous subreq finished first, we will have acquired their - * donation and should be able to unlock folios and/or donate nextwards. - */ - if (!subreq->consumed && - !prev_donated && - !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { - prev = list_prev_entry(subreq, rreq_link); - WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); - subreq->start += subreq->len; - subreq->len = 0; - subreq->transferred = 0; - trace_netfs_donate(rreq, subreq, prev, subreq->len, - netfs_trace_donate_to_prev); - trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_prev); - goto remove_subreq_locked; + if (stream->collected_to < front->start) { + trace_netfs_collect_gap(rreq, stream, front->start, 'F'); + stream->collected_to = front->start; + } + + if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) + notes |= HIT_PENDING; + smp_rmb(); /* Read counters after IN_PROGRESS flag. */ + transferred = READ_ONCE(front->transferred); + + /* If we can now collect the next folio, do so. We don't want + * to defer this as we have to decide whether we need to copy + * to the cache or not, and that may differ between adjacent + * subreqs. + */ + if (notes & BUFFERED) { + size_t fsize = PAGE_SIZE << rreq->front_folio_order; + + /* Clear the tail of a short read. */ + if (!(notes & HIT_PENDING) && + front->error == 0 && + transferred < front->len && + (test_bit(NETFS_SREQ_HIT_EOF, &front->flags) || + test_bit(NETFS_SREQ_CLEAR_TAIL, &front->flags))) { + netfs_clear_unread(front); + transferred = front->transferred = front->len; + trace_netfs_sreq(front, netfs_sreq_trace_clear); + } + + stream->collected_to = front->start + transferred; + rreq->collected_to = stream->collected_to; + + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &front->flags)) + notes |= COPY_TO_CACHE; + + if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { + rreq->abandon_to = front->start + front->len; + front->transferred = front->len; + transferred = front->len; + trace_netfs_rreq(rreq, netfs_rreq_trace_set_abandon); + } + if (front->start + transferred >= rreq->cleaned_to + fsize || + test_bit(NETFS_SREQ_HIT_EOF, &front->flags)) + netfs_read_unlock_folios(rreq, ¬es); + } else { + stream->collected_to = front->start + transferred; + rreq->collected_to = stream->collected_to; + } + + /* Stall if the front is still undergoing I/O. */ + if (notes & HIT_PENDING) + break; + + if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { + if (!stream->failed) { + stream->error = front->error; + rreq->error = front->error; + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + stream->failed = true; + } + notes |= MADE_PROGRESS | ABANDON_SREQ; + } else if (test_bit(NETFS_SREQ_NEED_RETRY, &front->flags)) { + stream->need_retry = true; + notes |= NEED_RETRY | MADE_PROGRESS; + break; + } else { + if (!stream->failed) + stream->transferred = stream->collected_to - rreq->start; + notes |= MADE_PROGRESS; + } + + /* Remove if completely consumed. */ + stream->source = front->source; + spin_lock(&rreq->lock); + + remove = front; + trace_netfs_sreq(front, netfs_sreq_trace_discard); + list_del_init(&front->rreq_link); + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + stream->front = front; + spin_unlock(&rreq->lock); + netfs_put_subrequest(remove, false, + notes & ABANDON_SREQ ? + netfs_sreq_trace_put_abandon : + netfs_sreq_trace_put_done); } - /* If we can't donate down the chain, donate up the chain instead. */ - excess = subreq->len - subreq->consumed + next_donated; + trace_netfs_collect_stream(rreq, stream); + trace_netfs_collect_state(rreq, rreq->collected_to, notes); - if (!subreq->consumed) - excess += prev_donated; + if (!(notes & BUFFERED)) + rreq->cleaned_to = rreq->collected_to; - if (list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - rreq->prev_donated = excess; - trace_netfs_donate(rreq, subreq, NULL, excess, - netfs_trace_donate_to_deferred_next); - } else { - next = list_next_entry(subreq, rreq_link); - WRITE_ONCE(next->prev_donated, excess); - trace_netfs_donate(rreq, subreq, next, excess, - netfs_trace_donate_to_next); + if (notes & NEED_RETRY) + goto need_retry; + if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) { + trace_netfs_rreq(rreq, netfs_rreq_trace_unpause); + clear_bit_unlock(NETFS_RREQ_PAUSE, &rreq->flags); + smp_mb__after_atomic(); /* Set PAUSE before task state */ + wake_up(&rreq->waitq); + } + + if (notes & MADE_PROGRESS) { + //cond_resched(); + goto reassess; } - trace_netfs_sreq(subreq, netfs_sreq_trace_donate_to_next); - subreq->len = subreq->consumed; - subreq->transferred = subreq->consumed; - goto remove_subreq_locked; - -remove_subreq: - spin_lock_bh(&rreq->lock); -remove_subreq_locked: - subreq->consumed = subreq->len; - list_del(&subreq->rreq_link); - spin_unlock_bh(&rreq->lock); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_consumed); - return true; - -bad: - /* Errr... prev and next both donated to us, but insufficient to finish - * the folio. + +out: + _leave(" = %x", notes); + return; + +need_retry: + /* Okay... We're going to have to retry parts of the stream. Note + * that any partially completed op will have had any wholly transferred + * folios removed from it. */ - printk("R=%08x[%x] s=%llx-%llx %zx/%zx/%zx\n", - rreq->debug_id, subreq->debug_index, - subreq->start, subreq->start + subreq->transferred - 1, - subreq->consumed, subreq->transferred, subreq->len); - printk("folio: %llx-%llx\n", fpos, fend - 1); - printk("donated: prev=%zx next=%zx\n", prev_donated, next_donated); - printk("s=%llx av=%zx part=%zx\n", start, avail, part); - BUG(); + _debug("retry"); + netfs_retry_reads(rreq); + goto out; } /* @@ -318,12 +343,13 @@ bad: static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; unsigned int i; /* Collect unbuffered reads and direct reads, adding up the transfer * sizes until we find the first short or failed subrequest. */ - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { rreq->transferred += subreq->transferred; if (subreq->transferred < subreq->len || @@ -356,89 +382,135 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) } /* - * Assess the state of a read request and decide what to do next. + * Do processing after reading a monolithic single object. + */ +static void netfs_rreq_assess_single(struct netfs_io_request *rreq) +{ + struct netfs_io_stream *stream = &rreq->io_streams[0]; + + if (!rreq->error && stream->source == NETFS_DOWNLOAD_FROM_SERVER && + fscache_resources_valid(&rreq->cache_resources)) { + trace_netfs_rreq(rreq, netfs_rreq_trace_dirty); + netfs_single_mark_inode_dirty(rreq->inode); + } + + if (rreq->iocb) { + rreq->iocb->ki_pos += rreq->transferred; + if (rreq->iocb->ki_complete) + rreq->iocb->ki_complete( + rreq->iocb, rreq->error ? rreq->error : rreq->transferred); + } + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +/* + * Perform the collection of subrequests and folios. * * Note that we're in normal kernel thread context at this point, possibly * running on a workqueue. */ -static void netfs_rreq_assess(struct netfs_io_request *rreq) +static void netfs_read_collection(struct netfs_io_request *rreq) { - trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + struct netfs_io_stream *stream = &rreq->io_streams[0]; - //netfs_rreq_is_still_valid(rreq); + netfs_collect_read_results(rreq); - if (test_and_clear_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags)) { - netfs_retry_reads(rreq); + /* We're done when the app thread has finished posting subreqs and the + * queue is empty. + */ + if (!test_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags)) + return; + smp_rmb(); /* Read ALL_QUEUED before subreq lists. */ + + if (!list_empty(&stream->subrequests)) return; - } - if (rreq->origin == NETFS_DIO_READ || - rreq->origin == NETFS_READ_GAPS) + /* Okay, declare that all I/O is complete. */ + rreq->transferred = stream->transferred; + trace_netfs_rreq(rreq, netfs_rreq_trace_complete); + + //netfs_rreq_is_still_valid(rreq); + + switch (rreq->origin) { + case NETFS_DIO_READ: + case NETFS_READ_GAPS: netfs_rreq_assess_dio(rreq); + break; + case NETFS_READ_SINGLE: + netfs_rreq_assess_single(rreq); + break; + default: + break; + } task_io_account_read(rreq->transferred); trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_done); netfs_clear_subrequests(rreq, false); netfs_unlock_abandoned_read_pages(rreq); - if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) - netfs_pgpriv2_write_to_the_cache(rreq); + if (unlikely(rreq->copy_to_cache)) + netfs_pgpriv2_end_copy_to_cache(rreq); } -void netfs_read_termination_worker(struct work_struct *work) +void netfs_read_collection_worker(struct work_struct *work) { - struct netfs_io_request *rreq = - container_of(work, struct netfs_io_request, work); + struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + netfs_see_request(rreq, netfs_rreq_trace_see_work); - netfs_rreq_assess(rreq); - netfs_put_request(rreq, false, netfs_rreq_trace_put_work_complete); + if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + netfs_read_collection(rreq); + netfs_put_request(rreq, false, netfs_rreq_trace_put_work); } /* - * Handle the completion of all outstanding I/O operations on a read request. - * We inherit a ref from the caller. + * Wake the collection work item. */ -void netfs_rreq_terminated(struct netfs_io_request *rreq, bool was_async) +void netfs_wake_read_collector(struct netfs_io_request *rreq) { - if (!was_async) - return netfs_rreq_assess(rreq); - if (!work_pending(&rreq->work)) { - netfs_get_request(rreq, netfs_rreq_trace_get_work); - if (!queue_work(system_unbound_wq, &rreq->work)) - netfs_put_request(rreq, was_async, netfs_rreq_trace_put_work_nq); + if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { + if (!work_pending(&rreq->work)) { + netfs_get_request(rreq, netfs_rreq_trace_get_work); + if (!queue_work(system_unbound_wq, &rreq->work)) + netfs_put_request(rreq, true, netfs_rreq_trace_put_work_nq); + } + } else { + trace_netfs_rreq(rreq, netfs_rreq_trace_wake_queue); + wake_up(&rreq->waitq); } } /** * netfs_read_subreq_progress - Note progress of a read operation. * @subreq: The read request that has terminated. - * @was_async: True if we're in an asynchronous context. * * This tells the read side of netfs lib that a contributory I/O operation has * made some progress and that it may be possible to unlock some folios. * * Before calling, the filesystem should update subreq->transferred to track * the amount of data copied into the output buffer. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. */ -void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, - bool was_async) +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + size_t fsize = PAGE_SIZE << rreq->front_folio_order; trace_netfs_sreq(subreq, netfs_sreq_trace_progress); - if (subreq->transferred > subreq->consumed && + /* If we are at the head of the queue, wake up the collector, + * getting a ref to it if we were the ones to do so. + */ + if (subreq->start + subreq->transferred > rreq->cleaned_to + fsize && (rreq->origin == NETFS_READAHEAD || rreq->origin == NETFS_READPAGE || - rreq->origin == NETFS_READ_FOR_WRITE)) { - netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + rreq->origin == NETFS_READ_FOR_WRITE) && + list_is_first(&subreq->rreq_link, &stream->subrequests) + ) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + netfs_wake_read_collector(rreq); } } EXPORT_SYMBOL(netfs_read_subreq_progress); @@ -446,27 +518,23 @@ EXPORT_SYMBOL(netfs_read_subreq_progress); /** * netfs_read_subreq_terminated - Note the termination of an I/O operation. * @subreq: The I/O request that has terminated. - * @error: Error code indicating type of completion. - * @was_async: The termination was asynchronous * * This tells the read helper that a contributory I/O operation has terminated, * one way or another, and that it should integrate the results. * - * The caller indicates the outcome of the operation through @error, supplying - * 0 to indicate a successful or retryable transfer (if NETFS_SREQ_NEED_RETRY - * is set) or a negative error code. The helper will look after reissuing I/O - * operations as appropriate and writing downloaded data to the cache. + * The caller indicates the outcome of the operation through @subreq->error, + * supplying 0 to indicate a successful or retryable transfer (if + * NETFS_SREQ_NEED_RETRY is set) or a negative error code. The helper will + * look after reissuing I/O operations as appropriate and writing downloaded + * data to the cache. * * Before calling, the filesystem should update subreq->transferred to track * the amount of data copied into the output buffer. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. */ -void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, - int error, bool was_async) +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; switch (subreq->source) { case NETFS_READ_FROM_CACHE: @@ -479,68 +547,156 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, break; } - if (rreq->origin != NETFS_DIO_READ) { - /* Collect buffered reads. - * - * If the read completed validly short, then we can clear the - * tail before going on to unlock the folios. - */ - if (error == 0 && subreq->transferred < subreq->len && - (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags) || - test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags))) { - netfs_clear_unread(subreq); - subreq->transferred = subreq->len; - trace_netfs_sreq(subreq, netfs_sreq_trace_clear); - } - if (subreq->transferred > subreq->consumed && - (rreq->origin == NETFS_READAHEAD || - rreq->origin == NETFS_READPAGE || - rreq->origin == NETFS_READ_FOR_WRITE)) { - netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - } - rreq->transferred += subreq->transferred; - } - /* Deal with retry requests, short reads and errors. If we retry * but don't make progress, we abandon the attempt. */ - if (!error && subreq->transferred < subreq->len) { + if (!subreq->error && subreq->transferred < subreq->len) { if (test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) { trace_netfs_sreq(subreq, netfs_sreq_trace_hit_eof); + } else if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { + trace_netfs_sreq(subreq, netfs_sreq_trace_need_clear); + } else if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + trace_netfs_sreq(subreq, netfs_sreq_trace_need_retry); + } else if (test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + trace_netfs_sreq(subreq, netfs_sreq_trace_partial_read); } else { + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + subreq->error = -ENODATA; trace_netfs_sreq(subreq, netfs_sreq_trace_short); - if (subreq->transferred > subreq->consumed) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else { - __set_bit(NETFS_SREQ_FAILED, &subreq->flags); - error = -ENODATA; - } } } - subreq->error = error; - trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - - if (unlikely(error < 0)) { - trace_netfs_failure(rreq, subreq, error, netfs_fail_read); + if (unlikely(subreq->error < 0)) { + trace_netfs_failure(rreq, subreq, subreq->error, netfs_fail_read); if (subreq->source == NETFS_READ_FROM_CACHE) { netfs_stat(&netfs_n_rh_read_failed); + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); } else { netfs_stat(&netfs_n_rh_download_failed); - set_bit(NETFS_RREQ_FAILED, &rreq->flags); - rreq->error = subreq->error; + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); } + trace_netfs_rreq(rreq, netfs_rreq_trace_set_pause); + set_bit(NETFS_RREQ_PAUSE, &rreq->flags); } - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, was_async); + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */ + + /* If we are at the head of the queue, wake up the collector. */ + if (list_is_first(&subreq->rreq_link, &stream->subrequests)) + netfs_wake_read_collector(rreq); - netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); + netfs_put_subrequest(subreq, true, netfs_sreq_trace_put_terminated); } EXPORT_SYMBOL(netfs_read_subreq_terminated); + +/* + * Handle termination of a read from the cache. + */ +void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + + if (transferred_or_error > 0) { + subreq->error = 0; + if (transferred_or_error > 0) { + subreq->transferred += transferred_or_error; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } + } else { + subreq->error = transferred_or_error; + } + netfs_read_subreq_terminated(subreq); +} + +/* + * Wait for the read operation to complete, successfully or otherwise. + */ +ssize_t netfs_wait_for_read(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + ssize_t ret; + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + subreq = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + if (subreq && + (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) || + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) { + __set_current_state(TASK_RUNNING); + netfs_read_collection(rreq); + continue; + } + + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + break; + + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); + + ret = rreq->error; + if (ret == 0) { + ret = rreq->transferred; + switch (rreq->origin) { + case NETFS_DIO_READ: + case NETFS_READ_SINGLE: + ret = rreq->transferred; + break; + default: + if (rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + break; + } + } + + return ret; +} + +/* + * Wait for a paused read operation to unpause or complete in some manner. + */ +void netfs_wait_for_pause(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause); + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + subreq = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + if (subreq && + (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) || + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) { + __set_current_state(TASK_RUNNING); + netfs_read_collection(rreq); + continue; + } + + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) || + !test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + break; + + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); +} diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index ba5af89d37fa..cf7727060215 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -14,52 +14,11 @@ #include "internal.h" /* - * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2. The - * third mark in the folio queue is used to indicate that this folio needs - * writing. - */ -void netfs_pgpriv2_mark_copy_to_cache(struct netfs_io_subrequest *subreq, - struct netfs_io_request *rreq, - struct folio_queue *folioq, - int slot) -{ - struct folio *folio = folioq_folio(folioq, slot); - - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folioq_mark3(folioq, slot); -} - -/* - * [DEPRECATED] Cancel PG_private_2 on all marked folios in the event of an - * unrecoverable error. - */ -static void netfs_pgpriv2_cancel(struct folio_queue *folioq) -{ - struct folio *folio; - int slot; - - while (folioq) { - if (!folioq->marks3) { - folioq = folioq->next; - continue; - } - - slot = __ffs(folioq->marks3); - folio = folioq_folio(folioq, slot); - - trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); - folio_end_private_2(folio); - folioq_unmark3(folioq, slot); - } -} - -/* * [DEPRECATED] Copy a folio to the cache with PG_private_2 set. */ -static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio *folio) +static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio *folio) { - struct netfs_io_stream *cache = &wreq->io_streams[1]; + struct netfs_io_stream *cache = &creq->io_streams[1]; size_t fsize = folio_size(folio), flen = fsize; loff_t fpos = folio_pos(folio), i_size; bool to_eof = false; @@ -70,17 +29,17 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio * of the page to beyond it, but cannot move i_size into or through the * page since we have it locked. */ - i_size = i_size_read(wreq->inode); + i_size = i_size_read(creq->inode); if (fpos >= i_size) { /* mmap beyond eof. */ _debug("beyond eof"); folio_end_private_2(folio); - return 0; + return; } - if (fpos + fsize > wreq->i_size) - wreq->i_size = i_size; + if (fpos + fsize > creq->i_size) + creq->i_size = i_size; if (flen > i_size - fpos) { flen = i_size - fpos; @@ -94,8 +53,10 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio trace_netfs_folio(folio, netfs_folio_trace_store_copy); /* Attach the folio to the rolling buffer. */ - if (netfs_buffer_append_folio(wreq, folio, false) < 0) - return -ENOMEM; + if (rolling_buffer_append(&creq->buffer, folio, 0) < 0) { + clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); + return; + } cache->submit_extendable_to = fsize; cache->submit_off = 0; @@ -109,11 +70,11 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio do { ssize_t part; - wreq->io_iter.iov_offset = cache->submit_off; + creq->buffer.iter.iov_offset = cache->submit_off; - atomic64_set(&wreq->issued_to, fpos + cache->submit_off); + atomic64_set(&creq->issued_to, fpos + cache->submit_off); cache->submit_extendable_to = fsize - cache->submit_off; - part = netfs_advance_write(wreq, cache, fpos + cache->submit_off, + part = netfs_advance_write(creq, cache, fpos + cache->submit_off, cache->submit_len, to_eof); cache->submit_off += part; if (part > cache->submit_len) @@ -122,94 +83,95 @@ static int netfs_pgpriv2_copy_folio(struct netfs_io_request *wreq, struct folio cache->submit_len -= part; } while (cache->submit_len > 0); - wreq->io_iter.iov_offset = 0; - iov_iter_advance(&wreq->io_iter, fsize); - atomic64_set(&wreq->issued_to, fpos + fsize); + creq->buffer.iter.iov_offset = 0; + rolling_buffer_advance(&creq->buffer, fsize); + atomic64_set(&creq->issued_to, fpos + fsize); if (flen < fsize) - netfs_issue_write(wreq, cache); - - _leave(" = 0"); - return 0; + netfs_issue_write(creq, cache); } /* - * [DEPRECATED] Go through the buffer and write any folios that are marked with - * the third mark to the cache. + * [DEPRECATED] Set up copying to the cache. */ -void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) +static struct netfs_io_request *netfs_pgpriv2_begin_copy_to_cache( + struct netfs_io_request *rreq, struct folio *folio) { - struct netfs_io_request *wreq; - struct folio_queue *folioq; - struct folio *folio; - int error = 0; - int slot = 0; - - _enter(""); + struct netfs_io_request *creq; if (!fscache_resources_valid(&rreq->cache_resources)) - goto couldnt_start; - - /* Need the first folio to be able to set up the op. */ - for (folioq = rreq->buffer; folioq; folioq = folioq->next) { - if (folioq->marks3) { - slot = __ffs(folioq->marks3); - break; - } - } - if (!folioq) - return; - folio = folioq_folio(folioq, slot); + goto cancel; - wreq = netfs_create_write_req(rreq->mapping, NULL, folio_pos(folio), + creq = netfs_create_write_req(rreq->mapping, NULL, folio_pos(folio), NETFS_PGPRIV2_COPY_TO_CACHE); - if (IS_ERR(wreq)) { - kleave(" [create %ld]", PTR_ERR(wreq)); - goto couldnt_start; - } + if (IS_ERR(creq)) + goto cancel; + + if (!creq->io_streams[1].avail) + goto cancel_put; - trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); + trace_netfs_write(creq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); + rreq->copy_to_cache = creq; + return creq; + +cancel_put: + netfs_put_request(creq, false, netfs_rreq_trace_put_return); +cancel: + rreq->copy_to_cache = ERR_PTR(-ENOBUFS); + clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); + return ERR_PTR(-ENOBUFS); +} - for (;;) { - error = netfs_pgpriv2_copy_folio(wreq, folio); - if (error < 0) - break; +/* + * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2 and add + * it to the copy write request. + */ +void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) +{ + struct netfs_io_request *creq = rreq->copy_to_cache; - folioq_unmark3(folioq, slot); - if (!folioq->marks3) { - folioq = folioq->next; - if (!folioq) - break; - } + if (!creq) + creq = netfs_pgpriv2_begin_copy_to_cache(rreq, folio); + if (IS_ERR(creq)) + return; - slot = __ffs(folioq->marks3); - folio = folioq_folio(folioq, slot); - } + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + netfs_pgpriv2_copy_folio(creq, folio); +} - netfs_issue_write(wreq, &wreq->io_streams[1]); +/* + * [DEPRECATED] End writing to the cache, flushing out any outstanding writes. + */ +void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_io_request *creq = rreq->copy_to_cache; + + if (IS_ERR_OR_NULL(creq)) + return; + + netfs_issue_write(creq, &creq->io_streams[1]); smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + set_bit(NETFS_RREQ_ALL_QUEUED, &creq->flags); - netfs_put_request(wreq, false, netfs_rreq_trace_put_return); - _leave(" = %d", error); -couldnt_start: - netfs_pgpriv2_cancel(rreq->buffer); + netfs_put_request(creq, false, netfs_rreq_trace_put_return); + creq->copy_to_cache = NULL; } /* * [DEPRECATED] Remove the PG_private_2 mark from any folios we've finished * copying. */ -bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) +bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *creq) { - struct folio_queue *folioq = wreq->buffer; - unsigned long long collected_to = wreq->collected_to; - unsigned int slot = wreq->buffer_head_slot; + struct folio_queue *folioq = creq->buffer.tail; + unsigned long long collected_to = creq->collected_to; + unsigned int slot = creq->buffer.first_tail_slot; bool made_progress = false; if (slot >= folioq_nr_slots(folioq)) { - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&creq->buffer); slot = 0; } @@ -221,16 +183,16 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) folio = folioq_folio(folioq, slot); if (WARN_ONCE(!folio_test_private_2(folio), "R=%08x: folio %lx is not marked private_2\n", - wreq->debug_id, folio->index)) + creq->debug_id, folio->index)) trace_netfs_folio(folio, netfs_folio_trace_not_under_wback); fpos = folio_pos(folio); fsize = folio_size(folio); flen = fsize; - fend = min_t(unsigned long long, fpos + flen, wreq->i_size); + fend = min_t(unsigned long long, fpos + flen, creq->i_size); - trace_netfs_collect_folio(wreq, folio, fend, collected_to); + trace_netfs_collect_folio(creq, folio, fend, collected_to); /* Unlock any folio we've transferred all of. */ if (collected_to < fend) @@ -238,7 +200,7 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) trace_netfs_folio(folio, netfs_folio_trace_end_copy); folio_end_private_2(folio); - wreq->cleaned_to = fpos + fsize; + creq->cleaned_to = fpos + fsize; made_progress = true; /* Clean up the head folioq. If we clear an entire folioq, then @@ -248,9 +210,9 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) folioq_clear(folioq, slot); slot++; if (slot >= folioq_nr_slots(folioq)) { - if (READ_ONCE(wreq->buffer_tail) == folioq) - break; - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&creq->buffer); + if (!folioq) + goto done; slot = 0; } @@ -258,7 +220,8 @@ bool netfs_pgpriv2_unlock_copied_folios(struct netfs_io_request *wreq) break; } - wreq->buffer = folioq; - wreq->buffer_head_slot = slot; + creq->buffer.tail = folioq; +done: + creq->buffer.first_tail_slot = slot; return made_progress; } diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 0350592ea804..2290af0d51ac 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -12,15 +12,7 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, struct netfs_io_subrequest *subreq) { - struct iov_iter *io_iter = &subreq->io_iter; - - if (iov_iter_is_folioq(io_iter)) { - subreq->curr_folioq = (struct folio_queue *)io_iter->folioq; - subreq->curr_folioq_slot = io_iter->folioq_slot; - subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot]; - } - - atomic_inc(&rreq->nr_outstanding); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); subreq->rreq->netfs_ops->issue_read(subreq); @@ -33,13 +25,12 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; - struct netfs_io_stream *stream0 = &rreq->io_streams[0]; - LIST_HEAD(sublist); - LIST_HEAD(queue); + struct netfs_io_stream *stream = &rreq->io_streams[0]; + struct list_head *next; _enter("R=%x", rreq->debug_id); - if (list_empty(&rreq->subrequests)) + if (list_empty(&stream->subrequests)) return; if (rreq->netfs_ops->retry_request) @@ -49,13 +40,13 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * up to the first permanently failed one. */ if (!rreq->netfs_ops->prepare_read && - !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { - struct netfs_io_subrequest *subreq; - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + !rreq->cache_resources.ops) { + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; netfs_reset_iter(subreq); netfs_reissue_read(rreq, subreq); } @@ -73,48 +64,44 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * populating with smaller subrequests. In the event that the subreq * we just launched finishes before we insert the next subreq, it'll * fill in rreq->prev_donated instead. - + * * Note: Alternatively, we could split the tail subrequest right before * we reissue it and fix up the donations under lock. */ - list_splice_init(&rreq->subrequests, &queue); + next = stream->subrequests.next; do { - struct netfs_io_subrequest *from; + struct netfs_io_subrequest *from, *to, *tmp; struct iov_iter source; unsigned long long start, len; - size_t part, deferred_next_donated = 0; + size_t part; bool boundary = false; /* Go through the subreqs and find the next span of contiguous * buffer that we then rejig (cifs, for example, needs the * rsize renegotiating) and reissue. */ - from = list_first_entry(&queue, struct netfs_io_subrequest, rreq_link); - list_move_tail(&from->rreq_link, &sublist); + from = list_entry(next, struct netfs_io_subrequest, rreq_link); + to = from; start = from->start + from->transferred; len = from->len - from->transferred; - _debug("from R=%08x[%x] s=%llx ctl=%zx/%zx/%zx", + _debug("from R=%08x[%x] s=%llx ctl=%zx/%zx", rreq->debug_id, from->debug_index, - from->start, from->consumed, from->transferred, from->len); + from->start, from->transferred, from->len); if (test_bit(NETFS_SREQ_FAILED, &from->flags) || !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) goto abandon; - deferred_next_donated = from->next_donated; - while ((subreq = list_first_entry_or_null( - &queue, struct netfs_io_subrequest, rreq_link))) { - if (subreq->start != start + len || - subreq->transferred > 0 || + list_for_each_continue(next, &stream->subrequests) { + subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); + if (subreq->start + subreq->transferred != start + len || + test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) || !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) break; - list_move_tail(&subreq->rreq_link, &sublist); - len += subreq->len; - deferred_next_donated = subreq->next_donated; - if (test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags)) - break; + to = subreq; + len += to->len; } _debug(" - range: %llx-%llx %llx", start, start + len - 1, len); @@ -127,36 +114,31 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) source.count = len; /* Work through the sublist. */ - while ((subreq = list_first_entry_or_null( - &sublist, struct netfs_io_subrequest, rreq_link))) { - list_del(&subreq->rreq_link); - + subreq = from; + list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { + if (!len) + break; subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start - subreq->transferred; subreq->len = len + subreq->transferred; - stream0->sreq_max_len = subreq->len; - __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; - spin_lock_bh(&rreq->lock); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - subreq->prev_donated += rreq->prev_donated; - rreq->prev_donated = 0; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - spin_unlock_bh(&rreq->lock); - - BUG_ON(!len); /* Renegotiate max_len (rsize) */ - if (rreq->netfs_ops->prepare_read(subreq) < 0) { + stream->sreq_max_len = subreq->len; + if (rreq->netfs_ops->prepare_read && + rreq->netfs_ops->prepare_read(subreq) < 0) { trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + goto abandon; } - part = umin(len, stream0->sreq_max_len); - if (unlikely(rreq->io_streams[0].sreq_max_segs)) - part = netfs_limit_iter(&source, 0, part, stream0->sreq_max_segs); + part = umin(len, stream->sreq_max_len); + if (unlikely(stream->sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream->sreq_max_segs); subreq->len = subreq->transferred + part; subreq->io_iter = source; iov_iter_truncate(&subreq->io_iter, part); @@ -166,58 +148,105 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) if (!len) { if (boundary) __set_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); - subreq->next_donated = deferred_next_donated; } else { __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); - subreq->next_donated = 0; } + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); - if (!len) + if (subreq == to) break; - - /* If we ran out of subrequests, allocate another. */ - if (list_empty(&sublist)) { - subreq = netfs_alloc_subrequest(rreq); - if (!subreq) - goto abandon; - subreq->source = NETFS_DOWNLOAD_FROM_SERVER; - subreq->start = start; - - /* We get two refs, but need just one. */ - netfs_put_subrequest(subreq, false, netfs_sreq_trace_new); - trace_netfs_sreq(subreq, netfs_sreq_trace_split); - list_add_tail(&subreq->rreq_link, &sublist); - } } /* If we managed to use fewer subreqs, we can discard the - * excess. + * excess; if we used the same number, then we're done. */ - while ((subreq = list_first_entry_or_null( - &sublist, struct netfs_io_subrequest, rreq_link))) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + if (!len) { + if (subreq == to) + continue; + list_for_each_entry_safe_from(subreq, tmp, + &stream->subrequests, rreq_link) { + trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + if (subreq == to) + break; + } + continue; } - } while (!list_empty(&queue)); + /* We ran out of subrequests, so we need to allocate some more + * and insert them after. + */ + do { + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) { + subreq = to; + goto abandon_after; + } + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->start = start; + subreq->len = len; + subreq->debug_index = atomic_inc_return(&rreq->subreq_counter); + subreq->stream_nr = stream->stream_nr; + subreq->retry_count = 1; + + trace_netfs_sreq_ref(rreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), + netfs_sreq_trace_new); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + + list_add(&subreq->rreq_link, &to->rreq_link); + to = list_next_entry(to, rreq_link); + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + + stream->sreq_max_len = umin(len, rreq->rsize); + stream->sreq_max_segs = 0; + if (unlikely(stream->sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream->sreq_max_segs); + + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read(subreq) < 0) { + trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + goto abandon; + } + + part = umin(len, stream->sreq_max_len); + subreq->len = subreq->transferred + part; + subreq->io_iter = source; + iov_iter_truncate(&subreq->io_iter, part); + iov_iter_advance(&source, part); + + len -= part; + start += part; + if (!len && boundary) { + __set_bit(NETFS_SREQ_BOUNDARY, &to->flags); + boundary = false; + } + + netfs_reissue_read(rreq, subreq); + } while (len); + + } while (!list_is_head(next, &stream->subrequests)); return; - /* If we hit ENOMEM, fail all remaining subrequests */ + /* If we hit an error, fail all remaining incomplete subrequests */ +abandon_after: + if (list_is_last(&subreq->rreq_link, &stream->subrequests)) + return; + subreq = list_next_entry(subreq, rreq_link); abandon: - list_splice_init(&sublist, &queue); - list_for_each_entry(subreq, &queue, rreq_link) { - if (!subreq->error) - subreq->error = -ENOMEM; - __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); + list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { + if (!subreq->error && + !test_bit(NETFS_SREQ_FAILED, &subreq->flags) && + !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) + continue; + subreq->error = -ENOMEM; + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); } - spin_lock_bh(&rreq->lock); - list_splice_tail_init(&queue, &rreq->subrequests); - spin_unlock_bh(&rreq->lock); } /* @@ -225,14 +254,19 @@ abandon: */ void netfs_retry_reads(struct netfs_io_request *rreq) { - trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream = &rreq->io_streams[0]; - atomic_inc(&rreq->nr_outstanding); + /* Wait for all outstanding I/O to quiesce before performing retries as + * we may need to renegotiate the I/O sizes. + */ + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + } + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); netfs_retry_read_subrequests(rreq); - - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_terminated(rreq, false); } /* @@ -243,7 +277,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) { struct folio_queue *p; - for (p = rreq->buffer; p; p = p->next) { + for (p = rreq->buffer.tail; p; p = p->next) { for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c new file mode 100644 index 000000000000..fea0ecdecc53 --- /dev/null +++ b/fs/netfs/read_single.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Single, monolithic object support (e.g. AFS directory). + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/uio.h> +#include <linux/sched/mm.h> +#include <linux/task_io_accounting_ops.h> +#include <linux/netfs.h> +#include "internal.h" + +/** + * netfs_single_mark_inode_dirty - Mark a single, monolithic object inode dirty + * @inode: The inode to mark + * + * Mark an inode that contains a single, monolithic object as dirty so that its + * writepages op will get called. If set, the SINGLE_NO_UPLOAD flag indicates + * that the object will only be written to the cache and not uploaded (e.g. AFS + * directory contents). + */ +void netfs_single_mark_inode_dirty(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + bool cache_only = test_bit(NETFS_ICTX_SINGLE_NO_UPLOAD, &ictx->flags); + bool caching = fscache_cookie_enabled(netfs_i_cookie(netfs_inode(inode))); + + if (cache_only && !caching) + return; + + mark_inode_dirty(inode); + + if (caching && !(inode->i_state & I_PINNING_NETFS_WB)) { + bool need_use = false; + + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_PINNING_NETFS_WB)) { + inode->i_state |= I_PINNING_NETFS_WB; + need_use = true; + } + spin_unlock(&inode->i_lock); + + if (need_use) + fscache_use_cookie(netfs_i_cookie(ictx), true); + } + +} +EXPORT_SYMBOL(netfs_single_mark_inode_dirty); + +static int netfs_single_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx) +{ + return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx)); +} + +static void netfs_single_cache_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (!cres->ops) { + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + return; + } + subreq->source = cres->ops->prepare_read(subreq, rreq->i_size); + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + +} + +static void netfs_single_read_cache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + _enter("R=%08x[%x]", rreq->debug_id, subreq->debug_index); + netfs_stat(&netfs_n_rh_read); + cres->ops->read(cres, subreq->start, &subreq->io_iter, NETFS_READ_HOLE_FAIL, + netfs_cache_read_terminated, subreq); +} + +/* + * Perform a read to a buffer from the cache or the server. Only a single + * subreq is permitted as the object must be fetched in a single transaction. + */ +static int netfs_single_dispatch_read(struct netfs_io_request *rreq) +{ + struct netfs_io_stream *stream = &rreq->io_streams[0]; + struct netfs_io_subrequest *subreq; + int ret = 0; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + return -ENOMEM; + + subreq->source = NETFS_SOURCE_UNKNOWN; + subreq->start = 0; + subreq->len = rreq->len; + subreq->io_iter = rreq->buffer.iter; + + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + + spin_lock(&rreq->lock); + list_add_tail(&subreq->rreq_link, &stream->subrequests); + trace_netfs_sreq(subreq, netfs_sreq_trace_added); + stream->front = subreq; + /* Store list pointers before active flag */ + smp_store_release(&stream->active, true); + spin_unlock(&rreq->lock); + + netfs_single_cache_prepare_read(rreq, subreq); + switch (subreq->source) { + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download); + if (rreq->netfs_ops->prepare_read) { + ret = rreq->netfs_ops->prepare_read(subreq); + if (ret < 0) + goto cancel; + } + + rreq->netfs_ops->issue_read(subreq); + rreq->submitted += subreq->len; + break; + case NETFS_READ_FROM_CACHE: + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + netfs_single_read_cache(rreq, subreq); + rreq->submitted += subreq->len; + ret = 0; + break; + default: + pr_warn("Unexpected single-read source %u\n", subreq->source); + WARN_ON_ONCE(true); + ret = -EIO; + break; + } + + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + return ret; +cancel: + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + return ret; +} + +/** + * netfs_read_single - Synchronously read a single blob of pages. + * @inode: The inode to read from. + * @file: The file we're using to read or NULL. + * @iter: The buffer we're reading into. + * + * Fulfil a read request for a single monolithic object by drawing data from + * the cache if possible, or the netfs if not. The buffer may be larger than + * the file content; unused beyond the EOF will be zero-filled. The content + * will be read with a single I/O request (though this may be retried). + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. If caching is enabled, + * the data will be stored as a single object into the cache. + */ +ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter) +{ + struct netfs_io_request *rreq; + struct netfs_inode *ictx = netfs_inode(inode); + ssize_t ret; + + rreq = netfs_alloc_request(inode->i_mapping, file, 0, iov_iter_count(iter), + NETFS_READ_SINGLE); + if (IS_ERR(rreq)) + return PTR_ERR(rreq); + + ret = netfs_single_begin_cache_read(rreq, ictx); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; + + netfs_stat(&netfs_n_rh_read_single); + trace_netfs_read(rreq, 0, rreq->len, netfs_read_trace_read_single); + + rreq->buffer.iter = *iter; + netfs_single_dispatch_read(rreq); + + ret = netfs_wait_for_read(rreq); + netfs_put_request(rreq, true, netfs_rreq_trace_put_return); + return ret; + +cleanup_free: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); + return ret; +} +EXPORT_SYMBOL(netfs_read_single); diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c new file mode 100644 index 000000000000..75d97af14b4a --- /dev/null +++ b/fs/netfs/rolling_buffer.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Rolling buffer helpers + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/bitops.h> +#include <linux/pagemap.h> +#include <linux/rolling_buffer.h> +#include <linux/slab.h> +#include "internal.h" + +static atomic_t debug_ids; + +/** + * netfs_folioq_alloc - Allocate a folio_queue struct + * @rreq_id: Associated debugging ID for tracing purposes + * @gfp: Allocation constraints + * @trace: Trace tag to indicate the purpose of the allocation + * + * Allocate, initialise and account the folio_queue struct and log a trace line + * to mark the allocation. + */ +struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp, + unsigned int /*enum netfs_folioq_trace*/ trace) +{ + struct folio_queue *fq; + + fq = kmalloc(sizeof(*fq), gfp); + if (fq) { + netfs_stat(&netfs_n_folioq); + folioq_init(fq, rreq_id); + fq->debug_id = atomic_inc_return(&debug_ids); + trace_netfs_folioq(fq, trace); + } + return fq; +} +EXPORT_SYMBOL(netfs_folioq_alloc); + +/** + * netfs_folioq_free - Free a folio_queue struct + * @folioq: The object to free + * @trace: Trace tag to indicate which free + * + * Free and unaccount the folio_queue struct. + */ +void netfs_folioq_free(struct folio_queue *folioq, + unsigned int /*enum netfs_trace_folioq*/ trace) +{ + trace_netfs_folioq(folioq, trace); + netfs_stat_d(&netfs_n_folioq); + kfree(folioq); +} +EXPORT_SYMBOL(netfs_folioq_free); + +/* + * Initialise a rolling buffer. We allocate an empty folio queue struct to so + * that the pointers can be independently driven by the producer and the + * consumer. + */ +int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, + unsigned int direction) +{ + struct folio_queue *fq; + + fq = netfs_folioq_alloc(rreq_id, GFP_NOFS, netfs_trace_folioq_rollbuf_init); + if (!fq) + return -ENOMEM; + + roll->head = fq; + roll->tail = fq; + iov_iter_folio_queue(&roll->iter, direction, fq, 0, 0, 0); + return 0; +} + +/* + * Add another folio_queue to a rolling buffer if there's no space left. + */ +int rolling_buffer_make_space(struct rolling_buffer *roll) +{ + struct folio_queue *fq, *head = roll->head; + + if (!folioq_full(head)) + return 0; + + fq = netfs_folioq_alloc(head->rreq_id, GFP_NOFS, netfs_trace_folioq_make_space); + if (!fq) + return -ENOMEM; + fq->prev = head; + + roll->head = fq; + if (folioq_full(head)) { + /* Make sure we don't leave the master iterator pointing to a + * block that might get immediately consumed. + */ + if (roll->iter.folioq == head && + roll->iter.folioq_slot == folioq_nr_slots(head)) { + roll->iter.folioq = fq; + roll->iter.folioq_slot = 0; + } + } + + /* Make sure the initialisation is stored before the next pointer. + * + * [!] NOTE: After we set head->next, the consumer is at liberty to + * immediately delete the old head. + */ + smp_store_release(&head->next, fq); + return 0; +} + +/* + * Decant the list of folios to read into a rolling buffer. + */ +ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + struct folio_batch *put_batch) +{ + struct folio_queue *fq; + struct page **vec; + int nr, ix, to; + ssize_t size = 0; + + if (rolling_buffer_make_space(roll) < 0) + return -ENOMEM; + + fq = roll->head; + vec = (struct page **)fq->vec.folios; + nr = __readahead_batch(ractl, vec + folio_batch_count(&fq->vec), + folio_batch_space(&fq->vec)); + ix = fq->vec.nr; + to = ix + nr; + fq->vec.nr = to; + for (; ix < to; ix++) { + struct folio *folio = folioq_folio(fq, ix); + unsigned int order = folio_order(folio); + + fq->orders[ix] = order; + size += PAGE_SIZE << order; + trace_netfs_folio(folio, netfs_folio_trace_read); + if (!folio_batch_add(put_batch, folio)) + folio_batch_release(put_batch); + } + WRITE_ONCE(roll->iter.count, roll->iter.count + size); + + /* Store the counter after setting the slot. */ + smp_store_release(&roll->next_head_slot, to); + + for (; ix < folioq_nr_slots(fq); ix++) + folioq_clear(fq, ix); + + return size; +} + +/* + * Append a folio to the rolling buffer. + */ +ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, + unsigned int flags) +{ + ssize_t size = folio_size(folio); + int slot; + + if (rolling_buffer_make_space(roll) < 0) + return -ENOMEM; + + slot = folioq_append(roll->head, folio); + if (flags & ROLLBUF_MARK_1) + folioq_mark(roll->head, slot); + if (flags & ROLLBUF_MARK_2) + folioq_mark2(roll->head, slot); + + WRITE_ONCE(roll->iter.count, roll->iter.count + size); + + /* Store the counter after setting the slot. */ + smp_store_release(&roll->next_head_slot, slot); + return size; +} + +/* + * Delete a spent buffer from a rolling queue and return the next in line. We + * don't return the last buffer to keep the pointers independent, but return + * NULL instead. + */ +struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll) +{ + struct folio_queue *spent = roll->tail, *next = READ_ONCE(spent->next); + + if (!next) + return NULL; + next->prev = NULL; + netfs_folioq_free(spent, netfs_trace_folioq_delete); + roll->tail = next; + return next; +} + +/* + * Clear out a rolling queue. Folios that have mark 1 set are put. + */ +void rolling_buffer_clear(struct rolling_buffer *roll) +{ + struct folio_batch fbatch; + struct folio_queue *p; + + folio_batch_init(&fbatch); + + while ((p = roll->tail)) { + roll->tail = p->next; + for (int slot = 0; slot < folioq_count(p); slot++) { + struct folio *folio = folioq_folio(p, slot); + + if (!folio) + continue; + if (folioq_is_marked(p, slot)) { + trace_netfs_folio(folio, netfs_folio_trace_put); + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + } + + netfs_folioq_free(p, netfs_trace_folioq_clear); + } + + folio_batch_release(&fbatch); +} diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 8e63516b40f6..f1af344266cc 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -12,6 +12,7 @@ atomic_t netfs_n_rh_dio_read; atomic_t netfs_n_rh_readahead; atomic_t netfs_n_rh_read_folio; +atomic_t netfs_n_rh_read_single; atomic_t netfs_n_rh_rreq; atomic_t netfs_n_rh_sreq; atomic_t netfs_n_rh_download; @@ -46,10 +47,11 @@ atomic_t netfs_n_folioq; int netfs_stats_show(struct seq_file *m, void *v) { - seq_printf(m, "Reads : DR=%u RA=%u RF=%u WB=%u WBZ=%u\n", + seq_printf(m, "Reads : DR=%u RA=%u RF=%u RS=%u WB=%u WBZ=%u\n", atomic_read(&netfs_n_rh_dio_read), atomic_read(&netfs_n_rh_readahead), atomic_read(&netfs_n_rh_read_folio), + atomic_read(&netfs_n_rh_read_single), atomic_read(&netfs_n_rh_write_begin), atomic_read(&netfs_n_rh_write_zskip)); seq_printf(m, "Writes : BW=%u WT=%u DW=%u WP=%u 2C=%u\n", diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 1d438be2e1b4..294f67795f79 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -17,10 +17,38 @@ #define HIT_PENDING 0x01 /* A front op was still pending */ #define NEED_REASSESS 0x02 /* Need to loop round and reassess */ #define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ -#define BUFFERED 0x08 /* The pagecache needs cleaning up */ +#define NEED_UNLOCK 0x08 /* The pagecache needs unlocking */ #define NEED_RETRY 0x10 /* A front op requests retrying */ #define SAW_FAILURE 0x20 /* One stream or hit a permanent failure */ +static void netfs_dump_request(const struct netfs_io_request *rreq) +{ + pr_err("Request R=%08x r=%d fl=%lx or=%x e=%ld\n", + rreq->debug_id, refcount_read(&rreq->ref), rreq->flags, + rreq->origin, rreq->error); + pr_err(" st=%llx tsl=%zx/%llx/%llx\n", + rreq->start, rreq->transferred, rreq->submitted, rreq->len); + pr_err(" cci=%llx/%llx/%llx\n", + rreq->cleaned_to, rreq->collected_to, atomic64_read(&rreq->issued_to)); + pr_err(" iw=%pSR\n", rreq->netfs_ops->issue_write); + for (int i = 0; i < NR_IO_STREAMS; i++) { + const struct netfs_io_subrequest *sreq; + const struct netfs_io_stream *s = &rreq->io_streams[i]; + + pr_err(" str[%x] s=%x e=%d acnf=%u,%u,%u,%u\n", + s->stream_nr, s->source, s->error, + s->avail, s->active, s->need_retry, s->failed); + pr_err(" str[%x] ct=%llx t=%zx\n", + s->stream_nr, s->collected_to, s->transferred); + list_for_each_entry(sreq, &s->subrequests, rreq_link) { + pr_err(" sreq[%x:%x] sc=%u s=%llx t=%zx/%zx r=%d f=%lx\n", + sreq->stream_nr, sreq->debug_index, sreq->source, + sreq->start, sreq->transferred, sreq->len, + refcount_read(&sreq->ref), sreq->flags); + } + } +} + /* * Successful completion of write of a folio to the server and/or cache. Note * that we are not allowed to lock the folio here on pain of deadlocking with @@ -83,9 +111,15 @@ end_wb: static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, unsigned int *notes) { - struct folio_queue *folioq = wreq->buffer; + struct folio_queue *folioq = wreq->buffer.tail; unsigned long long collected_to = wreq->collected_to; - unsigned int slot = wreq->buffer_head_slot; + unsigned int slot = wreq->buffer.first_tail_slot; + + if (WARN_ON_ONCE(!folioq)) { + pr_err("[!] Writeback unlock found empty rolling buffer!\n"); + netfs_dump_request(wreq); + return; + } if (wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) { if (netfs_pgpriv2_unlock_copied_folios(wreq)) @@ -94,7 +128,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, } if (slot >= folioq_nr_slots(folioq)) { - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&wreq->buffer); + if (!folioq) + return; slot = 0; } @@ -134,9 +170,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, folioq_clear(folioq, slot); slot++; if (slot >= folioq_nr_slots(folioq)) { - if (READ_ONCE(wreq->buffer_tail) == folioq) - break; - folioq = netfs_delete_buffer_head(wreq); + folioq = rolling_buffer_delete_spent(&wreq->buffer); + if (!folioq) + goto done; slot = 0; } @@ -144,223 +180,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq, break; } - wreq->buffer = folioq; - wreq->buffer_head_slot = slot; -} - -/* - * Perform retries on the streams that need it. - */ -static void netfs_retry_write_stream(struct netfs_io_request *wreq, - struct netfs_io_stream *stream) -{ - struct list_head *next; - - _enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr); - - if (list_empty(&stream->subrequests)) - return; - - if (stream->source == NETFS_UPLOAD_TO_SERVER && - wreq->netfs_ops->retry_request) - wreq->netfs_ops->retry_request(wreq, stream); - - if (unlikely(stream->failed)) - return; - - /* If there's no renegotiation to do, just resend each failed subreq. */ - if (!stream->prepare_write) { - struct netfs_io_subrequest *subreq; - - list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) - break; - if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { - struct iov_iter source = subreq->io_iter; - - iov_iter_revert(&source, subreq->len - source.count); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq, &source); - } - } - return; - } - - next = stream->subrequests.next; - - do { - struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp; - struct iov_iter source; - unsigned long long start, len; - size_t part; - bool boundary = false; - - /* Go through the stream and find the next span of contiguous - * data that we then rejig (cifs, for example, needs the wsize - * renegotiating) and reissue. - */ - from = list_entry(next, struct netfs_io_subrequest, rreq_link); - to = from; - start = from->start + from->transferred; - len = from->len - from->transferred; - - if (test_bit(NETFS_SREQ_FAILED, &from->flags) || - !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) - return; - - list_for_each_continue(next, &stream->subrequests) { - subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); - if (subreq->start + subreq->transferred != start + len || - test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) || - !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) - break; - to = subreq; - len += to->len; - } - - /* Determine the set of buffers we're going to use. Each - * subreq gets a subset of a single overall contiguous buffer. - */ - netfs_reset_iter(from); - source = from->io_iter; - source.count = len; - - /* Work through the sublist. */ - subreq = from; - list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { - if (!len) - break; - /* Renegotiate max_len (wsize) */ - trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - stream->prepare_write(subreq); - - part = min(len, stream->sreq_max_len); - subreq->len = part; - subreq->start = start; - subreq->transferred = 0; - len -= part; - start += part; - if (len && subreq == to && - __test_and_clear_bit(NETFS_SREQ_BOUNDARY, &to->flags)) - boundary = true; - - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - netfs_reissue_write(stream, subreq, &source); - if (subreq == to) - break; - } - - /* If we managed to use fewer subreqs, we can discard the - * excess; if we used the same number, then we're done. - */ - if (!len) { - if (subreq == to) - continue; - list_for_each_entry_safe_from(subreq, tmp, - &stream->subrequests, rreq_link) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); - if (subreq == to) - break; - } - continue; - } - - /* We ran out of subrequests, so we need to allocate some more - * and insert them after. - */ - do { - subreq = netfs_alloc_subrequest(wreq); - subreq->source = to->source; - subreq->start = start; - subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); - subreq->stream_nr = to->stream_nr; - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); - - trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, - refcount_read(&subreq->ref), - netfs_sreq_trace_new); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - - list_add(&subreq->rreq_link, &to->rreq_link); - to = list_next_entry(to, rreq_link); - trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - - stream->sreq_max_len = len; - stream->sreq_max_segs = INT_MAX; - switch (stream->source) { - case NETFS_UPLOAD_TO_SERVER: - netfs_stat(&netfs_n_wh_upload); - stream->sreq_max_len = umin(len, wreq->wsize); - break; - case NETFS_WRITE_TO_CACHE: - netfs_stat(&netfs_n_wh_write); - break; - default: - WARN_ON_ONCE(1); - } - - stream->prepare_write(subreq); - - part = umin(len, stream->sreq_max_len); - subreq->len = subreq->transferred + part; - len -= part; - start += part; - if (!len && boundary) { - __set_bit(NETFS_SREQ_BOUNDARY, &to->flags); - boundary = false; - } - - netfs_reissue_write(stream, subreq, &source); - if (!len) - break; - - } while (len); - - } while (!list_is_head(next, &stream->subrequests)); -} - -/* - * Perform retries on the streams that need it. If we're doing content - * encryption and the server copy changed due to a third-party write, we may - * need to do an RMW cycle and also rewrite the data to the cache. - */ -static void netfs_retry_writes(struct netfs_io_request *wreq) -{ - struct netfs_io_subrequest *subreq; - struct netfs_io_stream *stream; - int s; - - /* Wait for all outstanding I/O to quiesce before performing retries as - * we may need to renegotiate the I/O sizes. - */ - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (!stream->active) - continue; - - list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); - } - } - - // TODO: Enc: Fetch changed partial pages - // TODO: Enc: Reencrypt content if needed. - // TODO: Enc: Wind back transferred point. - // TODO: Enc: Mark cache pages for retry. - - for (s = 0; s < NR_IO_STREAMS; s++) { - stream = &wreq->io_streams[s]; - if (stream->need_retry) { - stream->need_retry = false; - netfs_retry_write_stream(wreq, stream); - } - } + wreq->buffer.tail = folioq; +done: + wreq->buffer.first_tail_slot = slot; } /* @@ -391,7 +213,7 @@ reassess_streams: if (wreq->origin == NETFS_WRITEBACK || wreq->origin == NETFS_WRITETHROUGH || wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) - notes = BUFFERED; + notes = NEED_UNLOCK; else notes = 0; @@ -450,14 +272,14 @@ reassess_streams: cancel: /* Remove if completely consumed. */ - spin_lock_bh(&wreq->lock); + spin_lock(&wreq->lock); remove = front; list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); stream->front = front; - spin_unlock_bh(&wreq->lock); + spin_unlock(&wreq->lock); netfs_put_subrequest(remove, false, notes & SAW_FAILURE ? netfs_sreq_trace_put_cancel : @@ -488,7 +310,7 @@ reassess_streams: trace_netfs_collect_state(wreq, wreq->collected_to, notes); /* Unlock any folios that we have now finished with. */ - if (notes & BUFFERED) { + if (notes & NEED_UNLOCK) { if (wreq->cleaned_to < wreq->collected_to) netfs_writeback_unlock_folios(wreq, ¬es); } else { @@ -502,7 +324,8 @@ reassess_streams: if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_unpause); clear_bit_unlock(NETFS_RREQ_PAUSE, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_PAUSE); + smp_mb__after_atomic(); /* Set PAUSE before task state */ + wake_up(&wreq->waitq); } if (notes & NEED_REASSESS) { @@ -605,8 +428,7 @@ void netfs_write_collection_worker(struct work_struct *work) _debug("finished"); trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags); if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); @@ -714,8 +536,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - wake_up_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); /* If we are at the head of the queue, wake up the collector, * transferring a ref to it if we were the ones to do so. diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index bf6d507578e5..69727411683e 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,9 +94,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; - bool is_buffered = (origin == NETFS_WRITEBACK || - origin == NETFS_WRITETHROUGH || - origin == NETFS_PGPRIV2_COPY_TO_CACHE); + bool is_cacheable = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITEBACK_SINGLE || + origin == NETFS_WRITETHROUGH || + origin == NETFS_PGPRIV2_COPY_TO_CACHE); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -105,8 +106,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (is_buffered && netfs_is_cache_enabled(ictx)) + if (is_cacheable && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); + if (rolling_buffer_init(&wreq->buffer, wreq->debug_id, ITER_SOURCE) < 0) + goto nomem; wreq->cleaned_to = wreq->start; @@ -129,6 +132,10 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, } return wreq; +nomem: + wreq->error = -ENOMEM; + netfs_put_request(wreq, false, netfs_rreq_trace_put_failed); + return ERR_PTR(-ENOMEM); } /** @@ -153,16 +160,15 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, loff_t start) { struct netfs_io_subrequest *subreq; - struct iov_iter *wreq_iter = &wreq->io_iter; + struct iov_iter *wreq_iter = &wreq->buffer.iter; /* Make sure we don't point the iterator at a used-up folio_queue * struct being used as a placeholder to prevent the queue from * collapsing. In such a case, extend the queue. */ if (iov_iter_is_folioq(wreq_iter) && - wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) { - netfs_buffer_make_space(wreq); - } + wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) + rolling_buffer_make_space(&wreq->buffer); subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; @@ -198,7 +204,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, * the list. The collector only goes nextwards and uses the lock to * remove entries off of the front. */ - spin_lock_bh(&wreq->lock); + spin_lock(&wreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { stream->front = subreq; @@ -209,7 +215,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, } } - spin_unlock_bh(&wreq->lock); + spin_unlock(&wreq->lock); stream->construct = subreq; } @@ -244,6 +250,8 @@ void netfs_reissue_write(struct netfs_io_stream *stream, iov_iter_advance(source, size); iov_iter_truncate(&subreq->io_iter, size); + subreq->retry_count++; + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_do_issue_write(stream, subreq); } @@ -266,9 +274,9 @@ void netfs_issue_write(struct netfs_io_request *wreq, * we can avoid overrunning the credits obtained (cifs) and try to parallelise * content-crypto preparation with network writes. */ -int netfs_advance_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start, size_t len, bool to_eof) +size_t netfs_advance_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start, size_t len, bool to_eof) { struct netfs_io_subrequest *subreq = stream->construct; size_t part; @@ -325,6 +333,9 @@ static int netfs_write_folio(struct netfs_io_request *wreq, _enter(""); + if (rolling_buffer_make_space(&wreq->buffer) < 0) + return -ENOMEM; + /* netfs_perform_write() may shift i_size around the page or from out * of the page to beyond it, but cannot move i_size into or through the * page since we have it locked. @@ -429,7 +440,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, } /* Attach the folio to the rolling buffer. */ - netfs_buffer_append_folio(wreq, folio, false); + rolling_buffer_append(&wreq->buffer, folio, 0); /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming @@ -442,7 +453,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq, stream = &wreq->io_streams[s]; stream->submit_off = foff; stream->submit_len = flen; - if ((stream->source == NETFS_WRITE_TO_CACHE && streamw) || + if (!stream->avail || + (stream->source == NETFS_WRITE_TO_CACHE && streamw) || (stream->source == NETFS_UPLOAD_TO_SERVER && fgroup == NETFS_FOLIO_COPY_TO_CACHE)) { stream->submit_off = UINT_MAX; @@ -476,7 +488,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, /* Advance the iterator(s). */ if (stream->submit_off > iter_off) { - iov_iter_advance(&wreq->io_iter, stream->submit_off - iter_off); + rolling_buffer_advance(&wreq->buffer, stream->submit_off - iter_off); iter_off = stream->submit_off; } @@ -494,7 +506,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, } if (fsize > iter_off) - iov_iter_advance(&wreq->io_iter, fsize - iter_off); + rolling_buffer_advance(&wreq->buffer, fsize - iter_off); atomic64_set(&wreq->issued_to, fpos + fsize); if (!debug) @@ -633,7 +645,7 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c struct folio **writethrough_cache) { _enter("R=%x ic=%zu ws=%u cp=%zu tp=%u", - wreq->debug_id, wreq->iter.count, wreq->wsize, copied, to_page_end); + wreq->debug_id, wreq->buffer.iter.count, wreq->wsize, copied, to_page_end); if (!*writethrough_cache) { if (folio_test_dirty(folio)) @@ -708,10 +720,10 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t part = netfs_advance_write(wreq, upload, start, len, false); start += part; len -= part; - iov_iter_advance(&wreq->io_iter, part); + rolling_buffer_advance(&wreq->buffer, part); if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_wait_pause); - wait_on_bit(&wreq->flags, NETFS_RREQ_PAUSE, TASK_UNINTERRUPTIBLE); + wait_event(wreq->waitq, !test_bit(NETFS_RREQ_PAUSE, &wreq->flags)); } if (test_bit(NETFS_RREQ_FAILED, &wreq->flags)) break; @@ -721,3 +733,194 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t _leave(" = %d", error); return error; } + +/* + * Write some of a pending folio data back to the server and/or the cache. + */ +static int netfs_write_folio_single(struct netfs_io_request *wreq, + struct folio *folio) +{ + struct netfs_io_stream *upload = &wreq->io_streams[0]; + struct netfs_io_stream *cache = &wreq->io_streams[1]; + struct netfs_io_stream *stream; + size_t iter_off = 0; + size_t fsize = folio_size(folio), flen; + loff_t fpos = folio_pos(folio); + bool to_eof = false; + bool no_debug = false; + + _enter(""); + + flen = folio_size(folio); + if (flen > wreq->i_size - fpos) { + flen = wreq->i_size - fpos; + folio_zero_segment(folio, flen, fsize); + to_eof = true; + } else if (flen == wreq->i_size - fpos) { + to_eof = true; + } + + _debug("folio %zx/%zx", flen, fsize); + + if (!upload->avail && !cache->avail) { + trace_netfs_folio(folio, netfs_folio_trace_cancel_store); + return 0; + } + + if (!upload->construct) + trace_netfs_folio(folio, netfs_folio_trace_store); + else + trace_netfs_folio(folio, netfs_folio_trace_store_plus); + + /* Attach the folio to the rolling buffer. */ + folio_get(folio); + rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK); + + /* Move the submission point forward to allow for write-streaming data + * not starting at the front of the page. We don't do write-streaming + * with the cache as the cache requires DIO alignment. + * + * Also skip uploading for data that's been read and just needs copying + * to the cache. + */ + for (int s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + stream->submit_off = 0; + stream->submit_len = flen; + if (!stream->avail) { + stream->submit_off = UINT_MAX; + stream->submit_len = 0; + } + } + + /* Attach the folio to one or more subrequests. For a big folio, we + * could end up with thousands of subrequests if the wsize is small - + * but we might need to wait during the creation of subrequests for + * network resources (eg. SMB credits). + */ + for (;;) { + ssize_t part; + size_t lowest_off = ULONG_MAX; + int choose_s = -1; + + /* Always add to the lowest-submitted stream first. */ + for (int s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + if (stream->submit_len > 0 && + stream->submit_off < lowest_off) { + lowest_off = stream->submit_off; + choose_s = s; + } + } + + if (choose_s < 0) + break; + stream = &wreq->io_streams[choose_s]; + + /* Advance the iterator(s). */ + if (stream->submit_off > iter_off) { + rolling_buffer_advance(&wreq->buffer, stream->submit_off - iter_off); + iter_off = stream->submit_off; + } + + atomic64_set(&wreq->issued_to, fpos + stream->submit_off); + stream->submit_extendable_to = fsize - stream->submit_off; + part = netfs_advance_write(wreq, stream, fpos + stream->submit_off, + stream->submit_len, to_eof); + stream->submit_off += part; + if (part > stream->submit_len) + stream->submit_len = 0; + else + stream->submit_len -= part; + if (part > 0) + no_debug = true; + } + + wreq->buffer.iter.iov_offset = 0; + if (fsize > iter_off) + rolling_buffer_advance(&wreq->buffer, fsize - iter_off); + atomic64_set(&wreq->issued_to, fpos + fsize); + + if (!no_debug) + kdebug("R=%x: No submit", wreq->debug_id); + _leave(" = 0"); + return 0; +} + +/** + * netfs_writeback_single - Write back a monolithic payload + * @mapping: The mapping to write from + * @wbc: Hints from the VM + * @iter: Data to write, must be ITER_FOLIOQ. + * + * Write a monolithic, non-pagecache object back to the server and/or + * the cache. + */ +int netfs_writeback_single(struct address_space *mapping, + struct writeback_control *wbc, + struct iov_iter *iter) +{ + struct netfs_io_request *wreq; + struct netfs_inode *ictx = netfs_inode(mapping->host); + struct folio_queue *fq; + size_t size = iov_iter_count(iter); + int ret; + + if (WARN_ON_ONCE(!iov_iter_is_folioq(iter))) + return -EIO; + + if (!mutex_trylock(&ictx->wb_lock)) { + if (wbc->sync_mode == WB_SYNC_NONE) { + netfs_stat(&netfs_n_wb_lock_skip); + return 0; + } + netfs_stat(&netfs_n_wb_lock_wait); + mutex_lock(&ictx->wb_lock); + } + + wreq = netfs_create_write_req(mapping, NULL, 0, NETFS_WRITEBACK_SINGLE); + if (IS_ERR(wreq)) { + ret = PTR_ERR(wreq); + goto couldnt_start; + } + + trace_netfs_write(wreq, netfs_write_trace_writeback); + netfs_stat(&netfs_n_wh_writepages); + + if (__test_and_set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags)) + wreq->netfs_ops->begin_writeback(wreq); + + for (fq = (struct folio_queue *)iter->folioq; fq; fq = fq->next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + struct folio *folio = folioq_folio(fq, slot); + size_t part = umin(folioq_folio_size(fq, slot), size); + + _debug("wbiter %lx %llx", folio->index, atomic64_read(&wreq->issued_to)); + + ret = netfs_write_folio_single(wreq, folio); + if (ret < 0) + goto stop; + size -= part; + if (size <= 0) + goto stop; + } + } + +stop: + for (int s = 0; s < NR_IO_STREAMS; s++) + netfs_issue_write(wreq, &wreq->io_streams[s]); + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); + + mutex_unlock(&ictx->wb_lock); + + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + _leave(" = %d", ret); + return ret; + +couldnt_start: + mutex_unlock(&ictx->wb_lock); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_writeback_single); diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c new file mode 100644 index 000000000000..c841a851dd73 --- /dev/null +++ b/fs/netfs/write_retry.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Network filesystem write retrying. + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include "internal.h" + +/* + * Perform retries on the streams that need it. + */ +static void netfs_retry_write_stream(struct netfs_io_request *wreq, + struct netfs_io_stream *stream) +{ + struct list_head *next; + + _enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr); + + if (list_empty(&stream->subrequests)) + return; + + if (stream->source == NETFS_UPLOAD_TO_SERVER && + wreq->netfs_ops->retry_request) + wreq->netfs_ops->retry_request(wreq, stream); + + if (unlikely(stream->failed)) + return; + + /* If there's no renegotiation to do, just resend each failed subreq. */ + if (!stream->prepare_write) { + struct netfs_io_subrequest *subreq; + + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) + break; + if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + struct iov_iter source = subreq->io_iter; + + iov_iter_revert(&source, subreq->len - source.count); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_reissue_write(stream, subreq, &source); + } + } + return; + } + + next = stream->subrequests.next; + + do { + struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp; + struct iov_iter source; + unsigned long long start, len; + size_t part; + bool boundary = false; + + /* Go through the stream and find the next span of contiguous + * data that we then rejig (cifs, for example, needs the wsize + * renegotiating) and reissue. + */ + from = list_entry(next, struct netfs_io_subrequest, rreq_link); + to = from; + start = from->start + from->transferred; + len = from->len - from->transferred; + + if (test_bit(NETFS_SREQ_FAILED, &from->flags) || + !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) + return; + + list_for_each_continue(next, &stream->subrequests) { + subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); + if (subreq->start + subreq->transferred != start + len || + test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) || + !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) + break; + to = subreq; + len += to->len; + } + + /* Determine the set of buffers we're going to use. Each + * subreq gets a subset of a single overall contiguous buffer. + */ + netfs_reset_iter(from); + source = from->io_iter; + source.count = len; + + /* Work through the sublist. */ + subreq = from; + list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { + if (!len) + break; + + subreq->start = start; + subreq->len = len; + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + subreq->retry_count++; + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + + /* Renegotiate max_len (wsize) */ + stream->sreq_max_len = len; + stream->prepare_write(subreq); + + part = umin(len, stream->sreq_max_len); + if (unlikely(stream->sreq_max_segs)) + part = netfs_limit_iter(&source, 0, part, stream->sreq_max_segs); + subreq->len = part; + subreq->transferred = 0; + len -= part; + start += part; + if (len && subreq == to && + __test_and_clear_bit(NETFS_SREQ_BOUNDARY, &to->flags)) + boundary = true; + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_reissue_write(stream, subreq, &source); + if (subreq == to) + break; + } + + /* If we managed to use fewer subreqs, we can discard the + * excess; if we used the same number, then we're done. + */ + if (!len) { + if (subreq == to) + continue; + list_for_each_entry_safe_from(subreq, tmp, + &stream->subrequests, rreq_link) { + trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); + if (subreq == to) + break; + } + continue; + } + + /* We ran out of subrequests, so we need to allocate some more + * and insert them after. + */ + do { + subreq = netfs_alloc_subrequest(wreq); + subreq->source = to->source; + subreq->start = start; + subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); + subreq->stream_nr = to->stream_nr; + subreq->retry_count = 1; + + trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, + refcount_read(&subreq->ref), + netfs_sreq_trace_new); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + + list_add(&subreq->rreq_link, &to->rreq_link); + to = list_next_entry(to, rreq_link); + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + + stream->sreq_max_len = len; + stream->sreq_max_segs = INT_MAX; + switch (stream->source) { + case NETFS_UPLOAD_TO_SERVER: + netfs_stat(&netfs_n_wh_upload); + stream->sreq_max_len = umin(len, wreq->wsize); + break; + case NETFS_WRITE_TO_CACHE: + netfs_stat(&netfs_n_wh_write); + break; + default: + WARN_ON_ONCE(1); + } + + stream->prepare_write(subreq); + + part = umin(len, stream->sreq_max_len); + subreq->len = subreq->transferred + part; + len -= part; + start += part; + if (!len && boundary) { + __set_bit(NETFS_SREQ_BOUNDARY, &to->flags); + boundary = false; + } + + netfs_reissue_write(stream, subreq, &source); + if (!len) + break; + + } while (len); + + } while (!list_is_head(next, &stream->subrequests)); +} + +/* + * Perform retries on the streams that need it. If we're doing content + * encryption and the server copy changed due to a third-party write, we may + * need to do an RMW cycle and also rewrite the data to the cache. + */ +void netfs_retry_writes(struct netfs_io_request *wreq) +{ + struct netfs_io_subrequest *subreq; + struct netfs_io_stream *stream; + int s; + + /* Wait for all outstanding I/O to quiesce before performing retries as + * we may need to renegotiate the I/O sizes. + */ + for (s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + if (!stream->active) + continue; + + list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, + TASK_UNINTERRUPTIBLE); + } + } + + // TODO: Enc: Fetch changed partial pages + // TODO: Enc: Reencrypt content if needed. + // TODO: Enc: Wind back transferred point. + // TODO: Enc: Mark cache pages for retry. + + for (s = 0; s < NR_IO_STREAMS; s++) { + stream = &wreq->io_streams[s]; + if (stream->need_retry) { + stream->need_retry = false; + netfs_retry_write_stream(wreq, stream); + } + } +} diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 810269ee0a50..e278a1ad1ca3 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -263,6 +263,12 @@ int nfs_netfs_readahead(struct readahead_control *ractl) static atomic_t nfs_netfs_debug_id; static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { + if (!file) { + if (WARN_ON_ONCE(rreq->origin != NETFS_PGPRIV2_COPY_TO_CACHE)) + return -EIO; + return 0; + } + rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ @@ -274,7 +280,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi static void nfs_netfs_free_request(struct netfs_io_request *rreq) { - put_nfs_open_context(rreq->netfs_priv); + if (rreq->netfs_priv) + put_nfs_open_context(rreq->netfs_priv); } static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) @@ -307,8 +314,10 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) &nfs_async_read_completion_ops); netfs = nfs_netfs_alloc(sreq); - if (!netfs) - return netfs_read_subreq_terminated(sreq, -ENOMEM, false); + if (!netfs) { + sreq->error = -ENOMEM; + return netfs_read_subreq_terminated(sreq); + } pgio.pg_netfs = netfs; /* used in completion */ diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 772d485e96d3..9d86868f4998 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -74,7 +74,8 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) */ netfs->sreq->transferred = min_t(s64, netfs->sreq->len, atomic64_read(&netfs->transferred)); - netfs_read_subreq_terminated(netfs->sreq, netfs->error, false); + netfs->sreq->error = netfs->error; + netfs_read_subreq_terminated(netfs->sreq); kfree(netfs); } static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 405f17e6e0b4..d615d520f8cf 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -114,6 +114,7 @@ static inline struct nfs4_label * nfs4_label_init_security(struct inode *dir, struct dentry *dentry, struct iattr *sattr, struct nfs4_label *label) { + struct lsm_context shim; int err; if (label == NULL) @@ -128,18 +129,25 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry, label->label = NULL; err = security_dentry_init_security(dentry, sattr->ia_mode, - &dentry->d_name, NULL, - (void **)&label->label, &label->len); - if (err == 0) - return label; + &dentry->d_name, NULL, &shim); + if (err) + return NULL; - return NULL; + label->label = shim.context; + label->len = shim.len; + return label; } static inline void nfs4_label_release_security(struct nfs4_label *label) { - if (label) - security_release_secctx(label->label, label->len); + struct lsm_context shim; + + if (label) { + shim.context = label->label; + shim.len = label->len; + shim.id = LSM_ID_UNDEF; + security_release_secctx(&shim); + } } static inline u32 *nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label) { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0d16b383a452..5f582713bf05 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1308,7 +1308,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, enum pnfs_iomode *iomode) { /* Serialise LAYOUTGET/LAYOUTRETURN */ - if (atomic_read(&lo->plh_outstanding) != 0) + if (atomic_read(&lo->plh_outstanding) != 0 && lo->plh_return_seq == 0) return false; if (test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) return false; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ae5c5e39afa0..aeb715b4a690 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -73,6 +73,7 @@ #include "nfs.h" #include "netns.h" #include "sysfs.h" +#include "nfs4idmap.h" #define NFSDBG_FACILITY NFSDBG_VFS diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 93e33d1ee891..4dc327e02456 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -27,7 +27,7 @@ int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp) int flags = nfsexp_flags(cred, exp); /* discard any old override before preparing the new set */ - revert_creds(get_cred(current_real_cred())); + put_cred(revert_creds(get_cred(current_real_cred()))); new = prepare_creds(); if (!new) return -ENOMEM; @@ -80,7 +80,6 @@ int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp) new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); put_cred(override_creds(new)); - put_cred(new); return 0; oom: diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index eacafe46e3b6..aa4712362b3b 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -40,24 +40,15 @@ #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put_work(struct work_struct *work) +static void expkey_put(struct kref *ref) { - struct svc_expkey *key = - container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work); + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree(key); -} - -static void expkey_put(struct kref *ref) -{ - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); - - INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work); - queue_rcu_work(system_wq, &key->ek_rcu_work); + kfree_rcu(key, ek_rcu); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -364,26 +355,16 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_put_work(struct work_struct *work) +static void svc_export_put(struct kref *ref) { - struct svc_export *exp = - container_of(to_rcu_work(work), struct svc_export, ex_rcu_work); - + struct svc_export *exp = container_of(ref, struct svc_export, h.ref); path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); kfree(exp->ex_uuid); - kfree(exp); -} - -static void svc_export_put(struct kref *ref) -{ - struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - - INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work); - queue_rcu_work(system_wq, &exp->ex_rcu_work); + kfree_rcu(exp, ex_rcu); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 6f2fbaae01fa..4d92b99c1ffd 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -75,7 +75,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_work ex_rcu_work; + struct rcu_head ex_rcu; unsigned long ex_xprtsec_modes; struct export_stats *ex_stats; }; @@ -92,7 +92,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_work ek_rcu_work; + struct rcu_head ek_rcu; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index a1cdba42c4fa..dc5c9d8e8202 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1248,7 +1248,7 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, beres = nfsd_file_do_acquire(NULL, net, cred, client, fhp, may_flags, NULL, pnf, true); - revert_creds(save_cred); + put_cred(revert_creds(save_cred)); return beres; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3877b53e429f..c083e539e898 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1100,7 +1100,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -1522,8 +1522,6 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) ses = c->cn_session; } spin_unlock(&clp->cl_lock); - if (!c) - return; err = setup_callback_client(clp, &conn, ses); if (err) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f8a10f90bc7a..ad44ad49274f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1347,7 +1347,6 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; - atomic_dec(©->cp_nn->pending_async_copies); kfree(copy->cp_src); kfree(copy); } @@ -1870,6 +1869,7 @@ do_callback: set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); trace_nfsd_copy_async_done(copy); nfsd4_send_cb_offload(copy); + atomic_dec(©->cp_nn->pending_async_copies); return 0; } @@ -1927,19 +1927,19 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > (int)rqstp->rq_pool->sp_nrthreads) - goto out_err; + goto out_dec_async_copy_err; async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) - goto out_err; + goto out_dec_async_copy_err; if (!nfs4_init_copy_state(nn, copy)) - goto out_err; + goto out_dec_async_copy_err; memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) - goto out_err; + goto out_dec_async_copy_err; spin_lock(&async_copy->cp_clp->async_lock); list_add(&async_copy->copies, &async_copy->cp_clp->async_copies); @@ -1954,6 +1954,9 @@ out: trace_nfsd_copy_done(copy, status); release_copy_files(copy); return status; +out_dec_async_copy_err: + if (async_copy) + atomic_dec(&nn->pending_async_copies); out_err: if (nfsd4_ssc_is_inter(copy)) { /* diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 4a765555bf84..7f2ceeb118a4 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -82,14 +82,13 @@ nfs4_save_creds(const struct cred **original_creds) new->fsuid = GLOBAL_ROOT_UID; new->fsgid = GLOBAL_ROOT_GID; *original_creds = override_creds(new); - put_cred(new); return 0; } static void nfs4_reset_creds(const struct cred *original) { - revert_creds(original); + put_cred(revert_creds(original)); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 53fac037611c..8dd2e2ada474 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2818,11 +2818,11 @@ static __be32 nfsd4_encode_nfsace4(struct xdr_stream *xdr, struct svc_rqst *rqst #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + const struct lsm_context *context) { __be32 *p; - p = xdr_reserve_space(xdr, len + 4 + 4 + 4); + p = xdr_reserve_space(xdr, context->len + 4 + 4 + 4); if (!p) return nfserr_resource; @@ -2832,13 +2832,13 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, */ *p++ = cpu_to_be32(0); /* lfs */ *p++ = cpu_to_be32(0); /* pi */ - p = xdr_encode_opaque(p, context, len); + p = xdr_encode_opaque(p, context->context, context->len); return 0; } #else static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + struct lsm_context *context) { return 0; } #endif @@ -2920,8 +2920,7 @@ struct nfsd4_fattr_args { struct kstatfs statfs; struct nfs4_acl *acl; #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - void *context; - int contextlen; + struct lsm_context context; #endif u32 rdattr_err; bool contextsupport; @@ -3376,8 +3375,7 @@ static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, static __be32 nfsd4_encode_fattr4_sec_label(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args) { - return nfsd4_encode_security_label(xdr, args->rqstp, - args->context, args->contextlen); + return nfsd4_encode_security_label(xdr, args->rqstp, &args->context); } #endif @@ -3527,7 +3525,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.ignore_crossmnt = (ignore_crossmnt != 0); args.acl = NULL; #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - args.context = NULL; + args.context.context = NULL; #endif /* @@ -3607,7 +3605,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), - &args.context, &args.contextlen); + &args.context); else err = -EOPNOTSUPP; args.contextsupport = (err == 0); @@ -3644,8 +3642,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, out: #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (args.context) - security_release_secctx(args.context, args.contextlen); + if (args.context.context) + security_release_secctx(&args.context); #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ kfree(args.acl); if (tempfh) { diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 6a831cb242df..98d6459724a7 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -222,7 +222,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); put_cred(override_creds(new)); - put_cred(new); } else { error = nfsd_setuser_and_check_port(rqstp, cred, exp); if (error) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 501ad7be5174..54a3fa0cf67e 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode) ii->i_flags = 0; memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); + btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; } void nilfs_btnode_cache_clear(struct address_space *btnc) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index ace22253fed0..2dbb15767df1 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -163,7 +163,7 @@ int nilfs_init_gcinode(struct inode *inode) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - inode->i_mapping->a_ops = &empty_aops; + inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index cf9ba481ae37..23f3a75edd50 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -276,6 +276,10 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +const struct address_space_operations nilfs_buffer_cache_aops = { + .invalidate_folio = block_invalidate_folio, +}; + static int nilfs_insert_inode_locked(struct inode *inode, struct nilfs_root *root, unsigned long ino) @@ -544,8 +548,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, inode = nilfs_iget_locked(sb, root, ino); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + + if (!(inode->i_state & I_NEW)) { + if (!inode->i_nlink) { + iput(inode); + return ERR_PTR(-ESTALE); + } return inode; + } err = __nilfs_read_inode(sb, root, ino, inode); if (unlikely(err)) { @@ -675,6 +685,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode) NILFS_I(s_inode)->i_flags = 0; memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; err = nilfs_attach_btree_node_cache(s_inode); if (unlikely(err)) { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9b108052d9f7..1d836a5540f3 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + if (inode == ERR_PTR(-ESTALE)) { + nilfs_error(dir->i_sb, + "deleted inode referenced: %lu", ino); + return ERR_PTR(-EIO); + } } return d_splice_alias(inode, dentry); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 45d03826eaf1..dff241c53fc5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; +extern const struct address_space_operations nilfs_buffer_cache_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; extern const struct inode_operations nilfs_symlink_inode_operations; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 24c7c5df4998..95646f7c46ca 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -223,7 +223,7 @@ static int fanotify_get_response(struct fsnotify_group *group, struct fanotify_perm_event *event, struct fsnotify_iter_info *iter_info) { - int ret; + int ret, errno; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -262,14 +262,23 @@ static int fanotify_get_response(struct fsnotify_group *group, ret = 0; break; case FAN_DENY: + /* Check custom errno from pre-content events */ + errno = fanotify_get_response_errno(event->response); + if (errno) { + ret = -errno; + break; + } + fallthrough; default: ret = -EPERM; } /* Check if the response should be audited */ - if (event->response & FAN_AUDIT) - audit_fanotify(event->response & ~FAN_AUDIT, - &event->audit_rule); + if (event->response & FAN_AUDIT) { + u32 response = event->response & + (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS); + audit_fanotify(response & ~FAN_AUDIT, &event->audit_rule); + } pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__, group, event, ret); @@ -548,9 +557,13 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path, return &pevent->fae; } -static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, +static struct fanotify_event *fanotify_alloc_perm_event(const void *data, + int data_type, gfp_t gfp) { + const struct path *path = fsnotify_data_path(data, data_type); + const struct file_range *range = + fsnotify_data_file_range(data, data_type); struct fanotify_perm_event *pevent; pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp); @@ -564,6 +577,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path, pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; + /* NULL ppos means no range info */ + pevent->ppos = range ? &range->pos : NULL; + pevent->count = range ? range->count : 0; path_get(path); return &pevent->fae; @@ -801,7 +817,7 @@ static struct fanotify_event *fanotify_alloc_event( old_memcg = set_active_memcg(group->memcg); if (fanotify_is_perm_event(mask)) { - event = fanotify_alloc_perm_event(path, gfp); + event = fanotify_alloc_perm_event(data, data_type, gfp); } else if (fanotify_is_error_event(mask)) { event = fanotify_alloc_error_event(group, fsid, data, data_type, &hash); @@ -909,8 +925,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(FAN_RENAME != FS_RENAME); + BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22); mask = fanotify_group_event_mask(group, iter_info, &match_mask, mask, data, data_type, dir); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index e5ab33cae6a7..c12cbc270539 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -425,6 +425,8 @@ FANOTIFY_PE(struct fanotify_event *event) struct fanotify_perm_event { struct fanotify_event fae; struct path path; + const loff_t *ppos; /* optional file range info */ + size_t count; u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ @@ -446,6 +448,14 @@ static inline bool fanotify_is_perm_event(u32 mask) mask & FANOTIFY_PERM_EVENTS; } +static inline bool fanotify_event_has_access_range(struct fanotify_event *event) +{ + if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS)) + return false; + + return FANOTIFY_PERM(event)->ppos; +} + static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) { return container_of(fse, struct fanotify_event, fse); @@ -518,3 +528,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark) return mflags; } + +static inline u32 fanotify_get_response_errno(int res) +{ + return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK; +} diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 2d85c71717d6..6ff94e312232 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -100,8 +100,7 @@ static void __init fanotify_sysctls_init(void) * * Internal and external open flags are stored together in field f_flags of * struct file. Only external open flags shall be allowed in event_f_flags. - * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be - * excluded. + * Internal flags like FMODE_EXEC shall be excluded. */ #define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \ O_ACCMODE | O_APPEND | O_NONBLOCK | \ @@ -118,10 +117,12 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; #define FANOTIFY_EVENT_ALIGN 4 #define FANOTIFY_FID_INFO_HDR_LEN \ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) -#define FANOTIFY_PIDFD_INFO_HDR_LEN \ +#define FANOTIFY_PIDFD_INFO_LEN \ sizeof(struct fanotify_event_info_pidfd) #define FANOTIFY_ERROR_INFO_LEN \ (sizeof(struct fanotify_event_info_error)) +#define FANOTIFY_RANGE_INFO_LEN \ + (sizeof(struct fanotify_event_info_range)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -159,9 +160,6 @@ static size_t fanotify_event_len(unsigned int info_mode, int fh_len; int dot_len = 0; - if (!info_mode) - return event_len; - if (fanotify_is_error_event(event->mask)) event_len += FANOTIFY_ERROR_INFO_LEN; @@ -176,14 +174,17 @@ static size_t fanotify_event_len(unsigned int info_mode, dot_len = 1; } - if (info_mode & FAN_REPORT_PIDFD) - event_len += FANOTIFY_PIDFD_INFO_HDR_LEN; - if (fanotify_event_has_object_fh(event)) { fh_len = fanotify_event_object_fh_len(event); event_len += fanotify_fid_info_len(fh_len, dot_len); } + if (info_mode & FAN_REPORT_PIDFD) + event_len += FANOTIFY_PIDFD_INFO_LEN; + + if (fanotify_event_has_access_range(event)) + event_len += FANOTIFY_RANGE_INFO_LEN; + return event_len; } @@ -258,12 +259,11 @@ static int create_fd(struct fsnotify_group *group, const struct path *path, return client_fd; /* - * we need a new file handle for the userspace program so it can read even if it was - * originally opened O_WRONLY. + * We provide an fd for the userspace program, so it could access the + * file without generating fanotify events itself. */ - new_file = dentry_open(path, - group->fanotify_data.f_flags | __FMODE_NONOTIFY, - current_cred()); + new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags, + current_cred()); if (IS_ERR(new_file)) { put_unused_fd(client_fd); client_fd = PTR_ERR(new_file); @@ -327,11 +327,12 @@ static int process_access_response(struct fsnotify_group *group, struct fanotify_perm_event *event; int fd = response_struct->fd; u32 response = response_struct->response; + int errno = fanotify_get_response_errno(response); int ret = info_len; struct fanotify_response_info_audit_rule friar; - pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__, - group, fd, response, info, info_len); + pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n", + __func__, group, fd, response, errno, info, info_len); /* * make sure the response is valid, if invalid we do nothing and either * userspace can send a valid response or we will clean it up after the @@ -342,7 +343,31 @@ static int process_access_response(struct fsnotify_group *group, switch (response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: + if (errno) + return -EINVAL; + break; case FAN_DENY: + /* Custom errno is supported only for pre-content groups */ + if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT) + return -EINVAL; + + /* + * Limit errno to values expected on open(2)/read(2)/write(2) + * of regular files. + */ + switch (errno) { + case 0: + case EIO: + case EPERM: + case EBUSY: + case ETXTBSY: + case EAGAIN: + case ENOSPC: + case EDQUOT: + break; + default: + return -EINVAL; + } break; default: return -EINVAL; @@ -506,7 +531,7 @@ static int copy_pidfd_info_to_user(int pidfd, size_t count) { struct fanotify_event_info_pidfd info = { }; - size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN; + size_t info_len = FANOTIFY_PIDFD_INFO_LEN; if (WARN_ON_ONCE(info_len > count)) return -EFAULT; @@ -521,6 +546,30 @@ static int copy_pidfd_info_to_user(int pidfd, return info_len; } +static size_t copy_range_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_perm_event *pevent = FANOTIFY_PERM(event); + struct fanotify_event_info_range info = { }; + size_t info_len = FANOTIFY_RANGE_INFO_LEN; + + if (WARN_ON_ONCE(info_len > count)) + return -EFAULT; + + if (WARN_ON_ONCE(!pevent->ppos)) + return -EINVAL; + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE; + info.hdr.len = info_len; + info.offset = *(pevent->ppos); + info.count = pevent->count; + + if (copy_to_user(buf, &info, info_len)) + return -EFAULT; + + return info_len; +} + static int copy_info_records_to_user(struct fanotify_event *event, struct fanotify_info *info, unsigned int info_mode, int pidfd, @@ -642,6 +691,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_event_has_access_range(event)) { + ret = copy_range_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } @@ -756,12 +814,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, buf += FAN_EVENT_METADATA_LEN; count -= FAN_EVENT_METADATA_LEN; - if (info_mode) { - ret = copy_info_records_to_user(event, info, info_mode, pidfd, - buf, count); - if (ret < 0) - goto out_close_fd; - } + ret = copy_info_records_to_user(event, info, info_mode, pidfd, + buf, count); + if (ret < 0) + goto out_close_fd; if (f) fd_install(fd, f); @@ -1294,7 +1350,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group) } static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, - unsigned int fan_flags) + __u32 mask, unsigned int fan_flags) { /* * Non evictable mark cannot be downgraded to evictable mark. @@ -1321,6 +1377,11 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) return -EEXIST; + /* For now pre-content events are not generated for directories */ + mask |= fsn_mark->mask; + if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) + return -EEXIST; + return 0; } @@ -1347,7 +1408,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, /* * Check if requested mark flags conflict with an existing mark flags. */ - ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags); + ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags); if (ret) goto out; @@ -1409,6 +1470,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; unsigned int internal_flags = 0; + struct file *file; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -1477,7 +1539,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) return -EINVAL; - f_flags = O_RDWR | __FMODE_NONOTIFY; + f_flags = O_RDWR; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; if (flags & FAN_NONBLOCK) @@ -1555,10 +1617,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) goto out_destroy_group; } - fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags); + fd = get_unused_fd_flags(f_flags); if (fd < 0) goto out_destroy_group; + file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group, + f_flags, FMODE_NONOTIFY); + if (IS_ERR(file)) { + put_unused_fd(fd); + fd = PTR_ERR(file); + goto out_destroy_group; + } + fd_install(fd, file); return fd; out_destroy_group: @@ -1638,12 +1708,24 @@ static int fanotify_events_supported(struct fsnotify_group *group, unsigned int flags) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + bool is_dir = d_is_dir(path->dentry); /* Strict validation of events in non-dir inode mask with v5.17+ APIs */ bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) || (mask & FAN_RENAME) || (flags & FAN_MARK_IGNORE); /* + * Filesystems need to opt-into pre-content evnets (a.k.a HSM) + * and they are only supported on regular files and directories. + */ + if (mask & FANOTIFY_PRE_CONTENT_EVENTS) { + if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM)) + return -EOPNOTSUPP; + if (!is_dir && !d_is_reg(path->dentry)) + return -EINVAL; + } + + /* * Some filesystems such as 'proc' acquire unusual locks when opening * files. For them fanotify permission events have high chances of * deadlocking the system - open done when reporting fanotify event @@ -1675,7 +1757,7 @@ static int fanotify_events_supported(struct fsnotify_group *group, * but because we always allowed it, error only when using new APIs. */ if (strict_dir_events && mark_type == FAN_MARK_INODE && - !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) + !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) return -ENOTDIR; return 0; @@ -1776,10 +1858,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EPERM; /* - * Permission events require minimum priority FAN_CLASS_CONTENT. + * Permission events are not allowed for FAN_CLASS_NOTIF. + * Pre-content permission events are not allowed for FAN_CLASS_CONTENT. */ if (mask & FANOTIFY_PERM_EVENTS && - group->priority < FSNOTIFY_PRIO_CONTENT) + group->priority == FSNOTIFY_PRIO_NORMAL) + return -EINVAL; + else if (mask & FANOTIFY_PRE_CONTENT_EVENTS && + group->priority == FSNOTIFY_PRIO_CONTENT) return -EINVAL; if (mask & FAN_FS_ERROR && @@ -1814,6 +1900,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME)) return -EINVAL; + /* Pre-content events are not currently generated for directories. */ + if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) + return -EINVAL; + if (mark_cmd == FAN_MARK_FLUSH) { if (mark_type == FAN_MARK_MOUNT) fsnotify_clear_vfsmount_marks_by_group(group); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index dec553034027..e933f9c65d90 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -47,10 +47,8 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); - if ((ret == FILEID_INVALID) || (ret < 0)) { - WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); + if ((ret == FILEID_INVALID) || (ret < 0)) return; - } f->handle_type = ret; f->handle_bytes = size * sizeof(u32); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index f976949d2634..8ee495a58d0a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -193,7 +193,7 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, return mask & marks_mask; } -/* Are there any inode/mount/sb objects that are interested in this event? */ +/* Are there any inode/mount/sb objects that watch for these events? */ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { @@ -203,6 +203,24 @@ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } +/* Report pre-content event with optional range info */ +int fsnotify_pre_content(const struct path *path, const loff_t *ppos, + size_t count) +{ + struct file_range range; + + /* Report page aligned range only when pos is known */ + if (!ppos) + return fsnotify_path(path, FS_PRE_ACCESS); + + range.path = path; + range.pos = PAGE_ALIGN_DOWN(*ppos); + range.count = PAGE_ALIGN(*ppos + count) - range.pos; + + return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range, + FSNOTIFY_EVENT_FILE_RANGE); +} + /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with @@ -623,11 +641,72 @@ out: } EXPORT_SYMBOL_GPL(fsnotify); +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +/* + * At open time we check fsnotify_sb_has_priority_watchers() and set the + * FMODE_NONOTIFY_ mode bits accordignly. + * Later, fsnotify permission hooks do not check if there are permission event + * watches, but that there were permission event watches at open time. + */ +void file_set_fsnotify_mode(struct file *file) +{ + struct dentry *dentry = file->f_path.dentry, *parent; + struct super_block *sb = dentry->d_sb; + __u32 mnt_mask, p_mask; + + /* Is it a file opened by fanotify? */ + if (FMODE_FSNOTIFY_NONE(file->f_mode)) + return; + + /* + * Permission events is a super set of pre-content events, so if there + * are no permission event watchers, there are also no pre-content event + * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit. + */ + if (likely(!fsnotify_sb_has_priority_watchers(sb, + FSNOTIFY_PRIO_CONTENT))) { + file->f_mode |= FMODE_NONOTIFY_PERM; + return; + } + + /* + * If there are permission event watchers but no pre-content event + * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. + */ + if ((!d_is_dir(dentry) && !d_is_reg(dentry)) || + likely(!fsnotify_sb_has_priority_watchers(sb, + FSNOTIFY_PRIO_PRE_CONTENT))) { + file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; + return; + } + + /* + * OK, there are some pre-content watchers. Check if anybody is + * watching for pre-content events on *this* file. + */ + mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); + if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask, + FSNOTIFY_PRE_CONTENT_EVENTS))) + return; + + /* Is parent watching for pre-content events on this file? */ + if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { + parent = dget_parent(dentry); + p_mask = fsnotify_inode_watches_children(d_inode(parent)); + dput(parent); + if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) + return; + } + /* Nobody watching for pre-content events from this file */ + file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; +} +#endif + static __init int fsnotify_init(void) { int ret; - BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); + BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 993375f0db67..cd7d11b0eb08 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -121,7 +121,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, event->sync_cookie = cookie; event->name_len = len; if (len) - strcpy(event->name, name->name); + strscpy(event->name, name->name, event->name_len + 1); ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { diff --git a/fs/nsfs.c b/fs/nsfs.c index c675fc40ce2d..663f8656158d 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -274,10 +274,7 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (usize < MNT_NS_INFO_SIZE_VER0) return -EINVAL; - if (previous) - mnt_ns = lookup_prev_mnt_ns(to_mnt_ns(ns)); - else - mnt_ns = lookup_next_mnt_ns(to_mnt_ns(ns)); + mnt_ns = get_sequential_mnt_ns(to_mnt_ns(ns), previous); if (IS_ERR(mnt_ns)) return PTR_ERR(mnt_ns); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 213206ebdd58..7799f4d16ce9 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1065,26 +1065,39 @@ int ocfs2_find_entry(const char *name, int namelen, { struct buffer_head *bh; struct ocfs2_dir_entry *res_dir = NULL; + int ret = 0; if (ocfs2_dir_indexed(dir)) return ocfs2_find_entry_dx(name, namelen, dir, lookup); + if (unlikely(i_size_read(dir) <= 0)) { + ret = -EFSCORRUPTED; + mlog_errno(ret); + goto out; + } /* * The unindexed dir code only uses part of the lookup * structure, so there's no reason to push it down further * than this. */ - if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + if (unlikely(i_size_read(dir) > dir->i_sb->s_blocksize)) { + ret = -EFSCORRUPTED; + mlog_errno(ret); + goto out; + } bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir); - else + } else { bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir); + } if (bh == NULL) return -ENOENT; lookup->dl_leaf_bh = bh; lookup->dl_entry = res_dir; - return 0; +out: + return ret; } /* @@ -2010,6 +2023,7 @@ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, * * Return 0 if the name does not exist * Return -EEXIST if the directory contains the name + * Return -EFSCORRUPTED if found corruption * * Callers should have i_rwsem + a cluster lock on dir */ @@ -2023,9 +2037,12 @@ int ocfs2_check_dir_for_entry(struct inode *dir, trace_ocfs2_check_dir_for_entry( (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name); - if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) { + ret = ocfs2_find_entry(name, namelen, dir, &lookup); + if (ret == 0) { ret = -EEXIST; mlog_errno(ret); + } else if (ret == -ENOENT) { + ret = 0; } ocfs2_free_dir_lookup_result(&lookup); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 8ac42ea81a17..d1aa04a5af1b 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < - left) { - if (bit_off == start) { + while (1) { + bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); + if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; @@ -998,29 +998,12 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, } } + if (bit_off >= left) + break; count = 1; start = bit_off + 1; } - /* clear the contiguous bits until the end boundary */ - if (count) { - blkno = la_start_blk + - ocfs2_clusters_to_blocks(osb->sb, - start - count); - - trace_ocfs2_sync_local_to_main_free( - count, start - count, - (unsigned long long)la_start_blk, - (unsigned long long)blkno); - - status = ocfs2_release_clusters(handle, - main_bm_inode, - main_bm_bh, blkno, - count); - if (status < 0) - mlog_errno(status); - } - bail: if (status) mlog_errno(status); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2b0daced98eb..3404e7a30c33 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -893,7 +893,7 @@ static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid) int status = 0; trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type); - if (!sb_has_quota_loaded(sb, type)) { + if (!sb_has_quota_active(sb, type)) { status = -ESRCH; goto out; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 73d3367c533b..2956d888c131 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -867,6 +867,7 @@ out: brelse(oinfo->dqi_libh); brelse(oinfo->dqi_lqi_bh); kfree(oinfo); + info->dqi_priv = NULL; return status; } diff --git a/fs/open.c b/fs/open.c index e6911101fe71..0a5d2f6061c6 100644 --- a/fs/open.c +++ b/fs/open.c @@ -81,14 +81,18 @@ long vfs_truncate(const struct path *path, loff_t length) if (!S_ISREG(inode->i_mode)) return -EINVAL; - error = mnt_want_write(path->mnt); - if (error) - goto out; - idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) - goto mnt_drop_write_and_out; + return error; + + error = fsnotify_truncate_perm(path, length); + if (error) + return error; + + error = mnt_want_write(path->mnt); + if (error) + return error; error = -EPERM; if (IS_APPEND(inode)) @@ -114,7 +118,7 @@ put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); -out: + return error; } EXPORT_SYMBOL_GPL(vfs_truncate); @@ -175,11 +179,18 @@ long do_ftruncate(struct file *file, loff_t length, int small) /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; - sb_start_write(inode->i_sb); + error = security_file_truncate(file); - if (!error) - error = do_truncate(file_mnt_idmap(file), dentry, length, - ATTR_MTIME | ATTR_CTIME, file); + if (error) + return error; + + error = fsnotify_truncate_perm(&file->f_path, length); + if (error) + return error; + + sb_start_write(inode->i_sb); + error = do_truncate(file_mnt_idmap(file), dentry, length, + ATTR_MTIME | ATTR_CTIME, file); sb_end_write(inode->i_sb); return error; @@ -402,7 +413,6 @@ static bool access_need_override_creds(int flags) static const struct cred *access_override_creds(void) { - const struct cred *old_cred; struct cred *override_cred; override_cred = prepare_creds(); @@ -447,13 +457,7 @@ static const struct cred *access_override_creds(void) * freeing. */ override_cred->non_rcu = 1; - - old_cred = override_creds(override_cred); - - /* override_cred() gets its own ref */ - put_cred(override_cred); - - return old_cred; + return override_creds(override_cred); } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) @@ -523,7 +527,7 @@ out_path_release: } out: if (old_cred) - revert_creds(old_cred); + put_cred(revert_creds(old_cred)); return res; } @@ -901,7 +905,7 @@ static int do_dentry_open(struct file *f, f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { - f->f_mode = FMODE_PATH | FMODE_OPENED; + f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY; f->f_op = &empty_fops; return 0; } @@ -929,6 +933,12 @@ static int do_dentry_open(struct file *f, if (error) goto cleanup_all; + /* + * Set FMODE_NONOTIFY_* bits according to existing permission watches. + * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't + * change anything. + */ + file_set_fsnotify_mode(f); error = fsnotify_open_perm(f); if (error) goto cleanup_all; @@ -1105,6 +1115,23 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred) +{ + struct file *f = alloc_empty_file(flags, cred); + if (!IS_ERR(f)) { + int error; + + f->f_mode |= FMODE_NONOTIFY; + error = vfs_open(path, f); + if (error) { + fput(f); + f = ERR_PTR(error); + } + } + return f; +} + /** * dentry_create - Create and open a file * @path: path to create @@ -1202,7 +1229,7 @@ inline struct open_how build_open_how(int flags, umode_t mode) inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; - u64 strip = __FMODE_NONOTIFY | O_CLOEXEC; + u64 strip = O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); @@ -1210,9 +1237,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) "struct open_flags doesn't yet handle flags > 32 bits"); /* - * Strip flags that either shouldn't be set by userspace like - * FMODE_NONOTIFY or that aren't relevant in determining struct - * open_flags like O_CLOEXEC. + * Strip flags that aren't relevant in determining struct open_flags. */ flags &= ~strip; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 3601ddfeddc2..0c28e5fa3407 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -415,13 +415,13 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, return err; } -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; - uuid_t *uuid = &real->d_sb->s_uuid; + uuid_t *uuid = &realinode->i_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ @@ -438,13 +438,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, * the price or reconnecting the dentry. */ dwords = buflen >> 2; - fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); + fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid, + &dwords, NULL, 0); buflen = (dwords << 2); err = -EIO; - if (WARN_ON(fh_type < 0) || - WARN_ON(buflen > MAX_HANDLE_SZ) || - WARN_ON(fh_type == FILEID_INVALID)) + if (fh_type < 0 || fh_type == FILEID_INVALID || + WARN_ON(buflen > MAX_HANDLE_SZ)) goto out_err; fh->fb.version = OVL_FH_VERSION; @@ -480,7 +480,7 @@ struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) if (!ovl_can_decode_fh(origin->d_sb)) return NULL; - return ovl_encode_real_fh(ofs, origin, false); + return ovl_encode_real_fh(ofs, d_inode(origin), false); } int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, @@ -505,7 +505,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, upper, true); + fh = ovl_encode_real_fh(ofs, d_inode(upper), true); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 08e683917d12..c9993ff66fc2 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -575,12 +575,12 @@ static const struct cred *ovl_setup_cred_for_create(struct dentry *dentry, } /* - * Caller is going to match this with revert_creds_light() and drop + * Caller is going to match this with revert_creds() and drop * referenec on the returned creds. * We must be called with creator creds already, otherwise we risk * leaking creds. */ - old_cred = override_creds_light(override_cred); + old_cred = override_creds(override_cred); WARN_ON_ONCE(old_cred != ovl_creds(dentry->d_sb)); return override_cred; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 5868cb222955..444aeeccb6da 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -176,35 +176,37 @@ static int ovl_connect_layer(struct dentry *dentry) * * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static int ovl_check_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct inode *inode) { - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); bool decodable = ofs->config.nfs_export; + struct dentry *dentry; + int err; /* No upper layer? */ if (!ovl_upper_mnt(ofs)) return 1; /* Lower file handle for non-upper non-decodable */ - if (!ovl_dentry_upper(dentry) && !decodable) + if (!ovl_inode_upper(inode) && !decodable) return 1; /* Upper file handle for pure upper */ - if (!ovl_dentry_lower(dentry)) + if (!ovl_inode_lower(inode)) return 0; /* * Root is never indexed, so if there's an upper layer, encode upper for * root. */ - if (dentry == dentry->d_sb->s_root) + if (inode == d_inode(inode->i_sb->s_root)) return 0; /* * Upper decodable file handle for non-indexed upper. */ - if (ovl_dentry_upper(dentry) && decodable && - !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (ovl_inode_upper(inode) && decodable && + !ovl_test_flag(OVL_INDEX, inode)) return 0; /* @@ -213,14 +215,23 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && decodable) - return ovl_connect_layer(dentry); + if (!decodable || !S_ISDIR(inode->i_mode)) + return 1; + + dentry = d_find_any_alias(inode); + if (!dentry) + return -ENOENT; + + err = ovl_connect_layer(dentry); + dput(dentry); + if (err < 0) + return err; /* Lower file handle for indexed and non-upper dir/non-dir */ return 1; } -static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, +static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode, u32 *fid, int buflen) { struct ovl_fh *fh = NULL; @@ -231,13 +242,13 @@ static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, * Check if we should encode a lower or upper file handle and maybe * copy up an ancestor to make lower file handle connectable. */ - err = enc_lower = ovl_check_encode_origin(dentry); + err = enc_lower = ovl_check_encode_origin(inode); if (enc_lower < 0) goto fail; /* Encode an upper or lower file handle */ - fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_dentry_lower(dentry) : - ovl_dentry_upper(dentry), !enc_lower); + fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) : + ovl_inode_upper(inode), !enc_lower); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -251,8 +262,8 @@ out: return err; fail: - pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i)\n", - dentry, err); + pr_warn_ratelimited("failed to encode file handle (ino=%lu, err=%i)\n", + inode->i_ino, err); goto out; } @@ -260,19 +271,13 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, struct inode *parent) { struct ovl_fs *ofs = OVL_FS(inode->i_sb); - struct dentry *dentry; int bytes, buflen = *max_len << 2; /* TODO: encode connectable file handles */ if (parent) return FILEID_INVALID; - dentry = d_find_any_alias(inode); - if (!dentry) - return FILEID_INVALID; - - bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); - dput(dentry); + bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen); if (bytes <= 0) return FILEID_INVALID; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 7e27b7d4adee..cea820cb3b55 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -542,7 +542,7 @@ int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, real, is_upper); + fh = ovl_encode_real_fh(ofs, d_inode(real), is_upper); err = PTR_ERR(fh); if (IS_ERR(fh)) { fh = NULL; @@ -738,7 +738,7 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, origin, false); + fh = ovl_encode_real_fh(ofs, d_inode(origin), false); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b361f35762be..0021e2025020 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -865,7 +865,7 @@ int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 9aa7493b1e10..0819c739cc2f 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -65,12 +65,12 @@ const struct cred *ovl_override_creds(struct super_block *sb) { struct ovl_fs *ofs = OVL_FS(sb); - return override_creds_light(ofs->creator_cred); + return override_creds(ofs->creator_cred); } void ovl_revert_creds(const struct cred *old_cred) { - revert_creds_light(old_cred); + revert_creds(old_cred); } /* diff --git a/fs/pidfs.c b/fs/pidfs.c index 618abb1fa1b8..049352f973de 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/anon_inodes.h> +#include <linux/exportfs.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/cgroup.h> @@ -23,6 +24,97 @@ #include "internal.h" #include "mount.h" +static struct rb_root pidfs_ino_tree = RB_ROOT; + +#if BITS_PER_LONG == 32 +static inline unsigned long pidfs_ino(u64 ino) +{ + return lower_32_bits(ino); +} + +/* On 32 bit the generation number are the upper 32 bits. */ +static inline u32 pidfs_gen(u64 ino) +{ + return upper_32_bits(ino); +} + +#else + +/* On 64 bit simply return ino. */ +static inline unsigned long pidfs_ino(u64 ino) +{ + return ino; +} + +/* On 64 bit the generation number is 0. */ +static inline u32 pidfs_gen(u64 ino) +{ + return 0; +} +#endif + +static int pidfs_ino_cmp(struct rb_node *a, const struct rb_node *b) +{ + struct pid *pid_a = rb_entry(a, struct pid, pidfs_node); + struct pid *pid_b = rb_entry(b, struct pid, pidfs_node); + u64 pid_ino_a = pid_a->ino; + u64 pid_ino_b = pid_b->ino; + + if (pid_ino_a < pid_ino_b) + return -1; + if (pid_ino_a > pid_ino_b) + return 1; + return 0; +} + +void pidfs_add_pid(struct pid *pid) +{ + static u64 pidfs_ino_nr = 2; + + /* + * On 64 bit nothing special happens. The 64bit number assigned + * to struct pid is the inode number. + * + * On 32 bit the 64 bit number assigned to struct pid is split + * into two 32 bit numbers. The lower 32 bits are used as the + * inode number and the upper 32 bits are used as the inode + * generation number. + * + * On 32 bit pidfs_ino() will return the lower 32 bit. When + * pidfs_ino() returns zero a wrap around happened. When a + * wraparound happens the 64 bit number will be incremented by 2 + * so inode numbering starts at 2 again. + * + * On 64 bit comparing two pidfds is as simple as comparing + * inode numbers. + * + * When a wraparound happens on 32 bit multiple pidfds with the + * same inode number are likely to exist (This isn't a problem + * since before pidfs pidfds used the anonymous inode meaning + * all pidfds had the same inode number.). Userspace can + * reconstruct the 64 bit identifier by retrieving both the + * inode number and the inode generation number to compare or + * use file handles. + */ + if (pidfs_ino(pidfs_ino_nr) == 0) + pidfs_ino_nr += 2; + + pid->ino = pidfs_ino_nr; + pid->stashed = NULL; + pidfs_ino_nr++; + + write_seqcount_begin(&pidmap_lock_seq); + rb_find_add_rcu(&pid->pidfs_node, &pidfs_ino_tree, pidfs_ino_cmp); + write_seqcount_end(&pidmap_lock_seq); +} + +void pidfs_remove_pid(struct pid *pid) +{ + write_seqcount_begin(&pidmap_lock_seq); + rb_erase(&pid->pidfs_node, &pidfs_ino_tree); + write_seqcount_end(&pidmap_lock_seq); +} + #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd @@ -190,6 +282,27 @@ static long pidfd_info(struct task_struct *task, unsigned int cmd, unsigned long return 0; } +static bool pidfs_ioctl_valid(unsigned int cmd) +{ + switch (cmd) { + case FS_IOC_GETVERSION: + case PIDFD_GET_CGROUP_NAMESPACE: + case PIDFD_GET_INFO: + case PIDFD_GET_IPC_NAMESPACE: + case PIDFD_GET_MNT_NAMESPACE: + case PIDFD_GET_NET_NAMESPACE: + case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: + case PIDFD_GET_TIME_NAMESPACE: + case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: + case PIDFD_GET_UTS_NAMESPACE: + case PIDFD_GET_USER_NAMESPACE: + case PIDFD_GET_PID_NAMESPACE: + return true; + } + + return false; +} + static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct task_struct *task __free(put_task) = NULL; @@ -198,6 +311,17 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct ns_common *ns_common = NULL; struct pid_namespace *pid_ns; + if (!pidfs_ioctl_valid(cmd)) + return -ENOIOCTLCMD; + + if (cmd == FS_IOC_GETVERSION) { + if (!arg) + return -EINVAL; + + __u32 __user *argp = (__u32 __user *)arg; + return put_user(file_inode(file)->i_generation, argp); + } + task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; @@ -318,40 +442,6 @@ struct pid *pidfd_pid(const struct file *file) static struct vfsmount *pidfs_mnt __ro_after_init; -#if BITS_PER_LONG == 32 -/* - * Provide a fallback mechanism for 32-bit systems so processes remain - * reliably comparable by inode number even on those systems. - */ -static DEFINE_IDA(pidfd_inum_ida); - -static int pidfs_inum(struct pid *pid, unsigned long *ino) -{ - int ret; - - ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1, - UINT_MAX, GFP_ATOMIC); - if (ret < 0) - return -ENOSPC; - - *ino = ret; - return 0; -} - -static inline void pidfs_free_inum(unsigned long ino) -{ - if (ino > 0) - ida_free(&pidfd_inum_ida, ino); -} -#else -static inline int pidfs_inum(struct pid *pid, unsigned long *ino) -{ - *ino = pid->ino; - return 0; -} -#define pidfs_free_inum(ino) ((void)(ino)) -#endif - /* * The vfs falls back to simple_setattr() if i_op->setattr() isn't * implemented. Let's reject it completely until we have a clean @@ -403,7 +493,6 @@ static void pidfs_evict_inode(struct inode *inode) clear_inode(inode); put_pid(pid); - pidfs_free_inum(inode->i_ino); } static const struct super_operations pidfs_sops = { @@ -421,25 +510,149 @@ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) return dynamic_dname(buffer, buflen, "anon_inode:[pidfd]"); } -static const struct dentry_operations pidfs_dentry_operations = { +const struct dentry_operations pidfs_dentry_operations = { .d_delete = always_delete_dentry, .d_dname = pidfs_dname, .d_prune = stashed_dentry_prune, }; +static int pidfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, + struct inode *parent) +{ + const struct pid *pid = inode->i_private; + + if (*max_len < 2) { + *max_len = 2; + return FILEID_INVALID; + } + + *max_len = 2; + *(u64 *)fh = pid->ino; + return FILEID_KERNFS; +} + +static int pidfs_ino_find(const void *key, const struct rb_node *node) +{ + const u64 pid_ino = *(u64 *)key; + const struct pid *pid = rb_entry(node, struct pid, pidfs_node); + + if (pid_ino < pid->ino) + return -1; + if (pid_ino > pid->ino) + return 1; + return 0; +} + +/* Find a struct pid based on the inode number. */ +static struct pid *pidfs_ino_get_pid(u64 ino) +{ + struct pid *pid; + struct rb_node *node; + unsigned int seq; + + guard(rcu)(); + do { + seq = read_seqcount_begin(&pidmap_lock_seq); + node = rb_find_rcu(&ino, &pidfs_ino_tree, pidfs_ino_find); + if (node) + break; + } while (read_seqcount_retry(&pidmap_lock_seq, seq)); + + if (!node) + return NULL; + + pid = rb_entry(node, struct pid, pidfs_node); + + /* Within our pid namespace hierarchy? */ + if (pid_vnr(pid) == 0) + return NULL; + + return get_pid(pid); +} + +static struct dentry *pidfs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type) +{ + int ret; + u64 pid_ino; + struct path path; + struct pid *pid; + + if (fh_len < 2) + return NULL; + + switch (fh_type) { + case FILEID_KERNFS: + pid_ino = *(u64 *)fid; + break; + default: + return NULL; + } + + pid = pidfs_ino_get_pid(pid_ino); + if (!pid) + return NULL; + + ret = path_from_stashed(&pid->stashed, pidfs_mnt, pid, &path); + if (ret < 0) + return ERR_PTR(ret); + + mntput(path.mnt); + return path.dentry; +} + +/* + * Make sure that we reject any nonsensical flags that users pass via + * open_by_handle_at(). Note that PIDFD_THREAD is defined as O_EXCL, and + * PIDFD_NONBLOCK as O_NONBLOCK. + */ +#define VALID_FILE_HANDLE_OPEN_FLAGS \ + (O_RDONLY | O_WRONLY | O_RDWR | O_NONBLOCK | O_CLOEXEC | O_EXCL) + +static int pidfs_export_permission(struct handle_to_path_ctx *ctx, + unsigned int oflags) +{ + if (oflags & ~(VALID_FILE_HANDLE_OPEN_FLAGS | O_LARGEFILE)) + return -EINVAL; + + /* + * pidfd_ino_get_pid() will verify that the struct pid is part + * of the caller's pid namespace hierarchy. No further + * permission checks are needed. + */ + return 0; +} + +static struct file *pidfs_export_open(struct path *path, unsigned int oflags) +{ + /* + * Clear O_LARGEFILE as open_by_handle_at() forces it and raise + * O_RDWR as pidfds always are. + */ + oflags &= ~O_LARGEFILE; + return dentry_open(path, oflags | O_RDWR, current_cred()); +} + +static const struct export_operations pidfs_export_operations = { + .encode_fh = pidfs_encode_fh, + .fh_to_dentry = pidfs_fh_to_dentry, + .open = pidfs_export_open, + .permission = pidfs_export_permission, +}; + static int pidfs_init_inode(struct inode *inode, void *data) { + const struct pid *pid = data; + inode->i_private = data; inode->i_flags |= S_PRIVATE; inode->i_mode |= S_IRWXU; inode->i_op = &pidfs_inode_operations; inode->i_fop = &pidfs_file_operations; - /* - * Inode numbering for pidfs start at RESERVED_PIDS + 1. This - * avoids collisions with the root inode which is 1 for pseudo - * filesystems. - */ - return pidfs_inum(data, &inode->i_ino); + inode->i_ino = pidfs_ino(pid->ino); + inode->i_generation = pidfs_gen(pid->ino); + return 0; } static void pidfs_put_data(void *data) @@ -462,6 +675,7 @@ static int pidfs_init_fs_context(struct fs_context *fc) return -ENOMEM; ctx->ops = &pidfs_sops; + ctx->eops = &pidfs_export_operations; ctx->dops = &pidfs_dentry_operations; fc->s_fs_info = (void *)&pidfs_stashed_ops; return 0; diff --git a/fs/pipe.c b/fs/pipe.c index 12b22c2723b7..82fede0f2111 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -253,7 +253,7 @@ 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, wake_next_reader = false; + bool wake_writer = false, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ @@ -264,14 +264,13 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) mutex_lock(&pipe->mutex); /* - * We only wake up writers if the pipe was full when we started - * reading in order to avoid unnecessary wakeups. + * We only wake up writers if the pipe was full when we started reading + * and it is no longer full after reading to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ - was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); @@ -340,8 +339,10 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) buf->len = 0; } - if (!buf->len) + if (!buf->len) { + wake_writer |= pipe_full(head, tail, pipe->max_usage); tail = pipe_update_tail(pipe, buf, tail); + } total_len -= chars; if (!total_len) break; /* common path: read succeeded */ @@ -377,7 +378,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) * _very_ unlikely case that the pipe was full, but we got * no data. */ - if (unlikely(was_full)) + if (unlikely(wake_writer)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); @@ -390,15 +391,15 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; - mutex_lock(&pipe->mutex); - was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); + wake_writer = false; wake_next_reader = true; + mutex_lock(&pipe->mutex); } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); - if (was_full) + if (wake_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); diff --git a/fs/pnode.c b/fs/pnode.c index a799e0315cc9..ef048f008bdd 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -611,10 +611,10 @@ int propagate_umount(struct list_head *list) continue; } else if (child->mnt.mnt_flags & MNT_UMOUNT) { /* - * We have come accross an partially unmounted - * mount in list that has not been visited yet. - * Remember it has been visited and continue - * about our merry way. + * We have come across a partially unmounted + * mount in a list that has not been visited + * yet. Remember it has been visited and + * continue about our merry way. */ list_add_tail(&child->mnt_umounting, &visited); continue; diff --git a/fs/proc/array.c b/fs/proc/array.c index 55ed3510d2bb..d6a0369caa93 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -500,7 +500,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE|PF_POSTCOREDUMP))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e376f48c4b8b..1cb33771bf9f 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -65,7 +65,11 @@ static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt) #endif static LIST_HEAD(kclist_head); -static DECLARE_RWSEM(kclist_lock); +static int kcore_nphdr; +static size_t kcore_phdrs_len; +static size_t kcore_notes_len; +static size_t kcore_data_offset; +DEFINE_STATIC_PERCPU_RWSEM(kclist_lock); static int kcore_need_update = 1; /* @@ -101,33 +105,32 @@ void __init kclist_add(struct kcore_list *new, void *addr, size_t size, list_add_tail(&new->list, &kclist_head); } -static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len, - size_t *data_offset) +static void update_kcore_size(void) { size_t try, size; struct kcore_list *m; - *nphdr = 1; /* PT_NOTE */ + kcore_nphdr = 1; /* PT_NOTE */ size = 0; list_for_each_entry(m, &kclist_head, list) { try = kc_vaddr_to_offset((size_t)m->addr + m->size); if (try > size) size = try; - *nphdr = *nphdr + 1; + kcore_nphdr++; } - *phdrs_len = *nphdr * sizeof(struct elf_phdr); - *notes_len = (4 * sizeof(struct elf_note) + - 3 * ALIGN(sizeof(CORE_STR), 4) + - VMCOREINFO_NOTE_NAME_BYTES + - ALIGN(sizeof(struct elf_prstatus), 4) + - ALIGN(sizeof(struct elf_prpsinfo), 4) + - ALIGN(arch_task_struct_size, 4) + - ALIGN(vmcoreinfo_size, 4)); - *data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len + - *notes_len); - return *data_offset + size; + kcore_phdrs_len = kcore_nphdr * sizeof(struct elf_phdr); + kcore_notes_len = (4 * sizeof(struct elf_note) + + 3 * ALIGN(sizeof(CORE_STR), 4) + + VMCOREINFO_NOTE_NAME_BYTES + + ALIGN(sizeof(struct elf_prstatus), 4) + + ALIGN(sizeof(struct elf_prpsinfo), 4) + + ALIGN(arch_task_struct_size, 4) + + ALIGN(vmcoreinfo_size, 4)); + kcore_data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + kcore_phdrs_len + + kcore_notes_len); + proc_root_kcore->size = kcore_data_offset + size; } #ifdef CONFIG_HIGHMEM @@ -270,12 +273,10 @@ static int kcore_update_ram(void) { LIST_HEAD(list); LIST_HEAD(garbage); - int nphdr; - size_t phdrs_len, notes_len, data_offset; struct kcore_list *tmp, *pos; int ret = 0; - down_write(&kclist_lock); + percpu_down_write(&kclist_lock); if (!xchg(&kcore_need_update, 0)) goto out; @@ -293,11 +294,10 @@ static int kcore_update_ram(void) } list_splice_tail(&list, &kclist_head); - proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, ¬es_len, - &data_offset); + update_kcore_size(); out: - up_write(&kclist_lock); + percpu_up_write(&kclist_lock); list_for_each_entry_safe(pos, tmp, &garbage, list) { list_del(&pos->list); kfree(pos); @@ -326,27 +326,24 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) struct file *file = iocb->ki_filp; char *buf = file->private_data; loff_t *fpos = &iocb->ki_pos; - size_t phdrs_offset, notes_offset, data_offset; + size_t phdrs_offset, notes_offset; size_t page_offline_frozen = 1; - size_t phdrs_len, notes_len; struct kcore_list *m; size_t tsz; - int nphdr; unsigned long start; size_t buflen = iov_iter_count(iter); size_t orig_buflen = buflen; int ret = 0; - down_read(&kclist_lock); + percpu_down_read(&kclist_lock); /* * Don't race against drivers that set PageOffline() and expect no * further page access. */ page_offline_freeze(); - get_kcore_size(&nphdr, &phdrs_len, ¬es_len, &data_offset); phdrs_offset = sizeof(struct elfhdr); - notes_offset = phdrs_offset + phdrs_len; + notes_offset = phdrs_offset + kcore_phdrs_len; /* ELF file header. */ if (buflen && *fpos < sizeof(struct elfhdr)) { @@ -368,7 +365,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) .e_flags = ELF_CORE_EFLAGS, .e_ehsize = sizeof(struct elfhdr), .e_phentsize = sizeof(struct elf_phdr), - .e_phnum = nphdr, + .e_phnum = kcore_nphdr, }; tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos); @@ -382,10 +379,10 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) } /* ELF program headers. */ - if (buflen && *fpos < phdrs_offset + phdrs_len) { + if (buflen && *fpos < phdrs_offset + kcore_phdrs_len) { struct elf_phdr *phdrs, *phdr; - phdrs = kzalloc(phdrs_len, GFP_KERNEL); + phdrs = kzalloc(kcore_phdrs_len, GFP_KERNEL); if (!phdrs) { ret = -ENOMEM; goto out; @@ -393,13 +390,14 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) phdrs[0].p_type = PT_NOTE; phdrs[0].p_offset = notes_offset; - phdrs[0].p_filesz = notes_len; + phdrs[0].p_filesz = kcore_notes_len; phdr = &phdrs[1]; list_for_each_entry(m, &kclist_head, list) { phdr->p_type = PT_LOAD; phdr->p_flags = PF_R | PF_W | PF_X; - phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset; + phdr->p_offset = kc_vaddr_to_offset(m->addr) + + kcore_data_offset; phdr->p_vaddr = (size_t)m->addr; if (m->type == KCORE_RAM) phdr->p_paddr = __pa(m->addr); @@ -412,7 +410,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) phdr++; } - tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos); + tsz = min_t(size_t, buflen, + phdrs_offset + kcore_phdrs_len - *fpos); if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz, iter) != tsz) { kfree(phdrs); @@ -426,7 +425,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) } /* ELF note segment. */ - if (buflen && *fpos < notes_offset + notes_len) { + if (buflen && *fpos < notes_offset + kcore_notes_len) { struct elf_prstatus prstatus = {}; struct elf_prpsinfo prpsinfo = { .pr_sname = 'R', @@ -438,7 +437,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) strscpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs)); - notes = kzalloc(notes_len, GFP_KERNEL); + notes = kzalloc(kcore_notes_len, GFP_KERNEL); if (!notes) { ret = -ENOMEM; goto out; @@ -459,9 +458,10 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) */ append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, - min(vmcoreinfo_size, notes_len - i)); + min(vmcoreinfo_size, kcore_notes_len - i)); - tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos); + tsz = min_t(size_t, buflen, + notes_offset + kcore_notes_len - *fpos); if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) { kfree(notes); ret = -EFAULT; @@ -477,7 +477,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) * Check to see if our file offset matches with any of * the addresses in the elf_phdr on our list. */ - start = kc_offset_to_vaddr(*fpos - data_offset); + start = kc_offset_to_vaddr(*fpos - kcore_data_offset); if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen) tsz = buflen; @@ -626,7 +626,7 @@ skip: out: page_offline_thaw(); - up_read(&kclist_lock); + percpu_up_read(&kclist_lock); if (ret) return ret; return orig_buflen - buflen; @@ -663,6 +663,7 @@ static int release_kcore(struct inode *inode, struct file *file) } static const struct proc_ops kcore_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, .proc_release = release_kcore, diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 8e159fc78c0a..c610224faf10 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -83,7 +83,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) - res = readlink_copy(buffer, buflen, name); + res = readlink_copy(buffer, buflen, name, strlen(name)); } put_task_struct(task); return res; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 38a5a3e9cba2..f02cd362309a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1810,7 +1810,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } for (; addr != end; addr += PAGE_SIZE, idx++) { - unsigned long cur_flags = flags; + u64 cur_flags = flags; pagemap_entry_t pme; if (folio && (flags & PM_PRESENT) && diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 3d8a82cee63e..658bf199d424 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -404,6 +404,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) if (!iov_iter_count(iter)) return acc; } + + cond_resched(); } return acc; diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index 65b2473e22ff..fa6b8cb788a1 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -89,7 +89,7 @@ static struct pstore_device_info *pstore_device_info; _##name_ = check_size(name, alignsize); \ else \ _##name_ = 0; \ - /* Synchronize module parameters with resuls. */ \ + /* Synchronize module parameters with results. */ \ name = _##name_ / 1024; \ dev->zone.name = _##name_; \ } @@ -121,7 +121,7 @@ static int __register_pstore_device(struct pstore_device_info *dev) if (pstore_device_info) return -EBUSY; - /* zero means not limit on which backends to attempt to store. */ + /* zero means no limit on which backends attempt to store. */ if (!dev->flags) dev->flags = UINT_MAX; diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 694db616663f..ceb5639a0629 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -1212,6 +1212,11 @@ static struct pstore_zone **psz_init_zones(enum pstore_type_id type, } c = total_size / record_size; + if (unlikely(!c)) { + pr_err("zone %s total_size too small\n", name); + return ERR_PTR(-EINVAL); + } + zones = kcalloc(c, sizeof(*zones), GFP_KERNEL); if (!zones) { pr_err("allocate for zones %s failed\n", name); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 85925ec0051a..3310d1ad4d0e 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -179,8 +179,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf) */ static const char *qnx6_checkroot(struct super_block *s) { - static char match_root[2][3] = {".\0\0", "..\0"}; - int i, error = 0; + int error = 0; struct qnx6_dir_entry *dir_entry; struct inode *root = d_inode(s->s_root); struct address_space *mapping = root->i_mapping; @@ -189,11 +188,9 @@ static const char *qnx6_checkroot(struct super_block *s) if (IS_ERR(folio)) return "error reading root directory"; dir_entry = kmap_local_folio(folio, 0); - for (i = 0; i < 2; i++) { - /* maximum 3 bytes - due to match_root limitation */ - if (strncmp(dir_entry[i].de_fname, match_root[i], 3)) - error = 1; - } + if (memcmp(dir_entry[0].de_fname, ".", 2) || + memcmp(dir_entry[1].de_fname, "..", 3)) + error = 1; folio_release_kmap(folio, dir_entry); if (error) return "error reading root directory."; diff --git a/fs/select.c b/fs/select.c index e223d1fe9d55..7da531b1cf6b 100644 --- a/fs/select.c +++ b/fs/select.c @@ -786,7 +786,7 @@ static inline int get_sigset_argpack(struct sigset_argpack *to, } return 0; Efault: - user_access_end(); + user_read_access_end(); return -EFAULT; } @@ -1355,7 +1355,7 @@ static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, } return 0; Efault: - user_access_end(); + user_read_access_end(); return -EFAULT; } diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig index 2aff6d1395ce..9f05f94e265a 100644 --- a/fs/smb/client/Kconfig +++ b/fs/smb/client/Kconfig @@ -2,7 +2,6 @@ config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET - select NETFS_SUPPORT select NLS select NLS_UCS2_UTILS select CRYPTO diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 7a43daacc815..e69968e88fe7 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -315,59 +315,72 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp) return 0; } -/* Server has provided av pairs/target info in the type 2 challenge - * packet and we have plucked it and stored within smb session. - * We parse that blob here to find netbios domain name to be used - * as part of ntlmv2 authentication (in Target String), if not already - * specified on the command line. - * If this function returns without any error but without fetching - * domain name, authentication may fail against some server but - * may not fail against other (those who are not very particular - * about target string i.e. for some, just user name might suffice. +#define AV_TYPE(av) (le16_to_cpu(av->type)) +#define AV_LEN(av) (le16_to_cpu(av->length)) +#define AV_DATA_PTR(av) ((void *)av->data) + +#define av_for_each_entry(ses, av) \ + for (av = NULL; (av = find_next_av(ses, av));) + +static struct ntlmssp2_name *find_next_av(struct cifs_ses *ses, + struct ntlmssp2_name *av) +{ + u16 len; + u8 *end; + + end = (u8 *)ses->auth_key.response + ses->auth_key.len; + if (!av) { + if (unlikely(!ses->auth_key.response || !ses->auth_key.len)) + return NULL; + av = (void *)ses->auth_key.response; + } else { + av = (void *)((u8 *)av + sizeof(*av) + AV_LEN(av)); + } + + if ((u8 *)av + sizeof(*av) > end) + return NULL; + + len = AV_LEN(av); + if (AV_TYPE(av) == NTLMSSP_AV_EOL) + return NULL; + if (!len || (u8 *)av + sizeof(*av) + len > end) + return NULL; + return av; +} + +/* + * Check if server has provided av pair of @type in the NTLMSSP + * CHALLENGE_MESSAGE blob. */ -static int -find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) +static int find_av_name(struct cifs_ses *ses, u16 type, char **name, u16 maxlen) { - unsigned int attrsize; - unsigned int type; - unsigned int onesize = sizeof(struct ntlmssp2_name); - unsigned char *blobptr; - unsigned char *blobend; - struct ntlmssp2_name *attrptr; + const struct nls_table *nlsc = ses->local_nls; + struct ntlmssp2_name *av; + u16 len, nlen; - if (!ses->auth_key.len || !ses->auth_key.response) + if (*name) return 0; - blobptr = ses->auth_key.response; - blobend = blobptr + ses->auth_key.len; - - while (blobptr + onesize < blobend) { - attrptr = (struct ntlmssp2_name *) blobptr; - type = le16_to_cpu(attrptr->type); - if (type == NTLMSSP_AV_EOL) - break; - blobptr += 2; /* advance attr type */ - attrsize = le16_to_cpu(attrptr->length); - blobptr += 2; /* advance attr size */ - if (blobptr + attrsize > blobend) + av_for_each_entry(ses, av) { + len = AV_LEN(av); + if (AV_TYPE(av) != type) + continue; + if (!IS_ALIGNED(len, sizeof(__le16))) { + cifs_dbg(VFS | ONCE, "%s: bad length(%u) for type %u\n", + __func__, len, type); + continue; + } + nlen = len / sizeof(__le16); + if (nlen <= maxlen) { + ++nlen; + *name = kmalloc(nlen, GFP_KERNEL); + if (!*name) + return -ENOMEM; + cifs_from_utf16(*name, AV_DATA_PTR(av), nlen, + len, nlsc, NO_MAP_UNI_RSVD); break; - if (type == NTLMSSP_AV_NB_DOMAIN_NAME) { - if (!attrsize || attrsize >= CIFS_MAX_DOMAINNAME_LEN) - break; - if (!ses->domainName) { - ses->domainName = - kmalloc(attrsize + 1, GFP_KERNEL); - if (!ses->domainName) - return -ENOMEM; - cifs_from_utf16(ses->domainName, - (__le16 *)blobptr, attrsize, attrsize, - nls_cp, NO_MAP_UNI_RSVD); - break; - } } - blobptr += attrsize; /* advance attr value */ } - return 0; } @@ -377,40 +390,16 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) * as part of ntlmv2 authentication (or local current time as * default in case of failure) */ -static __le64 -find_timestamp(struct cifs_ses *ses) +static __le64 find_timestamp(struct cifs_ses *ses) { - unsigned int attrsize; - unsigned int type; - unsigned int onesize = sizeof(struct ntlmssp2_name); - unsigned char *blobptr; - unsigned char *blobend; - struct ntlmssp2_name *attrptr; + struct ntlmssp2_name *av; struct timespec64 ts; - if (!ses->auth_key.len || !ses->auth_key.response) - return 0; - - blobptr = ses->auth_key.response; - blobend = blobptr + ses->auth_key.len; - - while (blobptr + onesize < blobend) { - attrptr = (struct ntlmssp2_name *) blobptr; - type = le16_to_cpu(attrptr->type); - if (type == NTLMSSP_AV_EOL) - break; - blobptr += 2; /* advance attr type */ - attrsize = le16_to_cpu(attrptr->length); - blobptr += 2; /* advance attr size */ - if (blobptr + attrsize > blobend) - break; - if (type == NTLMSSP_AV_TIMESTAMP) { - if (attrsize == sizeof(u64)) - return *((__le64 *)blobptr); - } - blobptr += attrsize; /* advance attr value */ + av_for_each_entry(ses, av) { + if (AV_TYPE(av) == NTLMSSP_AV_TIMESTAMP && + AV_LEN(av) == sizeof(u64)) + return *((__le64 *)AV_DATA_PTR(av)); } - ktime_get_real_ts64(&ts); return cpu_to_le64(cifs_UnixTimeToNT(ts)); } @@ -563,16 +552,29 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) { if (!ses->domainName) { if (ses->domainAuto) { - rc = find_domain_name(ses, nls_cp); - if (rc) { - cifs_dbg(VFS, "error %d finding domain name\n", - rc); + /* + * Domain (workgroup) hasn't been specified in + * mount options, so try to find it in + * CHALLENGE_MESSAGE message and then use it as + * part of NTLMv2 authentication. + */ + rc = find_av_name(ses, NTLMSSP_AV_NB_DOMAIN_NAME, + &ses->domainName, + CIFS_MAX_DOMAINNAME_LEN); + if (rc) goto setup_ntlmv2_rsp_ret; - } } else { ses->domainName = kstrdup("", GFP_KERNEL); + if (!ses->domainName) { + rc = -ENOMEM; + goto setup_ntlmv2_rsp_ret; + } } } + rc = find_av_name(ses, NTLMSSP_AV_DNS_DOMAIN_NAME, + &ses->dns_dom, CIFS_MAX_DOMAINNAME_LEN); + if (rc) + goto setup_ntlmv2_rsp_ret; } else { rc = build_avpair_blob(ses, nls_cp); if (rc) { diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index c9f9b6e97964..b800c9f585d8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -398,7 +398,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode = alloc_inode_sb(sb, cifs_inode_cachep, GFP_KERNEL); if (!cifs_inode) return NULL; - cifs_inode->cifsAttrs = 0x20; /* default */ + cifs_inode->cifsAttrs = ATTR_ARCHIVE; /* default */ cifs_inode->time = 0; /* * Until the file is open and we have gotten oplock info back from the @@ -2043,6 +2043,7 @@ exit_cifs(void) destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); destroy_workqueue(serverclose_wq); + destroy_workqueue(cfid_put_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 6e63abe461fd..49ffc040f736 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -811,23 +811,15 @@ struct TCP_Server_Info { bool use_swn_dstaddr; struct sockaddr_storage swn_dstaddr; #endif - struct mutex refpath_lock; /* protects leaf_fullpath */ /* - * leaf_fullpath: Canonical DFS referral path related to this - * connection. - * It is used in DFS cache refresher, reconnect and may - * change due to nested DFS links. - * - * Protected by @refpath_lock and @srv_lock. The @refpath_lock is - * mostly used for not requiring a copy of @leaf_fullpath when getting - * cached or new DFS referrals (which might also sleep during I/O). - * While @srv_lock is held for making string and NULL comparisons against - * both fields as in mount(2) and cache refresh. + * Canonical DFS referral path used in cifs_reconnect() for failover as + * well as in DFS cache refresher. * * format: \\HOST\SHARE[\OPTIONAL PATH] */ char *leaf_fullpath; bool dfs_conn:1; + char dns_dom[CIFS_MAX_DOMAINNAME_LEN + 1]; }; static inline bool is_smb1(struct TCP_Server_Info *server) @@ -1154,6 +1146,7 @@ struct cifs_ses { /* ========= end: protected by chan_lock ======== */ struct cifs_ses *dfs_root_ses; struct nls_table *local_nls; + char *dns_dom; /* FQDN of the domain */ }; static inline bool @@ -2311,4 +2304,24 @@ static inline bool cifs_ses_exiting(struct cifs_ses *ses) return ret; } +static inline bool cifs_netbios_name(const char *name, size_t namelen) +{ + bool ret = false; + size_t i; + + if (namelen >= 1 && namelen <= RFC1001_NAME_LEN) { + for (i = 0; i < namelen; i++) { + const unsigned char c = name[i]; + + if (c == '\\' || c == '/' || c == ':' || c == '*' || + c == '?' || c == '"' || c == '<' || c == '>' || + c == '|' || c == '.') + return false; + if (!ret && isalpha(c)) + ret = true; + } + } + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index ee78bb6741d6..5c047b00516f 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -649,7 +649,7 @@ typedef union smb_com_session_setup_andx { struct ntlmssp2_name { __le16 type; __le16 length; -/* char name[length]; */ + __u8 data[]; } __attribute__((packed)); struct ntlmv2_resp { @@ -1484,22 +1484,6 @@ struct file_notify_information { __u8 FileName[]; } __attribute__((packed)); -/* For IO_REPARSE_TAG_SYMLINK */ -struct reparse_symlink_data { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __le16 SubstituteNameOffset; - __le16 SubstituteNameLength; - __le16 PrintNameOffset; - __le16 PrintNameLength; - __le32 Flags; - char PathBuffer[]; -} __attribute__((packed)); - -/* Flag above */ -#define SYMLINK_FLAG_RELATIVE 0x00000001 - /* For IO_REPARSE_TAG_NFS */ #define NFS_SPECFILE_LNK 0x00000000014B4E4C #define NFS_SPECFILE_CHR 0x0000000000524843 diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 754417cb3294..223e5e231f42 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -474,9 +474,6 @@ extern int cifs_query_reparse_point(const unsigned int xid, const char *full_path, u32 *tag, struct kvec *rsp, int *rsp_buftype); -extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, - __u16 fid, char **symlinkinfo, - const struct nls_table *nls_codepage); extern int CIFSSMB_set_compression(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid); extern int CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, @@ -614,8 +611,6 @@ int cifs_alloc_hash(const char *name, struct shash_desc **sdesc); void cifs_free_hash(struct shash_desc **sdesc); int cifs_try_adding_channels(struct cifs_ses *ses); -bool is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface); bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); void cifs_ses_mark_for_reconnect(struct cifs_ses *ses); @@ -682,7 +677,7 @@ static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses, } int match_target_ip(struct TCP_Server_Info *server, - const char *share, size_t share_len, + const char *host, size_t hostlen, bool *result); int cifs_inval_name_dfs_link_error(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index bd42a419458e..7f1cacc89dbb 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -152,8 +152,17 @@ again: spin_unlock(&ses->ses_lock); rc = cifs_negotiate_protocol(0, ses, server); - if (!rc) + if (!rc) { rc = cifs_setup_session(0, ses, server, ses->local_nls); + if ((rc == -EACCES) || (rc == -EHOSTDOWN) || (rc == -EKEYREVOKED)) { + /* + * Try alternate password for next reconnect if an alternate + * password is available. + */ + if (ses->password2) + swap(ses->password2, ses->password); + } + } /* do we need to reconnect tcon? */ if (rc || !tcon->need_reconnect) { @@ -1258,14 +1267,6 @@ openRetry: return rc; } -static void cifs_readv_worker(struct work_struct *work) -{ - struct cifs_io_subrequest *rdata = - container_of(work, struct cifs_io_subrequest, subreq.work); - - netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); -} - static void cifs_readv_callback(struct mid_q_entry *mid) { @@ -1319,20 +1320,24 @@ cifs_readv_callback(struct mid_q_entry *mid) } if (rdata->result == -ENODATA) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && rdata->subreq.start + trans == ictx->remote_i_size) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + } else if (rdata->got_bytes > 0) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } + if (rdata->got_bytes) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } rdata->credits.value = 0; + rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; - INIT_WORK(&rdata->subreq.work, cifs_readv_worker); queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); add_credits(server, &credits, 0); @@ -1670,10 +1675,13 @@ cifs_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + if (written < wdata->subreq.len) { result = -ENOSPC; - else + } else { result = written; + if (written > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 2372538a1211..880d7cf8b730 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -72,10 +72,8 @@ static void cifs_prune_tlinks(struct work_struct *work); */ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) { - int rc; - int len; - char *unc; struct sockaddr_storage ss; + int rc; if (!server->hostname) return -EINVAL; @@ -84,32 +82,18 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) if (server->hostname[0] == '\0') return 0; - len = strlen(server->hostname) + 3; - - unc = kmalloc(len, GFP_KERNEL); - if (!unc) { - cifs_dbg(FYI, "%s: failed to create UNC path\n", __func__); - return -ENOMEM; - } - scnprintf(unc, len, "\\\\%s", server->hostname); - spin_lock(&server->srv_lock); ss = server->dstaddr; spin_unlock(&server->srv_lock); - rc = dns_resolve_server_name_to_ip(unc, (struct sockaddr *)&ss, NULL); - kfree(unc); - - if (rc < 0) { - cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n", - __func__, server->hostname, rc); - } else { + rc = dns_resolve_name(server->dns_dom, server->hostname, + strlen(server->hostname), + (struct sockaddr *)&ss); + if (!rc) { spin_lock(&server->srv_lock); memcpy(&server->dstaddr, &ss, sizeof(server->dstaddr)); spin_unlock(&server->srv_lock); - rc = 0; } - return rc; } @@ -438,7 +422,8 @@ static int __cifs_reconnect(struct TCP_Server_Info *server, } #ifdef CONFIG_CIFS_DFS_UPCALL -static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const char *target) +static int __reconnect_target_locked(struct TCP_Server_Info *server, + const char *target) { int rc; char *hostname; @@ -471,34 +456,43 @@ static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const cha return rc; } -static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_cache_tgt_list *tl, - struct dfs_cache_tgt_iterator **target_hint) +static int reconnect_target_locked(struct TCP_Server_Info *server, + struct dfs_cache_tgt_list *tl, + struct dfs_cache_tgt_iterator **target_hint) { - int rc; struct dfs_cache_tgt_iterator *tit; + int rc; *target_hint = NULL; /* If dfs target list is empty, then reconnect to last server */ tit = dfs_cache_get_tgt_iterator(tl); if (!tit) - return __reconnect_target_unlocked(server, server->hostname); + return __reconnect_target_locked(server, server->hostname); /* Otherwise, try every dfs target in @tl */ - for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) { - rc = __reconnect_target_unlocked(server, dfs_cache_get_tgt_name(tit)); + do { + const char *target = dfs_cache_get_tgt_name(tit); + + spin_lock(&server->srv_lock); + if (server->tcpStatus != CifsNeedReconnect) { + spin_unlock(&server->srv_lock); + return -ECONNRESET; + } + spin_unlock(&server->srv_lock); + rc = __reconnect_target_locked(server, target); if (!rc) { *target_hint = tit; break; } - } + } while ((tit = dfs_cache_get_next_tgt(tl, tit))); return rc; } static int reconnect_dfs_server(struct TCP_Server_Info *server) { struct dfs_cache_tgt_iterator *target_hint = NULL; - + const char *ref_path = server->leaf_fullpath + 1; DFS_CACHE_TGT_LIST(tl); int num_targets = 0; int rc = 0; @@ -511,10 +505,8 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) * through /proc/fs/cifs/dfscache or the target list is empty due to server settings after * refreshing the referral, so, in this case, default it to 1. */ - mutex_lock(&server->refpath_lock); - if (!dfs_cache_noreq_find(server->leaf_fullpath + 1, NULL, &tl)) + if (!dfs_cache_noreq_find(ref_path, NULL, &tl)) num_targets = dfs_cache_get_nr_tgts(&tl); - mutex_unlock(&server->refpath_lock); if (!num_targets) num_targets = 1; @@ -534,7 +526,7 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) try_to_freeze(); cifs_server_lock(server); - rc = reconnect_target_unlocked(server, &tl, &target_hint); + rc = reconnect_target_locked(server, &tl, &target_hint); if (rc) { /* Failed to reconnect socket */ cifs_server_unlock(server); @@ -558,9 +550,7 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) mod_delayed_work(cifsiod_wq, &server->reconnect, 0); } while (server->tcpStatus == CifsNeedReconnect); - mutex_lock(&server->refpath_lock); - dfs_cache_noreq_update_tgthint(server->leaf_fullpath + 1, target_hint); - mutex_unlock(&server->refpath_lock); + dfs_cache_noreq_update_tgthint(ref_path, target_hint); dfs_cache_free_tgts(&tl); /* Need to set up echo worker again once connection has been established */ @@ -575,13 +565,8 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { - mutex_lock(&server->refpath_lock); - if (!server->leaf_fullpath) { - mutex_unlock(&server->refpath_lock); + if (!server->leaf_fullpath) return __cifs_reconnect(server, mark_smb_session); - } - mutex_unlock(&server->refpath_lock); - return reconnect_dfs_server(server); } #else @@ -987,9 +972,13 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); + if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; + + /* Release netns reference for the socket. */ + put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1037,8 +1026,10 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } + /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); + kfree(server->hostname); kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -1535,42 +1526,10 @@ static int match_server(struct TCP_Server_Info *server, if (!cifs_match_ipaddr((struct sockaddr *)&ctx->srcaddr, (struct sockaddr *)&server->srcaddr)) return 0; - /* - * When matching cifs.ko superblocks (@match_super == true), we can't - * really match either @server->leaf_fullpath or @server->dstaddr - * directly since this @server might belong to a completely different - * server -- in case of domain-based DFS referrals or DFS links -- as - * provided earlier by mount(2) through 'source' and 'ip' options. - * - * Otherwise, match the DFS referral in @server->leaf_fullpath or the - * destination address in @server->dstaddr. - * - * When using 'nodfs' mount option, we avoid sharing it with DFS - * connections as they might failover. - */ - if (!match_super) { - if (!ctx->nodfs) { - if (server->leaf_fullpath) { - if (!ctx->leaf_fullpath || - strcasecmp(server->leaf_fullpath, - ctx->leaf_fullpath)) - return 0; - } else if (ctx->leaf_fullpath) { - return 0; - } - } else if (server->leaf_fullpath) { - return 0; - } - } - /* - * Match for a regular connection (address/hostname/port) which has no - * DFS referrals set. - */ - if (!server->leaf_fullpath && - (strcasecmp(server->hostname, ctx->server_hostname) || - !match_server_address(server, addr) || - !match_port(server, addr))) + if (strcasecmp(server->hostname, ctx->server_hostname) || + !match_server_address(server, addr) || + !match_port(server, addr)) return 0; if (!match_security(server, ctx)) @@ -1665,8 +1624,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) kfree_sensitive(server->session_key.response); server->session_key.response = NULL; server->session_key.len = 0; - kfree(server->hostname); - server->hostname = NULL; task = xchg(&server->tsk, NULL); if (task) @@ -1706,6 +1663,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, goto out_err; } } + if (ctx->dns_dom) + strscpy(tcp_ses->dns_dom, ctx->dns_dom); if (ctx->nosharesock) tcp_ses->nosharesock = true; @@ -1713,6 +1672,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; + + /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId); @@ -1752,9 +1713,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); -#ifdef CONFIG_CIFS_DFS_UPCALL - mutex_init(&tcp_ses->refpath_lock); -#endif memcpy(&tcp_ses->srcaddr, &ctx->srcaddr, sizeof(tcp_ses->srcaddr)); memcpy(&tcp_ses->dstaddr, &ctx->dstaddr, @@ -1844,6 +1802,7 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); + /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1852,8 +1811,10 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) + if (tcp_ses->ssocket) { sock_release(tcp_ses->ssocket); + put_net(cifs_net_ns(tcp_ses)); + } kfree(tcp_ses); } return ERR_PTR(rc); @@ -2267,12 +2228,13 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx __attribute__((unused)), struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { - int rc = 0; - int retries = 0; - unsigned int xid; - struct cifs_ses *ses; - struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr; + struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; + struct cifs_ses *ses; + unsigned int xid; + int retries = 0; + size_t len; + int rc = 0; xid = get_xid(); @@ -2362,6 +2324,14 @@ retry_old_session: ses->domainName = kstrdup(ctx->domainname, GFP_KERNEL); if (!ses->domainName) goto get_ses_fail; + + len = strnlen(ctx->domainname, CIFS_MAX_DOMAINNAME_LEN); + if (!cifs_netbios_name(ctx->domainname, len)) { + ses->dns_dom = kstrndup(ctx->domainname, + len, GFP_KERNEL); + if (!ses->dns_dom) + goto get_ses_fail; + } } strscpy(ses->workstation_name, ctx->workstation_name, sizeof(ses->workstation_name)); @@ -3131,20 +3101,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); - struct sock *sk; - rc = __sock_create(net, sfamily, SOCK_STREAM, - IPPROTO_TCP, &server->ssocket, 1); + rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - sk = server->ssocket->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + /* + * Grab netns reference for the socket. + * + * It'll be released here, on error, or in clean_demultiplex_info() upon server + * teardown. + */ + get_net(net); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3158,8 +3128,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) + if (rc < 0) { + put_net(cifs_net_ns(server)); return rc; + } /* * Eventually check for other socket options to change from @@ -3196,6 +3168,7 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); + put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; @@ -3204,6 +3177,9 @@ generic_ip_connect(struct TCP_Server_Info *server) if (sport == htons(RFC1001_PORT)) rc = ip_rfc1001_connect(server); + if (rc < 0) + put_net(cifs_net_ns(server)); + return rc; } diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 4647df9e1e3b..dad521336b5e 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -9,6 +9,8 @@ #include "fs_context.h" #include "dfs.h" +#define DFS_DOM(ctx) (ctx->dfs_root_ses ? ctx->dfs_root_ses->dns_dom : NULL) + /** * dfs_parse_target_referral - set fs context for dfs target referral * @@ -46,8 +48,8 @@ int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_para if (rc) goto out; - rc = dns_resolve_server_name_to_ip(path, (struct sockaddr *)&ctx->dstaddr, NULL); - + rc = dns_resolve_unc(DFS_DOM(ctx), path, + (struct sockaddr *)&ctx->dstaddr); out: kfree(path); return rc; @@ -59,8 +61,9 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) int rc; ctx->leaf_fullpath = (char *)full_path; + ctx->dns_dom = DFS_DOM(ctx); rc = cifs_mount_get_session(mnt_ctx); - ctx->leaf_fullpath = NULL; + ctx->leaf_fullpath = ctx->dns_dom = NULL; return rc; } @@ -95,15 +98,16 @@ static inline int parse_dfs_target(struct smb3_fs_context *ctx, return rc; } -static int setup_dfs_ref(struct cifs_mount_ctx *mnt_ctx, - struct dfs_info3_param *tgt, - struct dfs_ref_walk *rw) +static int setup_dfs_ref(struct dfs_info3_param *tgt, struct dfs_ref_walk *rw) { - struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct cifs_sb_info *cifs_sb = rw->mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = rw->mnt_ctx->fs_ctx; char *ref_path, *full_path; int rc; + set_root_smb_session(rw->mnt_ctx); + ref_walk_ses(rw) = ctx->dfs_root_ses; + full_path = smb3_fs_context_fullpath(ctx, CIFS_DIR_SEP(cifs_sb)); if (IS_ERR(full_path)) return PTR_ERR(full_path); @@ -120,35 +124,22 @@ static int setup_dfs_ref(struct cifs_mount_ctx *mnt_ctx, } ref_walk_path(rw) = ref_path; ref_walk_fpath(rw) = full_path; - ref_walk_ses(rw) = ctx->dfs_root_ses; - return 0; + + return dfs_get_referral(rw->mnt_ctx, + ref_walk_path(rw) + 1, + ref_walk_tl(rw)); } -static int __dfs_referral_walk(struct cifs_mount_ctx *mnt_ctx, - struct dfs_ref_walk *rw) +static int __dfs_referral_walk(struct dfs_ref_walk *rw) { - struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct smb3_fs_context *ctx = rw->mnt_ctx->fs_ctx; + struct cifs_mount_ctx *mnt_ctx = rw->mnt_ctx; struct dfs_info3_param tgt = {}; int rc = -ENOENT; again: do { ctx->dfs_root_ses = ref_walk_ses(rw); - if (ref_walk_empty(rw)) { - rc = dfs_get_referral(mnt_ctx, ref_walk_path(rw) + 1, - NULL, ref_walk_tl(rw)); - if (rc) { - rc = cifs_mount_get_tcon(mnt_ctx); - if (!rc) - rc = cifs_is_path_remote(mnt_ctx); - continue; - } - if (!ref_walk_num_tgts(rw)) { - rc = -ENOENT; - continue; - } - } - while (ref_walk_next_tgt(rw)) { rc = parse_dfs_target(ctx, rw, &tgt); if (rc) @@ -159,32 +150,29 @@ again: if (rc) continue; - ref_walk_set_tgt_hint(rw); if (tgt.flags & DFSREF_STORAGE_SERVER) { rc = cifs_mount_get_tcon(mnt_ctx); if (!rc) rc = cifs_is_path_remote(mnt_ctx); - if (!rc) + if (!rc) { + ref_walk_set_tgt_hint(rw); break; + } if (rc != -EREMOTE) continue; } - set_root_smb_session(mnt_ctx); rc = ref_walk_advance(rw); if (!rc) { - rc = setup_dfs_ref(mnt_ctx, &tgt, rw); - if (!rc) { - rc = -EREMOTE; - goto again; - } + rc = setup_dfs_ref(&tgt, rw); + if (rc) + break; + ref_walk_mark_end(rw); + goto again; } - if (rc != -ELOOP) - goto out; } } while (rc && ref_walk_descend(rw)); -out: free_dfs_info_param(&tgt); return rc; } @@ -201,10 +189,10 @@ static int dfs_referral_walk(struct cifs_mount_ctx *mnt_ctx, return rc; } - ref_walk_init(*rw); - rc = setup_dfs_ref(mnt_ctx, NULL, *rw); + ref_walk_init(*rw, mnt_ctx); + rc = setup_dfs_ref(NULL, *rw); if (!rc) - rc = __dfs_referral_walk(mnt_ctx, *rw); + rc = __dfs_referral_walk(*rw); return rc; } @@ -264,7 +252,7 @@ static int update_fs_context_dstaddr(struct smb3_fs_context *ctx) int rc = 0; if (!ctx->nodfs && ctx->dfs_automount) { - rc = dns_resolve_server_name_to_ip(ctx->source, addr, NULL); + rc = dns_resolve_unc(NULL, ctx->source, addr); if (!rc) cifs_set_port(addr, ctx->port); ctx->dfs_automount = false; @@ -294,7 +282,7 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) * to respond with PATH_NOT_COVERED to requests that include the prefix. */ if (!nodfs) { - rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL, NULL); + rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL); if (rc) { cifs_dbg(FYI, "%s: no dfs referral for %s: %d\n", __func__, ctx->UNC + 1, rc); @@ -314,10 +302,8 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) cifs_mount_put_conns(mnt_ctx); rc = get_session(mnt_ctx, NULL); } - if (!rc) { - set_root_smb_session(mnt_ctx); + if (!rc) rc = __dfs_mount_share(mnt_ctx); - } return rc; } diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index 1aa2bc65b3bc..ed4cd7cf1ec6 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -12,6 +12,7 @@ #include "dfs_cache.h" #include "cifs_unicode.h" #include <linux/namei.h> +#include <linux/errno.h> #define DFS_INTERLINK(v) \ (((v) & DFSREF_REFERRAL_SERVER) && !((v) & DFSREF_STORAGE_SERVER)) @@ -25,8 +26,9 @@ struct dfs_ref { }; struct dfs_ref_walk { - struct dfs_ref *ref; - struct dfs_ref refs[MAX_NESTED_LINKS]; + struct cifs_mount_ctx *mnt_ctx; + struct dfs_ref *ref; + struct dfs_ref refs[MAX_NESTED_LINKS]; }; #define ref_walk_start(w) ((w)->refs) @@ -35,7 +37,6 @@ struct dfs_ref_walk { #define ref_walk_descend(w) (--ref_walk_cur(w) >= ref_walk_start(w)) #define ref_walk_tit(w) (ref_walk_cur(w)->tit) -#define ref_walk_empty(w) (!ref_walk_tit(w)) #define ref_walk_path(w) (ref_walk_cur(w)->path) #define ref_walk_fpath(w) (ref_walk_cur(w)->full_path) #define ref_walk_tl(w) (&ref_walk_cur(w)->tl) @@ -51,9 +52,11 @@ static inline struct dfs_ref_walk *ref_walk_alloc(void) return rw; } -static inline void ref_walk_init(struct dfs_ref_walk *rw) +static inline void ref_walk_init(struct dfs_ref_walk *rw, + struct cifs_mount_ctx *mnt_ctx) { memset(rw, 0, sizeof(*rw)); + rw->mnt_ctx = mnt_ctx; ref_walk_cur(rw) = ref_walk_start(rw); } @@ -93,15 +96,23 @@ static inline int ref_walk_advance(struct dfs_ref_walk *rw) static inline struct dfs_cache_tgt_iterator * ref_walk_next_tgt(struct dfs_ref_walk *rw) { - struct dfs_cache_tgt_iterator *tit; struct dfs_ref *ref = ref_walk_cur(rw); + struct dfs_cache_tgt_iterator *tit; + + if (IS_ERR(ref->tit)) + return NULL; if (!ref->tit) tit = dfs_cache_get_tgt_iterator(&ref->tl); else tit = dfs_cache_get_next_tgt(&ref->tl, ref->tit); + + if (!tit) { + ref->tit = ERR_PTR(-ENOENT); + return NULL; + } ref->tit = tit; - return tit; + return ref->tit; } static inline int ref_walk_get_tgt(struct dfs_ref_walk *rw, @@ -112,11 +123,6 @@ static inline int ref_walk_get_tgt(struct dfs_ref_walk *rw, ref_walk_tit(rw), tgt); } -static inline int ref_walk_num_tgts(struct dfs_ref_walk *rw) -{ - return dfs_cache_get_nr_tgts(ref_walk_tl(rw)); -} - static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw) { dfs_cache_noreq_update_tgthint(ref_walk_path(rw) + 1, @@ -136,6 +142,15 @@ static inline void ref_walk_set_tcon(struct dfs_ref_walk *rw, } } +static inline void ref_walk_mark_end(struct dfs_ref_walk *rw) +{ + struct dfs_ref *ref = ref_walk_cur(rw) - 1; + + WARN_ON_ONCE(ref < ref_walk_start(rw)); + dfs_cache_noreq_update_tgthint(ref->path + 1, ref->tit); + ref->tit = ERR_PTR(-ENOENT); /* end marker */ +} + int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx); @@ -145,15 +160,16 @@ static inline char *dfs_get_path(struct cifs_sb_info *cifs_sb, const char *path) return dfs_cache_canonical_path(path, cifs_sb->local_nls, cifs_remap(cifs_sb)); } -static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *path, - struct dfs_info3_param *ref, struct dfs_cache_tgt_list *tl) +static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, + const char *path, + struct dfs_cache_tgt_list *tl) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses; return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls, - cifs_remap(cifs_sb), path, ref, tl); + cifs_remap(cifs_sb), path, NULL, tl); } /* diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 541608b0267e..5022bb1f122a 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1096,11 +1096,8 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, static bool target_share_equal(struct cifs_tcon *tcon, const char *s1) { struct TCP_Server_Info *server = tcon->ses->server; - struct sockaddr_storage ss; - const char *host; const char *s2 = &tcon->tree_name[1]; - size_t hostlen; - char unc[sizeof("\\\\") + SERVER_NAME_LENGTH] = {0}; + struct sockaddr_storage ss; bool match; int rc; @@ -1111,18 +1108,13 @@ static bool target_share_equal(struct cifs_tcon *tcon, const char *s1) * Resolve share's hostname and check if server address matches. Otherwise just ignore it * as we could not have upcall to resolve hostname or failed to convert ip address. */ - extract_unc_hostname(s1, &host, &hostlen); - scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host); - - rc = dns_resolve_server_name_to_ip(unc, (struct sockaddr *)&ss, NULL); - if (rc < 0) { - cifs_dbg(FYI, "%s: could not resolve %.*s. assuming server address matches.\n", - __func__, (int)hostlen, host); + rc = dns_resolve_unc(server->dns_dom, s1, (struct sockaddr *)&ss); + if (rc < 0) return true; - } cifs_server_lock(server); match = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss); + cifs_dbg(FYI, "%s: [share=%s] ipaddr matched: %s\n", __func__, s1, str_yes_no(match)); cifs_server_unlock(server); return match; @@ -1149,13 +1141,11 @@ static char *get_ses_refpath(struct cifs_ses *ses) struct TCP_Server_Info *server = ses->server; char *path = ERR_PTR(-ENOENT); - mutex_lock(&server->refpath_lock); if (server->leaf_fullpath) { - path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC); + path = kstrdup(server->leaf_fullpath + 1, GFP_KERNEL); if (!path) path = ERR_PTR(-ENOMEM); } - mutex_unlock(&server->refpath_lock); return path; } diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 864b194dbaa0..1822493dd084 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -627,7 +627,7 @@ int cifs_mknod(struct mnt_idmap *idmap, struct inode *inode, goto mknod_out; } - trace_smb3_mknod_enter(xid, tcon->ses->Suid, tcon->tid, full_path); + trace_smb3_mknod_enter(xid, tcon->tid, tcon->ses->Suid, full_path); rc = tcon->ses->server->ops->make_node(xid, inode, direntry, tcon, full_path, mode, @@ -635,9 +635,9 @@ int cifs_mknod(struct mnt_idmap *idmap, struct inode *inode, mknod_out: if (rc) - trace_smb3_mknod_err(xid, tcon->ses->Suid, tcon->tid, rc); + trace_smb3_mknod_err(xid, tcon->tid, tcon->ses->Suid, rc); else - trace_smb3_mknod_done(xid, tcon->ses->Suid, tcon->tid); + trace_smb3_mknod_done(xid, tcon->tid, tcon->ses->Suid); free_dentry_path(page); free_xid(xid); diff --git a/fs/smb/client/dns_resolve.c b/fs/smb/client/dns_resolve.c index 8bf8978bc5d6..de7f4b384718 100644 --- a/fs/smb/client/dns_resolve.c +++ b/fs/smb/client/dns_resolve.c @@ -20,69 +20,77 @@ #include "cifsproto.h" #include "cifs_debug.h" -/** - * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address. - * @unc: UNC path specifying the server (with '/' as delimiter) - * @ip_addr: Where to return the IP address. - * @expiry: Where to return the expiry time for the dns record. - * - * Returns zero success, -ve on error. - */ -int -dns_resolve_server_name_to_ip(const char *unc, struct sockaddr *ip_addr, time64_t *expiry) +static int resolve_name(const char *name, size_t namelen, struct sockaddr *addr) { - const char *hostname, *sep; char *ip; - int len, rc; + int rc; - if (!ip_addr || !unc) - return -EINVAL; + rc = dns_query(current->nsproxy->net_ns, NULL, name, + namelen, NULL, &ip, NULL, false); + if (rc < 0) { + cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", + __func__, (int)namelen, (int)namelen, name); + } else { + cifs_dbg(FYI, "%s: resolved: %*.*s to %s\n", + __func__, (int)namelen, (int)namelen, name, ip); - len = strlen(unc); - if (len < 3) { - cifs_dbg(FYI, "%s: unc is too short: %s\n", __func__, unc); - return -EINVAL; + rc = cifs_convert_address(addr, ip, strlen(ip)); + kfree(ip); + if (!rc) { + cifs_dbg(FYI, "%s: unable to determine ip address\n", + __func__); + rc = -EHOSTUNREACH; + } else { + rc = 0; + } } + return rc; +} - /* Discount leading slashes for cifs */ - len -= 2; - hostname = unc + 2; +/** + * dns_resolve_name - Perform an upcall to resolve hostname to an ip address. + * @dom: DNS domain name (or NULL) + * @name: Name to look up + * @namelen: Length of name + * @ip_addr: Where to return the IP address + * + * Returns zero on success, -ve code otherwise. + */ +int dns_resolve_name(const char *dom, const char *name, + size_t namelen, struct sockaddr *ip_addr) +{ + size_t len; + char *s; + int rc; - /* Search for server name delimiter */ - sep = memchr(hostname, '/', len); - if (sep) - len = sep - hostname; - else - cifs_dbg(FYI, "%s: probably server name is whole unc: %s\n", - __func__, unc); + cifs_dbg(FYI, "%s: dom=%s name=%.*s\n", __func__, dom, (int)namelen, name); + if (!ip_addr || !name || !*name || !namelen) + return -EINVAL; + cifs_dbg(FYI, "%s: hostname=%.*s\n", __func__, (int)namelen, name); /* Try to interpret hostname as an IPv4 or IPv6 address */ - rc = cifs_convert_address(ip_addr, hostname, len); + rc = cifs_convert_address(ip_addr, name, namelen); if (rc > 0) { - cifs_dbg(FYI, "%s: unc is IP, skipping dns upcall: %*.*s\n", __func__, len, len, - hostname); + cifs_dbg(FYI, "%s: unc is IP, skipping dns upcall: %*.*s\n", + __func__, (int)namelen, (int)namelen, name); return 0; } - /* Perform the upcall */ - rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len, - NULL, &ip, expiry, false); - if (rc < 0) { - cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", - __func__, len, len, hostname); - } else { - cifs_dbg(FYI, "%s: resolved: %*.*s to %s expiry %llu\n", - __func__, len, len, hostname, ip, - expiry ? (*expiry) : 0); - - rc = cifs_convert_address(ip_addr, ip, strlen(ip)); - kfree(ip); + /* + * If @name contains a NetBIOS name and @dom has been specified, then + * convert @name to an FQDN and try resolving it first. + */ + if (dom && *dom && cifs_netbios_name(name, namelen)) { + len = strnlen(dom, CIFS_MAX_DOMAINNAME_LEN) + namelen + 2; + s = kmalloc(len, GFP_KERNEL); + if (!s) + return -ENOMEM; - if (!rc) { - cifs_dbg(FYI, "%s: unable to determine ip address\n", __func__); - rc = -EHOSTUNREACH; - } else - rc = 0; + scnprintf(s, len, "%.*s.%s", (int)namelen, name, dom); + rc = resolve_name(s, len - 1, ip_addr); + kfree(s); + if (!rc) + return 0; } - return rc; + return resolve_name(name, namelen, ip_addr); } diff --git a/fs/smb/client/dns_resolve.h b/fs/smb/client/dns_resolve.h index 6eb0c15a2440..0dc706f2c422 100644 --- a/fs/smb/client/dns_resolve.h +++ b/fs/smb/client/dns_resolve.h @@ -12,9 +12,30 @@ #define _DNS_RESOLVE_H #include <linux/net.h> +#include "cifsglob.h" +#include "cifsproto.h" #ifdef __KERNEL__ -int dns_resolve_server_name_to_ip(const char *unc, struct sockaddr *ip_addr, time64_t *expiry); + +int dns_resolve_name(const char *dom, const char *name, + size_t namelen, struct sockaddr *ip_addr); + +static inline int dns_resolve_unc(const char *dom, const char *unc, + struct sockaddr *ip_addr) +{ + const char *name; + size_t namelen; + + if (!unc || strlen(unc) < 3) + return -EINVAL; + + extract_unc_hostname(unc, &name, &namelen); + if (!namelen) + return -EINVAL; + + return dns_resolve_name(dom, name, namelen, ip_addr); +} + #endif /* KERNEL */ #endif /* _DNS_RESOLVE_H */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a58a3333ecc3..79de2f2f9c41 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -227,7 +227,8 @@ static void cifs_issue_read(struct netfs_io_subrequest *subreq) return; failed: - netfs_read_subreq_terminated(subreq, rc, false); + subreq->error = rc; + netfs_read_subreq_terminated(subreq); } /* @@ -990,7 +991,11 @@ int cifs_open(struct inode *inode, struct file *file) } /* Get the cached handle as SMB2 close is deferred */ - rc = cifs_get_readable_path(tcon, full_path, &cfile); + if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { + rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + } else { + rc = cifs_get_readable_path(tcon, full_path, &cfile); + } if (rc == 0) { if (file->f_flags == cfile->f_flags) { file->private_data = cfile; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 49123f458d0c..5381f05420bc 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -385,6 +385,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->source = NULL; new_ctx->iocharset = NULL; new_ctx->leaf_fullpath = NULL; + new_ctx->dns_dom = NULL; /* * Make sure to stay in sync with smb3_cleanup_fs_context_contents() */ @@ -399,6 +400,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); DUP_CTX_STR(leaf_fullpath); + DUP_CTX_STR(dns_dom); return 0; } @@ -1863,6 +1865,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->prepath = NULL; kfree(ctx->leaf_fullpath); ctx->leaf_fullpath = NULL; + kfree(ctx->dns_dom); + ctx->dns_dom = NULL; } void diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index ac6baa774ad3..8813533345ee 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -295,6 +295,7 @@ struct smb3_fs_context { bool dfs_automount:1; /* set for dfs automount only */ enum cifs_reparse_type reparse_type; bool dfs_conn:1; /* set for dfs mounts */ + char *dns_dom; }; extern const struct fs_parameter_spec smb3_fs_parameters[]; diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 668098d3b108..93e9188b2632 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1947,6 +1947,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } + netfs_wait_for_outstanding_io(inode); cifs_close_deferred_file_under_dentry(tcon, full_path); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -2391,6 +2392,13 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; + /* + * CIFSSMBRenameOpenFile() uses SMB_SET_FILE_RENAME_INFORMATION + * which is SMB PASSTHROUGH level. + */ + if (!(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) + goto do_rename_exit; + oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -2464,8 +2472,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } cifs_close_deferred_file_under_dentry(tcon, from_name); - if (d_inode(target_dentry) != NULL) + if (d_inode(target_dentry) != NULL) { + netfs_wait_for_outstanding_io(d_inode(target_dentry)); cifs_close_deferred_file_under_dentry(tcon, to_name); + } rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 4373dd64b66d..b328dc5c7988 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -101,6 +101,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree_sensitive(buf_to_free->password2); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); + kfree(buf_to_free->dns_dom); kfree_sensitive(buf_to_free->auth_key.response); spin_lock(&buf_to_free->iface_lock); list_for_each_entry_safe(iface, niface, &buf_to_free->iface_list, @@ -908,9 +909,9 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, *num_of_nodes = le16_to_cpu(rsp->NumberOfReferrals); if (*num_of_nodes < 1) { - cifs_dbg(VFS, "num_referrals: must be at least > 0, but we get num_referrals = %d\n", - *num_of_nodes); - rc = -EINVAL; + cifs_dbg(VFS | ONCE, "%s: [path=%s] num_referrals must be at least > 0, but we got %d\n", + __func__, searchName, *num_of_nodes); + rc = -ENOENT; goto parse_DFS_referrals_exit; } @@ -1171,33 +1172,25 @@ void cifs_put_tcp_super(struct super_block *sb) #ifdef CONFIG_CIFS_DFS_UPCALL int match_target_ip(struct TCP_Server_Info *server, - const char *share, size_t share_len, + const char *host, size_t hostlen, bool *result) { - int rc; - char *target; struct sockaddr_storage ss; + int rc; - *result = false; - - target = kzalloc(share_len + 3, GFP_KERNEL); - if (!target) - return -ENOMEM; - - scnprintf(target, share_len + 3, "\\\\%.*s", (int)share_len, share); - - cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2); + cifs_dbg(FYI, "%s: hostname=%.*s\n", __func__, (int)hostlen, host); - rc = dns_resolve_server_name_to_ip(target, (struct sockaddr *)&ss, NULL); - kfree(target); + *result = false; + rc = dns_resolve_name(server->dns_dom, host, hostlen, + (struct sockaddr *)&ss); if (rc < 0) return rc; spin_lock(&server->srv_lock); *result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss); spin_unlock(&server->srv_lock); - cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result); + cifs_dbg(FYI, "%s: ip addresses matched: %s\n", __func__, str_yes_no(*result)); return 0; } diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index 0f788031b740..e3f9213131c4 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -196,11 +196,28 @@ static struct vfsmount *cifs_do_automount(struct path *path) struct smb3_fs_context tmp; char *full_path; struct vfsmount *mnt; + struct cifs_sb_info *mntpt_sb; + struct cifs_ses *ses; if (IS_ROOT(mntpt)) return ERR_PTR(-ESTALE); - cur_ctx = CIFS_SB(mntpt->d_sb)->ctx; + mntpt_sb = CIFS_SB(mntpt->d_sb); + ses = cifs_sb_master_tcon(mntpt_sb)->ses; + cur_ctx = mntpt_sb->ctx; + + /* + * At this point, the root session should be in the mntpt sb. We should + * bring the sb context passwords in sync with the root session's + * passwords. This would help prevent unnecessary retries and password + * swaps for automounts. + */ + mutex_lock(&ses->session_mutex); + rc = smb3_sync_session_ctx_passwords(mntpt_sb, ses); + mutex_unlock(&ses->session_mutex); + + if (rc) + return ERR_PTR(rc); fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, mntpt); if (IS_ERR(fc)) diff --git a/fs/smb/client/netmisc.c b/fs/smb/client/netmisc.c index 2a8d71221e5e..17b3e21ea868 100644 --- a/fs/smb/client/netmisc.c +++ b/fs/smb/client/netmisc.c @@ -775,10 +775,10 @@ cifs_print_status(__u32 status_code) int idx = 0; while (nt_errs[idx].nt_errstr != NULL) { - if (((nt_errs[idx].nt_errcode) & 0xFFFFFF) == - (status_code & 0xFFFFFF)) { + if (nt_errs[idx].nt_errcode == status_code) { pr_notice("Status code returned 0x%08x %s\n", status_code, nt_errs[idx].nt_errstr); + return; } idx++; } diff --git a/fs/smb/client/nterr.c b/fs/smb/client/nterr.c index 358a766375b4..d396a8e98a81 100644 --- a/fs/smb/client/nterr.c +++ b/fs/smb/client/nterr.c @@ -13,6 +13,13 @@ const struct nt_err_code_struct nt_errs[] = { {"NT_STATUS_OK", NT_STATUS_OK}, + {"NT_STATUS_MEDIA_CHANGED", NT_STATUS_MEDIA_CHANGED}, + {"NT_STATUS_END_OF_MEDIA", NT_STATUS_END_OF_MEDIA}, + {"NT_STATUS_MEDIA_CHECK", NT_STATUS_MEDIA_CHECK}, + {"NT_STATUS_NO_DATA_DETECTED", NT_STATUS_NO_DATA_DETECTED}, + {"NT_STATUS_STOPPED_ON_SYMLINK", NT_STATUS_STOPPED_ON_SYMLINK}, + {"NT_STATUS_DEVICE_REQUIRES_CLEANING", NT_STATUS_DEVICE_REQUIRES_CLEANING}, + {"NT_STATUS_DEVICE_DOOR_OPEN", NT_STATUS_DEVICE_DOOR_OPEN}, {"NT_STATUS_UNSUCCESSFUL", NT_STATUS_UNSUCCESSFUL}, {"NT_STATUS_NOT_IMPLEMENTED", NT_STATUS_NOT_IMPLEMENTED}, {"NT_STATUS_INVALID_INFO_CLASS", NT_STATUS_INVALID_INFO_CLASS}, @@ -670,5 +677,6 @@ const struct nt_err_code_struct nt_errs[] = { {"NT_STATUS_NO_MORE_ENTRIES", NT_STATUS_NO_MORE_ENTRIES}, {"NT_STATUS_MORE_ENTRIES", NT_STATUS_MORE_ENTRIES}, {"NT_STATUS_SOME_UNMAPPED", NT_STATUS_SOME_UNMAPPED}, + {"NT_STATUS_NO_SUCH_JOB", NT_STATUS_NO_SUCH_JOB}, {NULL, 0} }; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 273358d20a46..50f96259d9ad 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -413,7 +413,7 @@ ffirst_retry: cifsFile->invalidHandle = false; } else if ((rc == -EOPNOTSUPP) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; + cifs_autodisable_serverino(cifs_sb); goto ffirst_retry; } error_exit: diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 50b1aba20008..d88b41133e00 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -676,7 +676,7 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf return -ENOMEM; symname_utf16_len = utf8s_to_utf16s(buf->PathBuffer, symname_utf8_len, UTF16_LITTLE_ENDIAN, - symname_utf16, symname_utf8_len * 2); + (wchar_t *) symname_utf16, symname_utf8_len * 2); if (symname_utf16_len < 0) { kfree(symname_utf16); return symname_utf16_len; diff --git a/fs/smb/client/rfc1002pdu.h b/fs/smb/client/rfc1002pdu.h index ae1d025da294..ac82c2f3a4a2 100644 --- a/fs/smb/client/rfc1002pdu.h +++ b/fs/smb/client/rfc1002pdu.h @@ -24,7 +24,7 @@ struct rfc1002_session_packet { __u8 type; __u8 flags; - __u16 length; + __be16 length; union { struct { __u8 called_len; @@ -35,8 +35,8 @@ struct rfc1002_session_packet { __u8 scope2; /* null */ } __attribute__((packed)) session_req; struct { - __u32 retarget_ip_addr; - __u16 port; + __be32 retarget_ip_addr; + __be16 port; } __attribute__((packed)) retarget_resp; __u8 neg_ses_resp_error_code; /* POSITIVE_SESSION_RESPONSE packet does not include trailer. diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 0bb77f9ec686..91d4d409cb1d 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -27,31 +27,6 @@ static int cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface); -bool -is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface) -{ - struct sockaddr_in *i4 = (struct sockaddr_in *)&iface->sockaddr; - struct sockaddr_in6 *i6 = (struct sockaddr_in6 *)&iface->sockaddr; - struct sockaddr_in *s4 = (struct sockaddr_in *)&server->dstaddr; - struct sockaddr_in6 *s6 = (struct sockaddr_in6 *)&server->dstaddr; - - if (server->dstaddr.ss_family != iface->sockaddr.ss_family) - return false; - if (server->dstaddr.ss_family == AF_INET) { - if (s4->sin_addr.s_addr != i4->sin_addr.s_addr) - return false; - } else if (server->dstaddr.ss_family == AF_INET6) { - if (memcmp(&s6->sin6_addr, &i6->sin6_addr, - sizeof(i6->sin6_addr)) != 0) - return false; - } else { - /* unknown family.. */ - return false; - } - return true; -} - bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) { int i; @@ -488,11 +463,11 @@ cifs_ses_add_channel(struct cifs_ses *ses, if (iface->sockaddr.ss_family == AF_INET) cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI4)\n", - ses, iface->speed, iface->rdma_capable ? "yes" : "no", + ses, iface->speed, str_yes_no(iface->rdma_capable), &ipv4->sin_addr); else cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI6)\n", - ses, iface->speed, iface->rdma_capable ? "yes" : "no", + ses, iface->speed, str_yes_no(iface->rdma_capable), &ipv6->sin6_addr); /* diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index db3695eddcf9..749a83cd0deb 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -614,7 +614,13 @@ static int cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, * There may be higher info levels that work but are there Windows * server or network appliances for which IndexNumber field is not * guaranteed unique? + * + * CIFSGetSrvInodeNumber() uses SMB_QUERY_FILE_INTERNAL_INFO + * which is SMB PASSTHROUGH level therefore check for capability. + * Note that this function can be called with tcon == NULL. */ + if (tcon && !(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) + return -EOPNOTSUPP; return CIFSGetSrvInodeNumber(xid, tcon, full_path, uniqueid, cifs_sb->local_nls, cifs_remap(cifs_sb)); diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index e836bc2193dd..9ec44eab8dbc 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -42,14 +42,14 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) end = (struct smb2_error_context_rsp *)((u8 *)err + iov->iov_len); do { if (le32_to_cpu(p->ErrorId) == SMB2_ERROR_ID_DEFAULT) { - sym = (struct smb2_symlink_err_rsp *)&p->ErrorContextData; + sym = (struct smb2_symlink_err_rsp *)p->ErrorContextData; break; } cifs_dbg(FYI, "%s: skipping unhandled error context: 0x%x\n", __func__, le32_to_cpu(p->ErrorId)); len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); - p = (struct smb2_error_context_rsp *)((u8 *)&p->ErrorContextData + len); + p = (struct smb2_error_context_rsp *)(p->ErrorContextData + len); } while (p < end); } else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) && iov->iov_len >= SMB2_SYMLINK_STRUCT_SIZE) { diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index a55f0044d30b..c97f14757c27 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -176,27 +176,27 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct kvec *out_iov, int *out_buftype, struct dentry *dentry) { - struct reparse_data_buffer *rbuf; + struct smb2_query_info_rsp *qi_rsp = NULL; struct smb2_compound_vars *vars = NULL; - struct kvec *rsp_iov, *iov; - struct smb_rqst *rqst; - int rc; - __le16 *utf16_path = NULL; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - struct cifs_fid fid; + struct cifs_open_info_data *idata; struct cifs_ses *ses = tcon->ses; + struct reparse_data_buffer *rbuf; struct TCP_Server_Info *server; - int num_rqst = 0, i; int resp_buftype[MAX_COMPOUND]; - struct smb2_query_info_rsp *qi_rsp = NULL; - struct cifs_open_info_data *idata; + int retries = 0, cur_sleep = 1; + __u8 delete_pending[8] = {1,}; + struct kvec *rsp_iov, *iov; struct inode *inode = NULL; - int flags = 0; - __u8 delete_pending[8] = {1, 0, 0, 0, 0, 0, 0, 0}; + __le16 *utf16_path = NULL; + struct smb_rqst *rqst; unsigned int size[2]; - void *data[2]; + struct cifs_fid fid; + int num_rqst = 0, i; unsigned int len; - int retries = 0, cur_sleep = 1; + int tmp_rc, rc; + int flags = 0; + void *data[2]; replay_again: /* reinitialize for possible replay */ @@ -298,8 +298,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_query_info_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_query_info_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_POSIX_QUERY_INFO: rqst[num_rqst].rq_iov = &vars->qi_iov; @@ -334,18 +334,18 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_posix_query_info_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_posix_query_info_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_DELETE: - trace_smb3_delete_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_MKDIR: /* * Directories are created through parameters in the * SMB2_open() call. */ - trace_smb3_mkdir_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_RMDIR: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -363,7 +363,7 @@ replay_again: goto finished; smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); - trace_smb3_rmdir_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_EOF: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -398,7 +398,7 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_set_eof_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_INFO: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -429,8 +429,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_set_info_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_set_info_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_RENAME: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -469,7 +469,7 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_rename_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_HARDLINK: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -496,7 +496,7 @@ replay_again: goto finished; smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); - trace_smb3_hardlink_enter(xid, ses->Suid, tcon->tid, full_path); + trace_smb3_hardlink_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_REPARSE: rqst[num_rqst].rq_iov = vars->io_iov; @@ -523,8 +523,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_set_reparse_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_set_reparse_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_GET_REPARSE: rqst[num_rqst].rq_iov = vars->io_iov; @@ -549,8 +549,8 @@ replay_again: goto finished; } num_rqst++; - trace_smb3_get_reparse_compound_enter(xid, ses->Suid, - tcon->tid, full_path); + trace_smb3_get_reparse_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; case SMB2_OP_QUERY_WSL_EA: rqst[num_rqst].rq_iov = &vars->ea_iov; @@ -584,6 +584,8 @@ replay_again: goto finished; } num_rqst++; + trace_smb3_query_wsl_ea_compound_enter(xid, tcon->tid, + ses->Suid, full_path); break; default: cifs_dbg(VFS, "Invalid command\n"); @@ -637,7 +639,14 @@ finished: tcon->need_reconnect = true; } + tmp_rc = rc; for (i = 0; i < num_cmds; i++) { + char *buf = rsp_iov[i + i].iov_base; + + if (buf && resp_buftype[i + 1] != CIFS_NO_BUFFER) + rc = server->ops->map_error(buf, false); + else + rc = tmp_rc; switch (cmds[i]) { case SMB2_OP_QUERY_INFO: idata = in_iov[i].iov_base; @@ -656,11 +665,11 @@ finished: } SMB2_query_info_free(&rqst[num_rqst++]); if (rc) - trace_smb3_query_info_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_query_info_compound_err(xid, tcon->tid, + ses->Suid, rc); else - trace_smb3_query_info_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_query_info_compound_done(xid, tcon->tid, + ses->Suid); break; case SMB2_OP_POSIX_QUERY_INFO: idata = in_iov[i].iov_base; @@ -683,15 +692,15 @@ finished: SMB2_query_info_free(&rqst[num_rqst++]); if (rc) - trace_smb3_posix_query_info_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_posix_query_info_compound_err(xid, tcon->tid, + ses->Suid, rc); else - trace_smb3_posix_query_info_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_posix_query_info_compound_done(xid, tcon->tid, + ses->Suid); break; case SMB2_OP_DELETE: if (rc) - trace_smb3_delete_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc); else { /* * If dentry (hence, inode) is NULL, lease break is going to @@ -699,59 +708,59 @@ finished: */ if (inode) cifs_mark_open_handles_for_deleted_file(inode, full_path); - trace_smb3_delete_done(xid, ses->Suid, tcon->tid); + trace_smb3_delete_done(xid, tcon->tid, ses->Suid); } break; case SMB2_OP_MKDIR: if (rc) - trace_smb3_mkdir_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_mkdir_done(xid, ses->Suid, tcon->tid); + trace_smb3_mkdir_done(xid, tcon->tid, ses->Suid); break; case SMB2_OP_HARDLINK: if (rc) - trace_smb3_hardlink_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_hardlink_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_hardlink_done(xid, ses->Suid, tcon->tid); + trace_smb3_hardlink_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_RENAME: if (rc) - trace_smb3_rename_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_rename_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_rename_done(xid, ses->Suid, tcon->tid); + trace_smb3_rename_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_RMDIR: if (rc) - trace_smb3_rmdir_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_rmdir_done(xid, ses->Suid, tcon->tid); + trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_EOF: if (rc) - trace_smb3_set_eof_err(xid, ses->Suid, tcon->tid, rc); + trace_smb3_set_eof_err(xid, tcon->tid, ses->Suid, rc); else - trace_smb3_set_eof_done(xid, ses->Suid, tcon->tid); + trace_smb3_set_eof_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_INFO: if (rc) - trace_smb3_set_info_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_set_info_compound_err(xid, tcon->tid, + ses->Suid, rc); else - trace_smb3_set_info_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_set_info_compound_done(xid, tcon->tid, + ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_REPARSE: if (rc) { - trace_smb3_set_reparse_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_set_reparse_compound_err(xid, tcon->tid, + ses->Suid, rc); } else { - trace_smb3_set_reparse_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_set_reparse_compound_done(xid, tcon->tid, + ses->Suid); } SMB2_ioctl_free(&rqst[num_rqst++]); break; @@ -764,18 +773,18 @@ finished: rbuf = reparse_buf_ptr(iov); if (IS_ERR(rbuf)) { rc = PTR_ERR(rbuf); - trace_smb3_set_reparse_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_get_reparse_compound_err(xid, tcon->tid, + ses->Suid, rc); } else { idata->reparse.tag = le32_to_cpu(rbuf->ReparseTag); - trace_smb3_set_reparse_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_get_reparse_compound_done(xid, tcon->tid, + ses->Suid); } memset(iov, 0, sizeof(*iov)); resp_buftype[i + 1] = CIFS_NO_BUFFER; } else { - trace_smb3_set_reparse_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_get_reparse_compound_err(xid, tcon->tid, + ses->Suid, rc); } SMB2_ioctl_free(&rqst[num_rqst++]); break; @@ -792,17 +801,18 @@ finished: } } if (!rc) { - trace_smb3_query_wsl_ea_compound_done(xid, ses->Suid, - tcon->tid); + trace_smb3_query_wsl_ea_compound_done(xid, tcon->tid, + ses->Suid); } else { - trace_smb3_query_wsl_ea_compound_err(xid, ses->Suid, - tcon->tid, rc); + trace_smb3_query_wsl_ea_compound_err(xid, tcon->tid, + ses->Suid, rc); } SMB2_query_info_free(&rqst[num_rqst++]); break; } } SMB2_close_free(&rqst[num_rqst]); + rc = tmp_rc; num_cmds += 2; if (out_iov && out_buftype) { @@ -858,22 +868,52 @@ static int parse_create_response(struct cifs_open_info_data *data, return rc; } +/* Check only if SMB2_OP_QUERY_WSL_EA command failed in the compound chain */ +static bool ea_unsupported(int *cmds, int num_cmds, + struct kvec *out_iov, int *out_buftype) +{ + int i; + + if (cmds[num_cmds - 1] != SMB2_OP_QUERY_WSL_EA) + return false; + + for (i = 1; i < num_cmds - 1; i++) { + struct smb2_hdr *hdr = out_iov[i].iov_base; + + if (out_buftype[i] == CIFS_NO_BUFFER || !hdr || + hdr->Status != STATUS_SUCCESS) + return false; + } + return true; +} + +static inline void free_rsp_iov(struct kvec *iovs, int *buftype, int count) +{ + int i; + + for (i = 0; i < count; i++) { + free_rsp_buf(buftype[i], iovs[i].iov_base); + memset(&iovs[i], 0, sizeof(*iovs)); + buftype[i] = CIFS_NO_BUFFER; + } +} + int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, struct cifs_open_info_data *data) { + struct kvec in_iov[3], out_iov[5] = {}; + struct cached_fid *cfid = NULL; struct cifs_open_parms oparms; - __u32 create_options = 0; struct cifsFileInfo *cfile; - struct cached_fid *cfid = NULL; + __u32 create_options = 0; + int out_buftype[5] = {}; struct smb2_hdr *hdr; - struct kvec in_iov[3], out_iov[3] = {}; - int out_buftype[3] = {}; + int num_cmds = 0; int cmds[3]; bool islink; - int i, num_cmds = 0; int rc, rc2; data->adjust_tz = false; @@ -943,14 +983,14 @@ int smb2_query_path_info(const unsigned int xid, if (rc || !data->reparse_point) goto out; - if (!tcon->posix_extensions) - cmds[num_cmds++] = SMB2_OP_QUERY_WSL_EA; /* * Skip SMB2_OP_GET_REPARSE if symlink already parsed in create * response. */ if (data->reparse.tag != IO_REPARSE_TAG_SYMLINK) cmds[num_cmds++] = SMB2_OP_GET_REPARSE; + if (!tcon->posix_extensions) + cmds[num_cmds++] = SMB2_OP_QUERY_WSL_EA; oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_READ_ATTRIBUTES | @@ -958,9 +998,18 @@ int smb2_query_path_info(const unsigned int xid, FILE_OPEN, create_options | OPEN_REPARSE_POINT, ACL_NO_MODE); cifs_get_readable_path(tcon, full_path, &cfile); + free_rsp_iov(out_iov, out_buftype, ARRAY_SIZE(out_iov)); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, in_iov, cmds, num_cmds, - cfile, NULL, NULL, NULL); + cfile, out_iov, out_buftype, NULL); + if (rc && ea_unsupported(cmds, num_cmds, + out_iov, out_buftype)) { + if (data->reparse.tag != IO_REPARSE_TAG_LX_BLK && + data->reparse.tag != IO_REPARSE_TAG_LX_CHR) + rc = 0; + else + rc = -EOPNOTSUPP; + } break; case -EREMOTE: break; @@ -978,8 +1027,7 @@ int smb2_query_path_info(const unsigned int xid, } out: - for (i = 0; i < ARRAY_SIZE(out_buftype); i++) - free_rsp_buf(out_buftype[i], out_iov[i].iov_base); + free_rsp_iov(out_iov, out_buftype, ARRAY_SIZE(out_iov)); return rc; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 87cb1872db28..d640dcabc305 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -658,7 +658,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); - tmp_iface.speed = le64_to_cpu(p->LinkSpeed); + /* default to 1Gbps when link speed is unset */ + tmp_iface.speed = le64_to_cpu(p->LinkSpeed) ?: 1000000000; tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; tmp_iface.rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0; @@ -3007,9 +3008,9 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, num_of_nodes, target_nodes, nls_codepage, remap, search_name, true /* is_unicode */); - if (rc) { - cifs_tcon_dbg(VFS, "parse error in %s rc=%d\n", __func__, rc); - goto out; + if (rc && rc != -ENOENT) { + cifs_tcon_dbg(VFS, "%s: failed to parse DFS referral %s: %d\n", + __func__, search_name, rc); } out: @@ -4388,7 +4389,7 @@ static struct folio_queue *cifs_alloc_folioq_buffer(ssize_t size) p = kmalloc(sizeof(*p), GFP_NOFS); if (!p) goto nomem; - folioq_init(p); + folioq_init(p, 0); if (tail) { tail->next = p; p->prev = tail; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 010eae9d6c47..9f54596a6866 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4500,14 +4500,6 @@ smb2_new_read_req(void **buf, unsigned int *total_len, return rc; } -static void smb2_readv_worker(struct work_struct *work) -{ - struct cifs_io_subrequest *rdata = - container_of(work, struct cifs_io_subrequest, subreq.work); - - netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); -} - static void smb2_readv_callback(struct mid_q_entry *mid) { @@ -4615,15 +4607,17 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } + if (rdata->got_bytes) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; + rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress); - INIT_WORK(&rdata->subreq.work, smb2_readv_worker); - queue_work(cifsiod_wq, &rdata->subreq.work); + netfs_read_subreq_terminated(&rdata->subreq); release_mid(mid); trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, server->credits, server->in_flight, @@ -4840,10 +4834,14 @@ smb2_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + cifs_stats_bytes_written(tcon, written); + + if (written < wdata->subreq.len) { wdata->result = -ENOSPC; - else + } else if (written > 0) { wdata->subreq.len = written; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -5012,7 +5010,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) } #endif - if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) + if (wdata->subreq.retry_count > 0) smb2_set_replay(server, &rqst); cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n", @@ -5156,6 +5154,7 @@ replay_again: cifs_dbg(VFS, "Send error in write = %d\n", rc); } else { *nbytes = le32_to_cpu(rsp->DataLength); + cifs_stats_bytes_written(io_parms->tcon, *nbytes); trace_smb3_write_done(0, 0, xid, req->PersistentFileId, io_parms->tcon->tid, @@ -6204,7 +6203,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, req->StructureSize = cpu_to_le16(36); total_len += 12; - memcpy(req->LeaseKey, lease_key, 16); + memcpy(req->LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE); req->LeaseState = lease_state; flags |= CIFS_NO_RSP_BUF; diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 076d9e83e1a0..3c09a58dfd07 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -79,7 +79,7 @@ struct smb2_symlink_err_rsp { struct smb2_error_context_rsp { __le32 ErrorDataLength; __le32 ErrorId; - __u8 ErrorContextData; /* ErrorDataLength long array */ + __u8 ErrorContextData[] __counted_by_le(ErrorDataLength); } __packed; /* ErrorId values */ diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 12cbd3428a6d..52bcb55d9952 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -674,6 +674,7 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter); diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 1d1ffd0acaca..2a5b4a96bf99 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1016,6 +1016,8 @@ static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id, ses_enc_key = enc ? sess->smb3encryptionkey : sess->smb3decryptionkey; + if (enc) + ksmbd_user_session_get(sess); memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); return 0; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b30..f8a40f65db6a 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 3d01d9d15293..3f07a612c05b 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -111,7 +111,8 @@ struct ksmbd_startup_request { __u32 smb2_max_credits; /* MAX credits */ __u32 smbd_max_io_size; /* smbd read write size */ __u32 max_connections; /* Number of maximum simultaneous connections */ - __u32 reserved[126]; /* Reserved room */ + __s8 bind_interfaces_only; + __s8 reserved[503]; /* Reserved room */ __u32 ifc_list_sz; /* interfaces list size */ __s8 ____payload[]; }; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index df92d746e89c..71c6939dfbf1 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -263,8 +263,10 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); - if (sess) + if (sess) { sess->last_active = jiffies; + ksmbd_user_session_get(sess); + } up_read(&conn->session_lock); return sess; } @@ -275,6 +277,8 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); + if (sess) + ksmbd_user_session_get(sess); up_read(&sessions_table_lock); return sess; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 930d7566b52e..601e7fcbcf1e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -241,14 +241,14 @@ send: if (work->tcon) ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); - if (work->sess) - ksmbd_user_session_put(work->sess); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { rc = conn->ops->encrypt_resp(work); if (rc < 0) conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); } + if (work->sess) + ksmbd_user_session_put(work->sess); ksmbd_conn_write(work); } @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..995555febe7d 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,9 +42,11 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; + bool bind_interfaces_only; }; extern struct ksmbd_server_config server_conf; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4f539eeadbb0..f1efcd027475 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -38,6 +38,7 @@ #include "mgmt/user_session.h" #include "mgmt/ksmbd_ida.h" #include "ndr.h" +#include "transport_tcp.h" static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) { @@ -67,8 +68,10 @@ static inline bool check_session_id(struct ksmbd_conn *conn, u64 id) return false; sess = ksmbd_session_lookup_all(conn, id); - if (sess) + if (sess) { + ksmbd_user_session_put(sess); return true; + } pr_err("Invalid user session id: %llu\n", id); return false; } @@ -605,10 +608,8 @@ int smb2_check_user_session(struct ksmbd_work *work) /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); - if (work->sess) { - ksmbd_user_session_get(work->sess); + if (work->sess) return 1; - } ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); return -ENOENT; } @@ -695,6 +696,9 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) struct smb2_hdr *rsp_hdr; struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); + if (!in_work) + return; + if (allocate_interim_rsp_buf(in_work)) { pr_err("smb_allocate_rsp_buf failed!\n"); ksmbd_free_work_struct(in_work); @@ -1097,6 +1101,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1252,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; @@ -1701,29 +1707,35 @@ int smb2_sess_setup(struct ksmbd_work *work) if (conn->dialect != sess->dialect) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (!(req->hdr.Flags & SMB2_FLAGS_SIGNED)) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_IN_PROGRESS) { rc = -EACCES; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_EXPIRED) { rc = -EFAULT; + ksmbd_user_session_put(sess); goto out_err; } + ksmbd_user_session_put(sess); if (ksmbd_conn_need_reconnect(conn)) { rc = -EFAULT; @@ -1731,7 +1743,8 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (ksmbd_session_lookup(conn, sess_id)) { + sess = ksmbd_session_lookup(conn, sess_id); + if (!sess) { rc = -EACCES; goto out_err; } @@ -1742,7 +1755,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = true; - ksmbd_user_session_get(sess); } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { @@ -1769,7 +1781,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = false; - ksmbd_user_session_get(sess); } work->sess = sess; @@ -2197,9 +2208,9 @@ err_out: int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_logoff_req *req; struct smb2_logoff_rsp *rsp; - struct ksmbd_session *sess; u64 sess_id; int err; @@ -2221,11 +2232,6 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn); - /* - * Re-lookup session to validate if session is deleted - * while waiting request complete - */ - sess = ksmbd_session_lookup_all(conn, sess_id); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -3989,6 +3995,26 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->DeviceId = cpu_to_le32(ksmbd_kstat->kstat->rdev); posix_info->HardLinks = cpu_to_le32(ksmbd_kstat->kstat->nlink); posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode & 0777); + switch (ksmbd_kstat->kstat->mode & S_IFMT) { + case S_IFDIR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = S_ISDIR(ksmbd_kstat->kstat->mode) ? @@ -4228,6 +4254,7 @@ static bool __query_dir(struct dir_context *ctx, const char *name, int namlen, /* dot and dotdot entries are already reserved */ if (!strcmp(".", name) || !strcmp("..", name)) return true; + d_info->num_scan++; if (ksmbd_share_veto_filename(priv->work->tcon->share_conf, name)) return true; if (!match_pattern(name, namlen, priv->search_pattern)) @@ -4390,9 +4417,18 @@ int smb2_query_dir(struct ksmbd_work *work) query_dir_private.info_level = req->FileInformationClass; dir_fp->readdir_data.private = &query_dir_private; set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir); - +again: + d_info.num_scan = 0; rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx); /* + * num_entry can be 0 if the directory iteration stops before reaching + * the end of the directory and no file is matched with the search + * pattern. + */ + if (rc >= 0 && !d_info.num_entry && d_info.num_scan && + d_info.out_buf_len > 0) + goto again; + /* * req->OutputBufferLength is too small to contain even one entry. * In this case, it immediately returns OutputBufferLength 0 to client. */ @@ -5169,6 +5205,26 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->HardLinks = cpu_to_le32(stat.nlink); file_info->Mode = cpu_to_le32(stat.mode & 0777); + switch (stat.mode & S_IFMT) { + case S_IFDIR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + file_info->DeviceId = cpu_to_le32(stat.rdev); /* @@ -6016,15 +6072,13 @@ static int set_file_basic_info(struct ksmbd_file *fp, attrs.ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); } - attrs.ia_valid |= ATTR_CTIME; if (file_info->ChangeTime) - attrs.ia_ctime = ksmbd_NTtimeToUnix(file_info->ChangeTime); - else - attrs.ia_ctime = inode_get_ctime(inode); + inode_set_ctime_to_ts(inode, + ksmbd_NTtimeToUnix(file_info->ChangeTime)); if (file_info->LastWriteTime) { attrs.ia_mtime = ksmbd_NTtimeToUnix(file_info->LastWriteTime); - attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); + attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET | ATTR_CTIME); } if (file_info->Attributes) { @@ -6066,8 +6120,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, return -EACCES; inode_lock(inode); - inode_set_ctime_to_ts(inode, attrs.ia_ctime); - attrs.ia_valid &= ~ATTR_CTIME; rc = notify_change(idmap, dentry, &attrs, NULL); inode_unlock(inode); } @@ -7708,6 +7760,9 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, if (netdev->type == ARPHRD_LOOPBACK) continue; + if (!ksmbd_find_netdev_name_iface_list(netdev->name)) + continue; + flags = dev_get_flags(netdev); if (!(flags & IFF_RUNNING)) continue; @@ -8982,6 +9037,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) le64_to_cpu(tr_hdr->SessionId)); return -ECONNABORTED; } + ksmbd_user_session_put(sess); iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 649dacf7e8c4..17a0b18a8406 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -502,4 +502,14 @@ static inline void *smb2_get_msg(void *buf) return buf + 4; } +#define POSIX_TYPE_FILE 0 +#define POSIX_TYPE_DIR 1 +#define POSIX_TYPE_SYMLINK 2 +#define POSIX_TYPE_CHARDEV 3 +#define POSIX_TYPE_BLKDEV 4 +#define POSIX_TYPE_FIFO 5 +#define POSIX_TYPE_SOCKET 6 + +#define POSIX_FILETYPE_SHIFT 12 + #endif /* _SMB2PDU_H */ diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index f51cd0816b1a..425c756bcfb8 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -781,10 +781,6 @@ int __ksmbd_override_fsids(struct ksmbd_work *work, WARN_ON(work->saved_cred); work->saved_cred = override_creds(cred); - if (!work->saved_cred) { - abort_creds(cred); - return -EINVAL; - } return 0; } @@ -796,13 +792,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work) void ksmbd_revert_fsids(struct ksmbd_work *work) { const struct cred *cred; - WARN_ON(!work->saved_cred); - cred = current_cred(); - revert_creds(work->saved_cred); - put_cred(cred); + cred = revert_creds(work->saved_cred); work->saved_cred = NULL; + put_cred(cred); } __le32 smb_map_generic_desired_access(__le32 daccess) diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a..0460ebea6ff0 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); @@ -330,6 +333,7 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) ret = ksmbd_set_netbios_name(req->netbios_name); ret |= ksmbd_set_server_string(req->server_string); ret |= ksmbd_set_work_group(req->work_group); + server_conf.bind_interfaces_only = req->bind_interfaces_only; ret |= ksmbd_tcp_set_interfaces(KSMBD_STARTUP_CONFIG_INTERFACES(req), req->ifc_list_sz); if (ret) { @@ -623,6 +627,9 @@ ksmbd_ipc_spnego_authen_request(const char *spnego_blob, int blob_len) struct ksmbd_spnego_authen_request *req; struct ksmbd_spnego_authen_response *resp; + if (blob_len > KSMBD_IPC_MAX_PAYLOAD) + return NULL; + msg = ipc_msg_alloc(sizeof(struct ksmbd_spnego_authen_request) + blob_len + 1); if (!msg) @@ -802,6 +809,9 @@ struct ksmbd_rpc_command *ksmbd_rpc_write(struct ksmbd_session *sess, int handle struct ksmbd_rpc_command *req; struct ksmbd_rpc_command *resp; + if (payload_sz > KSMBD_IPC_MAX_PAYLOAD) + return NULL; + msg = ipc_msg_alloc(sizeof(struct ksmbd_rpc_command) + payload_sz + 1); if (!msg) return NULL; @@ -850,6 +860,9 @@ struct ksmbd_rpc_command *ksmbd_rpc_ioctl(struct ksmbd_session *sess, int handle struct ksmbd_rpc_command *req; struct ksmbd_rpc_command *resp; + if (payload_sz > KSMBD_IPC_MAX_PAYLOAD) + return NULL; + msg = ipc_msg_alloc(sizeof(struct ksmbd_rpc_command) + payload_sz + 1); if (!msg) return NULL; @@ -868,31 +881,6 @@ struct ksmbd_rpc_command *ksmbd_rpc_ioctl(struct ksmbd_session *sess, int handle return resp; } -struct ksmbd_rpc_command *ksmbd_rpc_rap(struct ksmbd_session *sess, void *payload, - size_t payload_sz) -{ - struct ksmbd_ipc_msg *msg; - struct ksmbd_rpc_command *req; - struct ksmbd_rpc_command *resp; - - msg = ipc_msg_alloc(sizeof(struct ksmbd_rpc_command) + payload_sz + 1); - if (!msg) - return NULL; - - msg->type = KSMBD_EVENT_RPC_REQUEST; - req = (struct ksmbd_rpc_command *)msg->payload; - req->handle = ksmbd_acquire_id(&ipc_ida); - req->flags = rpc_context_flags(sess); - req->flags |= KSMBD_RPC_RAP_METHOD; - req->payload_sz = payload_sz; - memcpy(req->payload, payload, payload_sz); - - resp = ipc_msg_send_request(msg, req->handle); - ipc_msg_handle_free(req->handle); - ipc_msg_free(msg); - return resp; -} - static int __ipc_heartbeat(void) { unsigned long delta; diff --git a/fs/smb/server/transport_ipc.h b/fs/smb/server/transport_ipc.h index d9b6737f8cd0..e51850f1423b 100644 --- a/fs/smb/server/transport_ipc.h +++ b/fs/smb/server/transport_ipc.h @@ -41,8 +41,6 @@ struct ksmbd_rpc_command *ksmbd_rpc_write(struct ksmbd_session *sess, int handle struct ksmbd_rpc_command *ksmbd_rpc_read(struct ksmbd_session *sess, int handle); struct ksmbd_rpc_command *ksmbd_rpc_ioctl(struct ksmbd_session *sess, int handle, void *payload, size_t payload_sz); -struct ksmbd_rpc_command *ksmbd_rpc_rap(struct ksmbd_session *sess, void *payload, - size_t payload_sz); void ksmbd_ipc_release(void); void ksmbd_ipc_soft_reset(void); int ksmbd_ipc_init(void); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 0ef3c9f0bfeb..c3785a5434f9 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2283,8 +2283,7 @@ out: ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN); if (ibdev) { - if (rdma_frwr_is_supported(&ibdev->attrs)) - rdma_capable = true; + rdma_capable = rdma_frwr_is_supported(&ibdev->attrs); ib_device_put(ibdev); } } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 0d9007285e30..7f38a3c3f5bd 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -504,32 +504,37 @@ out_clear: return ret; } +struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name) +{ + struct interface *iface; + + list_for_each_entry(iface, &iface_list, entry) + if (!strcmp(iface->name, netdev_name)) + return iface; + return NULL; +} + static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct interface *iface; - int ret, found = 0; + int ret; switch (event) { case NETDEV_UP: if (netif_is_bridge_port(netdev)) return NOTIFY_OK; - list_for_each_entry(iface, &iface_list, entry) { - if (!strcmp(iface->name, netdev->name)) { - found = 1; - if (iface->state != IFACE_STATE_DOWN) - break; - ksmbd_debug(CONN, "netdev-up event: netdev(%s) is going up\n", - iface->name); - ret = create_socket(iface); - if (ret) - return NOTIFY_OK; - break; - } + iface = ksmbd_find_netdev_name_iface_list(netdev->name); + if (iface && iface->state == IFACE_STATE_DOWN) { + ksmbd_debug(CONN, "netdev-up event: netdev(%s) is going up\n", + iface->name); + ret = create_socket(iface); + if (ret) + return NOTIFY_OK; } - if (!found && bind_additional_ifaces) { + if (!iface && bind_additional_ifaces) { iface = alloc_iface(kstrdup(netdev->name, KSMBD_DEFAULT_GFP)); if (!iface) return NOTIFY_OK; @@ -541,21 +546,19 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, } break; case NETDEV_DOWN: - list_for_each_entry(iface, &iface_list, entry) { - if (!strcmp(iface->name, netdev->name) && - iface->state == IFACE_STATE_CONFIGURED) { - ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", - iface->name); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - mutex_lock(&iface->sock_release_lock); - tcp_destroy_socket(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - mutex_unlock(&iface->sock_release_lock); - - iface->state = IFACE_STATE_DOWN; - break; - } + iface = ksmbd_find_netdev_name_iface_list(netdev->name); + if (iface && iface->state == IFACE_STATE_CONFIGURED) { + ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", + iface->name); + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + mutex_lock(&iface->sock_release_lock); + tcp_destroy_socket(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + mutex_unlock(&iface->sock_release_lock); + + iface->state = IFACE_STATE_DOWN; + break; } break; } @@ -624,18 +627,6 @@ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz) int sz = 0; if (!ifc_list_sz) { - struct net_device *netdev; - - rtnl_lock(); - for_each_netdev(&init_net, netdev) { - if (netif_is_bridge_port(netdev)) - continue; - if (!alloc_iface(kstrdup(netdev->name, KSMBD_DEFAULT_GFP))) { - rtnl_unlock(); - return -ENOMEM; - } - } - rtnl_unlock(); bind_additional_ifaces = 1; return 0; } diff --git a/fs/smb/server/transport_tcp.h b/fs/smb/server/transport_tcp.h index e338bebe322f..8c9aa624cfe3 100644 --- a/fs/smb/server/transport_tcp.h +++ b/fs/smb/server/transport_tcp.h @@ -7,6 +7,7 @@ #define __KSMBD_TRANSPORT_TCP_H__ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz); +struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name); int ksmbd_tcp_init(void); void ksmbd_tcp_destroy(void); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 88d167a5f8b7..6890016e1923 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1264,6 +1264,8 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, filepath, flags, path); + if (!is_last) + next[0] = '/'; if (err) goto out2; else if (is_last) @@ -1271,7 +1273,6 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, path_put(parent_path); *parent_path = *path; - next[0] = '/'; remain_len -= filename_len + 1; } @@ -1855,13 +1856,6 @@ void ksmbd_vfs_posix_lock_wait(struct file_lock *flock) wait_event(flock->c.flc_wait, !flock->c.flc_blocker); } -int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout) -{ - return wait_event_interruptible_timeout(flock->c.flc_wait, - !flock->c.flc_blocker, - timeout); -} - void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock) { locks_delete_block(flock); diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cb76f4b5bafe..2893f59803a6 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -43,6 +43,7 @@ struct ksmbd_dir_info { char *rptr; int name_len; int out_buf_len; + int num_scan; int num_entry; int data_count; int last_entry_offset; @@ -139,7 +140,6 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat); void ksmbd_vfs_posix_lock_wait(struct file_lock *flock); -int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout); void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock); int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, const struct path *path); diff --git a/fs/stat.c b/fs/stat.c index 0870e969a8a0..2c0e111a098a 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -725,6 +725,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; + tmp.stx_dio_read_offset_align = stat->dio_read_offset_align; tmp.stx_subvol = stat->subvol; tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; diff --git a/fs/unicode/mkutf8data.c b/fs/unicode/mkutf8data.c index 6b095dd32e0f..401f5d3aeb0c 100644 --- a/fs/unicode/mkutf8data.c +++ b/fs/unicode/mkutf8data.c @@ -2230,6 +2230,75 @@ static void nfdicf_init(void) file_fail(fold_name); } +static void ignore_init(void) +{ + FILE *file; + unsigned int unichar; + unsigned int first; + unsigned int last; + unsigned int *um; + int count; + int ret; + + if (verbose > 0) + printf("Parsing %s\n", prop_name); + file = fopen(prop_name, "r"); + if (!file) + open_fail(prop_name, errno); + assert(file); + count = 0; + while (fgets(line, LINESIZE, file)) { + ret = sscanf(line, "%X..%X ; %s # ", &first, &last, buf0); + if (ret == 3) { + if (strcmp(buf0, "Default_Ignorable_Code_Point")) + continue; + if (!utf32valid(first) || !utf32valid(last)) + line_fail(prop_name, line); + for (unichar = first; unichar <= last; unichar++) { + free(unicode_data[unichar].utf32nfdi); + um = malloc(sizeof(unsigned int)); + *um = 0; + unicode_data[unichar].utf32nfdi = um; + free(unicode_data[unichar].utf32nfdicf); + um = malloc(sizeof(unsigned int)); + *um = 0; + unicode_data[unichar].utf32nfdicf = um; + count++; + } + if (verbose > 1) + printf(" %X..%X Default_Ignorable_Code_Point\n", + first, last); + continue; + } + ret = sscanf(line, "%X ; %s # ", &unichar, buf0); + if (ret == 2) { + if (strcmp(buf0, "Default_Ignorable_Code_Point")) + continue; + if (!utf32valid(unichar)) + line_fail(prop_name, line); + free(unicode_data[unichar].utf32nfdi); + um = malloc(sizeof(unsigned int)); + *um = 0; + unicode_data[unichar].utf32nfdi = um; + free(unicode_data[unichar].utf32nfdicf); + um = malloc(sizeof(unsigned int)); + *um = 0; + unicode_data[unichar].utf32nfdicf = um; + if (verbose > 1) + printf(" %X Default_Ignorable_Code_Point\n", + unichar); + count++; + continue; + } + } + fclose(file); + + if (verbose > 0) + printf("Found %d entries\n", count); + if (count == 0) + file_fail(prop_name); +} + static void corrections_init(void) { FILE *file; @@ -3342,6 +3411,7 @@ int main(int argc, char *argv[]) ccc_init(); nfdi_init(); nfdicf_init(); + ignore_init(); corrections_init(); hangul_decompose(); nfdi_decompose(); diff --git a/fs/unicode/utf8data.c_shipped b/fs/unicode/utf8data.c_shipped index ef15d52900d0..73a93d49b3ba 100644 --- a/fs/unicode/utf8data.c_shipped +++ b/fs/unicode/utf8data.c_shipped @@ -82,58 +82,58 @@ static const struct utf8data utf8nfdidata[] = { { 0xc0100, 20736 } }; -static const unsigned char utf8data[64080] = { +static const unsigned char utf8data[64256] = { /* nfdicf_30100 */ - 0xd7,0x07,0x66,0x84,0x0c,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x96,0x1a,0xe3,0x60,0x15, - 0xe2,0x49,0x0e,0xc1,0xe0,0x4b,0x0d,0xcf,0x86,0x65,0x2d,0x0d,0x01,0x00,0xd4,0xb8, - 0xd3,0x27,0xe2,0x03,0xa3,0xe1,0xcb,0x35,0xe0,0x29,0x22,0xcf,0x86,0xc5,0xe4,0xfa, - 0x6c,0xe3,0x45,0x68,0xe2,0xdb,0x65,0xe1,0x0e,0x65,0xe0,0xd3,0x64,0xcf,0x86,0xe5, - 0x98,0x64,0x64,0x7b,0x64,0x0b,0x00,0xd2,0x0e,0xe1,0xb3,0x3c,0xe0,0x34,0xa3,0xcf, - 0x86,0xcf,0x06,0x01,0x00,0xd1,0x0c,0xe0,0x98,0xa8,0xcf,0x86,0xcf,0x06,0x02,0xff, + 0xd7,0x07,0x66,0x84,0x0c,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x99,0x1a,0xe3,0x63,0x15, + 0xe2,0x4c,0x0e,0xc1,0xe0,0x4e,0x0d,0xcf,0x86,0x65,0x2d,0x0d,0x01,0x00,0xd4,0xb8, + 0xd3,0x27,0xe2,0x89,0xa3,0xe1,0xce,0x35,0xe0,0x2c,0x22,0xcf,0x86,0xc5,0xe4,0x15, + 0x6d,0xe3,0x60,0x68,0xe2,0xf6,0x65,0xe1,0x29,0x65,0xe0,0xee,0x64,0xcf,0x86,0xe5, + 0xb3,0x64,0x64,0x96,0x64,0x0b,0x00,0xd2,0x0e,0xe1,0xb5,0x3c,0xe0,0xba,0xa3,0xcf, + 0x86,0xcf,0x06,0x01,0x00,0xd1,0x0c,0xe0,0x1e,0xa9,0xcf,0x86,0xcf,0x06,0x02,0xff, 0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01, - 0x00,0xe4,0xdf,0x45,0xe3,0x39,0x45,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x01,0xad, - 0xd0,0x21,0xcf,0x86,0xe5,0xfb,0xa9,0xe4,0x7a,0xa9,0xe3,0x39,0xa9,0xe2,0x18,0xa9, - 0xe1,0x07,0xa9,0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4, - 0x00,0xcf,0x86,0xe5,0xdd,0xab,0xd4,0x19,0xe3,0x1c,0xab,0xe2,0xfb,0xaa,0xe1,0xea, - 0xaa,0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3, - 0x83,0xab,0xe2,0x62,0xab,0xe1,0x51,0xab,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00, - 0x01,0xff,0xe9,0x9b,0xbb,0x00,0x83,0xe2,0x68,0xf9,0xe1,0x52,0xf6,0xe0,0xcf,0xf4, - 0xcf,0x86,0xd5,0x31,0xc4,0xe3,0x51,0x4e,0xe2,0xf2,0x4c,0xe1,0x09,0xcc,0xe0,0x99, - 0x4b,0xcf,0x86,0xe5,0x8b,0x49,0xe4,0xac,0x46,0xe3,0x76,0xbc,0xe2,0xcd,0xbb,0xe1, - 0xa8,0xbb,0xe0,0x81,0xbb,0xcf,0x86,0xe5,0x4e,0xbb,0x94,0x07,0x63,0x39,0xbb,0x07, - 0x00,0x07,0x00,0xe4,0x3b,0xf4,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b, - 0xe1,0x4a,0xe1,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x39,0xe2,0xcf,0x86, - 0xe5,0xfe,0xe1,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x39,0xe2,0xcf,0x06, - 0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0xd4,0xf3,0xe3,0xbd,0xf2, - 0xd2,0xa0,0xe1,0x73,0xe6,0xd0,0x21,0xcf,0x86,0xe5,0x74,0xe3,0xe4,0xf0,0xe2,0xe3, - 0xae,0xe2,0xe2,0x8d,0xe2,0xe1,0x7b,0xe2,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00, - 0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xd0,0xe4,0xe3,0x8f,0xe4, - 0xe2,0x6e,0xe4,0xe1,0x5d,0xe4,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff, - 0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0x57,0xe5,0xe1,0x46,0xe5,0x10,0x09, - 0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x77, - 0xe5,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac, - 0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0xbd,0xe5,0xd2,0x14,0xe1,0x8c,0xe5, + 0x00,0xe4,0xe1,0x45,0xe3,0x3b,0x45,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x87,0xad, + 0xd0,0x21,0xcf,0x86,0xe5,0x81,0xaa,0xe4,0x00,0xaa,0xe3,0xbf,0xa9,0xe2,0x9e,0xa9, + 0xe1,0x8d,0xa9,0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4, + 0x00,0xcf,0x86,0xe5,0x63,0xac,0xd4,0x19,0xe3,0xa2,0xab,0xe2,0x81,0xab,0xe1,0x70, + 0xab,0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3, + 0x09,0xac,0xe2,0xe8,0xab,0xe1,0xd7,0xab,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00, + 0x01,0xff,0xe9,0x9b,0xbb,0x00,0x83,0xe2,0x19,0xfa,0xe1,0xf2,0xf6,0xe0,0x6f,0xf5, + 0xcf,0x86,0xd5,0x31,0xc4,0xe3,0x54,0x4e,0xe2,0xf5,0x4c,0xe1,0xa4,0xcc,0xe0,0x9c, + 0x4b,0xcf,0x86,0xe5,0x8e,0x49,0xe4,0xaf,0x46,0xe3,0x11,0xbd,0xe2,0x68,0xbc,0xe1, + 0x43,0xbc,0xe0,0x1c,0xbc,0xcf,0x86,0xe5,0xe9,0xbb,0x94,0x07,0x63,0xd4,0xbb,0x07, + 0x00,0x07,0x00,0xe4,0xdb,0xf4,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b, + 0xe1,0xea,0xe1,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xd9,0xe2,0xcf,0x86, + 0xe5,0x9e,0xe2,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xd9,0xe2,0xcf,0x06, + 0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x74,0xf4,0xe3,0x5d,0xf3, + 0xd2,0xa0,0xe1,0x13,0xe7,0xd0,0x21,0xcf,0x86,0xe5,0x14,0xe4,0xe4,0x90,0xe3,0xe3, + 0x4e,0xe3,0xe2,0x2d,0xe3,0xe1,0x1b,0xe3,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00, + 0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x70,0xe5,0xe3,0x2f,0xe5, + 0xe2,0x0e,0xe5,0xe1,0xfd,0xe4,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff, + 0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xf7,0xe5,0xe1,0xe6,0xe5,0x10,0x09, + 0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x17, + 0xe6,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac, + 0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x5d,0xe6,0xd2,0x14,0xe1,0x2c,0xe6, 0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1, - 0x98,0xe5,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00, - 0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0xed,0xea,0xd4,0x19,0xe3,0x26,0xea,0xe2,0x04, - 0xea,0xe1,0xf3,0xe9,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5, - 0xb7,0x00,0xd3,0x18,0xe2,0x70,0xea,0xe1,0x5f,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3, - 0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x88,0xea,0x10, + 0x38,0xe6,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00, + 0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x8d,0xeb,0xd4,0x19,0xe3,0xc6,0xea,0xe2,0xa4, + 0xea,0xe1,0x93,0xea,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5, + 0xb7,0x00,0xd3,0x18,0xe2,0x10,0xeb,0xe1,0xff,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3, + 0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x28,0xeb,0x10, 0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10, 0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08, - 0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0x8a, - 0xec,0xd4,0x1a,0xe3,0xc2,0xeb,0xe2,0xa8,0xeb,0xe1,0x95,0xeb,0x10,0x08,0x05,0xff, - 0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x0a,0xec, - 0xe1,0xf8,0xeb,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3, - 0x00,0xd2,0x13,0xe1,0x26,0xec,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff, + 0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0x2a, + 0xed,0xd4,0x1a,0xe3,0x62,0xec,0xe2,0x48,0xec,0xe1,0x35,0xec,0x10,0x08,0x05,0xff, + 0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0xaa,0xec, + 0xe1,0x98,0xec,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3, + 0x00,0xd2,0x13,0xe1,0xc6,0xec,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff, 0xe7,0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05, 0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05, - 0xff,0xe7,0xaa,0xae,0x00,0xe0,0x3c,0xef,0xcf,0x86,0xd5,0x1d,0xe4,0xb1,0xed,0xe3, - 0x6d,0xed,0xe2,0x4b,0xed,0xe1,0x3a,0xed,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f, - 0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x58,0xee,0xe2,0x34,0xee,0xe1, - 0x23,0xee,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00, - 0xd3,0x18,0xe2,0xa3,0xee,0xe1,0x92,0xee,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1, - 0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xbb,0xee,0x10,0x08,0x05, + 0xff,0xe7,0xaa,0xae,0x00,0xe0,0xdc,0xef,0xcf,0x86,0xd5,0x1d,0xe4,0x51,0xee,0xe3, + 0x0d,0xee,0xe2,0xeb,0xed,0xe1,0xda,0xed,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f, + 0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xf8,0xee,0xe2,0xd4,0xee,0xe1, + 0xc3,0xee,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00, + 0xd3,0x18,0xe2,0x43,0xef,0xe1,0x32,0xef,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1, + 0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x5b,0xef,0x10,0x08,0x05, 0xff,0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05, 0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8, 0x9e,0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, @@ -141,152 +141,152 @@ static const unsigned char utf8data[64080] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* nfdi_30100 */ - 0x57,0x04,0x01,0x00,0xc6,0xd5,0x13,0xe4,0xa8,0x59,0xe3,0xe2,0x54,0xe2,0x5b,0x4f, - 0xc1,0xe0,0x87,0x4d,0xcf,0x06,0x01,0x00,0xd4,0xb8,0xd3,0x27,0xe2,0x89,0x9f,0xe1, - 0x91,0x8d,0xe0,0x21,0x71,0xcf,0x86,0xc5,0xe4,0x80,0x69,0xe3,0xcb,0x64,0xe2,0x61, - 0x62,0xe1,0x94,0x61,0xe0,0x59,0x61,0xcf,0x86,0xe5,0x1e,0x61,0x64,0x01,0x61,0x0b, - 0x00,0xd2,0x0e,0xe1,0x3f,0xa0,0xe0,0xba,0x9f,0xcf,0x86,0xcf,0x06,0x01,0x00,0xd1, - 0x0c,0xe0,0x1e,0xa5,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd0,0x08,0xcf,0x86,0xcf, - 0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xe4,0x1b,0xb6,0xe3,0x95, - 0xad,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x87,0xa9,0xd0,0x21,0xcf,0x86,0xe5,0x81, - 0xa6,0xe4,0x00,0xa6,0xe3,0xbf,0xa5,0xe2,0x9e,0xa5,0xe1,0x8d,0xa5,0x10,0x08,0x01, - 0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0xcf,0x86,0xe5,0x63,0xa8, - 0xd4,0x19,0xe3,0xa2,0xa7,0xe2,0x81,0xa7,0xe1,0x70,0xa7,0x10,0x08,0x01,0xff,0xe9, - 0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3,0x09,0xa8,0xe2,0xe8,0xa7,0xe1, - 0xd7,0xa7,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9,0x9b,0xbb,0x00, - 0x83,0xe2,0xee,0xf5,0xe1,0xd8,0xf2,0xe0,0x55,0xf1,0xcf,0x86,0xd5,0x31,0xc4,0xe3, - 0xd5,0xcb,0xe2,0xae,0xc9,0xe1,0x8f,0xc8,0xe0,0x1f,0xbf,0xcf,0x86,0xe5,0x12,0xbb, - 0xe4,0x0b,0xba,0xe3,0xfc,0xb8,0xe2,0x53,0xb8,0xe1,0x2e,0xb8,0xe0,0x07,0xb8,0xcf, - 0x86,0xe5,0xd4,0xb7,0x94,0x07,0x63,0xbf,0xb7,0x07,0x00,0x07,0x00,0xe4,0xc1,0xf0, - 0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1,0xd0,0xdd,0xcf,0x86,0xcf, - 0x06,0x05,0x00,0xd1,0x0e,0xe0,0xbf,0xde,0xcf,0x86,0xe5,0x84,0xde,0xcf,0x06,0x11, - 0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xbf,0xde,0xcf,0x06,0x13,0x00,0xcf,0x86,0xd5,0x06, - 0xcf,0x06,0x00,0x00,0xe4,0x5a,0xf0,0xe3,0x43,0xef,0xd2,0xa0,0xe1,0xf9,0xe2,0xd0, - 0x21,0xcf,0x86,0xe5,0xfa,0xdf,0xe4,0x76,0xdf,0xe3,0x34,0xdf,0xe2,0x13,0xdf,0xe1, - 0x01,0xdf,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00, - 0xcf,0x86,0xd5,0x1c,0xe4,0x56,0xe1,0xe3,0x15,0xe1,0xe2,0xf4,0xe0,0xe1,0xe3,0xe0, - 0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6,0x00,0xd4,0x34, - 0xd3,0x18,0xe2,0xdd,0xe1,0xe1,0xcc,0xe1,0x10,0x09,0x05,0xff,0xf0,0xa1,0x9a,0xa8, - 0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0xfd,0xe1,0x91,0x11,0x10,0x09,0x05, - 0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05,0xff,0xe5,0xac, - 0xbe,0x00,0xe3,0x43,0xe2,0xd2,0x14,0xe1,0x12,0xe2,0x10,0x08,0x05,0xff,0xe5,0xaf, - 0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0x1e,0xe2,0x10,0x08,0x05,0xff, - 0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1,0xd5,0xd0,0x6a,0xcf,0x86, - 0xe5,0x73,0xe7,0xd4,0x19,0xe3,0xac,0xe6,0xe2,0x8a,0xe6,0xe1,0x79,0xe6,0x10,0x08, - 0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7,0x00,0xd3,0x18,0xe2,0xf6, - 0xe6,0xe1,0xe5,0xe6,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00,0x05,0xff,0xf0, - 0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x0e,0xe7,0x10,0x08,0x05,0xff,0xe7,0x81,0xbd, - 0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x85,0x85, - 0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7,0x86,0x9c,0x00, - 0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0x10,0xe9,0xd4,0x1a,0xe3,0x48,0xe8, - 0xe2,0x2e,0xe8,0xe1,0x1b,0xe8,0x10,0x08,0x05,0xff,0xe7,0x9b,0xb4,0x00,0x05,0xff, - 0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x90,0xe8,0xe1,0x7e,0xe8,0x10,0x08,0x05, - 0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0xd2,0x13,0xe1,0xac,0xe8, - 0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80,0x00,0xd1,0x12, - 0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00, - 0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff,0xe7,0xaa,0xae,0x00,0xe0, - 0xc2,0xeb,0xcf,0x86,0xd5,0x1d,0xe4,0x37,0xea,0xe3,0xf3,0xe9,0xe2,0xd1,0xe9,0xe1, - 0xc0,0xe9,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95, - 0x00,0xd4,0x19,0xe3,0xde,0xea,0xe2,0xba,0xea,0xe1,0xa9,0xea,0x10,0x08,0x05,0xff, - 0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3,0x18,0xe2,0x29,0xeb,0xe1, - 0x18,0xeb,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00,0x05,0xff,0xf0,0xa7,0x83, - 0x92,0x00,0xd2,0x13,0xe1,0x41,0xeb,0x10,0x08,0x05,0xff,0xe8,0x9a,0x88,0x00,0x05, - 0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c,0xa8,0x00,0x05, - 0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00,0x05,0xff,0xe4, - 0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x57,0x04,0x01,0x00,0xc6,0xd5,0x16,0xe4,0xc2,0x59,0xe3,0xfb,0x54,0xe2,0x74,0x4f, + 0xc1,0xe0,0xa0,0x4d,0xcf,0x86,0x65,0x84,0x4d,0x01,0x00,0xd4,0xb8,0xd3,0x27,0xe2, + 0x0c,0xa0,0xe1,0xdf,0x8d,0xe0,0x39,0x71,0xcf,0x86,0xc5,0xe4,0x98,0x69,0xe3,0xe3, + 0x64,0xe2,0x79,0x62,0xe1,0xac,0x61,0xe0,0x71,0x61,0xcf,0x86,0xe5,0x36,0x61,0x64, + 0x19,0x61,0x0b,0x00,0xd2,0x0e,0xe1,0xc2,0xa0,0xe0,0x3d,0xa0,0xcf,0x86,0xcf,0x06, + 0x01,0x00,0xd1,0x0c,0xe0,0xa1,0xa5,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd0,0x08, + 0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xe4,0x9e, + 0xb6,0xe3,0x18,0xae,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x0a,0xaa,0xd0,0x21,0xcf, + 0x86,0xe5,0x04,0xa7,0xe4,0x83,0xa6,0xe3,0x42,0xa6,0xe2,0x21,0xa6,0xe1,0x10,0xa6, + 0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0xcf,0x86, + 0xe5,0xe6,0xa8,0xd4,0x19,0xe3,0x25,0xa8,0xe2,0x04,0xa8,0xe1,0xf3,0xa7,0x10,0x08, + 0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3,0x8c,0xa8,0xe2, + 0x6b,0xa8,0xe1,0x5a,0xa8,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9, + 0x9b,0xbb,0x00,0x83,0xe2,0x9c,0xf6,0xe1,0x75,0xf3,0xe0,0xf2,0xf1,0xcf,0x86,0xd5, + 0x31,0xc4,0xe3,0x6d,0xcc,0xe2,0x46,0xca,0xe1,0x27,0xc9,0xe0,0xb7,0xbf,0xcf,0x86, + 0xe5,0xaa,0xbb,0xe4,0xa3,0xba,0xe3,0x94,0xb9,0xe2,0xeb,0xb8,0xe1,0xc6,0xb8,0xe0, + 0x9f,0xb8,0xcf,0x86,0xe5,0x6c,0xb8,0x94,0x07,0x63,0x57,0xb8,0x07,0x00,0x07,0x00, + 0xe4,0x5e,0xf1,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1,0x6d,0xde, + 0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x5c,0xdf,0xcf,0x86,0xe5,0x21,0xdf, + 0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x5c,0xdf,0xcf,0x06,0x13,0x00,0xcf, + 0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0xf7,0xf0,0xe3,0xe0,0xef,0xd2,0xa0,0xe1, + 0x96,0xe3,0xd0,0x21,0xcf,0x86,0xe5,0x97,0xe0,0xe4,0x13,0xe0,0xe3,0xd1,0xdf,0xe2, + 0xb0,0xdf,0xe1,0x9e,0xdf,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4, + 0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xf3,0xe1,0xe3,0xb2,0xe1,0xe2,0x91,0xe1, + 0xe1,0x80,0xe1,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6, + 0x00,0xd4,0x34,0xd3,0x18,0xe2,0x7a,0xe2,0xe1,0x69,0xe2,0x10,0x09,0x05,0xff,0xf0, + 0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x9a,0xe2,0x91,0x11, + 0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05, + 0xff,0xe5,0xac,0xbe,0x00,0xe3,0xe0,0xe2,0xd2,0x14,0xe1,0xaf,0xe2,0x10,0x08,0x05, + 0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0xbb,0xe2,0x10, + 0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1,0xd5,0xd0, + 0x6a,0xcf,0x86,0xe5,0x10,0xe8,0xd4,0x19,0xe3,0x49,0xe7,0xe2,0x27,0xe7,0xe1,0x16, + 0xe7,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7,0x00,0xd3, + 0x18,0xe2,0x93,0xe7,0xe1,0x82,0xe7,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00, + 0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xab,0xe7,0x10,0x08,0x05,0xff, + 0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08,0x05,0xff, + 0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7, + 0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0xad,0xe9,0xd4,0x1a, + 0xe3,0xe5,0xe8,0xe2,0xcb,0xe8,0xe1,0xb8,0xe8,0x10,0x08,0x05,0xff,0xe7,0x9b,0xb4, + 0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x2d,0xe9,0xe1,0x1b,0xe9, + 0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0xd2,0x13, + 0xe1,0x49,0xe9,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80, + 0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff,0xf0,0xa5, + 0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff,0xe7,0xaa, + 0xae,0x00,0xe0,0x5f,0xec,0xcf,0x86,0xd5,0x1d,0xe4,0xd4,0xea,0xe3,0x90,0xea,0xe2, + 0x6e,0xea,0xe1,0x5d,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff, + 0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x7b,0xeb,0xe2,0x57,0xeb,0xe1,0x46,0xeb,0x10, + 0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3,0x18,0xe2, + 0xc6,0xeb,0xe1,0xb5,0xeb,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00,0x05,0xff, + 0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xde,0xeb,0x10,0x08,0x05,0xff,0xe8,0x9a, + 0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c, + 0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00, + 0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* nfdicf_30200 */ - 0xd7,0x07,0x66,0x84,0x05,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x96,0x13,0xe3,0x60,0x0e, - 0xe2,0x49,0x07,0xc1,0xe0,0x4b,0x06,0xcf,0x86,0x65,0x2d,0x06,0x01,0x00,0xd4,0x2a, - 0xe3,0xce,0x35,0xe2,0x02,0x9c,0xe1,0xca,0x2e,0xe0,0x28,0x1b,0xcf,0x86,0xc5,0xe4, - 0xf9,0x65,0xe3,0x44,0x61,0xe2,0xda,0x5e,0xe1,0x0d,0x5e,0xe0,0xd2,0x5d,0xcf,0x86, - 0xe5,0x97,0x5d,0x64,0x7a,0x5d,0x0b,0x00,0x83,0xe2,0xf6,0xf2,0xe1,0xe0,0xef,0xe0, - 0x5d,0xee,0xcf,0x86,0xd5,0x31,0xc4,0xe3,0xdf,0x47,0xe2,0x80,0x46,0xe1,0x97,0xc5, - 0xe0,0x27,0x45,0xcf,0x86,0xe5,0x19,0x43,0xe4,0x3a,0x40,0xe3,0x04,0xb6,0xe2,0x5b, - 0xb5,0xe1,0x36,0xb5,0xe0,0x0f,0xb5,0xcf,0x86,0xe5,0xdc,0xb4,0x94,0x07,0x63,0xc7, - 0xb4,0x07,0x00,0x07,0x00,0xe4,0xc9,0xed,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00, - 0xd2,0x0b,0xe1,0xd8,0xda,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xc7,0xdb, - 0xcf,0x86,0xe5,0x8c,0xdb,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xc7,0xdb, - 0xcf,0x06,0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x62,0xed,0xe3, - 0x4b,0xec,0xd2,0xa0,0xe1,0x01,0xe0,0xd0,0x21,0xcf,0x86,0xe5,0x02,0xdd,0xe4,0x7e, - 0xdc,0xe3,0x3c,0xdc,0xe2,0x1b,0xdc,0xe1,0x09,0xdc,0x10,0x08,0x05,0xff,0xe4,0xb8, - 0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x5e,0xde,0xe3, - 0x1d,0xde,0xe2,0xfc,0xdd,0xe1,0xeb,0xdd,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00, - 0x05,0xff,0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xe5,0xde,0xe1,0xd4,0xde, + 0xd7,0x07,0x66,0x84,0x05,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x99,0x13,0xe3,0x63,0x0e, + 0xe2,0x4c,0x07,0xc1,0xe0,0x4e,0x06,0xcf,0x86,0x65,0x2d,0x06,0x01,0x00,0xd4,0x2a, + 0xe3,0xd0,0x35,0xe2,0x88,0x9c,0xe1,0xcd,0x2e,0xe0,0x2b,0x1b,0xcf,0x86,0xc5,0xe4, + 0x14,0x66,0xe3,0x5f,0x61,0xe2,0xf5,0x5e,0xe1,0x28,0x5e,0xe0,0xed,0x5d,0xcf,0x86, + 0xe5,0xb2,0x5d,0x64,0x95,0x5d,0x0b,0x00,0x83,0xe2,0xa7,0xf3,0xe1,0x80,0xf0,0xe0, + 0xfd,0xee,0xcf,0x86,0xd5,0x31,0xc4,0xe3,0xe2,0x47,0xe2,0x83,0x46,0xe1,0x32,0xc6, + 0xe0,0x2a,0x45,0xcf,0x86,0xe5,0x1c,0x43,0xe4,0x3d,0x40,0xe3,0x9f,0xb6,0xe2,0xf6, + 0xb5,0xe1,0xd1,0xb5,0xe0,0xaa,0xb5,0xcf,0x86,0xe5,0x77,0xb5,0x94,0x07,0x63,0x62, + 0xb5,0x07,0x00,0x07,0x00,0xe4,0x69,0xee,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00, + 0xd2,0x0b,0xe1,0x78,0xdb,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x67,0xdc, + 0xcf,0x86,0xe5,0x2c,0xdc,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x67,0xdc, + 0xcf,0x06,0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x02,0xee,0xe3, + 0xeb,0xec,0xd2,0xa0,0xe1,0xa1,0xe0,0xd0,0x21,0xcf,0x86,0xe5,0xa2,0xdd,0xe4,0x1e, + 0xdd,0xe3,0xdc,0xdc,0xe2,0xbb,0xdc,0xe1,0xa9,0xdc,0x10,0x08,0x05,0xff,0xe4,0xb8, + 0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xfe,0xde,0xe3, + 0xbd,0xde,0xe2,0x9c,0xde,0xe1,0x8b,0xde,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00, + 0x05,0xff,0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0x85,0xdf,0xe1,0x74,0xdf, 0x10,0x09,0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00, - 0xe2,0x05,0xdf,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff, - 0xe5,0xac,0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x4b,0xdf,0xd2,0x14,0xe1, - 0x1a,0xdf,0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98, - 0x00,0xe1,0x26,0xdf,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0, - 0xa2,0x00,0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x7b,0xe4,0xd4,0x19,0xe3,0xb4,0xe3, - 0xe2,0x92,0xe3,0xe1,0x81,0xe3,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff, - 0xe6,0xb5,0xb7,0x00,0xd3,0x18,0xe2,0xfe,0xe3,0xe1,0xed,0xe3,0x10,0x09,0x05,0xff, - 0xf0,0xa3,0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x16, + 0xe2,0xa5,0xdf,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff, + 0xe5,0xac,0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0xeb,0xdf,0xd2,0x14,0xe1, + 0xba,0xdf,0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98, + 0x00,0xe1,0xc6,0xdf,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0, + 0xa2,0x00,0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x1b,0xe5,0xd4,0x19,0xe3,0x54,0xe4, + 0xe2,0x32,0xe4,0xe1,0x21,0xe4,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff, + 0xe6,0xb5,0xb7,0x00,0xd3,0x18,0xe2,0x9e,0xe4,0xe1,0x8d,0xe4,0x10,0x09,0x05,0xff, + 0xf0,0xa3,0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xb6, 0xe4,0x10,0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1, 0x11,0x10,0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00, 0x10,0x08,0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86, - 0xe5,0x18,0xe6,0xd4,0x1a,0xe3,0x50,0xe5,0xe2,0x36,0xe5,0xe1,0x23,0xe5,0x10,0x08, + 0xe5,0xb8,0xe6,0xd4,0x1a,0xe3,0xf0,0xe5,0xe2,0xd6,0xe5,0xe1,0xc3,0xe5,0x10,0x08, 0x05,0xff,0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2, - 0x98,0xe5,0xe1,0x86,0xe5,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4, - 0x83,0xa3,0x00,0xd2,0x13,0xe1,0xb4,0xe5,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00, + 0x38,0xe6,0xe1,0x26,0xe6,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4, + 0x83,0xa3,0x00,0xd2,0x13,0xe1,0x54,0xe6,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00, 0x05,0xff,0xe7,0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc, 0x00,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7, - 0x00,0x05,0xff,0xe7,0xaa,0xae,0x00,0xe0,0xca,0xe8,0xcf,0x86,0xd5,0x1d,0xe4,0x3f, - 0xe7,0xe3,0xfb,0xe6,0xe2,0xd9,0xe6,0xe1,0xc8,0xe6,0x10,0x09,0x05,0xff,0xf0,0xa3, - 0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xe6,0xe7,0xe2,0xc2, - 0xe7,0xe1,0xb1,0xe7,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f, - 0x8a,0x00,0xd3,0x18,0xe2,0x31,0xe8,0xe1,0x20,0xe8,0x10,0x09,0x05,0xff,0xf0,0xa6, - 0xbe,0xb1,0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x49,0xe8,0x10, + 0x00,0x05,0xff,0xe7,0xaa,0xae,0x00,0xe0,0x6a,0xe9,0xcf,0x86,0xd5,0x1d,0xe4,0xdf, + 0xe7,0xe3,0x9b,0xe7,0xe2,0x79,0xe7,0xe1,0x68,0xe7,0x10,0x09,0x05,0xff,0xf0,0xa3, + 0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x86,0xe8,0xe2,0x62, + 0xe8,0xe1,0x51,0xe8,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f, + 0x8a,0x00,0xd3,0x18,0xe2,0xd1,0xe8,0xe1,0xc0,0xe8,0x10,0x09,0x05,0xff,0xf0,0xa6, + 0xbe,0xb1,0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xe9,0xe8,0x10, 0x08,0x05,0xff,0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10, 0x08,0x05,0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05, 0xff,0xe8,0x9e,0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00, /* nfdi_30200 */ - 0x57,0x04,0x01,0x00,0xc6,0xd5,0x13,0xe4,0x68,0x53,0xe3,0xa2,0x4e,0xe2,0x1b,0x49, - 0xc1,0xe0,0x47,0x47,0xcf,0x06,0x01,0x00,0xd4,0x2a,0xe3,0x99,0x99,0xe2,0x48,0x99, - 0xe1,0x50,0x87,0xe0,0xe0,0x6a,0xcf,0x86,0xc5,0xe4,0x3f,0x63,0xe3,0x8a,0x5e,0xe2, - 0x20,0x5c,0xe1,0x53,0x5b,0xe0,0x18,0x5b,0xcf,0x86,0xe5,0xdd,0x5a,0x64,0xc0,0x5a, - 0x0b,0x00,0x83,0xe2,0x3c,0xf0,0xe1,0x26,0xed,0xe0,0xa3,0xeb,0xcf,0x86,0xd5,0x31, - 0xc4,0xe3,0x23,0xc6,0xe2,0xfc,0xc3,0xe1,0xdd,0xc2,0xe0,0x6d,0xb9,0xcf,0x86,0xe5, - 0x60,0xb5,0xe4,0x59,0xb4,0xe3,0x4a,0xb3,0xe2,0xa1,0xb2,0xe1,0x7c,0xb2,0xe0,0x55, - 0xb2,0xcf,0x86,0xe5,0x22,0xb2,0x94,0x07,0x63,0x0d,0xb2,0x07,0x00,0x07,0x00,0xe4, - 0x0f,0xeb,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1,0x1e,0xd8,0xcf, - 0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x0d,0xd9,0xcf,0x86,0xe5,0xd2,0xd8,0xcf, - 0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x0d,0xd9,0xcf,0x06,0x13,0x00,0xcf,0x86, - 0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0xa8,0xea,0xe3,0x91,0xe9,0xd2,0xa0,0xe1,0x47, - 0xdd,0xd0,0x21,0xcf,0x86,0xe5,0x48,0xda,0xe4,0xc4,0xd9,0xe3,0x82,0xd9,0xe2,0x61, - 0xd9,0xe1,0x4f,0xd9,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4,0xb8, - 0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xa4,0xdb,0xe3,0x63,0xdb,0xe2,0x42,0xdb,0xe1, - 0x31,0xdb,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6,0x00, - 0xd4,0x34,0xd3,0x18,0xe2,0x2b,0xdc,0xe1,0x1a,0xdc,0x10,0x09,0x05,0xff,0xf0,0xa1, - 0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x4b,0xdc,0x91,0x11,0x10, - 0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05,0xff, - 0xe5,0xac,0xbe,0x00,0xe3,0x91,0xdc,0xd2,0x14,0xe1,0x60,0xdc,0x10,0x08,0x05,0xff, - 0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0x6c,0xdc,0x10,0x08, - 0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1,0xd5,0xd0,0x6a, - 0xcf,0x86,0xe5,0xc1,0xe1,0xd4,0x19,0xe3,0xfa,0xe0,0xe2,0xd8,0xe0,0xe1,0xc7,0xe0, - 0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7,0x00,0xd3,0x18, - 0xe2,0x44,0xe1,0xe1,0x33,0xe1,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00,0x05, - 0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x5c,0xe1,0x10,0x08,0x05,0xff,0xe7, - 0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe7, - 0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7,0x86, - 0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0x5e,0xe3,0xd4,0x1a,0xe3, - 0x96,0xe2,0xe2,0x7c,0xe2,0xe1,0x69,0xe2,0x10,0x08,0x05,0xff,0xe7,0x9b,0xb4,0x00, - 0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0xde,0xe2,0xe1,0xcc,0xe2,0x10, - 0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0xd2,0x13,0xe1, - 0xfa,0xe2,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80,0x00, - 0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff,0xf0,0xa5,0xaa, - 0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff,0xe7,0xaa,0xae, - 0x00,0xe0,0x10,0xe6,0xcf,0x86,0xd5,0x1d,0xe4,0x85,0xe4,0xe3,0x41,0xe4,0xe2,0x1f, - 0xe4,0xe1,0x0e,0xe4,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff,0xe4, - 0x8f,0x95,0x00,0xd4,0x19,0xe3,0x2c,0xe5,0xe2,0x08,0xe5,0xe1,0xf7,0xe4,0x10,0x08, - 0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3,0x18,0xe2,0x77, - 0xe5,0xe1,0x66,0xe5,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00,0x05,0xff,0xf0, - 0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x8f,0xe5,0x10,0x08,0x05,0xff,0xe8,0x9a,0x88, - 0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c,0xa8, - 0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00,0x05, - 0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x57,0x04,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x82,0x53,0xe3,0xbb,0x4e,0xe2,0x34,0x49, + 0xc1,0xe0,0x60,0x47,0xcf,0x86,0x65,0x44,0x47,0x01,0x00,0xd4,0x2a,0xe3,0x1c,0x9a, + 0xe2,0xcb,0x99,0xe1,0x9e,0x87,0xe0,0xf8,0x6a,0xcf,0x86,0xc5,0xe4,0x57,0x63,0xe3, + 0xa2,0x5e,0xe2,0x38,0x5c,0xe1,0x6b,0x5b,0xe0,0x30,0x5b,0xcf,0x86,0xe5,0xf5,0x5a, + 0x64,0xd8,0x5a,0x0b,0x00,0x83,0xe2,0xea,0xf0,0xe1,0xc3,0xed,0xe0,0x40,0xec,0xcf, + 0x86,0xd5,0x31,0xc4,0xe3,0xbb,0xc6,0xe2,0x94,0xc4,0xe1,0x75,0xc3,0xe0,0x05,0xba, + 0xcf,0x86,0xe5,0xf8,0xb5,0xe4,0xf1,0xb4,0xe3,0xe2,0xb3,0xe2,0x39,0xb3,0xe1,0x14, + 0xb3,0xe0,0xed,0xb2,0xcf,0x86,0xe5,0xba,0xb2,0x94,0x07,0x63,0xa5,0xb2,0x07,0x00, + 0x07,0x00,0xe4,0xac,0xeb,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1, + 0xbb,0xd8,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xaa,0xd9,0xcf,0x86,0xe5, + 0x6f,0xd9,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xaa,0xd9,0xcf,0x06,0x13, + 0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x45,0xeb,0xe3,0x2e,0xea,0xd2, + 0xa0,0xe1,0xe4,0xdd,0xd0,0x21,0xcf,0x86,0xe5,0xe5,0xda,0xe4,0x61,0xda,0xe3,0x1f, + 0xda,0xe2,0xfe,0xd9,0xe1,0xec,0xd9,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05, + 0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x41,0xdc,0xe3,0x00,0xdc,0xe2, + 0xdf,0xdb,0xe1,0xce,0xdb,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5, + 0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xc8,0xdc,0xe1,0xb7,0xdc,0x10,0x09,0x05, + 0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0xe8,0xdc, + 0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88, + 0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x2e,0xdd,0xd2,0x14,0xe1,0xfd,0xdc,0x10, + 0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0x09, + 0xdd,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1, + 0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x5e,0xe2,0xd4,0x19,0xe3,0x97,0xe1,0xe2,0x75,0xe1, + 0xe1,0x64,0xe1,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7, + 0x00,0xd3,0x18,0xe2,0xe1,0xe1,0xe1,0xd0,0xe1,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd, + 0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xf9,0xe1,0x10,0x08, + 0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08, + 0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05, + 0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0xfb,0xe3, + 0xd4,0x1a,0xe3,0x33,0xe3,0xe2,0x19,0xe3,0xe1,0x06,0xe3,0x10,0x08,0x05,0xff,0xe7, + 0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x7b,0xe3,0xe1, + 0x69,0xe3,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00, + 0xd2,0x13,0xe1,0x97,0xe3,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7, + 0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff, + 0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff, + 0xe7,0xaa,0xae,0x00,0xe0,0xad,0xe6,0xcf,0x86,0xd5,0x1d,0xe4,0x22,0xe5,0xe3,0xde, + 0xe4,0xe2,0xbc,0xe4,0xe1,0xab,0xe4,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00, + 0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xc9,0xe5,0xe2,0xa5,0xe5,0xe1,0x94, + 0xe5,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3, + 0x18,0xe2,0x14,0xe6,0xe1,0x03,0xe6,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00, + 0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x2c,0xe6,0x10,0x08,0x05,0xff, + 0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, + 0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e, + 0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* nfdicf_c0100 */ 0xd7,0xb0,0x56,0x04,0x01,0x00,0x95,0xa8,0xd4,0x5e,0xd3,0x2e,0xd2,0x16,0xd1,0x0a, 0x10,0x04,0x01,0x00,0x01,0xff,0x61,0x00,0x10,0x06,0x01,0xff,0x62,0x00,0x01,0xff, @@ -299,3174 +299,3184 @@ static const unsigned char utf8data[64080] = { 0xd1,0x0c,0x10,0x06,0x01,0xff,0x74,0x00,0x01,0xff,0x75,0x00,0x10,0x06,0x01,0xff, 0x76,0x00,0x01,0xff,0x77,0x00,0x92,0x16,0xd1,0x0c,0x10,0x06,0x01,0xff,0x78,0x00, 0x01,0xff,0x79,0x00,0x10,0x06,0x01,0xff,0x7a,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0xc6,0xe5,0xf6,0x14,0xe4,0x6c,0x0d,0xe3,0x36,0x08,0xe2,0x1f,0x01,0xc1,0xd0,0x21, - 0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x13,0x52,0x04,0x01,0x00, - 0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xce,0xbc,0x00,0x01,0x00,0x01,0x00,0xcf, - 0x86,0xe5,0x9d,0x44,0xd4,0x7f,0xd3,0x3f,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x61,0xcc, - 0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc, - 0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x07,0x01,0xff,0xc3,0xa6,0x00,0x01, - 0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x80, - 0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x82,0x00,0x01, - 0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x80,0x00,0x01, - 0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00,0x01,0xff,0x69, - 0xcc,0x88,0x00,0xd3,0x3b,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff,0xc3,0xb0,0x00, - 0x01,0xff,0x6e,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80,0x00,0x01,0xff, - 0x6f,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82,0x00,0x01,0xff, - 0x6f,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1f, - 0xd1,0x0f,0x10,0x07,0x01,0xff,0xc3,0xb8,0x00,0x01,0xff,0x75,0xcc,0x80,0x00,0x10, - 0x08,0x01,0xff,0x75,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x82,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x75,0xcc,0x88,0x00,0x01,0xff,0x79,0xcc,0x81,0x00,0x10,0x07,0x01, - 0xff,0xc3,0xbe,0x00,0x01,0xff,0x73,0x73,0x00,0xe1,0xd4,0x03,0xe0,0xeb,0x01,0xcf, - 0x86,0xd5,0xfb,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61, - 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x86, - 0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa8, - 0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x63,0xcc,0x81,0x00,0x01, - 0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x63,0xcc,0x82, - 0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x63,0xcc,0x87,0x00,0x01, - 0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x63,0xcc,0x8c,0x00,0x01, - 0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x8c,0x00,0x01,0xff,0x64, - 0xcc,0x8c,0x00,0xd3,0x3b,0xd2,0x1b,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc4,0x91,0x00, - 0x01,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x84,0x00,0x01,0xff,0x65,0xcc,0x84,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0x86,0x00, - 0x10,0x08,0x01,0xff,0x65,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0xa8,0x00,0x01,0xff,0x65,0xcc,0xa8,0x00, - 0x10,0x08,0x01,0xff,0x65,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x67,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82,0x00,0x10,0x08, - 0x01,0xff,0x67,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4,0x7b,0xd3,0x3b, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x87,0x00,0x01,0xff,0x67,0xcc, - 0x87,0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0xa7,0x00,0x01,0xff,0x67,0xcc,0xa7,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x68,0xcc,0x82,0x00,0x01,0xff,0x68,0xcc,0x82,0x00, - 0x10,0x07,0x01,0xff,0xc4,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x69,0xcc,0x83,0x00,0x01,0xff,0x69,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x69, - 0xcc,0x84,0x00,0x01,0xff,0x69,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69, - 0xcc,0x86,0x00,0x01,0xff,0x69,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0xa8, - 0x00,0x01,0xff,0x69,0xcc,0xa8,0x00,0xd3,0x37,0xd2,0x17,0xd1,0x0c,0x10,0x08,0x01, - 0xff,0x69,0xcc,0x87,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc4,0xb3,0x00,0x01,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x6a,0xcc,0x82,0x00,0x01,0xff,0x6a,0xcc,0x82,0x00, - 0x10,0x08,0x01,0xff,0x6b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7,0x00,0xd2,0x1c, - 0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6c,0xcc,0x81,0x00,0x10,0x08,0x01,0xff, - 0x6c,0xcc,0x81,0x00,0x01,0xff,0x6c,0xcc,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x6c,0xcc,0xa7,0x00,0x01,0xff,0x6c,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x6c,0xcc, - 0x8c,0x00,0x01,0xff,0xc5,0x80,0x00,0xcf,0x86,0xd5,0xed,0xd4,0x72,0xd3,0x37,0xd2, - 0x17,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc5,0x82,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0x6e,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x81,0x00, - 0x01,0xff,0x6e,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x01,0xff, - 0x6e,0xcc,0x8c,0x00,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x8c,0x00, - 0x01,0xff,0xca,0xbc,0x6e,0x00,0x10,0x07,0x01,0xff,0xc5,0x8b,0x00,0x01,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0x84,0x00,0x10, - 0x08,0x01,0xff,0x6f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00,0xd3,0x3b,0xd2, - 0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01,0xff,0x6f,0xcc,0x8b, - 0x00,0x10,0x07,0x01,0xff,0xc5,0x93,0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x72,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x72,0xcc, - 0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x72,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x73,0xcc, - 0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x73,0xcc, - 0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x73,0xcc,0xa7,0x00, - 0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x7b,0xd3,0x3b,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x73,0xcc,0x8c,0x00,0x01,0xff,0x73,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff, - 0x74,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x74,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c,0x00,0x10,0x07,0x01,0xff,0xc5,0xa7, - 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x83,0x00,0x01, - 0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x84,0x00,0x01,0xff,0x75, - 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x86,0x00,0x01,0xff,0x75, - 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x8a,0x00,0x01,0xff,0x75,0xcc,0x8a, - 0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x8b,0x00,0x01, - 0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa8,0x00,0x01,0xff,0x75, - 0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x82,0x00,0x01,0xff,0x77, - 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x82,0x00,0x01,0xff,0x79,0xcc,0x82, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x79,0xcc,0x88,0x00,0x01,0xff,0x7a, - 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff,0x7a,0xcc,0x87, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff,0x7a,0xcc,0x8c, - 0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0xff,0x73,0x00,0xe0,0x65,0x01, - 0xcf,0x86,0xd5,0xb4,0xd4,0x5a,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x01,0x00, - 0x01,0xff,0xc9,0x93,0x00,0x10,0x07,0x01,0xff,0xc6,0x83,0x00,0x01,0x00,0xd1,0x0b, - 0x10,0x07,0x01,0xff,0xc6,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc9,0x94,0x00, - 0x01,0xff,0xc6,0x88,0x00,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc9, - 0x96,0x00,0x10,0x07,0x01,0xff,0xc9,0x97,0x00,0x01,0xff,0xc6,0x8c,0x00,0x51,0x04, - 0x01,0x00,0x10,0x07,0x01,0xff,0xc7,0x9d,0x00,0x01,0xff,0xc9,0x99,0x00,0xd3,0x32, - 0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0x9b,0x00,0x01,0xff,0xc6,0x92,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xa0,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc9, - 0xa3,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc9,0xa9,0x00,0x01,0xff,0xc9,0xa8,0x00, - 0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0x99,0x00,0x01,0x00,0x01,0x00,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xc9,0xaf,0x00,0x01,0xff,0xc9,0xb2,0x00,0x10,0x04,0x01, - 0x00,0x01,0xff,0xc9,0xb5,0x00,0xd4,0x5d,0xd3,0x34,0xd2,0x1b,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x10,0x07,0x01,0xff, - 0xc6,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0xa5,0x00,0x01,0x00, - 0x10,0x07,0x01,0xff,0xca,0x80,0x00,0x01,0xff,0xc6,0xa8,0x00,0xd2,0x0f,0x91,0x0b, - 0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x83,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01, - 0xff,0xc6,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x88,0x00,0x01,0xff,0x75, - 0xcc,0x9b,0x00,0xd3,0x33,0xd2,0x1d,0xd1,0x0f,0x10,0x08,0x01,0xff,0x75,0xcc,0x9b, - 0x00,0x01,0xff,0xca,0x8a,0x00,0x10,0x07,0x01,0xff,0xca,0x8b,0x00,0x01,0xff,0xc6, - 0xb4,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc6,0xb6,0x00,0x10,0x04,0x01, - 0x00,0x01,0xff,0xca,0x92,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0xb9, - 0x00,0x01,0x00,0x01,0x00,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0xbd,0x00,0x01,0x00, - 0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x44,0xd3,0x16,0x52,0x04,0x01,0x00,0x51,0x07, - 0x01,0xff,0xc7,0x86,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc7,0x89,0x00,0xd2,0x12, - 0x91,0x0b,0x10,0x07,0x01,0xff,0xc7,0x89,0x00,0x01,0x00,0x01,0xff,0xc7,0x8c,0x00, - 0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x61,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff, - 0x61,0xcc,0x8c,0x00,0x01,0xff,0x69,0xcc,0x8c,0x00,0xd3,0x46,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x10,0x08, - 0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x8c,0x00,0xd1,0x12,0x10,0x08, - 0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x10,0x0a, - 0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81,0x00, - 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff, - 0x75,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x8c,0x00, - 0x01,0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01,0xff,0x75,0xcc, - 0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00, - 0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x87,0xd3,0x41,0xd2,0x26,0xd1,0x14, - 0x10,0x0a,0x01,0xff,0x61,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x87,0xcc, - 0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x84,0x00,0x01,0xff,0xc3,0xa6,0xcc, - 0x84,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc7,0xa5,0x00,0x01,0x00,0x10,0x08,0x01, - 0xff,0x67,0xcc,0x8c,0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x10,0x08,0x01, - 0xff,0x6f,0xcc,0xa8,0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14,0x10,0x0a,0x01, - 0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x10, - 0x09,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0xd3, - 0x38,0xd2,0x1a,0xd1,0x0f,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00,0x01,0xff,0xc7, - 0xb3,0x00,0x10,0x07,0x01,0xff,0xc7,0xb3,0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x67,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x10,0x07,0x04,0xff,0xc6, - 0x95,0x00,0x04,0xff,0xc6,0xbf,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x6e, - 0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x8a, - 0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01, - 0xff,0xc3,0xa6,0xcc,0x81,0x00,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00,0x10,0x09,0x01, - 0xff,0xc3,0xb8,0xcc,0x81,0x00,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00,0xe2,0x31,0x02, - 0xe1,0xad,0x44,0xe0,0xc8,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0x8f,0x00,0x01,0xff,0x61,0xcc,0x8f,0x00, - 0x10,0x08,0x01,0xff,0x61,0xcc,0x91,0x00,0x01,0xff,0x61,0xcc,0x91,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x65,0xcc,0x8f,0x00,0x01,0xff,0x65,0xcc,0x8f,0x00,0x10,0x08, - 0x01,0xff,0x65,0xcc,0x91,0x00,0x01,0xff,0x65,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x69,0xcc,0x8f,0x00,0x01,0xff,0x69,0xcc,0x8f,0x00,0x10,0x08, - 0x01,0xff,0x69,0xcc,0x91,0x00,0x01,0xff,0x69,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x6f,0xcc,0x8f,0x00,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff, - 0x6f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc,0x91,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x72,0xcc,0x8f,0x00,0x01,0xff,0x72,0xcc,0x8f,0x00,0x10,0x08, - 0x01,0xff,0x72,0xcc,0x91,0x00,0x01,0xff,0x72,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x75,0xcc,0x8f,0x00,0x01,0xff,0x75,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff, - 0x75,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x04,0xff,0x73,0xcc,0xa6,0x00,0x04,0xff,0x73,0xcc,0xa6,0x00,0x10,0x08,0x04,0xff, - 0x74,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc,0xa6,0x00,0xd1,0x0b,0x10,0x07,0x04,0xff, - 0xc8,0x9d,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x68,0xcc,0x8c,0x00,0x04,0xff,0x68, - 0xcc,0x8c,0x00,0xd4,0x79,0xd3,0x31,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06,0xff,0xc6, - 0x9e,0x00,0x07,0x00,0x10,0x07,0x04,0xff,0xc8,0xa3,0x00,0x04,0x00,0xd1,0x0b,0x10, - 0x07,0x04,0xff,0xc8,0xa5,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x61,0xcc,0x87,0x00, - 0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x65,0xcc, - 0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x6f,0xcc,0x88,0xcc, - 0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10,0x0a,0x04,0xff, - 0x6f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x10,0x08, - 0x04,0xff,0x6f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0xd3,0x27,0xe2,0x0b, - 0x43,0xd1,0x14,0x10,0x0a,0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00,0x04,0xff,0x6f, - 0xcc,0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x79,0xcc,0x84,0x00,0x04,0xff,0x79, - 0xcc,0x84,0x00,0xd2,0x13,0x51,0x04,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0xa5, - 0x00,0x08,0xff,0xc8,0xbc,0x00,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08,0xff,0xc6,0x9a, - 0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0xa6,0x00,0x08,0x00,0xcf,0x86,0x95,0x5f,0x94, - 0x5b,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08,0xff,0xc9,0x82,0x00, - 0x10,0x04,0x09,0x00,0x09,0xff,0xc6,0x80,0x00,0xd1,0x0e,0x10,0x07,0x09,0xff,0xca, - 0x89,0x00,0x09,0xff,0xca,0x8c,0x00,0x10,0x07,0x09,0xff,0xc9,0x87,0x00,0x09,0x00, - 0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9,0x89,0x00,0x09,0x00,0x10,0x07,0x09, - 0xff,0xc9,0x8b,0x00,0x09,0x00,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9,0x8d,0x00,0x09, - 0x00,0x10,0x07,0x09,0xff,0xc9,0x8f,0x00,0x09,0x00,0x01,0x00,0x01,0x00,0xd1,0x8b, - 0xd0,0x0c,0xcf,0x86,0xe5,0xfa,0x42,0x64,0xd9,0x42,0x01,0xe6,0xcf,0x86,0xd5,0x2a, - 0xe4,0x82,0x43,0xe3,0x69,0x43,0xd2,0x11,0xe1,0x48,0x43,0x10,0x07,0x01,0xff,0xcc, - 0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0xe1,0x4f,0x43,0x10,0x09,0x01,0xff,0xcc,0x88, - 0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0x00,0xd4,0x0f,0x93,0x0b,0x92,0x07,0x61,0x94, - 0x43,0x01,0xea,0x06,0xe6,0x06,0xe6,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x0a, - 0xff,0xcd,0xb1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xcd,0xb3,0x00,0x0a,0x00,0xd1, - 0x0b,0x10,0x07,0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x10,0x07,0x0a,0xff,0xcd,0xb7, - 0x00,0x0a,0x00,0xd2,0x07,0x61,0x80,0x43,0x00,0x00,0x51,0x04,0x09,0x00,0x10,0x06, - 0x01,0xff,0x3b,0x00,0x10,0xff,0xcf,0xb3,0x00,0xe0,0x31,0x01,0xcf,0x86,0xd5,0xd3, - 0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x01,0x00,0x01,0xff, - 0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x81,0x00,0x01,0xff, - 0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x81,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00, - 0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x00,0x00,0x10, - 0x09,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0xd3, - 0x3c,0xd2,0x20,0xd1,0x12,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00, - 0x01,0xff,0xce,0xb1,0x00,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01,0xff,0xce,0xb3, - 0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb4,0x00,0x01,0xff,0xce,0xb5,0x00,0x10, - 0x07,0x01,0xff,0xce,0xb6,0x00,0x01,0xff,0xce,0xb7,0x00,0xd2,0x1c,0xd1,0x0e,0x10, - 0x07,0x01,0xff,0xce,0xb8,0x00,0x01,0xff,0xce,0xb9,0x00,0x10,0x07,0x01,0xff,0xce, - 0xba,0x00,0x01,0xff,0xce,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xbc,0x00, - 0x01,0xff,0xce,0xbd,0x00,0x10,0x07,0x01,0xff,0xce,0xbe,0x00,0x01,0xff,0xce,0xbf, - 0x00,0xe4,0x6e,0x43,0xd3,0x35,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01,0xff,0xcf,0x80, - 0x00,0x01,0xff,0xcf,0x81,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x83,0x00,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xcf,0x84,0x00,0x01,0xff,0xcf,0x85,0x00,0x10,0x07,0x01, - 0xff,0xcf,0x86,0x00,0x01,0xff,0xcf,0x87,0x00,0xe2,0x14,0x43,0xd1,0x0e,0x10,0x07, - 0x01,0xff,0xcf,0x88,0x00,0x01,0xff,0xcf,0x89,0x00,0x10,0x09,0x01,0xff,0xce,0xb9, - 0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc,0x88,0x00,0xcf,0x86,0xd5,0x94,0xd4,0x3c, - 0xd3,0x13,0x92,0x0f,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0x83,0x00,0x01, - 0x00,0x01,0x00,0xd2,0x07,0x61,0x23,0x43,0x01,0x00,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, - 0xcf,0x89,0xcc,0x81,0x00,0x0a,0xff,0xcf,0x97,0x00,0xd3,0x2c,0xd2,0x11,0xe1,0x2f, - 0x43,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01,0xff,0xce,0xb8,0x00,0xd1,0x10,0x10, - 0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0xff,0xcf,0x86,0x00,0x10,0x07,0x01, - 0xff,0xcf,0x80,0x00,0x04,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06,0xff,0xcf,0x99, - 0x00,0x06,0x00,0x10,0x07,0x01,0xff,0xcf,0x9b,0x00,0x04,0x00,0xd1,0x0b,0x10,0x07, - 0x01,0xff,0xcf,0x9d,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0x9f,0x00,0x04,0x00, - 0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xa1,0x00,0x04, - 0x00,0x10,0x07,0x01,0xff,0xcf,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff, - 0xcf,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xa7,0x00,0x01,0x00,0xd2,0x16, - 0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xa9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xcf, - 0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xad,0x00,0x01,0x00,0x10, - 0x07,0x01,0xff,0xcf,0xaf,0x00,0x01,0x00,0xd3,0x2b,0xd2,0x12,0x91,0x0e,0x10,0x07, - 0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xcf,0x81,0x00,0x01,0x00,0xd1,0x0e,0x10,0x07, - 0x05,0xff,0xce,0xb8,0x00,0x05,0xff,0xce,0xb5,0x00,0x10,0x04,0x06,0x00,0x07,0xff, - 0xcf,0xb8,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x07,0x00,0x07,0xff,0xcf,0xb2,0x00, - 0x10,0x07,0x07,0xff,0xcf,0xbb,0x00,0x07,0x00,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08, - 0xff,0xcd,0xbb,0x00,0x10,0x07,0x08,0xff,0xcd,0xbc,0x00,0x08,0xff,0xcd,0xbd,0x00, - 0xe3,0xd6,0x46,0xe2,0x3d,0x05,0xe1,0x27,0x02,0xe0,0x66,0x01,0xcf,0x86,0xd5,0xf0, - 0xd4,0x7e,0xd3,0x40,0xd2,0x22,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0,0xb5,0xcc,0x80, - 0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x07,0x01,0xff,0xd1,0x92,0x00,0x01, - 0xff,0xd0,0xb3,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x94,0x00,0x01, - 0xff,0xd1,0x95,0x00,0x10,0x07,0x01,0xff,0xd1,0x96,0x00,0x01,0xff,0xd1,0x96,0xcc, - 0x88,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x98,0x00,0x01,0xff,0xd1, - 0x99,0x00,0x10,0x07,0x01,0xff,0xd1,0x9a,0x00,0x01,0xff,0xd1,0x9b,0x00,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xd0,0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8,0xcc,0x80,0x00, - 0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x86,0x00,0x01,0xff,0xd1,0x9f,0x00,0xd3,0x38, - 0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xb0,0x00,0x01,0xff,0xd0,0xb1,0x00, - 0x10,0x07,0x01,0xff,0xd0,0xb2,0x00,0x01,0xff,0xd0,0xb3,0x00,0xd1,0x0e,0x10,0x07, - 0x01,0xff,0xd0,0xb4,0x00,0x01,0xff,0xd0,0xb5,0x00,0x10,0x07,0x01,0xff,0xd0,0xb6, - 0x00,0x01,0xff,0xd0,0xb7,0x00,0xd2,0x1e,0xd1,0x10,0x10,0x07,0x01,0xff,0xd0,0xb8, - 0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x10,0x07,0x01,0xff,0xd0,0xba,0x00,0x01, - 0xff,0xd0,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xbc,0x00,0x01,0xff,0xd0, - 0xbd,0x00,0x10,0x07,0x01,0xff,0xd0,0xbe,0x00,0x01,0xff,0xd0,0xbf,0x00,0xe4,0x0e, - 0x42,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x80,0x00,0x01,0xff, - 0xd1,0x81,0x00,0x10,0x07,0x01,0xff,0xd1,0x82,0x00,0x01,0xff,0xd1,0x83,0x00,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xd1,0x84,0x00,0x01,0xff,0xd1,0x85,0x00,0x10,0x07,0x01, - 0xff,0xd1,0x86,0x00,0x01,0xff,0xd1,0x87,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01, - 0xff,0xd1,0x88,0x00,0x01,0xff,0xd1,0x89,0x00,0x10,0x07,0x01,0xff,0xd1,0x8a,0x00, - 0x01,0xff,0xd1,0x8b,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x8c,0x00,0x01,0xff, - 0xd1,0x8d,0x00,0x10,0x07,0x01,0xff,0xd1,0x8e,0x00,0x01,0xff,0xd1,0x8f,0x00,0xcf, - 0x86,0xd5,0x07,0x64,0xb8,0x41,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b, - 0x10,0x07,0x01,0xff,0xd1,0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xa3,0x00, - 0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa5,0x00,0x01,0x00,0x10,0x07,0x01, - 0xff,0xd1,0xa7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa9, - 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07, - 0x01,0xff,0xd1,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xaf,0x00,0x01,0x00, - 0xd3,0x33,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb1,0x00,0x01,0x00,0x10, - 0x07,0x01,0xff,0xd1,0xb3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb5, - 0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb5,0xcc,0x8f,0x00,0x01,0xff,0xd1,0xb5, - 0xcc,0x8f,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb9,0x00,0x01,0x00, - 0x10,0x07,0x01,0xff,0xd1,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1, - 0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbf,0x00,0x01,0x00,0xe0,0x41,0x01, - 0xcf,0x86,0xd5,0x8e,0xd4,0x36,0xd3,0x11,0xe2,0x7a,0x41,0xe1,0x71,0x41,0x10,0x07, - 0x01,0xff,0xd2,0x81,0x00,0x01,0x00,0xd2,0x0f,0x51,0x04,0x04,0x00,0x10,0x07,0x06, - 0xff,0xd2,0x8b,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x04,0xff,0xd2,0x8d,0x00,0x04, - 0x00,0x10,0x07,0x04,0xff,0xd2,0x8f,0x00,0x04,0x00,0xd3,0x2c,0xd2,0x16,0xd1,0x0b, - 0x10,0x07,0x01,0xff,0xd2,0x91,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x93,0x00, - 0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x95,0x00,0x01,0x00,0x10,0x07,0x01, - 0xff,0xd2,0x97,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x99, - 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9b,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07, - 0x01,0xff,0xd2,0x9d,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9f,0x00,0x01,0x00, - 0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xa1,0x00,0x01, - 0x00,0x10,0x07,0x01,0xff,0xd2,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff, - 0xd2,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa7,0x00,0x01,0x00,0xd2,0x16, - 0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xa9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2, - 0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xad,0x00,0x01,0x00,0x10, - 0x07,0x01,0xff,0xd2,0xaf,0x00,0x01,0x00,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07, - 0x01,0xff,0xd2,0xb1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xb3,0x00,0x01,0x00, - 0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xb5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2, - 0xb7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xb9,0x00,0x01, - 0x00,0x10,0x07,0x01,0xff,0xd2,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff, - 0xd2,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbf,0x00,0x01,0x00,0xcf,0x86, - 0xd5,0xdc,0xd4,0x5a,0xd3,0x36,0xd2,0x20,0xd1,0x10,0x10,0x07,0x01,0xff,0xd3,0x8f, - 0x00,0x01,0xff,0xd0,0xb6,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0xb6,0xcc,0x86, - 0x00,0x01,0xff,0xd3,0x84,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x86, - 0x00,0x10,0x04,0x06,0x00,0x01,0xff,0xd3,0x88,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x04, - 0x01,0x00,0x06,0xff,0xd3,0x8a,0x00,0x10,0x04,0x06,0x00,0x01,0xff,0xd3,0x8c,0x00, - 0xe1,0x52,0x40,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8e,0x00,0xd3,0x41,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb0,0xcc, - 0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb0,0xcc, - 0x88,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x95,0x00,0x01,0x00,0x10,0x09,0x01, - 0xff,0xd0,0xb5,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0xd2,0x1d,0xd1, - 0x0b,0x10,0x07,0x01,0xff,0xd3,0x99,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0x99, - 0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xd0,0xb6,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x10,0x09,0x01,0xff, - 0xd0,0xb7,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0xd4,0x82,0xd3,0x41, - 0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa1,0x00,0x01,0x00,0x10,0x09,0x01, - 0xff,0xd0,0xb8,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00,0x10, - 0x09,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00,0xd2, - 0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa9,0x00,0x01,0x00,0x10,0x09,0x01,0xff, - 0xd3,0xa9,0xcc,0x88,0x00,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09, - 0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x10,0x09, - 0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0xd3,0x41, - 0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x01,0xff,0xd1, - 0x83,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0x01,0xff,0xd1, - 0x83,0xcc,0x8b,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00,0x01, - 0xff,0xd1,0x87,0xcc,0x88,0x00,0x10,0x07,0x08,0xff,0xd3,0xb7,0x00,0x08,0x00,0xd2, - 0x1d,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x8b,0xcc,0x88,0x00,0x01,0xff,0xd1,0x8b, - 0xcc,0x88,0x00,0x10,0x07,0x09,0xff,0xd3,0xbb,0x00,0x09,0x00,0xd1,0x0b,0x10,0x07, - 0x09,0xff,0xd3,0xbd,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd3,0xbf,0x00,0x09,0x00, - 0xe1,0x26,0x02,0xe0,0x78,0x01,0xcf,0x86,0xd5,0xb0,0xd4,0x58,0xd3,0x2c,0xd2,0x16, - 0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x81,0x00,0x06,0x00,0x10,0x07,0x06,0xff,0xd4, - 0x83,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x85,0x00,0x06,0x00,0x10, - 0x07,0x06,0xff,0xd4,0x87,0x00,0x06,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06,0xff, - 0xd4,0x89,0x00,0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x8b,0x00,0x06,0x00,0xd1,0x0b, - 0x10,0x07,0x06,0xff,0xd4,0x8d,0x00,0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x8f,0x00, - 0x06,0x00,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xd4,0x91,0x00,0x09, - 0x00,0x10,0x07,0x09,0xff,0xd4,0x93,0x00,0x09,0x00,0xd1,0x0b,0x10,0x07,0x0a,0xff, - 0xd4,0x95,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x97,0x00,0x0a,0x00,0xd2,0x16, - 0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x99,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4, - 0x9b,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x9d,0x00,0x0a,0x00,0x10, - 0x07,0x0a,0xff,0xd4,0x9f,0x00,0x0a,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b, - 0x10,0x07,0x0a,0xff,0xd4,0xa1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0xa3,0x00, - 0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xd4,0xa5,0x00,0x0b,0x00,0x10,0x07,0x0c, - 0xff,0xd4,0xa7,0x00,0x0c,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x10,0xff,0xd4,0xa9, - 0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xab,0x00,0x10,0x00,0xd1,0x0b,0x10,0x07, - 0x10,0xff,0xd4,0xad,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xaf,0x00,0x10,0x00, - 0xd3,0x35,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x00,0x00,0x01,0xff,0xd5,0xa1,0x00,0x10, - 0x07,0x01,0xff,0xd5,0xa2,0x00,0x01,0xff,0xd5,0xa3,0x00,0xd1,0x0e,0x10,0x07,0x01, - 0xff,0xd5,0xa4,0x00,0x01,0xff,0xd5,0xa5,0x00,0x10,0x07,0x01,0xff,0xd5,0xa6,0x00, - 0x01,0xff,0xd5,0xa7,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xa8,0x00, - 0x01,0xff,0xd5,0xa9,0x00,0x10,0x07,0x01,0xff,0xd5,0xaa,0x00,0x01,0xff,0xd5,0xab, - 0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xac,0x00,0x01,0xff,0xd5,0xad,0x00,0x10, - 0x07,0x01,0xff,0xd5,0xae,0x00,0x01,0xff,0xd5,0xaf,0x00,0xcf,0x86,0xe5,0xf1,0x3e, - 0xd4,0x70,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xb0,0x00,0x01, - 0xff,0xd5,0xb1,0x00,0x10,0x07,0x01,0xff,0xd5,0xb2,0x00,0x01,0xff,0xd5,0xb3,0x00, - 0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xb4,0x00,0x01,0xff,0xd5,0xb5,0x00,0x10,0x07, - 0x01,0xff,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb7,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07, - 0x01,0xff,0xd5,0xb8,0x00,0x01,0xff,0xd5,0xb9,0x00,0x10,0x07,0x01,0xff,0xd5,0xba, - 0x00,0x01,0xff,0xd5,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xbc,0x00,0x01, - 0xff,0xd5,0xbd,0x00,0x10,0x07,0x01,0xff,0xd5,0xbe,0x00,0x01,0xff,0xd5,0xbf,0x00, - 0xe3,0x70,0x3e,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x80,0x00,0x01,0xff, - 0xd6,0x81,0x00,0x10,0x07,0x01,0xff,0xd6,0x82,0x00,0x01,0xff,0xd6,0x83,0x00,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xd6,0x84,0x00,0x01,0xff,0xd6,0x85,0x00,0x10,0x07,0x01, - 0xff,0xd6,0x86,0x00,0x00,0x00,0xe0,0x18,0x3f,0xcf,0x86,0xe5,0xa9,0x3e,0xe4,0x80, - 0x3e,0xe3,0x5f,0x3e,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0xd5,0xa5,0xd6,0x82,0x00,0xe4,0x3e,0x25,0xe3,0xc4,0x1a,0xe2,0xf8,0x80, - 0xe1,0xc0,0x13,0xd0,0x1e,0xcf,0x86,0xc5,0xe4,0xf0,0x4a,0xe3,0x3b,0x46,0xe2,0xd1, - 0x43,0xe1,0x04,0x43,0xe0,0xc9,0x42,0xcf,0x86,0xe5,0x8e,0x42,0x64,0x71,0x42,0x0b, - 0x00,0xcf,0x86,0xe5,0xfa,0x01,0xe4,0xd5,0x55,0xe3,0x76,0x01,0xe2,0x76,0x53,0xd1, - 0x0c,0xe0,0xd7,0x52,0xcf,0x86,0x65,0x75,0x52,0x04,0x00,0xe0,0x0d,0x01,0xcf,0x86, - 0xd5,0x0a,0xe4,0xf8,0x52,0x63,0xe7,0x52,0x0a,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x80,0x00,0x01,0xff,0xe2,0xb4,0x81,0x00, - 0x10,0x08,0x01,0xff,0xe2,0xb4,0x82,0x00,0x01,0xff,0xe2,0xb4,0x83,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe2,0xb4,0x84,0x00,0x01,0xff,0xe2,0xb4,0x85,0x00,0x10,0x08, - 0x01,0xff,0xe2,0xb4,0x86,0x00,0x01,0xff,0xe2,0xb4,0x87,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe2,0xb4,0x88,0x00,0x01,0xff,0xe2,0xb4,0x89,0x00,0x10,0x08, - 0x01,0xff,0xe2,0xb4,0x8a,0x00,0x01,0xff,0xe2,0xb4,0x8b,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe2,0xb4,0x8c,0x00,0x01,0xff,0xe2,0xb4,0x8d,0x00,0x10,0x08,0x01,0xff, - 0xe2,0xb4,0x8e,0x00,0x01,0xff,0xe2,0xb4,0x8f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe2,0xb4,0x90,0x00,0x01,0xff,0xe2,0xb4,0x91,0x00,0x10,0x08, - 0x01,0xff,0xe2,0xb4,0x92,0x00,0x01,0xff,0xe2,0xb4,0x93,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe2,0xb4,0x94,0x00,0x01,0xff,0xe2,0xb4,0x95,0x00,0x10,0x08,0x01,0xff, - 0xe2,0xb4,0x96,0x00,0x01,0xff,0xe2,0xb4,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe2,0xb4,0x98,0x00,0x01,0xff,0xe2,0xb4,0x99,0x00,0x10,0x08,0x01,0xff, - 0xe2,0xb4,0x9a,0x00,0x01,0xff,0xe2,0xb4,0x9b,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe2,0xb4,0x9c,0x00,0x01,0xff,0xe2,0xb4,0x9d,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4, - 0x9e,0x00,0x01,0xff,0xe2,0xb4,0x9f,0x00,0xcf,0x86,0xe5,0x2a,0x52,0x94,0x50,0xd3, - 0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa0,0x00,0x01,0xff,0xe2, - 0xb4,0xa1,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa2,0x00,0x01,0xff,0xe2,0xb4,0xa3, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa4,0x00,0x01,0xff,0xe2,0xb4,0xa5, - 0x00,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xa7,0x00,0x52,0x04,0x00,0x00,0x91, - 0x0c,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xad,0x00,0x00,0x00,0x01,0x00,0xd2, - 0x1b,0xe1,0xce,0x52,0xe0,0x7f,0x52,0xcf,0x86,0x95,0x0f,0x94,0x0b,0x93,0x07,0x62, - 0x64,0x52,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xd1,0x13,0xe0,0xa5,0x53,0xcf, - 0x86,0x95,0x0a,0xe4,0x7a,0x53,0x63,0x69,0x53,0x04,0x00,0x04,0x00,0xd0,0x0d,0xcf, - 0x86,0x95,0x07,0x64,0xf4,0x53,0x08,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00, - 0x54,0x04,0x04,0x00,0xd3,0x07,0x62,0x01,0x54,0x04,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x11,0xff,0xe1,0x8f,0xb0,0x00,0x11,0xff,0xe1,0x8f,0xb1,0x00,0x10,0x08,0x11, - 0xff,0xe1,0x8f,0xb2,0x00,0x11,0xff,0xe1,0x8f,0xb3,0x00,0x91,0x10,0x10,0x08,0x11, - 0xff,0xe1,0x8f,0xb4,0x00,0x11,0xff,0xe1,0x8f,0xb5,0x00,0x00,0x00,0xd4,0x1c,0xe3, - 0x92,0x56,0xe2,0xc9,0x55,0xe1,0x8c,0x55,0xe0,0x6d,0x55,0xcf,0x86,0x95,0x0a,0xe4, - 0x56,0x55,0x63,0x45,0x55,0x04,0x00,0x04,0x00,0xe3,0xd2,0x01,0xe2,0xdd,0x59,0xd1, - 0x0c,0xe0,0xfe,0x58,0xcf,0x86,0x65,0xd7,0x58,0x0a,0x00,0xe0,0x4e,0x59,0xcf,0x86, - 0xd5,0xc5,0xd4,0x45,0xd3,0x31,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x12,0xff,0xd0,0xb2, - 0x00,0x12,0xff,0xd0,0xb4,0x00,0x10,0x07,0x12,0xff,0xd0,0xbe,0x00,0x12,0xff,0xd1, - 0x81,0x00,0x51,0x07,0x12,0xff,0xd1,0x82,0x00,0x10,0x07,0x12,0xff,0xd1,0x8a,0x00, - 0x12,0xff,0xd1,0xa3,0x00,0x92,0x10,0x91,0x0c,0x10,0x08,0x12,0xff,0xea,0x99,0x8b, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x14, - 0xff,0xe1,0x83,0x90,0x00,0x14,0xff,0xe1,0x83,0x91,0x00,0x10,0x08,0x14,0xff,0xe1, - 0x83,0x92,0x00,0x14,0xff,0xe1,0x83,0x93,0x00,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1, - 0x83,0x94,0x00,0x14,0xff,0xe1,0x83,0x95,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0x96, - 0x00,0x14,0xff,0xe1,0x83,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1, - 0x83,0x98,0x00,0x14,0xff,0xe1,0x83,0x99,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0x9a, - 0x00,0x14,0xff,0xe1,0x83,0x9b,0x00,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1,0x83,0x9c, - 0x00,0x14,0xff,0xe1,0x83,0x9d,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0x9e,0x00,0x14, - 0xff,0xe1,0x83,0x9f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x14, - 0xff,0xe1,0x83,0xa0,0x00,0x14,0xff,0xe1,0x83,0xa1,0x00,0x10,0x08,0x14,0xff,0xe1, - 0x83,0xa2,0x00,0x14,0xff,0xe1,0x83,0xa3,0x00,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1, - 0x83,0xa4,0x00,0x14,0xff,0xe1,0x83,0xa5,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0xa6, - 0x00,0x14,0xff,0xe1,0x83,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1, - 0x83,0xa8,0x00,0x14,0xff,0xe1,0x83,0xa9,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0xaa, - 0x00,0x14,0xff,0xe1,0x83,0xab,0x00,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1,0x83,0xac, - 0x00,0x14,0xff,0xe1,0x83,0xad,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0xae,0x00,0x14, - 0xff,0xe1,0x83,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1, - 0x83,0xb0,0x00,0x14,0xff,0xe1,0x83,0xb1,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0xb2, - 0x00,0x14,0xff,0xe1,0x83,0xb3,0x00,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1,0x83,0xb4, - 0x00,0x14,0xff,0xe1,0x83,0xb5,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0xb6,0x00,0x14, - 0xff,0xe1,0x83,0xb7,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x14,0xff,0xe1,0x83,0xb8, - 0x00,0x14,0xff,0xe1,0x83,0xb9,0x00,0x10,0x08,0x14,0xff,0xe1,0x83,0xba,0x00,0x00, - 0x00,0xd1,0x0c,0x10,0x04,0x00,0x00,0x14,0xff,0xe1,0x83,0xbd,0x00,0x10,0x08,0x14, - 0xff,0xe1,0x83,0xbe,0x00,0x14,0xff,0xe1,0x83,0xbf,0x00,0xe2,0x9d,0x08,0xe1,0x48, - 0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84,0xd3,0x40,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa5,0x00,0x01,0xff,0x61,0xcc,0xa5,0x00,0x10, - 0x08,0x01,0xff,0x62,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc,0x87,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x62,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc,0xa3,0x00,0x10,0x08,0x01, - 0xff,0x62,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00,0xd2,0x24,0xd1,0x14,0x10, - 0x0a,0x01,0xff,0x63,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc,0xa7,0xcc,0x81, - 0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x87,0x00,0x01,0xff,0x64,0xcc,0x87,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa3,0x00,0x01,0xff,0x64,0xcc,0xa3,0x00,0x10, - 0x08,0x01,0xff,0x64,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc,0xb1,0x00,0xd3,0x48,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa7,0x00,0x01,0xff,0x64,0xcc,0xa7, - 0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xad,0x00,0x01,0xff,0x64,0xcc,0xad,0x00,0xd1, - 0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff,0x65,0xcc,0x84, - 0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0x01,0xff,0x65, - 0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0xad, - 0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0xb0,0x00,0x01, - 0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86, - 0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x66,0xcc,0x87, - 0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x67,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc,0x84,0x00,0x10,0x08,0x01, - 0xff,0x68,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x68,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x68, - 0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x68,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x68, - 0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69, - 0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a,0x01,0xff,0x69,0xcc,0x88, - 0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00,0xd3,0x40,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x81,0x00,0x01,0xff,0x6b,0xcc,0x81,0x00,0x10, - 0x08,0x01,0xff,0x6b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc,0xa3,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x6b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc,0xb1,0x00,0x10,0x08,0x01, - 0xff,0x6c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00,0xd2,0x24,0xd1,0x14,0x10, - 0x0a,0x01,0xff,0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff,0x6c,0xcc,0xa3,0xcc,0x84, - 0x00,0x10,0x08,0x01,0xff,0x6c,0xcc,0xb1,0x00,0x01,0xff,0x6c,0xcc,0xb1,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x6c,0xcc,0xad,0x00,0x01,0xff,0x6c,0xcc,0xad,0x00,0x10, - 0x08,0x01,0xff,0x6d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc,0x81,0x00,0xcf,0x86,0xe5, - 0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6d,0xcc, - 0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6d,0xcc,0xa3,0x00, - 0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x87,0x00, - 0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa3,0x00,0x01,0xff, - 0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0xb1,0x00, - 0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xad,0x00,0x01,0xff, - 0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00, - 0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x83,0xcc, - 0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3,0x48,0xd2,0x28,0xd1,0x14, - 0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x84,0xcc, - 0x80,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc, - 0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x70,0xcc,0x81,0x00,0x01,0xff, - 0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x70,0xcc,0x87,0x00,0x01,0xff,0x70,0xcc, - 0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x87,0x00,0x01,0xff, - 0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xa3,0x00,0x01,0xff,0x72,0xcc, - 0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff, - 0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xb1,0x00,0x01,0xff, - 0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x73,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x73,0xcc, - 0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x73,0xcc, - 0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x10,0x0a,0x01,0xff, - 0x73,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87,0x00,0xd2,0x24, - 0xd1,0x14,0x10,0x0a,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc, - 0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0x87,0x00,0x01,0xff,0x74,0xcc, - 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xa3,0x00,0x01,0xff,0x74,0xcc, - 0xa3,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0xb1,0x00,0x01,0xff,0x74,0xcc,0xb1,0x00, - 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xad,0x00,0x01,0xff, - 0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa4,0x00,0x01,0xff,0x75,0xcc, - 0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0xb0,0x00,0x01,0xff,0x75,0xcc, - 0xb0,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xad,0x00,0x01,0xff,0x75,0xcc,0xad,0x00, - 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x01,0xff, - 0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00, - 0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x76,0xcc, - 0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x76,0xcc,0xa3,0x00, - 0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x11,0x02,0xcf,0x86,0xd5,0xe2,0xd4,0x80,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x80,0x00,0x01,0xff,0x77, - 0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x81,0x00,0x01,0xff,0x77,0xcc,0x81, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x88,0x00,0x01,0xff,0x77,0xcc,0x88, - 0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x87,0x00,0x01,0xff,0x77,0xcc,0x87,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0xa3,0x00,0x01,0xff,0x77,0xcc,0xa3, - 0x00,0x10,0x08,0x01,0xff,0x78,0xcc,0x87,0x00,0x01,0xff,0x78,0xcc,0x87,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x78,0xcc,0x88,0x00,0x01,0xff,0x78,0xcc,0x88,0x00,0x10, - 0x08,0x01,0xff,0x79,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc,0x87,0x00,0xd3,0x33,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x82,0x00,0x01,0xff,0x7a,0xcc,0x82, - 0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0xa3,0x00,0x01,0xff,0x7a,0xcc,0xa3,0x00,0xe1, - 0xc4,0x58,0x10,0x08,0x01,0xff,0x7a,0xcc,0xb1,0x00,0x01,0xff,0x7a,0xcc,0xb1,0x00, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01,0xff,0x79,0xcc, - 0x8a,0x00,0x10,0x08,0x01,0xff,0x61,0xca,0xbe,0x00,0x02,0xff,0x73,0xcc,0x87,0x00, - 0x51,0x04,0x0a,0x00,0x10,0x07,0x0a,0xff,0x73,0x73,0x00,0x0a,0x00,0xd4,0x98,0xd3, - 0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa3,0x00,0x01,0xff,0x61, - 0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x89, - 0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x01,0xff,0x61, - 0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0x01, - 0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61, - 0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a,0x01, - 0xff,0x61,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x83,0x00,0xd1, - 0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0xa3, - 0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0x01,0xff,0x61, - 0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61, - 0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00,0x10,0x0a,0x01, - 0xff,0x61,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x89,0x00,0xd1, - 0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x86, - 0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0x01,0xff,0x61, - 0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0xa3, - 0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x89,0x00,0x01, - 0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x83,0x00,0x01, - 0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0x01, - 0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01,0xd4,0x90,0xd3,0x50, - 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x01,0xff, - 0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00, - 0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc, - 0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff, - 0x65,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x89,0x00,0x01,0xff,0x69,0xcc,0x89,0x00, - 0x10,0x08,0x01,0xff,0x69,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc,0xa3,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x6f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc,0xa3,0x00,0x10,0x08, - 0x01,0xff,0x6f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00,0xd3,0x50,0xd2,0x28, - 0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc, - 0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0x01,0xff, - 0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc, - 0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc, - 0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0xd2,0x28,0xd1,0x14, - 0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x6f,0xcc,0xa3,0xcc, - 0x82,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc, - 0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00, - 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc, - 0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98,0xd3,0x48,0xd2,0x28, - 0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc, - 0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff, - 0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0xa3,0x00, - 0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x89,0x00,0x01,0xff, - 0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc, - 0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc, - 0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x75,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x89,0x00, - 0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc, - 0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc, - 0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x79,0xcc, - 0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x79,0xcc, - 0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x89,0x00, - 0x01,0xff,0x79,0xcc,0x89,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x01,0xff,0x79,0xcc, - 0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbb,0x00, - 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbd,0x00,0x0a,0x00,0x10,0x08, - 0x0a,0xff,0xe1,0xbb,0xbf,0x00,0x0a,0x00,0xe1,0xbf,0x02,0xe0,0xa1,0x01,0xcf,0x86, - 0xd5,0xc6,0xd4,0x6c,0xd3,0x18,0xe2,0xc0,0x58,0xe1,0xa9,0x58,0x10,0x09,0x01,0xff, - 0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0x00, - 0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x81, - 0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1, - 0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0x00,0xd3,0x18, - 0xe2,0xfc,0x58,0xe1,0xe5,0x58,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x93,0x00,0x01, - 0xff,0xce,0xb5,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5, - 0xcc,0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb5, - 0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16, - 0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb5,0xcc, - 0x94,0xcc,0x81,0x00,0x00,0x00,0xd4,0x6c,0xd3,0x18,0xe2,0x26,0x59,0xe1,0x0f,0x59, - 0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0x00, - 0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce, - 0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0x00,0x01, - 0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7, - 0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b, - 0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd, - 0x82,0x00,0xd3,0x18,0xe2,0x62,0x59,0xe1,0x4b,0x59,0x10,0x09,0x01,0xff,0xce,0xb9, - 0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0x00,0x10,0x0b, - 0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc, - 0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x81,0x00,0x01, - 0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93, - 0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82,0x00,0xcf,0x86,0xd5,0xac, - 0xd4,0x5a,0xd3,0x18,0xe2,0x9f,0x59,0xe1,0x88,0x59,0x10,0x09,0x01,0xff,0xce,0xbf, - 0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00,0x10,0x0b, - 0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc, - 0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x81,0x00,0x01, - 0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x18,0xe2,0xc9,0x59,0xe1, - 0xb2,0x59,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff,0xcf,0x85,0xcc, - 0x94,0x00,0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94, - 0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x0f, - 0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00,0x10,0x04,0x00, - 0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00,0xe4,0x85,0x5a,0xd3,0x18,0xe2, - 0x04,0x5a,0xe1,0xed,0x59,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93,0x00,0x01,0xff, - 0xcf,0x89,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc, - 0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc, - 0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10, - 0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94, - 0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff, - 0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xe0,0xd9,0x02,0xcf,0x86,0xe5,0x91,0x01,0xd4, - 0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xce, - 0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce, - 0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x80, - 0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x81,0xce, - 0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01, - 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94, - 0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, - 0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01, - 0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94, - 0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc, - 0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10, - 0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1, - 0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01, - 0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xce,0xb9, - 0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff, - 0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce, - 0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81, - 0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10, - 0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94, - 0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01, - 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94, - 0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82,0xce, - 0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd4,0xc8,0xd3, - 0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xce,0xb9,0x00, - 0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc, - 0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0xce,0xb9, - 0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00, - 0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xcf, - 0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82, - 0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xce, - 0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xcf, - 0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80, - 0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0xce, - 0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01, - 0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94, - 0xcd,0x82,0xce,0xb9,0x00,0xd3,0x49,0xd2,0x26,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, - 0xb1,0xcc,0x86,0x00,0x01,0xff,0xce,0xb1,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce, - 0xb1,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xce,0xb9,0x00,0xd1,0x0f,0x10, - 0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff, - 0xce,0xb1,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x81,0x00,0xe1,0xa5,0x5a,0x10,0x09,0x01,0xff,0xce,0xb1,0xce,0xb9,0x00,0x01,0x00, - 0xcf,0x86,0xd5,0xbd,0xd4,0x7e,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10,0x04,0x01,0x00, - 0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x80,0xce, - 0xb9,0x00,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce, - 0xb7,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcd,0x82, - 0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81,0x00,0x10,0x09, - 0x01,0xff,0xce,0xb7,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0xe1,0xb4, - 0x5a,0x10,0x09,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0x01,0xff,0xe1,0xbe,0xbf,0xcc, - 0x80,0x00,0xd3,0x18,0xe2,0xda,0x5a,0xe1,0xc3,0x5a,0x10,0x09,0x01,0xff,0xce,0xb9, - 0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0xe2,0xfe,0x5a,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0x10, - 0x09,0x01,0xff,0xce,0xb9,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0xd4, - 0x51,0xd3,0x18,0xe2,0x21,0x5b,0xe1,0x0a,0x5b,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc, - 0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01, - 0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00,0x10,0x09,0x01, - 0xff,0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0xe1,0x41,0x5b, - 0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x80,0x00, - 0xd3,0x3b,0xd2,0x18,0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x80, - 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff, - 0xcf,0x89,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcd, - 0x82,0x00,0x01,0xff,0xcf,0x89,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x10, - 0x09,0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0xe1, - 0x4b,0x5b,0x10,0x09,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0x01,0xff,0xc2,0xb4,0x00, - 0xe0,0xa2,0x67,0xcf,0x86,0xe5,0x24,0x02,0xe4,0x26,0x01,0xe3,0x1b,0x5e,0xd2,0x2b, - 0xe1,0xf5,0x5b,0xe0,0x7a,0x5b,0xcf,0x86,0xe5,0x5f,0x5b,0x94,0x1c,0x93,0x18,0x92, - 0x14,0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01,0xff,0xe2,0x80,0x83, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd1,0xd6,0xd0,0x46,0xcf,0x86,0x55, - 0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, - 0x07,0x01,0xff,0xcf,0x89,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01,0x00,0x10,0x06, - 0x01,0xff,0x6b,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x01,0x00,0xe3,0xba,0x5c,0x92, - 0x10,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0x8e,0x00,0x01,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0x0a,0xe4,0xd7,0x5c,0x63,0xc2,0x5c,0x06,0x00,0x94,0x80,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb0,0x00,0x01,0xff,0xe2, - 0x85,0xb1,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb2,0x00,0x01,0xff,0xe2,0x85,0xb3, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb4,0x00,0x01,0xff,0xe2,0x85,0xb5, - 0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb6,0x00,0x01,0xff,0xe2,0x85,0xb7,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb8,0x00,0x01,0xff,0xe2,0x85,0xb9, - 0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xba,0x00,0x01,0xff,0xe2,0x85,0xbb,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xbc,0x00,0x01,0xff,0xe2,0x85,0xbd,0x00,0x10, - 0x08,0x01,0xff,0xe2,0x85,0xbe,0x00,0x01,0xff,0xe2,0x85,0xbf,0x00,0x01,0x00,0xe0, - 0xc9,0x5c,0xcf,0x86,0xe5,0xa8,0x5c,0xe4,0x87,0x5c,0xe3,0x76,0x5c,0xe2,0x69,0x5c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0xff,0xe2,0x86,0x84,0x00,0xe3,0xb8, - 0x60,0xe2,0x85,0x60,0xd1,0x0c,0xe0,0x32,0x60,0xcf,0x86,0x65,0x13,0x60,0x01,0x00, - 0xd0,0x62,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x18,0x52,0x04, - 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x90,0x00,0x01,0xff, - 0xe2,0x93,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x92,0x00, - 0x01,0xff,0xe2,0x93,0x93,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x94,0x00,0x01,0xff, - 0xe2,0x93,0x95,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x96,0x00,0x01,0xff, - 0xe2,0x93,0x97,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x98,0x00,0x01,0xff,0xe2,0x93, - 0x99,0x00,0xcf,0x86,0xe5,0xec,0x5f,0x94,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe2,0x93,0x9a,0x00,0x01,0xff,0xe2,0x93,0x9b,0x00,0x10,0x08,0x01, - 0xff,0xe2,0x93,0x9c,0x00,0x01,0xff,0xe2,0x93,0x9d,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe2,0x93,0x9e,0x00,0x01,0xff,0xe2,0x93,0x9f,0x00,0x10,0x08,0x01,0xff,0xe2, - 0x93,0xa0,0x00,0x01,0xff,0xe2,0x93,0xa1,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe2,0x93,0xa2,0x00,0x01,0xff,0xe2,0x93,0xa3,0x00,0x10,0x08,0x01,0xff,0xe2, - 0x93,0xa4,0x00,0x01,0xff,0xe2,0x93,0xa5,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2, - 0x93,0xa6,0x00,0x01,0xff,0xe2,0x93,0xa7,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0xa8, - 0x00,0x01,0xff,0xe2,0x93,0xa9,0x00,0x01,0x00,0xd4,0x0c,0xe3,0xc8,0x61,0xe2,0xc1, - 0x61,0xcf,0x06,0x04,0x00,0xe3,0xa1,0x64,0xe2,0x94,0x63,0xe1,0x2e,0x02,0xe0,0x84, - 0x01,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe2,0xb0,0xb0,0x00,0x08,0xff,0xe2,0xb0,0xb1,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb0,0xb2,0x00,0x08,0xff,0xe2,0xb0,0xb3,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb0,0xb4,0x00,0x08,0xff,0xe2,0xb0,0xb5,0x00,0x10,0x08,0x08,0xff,0xe2,0xb0, - 0xb6,0x00,0x08,0xff,0xe2,0xb0,0xb7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb0,0xb8,0x00,0x08,0xff,0xe2,0xb0,0xb9,0x00,0x10,0x08,0x08,0xff,0xe2,0xb0, - 0xba,0x00,0x08,0xff,0xe2,0xb0,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb0, - 0xbc,0x00,0x08,0xff,0xe2,0xb0,0xbd,0x00,0x10,0x08,0x08,0xff,0xe2,0xb0,0xbe,0x00, - 0x08,0xff,0xe2,0xb0,0xbf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x80,0x00,0x08,0xff,0xe2,0xb1,0x81,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x82,0x00,0x08,0xff,0xe2,0xb1,0x83,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x84,0x00,0x08,0xff,0xe2,0xb1,0x85,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x86,0x00, - 0x08,0xff,0xe2,0xb1,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x88,0x00,0x08,0xff,0xe2,0xb1,0x89,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x8a,0x00, - 0x08,0xff,0xe2,0xb1,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1,0x8c,0x00, - 0x08,0xff,0xe2,0xb1,0x8d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x8e,0x00,0x08,0xff, - 0xe2,0xb1,0x8f,0x00,0x94,0x7c,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x90,0x00,0x08,0xff,0xe2,0xb1,0x91,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x92,0x00,0x08,0xff,0xe2,0xb1,0x93,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x94,0x00,0x08,0xff,0xe2,0xb1,0x95,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x96,0x00, - 0x08,0xff,0xe2,0xb1,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x98,0x00,0x08,0xff,0xe2,0xb1,0x99,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x9a,0x00, - 0x08,0xff,0xe2,0xb1,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1,0x9c,0x00, - 0x08,0xff,0xe2,0xb1,0x9d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x9e,0x00,0x00,0x00, - 0x08,0x00,0xcf,0x86,0xd5,0x07,0x64,0x84,0x61,0x08,0x00,0xd4,0x63,0xd3,0x32,0xd2, - 0x1b,0xd1,0x0c,0x10,0x08,0x09,0xff,0xe2,0xb1,0xa1,0x00,0x09,0x00,0x10,0x07,0x09, - 0xff,0xc9,0xab,0x00,0x09,0xff,0xe1,0xb5,0xbd,0x00,0xd1,0x0b,0x10,0x07,0x09,0xff, - 0xc9,0xbd,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xa8,0x00,0xd2, - 0x18,0xd1,0x0c,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xaa,0x00,0x10,0x04,0x09, - 0x00,0x09,0xff,0xe2,0xb1,0xac,0x00,0xd1,0x0b,0x10,0x04,0x09,0x00,0x0a,0xff,0xc9, - 0x91,0x00,0x10,0x07,0x0a,0xff,0xc9,0xb1,0x00,0x0a,0xff,0xc9,0x90,0x00,0xd3,0x27, - 0xd2,0x17,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xc9,0x92,0x00,0x0a,0x00,0x10,0x08,0x0a, - 0xff,0xe2,0xb1,0xb3,0x00,0x0a,0x00,0x91,0x0c,0x10,0x04,0x09,0x00,0x09,0xff,0xe2, - 0xb1,0xb6,0x00,0x09,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x07,0x0b, - 0xff,0xc8,0xbf,0x00,0x0b,0xff,0xc9,0x80,0x00,0xe0,0x83,0x01,0xcf,0x86,0xd5,0xc0, - 0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x81,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x83,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x87,0x00, - 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x89,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8f,0x00,0x08,0x00, - 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x91,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x97,0x00,0x08,0x00, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x99,0x00,0x08,0x00,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, - 0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x9f,0x00,0x08,0x00,0xd4,0x60, - 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa1,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0xa3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0xa5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa7,0x00,0x08,0x00, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa9,0x00,0x08,0x00,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0xab,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, - 0xad,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xaf,0x00,0x08,0x00,0xd3,0x30, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb1,0x00,0x08,0x00,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0xb3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, - 0xb5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb7,0x00,0x08,0x00,0xd2,0x18, - 0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb9,0x00,0x08,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0xbb,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xbd,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xbf,0x00,0x08,0x00,0xcf,0x86,0xd5,0xc0, - 0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x81,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x83,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb3,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x87,0x00, - 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x89,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb3,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb3,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8f,0x00,0x08,0x00, - 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x91,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb3,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb3,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x97,0x00,0x08,0x00, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x99,0x00,0x08,0x00,0x10,0x08, - 0x08,0xff,0xe2,0xb3,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3, - 0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x9f,0x00,0x08,0x00,0xd4,0x3b, - 0xd3,0x1c,0x92,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa1,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb3,0xa3,0x00,0x08,0x00,0x08,0x00,0xd2,0x10,0x51,0x04, - 0x08,0x00,0x10,0x04,0x08,0x00,0x0b,0xff,0xe2,0xb3,0xac,0x00,0xe1,0xd0,0x5e,0x10, - 0x04,0x0b,0x00,0x0b,0xff,0xe2,0xb3,0xae,0x00,0xe3,0xd5,0x5e,0x92,0x10,0x51,0x04, - 0x0b,0xe6,0x10,0x08,0x0d,0xff,0xe2,0xb3,0xb3,0x00,0x0d,0x00,0x00,0x00,0xe2,0x98, - 0x08,0xd1,0x0b,0xe0,0x8d,0x66,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe0,0xe1,0x6b,0xcf, - 0x86,0xe5,0xa7,0x05,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x0c,0xe2,0x74,0x67,0xe1, - 0x0b,0x67,0xcf,0x06,0x04,0x00,0xe2,0xdb,0x01,0xe1,0x26,0x01,0xd0,0x09,0xcf,0x86, - 0x65,0x70,0x67,0x0a,0x00,0xcf,0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1, - 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, - 0x99,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x85,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x99,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x8b, - 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x8d,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x99,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x99,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x93, - 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x95,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x99,0x97,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x99,0x99,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x9b,0x00,0x0a, - 0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x9d,0x00,0x0a,0x00,0x10,0x08,0x0a, - 0xff,0xea,0x99,0x9f,0x00,0x0a,0x00,0xe4,0xd9,0x66,0xd3,0x30,0xd2,0x18,0xd1,0x0c, - 0x10,0x08,0x0c,0xff,0xea,0x99,0xa1,0x00,0x0c,0x00,0x10,0x08,0x0a,0xff,0xea,0x99, - 0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0xa5,0x00,0x0a,0x00, - 0x10,0x08,0x0a,0xff,0xea,0x99,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08, - 0x0a,0xff,0xea,0x99,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0xab,0x00, - 0x0a,0x00,0xe1,0x88,0x66,0x10,0x08,0x0a,0xff,0xea,0x99,0xad,0x00,0x0a,0x00,0xe0, - 0xb1,0x66,0xcf,0x86,0x95,0xab,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08, - 0x0a,0xff,0xea,0x9a,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x83,0x00, - 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x85,0x00,0x0a,0x00,0x10,0x08, - 0x0a,0xff,0xea,0x9a,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff, - 0xea,0x9a,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8b,0x00,0x0a,0x00, - 0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff, - 0xea,0x9a,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff, - 0xea,0x9a,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x93,0x00,0x0a,0x00, - 0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x95,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff, - 0xea,0x9a,0x97,0x00,0x0a,0x00,0xe2,0x0e,0x66,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea, - 0x9a,0x99,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9a,0x9b,0x00,0x10,0x00,0x0b, - 0x00,0xe1,0x10,0x02,0xd0,0xb9,0xcf,0x86,0xd5,0x07,0x64,0x1a,0x66,0x08,0x00,0xd4, - 0x58,0xd3,0x28,0xd2,0x10,0x51,0x04,0x09,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa3, - 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa5,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x9c,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9c,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xab,0x00,0x0a, - 0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xad,0x00,0x0a,0x00,0x10,0x08,0x0a, - 0xff,0xea,0x9c,0xaf,0x00,0x0a,0x00,0xd3,0x28,0xd2,0x10,0x51,0x04,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x9c,0xb3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, - 0x9c,0xb5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb7,0x00,0x0a,0x00,0xd2, - 0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb9,0x00,0x0a,0x00,0x10,0x08,0x0a, - 0xff,0xea,0x9c,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xbd, - 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xbf,0x00,0x0a,0x00,0xcf,0x86,0xd5, - 0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x81, - 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x9d,0x85,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x87, - 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x89,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9d,0x8d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8f,0x00,0x0a, - 0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x91,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9d,0x95,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x97,0x00,0x0a, - 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x99,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x9d,0x9b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, - 0x9d,0x9d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9f,0x00,0x0a,0x00,0xd4, - 0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa1,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9d,0xa5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa7,0x00,0x0a, - 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa9,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x9d,0xab,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, - 0x9d,0xad,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xaf,0x00,0x0a,0x00,0x53, - 0x04,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9d,0xba, - 0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9d,0xbc,0x00,0xd1,0x0c,0x10,0x04,0x0a, - 0x00,0x0a,0xff,0xe1,0xb5,0xb9,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xbf,0x00,0x0a, - 0x00,0xe0,0x71,0x01,0xcf,0x86,0xd5,0xa6,0xd4,0x4e,0xd3,0x30,0xd2,0x18,0xd1,0x0c, - 0x10,0x08,0x0a,0xff,0xea,0x9e,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9e, - 0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x85,0x00,0x0a,0x00, - 0x10,0x08,0x0a,0xff,0xea,0x9e,0x87,0x00,0x0a,0x00,0xd2,0x10,0x51,0x04,0x0a,0x00, - 0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9e,0x8c,0x00,0xe1,0x16,0x64,0x10,0x04,0x0a, - 0x00,0x0c,0xff,0xc9,0xa5,0x00,0xd3,0x28,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0c,0xff, - 0xea,0x9e,0x91,0x00,0x0c,0x00,0x10,0x08,0x0d,0xff,0xea,0x9e,0x93,0x00,0x0d,0x00, - 0x51,0x04,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x97,0x00,0x10,0x00,0xd2,0x18, - 0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e,0x99,0x00,0x10,0x00,0x10,0x08,0x10,0xff, - 0xea,0x9e,0x9b,0x00,0x10,0x00,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e,0x9d,0x00, - 0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x9f,0x00,0x10,0x00,0xd4,0x63,0xd3,0x30, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa1,0x00,0x0c,0x00,0x10,0x08, - 0x0c,0xff,0xea,0x9e,0xa3,0x00,0x0c,0x00,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e, - 0xa5,0x00,0x0c,0x00,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa7,0x00,0x0c,0x00,0xd2,0x1a, - 0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa9,0x00,0x0c,0x00,0x10,0x07,0x0d,0xff, - 0xc9,0xa6,0x00,0x10,0xff,0xc9,0x9c,0x00,0xd1,0x0e,0x10,0x07,0x10,0xff,0xc9,0xa1, - 0x00,0x10,0xff,0xc9,0xac,0x00,0x10,0x07,0x12,0xff,0xc9,0xaa,0x00,0x14,0x00,0xd3, - 0x35,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x10,0xff,0xca,0x9e,0x00,0x10,0xff,0xca,0x87, - 0x00,0x10,0x07,0x11,0xff,0xca,0x9d,0x00,0x11,0xff,0xea,0xad,0x93,0x00,0xd1,0x0c, - 0x10,0x08,0x11,0xff,0xea,0x9e,0xb5,0x00,0x11,0x00,0x10,0x08,0x11,0xff,0xea,0x9e, - 0xb7,0x00,0x11,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x14,0xff,0xea,0x9e,0xb9,0x00, - 0x14,0x00,0x10,0x08,0x15,0xff,0xea,0x9e,0xbb,0x00,0x15,0x00,0xd1,0x0c,0x10,0x08, - 0x15,0xff,0xea,0x9e,0xbd,0x00,0x15,0x00,0x10,0x08,0x15,0xff,0xea,0x9e,0xbf,0x00, - 0x15,0x00,0xcf,0x86,0xe5,0x50,0x63,0x94,0x2f,0x93,0x2b,0xd2,0x10,0x51,0x04,0x00, - 0x00,0x10,0x08,0x15,0xff,0xea,0x9f,0x83,0x00,0x15,0x00,0xd1,0x0f,0x10,0x08,0x15, - 0xff,0xea,0x9e,0x94,0x00,0x15,0xff,0xca,0x82,0x00,0x10,0x08,0x15,0xff,0xe1,0xb6, - 0x8e,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe4,0x30,0x66,0xd3,0x1d,0xe2,0xd7,0x63, - 0xe1,0x86,0x63,0xe0,0x73,0x63,0xcf,0x86,0xe5,0x54,0x63,0x94,0x0b,0x93,0x07,0x62, - 0x3f,0x63,0x08,0x00,0x08,0x00,0x08,0x00,0xd2,0x0f,0xe1,0xd6,0x64,0xe0,0xa3,0x64, - 0xcf,0x86,0x65,0x88,0x64,0x0a,0x00,0xd1,0xab,0xd0,0x1a,0xcf,0x86,0xe5,0x93,0x65, - 0xe4,0x76,0x65,0xe3,0x5d,0x65,0xe2,0x50,0x65,0x91,0x08,0x10,0x04,0x00,0x00,0x0c, - 0x00,0x0c,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x0b,0x93,0x07,0x62,0xa3,0x65, - 0x11,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, - 0xa0,0x00,0x11,0xff,0xe1,0x8e,0xa1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa2,0x00, - 0x11,0xff,0xe1,0x8e,0xa3,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa4,0x00, - 0x11,0xff,0xe1,0x8e,0xa5,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa6,0x00,0x11,0xff, - 0xe1,0x8e,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa8,0x00, - 0x11,0xff,0xe1,0x8e,0xa9,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xaa,0x00,0x11,0xff, - 0xe1,0x8e,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xac,0x00,0x11,0xff, - 0xe1,0x8e,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xae,0x00,0x11,0xff,0xe1,0x8e, - 0xaf,0x00,0xe0,0x2e,0x65,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb0,0x00,0x11,0xff,0xe1,0x8e,0xb1,0x00, - 0x10,0x08,0x11,0xff,0xe1,0x8e,0xb2,0x00,0x11,0xff,0xe1,0x8e,0xb3,0x00,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8e,0xb4,0x00,0x11,0xff,0xe1,0x8e,0xb5,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8e,0xb6,0x00,0x11,0xff,0xe1,0x8e,0xb7,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8e,0xb8,0x00,0x11,0xff,0xe1,0x8e,0xb9,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8e,0xba,0x00,0x11,0xff,0xe1,0x8e,0xbb,0x00,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8e,0xbc,0x00,0x11,0xff,0xe1,0x8e,0xbd,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8e,0xbe,0x00,0x11,0xff,0xe1,0x8e,0xbf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x80,0x00,0x11,0xff,0xe1,0x8f,0x81,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x82,0x00,0x11,0xff,0xe1,0x8f,0x83,0x00,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x84,0x00,0x11,0xff,0xe1,0x8f,0x85,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x86,0x00,0x11,0xff,0xe1,0x8f,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x88,0x00,0x11,0xff,0xe1,0x8f,0x89,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x8a,0x00,0x11,0xff,0xe1,0x8f,0x8b,0x00,0xd1,0x10,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x8c,0x00,0x11,0xff,0xe1,0x8f,0x8d,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, - 0x8e,0x00,0x11,0xff,0xe1,0x8f,0x8f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x90,0x00,0x11,0xff,0xe1,0x8f,0x91,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x92,0x00,0x11,0xff,0xe1,0x8f,0x93,0x00,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x94,0x00,0x11,0xff,0xe1,0x8f,0x95,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x96,0x00,0x11,0xff,0xe1,0x8f,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x98,0x00,0x11,0xff,0xe1,0x8f,0x99,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x9a,0x00,0x11,0xff,0xe1,0x8f,0x9b,0x00,0xd1,0x10,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x9c,0x00,0x11,0xff,0xe1,0x8f,0x9d,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, - 0x9e,0x00,0x11,0xff,0xe1,0x8f,0x9f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0xa0,0x00,0x11,0xff,0xe1,0x8f,0xa1,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0xa2,0x00,0x11,0xff,0xe1,0x8f,0xa3,0x00,0xd1,0x10,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0xa4,0x00,0x11,0xff,0xe1,0x8f,0xa5,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, - 0xa6,0x00,0x11,0xff,0xe1,0x8f,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0xa8,0x00,0x11,0xff,0xe1,0x8f,0xa9,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, - 0xaa,0x00,0x11,0xff,0xe1,0x8f,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f, - 0xac,0x00,0x11,0xff,0xe1,0x8f,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f,0xae,0x00, - 0x11,0xff,0xe1,0x8f,0xaf,0x00,0xd1,0x0c,0xe0,0x67,0x63,0xcf,0x86,0xcf,0x06,0x02, - 0xff,0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06, - 0x01,0x00,0xd4,0xae,0xd3,0x09,0xe2,0xd0,0x63,0xcf,0x06,0x01,0x00,0xd2,0x27,0xe1, - 0x9b,0x6f,0xe0,0xa2,0x6d,0xcf,0x86,0xe5,0xbb,0x6c,0xe4,0x4a,0x6c,0xe3,0x15,0x6c, - 0xe2,0xf4,0x6b,0xe1,0xe3,0x6b,0x10,0x08,0x01,0xff,0xe5,0x88,0x87,0x00,0x01,0xff, - 0xe5,0xba,0xa6,0x00,0xe1,0xf0,0x73,0xe0,0x64,0x73,0xcf,0x86,0xe5,0x9e,0x72,0xd4, - 0x3b,0x93,0x37,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x01,0xff,0x66,0x66,0x00,0x01,0xff, - 0x66,0x69,0x00,0x10,0x07,0x01,0xff,0x66,0x6c,0x00,0x01,0xff,0x66,0x66,0x69,0x00, - 0xd1,0x0f,0x10,0x08,0x01,0xff,0x66,0x66,0x6c,0x00,0x01,0xff,0x73,0x74,0x00,0x10, - 0x07,0x01,0xff,0x73,0x74,0x00,0x00,0x00,0x00,0x00,0xe3,0x44,0x72,0xd2,0x11,0x51, - 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xd5,0xb4,0xd5,0xb6,0x00,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xd5,0xb4,0xd5,0xa5,0x00,0x01,0xff,0xd5,0xb4,0xd5,0xab,0x00, - 0x10,0x09,0x01,0xff,0xd5,0xbe,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb4,0xd5,0xad,0x00, - 0xd3,0x09,0xe2,0xbc,0x73,0xcf,0x06,0x01,0x00,0xd2,0x12,0xe1,0xab,0x74,0xe0,0x3c, - 0x74,0xcf,0x86,0xe5,0x19,0x74,0x64,0x08,0x74,0x06,0x00,0xe1,0x11,0x75,0xe0,0xde, - 0x74,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x7c,0xd3,0x3c,0xd2, - 0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xef,0xbd,0x81,0x00,0x10,0x08,0x01, - 0xff,0xef,0xbd,0x82,0x00,0x01,0xff,0xef,0xbd,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xef,0xbd,0x84,0x00,0x01,0xff,0xef,0xbd,0x85,0x00,0x10,0x08,0x01,0xff,0xef, - 0xbd,0x86,0x00,0x01,0xff,0xef,0xbd,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xef,0xbd,0x88,0x00,0x01,0xff,0xef,0xbd,0x89,0x00,0x10,0x08,0x01,0xff,0xef, - 0xbd,0x8a,0x00,0x01,0xff,0xef,0xbd,0x8b,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xef, - 0xbd,0x8c,0x00,0x01,0xff,0xef,0xbd,0x8d,0x00,0x10,0x08,0x01,0xff,0xef,0xbd,0x8e, - 0x00,0x01,0xff,0xef,0xbd,0x8f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xef,0xbd,0x90,0x00,0x01,0xff,0xef,0xbd,0x91,0x00,0x10,0x08,0x01,0xff,0xef, - 0xbd,0x92,0x00,0x01,0xff,0xef,0xbd,0x93,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xef, - 0xbd,0x94,0x00,0x01,0xff,0xef,0xbd,0x95,0x00,0x10,0x08,0x01,0xff,0xef,0xbd,0x96, - 0x00,0x01,0xff,0xef,0xbd,0x97,0x00,0x92,0x1c,0xd1,0x10,0x10,0x08,0x01,0xff,0xef, - 0xbd,0x98,0x00,0x01,0xff,0xef,0xbd,0x99,0x00,0x10,0x08,0x01,0xff,0xef,0xbd,0x9a, - 0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0xd9,0xb2,0xe1,0xc3,0xaf,0xe0,0x40,0xae,0xcf, - 0x86,0xe5,0xe4,0x9a,0xc4,0xe3,0xc1,0x07,0xe2,0x62,0x06,0xe1,0x79,0x85,0xe0,0x09, - 0x05,0xcf,0x86,0xe5,0xfb,0x02,0xd4,0x1c,0xe3,0xe7,0x75,0xe2,0x3e,0x75,0xe1,0x19, - 0x75,0xe0,0xf2,0x74,0xcf,0x86,0xe5,0xbf,0x74,0x94,0x07,0x63,0xaa,0x74,0x07,0x00, - 0x07,0x00,0xe3,0x93,0x77,0xe2,0x58,0x77,0xe1,0x77,0x01,0xe0,0xf0,0x76,0xcf,0x86, - 0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0, - 0x90,0x90,0xa8,0x00,0x05,0xff,0xf0,0x90,0x90,0xa9,0x00,0x10,0x09,0x05,0xff,0xf0, - 0x90,0x90,0xaa,0x00,0x05,0xff,0xf0,0x90,0x90,0xab,0x00,0xd1,0x12,0x10,0x09,0x05, - 0xff,0xf0,0x90,0x90,0xac,0x00,0x05,0xff,0xf0,0x90,0x90,0xad,0x00,0x10,0x09,0x05, - 0xff,0xf0,0x90,0x90,0xae,0x00,0x05,0xff,0xf0,0x90,0x90,0xaf,0x00,0xd2,0x24,0xd1, - 0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb0,0x00,0x05,0xff,0xf0,0x90,0x90,0xb1, - 0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb2,0x00,0x05,0xff,0xf0,0x90,0x90,0xb3, - 0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb4,0x00,0x05,0xff,0xf0,0x90, - 0x90,0xb5,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb6,0x00,0x05,0xff,0xf0,0x90, - 0x90,0xb7,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90, - 0xb8,0x00,0x05,0xff,0xf0,0x90,0x90,0xb9,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90, - 0xba,0x00,0x05,0xff,0xf0,0x90,0x90,0xbb,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0, - 0x90,0x90,0xbc,0x00,0x05,0xff,0xf0,0x90,0x90,0xbd,0x00,0x10,0x09,0x05,0xff,0xf0, - 0x90,0x90,0xbe,0x00,0x05,0xff,0xf0,0x90,0x90,0xbf,0x00,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x05,0xff,0xf0,0x90,0x91,0x80,0x00,0x05,0xff,0xf0,0x90,0x91,0x81,0x00,0x10, - 0x09,0x05,0xff,0xf0,0x90,0x91,0x82,0x00,0x05,0xff,0xf0,0x90,0x91,0x83,0x00,0xd1, - 0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x84,0x00,0x05,0xff,0xf0,0x90,0x91,0x85, - 0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x86,0x00,0x05,0xff,0xf0,0x90,0x91,0x87, - 0x00,0x94,0x4c,0x93,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91, - 0x88,0x00,0x05,0xff,0xf0,0x90,0x91,0x89,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91, - 0x8a,0x00,0x05,0xff,0xf0,0x90,0x91,0x8b,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0, - 0x90,0x91,0x8c,0x00,0x05,0xff,0xf0,0x90,0x91,0x8d,0x00,0x10,0x09,0x07,0xff,0xf0, - 0x90,0x91,0x8e,0x00,0x07,0xff,0xf0,0x90,0x91,0x8f,0x00,0x05,0x00,0x05,0x00,0xd0, - 0xa0,0xcf,0x86,0xd5,0x07,0x64,0x98,0x75,0x07,0x00,0xd4,0x07,0x63,0xa5,0x75,0x07, - 0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0x98,0x00, - 0x12,0xff,0xf0,0x90,0x93,0x99,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0x9a,0x00, - 0x12,0xff,0xf0,0x90,0x93,0x9b,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93, - 0x9c,0x00,0x12,0xff,0xf0,0x90,0x93,0x9d,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93, - 0x9e,0x00,0x12,0xff,0xf0,0x90,0x93,0x9f,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12, - 0xff,0xf0,0x90,0x93,0xa0,0x00,0x12,0xff,0xf0,0x90,0x93,0xa1,0x00,0x10,0x09,0x12, - 0xff,0xf0,0x90,0x93,0xa2,0x00,0x12,0xff,0xf0,0x90,0x93,0xa3,0x00,0xd1,0x12,0x10, - 0x09,0x12,0xff,0xf0,0x90,0x93,0xa4,0x00,0x12,0xff,0xf0,0x90,0x93,0xa5,0x00,0x10, - 0x09,0x12,0xff,0xf0,0x90,0x93,0xa6,0x00,0x12,0xff,0xf0,0x90,0x93,0xa7,0x00,0xcf, - 0x86,0xe5,0x2e,0x75,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff, - 0xf0,0x90,0x93,0xa8,0x00,0x12,0xff,0xf0,0x90,0x93,0xa9,0x00,0x10,0x09,0x12,0xff, - 0xf0,0x90,0x93,0xaa,0x00,0x12,0xff,0xf0,0x90,0x93,0xab,0x00,0xd1,0x12,0x10,0x09, - 0x12,0xff,0xf0,0x90,0x93,0xac,0x00,0x12,0xff,0xf0,0x90,0x93,0xad,0x00,0x10,0x09, - 0x12,0xff,0xf0,0x90,0x93,0xae,0x00,0x12,0xff,0xf0,0x90,0x93,0xaf,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb0,0x00,0x12,0xff,0xf0,0x90,0x93, - 0xb1,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb2,0x00,0x12,0xff,0xf0,0x90,0x93, - 0xb3,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb4,0x00,0x12,0xff,0xf0, - 0x90,0x93,0xb5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb6,0x00,0x12,0xff,0xf0, - 0x90,0x93,0xb7,0x00,0x93,0x28,0x92,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90, - 0x93,0xb8,0x00,0x12,0xff,0xf0,0x90,0x93,0xb9,0x00,0x10,0x09,0x12,0xff,0xf0,0x90, - 0x93,0xba,0x00,0x12,0xff,0xf0,0x90,0x93,0xbb,0x00,0x00,0x00,0x12,0x00,0xd4,0x1f, - 0xe3,0x47,0x76,0xe2,0xd2,0x75,0xe1,0x71,0x75,0xe0,0x52,0x75,0xcf,0x86,0xe5,0x1f, - 0x75,0x94,0x0a,0xe3,0x0a,0x75,0x62,0x01,0x75,0x07,0x00,0x07,0x00,0xe3,0x46,0x78, - 0xe2,0x17,0x78,0xd1,0x09,0xe0,0xb4,0x77,0xcf,0x06,0x0b,0x00,0xe0,0xe7,0x77,0xcf, - 0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11,0xff, - 0xf0,0x90,0xb3,0x80,0x00,0x11,0xff,0xf0,0x90,0xb3,0x81,0x00,0x10,0x09,0x11,0xff, - 0xf0,0x90,0xb3,0x82,0x00,0x11,0xff,0xf0,0x90,0xb3,0x83,0x00,0xd1,0x12,0x10,0x09, - 0x11,0xff,0xf0,0x90,0xb3,0x84,0x00,0x11,0xff,0xf0,0x90,0xb3,0x85,0x00,0x10,0x09, - 0x11,0xff,0xf0,0x90,0xb3,0x86,0x00,0x11,0xff,0xf0,0x90,0xb3,0x87,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x88,0x00,0x11,0xff,0xf0,0x90,0xb3, - 0x89,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8a,0x00,0x11,0xff,0xf0,0x90,0xb3, - 0x8b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8c,0x00,0x11,0xff,0xf0, - 0x90,0xb3,0x8d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8e,0x00,0x11,0xff,0xf0, - 0x90,0xb3,0x8f,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90, - 0xb3,0x90,0x00,0x11,0xff,0xf0,0x90,0xb3,0x91,0x00,0x10,0x09,0x11,0xff,0xf0,0x90, - 0xb3,0x92,0x00,0x11,0xff,0xf0,0x90,0xb3,0x93,0x00,0xd1,0x12,0x10,0x09,0x11,0xff, - 0xf0,0x90,0xb3,0x94,0x00,0x11,0xff,0xf0,0x90,0xb3,0x95,0x00,0x10,0x09,0x11,0xff, - 0xf0,0x90,0xb3,0x96,0x00,0x11,0xff,0xf0,0x90,0xb3,0x97,0x00,0xd2,0x24,0xd1,0x12, - 0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x98,0x00,0x11,0xff,0xf0,0x90,0xb3,0x99,0x00, - 0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9a,0x00,0x11,0xff,0xf0,0x90,0xb3,0x9b,0x00, - 0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9c,0x00,0x11,0xff,0xf0,0x90,0xb3, - 0x9d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9e,0x00,0x11,0xff,0xf0,0x90,0xb3, - 0x9f,0x00,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90, - 0xb3,0xa0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa1,0x00,0x10,0x09,0x11,0xff,0xf0,0x90, - 0xb3,0xa2,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa3,0x00,0xd1,0x12,0x10,0x09,0x11,0xff, - 0xf0,0x90,0xb3,0xa4,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa5,0x00,0x10,0x09,0x11,0xff, - 0xf0,0x90,0xb3,0xa6,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa7,0x00,0xd2,0x24,0xd1,0x12, - 0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xa8,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa9,0x00, - 0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xaa,0x00,0x11,0xff,0xf0,0x90,0xb3,0xab,0x00, - 0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xac,0x00,0x11,0xff,0xf0,0x90,0xb3, - 0xad,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xae,0x00,0x11,0xff,0xf0,0x90,0xb3, - 0xaf,0x00,0x93,0x23,0x92,0x1f,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xb0, - 0x00,0x11,0xff,0xf0,0x90,0xb3,0xb1,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xb2, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x15,0xe4,0xf9,0x7a,0xe3,0x03, - 0x79,0xe2,0xfc,0x77,0xe1,0x4c,0x77,0xe0,0x05,0x77,0xcf,0x06,0x0c,0x00,0xe4,0x53, - 0x7e,0xe3,0xac,0x7d,0xe2,0x55,0x7d,0xd1,0x0c,0xe0,0x1a,0x7d,0xcf,0x86,0x65,0xfb, - 0x7c,0x14,0x00,0xe0,0x1e,0x7d,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4,0x90,0xd3,0x48, - 0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x80,0x00,0x10,0xff,0xf0, - 0x91,0xa3,0x81,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x82,0x00,0x10,0xff,0xf0, - 0x91,0xa3,0x83,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x84,0x00,0x10, - 0xff,0xf0,0x91,0xa3,0x85,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x86,0x00,0x10, - 0xff,0xf0,0x91,0xa3,0x87,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91, - 0xa3,0x88,0x00,0x10,0xff,0xf0,0x91,0xa3,0x89,0x00,0x10,0x09,0x10,0xff,0xf0,0x91, - 0xa3,0x8a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8b,0x00,0xd1,0x12,0x10,0x09,0x10,0xff, - 0xf0,0x91,0xa3,0x8c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8d,0x00,0x10,0x09,0x10,0xff, - 0xf0,0x91,0xa3,0x8e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8f,0x00,0xd3,0x48,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x90,0x00,0x10,0xff,0xf0,0x91,0xa3, - 0x91,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x92,0x00,0x10,0xff,0xf0,0x91,0xa3, - 0x93,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x94,0x00,0x10,0xff,0xf0, - 0x91,0xa3,0x95,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x96,0x00,0x10,0xff,0xf0, - 0x91,0xa3,0x97,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x98, - 0x00,0x10,0xff,0xf0,0x91,0xa3,0x99,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x9a, - 0x00,0x10,0xff,0xf0,0x91,0xa3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91, - 0xa3,0x9c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9d,0x00,0x10,0x09,0x10,0xff,0xf0,0x91, - 0xa3,0x9e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9f,0x00,0xd1,0x11,0xe0,0x7a,0x80,0xcf, - 0x86,0xe5,0x71,0x80,0xe4,0x3a,0x80,0xcf,0x06,0x00,0x00,0xe0,0x43,0x82,0xcf,0x86, - 0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x09,0xe3,0x78,0x80,0xcf,0x06,0x0c,0x00,0xd3, - 0x06,0xcf,0x06,0x00,0x00,0xe2,0xa3,0x81,0xe1,0x7e,0x81,0xd0,0x06,0xcf,0x06,0x00, - 0x00,0xcf,0x86,0xa5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09, - 0x14,0xff,0xf0,0x96,0xb9,0xa0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa1,0x00,0x10,0x09, - 0x14,0xff,0xf0,0x96,0xb9,0xa2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa3,0x00,0xd1,0x12, - 0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa4,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa5,0x00, - 0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa6,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa7,0x00, - 0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa8,0x00,0x14,0xff,0xf0, - 0x96,0xb9,0xa9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xaa,0x00,0x14,0xff,0xf0, - 0x96,0xb9,0xab,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xac,0x00,0x14, - 0xff,0xf0,0x96,0xb9,0xad,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xae,0x00,0x14, - 0xff,0xf0,0x96,0xb9,0xaf,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff, - 0xf0,0x96,0xb9,0xb0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb1,0x00,0x10,0x09,0x14,0xff, - 0xf0,0x96,0xb9,0xb2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb3,0x00,0xd1,0x12,0x10,0x09, - 0x14,0xff,0xf0,0x96,0xb9,0xb4,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb5,0x00,0x10,0x09, - 0x14,0xff,0xf0,0x96,0xb9,0xb6,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb7,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb8,0x00,0x14,0xff,0xf0,0x96,0xb9, - 0xb9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xba,0x00,0x14,0xff,0xf0,0x96,0xb9, - 0xbb,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbc,0x00,0x14,0xff,0xf0, - 0x96,0xb9,0xbd,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbe,0x00,0x14,0xff,0xf0, - 0x96,0xb9,0xbf,0x00,0x14,0x00,0xd2,0x14,0xe1,0x8d,0x81,0xe0,0x84,0x81,0xcf,0x86, - 0xe5,0x45,0x81,0xe4,0x02,0x81,0xcf,0x06,0x12,0x00,0xd1,0x0b,0xe0,0xb8,0x82,0xcf, - 0x86,0xcf,0x06,0x00,0x00,0xe0,0xf8,0x8a,0xcf,0x86,0xd5,0x22,0xe4,0x33,0x88,0xe3, - 0xf6,0x87,0xe2,0x9b,0x87,0xe1,0x94,0x87,0xe0,0x8d,0x87,0xcf,0x86,0xe5,0x5e,0x87, - 0xe4,0x45,0x87,0x93,0x07,0x62,0x34,0x87,0x12,0xe6,0x12,0xe6,0xe4,0x99,0x88,0xe3, - 0x92,0x88,0xd2,0x09,0xe1,0x1b,0x88,0xcf,0x06,0x10,0x00,0xe1,0x82,0x88,0xe0,0x4f, - 0x88,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09, - 0x12,0xff,0xf0,0x9e,0xa4,0xa2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa3,0x00,0x10,0x09, - 0x12,0xff,0xf0,0x9e,0xa4,0xa4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa5,0x00,0xd1,0x12, - 0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa6,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa7,0x00, - 0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa8,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa9,0x00, - 0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xaa,0x00,0x12,0xff,0xf0, - 0x9e,0xa4,0xab,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xac,0x00,0x12,0xff,0xf0, - 0x9e,0xa4,0xad,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xae,0x00,0x12, - 0xff,0xf0,0x9e,0xa4,0xaf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb0,0x00,0x12, - 0xff,0xf0,0x9e,0xa4,0xb1,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff, - 0xf0,0x9e,0xa4,0xb2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb3,0x00,0x10,0x09,0x12,0xff, - 0xf0,0x9e,0xa4,0xb4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb5,0x00,0xd1,0x12,0x10,0x09, - 0x12,0xff,0xf0,0x9e,0xa4,0xb6,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb7,0x00,0x10,0x09, - 0x12,0xff,0xf0,0x9e,0xa4,0xb8,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb9,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xba,0x00,0x12,0xff,0xf0,0x9e,0xa4, - 0xbb,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbc,0x00,0x12,0xff,0xf0,0x9e,0xa4, - 0xbd,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbe,0x00,0x12,0xff,0xf0, - 0x9e,0xa4,0xbf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa5,0x80,0x00,0x12,0xff,0xf0, - 0x9e,0xa5,0x81,0x00,0x94,0x1e,0x93,0x1a,0x92,0x16,0x91,0x12,0x10,0x09,0x12,0xff, - 0xf0,0x9e,0xa5,0x82,0x00,0x12,0xff,0xf0,0x9e,0xa5,0x83,0x00,0x12,0x00,0x12,0x00, - 0x12,0x00,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - /* nfdi_c0100 */ - 0x57,0x04,0x01,0x00,0xc6,0xe5,0x91,0x13,0xe4,0x27,0x0c,0xe3,0x61,0x07,0xe2,0xda, - 0x01,0xc1,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0xe4,0xd4,0x7c,0xd3,0x3c, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0x80,0x00,0x01,0xff,0x41,0xcc, - 0x81,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x82,0x00,0x01,0xff,0x41,0xcc,0x83,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0x88,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0x43,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x45,0xcc,0x80,0x00,0x01,0xff,0x45,0xcc,0x81,0x00,0x10,0x08,0x01,0xff, - 0x45,0xcc,0x82,0x00,0x01,0xff,0x45,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x49,0xcc,0x80,0x00,0x01,0xff,0x49,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x49,0xcc, - 0x82,0x00,0x01,0xff,0x49,0xcc,0x88,0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04, - 0x01,0x00,0x01,0xff,0x4e,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x80,0x00, - 0x01,0xff,0x4f,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x82,0x00, - 0x01,0xff,0x4f,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x88,0x00,0x01,0x00, - 0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x55,0xcc,0x80,0x00,0x10,0x08, - 0x01,0xff,0x55,0xcc,0x81,0x00,0x01,0xff,0x55,0xcc,0x82,0x00,0x91,0x10,0x10,0x08, - 0x01,0xff,0x55,0xcc,0x88,0x00,0x01,0xff,0x59,0xcc,0x81,0x00,0x01,0x00,0xd4,0x7c, - 0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff, - 0x61,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc, - 0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc, - 0x8a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x65,0xcc,0x80,0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08, - 0x01,0xff,0x65,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x69,0xcc,0x80,0x00,0x01,0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff, - 0x69,0xcc,0x82,0x00,0x01,0xff,0x69,0xcc,0x88,0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c, - 0x10,0x04,0x01,0x00,0x01,0xff,0x6e,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc, - 0x80,0x00,0x01,0xff,0x6f,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc, - 0x82,0x00,0x01,0xff,0x6f,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00, - 0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x75,0xcc,0x80,0x00, - 0x10,0x08,0x01,0xff,0x75,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x82,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x75,0xcc,0x88,0x00,0x01,0xff,0x79,0xcc,0x81,0x00,0x10,0x04, - 0x01,0x00,0x01,0xff,0x79,0xcc,0x88,0x00,0xe1,0x9a,0x03,0xe0,0xd3,0x01,0xcf,0x86, - 0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc, - 0x84,0x00,0x01,0xff,0x61,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x86,0x00, - 0x01,0xff,0x61,0xcc,0x86,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa8,0x00, - 0x01,0xff,0x61,0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x43,0xcc,0x81,0x00,0x01,0xff, - 0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x43,0xcc,0x82,0x00, - 0x01,0xff,0x63,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x43,0xcc,0x87,0x00,0x01,0xff, - 0x63,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x43,0xcc,0x8c,0x00,0x01,0xff, - 0x63,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0x8c,0x00,0x01,0xff,0x64,0xcc, - 0x8c,0x00,0xd3,0x34,0xd2,0x14,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x45,0xcc, - 0x84,0x00,0x01,0xff,0x65,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc, - 0x86,0x00,0x01,0xff,0x65,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x87,0x00, - 0x01,0xff,0x65,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc, - 0xa8,0x00,0x01,0xff,0x65,0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x8c,0x00, - 0x01,0xff,0x65,0xcc,0x8c,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x82,0x00, - 0x01,0xff,0x67,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0x86,0x00,0x01,0xff, - 0x67,0xcc,0x86,0x00,0xd4,0x74,0xd3,0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x47,0xcc,0x87,0x00,0x01,0xff,0x67,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x47,0xcc, - 0xa7,0x00,0x01,0xff,0x67,0xcc,0xa7,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x48,0xcc, - 0x82,0x00,0x01,0xff,0x68,0xcc,0x82,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x49,0xcc,0x83,0x00,0x01,0xff,0x69,0xcc,0x83,0x00,0x10,0x08,0x01,0xff, - 0x49,0xcc,0x84,0x00,0x01,0xff,0x69,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x49,0xcc,0x86,0x00,0x01,0xff,0x69,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x49,0xcc, - 0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8,0x00,0xd3,0x30,0xd2,0x10,0x91,0x0c,0x10,0x08, - 0x01,0xff,0x49,0xcc,0x87,0x00,0x01,0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x4a,0xcc,0x82,0x00,0x01,0xff,0x6a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc, - 0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7,0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00, - 0x01,0xff,0x4c,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff, - 0x4c,0xcc,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff, - 0x4c,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x6c,0xcc,0x8c,0x00,0x01,0x00,0xcf,0x86, - 0xd5,0xd4,0xd4,0x60,0xd3,0x30,0xd2,0x10,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0x4e,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x81,0x00, - 0x01,0xff,0x4e,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x01,0xff, - 0x4e,0xcc,0x8c,0x00,0xd2,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x6e,0xcc,0x8c,0x00, - 0x01,0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x84,0x00,0x01,0xff, - 0x6f,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc, - 0x86,0x00,0xd3,0x34,0xd2,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8b,0x00, - 0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc, - 0x81,0x00,0x01,0xff,0x72,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa7,0x00, - 0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc, - 0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x53,0xcc,0x81,0x00, - 0x01,0xff,0x73,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x82,0x00, - 0x01,0xff,0x73,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x53,0xcc,0xa7,0x00,0x01,0xff, - 0x73,0xcc,0xa7,0x00,0xd4,0x74,0xd3,0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x53,0xcc,0x8c,0x00,0x01,0xff,0x73,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x54,0xcc, - 0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x54,0xcc, - 0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x55,0xcc,0x83,0x00,0x01,0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff, - 0x55,0xcc,0x84,0x00,0x01,0xff,0x75,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x55,0xcc,0x86,0x00,0x01,0xff,0x75,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x55,0xcc, - 0x8a,0x00,0x01,0xff,0x75,0xcc,0x8a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x55,0xcc,0x8b,0x00,0x01,0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff, - 0x55,0xcc,0xa8,0x00,0x01,0xff,0x75,0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x57,0xcc,0x82,0x00,0x01,0xff,0x77,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x59,0xcc, - 0x82,0x00,0x01,0xff,0x79,0xcc,0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x59,0xcc,0x88,0x00,0x01,0xff,0x5a,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc, - 0x81,0x00,0x01,0xff,0x5a,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc, - 0x87,0x00,0x01,0xff,0x5a,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00, - 0x01,0x00,0xd0,0x4a,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x2c,0xd3,0x18,0x92,0x14, - 0x91,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00, - 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0x55,0xcc,0x9b,0x00,0x93,0x14,0x92,0x10,0x91,0x0c,0x10,0x08,0x01,0xff, - 0x75,0xcc,0x9b,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xb4, - 0xd4,0x24,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00, - 0x01,0xff,0x41,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff, - 0x49,0xcc,0x8c,0x00,0xd3,0x46,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc, - 0x8c,0x00,0x01,0xff,0x4f,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00, - 0x01,0xff,0x55,0xcc,0x8c,0x00,0xd1,0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00, - 0x01,0xff,0x55,0xcc,0x88,0xcc,0x84,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc, - 0x84,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x75,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x8c,0x00, - 0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc, - 0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00, - 0x10,0x0a,0x01,0xff,0x41,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc, - 0x84,0x00,0xd4,0x80,0xd3,0x3a,0xd2,0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc, - 0x87,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff, - 0xc3,0x86,0xcc,0x84,0x00,0x01,0xff,0xc3,0xa6,0xcc,0x84,0x00,0x51,0x04,0x01,0x00, - 0x10,0x08,0x01,0xff,0x47,0xcc,0x8c,0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00, - 0x10,0x08,0x01,0xff,0x4f,0xcc,0xa8,0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14, - 0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa8,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc, - 0x84,0x00,0x10,0x09,0x01,0xff,0xc6,0xb7,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc, - 0x8c,0x00,0xd3,0x24,0xd2,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00, - 0x01,0x00,0x01,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x81,0x00,0x01,0xff, - 0x67,0xcc,0x81,0x00,0x04,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x4e,0xcc, - 0x80,0x00,0x04,0xff,0x6e,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x8a,0xcc, - 0x81,0x00,0x01,0xff,0x61,0xcc,0x8a,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xc3,0x86,0xcc,0x81,0x00,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, - 0xc3,0x98,0xcc,0x81,0x00,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00,0xe2,0x07,0x02,0xe1, - 0xae,0x01,0xe0,0x93,0x01,0xcf,0x86,0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0x8f,0x00,0x01,0xff,0x61,0xcc,0x8f,0x00,0x10, - 0x08,0x01,0xff,0x41,0xcc,0x91,0x00,0x01,0xff,0x61,0xcc,0x91,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x45,0xcc,0x8f,0x00,0x01,0xff,0x65,0xcc,0x8f,0x00,0x10,0x08,0x01, - 0xff,0x45,0xcc,0x91,0x00,0x01,0xff,0x65,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x49,0xcc,0x8f,0x00,0x01,0xff,0x69,0xcc,0x8f,0x00,0x10,0x08,0x01, - 0xff,0x49,0xcc,0x91,0x00,0x01,0xff,0x69,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x4f,0xcc,0x8f,0x00,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x4f, - 0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc,0x91,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x52,0xcc,0x8f,0x00,0x01,0xff,0x72,0xcc,0x8f,0x00,0x10,0x08,0x01, - 0xff,0x52,0xcc,0x91,0x00,0x01,0xff,0x72,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x55,0xcc,0x8f,0x00,0x01,0xff,0x75,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x55, - 0xcc,0x91,0x00,0x01,0xff,0x75,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x04, - 0xff,0x53,0xcc,0xa6,0x00,0x04,0xff,0x73,0xcc,0xa6,0x00,0x10,0x08,0x04,0xff,0x54, - 0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc,0xa6,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04, - 0xff,0x48,0xcc,0x8c,0x00,0x04,0xff,0x68,0xcc,0x8c,0x00,0xd4,0x68,0xd3,0x20,0xd2, - 0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x07,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10, - 0x08,0x04,0xff,0x41,0xcc,0x87,0x00,0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1, - 0x10,0x10,0x08,0x04,0xff,0x45,0xcc,0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10, - 0x0a,0x04,0xff,0x4f,0xcc,0x88,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84, - 0x00,0xd1,0x14,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f, - 0xcc,0x83,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x4f,0xcc,0x87,0x00,0x04,0xff,0x6f, - 0xcc,0x87,0x00,0x93,0x30,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x87, - 0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x59, - 0xcc,0x84,0x00,0x04,0xff,0x79,0xcc,0x84,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07, - 0x00,0x08,0x00,0x08,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08,0x11, - 0x04,0x08,0x00,0x09,0x00,0x09,0x00,0x09,0x00,0x01,0x00,0x01,0x00,0xd0,0x22,0xcf, - 0x86,0x55,0x04,0x01,0x00,0x94,0x18,0x53,0x04,0x01,0x00,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x01,0x00,0x04,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x07,0x00,0x01,0x00,0xcf, - 0x86,0xd5,0x18,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51, - 0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x94,0x18,0x53,0x04,0x01,0x00,0xd2, - 0x08,0x11,0x04,0x01,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07, - 0x00,0x07,0x00,0xe1,0x34,0x01,0xd0,0x72,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0xe6, - 0xd3,0x10,0x52,0x04,0x01,0xe6,0x91,0x08,0x10,0x04,0x01,0xe6,0x01,0xe8,0x01,0xdc, - 0x92,0x0c,0x51,0x04,0x01,0xdc,0x10,0x04,0x01,0xe8,0x01,0xd8,0x01,0xdc,0xd4,0x2c, - 0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0xdc,0x01,0xca,0x10,0x04,0x01,0xca, - 0x01,0xdc,0x51,0x04,0x01,0xdc,0x10,0x04,0x01,0xdc,0x01,0xca,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x01,0xca,0x01,0xdc,0x01,0xdc,0x01,0xdc,0xd3,0x08,0x12,0x04,0x01,0xdc, - 0x01,0x01,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x01,0x01,0xdc,0x01,0xdc,0x91,0x08, - 0x10,0x04,0x01,0xdc,0x01,0xe6,0x01,0xe6,0xcf,0x86,0xd5,0x7e,0xd4,0x46,0xd3,0x2e, - 0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01,0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00, - 0x10,0x04,0x01,0xe6,0x01,0xff,0xcc,0x93,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcc, - 0x88,0xcc,0x81,0x00,0x01,0xf0,0x10,0x04,0x04,0xe6,0x04,0xdc,0xd2,0x08,0x11,0x04, - 0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x04,0xdc, - 0x06,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x07,0xe6,0x10,0x04,0x07,0xe6,0x07,0xdc, - 0x51,0x04,0x07,0xdc,0x10,0x04,0x07,0xdc,0x07,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x08,0xe8,0x08,0xdc,0x10,0x04,0x08,0xdc,0x08,0xe6,0xd1,0x08,0x10,0x04,0x08,0xe9, - 0x07,0xea,0x10,0x04,0x07,0xea,0x07,0xe9,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04, - 0x01,0xea,0x10,0x04,0x04,0xe9,0x06,0xe6,0x06,0xe6,0x06,0xe6,0xd3,0x13,0x52,0x04, - 0x0a,0x00,0x91,0x0b,0x10,0x07,0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x0a,0x00,0xd2, - 0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x01,0x00,0x09,0x00,0x51,0x04,0x09,0x00,0x10, - 0x06,0x01,0xff,0x3b,0x00,0x10,0x00,0xd0,0xe1,0xcf,0x86,0xd5,0x7a,0xd4,0x5f,0xd3, - 0x21,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcc, - 0x81,0x00,0x10,0x09,0x01,0xff,0xce,0x91,0xcc,0x81,0x00,0x01,0xff,0xc2,0xb7,0x00, - 0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x95,0xcc,0x81,0x00,0x01,0xff,0xce, - 0x97,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0x00,0x00,0xd1, - 0x0d,0x10,0x09,0x01,0xff,0xce,0x9f,0xcc,0x81,0x00,0x00,0x00,0x10,0x09,0x01,0xff, - 0xce,0xa5,0xcc,0x81,0x00,0x01,0xff,0xce,0xa9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13, - 0x91,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0x01,0x00,0xd4,0x4a,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10, - 0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01, - 0xff,0xce,0x99,0xcc,0x88,0x00,0x01,0xff,0xce,0xa5,0xcc,0x88,0x00,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0xb1,0xcc,0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81,0x00,0x10, - 0x09,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0x93, - 0x17,0x92,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x81,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x39,0x53,0x04, - 0x01,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x88, - 0x00,0x01,0xff,0xcf,0x85,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf, - 0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89, - 0xcc,0x81,0x00,0x0a,0x00,0xd3,0x26,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x01,0xff,0xcf,0x92,0xcc,0x81,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcf,0x92, - 0xcc,0x88,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0xd2,0x0c,0x51,0x04,0x06, - 0x00,0x10,0x04,0x01,0x00,0x04,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10, - 0x04,0x01,0x00,0x04,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, - 0x00,0x04,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51, - 0x04,0x05,0x00,0x10,0x04,0x06,0x00,0x07,0x00,0x12,0x04,0x07,0x00,0x08,0x00,0xe3, - 0x47,0x04,0xe2,0xbe,0x02,0xe1,0x07,0x01,0xd0,0x8b,0xcf,0x86,0xd5,0x6c,0xd4,0x53, - 0xd3,0x30,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0,0x95,0xcc,0x80,0x00,0x01, - 0xff,0xd0,0x95,0xcc,0x88,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x93,0xcc,0x81, - 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x86,0xcc,0x88,0x00, - 0x52,0x04,0x01,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x9a,0xcc,0x81,0x00,0x04, - 0xff,0xd0,0x98,0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x86,0x00,0x01, - 0x00,0x53,0x04,0x01,0x00,0x92,0x11,0x91,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xd0, - 0x98,0xcc,0x86,0x00,0x01,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00, - 0x92,0x11,0x91,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x01, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0x57,0x54,0x04,0x01,0x00,0xd3,0x30,0xd2,0x1f,0xd1, - 0x12,0x10,0x09,0x04,0xff,0xd0,0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88, - 0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0xb3,0xcc,0x81,0x00,0x51,0x04,0x01,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0xd1,0x96,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xd0,0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8,0xcc,0x80, - 0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x86,0x00,0x01,0x00,0x54,0x04,0x01,0x00, - 0x93,0x1a,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb4, - 0xcc,0x8f,0x00,0x01,0xff,0xd1,0xb5,0xcc,0x8f,0x00,0x01,0x00,0xd0,0x2e,0xcf,0x86, - 0x95,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x01,0xe6,0x51,0x04,0x01,0xe6,0x10,0x04,0x01,0xe6,0x0a,0xe6,0x92,0x08,0x11,0x04, - 0x04,0x00,0x06,0x00,0x04,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xbe,0xd4,0x4a, - 0xd3,0x2a,0xd2,0x1a,0xd1,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x96,0xcc,0x86, - 0x00,0x10,0x09,0x01,0xff,0xd0,0xb6,0xcc,0x86,0x00,0x01,0x00,0xd1,0x08,0x10,0x04, - 0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00, - 0x06,0x00,0x10,0x04,0x06,0x00,0x09,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xd0,0x90,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09, - 0x01,0xff,0xd0,0x90,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x51,0x04, - 0x01,0x00,0x10,0x09,0x01,0xff,0xd0,0x95,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc, - 0x86,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0x98,0xcc,0x88, - 0x00,0x01,0xff,0xd3,0x99,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x96, - 0xcc,0x88,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0x97, - 0xcc,0x88,0x00,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0xd4,0x74,0xd3,0x3a,0xd2,0x16, - 0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd0,0x98,0xcc,0x84,0x00,0x01,0xff,0xd0, - 0xb8,0xcc,0x84,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x98,0xcc,0x88,0x00,0x01, - 0xff,0xd0,0xb8,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0x9e,0xcc,0x88,0x00,0x01, - 0xff,0xd0,0xbe,0xcc,0x88,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, - 0xd3,0xa8,0xcc,0x88,0x00,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09, - 0x04,0xff,0xd0,0xad,0xcc,0x88,0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x10,0x09, - 0x01,0xff,0xd0,0xa3,0xcc,0x84,0x00,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0xd3,0x3a, - 0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x88,0x00,0x01,0xff,0xd1, - 0x83,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x8b,0x00,0x01,0xff,0xd1, - 0x83,0xcc,0x8b,0x00,0x91,0x12,0x10,0x09,0x01,0xff,0xd0,0xa7,0xcc,0x88,0x00,0x01, - 0xff,0xd1,0x87,0xcc,0x88,0x00,0x08,0x00,0x92,0x16,0x91,0x12,0x10,0x09,0x01,0xff, - 0xd0,0xab,0xcc,0x88,0x00,0x01,0xff,0xd1,0x8b,0xcc,0x88,0x00,0x09,0x00,0x09,0x00, - 0xd1,0x74,0xd0,0x36,0xcf,0x86,0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04, - 0x09,0x00,0x0a,0x00,0x0a,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x0a,0x00,0x11,0x04, - 0x0b,0x00,0x0c,0x00,0x10,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0x00, - 0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x14, - 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0xd0,0xba,0xcf,0x86,0xd5,0x4c,0xd4,0x24,0x53,0x04,0x01,0x00, - 0xd2,0x10,0xd1,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x10,0x04,0x04,0x00,0x00,0x00, - 0xd1,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x0d,0x00,0xd3,0x18, - 0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x02,0xdc,0x02,0xe6,0x51,0x04,0x02,0xe6, - 0x10,0x04,0x02,0xdc,0x02,0xe6,0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xde, - 0x02,0xdc,0x02,0xe6,0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04, - 0x08,0xdc,0x02,0xdc,0x02,0xdc,0xd2,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc, - 0x02,0xe6,0xd1,0x08,0x10,0x04,0x02,0xe6,0x02,0xde,0x10,0x04,0x02,0xe4,0x02,0xe6, - 0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x0a,0x01,0x0b,0x10,0x04,0x01,0x0c, - 0x01,0x0d,0xd1,0x08,0x10,0x04,0x01,0x0e,0x01,0x0f,0x10,0x04,0x01,0x10,0x01,0x11, - 0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x12,0x01,0x13,0x10,0x04,0x09,0x13,0x01,0x14, - 0xd1,0x08,0x10,0x04,0x01,0x15,0x01,0x16,0x10,0x04,0x01,0x00,0x01,0x17,0xcf,0x86, - 0xd5,0x28,0x94,0x24,0x93,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x18, - 0x10,0x04,0x01,0x19,0x01,0x00,0xd1,0x08,0x10,0x04,0x02,0xe6,0x08,0xdc,0x10,0x04, - 0x08,0x00,0x08,0x12,0x00,0x00,0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x14,0x00,0x93,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0xe2,0xfa,0x01,0xe1,0x2a,0x01,0xd0,0xa7,0xcf,0x86, - 0xd5,0x54,0xd4,0x28,0xd3,0x10,0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x0d,0x00, - 0x10,0x00,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x08,0x00, - 0x91,0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x07,0x00,0xd3,0x0c,0x52,0x04,0x07,0xe6, - 0x11,0x04,0x07,0xe6,0x0a,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0a,0x1e,0x0a,0x1f, - 0x10,0x04,0x0a,0x20,0x01,0x00,0xd1,0x08,0x10,0x04,0x0f,0x00,0x00,0x00,0x10,0x04, - 0x08,0x00,0x01,0x00,0xd4,0x3d,0x93,0x39,0xd2,0x1a,0xd1,0x08,0x10,0x04,0x0c,0x00, - 0x01,0x00,0x10,0x09,0x01,0xff,0xd8,0xa7,0xd9,0x93,0x00,0x01,0xff,0xd8,0xa7,0xd9, - 0x94,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd9,0x88,0xd9,0x94,0x00,0x01,0xff,0xd8, - 0xa7,0xd9,0x95,0x00,0x10,0x09,0x01,0xff,0xd9,0x8a,0xd9,0x94,0x00,0x01,0x00,0x01, - 0x00,0x53,0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0a, - 0x00,0x0a,0x00,0xcf,0x86,0xd5,0x5c,0xd4,0x20,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51, - 0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0x1b,0xd1,0x08,0x10,0x04,0x01,0x1c,0x01, - 0x1d,0x10,0x04,0x01,0x1e,0x01,0x1f,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01, - 0x20,0x01,0x21,0x10,0x04,0x01,0x22,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xe6,0x04, - 0xdc,0x10,0x04,0x07,0xdc,0x07,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x07,0xe6,0x08, - 0xe6,0x08,0xe6,0xd1,0x08,0x10,0x04,0x08,0xdc,0x08,0xe6,0x10,0x04,0x08,0xe6,0x0c, - 0xdc,0xd4,0x10,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06, - 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x23,0x01,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53, - 0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x04,0x00,0x01,0x00,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x04,0x00,0xcf,0x86,0xd5,0x5b,0xd4,0x2e,0xd3,0x1e,0x92,0x1a,0xd1, - 0x0d,0x10,0x09,0x01,0xff,0xdb,0x95,0xd9,0x94,0x00,0x01,0x00,0x10,0x09,0x01,0xff, - 0xdb,0x81,0xd9,0x94,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x04,0x00,0xd3,0x19,0xd2,0x11,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x01,0xff,0xdb,0x92,0xd9,0x94,0x00,0x11,0x04,0x01,0x00,0x01,0xe6, - 0x52,0x04,0x01,0xe6,0xd1,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00, - 0x01,0xe6,0xd4,0x38,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x01,0xe6,0x10,0x04,0x01,0xe6, - 0x01,0xdc,0xd1,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6, - 0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0xdc,0x01,0xe6, - 0x91,0x08,0x10,0x04,0x01,0xe6,0x01,0xdc,0x07,0x00,0x53,0x04,0x01,0x00,0xd2,0x08, - 0x11,0x04,0x01,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00, - 0xd1,0xc8,0xd0,0x76,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x04,0x00,0x52,0x04, - 0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x93,0x10,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x04,0x00,0x04,0x24,0x04,0x00,0x04,0x00,0x04,0x00,0xd4,0x14, - 0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x07,0x00, - 0x07,0x00,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x04,0xe6, - 0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10,0x04,0x04,0xe6,0x04,0xdc,0xd2,0x0c, - 0x51,0x04,0x04,0xdc,0x10,0x04,0x04,0xe6,0x04,0xdc,0xd1,0x08,0x10,0x04,0x04,0xdc, - 0x04,0xe6,0x10,0x04,0x04,0xdc,0x04,0xe6,0xcf,0x86,0xd5,0x3c,0x94,0x38,0xd3,0x1c, - 0xd2,0x0c,0x51,0x04,0x04,0xe6,0x10,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04, - 0x04,0xdc,0x04,0xe6,0x10,0x04,0x04,0xdc,0x04,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x04,0xdc,0x04,0xe6,0x10,0x04,0x04,0xe6,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00, - 0x07,0x00,0x07,0x00,0x08,0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00, - 0x11,0x04,0x08,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x04,0x00, - 0x54,0x04,0x04,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x14,0x53,0x04, - 0x09,0x00,0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xe6,0x09,0xe6, - 0xd3,0x10,0x92,0x0c,0x51,0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0x00, - 0xd2,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x91,0x08,0x10,0x04, - 0x00,0x00,0x14,0xdc,0x14,0x00,0xe4,0x78,0x57,0xe3,0xda,0x3e,0xe2,0x89,0x3e,0xe1, - 0x91,0x2c,0xe0,0x21,0x10,0xcf,0x86,0xc5,0xe4,0x80,0x08,0xe3,0xcb,0x03,0xe2,0x61, - 0x01,0xd1,0x94,0xd0,0x5a,0xcf,0x86,0xd5,0x20,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52, - 0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x0b,0xe6,0x92,0x0c,0x51,0x04,0x0b,0xe6,0x10, - 0x04,0x0b,0x00,0x0b,0xe6,0x0b,0xe6,0xd4,0x24,0xd3,0x10,0x52,0x04,0x0b,0xe6,0x91, - 0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6,0x0b,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b, - 0x00,0x0b,0xe6,0x0b,0xe6,0x11,0x04,0x0b,0xe6,0x00,0x00,0x53,0x04,0x0b,0x00,0x52, - 0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xcf,0x86,0xd5, - 0x20,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0c, - 0x00,0x0c,0xdc,0x0c,0xdc,0x51,0x04,0x00,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x94, - 0x14,0x53,0x04,0x13,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xd0,0x4a,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4,0x20,0xd3, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0d,0x00,0x10,0x00,0x0d,0x00,0x0d,0x00,0x52, - 0x04,0x0d,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x10,0x00,0x10,0x00,0xd3,0x18,0xd2, - 0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0x91,0x08,0x10,0x04,0x11, - 0x00,0x00,0x00,0x12,0x00,0x52,0x04,0x12,0x00,0x11,0x04,0x12,0x00,0x00,0x00,0xcf, - 0x86,0xd5,0x18,0x54,0x04,0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10, - 0x04,0x00,0x00,0x14,0xdc,0x12,0xe6,0x12,0xe6,0xd4,0x30,0xd3,0x18,0xd2,0x0c,0x51, - 0x04,0x12,0xe6,0x10,0x04,0x12,0x00,0x11,0xdc,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d, - 0xdc,0x0d,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x0d,0xe6,0x91, - 0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x0d,0xdc,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10, - 0x04,0x0d,0x1b,0x0d,0x1c,0x10,0x04,0x0d,0x1d,0x0d,0xe6,0x51,0x04,0x0d,0xe6,0x10, - 0x04,0x0d,0xdc,0x0d,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x10, - 0x04,0x0d,0xdc,0x0d,0xe6,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x10,0xe6,0xe1, - 0x3a,0x01,0xd0,0x77,0xcf,0x86,0xd5,0x20,0x94,0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08, - 0x10,0x04,0x0b,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x07,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x1b,0x53,0x04,0x01,0x00,0x92,0x13,0x91,0x0f, - 0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa4,0xa8,0xe0,0xa4,0xbc,0x00,0x01,0x00,0x01, - 0x00,0xd3,0x26,0xd2,0x13,0x91,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa4,0xb0, - 0xe0,0xa4,0xbc,0x00,0x01,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xa4,0xb3,0xe0, - 0xa4,0xbc,0x00,0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x91, - 0x08,0x10,0x04,0x01,0x07,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x8c,0xd4,0x18,0x53, - 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x10, - 0x04,0x0b,0x00,0x0c,0x00,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01, - 0xe6,0x10,0x04,0x01,0xdc,0x01,0xe6,0x91,0x08,0x10,0x04,0x01,0xe6,0x0b,0x00,0x0c, - 0x00,0xd2,0x2c,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa4,0x95,0xe0,0xa4,0xbc,0x00, - 0x01,0xff,0xe0,0xa4,0x96,0xe0,0xa4,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa4,0x97, - 0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0x9c,0xe0,0xa4,0xbc,0x00,0xd1,0x16,0x10, - 0x0b,0x01,0xff,0xe0,0xa4,0xa1,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xa2,0xe0, - 0xa4,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa4,0xab,0xe0,0xa4,0xbc,0x00,0x01,0xff, - 0xe0,0xa4,0xaf,0xe0,0xa4,0xbc,0x00,0x54,0x04,0x01,0x00,0xd3,0x14,0x92,0x10,0xd1, - 0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04,0x0a,0x00,0x0c,0x00,0x0c,0x00,0xd2, - 0x10,0xd1,0x08,0x10,0x04,0x10,0x00,0x0b,0x00,0x10,0x04,0x0b,0x00,0x09,0x00,0x91, - 0x08,0x10,0x04,0x09,0x00,0x08,0x00,0x09,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x44,0xd4, - 0x2c,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10, - 0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x08,0x11, - 0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x07,0x00,0x01,0x00,0xcf, - 0x86,0xd5,0x7b,0xd4,0x42,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01, - 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x17,0xd1,0x08,0x10,0x04,0x01, - 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xe0,0xa7,0x87,0xe0,0xa6,0xbe,0x00, - 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xa7,0x87,0xe0,0xa7,0x97,0x00,0x01,0x09,0x10, - 0x04,0x08,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10, - 0x04,0x00,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0, - 0xa6,0xa1,0xe0,0xa6,0xbc,0x00,0x01,0xff,0xe0,0xa6,0xa2,0xe0,0xa6,0xbc,0x00,0x10, - 0x04,0x00,0x00,0x01,0xff,0xe0,0xa6,0xaf,0xe0,0xa6,0xbc,0x00,0xd4,0x10,0x93,0x0c, - 0x52,0x04,0x01,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00, - 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x13,0x00, - 0x10,0x04,0x14,0xe6,0x00,0x00,0xe2,0x48,0x02,0xe1,0x4f,0x01,0xd0,0xa4,0xcf,0x86, - 0xd5,0x4c,0xd4,0x34,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x07,0x00, - 0x10,0x04,0x01,0x00,0x07,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00, - 0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, - 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd3,0x2e,0xd2,0x17,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0xe0,0xa8,0xb2,0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01, - 0x00,0x10,0x0b,0x01,0xff,0xe0,0xa8,0xb8,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd2,0x08, - 0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x00,0x00,0x01,0x00, - 0xcf,0x86,0xd5,0x80,0xd4,0x34,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, - 0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x10, - 0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08, - 0x10,0x04,0x01,0x00,0x01,0x09,0x00,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x00,0x00,0x0a,0x00,0x00,0x00,0x00,0x00,0xd2,0x25,0xd1,0x0f,0x10,0x04,0x00,0x00, - 0x01,0xff,0xe0,0xa8,0x96,0xe0,0xa8,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa8,0x97, - 0xe0,0xa8,0xbc,0x00,0x01,0xff,0xe0,0xa8,0x9c,0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10, - 0x04,0x01,0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa8,0xab,0xe0,0xa8,0xbc,0x00, - 0x00,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0x93,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00, - 0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0xd0,0x82,0xcf,0x86,0xd5,0x40,0xd4,0x2c, - 0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x91,0x08, - 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04, - 0x07,0x00,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, - 0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, - 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08, - 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00, - 0x91,0x08,0x10,0x04,0x01,0x07,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x3c,0xd4,0x28, - 0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00, - 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04, - 0x01,0x00,0x01,0x09,0x00,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x91,0x08, - 0x10,0x04,0x01,0x00,0x07,0x00,0x07,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0d,0x00,0x07,0x00,0x00,0x00,0x00,0x00, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x11,0x00,0x13,0x00,0x13,0x00,0xe1,0x24, - 0x01,0xd0,0x86,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01, - 0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, - 0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10, - 0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2, - 0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00, - 0x00,0x07,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10, - 0x04,0x01,0x07,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x73,0xd4,0x45,0xd3,0x14,0x52, - 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01, - 0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xad,0x87,0xe0,0xad,0x96,0x00, - 0x00,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xe0,0xad,0x87,0xe0,0xac,0xbe,0x00,0x91, - 0x0f,0x10,0x0b,0x01,0xff,0xe0,0xad,0x87,0xe0,0xad,0x97,0x00,0x01,0x09,0x00,0x00, - 0xd3,0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x52,0x04,0x00,0x00, - 0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xac,0xa1,0xe0,0xac,0xbc,0x00,0x01,0xff,0xe0, - 0xac,0xa2,0xe0,0xac,0xbc,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd4,0x14,0x93,0x10, - 0xd2,0x08,0x11,0x04,0x01,0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00, - 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x0c,0x00,0x0c,0x00, - 0x00,0x00,0xd0,0xb1,0xcf,0x86,0xd5,0x63,0xd4,0x28,0xd3,0x14,0xd2,0x08,0x11,0x04, - 0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00, - 0xd3,0x1f,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x0f, - 0x10,0x0b,0x01,0xff,0xe0,0xae,0x92,0xe0,0xaf,0x97,0x00,0x01,0x00,0x00,0x00,0xd2, - 0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x91, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x51, - 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x00,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11, - 0x04,0x00,0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, - 0x04,0x08,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0x61,0xd4,0x45,0xd3,0x14,0xd2,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0,0xae, - 0xbe,0x00,0x01,0xff,0xe0,0xaf,0x87,0xe0,0xae,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01, - 0xff,0xe0,0xaf,0x86,0xe0,0xaf,0x97,0x00,0x01,0x09,0x00,0x00,0x93,0x18,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x01,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04, - 0x00,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04, - 0x01,0x00,0x10,0x04,0x01,0x00,0x07,0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00, - 0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xe3,0x1c,0x04,0xe2,0x1a,0x02,0xd1,0xf3, - 0xd0,0x76,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00, - 0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00, - 0x01,0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x10,0x00, - 0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04, - 0x00,0x00,0x0a,0x00,0x01,0x00,0xcf,0x86,0xd5,0x53,0xd4,0x2f,0xd3,0x10,0x52,0x04, - 0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0xd2,0x13,0x91,0x0f, - 0x10,0x0b,0x01,0xff,0xe0,0xb1,0x86,0xe0,0xb1,0x96,0x00,0x00,0x00,0x01,0x00,0x91, - 0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1, - 0x08,0x10,0x04,0x00,0x00,0x01,0x54,0x10,0x04,0x01,0x5b,0x00,0x00,0x92,0x0c,0x51, - 0x04,0x0a,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2, - 0x08,0x11,0x04,0x01,0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93, - 0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0a, - 0x00,0xd0,0x76,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x12,0x00,0x10,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01, - 0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10, - 0x04,0x07,0x07,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x82,0xd4,0x5e,0xd3,0x2a,0xd2, - 0x13,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb2,0xbf,0xe0,0xb3,0x95,0x00,0x01,0x00, - 0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff, - 0xe0,0xb3,0x86,0xe0,0xb3,0x95,0x00,0xd2,0x28,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0, - 0xb3,0x86,0xe0,0xb3,0x96,0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0, - 0xb3,0x82,0x00,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x82,0xe0,0xb3,0x95,0x00,0x91, - 0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1, - 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52,0x04,0x00, - 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2, - 0x08,0x11,0x04,0x01,0x00,0x09,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93, - 0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xe1,0x06,0x01,0xd0,0x6e,0xcf,0x86,0xd5,0x3c,0xd4,0x28, - 0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x13,0x00,0x10,0x00,0x01,0x00,0x91,0x08, - 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04, - 0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00, - 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x0c,0x00,0x13,0x09,0x91,0x08,0x10,0x04, - 0x13,0x09,0x0a,0x00,0x01,0x00,0xcf,0x86,0xd5,0x65,0xd4,0x45,0xd3,0x10,0x52,0x04, - 0x01,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08, - 0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb4,0xbe, - 0x00,0x01,0xff,0xe0,0xb5,0x87,0xe0,0xb4,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff, - 0xe0,0xb5,0x86,0xe0,0xb5,0x97,0x00,0x01,0x09,0x10,0x04,0x0c,0x00,0x12,0x00,0xd3, - 0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x01,0x00,0x52, - 0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x11,0x00,0xd4,0x14,0x93, - 0x10,0xd2,0x08,0x11,0x04,0x01,0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01, - 0x00,0xd3,0x0c,0x52,0x04,0x0a,0x00,0x11,0x04,0x0a,0x00,0x12,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x12,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x5a,0xcf,0x86,0xd5, - 0x34,0xd4,0x18,0x93,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x91,0x08,0x10, - 0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x04, - 0x00,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x04,0x00,0x10, - 0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x00, - 0x00,0x04,0x00,0x00,0x00,0xcf,0x86,0xd5,0x77,0xd4,0x28,0xd3,0x10,0x52,0x04,0x04, - 0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x51,0x04,0x00, - 0x00,0x10,0x04,0x04,0x09,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x04, - 0x00,0xd3,0x14,0x52,0x04,0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x10, - 0x04,0x04,0x00,0x00,0x00,0xd2,0x13,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe0, - 0xb7,0x99,0xe0,0xb7,0x8a,0x00,0x04,0x00,0xd1,0x19,0x10,0x0b,0x04,0xff,0xe0,0xb7, - 0x99,0xe0,0xb7,0x8f,0x00,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0xe0,0xb7,0x8a, - 0x00,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x9f,0x00,0x04,0x00,0xd4,0x10, - 0x93,0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x14, - 0xd2,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xe2,0x31,0x01,0xd1,0x58,0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94, - 0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51, - 0x04,0x01,0x67,0x10,0x04,0x01,0x09,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00, - 0x00,0x01,0x00,0xcf,0x86,0x95,0x18,0xd4,0x0c,0x53,0x04,0x01,0x00,0x12,0x04,0x01, - 0x6b,0x01,0x00,0x53,0x04,0x01,0x00,0x12,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd0, - 0x9e,0xcf,0x86,0xd5,0x54,0xd4,0x3c,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00, - 0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x10,0x04,0x15,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x15, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x15, - 0x00,0xd3,0x08,0x12,0x04,0x15,0x00,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x15,0x00,0x01,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10, - 0x04,0x00,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x15,0x00,0x01,0x00,0x91,0x08,0x10, - 0x04,0x15,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, - 0x76,0x10,0x04,0x15,0x09,0x01,0x00,0x11,0x04,0x01,0x00,0x00,0x00,0xcf,0x86,0x95, - 0x34,0xd4,0x20,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52,0x04,0x01,0x7a,0x11,0x04,0x01,0x00,0x00, - 0x00,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x01, - 0x00,0x0d,0x00,0x00,0x00,0xe1,0x2b,0x01,0xd0,0x3e,0xcf,0x86,0xd5,0x14,0x54,0x04, - 0x02,0x00,0x53,0x04,0x02,0x00,0x92,0x08,0x11,0x04,0x02,0xdc,0x02,0x00,0x02,0x00, - 0x54,0x04,0x02,0x00,0xd3,0x14,0x52,0x04,0x02,0x00,0xd1,0x08,0x10,0x04,0x02,0x00, - 0x02,0xdc,0x10,0x04,0x02,0x00,0x02,0xdc,0x92,0x0c,0x91,0x08,0x10,0x04,0x02,0x00, - 0x02,0xd8,0x02,0x00,0x02,0x00,0xcf,0x86,0xd5,0x73,0xd4,0x36,0xd3,0x17,0x92,0x13, - 0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x82,0xe0,0xbe,0xb7, - 0x00,0x02,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x02,0x00,0x02,0x00,0x91, - 0x0f,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x8c,0xe0,0xbe,0xb7,0x00,0x02,0x00, - 0xd3,0x26,0xd2,0x13,0x51,0x04,0x02,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x91,0xe0, - 0xbe,0xb7,0x00,0x02,0x00,0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0, - 0xbd,0x96,0xe0,0xbe,0xb7,0x00,0x52,0x04,0x02,0x00,0x91,0x0f,0x10,0x0b,0x02,0xff, - 0xe0,0xbd,0x9b,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x02,0x00,0xd4,0x27,0x53,0x04,0x02, - 0x00,0xd2,0x17,0xd1,0x0f,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x80,0xe0,0xbe, - 0xb5,0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00, - 0x00,0x00,0xd3,0x35,0xd2,0x17,0xd1,0x08,0x10,0x04,0x00,0x00,0x02,0x81,0x10,0x04, - 0x02,0x82,0x02,0xff,0xe0,0xbd,0xb1,0xe0,0xbd,0xb2,0x00,0xd1,0x0f,0x10,0x04,0x02, - 0x84,0x02,0xff,0xe0,0xbd,0xb1,0xe0,0xbd,0xb4,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbe, - 0xb2,0xe0,0xbe,0x80,0x00,0x02,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0, - 0xbe,0xb3,0xe0,0xbe,0x80,0x00,0x02,0x00,0x02,0x82,0x11,0x04,0x02,0x82,0x02,0x00, - 0xd0,0xd3,0xcf,0x86,0xd5,0x65,0xd4,0x27,0xd3,0x1f,0xd2,0x13,0x91,0x0f,0x10,0x04, - 0x02,0x82,0x02,0xff,0xe0,0xbd,0xb1,0xe0,0xbe,0x80,0x00,0x02,0xe6,0x91,0x08,0x10, - 0x04,0x02,0x09,0x02,0x00,0x02,0xe6,0x12,0x04,0x02,0x00,0x0c,0x00,0xd3,0x1f,0xd2, - 0x13,0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x92,0xe0,0xbe, - 0xb7,0x00,0x51,0x04,0x02,0x00,0x10,0x04,0x04,0x00,0x02,0x00,0xd2,0x0c,0x91,0x08, - 0x10,0x04,0x00,0x00,0x02,0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00,0x02,0xff, - 0xe0,0xbe,0x9c,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd4,0x3d,0xd3,0x26,0xd2,0x13,0x51, - 0x04,0x02,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xa1,0xe0,0xbe,0xb7,0x00,0x02,0x00, - 0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0xa6,0xe0,0xbe,0xb7, - 0x00,0x52,0x04,0x02,0x00,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xab,0xe0,0xbe, - 0xb7,0x00,0x02,0x00,0x04,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00, - 0x02,0x00,0x02,0x00,0x02,0x00,0xd2,0x13,0x91,0x0f,0x10,0x04,0x04,0x00,0x02,0xff, - 0xe0,0xbe,0x90,0xe0,0xbe,0xb5,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00, - 0x00,0x04,0x00,0xcf,0x86,0x95,0x4c,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0xdc,0x04,0x00,0x52,0x04,0x04,0x00,0xd1,0x08,0x10, - 0x04,0x04,0x00,0x00,0x00,0x10,0x04,0x0a,0x00,0x04,0x00,0xd3,0x14,0xd2,0x08,0x11, - 0x04,0x08,0x00,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0x92, - 0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0xcf,0x86,0xe5,0xcc,0x04,0xe4,0x63,0x03,0xe3,0x65,0x01,0xe2,0x04, - 0x01,0xd1,0x7f,0xd0,0x65,0xcf,0x86,0x55,0x04,0x04,0x00,0xd4,0x33,0xd3,0x1f,0xd2, - 0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x0a,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10, - 0x0b,0x04,0xff,0xe1,0x80,0xa5,0xe1,0x80,0xae,0x00,0x04,0x00,0x92,0x10,0xd1,0x08, - 0x10,0x04,0x0a,0x00,0x04,0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x04,0x00,0xd3,0x18, - 0xd2,0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x51,0x04,0x0a,0x00, - 0x10,0x04,0x04,0x00,0x04,0x07,0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0x09, - 0x10,0x04,0x0a,0x09,0x0a,0x00,0x0a,0x00,0xcf,0x86,0x95,0x14,0x54,0x04,0x04,0x00, - 0x53,0x04,0x04,0x00,0x92,0x08,0x11,0x04,0x04,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00, - 0xd0,0x2e,0xcf,0x86,0x95,0x28,0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00, - 0x91,0x08,0x10,0x04,0x0a,0x00,0x0a,0xdc,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08, - 0x11,0x04,0x0a,0x00,0x0b,0x00,0x11,0x04,0x0b,0x00,0x0a,0x00,0x01,0x00,0xcf,0x86, - 0xd5,0x24,0x94,0x20,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04, - 0x00,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00, - 0x00,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04, - 0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x06,0x00, - 0x08,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0d,0x00, - 0x0d,0x00,0xd1,0x28,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x95,0x1c,0x54,0x04, - 0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x51,0x04, - 0x0b,0x00,0x10,0x04,0x0b,0x00,0x01,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04, - 0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x0b,0x00,0x0b,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04, - 0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x0b,0x00, - 0xe2,0x21,0x01,0xd1,0x6c,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x52, - 0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00,0x04, - 0x00,0x04,0x00,0xcf,0x86,0x95,0x48,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04, - 0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x04, - 0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xd0, - 0x62,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04, - 0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00, - 0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xd4,0x14,0x53,0x04,0x04, - 0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd3, - 0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04, - 0x00,0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00, - 0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04, - 0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x93,0x10,0x52,0x04,0x04,0x00,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x94,0x14,0x53,0x04,0x04, - 0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04, - 0x00,0xd1,0x9c,0xd0,0x3e,0xcf,0x86,0x95,0x38,0xd4,0x14,0x53,0x04,0x04,0x00,0x52, - 0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd3,0x14,0xd2, - 0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00, - 0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04, - 0x00,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04, - 0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00,0x53,0x04,0x04,0x00,0xd2,0x0c,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x0c, - 0xe6,0x10,0x04,0x0c,0xe6,0x08,0xe6,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x08,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x53,0x04,0x04,0x00,0x52, - 0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a,0xcf, - 0x86,0x95,0x14,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08, - 0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04, - 0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x11,0x00,0x00, - 0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0xd3,0x30,0xd2,0x2a,0xd1, - 0x24,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x0b,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf, - 0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd2,0x6c,0xd1,0x24,0xd0, - 0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93, - 0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x0b,0x00,0x0b, - 0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x52, - 0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xcf, - 0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x04,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x46,0xcf,0x86,0xd5,0x28,0xd4, - 0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x00, - 0x00,0x06,0x00,0x93,0x10,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x09,0x00, - 0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x06,0x00,0x93,0x14,0x52,0x04,0x06,0x00,0xd1, - 0x08,0x10,0x04,0x06,0x09,0x06,0x00,0x10,0x04,0x06,0x00,0x00,0x00,0x00,0x00,0xcf, - 0x86,0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x06,0x00,0x00,0x00,0x00, - 0x00,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06, - 0x00,0x00,0x00,0x06,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x00, - 0x00,0x06,0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0xd5, - 0x24,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x04, - 0x09,0x04,0x00,0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x07, - 0xe6,0x00,0x00,0xd4,0x10,0x53,0x04,0x04,0x00,0x92,0x08,0x11,0x04,0x04,0x00,0x00, - 0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x08,0x11,0x04,0x07,0x00,0x00,0x00,0x00, - 0x00,0xe4,0xac,0x03,0xe3,0x4d,0x01,0xd2,0x84,0xd1,0x48,0xd0,0x2a,0xcf,0x86,0x95, - 0x24,0xd4,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10, - 0x04,0x04,0x00,0x00,0x00,0x53,0x04,0x04,0x00,0x92,0x08,0x11,0x04,0x04,0x00,0x00, - 0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x53, - 0x04,0x04,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x04,0x00,0x94,0x18,0x53,0x04,0x04,0x00,0x92, - 0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0xe4,0x10,0x04,0x0a,0x00,0x00,0x00,0x00, - 0x00,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x0c,0x52, - 0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x42,0xcf, - 0x86,0xd5,0x1c,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0xd1, - 0x08,0x10,0x04,0x07,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0xd4,0x0c,0x53, - 0x04,0x07,0x00,0x12,0x04,0x07,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x10,0xd1, - 0x08,0x10,0x04,0x07,0x00,0x07,0xde,0x10,0x04,0x07,0xe6,0x07,0xdc,0x00,0x00,0xcf, - 0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x00, - 0x00,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd4,0x10,0x53,0x04,0x07,0x00,0x52, - 0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x07,0x00,0x91, - 0x08,0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a,0xcf,0x86,0x55, - 0x04,0x08,0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00,0x0b, - 0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x95,0x28,0xd4,0x10,0x53,0x04,0x08,0x00,0x92, - 0x08,0x11,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0xd2,0x0c,0x51, - 0x04,0x08,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x08,0x00,0x07, - 0x00,0xd2,0xe4,0xd1,0x80,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x54,0x04,0x08,0x00,0xd3, - 0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x08,0xe6,0xd2, - 0x0c,0x91,0x08,0x10,0x04,0x08,0xdc,0x08,0x00,0x08,0x00,0x11,0x04,0x00,0x00,0x08, - 0x00,0x0b,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x52, - 0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xd4,0x14,0x93, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00,0x0b, - 0x00,0xd3,0x10,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6,0x0b, - 0xe6,0x52,0x04,0x0b,0xe6,0xd1,0x08,0x10,0x04,0x0b,0xe6,0x00,0x00,0x10,0x04,0x00, - 0x00,0x0b,0xdc,0xd0,0x5e,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0b,0x00,0x92, - 0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0b,0x00,0x92,0x08,0x11, - 0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd4,0x10,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b, - 0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x10,0xe6,0x91,0x08,0x10, - 0x04,0x10,0xe6,0x10,0xdc,0x10,0xdc,0xd2,0x0c,0x51,0x04,0x10,0xdc,0x10,0x04,0x10, - 0xdc,0x10,0xe6,0xd1,0x08,0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0x04,0x10,0x00,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xe1,0x1e,0x01,0xd0,0xaa,0xcf,0x86,0xd5,0x6e,0xd4,0x53, - 0xd3,0x17,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac, - 0x85,0xe1,0xac,0xb5,0x00,0x09,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x09,0xff,0xe1, - 0xac,0x87,0xe1,0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x89,0xe1, - 0xac,0xb5,0x00,0x09,0x00,0xd1,0x0f,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8b,0xe1,0xac, - 0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8d,0xe1,0xac,0xb5,0x00,0x09, - 0x00,0x93,0x17,0x92,0x13,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x91, - 0xe1,0xac,0xb5,0x00,0x09,0x00,0x09,0x00,0x09,0x00,0x54,0x04,0x09,0x00,0xd3,0x10, - 0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x07,0x09,0x00,0x09,0x00,0xd2,0x13, - 0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xba,0xe1,0xac,0xb5, - 0x00,0x91,0x0f,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xbc,0xe1,0xac,0xb5,0x00, - 0x09,0x00,0xcf,0x86,0xd5,0x3d,0x94,0x39,0xd3,0x31,0xd2,0x25,0xd1,0x16,0x10,0x0b, - 0x09,0xff,0xe1,0xac,0xbe,0xe1,0xac,0xb5,0x00,0x09,0xff,0xe1,0xac,0xbf,0xe1,0xac, - 0xb5,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xad,0x82,0xe1,0xac,0xb5,0x00,0x91, - 0x08,0x10,0x04,0x09,0x09,0x09,0x00,0x09,0x00,0x12,0x04,0x09,0x00,0x00,0x00,0x09, - 0x00,0xd4,0x1c,0x53,0x04,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09, - 0x00,0x09,0xe6,0x91,0x08,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0xe6,0xd3,0x08,0x12, - 0x04,0x09,0xe6,0x09,0x00,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x00, - 0x00,0x00,0x00,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x18,0x53,0x04,0x0a, - 0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x09,0x0d,0x09,0x11,0x04,0x0d, - 0x00,0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x0d,0x00,0x0d, - 0x00,0xcf,0x86,0x55,0x04,0x0c,0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x0c,0x00,0x51, - 0x04,0x0c,0x00,0x10,0x04,0x0c,0x07,0x0c,0x00,0x0c,0x00,0xd3,0x0c,0x92,0x08,0x11, - 0x04,0x0c,0x00,0x0c,0x09,0x00,0x00,0x12,0x04,0x00,0x00,0x0c,0x00,0xe3,0xb2,0x01, - 0xe2,0x09,0x01,0xd1,0x4c,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x0a,0x00,0x54,0x04,0x0a, - 0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a, - 0x07,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00,0xcf, - 0x86,0x95,0x1c,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00,0x00, - 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0, - 0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x14,0x00,0x54,0x04,0x14,0x00,0x53, - 0x04,0x14,0x00,0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x14,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x08,0x13, - 0x04,0x0d,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04,0x0b, - 0xe6,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x01,0x0b,0xdc,0x0b,0xdc,0x92,0x08,0x11, - 0x04,0x0b,0xdc,0x0b,0xe6,0x0b,0xdc,0xd4,0x28,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x01,0x0b,0x01,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b, - 0x01,0x0b,0x00,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xdc,0x0b,0x00,0xd3, - 0x1c,0xd2,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0d,0x00,0xd1,0x08,0x10, - 0x04,0x0d,0xe6,0x0d,0x00,0x10,0x04,0x0d,0x00,0x13,0x00,0x92,0x0c,0x51,0x04,0x10, - 0xe6,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06,0x07, - 0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x94,0x0c,0x53,0x04,0x07,0x00,0x12,0x04,0x07, - 0x00,0x08,0x00,0x08,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0xd5,0x40,0xd4, - 0x2c,0xd3,0x10,0x92,0x0c,0x51,0x04,0x08,0xe6,0x10,0x04,0x08,0xdc,0x08,0xe6,0x09, - 0xe6,0xd2,0x0c,0x51,0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x0a,0xe6,0xd1,0x08,0x10, - 0x04,0x0a,0xe6,0x0a,0xea,0x10,0x04,0x0a,0xd6,0x0a,0xdc,0x93,0x10,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x0a,0xca,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0xd4,0x14,0x93, - 0x10,0x52,0x04,0x0a,0xe6,0x51,0x04,0x0a,0xe6,0x10,0x04,0x0a,0xe6,0x10,0xe6,0x10, - 0xe6,0xd3,0x10,0x52,0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x13,0xe8,0x13, - 0xe4,0xd2,0x10,0xd1,0x08,0x10,0x04,0x13,0xe4,0x13,0xdc,0x10,0x04,0x00,0x00,0x12, - 0xe6,0xd1,0x08,0x10,0x04,0x0c,0xe9,0x0b,0xdc,0x10,0x04,0x09,0xe6,0x09,0xdc,0xe2, - 0x80,0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa5,0x00,0x01,0xff,0x61, - 0xcc,0xa5,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc,0x87, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x42,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc,0xa3, - 0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00,0xd2, - 0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x43,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff,0x63, - 0xcc,0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0x87,0x00,0x01,0xff,0x64, - 0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa3,0x00,0x01,0xff,0x64, - 0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc,0xb1, - 0x00,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa7,0x00,0x01, - 0xff,0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xad,0x00,0x01,0xff,0x64, - 0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc,0x80,0x00,0x01, - 0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc,0x81, - 0x00,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x45,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x45, - 0xcc,0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45, - 0xcc,0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08,0x01, - 0xff,0x46,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc,0x84, - 0x00,0x10,0x08,0x01,0xff,0x48,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00,0x10, - 0x08,0x01,0xff,0x48,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00,0x10, - 0x08,0x01,0xff,0x48,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x49,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a,0x01, - 0xff,0x49,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0x81,0x00,0x01,0xff,0x6b, - 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc,0xa3, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc,0xb1, - 0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00,0xd2, - 0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff,0x6c, - 0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xb1,0x00,0x01,0xff,0x6c, - 0xcc,0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4c,0xcc,0xad,0x00,0x01,0xff,0x6c, - 0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x4d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc,0x81, - 0x00,0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x4d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01,0xff, - 0x4d,0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x4e,0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x4e,0xcc, - 0xa3,0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x4e,0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x4e,0xcc, - 0xad,0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc, - 0x83,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff, - 0x4f,0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3,0x48, - 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff, - 0x6f,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x81,0x00, - 0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x50,0xcc, - 0x81,0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x50,0xcc,0x87,0x00, - 0x01,0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc, - 0x87,0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa3,0x00, - 0x01,0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x52,0xcc,0xa3,0xcc, - 0x84,0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x52,0xcc, - 0xb1,0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x53,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10,0x08, - 0x01,0xff,0x53,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x53,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87,0x00, - 0x10,0x0a,0x01,0xff,0x53,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c,0xcc, - 0x87,0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x53,0xcc,0xa3,0xcc,0x87,0x00, - 0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0x87,0x00, - 0x01,0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0xa3,0x00, - 0x01,0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xb1,0x00,0x01,0xff, - 0x74,0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x54,0xcc, - 0xad,0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa4,0x00, - 0x01,0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0xb0,0x00, - 0x01,0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xad,0x00,0x01,0xff, - 0x75,0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x83,0xcc, - 0x81,0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x55,0xcc, - 0x84,0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x56,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01,0xff, - 0x56,0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x10,0x02,0xcf,0x86,0xd5, - 0xe1,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x80, - 0x00,0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x81,0x00,0x01, - 0xff,0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x88,0x00,0x01, - 0xff,0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x87,0x00,0x01,0xff,0x77, - 0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0xa3,0x00,0x01, - 0xff,0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x58,0xcc,0x87,0x00,0x01,0xff,0x78, - 0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x58,0xcc,0x88,0x00,0x01,0xff,0x78, - 0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc,0x87, - 0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0x82,0x00,0x01, - 0xff,0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x5a,0xcc,0xa3,0x00,0x01,0xff,0x7a, - 0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0xb1,0x00,0x01,0xff,0x7a, - 0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x68,0xcc,0xb1,0x00,0x01,0xff,0x74,0xcc,0x88, - 0x00,0x92,0x1d,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01,0xff,0x79, - 0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x02,0xff,0xc5,0xbf,0xcc,0x87,0x00,0x0a,0x00, - 0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa3,0x00, - 0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x89,0x00,0x01,0xff, - 0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x81,0x00, - 0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc, + 0xc6,0xe5,0xf9,0x14,0xe4,0x6f,0x0d,0xe3,0x39,0x08,0xe2,0x22,0x01,0xc1,0xd0,0x24, + 0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x07,0x63,0xd8,0x43,0x01,0x00,0x93,0x13,0x52, + 0x04,0x01,0x00,0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xce,0xbc,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xe5,0xb3,0x44,0xd4,0x7f,0xd3,0x3f,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x07,0x01,0xff,0xc3, + 0xa6,0x00,0x01,0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x65,0xcc,0x80,0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, + 0x82,0x00,0x01,0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc, + 0x80,0x00,0x01,0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00, + 0x01,0xff,0x69,0xcc,0x88,0x00,0xd3,0x3b,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff, + 0xc3,0xb0,0x00,0x01,0xff,0x6e,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80, + 0x00,0x01,0xff,0x6f,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82, + 0x00,0x01,0xff,0x6f,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01, + 0x00,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff,0xc3,0xb8,0x00,0x01,0xff,0x75,0xcc, + 0x80,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x82,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x88,0x00,0x01,0xff,0x79,0xcc,0x81,0x00, + 0x10,0x07,0x01,0xff,0xc3,0xbe,0x00,0x01,0xff,0x73,0x73,0x00,0xe1,0xd4,0x03,0xe0, + 0xeb,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x61,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84,0x00,0x10,0x08,0x01,0xff, + 0x61,0xcc,0x86,0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x61,0xcc,0xa8,0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x63,0xcc, + 0x81,0x00,0x01,0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x63,0xcc,0x82,0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x63,0xcc, + 0x87,0x00,0x01,0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x63,0xcc, + 0x8c,0x00,0x01,0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x8c,0x00, + 0x01,0xff,0x64,0xcc,0x8c,0x00,0xd3,0x3b,0xd2,0x1b,0xd1,0x0b,0x10,0x07,0x01,0xff, + 0xc4,0x91,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x84,0x00,0x01,0xff,0x65, + 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x86,0x00,0x01,0xff,0x65, + 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0xa8,0x00,0x01,0xff,0x65, + 0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82, + 0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4, + 0x7b,0xd3,0x3b,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x87,0x00,0x01, + 0xff,0x67,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0xa7,0x00,0x01,0xff,0x67, + 0xcc,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x68,0xcc,0x82,0x00,0x01,0xff,0x68, + 0xcc,0x82,0x00,0x10,0x07,0x01,0xff,0xc4,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x69,0xcc,0x83,0x00,0x01,0xff,0x69,0xcc,0x83,0x00,0x10,0x08, + 0x01,0xff,0x69,0xcc,0x84,0x00,0x01,0xff,0x69,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x69,0xcc,0x86,0x00,0x01,0xff,0x69,0xcc,0x86,0x00,0x10,0x08,0x01,0xff, + 0x69,0xcc,0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8,0x00,0xd3,0x37,0xd2,0x17,0xd1,0x0c, + 0x10,0x08,0x01,0xff,0x69,0xcc,0x87,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc4,0xb3, + 0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6a,0xcc,0x82,0x00,0x01,0xff,0x6a, + 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x6b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7, + 0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6c,0xcc,0x81,0x00,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff,0x6c,0xcc,0xa7,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff,0x6c,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x6c,0xcc,0x8c,0x00,0x01,0xff,0xc5,0x80,0x00,0xcf,0x86,0xd5,0xed,0xd4,0x72, + 0xd3,0x37,0xd2,0x17,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc5,0x82,0x00,0x10, + 0x04,0x01,0x00,0x01,0xff,0x6e,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0x81,0x00,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa7, + 0x00,0x01,0xff,0x6e,0xcc,0x8c,0x00,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0x8c,0x00,0x01,0xff,0xca,0xbc,0x6e,0x00,0x10,0x07,0x01,0xff,0xc5,0x8b,0x00, + 0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc, + 0x84,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00, + 0xd3,0x3b,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01,0xff, + 0x6f,0xcc,0x8b,0x00,0x10,0x07,0x01,0xff,0xc5,0x93,0x00,0x01,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x72,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81,0x00,0x10,0x08,0x01, + 0xff,0x72,0xcc,0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x72,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x73,0xcc,0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x73,0xcc,0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x73, + 0xcc,0xa7,0x00,0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x7b,0xd3,0x3b,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x73,0xcc,0x8c,0x00,0x01,0xff,0x73,0xcc,0x8c,0x00,0x10, + 0x08,0x01,0xff,0x74,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x74,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c,0x00,0x10,0x07,0x01, + 0xff,0xc5,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc, + 0x83,0x00,0x01,0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x84,0x00, + 0x01,0xff,0x75,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x86,0x00, + 0x01,0xff,0x75,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x8a,0x00,0x01,0xff, + 0x75,0xcc,0x8a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc, + 0x8b,0x00,0x01,0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa8,0x00, + 0x01,0xff,0x75,0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x82,0x00, + 0x01,0xff,0x77,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x82,0x00,0x01,0xff, + 0x79,0xcc,0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x79,0xcc,0x88,0x00, + 0x01,0xff,0x7a,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff, + 0x7a,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff, + 0x7a,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0xff,0x73,0x00, + 0xe0,0x65,0x01,0xcf,0x86,0xd5,0xb4,0xd4,0x5a,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10, + 0x04,0x01,0x00,0x01,0xff,0xc9,0x93,0x00,0x10,0x07,0x01,0xff,0xc6,0x83,0x00,0x01, + 0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff, + 0xc9,0x94,0x00,0x01,0xff,0xc6,0x88,0x00,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x01,0x00, + 0x01,0xff,0xc9,0x96,0x00,0x10,0x07,0x01,0xff,0xc9,0x97,0x00,0x01,0xff,0xc6,0x8c, + 0x00,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xc7,0x9d,0x00,0x01,0xff,0xc9,0x99, + 0x00,0xd3,0x32,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0x9b,0x00,0x01,0xff, + 0xc6,0x92,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xa0,0x00,0xd1,0x0b,0x10,0x07, + 0x01,0xff,0xc9,0xa3,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc9,0xa9,0x00,0x01,0xff, + 0xc9,0xa8,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0x99,0x00,0x01,0x00, + 0x01,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0xaf,0x00,0x01,0xff,0xc9,0xb2,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xb5,0x00,0xd4,0x5d,0xd3,0x34,0xd2,0x1b,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x10, + 0x07,0x01,0xff,0xc6,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0xa5, + 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x80,0x00,0x01,0xff,0xc6,0xa8,0x00,0xd2, + 0x0f,0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x83,0x00,0x01,0x00,0xd1,0x0b, + 0x10,0x07,0x01,0xff,0xc6,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x88,0x00, + 0x01,0xff,0x75,0xcc,0x9b,0x00,0xd3,0x33,0xd2,0x1d,0xd1,0x0f,0x10,0x08,0x01,0xff, + 0x75,0xcc,0x9b,0x00,0x01,0xff,0xca,0x8a,0x00,0x10,0x07,0x01,0xff,0xca,0x8b,0x00, + 0x01,0xff,0xc6,0xb4,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc6,0xb6,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x92,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01, + 0xff,0xc6,0xb9,0x00,0x01,0x00,0x01,0x00,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0xbd, + 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x44,0xd3,0x16,0x52,0x04,0x01, + 0x00,0x51,0x07,0x01,0xff,0xc7,0x86,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc7,0x89, + 0x00,0xd2,0x12,0x91,0x0b,0x10,0x07,0x01,0xff,0xc7,0x89,0x00,0x01,0x00,0x01,0xff, + 0xc7,0x8c,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x61,0xcc,0x8c,0x00,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff,0x69,0xcc,0x8c,0x00,0xd3,0x46,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x6f,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x8c,0x00,0xd1, + 0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84, + 0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x75,0xcc,0x88, + 0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81, + 0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88, + 0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01, + 0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x88, + 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x87,0xd3,0x41,0xd2, + 0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61, + 0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x84,0x00,0x01,0xff, + 0xc3,0xa6,0xcc,0x84,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc7,0xa5,0x00,0x01,0x00, + 0x10,0x08,0x01,0xff,0x67,0xcc,0x8c,0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00, + 0x10,0x08,0x01,0xff,0x6f,0xcc,0xa8,0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14, + 0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc, + 0x84,0x00,0x10,0x09,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc, + 0x8c,0x00,0xd3,0x38,0xd2,0x1a,0xd1,0x0f,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00, + 0x01,0xff,0xc7,0xb3,0x00,0x10,0x07,0x01,0xff,0xc7,0xb3,0x00,0x01,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x67,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x10,0x07, + 0x04,0xff,0xc6,0x95,0x00,0x04,0xff,0xc6,0xbf,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08, + 0x04,0xff,0x6e,0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff, + 0x61,0xcc,0x8a,0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a,0xcc,0x81,0x00,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00, + 0x10,0x09,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00, + 0xe2,0x31,0x02,0xe1,0xc3,0x44,0xe0,0xc8,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0x8f,0x00,0x01,0xff,0x61, + 0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x91,0x00,0x01,0xff,0x61,0xcc,0x91, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x8f,0x00,0x01,0xff,0x65,0xcc,0x8f, + 0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x91,0x00,0x01,0xff,0x65,0xcc,0x91,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8f,0x00,0x01,0xff,0x69,0xcc,0x8f, + 0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x91,0x00,0x01,0xff,0x69,0xcc,0x91,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x10, + 0x08,0x01,0xff,0x6f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc,0x91,0x00,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x8f,0x00,0x01,0xff,0x72,0xcc,0x8f, + 0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0x91,0x00,0x01,0xff,0x72,0xcc,0x91,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x8f,0x00,0x01,0xff,0x75,0xcc,0x8f,0x00,0x10, + 0x08,0x01,0xff,0x75,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc,0x91,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x04,0xff,0x73,0xcc,0xa6,0x00,0x04,0xff,0x73,0xcc,0xa6,0x00,0x10, + 0x08,0x04,0xff,0x74,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc,0xa6,0x00,0xd1,0x0b,0x10, + 0x07,0x04,0xff,0xc8,0x9d,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x68,0xcc,0x8c,0x00, + 0x04,0xff,0x68,0xcc,0x8c,0x00,0xd4,0x79,0xd3,0x31,0xd2,0x16,0xd1,0x0b,0x10,0x07, + 0x06,0xff,0xc6,0x9e,0x00,0x07,0x00,0x10,0x07,0x04,0xff,0xc8,0xa3,0x00,0x04,0x00, + 0xd1,0x0b,0x10,0x07,0x04,0xff,0xc8,0xa5,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x61, + 0xcc,0x87,0x00,0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04, + 0xff,0x65,0xcc,0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x6f, + 0xcc,0x88,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10, + 0x0a,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84, + 0x00,0x10,0x08,0x04,0xff,0x6f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0xd3, + 0x27,0xe2,0x21,0x43,0xd1,0x14,0x10,0x0a,0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00, + 0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x79,0xcc,0x84,0x00, + 0x04,0xff,0x79,0xcc,0x84,0x00,0xd2,0x13,0x51,0x04,0x08,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0xa5,0x00,0x08,0xff,0xc8,0xbc,0x00,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08, + 0xff,0xc6,0x9a,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0xa6,0x00,0x08,0x00,0xcf,0x86, + 0x95,0x5f,0x94,0x5b,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08,0xff, + 0xc9,0x82,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xc6,0x80,0x00,0xd1,0x0e,0x10,0x07, + 0x09,0xff,0xca,0x89,0x00,0x09,0xff,0xca,0x8c,0x00,0x10,0x07,0x09,0xff,0xc9,0x87, + 0x00,0x09,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9,0x89,0x00,0x09,0x00, + 0x10,0x07,0x09,0xff,0xc9,0x8b,0x00,0x09,0x00,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9, + 0x8d,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xc9,0x8f,0x00,0x09,0x00,0x01,0x00,0x01, + 0x00,0xd1,0x8b,0xd0,0x0c,0xcf,0x86,0xe5,0x10,0x43,0x64,0xef,0x42,0x01,0xe6,0xcf, + 0x86,0xd5,0x2a,0xe4,0x99,0x43,0xe3,0x7f,0x43,0xd2,0x11,0xe1,0x5e,0x43,0x10,0x07, + 0x01,0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0xe1,0x65,0x43,0x10,0x09,0x01, + 0xff,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0x00,0xd4,0x0f,0x93,0x0b,0x92, + 0x07,0x61,0xab,0x43,0x01,0xea,0x06,0xe6,0x06,0xe6,0xd3,0x2c,0xd2,0x16,0xd1,0x0b, + 0x10,0x07,0x0a,0xff,0xcd,0xb1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xcd,0xb3,0x00, + 0x0a,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x10,0x07,0x0a, + 0xff,0xcd,0xb7,0x00,0x0a,0x00,0xd2,0x07,0x61,0x97,0x43,0x00,0x00,0x51,0x04,0x09, + 0x00,0x10,0x06,0x01,0xff,0x3b,0x00,0x10,0xff,0xcf,0xb3,0x00,0xe0,0x31,0x01,0xcf, + 0x86,0xd5,0xd3,0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x01, + 0x00,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x81, + 0x00,0x01,0xff,0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5, + 0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9, + 0xcc,0x81,0x00,0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00, + 0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x81,0x00,0xd3,0x3c,0xd2,0x20,0xd1,0x12,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x88, + 0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0x00,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01, + 0xff,0xce,0xb3,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb4,0x00,0x01,0xff,0xce, + 0xb5,0x00,0x10,0x07,0x01,0xff,0xce,0xb6,0x00,0x01,0xff,0xce,0xb7,0x00,0xd2,0x1c, + 0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb8,0x00,0x01,0xff,0xce,0xb9,0x00,0x10,0x07, + 0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xce,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff, + 0xce,0xbc,0x00,0x01,0xff,0xce,0xbd,0x00,0x10,0x07,0x01,0xff,0xce,0xbe,0x00,0x01, + 0xff,0xce,0xbf,0x00,0xe4,0x85,0x43,0xd3,0x35,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01, + 0xff,0xcf,0x80,0x00,0x01,0xff,0xcf,0x81,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf, + 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xcf,0x84,0x00,0x01,0xff,0xcf,0x85,0x00, + 0x10,0x07,0x01,0xff,0xcf,0x86,0x00,0x01,0xff,0xcf,0x87,0x00,0xe2,0x2b,0x43,0xd1, + 0x0e,0x10,0x07,0x01,0xff,0xcf,0x88,0x00,0x01,0xff,0xcf,0x89,0x00,0x10,0x09,0x01, + 0xff,0xce,0xb9,0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc,0x88,0x00,0xcf,0x86,0xd5, + 0x94,0xd4,0x3c,0xd3,0x13,0x92,0x0f,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xcf, + 0x83,0x00,0x01,0x00,0x01,0x00,0xd2,0x07,0x61,0x3a,0x43,0x01,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x10, + 0x09,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x0a,0xff,0xcf,0x97,0x00,0xd3,0x2c,0xd2, + 0x11,0xe1,0x46,0x43,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01,0xff,0xce,0xb8,0x00, + 0xd1,0x10,0x10,0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0xff,0xcf,0x86,0x00, + 0x10,0x07,0x01,0xff,0xcf,0x80,0x00,0x04,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06, + 0xff,0xcf,0x99,0x00,0x06,0x00,0x10,0x07,0x01,0xff,0xcf,0x9b,0x00,0x04,0x00,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xcf,0x9d,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0x9f, + 0x00,0x04,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf, + 0xa1,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10, + 0x07,0x01,0xff,0xcf,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xa7,0x00,0x01, + 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xa9,0x00,0x01,0x00,0x10,0x07, + 0x01,0xff,0xcf,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xad,0x00, + 0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xaf,0x00,0x01,0x00,0xd3,0x2b,0xd2,0x12,0x91, + 0x0e,0x10,0x07,0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xcf,0x81,0x00,0x01,0x00,0xd1, + 0x0e,0x10,0x07,0x05,0xff,0xce,0xb8,0x00,0x05,0xff,0xce,0xb5,0x00,0x10,0x04,0x06, + 0x00,0x07,0xff,0xcf,0xb8,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x07,0x00,0x07,0xff, + 0xcf,0xb2,0x00,0x10,0x07,0x07,0xff,0xcf,0xbb,0x00,0x07,0x00,0xd1,0x0b,0x10,0x04, + 0x08,0x00,0x08,0xff,0xcd,0xbb,0x00,0x10,0x07,0x08,0xff,0xcd,0xbc,0x00,0x08,0xff, + 0xcd,0xbd,0x00,0xe3,0xed,0x46,0xe2,0x3d,0x05,0xe1,0x27,0x02,0xe0,0x66,0x01,0xcf, + 0x86,0xd5,0xf0,0xd4,0x7e,0xd3,0x40,0xd2,0x22,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0, + 0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x07,0x01,0xff,0xd1, + 0x92,0x00,0x01,0xff,0xd0,0xb3,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1, + 0x94,0x00,0x01,0xff,0xd1,0x95,0x00,0x10,0x07,0x01,0xff,0xd1,0x96,0x00,0x01,0xff, + 0xd1,0x96,0xcc,0x88,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x98,0x00, + 0x01,0xff,0xd1,0x99,0x00,0x10,0x07,0x01,0xff,0xd1,0x9a,0x00,0x01,0xff,0xd1,0x9b, + 0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8, + 0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x86,0x00,0x01,0xff,0xd1,0x9f, + 0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xb0,0x00,0x01,0xff, + 0xd0,0xb1,0x00,0x10,0x07,0x01,0xff,0xd0,0xb2,0x00,0x01,0xff,0xd0,0xb3,0x00,0xd1, + 0x0e,0x10,0x07,0x01,0xff,0xd0,0xb4,0x00,0x01,0xff,0xd0,0xb5,0x00,0x10,0x07,0x01, + 0xff,0xd0,0xb6,0x00,0x01,0xff,0xd0,0xb7,0x00,0xd2,0x1e,0xd1,0x10,0x10,0x07,0x01, + 0xff,0xd0,0xb8,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x10,0x07,0x01,0xff,0xd0, + 0xba,0x00,0x01,0xff,0xd0,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xbc,0x00, + 0x01,0xff,0xd0,0xbd,0x00,0x10,0x07,0x01,0xff,0xd0,0xbe,0x00,0x01,0xff,0xd0,0xbf, + 0x00,0xe4,0x25,0x42,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x80, + 0x00,0x01,0xff,0xd1,0x81,0x00,0x10,0x07,0x01,0xff,0xd1,0x82,0x00,0x01,0xff,0xd1, + 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x84,0x00,0x01,0xff,0xd1,0x85,0x00, + 0x10,0x07,0x01,0xff,0xd1,0x86,0x00,0x01,0xff,0xd1,0x87,0x00,0xd2,0x1c,0xd1,0x0e, + 0x10,0x07,0x01,0xff,0xd1,0x88,0x00,0x01,0xff,0xd1,0x89,0x00,0x10,0x07,0x01,0xff, + 0xd1,0x8a,0x00,0x01,0xff,0xd1,0x8b,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x8c, + 0x00,0x01,0xff,0xd1,0x8d,0x00,0x10,0x07,0x01,0xff,0xd1,0x8e,0x00,0x01,0xff,0xd1, + 0x8f,0x00,0xcf,0x86,0xd5,0x07,0x64,0xcf,0x41,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2, + 0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff, + 0xd1,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa5,0x00,0x01,0x00, + 0x10,0x07,0x01,0xff,0xd1,0xa7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01, + 0xff,0xd1,0xa9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xab,0x00,0x01,0x00,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xd1,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xaf, + 0x00,0x01,0x00,0xd3,0x33,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb1,0x00, + 0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xb3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01, + 0xff,0xd1,0xb5,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb5,0xcc,0x8f,0x00,0x01, + 0xff,0xd1,0xb5,0xcc,0x8f,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb9, + 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07, + 0x01,0xff,0xd1,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbf,0x00,0x01,0x00, + 0xe0,0x41,0x01,0xcf,0x86,0xd5,0x8e,0xd4,0x36,0xd3,0x11,0xe2,0x91,0x41,0xe1,0x88, + 0x41,0x10,0x07,0x01,0xff,0xd2,0x81,0x00,0x01,0x00,0xd2,0x0f,0x51,0x04,0x04,0x00, + 0x10,0x07,0x06,0xff,0xd2,0x8b,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x04,0xff,0xd2, + 0x8d,0x00,0x04,0x00,0x10,0x07,0x04,0xff,0xd2,0x8f,0x00,0x04,0x00,0xd3,0x2c,0xd2, + 0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x91,0x00,0x01,0x00,0x10,0x07,0x01,0xff, + 0xd2,0x93,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x95,0x00,0x01,0x00, + 0x10,0x07,0x01,0xff,0xd2,0x97,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01, + 0xff,0xd2,0x99,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9b,0x00,0x01,0x00,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xd2,0x9d,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9f, + 0x00,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2, + 0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10, + 0x07,0x01,0xff,0xd2,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa7,0x00,0x01, + 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xa9,0x00,0x01,0x00,0x10,0x07, + 0x01,0xff,0xd2,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xad,0x00, + 0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xaf,0x00,0x01,0x00,0xd3,0x2c,0xd2,0x16,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xd2,0xb1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xb3, + 0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xb5,0x00,0x01,0x00,0x10,0x07, + 0x01,0xff,0xd2,0xb7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2, + 0xb9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10, + 0x07,0x01,0xff,0xd2,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbf,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0xdc,0xd4,0x5a,0xd3,0x36,0xd2,0x20,0xd1,0x10,0x10,0x07,0x01, + 0xff,0xd3,0x8f,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0, + 0xb6,0xcc,0x86,0x00,0x01,0xff,0xd3,0x84,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x06, + 0xff,0xd3,0x86,0x00,0x10,0x04,0x06,0x00,0x01,0xff,0xd3,0x88,0x00,0xd2,0x16,0xd1, + 0x0b,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8a,0x00,0x10,0x04,0x06,0x00,0x01,0xff, + 0xd3,0x8c,0x00,0xe1,0x69,0x40,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8e,0x00,0xd3, + 0x41,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x01,0xff, + 0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x01,0xff, + 0xd0,0xb0,0xcc,0x88,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x95,0x00,0x01,0x00, + 0x10,0x09,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00, + 0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x99,0x00,0x01,0x00,0x10,0x09,0x01, + 0xff,0xd3,0x99,0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc,0x88,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x10, + 0x09,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0xd4, + 0x82,0xd3,0x41,0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa1,0x00,0x01,0x00, + 0x10,0x09,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc, + 0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc, + 0x88,0x00,0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa9,0x00,0x01,0x00,0x10, + 0x09,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1, + 0x12,0x10,0x09,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88, + 0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0x01,0xff,0xd1,0x83,0xcc,0x84, + 0x00,0xd3,0x41,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00, + 0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00, + 0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x87,0xcc, + 0x88,0x00,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00,0x10,0x07,0x08,0xff,0xd3,0xb7,0x00, + 0x08,0x00,0xd2,0x1d,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x8b,0xcc,0x88,0x00,0x01, + 0xff,0xd1,0x8b,0xcc,0x88,0x00,0x10,0x07,0x09,0xff,0xd3,0xbb,0x00,0x09,0x00,0xd1, + 0x0b,0x10,0x07,0x09,0xff,0xd3,0xbd,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd3,0xbf, + 0x00,0x09,0x00,0xe1,0x26,0x02,0xe0,0x78,0x01,0xcf,0x86,0xd5,0xb0,0xd4,0x58,0xd3, + 0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x81,0x00,0x06,0x00,0x10,0x07, + 0x06,0xff,0xd4,0x83,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x85,0x00, + 0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x87,0x00,0x06,0x00,0xd2,0x16,0xd1,0x0b,0x10, + 0x07,0x06,0xff,0xd4,0x89,0x00,0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x8b,0x00,0x06, + 0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x8d,0x00,0x06,0x00,0x10,0x07,0x06,0xff, + 0xd4,0x8f,0x00,0x06,0x00,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xd4, + 0x91,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd4,0x93,0x00,0x09,0x00,0xd1,0x0b,0x10, + 0x07,0x0a,0xff,0xd4,0x95,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x97,0x00,0x0a, + 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x99,0x00,0x0a,0x00,0x10,0x07, + 0x0a,0xff,0xd4,0x9b,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x9d,0x00, + 0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x9f,0x00,0x0a,0x00,0xd4,0x58,0xd3,0x2c,0xd2, + 0x16,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0xa1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff, + 0xd4,0xa3,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xd4,0xa5,0x00,0x0b,0x00, + 0x10,0x07,0x0c,0xff,0xd4,0xa7,0x00,0x0c,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x10, + 0xff,0xd4,0xa9,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xab,0x00,0x10,0x00,0xd1, + 0x0b,0x10,0x07,0x10,0xff,0xd4,0xad,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xaf, + 0x00,0x10,0x00,0xd3,0x35,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x00,0x00,0x01,0xff,0xd5, + 0xa1,0x00,0x10,0x07,0x01,0xff,0xd5,0xa2,0x00,0x01,0xff,0xd5,0xa3,0x00,0xd1,0x0e, + 0x10,0x07,0x01,0xff,0xd5,0xa4,0x00,0x01,0xff,0xd5,0xa5,0x00,0x10,0x07,0x01,0xff, + 0xd5,0xa6,0x00,0x01,0xff,0xd5,0xa7,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff, + 0xd5,0xa8,0x00,0x01,0xff,0xd5,0xa9,0x00,0x10,0x07,0x01,0xff,0xd5,0xaa,0x00,0x01, + 0xff,0xd5,0xab,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xac,0x00,0x01,0xff,0xd5, + 0xad,0x00,0x10,0x07,0x01,0xff,0xd5,0xae,0x00,0x01,0xff,0xd5,0xaf,0x00,0xcf,0x86, + 0xe5,0x08,0x3f,0xd4,0x70,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5, + 0xb0,0x00,0x01,0xff,0xd5,0xb1,0x00,0x10,0x07,0x01,0xff,0xd5,0xb2,0x00,0x01,0xff, + 0xd5,0xb3,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xb4,0x00,0x01,0xff,0xd5,0xb5, + 0x00,0x10,0x07,0x01,0xff,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb7,0x00,0xd2,0x1c,0xd1, + 0x0e,0x10,0x07,0x01,0xff,0xd5,0xb8,0x00,0x01,0xff,0xd5,0xb9,0x00,0x10,0x07,0x01, + 0xff,0xd5,0xba,0x00,0x01,0xff,0xd5,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5, + 0xbc,0x00,0x01,0xff,0xd5,0xbd,0x00,0x10,0x07,0x01,0xff,0xd5,0xbe,0x00,0x01,0xff, + 0xd5,0xbf,0x00,0xe3,0x87,0x3e,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x80, + 0x00,0x01,0xff,0xd6,0x81,0x00,0x10,0x07,0x01,0xff,0xd6,0x82,0x00,0x01,0xff,0xd6, + 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x84,0x00,0x01,0xff,0xd6,0x85,0x00, + 0x10,0x07,0x01,0xff,0xd6,0x86,0x00,0x00,0x00,0xe0,0x2f,0x3f,0xcf,0x86,0xe5,0xc0, + 0x3e,0xe4,0x97,0x3e,0xe3,0x76,0x3e,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x01,0xff,0xd5,0xa5,0xd6,0x82,0x00,0xe4,0x3e,0x25,0xe3,0xc3,0x1a, + 0xe2,0x7b,0x81,0xe1,0xc0,0x13,0xd0,0x1e,0xcf,0x86,0xc5,0xe4,0x08,0x4b,0xe3,0x53, + 0x46,0xe2,0xe9,0x43,0xe1,0x1c,0x43,0xe0,0xe1,0x42,0xcf,0x86,0xe5,0xa6,0x42,0x64, + 0x89,0x42,0x0b,0x00,0xcf,0x86,0xe5,0xfa,0x01,0xe4,0x03,0x56,0xe3,0x76,0x01,0xe2, + 0x8e,0x53,0xd1,0x0c,0xe0,0xef,0x52,0xcf,0x86,0x65,0x8d,0x52,0x04,0x00,0xe0,0x0d, + 0x01,0xcf,0x86,0xd5,0x0a,0xe4,0x10,0x53,0x63,0xff,0x52,0x0a,0x00,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x80,0x00,0x01,0xff,0xe2, + 0xb4,0x81,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x82,0x00,0x01,0xff,0xe2,0xb4,0x83, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x84,0x00,0x01,0xff,0xe2,0xb4,0x85, + 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x86,0x00,0x01,0xff,0xe2,0xb4,0x87,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x88,0x00,0x01,0xff,0xe2,0xb4,0x89, + 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x8a,0x00,0x01,0xff,0xe2,0xb4,0x8b,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x8c,0x00,0x01,0xff,0xe2,0xb4,0x8d,0x00,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x8e,0x00,0x01,0xff,0xe2,0xb4,0x8f,0x00,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x90,0x00,0x01,0xff,0xe2,0xb4,0x91, + 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x92,0x00,0x01,0xff,0xe2,0xb4,0x93,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x94,0x00,0x01,0xff,0xe2,0xb4,0x95,0x00,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x96,0x00,0x01,0xff,0xe2,0xb4,0x97,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x98,0x00,0x01,0xff,0xe2,0xb4,0x99,0x00,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x9a,0x00,0x01,0xff,0xe2,0xb4,0x9b,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x9c,0x00,0x01,0xff,0xe2,0xb4,0x9d,0x00,0x10,0x08,0x01, + 0xff,0xe2,0xb4,0x9e,0x00,0x01,0xff,0xe2,0xb4,0x9f,0x00,0xcf,0x86,0xe5,0x42,0x52, + 0x94,0x50,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa0,0x00, + 0x01,0xff,0xe2,0xb4,0xa1,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa2,0x00,0x01,0xff, + 0xe2,0xb4,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa4,0x00,0x01,0xff, + 0xe2,0xb4,0xa5,0x00,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xa7,0x00,0x52,0x04, + 0x00,0x00,0x91,0x0c,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xad,0x00,0x00,0x00, + 0x01,0x00,0xd2,0x1b,0xe1,0xfc,0x52,0xe0,0xad,0x52,0xcf,0x86,0x95,0x0f,0x94,0x0b, + 0x93,0x07,0x62,0x92,0x52,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xd1,0x13,0xe0, + 0xd3,0x53,0xcf,0x86,0x95,0x0a,0xe4,0xa8,0x53,0x63,0x97,0x53,0x04,0x00,0x04,0x00, + 0xd0,0x0d,0xcf,0x86,0x95,0x07,0x64,0x22,0x54,0x08,0x00,0x04,0x00,0xcf,0x86,0x55, + 0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x07,0x62,0x2f,0x54,0x04,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0xb0,0x00,0x11,0xff,0xe1,0x8f,0xb1,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0xb2,0x00,0x11,0xff,0xe1,0x8f,0xb3,0x00,0x91,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0xb4,0x00,0x11,0xff,0xe1,0x8f,0xb5,0x00,0x00,0x00, + 0xd4,0x1c,0xe3,0xe0,0x56,0xe2,0x17,0x56,0xe1,0xda,0x55,0xe0,0xbb,0x55,0xcf,0x86, + 0x95,0x0a,0xe4,0xa4,0x55,0x63,0x88,0x55,0x04,0x00,0x04,0x00,0xe3,0xd2,0x01,0xe2, + 0x2b,0x5a,0xd1,0x0c,0xe0,0x4c,0x59,0xcf,0x86,0x65,0x25,0x59,0x0a,0x00,0xe0,0x9c, + 0x59,0xcf,0x86,0xd5,0xc5,0xd4,0x45,0xd3,0x31,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x12, + 0xff,0xd0,0xb2,0x00,0x12,0xff,0xd0,0xb4,0x00,0x10,0x07,0x12,0xff,0xd0,0xbe,0x00, + 0x12,0xff,0xd1,0x81,0x00,0x51,0x07,0x12,0xff,0xd1,0x82,0x00,0x10,0x07,0x12,0xff, + 0xd1,0x8a,0x00,0x12,0xff,0xd1,0xa3,0x00,0x92,0x10,0x91,0x0c,0x10,0x08,0x12,0xff, + 0xea,0x99,0x8b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x14,0xff,0xe1,0x83,0x90,0x00,0x14,0xff,0xe1,0x83,0x91,0x00,0x10,0x08, + 0x14,0xff,0xe1,0x83,0x92,0x00,0x14,0xff,0xe1,0x83,0x93,0x00,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0x94,0x00,0x14,0xff,0xe1,0x83,0x95,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0x96,0x00,0x14,0xff,0xe1,0x83,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0x98,0x00,0x14,0xff,0xe1,0x83,0x99,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0x9a,0x00,0x14,0xff,0xe1,0x83,0x9b,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0x9c,0x00,0x14,0xff,0xe1,0x83,0x9d,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0x9e,0x00,0x14,0xff,0xe1,0x83,0x9f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x14,0xff,0xe1,0x83,0xa0,0x00,0x14,0xff,0xe1,0x83,0xa1,0x00,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xa2,0x00,0x14,0xff,0xe1,0x83,0xa3,0x00,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xa4,0x00,0x14,0xff,0xe1,0x83,0xa5,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xa6,0x00,0x14,0xff,0xe1,0x83,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xa8,0x00,0x14,0xff,0xe1,0x83,0xa9,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xaa,0x00,0x14,0xff,0xe1,0x83,0xab,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xac,0x00,0x14,0xff,0xe1,0x83,0xad,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0xae,0x00,0x14,0xff,0xe1,0x83,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xb0,0x00,0x14,0xff,0xe1,0x83,0xb1,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xb2,0x00,0x14,0xff,0xe1,0x83,0xb3,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xb4,0x00,0x14,0xff,0xe1,0x83,0xb5,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0xb6,0x00,0x14,0xff,0xe1,0x83,0xb7,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xb8,0x00,0x14,0xff,0xe1,0x83,0xb9,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0xba,0x00,0x00,0x00,0xd1,0x0c,0x10,0x04,0x00,0x00,0x14,0xff,0xe1,0x83,0xbd,0x00, + 0x10,0x08,0x14,0xff,0xe1,0x83,0xbe,0x00,0x14,0xff,0xe1,0x83,0xbf,0x00,0xe2,0x9d, + 0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa5,0x00,0x01,0xff,0x61,0xcc, + 0xa5,0x00,0x10,0x08,0x01,0xff,0x62,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc,0x87,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x62,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc,0xa3,0x00, + 0x10,0x08,0x01,0xff,0x62,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00,0xd2,0x24, + 0xd1,0x14,0x10,0x0a,0x01,0xff,0x63,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc, + 0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x87,0x00,0x01,0xff,0x64,0xcc, + 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa3,0x00,0x01,0xff,0x64,0xcc, + 0xa3,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc,0xb1,0x00, + 0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa7,0x00,0x01,0xff, + 0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xad,0x00,0x01,0xff,0x64,0xcc, + 0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff, + 0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00, + 0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x65,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, + 0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc, + 0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08,0x01,0xff, + 0x66,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc,0x84,0x00, + 0x10,0x08,0x01,0xff,0x68,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x68,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00,0x10,0x08, + 0x01,0xff,0x68,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x68,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00,0x10,0x08, + 0x01,0xff,0x68,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x69,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a,0x01,0xff, + 0x69,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x81,0x00,0x01,0xff,0x6b,0xcc, + 0x81,0x00,0x10,0x08,0x01,0xff,0x6b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc,0xa3,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc,0xb1,0x00, + 0x10,0x08,0x01,0xff,0x6c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00,0xd2,0x24, + 0xd1,0x14,0x10,0x0a,0x01,0xff,0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff,0x6c,0xcc, + 0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x6c,0xcc,0xb1,0x00,0x01,0xff,0x6c,0xcc, + 0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6c,0xcc,0xad,0x00,0x01,0xff,0x6c,0xcc, + 0xad,0x00,0x10,0x08,0x01,0xff,0x6d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc,0x81,0x00, + 0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x6d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6d, + 0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa3, + 0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xad, + 0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x83, + 0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f, + 0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3,0x48,0xd2, + 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff,0x6f, + 0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0x01, + 0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x70,0xcc,0x81, + 0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x70,0xcc,0x87,0x00,0x01, + 0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x87, + 0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xa3,0x00,0x01, + 0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84, + 0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xb1, + 0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x73,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10,0x08,0x01, + 0xff,0x73,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01, + 0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x10, + 0x0a,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87, + 0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x01, + 0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0x87,0x00,0x01, + 0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xa3,0x00,0x01, + 0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0xb1,0x00,0x01,0xff,0x74, + 0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xad, + 0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa4,0x00,0x01, + 0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0xb0,0x00,0x01, + 0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xad,0x00,0x01,0xff,0x75, + 0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81, + 0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x84, + 0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x76,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x76, + 0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x11,0x02,0xcf,0x86,0xd5,0xe2, + 0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x80,0x00, + 0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x81,0x00,0x01,0xff, + 0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x88,0x00,0x01,0xff, + 0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x87,0x00,0x01,0xff,0x77,0xcc, + 0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0xa3,0x00,0x01,0xff, + 0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x78,0xcc,0x87,0x00,0x01,0xff,0x78,0xcc, + 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x78,0xcc,0x88,0x00,0x01,0xff,0x78,0xcc, + 0x88,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc,0x87,0x00, + 0xd3,0x33,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x82,0x00,0x01,0xff, + 0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0xa3,0x00,0x01,0xff,0x7a,0xcc, + 0xa3,0x00,0xe1,0x12,0x59,0x10,0x08,0x01,0xff,0x7a,0xcc,0xb1,0x00,0x01,0xff,0x7a, + 0xcc,0xb1,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01, + 0xff,0x79,0xcc,0x8a,0x00,0x10,0x08,0x01,0xff,0x61,0xca,0xbe,0x00,0x02,0xff,0x73, + 0xcc,0x87,0x00,0x51,0x04,0x0a,0x00,0x10,0x07,0x0a,0xff,0x73,0x73,0x00,0x0a,0x00, + 0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa3,0x00, + 0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x89,0x00,0x01,0xff, + 0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00, + 0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc, 0x80,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x41,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00, - 0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc, - 0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, - 0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x81,0x00, + 0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00, + 0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc, + 0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, + 0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00, 0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x41,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00, - 0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc, - 0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x83,0x00,0x01,0xff, - 0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x86,0x00, + 0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00, + 0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc, + 0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x01,0xff, + 0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00, 0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x45,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x45,0xcc, - 0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc, - 0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82,0xcc, + 0x65,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, + 0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc, + 0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc, 0x81,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01,0xd4, - 0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82,0xcc,0x80, - 0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82, + 0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80, + 0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82, 0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01, - 0xff,0x45,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x10, - 0x0a,0x01,0xff,0x45,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x89,0x00,0x01,0xff,0x69, - 0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc,0xa3, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc,0xa3, - 0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00,0xd3, - 0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc,0x81,0x00,0x01, - 0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc,0x80, - 0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f, + 0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x10, + 0x0a,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x89,0x00,0x01,0xff,0x69, + 0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc,0xa3, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc,0xa3, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00,0xd3, + 0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x01, + 0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80, + 0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f, 0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a,0x01, - 0xff,0x4f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0xd2, - 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x6f, - 0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x81,0x00,0x01, - 0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b, - 0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x4f, + 0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0xd2, + 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x6f, + 0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0x01, + 0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b, + 0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f, 0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98,0xd3, - 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x83,0x00,0x01, - 0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0xa3, - 0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55, - 0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x89, - 0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x55, + 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x01, + 0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3, + 0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75, + 0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x89, + 0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75, 0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a,0x01, - 0xff,0x55,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0xd1, - 0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc,0x9b, - 0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff,0x75, - 0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x55, + 0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0xd1, + 0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc,0x9b, + 0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff,0x75, + 0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75, 0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08,0x01, - 0xff,0x59,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x59,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x59, - 0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0x92,0x14,0x91,0x10,0x10,0x08,0x01, - 0xff,0x59,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x0a,0x00,0x0a,0x00,0xe1, - 0xc0,0x04,0xe0,0x80,0x02,0xcf,0x86,0xe5,0x2d,0x01,0xd4,0xa8,0xd3,0x54,0xd2,0x28, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce, - 0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93, - 0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, - 0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0x00, - 0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x91,0xcc,0x93,0x00,0x01,0xff,0xce, - 0x91,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80,0x00,0x01, - 0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x91, - 0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b, - 0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcd, - 0x82,0x00,0xd3,0x42,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x93, - 0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93, - 0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b, - 0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc, - 0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x95,0xcc,0x93, - 0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x95,0xcc,0x93, - 0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b, - 0x01,0xff,0xce,0x95,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0xcc, - 0x81,0x00,0x00,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff, - 0xce,0xb7,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0x00, - 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce, - 0xb7,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82, - 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0x97,0xcc,0x93,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0x00,0x10,0x0b, - 0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc, - 0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81,0x00,0x01, - 0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93, - 0xcd,0x82,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x82,0x00,0xd3,0x54,0xd2,0x28, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc, - 0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce, - 0xb9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93, - 0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, - 0xce,0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82,0x00, - 0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x93,0x00,0x01,0xff,0xce, - 0x99,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcc,0x80,0x00,0x01, - 0xff,0xce,0x99,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x99, - 0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b, - 0x01,0xff,0xce,0x99,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x99,0xcc,0x94,0xcd, - 0x82,0x00,0xcf,0x86,0xe5,0x13,0x01,0xd4,0x84,0xd3,0x42,0xd2,0x28,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00,0x10, - 0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94, - 0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x81,0x00, - 0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0x9f,0xcc,0x93,0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0x00,0x10, - 0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc,0x94, - 0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x81,0x00, - 0x01,0xff,0xce,0x9f,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x54,0xd2,0x28,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94, - 0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85, - 0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93,0xcc, - 0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf, - 0x85,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00,0xd2, - 0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0x00,0x10,0x04, - 0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x0f,0x10,0x04,0x00, - 0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x81,0x00,0x10,0x04,0x00,0x00,0x01,0xff, - 0xce,0xa5,0xcc,0x94,0xcd,0x82,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0x10, - 0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94, - 0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0x00, - 0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc, - 0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xce,0xa9,0xcc,0x93,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94, - 0x00,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xa9, - 0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc, - 0x81,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce, - 0xa9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0x00,0xd3, - 0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01,0xff, - 0xce,0xb1,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01,0xff, - 0xce,0xb5,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80,0x00, - 0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, - 0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xcf, - 0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x91,0x12,0x10,0x09,0x01, - 0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x00,0x00,0xe0, - 0xe1,0x02,0xcf,0x86,0xe5,0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10, - 0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94, - 0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00, - 0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01, - 0xff,0xce,0xb1,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94, - 0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xcd, - 0x85,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1, - 0x16,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0x91, - 0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80,0xcd, - 0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10, - 0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0x91, - 0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd, - 0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd3, - 0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x85,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc, - 0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xcd,0x85, - 0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce, - 0xb7,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82, - 0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcd, - 0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce, - 0x97,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x80, - 0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81,0xcd, - 0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01, - 0xff,0xce,0x97,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94, - 0xcd,0x82,0xcd,0x85,0x00,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01, - 0xff,0xcf,0x89,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x85, - 0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff, - 0xcf,0x89,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf, - 0x89,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81, - 0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00, - 0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16,0x10, - 0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94, - 0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00, - 0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01, - 0xff,0xce,0xa9,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94, - 0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x82,0xcd, - 0x85,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd3,0x49,0xd2, - 0x26,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce,0xb1, - 0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff, - 0xce,0xb1,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81,0xcd, - 0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff,0xce, - 0xb1,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x91, - 0xcc,0x86,0x00,0x01,0xff,0xce,0x91,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0x91, - 0xcc,0x80,0x00,0x01,0xff,0xce,0x91,0xcc,0x81,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff, - 0xce,0x91,0xcd,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xb9,0x00,0x01,0x00, - 0xcf,0x86,0xe5,0x16,0x01,0xd4,0x8f,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10,0x04,0x01, - 0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x80, - 0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff, - 0xce,0xb7,0xcc,0x81,0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcd, - 0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0x95,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x81,0x00,0x10, - 0x09,0x01,0xff,0xce,0x97,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00,0xd1, - 0x13,0x10,0x09,0x01,0xff,0xce,0x97,0xcd,0x85,0x00,0x01,0xff,0xe1,0xbe,0xbf,0xcc, - 0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbe,0xbf,0xcc,0x81,0x00,0x01,0xff,0xe1,0xbe, - 0xbf,0xcd,0x82,0x00,0xd3,0x40,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9, - 0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce,0xb9, - 0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x51,0x04, - 0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc, - 0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x86, - 0x00,0x01,0xff,0xce,0x99,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x80, - 0x00,0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x04,0x00,0x00,0x01,0xff, - 0xe1,0xbf,0xbe,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbf,0xbe,0xcc,0x81,0x00, - 0x01,0xff,0xe1,0xbf,0xbe,0xcd,0x82,0x00,0xd4,0x93,0xd3,0x4e,0xd2,0x28,0xd1,0x12, + 0xff,0x79,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x79,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x79, + 0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x79,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x10,0x08,0x0a,0xff,0xe1, + 0xbb,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbd,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbf,0x00,0x0a,0x00,0xe1,0xbf,0x02,0xe0,0xa1, + 0x01,0xcf,0x86,0xd5,0xc6,0xd4,0x6c,0xd3,0x18,0xe2,0x0e,0x59,0xe1,0xf7,0x58,0x10, + 0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0x00,0xd2, + 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1, + 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, + 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82, + 0x00,0xd3,0x18,0xe2,0x4a,0x59,0xe1,0x33,0x59,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc, + 0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xce,0xb5,0xcc,0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb5,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80, + 0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff, + 0xce,0xb5,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd4,0x6c,0xd3,0x18,0xe2,0x74,0x59, + 0xe1,0x5d,0x59,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7, + 0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00, + 0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc, + 0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01, + 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81, + 0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7, + 0xcc,0x94,0xcd,0x82,0x00,0xd3,0x18,0xe2,0xb0,0x59,0xe1,0x99,0x59,0x10,0x09,0x01, + 0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0x00,0xd2,0x28,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94, + 0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9, + 0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce, + 0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82,0x00,0xcf, + 0x86,0xd5,0xac,0xd4,0x5a,0xd3,0x18,0xe2,0xed,0x59,0xe1,0xd6,0x59,0x10,0x09,0x01, + 0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00,0xd2,0x28,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94, + 0x00,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf, + 0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x18,0xe2, + 0x17,0x5a,0xe1,0x00,0x5a,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff, + 0xcf,0x85,0xcc,0x94,0x00,0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xcf, + 0x85,0xcc,0x94,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x80, + 0x00,0xd1,0x0f,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00, + 0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00,0xe4,0xd3,0x5a, + 0xd3,0x18,0xe2,0x52,0x5a,0xe1,0x3b,0x5a,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0x00, + 0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xcf, + 0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xe0,0xd9,0x02,0xcf,0x86,0xe5, + 0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1, + 0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d, + 0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc, + 0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93, + 0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00, + 0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb1,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff, + 0xce,0xb1,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00, + 0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb1,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1, + 0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce, + 0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01, + 0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x64,0xd2,0x30,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc, + 0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0xce,0xb9, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d, + 0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc, + 0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82, + 0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30, + 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb7,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80, + 0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a, + 0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb7,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93, + 0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00, + 0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93, + 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc, + 0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81, + 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d, + 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89, + 0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d, + 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93, + 0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00, + 0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf, + 0x89,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x49,0xd2,0x26,0xd1,0x12,0x10,0x09, + 0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce,0xb1,0xcc,0x84,0x00,0x10,0x0b, + 0x01,0xff,0xce,0xb1,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xce,0xb9,0x00, + 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10, + 0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcd,0x82,0xce,0xb9, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x81,0x00,0xe1,0xf3,0x5a,0x10,0x09,0x01,0xff,0xce,0xb1,0xce,0xb9, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0xbd,0xd4,0x7e,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10, + 0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7, + 0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0xd1,0x0f,0x10,0x0b, + 0x01,0xff,0xce,0xb7,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce, + 0xb7,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81, + 0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81, + 0x00,0xe1,0x02,0x5b,0x10,0x09,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0x01,0xff,0xe1, + 0xbe,0xbf,0xcc,0x80,0x00,0xd3,0x18,0xe2,0x28,0x5b,0xe1,0x11,0x5b,0x10,0x09,0x01, + 0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0xe2,0x4c,0x5b, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc, + 0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc, + 0x81,0x00,0xd4,0x51,0xd3,0x18,0xe2,0x6f,0x5b,0xe1,0x58,0x5b,0x10,0x09,0x01,0xff, + 0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00,0xd2,0x24,0xd1,0x12, 0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00, - 0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc, - 0x88,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x93,0x00,0x01, - 0xff,0xcf,0x81,0xcc,0x94,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcd,0x82,0x00,0x01, - 0xff,0xcf,0x85,0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xce,0xa5,0xcc,0x86,0x00,0x01,0xff,0xce,0xa5,0xcc,0x84,0x00,0x10,0x09,0x01,0xff, - 0xce,0xa5,0xcc,0x80,0x00,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0xa1,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x80,0x00,0x10,0x09, - 0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x01,0xff,0x60,0x00,0xd3,0x3b,0xd2,0x18,0x51, - 0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff, - 0xcf,0x89,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81,0xcd, - 0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcd,0x82,0x00,0x01,0xff,0xcf, - 0x89,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x9f, - 0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xa9, - 0xcc,0x80,0x00,0x01,0xff,0xce,0xa9,0xcc,0x81,0x00,0xd1,0x10,0x10,0x09,0x01,0xff, - 0xce,0xa9,0xcd,0x85,0x00,0x01,0xff,0xc2,0xb4,0x00,0x10,0x04,0x01,0x00,0x00,0x00, - 0xe0,0x62,0x0c,0xcf,0x86,0xe5,0x9f,0x08,0xe4,0xf8,0x05,0xe3,0xdb,0x02,0xe2,0xa1, - 0x01,0xd1,0xb4,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x94,0x1c,0x93,0x18,0x92,0x14,0x91, - 0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01,0xff,0xe2,0x80,0x83,0x00,0x01, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x53,0x04,0x01,0x00,0x52,0x04,0x01, - 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x01,0x00,0xcf,0x86,0xd5, - 0x48,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x06,0x00,0x52,0x04,0x04,0x00,0x11,0x04,0x04,0x00,0x06,0x00,0xd3,0x1c,0xd2, - 0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x06,0x00,0x07,0x00,0xd1,0x08,0x10,0x04,0x07, - 0x00,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08, - 0x00,0x10,0x04,0x08,0x00,0x06,0x00,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x06,0x00,0x91, - 0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x0f,0x00,0x92,0x08,0x11,0x04,0x0f,0x00,0x01, - 0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x00, - 0x00,0x01,0x00,0x01,0x00,0xd0,0x7e,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x53,0x04,0x01, - 0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xd3, - 0x10,0x52,0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0c,0x00,0x0c,0x00,0x52, - 0x04,0x0c,0x00,0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xd4,0x1c,0x53, - 0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x02,0x00,0x91, - 0x08,0x10,0x04,0x03,0x00,0x04,0x00,0x04,0x00,0xd3,0x10,0xd2,0x08,0x11,0x04,0x06, - 0x00,0x08,0x00,0x11,0x04,0x08,0x00,0x0b,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0b, - 0x00,0x0c,0x00,0x10,0x04,0x0e,0x00,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x11, - 0x00,0x13,0x00,0xcf,0x86,0xd5,0x28,0x54,0x04,0x00,0x00,0xd3,0x0c,0x92,0x08,0x11, - 0x04,0x01,0xe6,0x01,0x01,0x01,0xe6,0xd2,0x0c,0x51,0x04,0x01,0x01,0x10,0x04,0x01, - 0x01,0x01,0xe6,0x91,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x01,0x00,0xd4,0x30,0xd3, - 0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x04,0x00,0xd1,0x08,0x10, - 0x04,0x06,0x00,0x06,0x01,0x10,0x04,0x06,0x01,0x06,0xe6,0x92,0x10,0xd1,0x08,0x10, - 0x04,0x06,0xdc,0x06,0xe6,0x10,0x04,0x06,0x01,0x08,0x01,0x09,0xdc,0x93,0x10,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x0a,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, - 0x81,0xd0,0x4f,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01, - 0x00,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xa9,0x00,0x01,0x00,0x92,0x12, - 0x51,0x04,0x01,0x00,0x10,0x06,0x01,0xff,0x4b,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00, - 0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00, - 0x10,0x04,0x04,0x00,0x07,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x06,0x00,0x06,0x00, - 0xcf,0x86,0x95,0x2c,0xd4,0x18,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0xd1,0x08, - 0x10,0x04,0x08,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x93,0x10,0x92,0x0c, - 0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0xd0,0x68,0xcf,0x86,0xd5,0x48,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00, - 0x10,0x04,0x01,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x11,0x00,0x00,0x00,0x53,0x04, - 0x01,0x00,0x92,0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x90,0xcc, - 0xb8,0x00,0x01,0xff,0xe2,0x86,0x92,0xcc,0xb8,0x00,0x01,0x00,0x94,0x1a,0x53,0x04, - 0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86, - 0x94,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0x53,0x04, - 0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x87, - 0x90,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2,0x87,0x94,0xcc,0xb8,0x00,0x01,0xff, - 0xe2,0x87,0x92,0xcc,0xb8,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00,0x93,0x08,0x12,0x04, - 0x04,0x00,0x06,0x00,0x06,0x00,0xe2,0x38,0x02,0xe1,0x3f,0x01,0xd0,0x68,0xcf,0x86, - 0xd5,0x3e,0x94,0x3a,0xd3,0x16,0x52,0x04,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff, - 0xe2,0x88,0x83,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0xd2,0x12,0x91,0x0e,0x10,0x04, - 0x01,0x00,0x01,0xff,0xe2,0x88,0x88,0xcc,0xb8,0x00,0x01,0x00,0x91,0x0e,0x10,0x0a, - 0x01,0xff,0xe2,0x88,0x8b,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x24, - 0x93,0x20,0x52,0x04,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa3,0xcc, - 0xb8,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa5,0xcc,0xb8,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x48,0x94,0x44,0xd3,0x2e,0xd2,0x12,0x91,0x0e, - 0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x88,0xbc,0xcc,0xb8,0x00,0x01,0x00,0xd1,0x0e, - 0x10,0x0a,0x01,0xff,0xe2,0x89,0x83,0xcc,0xb8,0x00,0x01,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0xe2,0x89,0x85,0xcc,0xb8,0x00,0x92,0x12,0x91,0x0e,0x10,0x04,0x01,0x00, - 0x01,0xff,0xe2,0x89,0x88,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x40, - 0xd3,0x1e,0x92,0x1a,0xd1,0x0c,0x10,0x08,0x01,0xff,0x3d,0xcc,0xb8,0x00,0x01,0x00, - 0x10,0x0a,0x01,0xff,0xe2,0x89,0xa1,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x52,0x04, - 0x01,0x00,0xd1,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x89,0x8d,0xcc,0xb8,0x00, - 0x10,0x08,0x01,0xff,0x3c,0xcc,0xb8,0x00,0x01,0xff,0x3e,0xcc,0xb8,0x00,0xd3,0x30, - 0xd2,0x18,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xa4,0xcc,0xb8,0x00,0x01,0xff, - 0xe2,0x89,0xa5,0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89, - 0xb2,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xb3,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18, - 0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xb6,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89, - 0xb7,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x50,0x94,0x4c, - 0xd3,0x30,0xd2,0x18,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xba,0xcc,0xb8,0x00, - 0x01,0xff,0xe2,0x89,0xbb,0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff, - 0xe2,0x8a,0x82,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x83,0xcc,0xb8,0x00,0x01,0x00, - 0x92,0x18,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x86,0xcc,0xb8,0x00,0x01,0xff, - 0xe2,0x8a,0x87,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x30,0x53,0x04, - 0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa2,0xcc, - 0xb8,0x00,0x01,0xff,0xe2,0x8a,0xa8,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a, - 0xa9,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0xab,0xcc,0xb8,0x00,0x01,0x00,0xcf,0x86, - 0x55,0x04,0x01,0x00,0xd4,0x5c,0xd3,0x2c,0x92,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff, - 0xe2,0x89,0xbc,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xbd,0xcc,0xb8,0x00,0x10,0x0a, - 0x01,0xff,0xe2,0x8a,0x91,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x92,0xcc,0xb8,0x00, - 0x01,0x00,0xd2,0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb2,0xcc, - 0xb8,0x00,0x01,0xff,0xe2,0x8a,0xb3,0xcc,0xb8,0x00,0x91,0x14,0x10,0x0a,0x01,0xff, - 0xe2,0x8a,0xb4,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0xb5,0xcc,0xb8,0x00,0x01,0x00, - 0x93,0x0c,0x92,0x08,0x11,0x04,0x01,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xd1,0x64, - 0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x01,0x00,0x04,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x20,0x53,0x04, - 0x01,0x00,0x92,0x18,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x80,0x88,0x00, - 0x10,0x08,0x01,0xff,0xe3,0x80,0x89,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86, - 0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04, - 0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00, - 0x04,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00, - 0x92,0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x06,0x00,0x06,0x00,0x06,0x00, - 0xcf,0x86,0xd5,0x2c,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04, - 0x06,0x00,0x10,0x04,0x06,0x00,0x07,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x07,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0x12,0x04,0x08,0x00,0x09,0x00,0xd4,0x14, - 0x53,0x04,0x09,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x0c,0x00, - 0x0c,0x00,0xd3,0x08,0x12,0x04,0x0c,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10,0x00, - 0x10,0x04,0x10,0x00,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00, - 0xd3,0xa6,0xd2,0x74,0xd1,0x40,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18, - 0x93,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04, - 0x04,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04, - 0x01,0x00,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x01,0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00, - 0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x06,0x00,0x06,0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00, - 0x10,0x04,0x06,0x00,0x07,0x00,0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x1a,0xcf,0x86, - 0x95,0x14,0x54,0x04,0x01,0x00,0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00, - 0x06,0x00,0x06,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00, - 0x13,0x04,0x04,0x00,0x06,0x00,0xd2,0xdc,0xd1,0x48,0xd0,0x26,0xcf,0x86,0x95,0x20, - 0x54,0x04,0x01,0x00,0xd3,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x07,0x00,0x06,0x00, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x08,0x00,0x04,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04, - 0x04,0x00,0x06,0x00,0x06,0x00,0x52,0x04,0x06,0x00,0x11,0x04,0x06,0x00,0x08,0x00, - 0xd0,0x5e,0xcf,0x86,0xd5,0x2c,0xd4,0x10,0x53,0x04,0x06,0x00,0x92,0x08,0x11,0x04, - 0x06,0x00,0x07,0x00,0x07,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00, - 0x08,0x00,0x52,0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0a,0x00,0x0b,0x00, - 0xd4,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x08,0x00, - 0xd3,0x10,0x92,0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, - 0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86, - 0xd5,0x1c,0x94,0x18,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00, - 0x51,0x04,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0b,0x00,0x94,0x14,0x93,0x10, - 0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0c,0x00,0x0b,0x00, - 0x0b,0x00,0xd1,0xa8,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x0c,0x00,0x01,0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x01,0x00,0x01,0x00, - 0x94,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x18,0x53,0x04,0x01,0x00, - 0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x04,0x0c,0x00, - 0x01,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0c,0x00, - 0x51,0x04,0x0c,0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x52,0x04,0x01,0x00,0x51,0x04, - 0x01,0x00,0x10,0x04,0x01,0x00,0x0c,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0c,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x06,0x00,0x93,0x0c,0x52,0x04, - 0x06,0x00,0x11,0x04,0x06,0x00,0x01,0x00,0x01,0x00,0xd0,0x3e,0xcf,0x86,0xd5,0x18, - 0x54,0x04,0x01,0x00,0x93,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x0c,0x00,0x0c,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0c,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04, - 0x01,0x00,0x10,0x04,0x01,0x00,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0x94,0x28,0xd3,0x10, - 0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0xd2,0x0c, - 0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x0d,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, - 0x0d,0x00,0x0c,0x00,0x06,0x00,0x94,0x0c,0x53,0x04,0x06,0x00,0x12,0x04,0x06,0x00, - 0x0a,0x00,0x06,0x00,0xe4,0x39,0x01,0xd3,0x0c,0xd2,0x06,0xcf,0x06,0x04,0x00,0xcf, - 0x06,0x06,0x00,0xd2,0x30,0xd1,0x06,0xcf,0x06,0x06,0x00,0xd0,0x06,0xcf,0x06,0x06, - 0x00,0xcf,0x86,0x95,0x1e,0x54,0x04,0x06,0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06, - 0x00,0x91,0x0e,0x10,0x0a,0x06,0xff,0xe2,0xab,0x9d,0xcc,0xb8,0x00,0x06,0x00,0x06, - 0x00,0x06,0x00,0xd1,0x80,0xd0,0x3a,0xcf,0x86,0xd5,0x28,0xd4,0x10,0x53,0x04,0x07, - 0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x08,0x00,0xd3,0x08,0x12,0x04,0x08, - 0x00,0x09,0x00,0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a, - 0x00,0x94,0x0c,0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf, - 0x86,0xd5,0x30,0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10, - 0x04,0x0a,0x00,0x10,0x00,0x10,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08,0x10, - 0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x10,0x00,0x10, - 0x00,0x54,0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10, - 0x00,0x10,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c,0x52, - 0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0x53, - 0x04,0x10,0x00,0xd2,0x08,0x11,0x04,0x10,0x00,0x14,0x00,0x91,0x08,0x10,0x04,0x14, - 0x00,0x10,0x00,0x10,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x10,0x00,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x15,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x92, - 0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd4, - 0x0c,0x53,0x04,0x14,0x00,0x12,0x04,0x14,0x00,0x11,0x00,0x53,0x04,0x14,0x00,0x52, - 0x04,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0xe3,0xb9,0x01, - 0xd2,0xac,0xd1,0x68,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x08,0x00,0x94,0x14,0x53,0x04, - 0x08,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00, - 0x08,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x52,0x04, - 0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xd4,0x14,0x53,0x04, - 0x09,0x00,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, - 0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0a,0x00,0x0a,0x00,0x09,0x00, - 0x52,0x04,0x0a,0x00,0x11,0x04,0x0a,0x00,0x0b,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00, - 0xcf,0x86,0x55,0x04,0x08,0x00,0xd4,0x1c,0x53,0x04,0x08,0x00,0xd2,0x0c,0x51,0x04, - 0x08,0x00,0x10,0x04,0x08,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, - 0x0b,0xe6,0xd3,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0d,0x00,0x00,0x00,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd1,0x6c,0xd0,0x2a, - 0xcf,0x86,0x55,0x04,0x08,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04, - 0x08,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04, - 0x00,0x00,0x0d,0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x55,0x04,0x08,0x00,0xd4,0x1c, - 0xd3,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0d,0x00,0x52,0x04,0x00,0x00, - 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x08,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04, - 0x00,0x00,0x10,0x04,0x00,0x00,0x0c,0x09,0xd0,0x5a,0xcf,0x86,0xd5,0x18,0x54,0x04, - 0x08,0x00,0x93,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00, - 0x00,0x00,0x00,0x00,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00, - 0x10,0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04, - 0x08,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04, - 0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00, - 0x00,0x00,0xcf,0x86,0x95,0x40,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04, - 0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00, - 0x10,0x04,0x08,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00, - 0x10,0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04, - 0x08,0x00,0x00,0x00,0x0a,0xe6,0xd2,0x9c,0xd1,0x68,0xd0,0x32,0xcf,0x86,0xd5,0x14, - 0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x0a,0x00,0x11,0x04,0x08,0x00, - 0x0a,0x00,0x54,0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0a,0x00, - 0x0b,0x00,0x0d,0x00,0x0d,0x00,0x12,0x04,0x0d,0x00,0x10,0x00,0xcf,0x86,0x95,0x30, - 0x94,0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x12,0x00, - 0x91,0x08,0x10,0x04,0x12,0x00,0x13,0x00,0x13,0x00,0xd2,0x08,0x11,0x04,0x13,0x00, - 0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0x00,0x00,0x00,0x00, - 0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c, - 0x51,0x04,0x04,0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86, - 0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x00,0x00, - 0x00,0x00,0xd1,0x06,0xcf,0x06,0x04,0x00,0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86, - 0xd5,0x14,0x54,0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04,0x00, - 0x00,0x00,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x04,0x00,0x12,0x04,0x04,0x00, - 0x00,0x00,0xcf,0x86,0xe5,0x8d,0x05,0xe4,0x86,0x05,0xe3,0x7d,0x04,0xe2,0xe4,0x03, - 0xe1,0xc0,0x01,0xd0,0x3e,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x1c,0x53,0x04,0x01, - 0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0xda,0x01,0xe4,0x91,0x08,0x10, - 0x04,0x01,0xe8,0x01,0xde,0x01,0xe0,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x04, - 0x00,0x10,0x04,0x04,0x00,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x04,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0xaa,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01, - 0xff,0xe3,0x81,0x8b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81, - 0x8d,0xe3,0x82,0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01, - 0xff,0xe3,0x81,0x8f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81, - 0x91,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x93, - 0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x95,0xe3,0x82,0x99, - 0x00,0x01,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x97,0xe3,0x82, - 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x99,0xe3,0x82,0x99,0x00,0x01, - 0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x9b,0xe3,0x82,0x99,0x00,0x01,0x00, - 0x10,0x0b,0x01,0xff,0xe3,0x81,0x9d,0xe3,0x82,0x99,0x00,0x01,0x00,0xd4,0x53,0xd3, - 0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x9f,0xe3,0x82,0x99,0x00, - 0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xa1,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1, - 0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x81,0xa4,0xe3,0x82,0x99,0x00,0x10,0x04, - 0x01,0x00,0x01,0xff,0xe3,0x81,0xa6,0xe3,0x82,0x99,0x00,0x92,0x13,0x91,0x0f,0x10, - 0x04,0x01,0x00,0x01,0xff,0xe3,0x81,0xa8,0xe3,0x82,0x99,0x00,0x01,0x00,0x01,0x00, - 0xd3,0x4a,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xaf,0xe3,0x82,0x99, - 0x00,0x01,0xff,0xe3,0x81,0xaf,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00,0x01,0xff, - 0xe3,0x81,0xb2,0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb2, - 0xe3,0x82,0x9a,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb5,0xe3,0x82,0x99, - 0x00,0x01,0xff,0xe3,0x81,0xb5,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x04, - 0x01,0x00,0x01,0xff,0xe3,0x81,0xb8,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01,0xff,0xe3, - 0x81,0xb8,0xe3,0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81, - 0xbb,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82,0x9a,0x00,0x01,0x00, - 0xd0,0xee,0xcf,0x86,0xd5,0x42,0x54,0x04,0x01,0x00,0xd3,0x1b,0x52,0x04,0x01,0x00, - 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x86,0xe3,0x82,0x99,0x00,0x06,0x00,0x10, - 0x04,0x06,0x00,0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x08,0x10, - 0x04,0x01,0x08,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0x9d, - 0xe3,0x82,0x99,0x00,0x06,0x00,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x06,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b, - 0x01,0xff,0xe3,0x82,0xab,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3, - 0x82,0xad,0xe3,0x82,0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b, - 0x01,0xff,0xe3,0x82,0xaf,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3, - 0x82,0xb1,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82, - 0xb3,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb5,0xe3,0x82, - 0x99,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb7,0xe3, - 0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb9,0xe3,0x82,0x99,0x00, - 0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbb,0xe3,0x82,0x99,0x00,0x01, - 0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbd,0xe3,0x82,0x99,0x00,0x01,0x00,0xcf,0x86, - 0xd5,0xd5,0xd4,0x53,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82, - 0xbf,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x81,0xe3,0x82, - 0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x84,0xe3, - 0x82,0x99,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x86,0xe3,0x82,0x99,0x00, - 0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x88,0xe3,0x82,0x99, - 0x00,0x01,0x00,0x01,0x00,0xd3,0x4a,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3, - 0x83,0x8f,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x8f,0xe3,0x82,0x9a,0x00,0x10, - 0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x92,0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b, - 0x01,0xff,0xe3,0x83,0x92,0xe3,0x82,0x9a,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3, - 0x83,0x95,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x95,0xe3,0x82,0x9a,0x00,0xd2, - 0x1e,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x98,0xe3,0x82,0x99,0x00, - 0x10,0x0b,0x01,0xff,0xe3,0x83,0x98,0xe3,0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10, - 0x0b,0x01,0xff,0xe3,0x83,0x9b,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x9b,0xe3, - 0x82,0x9a,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x22,0x52,0x04,0x01,0x00,0xd1, - 0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xa6,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x04, - 0x01,0x00,0x01,0xff,0xe3,0x83,0xaf,0xe3,0x82,0x99,0x00,0xd2,0x25,0xd1,0x16,0x10, - 0x0b,0x01,0xff,0xe3,0x83,0xb0,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0xb1,0xe3, - 0x82,0x99,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0xb2,0xe3,0x82,0x99,0x00,0x01,0x00, - 0x51,0x04,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0xbd,0xe3,0x82,0x99,0x00,0x06, - 0x00,0xd1,0x4c,0xd0,0x46,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x00, - 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4, - 0x18,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a, - 0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x06,0x01,0x00,0xd0,0x32,0xcf, - 0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x54,0x04,0x04,0x00,0x53,0x04,0x04, - 0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xcf, - 0x86,0xd5,0x08,0x14,0x04,0x08,0x00,0x0a,0x00,0x94,0x0c,0x93,0x08,0x12,0x04,0x0a, - 0x00,0x00,0x00,0x00,0x00,0x06,0x00,0xd2,0xa4,0xd1,0x5c,0xd0,0x22,0xcf,0x86,0x95, - 0x1c,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10, - 0x04,0x01,0x00,0x07,0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x01,0x00,0xcf,0x86,0xd5, - 0x20,0xd4,0x0c,0x93,0x08,0x12,0x04,0x01,0x00,0x0b,0x00,0x0b,0x00,0x93,0x10,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0x54, - 0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x07,0x00,0x10, - 0x04,0x08,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01, - 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x06,0x00,0x06, - 0x00,0x06,0x00,0xcf,0x86,0xd5,0x10,0x94,0x0c,0x53,0x04,0x01,0x00,0x12,0x04,0x01, - 0x00,0x07,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01, - 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x16,0x00,0xd1,0x30,0xd0,0x06,0xcf, - 0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x10,0x52, - 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x07,0x00,0x92,0x0c,0x51, - 0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x01,0x00,0x01,0x00,0xd0,0x06,0xcf,0x06,0x01, - 0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01, - 0x00,0x11,0x04,0x01,0x00,0x07,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x07,0x00,0xcf,0x06,0x04, - 0x00,0xcf,0x06,0x04,0x00,0xd1,0x48,0xd0,0x40,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x04, - 0x00,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x2c,0xd2,0x06,0xcf,0x06,0x04,0x00,0xd1, - 0x06,0xcf,0x06,0x04,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04, - 0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xcf, - 0x06,0x07,0x00,0xcf,0x06,0x01,0x00,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xcf, - 0x06,0x01,0x00,0xe2,0x71,0x05,0xd1,0x8c,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00, - 0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xd4,0x06,0xcf,0x06,0x01,0x00,0xd3,0x06, - 0xcf,0x06,0x01,0x00,0xd2,0x06,0xcf,0x06,0x01,0x00,0xd1,0x06,0xcf,0x06,0x01,0x00, - 0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x01,0x00, - 0x11,0x04,0x01,0x00,0x08,0x00,0x08,0x00,0x53,0x04,0x08,0x00,0x12,0x04,0x08,0x00, - 0x0a,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0b,0x00, - 0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x11,0x00,0x11,0x00,0x93,0x0c, - 0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x13,0x00,0x13,0x00,0x94,0x14,0x53,0x04, - 0x13,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00, - 0x00,0x00,0xe0,0xdb,0x04,0xcf,0x86,0xe5,0xdf,0x01,0xd4,0x06,0xcf,0x06,0x04,0x00, - 0xd3,0x74,0xd2,0x6e,0xd1,0x06,0xcf,0x06,0x04,0x00,0xd0,0x3e,0xcf,0x86,0xd5,0x18, - 0x94,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00, - 0x00,0x00,0x00,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x04,0x00, - 0x06,0x00,0x04,0x00,0x04,0x00,0x93,0x10,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04, - 0x06,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86,0x95,0x24,0x94,0x20,0x93,0x1c, - 0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x04,0x00,0xd1,0x08,0x10,0x04, - 0x04,0x00,0x06,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0x0b,0x00, - 0xcf,0x06,0x0a,0x00,0xd2,0x84,0xd1,0x4c,0xd0,0x16,0xcf,0x86,0x55,0x04,0x0a,0x00, - 0x94,0x0c,0x53,0x04,0x0a,0x00,0x12,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, - 0x55,0x04,0x0a,0x00,0xd4,0x1c,0xd3,0x0c,0x92,0x08,0x11,0x04,0x0c,0x00,0x0a,0x00, - 0x0a,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a,0xe6, - 0xd3,0x08,0x12,0x04,0x0a,0x00,0x0d,0xe6,0x52,0x04,0x0d,0xe6,0x11,0x04,0x0a,0xe6, - 0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00, - 0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x11,0xe6,0x0d,0xe6,0x0b,0x00, - 0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x0c,0x92,0x08,0x11,0x04, - 0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x00,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x24, - 0x54,0x04,0x08,0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04, - 0x08,0x00,0x09,0x00,0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00, - 0x0a,0x00,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, - 0x0a,0x00,0x0a,0x00,0xcf,0x06,0x0a,0x00,0xd0,0x5e,0xcf,0x86,0xd5,0x28,0xd4,0x18, - 0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0xd1,0x08,0x10,0x04,0x0a,0x00,0x0c,0x00, - 0x10,0x04,0x0c,0x00,0x11,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x0c,0x00,0x0d,0x00, - 0x10,0x00,0x10,0x00,0xd4,0x1c,0x53,0x04,0x0c,0x00,0xd2,0x0c,0x51,0x04,0x0c,0x00, - 0x10,0x04,0x0d,0x00,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x12,0x00,0x14,0x00, - 0xd3,0x0c,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0x92,0x08,0x11,0x04, - 0x14,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x1c,0x94,0x18,0x93,0x14,0xd2,0x08, - 0x11,0x04,0x00,0x00,0x15,0x00,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x54,0x04,0x00,0x00,0xd3,0x10,0x52,0x04,0x00,0x00,0x51,0x04, - 0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04, - 0x0c,0x00,0x0a,0x00,0x0a,0x00,0xe4,0xf2,0x02,0xe3,0x65,0x01,0xd2,0x98,0xd1,0x48, - 0xd0,0x36,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x08,0x00,0x51,0x04, - 0x08,0x00,0x10,0x04,0x08,0x09,0x08,0x00,0x08,0x00,0x08,0x00,0xd4,0x0c,0x53,0x04, - 0x08,0x00,0x12,0x04,0x08,0x00,0x00,0x00,0x53,0x04,0x0b,0x00,0x92,0x08,0x11,0x04, - 0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0x54,0x04,0x09,0x00, - 0x13,0x04,0x09,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x0a,0x00,0xcf,0x86,0xd5,0x2c, - 0xd4,0x1c,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x09,0x12,0x00, - 0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x0a,0x00,0x53,0x04,0x0a,0x00, - 0x92,0x08,0x11,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x0b,0xe6,0xd3,0x0c, - 0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x11,0x04, - 0x11,0x00,0x14,0x00,0xd1,0x60,0xd0,0x22,0xcf,0x86,0x55,0x04,0x0a,0x00,0x94,0x18, - 0x53,0x04,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a,0xdc, - 0x11,0x04,0x0a,0xdc,0x0a,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x0a,0x00, - 0xd3,0x10,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a,0x09,0x00,0x00, - 0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0x54,0x04, - 0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00, - 0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00, - 0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0x07,0x0b,0x00, - 0x0b,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x20,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00, - 0x10,0x04,0x00,0x00,0x0b,0x00,0x53,0x04,0x0b,0x00,0xd2,0x08,0x11,0x04,0x0b,0x00, - 0x00,0x00,0x11,0x04,0x00,0x00,0x0b,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, - 0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0xd2,0xd0, - 0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0a,0x00,0x54,0x04,0x0a,0x00,0x93,0x10, - 0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00, - 0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x11,0x04, - 0x0a,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x00,0x00, - 0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x12,0x04,0x0b,0x00,0x10,0x00, - 0xd0,0x3a,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0xd3,0x1c,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0xe6,0xd1,0x08,0x10,0x04,0x0b,0xdc, - 0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0xe6, - 0x0b,0x00,0x0b,0x00,0x11,0x04,0x0b,0x00,0x0b,0xe6,0xcf,0x86,0xd5,0x2c,0xd4,0x18, - 0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6,0x10,0x04,0x0b,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00, - 0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00,0x54,0x04,0x0d,0x00,0x93,0x10,0x52,0x04, - 0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x09,0x00,0x00,0x00,0x00,0xd1,0x8c, - 0xd0,0x72,0xcf,0x86,0xd5,0x4c,0xd4,0x30,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00, + 0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00, + 0xe1,0x8f,0x5b,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8, + 0xcc,0x80,0x00,0xd3,0x3b,0xd2,0x18,0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf, + 0x89,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0xd1,0x0f,0x10, + 0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff, + 0xcf,0x89,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc, + 0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x81,0x00,0xe1,0x99,0x5b,0x10,0x09,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0x01,0xff, + 0xc2,0xb4,0x00,0xe0,0x0c,0x68,0xcf,0x86,0xe5,0x23,0x02,0xe4,0x25,0x01,0xe3,0x85, + 0x5e,0xd2,0x2a,0xe1,0x5f,0x5c,0xe0,0xdd,0x5b,0xcf,0x86,0xe5,0xbb,0x5b,0x94,0x1b, + 0xe3,0xa4,0x5b,0x92,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01, + 0xff,0xe2,0x80,0x83,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd1,0xd6,0xd0,0x46,0xcf, + 0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04,0x01, + 0x00,0x10,0x07,0x01,0xff,0xcf,0x89,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01,0x00, + 0x10,0x06,0x01,0xff,0x6b,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x01,0x00,0xe3,0x25, + 0x5d,0x92,0x10,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0x8e,0x00,0x01, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x0a,0xe4,0x42,0x5d,0x63,0x2d,0x5d,0x06,0x00,0x94, + 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb0,0x00,0x01, + 0xff,0xe2,0x85,0xb1,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb2,0x00,0x01,0xff,0xe2, + 0x85,0xb3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb4,0x00,0x01,0xff,0xe2, + 0x85,0xb5,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb6,0x00,0x01,0xff,0xe2,0x85,0xb7, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb8,0x00,0x01,0xff,0xe2, + 0x85,0xb9,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xba,0x00,0x01,0xff,0xe2,0x85,0xbb, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xbc,0x00,0x01,0xff,0xe2,0x85,0xbd, + 0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xbe,0x00,0x01,0xff,0xe2,0x85,0xbf,0x00,0x01, + 0x00,0xe0,0x34,0x5d,0xcf,0x86,0xe5,0x13,0x5d,0xe4,0xf2,0x5c,0xe3,0xe1,0x5c,0xe2, + 0xd4,0x5c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0xff,0xe2,0x86,0x84,0x00, + 0xe3,0x23,0x61,0xe2,0xf0,0x60,0xd1,0x0c,0xe0,0x9d,0x60,0xcf,0x86,0x65,0x7e,0x60, + 0x01,0x00,0xd0,0x62,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x18, + 0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x90,0x00, + 0x01,0xff,0xe2,0x93,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93, + 0x92,0x00,0x01,0xff,0xe2,0x93,0x93,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x94,0x00, + 0x01,0xff,0xe2,0x93,0x95,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x96,0x00, + 0x01,0xff,0xe2,0x93,0x97,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x98,0x00,0x01,0xff, + 0xe2,0x93,0x99,0x00,0xcf,0x86,0xe5,0x57,0x60,0x94,0x80,0xd3,0x40,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x9a,0x00,0x01,0xff,0xe2,0x93,0x9b,0x00,0x10, + 0x08,0x01,0xff,0xe2,0x93,0x9c,0x00,0x01,0xff,0xe2,0x93,0x9d,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe2,0x93,0x9e,0x00,0x01,0xff,0xe2,0x93,0x9f,0x00,0x10,0x08,0x01, + 0xff,0xe2,0x93,0xa0,0x00,0x01,0xff,0xe2,0x93,0xa1,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe2,0x93,0xa2,0x00,0x01,0xff,0xe2,0x93,0xa3,0x00,0x10,0x08,0x01, + 0xff,0xe2,0x93,0xa4,0x00,0x01,0xff,0xe2,0x93,0xa5,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe2,0x93,0xa6,0x00,0x01,0xff,0xe2,0x93,0xa7,0x00,0x10,0x08,0x01,0xff,0xe2, + 0x93,0xa8,0x00,0x01,0xff,0xe2,0x93,0xa9,0x00,0x01,0x00,0xd4,0x0c,0xe3,0x33,0x62, + 0xe2,0x2c,0x62,0xcf,0x06,0x04,0x00,0xe3,0x0c,0x65,0xe2,0xff,0x63,0xe1,0x2e,0x02, + 0xe0,0x84,0x01,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x08,0xff,0xe2,0xb0,0xb0,0x00,0x08,0xff,0xe2,0xb0,0xb1,0x00,0x10,0x08, + 0x08,0xff,0xe2,0xb0,0xb2,0x00,0x08,0xff,0xe2,0xb0,0xb3,0x00,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb0,0xb4,0x00,0x08,0xff,0xe2,0xb0,0xb5,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb0,0xb6,0x00,0x08,0xff,0xe2,0xb0,0xb7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb0,0xb8,0x00,0x08,0xff,0xe2,0xb0,0xb9,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb0,0xba,0x00,0x08,0xff,0xe2,0xb0,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb0,0xbc,0x00,0x08,0xff,0xe2,0xb0,0xbd,0x00,0x10,0x08,0x08,0xff,0xe2,0xb0, + 0xbe,0x00,0x08,0xff,0xe2,0xb0,0xbf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb1,0x80,0x00,0x08,0xff,0xe2,0xb1,0x81,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x82,0x00,0x08,0xff,0xe2,0xb1,0x83,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x84,0x00,0x08,0xff,0xe2,0xb1,0x85,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x86,0x00,0x08,0xff,0xe2,0xb1,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x88,0x00,0x08,0xff,0xe2,0xb1,0x89,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x8a,0x00,0x08,0xff,0xe2,0xb1,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x8c,0x00,0x08,0xff,0xe2,0xb1,0x8d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x8e,0x00, + 0x08,0xff,0xe2,0xb1,0x8f,0x00,0x94,0x7c,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb1,0x90,0x00,0x08,0xff,0xe2,0xb1,0x91,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x92,0x00,0x08,0xff,0xe2,0xb1,0x93,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x94,0x00,0x08,0xff,0xe2,0xb1,0x95,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x96,0x00,0x08,0xff,0xe2,0xb1,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x98,0x00,0x08,0xff,0xe2,0xb1,0x99,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x9a,0x00,0x08,0xff,0xe2,0xb1,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x9c,0x00,0x08,0xff,0xe2,0xb1,0x9d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x9e,0x00, + 0x00,0x00,0x08,0x00,0xcf,0x86,0xd5,0x07,0x64,0xef,0x61,0x08,0x00,0xd4,0x63,0xd3, + 0x32,0xd2,0x1b,0xd1,0x0c,0x10,0x08,0x09,0xff,0xe2,0xb1,0xa1,0x00,0x09,0x00,0x10, + 0x07,0x09,0xff,0xc9,0xab,0x00,0x09,0xff,0xe1,0xb5,0xbd,0x00,0xd1,0x0b,0x10,0x07, + 0x09,0xff,0xc9,0xbd,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xa8, + 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xaa,0x00,0x10, + 0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xac,0x00,0xd1,0x0b,0x10,0x04,0x09,0x00,0x0a, + 0xff,0xc9,0x91,0x00,0x10,0x07,0x0a,0xff,0xc9,0xb1,0x00,0x0a,0xff,0xc9,0x90,0x00, + 0xd3,0x27,0xd2,0x17,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xc9,0x92,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xe2,0xb1,0xb3,0x00,0x0a,0x00,0x91,0x0c,0x10,0x04,0x09,0x00,0x09, + 0xff,0xe2,0xb1,0xb6,0x00,0x09,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10, + 0x07,0x0b,0xff,0xc8,0xbf,0x00,0x0b,0xff,0xc9,0x80,0x00,0xe0,0x83,0x01,0xcf,0x86, + 0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, + 0x81,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x83,0x00,0x08,0x00,0xd1,0x0c, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2, + 0x87,0x00,0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x89,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8f,0x00, + 0x08,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x91,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x97,0x00, + 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x99,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb2,0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x9f,0x00,0x08,0x00, + 0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa1,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0xa5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa7,0x00, + 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa9,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0xab,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb2,0xad,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xaf,0x00,0x08,0x00, + 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb1,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0xb3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb2,0xb5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb7,0x00,0x08,0x00, + 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb9,0x00,0x08,0x00,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0xbb,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, + 0xbd,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xbf,0x00,0x08,0x00,0xcf,0x86, + 0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3, + 0x81,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x83,0x00,0x08,0x00,0xd1,0x0c, + 0x10,0x08,0x08,0xff,0xe2,0xb3,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3, + 0x87,0x00,0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x89,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb3,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8f,0x00, + 0x08,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x91,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb3,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x97,0x00, + 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x99,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb3,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb3,0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x9f,0x00,0x08,0x00, + 0xd4,0x3b,0xd3,0x1c,0x92,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa1,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa3,0x00,0x08,0x00,0x08,0x00,0xd2,0x10, + 0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x0b,0xff,0xe2,0xb3,0xac,0x00,0xe1,0x3b, + 0x5f,0x10,0x04,0x0b,0x00,0x0b,0xff,0xe2,0xb3,0xae,0x00,0xe3,0x40,0x5f,0x92,0x10, + 0x51,0x04,0x0b,0xe6,0x10,0x08,0x0d,0xff,0xe2,0xb3,0xb3,0x00,0x0d,0x00,0x00,0x00, + 0xe2,0x98,0x08,0xd1,0x0b,0xe0,0x11,0x67,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe0,0x65, + 0x6c,0xcf,0x86,0xe5,0xa7,0x05,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x0c,0xe2,0xf8, + 0x67,0xe1,0x8f,0x67,0xcf,0x06,0x04,0x00,0xe2,0xdb,0x01,0xe1,0x26,0x01,0xd0,0x09, + 0xcf,0x86,0x65,0xf4,0x67,0x0a,0x00,0xcf,0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2, + 0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a, + 0xff,0xea,0x99,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x85, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1, + 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x99,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x8d,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1, + 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x99,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x95,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x97,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x99,0x99,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x9b, + 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x9d,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xea,0x99,0x9f,0x00,0x0a,0x00,0xe4,0x5d,0x67,0xd3,0x30,0xd2,0x18, + 0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x99,0xa1,0x00,0x0c,0x00,0x10,0x08,0x0a,0xff, + 0xea,0x99,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0xa5,0x00, + 0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x0a,0xff,0xea,0x99,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99, + 0xab,0x00,0x0a,0x00,0xe1,0x0c,0x67,0x10,0x08,0x0a,0xff,0xea,0x99,0xad,0x00,0x0a, + 0x00,0xe0,0x35,0x67,0xcf,0x86,0x95,0xab,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x0a,0xff,0xea,0x9a,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a, + 0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x85,0x00,0x0a,0x00, + 0x10,0x08,0x0a,0xff,0xea,0x9a,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8b,0x00, + 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8d,0x00,0x0a,0x00,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x93,0x00, + 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x95,0x00,0x0a,0x00,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x97,0x00,0x0a,0x00,0xe2,0x92,0x66,0xd1,0x0c,0x10,0x08,0x10, + 0xff,0xea,0x9a,0x99,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9a,0x9b,0x00,0x10, + 0x00,0x0b,0x00,0xe1,0x10,0x02,0xd0,0xb9,0xcf,0x86,0xd5,0x07,0x64,0x9e,0x66,0x08, + 0x00,0xd4,0x58,0xd3,0x28,0xd2,0x10,0x51,0x04,0x09,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x9c,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa5,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9c,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xab, + 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xad,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xea,0x9c,0xaf,0x00,0x0a,0x00,0xd3,0x28,0xd2,0x10,0x51,0x04,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, + 0xff,0xea,0x9c,0xb5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb7,0x00,0x0a, + 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb9,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xea,0x9c,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, + 0x9c,0xbd,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xbf,0x00,0x0a,0x00,0xcf, + 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, + 0x9d,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x83,0x00,0x0a,0x00,0xd1, + 0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x85,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x9d,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x89, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9d,0x8d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8f, + 0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x91, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9d,0x95,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x97, + 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x99,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, + 0xff,0xea,0x9d,0x9d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9f,0x00,0x0a, + 0x00,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa1, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9d,0xa5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa7, + 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa9,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xab,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, + 0xff,0xea,0x9d,0xad,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xaf,0x00,0x0a, + 0x00,0x53,0x04,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea, + 0x9d,0xba,0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9d,0xbc,0x00,0xd1,0x0c,0x10, + 0x04,0x0a,0x00,0x0a,0xff,0xe1,0xb5,0xb9,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xbf, + 0x00,0x0a,0x00,0xe0,0x71,0x01,0xcf,0x86,0xd5,0xa6,0xd4,0x4e,0xd3,0x30,0xd2,0x18, + 0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff, + 0xea,0x9e,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x85,0x00, + 0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9e,0x87,0x00,0x0a,0x00,0xd2,0x10,0x51,0x04, + 0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9e,0x8c,0x00,0xe1,0x9a,0x64,0x10, + 0x04,0x0a,0x00,0x0c,0xff,0xc9,0xa5,0x00,0xd3,0x28,0xd2,0x18,0xd1,0x0c,0x10,0x08, + 0x0c,0xff,0xea,0x9e,0x91,0x00,0x0c,0x00,0x10,0x08,0x0d,0xff,0xea,0x9e,0x93,0x00, + 0x0d,0x00,0x51,0x04,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x97,0x00,0x10,0x00, + 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e,0x99,0x00,0x10,0x00,0x10,0x08, + 0x10,0xff,0xea,0x9e,0x9b,0x00,0x10,0x00,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e, + 0x9d,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x9f,0x00,0x10,0x00,0xd4,0x63, + 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa1,0x00,0x0c,0x00, + 0x10,0x08,0x0c,0xff,0xea,0x9e,0xa3,0x00,0x0c,0x00,0xd1,0x0c,0x10,0x08,0x0c,0xff, + 0xea,0x9e,0xa5,0x00,0x0c,0x00,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa7,0x00,0x0c,0x00, + 0xd2,0x1a,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa9,0x00,0x0c,0x00,0x10,0x07, + 0x0d,0xff,0xc9,0xa6,0x00,0x10,0xff,0xc9,0x9c,0x00,0xd1,0x0e,0x10,0x07,0x10,0xff, + 0xc9,0xa1,0x00,0x10,0xff,0xc9,0xac,0x00,0x10,0x07,0x12,0xff,0xc9,0xaa,0x00,0x14, + 0x00,0xd3,0x35,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x10,0xff,0xca,0x9e,0x00,0x10,0xff, + 0xca,0x87,0x00,0x10,0x07,0x11,0xff,0xca,0x9d,0x00,0x11,0xff,0xea,0xad,0x93,0x00, + 0xd1,0x0c,0x10,0x08,0x11,0xff,0xea,0x9e,0xb5,0x00,0x11,0x00,0x10,0x08,0x11,0xff, + 0xea,0x9e,0xb7,0x00,0x11,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x14,0xff,0xea,0x9e, + 0xb9,0x00,0x14,0x00,0x10,0x08,0x15,0xff,0xea,0x9e,0xbb,0x00,0x15,0x00,0xd1,0x0c, + 0x10,0x08,0x15,0xff,0xea,0x9e,0xbd,0x00,0x15,0x00,0x10,0x08,0x15,0xff,0xea,0x9e, + 0xbf,0x00,0x15,0x00,0xcf,0x86,0xe5,0xd4,0x63,0x94,0x2f,0x93,0x2b,0xd2,0x10,0x51, + 0x04,0x00,0x00,0x10,0x08,0x15,0xff,0xea,0x9f,0x83,0x00,0x15,0x00,0xd1,0x0f,0x10, + 0x08,0x15,0xff,0xea,0x9e,0x94,0x00,0x15,0xff,0xca,0x82,0x00,0x10,0x08,0x15,0xff, + 0xe1,0xb6,0x8e,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe4,0xb4,0x66,0xd3,0x1d,0xe2, + 0x5b,0x64,0xe1,0x0a,0x64,0xe0,0xf7,0x63,0xcf,0x86,0xe5,0xd8,0x63,0x94,0x0b,0x93, + 0x07,0x62,0xc3,0x63,0x08,0x00,0x08,0x00,0x08,0x00,0xd2,0x0f,0xe1,0x5a,0x65,0xe0, + 0x27,0x65,0xcf,0x86,0x65,0x0c,0x65,0x0a,0x00,0xd1,0xab,0xd0,0x1a,0xcf,0x86,0xe5, + 0x17,0x66,0xe4,0xfa,0x65,0xe3,0xe1,0x65,0xe2,0xd4,0x65,0x91,0x08,0x10,0x04,0x00, + 0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x0b,0x93,0x07,0x62, + 0x27,0x66,0x11,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff, + 0xe1,0x8e,0xa0,0x00,0x11,0xff,0xe1,0x8e,0xa1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e, + 0xa2,0x00,0x11,0xff,0xe1,0x8e,0xa3,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, + 0xa4,0x00,0x11,0xff,0xe1,0x8e,0xa5,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa6,0x00, + 0x11,0xff,0xe1,0x8e,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, + 0xa8,0x00,0x11,0xff,0xe1,0x8e,0xa9,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xaa,0x00, + 0x11,0xff,0xe1,0x8e,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xac,0x00, + 0x11,0xff,0xe1,0x8e,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xae,0x00,0x11,0xff, + 0xe1,0x8e,0xaf,0x00,0xe0,0xb2,0x65,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb0,0x00,0x11,0xff,0xe1,0x8e, + 0xb1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb2,0x00,0x11,0xff,0xe1,0x8e,0xb3,0x00, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb4,0x00,0x11,0xff,0xe1,0x8e,0xb5,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8e,0xb6,0x00,0x11,0xff,0xe1,0x8e,0xb7,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb8,0x00,0x11,0xff,0xe1,0x8e,0xb9,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8e,0xba,0x00,0x11,0xff,0xe1,0x8e,0xbb,0x00,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8e,0xbc,0x00,0x11,0xff,0xe1,0x8e,0xbd,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8e,0xbe,0x00,0x11,0xff,0xe1,0x8e,0xbf,0x00,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0x80,0x00,0x11,0xff,0xe1,0x8f,0x81,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x82,0x00,0x11,0xff,0xe1,0x8f,0x83,0x00,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x84,0x00,0x11,0xff,0xe1,0x8f,0x85,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x86,0x00,0x11,0xff,0xe1,0x8f,0x87,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x88,0x00,0x11,0xff,0xe1,0x8f,0x89,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x8a,0x00,0x11,0xff,0xe1,0x8f,0x8b,0x00,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x8c,0x00,0x11,0xff,0xe1,0x8f,0x8d,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0x8e,0x00,0x11,0xff,0xe1,0x8f,0x8f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0x90,0x00,0x11,0xff,0xe1,0x8f,0x91,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x92,0x00,0x11,0xff,0xe1,0x8f,0x93,0x00,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x94,0x00,0x11,0xff,0xe1,0x8f,0x95,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x96,0x00,0x11,0xff,0xe1,0x8f,0x97,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x98,0x00,0x11,0xff,0xe1,0x8f,0x99,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x9a,0x00,0x11,0xff,0xe1,0x8f,0x9b,0x00,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x9c,0x00,0x11,0xff,0xe1,0x8f,0x9d,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0x9e,0x00,0x11,0xff,0xe1,0x8f,0x9f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0xa0,0x00,0x11,0xff,0xe1,0x8f,0xa1,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0xa2,0x00,0x11,0xff,0xe1,0x8f,0xa3,0x00,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0xa4,0x00,0x11,0xff,0xe1,0x8f,0xa5,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0xa6,0x00,0x11,0xff,0xe1,0x8f,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0xa8,0x00,0x11,0xff,0xe1,0x8f,0xa9,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0xaa,0x00,0x11,0xff,0xe1,0x8f,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0xac,0x00,0x11,0xff,0xe1,0x8f,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, + 0xae,0x00,0x11,0xff,0xe1,0x8f,0xaf,0x00,0xd1,0x0c,0xe0,0xeb,0x63,0xcf,0x86,0xcf, + 0x06,0x02,0xff,0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06, + 0xcf,0x06,0x01,0x00,0xd4,0xae,0xd3,0x09,0xe2,0x54,0x64,0xcf,0x06,0x01,0x00,0xd2, + 0x27,0xe1,0x1f,0x70,0xe0,0x26,0x6e,0xcf,0x86,0xe5,0x3f,0x6d,0xe4,0xce,0x6c,0xe3, + 0x99,0x6c,0xe2,0x78,0x6c,0xe1,0x67,0x6c,0x10,0x08,0x01,0xff,0xe5,0x88,0x87,0x00, + 0x01,0xff,0xe5,0xba,0xa6,0x00,0xe1,0x74,0x74,0xe0,0xe8,0x73,0xcf,0x86,0xe5,0x22, + 0x73,0xd4,0x3b,0x93,0x37,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x01,0xff,0x66,0x66,0x00, + 0x01,0xff,0x66,0x69,0x00,0x10,0x07,0x01,0xff,0x66,0x6c,0x00,0x01,0xff,0x66,0x66, + 0x69,0x00,0xd1,0x0f,0x10,0x08,0x01,0xff,0x66,0x66,0x6c,0x00,0x01,0xff,0x73,0x74, + 0x00,0x10,0x07,0x01,0xff,0x73,0x74,0x00,0x00,0x00,0x00,0x00,0xe3,0xc8,0x72,0xd2, + 0x11,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xd5,0xb4,0xd5,0xb6,0x00, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xd5,0xb4,0xd5,0xa5,0x00,0x01,0xff,0xd5,0xb4,0xd5, + 0xab,0x00,0x10,0x09,0x01,0xff,0xd5,0xbe,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb4,0xd5, + 0xad,0x00,0xd3,0x09,0xe2,0x40,0x74,0xcf,0x06,0x01,0x00,0xd2,0x13,0xe1,0x30,0x75, + 0xe0,0xc1,0x74,0xcf,0x86,0xe5,0x9e,0x74,0x64,0x8d,0x74,0x06,0xff,0x00,0xe1,0x96, + 0x75,0xe0,0x63,0x75,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x7c, + 0xd3,0x3c,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xef,0xbd,0x81,0x00, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x82,0x00,0x01,0xff,0xef,0xbd,0x83,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x84,0x00,0x01,0xff,0xef,0xbd,0x85,0x00,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x86,0x00,0x01,0xff,0xef,0xbd,0x87,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x88,0x00,0x01,0xff,0xef,0xbd,0x89,0x00,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x8a,0x00,0x01,0xff,0xef,0xbd,0x8b,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x8c,0x00,0x01,0xff,0xef,0xbd,0x8d,0x00,0x10,0x08,0x01,0xff, + 0xef,0xbd,0x8e,0x00,0x01,0xff,0xef,0xbd,0x8f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x90,0x00,0x01,0xff,0xef,0xbd,0x91,0x00,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x92,0x00,0x01,0xff,0xef,0xbd,0x93,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x94,0x00,0x01,0xff,0xef,0xbd,0x95,0x00,0x10,0x08,0x01,0xff, + 0xef,0xbd,0x96,0x00,0x01,0xff,0xef,0xbd,0x97,0x00,0x92,0x1c,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x98,0x00,0x01,0xff,0xef,0xbd,0x99,0x00,0x10,0x08,0x01,0xff, + 0xef,0xbd,0x9a,0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0x87,0xb3,0xe1,0x60,0xb0,0xe0, + 0xdd,0xae,0xcf,0x86,0xe5,0x81,0x9b,0xc4,0xe3,0xc1,0x07,0xe2,0x62,0x06,0xe1,0x11, + 0x86,0xe0,0x09,0x05,0xcf,0x86,0xe5,0xfb,0x02,0xd4,0x1c,0xe3,0x7f,0x76,0xe2,0xd6, + 0x75,0xe1,0xb1,0x75,0xe0,0x8a,0x75,0xcf,0x86,0xe5,0x57,0x75,0x94,0x07,0x63,0x42, + 0x75,0x07,0x00,0x07,0x00,0xe3,0x2b,0x78,0xe2,0xf0,0x77,0xe1,0x77,0x01,0xe0,0x88, + 0x77,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xa8,0x00,0x05,0xff,0xf0,0x90,0x90,0xa9,0x00,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xaa,0x00,0x05,0xff,0xf0,0x90,0x90,0xab,0x00,0xd1,0x12, + 0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xac,0x00,0x05,0xff,0xf0,0x90,0x90,0xad,0x00, + 0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xae,0x00,0x05,0xff,0xf0,0x90,0x90,0xaf,0x00, + 0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb0,0x00,0x05,0xff,0xf0, + 0x90,0x90,0xb1,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb2,0x00,0x05,0xff,0xf0, + 0x90,0x90,0xb3,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb4,0x00,0x05, + 0xff,0xf0,0x90,0x90,0xb5,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb6,0x00,0x05, + 0xff,0xf0,0x90,0x90,0xb7,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x90,0xb8,0x00,0x05,0xff,0xf0,0x90,0x90,0xb9,0x00,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x90,0xba,0x00,0x05,0xff,0xf0,0x90,0x90,0xbb,0x00,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xbc,0x00,0x05,0xff,0xf0,0x90,0x90,0xbd,0x00,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xbe,0x00,0x05,0xff,0xf0,0x90,0x90,0xbf,0x00,0xd2,0x24, + 0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x80,0x00,0x05,0xff,0xf0,0x90,0x91, + 0x81,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x82,0x00,0x05,0xff,0xf0,0x90,0x91, + 0x83,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x84,0x00,0x05,0xff,0xf0, + 0x90,0x91,0x85,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x86,0x00,0x05,0xff,0xf0, + 0x90,0x91,0x87,0x00,0x94,0x4c,0x93,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x91,0x88,0x00,0x05,0xff,0xf0,0x90,0x91,0x89,0x00,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x91,0x8a,0x00,0x05,0xff,0xf0,0x90,0x91,0x8b,0x00,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x91,0x8c,0x00,0x05,0xff,0xf0,0x90,0x91,0x8d,0x00,0x10,0x09, + 0x07,0xff,0xf0,0x90,0x91,0x8e,0x00,0x07,0xff,0xf0,0x90,0x91,0x8f,0x00,0x05,0x00, + 0x05,0x00,0xd0,0xa0,0xcf,0x86,0xd5,0x07,0x64,0x30,0x76,0x07,0x00,0xd4,0x07,0x63, + 0x3d,0x76,0x07,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90, + 0x93,0x98,0x00,0x12,0xff,0xf0,0x90,0x93,0x99,0x00,0x10,0x09,0x12,0xff,0xf0,0x90, + 0x93,0x9a,0x00,0x12,0xff,0xf0,0x90,0x93,0x9b,0x00,0xd1,0x12,0x10,0x09,0x12,0xff, + 0xf0,0x90,0x93,0x9c,0x00,0x12,0xff,0xf0,0x90,0x93,0x9d,0x00,0x10,0x09,0x12,0xff, + 0xf0,0x90,0x93,0x9e,0x00,0x12,0xff,0xf0,0x90,0x93,0x9f,0x00,0xd2,0x24,0xd1,0x12, + 0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa0,0x00,0x12,0xff,0xf0,0x90,0x93,0xa1,0x00, + 0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa2,0x00,0x12,0xff,0xf0,0x90,0x93,0xa3,0x00, + 0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa4,0x00,0x12,0xff,0xf0,0x90,0x93, + 0xa5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa6,0x00,0x12,0xff,0xf0,0x90,0x93, + 0xa7,0x00,0xcf,0x86,0xe5,0xc6,0x75,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x12,0xff,0xf0,0x90,0x93,0xa8,0x00,0x12,0xff,0xf0,0x90,0x93,0xa9,0x00,0x10, + 0x09,0x12,0xff,0xf0,0x90,0x93,0xaa,0x00,0x12,0xff,0xf0,0x90,0x93,0xab,0x00,0xd1, + 0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xac,0x00,0x12,0xff,0xf0,0x90,0x93,0xad, + 0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xae,0x00,0x12,0xff,0xf0,0x90,0x93,0xaf, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb0,0x00,0x12,0xff, + 0xf0,0x90,0x93,0xb1,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb2,0x00,0x12,0xff, + 0xf0,0x90,0x93,0xb3,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb4,0x00, + 0x12,0xff,0xf0,0x90,0x93,0xb5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb6,0x00, + 0x12,0xff,0xf0,0x90,0x93,0xb7,0x00,0x93,0x28,0x92,0x24,0xd1,0x12,0x10,0x09,0x12, + 0xff,0xf0,0x90,0x93,0xb8,0x00,0x12,0xff,0xf0,0x90,0x93,0xb9,0x00,0x10,0x09,0x12, + 0xff,0xf0,0x90,0x93,0xba,0x00,0x12,0xff,0xf0,0x90,0x93,0xbb,0x00,0x00,0x00,0x12, + 0x00,0xd4,0x1f,0xe3,0xdf,0x76,0xe2,0x6a,0x76,0xe1,0x09,0x76,0xe0,0xea,0x75,0xcf, + 0x86,0xe5,0xb7,0x75,0x94,0x0a,0xe3,0xa2,0x75,0x62,0x99,0x75,0x07,0x00,0x07,0x00, + 0xe3,0xde,0x78,0xe2,0xaf,0x78,0xd1,0x09,0xe0,0x4c,0x78,0xcf,0x06,0x0b,0x00,0xe0, + 0x7f,0x78,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x80,0x00,0x11,0xff,0xf0,0x90,0xb3,0x81,0x00,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x82,0x00,0x11,0xff,0xf0,0x90,0xb3,0x83,0x00,0xd1, + 0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x84,0x00,0x11,0xff,0xf0,0x90,0xb3,0x85, + 0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x86,0x00,0x11,0xff,0xf0,0x90,0xb3,0x87, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x88,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x89,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8a,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x8b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8c,0x00, + 0x11,0xff,0xf0,0x90,0xb3,0x8d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8e,0x00, + 0x11,0xff,0xf0,0x90,0xb3,0x8f,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0x90,0x00,0x11,0xff,0xf0,0x90,0xb3,0x91,0x00,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0x92,0x00,0x11,0xff,0xf0,0x90,0xb3,0x93,0x00,0xd1,0x12,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x94,0x00,0x11,0xff,0xf0,0x90,0xb3,0x95,0x00,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x96,0x00,0x11,0xff,0xf0,0x90,0xb3,0x97,0x00,0xd2, + 0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x98,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0x99,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9a,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9c,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x9d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9e,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x9f,0x00,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0xa0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa1,0x00,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0xa2,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa3,0x00,0xd1,0x12,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0xa4,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa5,0x00,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0xa6,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa7,0x00,0xd2, + 0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xa8,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0xa9,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xaa,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0xab,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xac,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0xad,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xae,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0xaf,0x00,0x93,0x23,0x92,0x1f,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0, + 0x90,0xb3,0xb0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xb1,0x00,0x10,0x09,0x11,0xff,0xf0, + 0x90,0xb3,0xb2,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x15,0xe4,0x91, + 0x7b,0xe3,0x9b,0x79,0xe2,0x94,0x78,0xe1,0xe4,0x77,0xe0,0x9d,0x77,0xcf,0x06,0x0c, + 0x00,0xe4,0xeb,0x7e,0xe3,0x44,0x7e,0xe2,0xed,0x7d,0xd1,0x0c,0xe0,0xb2,0x7d,0xcf, + 0x86,0x65,0x93,0x7d,0x14,0x00,0xe0,0xb6,0x7d,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4, + 0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x80,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x81,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x82,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x83,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3, + 0x84,0x00,0x10,0xff,0xf0,0x91,0xa3,0x85,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3, + 0x86,0x00,0x10,0xff,0xf0,0x91,0xa3,0x87,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x88,0x00,0x10,0xff,0xf0,0x91,0xa3,0x89,0x00,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x8a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8b,0x00,0xd1,0x12,0x10, + 0x09,0x10,0xff,0xf0,0x91,0xa3,0x8c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8d,0x00,0x10, + 0x09,0x10,0xff,0xf0,0x91,0xa3,0x8e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8f,0x00,0xd3, + 0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x90,0x00,0x10,0xff, + 0xf0,0x91,0xa3,0x91,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x92,0x00,0x10,0xff, + 0xf0,0x91,0xa3,0x93,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x94,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x95,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x96,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x97,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0, + 0x91,0xa3,0x98,0x00,0x10,0xff,0xf0,0x91,0xa3,0x99,0x00,0x10,0x09,0x10,0xff,0xf0, + 0x91,0xa3,0x9a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x9c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9d,0x00,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x9e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9f,0x00,0xd1,0x11,0xe0, + 0x12,0x81,0xcf,0x86,0xe5,0x09,0x81,0xe4,0xd2,0x80,0xcf,0x06,0x00,0x00,0xe0,0xdb, + 0x82,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x09,0xe3,0x10,0x81,0xcf,0x06, + 0x0c,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xe2,0x3b,0x82,0xe1,0x16,0x82,0xd0,0x06, + 0xcf,0x06,0x00,0x00,0xcf,0x86,0xa5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1, + 0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa1, + 0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa3, + 0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa4,0x00,0x14,0xff,0xf0,0x96, + 0xb9,0xa5,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa6,0x00,0x14,0xff,0xf0,0x96, + 0xb9,0xa7,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa8,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xa9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xaa,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xab,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9, + 0xac,0x00,0x14,0xff,0xf0,0x96,0xb9,0xad,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9, + 0xae,0x00,0x14,0xff,0xf0,0x96,0xb9,0xaf,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x14,0xff,0xf0,0x96,0xb9,0xb0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb1,0x00,0x10, + 0x09,0x14,0xff,0xf0,0x96,0xb9,0xb2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb3,0x00,0xd1, + 0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb4,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb5, + 0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb6,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb7, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb8,0x00,0x14,0xff, + 0xf0,0x96,0xb9,0xb9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xba,0x00,0x14,0xff, + 0xf0,0x96,0xb9,0xbb,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbc,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xbd,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbe,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xbf,0x00,0x14,0x00,0xd2,0x14,0xe1,0x25,0x82,0xe0,0x1c, + 0x82,0xcf,0x86,0xe5,0xdd,0x81,0xe4,0x9a,0x81,0xcf,0x06,0x12,0x00,0xd1,0x0b,0xe0, + 0x51,0x83,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0x95,0x8b,0xcf,0x86,0xd5,0x22,0xe4, + 0xd0,0x88,0xe3,0x93,0x88,0xe2,0x38,0x88,0xe1,0x31,0x88,0xe0,0x2a,0x88,0xcf,0x86, + 0xe5,0xfb,0x87,0xe4,0xe2,0x87,0x93,0x07,0x62,0xd1,0x87,0x12,0xe6,0x12,0xe6,0xe4, + 0x36,0x89,0xe3,0x2f,0x89,0xd2,0x09,0xe1,0xb8,0x88,0xcf,0x06,0x10,0x00,0xe1,0x1f, + 0x89,0xe0,0xec,0x88,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1, + 0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa3, + 0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa5, + 0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa6,0x00,0x12,0xff,0xf0,0x9e, + 0xa4,0xa7,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa8,0x00,0x12,0xff,0xf0,0x9e, + 0xa4,0xa9,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xaa,0x00, + 0x12,0xff,0xf0,0x9e,0xa4,0xab,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xac,0x00, + 0x12,0xff,0xf0,0x9e,0xa4,0xad,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4, + 0xae,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xaf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4, + 0xb0,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb1,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb3,0x00,0x10, + 0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb5,0x00,0xd1, + 0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb6,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb7, + 0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb8,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb9, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xba,0x00,0x12,0xff, + 0xf0,0x9e,0xa4,0xbb,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbc,0x00,0x12,0xff, + 0xf0,0x9e,0xa4,0xbd,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbe,0x00, + 0x12,0xff,0xf0,0x9e,0xa4,0xbf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa5,0x80,0x00, + 0x12,0xff,0xf0,0x9e,0xa5,0x81,0x00,0x94,0x1e,0x93,0x1a,0x92,0x16,0x91,0x12,0x10, + 0x09,0x12,0xff,0xf0,0x9e,0xa5,0x82,0x00,0x12,0xff,0xf0,0x9e,0xa5,0x83,0x00,0x12, + 0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + /* nfdi_c0100 */ + 0x57,0x04,0x01,0x00,0xc6,0xe5,0xac,0x13,0xe4,0x41,0x0c,0xe3,0x7a,0x07,0xe2,0xf3, + 0x01,0xc1,0xd0,0x1f,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x53,0x04,0x01,0x00, + 0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x04,0x01,0x00,0x01,0xff,0x00,0x01,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0xe4,0xd4,0x7c,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x41,0xcc,0x80,0x00,0x01,0xff,0x41,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x41, + 0xcc,0x82,0x00,0x01,0xff,0x41,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x41, + 0xcc,0x88,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x43, + 0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x80,0x00,0x01, + 0xff,0x45,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x82,0x00,0x01,0xff,0x45, + 0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x80,0x00,0x01,0xff,0x49, + 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x82,0x00,0x01,0xff,0x49,0xcc,0x88, + 0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x4e,0xcc,0x83, + 0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x80,0x00,0x01,0xff,0x4f,0xcc,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x82,0x00,0x01,0xff,0x4f,0xcc,0x83,0x00,0x10, + 0x08,0x01,0xff,0x4f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01, + 0x00,0x01,0xff,0x55,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x81,0x00,0x01, + 0xff,0x55,0xcc,0x82,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x88,0x00,0x01, + 0xff,0x59,0xcc,0x81,0x00,0x01,0x00,0xd4,0x7c,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x80, + 0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x82,0x00,0x01, + 0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x80,0x00,0x01, + 0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00,0x01,0xff,0x69, + 0xcc,0x88,0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6e, + 0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x81, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82,0x00,0x01,0xff,0x6f,0xcc,0x83, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10, + 0x04,0x01,0x00,0x01,0xff,0x75,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x81, + 0x00,0x01,0xff,0x75,0xcc,0x82,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x88, + 0x00,0x01,0xff,0x79,0xcc,0x81,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x79,0xcc,0x88, + 0x00,0xe1,0x9a,0x03,0xe0,0xd3,0x01,0xcf,0x86,0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84, + 0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x86,0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa8,0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10, + 0x08,0x01,0xff,0x43,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x43,0xcc,0x82,0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10, + 0x08,0x01,0xff,0x43,0xcc,0x87,0x00,0x01,0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x43,0xcc,0x8c,0x00,0x01,0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x44,0xcc,0x8c,0x00,0x01,0xff,0x64,0xcc,0x8c,0x00,0xd3,0x34,0xd2,0x14,0x51, + 0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x84,0x00,0x01,0xff,0x65,0xcc,0x84, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0x86, + 0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0xa8,0x00,0x01,0xff,0x65,0xcc,0xa8, + 0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82,0x00,0x10, + 0x08,0x01,0xff,0x47,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4,0x74,0xd3, + 0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x87,0x00,0x01,0xff,0x67, + 0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0xa7,0x00,0x01,0xff,0x67,0xcc,0xa7, + 0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0x82,0x00,0x01,0xff,0x68,0xcc,0x82, + 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x83,0x00,0x01, + 0xff,0x69,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x84,0x00,0x01,0xff,0x69, + 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x86,0x00,0x01,0xff,0x69, + 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8, + 0x00,0xd3,0x30,0xd2,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x49,0xcc,0x87,0x00,0x01, + 0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4a,0xcc,0x82,0x00,0x01,0xff,0x6a, + 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7, + 0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x4c,0xcc,0x81,0x00,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff,0x4c,0xcc,0xa7,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff,0x4c,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x6c,0xcc,0x8c,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x60,0xd3,0x30,0xd2, + 0x10,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x4e,0xcc,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x81,0x00,0x01,0xff,0x4e,0xcc,0xa7,0x00,0x10, + 0x08,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x01,0xff,0x4e,0xcc,0x8c,0x00,0xd2,0x10,0x91, + 0x0c,0x10,0x08,0x01,0xff,0x6e,0xcc,0x8c,0x00,0x01,0x00,0x01,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x4f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0x84,0x00,0x10,0x08,0x01, + 0xff,0x4f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00,0xd3,0x34,0xd2,0x14,0x91, + 0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8b,0x00,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81, + 0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x53,0xcc,0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10, + 0x08,0x01,0xff,0x53,0xcc,0xa7,0x00,0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x74,0xd3, + 0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x8c,0x00,0x01,0xff,0x73, + 0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7, + 0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c, + 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x83,0x00,0x01, + 0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x84,0x00,0x01,0xff,0x75, + 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x86,0x00,0x01,0xff,0x75, + 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x8a,0x00,0x01,0xff,0x75,0xcc,0x8a, + 0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x8b,0x00,0x01, + 0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa8,0x00,0x01,0xff,0x75, + 0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x82,0x00,0x01,0xff,0x77, + 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x82,0x00,0x01,0xff,0x79,0xcc,0x82, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x59,0xcc,0x88,0x00,0x01,0xff,0x5a, + 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff,0x5a,0xcc,0x87, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff,0x5a,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0x00,0xd0,0x4a,0xcf,0x86,0x55, + 0x04,0x01,0x00,0xd4,0x2c,0xd3,0x18,0x92,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0x4f, + 0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01, + 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x55,0xcc,0x9b,0x00,0x93, + 0x14,0x92,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x75,0xcc,0x9b,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xb4,0xd4,0x24,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x41,0xcc,0x8c,0x00,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff,0x49,0xcc,0x8c,0x00,0xd3,0x46,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x4f,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x8c,0x00,0xd1, + 0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x84, + 0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x55,0xcc,0x88, + 0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81, + 0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88, + 0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01, + 0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x88, + 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x80,0xd3,0x3a,0xd2, + 0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61, + 0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0x86,0xcc,0x84,0x00,0x01,0xff, + 0xc3,0xa6,0xcc,0x84,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0x8c, + 0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b, + 0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa8, + 0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa8, + 0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc6, + 0xb7,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0xd3,0x24,0xd2,0x10,0x91, + 0x0c,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00,0x01,0x00,0x01,0x00,0x91,0x10,0x10, + 0x08,0x01,0xff,0x47,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x04,0x00,0xd2, + 0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x4e,0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80, + 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x8a,0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a, + 0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xc3,0x86,0xcc,0x81,0x00,0x01,0xff, + 0xc3,0xa6,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xc3,0x98,0xcc,0x81,0x00,0x01,0xff, + 0xc3,0xb8,0xcc,0x81,0x00,0xe2,0x07,0x02,0xe1,0xae,0x01,0xe0,0x93,0x01,0xcf,0x86, + 0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc, + 0x8f,0x00,0x01,0xff,0x61,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x91,0x00, + 0x01,0xff,0x61,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x8f,0x00, + 0x01,0xff,0x65,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x91,0x00,0x01,0xff, + 0x65,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x8f,0x00, + 0x01,0xff,0x69,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x91,0x00,0x01,0xff, + 0x69,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8f,0x00,0x01,0xff, + 0x6f,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc, + 0x91,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x8f,0x00, + 0x01,0xff,0x72,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0x91,0x00,0x01,0xff, + 0x72,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x8f,0x00,0x01,0xff, + 0x75,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc, + 0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x04,0xff,0x53,0xcc,0xa6,0x00,0x04,0xff, + 0x73,0xcc,0xa6,0x00,0x10,0x08,0x04,0xff,0x54,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc, + 0xa6,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04,0xff,0x48,0xcc,0x8c,0x00,0x04,0xff, + 0x68,0xcc,0x8c,0x00,0xd4,0x68,0xd3,0x20,0xd2,0x0c,0x91,0x08,0x10,0x04,0x06,0x00, + 0x07,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04,0xff,0x41,0xcc,0x87,0x00, + 0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x45,0xcc, + 0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x88,0xcc, + 0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10,0x0a,0x04,0xff, + 0x4f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x10,0x08, + 0x04,0xff,0x4f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0x93,0x30,0xd2,0x24, + 0xd1,0x14,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x87,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc, + 0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x59,0xcc,0x84,0x00,0x04,0xff,0x79,0xcc, + 0x84,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0xcf,0x86, + 0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x08,0x00,0x09,0x00,0x09,0x00, + 0x09,0x00,0x01,0x00,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18, + 0x53,0x04,0x01,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00, + 0x11,0x04,0x04,0x00,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01,0x00, + 0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x04,0x00,0x94,0x18,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00,0x07,0x00,0xe1,0x35,0x01,0xd0, + 0x72,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0xe6,0xd3,0x10,0x52,0x04,0x01,0xe6,0x91, + 0x08,0x10,0x04,0x01,0xe6,0x01,0xe8,0x01,0xdc,0x92,0x0c,0x51,0x04,0x01,0xdc,0x10, + 0x04,0x01,0xe8,0x01,0xd8,0x01,0xdc,0xd4,0x2c,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10, + 0x04,0x01,0xdc,0x01,0xca,0x10,0x04,0x01,0xca,0x01,0xdc,0x51,0x04,0x01,0xdc,0x10, + 0x04,0x01,0xdc,0x01,0xca,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0xca,0x01,0xdc,0x01, + 0xdc,0x01,0xdc,0xd3,0x08,0x12,0x04,0x01,0xdc,0x01,0x01,0xd2,0x0c,0x91,0x08,0x10, + 0x04,0x01,0x01,0x01,0xdc,0x01,0xdc,0x91,0x08,0x10,0x04,0x01,0xdc,0x01,0xe6,0x01, + 0xe6,0xcf,0x86,0xd5,0x7f,0xd4,0x47,0xd3,0x2e,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01, + 0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0x10,0x04,0x01,0xe6,0x01,0xff,0xcc, + 0x93,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcc,0x88,0xcc,0x81,0x00,0x01,0xf0,0x10, + 0x04,0x04,0xe6,0x04,0xdc,0xd2,0x08,0x11,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10, + 0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x04,0xdc,0x06,0xff,0x00,0xd3,0x18,0xd2,0x0c, + 0x51,0x04,0x07,0xe6,0x10,0x04,0x07,0xe6,0x07,0xdc,0x51,0x04,0x07,0xdc,0x10,0x04, + 0x07,0xdc,0x07,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe8,0x08,0xdc,0x10,0x04, + 0x08,0xdc,0x08,0xe6,0xd1,0x08,0x10,0x04,0x08,0xe9,0x07,0xea,0x10,0x04,0x07,0xea, + 0x07,0xe9,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0xea,0x10,0x04,0x04,0xe9, + 0x06,0xe6,0x06,0xe6,0x06,0xe6,0xd3,0x13,0x52,0x04,0x0a,0x00,0x91,0x0b,0x10,0x07, + 0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10, + 0x04,0x01,0x00,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x06,0x01,0xff,0x3b,0x00,0x10, + 0x00,0xd0,0xe1,0xcf,0x86,0xd5,0x7a,0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1, + 0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, + 0xce,0x91,0xcc,0x81,0x00,0x01,0xff,0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09, + 0x01,0xff,0xce,0x95,0xcc,0x81,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00,0x10,0x09, + 0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce, + 0x9f,0xcc,0x81,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0x01, + 0xff,0xce,0xa9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff, + 0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4, + 0x4a,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01, + 0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x88,0x00, + 0x01,0xff,0xce,0xa5,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13,0x91,0x0f,0x10, + 0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x39,0x53,0x04,0x01,0x00,0xd2,0x16,0x51,0x04, + 0x01,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc, + 0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf, + 0x85,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x0a,0x00,0xd3, + 0x26,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xcf,0x92,0xcc, + 0x81,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0x00,0x10, + 0x04,0x01,0x00,0x04,0x00,0xd2,0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x01,0x00,0x04, + 0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0xd4, + 0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x06, + 0x00,0x07,0x00,0x12,0x04,0x07,0x00,0x08,0x00,0xe3,0x47,0x04,0xe2,0xbe,0x02,0xe1, + 0x07,0x01,0xd0,0x8b,0xcf,0x86,0xd5,0x6c,0xd4,0x53,0xd3,0x30,0xd2,0x1f,0xd1,0x12, + 0x10,0x09,0x04,0xff,0xd0,0x95,0xcc,0x80,0x00,0x01,0xff,0xd0,0x95,0xcc,0x88,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x93,0xcc,0x81,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x01,0xff,0xd0,0x86,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xd0,0x9a,0xcc,0x81,0x00,0x04,0xff,0xd0,0x98,0xcc,0x80,0x00, + 0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x86,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0x92, + 0x11,0x91,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x98,0xcc,0x86,0x00,0x01,0x00, + 0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x11,0x91,0x0d,0x10,0x04, + 0x01,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5, + 0x57,0x54,0x04,0x01,0x00,0xd3,0x30,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0, + 0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0xd0,0xb3,0xcc,0x81,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, + 0xd1,0x96,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0, + 0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8,0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd1, + 0x83,0xcc,0x86,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x1a,0x52,0x04,0x01,0x00, + 0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb4,0xcc,0x8f,0x00,0x01,0xff,0xd1, + 0xb5,0xcc,0x8f,0x00,0x01,0x00,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x94,0x24,0xd3,0x18, + 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0x51,0x04,0x01,0xe6, + 0x10,0x04,0x01,0xe6,0x0a,0xe6,0x92,0x08,0x11,0x04,0x04,0x00,0x06,0x00,0x04,0x00, + 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xbe,0xd4,0x4a,0xd3,0x2a,0xd2,0x1a,0xd1,0x0d, + 0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x96,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0, + 0xb6,0xcc,0x86,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, + 0x06,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, + 0x06,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00, + 0x09,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x90,0xcc,0x86, + 0x00,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0x90,0xcc,0x88, + 0x00,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, + 0xd0,0x95,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0xd2,0x16,0x51,0x04, + 0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0x98,0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc, + 0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x96,0xcc,0x88,0x00,0x01,0xff,0xd0, + 0xb6,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0x97,0xcc,0x88,0x00,0x01,0xff,0xd0, + 0xb7,0xcc,0x88,0x00,0xd4,0x74,0xd3,0x3a,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09, + 0x01,0xff,0xd0,0x98,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xd0,0x98,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00, + 0x10,0x09,0x01,0xff,0xd0,0x9e,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00, + 0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0xa8,0xcc,0x88,0x00,0x01, + 0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0,0xad,0xcc,0x88, + 0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x84, + 0x00,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09, + 0x01,0xff,0xd0,0xa3,0xcc,0x88,0x00,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x10,0x09, + 0x01,0xff,0xd0,0xa3,0xcc,0x8b,0x00,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0x91,0x12, + 0x10,0x09,0x01,0xff,0xd0,0xa7,0xcc,0x88,0x00,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00, + 0x08,0x00,0x92,0x16,0x91,0x12,0x10,0x09,0x01,0xff,0xd0,0xab,0xcc,0x88,0x00,0x01, + 0xff,0xd1,0x8b,0xcc,0x88,0x00,0x09,0x00,0x09,0x00,0xd1,0x74,0xd0,0x36,0xcf,0x86, + 0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, + 0xd4,0x10,0x93,0x0c,0x52,0x04,0x0a,0x00,0x11,0x04,0x0b,0x00,0x0c,0x00,0x10,0x00, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00, + 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0xba, + 0xcf,0x86,0xd5,0x4c,0xd4,0x24,0x53,0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x14,0x00,0x01,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x10,0x00,0x10,0x04,0x10,0x00,0x0d,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x00,0x00,0x02,0xdc,0x02,0xe6,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc,0x02,0xe6, + 0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xde,0x02,0xdc,0x02,0xe6,0xd4,0x2c, + 0xd3,0x10,0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x08,0xdc,0x02,0xdc,0x02,0xdc, + 0xd2,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc,0x02,0xe6,0xd1,0x08,0x10,0x04, + 0x02,0xe6,0x02,0xde,0x10,0x04,0x02,0xe4,0x02,0xe6,0xd3,0x20,0xd2,0x10,0xd1,0x08, + 0x10,0x04,0x01,0x0a,0x01,0x0b,0x10,0x04,0x01,0x0c,0x01,0x0d,0xd1,0x08,0x10,0x04, + 0x01,0x0e,0x01,0x0f,0x10,0x04,0x01,0x10,0x01,0x11,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x01,0x12,0x01,0x13,0x10,0x04,0x09,0x13,0x01,0x14,0xd1,0x08,0x10,0x04,0x01,0x15, + 0x01,0x16,0x10,0x04,0x01,0x00,0x01,0x17,0xcf,0x86,0xd5,0x28,0x94,0x24,0x93,0x20, + 0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x18,0x10,0x04,0x01,0x19,0x01,0x00, + 0xd1,0x08,0x10,0x04,0x02,0xe6,0x08,0xdc,0x10,0x04,0x08,0x00,0x08,0x12,0x00,0x00, + 0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, + 0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x93,0x10, + 0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xe2,0xfb,0x01,0xe1,0x2b,0x01,0xd0,0xa8,0xcf,0x86,0xd5,0x55,0xd4,0x28,0xd3,0x10, + 0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x10,0x00,0x0a,0x00,0xd2,0x0c, + 0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x08,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x07,0x00,0x07,0x00,0xd3,0x0c,0x52,0x04,0x07,0xe6,0x11,0x04,0x07,0xe6,0x0a,0xe6, + 0xd2,0x10,0xd1,0x08,0x10,0x04,0x0a,0x1e,0x0a,0x1f,0x10,0x04,0x0a,0x20,0x01,0x00, + 0xd1,0x09,0x10,0x05,0x0f,0xff,0x00,0x00,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0xd4, + 0x3d,0x93,0x39,0xd2,0x1a,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x09,0x01, + 0xff,0xd8,0xa7,0xd9,0x93,0x00,0x01,0xff,0xd8,0xa7,0xd9,0x94,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xd9,0x88,0xd9,0x94,0x00,0x01,0xff,0xd8,0xa7,0xd9,0x95,0x00,0x10, + 0x09,0x01,0xff,0xd9,0x8a,0xd9,0x94,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00, + 0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x86, + 0xd5,0x5c,0xd4,0x20,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, + 0x01,0x00,0x01,0x1b,0xd1,0x08,0x10,0x04,0x01,0x1c,0x01,0x1d,0x10,0x04,0x01,0x1e, + 0x01,0x1f,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x20,0x01,0x21,0x10,0x04, + 0x01,0x22,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x07,0xdc, + 0x07,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x07,0xe6,0x08,0xe6,0x08,0xe6,0xd1,0x08, + 0x10,0x04,0x08,0xdc,0x08,0xe6,0x10,0x04,0x08,0xe6,0x0c,0xdc,0xd4,0x10,0x53,0x04, + 0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06,0x00,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x01,0x23,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x22, + 0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x08, + 0x11,0x04,0x04,0x00,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00, + 0xcf,0x86,0xd5,0x5b,0xd4,0x2e,0xd3,0x1e,0x92,0x1a,0xd1,0x0d,0x10,0x09,0x01,0xff, + 0xdb,0x95,0xd9,0x94,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xdb,0x81,0xd9,0x94,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x04,0x00,0xd3,0x19,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, + 0xdb,0x92,0xd9,0x94,0x00,0x11,0x04,0x01,0x00,0x01,0xe6,0x52,0x04,0x01,0xe6,0xd1, + 0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0xd4,0x38,0xd3, + 0x1c,0xd2,0x0c,0x51,0x04,0x01,0xe6,0x10,0x04,0x01,0xe6,0x01,0xdc,0xd1,0x08,0x10, + 0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0xd2,0x10,0xd1,0x08,0x10, + 0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0xdc,0x01,0xe6,0x91,0x08,0x10,0x04,0x01, + 0xe6,0x01,0xdc,0x07,0x00,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x04, + 0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00,0xd1,0xc8,0xd0,0x76,0xcf, + 0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04, + 0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04, + 0x00,0x04,0x24,0x04,0x00,0x04,0x00,0x04,0x00,0xd4,0x14,0x53,0x04,0x04,0x00,0x52, + 0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x07,0x00,0x07,0x00,0xd3,0x1c,0xd2, + 0x0c,0x91,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04, + 0xdc,0x04,0xe6,0x10,0x04,0x04,0xe6,0x04,0xdc,0xd2,0x0c,0x51,0x04,0x04,0xdc,0x10, + 0x04,0x04,0xe6,0x04,0xdc,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10,0x04,0x04, + 0xdc,0x04,0xe6,0xcf,0x86,0xd5,0x3c,0x94,0x38,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x04, + 0xe6,0x10,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10, + 0x04,0x04,0xdc,0x04,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10, + 0x04,0x04,0xe6,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x08, + 0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0a, + 0x00,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93, + 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x14,0x53,0x04,0x09,0x00,0x92,0x0c,0x51, + 0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xe6,0x09,0xe6,0xd3,0x10,0x92,0x0c,0x51, + 0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09, + 0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x14,0xdc,0x14, + 0x00,0xe4,0xf8,0x57,0xe3,0x45,0x3f,0xe2,0xf4,0x3e,0xe1,0xc7,0x2c,0xe0,0x21,0x10, + 0xcf,0x86,0xc5,0xe4,0x80,0x08,0xe3,0xcb,0x03,0xe2,0x61,0x01,0xd1,0x94,0xd0,0x5a, + 0xcf,0x86,0xd5,0x20,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52,0x04,0x0b,0x00,0x11,0x04, + 0x0b,0x00,0x0b,0xe6,0x92,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04,0x0b,0x00,0x0b,0xe6, + 0x0b,0xe6,0xd4,0x24,0xd3,0x10,0x52,0x04,0x0b,0xe6,0x91,0x08,0x10,0x04,0x0b,0x00, + 0x0b,0xe6,0x0b,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6,0x0b,0xe6, + 0x11,0x04,0x0b,0xe6,0x00,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04, + 0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xcf,0x86,0xd5,0x20,0x54,0x04,0x0c,0x00, + 0x53,0x04,0x0c,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0c,0xdc,0x0c,0xdc, + 0x51,0x04,0x00,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x13,0x00, + 0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd0,0x4a,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4,0x20,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0d,0x00,0x10,0x00,0x0d,0x00,0x0d,0x00,0x52,0x04,0x0d,0x00,0x91,0x08, + 0x10,0x04,0x0d,0x00,0x10,0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00, + 0x10,0x04,0x10,0x00,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x12,0x00, + 0x52,0x04,0x12,0x00,0x11,0x04,0x12,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04, + 0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x14,0xdc, + 0x12,0xe6,0x12,0xe6,0xd4,0x30,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x12,0xe6,0x10,0x04, + 0x12,0x00,0x11,0xdc,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xdc,0x0d,0xe6,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x0d,0xe6,0x91,0x08,0x10,0x04,0x0d,0xe6, + 0x0d,0xdc,0x0d,0xdc,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0x1b,0x0d,0x1c, + 0x10,0x04,0x0d,0x1d,0x0d,0xe6,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xdc,0x0d,0xe6, + 0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x10,0x04,0x0d,0xdc,0x0d,0xe6, + 0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x10,0xe6,0xe1,0x3a,0x01,0xd0,0x77,0xcf, + 0x86,0xd5,0x20,0x94,0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x01, + 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0xd4,0x1b,0x53,0x04,0x01,0x00,0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe0,0xa4,0xa8,0xe0,0xa4,0xbc,0x00,0x01,0x00,0x01,0x00,0xd3,0x26,0xd2,0x13, + 0x91,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa4,0xb0,0xe0,0xa4,0xbc,0x00,0x01, + 0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xa4,0xb3,0xe0,0xa4,0xbc,0x00,0x01,0x00, + 0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x91,0x08,0x10,0x04,0x01,0x07, + 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x8c,0xd4,0x18,0x53,0x04,0x01,0x00,0x52,0x04, + 0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x10,0x04,0x0b,0x00,0x0c,0x00, + 0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x10,0x04,0x01,0xdc, + 0x01,0xe6,0x91,0x08,0x10,0x04,0x01,0xe6,0x0b,0x00,0x0c,0x00,0xd2,0x2c,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xe0,0xa4,0x95,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0x96, + 0xe0,0xa4,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa4,0x97,0xe0,0xa4,0xbc,0x00,0x01, + 0xff,0xe0,0xa4,0x9c,0xe0,0xa4,0xbc,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa4, + 0xa1,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xa2,0xe0,0xa4,0xbc,0x00,0x10,0x0b, + 0x01,0xff,0xe0,0xa4,0xab,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xaf,0xe0,0xa4, + 0xbc,0x00,0x54,0x04,0x01,0x00,0xd3,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, + 0x0a,0x00,0x10,0x04,0x0a,0x00,0x0c,0x00,0x0c,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x10,0x00,0x0b,0x00,0x10,0x04,0x0b,0x00,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00, + 0x08,0x00,0x09,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00, + 0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, + 0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, + 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, + 0xd3,0x18,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00, + 0x91,0x08,0x10,0x04,0x01,0x07,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x42, + 0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04, + 0x00,0x00,0x01,0x00,0xd2,0x17,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04, + 0x00,0x00,0x01,0xff,0xe0,0xa7,0x87,0xe0,0xa6,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01, + 0xff,0xe0,0xa7,0x87,0xe0,0xa7,0x97,0x00,0x01,0x09,0x10,0x04,0x08,0x00,0x00,0x00, + 0xd3,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, + 0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa6,0xa1,0xe0,0xa6,0xbc, + 0x00,0x01,0xff,0xe0,0xa6,0xa2,0xe0,0xa6,0xbc,0x00,0x10,0x04,0x00,0x00,0x01,0xff, + 0xe0,0xa6,0xaf,0xe0,0xa6,0xbc,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x01,0x00,0x11, + 0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x14,0xe6,0x00, + 0x00,0xe2,0x48,0x02,0xe1,0x4f,0x01,0xd0,0xa4,0xcf,0x86,0xd5,0x4c,0xd4,0x34,0xd3, + 0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x10,0x04,0x01,0x00,0x07, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01, + 0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x2e,0xd2,0x17,0xd1, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa8,0xb2, + 0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x0b,0x01,0xff, + 0xe0,0xa8,0xb8,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00, + 0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x00,0x00,0x01,0x00,0xcf,0x86,0xd5,0x80,0xd4, + 0x34,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51, + 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01, + 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x01, + 0x09,0x00,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x00, + 0x00,0x00,0x00,0xd2,0x25,0xd1,0x0f,0x10,0x04,0x00,0x00,0x01,0xff,0xe0,0xa8,0x96, + 0xe0,0xa8,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa8,0x97,0xe0,0xa8,0xbc,0x00,0x01, + 0xff,0xe0,0xa8,0x9c,0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00, + 0x10,0x0b,0x01,0xff,0xe0,0xa8,0xab,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd4,0x10,0x93, + 0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x14,0x52, + 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04,0x14,0x00,0x00, + 0x00,0x00,0x00,0xd0,0x82,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, + 0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x10, + 0x04,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, + 0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01, + 0x07,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x10,0x52,0x04,0x01, + 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x00, + 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x07, + 0x00,0x07,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x0d,0x00,0x07,0x00,0x00,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x11,0x00,0x13,0x00,0x13,0x00,0xe1,0x24,0x01,0xd0,0x86,0xcf,0x86, + 0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00, + 0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14, + 0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x73,0xd4,0x45,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08, + 0x10,0x04,0x0a,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x0f, + 0x10,0x0b,0x01,0xff,0xe0,0xad,0x87,0xe0,0xad,0x96,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x01,0xff,0xe0,0xad,0x87,0xe0,0xac,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff, + 0xe0,0xad,0x87,0xe0,0xad,0x97,0x00,0x01,0x09,0x00,0x00,0xd3,0x0c,0x52,0x04,0x00, + 0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01, + 0xff,0xe0,0xac,0xa1,0xe0,0xac,0xbc,0x00,0x01,0xff,0xe0,0xac,0xa2,0xe0,0xac,0xbc, + 0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01, + 0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x0c,0x00,0x0c,0x00,0x00,0x00,0xd0,0xb1,0xcf, + 0x86,0xd5,0x63,0xd4,0x28,0xd3,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x91, + 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd3,0x1f,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0, + 0xae,0x92,0xe0,0xaf,0x97,0x00,0x01,0x00,0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x00,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x00,0x00,0x01,0x00,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04, + 0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c, + 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00, + 0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x08,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xcf,0x86, + 0xd5,0x61,0xd4,0x45,0xd3,0x14,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08,0x10,0x04,0x01,0x00, + 0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0,0xae,0xbe,0x00,0x01,0xff,0xe0, + 0xaf,0x87,0xe0,0xae,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0, + 0xaf,0x97,0x00,0x01,0x09,0x00,0x00,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0a, + 0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x00, + 0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x08, + 0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x07,0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00, + 0x00,0x00,0x00,0xe3,0x1c,0x04,0xe2,0x1a,0x02,0xd1,0xf3,0xd0,0x76,0xcf,0x86,0xd5, + 0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01, + 0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01, + 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3, + 0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0xd2, + 0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0x53,0xd4,0x2f,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10, + 0x04,0x01,0x00,0x00,0x00,0x01,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0, + 0xb1,0x86,0xe0,0xb1,0x96,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x01,0x54,0x10,0x04,0x01,0x5b,0x00,0x00,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04, + 0x11,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01,0x00, + 0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x52,0x04,0x00,0x00, + 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0a,0x00,0xd0,0x76,0xcf,0x86, + 0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x10,0x00, + 0x01,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00, + 0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, + 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, + 0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x07,0x07,0x07,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x82,0xd4,0x5e,0xd3,0x2a,0xd2,0x13,0x91,0x0f,0x10,0x0b, + 0x01,0xff,0xe0,0xb2,0xbf,0xe0,0xb3,0x95,0x00,0x01,0x00,0x01,0x00,0xd1,0x08,0x10, + 0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3, + 0x95,0x00,0xd2,0x28,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x96, + 0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x82,0x00,0x01,0xff, + 0xe0,0xb3,0x86,0xe0,0xb3,0x82,0xe0,0xb3,0x95,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00, + 0x10,0x04,0x01,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01,0x00, + 0x09,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08, + 0x10,0x04,0x00,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xe1,0x06,0x01,0xd0,0x6e,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x13,0x00,0x10,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, + 0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01, + 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, + 0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x0c,0x00,0x13,0x09,0x91,0x08,0x10,0x04,0x13,0x09,0x0a,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0x65,0xd4,0x45,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10, + 0x04,0x0a,0x00,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08,0x10,0x04,0x01,0x00,0x00, + 0x00,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb4,0xbe,0x00,0x01,0xff,0xe0,0xb5, + 0x87,0xe0,0xb4,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb5, + 0x97,0x00,0x01,0x09,0x10,0x04,0x0c,0x00,0x12,0x00,0xd3,0x10,0x52,0x04,0x00,0x00, + 0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x01,0x00,0x52,0x04,0x12,0x00,0x51,0x04, + 0x12,0x00,0x10,0x04,0x12,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04, + 0x01,0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x0c,0x52,0x04, + 0x0a,0x00,0x11,0x04,0x0a,0x00,0x12,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00, + 0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x5a,0xcf,0x86,0xd5,0x34,0xd4,0x18,0x93,0x14, + 0xd2,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x04,0x00, + 0x04,0x00,0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04, + 0x04,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x54,0x04, + 0x04,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x00,0x00,0x04,0x00, + 0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x04,0x00,0x00,0x00, + 0xcf,0x86,0xd5,0x77,0xd4,0x28,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00, + 0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x04,0x09, + 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x04,0x00,0xd3,0x14,0x52,0x04, + 0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x10,0x04,0x04,0x00,0x00,0x00, + 0xd2,0x13,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8a, + 0x00,0x04,0x00,0xd1,0x19,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0x00, + 0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0xe0,0xb7,0x8a,0x00,0x10,0x0b,0x04,0xff, + 0xe0,0xb7,0x99,0xe0,0xb7,0x9f,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x00, + 0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x14,0xd2,0x08,0x11,0x04,0x00, + 0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe2, + 0x31,0x01,0xd1,0x58,0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x67,0x10,0x04, + 0x01,0x09,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xcf,0x86, + 0x95,0x18,0xd4,0x0c,0x53,0x04,0x01,0x00,0x12,0x04,0x01,0x6b,0x01,0x00,0x53,0x04, + 0x01,0x00,0x12,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd0,0x9e,0xcf,0x86,0xd5,0x54, + 0xd4,0x3c,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04, + 0x01,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x15,0x00, + 0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x15,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x15,0x00,0xd3,0x08,0x12,0x04, + 0x15,0x00,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00, + 0x01,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x15,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00, + 0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x76,0x10,0x04,0x15,0x09, + 0x01,0x00,0x11,0x04,0x01,0x00,0x00,0x00,0xcf,0x86,0x95,0x34,0xd4,0x20,0xd3,0x14, + 0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x52,0x04,0x01,0x7a,0x11,0x04,0x01,0x00,0x00,0x00,0x53,0x04,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x01,0x00,0x0d,0x00,0x00,0x00, + 0xe1,0x2b,0x01,0xd0,0x3e,0xcf,0x86,0xd5,0x14,0x54,0x04,0x02,0x00,0x53,0x04,0x02, + 0x00,0x92,0x08,0x11,0x04,0x02,0xdc,0x02,0x00,0x02,0x00,0x54,0x04,0x02,0x00,0xd3, + 0x14,0x52,0x04,0x02,0x00,0xd1,0x08,0x10,0x04,0x02,0x00,0x02,0xdc,0x10,0x04,0x02, + 0x00,0x02,0xdc,0x92,0x0c,0x91,0x08,0x10,0x04,0x02,0x00,0x02,0xd8,0x02,0x00,0x02, + 0x00,0xcf,0x86,0xd5,0x73,0xd4,0x36,0xd3,0x17,0x92,0x13,0x51,0x04,0x02,0x00,0x10, + 0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x82,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x00,0x00,0x02,0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00, + 0x02,0xff,0xe0,0xbd,0x8c,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd3,0x26,0xd2,0x13,0x51, + 0x04,0x02,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x91,0xe0,0xbe,0xb7,0x00,0x02,0x00, + 0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x96,0xe0,0xbe,0xb7, + 0x00,0x52,0x04,0x02,0x00,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x9b,0xe0,0xbe, + 0xb7,0x00,0x02,0x00,0x02,0x00,0xd4,0x27,0x53,0x04,0x02,0x00,0xd2,0x17,0xd1,0x0f, + 0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x80,0xe0,0xbe,0xb5,0x00,0x10,0x04,0x04, + 0x00,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0xd3,0x35,0xd2, + 0x17,0xd1,0x08,0x10,0x04,0x00,0x00,0x02,0x81,0x10,0x04,0x02,0x82,0x02,0xff,0xe0, + 0xbd,0xb1,0xe0,0xbd,0xb2,0x00,0xd1,0x0f,0x10,0x04,0x02,0x84,0x02,0xff,0xe0,0xbd, + 0xb1,0xe0,0xbd,0xb4,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xb2,0xe0,0xbe,0x80,0x00, + 0x02,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xb3,0xe0,0xbe,0x80, + 0x00,0x02,0x00,0x02,0x82,0x11,0x04,0x02,0x82,0x02,0x00,0xd0,0xd3,0xcf,0x86,0xd5, + 0x65,0xd4,0x27,0xd3,0x1f,0xd2,0x13,0x91,0x0f,0x10,0x04,0x02,0x82,0x02,0xff,0xe0, + 0xbd,0xb1,0xe0,0xbe,0x80,0x00,0x02,0xe6,0x91,0x08,0x10,0x04,0x02,0x09,0x02,0x00, + 0x02,0xe6,0x12,0x04,0x02,0x00,0x0c,0x00,0xd3,0x1f,0xd2,0x13,0x51,0x04,0x02,0x00, + 0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x92,0xe0,0xbe,0xb7,0x00,0x51,0x04,0x02, + 0x00,0x10,0x04,0x04,0x00,0x02,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x02, + 0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x9c,0xe0,0xbe, + 0xb7,0x00,0x02,0x00,0xd4,0x3d,0xd3,0x26,0xd2,0x13,0x51,0x04,0x02,0x00,0x10,0x0b, + 0x02,0xff,0xe0,0xbe,0xa1,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x51,0x04,0x02,0x00,0x10, + 0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0xa6,0xe0,0xbe,0xb7,0x00,0x52,0x04,0x02,0x00, + 0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xab,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x04, + 0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x02,0x00,0x02,0x00,0x02, + 0x00,0xd2,0x13,0x91,0x0f,0x10,0x04,0x04,0x00,0x02,0xff,0xe0,0xbe,0x90,0xe0,0xbe, + 0xb5,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xcf,0x86, + 0x95,0x4c,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04, + 0x04,0xdc,0x04,0x00,0x52,0x04,0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00, + 0x10,0x04,0x0a,0x00,0x04,0x00,0xd3,0x14,0xd2,0x08,0x11,0x04,0x08,0x00,0x0a,0x00, + 0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04, + 0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, + 0xe5,0xf7,0x04,0xe4,0x79,0x03,0xe3,0x7b,0x01,0xe2,0x04,0x01,0xd1,0x7f,0xd0,0x65, + 0xcf,0x86,0x55,0x04,0x04,0x00,0xd4,0x33,0xd3,0x1f,0xd2,0x0c,0x51,0x04,0x04,0x00, + 0x10,0x04,0x0a,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe1,0x80, + 0xa5,0xe1,0x80,0xae,0x00,0x04,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0a,0x00,0x04, + 0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x04,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x04, + 0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x04,0x00,0x04, + 0x07,0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0x09,0x10,0x04,0x0a,0x09,0x0a, + 0x00,0x0a,0x00,0xcf,0x86,0x95,0x14,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92, + 0x08,0x11,0x04,0x04,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x2e,0xcf,0x86,0x95, + 0x28,0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a, + 0x00,0x0a,0xdc,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00,0x0b, + 0x00,0x11,0x04,0x0b,0x00,0x0a,0x00,0x01,0x00,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3, + 0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x52, + 0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x00,0x00,0x01,0x00,0x54, + 0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x06,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x06,0x00,0x08,0x00,0x10,0x04,0x08, + 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0d,0x00,0x0d,0x00,0xd1,0x3e,0xd0, + 0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x1d,0x54,0x04,0x01,0x00,0x53,0x04,0x01, + 0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, + 0x00,0x01,0xff,0x00,0x94,0x15,0x93,0x11,0x92,0x0d,0x91,0x09,0x10,0x05,0x01,0xff, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55, + 0x04,0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x0b,0x00,0x0b,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54, + 0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x0b, + 0x00,0xe2,0x21,0x01,0xd1,0x6c,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10, + 0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00, + 0x04,0x00,0x04,0x00,0xcf,0x86,0x95,0x48,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0xd3,0x10,0x52,0x04, + 0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08, + 0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00, + 0xd0,0x62,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04, + 0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00, + 0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xd4,0x14,0x53,0x04, + 0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, + 0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04, + 0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00, + 0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x93,0x10,0x52,0x04,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x94,0x14,0x53,0x04, + 0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, + 0x04,0x00,0xd1,0x9c,0xd0,0x3e,0xcf,0x86,0x95,0x38,0xd4,0x14,0x53,0x04,0x04,0x00, + 0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd3,0x14, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00, + 0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, + 0x04,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04, + 0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00,0x53,0x04,0x04,0x00,0xd2,0x0c, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x0c,0xe6,0x10,0x04,0x0c,0xe6,0x08,0xe6,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x08,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x53,0x04,0x04,0x00, + 0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a, + 0xcf,0x86,0x95,0x14,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04, + 0x08,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04, + 0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x11,0x00, + 0x00,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0xd3,0x30,0xd2,0x2a, + 0xd1,0x24,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0b,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00, + 0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd2,0x6c,0xd1,0x24, + 0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00, + 0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x0b,0x00, + 0x0b,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00, + 0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00, + 0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x04,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x46,0xcf,0x86,0xd5,0x28, + 0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x00, + 0x00,0x00,0x06,0x00,0x93,0x10,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x09, + 0x00,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x06,0x00,0x93,0x14,0x52,0x04,0x06,0x00, + 0xd1,0x08,0x10,0x04,0x06,0x09,0x06,0x00,0x10,0x04,0x06,0x00,0x00,0x00,0x00,0x00, + 0xcf,0x86,0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x06,0x00,0x00,0x00, + 0x00,0x00,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04, + 0x06,0x00,0x00,0x00,0x06,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00, + 0x00,0x00,0x06,0x00,0x00,0x00,0x00,0x00,0xd0,0x1b,0xcf,0x86,0x55,0x04,0x04,0x00, + 0x54,0x04,0x04,0x00,0x93,0x0d,0x52,0x04,0x04,0x00,0x11,0x05,0x04,0xff,0x00,0x04, + 0x00,0x04,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x51, + 0x04,0x04,0x00,0x10,0x04,0x04,0x09,0x04,0x00,0x04,0x00,0x52,0x04,0x04,0x00,0x91, + 0x08,0x10,0x04,0x04,0x00,0x07,0xe6,0x00,0x00,0xd4,0x10,0x53,0x04,0x04,0x00,0x92, + 0x08,0x11,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x08,0x11, + 0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xe4,0xb7,0x03,0xe3,0x58,0x01,0xd2,0x8f,0xd1, + 0x53,0xd0,0x35,0xcf,0x86,0x95,0x2f,0xd4,0x1f,0x53,0x04,0x04,0x00,0xd2,0x0d,0x51, + 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x04,0xff,0x00,0x51,0x05,0x04,0xff,0x00,0x10, + 0x05,0x04,0xff,0x00,0x00,0x00,0x53,0x04,0x04,0x00,0x92,0x08,0x11,0x04,0x04,0x00, + 0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00, + 0x53,0x04,0x04,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x04,0x00,0x94,0x18,0x53,0x04,0x04,0x00, + 0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0xe4,0x10,0x04,0x0a,0x00,0x00,0x00, + 0x00,0x00,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x0c, + 0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x42, + 0xcf,0x86,0xd5,0x1c,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00, + 0xd1,0x08,0x10,0x04,0x07,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0xd4,0x0c, + 0x53,0x04,0x07,0x00,0x12,0x04,0x07,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x10, + 0xd1,0x08,0x10,0x04,0x07,0x00,0x07,0xde,0x10,0x04,0x07,0xe6,0x07,0xdc,0x00,0x00, + 0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00, + 0x00,0x00,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd4,0x10,0x53,0x04,0x07,0x00, + 0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x07,0x00, + 0x91,0x08,0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a,0xcf,0x86, + 0x55,0x04,0x08,0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00, + 0x0b,0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x95,0x28,0xd4,0x10,0x53,0x04,0x08,0x00, + 0x92,0x08,0x11,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0xd2,0x0c, + 0x51,0x04,0x08,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x08,0x00, + 0x07,0x00,0xd2,0xe4,0xd1,0x80,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x54,0x04,0x08,0x00, + 0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x08,0xe6, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x08,0xdc,0x08,0x00,0x08,0x00,0x11,0x04,0x00,0x00, + 0x08,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00, + 0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xd4,0x14, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00, + 0x0b,0x00,0xd3,0x10,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6, + 0x0b,0xe6,0x52,0x04,0x0b,0xe6,0xd1,0x08,0x10,0x04,0x0b,0xe6,0x00,0x00,0x10,0x04, + 0x00,0x00,0x0b,0xdc,0xd0,0x5e,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0b,0x00, + 0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0b,0x00,0x92,0x08, + 0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd4,0x10,0x53,0x04,0x0b,0x00,0x52,0x04, + 0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x10,0xe6,0x91,0x08, + 0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0xdc,0xd2,0x0c,0x51,0x04,0x10,0xdc,0x10,0x04, + 0x10,0xdc,0x10,0xe6,0xd1,0x08,0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0x04,0x10,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xe1,0x1e,0x01,0xd0,0xaa,0xcf,0x86,0xd5,0x6e,0xd4, + 0x53,0xd3,0x17,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1, + 0xac,0x85,0xe1,0xac,0xb5,0x00,0x09,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x09,0xff, + 0xe1,0xac,0x87,0xe1,0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x89, + 0xe1,0xac,0xb5,0x00,0x09,0x00,0xd1,0x0f,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8b,0xe1, + 0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8d,0xe1,0xac,0xb5,0x00, + 0x09,0x00,0x93,0x17,0x92,0x13,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac, + 0x91,0xe1,0xac,0xb5,0x00,0x09,0x00,0x09,0x00,0x09,0x00,0x54,0x04,0x09,0x00,0xd3, + 0x10,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x07,0x09,0x00,0x09,0x00,0xd2, + 0x13,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xba,0xe1,0xac, + 0xb5,0x00,0x91,0x0f,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xbc,0xe1,0xac,0xb5, + 0x00,0x09,0x00,0xcf,0x86,0xd5,0x3d,0x94,0x39,0xd3,0x31,0xd2,0x25,0xd1,0x16,0x10, + 0x0b,0x09,0xff,0xe1,0xac,0xbe,0xe1,0xac,0xb5,0x00,0x09,0xff,0xe1,0xac,0xbf,0xe1, + 0xac,0xb5,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xad,0x82,0xe1,0xac,0xb5,0x00, + 0x91,0x08,0x10,0x04,0x09,0x09,0x09,0x00,0x09,0x00,0x12,0x04,0x09,0x00,0x00,0x00, + 0x09,0x00,0xd4,0x1c,0x53,0x04,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09,0x00,0x10,0x04, + 0x09,0x00,0x09,0xe6,0x91,0x08,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0xe6,0xd3,0x08, + 0x12,0x04,0x09,0xe6,0x09,0x00,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00, + 0x00,0x00,0x00,0x00,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x18,0x53,0x04, + 0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x09,0x0d,0x09,0x11,0x04, + 0x0d,0x00,0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x0d,0x00, + 0x0d,0x00,0xcf,0x86,0x55,0x04,0x0c,0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x0c,0x00, + 0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x07,0x0c,0x00,0x0c,0x00,0xd3,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x0c,0x09,0x00,0x00,0x12,0x04,0x00,0x00,0x0c,0x00,0xe3,0xb2, + 0x01,0xe2,0x09,0x01,0xd1,0x4c,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x0a,0x00,0x54,0x04, + 0x0a,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00, + 0x0a,0x07,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00, + 0xcf,0x86,0x95,0x1c,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00, + 0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00, + 0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x14,0x00,0x54,0x04,0x14,0x00, + 0x53,0x04,0x14,0x00,0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00, + 0x91,0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x14,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x08, + 0x13,0x04,0x0d,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04, + 0x0b,0xe6,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x01,0x0b,0xdc,0x0b,0xdc,0x92,0x08, + 0x11,0x04,0x0b,0xdc,0x0b,0xe6,0x0b,0xdc,0xd4,0x28,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x01,0x0b,0x01,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x0b,0x01,0x0b,0x00,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xdc,0x0b,0x00, + 0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0d,0x00,0xd1,0x08, + 0x10,0x04,0x0d,0xe6,0x0d,0x00,0x10,0x04,0x0d,0x00,0x13,0x00,0x92,0x0c,0x51,0x04, + 0x10,0xe6,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06, + 0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x94,0x0c,0x53,0x04,0x07,0x00,0x12,0x04, + 0x07,0x00,0x08,0x00,0x08,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0xd5,0x40, + 0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x51,0x04,0x08,0xe6,0x10,0x04,0x08,0xdc,0x08,0xe6, + 0x09,0xe6,0xd2,0x0c,0x51,0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x0a,0xe6,0xd1,0x08, + 0x10,0x04,0x0a,0xe6,0x0a,0xea,0x10,0x04,0x0a,0xd6,0x0a,0xdc,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x0a,0xca,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0xd4,0x14, + 0x93,0x10,0x52,0x04,0x0a,0xe6,0x51,0x04,0x0a,0xe6,0x10,0x04,0x0a,0xe6,0x10,0xe6, + 0x10,0xe6,0xd3,0x10,0x52,0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x13,0xe8, + 0x13,0xe4,0xd2,0x10,0xd1,0x08,0x10,0x04,0x13,0xe4,0x13,0xdc,0x10,0x04,0x00,0x00, + 0x12,0xe6,0xd1,0x08,0x10,0x04,0x0c,0xe9,0x0b,0xdc,0x10,0x04,0x09,0xe6,0x09,0xdc, + 0xe2,0x80,0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84, + 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa5,0x00,0x01,0xff, + 0x61,0xcc,0xa5,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc, + 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x42,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc, + 0xa3,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00, + 0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x43,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff, + 0x63,0xcc,0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0x87,0x00,0x01,0xff, + 0x64,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa3,0x00,0x01,0xff, + 0x64,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc, + 0xb1,0x00,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa7,0x00, + 0x01,0xff,0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xad,0x00,0x01,0xff, + 0x64,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc,0x80,0x00, + 0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc, + 0x81,0x00,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x45,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff, + 0x45,0xcc,0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x45,0xcc,0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08, + 0x01,0xff,0x46,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc, + 0x84,0x00,0x10,0x08,0x01,0xff,0x48,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00, + 0x10,0x08,0x01,0xff,0x48,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00, + 0x10,0x08,0x01,0xff,0x48,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x49,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a, + 0x01,0xff,0x49,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00, + 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0x81,0x00,0x01,0xff, + 0x6b,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc, + 0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc, + 0xb1,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00, + 0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff, + 0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xb1,0x00,0x01,0xff, + 0x6c,0xcc,0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4c,0xcc,0xad,0x00,0x01,0xff, + 0x6c,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x4d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc, + 0x81,0x00,0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x4d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01, + 0xff,0x4d,0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x4e,0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x4e, + 0xcc,0xa3,0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x4e,0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x4e, + 0xcc,0xad,0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f, + 0xcc,0x83,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01, + 0xff,0x4f,0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3, + 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x80,0x00,0x01, + 0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x81, + 0x00,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x50, + 0xcc,0x81,0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x50,0xcc,0x87, + 0x00,0x01,0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52, + 0xcc,0x87,0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa3, + 0x00,0x01,0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x52,0xcc,0xa3, + 0xcc,0x84,0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x52, + 0xcc,0xb1,0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10, + 0x08,0x01,0xff,0x53,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10, + 0x0a,0x01,0xff,0x53,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87, + 0x00,0x10,0x0a,0x01,0xff,0x53,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c, + 0xcc,0x87,0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x53,0xcc,0xa3,0xcc,0x87, + 0x00,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0x87, + 0x00,0x01,0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0xa3, + 0x00,0x01,0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xb1,0x00,0x01, + 0xff,0x74,0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x54, + 0xcc,0xad,0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa4, + 0x00,0x01,0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0xb0, + 0x00,0x01,0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xad,0x00,0x01, + 0xff,0x75,0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x83, + 0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x55, + 0xcc,0x84,0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x56,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01, + 0xff,0x56,0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x10,0x02,0xcf,0x86, + 0xd5,0xe1,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc, + 0x80,0x00,0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x81,0x00, + 0x01,0xff,0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x88,0x00, + 0x01,0xff,0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x87,0x00,0x01,0xff, + 0x77,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0xa3,0x00, + 0x01,0xff,0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x58,0xcc,0x87,0x00,0x01,0xff, + 0x78,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x58,0xcc,0x88,0x00,0x01,0xff, + 0x78,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc, + 0x87,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0x82,0x00, + 0x01,0xff,0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x5a,0xcc,0xa3,0x00,0x01,0xff, + 0x7a,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0xb1,0x00,0x01,0xff, + 0x7a,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x68,0xcc,0xb1,0x00,0x01,0xff,0x74,0xcc, + 0x88,0x00,0x92,0x1d,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01,0xff, + 0x79,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x02,0xff,0xc5,0xbf,0xcc,0x87,0x00,0x0a, + 0x00,0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa3, + 0x00,0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x89,0x00,0x01, + 0xff,0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x81, + 0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82, + 0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10, + 0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89, + 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82, + 0xcc,0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x82,0x00,0x01, + 0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x81, + 0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10, + 0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80, + 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86, + 0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x83,0x00,0x01, + 0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x86, + 0x00,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x45,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x45, + 0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45, + 0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82, + 0xcc,0x81,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01, + 0xd4,0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82,0xcc, + 0x80,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc, + 0x82,0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a, + 0x01,0xff,0x45,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00, + 0x10,0x0a,0x01,0xff,0x45,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc, + 0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x89,0x00,0x01,0xff, + 0x69,0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc, + 0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc, + 0xa3,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00, + 0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc,0x81,0x00, + 0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc, + 0x80,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x4f,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a, + 0x01,0xff,0x4f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00, + 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, + 0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x81,0x00, + 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc, + 0x9b,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff, + 0x4f,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98, + 0xd3,0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x83,0x00, + 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc, + 0xa3,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x55,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x55,0xcc, + 0x89,0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x55,0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a, + 0x01,0xff,0x55,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00, + 0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc, + 0x9b,0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff, + 0x75,0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x55,0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08, + 0x01,0xff,0x59,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x59,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff, + 0x59,0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0x92,0x14,0x91,0x10,0x10,0x08, + 0x01,0xff,0x59,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x0a,0x00,0x0a,0x00, + 0xe1,0xc0,0x04,0xe0,0x80,0x02,0xcf,0x86,0xe5,0x2d,0x01,0xd4,0xa8,0xd3,0x54,0xd2, + 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1, + 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, + 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82, + 0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x91,0xcc,0x93,0x00,0x01,0xff, + 0xce,0x91,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80,0x00, + 0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce, + 0x91,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x81,0x00,0x10, + 0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x91,0xcc,0x94, + 0xcd,0x82,0x00,0xd3,0x42,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc, + 0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc, + 0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10, + 0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94, + 0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x95,0xcc, + 0x93,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x95,0xcc, + 0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10, + 0x0b,0x01,0xff,0xce,0x95,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x95,0xcc,0x94, + 0xcc,0x81,0x00,0x00,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80, + 0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff, + 0xce,0xb7,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd, + 0x82,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xce,0x97,0xcc,0x93,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0x00,0x10, + 0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x94, + 0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81,0x00, + 0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc, + 0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x82,0x00,0xd3,0x54,0xd2, + 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9, + 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc, + 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82, + 0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x93,0x00,0x01,0xff, + 0xce,0x99,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcc,0x80,0x00, + 0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce, + 0x99,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x81,0x00,0x10, + 0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x99,0xcc,0x94, + 0xcd,0x82,0x00,0xcf,0x86,0xe5,0x13,0x01,0xd4,0x84,0xd3,0x42,0xd2,0x28,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00, + 0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc, + 0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x81, + 0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xce,0x9f,0xcc,0x93,0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0x00, + 0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc, + 0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x81, + 0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x54,0xd2,0x28, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff,0xcf,0x85,0xcc, + 0x94,0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf, + 0x85,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93, + 0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, + 0xcf,0x85,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00, + 0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0x00,0x10, + 0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x0f,0x10,0x04, + 0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x81,0x00,0x10,0x04,0x00,0x00,0x01, + 0xff,0xce,0xa5,0xcc,0x94,0xcd,0x82,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00, + 0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89, + 0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xa9,0xcc,0x93,0x00,0x01,0xff,0xce,0xa9,0xcc, + 0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce, + 0xa9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93, + 0xcc,0x81,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, + 0xce,0xa9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0x00, + 0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01, + 0xff,0xce,0xb1,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01, + 0xff,0xce,0xb5,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80, + 0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff, + 0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, + 0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x91,0x12,0x10,0x09, + 0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x00,0x00, + 0xe0,0xe1,0x02,0xcf,0x86,0xe5,0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc, + 0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d, + 0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc, + 0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82, + 0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30, + 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce, + 0x91,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80, + 0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a, + 0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce, + 0x91,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93, + 0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00, + 0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7, + 0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xcd, + 0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff, + 0xce,0xb7,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd, + 0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93, + 0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff, + 0xce,0x97,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc, + 0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81, + 0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d, + 0x01,0xff,0xce,0x97,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc, + 0x94,0xcd,0x82,0xcd,0x85,0x00,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b, + 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd, + 0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01, + 0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc, + 0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xcd,0x85, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc, + 0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d, + 0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc, + 0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x82, + 0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd3,0x49, + 0xd2,0x26,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce, + 0xb1,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x80,0xcd,0x85,0x00,0x01, + 0xff,0xce,0xb1,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81, + 0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff, + 0xce,0xb1,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, + 0x91,0xcc,0x86,0x00,0x01,0xff,0xce,0x91,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce, + 0x91,0xcc,0x80,0x00,0x01,0xff,0xce,0x91,0xcc,0x81,0x00,0xd1,0x0d,0x10,0x09,0x01, + 0xff,0xce,0x91,0xcd,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xb9,0x00,0x01, + 0x00,0xcf,0x86,0xe5,0x16,0x01,0xd4,0x8f,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10,0x04, + 0x01,0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc, + 0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01, + 0xff,0xce,0xb7,0xcc,0x81,0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb7, + 0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xce,0x95,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x81,0x00, + 0x10,0x09,0x01,0xff,0xce,0x97,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00, + 0xd1,0x13,0x10,0x09,0x01,0xff,0xce,0x97,0xcd,0x85,0x00,0x01,0xff,0xe1,0xbe,0xbf, + 0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbe,0xbf,0xcc,0x81,0x00,0x01,0xff,0xe1, + 0xbe,0xbf,0xcd,0x82,0x00,0xd3,0x40,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, + 0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce, + 0xb9,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x51, + 0x04,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9, + 0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc, + 0x86,0x00,0x01,0xff,0xce,0x99,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc, + 0x80,0x00,0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x04,0x00,0x00,0x01, + 0xff,0xe1,0xbf,0xbe,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbf,0xbe,0xcc,0x81, + 0x00,0x01,0xff,0xe1,0xbf,0xbe,0xcd,0x82,0x00,0xd4,0x93,0xd3,0x4e,0xd2,0x28,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84, + 0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85, + 0xcc,0x88,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x93,0x00, + 0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcd,0x82,0x00, + 0x01,0xff,0xcf,0x85,0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xce,0xa5,0xcc,0x86,0x00,0x01,0xff,0xce,0xa5,0xcc,0x84,0x00,0x10,0x09,0x01, + 0xff,0xce,0xa5,0xcc,0x80,0x00,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xce,0xa1,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x80,0x00,0x10, + 0x09,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x01,0xff,0x60,0x00,0xd3,0x3b,0xd2,0x18, + 0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x80,0xcd,0x85,0x00,0x01, + 0xff,0xcf,0x89,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81, + 0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcd,0x82,0x00,0x01,0xff, + 0xcf,0x89,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, + 0x9f,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce, + 0xa9,0xcc,0x80,0x00,0x01,0xff,0xce,0xa9,0xcc,0x81,0x00,0xd1,0x10,0x10,0x09,0x01, + 0xff,0xce,0xa9,0xcd,0x85,0x00,0x01,0xff,0xc2,0xb4,0x00,0x10,0x04,0x01,0x00,0x00, + 0x00,0xe0,0x7e,0x0c,0xcf,0x86,0xe5,0xbb,0x08,0xe4,0x14,0x06,0xe3,0xf7,0x02,0xe2, + 0xbd,0x01,0xd1,0xd0,0xd0,0x4f,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0xd3,0x18,0x92,0x14, + 0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01,0xff,0xe2,0x80,0x83,0x00, + 0x01,0x00,0x01,0x00,0x92,0x0d,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, + 0x00,0x01,0xff,0x00,0x01,0x00,0x94,0x1b,0x53,0x04,0x01,0x00,0xd2,0x09,0x11,0x04, + 0x01,0x00,0x01,0xff,0x00,0x51,0x05,0x01,0xff,0x00,0x10,0x05,0x01,0xff,0x00,0x04, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x48,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x01,0x00,0x51, + 0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x52,0x04,0x04,0x00,0x11,0x04,0x04, + 0x00,0x06,0x00,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x06,0x00,0x07, + 0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0x52, + 0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0xd4,0x23,0xd3, + 0x14,0x52,0x05,0x06,0xff,0x00,0x91,0x0a,0x10,0x05,0x0a,0xff,0x00,0x00,0xff,0x00, + 0x0f,0xff,0x00,0x92,0x0a,0x11,0x05,0x0f,0xff,0x00,0x01,0xff,0x00,0x01,0xff,0x00, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x00,0x00,0x01,0x00, + 0x01,0x00,0xd0,0x7e,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x53,0x04,0x01,0x00,0x52,0x04, + 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xd3,0x10,0x52,0x04, + 0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0c,0x00,0x0c,0x00,0x52,0x04,0x0c,0x00, + 0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00, + 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x02,0x00,0x91,0x08,0x10,0x04, + 0x03,0x00,0x04,0x00,0x04,0x00,0xd3,0x10,0xd2,0x08,0x11,0x04,0x06,0x00,0x08,0x00, + 0x11,0x04,0x08,0x00,0x0b,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00, + 0x10,0x04,0x0e,0x00,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x11,0x00,0x13,0x00, + 0xcf,0x86,0xd5,0x28,0x54,0x04,0x00,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x01,0xe6, + 0x01,0x01,0x01,0xe6,0xd2,0x0c,0x51,0x04,0x01,0x01,0x10,0x04,0x01,0x01,0x01,0xe6, + 0x91,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x04,0x00,0xd1,0x08,0x10,0x04,0x06,0x00, + 0x06,0x01,0x10,0x04,0x06,0x01,0x06,0xe6,0x92,0x10,0xd1,0x08,0x10,0x04,0x06,0xdc, + 0x06,0xe6,0x10,0x04,0x06,0x01,0x08,0x01,0x09,0xdc,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0a,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x81,0xd0,0x4f, + 0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04, + 0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xa9,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01, + 0x00,0x10,0x06,0x01,0xff,0x4b,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00,0x01,0x00,0x53, + 0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x04, + 0x00,0x07,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0x95, + 0x2c,0xd4,0x18,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0xd1,0x08,0x10,0x04,0x08, + 0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b, + 0x00,0x10,0x04,0x0b,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x68,0xcf, + 0x86,0xd5,0x48,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x11,0x00,0x00,0x00,0x53,0x04,0x01,0x00,0x92, + 0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x90,0xcc,0xb8,0x00,0x01, + 0xff,0xe2,0x86,0x92,0xcc,0xb8,0x00,0x01,0x00,0x94,0x1a,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x94,0xcc,0xb8, + 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x87,0x90,0xcc,0xb8, + 0x00,0x10,0x0a,0x01,0xff,0xe2,0x87,0x94,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x87,0x92, + 0xcc,0xb8,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x06, + 0x00,0x06,0x00,0xe2,0x38,0x02,0xe1,0x3f,0x01,0xd0,0x68,0xcf,0x86,0xd5,0x3e,0x94, + 0x3a,0xd3,0x16,0x52,0x04,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0x83, + 0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0xd2,0x12,0x91,0x0e,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe2,0x88,0x88,0xcc,0xb8,0x00,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff,0xe2, + 0x88,0x8b,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x24,0x93,0x20,0x52, + 0x04,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa3,0xcc,0xb8,0x00,0x01, + 0x00,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa5,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0x48,0x94,0x44,0xd3,0x2e,0xd2,0x12,0x91,0x0e,0x10,0x04,0x01, + 0x00,0x01,0xff,0xe2,0x88,0xbc,0xcc,0xb8,0x00,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01, + 0xff,0xe2,0x89,0x83,0xcc,0xb8,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe2, + 0x89,0x85,0xcc,0xb8,0x00,0x92,0x12,0x91,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2, + 0x89,0x88,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x40,0xd3,0x1e,0x92, + 0x1a,0xd1,0x0c,0x10,0x08,0x01,0xff,0x3d,0xcc,0xb8,0x00,0x01,0x00,0x10,0x0a,0x01, + 0xff,0xe2,0x89,0xa1,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1, + 0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x89,0x8d,0xcc,0xb8,0x00,0x10,0x08,0x01, + 0xff,0x3c,0xcc,0xb8,0x00,0x01,0xff,0x3e,0xcc,0xb8,0x00,0xd3,0x30,0xd2,0x18,0x91, + 0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xa4,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xa5, + 0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xb2,0xcc,0xb8, + 0x00,0x01,0xff,0xe2,0x89,0xb3,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18,0x91,0x14,0x10, + 0x0a,0x01,0xff,0xe2,0x89,0xb6,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xb7,0xcc,0xb8, + 0x00,0x01,0x00,0x01,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x50,0x94,0x4c,0xd3,0x30,0xd2, + 0x18,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xba,0xcc,0xb8,0x00,0x01,0xff,0xe2, + 0x89,0xbb,0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x82, + 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x83,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18,0x91, + 0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x86,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x87, + 0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x30,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa2,0xcc,0xb8,0x00,0x01, + 0xff,0xe2,0x8a,0xa8,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa9,0xcc,0xb8, + 0x00,0x01,0xff,0xe2,0x8a,0xab,0xcc,0xb8,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01, + 0x00,0xd4,0x5c,0xd3,0x2c,0x92,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xbc, + 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xbd,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2, + 0x8a,0x91,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x92,0xcc,0xb8,0x00,0x01,0x00,0xd2, + 0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb2,0xcc,0xb8,0x00,0x01, + 0xff,0xe2,0x8a,0xb3,0xcc,0xb8,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb4, + 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0xb5,0xcc,0xb8,0x00,0x01,0x00,0x93,0x0c,0x92, + 0x08,0x11,0x04,0x01,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xd1,0x64,0xd0,0x3e,0xcf, + 0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x20,0x53,0x04,0x01,0x00,0x92, + 0x18,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x80,0x88,0x00,0x10,0x08,0x01, + 0xff,0xe3,0x80,0x89,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01, + 0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00,0x04,0x00,0xd0, + 0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51, + 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5, + 0x2c,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00,0x10, + 0x04,0x06,0x00,0x07,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x08, + 0x00,0x08,0x00,0x08,0x00,0x12,0x04,0x08,0x00,0x09,0x00,0xd4,0x14,0x53,0x04,0x09, + 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xd3, + 0x08,0x12,0x04,0x0c,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10, + 0x00,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0xd3,0xa6,0xd2, + 0x74,0xd1,0x40,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18,0x93,0x14,0x52, + 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x04,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x92, + 0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01, + 0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x14,0x53, + 0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x06, + 0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x06, + 0x00,0x07,0x00,0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54, + 0x04,0x01,0x00,0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06,0x00,0x06, + 0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x13,0x04,0x04, + 0x00,0x06,0x00,0xd2,0xdc,0xd1,0x48,0xd0,0x26,0xcf,0x86,0x95,0x20,0x54,0x04,0x01, + 0x00,0xd3,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x07,0x00,0x06,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x08,0x00,0x04,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55, + 0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x04,0x00,0x06, + 0x00,0x06,0x00,0x52,0x04,0x06,0x00,0x11,0x04,0x06,0x00,0x08,0x00,0xd0,0x5e,0xcf, + 0x86,0xd5,0x2c,0xd4,0x10,0x53,0x04,0x06,0x00,0x92,0x08,0x11,0x04,0x06,0x00,0x07, + 0x00,0x07,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x52, + 0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0a,0x00,0x0b,0x00,0xd4,0x10,0x93, + 0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd3,0x10,0x92, + 0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x52,0x04,0x0a, + 0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x1c,0x94, + 0x18,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b, + 0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0b,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51, + 0x04,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0c,0x00,0x0b,0x00,0x0b,0x00,0xd1, + 0xa8,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10, + 0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x01, + 0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x53, + 0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x18,0x53,0x04,0x01,0x00,0x52,0x04,0x01, + 0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x04,0x0c,0x00,0x01,0x00,0xd3, + 0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0c,0x00,0x51,0x04,0x0c, + 0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x0c,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x06,0x00,0x93,0x0c,0x52,0x04,0x06,0x00,0x11, + 0x04,0x06,0x00,0x01,0x00,0x01,0x00,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01, + 0x00,0x93,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x0c, + 0x00,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0x94,0x28,0xd3,0x10,0x52,0x04,0x08, + 0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09, + 0x00,0x10,0x04,0x09,0x00,0x0d,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0d,0x00,0x0c, + 0x00,0x06,0x00,0x94,0x0c,0x53,0x04,0x06,0x00,0x12,0x04,0x06,0x00,0x0a,0x00,0x06, + 0x00,0xe4,0x39,0x01,0xd3,0x0c,0xd2,0x06,0xcf,0x06,0x04,0x00,0xcf,0x06,0x06,0x00, + 0xd2,0x30,0xd1,0x06,0xcf,0x06,0x06,0x00,0xd0,0x06,0xcf,0x06,0x06,0x00,0xcf,0x86, + 0x95,0x1e,0x54,0x04,0x06,0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x0e, + 0x10,0x0a,0x06,0xff,0xe2,0xab,0x9d,0xcc,0xb8,0x00,0x06,0x00,0x06,0x00,0x06,0x00, + 0xd1,0x80,0xd0,0x3a,0xcf,0x86,0xd5,0x28,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04, + 0x07,0x00,0x11,0x04,0x07,0x00,0x08,0x00,0xd3,0x08,0x12,0x04,0x08,0x00,0x09,0x00, + 0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x94,0x0c, + 0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x30, + 0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, + 0x10,0x00,0x10,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, + 0x0b,0x00,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x10,0x00,0x10,0x00,0x54,0x04, + 0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00, + 0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00, + 0x11,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, + 0xd2,0x08,0x11,0x04,0x10,0x00,0x14,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x10,0x00, + 0x10,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x10,0x00,0x15,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, + 0x10,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd4,0x0c,0x53,0x04, + 0x14,0x00,0x12,0x04,0x14,0x00,0x11,0x00,0x53,0x04,0x14,0x00,0x52,0x04,0x14,0x00, + 0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0xe3,0xb9,0x01,0xd2,0xac,0xd1, + 0x68,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x08,0x00,0x94,0x14,0x53,0x04,0x08,0x00,0x52, + 0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x08,0x00,0xcf, + 0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00,0x51, + 0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x09,0x00,0x52, + 0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0xd3,0x10,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0a,0x00,0x0a,0x00,0x09,0x00,0x52,0x04,0x0a, + 0x00,0x11,0x04,0x0a,0x00,0x0b,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0x55, + 0x04,0x08,0x00,0xd4,0x1c,0x53,0x04,0x08,0x00,0xd2,0x0c,0x51,0x04,0x08,0x00,0x10, + 0x04,0x08,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd3, + 0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0d,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd1,0x6c,0xd0,0x2a,0xcf,0x86,0x55, + 0x04,0x08,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10, + 0x04,0x00,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d, + 0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x55,0x04,0x08,0x00,0xd4,0x1c,0xd3,0x0c,0x52, + 0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00, + 0x00,0x10,0x04,0x00,0x00,0x08,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10, + 0x04,0x00,0x00,0x0c,0x09,0xd0,0x5a,0xcf,0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x93, + 0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x00, + 0x00,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, + 0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, + 0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, + 0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xcf, + 0x86,0x95,0x40,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10, + 0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, + 0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, + 0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, + 0x00,0x0a,0xe6,0xd2,0x9c,0xd1,0x68,0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x08, + 0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x0a,0x00,0x11,0x04,0x08,0x00,0x0a,0x00,0x54, + 0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0d, + 0x00,0x0d,0x00,0x12,0x04,0x0d,0x00,0x10,0x00,0xcf,0x86,0x95,0x30,0x94,0x2c,0xd3, + 0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x12,0x00,0x91,0x08,0x10, + 0x04,0x12,0x00,0x13,0x00,0x13,0x00,0xd2,0x08,0x11,0x04,0x13,0x00,0x14,0x00,0x51, + 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf, + 0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51,0x04,0x04, + 0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04, + 0x00,0x54,0x04,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x06,0xcf,0x06,0x04,0x00,0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0xd5,0x14,0x54, + 0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x00, + 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x04,0x00,0x12,0x04,0x04,0x00,0x00,0x00,0xcf, + 0x86,0xe5,0xa6,0x05,0xe4,0x9f,0x05,0xe3,0x96,0x04,0xe2,0xe4,0x03,0xe1,0xc0,0x01, + 0xd0,0x3e,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c, + 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0xda,0x01,0xe4,0x91,0x08,0x10,0x04,0x01,0xe8, + 0x01,0xde,0x01,0xe0,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x04,0x00,0x10,0x04, + 0x04,0x00,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x04,0x00,0x01,0x00,0xcf,0x86, + 0xd5,0xaa,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81, + 0x8b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x8d,0xe3,0x82, + 0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81, + 0x8f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x91,0xe3,0x82, + 0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x93,0xe3,0x82,0x99, + 0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x95,0xe3,0x82,0x99,0x00,0x01,0x00, + 0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x97,0xe3,0x82,0x99,0x00,0x01, + 0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x99,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f, + 0x10,0x0b,0x01,0xff,0xe3,0x81,0x9b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01, + 0xff,0xe3,0x81,0x9d,0xe3,0x82,0x99,0x00,0x01,0x00,0xd4,0x53,0xd3,0x3c,0xd2,0x1e, + 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x9f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10, + 0x0b,0x01,0xff,0xe3,0x81,0xa1,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x04, + 0x01,0x00,0x01,0xff,0xe3,0x81,0xa4,0xe3,0x82,0x99,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe3,0x81,0xa6,0xe3,0x82,0x99,0x00,0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00, + 0x01,0xff,0xe3,0x81,0xa8,0xe3,0x82,0x99,0x00,0x01,0x00,0x01,0x00,0xd3,0x4a,0xd2, + 0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xaf,0xe3,0x82,0x99,0x00,0x01,0xff, + 0xe3,0x81,0xaf,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x81,0xb2, + 0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb2,0xe3,0x82,0x9a, + 0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb5,0xe3,0x82,0x99,0x00,0x01,0xff, + 0xe3,0x81,0xb5,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe3,0x81,0xb8,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb8,0xe3, + 0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82, + 0x99,0x00,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82,0x9a,0x00,0x01,0x00,0xd0,0xee,0xcf, + 0x86,0xd5,0x42,0x54,0x04,0x01,0x00,0xd3,0x1b,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10, + 0x0b,0x01,0xff,0xe3,0x81,0x86,0xe3,0x82,0x99,0x00,0x06,0x00,0x10,0x04,0x06,0x00, + 0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x08,0x10,0x04,0x01,0x08, + 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0x9d,0xe3,0x82,0x99, + 0x00,0x06,0x00,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x01, + 0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, + 0x82,0xab,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xad,0xe3, + 0x82,0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, + 0x82,0xaf,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb1,0xe3, + 0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb3,0xe3,0x82, + 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb5,0xe3,0x82,0x99,0x00,0x01, + 0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb7,0xe3,0x82,0x99,0x00, + 0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb9,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1, + 0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbb,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b, + 0x01,0xff,0xe3,0x82,0xbd,0xe3,0x82,0x99,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd5,0xd4, + 0x53,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbf,0xe3,0x82, + 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x81,0xe3,0x82,0x99,0x00,0x01, + 0x00,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x84,0xe3,0x82,0x99,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x86,0xe3,0x82,0x99,0x00,0x92,0x13,0x91, + 0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x88,0xe3,0x82,0x99,0x00,0x01,0x00, + 0x01,0x00,0xd3,0x4a,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x83,0x8f,0xe3, + 0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x8f,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00, + 0x01,0xff,0xe3,0x83,0x92,0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, + 0x83,0x92,0xe3,0x82,0x9a,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x95,0xe3, + 0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x95,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f, + 0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x98,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01, + 0xff,0xe3,0x83,0x98,0xe3,0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff, + 0xe3,0x83,0x9b,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x9b,0xe3,0x82,0x9a,0x00, + 0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x22,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b, + 0x01,0xff,0xe3,0x82,0xa6,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe3,0x83,0xaf,0xe3,0x82,0x99,0x00,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff, + 0xe3,0x83,0xb0,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0xb1,0xe3,0x82,0x99,0x00, + 0x10,0x0b,0x01,0xff,0xe3,0x83,0xb2,0xe3,0x82,0x99,0x00,0x01,0x00,0x51,0x04,0x01, + 0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0xbd,0xe3,0x82,0x99,0x00,0x06,0x00,0xd1,0x65, + 0xd0,0x46,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x91,0x08, + 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x18,0x53,0x04, + 0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04, + 0x13,0x00,0x14,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x93,0x11, + 0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x05,0x01,0xff,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x54, + 0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x08,0x00,0x0a,0x00,0x94, + 0x0c,0x93,0x08,0x12,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x06,0x00,0xd2,0xa4,0xd1, + 0x5c,0xd0,0x22,0xcf,0x86,0x95,0x1c,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x10,0x04,0x07,0x00,0x00, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x20,0xd4,0x0c,0x93,0x08,0x12,0x04,0x01,0x00,0x0b, + 0x00,0x0b,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x06,0x00,0x06, + 0x00,0x06,0x00,0x06,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01, + 0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55, + 0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, + 0x00,0x06,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5,0x10,0x94,0x0c,0x53, + 0x04,0x01,0x00,0x12,0x04,0x01,0x00,0x07,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53, + 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x16, + 0x00,0xd1,0x30,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54, + 0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x01,0x00,0x01, + 0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x01,0x00,0x53, + 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x07,0x00,0x54,0x04,0x01, + 0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x07,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd1,0x48,0xd0,0x40,0xcf, + 0x86,0xd5,0x06,0xcf,0x06,0x04,0x00,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x2c,0xd2, + 0x06,0xcf,0x06,0x04,0x00,0xd1,0x06,0xcf,0x06,0x04,0x00,0xd0,0x1a,0xcf,0x86,0x55, + 0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x07,0x00,0xcf,0x06,0x01,0x00,0xcf,0x86,0xcf, + 0x06,0x01,0x00,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe2,0x71,0x05,0xd1,0x8c,0xd0,0x08, + 0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xd4,0x06, + 0xcf,0x06,0x01,0x00,0xd3,0x06,0xcf,0x06,0x01,0x00,0xd2,0x06,0xcf,0x06,0x01,0x00, + 0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x10, + 0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x08,0x00,0x08,0x00,0x53,0x04, + 0x08,0x00,0x12,0x04,0x08,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0xd3,0x08, + 0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0d,0x00, + 0x11,0x00,0x11,0x00,0x93,0x0c,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x13,0x00, + 0x13,0x00,0x94,0x14,0x53,0x04,0x13,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04, + 0x13,0x00,0x14,0x00,0x14,0x00,0x00,0x00,0xe0,0xdb,0x04,0xcf,0x86,0xe5,0xdf,0x01, + 0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x74,0xd2,0x6e,0xd1,0x06,0xcf,0x06,0x04,0x00, + 0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00, + 0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c, + 0x92,0x08,0x11,0x04,0x04,0x00,0x06,0x00,0x04,0x00,0x04,0x00,0x93,0x10,0x52,0x04, + 0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86, + 0x95,0x24,0x94,0x20,0x93,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00, + 0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x10,0x04,0x04,0x00,0x00,0x00, + 0x00,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x06,0x0a,0x00,0xd2,0x84,0xd1,0x4c,0xd0,0x16, + 0xcf,0x86,0x55,0x04,0x0a,0x00,0x94,0x0c,0x53,0x04,0x0a,0x00,0x12,0x04,0x0a,0x00, + 0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x1c,0xd3,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x0a,0x00,0x0a,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00, + 0x10,0x04,0x0a,0x00,0x0a,0xe6,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0d,0xe6,0x52,0x04, + 0x0d,0xe6,0x11,0x04,0x0a,0xe6,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x0a,0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, + 0x11,0xe6,0x0d,0xe6,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00, + 0x93,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x00,0x00,0xd1,0x40, + 0xd0,0x3a,0xcf,0x86,0xd5,0x24,0x54,0x04,0x08,0x00,0xd3,0x10,0x52,0x04,0x08,0x00, + 0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0x92,0x0c,0x51,0x04,0x09,0x00, + 0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04, + 0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x06,0x0a,0x00,0xd0,0x5e, + 0xcf,0x86,0xd5,0x28,0xd4,0x18,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0xd1,0x08, + 0x10,0x04,0x0a,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x11,0x00,0x93,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x0d,0x00,0x10,0x00,0x10,0x00,0xd4,0x1c,0x53,0x04,0x0c,0x00, + 0xd2,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0d,0x00,0x10,0x00,0x51,0x04,0x10,0x00, + 0x10,0x04,0x12,0x00,0x14,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00, + 0x11,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x1c, + 0x94,0x18,0x93,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x51,0x04,0x15,0x00, + 0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x00,0x00,0xd3,0x10, + 0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x92,0x0c, + 0x51,0x04,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0a,0x00,0x0a,0x00,0xe4,0xf2,0x02,0xe3, + 0x65,0x01,0xd2,0x98,0xd1,0x48,0xd0,0x36,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10, + 0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x09,0x08,0x00,0x08,0x00, + 0x08,0x00,0xd4,0x0c,0x53,0x04,0x08,0x00,0x12,0x04,0x08,0x00,0x00,0x00,0x53,0x04, + 0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04, + 0x09,0x00,0x54,0x04,0x09,0x00,0x13,0x04,0x09,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06, + 0x0a,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08, + 0x10,0x04,0x0a,0x09,0x12,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00, + 0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x00,0x00,0x00,0x00, + 0x54,0x04,0x0b,0xe6,0xd3,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00, + 0x52,0x04,0x0b,0x00,0x11,0x04,0x11,0x00,0x14,0x00,0xd1,0x60,0xd0,0x22,0xcf,0x86, + 0x55,0x04,0x0a,0x00,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00, + 0x10,0x04,0x0a,0x00,0x0a,0xdc,0x11,0x04,0x0a,0xdc,0x0a,0x00,0x0a,0x00,0xcf,0x86, + 0xd5,0x24,0x54,0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04, + 0x0a,0x00,0x0a,0x09,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, + 0x00,0x00,0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00, + 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04, + 0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04, + 0x0b,0x00,0x0b,0x07,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x20,0xd3,0x10, + 0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00,0x52,0x04, + 0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x53,0x04,0x0b,0x00, + 0xd2,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x0b,0x00,0x54,0x04, + 0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x00,0x00,0xd2,0xd0,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0a,0x00, + 0x54,0x04,0x0a,0x00,0x93,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04, + 0x0a,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0a,0x00, + 0x52,0x04,0x0a,0x00,0x11,0x04,0x0a,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x92,0x08, + 0x11,0x04,0x0a,0x00,0x00,0x00,0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00, + 0x12,0x04,0x0b,0x00,0x10,0x00,0xd0,0x3a,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04, + 0x0b,0x00,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0xe6, + 0xd1,0x08,0x10,0x04,0x0b,0xdc,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x11,0x04,0x0b,0x00,0x0b,0xe6, + 0xcf,0x86,0xd5,0x2c,0xd4,0x18,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00, + 0x0b,0xe6,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x00,0x00, + 0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00,0x54,0x04, + 0x0d,0x00,0x93,0x10,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x09, + 0x00,0x00,0x00,0x00,0xd1,0x8c,0xd0,0x72,0xcf,0x86,0xd5,0x4c,0xd4,0x30,0xd3,0x18, 0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00, - 0x10,0x04,0x0c,0x00,0x00,0x00,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, - 0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00, - 0x94,0x20,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, - 0x00,0x00,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00, - 0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x11,0x00, - 0x11,0x04,0x10,0x00,0x15,0x00,0x00,0x00,0x11,0x00,0xd0,0x06,0xcf,0x06,0x11,0x00, - 0xcf,0x86,0x55,0x04,0x0b,0x00,0xd4,0x14,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00, - 0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x00,0x00,0x53,0x04,0x0b,0x00,0x92,0x08, - 0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x02,0xff,0xff,0xcf,0x86,0xcf, - 0x06,0x02,0xff,0xff,0xd1,0x76,0xd0,0x09,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xcf, - 0x86,0x85,0xd4,0x07,0xcf,0x06,0x02,0xff,0xff,0xd3,0x07,0xcf,0x06,0x02,0xff,0xff, - 0xd2,0x07,0xcf,0x06,0x02,0xff,0xff,0xd1,0x07,0xcf,0x06,0x02,0xff,0xff,0xd0,0x18, - 0xcf,0x86,0x55,0x05,0x02,0xff,0xff,0x94,0x0d,0x93,0x09,0x12,0x05,0x02,0xff,0xff, - 0x00,0x00,0x00,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3,0x10,0x52,0x04, - 0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x92,0x0c,0x51,0x04, - 0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00,0x0b,0x00,0x54,0x04,0x0b,0x00, - 0x53,0x04,0x0b,0x00,0x12,0x04,0x0b,0x00,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06, - 0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xe4,0x9c,0x10,0xe3,0x16,0x08, - 0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x08,0x04,0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01, - 0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xb1,0x88, - 0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0x10,0x08,0x01,0xff,0xe8,0xbb,0x8a,0x00,0x01, - 0xff,0xe8,0xb3,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xbb,0x91,0x00,0x01, - 0xff,0xe4,0xb8,0xb2,0x00,0x10,0x08,0x01,0xff,0xe5,0x8f,0xa5,0x00,0x01,0xff,0xe9, - 0xbe,0x9c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xbe,0x9c,0x00,0x01, - 0xff,0xe5,0xa5,0x91,0x00,0x10,0x08,0x01,0xff,0xe9,0x87,0x91,0x00,0x01,0xff,0xe5, - 0x96,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xa5,0x88,0x00,0x01,0xff,0xe6, - 0x87,0xb6,0x00,0x10,0x08,0x01,0xff,0xe7,0x99,0xa9,0x00,0x01,0xff,0xe7,0xbe,0x85, - 0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x98,0xbf,0x00,0x01, - 0xff,0xe8,0x9e,0xba,0x00,0x10,0x08,0x01,0xff,0xe8,0xa3,0xb8,0x00,0x01,0xff,0xe9, - 0x82,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xa8,0x82,0x00,0x01,0xff,0xe6, - 0xb4,0x9b,0x00,0x10,0x08,0x01,0xff,0xe7,0x83,0x99,0x00,0x01,0xff,0xe7,0x8f,0x9e, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x90,0xbd,0x00,0x01,0xff,0xe9, - 0x85,0xaa,0x00,0x10,0x08,0x01,0xff,0xe9,0xa7,0xb1,0x00,0x01,0xff,0xe4,0xba,0x82, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x8d,0xb5,0x00,0x01,0xff,0xe6,0xac,0x84, - 0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x9b,0x00,0x01,0xff,0xe8,0x98,0xad,0x00,0xd4, - 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xb8,0x9e,0x00,0x01, - 0xff,0xe5,0xb5,0x90,0x00,0x10,0x08,0x01,0xff,0xe6,0xbf,0xab,0x00,0x01,0xff,0xe8, - 0x97,0x8d,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xa5,0xa4,0x00,0x01,0xff,0xe6, - 0x8b,0x89,0x00,0x10,0x08,0x01,0xff,0xe8,0x87,0x98,0x00,0x01,0xff,0xe8,0xa0,0x9f, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xbb,0x8a,0x00,0x01,0xff,0xe6, - 0x9c,0x97,0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0xaa,0x00,0x01,0xff,0xe7,0x8b,0xbc, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x83,0x8e,0x00,0x01,0xff,0xe4,0xbe,0x86, - 0x00,0x10,0x08,0x01,0xff,0xe5,0x86,0xb7,0x00,0x01,0xff,0xe5,0x8b,0x9e,0x00,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x93,0x84,0x00,0x01,0xff,0xe6, - 0xab,0x93,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x90,0x00,0x01,0xff,0xe7,0x9b,0xa7, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x80,0x81,0x00,0x01,0xff,0xe8,0x98,0x86, - 0x00,0x10,0x08,0x01,0xff,0xe8,0x99,0x9c,0x00,0x01,0xff,0xe8,0xb7,0xaf,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9c,0xb2,0x00,0x01,0xff,0xe9,0xad,0xaf, - 0x00,0x10,0x08,0x01,0xff,0xe9,0xb7,0xba,0x00,0x01,0xff,0xe7,0xa2,0x8c,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe7,0xa5,0xbf,0x00,0x01,0xff,0xe7,0xb6,0xa0,0x00,0x10, - 0x08,0x01,0xff,0xe8,0x8f,0x89,0x00,0x01,0xff,0xe9,0x8c,0x84,0x00,0xcf,0x86,0xe5, - 0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xb9, - 0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0x10,0x08,0x01,0xff,0xe5,0xa3,0x9f,0x00, - 0x01,0xff,0xe5,0xbc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xb1,0xa0,0x00, - 0x01,0xff,0xe8,0x81,0xbe,0x00,0x10,0x08,0x01,0xff,0xe7,0x89,0xa2,0x00,0x01,0xff, - 0xe7,0xa3,0x8a,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xb3,0x82,0x00, - 0x01,0xff,0xe9,0x9b,0xb7,0x00,0x10,0x08,0x01,0xff,0xe5,0xa3,0x98,0x00,0x01,0xff, - 0xe5,0xb1,0xa2,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xa8,0x93,0x00,0x01,0xff, - 0xe6,0xb7,0x9a,0x00,0x10,0x08,0x01,0xff,0xe6,0xbc,0x8f,0x00,0x01,0xff,0xe7,0xb4, - 0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00, - 0x01,0xff,0xe9,0x99,0x8b,0x00,0x10,0x08,0x01,0xff,0xe5,0x8b,0x92,0x00,0x01,0xff, - 0xe8,0x82,0x8b,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x87,0x9c,0x00,0x01,0xff, - 0xe5,0x87,0x8c,0x00,0x10,0x08,0x01,0xff,0xe7,0xa8,0x9c,0x00,0x01,0xff,0xe7,0xb6, - 0xbe,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x8f,0xb1,0x00,0x01,0xff, - 0xe9,0x99,0xb5,0x00,0x10,0x08,0x01,0xff,0xe8,0xae,0x80,0x00,0x01,0xff,0xe6,0x8b, - 0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xa8,0x82,0x00,0x01,0xff,0xe8,0xab, - 0xbe,0x00,0x10,0x08,0x01,0xff,0xe4,0xb8,0xb9,0x00,0x01,0xff,0xe5,0xaf,0xa7,0x00, - 0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x80,0x92,0x00, - 0x01,0xff,0xe7,0x8e,0x87,0x00,0x10,0x08,0x01,0xff,0xe7,0x95,0xb0,0x00,0x01,0xff, - 0xe5,0x8c,0x97,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa3,0xbb,0x00,0x01,0xff, - 0xe4,0xbe,0xbf,0x00,0x10,0x08,0x01,0xff,0xe5,0xbe,0xa9,0x00,0x01,0xff,0xe4,0xb8, - 0x8d,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xb3,0x8c,0x00,0x01,0xff, - 0xe6,0x95,0xb8,0x00,0x10,0x08,0x01,0xff,0xe7,0xb4,0xa2,0x00,0x01,0xff,0xe5,0x8f, - 0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xa1,0x9e,0x00,0x01,0xff,0xe7,0x9c, - 0x81,0x00,0x10,0x08,0x01,0xff,0xe8,0x91,0x89,0x00,0x01,0xff,0xe8,0xaa,0xaa,0x00, - 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xae,0xba,0x00,0x01,0xff, - 0xe8,0xbe,0xb0,0x00,0x10,0x08,0x01,0xff,0xe6,0xb2,0x88,0x00,0x01,0xff,0xe6,0x8b, - 0xbe,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x8b,0xa5,0x00,0x01,0xff,0xe6,0x8e, - 0xa0,0x00,0x10,0x08,0x01,0xff,0xe7,0x95,0xa5,0x00,0x01,0xff,0xe4,0xba,0xae,0x00, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x85,0xa9,0x00,0x01,0xff,0xe5,0x87, - 0x89,0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0x81,0x00,0x01,0xff,0xe7,0xb3,0xa7,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x89,0xaf,0x00,0x01,0xff,0xe8,0xab,0x92,0x00, - 0x10,0x08,0x01,0xff,0xe9,0x87,0x8f,0x00,0x01,0xff,0xe5,0x8b,0xb5,0x00,0xe0,0x04, - 0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe5,0x91,0x82,0x00,0x01,0xff,0xe5,0xa5,0xb3,0x00,0x10,0x08,0x01,0xff, - 0xe5,0xbb,0xac,0x00,0x01,0xff,0xe6,0x97,0x85,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe6,0xbf,0xbe,0x00,0x01,0xff,0xe7,0xa4,0xaa,0x00,0x10,0x08,0x01,0xff,0xe9,0x96, - 0xad,0x00,0x01,0xff,0xe9,0xa9,0xaa,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe9,0xba,0x97,0x00,0x01,0xff,0xe9,0xbb,0x8e,0x00,0x10,0x08,0x01,0xff,0xe5,0x8a, - 0x9b,0x00,0x01,0xff,0xe6,0x9b,0x86,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xad, - 0xb7,0x00,0x01,0xff,0xe8,0xbd,0xa2,0x00,0x10,0x08,0x01,0xff,0xe5,0xb9,0xb4,0x00, - 0x01,0xff,0xe6,0x86,0x90,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe6,0x88,0x80,0x00,0x01,0xff,0xe6,0x92,0x9a,0x00,0x10,0x08,0x01,0xff,0xe6,0xbc, - 0xa3,0x00,0x01,0xff,0xe7,0x85,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0x92, - 0x89,0x00,0x01,0xff,0xe7,0xa7,0x8a,0x00,0x10,0x08,0x01,0xff,0xe7,0xb7,0xb4,0x00, - 0x01,0xff,0xe8,0x81,0xaf,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xbc, - 0xa6,0x00,0x01,0xff,0xe8,0x93,0xae,0x00,0x10,0x08,0x01,0xff,0xe9,0x80,0xa3,0x00, - 0x01,0xff,0xe9,0x8d,0x8a,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x88,0x97,0x00, - 0x01,0xff,0xe5,0x8a,0xa3,0x00,0x10,0x08,0x01,0xff,0xe5,0x92,0xbd,0x00,0x01,0xff, - 0xe7,0x83,0x88,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe8,0xa3,0x82,0x00,0x01,0xff,0xe8,0xaa,0xaa,0x00,0x10,0x08,0x01,0xff,0xe5,0xbb, - 0x89,0x00,0x01,0xff,0xe5,0xbf,0xb5,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x8d, - 0xbb,0x00,0x01,0xff,0xe6,0xae,0xae,0x00,0x10,0x08,0x01,0xff,0xe7,0xb0,0xbe,0x00, - 0x01,0xff,0xe7,0x8d,0xb5,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe4,0xbb, - 0xa4,0x00,0x01,0xff,0xe5,0x9b,0xb9,0x00,0x10,0x08,0x01,0xff,0xe5,0xaf,0xa7,0x00, - 0x01,0xff,0xe5,0xb6,0xba,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x80,0x9c,0x00, - 0x01,0xff,0xe7,0x8e,0xb2,0x00,0x10,0x08,0x01,0xff,0xe7,0x91,0xa9,0x00,0x01,0xff, - 0xe7,0xbe,0x9a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x81, - 0x86,0x00,0x01,0xff,0xe9,0x88,0xb4,0x00,0x10,0x08,0x01,0xff,0xe9,0x9b,0xb6,0x00, - 0x01,0xff,0xe9,0x9d,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xa0,0x98,0x00, - 0x01,0xff,0xe4,0xbe,0x8b,0x00,0x10,0x08,0x01,0xff,0xe7,0xa6,0xae,0x00,0x01,0xff, - 0xe9,0x86,0xb4,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9a,0xb8,0x00, - 0x01,0xff,0xe6,0x83,0xa1,0x00,0x10,0x08,0x01,0xff,0xe4,0xba,0x86,0x00,0x01,0xff, - 0xe5,0x83,0x9a,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xaf,0xae,0x00,0x01,0xff, - 0xe5,0xb0,0xbf,0x00,0x10,0x08,0x01,0xff,0xe6,0x96,0x99,0x00,0x01,0xff,0xe6,0xa8, - 0x82,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe7,0x87,0x8e,0x00,0x01,0xff,0xe7,0x99,0x82,0x00,0x10,0x08,0x01, - 0xff,0xe8,0x93,0xbc,0x00,0x01,0xff,0xe9,0x81,0xbc,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe9,0xbe,0x8d,0x00,0x01,0xff,0xe6,0x9a,0x88,0x00,0x10,0x08,0x01,0xff,0xe9, - 0x98,0xae,0x00,0x01,0xff,0xe5,0x8a,0x89,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe6,0x9d,0xbb,0x00,0x01,0xff,0xe6,0x9f,0xb3,0x00,0x10,0x08,0x01,0xff,0xe6, - 0xb5,0x81,0x00,0x01,0xff,0xe6,0xba,0x9c,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7, - 0x90,0x89,0x00,0x01,0xff,0xe7,0x95,0x99,0x00,0x10,0x08,0x01,0xff,0xe7,0xa1,0xab, - 0x00,0x01,0xff,0xe7,0xb4,0x90,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe9,0xa1,0x9e,0x00,0x01,0xff,0xe5,0x85,0xad,0x00,0x10,0x08,0x01,0xff,0xe6, - 0x88,0xae,0x00,0x01,0xff,0xe9,0x99,0xb8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, - 0x80,0xab,0x00,0x01,0xff,0xe5,0xb4,0x99,0x00,0x10,0x08,0x01,0xff,0xe6,0xb7,0xaa, - 0x00,0x01,0xff,0xe8,0xbc,0xaa,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, - 0xbe,0x8b,0x00,0x01,0xff,0xe6,0x85,0x84,0x00,0x10,0x08,0x01,0xff,0xe6,0xa0,0x97, - 0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9a,0x86, - 0x00,0x01,0xff,0xe5,0x88,0xa9,0x00,0x10,0x08,0x01,0xff,0xe5,0x90,0x8f,0x00,0x01, - 0xff,0xe5,0xb1,0xa5,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe6,0x98,0x93,0x00,0x01,0xff,0xe6,0x9d,0x8e,0x00,0x10,0x08,0x01,0xff,0xe6, - 0xa2,0xa8,0x00,0x01,0xff,0xe6,0xb3,0xa5,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7, - 0x90,0x86,0x00,0x01,0xff,0xe7,0x97,0xa2,0x00,0x10,0x08,0x01,0xff,0xe7,0xbd,0xb9, - 0x00,0x01,0xff,0xe8,0xa3,0x8f,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, - 0xa3,0xa1,0x00,0x01,0xff,0xe9,0x87,0x8c,0x00,0x10,0x08,0x01,0xff,0xe9,0x9b,0xa2, - 0x00,0x01,0xff,0xe5,0x8c,0xbf,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xba,0xba, - 0x00,0x01,0xff,0xe5,0x90,0x9d,0x00,0x10,0x08,0x01,0xff,0xe7,0x87,0x90,0x00,0x01, - 0xff,0xe7,0x92,0x98,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, - 0x97,0xba,0x00,0x01,0xff,0xe9,0x9a,0xa3,0x00,0x10,0x08,0x01,0xff,0xe9,0xb1,0x97, - 0x00,0x01,0xff,0xe9,0xba,0x9f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x9e,0x97, - 0x00,0x01,0xff,0xe6,0xb7,0x8b,0x00,0x10,0x08,0x01,0xff,0xe8,0x87,0xa8,0x00,0x01, - 0xff,0xe7,0xab,0x8b,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xac,0xa0, - 0x00,0x01,0xff,0xe7,0xb2,0x92,0x00,0x10,0x08,0x01,0xff,0xe7,0x8b,0x80,0x00,0x01, - 0xff,0xe7,0x82,0x99,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xad,0x98,0x00,0x01, - 0xff,0xe4,0xbb,0x80,0x00,0x10,0x08,0x01,0xff,0xe8,0x8c,0xb6,0x00,0x01,0xff,0xe5, - 0x88,0xba,0x00,0xe2,0xad,0x06,0xe1,0xc4,0x03,0xe0,0xcb,0x01,0xcf,0x86,0xd5,0xe4, - 0xd4,0x74,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x88,0x87,0x00, - 0x01,0xff,0xe5,0xba,0xa6,0x00,0x10,0x08,0x01,0xff,0xe6,0x8b,0x93,0x00,0x01,0xff, - 0xe7,0xb3,0x96,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xae,0x85,0x00,0x01,0xff, - 0xe6,0xb4,0x9e,0x00,0x10,0x08,0x01,0xff,0xe6,0x9a,0xb4,0x00,0x01,0xff,0xe8,0xbc, - 0xbb,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xa1,0x8c,0x00,0x01,0xff, - 0xe9,0x99,0x8d,0x00,0x10,0x08,0x01,0xff,0xe8,0xa6,0x8b,0x00,0x01,0xff,0xe5,0xbb, - 0x93,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0xe5,0x85,0x80,0x00,0x01,0xff,0xe5,0x97, - 0x80,0x00,0x01,0x00,0xd3,0x34,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x01,0xff,0xe5,0xa1, - 0x9a,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe6,0x99,0xb4,0x00,0x01,0x00,0xd1,0x0c, - 0x10,0x04,0x01,0x00,0x01,0xff,0xe5,0x87,0x9e,0x00,0x10,0x08,0x01,0xff,0xe7,0x8c, - 0xaa,0x00,0x01,0xff,0xe7,0x9b,0x8a,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe7,0xa4,0xbc,0x00,0x01,0xff,0xe7,0xa5,0x9e,0x00,0x10,0x08,0x01,0xff,0xe7,0xa5, - 0xa5,0x00,0x01,0xff,0xe7,0xa6,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9d, - 0x96,0x00,0x01,0xff,0xe7,0xb2,0xbe,0x00,0x10,0x08,0x01,0xff,0xe7,0xbe,0xbd,0x00, - 0x01,0x00,0xd4,0x64,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x01,0xff,0xe8,0x98, - 0x92,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe8,0xab,0xb8,0x00,0x01,0x00,0xd1,0x0c, - 0x10,0x04,0x01,0x00,0x01,0xff,0xe9,0x80,0xb8,0x00,0x10,0x08,0x01,0xff,0xe9,0x83, - 0xbd,0x00,0x01,0x00,0xd2,0x14,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe9,0xa3, - 0xaf,0x00,0x01,0xff,0xe9,0xa3,0xbc,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xa4, - 0xa8,0x00,0x01,0xff,0xe9,0xb6,0xb4,0x00,0x10,0x08,0x0d,0xff,0xe9,0x83,0x9e,0x00, - 0x0d,0xff,0xe9,0x9a,0xb7,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff, - 0xe4,0xbe,0xae,0x00,0x06,0xff,0xe5,0x83,0xa7,0x00,0x10,0x08,0x06,0xff,0xe5,0x85, - 0x8d,0x00,0x06,0xff,0xe5,0x8b,0x89,0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe5,0x8b, - 0xa4,0x00,0x06,0xff,0xe5,0x8d,0x91,0x00,0x10,0x08,0x06,0xff,0xe5,0x96,0x9d,0x00, - 0x06,0xff,0xe5,0x98,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe5,0x99, - 0xa8,0x00,0x06,0xff,0xe5,0xa1,0x80,0x00,0x10,0x08,0x06,0xff,0xe5,0xa2,0xa8,0x00, - 0x06,0xff,0xe5,0xb1,0xa4,0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe5,0xb1,0xae,0x00, - 0x06,0xff,0xe6,0x82,0x94,0x00,0x10,0x08,0x06,0xff,0xe6,0x85,0xa8,0x00,0x06,0xff, - 0xe6,0x86,0x8e,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x06,0xff,0xe6,0x87,0xb2,0x00,0x06,0xff,0xe6,0x95,0x8f,0x00,0x10, - 0x08,0x06,0xff,0xe6,0x97,0xa2,0x00,0x06,0xff,0xe6,0x9a,0x91,0x00,0xd1,0x10,0x10, - 0x08,0x06,0xff,0xe6,0xa2,0x85,0x00,0x06,0xff,0xe6,0xb5,0xb7,0x00,0x10,0x08,0x06, - 0xff,0xe6,0xb8,0x9a,0x00,0x06,0xff,0xe6,0xbc,0xa2,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x06,0xff,0xe7,0x85,0xae,0x00,0x06,0xff,0xe7,0x88,0xab,0x00,0x10,0x08,0x06, - 0xff,0xe7,0x90,0xa2,0x00,0x06,0xff,0xe7,0xa2,0x91,0x00,0xd1,0x10,0x10,0x08,0x06, - 0xff,0xe7,0xa4,0xbe,0x00,0x06,0xff,0xe7,0xa5,0x89,0x00,0x10,0x08,0x06,0xff,0xe7, - 0xa5,0x88,0x00,0x06,0xff,0xe7,0xa5,0x90,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x06,0xff,0xe7,0xa5,0x96,0x00,0x06,0xff,0xe7,0xa5,0x9d,0x00,0x10,0x08,0x06, - 0xff,0xe7,0xa6,0x8d,0x00,0x06,0xff,0xe7,0xa6,0x8e,0x00,0xd1,0x10,0x10,0x08,0x06, - 0xff,0xe7,0xa9,0x80,0x00,0x06,0xff,0xe7,0xaa,0x81,0x00,0x10,0x08,0x06,0xff,0xe7, - 0xaf,0x80,0x00,0x06,0xff,0xe7,0xb7,0xb4,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06, - 0xff,0xe7,0xb8,0x89,0x00,0x06,0xff,0xe7,0xb9,0x81,0x00,0x10,0x08,0x06,0xff,0xe7, - 0xbd,0xb2,0x00,0x06,0xff,0xe8,0x80,0x85,0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8, - 0x87,0xad,0x00,0x06,0xff,0xe8,0x89,0xb9,0x00,0x10,0x08,0x06,0xff,0xe8,0x89,0xb9, - 0x00,0x06,0xff,0xe8,0x91,0x97,0x00,0xd4,0x75,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x06,0xff,0xe8,0xa4,0x90,0x00,0x06,0xff,0xe8,0xa6,0x96,0x00,0x10,0x08,0x06, - 0xff,0xe8,0xac,0x81,0x00,0x06,0xff,0xe8,0xac,0xb9,0x00,0xd1,0x10,0x10,0x08,0x06, - 0xff,0xe8,0xb3,0x93,0x00,0x06,0xff,0xe8,0xb4,0x88,0x00,0x10,0x08,0x06,0xff,0xe8, - 0xbe,0xb6,0x00,0x06,0xff,0xe9,0x80,0xb8,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06, - 0xff,0xe9,0x9b,0xa3,0x00,0x06,0xff,0xe9,0x9f,0xbf,0x00,0x10,0x08,0x06,0xff,0xe9, - 0xa0,0xbb,0x00,0x0b,0xff,0xe6,0x81,0xb5,0x00,0x91,0x11,0x10,0x09,0x0b,0xff,0xf0, - 0xa4,0x8b,0xae,0x00,0x0b,0xff,0xe8,0x88,0x98,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x08,0xff,0xe4,0xb8,0xa6,0x00,0x08,0xff,0xe5,0x86,0xb5,0x00, - 0x10,0x08,0x08,0xff,0xe5,0x85,0xa8,0x00,0x08,0xff,0xe4,0xbe,0x80,0x00,0xd1,0x10, - 0x10,0x08,0x08,0xff,0xe5,0x85,0x85,0x00,0x08,0xff,0xe5,0x86,0x80,0x00,0x10,0x08, - 0x08,0xff,0xe5,0x8b,0x87,0x00,0x08,0xff,0xe5,0x8b,0xba,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x08,0xff,0xe5,0x96,0x9d,0x00,0x08,0xff,0xe5,0x95,0x95,0x00,0x10,0x08, - 0x08,0xff,0xe5,0x96,0x99,0x00,0x08,0xff,0xe5,0x97,0xa2,0x00,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe5,0xa1,0x9a,0x00,0x08,0xff,0xe5,0xa2,0xb3,0x00,0x10,0x08,0x08,0xff, - 0xe5,0xa5,0x84,0x00,0x08,0xff,0xe5,0xa5,0x94,0x00,0xe0,0x04,0x02,0xcf,0x86,0xe5, - 0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0xa9, - 0xa2,0x00,0x08,0xff,0xe5,0xac,0xa8,0x00,0x10,0x08,0x08,0xff,0xe5,0xbb,0x92,0x00, - 0x08,0xff,0xe5,0xbb,0x99,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0xbd,0xa9,0x00, - 0x08,0xff,0xe5,0xbe,0xad,0x00,0x10,0x08,0x08,0xff,0xe6,0x83,0x98,0x00,0x08,0xff, - 0xe6,0x85,0x8e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe6,0x84,0x88,0x00, - 0x08,0xff,0xe6,0x86,0x8e,0x00,0x10,0x08,0x08,0xff,0xe6,0x85,0xa0,0x00,0x08,0xff, - 0xe6,0x87,0xb2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe6,0x88,0xb4,0x00,0x08,0xff, - 0xe6,0x8f,0x84,0x00,0x10,0x08,0x08,0xff,0xe6,0x90,0x9c,0x00,0x08,0xff,0xe6,0x91, - 0x92,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe6,0x95,0x96,0x00, - 0x08,0xff,0xe6,0x99,0xb4,0x00,0x10,0x08,0x08,0xff,0xe6,0x9c,0x97,0x00,0x08,0xff, - 0xe6,0x9c,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe6,0x9d,0x96,0x00,0x08,0xff, - 0xe6,0xad,0xb9,0x00,0x10,0x08,0x08,0xff,0xe6,0xae,0xba,0x00,0x08,0xff,0xe6,0xb5, - 0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe6,0xbb,0x9b,0x00,0x08,0xff, - 0xe6,0xbb,0x8b,0x00,0x10,0x08,0x08,0xff,0xe6,0xbc,0xa2,0x00,0x08,0xff,0xe7,0x80, - 0x9e,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x85,0xae,0x00,0x08,0xff,0xe7,0x9e, - 0xa7,0x00,0x10,0x08,0x08,0xff,0xe7,0x88,0xb5,0x00,0x08,0xff,0xe7,0x8a,0xaf,0x00, - 0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x8c,0xaa,0x00, - 0x08,0xff,0xe7,0x91,0xb1,0x00,0x10,0x08,0x08,0xff,0xe7,0x94,0x86,0x00,0x08,0xff, - 0xe7,0x94,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x98,0x9d,0x00,0x08,0xff, - 0xe7,0x98,0x9f,0x00,0x10,0x08,0x08,0xff,0xe7,0x9b,0x8a,0x00,0x08,0xff,0xe7,0x9b, - 0x9b,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x9b,0xb4,0x00,0x08,0xff, - 0xe7,0x9d,0x8a,0x00,0x10,0x08,0x08,0xff,0xe7,0x9d,0x80,0x00,0x08,0xff,0xe7,0xa3, - 0x8c,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0xaa,0xb1,0x00,0x08,0xff,0xe7,0xaf, - 0x80,0x00,0x10,0x08,0x08,0xff,0xe7,0xb1,0xbb,0x00,0x08,0xff,0xe7,0xb5,0x9b,0x00, - 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0xb7,0xb4,0x00,0x08,0xff, - 0xe7,0xbc,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0x80,0x85,0x00,0x08,0xff,0xe8,0x8d, - 0x92,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0x8f,0xaf,0x00,0x08,0xff,0xe8,0x9d, - 0xb9,0x00,0x10,0x08,0x08,0xff,0xe8,0xa5,0x81,0x00,0x08,0xff,0xe8,0xa6,0x86,0x00, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xa6,0x96,0x00,0x08,0xff,0xe8,0xaa, - 0xbf,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xb8,0x00,0x08,0xff,0xe8,0xab,0x8b,0x00, - 0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xac,0x81,0x00,0x08,0xff,0xe8,0xab,0xbe,0x00, - 0x10,0x08,0x08,0xff,0xe8,0xab,0xad,0x00,0x08,0xff,0xe8,0xac,0xb9,0x00,0xcf,0x86, - 0x95,0xde,0xd4,0x81,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xae, - 0x8a,0x00,0x08,0xff,0xe8,0xb4,0x88,0x00,0x10,0x08,0x08,0xff,0xe8,0xbc,0xb8,0x00, - 0x08,0xff,0xe9,0x81,0xb2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe9,0x86,0x99,0x00, - 0x08,0xff,0xe9,0x89,0xb6,0x00,0x10,0x08,0x08,0xff,0xe9,0x99,0xbc,0x00,0x08,0xff, - 0xe9,0x9b,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe9,0x9d,0x96,0x00, - 0x08,0xff,0xe9,0x9f,0x9b,0x00,0x10,0x08,0x08,0xff,0xe9,0x9f,0xbf,0x00,0x08,0xff, - 0xe9,0xa0,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe9,0xa0,0xbb,0x00,0x08,0xff, - 0xe9,0xac,0x92,0x00,0x10,0x08,0x08,0xff,0xe9,0xbe,0x9c,0x00,0x08,0xff,0xf0,0xa2, - 0xa1,0x8a,0x00,0xd3,0x45,0xd2,0x22,0xd1,0x12,0x10,0x09,0x08,0xff,0xf0,0xa2,0xa1, - 0x84,0x00,0x08,0xff,0xf0,0xa3,0x8f,0x95,0x00,0x10,0x08,0x08,0xff,0xe3,0xae,0x9d, - 0x00,0x08,0xff,0xe4,0x80,0x98,0x00,0xd1,0x11,0x10,0x08,0x08,0xff,0xe4,0x80,0xb9, - 0x00,0x08,0xff,0xf0,0xa5,0x89,0x89,0x00,0x10,0x09,0x08,0xff,0xf0,0xa5,0xb3,0x90, - 0x00,0x08,0xff,0xf0,0xa7,0xbb,0x93,0x00,0x92,0x14,0x91,0x10,0x10,0x08,0x08,0xff, - 0xe9,0xbd,0x83,0x00,0x08,0xff,0xe9,0xbe,0x8e,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xe1,0x94,0x01,0xe0,0x08,0x01,0xcf,0x86,0xd5,0x42,0xd4,0x14,0x93,0x10,0x52,0x04, - 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd3,0x10, - 0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04, - 0x00,0x00,0xd1,0x0d,0x10,0x04,0x00,0x00,0x04,0xff,0xd7,0x99,0xd6,0xb4,0x00,0x10, - 0x04,0x01,0x1a,0x01,0xff,0xd7,0xb2,0xd6,0xb7,0x00,0xd4,0x42,0x53,0x04,0x01,0x00, - 0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd7,0xa9,0xd7,0x81,0x00,0x01, - 0xff,0xd7,0xa9,0xd7,0x82,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xd7,0xa9,0xd6,0xbc, - 0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7,0x82,0x00,0x10,0x09,0x01,0xff, - 0xd7,0x90,0xd6,0xb7,0x00,0x01,0xff,0xd7,0x90,0xd6,0xb8,0x00,0xd3,0x43,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xbc,0x00,0x01,0xff,0xd7,0x91,0xd6, - 0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x92,0xd6,0xbc,0x00,0x01,0xff,0xd7,0x93,0xd6, - 0xbc,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x94,0xd6,0xbc,0x00,0x01,0xff,0xd7, - 0x95,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x96,0xd6,0xbc,0x00,0x00,0x00,0xd2, - 0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x98,0xd6,0xbc,0x00,0x01,0xff,0xd7,0x99, - 0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x9a,0xd6,0xbc,0x00,0x01,0xff,0xd7,0x9b, - 0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7,0x9c,0xd6,0xbc,0x00,0x00,0x00, - 0x10,0x09,0x01,0xff,0xd7,0x9e,0xd6,0xbc,0x00,0x00,0x00,0xcf,0x86,0x95,0x85,0x94, - 0x81,0xd3,0x3e,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0xa0,0xd6,0xbc,0x00, - 0x01,0xff,0xd7,0xa1,0xd6,0xbc,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xd7,0xa3,0xd6, - 0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7,0xa4,0xd6,0xbc,0x00,0x00,0x00,0x10, - 0x09,0x01,0xff,0xd7,0xa6,0xd6,0xbc,0x00,0x01,0xff,0xd7,0xa7,0xd6,0xbc,0x00,0xd2, - 0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0xa8,0xd6,0xbc,0x00,0x01,0xff,0xd7,0xa9, - 0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0xaa,0xd6,0xbc,0x00,0x01,0xff,0xd7,0x95, - 0xd6,0xb9,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x91,0xd6,0xbf,0x00,0x01,0xff, - 0xd7,0x9b,0xd6,0xbf,0x00,0x10,0x09,0x01,0xff,0xd7,0xa4,0xd6,0xbf,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00, - 0x93,0x0c,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86, - 0x95,0x24,0xd4,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x0c,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0xd3,0x5a,0xd2,0x06,0xcf,0x06,0x01,0x00,0xd1,0x14, - 0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x95,0x08,0x14,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54,0x04,0x01,0x00,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x0c, - 0x94,0x08,0x13,0x04,0x01,0x00,0x00,0x00,0x05,0x00,0x54,0x04,0x05,0x00,0x53,0x04, - 0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x07,0x00,0x00,0x00, - 0xd2,0xcc,0xd1,0xa4,0xd0,0x36,0xcf,0x86,0xd5,0x14,0x54,0x04,0x06,0x00,0x53,0x04, - 0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x94,0x1c,0xd3,0x10, - 0x52,0x04,0x01,0xe6,0x51,0x04,0x0a,0xe6,0x10,0x04,0x0a,0xe6,0x10,0xdc,0x52,0x04, - 0x10,0xdc,0x11,0x04,0x10,0xdc,0x11,0xe6,0x01,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24, - 0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, - 0x06,0x00,0x07,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00, - 0x01,0x00,0x01,0x00,0xd4,0x18,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00, - 0x10,0x04,0x01,0x00,0x00,0x00,0x12,0x04,0x01,0x00,0x00,0x00,0x93,0x18,0xd2,0x0c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04, - 0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08, - 0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd1,0x50,0xd0,0x1e, - 0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18, - 0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00, - 0x10,0x04,0x01,0x00,0x06,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x06,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86, - 0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x18, - 0xd3,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x92,0x08,0x11,0x04, - 0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0xd2,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x00,0x00,0xd4,0x20,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00, - 0x10,0x04,0x01,0x00,0x00,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04, - 0x01,0x00,0x00,0x00,0x53,0x04,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, - 0x04,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x03,0x00,0x01,0x00,0x01,0x00,0x83,0xe2, - 0x30,0x3e,0xe1,0x1a,0x3b,0xe0,0x97,0x39,0xcf,0x86,0xe5,0x3b,0x26,0xc4,0xe3,0x16, - 0x14,0xe2,0xef,0x11,0xe1,0xd0,0x10,0xe0,0x60,0x07,0xcf,0x86,0xe5,0x53,0x03,0xe4, - 0x4c,0x02,0xe3,0x3d,0x01,0xd2,0x94,0xd1,0x70,0xd0,0x4a,0xcf,0x86,0xd5,0x18,0x94, - 0x14,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07, - 0x00,0x07,0x00,0x07,0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07, - 0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x07,0x00,0x53,0x04,0x07,0x00,0xd2,0x0c,0x51, - 0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00, - 0x00,0x07,0x00,0xcf,0x86,0x95,0x20,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04,0x07, - 0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11, - 0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0x55, - 0x04,0x07,0x00,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x92,0x0c,0x51,0x04,0x07, - 0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5, - 0x20,0x94,0x1c,0x93,0x18,0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00, - 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54, - 0x04,0x07,0x00,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00, - 0x00,0x07,0x00,0x07,0x00,0xcf,0x06,0x08,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4, - 0x20,0x53,0x04,0x08,0x00,0xd2,0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x10, - 0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x53, - 0x04,0x0a,0x00,0x12,0x04,0x0a,0x00,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf, - 0x86,0xd5,0x08,0x14,0x04,0x00,0x00,0x0a,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a, - 0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0a,0xdc,0x00,0x00,0xd2, - 0x5e,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x0a, - 0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00, - 0x00,0x00,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x0a,0x00,0x93,0x10,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd4, - 0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0xdc,0x10,0x00,0x10,0x00,0x10, - 0x00,0x10,0x00,0x53,0x04,0x10,0x00,0x12,0x04,0x10,0x00,0x00,0x00,0xd1,0x70,0xd0, - 0x36,0xcf,0x86,0xd5,0x18,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05, - 0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x10,0x00,0x94,0x18,0xd3,0x08,0x12, - 0x04,0x05,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x13, - 0x00,0x13,0x00,0x05,0x00,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x05,0x00,0x92, - 0x0c,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x54, - 0x04,0x10,0x00,0xd3,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x10,0xe6,0x92, - 0x0c,0x51,0x04,0x10,0xe6,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf, - 0x86,0x95,0x18,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x51, - 0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0x08,0x00,0xcf,0x86,0x95,0x1c,0xd4, - 0x0c,0x93,0x08,0x12,0x04,0x08,0x00,0x00,0x00,0x08,0x00,0x93,0x0c,0x52,0x04,0x08, - 0x00,0x11,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0xba,0xd2,0x80,0xd1, - 0x34,0xd0,0x1a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x05, - 0x00,0x11,0x04,0x05,0x00,0x07,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0x95,0x14,0x94, - 0x10,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x07,0x00,0x07, - 0x00,0x07,0x00,0xd0,0x2a,0xcf,0x86,0xd5,0x14,0x54,0x04,0x07,0x00,0x53,0x04,0x07, - 0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x94,0x10,0x53,0x04,0x07, - 0x00,0x92,0x08,0x11,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xcf,0x86,0xd5, - 0x10,0x54,0x04,0x12,0x00,0x93,0x08,0x12,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x54, - 0x04,0x12,0x00,0x53,0x04,0x12,0x00,0x12,0x04,0x12,0x00,0x00,0x00,0xd1,0x34,0xd0, - 0x12,0xcf,0x86,0x55,0x04,0x10,0x00,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x10, - 0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x10,0x00,0x00, - 0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x10,0x00,0xd1,0x40,0xd0,0x1e,0xcf, - 0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00,0x51, - 0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x14,0x54, - 0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x00, - 0x00,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe4, - 0xce,0x02,0xe3,0x45,0x01,0xd2,0xd0,0xd1,0x70,0xd0,0x52,0xcf,0x86,0xd5,0x20,0x94, - 0x1c,0xd3,0x0c,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x07,0x00,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07, - 0x00,0xd3,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07, - 0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xd1,0x08,0x10, - 0x04,0x07,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86,0x95,0x18,0x54, - 0x04,0x0b,0x00,0x93,0x10,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00, - 0x00,0x0b,0x00,0x0b,0x00,0x10,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10, - 0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10, - 0x00,0x00,0x00,0x94,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10, - 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, - 0x04,0x11,0x00,0xd3,0x14,0xd2,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00, - 0x00,0x11,0x04,0x11,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00, - 0x00,0x11,0x00,0x11,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x1c,0x54,0x04,0x09, - 0x00,0x53,0x04,0x09,0x00,0xd2,0x08,0x11,0x04,0x09,0x00,0x0b,0x00,0x51,0x04,0x00, - 0x00,0x10,0x04,0x00,0x00,0x09,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2, - 0x08,0x11,0x04,0x0a,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a, - 0x00,0xcf,0x06,0x00,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d, - 0x00,0x53,0x04,0x0d,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x11,0x00,0x0d,0x00,0xcf, - 0x86,0x95,0x14,0x54,0x04,0x11,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x11, - 0x00,0x11,0x00,0x11,0x00,0x11,0x00,0xd2,0xec,0xd1,0xa4,0xd0,0x76,0xcf,0x86,0xd5, - 0x48,0xd4,0x28,0xd3,0x14,0x52,0x04,0x08,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x08, - 0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x08, - 0x00,0x08,0xdc,0x10,0x04,0x08,0x00,0x08,0xe6,0xd3,0x10,0x52,0x04,0x08,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00, - 0x00,0x08,0x00,0x08,0x00,0x08,0x00,0x54,0x04,0x08,0x00,0xd3,0x0c,0x52,0x04,0x08, - 0x00,0x11,0x04,0x14,0x00,0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe6,0x08, - 0x01,0x10,0x04,0x08,0xdc,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x08, - 0x09,0xcf,0x86,0x95,0x28,0xd4,0x14,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd0,0x0a,0xcf, - 0x86,0x15,0x04,0x10,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x24,0xd3, - 0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0xe6,0x10,0x04,0x10, - 0xdc,0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10, - 0x00,0x93,0x10,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00, - 0x00,0x00,0x00,0xd1,0x54,0xd0,0x26,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b, - 0x00,0xd3,0x0c,0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x14,0x54, - 0x04,0x0b,0x00,0x93,0x0c,0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x0b, - 0x00,0x54,0x04,0x0b,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, - 0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x54,0x04,0x10, - 0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c,0x91, - 0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00, - 0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00, - 0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x96,0xd2, - 0x68,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x0b,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53, - 0x04,0x0b,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x11,0x00,0x54,0x04,0x11, - 0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0xd3,0x10,0x92, - 0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x92,0x08,0x11, - 0x04,0x00,0x00,0x11,0x00,0x11,0x00,0xd1,0x28,0xd0,0x22,0xcf,0x86,0x55,0x04,0x14, - 0x00,0xd4,0x0c,0x93,0x08,0x12,0x04,0x14,0x00,0x14,0xe6,0x00,0x00,0x53,0x04,0x14, - 0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xd2,0x2a,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55, - 0x04,0x00,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51, - 0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x58,0xd0, - 0x12,0xcf,0x86,0x55,0x04,0x14,0x00,0x94,0x08,0x13,0x04,0x14,0x00,0x00,0x00,0x14, - 0x00,0xcf,0x86,0x95,0x40,0xd4,0x24,0xd3,0x0c,0x52,0x04,0x14,0x00,0x11,0x04,0x14, - 0x00,0x14,0xdc,0xd2,0x0c,0x51,0x04,0x14,0xe6,0x10,0x04,0x14,0xe6,0x14,0xdc,0x91, - 0x08,0x10,0x04,0x14,0xe6,0x14,0xdc,0x14,0xdc,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x14,0xdc,0x14,0x00,0x14,0x00,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00, - 0x00,0x54,0x04,0x15,0x00,0x93,0x10,0x52,0x04,0x15,0x00,0x51,0x04,0x15,0x00,0x10, - 0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xe5,0x0f,0x06,0xe4,0xf8,0x03,0xe3, - 0x02,0x02,0xd2,0xfb,0xd1,0x4c,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0xd5,0x2c, - 0xd4,0x1c,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x09, - 0x0c,0x00,0x52,0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x00,0x00,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04, - 0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x09, - 0xd0,0x69,0xcf,0x86,0xd5,0x32,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0xd2,0x15, - 0x51,0x04,0x0b,0x00,0x10,0x0d,0x0b,0xff,0xf0,0x91,0x82,0x99,0xf0,0x91,0x82,0xba, - 0x00,0x0b,0x00,0x91,0x11,0x10,0x0d,0x0b,0xff,0xf0,0x91,0x82,0x9b,0xf0,0x91,0x82, - 0xba,0x00,0x0b,0x00,0x0b,0x00,0xd4,0x1d,0x53,0x04,0x0b,0x00,0x92,0x15,0x51,0x04, - 0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xff,0xf0,0x91,0x82,0xa5,0xf0,0x91,0x82,0xba, - 0x00,0x0b,0x00,0x53,0x04,0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0b, - 0x09,0x10,0x04,0x0b,0x07,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3, - 0x0c,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x00,0x00,0x0d,0x00,0xd4,0x14,0x53,0x04,0x0d, - 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53, - 0x04,0x0d,0x00,0x92,0x08,0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0xd1,0x96,0xd0, - 0x5c,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x0d,0xe6,0x10, - 0x04,0x0d,0xe6,0x0d,0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd4,0x26,0x53,0x04,0x0d, - 0x00,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x0d,0x0d,0xff,0xf0,0x91,0x84, - 0xb1,0xf0,0x91,0x84,0xa7,0x00,0x0d,0xff,0xf0,0x91,0x84,0xb2,0xf0,0x91,0x84,0xa7, - 0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x0d,0x09,0x91, - 0x08,0x10,0x04,0x0d,0x09,0x00,0x00,0x0d,0x00,0x0d,0x00,0xcf,0x86,0xd5,0x18,0x94, - 0x14,0x93,0x10,0x52,0x04,0x0d,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00, - 0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x10, - 0x00,0x10,0x04,0x10,0x00,0x10,0x07,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00, - 0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0d,0x09,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd2, - 0x10,0xd1,0x08,0x10,0x04,0x0d,0x00,0x11,0x00,0x10,0x04,0x11,0x07,0x11,0x00,0x91, - 0x08,0x10,0x04,0x11,0x00,0x10,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x0c,0x51, - 0x04,0x0d,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x93, - 0x10,0x52,0x04,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0xd2,0xc8,0xd1,0x48,0xd0,0x42,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x93, - 0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10, - 0x00,0x54,0x04,0x10,0x00,0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10, - 0x00,0x10,0x09,0x10,0x04,0x10,0x07,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10, - 0x00,0x10,0x04,0x12,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd0,0x52,0xcf,0x86,0xd5, - 0x3c,0xd4,0x28,0xd3,0x10,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11, - 0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x00,0x51, - 0x04,0x11,0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x53,0x04,0x11,0x00,0x52,0x04,0x11, - 0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x94,0x10,0x53,0x04,0x11, - 0x00,0x92,0x08,0x11,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55, - 0x04,0x10,0x00,0xd4,0x18,0x53,0x04,0x10,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x10, - 0x00,0x10,0x07,0x10,0x04,0x10,0x09,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92, - 0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xe1,0x27,0x01,0xd0,0x8a,0xcf,0x86, - 0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x10,0x00, - 0x10,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10,0x00, - 0xd1,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x93,0x14, - 0x92,0x10,0xd1,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00, - 0x10,0x00,0x10,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x10,0x00,0x00,0x00,0x10,0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x10,0x00,0x00,0x00,0x10,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00, - 0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x00,0x00,0x14,0x07,0x91,0x08,0x10,0x04, - 0x10,0x07,0x10,0x00,0x10,0x00,0xcf,0x86,0xd5,0x6a,0xd4,0x42,0xd3,0x14,0x52,0x04, - 0x10,0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00, - 0xd2,0x19,0xd1,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0xff, - 0xf0,0x91,0x8d,0x87,0xf0,0x91,0x8c,0xbe,0x00,0x91,0x11,0x10,0x0d,0x10,0xff,0xf0, - 0x91,0x8d,0x87,0xf0,0x91,0x8d,0x97,0x00,0x10,0x09,0x00,0x00,0xd3,0x18,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x10,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00, - 0x10,0x00,0xd4,0x1c,0xd3,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0xe6, - 0x52,0x04,0x10,0xe6,0x91,0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x93,0x10, - 0x52,0x04,0x10,0xe6,0x91,0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x00,0x00, - 0xcf,0x06,0x00,0x00,0xe3,0x30,0x01,0xd2,0xb7,0xd1,0x48,0xd0,0x06,0xcf,0x06,0x12, - 0x00,0xcf,0x86,0x95,0x3c,0xd4,0x1c,0x93,0x18,0xd2,0x0c,0x51,0x04,0x12,0x00,0x10, - 0x04,0x12,0x09,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x07,0x12,0x00,0x12, - 0x00,0x53,0x04,0x12,0x00,0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x00,0x00,0x12, - 0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x12,0x00,0x10,0x04,0x14,0xe6,0x15,0x00,0x00, - 0x00,0xd0,0x45,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10, - 0x00,0xd2,0x15,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10,0xff,0xf0,0x91,0x92, - 0xb9,0xf0,0x91,0x92,0xba,0x00,0xd1,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9, - 0xf0,0x91,0x92,0xb0,0x00,0x10,0x00,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0, - 0x91,0x92,0xbd,0x00,0x10,0x00,0xcf,0x86,0x95,0x24,0xd4,0x14,0x93,0x10,0x92,0x0c, - 0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x09,0x10,0x07,0x10,0x00,0x00,0x00,0x53,0x04, - 0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x06, - 0xcf,0x06,0x00,0x00,0xd0,0x40,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00, - 0xd3,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0xd2,0x1e,0x51,0x04, - 0x10,0x00,0x10,0x0d,0x10,0xff,0xf0,0x91,0x96,0xb8,0xf0,0x91,0x96,0xaf,0x00,0x10, - 0xff,0xf0,0x91,0x96,0xb9,0xf0,0x91,0x96,0xaf,0x00,0x51,0x04,0x10,0x00,0x10,0x04, - 0x10,0x00,0x10,0x09,0xcf,0x86,0x95,0x2c,0xd4,0x1c,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x10,0x07,0x10,0x00,0x10,0x00,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00, - 0x11,0x00,0x11,0x00,0x53,0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00, - 0x00,0x00,0x00,0x00,0xd2,0xa0,0xd1,0x5c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00, - 0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00, - 0x10,0x04,0x10,0x00,0x10,0x09,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x93,0x10,0x52,0x04, - 0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04, - 0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14,0x53,0x04, - 0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0xd3,0x10, - 0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x09,0x0d,0x07,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x14, - 0x94,0x10,0x53,0x04,0x0d,0x00,0x92,0x08,0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x54,0x04,0x11,0x00, - 0x53,0x04,0x11,0x00,0xd2,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x14,0x00,0x00,0x00, - 0x91,0x08,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x94,0x14,0x53,0x04,0x11,0x00, - 0x92,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x11,0x09,0x00,0x00,0x11,0x00, - 0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xe4,0x59,0x01,0xd3,0xb2,0xd2,0x5c,0xd1, - 0x28,0xd0,0x22,0xcf,0x86,0x55,0x04,0x14,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14, - 0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x14,0x00,0x14,0x09,0x10,0x04,0x14,0x07,0x14, - 0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x00,0x00,0x10, - 0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x10,0x92,0x0c,0x51, - 0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51, - 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0, - 0x1a,0xcf,0x86,0x55,0x04,0x00,0x00,0x94,0x10,0x53,0x04,0x15,0x00,0x92,0x08,0x11, - 0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x15, - 0x00,0x53,0x04,0x15,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x94, - 0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x15,0x09,0x15,0x00,0x15,0x00,0x91, - 0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xa0,0xd1, - 0x3c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x93,0x10,0x52, - 0x04,0x13,0x00,0x91,0x08,0x10,0x04,0x13,0x09,0x13,0x00,0x13,0x00,0x13,0x00,0xcf, - 0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10, - 0x04,0x13,0x00,0x13,0x09,0x00,0x00,0x13,0x00,0x13,0x00,0xd0,0x46,0xcf,0x86,0xd5, - 0x2c,0xd4,0x10,0x93,0x0c,0x52,0x04,0x13,0x00,0x11,0x04,0x15,0x00,0x13,0x00,0x13, - 0x00,0x53,0x04,0x13,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x13,0x00,0x13,0x09,0x13, - 0x00,0x91,0x08,0x10,0x04,0x13,0x00,0x14,0x00,0x13,0x00,0x94,0x14,0x93,0x10,0x92, - 0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xe3,0xa9,0x01,0xd2,0xb0,0xd1,0x6c,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14, - 0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x12,0x00, - 0x12,0x00,0x12,0x00,0x54,0x04,0x12,0x00,0xd3,0x10,0x52,0x04,0x12,0x00,0x51,0x04, - 0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00, - 0x10,0x04,0x12,0x00,0x12,0x09,0xcf,0x86,0xd5,0x14,0x94,0x10,0x93,0x0c,0x52,0x04, - 0x12,0x00,0x11,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0x94,0x14,0x53,0x04, - 0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00, - 0x12,0x00,0xd0,0x3e,0xcf,0x86,0xd5,0x14,0x54,0x04,0x12,0x00,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0xd4,0x14,0x53,0x04,0x12,0x00, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x93,0x10, - 0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00, - 0xcf,0x06,0x00,0x00,0xd1,0xa0,0xd0,0x52,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3,0x10, - 0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x92,0x0c, - 0x51,0x04,0x13,0x00,0x10,0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x54,0x04, - 0x13,0x00,0xd3,0x10,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00, - 0x00,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x51,0x04, - 0x13,0x00,0x10,0x04,0x00,0x00,0x13,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0x93,0x14, - 0xd2,0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x07,0x13,0x00,0x11,0x04,0x13,0x09, - 0x13,0x00,0x00,0x00,0x53,0x04,0x13,0x00,0x92,0x08,0x11,0x04,0x13,0x00,0x00,0x00, - 0x00,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04, - 0x00,0x00,0x14,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x14,0x00, - 0x14,0x00,0x14,0x00,0xd0,0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x14,0x53,0x04,0x14,0x00, - 0x52,0x04,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0xd3,0x18, - 0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x51,0x04,0x14,0x00, - 0x10,0x04,0x14,0x00,0x14,0x09,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x94,0x10,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06, - 0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04, - 0x14,0x00,0x53,0x04,0x14,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00, - 0xcf,0x86,0x55,0x04,0x15,0x00,0x54,0x04,0x15,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04, - 0x15,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x15,0x00,0xd0,0xca,0xcf,0x86,0xd5,0xc2,0xd4,0x54,0xd3,0x06,0xcf,0x06, - 0x09,0x00,0xd2,0x06,0xcf,0x06,0x09,0x00,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x09,0x00, - 0xcf,0x86,0x55,0x04,0x09,0x00,0x94,0x14,0x53,0x04,0x09,0x00,0x52,0x04,0x09,0x00, - 0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x10,0x00,0x10,0x00,0xd0,0x1e,0xcf,0x86, - 0x95,0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x10,0x00,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x68, - 0xd2,0x46,0xd1,0x40,0xd0,0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09,0x00, - 0xd4,0x20,0xd3,0x10,0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x10,0x00, - 0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00, - 0x93,0x10,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0xcf,0x06,0x11,0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86, - 0x95,0x10,0x94,0x0c,0x93,0x08,0x12,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86, - 0xd5,0x4c,0xd4,0x06,0xcf,0x06,0x0b,0x00,0xd3,0x40,0xd2,0x3a,0xd1,0x34,0xd0,0x2e, - 0xcf,0x86,0x55,0x04,0x0b,0x00,0xd4,0x14,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00, - 0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x53,0x04,0x15,0x00,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00, - 0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00, - 0xd1,0x4c,0xd0,0x44,0xcf,0x86,0xd5,0x3c,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06, - 0xcf,0x06,0x11,0x00,0xd2,0x2a,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86, - 0x95,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04, - 0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06, - 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0xd2,0x01,0xcf, - 0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x0b,0x01,0xd3,0x06,0xcf,0x06,0x0c,0x00, - 0xd2,0x84,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00, - 0x53,0x04,0x0c,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04, - 0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14,0x53,0x04, - 0x10,0x00,0xd2,0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x10,0x00, - 0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x00,0x00, - 0x10,0x00,0xd4,0x10,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00, - 0x00,0x00,0x93,0x10,0x52,0x04,0x10,0x01,0x91,0x08,0x10,0x04,0x10,0x01,0x10,0x00, - 0x00,0x00,0x00,0x00,0xd1,0x6c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04, - 0x10,0x00,0x93,0x10,0x52,0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x10,0xe6, - 0x10,0x00,0x10,0x00,0xcf,0x86,0xd5,0x24,0xd4,0x10,0x93,0x0c,0x52,0x04,0x10,0x00, - 0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04, - 0x10,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c, - 0x51,0x04,0x10,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04, - 0x10,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00, - 0xd0,0x0e,0xcf,0x86,0x95,0x08,0x14,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06, - 0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x30,0xd1,0x0c,0xd0,0x06,0xcf,0x06, - 0x00,0x00,0xcf,0x06,0x14,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x14,0x00, - 0x53,0x04,0x14,0x00,0x92,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x4c,0xd0,0x06,0xcf,0x06,0x0d,0x00, - 0xcf,0x86,0xd5,0x2c,0x94,0x28,0xd3,0x10,0x52,0x04,0x0d,0x00,0x91,0x08,0x10,0x04, - 0x0d,0x00,0x15,0x00,0x15,0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00, - 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0d,0x00,0x54,0x04, - 0x0d,0x00,0x53,0x04,0x0d,0x00,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04, - 0x0d,0x00,0x15,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x15,0x00, - 0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00, - 0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x12,0x00,0x13,0x00,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, - 0xcf,0x06,0x12,0x00,0xe2,0xc5,0x01,0xd1,0x8e,0xd0,0x86,0xcf,0x86,0xd5,0x48,0xd4, - 0x06,0xcf,0x06,0x12,0x00,0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x06,0xcf,0x06,0x12, - 0x00,0xd1,0x06,0xcf,0x06,0x12,0x00,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55, - 0x04,0x12,0x00,0xd4,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10, - 0x04,0x12,0x00,0x14,0x00,0x14,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x14,0x00,0x15, - 0x00,0x15,0x00,0x00,0x00,0xd4,0x36,0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x2a,0xd1, - 0x06,0xcf,0x06,0x12,0x00,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12, - 0x00,0x54,0x04,0x12,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12, + 0x10,0x04,0x0c,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00, + 0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x93,0x18,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04, + 0x0c,0x00,0x00,0x00,0x00,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04, + 0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00, + 0x10,0x04,0x0c,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x94,0x10, + 0x93,0x0c,0x52,0x04,0x11,0x00,0x11,0x04,0x10,0x00,0x15,0x00,0x00,0x00,0x11,0x00, + 0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0xd4,0x14,0x53,0x04, + 0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x00,0x00, + 0x53,0x04,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x06, + 0x02,0xff,0xff,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd1,0x76,0xd0,0x09,0xcf,0x86, + 0xcf,0x06,0x02,0xff,0xff,0xcf,0x86,0x85,0xd4,0x07,0xcf,0x06,0x02,0xff,0xff,0xd3, + 0x07,0xcf,0x06,0x02,0xff,0xff,0xd2,0x07,0xcf,0x06,0x02,0xff,0xff,0xd1,0x07,0xcf, + 0x06,0x02,0xff,0xff,0xd0,0x18,0xcf,0x86,0x55,0x05,0x02,0xff,0xff,0x94,0x0d,0x93, + 0x09,0x12,0x05,0x02,0xff,0xff,0x00,0x00,0x00,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x24, + 0x94,0x20,0xd3,0x10,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, + 0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00, + 0x0b,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x12,0x04,0x0b,0x00,0x00,0x00, + 0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00, + 0xe4,0x9c,0x10,0xe3,0x16,0x08,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x08,0x04,0xe0, + 0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0x10,0x08,0x01, + 0xff,0xe8,0xbb,0x8a,0x00,0x01,0xff,0xe8,0xb3,0x88,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe6,0xbb,0x91,0x00,0x01,0xff,0xe4,0xb8,0xb2,0x00,0x10,0x08,0x01,0xff,0xe5, + 0x8f,0xa5,0x00,0x01,0xff,0xe9,0xbe,0x9c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe9,0xbe,0x9c,0x00,0x01,0xff,0xe5,0xa5,0x91,0x00,0x10,0x08,0x01,0xff,0xe9, + 0x87,0x91,0x00,0x01,0xff,0xe5,0x96,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, + 0xa5,0x88,0x00,0x01,0xff,0xe6,0x87,0xb6,0x00,0x10,0x08,0x01,0xff,0xe7,0x99,0xa9, + 0x00,0x01,0xff,0xe7,0xbe,0x85,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe8,0x98,0xbf,0x00,0x01,0xff,0xe8,0x9e,0xba,0x00,0x10,0x08,0x01,0xff,0xe8, + 0xa3,0xb8,0x00,0x01,0xff,0xe9,0x82,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6, + 0xa8,0x82,0x00,0x01,0xff,0xe6,0xb4,0x9b,0x00,0x10,0x08,0x01,0xff,0xe7,0x83,0x99, + 0x00,0x01,0xff,0xe7,0x8f,0x9e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, + 0x90,0xbd,0x00,0x01,0xff,0xe9,0x85,0xaa,0x00,0x10,0x08,0x01,0xff,0xe9,0xa7,0xb1, + 0x00,0x01,0xff,0xe4,0xba,0x82,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x8d,0xb5, + 0x00,0x01,0xff,0xe6,0xac,0x84,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x9b,0x00,0x01, + 0xff,0xe8,0x98,0xad,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe9,0xb8,0x9e,0x00,0x01,0xff,0xe5,0xb5,0x90,0x00,0x10,0x08,0x01,0xff,0xe6, + 0xbf,0xab,0x00,0x01,0xff,0xe8,0x97,0x8d,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, + 0xa5,0xa4,0x00,0x01,0xff,0xe6,0x8b,0x89,0x00,0x10,0x08,0x01,0xff,0xe8,0x87,0x98, + 0x00,0x01,0xff,0xe8,0xa0,0x9f,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, + 0xbb,0x8a,0x00,0x01,0xff,0xe6,0x9c,0x97,0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0xaa, + 0x00,0x01,0xff,0xe7,0x8b,0xbc,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x83,0x8e, + 0x00,0x01,0xff,0xe4,0xbe,0x86,0x00,0x10,0x08,0x01,0xff,0xe5,0x86,0xb7,0x00,0x01, + 0xff,0xe5,0x8b,0x9e,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6, + 0x93,0x84,0x00,0x01,0xff,0xe6,0xab,0x93,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x90, + 0x00,0x01,0xff,0xe7,0x9b,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x80,0x81, + 0x00,0x01,0xff,0xe8,0x98,0x86,0x00,0x10,0x08,0x01,0xff,0xe8,0x99,0x9c,0x00,0x01, + 0xff,0xe8,0xb7,0xaf,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9c,0xb2, + 0x00,0x01,0xff,0xe9,0xad,0xaf,0x00,0x10,0x08,0x01,0xff,0xe9,0xb7,0xba,0x00,0x01, + 0xff,0xe7,0xa2,0x8c,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa5,0xbf,0x00,0x01, + 0xff,0xe7,0xb6,0xa0,0x00,0x10,0x08,0x01,0xff,0xe8,0x8f,0x89,0x00,0x01,0xff,0xe9, + 0x8c,0x84,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0x10,0x08, + 0x01,0xff,0xe5,0xa3,0x9f,0x00,0x01,0xff,0xe5,0xbc,0x84,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe7,0xb1,0xa0,0x00,0x01,0xff,0xe8,0x81,0xbe,0x00,0x10,0x08,0x01,0xff, + 0xe7,0x89,0xa2,0x00,0x01,0xff,0xe7,0xa3,0x8a,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe8,0xb3,0x82,0x00,0x01,0xff,0xe9,0x9b,0xb7,0x00,0x10,0x08,0x01,0xff, + 0xe5,0xa3,0x98,0x00,0x01,0xff,0xe5,0xb1,0xa2,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe6,0xa8,0x93,0x00,0x01,0xff,0xe6,0xb7,0x9a,0x00,0x10,0x08,0x01,0xff,0xe6,0xbc, + 0x8f,0x00,0x01,0xff,0xe7,0xb4,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9,0x99,0x8b,0x00,0x10,0x08,0x01,0xff, + 0xe5,0x8b,0x92,0x00,0x01,0xff,0xe8,0x82,0x8b,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe5,0x87,0x9c,0x00,0x01,0xff,0xe5,0x87,0x8c,0x00,0x10,0x08,0x01,0xff,0xe7,0xa8, + 0x9c,0x00,0x01,0xff,0xe7,0xb6,0xbe,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe8,0x8f,0xb1,0x00,0x01,0xff,0xe9,0x99,0xb5,0x00,0x10,0x08,0x01,0xff,0xe8,0xae, + 0x80,0x00,0x01,0xff,0xe6,0x8b,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xa8, + 0x82,0x00,0x01,0xff,0xe8,0xab,0xbe,0x00,0x10,0x08,0x01,0xff,0xe4,0xb8,0xb9,0x00, + 0x01,0xff,0xe5,0xaf,0xa7,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe6,0x80,0x92,0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0x10,0x08,0x01,0xff, + 0xe7,0x95,0xb0,0x00,0x01,0xff,0xe5,0x8c,0x97,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe7,0xa3,0xbb,0x00,0x01,0xff,0xe4,0xbe,0xbf,0x00,0x10,0x08,0x01,0xff,0xe5,0xbe, + 0xa9,0x00,0x01,0xff,0xe4,0xb8,0x8d,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe6,0xb3,0x8c,0x00,0x01,0xff,0xe6,0x95,0xb8,0x00,0x10,0x08,0x01,0xff,0xe7,0xb4, + 0xa2,0x00,0x01,0xff,0xe5,0x8f,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xa1, + 0x9e,0x00,0x01,0xff,0xe7,0x9c,0x81,0x00,0x10,0x08,0x01,0xff,0xe8,0x91,0x89,0x00, + 0x01,0xff,0xe8,0xaa,0xaa,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe6,0xae,0xba,0x00,0x01,0xff,0xe8,0xbe,0xb0,0x00,0x10,0x08,0x01,0xff,0xe6,0xb2, + 0x88,0x00,0x01,0xff,0xe6,0x8b,0xbe,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x8b, + 0xa5,0x00,0x01,0xff,0xe6,0x8e,0xa0,0x00,0x10,0x08,0x01,0xff,0xe7,0x95,0xa5,0x00, + 0x01,0xff,0xe4,0xba,0xae,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x85, + 0xa9,0x00,0x01,0xff,0xe5,0x87,0x89,0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0x81,0x00, + 0x01,0xff,0xe7,0xb3,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x89,0xaf,0x00, + 0x01,0xff,0xe8,0xab,0x92,0x00,0x10,0x08,0x01,0xff,0xe9,0x87,0x8f,0x00,0x01,0xff, + 0xe5,0x8b,0xb5,0x00,0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x91,0x82,0x00,0x01,0xff,0xe5,0xa5, + 0xb3,0x00,0x10,0x08,0x01,0xff,0xe5,0xbb,0xac,0x00,0x01,0xff,0xe6,0x97,0x85,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xbf,0xbe,0x00,0x01,0xff,0xe7,0xa4,0xaa,0x00, + 0x10,0x08,0x01,0xff,0xe9,0x96,0xad,0x00,0x01,0xff,0xe9,0xa9,0xaa,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xba,0x97,0x00,0x01,0xff,0xe9,0xbb,0x8e,0x00, + 0x10,0x08,0x01,0xff,0xe5,0x8a,0x9b,0x00,0x01,0xff,0xe6,0x9b,0x86,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe6,0xad,0xb7,0x00,0x01,0xff,0xe8,0xbd,0xa2,0x00,0x10,0x08, + 0x01,0xff,0xe5,0xb9,0xb4,0x00,0x01,0xff,0xe6,0x86,0x90,0x00,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x88,0x80,0x00,0x01,0xff,0xe6,0x92,0x9a,0x00, + 0x10,0x08,0x01,0xff,0xe6,0xbc,0xa3,0x00,0x01,0xff,0xe7,0x85,0x89,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe7,0x92,0x89,0x00,0x01,0xff,0xe7,0xa7,0x8a,0x00,0x10,0x08, + 0x01,0xff,0xe7,0xb7,0xb4,0x00,0x01,0xff,0xe8,0x81,0xaf,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe8,0xbc,0xa6,0x00,0x01,0xff,0xe8,0x93,0xae,0x00,0x10,0x08, + 0x01,0xff,0xe9,0x80,0xa3,0x00,0x01,0xff,0xe9,0x8d,0x8a,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe5,0x88,0x97,0x00,0x01,0xff,0xe5,0x8a,0xa3,0x00,0x10,0x08,0x01,0xff, + 0xe5,0x92,0xbd,0x00,0x01,0xff,0xe7,0x83,0x88,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xa3,0x82,0x00,0x01,0xff,0xe8,0xaa,0xaa,0x00, + 0x10,0x08,0x01,0xff,0xe5,0xbb,0x89,0x00,0x01,0xff,0xe5,0xbf,0xb5,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe6,0x8d,0xbb,0x00,0x01,0xff,0xe6,0xae,0xae,0x00,0x10,0x08, + 0x01,0xff,0xe7,0xb0,0xbe,0x00,0x01,0xff,0xe7,0x8d,0xb5,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe4,0xbb,0xa4,0x00,0x01,0xff,0xe5,0x9b,0xb9,0x00,0x10,0x08, + 0x01,0xff,0xe5,0xaf,0xa7,0x00,0x01,0xff,0xe5,0xb6,0xba,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe6,0x80,0x9c,0x00,0x01,0xff,0xe7,0x8e,0xb2,0x00,0x10,0x08,0x01,0xff, + 0xe7,0x91,0xa9,0x00,0x01,0xff,0xe7,0xbe,0x9a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe8,0x81,0x86,0x00,0x01,0xff,0xe9,0x88,0xb4,0x00,0x10,0x08, + 0x01,0xff,0xe9,0x9b,0xb6,0x00,0x01,0xff,0xe9,0x9d,0x88,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe9,0xa0,0x98,0x00,0x01,0xff,0xe4,0xbe,0x8b,0x00,0x10,0x08,0x01,0xff, + 0xe7,0xa6,0xae,0x00,0x01,0xff,0xe9,0x86,0xb4,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe9,0x9a,0xb8,0x00,0x01,0xff,0xe6,0x83,0xa1,0x00,0x10,0x08,0x01,0xff, + 0xe4,0xba,0x86,0x00,0x01,0xff,0xe5,0x83,0x9a,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe5,0xaf,0xae,0x00,0x01,0xff,0xe5,0xb0,0xbf,0x00,0x10,0x08,0x01,0xff,0xe6,0x96, + 0x99,0x00,0x01,0xff,0xe6,0xa8,0x82,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0x87,0x8e,0x00,0x01,0xff,0xe7, + 0x99,0x82,0x00,0x10,0x08,0x01,0xff,0xe8,0x93,0xbc,0x00,0x01,0xff,0xe9,0x81,0xbc, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xbe,0x8d,0x00,0x01,0xff,0xe6,0x9a,0x88, + 0x00,0x10,0x08,0x01,0xff,0xe9,0x98,0xae,0x00,0x01,0xff,0xe5,0x8a,0x89,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x9d,0xbb,0x00,0x01,0xff,0xe6,0x9f,0xb3, + 0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0x81,0x00,0x01,0xff,0xe6,0xba,0x9c,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe7,0x90,0x89,0x00,0x01,0xff,0xe7,0x95,0x99,0x00,0x10, + 0x08,0x01,0xff,0xe7,0xa1,0xab,0x00,0x01,0xff,0xe7,0xb4,0x90,0x00,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xa1,0x9e,0x00,0x01,0xff,0xe5,0x85,0xad, + 0x00,0x10,0x08,0x01,0xff,0xe6,0x88,0xae,0x00,0x01,0xff,0xe9,0x99,0xb8,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe5,0x80,0xab,0x00,0x01,0xff,0xe5,0xb4,0x99,0x00,0x10, + 0x08,0x01,0xff,0xe6,0xb7,0xaa,0x00,0x01,0xff,0xe8,0xbc,0xaa,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe5,0xbe,0x8b,0x00,0x01,0xff,0xe6,0x85,0x84,0x00,0x10, + 0x08,0x01,0xff,0xe6,0xa0,0x97,0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe9,0x9a,0x86,0x00,0x01,0xff,0xe5,0x88,0xa9,0x00,0x10,0x08,0x01, + 0xff,0xe5,0x90,0x8f,0x00,0x01,0xff,0xe5,0xb1,0xa5,0x00,0xd4,0x80,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x98,0x93,0x00,0x01,0xff,0xe6,0x9d,0x8e, + 0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0xa8,0x00,0x01,0xff,0xe6,0xb3,0xa5,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe7,0x90,0x86,0x00,0x01,0xff,0xe7,0x97,0xa2,0x00,0x10, + 0x08,0x01,0xff,0xe7,0xbd,0xb9,0x00,0x01,0xff,0xe8,0xa3,0x8f,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe8,0xa3,0xa1,0x00,0x01,0xff,0xe9,0x87,0x8c,0x00,0x10, + 0x08,0x01,0xff,0xe9,0x9b,0xa2,0x00,0x01,0xff,0xe5,0x8c,0xbf,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe6,0xba,0xba,0x00,0x01,0xff,0xe5,0x90,0x9d,0x00,0x10,0x08,0x01, + 0xff,0xe7,0x87,0x90,0x00,0x01,0xff,0xe7,0x92,0x98,0x00,0xd3,0x40,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe8,0x97,0xba,0x00,0x01,0xff,0xe9,0x9a,0xa3,0x00,0x10, + 0x08,0x01,0xff,0xe9,0xb1,0x97,0x00,0x01,0xff,0xe9,0xba,0x9f,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe6,0x9e,0x97,0x00,0x01,0xff,0xe6,0xb7,0x8b,0x00,0x10,0x08,0x01, + 0xff,0xe8,0x87,0xa8,0x00,0x01,0xff,0xe7,0xab,0x8b,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe7,0xac,0xa0,0x00,0x01,0xff,0xe7,0xb2,0x92,0x00,0x10,0x08,0x01, + 0xff,0xe7,0x8b,0x80,0x00,0x01,0xff,0xe7,0x82,0x99,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe8,0xad,0x98,0x00,0x01,0xff,0xe4,0xbb,0x80,0x00,0x10,0x08,0x01,0xff,0xe8, + 0x8c,0xb6,0x00,0x01,0xff,0xe5,0x88,0xba,0x00,0xe2,0xad,0x06,0xe1,0xc4,0x03,0xe0, + 0xcb,0x01,0xcf,0x86,0xd5,0xe4,0xd4,0x74,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe5,0x88,0x87,0x00,0x01,0xff,0xe5,0xba,0xa6,0x00,0x10,0x08,0x01,0xff, + 0xe6,0x8b,0x93,0x00,0x01,0xff,0xe7,0xb3,0x96,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe5,0xae,0x85,0x00,0x01,0xff,0xe6,0xb4,0x9e,0x00,0x10,0x08,0x01,0xff,0xe6,0x9a, + 0xb4,0x00,0x01,0xff,0xe8,0xbc,0xbb,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe8,0xa1,0x8c,0x00,0x01,0xff,0xe9,0x99,0x8d,0x00,0x10,0x08,0x01,0xff,0xe8,0xa6, + 0x8b,0x00,0x01,0xff,0xe5,0xbb,0x93,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0xe5,0x85, + 0x80,0x00,0x01,0xff,0xe5,0x97,0x80,0x00,0x01,0x00,0xd3,0x34,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x01,0xff,0xe5,0xa1,0x9a,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe6,0x99, + 0xb4,0x00,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe5,0x87,0x9e,0x00, + 0x10,0x08,0x01,0xff,0xe7,0x8c,0xaa,0x00,0x01,0xff,0xe7,0x9b,0x8a,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa4,0xbc,0x00,0x01,0xff,0xe7,0xa5,0x9e,0x00, + 0x10,0x08,0x01,0xff,0xe7,0xa5,0xa5,0x00,0x01,0xff,0xe7,0xa6,0x8f,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe9,0x9d,0x96,0x00,0x01,0xff,0xe7,0xb2,0xbe,0x00,0x10,0x08, + 0x01,0xff,0xe7,0xbe,0xbd,0x00,0x01,0x00,0xd4,0x64,0xd3,0x30,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x01,0xff,0xe8,0x98,0x92,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe8,0xab, + 0xb8,0x00,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe9,0x80,0xb8,0x00, + 0x10,0x08,0x01,0xff,0xe9,0x83,0xbd,0x00,0x01,0x00,0xd2,0x14,0x51,0x04,0x01,0x00, + 0x10,0x08,0x01,0xff,0xe9,0xa3,0xaf,0x00,0x01,0xff,0xe9,0xa3,0xbc,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe9,0xa4,0xa8,0x00,0x01,0xff,0xe9,0xb6,0xb4,0x00,0x10,0x08, + 0x0d,0xff,0xe9,0x83,0x9e,0x00,0x0d,0xff,0xe9,0x9a,0xb7,0x00,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x06,0xff,0xe4,0xbe,0xae,0x00,0x06,0xff,0xe5,0x83,0xa7,0x00, + 0x10,0x08,0x06,0xff,0xe5,0x85,0x8d,0x00,0x06,0xff,0xe5,0x8b,0x89,0x00,0xd1,0x10, + 0x10,0x08,0x06,0xff,0xe5,0x8b,0xa4,0x00,0x06,0xff,0xe5,0x8d,0x91,0x00,0x10,0x08, + 0x06,0xff,0xe5,0x96,0x9d,0x00,0x06,0xff,0xe5,0x98,0x86,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x06,0xff,0xe5,0x99,0xa8,0x00,0x06,0xff,0xe5,0xa1,0x80,0x00,0x10,0x08, + 0x06,0xff,0xe5,0xa2,0xa8,0x00,0x06,0xff,0xe5,0xb1,0xa4,0x00,0xd1,0x10,0x10,0x08, + 0x06,0xff,0xe5,0xb1,0xae,0x00,0x06,0xff,0xe6,0x82,0x94,0x00,0x10,0x08,0x06,0xff, + 0xe6,0x85,0xa8,0x00,0x06,0xff,0xe6,0x86,0x8e,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4, + 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe6,0x87,0xb2,0x00,0x06, + 0xff,0xe6,0x95,0x8f,0x00,0x10,0x08,0x06,0xff,0xe6,0x97,0xa2,0x00,0x06,0xff,0xe6, + 0x9a,0x91,0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe6,0xa2,0x85,0x00,0x06,0xff,0xe6, + 0xb5,0xb7,0x00,0x10,0x08,0x06,0xff,0xe6,0xb8,0x9a,0x00,0x06,0xff,0xe6,0xbc,0xa2, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0x85,0xae,0x00,0x06,0xff,0xe7, + 0x88,0xab,0x00,0x10,0x08,0x06,0xff,0xe7,0x90,0xa2,0x00,0x06,0xff,0xe7,0xa2,0x91, + 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa4,0xbe,0x00,0x06,0xff,0xe7,0xa5,0x89, + 0x00,0x10,0x08,0x06,0xff,0xe7,0xa5,0x88,0x00,0x06,0xff,0xe7,0xa5,0x90,0x00,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa5,0x96,0x00,0x06,0xff,0xe7, + 0xa5,0x9d,0x00,0x10,0x08,0x06,0xff,0xe7,0xa6,0x8d,0x00,0x06,0xff,0xe7,0xa6,0x8e, + 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa9,0x80,0x00,0x06,0xff,0xe7,0xaa,0x81, + 0x00,0x10,0x08,0x06,0xff,0xe7,0xaf,0x80,0x00,0x06,0xff,0xe7,0xb7,0xb4,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xb8,0x89,0x00,0x06,0xff,0xe7,0xb9,0x81, + 0x00,0x10,0x08,0x06,0xff,0xe7,0xbd,0xb2,0x00,0x06,0xff,0xe8,0x80,0x85,0x00,0xd1, + 0x10,0x10,0x08,0x06,0xff,0xe8,0x87,0xad,0x00,0x06,0xff,0xe8,0x89,0xb9,0x00,0x10, + 0x08,0x06,0xff,0xe8,0x89,0xb9,0x00,0x06,0xff,0xe8,0x91,0x97,0x00,0xd4,0x75,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8,0xa4,0x90,0x00,0x06,0xff,0xe8, + 0xa6,0x96,0x00,0x10,0x08,0x06,0xff,0xe8,0xac,0x81,0x00,0x06,0xff,0xe8,0xac,0xb9, + 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8,0xb3,0x93,0x00,0x06,0xff,0xe8,0xb4,0x88, + 0x00,0x10,0x08,0x06,0xff,0xe8,0xbe,0xb6,0x00,0x06,0xff,0xe9,0x80,0xb8,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe9,0x9b,0xa3,0x00,0x06,0xff,0xe9,0x9f,0xbf, + 0x00,0x10,0x08,0x06,0xff,0xe9,0xa0,0xbb,0x00,0x0b,0xff,0xe6,0x81,0xb5,0x00,0x91, + 0x11,0x10,0x09,0x0b,0xff,0xf0,0xa4,0x8b,0xae,0x00,0x0b,0xff,0xe8,0x88,0x98,0x00, + 0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe4,0xb8,0xa6,0x00, + 0x08,0xff,0xe5,0x86,0xb5,0x00,0x10,0x08,0x08,0xff,0xe5,0x85,0xa8,0x00,0x08,0xff, + 0xe4,0xbe,0x80,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0x85,0x85,0x00,0x08,0xff, + 0xe5,0x86,0x80,0x00,0x10,0x08,0x08,0xff,0xe5,0x8b,0x87,0x00,0x08,0xff,0xe5,0x8b, + 0xba,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0x96,0x9d,0x00,0x08,0xff, + 0xe5,0x95,0x95,0x00,0x10,0x08,0x08,0xff,0xe5,0x96,0x99,0x00,0x08,0xff,0xe5,0x97, + 0xa2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0xa1,0x9a,0x00,0x08,0xff,0xe5,0xa2, + 0xb3,0x00,0x10,0x08,0x08,0xff,0xe5,0xa5,0x84,0x00,0x08,0xff,0xe5,0xa5,0x94,0x00, + 0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x08,0xff,0xe5,0xa9,0xa2,0x00,0x08,0xff,0xe5,0xac,0xa8,0x00,0x10,0x08, + 0x08,0xff,0xe5,0xbb,0x92,0x00,0x08,0xff,0xe5,0xbb,0x99,0x00,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe5,0xbd,0xa9,0x00,0x08,0xff,0xe5,0xbe,0xad,0x00,0x10,0x08,0x08,0xff, + 0xe6,0x83,0x98,0x00,0x08,0xff,0xe6,0x85,0x8e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe6,0x84,0x88,0x00,0x08,0xff,0xe6,0x86,0x8e,0x00,0x10,0x08,0x08,0xff, + 0xe6,0x85,0xa0,0x00,0x08,0xff,0xe6,0x87,0xb2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe6,0x88,0xb4,0x00,0x08,0xff,0xe6,0x8f,0x84,0x00,0x10,0x08,0x08,0xff,0xe6,0x90, + 0x9c,0x00,0x08,0xff,0xe6,0x91,0x92,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe6,0x95,0x96,0x00,0x08,0xff,0xe6,0x99,0xb4,0x00,0x10,0x08,0x08,0xff, + 0xe6,0x9c,0x97,0x00,0x08,0xff,0xe6,0x9c,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe6,0x9d,0x96,0x00,0x08,0xff,0xe6,0xad,0xb9,0x00,0x10,0x08,0x08,0xff,0xe6,0xae, + 0xba,0x00,0x08,0xff,0xe6,0xb5,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe6,0xbb,0x9b,0x00,0x08,0xff,0xe6,0xbb,0x8b,0x00,0x10,0x08,0x08,0xff,0xe6,0xbc, + 0xa2,0x00,0x08,0xff,0xe7,0x80,0x9e,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x85, + 0xae,0x00,0x08,0xff,0xe7,0x9e,0xa7,0x00,0x10,0x08,0x08,0xff,0xe7,0x88,0xb5,0x00, + 0x08,0xff,0xe7,0x8a,0xaf,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe7,0x8c,0xaa,0x00,0x08,0xff,0xe7,0x91,0xb1,0x00,0x10,0x08,0x08,0xff, + 0xe7,0x94,0x86,0x00,0x08,0xff,0xe7,0x94,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe7,0x98,0x9d,0x00,0x08,0xff,0xe7,0x98,0x9f,0x00,0x10,0x08,0x08,0xff,0xe7,0x9b, + 0x8a,0x00,0x08,0xff,0xe7,0x9b,0x9b,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe7,0x9b,0xb4,0x00,0x08,0xff,0xe7,0x9d,0x8a,0x00,0x10,0x08,0x08,0xff,0xe7,0x9d, + 0x80,0x00,0x08,0xff,0xe7,0xa3,0x8c,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0xaa, + 0xb1,0x00,0x08,0xff,0xe7,0xaf,0x80,0x00,0x10,0x08,0x08,0xff,0xe7,0xb1,0xbb,0x00, + 0x08,0xff,0xe7,0xb5,0x9b,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe7,0xb7,0xb4,0x00,0x08,0xff,0xe7,0xbc,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0x80, + 0x85,0x00,0x08,0xff,0xe8,0x8d,0x92,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0x8f, + 0xaf,0x00,0x08,0xff,0xe8,0x9d,0xb9,0x00,0x10,0x08,0x08,0xff,0xe8,0xa5,0x81,0x00, + 0x08,0xff,0xe8,0xa6,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xa6, + 0x96,0x00,0x08,0xff,0xe8,0xaa,0xbf,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xb8,0x00, + 0x08,0xff,0xe8,0xab,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xac,0x81,0x00, + 0x08,0xff,0xe8,0xab,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xad,0x00,0x08,0xff, + 0xe8,0xac,0xb9,0x00,0xcf,0x86,0x95,0xde,0xd4,0x81,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x08,0xff,0xe8,0xae,0x8a,0x00,0x08,0xff,0xe8,0xb4,0x88,0x00,0x10,0x08, + 0x08,0xff,0xe8,0xbc,0xb8,0x00,0x08,0xff,0xe9,0x81,0xb2,0x00,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe9,0x86,0x99,0x00,0x08,0xff,0xe9,0x89,0xb6,0x00,0x10,0x08,0x08,0xff, + 0xe9,0x99,0xbc,0x00,0x08,0xff,0xe9,0x9b,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe9,0x9d,0x96,0x00,0x08,0xff,0xe9,0x9f,0x9b,0x00,0x10,0x08,0x08,0xff, + 0xe9,0x9f,0xbf,0x00,0x08,0xff,0xe9,0xa0,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe9,0xa0,0xbb,0x00,0x08,0xff,0xe9,0xac,0x92,0x00,0x10,0x08,0x08,0xff,0xe9,0xbe, + 0x9c,0x00,0x08,0xff,0xf0,0xa2,0xa1,0x8a,0x00,0xd3,0x45,0xd2,0x22,0xd1,0x12,0x10, + 0x09,0x08,0xff,0xf0,0xa2,0xa1,0x84,0x00,0x08,0xff,0xf0,0xa3,0x8f,0x95,0x00,0x10, + 0x08,0x08,0xff,0xe3,0xae,0x9d,0x00,0x08,0xff,0xe4,0x80,0x98,0x00,0xd1,0x11,0x10, + 0x08,0x08,0xff,0xe4,0x80,0xb9,0x00,0x08,0xff,0xf0,0xa5,0x89,0x89,0x00,0x10,0x09, + 0x08,0xff,0xf0,0xa5,0xb3,0x90,0x00,0x08,0xff,0xf0,0xa7,0xbb,0x93,0x00,0x92,0x14, + 0x91,0x10,0x10,0x08,0x08,0xff,0xe9,0xbd,0x83,0x00,0x08,0xff,0xe9,0xbe,0x8e,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0xe1,0x94,0x01,0xe0,0x08,0x01,0xcf,0x86,0xd5,0x42, + 0xd4,0x14,0x93,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x00,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x00,0x00,0x04,0xff, + 0xd7,0x99,0xd6,0xb4,0x00,0x10,0x04,0x01,0x1a,0x01,0xff,0xd7,0xb2,0xd6,0xb7,0x00, + 0xd4,0x42,0x53,0x04,0x01,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, + 0xd7,0xa9,0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd7,0x82,0x00,0xd1,0x16,0x10,0x0b, + 0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7, + 0x82,0x00,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xb7,0x00,0x01,0xff,0xd7,0x90,0xd6, + 0xb8,0x00,0xd3,0x43,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xbc, + 0x00,0x01,0xff,0xd7,0x91,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x92,0xd6,0xbc, + 0x00,0x01,0xff,0xd7,0x93,0xd6,0xbc,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x94, + 0xd6,0xbc,0x00,0x01,0xff,0xd7,0x95,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x96, + 0xd6,0xbc,0x00,0x00,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x98,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0x99,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x9a,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0x9b,0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7, + 0x9c,0xd6,0xbc,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xd7,0x9e,0xd6,0xbc,0x00,0x00, + 0x00,0xcf,0x86,0x95,0x85,0x94,0x81,0xd3,0x3e,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xd7,0xa0,0xd6,0xbc,0x00,0x01,0xff,0xd7,0xa1,0xd6,0xbc,0x00,0x10,0x04,0x00, + 0x00,0x01,0xff,0xd7,0xa3,0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7,0xa4, + 0xd6,0xbc,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xd7,0xa6,0xd6,0xbc,0x00,0x01,0xff, + 0xd7,0xa7,0xd6,0xbc,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0xa8,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0xaa,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0x95,0xd6,0xb9,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7, + 0x91,0xd6,0xbf,0x00,0x01,0xff,0xd7,0x9b,0xd6,0xbf,0x00,0x10,0x09,0x01,0xff,0xd7, + 0xa4,0xd6,0xbf,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04, + 0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00, + 0x0c,0x00,0x0c,0x00,0xcf,0x86,0x95,0x24,0xd4,0x10,0x93,0x0c,0x92,0x08,0x11,0x04, + 0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00, + 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd3,0x5a,0xd2,0x06, + 0xcf,0x06,0x01,0x00,0xd1,0x14,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x95,0x08, + 0x14,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54,0x04, + 0x01,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x0c,0x94,0x08,0x13,0x04,0x01,0x00,0x00,0x00,0x05,0x00, + 0x54,0x04,0x05,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04, + 0x06,0x00,0x07,0x00,0x00,0x00,0xd2,0xce,0xd1,0xa5,0xd0,0x37,0xcf,0x86,0xd5,0x15, + 0x54,0x05,0x06,0xff,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00,0x00, + 0x00,0x00,0x00,0x94,0x1c,0xd3,0x10,0x52,0x04,0x01,0xe6,0x51,0x04,0x0a,0xe6,0x10, + 0x04,0x0a,0xe6,0x10,0xdc,0x52,0x04,0x10,0xdc,0x11,0x04,0x10,0xdc,0x11,0xe6,0x01, + 0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10, + 0x04,0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00,0x07,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x07,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd4,0x18,0xd3,0x10,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x12,0x04,0x01, + 0x00,0x00,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06, + 0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x06,0xcf, + 0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01, + 0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x01,0xff,0x00,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10, + 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00, + 0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x94,0x14, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0xd0,0x2f,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x15,0x93,0x11, + 0x92,0x0d,0x91,0x09,0x10,0x05,0x01,0xff,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x18,0xd3,0x0c,0x92,0x08,0x11,0x04,0x00, + 0x00,0x01,0x00,0x01,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3, + 0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x00, + 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd4,0x20,0xd3, + 0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x53,0x05,0x00, + 0xff,0x00,0xd2,0x0d,0x91,0x09,0x10,0x05,0x00,0xff,0x00,0x04,0x00,0x04,0x00,0x91, + 0x08,0x10,0x04,0x03,0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0x46,0x3e,0xe1,0x1f,0x3b, + 0xe0,0x9c,0x39,0xcf,0x86,0xe5,0x40,0x26,0xc4,0xe3,0x16,0x14,0xe2,0xef,0x11,0xe1, + 0xd0,0x10,0xe0,0x60,0x07,0xcf,0x86,0xe5,0x53,0x03,0xe4,0x4c,0x02,0xe3,0x3d,0x01, + 0xd2,0x94,0xd1,0x70,0xd0,0x4a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x07,0x00, + 0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00, + 0xd4,0x14,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00, + 0x00,0x00,0x07,0x00,0x53,0x04,0x07,0x00,0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04, + 0x07,0x00,0x00,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86, + 0x95,0x20,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00, + 0x00,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00, + 0x00,0x00,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x54,0x04, + 0x07,0x00,0x53,0x04,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00, + 0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x94,0x1c,0x93,0x18, + 0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x51,0x04,0x00,0x00, + 0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07,0x00,0x93,0x10, + 0x52,0x04,0x07,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00, + 0xcf,0x06,0x08,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4,0x20,0x53,0x04,0x08,0x00, + 0xd2,0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x10,0x00,0xd1,0x08,0x10,0x04, + 0x10,0x00,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x12,0x04, + 0x0a,0x00,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04, + 0x00,0x00,0x0a,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00, + 0x91,0x08,0x10,0x04,0x0a,0x00,0x0a,0xdc,0x00,0x00,0xd2,0x5e,0xd1,0x06,0xcf,0x06, + 0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00, + 0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x0a,0x00, + 0xcf,0x86,0xd5,0x18,0x54,0x04,0x0a,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x0a,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x10,0xdc,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04, + 0x10,0x00,0x12,0x04,0x10,0x00,0x00,0x00,0xd1,0x70,0xd0,0x36,0xcf,0x86,0xd5,0x18, + 0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x51,0x04,0x05,0x00, + 0x10,0x04,0x05,0x00,0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x05,0x00,0x00,0x00, + 0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x05,0x00, + 0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x05,0x00,0x92,0x0c,0x51,0x04,0x05,0x00, + 0x10,0x04,0x05,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x0c, + 0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x10,0xe6,0x92,0x0c,0x51,0x04,0x10,0xe6, + 0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04, + 0x00,0x00,0x07,0x00,0x08,0x00,0xcf,0x86,0x95,0x1c,0xd4,0x0c,0x93,0x08,0x12,0x04, + 0x08,0x00,0x00,0x00,0x08,0x00,0x93,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0xba,0xd2,0x80,0xd1,0x34,0xd0,0x1a,0xcf,0x86, + 0x55,0x04,0x05,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00, + 0x07,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x53,0x04,0x05,0x00, + 0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd0,0x2a, + 0xcf,0x86,0xd5,0x14,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00, + 0x11,0x04,0x07,0x00,0x00,0x00,0x94,0x10,0x53,0x04,0x07,0x00,0x92,0x08,0x11,0x04, + 0x07,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xcf,0x86,0xd5,0x10,0x54,0x04,0x12,0x00, + 0x93,0x08,0x12,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x54,0x04,0x12,0x00,0x53,0x04, + 0x12,0x00,0x12,0x04,0x12,0x00,0x00,0x00,0xd1,0x34,0xd0,0x12,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x10,0x00,0x00,0x00,0x52,0x04,0x00,0x00, + 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00, + 0xd2,0x06,0xcf,0x06,0x10,0x00,0xd1,0x40,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00, + 0x54,0x04,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c, + 0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x08,0x13,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe4,0xce,0x02,0xe3,0x45,0x01, + 0xd2,0xd0,0xd1,0x70,0xd0,0x52,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3,0x0c,0x52,0x04, + 0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00, + 0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07,0x00,0xd3,0x10,0x52,0x04, + 0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xd2,0x0c,0x91,0x08, + 0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x00,0x00, + 0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86,0x95,0x18,0x54,0x04,0x0b,0x00,0x93,0x10, + 0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00, + 0x10,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, + 0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14, + 0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00, + 0x10,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x11,0x00,0xd3,0x14, + 0xd2,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x04,0x11,0x00, + 0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00, + 0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x1c,0x54,0x04,0x09,0x00,0x53,0x04,0x09,0x00, + 0xd2,0x08,0x11,0x04,0x09,0x00,0x0b,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00, + 0x09,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00, + 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0xcf,0x06,0x00,0x00, + 0xd0,0x1a,0xcf,0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0x53,0x04,0x0d,0x00, + 0x52,0x04,0x00,0x00,0x11,0x04,0x11,0x00,0x0d,0x00,0xcf,0x86,0x95,0x14,0x54,0x04, + 0x11,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x11,0x00, + 0x11,0x00,0xd2,0xec,0xd1,0xa4,0xd0,0x76,0xcf,0x86,0xd5,0x48,0xd4,0x28,0xd3,0x14, + 0x52,0x04,0x08,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x10,0x04,0x08,0x00, + 0x00,0x00,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x08,0x00,0x08,0xdc,0x10,0x04, + 0x08,0x00,0x08,0xe6,0xd3,0x10,0x52,0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x00,0x00, + 0x08,0x00,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x08,0x00, + 0x08,0x00,0x54,0x04,0x08,0x00,0xd3,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x14,0x00, + 0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe6,0x08,0x01,0x10,0x04,0x08,0xdc, + 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x08,0x09,0xcf,0x86,0x95,0x28, + 0xd4,0x14,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x08,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x10,0x00, + 0x00,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x24,0xd3,0x14,0x52,0x04,0x10,0x00, + 0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0xe6,0x10,0x04,0x10,0xdc,0x00,0x00,0x92,0x0c, + 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x52,0x04, + 0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd1,0x54, + 0xd0,0x26,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52,0x04, + 0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, + 0x0b,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x0b,0x00,0x93,0x0c, + 0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x0b,0x00,0x54,0x04,0x0b,0x00, + 0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00, + 0x0b,0x00,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x54,0x04,0x10,0x00,0xd3,0x0c,0x92,0x08, + 0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, + 0x10,0x00,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14, + 0x53,0x04,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00, + 0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x96,0xd2,0x68,0xd1,0x24,0xd0,0x06, + 0xcf,0x06,0x0b,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x0b,0x00,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd0,0x1e,0xcf,0x86,0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0x93,0x10,0x92,0x0c, + 0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, + 0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x11,0x00, + 0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x11,0x00, + 0x11,0x00,0xd1,0x28,0xd0,0x22,0xcf,0x86,0x55,0x04,0x14,0x00,0xd4,0x0c,0x93,0x08, + 0x12,0x04,0x14,0x00,0x14,0xe6,0x00,0x00,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04, + 0x14,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a, + 0xd1,0x24,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04, + 0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04, + 0x0b,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x58,0xd0,0x12,0xcf,0x86,0x55,0x04, + 0x14,0x00,0x94,0x08,0x13,0x04,0x14,0x00,0x00,0x00,0x14,0x00,0xcf,0x86,0x95,0x40, + 0xd4,0x24,0xd3,0x0c,0x52,0x04,0x14,0x00,0x11,0x04,0x14,0x00,0x14,0xdc,0xd2,0x0c, + 0x51,0x04,0x14,0xe6,0x10,0x04,0x14,0xe6,0x14,0xdc,0x91,0x08,0x10,0x04,0x14,0xe6, + 0x14,0xdc,0x14,0xdc,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0xdc,0x14,0x00, + 0x14,0x00,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x15,0x00, + 0x93,0x10,0x52,0x04,0x15,0x00,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00, + 0x00,0x00,0xcf,0x86,0xe5,0x0f,0x06,0xe4,0xf8,0x03,0xe3,0x02,0x02,0xd2,0xfb,0xd1, + 0x4c,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x1c,0xd3,0x10,0x52, + 0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x09,0x0c,0x00,0x52,0x04,0x0c, + 0x00,0x11,0x04,0x0c,0x00,0x00,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x0c, + 0x00,0x0c,0x00,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00, + 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x09,0xd0,0x69,0xcf,0x86,0xd5, + 0x32,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0xd2,0x15,0x51,0x04,0x0b,0x00,0x10, + 0x0d,0x0b,0xff,0xf0,0x91,0x82,0x99,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x91,0x11, + 0x10,0x0d,0x0b,0xff,0xf0,0x91,0x82,0x9b,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x0b, + 0x00,0xd4,0x1d,0x53,0x04,0x0b,0x00,0x92,0x15,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, + 0x00,0x0b,0xff,0xf0,0x91,0x82,0xa5,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x53,0x04, + 0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x10,0x04,0x0b,0x07, + 0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3,0x0c,0x92,0x08,0x11,0x04, + 0x0b,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00, + 0x14,0x00,0x00,0x00,0x0d,0x00,0xd4,0x14,0x53,0x04,0x0d,0x00,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x08, + 0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0xd1,0x96,0xd0,0x5c,0xcf,0x86,0xd5,0x18, + 0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x0d,0x00, + 0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd4,0x26,0x53,0x04,0x0d,0x00,0x52,0x04,0x0d,0x00, + 0x51,0x04,0x0d,0x00,0x10,0x0d,0x0d,0xff,0xf0,0x91,0x84,0xb1,0xf0,0x91,0x84,0xa7, + 0x00,0x0d,0xff,0xf0,0x91,0x84,0xb2,0xf0,0x91,0x84,0xa7,0x00,0x93,0x18,0xd2,0x0c, + 0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x0d,0x09,0x91,0x08,0x10,0x04,0x0d,0x09, + 0x00,0x00,0x0d,0x00,0x0d,0x00,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04, + 0x0d,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x10,0x00, + 0x54,0x04,0x10,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00, + 0x10,0x07,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0,0x06, + 0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0d,0x09,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x0d,0x00,0x11,0x00,0x10,0x04,0x11,0x07,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00, + 0x10,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04, + 0x10,0x00,0x11,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00, + 0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xc8,0xd1,0x48, + 0xd0,0x42,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, + 0x10,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x54,0x04,0x10,0x00, + 0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0x09,0x10,0x04, + 0x10,0x07,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x12,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xd0,0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x10, + 0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04, + 0x00,0x00,0x11,0x00,0x53,0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00, + 0x10,0x04,0x00,0x00,0x11,0x00,0x94,0x10,0x53,0x04,0x11,0x00,0x92,0x08,0x11,0x04, + 0x11,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x18, + 0x53,0x04,0x10,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0x07,0x10,0x04, + 0x10,0x09,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00, + 0x00,0x00,0x00,0x00,0xe1,0x27,0x01,0xd0,0x8a,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3, + 0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x10,0x00,0x10,0x00,0x91,0x08,0x10, + 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10, + 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0xd4, + 0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10, + 0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10, + 0x00,0x10,0x04,0x00,0x00,0x14,0x07,0x91,0x08,0x10,0x04,0x10,0x07,0x10,0x00,0x10, + 0x00,0xcf,0x86,0xd5,0x6a,0xd4,0x42,0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0xd2,0x19,0xd1,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0xff,0xf0,0x91,0x8d,0x87,0xf0, + 0x91,0x8c,0xbe,0x00,0x91,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x8d,0x87,0xf0,0x91, + 0x8d,0x97,0x00,0x10,0x09,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11, + 0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x52, + 0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd4,0x1c,0xd3, + 0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0xe6,0x52,0x04,0x10,0xe6,0x91, + 0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x10,0xe6,0x91, + 0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3, + 0x30,0x01,0xd2,0xb7,0xd1,0x48,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x95,0x3c, + 0xd4,0x1c,0x93,0x18,0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x09,0x12,0x00, + 0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x07,0x12,0x00,0x12,0x00,0x53,0x04,0x12,0x00, + 0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x00,0x00,0x12,0x00,0xd1,0x08,0x10,0x04, + 0x00,0x00,0x12,0x00,0x10,0x04,0x14,0xe6,0x15,0x00,0x00,0x00,0xd0,0x45,0xcf,0x86, + 0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0xd2,0x15,0x51,0x04, + 0x10,0x00,0x10,0x04,0x10,0x00,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xba, + 0x00,0xd1,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xb0,0x00, + 0x10,0x00,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xbd,0x00,0x10, + 0x00,0xcf,0x86,0x95,0x24,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10, + 0x04,0x10,0x09,0x10,0x07,0x10,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11, + 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0, + 0x40,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x0c,0x52,0x04,0x10, + 0x00,0x11,0x04,0x10,0x00,0x00,0x00,0xd2,0x1e,0x51,0x04,0x10,0x00,0x10,0x0d,0x10, + 0xff,0xf0,0x91,0x96,0xb8,0xf0,0x91,0x96,0xaf,0x00,0x10,0xff,0xf0,0x91,0x96,0xb9, + 0xf0,0x91,0x96,0xaf,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10,0x09,0xcf, + 0x86,0x95,0x2c,0xd4,0x1c,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x07,0x10, + 0x00,0x10,0x00,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0x53, + 0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0xd2, + 0xa0,0xd1,0x5c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53, + 0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10, + 0x09,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x93,0x10,0x52,0x04,0x10,0x00,0x91,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11, + 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12, + 0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x2a,0xcf, + 0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0xd3,0x10,0x52,0x04,0x0d,0x00,0x51, + 0x04,0x0d,0x00,0x10,0x04,0x0d,0x09,0x0d,0x07,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x53,0x04,0x0d, + 0x00,0x92,0x08,0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x54,0x04,0x11,0x00,0x53,0x04,0x11,0x00,0xd2, + 0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00, + 0x00,0x11,0x00,0x11,0x00,0x94,0x14,0x53,0x04,0x11,0x00,0x92,0x0c,0x51,0x04,0x11, + 0x00,0x10,0x04,0x11,0x00,0x11,0x09,0x00,0x00,0x11,0x00,0xcf,0x06,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xe4,0x59,0x01,0xd3,0xb2,0xd2,0x5c,0xd1,0x28,0xd0,0x22,0xcf,0x86, + 0x55,0x04,0x14,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14,0x00,0x92,0x10,0xd1,0x08, + 0x10,0x04,0x14,0x00,0x14,0x09,0x10,0x04,0x14,0x07,0x14,0x00,0x00,0x00,0xcf,0x06, + 0x00,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, + 0x00,0x00,0x10,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04, + 0x00,0x00,0x94,0x10,0x53,0x04,0x15,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00, + 0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x15,0x00,0x53,0x04,0x15,0x00, + 0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x94,0x1c,0x93,0x18,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x15,0x09,0x15,0x00,0x15,0x00,0x91,0x08,0x10,0x04,0x15,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xa0,0xd1,0x3c,0xd0,0x1e,0xcf,0x86, + 0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x93,0x10,0x52,0x04,0x13,0x00,0x91,0x08, + 0x10,0x04,0x13,0x09,0x13,0x00,0x13,0x00,0x13,0x00,0xcf,0x86,0x95,0x18,0x94,0x14, + 0x93,0x10,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x13,0x09, + 0x00,0x00,0x13,0x00,0x13,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4,0x10,0x93,0x0c, + 0x52,0x04,0x13,0x00,0x11,0x04,0x15,0x00,0x13,0x00,0x13,0x00,0x53,0x04,0x13,0x00, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x13,0x00,0x13,0x09,0x13,0x00,0x91,0x08,0x10,0x04, + 0x13,0x00,0x14,0x00,0x13,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x13,0x00, + 0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3,0xa9,0x01,0xd2, + 0xb0,0xd1,0x6c,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x54, + 0x04,0x12,0x00,0xd3,0x10,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12, + 0x00,0x00,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x12, + 0x09,0xcf,0x86,0xd5,0x14,0x94,0x10,0x93,0x0c,0x52,0x04,0x12,0x00,0x11,0x04,0x12, + 0x00,0x00,0x00,0x00,0x00,0x12,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12, + 0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xd0,0x3e,0xcf, + 0x86,0xd5,0x14,0x54,0x04,0x12,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x12, + 0x00,0x12,0x00,0x12,0x00,0xd4,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x93,0x10,0x52,0x04,0x12,0x00,0x51, + 0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1, + 0xa0,0xd0,0x52,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3,0x10,0x52,0x04,0x13,0x00,0x51, + 0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10, + 0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x54,0x04,0x13,0x00,0xd3,0x10,0x52, + 0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0xd2,0x0c,0x51, + 0x04,0x00,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x00, + 0x00,0x13,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x51,0x04,0x13, + 0x00,0x10,0x04,0x13,0x07,0x13,0x00,0x11,0x04,0x13,0x09,0x13,0x00,0x00,0x00,0x53, + 0x04,0x13,0x00,0x92,0x08,0x11,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x94,0x20,0xd3, + 0x10,0x52,0x04,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd0, + 0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x14,0x53,0x04,0x14,0x00,0x52,0x04,0x14,0x00,0x51, + 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x14, + 0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x14, + 0x09,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94, + 0x10,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14, + 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x15, + 0x00,0x54,0x04,0x15,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x15,0x00,0x00,0x00,0x00, + 0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0xd0, + 0xca,0xcf,0x86,0xd5,0xc2,0xd4,0x54,0xd3,0x06,0xcf,0x06,0x09,0x00,0xd2,0x06,0xcf, + 0x06,0x09,0x00,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09, + 0x00,0x94,0x14,0x53,0x04,0x09,0x00,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10, + 0x04,0x09,0x00,0x10,0x00,0x10,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x10, + 0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x11,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x68,0xd2,0x46,0xd1,0x40,0xd0, + 0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x20,0xd3,0x10,0x92, + 0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10, + 0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x09, + 0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x11, + 0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x95,0x10,0x94,0x0c,0x93, + 0x08,0x12,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x4c,0xd4,0x06,0xcf, + 0x06,0x0b,0x00,0xd3,0x40,0xd2,0x3a,0xd1,0x34,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0b, + 0x00,0xd4,0x14,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10, + 0x04,0x0b,0x00,0x00,0x00,0x53,0x04,0x15,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf, - 0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5, - 0xa2,0xd4,0x9c,0xd3,0x74,0xd2,0x26,0xd1,0x20,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x94, - 0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x0c,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13, - 0x00,0x13,0x00,0xcf,0x06,0x13,0x00,0xcf,0x06,0x13,0x00,0xd1,0x48,0xd0,0x1e,0xcf, - 0x86,0x95,0x18,0x54,0x04,0x13,0x00,0x53,0x04,0x13,0x00,0x52,0x04,0x13,0x00,0x51, - 0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54, - 0x04,0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x94,0x0c,0x93,0x08,0x12,0x04,0x00,0x00,0x15,0x00,0x00, - 0x00,0x13,0x00,0xcf,0x06,0x13,0x00,0xd2,0x22,0xd1,0x06,0xcf,0x06,0x13,0x00,0xd0, - 0x06,0xcf,0x06,0x13,0x00,0xcf,0x86,0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x53, - 0x04,0x13,0x00,0x12,0x04,0x13,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x7e,0xd2,0x78,0xd1,0x34,0xd0,0x06,0xcf, - 0x06,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x92, - 0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10, - 0x00,0x52,0x04,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0, - 0x3e,0xcf,0x86,0xd5,0x2c,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0xd2,0x08,0x11, - 0x04,0x10,0x00,0x00,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x01,0x10,0x00,0x94, - 0x0c,0x93,0x08,0x12,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xe1,0x92,0x04,0xd0,0x08,0xcf,0x86, - 0xcf,0x06,0x00,0x00,0xcf,0x86,0xe5,0x2f,0x04,0xe4,0x7f,0x02,0xe3,0xf4,0x01,0xd2, - 0x26,0xd1,0x06,0xcf,0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x55, - 0x04,0x05,0x00,0x54,0x04,0x05,0x00,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05, - 0x00,0x00,0x00,0x00,0x00,0xd1,0xeb,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94, - 0x20,0xd3,0x10,0x52,0x04,0x05,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00, - 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x05,0x00,0x05,0x00,0x05, - 0x00,0xcf,0x86,0xd5,0x2a,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05, - 0x00,0x51,0x04,0x05,0x00,0x10,0x0d,0x05,0xff,0xf0,0x9d,0x85,0x97,0xf0,0x9d,0x85, - 0xa5,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0x00,0xd4,0x75,0xd3, - 0x61,0xd2,0x44,0xd1,0x22,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85, - 0xa5,0xf0,0x9d,0x85,0xae,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5, - 0xf0,0x9d,0x85,0xaf,0x00,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85, - 0xa5,0xf0,0x9d,0x85,0xb0,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5, - 0xf0,0x9d,0x85,0xb1,0x00,0xd1,0x15,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0, - 0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xb2,0x00,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0x01, - 0xd2,0x08,0x11,0x04,0x05,0x01,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe2, - 0x05,0xd8,0xd3,0x10,0x92,0x0c,0x51,0x04,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0x00, - 0x05,0x00,0x92,0x0c,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x05,0xdc,0x05,0xdc, + 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x4c,0xd0,0x44,0xcf, + 0x86,0xd5,0x3c,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2, + 0x2a,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x93, + 0x10,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0xd2,0x01,0xcf,0x86,0xd5,0x06,0xcf,0x06, + 0x00,0x00,0xe4,0x0b,0x01,0xd3,0x06,0xcf,0x06,0x0c,0x00,0xd2,0x84,0xd1,0x50,0xd0, + 0x1e,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5, + 0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10, + 0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x10,0x00,0xd2,0x08,0x11, + 0x04,0x10,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x00,0x00,0xd0,0x06,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x00,0x00,0x10,0x00,0xd4,0x10,0x53, + 0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x93,0x10,0x52, + 0x04,0x10,0x01,0x91,0x08,0x10,0x04,0x10,0x01,0x10,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x6c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x93,0x10,0x52, + 0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x10,0xe6,0x10,0x00,0x10,0x00,0xcf, + 0x86,0xd5,0x24,0xd4,0x10,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00, + 0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x00, + 0x00,0x10,0x00,0x10,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10, + 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x00, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd0,0x0e,0xcf,0x86,0x95, + 0x08,0x14,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf, + 0x06,0x00,0x00,0xd2,0x30,0xd1,0x0c,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x06,0x14, + 0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x14,0x00,0x53,0x04,0x14,0x00,0x92, + 0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xd1,0x4c,0xd0,0x06,0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x2c,0x94, + 0x28,0xd3,0x10,0x52,0x04,0x0d,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x15,0x00,0x15, + 0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x51,0x04,0x00, + 0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0d,0x00,0x54,0x04,0x0d,0x00,0x53,0x04,0x0d, + 0x00,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x15,0x00,0xd0, + 0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x15,0x00,0x52,0x04,0x00,0x00,0x51, + 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x00,0x00,0xcf,0x86,0x55, + 0x04,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x13, + 0x00,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xcf,0x06,0x12,0x00,0xe2, + 0xc6,0x01,0xd1,0x8e,0xd0,0x86,0xcf,0x86,0xd5,0x48,0xd4,0x06,0xcf,0x06,0x12,0x00, + 0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x06,0xcf,0x06,0x12,0x00,0xd1,0x06,0xcf,0x06, + 0x12,0x00,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12,0x00,0xd4,0x14, + 0x53,0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x14,0x00, + 0x14,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0x00,0x00, + 0xd4,0x36,0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06,0x12,0x00, + 0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12,0x00,0x54,0x04,0x12,0x00, + 0x93,0x10,0x92,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0xa2,0xd4,0x9c,0xd3,0x74, + 0xd2,0x26,0xd1,0x20,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0xcf,0x06, + 0x13,0x00,0xcf,0x06,0x13,0x00,0xd1,0x48,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x13,0x00,0x53,0x04,0x13,0x00,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04, + 0x13,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x00,0x00,0x93,0x10, + 0x92,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x94,0x0c,0x93,0x08,0x12,0x04,0x00,0x00,0x15,0x00,0x00,0x00,0x13,0x00,0xcf,0x06, + 0x13,0x00,0xd2,0x22,0xd1,0x06,0xcf,0x06,0x13,0x00,0xd0,0x06,0xcf,0x06,0x13,0x00, + 0xcf,0x86,0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x53,0x04,0x13,0x00,0x12,0x04, + 0x13,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06, + 0x00,0x00,0xd3,0x7f,0xd2,0x79,0xd1,0x34,0xd0,0x06,0xcf,0x06,0x10,0x00,0xcf,0x86, + 0x55,0x04,0x10,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00, + 0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00, + 0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0,0x3f,0xcf,0x86,0xd5,0x2c, + 0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0xd2,0x08,0x11,0x04,0x10,0x00,0x00,0x00, + 0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x01,0x10,0x00,0x94,0x0d,0x93,0x09,0x12,0x05, + 0x10,0xff,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xe1,0x96,0x04,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xcf,0x86,0xe5,0x33,0x04,0xe4,0x83,0x02,0xe3,0xf8,0x01,0xd2,0x26,0xd1,0x06,0xcf, + 0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x55,0x04,0x05,0x00,0x54, + 0x04,0x05,0x00,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x00,0x00,0x00, + 0x00,0xd1,0xef,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94,0x20,0xd3,0x10,0x52, + 0x04,0x05,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0xd5, + 0x2a,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x51,0x04,0x05, + 0x00,0x10,0x0d,0x05,0xff,0xf0,0x9d,0x85,0x97,0xf0,0x9d,0x85,0xa5,0x00,0x05,0xff, + 0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0x00,0xd4,0x75,0xd3,0x61,0xd2,0x44,0xd1, + 0x22,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85, + 0xae,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xaf, + 0x00,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85, + 0xb0,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xb1, + 0x00,0xd1,0x15,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0, + 0x9d,0x85,0xb2,0x00,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0x01,0xd2,0x08,0x11,0x04, + 0x05,0x01,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe2,0x05,0xd8,0xd3,0x12, + 0x92,0x0d,0x51,0x04,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0xff,0x00,0x05,0xff,0x00, + 0x92,0x0e,0x51,0x05,0x05,0xff,0x00,0x10,0x05,0x05,0xff,0x00,0x05,0xdc,0x05,0xdc, 0xd0,0x97,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x05,0xdc, 0x10,0x04,0x05,0xdc,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe6,0x05,0xe6, 0x92,0x08,0x11,0x04,0x05,0xe6,0x05,0xdc,0x05,0x00,0x05,0x00,0xd4,0x14,0x53,0x04, @@ -4080,20 +4090,21 @@ static const unsigned char utf8data[64080] = { 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, - 0x00,0xd4,0xc8,0xd3,0x70,0xd2,0x68,0xd1,0x60,0xd0,0x58,0xcf,0x86,0xd5,0x50,0xd4, - 0x4a,0xd3,0x44,0xd2,0x2a,0xd1,0x24,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x05,0x00,0xcf,0x06,0x05,0x00,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, - 0x06,0x07,0x00,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x14, - 0x04,0x07,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf, - 0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2, - 0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00, - 0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52, - 0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xcf,0x06,0x02,0x00,0x81, - 0x80,0xcf,0x86,0x85,0x84,0xcf,0x86,0xcf,0x06,0x02,0x00,0x00,0x00,0x00,0x00,0x00 + 0x00,0xd4,0xd9,0xd3,0x81,0xd2,0x79,0xd1,0x71,0xd0,0x69,0xcf,0x86,0xd5,0x60,0xd4, + 0x59,0xd3,0x52,0xd2,0x33,0xd1,0x2c,0xd0,0x25,0xcf,0x86,0x95,0x1e,0x94,0x19,0x93, + 0x14,0x92,0x0f,0x91,0x0a,0x10,0x05,0x00,0xff,0x00,0x05,0xff,0x00,0x00,0xff,0x00, + 0x00,0xff,0x00,0x00,0xff,0x00,0x00,0xff,0x00,0x05,0xff,0x00,0xcf,0x06,0x05,0xff, + 0x00,0xcf,0x06,0x00,0xff,0x00,0xd1,0x07,0xcf,0x06,0x07,0xff,0x00,0xd0,0x07,0xcf, + 0x06,0x07,0xff,0x00,0xcf,0x86,0x55,0x05,0x07,0xff,0x00,0x14,0x05,0x07,0xff,0x00, + 0x00,0xff,0x00,0xcf,0x06,0x00,0xff,0x00,0xcf,0x06,0x00,0xff,0x00,0xcf,0x06,0x00, + 0xff,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, + 0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86, + 0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06, + 0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00, + 0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06, + 0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00, + 0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xcf,0x06,0x02,0x00, + 0x81,0x80,0xcf,0x86,0x85,0x84,0xcf,0x86,0xcf,0x06,0x02,0x00,0x00,0x00,0x00,0x00 }; const struct utf8data_table utf8_data_table = { diff --git a/fs/vboxsf/Kconfig b/fs/vboxsf/Kconfig index b84586ae08b3..d4694026db8b 100644 --- a/fs/vboxsf/Kconfig +++ b/fs/vboxsf/Kconfig @@ -1,6 +1,6 @@ config VBOXSF_FS tristate "VirtualBox guest shared folder (vboxsf) support" - depends on X86 && VBOXGUEST + depends on (ARM64 || X86) && VBOXGUEST select NLS help VirtualBox hosts can share folders with guests, this driver diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index ed9b0dabc1f1..7afa51e41427 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -51,6 +51,8 @@ xfs-y += $(addprefix libxfs/, \ xfs_rmap_btree.o \ xfs_refcount.o \ xfs_refcount_btree.o \ + xfs_rtrefcount_btree.o \ + xfs_rtrmap_btree.o \ xfs_sb.o \ xfs_symlink_remote.o \ xfs_trans_inode.o \ @@ -193,6 +195,8 @@ xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \ rgsuper.o \ rtbitmap.o \ + rtrefcount.o \ + rtrmap.o \ rtsummary.o \ ) @@ -232,6 +236,8 @@ xfs-y += $(addprefix scrub/, \ xfs-$(CONFIG_XFS_RT) += $(addprefix scrub/, \ rtbitmap_repair.o \ + rtrefcount_repair.o \ + rtrmap_repair.o \ rtsummary_repair.o \ ) diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index f5d853089019..fb79215a509d 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -114,6 +114,7 @@ xfs_ag_resv_needed( case XFS_AG_RESV_RMAPBT: len -= xfs_perag_resv(pag, type)->ar_reserved; break; + case XFS_AG_RESV_METAFILE: case XFS_AG_RESV_NONE: /* empty */ break; @@ -347,6 +348,7 @@ xfs_ag_resv_alloc_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: @@ -389,6 +391,7 @@ xfs_ag_resv_free_extent( switch (type) { case XFS_AG_RESV_AGFL: + case XFS_AG_RESV_METAFILE: return; case XFS_AG_RESV_METADATA: case XFS_AG_RESV_RMAPBT: diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 17875ad865f5..8c04acd30d48 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1004,9 +1004,7 @@ xfs_attr_add_fork( unsigned int blks; /* space reservation */ int error; /* error return value */ - if (xfs_is_metadir_inode(ip)) - ASSERT(XFS_IS_DQDETACHED(ip)); - else + if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); blks = XFS_ADDAFORK_SPACE_RES(mp); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 5255f93bae31..40ad22fb808b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -615,7 +615,7 @@ xfs_bmap_btree_to_extents( xfs_trans_binval(tp, cbp); if (cur->bc_levels[0].bp == cbp) cur->bc_levels[0].bp = NULL; - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); ifp->if_format = XFS_DINODE_FMT_EXTENTS; *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); @@ -659,12 +659,11 @@ xfs_bmap_extents_to_btree( * Make space in the inode incore. This needs to be undone if we fail * to expand the root. */ - xfs_iroot_realloc(ip, 1, whichfork); + block = xfs_bmap_broot_realloc(ip, whichfork, 1); /* * Fill in the root. */ - block = ifp->if_broot; xfs_bmbt_init_block(ip, block, NULL, 1, 1); /* * Need a cursor. Can't allocate until bb_level is filled in. @@ -746,7 +745,7 @@ xfs_bmap_extents_to_btree( out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); out_root_realloc: - xfs_iroot_realloc(ip, -1, whichfork); + xfs_bmap_broot_realloc(ip, whichfork, 0); ifp->if_format = XFS_DINODE_FMT_EXTENTS; ASSERT(ifp->if_broot == NULL); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); @@ -1043,9 +1042,7 @@ xfs_bmap_add_attrfork( int error; /* error return value */ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); - if (xfs_is_metadir_inode(ip)) - ASSERT(XFS_IS_DQDETACHED(ip)); - else + if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); ASSERT(!xfs_inode_has_attr_fork(ip)); @@ -4567,8 +4564,9 @@ xfs_bmapi_write( * the refcount btree for orphan recovery. */ if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, - bma.length); + xfs_refcount_alloc_cow_extent(tp, + XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); } /* Deal with the allocated space we found. */ @@ -4743,7 +4741,8 @@ xfs_bmapi_convert_one_delalloc( *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) - xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length); + xfs_refcount_alloc_cow_extent(tp, XFS_IS_REALTIME_INODE(ip), + bma.blkno, bma.length); error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, whichfork); @@ -5391,7 +5390,7 @@ xfs_bmap_del_extent_real( bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { - xfs_refcount_decrease_extent(tp, del); + xfs_refcount_decrease_extent(tp, isrt, del); } else if (isrt && !xfs_has_rtgroups(mp)) { error = xfs_bmap_free_rtblocks(tp, del); } else { @@ -6501,9 +6500,8 @@ xfs_get_extsz_hint( * No point in aligning allocations if we need to COW to actually * write to them. */ - if (xfs_is_always_cow_inode(ip)) - return 0; - if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) + if (!xfs_is_always_cow_inode(ip) && + (ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize) return ip->i_extsize; if (XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1) @@ -6526,7 +6524,13 @@ xfs_get_cowextsz_hint( a = 0; if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) a = ip->i_cowextsize; - b = xfs_get_extsz_hint(ip); + if (XFS_IS_REALTIME_INODE(ip)) { + b = 0; + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) + b = ip->i_extsize; + } else { + b = xfs_get_extsz_hint(ip); + } a = max(a, b); if (a == 0) diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 3464be771f95..908d7b050e9c 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -516,6 +516,116 @@ xfs_bmbt_keys_contiguous( be64_to_cpu(key2->bmbt.br_startoff)); } +static inline void +xfs_bmbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_bmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_bmbt_ptr_t)); +} + +/* + * Reallocate the space for if_broot based on the number of records. Move the + * records and pointers in if_broot to fit the new size. When shrinking this + * will eliminate holes between the records and pointers created by the caller. + * When growing this will create holes to be filled in by the caller. + * + * The caller must not request to add more records than would fit in the + * on-disk inode root. If the if_broot is currently NULL, then if we are + * adding records, one will be allocated. The caller must also not request + * that the number of records go below zero, although it can go to zero. + * + * ip -- the inode whose if_broot area is changing + * whichfork -- which inode fork to change + * new_numrecs -- the new number of records requested for the if_broot array + * + * Returns the incore btree root block. + */ +struct xfs_btree_block * +xfs_bmap_broot_realloc( + struct xfs_inode *ip, + int whichfork, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + + /* + * Block mapping btrees do not support storing zero records; if this + * happens, the fork is being changed to FMT_EXTENTS. Free the broot + * and get out. + */ + if (new_numrecs == 0) + return xfs_broot_realloc(ifp, 0); + + new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just + * allocate it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need + * to realloc() it and shift the pointers to their new + * location. The records don't change location because + * they are kept butted up against the btree block header. + */ + old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + xfs_bmbt_move_ptrs(mp, broot, old_size, new_size, old_numrecs); + return broot; + } + + /* + * We're reducing, but not totally eliminating, numrecs. In this case, + * we are shrinking the if_broot buffer, so it must already exist. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); + + /* + * Shrink the btree root by moving the bmbt pointers, since they are + * not butted up against the btree block header, then reallocating + * broot. + */ + xfs_bmbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(broot) <= + xfs_inode_fork_size(ip, whichfork)); + return broot; +} + +static struct xfs_btree_block * +xfs_bmbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + return xfs_bmap_broot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + new_numrecs); +} + const struct xfs_btree_ops xfs_bmbt_ops = { .name = "bmap", .type = XFS_BTREE_TYPE_INODE, @@ -543,6 +653,7 @@ const struct xfs_btree_ops xfs_bmbt_ops = { .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, .keys_contiguous = xfs_bmbt_keys_contiguous, + .broot_realloc = xfs_bmbt_broot_realloc, }; /* diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h index 49a3bae3f6ec..b238d559ab03 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.h +++ b/fs/xfs/libxfs/xfs_bmap_btree.h @@ -198,4 +198,7 @@ xfs_bmap_bmdr_space(struct xfs_btree_block *bb) return xfs_bmdr_space_calc(be16_to_cpu(bb->bb_numrecs)); } +struct xfs_btree_block *xfs_bmap_broot_realloc(struct xfs_inode *ip, + int whichfork, unsigned int new_numrecs); + #endif /* __XFS_BMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 2b5fc5fd1643..299ce7fd11b0 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -30,6 +30,12 @@ #include "xfs_health.h" #include "xfs_buf_mem.h" #include "xfs_btree_mem.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap.h" +#include "xfs_rmap.h" +#include "xfs_quota.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" /* * Btree magic numbers. @@ -1537,12 +1543,16 @@ xfs_btree_log_recs( int first, int last) { + if (!bp) { + xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, + xfs_ilog_fbroot(cur->bc_ino.whichfork)); + return; + } xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_rec_offset(cur, first), xfs_btree_rec_offset(cur, last + 1) - 1); - } /* @@ -3078,6 +3088,131 @@ xfs_btree_split( #define xfs_btree_split __xfs_btree_split #endif /* __KERNEL__ */ +/* Move the records from a root leaf block to a separate block. */ +STATIC void +xfs_btree_promote_leaf_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + union xfs_btree_key *kp; + union xfs_btree_ptr *pp; + struct xfs_btree_block *broot; + int numrecs = xfs_btree_get_numrecs(block); + + /* Copy the records from the leaf broot into the new child block. */ + rp = xfs_btree_rec_addr(cur, 1, block); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, crp, rp, numrecs); + + /* + * Increment the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * leaf to a node block. Free the existing leaf broot so that nobody + * thinks we need to migrate node pointers when we realloc the broot + * buffer after bumping nlevels. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels++; + cur->bc_levels[1].ptr = 1; + + /* + * Allocate a new node broot and initialize it to point to the new + * child block. + */ + broot = cur->bc_ops->broot_realloc(cur, 1); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, + cur->bc_nlevels - 1, 1, cur->bc_ino.ip->i_ino); + + pp = xfs_btree_ptr_addr(cur, 1, broot); + kp = xfs_btree_key_addr(cur, 1, broot); + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, 0, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_recs(cur, cbp, 1, numrecs); +} + +/* + * Move the keys and pointers from a root block to a separate block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_promote_node_iroot( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + int level, + struct xfs_buf *cbp, + union xfs_btree_ptr *cptr, + struct xfs_btree_block *cblock) +{ + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + int numrecs = xfs_btree_get_numrecs(block); + + /* + * Increase tree height, adjusting the root block level to match. + * We cannot change the root btree node size until we've copied the + * block contents to the new child block. + */ + be16_add_cpu(&block->bb_level, 1); + cur->bc_nlevels++; + cur->bc_levels[level + 1].ptr = 1; + + /* + * Adjust the root btree record count, then copy the keys from the old + * root to the new child block. + */ + xfs_btree_set_numrecs(block, 1); + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, ckp, kp, numrecs); + + /* Check the pointers and copy them to the new child block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, cpp, pp, numrecs); + + /* + * Set the first keyptr to point to the new child block, then shrink + * the memory buffer for the root block. + */ + error = xfs_btree_debug_check_ptr(cur, cptr, 0, level); + if (error) + return error; + xfs_btree_copy_ptrs(cur, pp, cptr, 1); + xfs_btree_get_keys(cur, cblock, kp); + + cur->bc_ops->broot_realloc(cur, 1); + + /* Attach the new block to the cursor and log it. */ + xfs_btree_setbuf(cur, level, cbp); + xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); + xfs_btree_log_keys(cur, cbp, 1, numrecs); + xfs_btree_log_ptrs(cur, cbp, 1, numrecs); + return 0; +} + /* * Copy the old inode root contents into a real block and make the * broot point to it. @@ -3091,14 +3226,10 @@ xfs_btree_new_iroot( struct xfs_buf *cbp; /* buffer for cblock */ struct xfs_btree_block *block; /* btree block */ struct xfs_btree_block *cblock; /* child btree block */ - union xfs_btree_key *ckp; /* child key pointer */ - union xfs_btree_ptr *cpp; /* child ptr pointer */ - union xfs_btree_key *kp; /* pointer to btree key */ - union xfs_btree_ptr *pp; /* pointer to block addr */ + union xfs_btree_ptr aptr; union xfs_btree_ptr nptr; /* new block addr */ int level; /* btree level */ int error; /* error return code */ - int i; /* loop counter */ XFS_BTREE_STATS_INC(cur, newroot); @@ -3107,10 +3238,15 @@ xfs_btree_new_iroot( level = cur->bc_nlevels - 1; block = xfs_btree_get_iroot(cur); - pp = xfs_btree_ptr_addr(cur, 1, block); + ASSERT(level > 0 || (cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)); + if (level > 0) + aptr = *xfs_btree_ptr_addr(cur, 1, block); + else + aptr.l = cpu_to_be64(XFS_INO_TO_FSB(cur->bc_mp, + cur->bc_ino.ip->i_ino)); /* Allocate the new block. If we can't do it, we're toast. Give up. */ - error = xfs_btree_alloc_block(cur, pp, &nptr, stat); + error = xfs_btree_alloc_block(cur, &aptr, &nptr, stat); if (error) goto error0; if (*stat == 0) @@ -3136,47 +3272,16 @@ xfs_btree_new_iroot( cblock->bb_u.s.bb_blkno = bno; } - be16_add_cpu(&block->bb_level, 1); - xfs_btree_set_numrecs(block, 1); - cur->bc_nlevels++; - ASSERT(cur->bc_nlevels <= cur->bc_maxlevels); - cur->bc_levels[level + 1].ptr = 1; - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, ckp, kp, xfs_btree_get_numrecs(cblock)); - - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) { - error = xfs_btree_debug_check_ptr(cur, pp, i, level); + if (level > 0) { + error = xfs_btree_promote_node_iroot(cur, block, level, cbp, + &nptr, cblock); if (error) goto error0; + } else { + xfs_btree_promote_leaf_iroot(cur, block, cbp, &nptr, cblock); } - xfs_btree_copy_ptrs(cur, cpp, pp, xfs_btree_get_numrecs(cblock)); - - error = xfs_btree_debug_check_ptr(cur, &nptr, 0, level); - if (error) - goto error0; - - xfs_btree_copy_ptrs(cur, pp, &nptr, 1); - - xfs_iroot_realloc(cur->bc_ino.ip, - 1 - xfs_btree_get_numrecs(cblock), - cur->bc_ino.whichfork); - - xfs_btree_setbuf(cur, level, cbp); - - /* - * Do all this logging at the end so that - * the root is at the right level. - */ - xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); - xfs_btree_log_keys(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); - - *logflags |= - XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); + *logflags |= XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); *stat = 1; return 0; error0: @@ -3347,7 +3452,7 @@ xfs_btree_make_block_unfull( if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ - xfs_iroot_realloc(ip, 1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ @@ -3557,14 +3662,31 @@ xfs_btree_insrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we just inserted into a new tree block, we have to - * recalculate nkey here because nkey is out of date. + * Update btree keys to reflect the newly added record or keyptr. + * There are three cases here to be aware of. Normally, all we have to + * do is walk towards the root, updating keys as necessary. + * + * If the caller had us target a full block for the insertion, we dealt + * with that by calling the _make_block_unfull function. If the + * "make unfull" function splits the block, it'll hand us back the key + * and pointer of the new block. We haven't yet added the new block to + * the next level up, so if we decide to add the new record to the new + * block (bp->b_bn != old_bn), we have to update the caller's pointer + * so that the caller adds the new block with the correct key. * - * Otherwise we're just updating an existing block (having shoved - * some records into the new tree block), so use the regular key - * update mechanism. + * However, there is a third possibility-- if the selected block is the + * root block of an inode-rooted btree and cannot be expanded further, + * the "make unfull" function moves the root block contents to a new + * block and updates the root block to point to the new block. In this + * case, no block pointer is passed back because the block has already + * been added to the btree. In this case, we need to use the regular + * key update function, just like the first case. This is critical for + * overlapping btrees, because the high key must be updated to reflect + * the entire tree, not just the subtree accessible through the first + * child of the root (which is now two levels down from the root). */ - if (bp && xfs_buf_daddr(bp) != old_bn) { + if (!xfs_btree_ptr_is_null(cur, &nptr) && + bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); @@ -3676,6 +3798,97 @@ error0: return error; } +/* Move the records from a child leaf block to the root block. */ +STATIC void +xfs_btree_demote_leaf_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int numrecs) +{ + union xfs_btree_rec *rp; + union xfs_btree_rec *crp; + struct xfs_btree_block *broot; + + /* + * Decrease the tree height. + * + * Trickery here: The amount of memory that we need per record for the + * ifork's btree root block may change when we convert the broot from a + * node to a leaf. Free the old node broot so that we can get a fresh + * leaf broot. + */ + cur->bc_ops->broot_realloc(cur, 0); + cur->bc_nlevels--; + + /* + * Allocate a new leaf broot and copy the records from the old child. + * Detach the old child from the cursor. + */ + broot = cur->bc_ops->broot_realloc(cur, numrecs); + xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, 0, numrecs, + cur->bc_ino.ip->i_ino); + + rp = xfs_btree_rec_addr(cur, 1, broot); + crp = xfs_btree_rec_addr(cur, 1, cblock); + xfs_btree_copy_recs(cur, rp, crp, numrecs); + + cur->bc_levels[0].bp = NULL; +} + +/* + * Move the keyptrs from a child node block to the root block. + * + * Since the keyptr size does not change, all we have to do is increase the + * tree height, copy the keyptrs to the new internal node (cblock), shrink + * the root, and copy the pointers there. + */ +STATIC int +xfs_btree_demote_node_child( + struct xfs_btree_cur *cur, + struct xfs_btree_block *cblock, + int level, + int numrecs) +{ + struct xfs_btree_block *block; + union xfs_btree_key *ckp; + union xfs_btree_key *kp; + union xfs_btree_ptr *cpp; + union xfs_btree_ptr *pp; + int i; + int error; + + /* + * Adjust the root btree node size and the record count to match the + * doomed child so that we can copy the keyptrs ahead of changing the + * tree shape. + */ + block = cur->bc_ops->broot_realloc(cur, numrecs); + + xfs_btree_set_numrecs(block, numrecs); + ASSERT(block->bb_numrecs == cblock->bb_numrecs); + + /* Copy keys from the doomed block. */ + kp = xfs_btree_key_addr(cur, 1, block); + ckp = xfs_btree_key_addr(cur, 1, cblock); + xfs_btree_copy_keys(cur, kp, ckp, numrecs); + + /* Copy pointers from the doomed block. */ + pp = xfs_btree_ptr_addr(cur, 1, block); + cpp = xfs_btree_ptr_addr(cur, 1, cblock); + for (i = 0; i < numrecs; i++) { + error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (error) + return error; + } + xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + + /* Decrease tree height, adjusting the root block level to match. */ + cur->bc_levels[level - 1].bp = NULL; + be16_add_cpu(&block->bb_level, -1); + cur->bc_nlevels--; + return 0; +} + /* * Try to merge a non-leaf block back into the inode root. * @@ -3688,34 +3901,31 @@ STATIC int xfs_btree_kill_iroot( struct xfs_btree_cur *cur) { - int whichfork = cur->bc_ino.whichfork; struct xfs_inode *ip = cur->bc_ino.ip; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; struct xfs_btree_block *cblock; - union xfs_btree_key *kp; - union xfs_btree_key *ckp; - union xfs_btree_ptr *pp; - union xfs_btree_ptr *cpp; struct xfs_buf *cbp; int level; - int index; int numrecs; int error; #ifdef DEBUG union xfs_btree_ptr ptr; #endif - int i; ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); - ASSERT(cur->bc_nlevels > 1); + ASSERT((cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS) || + cur->bc_nlevels > 1); /* * Don't deal with the root block needs to be a leaf case. * We're just going to turn the thing back into extents anyway. */ level = cur->bc_nlevels - 1; - if (level == 1) + if (level == 1 && !(cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) + goto out0; + + /* If we're already a leaf, jump out. */ + if (level == 0) goto out0; /* @@ -3745,40 +3955,20 @@ xfs_btree_kill_iroot( ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif - index = numrecs - cur->bc_ops->get_maxrecs(cur, level); - if (index) { - xfs_iroot_realloc(cur->bc_ino.ip, index, - cur->bc_ino.whichfork); - block = ifp->if_broot; - } - - be16_add_cpu(&block->bb_numrecs, index); - ASSERT(block->bb_numrecs == cblock->bb_numrecs); - - kp = xfs_btree_key_addr(cur, 1, block); - ckp = xfs_btree_key_addr(cur, 1, cblock); - xfs_btree_copy_keys(cur, kp, ckp, numrecs); - - pp = xfs_btree_ptr_addr(cur, 1, block); - cpp = xfs_btree_ptr_addr(cur, 1, cblock); - - for (i = 0; i < numrecs; i++) { - error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); + if (level > 1) { + error = xfs_btree_demote_node_child(cur, cblock, level, + numrecs); if (error) return error; - } - - xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); + } else + xfs_btree_demote_leaf_child(cur, cblock, numrecs); error = xfs_btree_free_block(cur, cbp); if (error) return error; - cur->bc_levels[level - 1].bp = NULL; - be16_add_cpu(&block->bb_level, -1); xfs_trans_log_inode(cur->bc_tp, ip, XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork)); - cur->bc_nlevels--; out0: return 0; } @@ -3932,10 +4122,10 @@ xfs_btree_delrec( /* * We're at the root level. First, shrink the root block in-memory. * Try to get rid of the next level down. If we can't then there's - * nothing left to do. + * nothing left to do. numrecs was decremented above. */ if (xfs_btree_at_iroot(cur, level)) { - xfs_iroot_realloc(cur->bc_ino.ip, -1, cur->bc_ino.whichfork); + cur->bc_ops->broot_realloc(cur, numrecs); error = xfs_btree_kill_iroot(cur); if (error) @@ -5144,7 +5334,7 @@ xfs_btree_count_blocks_helper( int level, void *data) { - xfs_extlen_t *blocks = data; + xfs_filblks_t *blocks = data; (*blocks)++; return 0; @@ -5154,7 +5344,7 @@ xfs_btree_count_blocks_helper( int xfs_btree_count_blocks( struct xfs_btree_cur *cur, - xfs_extlen_t *blocks) + xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, @@ -5343,6 +5533,12 @@ xfs_btree_init_cur_caches(void) error = xfs_refcountbt_init_cur_cache(); if (error) goto err; + error = xfs_rtrmapbt_init_cur_cache(); + if (error) + goto err; + error = xfs_rtrefcountbt_init_cur_cache(); + if (error) + goto err; return 0; err: @@ -5359,6 +5555,8 @@ xfs_btree_destroy_cur_caches(void) xfs_bmbt_destroy_cur_cache(); xfs_rmapbt_destroy_cur_cache(); xfs_refcountbt_destroy_cur_cache(); + xfs_rtrmapbt_destroy_cur_cache(); + xfs_rtrefcountbt_destroy_cur_cache(); } /* Move the btree cursor before the first record. */ @@ -5387,3 +5585,67 @@ xfs_btree_goto_left_edge( return 0; } + +/* Allocate a block for an inode-rooted metadata btree. */ +int +xfs_btree_alloc_metafile_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + struct xfs_alloc_arg args = { + .mp = cur->bc_mp, + .tp = cur->bc_tp, + .resv = XFS_AG_RESV_METAFILE, + .minlen = 1, + .maxlen = 1, + .prod = 1, + }; + struct xfs_inode *ip = cur->bc_ino.ip; + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_alloc_vextent_start_ag(&args, + XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino)); + if (error) + return error; + if (args.fsbno == NULLFSBLOCK) { + *stat = 0; + return 0; + } + ASSERT(args.len == 1); + + xfs_metafile_resv_alloc_space(ip, &args); + + new->l = cpu_to_be64(args.fsbno); + *stat = 1; + return 0; +} + +/* Free a block from an inode-rooted metadata btree. */ +int +xfs_btree_free_metafile_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + struct xfs_owner_info oinfo; + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip = cur->bc_ino.ip; + struct xfs_trans *tp = cur->bc_tp; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); + int error; + + ASSERT(xfs_is_metadir_inode(ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); + error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE, + 0); + if (error) + return error; + + xfs_metafile_resv_free_space(ip, tp, 1); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 3b739459ebb0..355b304696e6 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -135,7 +135,7 @@ struct xfs_btree_ops { /* offset of btree stats array */ unsigned int statoff; - /* sick mask for health reporting (only for XFS_BTREE_TYPE_AG) */ + /* sick mask for health reporting (not for bmap btrees) */ unsigned int sick_mask; /* cursor operations */ @@ -213,11 +213,27 @@ struct xfs_btree_ops { const union xfs_btree_key *key1, const union xfs_btree_key *key2, const union xfs_btree_key *mask); + + /* + * Reallocate the space for if_broot to fit the number of records. + * Move the records and pointers in if_broot to fit the new size. When + * shrinking this will eliminate holes between the records and pointers + * created by the caller. When growing this will create holes to be + * filled in by the caller. + * + * The caller must not request to add more records than would fit in + * the on-disk inode root. If the if_broot is currently NULL, then if + * we are adding records, one will be allocated. The caller must also + * not request that the number of records go below zero, although it + * can go to zero. + */ + struct xfs_btree_block *(*broot_realloc)(struct xfs_btree_cur *cur, + unsigned int new_numrecs); }; /* btree geometry flags */ #define XFS_BTGEO_OVERLAPPING (1U << 0) /* overlapping intervals */ - +#define XFS_BTGEO_IROOT_RECORDS (1U << 1) /* iroot can store records */ union xfs_btree_irec { struct xfs_alloc_rec_incore a; @@ -281,7 +297,7 @@ struct xfs_btree_cur struct { unsigned int nr_ops; /* # record updates */ unsigned int shape_changes; /* # of extent splits */ - } bc_refc; /* refcountbt */ + } bc_refc; /* refcountbt/rtrefcountbt */ }; /* Must be at the end of the struct! */ @@ -484,7 +500,7 @@ typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level, int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data); -int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_filblks_t *blocks); union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block); @@ -687,4 +703,10 @@ xfs_btree_at_iroot( level == cur->bc_nlevels - 1; } +int xfs_btree_alloc_metafile_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, union xfs_btree_ptr *newp, + int *stat); +int xfs_btree_free_metafile_block(struct xfs_btree_cur *cur, + struct xfs_buf *bp); + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c index df3d613675a1..f2f7b4305413 100644 --- a/fs/xfs/libxfs/xfs_btree_mem.c +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -18,6 +18,7 @@ #include "xfs_ag.h" #include "xfs_buf_item.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" /* Set the root of an in-memory btree. */ void diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index 694929703152..5ed84f9cc877 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -134,6 +134,7 @@ xfs_btree_stage_ifakeroot( cur->bc_ino.ifake = ifake; cur->bc_nlevels = ifake->if_levels; cur->bc_ino.forksize = ifake->if_fork_size; + cur->bc_ino.whichfork = XFS_STAGING_FORK; cur->bc_flags |= XFS_BTREE_STAGING; } @@ -573,6 +574,7 @@ xfs_btree_bload_compute_geometry( struct xfs_btree_bload *bbl, uint64_t nr_records) { + const struct xfs_btree_ops *ops = cur->bc_ops; uint64_t nr_blocks = 0; uint64_t nr_this_level; @@ -599,7 +601,7 @@ xfs_btree_bload_compute_geometry( xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level, &avg_per_block, &level_blocks, &dontcare64); - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + if (ops->type == XFS_BTREE_TYPE_INODE) { /* * If all the items we want to store at this level * would fit in the inode root block, then we have our @@ -607,7 +609,9 @@ xfs_btree_bload_compute_geometry( * * Note that bmap btrees forbid records in the root. */ - if (level != 0 && nr_this_level <= avg_per_block) { + if ((level != 0 || + (ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) && + nr_this_level <= avg_per_block) { nr_blocks++; break; } @@ -658,7 +662,7 @@ xfs_btree_bload_compute_geometry( return -EOVERFLOW; bbl->btree_height = cur->bc_nlevels; - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) + if (ops->type == XFS_BTREE_TYPE_INODE) bbl->nr_blocks = nr_blocks - 1; else bbl->nr_blocks = nr_blocks; diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index ec51b8465e61..9effd95ddcd4 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -68,7 +68,9 @@ struct xfs_defer_op_type { extern const struct xfs_defer_op_type xfs_bmap_update_defer_type; extern const struct xfs_defer_op_type xfs_refcount_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type; extern const struct xfs_defer_op_type xfs_rmap_update_defer_type; +extern const struct xfs_defer_op_type xfs_rtrmap_update_defer_type; extern const struct xfs_defer_op_type xfs_extent_free_defer_type; extern const struct xfs_defer_op_type xfs_agfl_free_defer_type; extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type; diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 202468223bf9..1775abcfa04d 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -197,7 +197,7 @@ xfs_da_unmount( /* * Return 1 if directory contains only "." and "..". */ -int +static bool xfs_dir_isempty( xfs_inode_t *dp) { @@ -205,9 +205,9 @@ xfs_dir_isempty( ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_disk_size == 0) /* might happen during shutdown. */ - return 1; + return true; if (dp->i_disk_size > xfs_inode_data_fork_size(dp)) - return 0; + return false; sfp = dp->i_df.if_data; return !sfp->count; } @@ -379,12 +379,11 @@ xfs_dir_cilookup_result( !(args->op_flags & XFS_DA_OP_CILOOKUP)) return -EEXIST; - args->value = kmalloc(len, + args->value = kmemdup(name, len, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_RETRY_MAYFAIL); if (!args->value) return -ENOMEM; - memcpy(args->value, name, len); args->valuelen = len; return -EEXIST; } diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index 576068ed81fa..a6594a5a941d 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -58,7 +58,6 @@ extern void xfs_dir_startup(void); extern int xfs_da_mount(struct xfs_mount *mp); extern void xfs_da_unmount(struct xfs_mount *mp); -extern int xfs_dir_isempty(struct xfs_inode *dp); extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_inode *pdp); extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp, diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 7002d7676a78..a53c5d40e084 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -64,7 +64,8 @@ #define XFS_ERRTAG_WB_DELAY_MS 42 #define XFS_ERRTAG_WRITE_DELAY_MS 43 #define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44 -#define XFS_ERRTAG_MAX 45 +#define XFS_ERRTAG_METAFILE_RESV_CRITICAL 45 +#define XFS_ERRTAG_MAX 46 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -113,5 +114,6 @@ #define XFS_RANDOM_WB_DELAY_MS 3000 #define XFS_RANDOM_WRITE_DELAY_MS 3000 #define XFS_RANDOM_EXCHMAPS_FINISH_ONE 1 +#define XFS_RANDOM_METAFILE_RESV_CRITICAL 4 #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 2021396651de..3f1d6a98c118 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -662,7 +662,9 @@ xfs_exchmaps_rmapbt_blocks( if (!xfs_has_rmapbt(mp)) return 0; if (XFS_IS_REALTIME_INODE(req->ip1)) - return 0; + return howmany_64(req->nr_exchanges, + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * + XFS_RTRMAPADD_SPACE_RES(mp); return howmany_64(req->nr_exchanges, XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 4d47a3e723aa..b1007fb661ba 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -857,6 +857,8 @@ enum xfs_metafile_type { XFS_METAFILE_PRJQUOTA, /* project quota */ XFS_METAFILE_RTBITMAP, /* rt bitmap */ XFS_METAFILE_RTSUMMARY, /* rt summary */ + XFS_METAFILE_RTRMAP, /* rt rmap */ + XFS_METAFILE_RTREFCOUNT, /* rt refcount */ XFS_METAFILE_MAX } __packed; @@ -868,7 +870,9 @@ enum xfs_metafile_type { { XFS_METAFILE_GRPQUOTA, "grpquota" }, \ { XFS_METAFILE_PRJQUOTA, "prjquota" }, \ { XFS_METAFILE_RTBITMAP, "rtbitmap" }, \ - { XFS_METAFILE_RTSUMMARY, "rtsummary" } + { XFS_METAFILE_RTSUMMARY, "rtsummary" }, \ + { XFS_METAFILE_RTRMAP, "rtrmap" }, \ + { XFS_METAFILE_RTREFCOUNT, "rtrefcount" } /* * On-disk inode structure. @@ -997,7 +1001,8 @@ enum xfs_dinode_fmt { XFS_DINODE_FMT_LOCAL, /* bulk data */ XFS_DINODE_FMT_EXTENTS, /* struct xfs_bmbt_rec */ XFS_DINODE_FMT_BTREE, /* struct xfs_bmdr_block */ - XFS_DINODE_FMT_UUID /* added long ago, but never used */ + XFS_DINODE_FMT_UUID, /* added long ago, but never used */ + XFS_DINODE_FMT_META_BTREE, /* metadata btree */ }; #define XFS_INODE_FORMAT_STR \ @@ -1005,7 +1010,8 @@ enum xfs_dinode_fmt { { XFS_DINODE_FMT_LOCAL, "local" }, \ { XFS_DINODE_FMT_EXTENTS, "extent" }, \ { XFS_DINODE_FMT_BTREE, "btree" }, \ - { XFS_DINODE_FMT_UUID, "uuid" } + { XFS_DINODE_FMT_UUID, "uuid" }, \ + { XFS_DINODE_FMT_META_BTREE, "meta_btree" } /* * Max values for extnum and aextnum. @@ -1726,6 +1732,24 @@ typedef __be32 xfs_rmap_ptr_t; XFS_IBT_BLOCK(mp) + 1) /* + * Realtime Reverse mapping btree format definitions + * + * This is a btree for reverse mapping records for realtime volumes + */ +#define XFS_RTRMAP_CRC_MAGIC 0x4d415052 /* 'MAPR' */ + +/* + * rtrmap root header, on-disk form only. + */ +struct xfs_rtrmap_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-based btree pointer type */ +typedef __be64 xfs_rtrmap_ptr_t; + +/* * Reference Count Btree format definitions * */ @@ -1768,12 +1792,29 @@ struct xfs_refcount_key { __be32 rc_startblock; /* starting block number */ }; -#define MAXREFCOUNT ((xfs_nlink_t)~0U) -#define MAXREFCEXTLEN ((xfs_extlen_t)~0U) +#define XFS_REFC_REFCOUNT_MAX ((xfs_nlink_t)~0U) +#define XFS_REFC_LEN_MAX ((xfs_extlen_t)~0U) /* btree pointer type */ typedef __be32 xfs_refcount_ptr_t; +/* + * Realtime Reference Count btree format definitions + * + * This is a btree for reference count records for realtime volumes + */ +#define XFS_RTREFC_CRC_MAGIC 0x52434e54 /* 'RCNT' */ + +/* + * rt refcount root header, on-disk form only. + */ +struct xfs_rtrefcount_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + +/* inode-rooted btree pointer type */ +typedef __be64 xfs_rtrefcount_ptr_t; /* * BMAP Btree format definitions diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 41ce4d3d650e..2c3171262b44 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -737,9 +737,11 @@ struct xfs_scrub_metadata { #define XFS_SCRUB_TYPE_DIRTREE 28 /* directory tree structure */ #define XFS_SCRUB_TYPE_METAPATH 29 /* metadata directory tree paths */ #define XFS_SCRUB_TYPE_RGSUPER 30 /* realtime superblock */ +#define XFS_SCRUB_TYPE_RTRMAPBT 31 /* rtgroup reverse mapping btree */ +#define XFS_SCRUB_TYPE_RTREFCBT 32 /* realtime reference count btree */ /* Number of scrub subcommands. */ -#define XFS_SCRUB_TYPE_NR 31 +#define XFS_SCRUB_TYPE_NR 33 /* * This special type code only applies to the vectored scrub implementation. @@ -829,9 +831,11 @@ struct xfs_scrub_vec_head { #define XFS_SCRUB_METAPATH_USRQUOTA (5) /* user quota */ #define XFS_SCRUB_METAPATH_GRPQUOTA (6) /* group quota */ #define XFS_SCRUB_METAPATH_PRJQUOTA (7) /* project quota */ +#define XFS_SCRUB_METAPATH_RTRMAPBT (8) /* realtime reverse mapping */ +#define XFS_SCRUB_METAPATH_RTREFCOUNTBT (9) /* realtime refcount */ /* Number of metapath sm_ino values */ -#define XFS_SCRUB_METAPATH_NR (8) +#define XFS_SCRUB_METAPATH_NR (10) /* * ioctl limits @@ -993,6 +997,8 @@ struct xfs_rtgroup_geometry { #define XFS_RTGROUP_GEOM_SICK_SUPER (1U << 0) /* superblock */ #define XFS_RTGROUP_GEOM_SICK_BITMAP (1U << 1) /* rtbitmap */ #define XFS_RTGROUP_GEOM_SICK_SUMMARY (1U << 2) /* rtsummary */ +#define XFS_RTGROUP_GEOM_SICK_RMAPBT (1U << 3) /* reverse mappings */ +#define XFS_RTGROUP_GEOM_SICK_REFCNTBT (1U << 4) /* reference counts */ /* * ioctl commands that are used by Linux filesystems diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h index d34986ac18c3..b31000f7190c 100644 --- a/fs/xfs/libxfs/xfs_health.h +++ b/fs/xfs/libxfs/xfs_health.h @@ -70,6 +70,8 @@ struct xfs_rtgroup; #define XFS_SICK_RG_SUPER (1 << 0) /* rt group superblock */ #define XFS_SICK_RG_BITMAP (1 << 1) /* rt group bitmap */ #define XFS_SICK_RG_SUMMARY (1 << 2) /* rt groups summary */ +#define XFS_SICK_RG_RMAPBT (1 << 3) /* reverse mappings */ +#define XFS_SICK_RG_REFCNTBT (1 << 4) /* reference counts */ /* Observable health issues for AG metadata. */ #define XFS_SICK_AG_SB (1 << 0) /* superblock */ @@ -115,7 +117,9 @@ struct xfs_rtgroup; #define XFS_SICK_RG_PRIMARY (XFS_SICK_RG_SUPER | \ XFS_SICK_RG_BITMAP | \ - XFS_SICK_RG_SUMMARY) + XFS_SICK_RG_SUMMARY | \ + XFS_SICK_RG_RMAPBT | \ + XFS_SICK_RG_REFCNTBT) #define XFS_SICK_AG_PRIMARY (XFS_SICK_AG_SB | \ XFS_SICK_AG_AGF | \ diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 9b34896dd1a3..6f270d8f4270 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -744,6 +744,7 @@ xfs_finobt_count_blocks( { struct xfs_buf *agbp = NULL; struct xfs_btree_cur *cur; + xfs_filblks_t blocks; int error; error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); @@ -751,9 +752,10 @@ xfs_finobt_count_blocks( return error; cur = xfs_finobt_init_cursor(pag, tp, agbp); - error = xfs_btree_count_blocks(cur, tree_blocks); + error = xfs_btree_count_blocks(cur, &blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); + *tree_blocks = blocks; return error; } diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 424861fbf1bd..f24fa628fecf 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -441,6 +441,30 @@ xfs_dinode_verify_fork( if (di_nextents > max_extents) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp)) + return __this_address; + if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA))) + return __this_address; + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use + * the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(mp)) + return __this_address; + break; + case XFS_METAFILE_RTREFCOUNT: + /* same comment about growfs and rmap inodes applies */ + if (!xfs_has_reflink(mp)) + return __this_address; + break; + default: + return __this_address; + } + break; default: return __this_address; } @@ -460,6 +484,10 @@ xfs_dinode_verify_forkoff( if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3)) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp) || !xfs_has_parent(mp)) + return __this_address; + fallthrough; case XFS_DINODE_FMT_LOCAL: /* fall through ... */ case XFS_DINODE_FMT_EXTENTS: /* fall through ... */ case XFS_DINODE_FMT_BTREE: @@ -637,9 +665,6 @@ xfs_dinode_verify( if (mode && nextents + naextents > nblocks) return __this_address; - if (nextents + naextents == 0 && nblocks != 0) - return __this_address; - if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents) return __this_address; @@ -723,7 +748,8 @@ xfs_dinode_verify( return __this_address; /* don't let reflink and realtime mix */ - if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME)) + if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME) && + !xfs_has_rtreflink(mp)) return __this_address; /* COW extent size hint validation */ @@ -743,6 +769,12 @@ xfs_dinode_verify( return fa; } + /* metadata inodes containing btrees always have zero extent count */ + if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) { + if (nextents + naextents == 0 && nblocks != 0) + return __this_address; + } + return NULL; } @@ -878,11 +910,29 @@ xfs_inode_validate_cowextsize( bool rt_flag; bool hint_flag; uint32_t cowextsize_bytes; + uint32_t blocksize_bytes; rt_flag = (flags & XFS_DIFLAG_REALTIME); hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE); cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize); + /* + * Similar to extent size hints, a directory can be configured to + * propagate realtime status and a CoW extent size hint to newly + * created files even if there is no realtime device, and the hints on + * disk can become misaligned if the sysadmin changes the rt extent + * size while adding the realtime device. + * + * Therefore, we can only enforce the rextsize alignment check against + * regular realtime files, and rely on callers to decide when alignment + * checks are appropriate, and fix things up as needed. + */ + + if (rt_flag) + blocksize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); + else + blocksize_bytes = mp->m_sb.sb_blocksize; + if (hint_flag && !xfs_has_reflink(mp)) return __this_address; @@ -896,16 +946,13 @@ xfs_inode_validate_cowextsize( if (mode && !hint_flag && cowextsize != 0) return __this_address; - if (hint_flag && rt_flag) - return __this_address; - - if (cowextsize_bytes % mp->m_sb.sb_blocksize) + if (cowextsize_bytes % blocksize_bytes) return __this_address; if (cowextsize > XFS_MAX_BMBT_EXTLEN) return __this_address; - if (cowextsize > mp->m_sb.sb_agblocks / 2) + if (!rt_flag && cowextsize > mp->m_sb.sb_agblocks / 2) return __this_address; return NULL; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 1158ca48626b..4f99b90add55 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -27,6 +27,8 @@ #include "xfs_errortag.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_ifork_cache; @@ -178,7 +180,7 @@ xfs_iformat_btree( struct xfs_mount *mp = ip->i_mount; xfs_bmdr_block_t *dfp; struct xfs_ifork *ifp; - /* REFERENCED */ + struct xfs_btree_block *broot; int nrecs; int size; int level; @@ -211,16 +213,13 @@ xfs_iformat_btree( return -EFSCORRUPTED; } - ifp->if_broot_bytes = size; - ifp->if_broot = kmalloc(size, - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - ASSERT(ifp->if_broot != NULL); + broot = xfs_broot_alloc(ifp, size); /* * Copy and convert from the on-disk structure * to the in-memory structure. */ xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork), - ifp->if_broot, size); + broot, size); ifp->if_bytes = 0; ifp->if_data = NULL; @@ -270,6 +269,16 @@ xfs_iformat_data_fork( return xfs_iformat_extents(ip, dip, XFS_DATA_FORK); case XFS_DINODE_FMT_BTREE: return xfs_iformat_btree(ip, dip, XFS_DATA_FORK); + case XFS_DINODE_FMT_META_BTREE: + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + return xfs_iformat_rtrmap(ip, dip); + case XFS_METAFILE_RTREFCOUNT: + return xfs_iformat_rtrefcount(ip, dip); + default: + break; + } + fallthrough; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); @@ -363,135 +372,68 @@ xfs_iformat_attr_fork( } /* - * Reallocate the space for if_broot based on the number of records - * being added or deleted as indicated in rec_diff. Move the records - * and pointers in if_broot to fit the new size. When shrinking this - * will eliminate holes between the records and pointers created by - * the caller. When growing this will create holes to be filled in - * by the caller. - * - * The caller must not request to add more records than would fit in - * the on-disk inode root. If the if_broot is currently NULL, then - * if we are adding records, one will be allocated. The caller must also - * not request that the number of records go below zero, although - * it can go to zero. - * - * ip -- the inode whose if_broot area is changing - * ext_diff -- the change in the number of records, positive or negative, - * requested for the if_broot array. + * Allocate the if_broot component of an inode fork so that it is @new_size + * bytes in size, using __GFP_NOLOCKDEP like all the other code that + * initializes a broot during inode load. Returns if_broot. */ -void -xfs_iroot_realloc( - xfs_inode_t *ip, - int rec_diff, - int whichfork) +struct xfs_btree_block * +xfs_broot_alloc( + struct xfs_ifork *ifp, + size_t new_size) { - struct xfs_mount *mp = ip->i_mount; - int cur_max; - struct xfs_ifork *ifp; - struct xfs_btree_block *new_broot; - int new_max; - size_t new_size; - char *np; - char *op; + ASSERT(ifp->if_broot == NULL); - /* - * Handle the degenerate case quietly. - */ - if (rec_diff == 0) { - return; - } + ifp->if_broot = kmalloc(new_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; +} - ifp = xfs_ifork_ptr(ip, whichfork); - if (rec_diff > 0) { - /* - * If there wasn't any memory allocated before, just - * allocate it now and get out. - */ - if (ifp->if_broot_bytes == 0) { - new_size = xfs_bmap_broot_space_calc(mp, rec_diff); - ifp->if_broot = kmalloc(new_size, - GFP_KERNEL | __GFP_NOFAIL); - ifp->if_broot_bytes = (int)new_size; - return; - } +/* + * Reallocate the if_broot component of an inode fork so that it is @new_size + * bytes in size. Returns if_broot. + */ +struct xfs_btree_block * +xfs_broot_realloc( + struct xfs_ifork *ifp, + size_t new_size) +{ + /* No size change? No action needed. */ + if (new_size == ifp->if_broot_bytes) + return ifp->if_broot; - /* - * If there is already an existing if_broot, then we need - * to realloc() it and shift the pointers to their new - * location. The records don't change location because - * they are kept butted up against the btree block header. - */ - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); - new_max = cur_max + rec_diff; - new_size = xfs_bmap_broot_space_calc(mp, new_max); - ifp->if_broot = krealloc(ifp->if_broot, new_size, - GFP_KERNEL | __GFP_NOFAIL); - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - (int)new_size); - ifp->if_broot_bytes = (int)new_size; - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); - return; + /* New size is zero, free it. */ + if (new_size == 0) { + ifp->if_broot_bytes = 0; + kfree(ifp->if_broot); + ifp->if_broot = NULL; + return NULL; } /* - * rec_diff is less than 0. In this case, we are shrinking the - * if_broot buffer. It must already exist. If we go to zero - * records, just get rid of the root and clear the status bit. + * Shrinking the iroot means we allocate a new smaller object and copy + * it. We don't trust krealloc not to nop on realloc-down. */ - ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0)); - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); - new_max = cur_max + rec_diff; - ASSERT(new_max >= 0); - if (new_max > 0) - new_size = xfs_bmap_broot_space_calc(mp, new_max); - else - new_size = 0; - if (new_size > 0) { - new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); - /* - * First copy over the btree block header. - */ - memcpy(new_broot, ifp->if_broot, - xfs_bmbt_block_len(ip->i_mount)); - } else { - new_broot = NULL; + if (ifp->if_broot_bytes > 0 && ifp->if_broot_bytes > new_size) { + struct xfs_btree_block *old_broot = ifp->if_broot; + + ifp->if_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + memcpy(ifp->if_broot, old_broot, new_size); + kfree(old_broot); + return ifp->if_broot; } /* - * Only copy the keys and pointers if there are any. + * Growing the iroot means we can krealloc. This may get us the same + * object. */ - if (new_max > 0) { - /* - * First copy the keys. - */ - op = (char *)xfs_bmbt_key_addr(mp, ifp->if_broot, 1); - np = (char *)xfs_bmbt_key_addr(mp, new_broot, 1); - memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_key_t)); - - /* - * Then copy the pointers. - */ - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, new_broot, 1, - (int)new_size); - memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - } - kfree(ifp->if_broot); - ifp->if_broot = new_broot; - ifp->if_broot_bytes = (int)new_size; - if (ifp->if_broot) - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - return; + ifp->if_broot = krealloc(ifp->if_broot, new_size, + GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; } - /* * This is called when the amount of space needed for if_data * is increased or decreased. The change in size is indicated by @@ -671,6 +613,25 @@ xfs_iflush_fork( } break; + case XFS_DINODE_FMT_META_BTREE: + ASSERT(whichfork == XFS_DATA_FORK); + + if (!(iip->ili_fields & brootflag[whichfork])) + break; + + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + xfs_iflush_rtrmap(ip, dip); + break; + case XFS_METAFILE_RTREFCOUNT: + xfs_iflush_rtrefcount(ip, dip); + break; + default: + ASSERT(0); + break; + } + break; + default: ASSERT(0); break; diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 2373d12fd474..69ed0919d60b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -170,7 +170,11 @@ void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, void xfs_idestroy_fork(struct xfs_ifork *ifp); void * xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, int whichfork); -void xfs_iroot_realloc(struct xfs_inode *, int, int); +struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, + size_t new_size); +struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, + size_t new_size); + int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 15dec19b6c32..a472ac2e45d0 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -250,6 +250,10 @@ typedef struct xfs_trans_header { #define XFS_LI_XMD 0x1249 /* mapping exchange done */ #define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */ #define XFS_LI_EFD_RT 0x124b /* realtime extent free done */ +#define XFS_LI_RUI_RT 0x124c /* realtime rmap update intent */ +#define XFS_LI_RUD_RT 0x124d /* realtime rmap update done */ +#define XFS_LI_CUI_RT 0x124e /* realtime refcount update intent */ +#define XFS_LI_CUD_RT 0x124f /* realtime refcount update done */ #define XFS_LI_TYPE_DESC \ { XFS_LI_EFI, "XFS_LI_EFI" }, \ @@ -271,7 +275,11 @@ typedef struct xfs_trans_header { { XFS_LI_XMI, "XFS_LI_XMI" }, \ { XFS_LI_XMD, "XFS_LI_XMD" }, \ { XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \ - { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" } + { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }, \ + { XFS_LI_RUI_RT, "XFS_LI_RUI_RT" }, \ + { XFS_LI_RUD_RT, "XFS_LI_RUD_RT" }, \ + { XFS_LI_CUI_RT, "XFS_LI_CUI_RT" }, \ + { XFS_LI_CUD_RT, "XFS_LI_CUD_RT" } /* * Inode Log Item Format definitions. @@ -351,12 +359,6 @@ struct xfs_inode_log_format_32 { */ #define XFS_ILOG_IVERSION 0x8000 -#define XFS_ILOG_NONCORE (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ - XFS_ILOG_DBROOT | XFS_ILOG_DEV | \ - XFS_ILOG_ADATA | XFS_ILOG_AEXT | \ - XFS_ILOG_ABROOT | XFS_ILOG_DOWNER | \ - XFS_ILOG_AOWNER) - #define XFS_ILOG_DFORK (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ XFS_ILOG_DBROOT) diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 5397a8ff004d..66c7916fb5cd 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -79,6 +79,10 @@ extern const struct xlog_recover_item_ops xlog_xmi_item_ops; extern const struct xlog_recover_item_ops xlog_xmd_item_ops; extern const struct xlog_recover_item_ops xlog_rtefi_item_ops; extern const struct xlog_recover_item_ops xlog_rtefd_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtrud_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcui_item_ops; +extern const struct xlog_recover_item_ops xlog_rtcud_item_ops; /* * Macros, structures, prototypes for internal log manager use. diff --git a/fs/xfs/libxfs/xfs_metadir.c b/fs/xfs/libxfs/xfs_metadir.c index bae7377c0f22..178e89711cb7 100644 --- a/fs/xfs/libxfs/xfs_metadir.c +++ b/fs/xfs/libxfs/xfs_metadir.c @@ -29,6 +29,10 @@ #include "xfs_dir2_priv.h" #include "xfs_parent.h" #include "xfs_health.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_btree.h" +#include "xfs_alloc.h" /* * Metadata Directory Tree diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c index adeb25d1a444..2f5f554a36d4 100644 --- a/fs/xfs/libxfs/xfs_metafile.c +++ b/fs/xfs/libxfs/xfs_metafile.c @@ -17,6 +17,28 @@ #include "xfs_metafile.h" #include "xfs_trace.h" #include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_errortag.h" +#include "xfs_error.h" +#include "xfs_alloc.h" + +static const struct { + enum xfs_metafile_type mtype; + const char *name; +} xfs_metafile_type_strs[] = { XFS_METAFILE_TYPE_STR }; + +const char * +xfs_metafile_type_str(enum xfs_metafile_type metatype) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(xfs_metafile_type_strs); i++) { + if (xfs_metafile_type_strs[i].mtype == metatype) + return xfs_metafile_type_strs[i].name; + } + + return NULL; +} /* Set up an inode to be recognized as a metadata directory inode. */ void @@ -50,3 +72,204 @@ xfs_metafile_clear_iflag( ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } + +/* + * Is the amount of space that could be allocated towards a given metadata + * file at or beneath a certain threshold? + */ +static inline bool +xfs_metafile_resv_can_cover( + struct xfs_inode *ip, + int64_t rhs) +{ + /* + * The amount of space that can be allocated to this metadata file is + * the remaining reservation for the particular metadata file + the + * global free block count. Take care of the first case to avoid + * touching the per-cpu counter. + */ + if (ip->i_delayed_blks >= rhs) + return true; + + /* + * There aren't enough blocks left in the inode's reservation, but it + * isn't critical unless there also isn't enough free space. + */ + return __percpu_counter_compare(&ip->i_mount->m_fdblocks, + rhs - ip->i_delayed_blks, 2048) >= 0; +} + +/* + * Is this metadata file critically low on blocks? For now we'll define that + * as the number of blocks we can get our hands on being less than 10% of what + * we reserved or less than some arbitrary number (maximum btree height). + */ +bool +xfs_metafile_resv_critical( + struct xfs_inode *ip) +{ + uint64_t asked_low_water; + + if (!ip) + return false; + + ASSERT(xfs_is_metadir_inode(ip)); + trace_xfs_metafile_resv_critical(ip, 0); + + if (!xfs_metafile_resv_can_cover(ip, ip->i_mount->m_rtbtree_maxlevels)) + return true; + + asked_low_water = div_u64(ip->i_meta_resv_asked, 10); + if (!xfs_metafile_resv_can_cover(ip, asked_low_water)) + return true; + + return XFS_TEST_ERROR(false, ip->i_mount, + XFS_ERRTAG_METAFILE_RESV_CRITICAL); +} + +/* Allocate a block from the metadata file's reservation. */ +void +xfs_metafile_resv_alloc_space( + struct xfs_inode *ip, + struct xfs_alloc_arg *args) +{ + int64_t len = args->len; + + ASSERT(xfs_is_metadir_inode(ip)); + ASSERT(args->resv == XFS_AG_RESV_METAFILE); + + trace_xfs_metafile_resv_alloc_space(ip, args->len); + + /* + * Allocate the blocks from the metadata inode's block reservation + * and update the ondisk sb counter. + */ + if (ip->i_delayed_blks > 0) { + int64_t from_resv; + + from_resv = min_t(int64_t, len, ip->i_delayed_blks); + ip->i_delayed_blks -= from_resv; + xfs_mod_delalloc(ip, 0, -from_resv); + xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS, + -from_resv); + len -= from_resv; + } + + /* + * Any allocation in excess of the reservation requires in-core and + * on-disk fdblocks updates. If we can grab @len blocks from the + * in-core fdblocks then all we need to do is update the on-disk + * superblock; if not, then try to steal some from the transaction's + * block reservation. Overruns are only expected for rmap btrees. + */ + if (len) { + unsigned int field; + int error; + + error = xfs_dec_fdblocks(ip->i_mount, len, true); + if (error) + field = XFS_TRANS_SB_FDBLOCKS; + else + field = XFS_TRANS_SB_RES_FDBLOCKS; + + xfs_trans_mod_sb(args->tp, field, -len); + } + + ip->i_nblocks += args->len; + xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE); +} + +/* Free a block to the metadata file's reservation. */ +void +xfs_metafile_resv_free_space( + struct xfs_inode *ip, + struct xfs_trans *tp, + xfs_filblks_t len) +{ + int64_t to_resv; + + ASSERT(xfs_is_metadir_inode(ip)); + trace_xfs_metafile_resv_free_space(ip, len); + + ip->i_nblocks -= len; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + /* + * Add the freed blocks back into the inode's delalloc reservation + * until it reaches the maximum size. Update the ondisk fdblocks only. + */ + to_resv = ip->i_meta_resv_asked - (ip->i_nblocks + ip->i_delayed_blks); + if (to_resv > 0) { + to_resv = min_t(int64_t, to_resv, len); + ip->i_delayed_blks += to_resv; + xfs_mod_delalloc(ip, 0, to_resv); + xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv); + len -= to_resv; + } + + /* + * Everything else goes back to the filesystem, so update the in-core + * and on-disk counters. + */ + if (len) + xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len); +} + +/* Release a metadata file's space reservation. */ +void +xfs_metafile_resv_free( + struct xfs_inode *ip) +{ + /* Non-btree metadata inodes don't need space reservations. */ + if (!ip || !ip->i_meta_resv_asked) + return; + + ASSERT(xfs_is_metadir_inode(ip)); + trace_xfs_metafile_resv_free(ip, 0); + + if (ip->i_delayed_blks) { + xfs_mod_delalloc(ip, 0, -ip->i_delayed_blks); + xfs_add_fdblocks(ip->i_mount, ip->i_delayed_blks); + ip->i_delayed_blks = 0; + } + ip->i_meta_resv_asked = 0; +} + +/* Set up a metadata file's space reservation. */ +int +xfs_metafile_resv_init( + struct xfs_inode *ip, + xfs_filblks_t ask) +{ + xfs_filblks_t hidden_space; + xfs_filblks_t used; + int error; + + if (!ip || ip->i_meta_resv_asked > 0) + return 0; + + ASSERT(xfs_is_metadir_inode(ip)); + + /* + * Space taken by all other metadata btrees are accounted on-disk as + * used space. We therefore only hide the space that is reserved but + * not used by the trees. + */ + used = ip->i_nblocks; + if (used > ask) + ask = used; + hidden_space = ask - used; + + error = xfs_dec_fdblocks(ip->i_mount, hidden_space, true); + if (error) { + trace_xfs_metafile_resv_init_error(ip, error, _RET_IP_); + return error; + } + + xfs_mod_delalloc(ip, 0, hidden_space); + ip->i_delayed_blks = hidden_space; + ip->i_meta_resv_asked = ask; + + trace_xfs_metafile_resv_init(ip, ask); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h index acec400123db..95af4b52e5a7 100644 --- a/fs/xfs/libxfs/xfs_metafile.h +++ b/fs/xfs/libxfs/xfs_metafile.h @@ -6,6 +6,8 @@ #ifndef __XFS_METAFILE_H__ #define __XFS_METAFILE_H__ +const char *xfs_metafile_type_str(enum xfs_metafile_type metatype); + /* All metadata files must have these flags set. */ #define XFS_METAFILE_DIFLAGS (XFS_DIFLAG_IMMUTABLE | \ XFS_DIFLAG_SYNC | \ @@ -21,6 +23,17 @@ void xfs_metafile_set_iflag(struct xfs_trans *tp, struct xfs_inode *ip, enum xfs_metafile_type metafile_type); void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip); +/* Space reservations for metadata inodes. */ +struct xfs_alloc_arg; + +bool xfs_metafile_resv_critical(struct xfs_inode *ip); +void xfs_metafile_resv_alloc_space(struct xfs_inode *ip, + struct xfs_alloc_arg *args); +void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp, + xfs_filblks_t len); +void xfs_metafile_resv_free(struct xfs_inode *ip); +int xfs_metafile_resv_init(struct xfs_inode *ip, xfs_filblks_t ask); + /* Code specific to kernel/userspace; must be provided externally. */ int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino, diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h index ad0dedf00f18..a85ecddaa48e 100644 --- a/fs/xfs/libxfs/xfs_ondisk.h +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -83,6 +83,10 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(union xfs_rtword_raw, 4); XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo, 48); + XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root, 4); + XFS_CHECK_STRUCT_SIZE(xfs_rtrefcount_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrefcount_root, 4); /* * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 2dbab68b4fe6..cebe83f7842a 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -25,6 +25,9 @@ #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_refcount_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_refcount_intent_cache; @@ -128,7 +131,7 @@ xfs_refcount_check_irec( struct xfs_perag *pag, const struct xfs_refcount_irec *irec) { - if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) return __this_address; if (!xfs_refcount_check_domain(irec)) @@ -138,12 +141,43 @@ xfs_refcount_check_irec( if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) return __this_address; - if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) return __this_address; return NULL; } +xfs_failaddr_t +xfs_rtrefcount_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_blockcount == 0 || irec->rc_blockcount > XFS_REFC_LEN_MAX) + return __this_address; + + if (!xfs_refcount_check_domain(irec)) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_rgbext(rtg, irec->rc_startblock, irec->rc_blockcount)) + return __this_address; + + if (irec->rc_refcount == 0 || irec->rc_refcount > XFS_REFC_REFCOUNT_MAX) + return __this_address; + + return NULL; +} + +static inline xfs_failaddr_t +xfs_refcount_check_btrec( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec) +{ + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + return xfs_rtrefcount_check_irec(to_rtg(cur->bc_group), irec); + return xfs_refcount_check_irec(to_perag(cur->bc_group), irec); +} + static inline int xfs_refcount_complain_bad_rec( struct xfs_btree_cur *cur, @@ -152,9 +186,15 @@ xfs_refcount_complain_bad_rec( { struct xfs_mount *mp = cur->bc_mp; - xfs_warn(mp, + if (xfs_btree_is_rtrefcount(cur->bc_ops)) { + xfs_warn(mp, + "RT Refcount BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); + } else { + xfs_warn(mp, "Refcount BTree record corruption in AG %d detected at %pS!", cur->bc_group->xg_gno, fa); + } xfs_warn(mp, "Start block 0x%x, block count 0x%x, references 0x%x", irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); @@ -180,7 +220,7 @@ xfs_refcount_get_rec( return error; xfs_refcount_btrec_to_irec(rec, irec); - fa = xfs_refcount_check_irec(to_perag(cur->bc_group), irec); + fa = xfs_refcount_check_btrec(cur, irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, irec); @@ -853,9 +893,9 @@ xfs_refc_merge_refcount( const struct xfs_refcount_irec *irec, enum xfs_refc_adjust_op adjust) { - /* Once a record hits MAXREFCOUNT, it is pinned there forever */ - if (irec->rc_refcount == MAXREFCOUNT) - return MAXREFCOUNT; + /* Once a record hits XFS_REFC_REFCOUNT_MAX, it is pinned forever */ + if (irec->rc_refcount == XFS_REFC_REFCOUNT_MAX) + return XFS_REFC_REFCOUNT_MAX; return irec->rc_refcount + adjust; } @@ -898,7 +938,7 @@ xfs_refc_want_merge_center( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount + right->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; *ulenp = ulen; @@ -933,7 +973,7 @@ xfs_refc_want_merge_left( * hence we need to catch u32 addition overflows here. */ ulen += cleft->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -967,7 +1007,7 @@ xfs_refc_want_merge_right( * hence we need to catch u32 addition overflows here. */ ulen += cright->rc_blockcount; - if (ulen >= MAXREFCEXTLEN) + if (ulen >= XFS_REFC_LEN_MAX) return false; return true; @@ -1065,7 +1105,7 @@ xfs_refcount_still_have_space( */ overhead = xfs_allocfree_block_count(cur->bc_mp, cur->bc_refc.shape_changes); - overhead += cur->bc_mp->m_refc_maxlevels; + overhead += cur->bc_maxlevels; overhead *= cur->bc_mp->m_sb.sb_blocksize; /* @@ -1085,6 +1125,22 @@ xfs_refcount_still_have_space( cur->bc_refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } +/* Schedule an extent free. */ +static int +xrefc_free_extent( + struct xfs_btree_cur *cur, + struct xfs_refcount_irec *rec) +{ + unsigned int flags = 0; + + if (xfs_btree_is_rtrefcount(cur->bc_ops)) + flags |= XFS_FREE_EXTENT_REALTIME; + + return xfs_free_extent_later(cur->bc_tp, + xfs_gbno_to_fsb(cur->bc_group, rec->rc_startblock), + rec->rc_blockcount, NULL, XFS_AG_RESV_NONE, flags); +} + /* * Adjust the refcounts of middle extents. At this point we should have * split extents that crossed the adjustment range; merged with adjacent @@ -1101,7 +1157,6 @@ xfs_refcount_adjust_extents( struct xfs_refcount_irec ext, tmp; int error; int found_rec, found_tmp; - xfs_fsblock_t fsbno; /* Merging did all the work already. */ if (*aglen == 0) @@ -1117,7 +1172,7 @@ xfs_refcount_adjust_extents( if (error) goto out_error; if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_SHARED; @@ -1154,11 +1209,7 @@ xfs_refcount_adjust_extents( goto out_error; } } else { - fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), - tmp.rc_startblock); - error = xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + error = xrefc_free_extent(cur, &tmp); if (error) goto out_error; } @@ -1196,7 +1247,7 @@ xfs_refcount_adjust_extents( * Adjust the reference count and either update the tree * (incr) or free the blocks (decr). */ - if (ext.rc_refcount == MAXREFCOUNT) + if (ext.rc_refcount == XFS_REFC_REFCOUNT_MAX) goto skip; ext.rc_refcount += adj; trace_xfs_refcount_modify_extent(cur, &ext); @@ -1216,11 +1267,7 @@ xfs_refcount_adjust_extents( } goto advloop; } else { - fsbno = xfs_agbno_to_fsb(to_perag(cur->bc_group), - ext.rc_startblock); - error = xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + error = xrefc_free_extent(cur, &ext); if (error) goto out_error; } @@ -1417,12 +1464,122 @@ xfs_refcount_finish_one( } /* + * Set up a continuation a deferred rtrefcount operation by updating the + * intent. Checks to make sure we're not going to run off the end of the + * rtgroup. + */ +static inline int +xfs_rtrefcount_continue_op( + struct xfs_btree_cur *cur, + struct xfs_refcount_intent *ri, + xfs_agblock_t new_agbno) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + if (XFS_IS_CORRUPT(mp, !xfs_verify_rgbext(rtg, new_agbno, + ri->ri_blockcount))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + ri->ri_startblock = xfs_rgbno_to_rtb(rtg, new_agbno); + + ASSERT(xfs_verify_rtbext(mp, ri->ri_startblock, ri->ri_blockcount)); + return 0; +} + +/* + * Process one of the deferred realtime refcount operations. We pass back the + * btree cursor to maintain our lock on the btree between calls. + */ +int +xfs_rtrefcount_finish_one( + struct xfs_trans *tp, + struct xfs_refcount_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + struct xfs_btree_cur *rcur = *pcur; + int error = 0; + xfs_rgblock_t bno; + unsigned long nr_ops = 0; + int shape_changes = 0; + + bno = xfs_rtb_to_rgbno(mp, ri->ri_startblock); + + trace_xfs_refcount_deferred(mp, ri); + + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) + return -EIO; + + /* + * If we haven't gotten a cursor or the cursor AG doesn't match + * the startblock, get one now. + */ + if (rcur != NULL && rcur->bc_group != ri->ri_group) { + nr_ops = rcur->bc_refc.nr_ops; + shape_changes = rcur->bc_refc.shape_changes; + xfs_btree_del_cursor(rcur, 0); + rcur = NULL; + *pcur = NULL; + } + if (rcur == NULL) { + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_REFCOUNT); + *pcur = rcur = xfs_rtrefcountbt_init_cursor(tp, rtg); + + rcur->bc_refc.nr_ops = nr_ops; + rcur->bc_refc.shape_changes = shape_changes; + } + + switch (ri->ri_type) { + case XFS_REFCOUNT_INCREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_INCREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_DECREASE: + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_DECREASE); + if (error) + return error; + if (ri->ri_blockcount > 0) + error = xfs_rtrefcount_continue_op(rcur, ri, bno); + break; + case XFS_REFCOUNT_ALLOC_COW: + error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + case XFS_REFCOUNT_FREE_COW: + error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); + if (error) + return error; + ri->ri_blockcount = 0; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + if (!error && ri->ri_blockcount > 0) + trace_xfs_refcount_finish_one_leftover(mp, ri); + return error; +} + +/* * Record a refcount intent for later processing. */ static void __xfs_refcount_add( struct xfs_trans *tp, enum xfs_refcount_intent_type type, + bool isrt, xfs_fsblock_t startblock, xfs_extlen_t blockcount) { @@ -1434,6 +1591,7 @@ __xfs_refcount_add( ri->ri_type = type; ri->ri_startblock = startblock; ri->ri_blockcount = blockcount; + ri->ri_realtime = isrt; xfs_refcount_defer_add(tp, ri); } @@ -1444,12 +1602,13 @@ __xfs_refcount_add( void xfs_refcount_increase_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1459,12 +1618,13 @@ xfs_refcount_increase_extent( void xfs_refcount_decrease_extent( struct xfs_trans *tp, + bool isrt, struct xfs_bmbt_irec *PREV) { if (!xfs_has_reflink(tp->t_mountp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, PREV->br_startblock, + __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, isrt, PREV->br_startblock, PREV->br_blockcount); } @@ -1666,7 +1826,7 @@ xfs_refcount_adjust_cow_extents( goto out_error; } if (!found_rec) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; + ext.rc_startblock = xfs_group_max_blocks(cur->bc_group); ext.rc_blockcount = 0; ext.rc_refcount = 0; ext.rc_domain = XFS_REFC_DOMAIN_COW; @@ -1820,6 +1980,7 @@ __xfs_refcount_cow_free( void xfs_refcount_alloc_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1828,17 +1989,17 @@ xfs_refcount_alloc_cow_extent( if (!xfs_has_reflink(mp)) return; - __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len); + __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, isrt, fsb, len); /* Add rmap entry */ - xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + xfs_rmap_alloc_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ void xfs_refcount_free_cow_extent( struct xfs_trans *tp, + bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len) { @@ -1848,9 +2009,8 @@ xfs_refcount_free_cow_extent( return; /* Remove rmap entry */ - xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb), - XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); - __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len); + xfs_rmap_free_extent(tp, isrt, fsb, len, XFS_RMAP_OWN_COW); + __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, isrt, fsb, len); } struct xfs_refcount_recovery { @@ -1879,8 +2039,7 @@ xfs_refcount_recover_extent( INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - if (xfs_refcount_check_irec(to_perag(cur->bc_group), &rr->rr_rrec) != - NULL || + if (xfs_refcount_check_btrec(cur, &rr->rr_rrec) != NULL || XFS_IS_CORRUPT(cur->bc_mp, rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { xfs_btree_mark_sick(cur); @@ -1895,12 +2054,13 @@ xfs_refcount_recover_extent( /* Find and remove leftover CoW reservations. */ int xfs_refcount_recover_cow_leftovers( - struct xfs_mount *mp, - struct xfs_perag *pag) + struct xfs_group *xg) { + struct xfs_mount *mp = xg->xg_mount; + bool isrt = xg->xg_type == XG_TYPE_RTG; struct xfs_trans *tp; struct xfs_btree_cur *cur; - struct xfs_buf *agbp; + struct xfs_buf *agbp = NULL; struct xfs_refcount_recovery *rr, *n; struct list_head debris; union xfs_btree_irec low = { @@ -1913,10 +2073,19 @@ xfs_refcount_recover_cow_leftovers( xfs_fsblock_t fsb; int error; - /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ + /* reflink filesystems must not have groups larger than 2^31-1 blocks */ + BUILD_BUG_ON(XFS_MAX_RGBLOCKS >= XFS_REFC_COWFLAG); BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); - if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) - return -EOPNOTSUPP; + + if (isrt) { + if (!xfs_has_rtgroups(mp)) + return 0; + if (xfs_group_max_blocks(xg) >= XFS_MAX_RGBLOCKS) + return -EOPNOTSUPP; + } else { + if (xfs_group_max_blocks(xg) > XFS_MAX_CRC_AG_BLOCKS) + return -EOPNOTSUPP; + } INIT_LIST_HEAD(&debris); @@ -1934,16 +2103,24 @@ xfs_refcount_recover_cow_leftovers( if (error) return error; - error = xfs_alloc_read_agf(pag, tp, 0, &agbp); - if (error) - goto out_trans; - cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + if (isrt) { + xfs_rtgroup_lock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(xg)); + } else { + error = xfs_alloc_read_agf(to_perag(xg), tp, 0, &agbp); + if (error) + goto out_trans; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, to_perag(xg)); + } /* Find all the leftover CoW staging extents. */ error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agbp); + if (agbp) + xfs_trans_brelse(tp, agbp); + else + xfs_rtgroup_unlock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT); xfs_trans_cancel(tp); if (error) goto out_free; @@ -1956,14 +2133,15 @@ xfs_refcount_recover_cow_leftovers( goto out_free; /* Free the orphan record */ - fsb = xfs_agbno_to_fsb(pag, rr->rr_rrec.rc_startblock); - xfs_refcount_free_cow_extent(tp, fsb, + fsb = xfs_gbno_to_fsb(xg, rr->rr_rrec.rc_startblock); + xfs_refcount_free_cow_extent(tp, isrt, fsb, rr->rr_rrec.rc_blockcount); /* Free the block. */ error = xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) goto out_trans; @@ -2028,7 +2206,7 @@ xfs_refcount_query_range_helper( xfs_failaddr_t fa; xfs_refcount_btrec_to_irec(rec, &irec); - fa = xfs_refcount_check_irec(to_perag(cur->bc_group), &irec); + fa = xfs_refcount_check_btrec(cur, &irec); if (fa) return xfs_refcount_complain_bad_rec(cur, fa, &irec); diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 62d78afcf1f3..f2e299a716a4 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -12,6 +12,7 @@ struct xfs_perag; struct xfs_btree_cur; struct xfs_bmbt_irec; struct xfs_refcount_irec; +struct xfs_rtgroup; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); @@ -60,6 +61,7 @@ struct xfs_refcount_intent { enum xfs_refcount_intent_type ri_type; xfs_extlen_t ri_blockcount; xfs_fsblock_t ri_startblock; + bool ri_realtime; }; /* Check that the refcount is appropriate for the record domain. */ @@ -74,24 +76,25 @@ xfs_refcount_check_domain( return true; } -void xfs_refcount_increase_extent(struct xfs_trans *tp, +void xfs_refcount_increase_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -void xfs_refcount_decrease_extent(struct xfs_trans *tp, +void xfs_refcount_decrease_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); -extern int xfs_refcount_finish_one(struct xfs_trans *tp, +int xfs_refcount_finish_one(struct xfs_trans *tp, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); +int xfs_rtrefcount_finish_one(struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_end_of_shared); -void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -void xfs_refcount_free_cow_extent(struct xfs_trans *tp, xfs_fsblock_t fsb, - xfs_extlen_t len); -extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, - struct xfs_perag *pag); +void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +void xfs_refcount_free_cow_extent(struct xfs_trans *tp, bool isrt, + xfs_fsblock_t fsb, xfs_extlen_t len); +int xfs_refcount_recover_cow_leftovers(struct xfs_group *xg); /* * While we're adjusting the refcounts records of an extent, we have @@ -120,6 +123,8 @@ extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag, const struct xfs_refcount_irec *irec); +xfs_failaddr_t xfs_rtrefcount_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_refcount_irec *irec); extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index d0df68dc3131..3cdf50563fec 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -25,6 +25,8 @@ #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_rmap_item.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" struct kmem_cache *xfs_rmap_intent_cache; @@ -264,11 +266,77 @@ xfs_rmap_check_irec( return NULL; } +static xfs_failaddr_t +xfs_rtrmap_check_meta_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (irec->rm_offset != 0) + return __this_address; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return __this_address; + + switch (irec->rm_owner) { + case XFS_RMAP_OWN_FS: + if (irec->rm_startblock != 0) + return __this_address; + if (irec->rm_blockcount != mp->m_sb.sb_rextsize) + return __this_address; + return NULL; + case XFS_RMAP_OWN_COW: + if (!xfs_has_rtreflink(mp)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, + irec->rm_blockcount)) + return __this_address; + return NULL; + default: + return __this_address; + } + + return NULL; +} + +static xfs_failaddr_t +xfs_rtrmap_check_inode_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = rtg_mount(rtg); + + if (!xfs_verify_ino(mp, irec->rm_owner)) + return __this_address; + if (!xfs_verify_rgbext(rtg, irec->rm_startblock, irec->rm_blockcount)) + return __this_address; + if (!xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount)) + return __this_address; + return NULL; +} + +xfs_failaddr_t +xfs_rtrmap_check_irec( + struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec) +{ + if (irec->rm_blockcount == 0) + return __this_address; + if (irec->rm_flags & (XFS_RMAP_BMBT_BLOCK | XFS_RMAP_ATTR_FORK)) + return __this_address; + if (XFS_RMAP_NON_INODE_OWNER(irec->rm_owner)) + return xfs_rtrmap_check_meta_irec(rtg, irec); + return xfs_rtrmap_check_inode_irec(rtg, irec); +} + static inline xfs_failaddr_t xfs_rmap_check_btrec( struct xfs_btree_cur *cur, const struct xfs_rmap_irec *irec) { + if (xfs_btree_is_rtrmap(cur->bc_ops) || + xfs_btree_is_mem_rtrmap(cur->bc_ops)) + return xfs_rtrmap_check_irec(to_rtg(cur->bc_group), irec); return xfs_rmap_check_irec(to_perag(cur->bc_group), irec); } @@ -283,6 +351,10 @@ xfs_rmap_complain_bad_rec( if (xfs_btree_is_mem_rmap(cur->bc_ops)) xfs_warn(mp, "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa); + else if (xfs_btree_is_rtrmap(cur->bc_ops)) + xfs_warn(mp, + "RT Reverse Mapping BTree record corruption in rtgroup %u detected at %pS!", + cur->bc_group->xg_gno, fa); else xfs_warn(mp, "Reverse Mapping BTree record corruption in AG %d detected at %pS!", @@ -525,7 +597,7 @@ xfs_rmap_free_check_owner( struct xfs_btree_cur *cur, uint64_t ltoff, struct xfs_rmap_irec *rec, - xfs_filblks_t len, + xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags) @@ -2556,6 +2628,47 @@ __xfs_rmap_finish_intent( } } +static int +xfs_rmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_perag *pag = to_perag(ri->ri_group); + struct xfs_buf *agbp = NULL; + int error; + + /* + * Refresh the freelist before we start changing the rmapbt, because a + * shape change could cause us to allocate blocks. + */ + error = xfs_free_extent_fix_freelist(tp, pag, &agbp); + if (error) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return error; + } + if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + return -EFSCORRUPTED; + } + *pcur = xfs_rmapbt_init_cursor(tp->t_mountp, tp, agbp, pag); + return 0; +} + +static int +xfs_rtrmap_finish_init_cursor( + struct xfs_trans *tp, + struct xfs_rmap_intent *ri, + struct xfs_btree_cur **pcur) +{ + struct xfs_rtgroup *rtg = to_rtg(ri->ri_group); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); + *pcur = xfs_rtrmapbt_init_cursor(tp, rtg); + return 0; +} + /* * Process one of the deferred rmap operations. We pass back the * btree cursor to maintain our lock on the rmapbt between calls. @@ -2571,8 +2684,6 @@ xfs_rmap_finish_one( { struct xfs_owner_info oinfo; struct xfs_mount *mp = tp->t_mountp; - struct xfs_btree_cur *rcur = *pcur; - struct xfs_buf *agbp = NULL; xfs_agblock_t bno; bool unwritten; int error = 0; @@ -2586,38 +2697,26 @@ xfs_rmap_finish_one( * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ - if (rcur != NULL && rcur->bc_group != ri->ri_group) { - xfs_btree_del_cursor(rcur, 0); - rcur = NULL; + if (*pcur != NULL && (*pcur)->bc_group != ri->ri_group) { + xfs_btree_del_cursor(*pcur, 0); *pcur = NULL; } - if (rcur == NULL) { - struct xfs_perag *pag = to_perag(ri->ri_group); - - /* - * Refresh the freelist before we start changing the - * rmapbt, because a shape change could cause us to - * allocate blocks. - */ - error = xfs_free_extent_fix_freelist(tp, pag, &agbp); - if (error) { - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); + if (*pcur == NULL) { + if (ri->ri_group->xg_type == XG_TYPE_RTG) + error = xfs_rtrmap_finish_init_cursor(tp, ri, pcur); + else + error = xfs_rmap_finish_init_cursor(tp, ri, pcur); + if (error) return error; - } - if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL); - return -EFSCORRUPTED; - } - - *pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); } xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork, ri->ri_bmap.br_startoff); unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN; - bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock); - error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno, + bno = xfs_fsb_to_gbno(mp, ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); + error = __xfs_rmap_finish_intent(*pcur, ri->ri_type, bno, ri->ri_bmap.br_blockcount, &oinfo, unwritten); if (error) return error; @@ -2647,6 +2746,7 @@ __xfs_rmap_add( struct xfs_trans *tp, enum xfs_rmap_intent_type type, uint64_t owner, + bool isrt, int whichfork, struct xfs_bmbt_irec *bmap) { @@ -2658,6 +2758,7 @@ __xfs_rmap_add( ri->ri_owner = owner; ri->ri_whichfork = whichfork; ri->ri_bmap = *bmap; + ri->ri_realtime = isrt; xfs_rmap_defer_add(tp, ri); } @@ -2671,6 +2772,7 @@ xfs_rmap_map_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_MAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2678,7 +2780,7 @@ xfs_rmap_map_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_MAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Unmap an extent out of a file. */ @@ -2690,6 +2792,7 @@ xfs_rmap_unmap_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork)) return; @@ -2697,7 +2800,7 @@ xfs_rmap_unmap_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_UNMAP_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* @@ -2715,6 +2818,7 @@ xfs_rmap_convert_extent( struct xfs_bmbt_irec *PREV) { enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT; + bool isrt = xfs_ifork_is_realtime(ip, whichfork); if (!xfs_rmap_update_is_needed(mp, whichfork)) return; @@ -2722,15 +2826,15 @@ xfs_rmap_convert_extent( if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip)) type = XFS_RMAP_CONVERT_SHARED; - __xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV); + __xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV); } /* Schedule the creation of an rmap for non-file data. */ void xfs_rmap_alloc_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2739,20 +2843,20 @@ xfs_rmap_alloc_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, isrt, XFS_DATA_FORK, &bmap); } /* Schedule the deletion of an rmap for non-file data. */ void xfs_rmap_free_extent( struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, + bool isrt, + xfs_fsblock_t fsbno, xfs_extlen_t len, uint64_t owner) { @@ -2761,12 +2865,12 @@ xfs_rmap_free_extent( if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK)) return; - bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno); + bmap.br_startblock = fsbno; bmap.br_blockcount = len; bmap.br_startoff = 0; bmap.br_state = XFS_EXT_NORM; - __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap); + __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, isrt, XFS_DATA_FORK, &bmap); } /* Compare rmap records. Returns -1 if a < b, 1 if a > b, and 0 if equal. */ diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 96b4321d8310..5f39f6e53cd1 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -7,6 +7,7 @@ #define __XFS_RMAP_H__ struct xfs_perag; +struct xfs_rtgroup; static inline void xfs_rmap_ino_bmbt_owner( @@ -174,6 +175,7 @@ struct xfs_rmap_intent { uint64_t ri_owner; struct xfs_bmbt_irec ri_bmap; struct xfs_group *ri_group; + bool ri_realtime; }; /* functions for updating the rmapbt based on bmbt map/unmap operations */ @@ -184,10 +186,10 @@ void xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip, void xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *imap); -void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); -void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner); +void xfs_rmap_alloc_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); +void xfs_rmap_free_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno, + xfs_extlen_t len, uint64_t owner); int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri, struct xfs_btree_cur **pcur); @@ -206,6 +208,8 @@ xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec); xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag, const struct xfs_rmap_irec *irec); +xfs_failaddr_t xfs_rtrmap_check_irec(struct xfs_rtgroup *rtg, + const struct xfs_rmap_irec *irec); int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome); diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 4ddfb7e395b3..770adf60dd73 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1055,7 +1055,7 @@ xfs_rtfree_extent( xfs_rtxlen_t len) /* length of extent freed */ { struct xfs_mount *mp = tp->t_mountp; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xfs_rtalloc_args args = { .mp = mp, .tp = tp, diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h index 16563a44bd13..22e5d9cd95f4 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.h +++ b/fs/xfs/libxfs/xfs_rtbitmap.h @@ -135,6 +135,15 @@ xfs_rtb_to_rtx( return div_u64(rtbno, mp->m_sb.sb_rextsize); } +/* Return the offset of a rtgroup block number within an rt extent. */ +static inline xfs_extlen_t +xfs_rgbno_to_rtxoff( + struct xfs_mount *mp, + xfs_rgblock_t rgbno) +{ + return rgbno % mp->m_sb.sb_rextsize; +} + /* Return the offset of an rt block number within an rt extent. */ static inline xfs_extlen_t xfs_rtb_to_rtxoff( diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index e74bb059f24f..d84d32f1b48f 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -33,6 +33,8 @@ #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_metadir.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* Find the first usable fsblock in this rtgroup. */ static inline uint32_t @@ -197,11 +199,17 @@ xfs_rtgroup_lock( * Lock both realtime free space metadata inodes for a freespace * update. */ - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL); - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL); + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL); } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { - xfs_ilock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED); + xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_ilock(rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Unlock metadata inodes associated with this rt group. */ @@ -214,11 +222,17 @@ xfs_rtgroup_unlock( ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || !(rtglock_flags & XFS_RTGLOCK_BITMAP)); + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_iunlock(rtg_refcount(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL); + if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_SUMMARY], XFS_ILOCK_EXCL); - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_EXCL); + xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL); + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { - xfs_iunlock(rtg->rtg_inodes[XFS_RTGI_BITMAP], XFS_ILOCK_SHARED); + xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); } } @@ -236,11 +250,15 @@ xfs_rtgroup_trans_join( ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)); if (rtglock_flags & XFS_RTGLOCK_BITMAP) { - xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_BITMAP], - XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, rtg->rtg_inodes[XFS_RTGI_SUMMARY], - XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL); } + + if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) + xfs_trans_ijoin(tp, rtg_rmap(rtg), XFS_ILOCK_EXCL); + + if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) + xfs_trans_ijoin(tp, rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Retrieve rt group geometry. */ @@ -284,7 +302,8 @@ xfs_rtginode_ilock_print_fn( const struct xfs_inode *ip = container_of(m, struct xfs_inode, i_lock.dep_map); - printk(KERN_CONT " rgno=%u", ip->i_projid); + printk(KERN_CONT " rgno=%u metatype=%s", ip->i_projid, + xfs_metafile_type_str(ip->i_metatype)); } /* @@ -316,8 +335,10 @@ struct xfs_rtginode_ops { unsigned int sick; /* rtgroup sickness flag */ + unsigned int fmt_mask; /* all valid data fork formats */ + /* Does the fs have this feature? */ - bool (*enabled)(struct xfs_mount *mp); + bool (*enabled)(const struct xfs_mount *mp); /* Create this rtgroup metadata inode and initialize it. */ int (*create)(struct xfs_rtgroup *rtg, @@ -331,14 +352,40 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { .name = "bitmap", .metafile_type = XFS_METAFILE_RTBITMAP, .sick = XFS_SICK_RG_BITMAP, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), .create = xfs_rtbitmap_create, }, [XFS_RTGI_SUMMARY] = { .name = "summary", .metafile_type = XFS_METAFILE_RTSUMMARY, .sick = XFS_SICK_RG_SUMMARY, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), .create = xfs_rtsummary_create, }, + [XFS_RTGI_RMAP] = { + .name = "rmap", + .metafile_type = XFS_METAFILE_RTRMAP, + .sick = XFS_SICK_RG_RMAPBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use the + * rtrmapbt predicate here. + */ + .enabled = xfs_has_rmapbt, + .create = xfs_rtrmapbt_create, + }, + [XFS_RTGI_REFCOUNT] = { + .name = "refcount", + .metafile_type = XFS_METAFILE_RTREFCOUNT, + .sick = XFS_SICK_RG_REFCNTBT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* same comment about growfs and rmap inodes applies here */ + .enabled = xfs_has_reflink, + .create = xfs_rtrefcountbt_create, + }, }; /* Return the shortname of this rtgroup inode. */ @@ -435,8 +482,7 @@ xfs_rtginode_load( return error; } - if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && - ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) { + if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) { xfs_irele(ip); xfs_rtginode_mark_sick(rtg, type); return -EFSCORRUPTED; @@ -496,7 +542,7 @@ xfs_rtginode_create( error = xfs_metadir_create(&upd, S_IFREG); if (error) - return error; + goto out_cancel; xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type); diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 7e7e491ff06f..03f39d4e43fc 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -14,6 +14,8 @@ struct xfs_trans; enum xfs_rtg_inodes { XFS_RTGI_BITMAP, /* allocation bitmap */ XFS_RTGI_SUMMARY, /* allocation summary */ + XFS_RTGI_RMAP, /* rmap btree inode */ + XFS_RTGI_REFCOUNT, /* refcount btree inode */ XFS_RTGI_MAX, }; @@ -64,6 +66,26 @@ static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg) return rtg->rtg_group.xg_gno; } +static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_BITMAP]; +} + +static inline struct xfs_inode *rtg_summary(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_SUMMARY]; +} + +static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_RMAP]; +} + +static inline struct xfs_inode *rtg_refcount(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_REFCOUNT]; +} + /* Passive rtgroup references */ static inline struct xfs_rtgroup * xfs_rtgroup_get( @@ -122,6 +144,32 @@ xfs_rtgroup_next( return xfs_rtgroup_next_range(mp, rtg, 0, mp->m_sb.sb_rgcount - 1); } +static inline bool +xfs_verify_rgbno( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbno(rtg_group(rtg), rgbno); +} + +/* + * Check that [@rgbno,@len] is a valid extent range in @rtg. + * + * Must only be used for RTG-enabled file systems. + */ +static inline bool +xfs_verify_rgbext( + struct xfs_rtgroup *rtg, + xfs_rgblock_t rgbno, + xfs_extlen_t len) +{ + ASSERT(xfs_has_rtgroups(rtg_mount(rtg))); + + return xfs_verify_gbext(rtg_group(rtg), rgbno, len); +} + static inline xfs_rtblock_t xfs_rgbno_to_rtb( struct xfs_rtgroup *rtg, @@ -223,9 +271,15 @@ int xfs_update_last_rtgroup_size(struct xfs_mount *mp, #define XFS_RTGLOCK_BITMAP (1U << 0) /* Lock the rt bitmap inode in shared mode */ #define XFS_RTGLOCK_BITMAP_SHARED (1U << 1) +/* Lock the rt rmap inode in exclusive mode */ +#define XFS_RTGLOCK_RMAP (1U << 2) +/* Lock the rt refcount inode in exclusive mode */ +#define XFS_RTGLOCK_REFCOUNT (1U << 3) #define XFS_RTGLOCK_ALL_FLAGS (XFS_RTGLOCK_BITMAP | \ - XFS_RTGLOCK_BITMAP_SHARED) + XFS_RTGLOCK_BITMAP_SHARED | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) void xfs_rtgroup_lock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); void xfs_rtgroup_unlock(struct xfs_rtgroup *rtg, unsigned int rtglock_flags); @@ -248,6 +302,8 @@ int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, bool init); void xfs_rtginode_irele(struct xfs_inode **ipp); +void xfs_rtginode_irele(struct xfs_inode **ipp); + static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno, enum xfs_rtg_inodes type) { @@ -272,7 +328,7 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, } # define xfs_rtgroup_extents(mp, rgno) (0) -# define xfs_update_last_rtgroup_size(mp, rgno) (-EOPNOTSUPP) +# define xfs_update_last_rtgroup_size(mp, rgno) (0) # define xfs_rtgroup_lock(rtg, gf) ((void)0) # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c new file mode 100644 index 000000000000..3db5e7a4a945 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_refcount.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "xfs_metafile.h" +#include "xfs_health.h" + +static struct kmem_cache *xfs_rtrefcountbt_cur_cache; + +/* + * Realtime Reference Count btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_refcount_btree.c for more information. + * + * This tree is basically the same as the regular refcount btree except that + * it's rooted in an inode. + */ + +static struct xfs_btree_cur * +xfs_rtrefcountbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrefcountbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrefcountbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrefc_mnr[level != 0]; +} + +STATIC int +xfs_rtrefcountbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrefcountbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrefc_mxr[level != 0]; +} + +/* + * Calculate number of records in a realtime refcount btree inode root. + */ +unsigned int +xfs_rtrefcountbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrefcount_root); + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (2 * sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrefcountbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork so that + * we can resize the in-memory buffer to match it. After a resize to the + * maximum size this function returns the same value as + * xfs_rtrefcountbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrefcountbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrefc_mxr[level != 0]; + return xfs_rtrefcountbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +STATIC void +xfs_rtrefcountbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->refc.rc_startblock = rec->refc.rc_startblock; +} + +STATIC void +xfs_rtrefcountbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + __u32 x; + + x = be32_to_cpu(rec->refc.rc_startblock); + x += be32_to_cpu(rec->refc.rc_blockcount) - 1; + key->refc.rc_startblock = cpu_to_be32(x); +} + +STATIC void +xfs_rtrefcountbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec->refc.rc_startblock = cpu_to_be32(start); + rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount); + rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount); +} + +STATIC void +xfs_rtrefcountbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +STATIC int64_t +xfs_rtrefcountbt_key_diff( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + const struct xfs_refcount_key *kp = &key->refc; + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + return (int64_t)be32_to_cpu(kp->rc_startblock) - start; +} + +STATIC int64_t +xfs_rtrefcountbt_diff_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return (int64_t)be32_to_cpu(k1->refc.rc_startblock) - + be32_to_cpu(k2->refc.rc_startblock); +} + +static xfs_failaddr_t +xfs_rtrefcountbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_reflink(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrefc_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrefc_mxr[level != 0]); +} + +static void +xfs_rtrefcountbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrefcountbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrefcountbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrefcountbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops = { + .name = "xfs_rtrefcountbt", + .magic = { 0, cpu_to_be32(XFS_RTREFC_CRC_MAGIC) }, + .verify_read = xfs_rtrefcountbt_read_verify, + .verify_write = xfs_rtrefcountbt_write_verify, + .verify_struct = xfs_rtrefcountbt_verify, +}; + +STATIC int +xfs_rtrefcountbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + return be32_to_cpu(k1->refc.rc_startblock) < + be32_to_cpu(k2->refc.rc_startblock); +} + +STATIC int +xfs_rtrefcountbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + return be32_to_cpu(r1->refc.rc_startblock) + + be32_to_cpu(r1->refc.rc_blockcount) <= + be32_to_cpu(r2->refc.rc_startblock); +} + +STATIC enum xbtree_key_contig +xfs_rtrefcountbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->refc.rc_startblock); + + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), + be32_to_cpu(key2->refc.rc_startblock)); +} + +static inline void +xfs_rtrefcountbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrefcount_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrefcountbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrefcount_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrefcountbt_maxrecs(mp, old_size, level); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, broot, old_size, + new_size, old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, ifp->if_broot, old_size, + new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrefcount_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrefcountbt_ops = { + .name = "rtrefcount", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_refcount_rec), + .key_len = sizeof(struct xfs_refcount_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_REFC_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrefcbt_2), + .sick_mask = XFS_SICK_RG_REFCNTBT, + + .dup_cursor = xfs_rtrefcountbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrefcountbt_get_minrecs, + .get_maxrecs = xfs_rtrefcountbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrefcountbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrefcountbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrefcountbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrefcountbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrefcountbt_init_ptr_from_cur, + .key_diff = xfs_rtrefcountbt_key_diff, + .buf_ops = &xfs_rtrefcountbt_buf_ops, + .diff_two_keys = xfs_rtrefcountbt_diff_two_keys, + .keys_inorder = xfs_rtrefcountbt_keys_inorder, + .recs_inorder = xfs_rtrefcountbt_recs_inorder, + .keys_contiguous = xfs_rtrefcountbt_keys_contiguous, + .broot_realloc = xfs_rtrefcountbt_broot_realloc, +}; + +/* Allocate a new rt refcount btree cursor. */ +struct xfs_btree_cur * +xfs_rtrefcountbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_refcount(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrefcountbt_ops, + mp->m_rtrefc_maxlevels, xfs_rtrefcountbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_refc.nr_ops = 0; + cur->bc_refc.shape_changes = 0; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + cur->bc_ino.whichfork = XFS_DATA_FORK; + return cur; +} + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrefcountbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a realtime refcount btree block. */ +static inline unsigned int +xfs_rtrefcountbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Calculate number of records in an refcount btree block. + */ +unsigned int +xfs_rtrefcountbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTREFCOUNT_BLOCK_LEN; + return xfs_rtrefcountbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime refcount btrees. */ +unsigned int +xfs_rtrefcountbt_maxlevels_ondisk(void) +{ + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; + + /* We need at most one record for every block in an rt group. */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); +} + +int __init +xfs_rtrefcountbt_init_cur_cache(void) +{ + xfs_rtrefcountbt_cur_cache = kmem_cache_create("xfs_rtrefcountbt_cur", + xfs_btree_cur_sizeof( + xfs_rtrefcountbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrefcountbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrefcountbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrefcountbt_cur_cache); + xfs_rtrefcountbt_cur_cache = NULL; +} + +/* Compute the maximum height of a realtime refcount btree. */ +void +xfs_rtrefcountbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtreflink(mp)) { + mp->m_rtrefc_maxlevels = 0; + return; + } + + /* + * The realtime refcountbt lives on the data device, which means that + * its maximum height is constrained by the size of the data device and + * the height required to store one refcount record for each rtextent + * in an rt group. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrefc_mnr, + mp->m_sb.sb_dblocks); + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrefc_mnr, + mp->m_sb.sb_rgextents); + + /* Add one level to handle the inode root level. */ + mp->m_rtrefc_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrefcount btree size for some records. */ +unsigned long long +xfs_rtrefcountbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrefc_mnr, len); +} + +/* + * Calculate the maximum refcount btree size. + */ +static unsigned long long +xfs_rtrefcountbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrefc_mxr[0] == 0) + return 0; + + return xfs_rtrefcountbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + * We need enough space to hold one record for every rt extent in the rtgroup. + */ +xfs_filblks_t +xfs_rtrefcountbt_calc_reserves( + struct xfs_mount *mp) +{ + if (!xfs_has_rtreflink(mp)) + return 0; + + return xfs_rtrefcountbt_max_size(mp, mp->m_sb.sb_rgextents); +} + +/* + * Convert on-disk form of btree root to in-memory form. + */ +STATIC void +xfs_rtrefcountbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrefcount_root *dblock, + int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + unsigned int rblocklen; + + rblocklen = xfs_rtrefcount_broot_space(mp, dblock); + + xfs_btree_init_block(mp, rblock, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + tkp = xfs_rtrefcount_key_addr(rblock, 1); + fpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + trp = xfs_rtrefcount_rec_addr(rblock, 1); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reference count btree root in from disk. */ +int +xfs_iformat_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrefcount inodes before adding a realtime + * volume to the filesystem, so we cannot use the rtrefcount predicate + * here. + */ + if (!xfs_has_reflink(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrefc_maxlevels || + xfs_rtrefcount_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrefcount_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrefcountbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* + * Convert in-memory form of btree root to on-disk form. + */ +void +xfs_rtrefcountbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + int rblocklen, + struct xfs_rtrefcount_root *dblock, + int dblocklen) +{ + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int maxrecs; + unsigned int numrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTREFC_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_key_addr(rblock, 1); + tkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + fpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_rec_addr(rblock, 1); + trp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reference count btree root out to disk. */ +void +xfs_iflush_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrefcount_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrefcountbt_to_disk(ip->i_mount, ifp->if_broot, + ifp->if_broot_bytes, dfp, + XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime refcount btree inode. + */ +int +xfs_rtrefcountbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, + xfs_rtrefcount_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + return 0; +} diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.h b/fs/xfs/libxfs/xfs_rtrefcount_btree.h new file mode 100644 index 000000000000..a99b7a8aec86 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_RTREFCOUNT_BTREE_H__ +#define __XFS_RTREFCOUNT_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; + +/* refcounts only exist on crc enabled filesystems */ +#define XFS_RTREFCOUNT_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrefcountbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrefcountbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrefcountbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrefcountbt_maxrecs(struct xfs_mount *mp, + unsigned int blocklen, bool leaf); +void xfs_rtrefcountbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrefcountbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrefcountbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_refcount_rec * +xfs_rtrefcount_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)block + XFS_RTREFCOUNT_BLOCK_LEN + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +unsigned int xfs_rtrefcountbt_maxlevels_ondisk(void); +int __init xfs_rtrefcountbt_init_cur_cache(void); +void xfs_rtrefcountbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrefcountbt_calc_reserves(struct xfs_mount *mp); +unsigned long long xfs_rtrefcountbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +/* Addresses of key, pointers, and records within an ondisk rtrefcount block. */ + +static inline struct xfs_refcount_rec * +xfs_rtrefcount_droot_rec_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_droot_key_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_droot_ptr_addr( + struct xfs_rtrefcount_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)(block + 1) + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrefcount_ptr_addr(bb, index, + xfs_rtrefcountbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrefcount_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTREFCOUNT_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrefcount_broot_space(struct xfs_mount *mp, struct xfs_rtrefcount_root *bb) +{ + return xfs_rtrefcount_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrefcount_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrefcount_root); + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrefcount_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrefcount_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrefcountbt_to_disk(struct xfs_mount *mp, + struct xfs_btree_block *rblock, int rblocklen, + struct xfs_rtrefcount_root *dblock, int dblocklen); +void xfs_iflush_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrefcountbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); + +#endif /* __XFS_RTREFCOUNT_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c new file mode 100644 index 000000000000..e4ec36943cb7 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -0,0 +1,1035 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_bit.h" +#include "xfs_sb.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_alloc.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_metafile.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_trace.h" +#include "xfs_cksum.h" +#include "xfs_error.h" +#include "xfs_extent_busy.h" +#include "xfs_rtgroup.h" +#include "xfs_bmap.h" +#include "xfs_health.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" + +static struct kmem_cache *xfs_rtrmapbt_cur_cache; + +/* + * Realtime Reverse Map btree. + * + * This is a btree used to track the owner(s) of a given extent in the realtime + * device. See the comments in xfs_rmap_btree.c for more information. + * + * This tree is basically the same as the regular rmap btree except that it + * is rooted in an inode and does not live in free space. + */ + +static struct xfs_btree_cur * +xfs_rtrmapbt_dup_cursor( + struct xfs_btree_cur *cur) +{ + return xfs_rtrmapbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); +} + +STATIC int +xfs_rtrmapbt_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0) / 2; + } + + return cur->bc_mp->m_rtrmap_mnr[level != 0]; +} + +STATIC int +xfs_rtrmapbt_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level == cur->bc_nlevels - 1) { + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + + return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, + level == 0); + } + + return cur->bc_mp->m_rtrmap_mxr[level != 0]; +} + +/* Calculate number of records in the ondisk realtime rmap btree inode root. */ +unsigned int +xfs_rtrmapbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrmap_root); + + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork + * so that we can resize the in-memory buffer to match it. After a + * resize to the maximum size this function returns the same value + * as xfs_rtrmapbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrmapbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrmap_mxr[level != 0]; + return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + +/* + * Convert the ondisk record's offset field into the ondisk key's offset field. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) +{ + return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); +} + +STATIC void +xfs_rtrmapbt_init_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + key->rmap.rm_startblock = rec->rmap.rm_startblock; + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); +} + +STATIC void +xfs_rtrmapbt_init_high_key_from_rec( + union xfs_btree_key *key, + const union xfs_btree_rec *rec) +{ + uint64_t off; + int adj; + + adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; + + key->rmap.rm_startblock = rec->rmap.rm_startblock; + be32_add_cpu(&key->rmap.rm_startblock, adj); + key->rmap.rm_owner = rec->rmap.rm_owner; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); + if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || + XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) + return; + off = be64_to_cpu(key->rmap.rm_offset); + off = (XFS_RMAP_OFF(off) + adj) | (off & ~XFS_RMAP_OFF_MASK); + key->rmap.rm_offset = cpu_to_be64(off); +} + +STATIC void +xfs_rtrmapbt_init_rec_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_rec *rec) +{ + rec->rmap.rm_startblock = cpu_to_be32(cur->bc_rec.r.rm_startblock); + rec->rmap.rm_blockcount = cpu_to_be32(cur->bc_rec.r.rm_blockcount); + rec->rmap.rm_owner = cpu_to_be64(cur->bc_rec.r.rm_owner); + rec->rmap.rm_offset = cpu_to_be64( + xfs_rmap_irec_offset_pack(&cur->bc_rec.r)); +} + +STATIC void +xfs_rtrmapbt_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ptr->l = 0; +} + +/* + * Mask the appropriate parts of the ondisk key field for a key comparison. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline uint64_t offset_keymask(uint64_t offset) +{ + return offset & ~XFS_RMAP_OFF_UNWRITTEN; +} + +STATIC int64_t +xfs_rtrmapbt_key_diff( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key) +{ + struct xfs_rmap_irec *rec = &cur->bc_rec.r; + const struct xfs_rmap_key *kp = &key->rmap; + __u64 x, y; + int64_t d; + + d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; + if (d) + return d; + + x = be64_to_cpu(kp->rm_owner); + y = rec->rm_owner; + if (x > y) + return 1; + else if (y > x) + return -1; + + x = offset_keymask(be64_to_cpu(kp->rm_offset)); + y = offset_keymask(xfs_rmap_irec_offset_pack(rec)); + if (x > y) + return 1; + else if (y > x) + return -1; + return 0; +} + +STATIC int64_t +xfs_rtrmapbt_diff_two_keys( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) +{ + const struct xfs_rmap_key *kp1 = &k1->rmap; + const struct xfs_rmap_key *kp2 = &k2->rmap; + int64_t d; + __u64 x, y; + + /* Doesn't make sense to mask off the physical space part */ + ASSERT(!mask || mask->rmap.rm_startblock); + + d = (int64_t)be32_to_cpu(kp1->rm_startblock) - + be32_to_cpu(kp2->rm_startblock); + if (d) + return d; + + if (!mask || mask->rmap.rm_owner) { + x = be64_to_cpu(kp1->rm_owner); + y = be64_to_cpu(kp2->rm_owner); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + if (!mask || mask->rmap.rm_offset) { + /* Doesn't make sense to allow offset but not owner */ + ASSERT(!mask || mask->rmap.rm_owner); + + x = offset_keymask(be64_to_cpu(kp1->rm_offset)); + y = offset_keymask(be64_to_cpu(kp2->rm_offset)); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + return 0; +} + +static xfs_failaddr_t +xfs_rtrmapbt_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + int level; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + if (!xfs_has_rmapbt(mp)) + return __this_address; + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + level = be16_to_cpu(block->bb_level); + if (level > mp->m_rtrmap_maxlevels) + return __this_address; + + return xfs_btree_fsblock_verify(bp, mp->m_rtrmap_mxr[level != 0]); +} + +static void +xfs_rtrmapbt_read_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + if (!xfs_btree_fsblock_verify_crc(bp)) + xfs_verifier_error(bp, -EFSBADCRC, __this_address); + else { + fa = xfs_rtrmapbt_verify(bp); + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + } + + if (bp->b_error) + trace_xfs_btree_corrupt(bp, _RET_IP_); +} + +static void +xfs_rtrmapbt_write_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa; + + fa = xfs_rtrmapbt_verify(bp); + if (fa) { + trace_xfs_btree_corrupt(bp, _RET_IP_); + xfs_verifier_error(bp, -EFSCORRUPTED, fa); + return; + } + xfs_btree_fsblock_calc_crc(bp); + +} + +const struct xfs_buf_ops xfs_rtrmapbt_buf_ops = { + .name = "xfs_rtrmapbt", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_read_verify, + .verify_write = xfs_rtrmapbt_write_verify, + .verify_struct = xfs_rtrmapbt_verify, +}; + +STATIC int +xfs_rtrmapbt_keys_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_key *k1, + const union xfs_btree_key *k2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(k1->rmap.rm_startblock); + y = be32_to_cpu(k2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(k1->rmap.rm_owner); + b = be64_to_cpu(k2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC int +xfs_rtrmapbt_recs_inorder( + struct xfs_btree_cur *cur, + const union xfs_btree_rec *r1, + const union xfs_btree_rec *r2) +{ + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; + + x = be32_to_cpu(r1->rmap.rm_startblock); + y = be32_to_cpu(r2->rmap.rm_startblock); + if (x < y) + return 1; + else if (x > y) + return 0; + a = be64_to_cpu(r1->rmap.rm_owner); + b = be64_to_cpu(r2->rmap.rm_owner); + if (a < b) + return 1; + else if (a > b) + return 0; + a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); + if (a <= b) + return 1; + return 0; +} + +STATIC enum xbtree_key_contig +xfs_rtrmapbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + ASSERT(!mask || mask->rmap.rm_startblock); + + /* + * We only support checking contiguity of the physical space component. + * If any callers ever need more specificity than that, they'll have to + * implement it here. + */ + ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); + + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), + be32_to_cpu(key2->rmap.rm_startblock)); +} + +static inline void +xfs_rtrmapbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrmapbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrmap_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size, + old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, + new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrmap_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + +const struct xfs_btree_ops xfs_rtrmapbt_ops = { + .name = "rtrmap", + .type = XFS_BTREE_TYPE_INODE, + .geom_flags = XFS_BTGEO_OVERLAPPING | + XFS_BTGEO_IROOT_RECORDS, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_2), + .sick_mask = XFS_SICK_RG_RMAPBT, + + .dup_cursor = xfs_rtrmapbt_dup_cursor, + .alloc_block = xfs_btree_alloc_metafile_block, + .free_block = xfs_btree_free_metafile_block, + .get_minrecs = xfs_rtrmapbt_get_minrecs, + .get_maxrecs = xfs_rtrmapbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrmapbt_get_dmaxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfs_rtrmapbt_init_ptr_from_cur, + .key_diff = xfs_rtrmapbt_key_diff, + .buf_ops = &xfs_rtrmapbt_buf_ops, + .diff_two_keys = xfs_rtrmapbt_diff_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, + .broot_realloc = xfs_rtrmapbt_broot_realloc, +}; + +/* Allocate a new rt rmap btree cursor. */ +struct xfs_btree_cur * +xfs_rtrmapbt_init_cursor( + struct xfs_trans *tp, + struct xfs_rtgroup *rtg) +{ + struct xfs_inode *ip = rtg_rmap(rtg); + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + + cur->bc_ino.ip = ip; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + cur->bc_ino.whichfork = XFS_DATA_FORK; + cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; + cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); + + return cur; +} + +#ifdef CONFIG_XFS_BTREE_IN_MEM +/* + * Validate an in-memory realtime rmap btree block. Callers are allowed to + * generate an in-memory btree even if the ondisk feature is not enabled. + */ +static xfs_failaddr_t +xfs_rtrmapbt_mem_verify( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_mount; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + xfs_failaddr_t fa; + unsigned int level; + unsigned int maxrecs; + + if (!xfs_verify_magic(bp, block->bb_magic)) + return __this_address; + + fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); + if (fa) + return fa; + + level = be16_to_cpu(block->bb_level); + if (xfs_has_rmapbt(mp)) { + if (level >= mp->m_rtrmap_maxlevels) + return __this_address; + } else { + if (level >= xfs_rtrmapbt_maxlevels_ondisk()) + return __this_address; + } + + maxrecs = xfs_rtrmapbt_maxrecs(mp, XFBNO_BLOCKSIZE, level == 0); + return xfs_btree_memblock_verify(bp, maxrecs); +} + +static void +xfs_rtrmapbt_mem_rw_verify( + struct xfs_buf *bp) +{ + xfs_failaddr_t fa = xfs_rtrmapbt_mem_verify(bp); + + if (fa) + xfs_verifier_error(bp, -EFSCORRUPTED, fa); +} + +/* skip crc checks on in-memory btrees to save time */ +static const struct xfs_buf_ops xfs_rtrmapbt_mem_buf_ops = { + .name = "xfs_rtrmapbt_mem", + .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, + .verify_read = xfs_rtrmapbt_mem_rw_verify, + .verify_write = xfs_rtrmapbt_mem_rw_verify, + .verify_struct = xfs_rtrmapbt_mem_verify, +}; + +const struct xfs_btree_ops xfs_rtrmapbt_mem_ops = { + .type = XFS_BTREE_TYPE_MEM, + .geom_flags = XFS_BTGEO_OVERLAPPING, + + .rec_len = sizeof(struct xfs_rmap_rec), + /* Overlapping btree; 2 keys per pointer. */ + .key_len = 2 * sizeof(struct xfs_rmap_key), + .ptr_len = XFS_BTREE_LONG_PTR_LEN, + + .lru_refs = XFS_RMAP_BTREE_REF, + .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_mem_2), + + .dup_cursor = xfbtree_dup_cursor, + .set_root = xfbtree_set_root, + .alloc_block = xfbtree_alloc_block, + .free_block = xfbtree_free_block, + .get_minrecs = xfbtree_get_minrecs, + .get_maxrecs = xfbtree_get_maxrecs, + .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, + .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, + .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, + .init_ptr_from_cur = xfbtree_init_ptr_from_cur, + .key_diff = xfs_rtrmapbt_key_diff, + .buf_ops = &xfs_rtrmapbt_mem_buf_ops, + .diff_two_keys = xfs_rtrmapbt_diff_two_keys, + .keys_inorder = xfs_rtrmapbt_keys_inorder, + .recs_inorder = xfs_rtrmapbt_recs_inorder, + .keys_contiguous = xfs_rtrmapbt_keys_contiguous, +}; + +/* Create a cursor for an in-memory btree. */ +struct xfs_btree_cur * +xfs_rtrmapbt_mem_cursor( + struct xfs_rtgroup *rtg, + struct xfs_trans *tp, + struct xfbtree *xfbt) +{ + struct xfs_mount *mp = rtg_mount(rtg); + struct xfs_btree_cur *cur; + + cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, + mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + cur->bc_mem.xfbtree = xfbt; + cur->bc_nlevels = xfbt->nlevels; + cur->bc_group = xfs_group_hold(rtg_group(rtg)); + return cur; +} + +/* Create an in-memory realtime rmap btree. */ +int +xfs_rtrmapbt_mem_init( + struct xfs_mount *mp, + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + xfs_rgnumber_t rgno) +{ + xfbt->owner = rgno; + return xfbtree_init(mp, xfbt, btp, &xfs_rtrmapbt_mem_ops); +} +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + +/* + * Install a new rt reverse mapping btree root. Caller is responsible for + * invalidating and freeing the old btree blocks. + */ +void +xfs_rtrmapbt_commit_staged_btree( + struct xfs_btree_cur *cur, + struct xfs_trans *tp) +{ + struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; + struct xfs_ifork *ifp; + int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; + + ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); + + /* + * Free any resources hanging off the real fork, then shallow-copy the + * staging fork's contents into the real fork to transfer everything + * we just built. + */ + ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); + xfs_idestroy_fork(ifp); + memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); + + cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; + xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); + xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); +} + +/* Calculate number of records in a rt reverse mapping btree block. */ +static inline unsigned int +xfs_rtrmapbt_block_maxrecs( + unsigned int blocklen, + bool leaf) +{ + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / + (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Calculate number of records in an rt reverse mapping btree block. + */ +unsigned int +xfs_rtrmapbt_maxrecs( + struct xfs_mount *mp, + unsigned int blocklen, + bool leaf) +{ + blocklen -= XFS_RTRMAP_BLOCK_LEN; + return xfs_rtrmapbt_block_maxrecs(blocklen, leaf); +} + +/* Compute the max possible height for realtime reverse mapping btrees. */ +unsigned int +xfs_rtrmapbt_maxlevels_ondisk(void) +{ + unsigned long long max_dblocks; + unsigned int minrecs[2]; + unsigned int blocklen; + + blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; + + minrecs[0] = xfs_rtrmapbt_block_maxrecs(blocklen, true) / 2; + minrecs[1] = xfs_rtrmapbt_block_maxrecs(blocklen, false) / 2; + + /* + * Compute the asymptotic maxlevels for an rtrmapbt on any rtreflink fs. + * + * On a reflink filesystem, each block in an rtgroup can have up to + * 2^32 (per the refcount record format) owners, which means that + * theoretically we could face up to 2^64 rmap records. However, we're + * likely to run out of blocks in the data device long before that + * happens, which means that we must compute the max height based on + * what the btree will look like if it consumes almost all the blocks + * in the data device due to maximal sharing factor. + */ + max_dblocks = -1U; /* max ag count */ + max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; + return xfs_btree_space_to_height(minrecs, max_dblocks); +} + +int __init +xfs_rtrmapbt_init_cur_cache(void) +{ + xfs_rtrmapbt_cur_cache = kmem_cache_create("xfs_rtrmapbt_cur", + xfs_btree_cur_sizeof(xfs_rtrmapbt_maxlevels_ondisk()), + 0, 0, NULL); + + if (!xfs_rtrmapbt_cur_cache) + return -ENOMEM; + return 0; +} + +void +xfs_rtrmapbt_destroy_cur_cache(void) +{ + kmem_cache_destroy(xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_cur_cache = NULL; +} + +/* Compute the maximum height of an rt reverse mapping btree. */ +void +xfs_rtrmapbt_compute_maxlevels( + struct xfs_mount *mp) +{ + unsigned int d_maxlevels, r_maxlevels; + + if (!xfs_has_rtrmapbt(mp)) { + mp->m_rtrmap_maxlevels = 0; + return; + } + + /* + * The realtime rmapbt lives on the data device, which means that its + * maximum height is constrained by the size of the data device and + * the height required to store one rmap record for each block in an + * rt group. + * + * On a reflink filesystem, each rt block can have up to 2^32 (per the + * refcount record format) owners, which means that theoretically we + * could face up to 2^64 rmap records. This makes the computation of + * maxlevels based on record count meaningless, so we only consider the + * size of the data device. + */ + d_maxlevels = xfs_btree_space_to_height(mp->m_rtrmap_mnr, + mp->m_sb.sb_dblocks); + if (xfs_has_rtreflink(mp)) { + mp->m_rtrmap_maxlevels = d_maxlevels + 1; + return; + } + + r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrmap_mnr, + mp->m_groups[XG_TYPE_RTG].blocks); + + /* Add one level to handle the inode root level. */ + mp->m_rtrmap_maxlevels = min(d_maxlevels, r_maxlevels) + 1; +} + +/* Calculate the rtrmap btree size for some records. */ +unsigned long long +xfs_rtrmapbt_calc_size( + struct xfs_mount *mp, + unsigned long long len) +{ + return xfs_btree_calc_size(mp->m_rtrmap_mnr, len); +} + +/* + * Calculate the maximum rmap btree size. + */ +static unsigned long long +xfs_rtrmapbt_max_size( + struct xfs_mount *mp, + xfs_rtblock_t rtblocks) +{ + /* Bail out if we're uninitialized, which can happen in mkfs. */ + if (mp->m_rtrmap_mxr[0] == 0) + return 0; + + return xfs_rtrmapbt_calc_size(mp, rtblocks); +} + +/* + * Figure out how many blocks to reserve and how many are used by this btree. + */ +xfs_filblks_t +xfs_rtrmapbt_calc_reserves( + struct xfs_mount *mp) +{ + uint32_t blocks = mp->m_groups[XG_TYPE_RTG].blocks; + + if (!xfs_has_rtrmapbt(mp)) + return 0; + + /* Reserve 1% of the rtgroup or enough for 1 block per record. */ + return max_t(xfs_filblks_t, blocks / 100, + xfs_rtrmapbt_max_size(mp, blocks)); +} + +/* Convert on-disk form of btree root to in-memory form. */ +STATIC void +xfs_rtrmapbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int rblocklen = xfs_rtrmap_broot_space(mp, dblock); + unsigned int numrecs; + unsigned int maxrecs; + + xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + numrecs = be16_to_cpu(dblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_droot_key_addr(dblock, 1); + tkp = xfs_rtrmap_key_addr(rblock, 1); + fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_droot_rec_addr(dblock, 1); + trp = xfs_rtrmap_rec_addr(rblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reverse mapping btree root in from disk. */ +int +xfs_iformat_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrmap inodes before adding a realtime volume + * to the filesystem, so we cannot use the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(ip->i_mount)) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrmap_maxlevels || + xfs_rtrmap_droot_space_calc(level, numrecs) > dsize) { + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); + return -EFSCORRUPTED; + } + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrmap_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* Convert in-memory form of btree root to on-disk form. */ +void +xfs_rtrmapbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + unsigned int rblocklen, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen) +{ + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + numrecs = be16_to_cpu(rblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_key_addr(rblock, 1); + tkp = xfs_rtrmap_droot_key_addr(dblock, 1); + fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_rec_addr(rblock, 1); + trp = xfs_rtrmap_droot_rec_addr(dblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reverse mapping btree root out to disk. */ +void +xfs_iflush_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes, + dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} + +/* + * Create a realtime rmap btree inode. + */ +int +xfs_rtrmapbt_create( + struct xfs_rtgroup *rtg, + struct xfs_inode *ip, + struct xfs_trans *tp, + bool init) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_mount *mp = ip->i_mount; + struct xfs_btree_block *broot; + + ifp->if_format = XFS_DINODE_FMT_META_BTREE; + ASSERT(ifp->if_broot_bytes == 0); + ASSERT(ifp->if_bytes == 0); + + /* Initialize the empty incore btree root. */ + broot = xfs_broot_realloc(ifp, xfs_rtrmap_broot_space_calc(mp, 0, 0)); + if (broot) + xfs_btree_init_block(mp, broot, &xfs_rtrmapbt_ops, 0, 0, + ip->i_ino); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); + + return 0; +} + +/* + * Initialize an rmap for a realtime superblock using the potentially updated + * rt geometry in the provided @mp. + */ +int +xfs_rtrmapbt_init_rtsb( + struct xfs_mount *mp, + struct xfs_rtgroup *rtg, + struct xfs_trans *tp) +{ + struct xfs_rmap_irec rmap = { + .rm_blockcount = mp->m_sb.sb_rextsize, + .rm_owner = XFS_RMAP_OWN_FS, + }; + struct xfs_btree_cur *cur; + int error; + + ASSERT(xfs_has_rtsb(mp)); + ASSERT(rtg_rgno(rtg) == 0); + + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + error = xfs_rmap_map_raw(cur, &rmap); + xfs_btree_del_cursor(cur, error); + return error; +} diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h new file mode 100644 index 000000000000..9d0915089891 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_RTRMAP_BTREE_H__ +#define __XFS_RTRMAP_BTREE_H__ + +struct xfs_buf; +struct xfs_btree_cur; +struct xfs_mount; +struct xbtree_ifakeroot; +struct xfs_rtgroup; +struct xfbtree; + +/* rmaps only exist on crc enabled filesystems */ +#define XFS_RTRMAP_BLOCK_LEN XFS_BTREE_LBLOCK_CRC_LEN + +struct xfs_btree_cur *xfs_rtrmapbt_init_cursor(struct xfs_trans *tp, + struct xfs_rtgroup *rtg); +struct xfs_btree_cur *xfs_rtrmapbt_stage_cursor(struct xfs_mount *mp, + struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xbtree_ifakeroot *ifake); +void xfs_rtrmapbt_commit_staged_btree(struct xfs_btree_cur *cur, + struct xfs_trans *tp); +unsigned int xfs_rtrmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, + bool leaf); +void xfs_rtrmapbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrmapbt_droot_maxrecs(unsigned int blocklen, bool leaf); + +/* + * Addresses of records, keys, and pointers within an incore rtrmapbt block. + * + * (note that some of these may appear unused, but they are used in userspace) + */ +static inline struct xfs_rmap_rec * +xfs_rtrmap_rec_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_high_key_addr( + struct xfs_btree_block *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + sizeof(struct xfs_rmap_key) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_ptr_addr( + struct xfs_btree_block *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)block + XFS_RTRMAP_BLOCK_LEN + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +unsigned int xfs_rtrmapbt_maxlevels_ondisk(void); + +int __init xfs_rtrmapbt_init_cur_cache(void); +void xfs_rtrmapbt_destroy_cur_cache(void); + +xfs_filblks_t xfs_rtrmapbt_calc_reserves(struct xfs_mount *mp); + +/* Addresses of key, pointers, and records within an ondisk rtrmapbt block. */ + +static inline struct xfs_rmap_rec * +xfs_rtrmap_droot_rec_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_droot_key_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)(block + 1) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_droot_ptr_addr( + struct xfs_rtrmap_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)(block + 1) + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrmap_ptr_addr(bb, index, + xfs_rtrmapbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrmap_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTRMAP_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrmap_broot_space(struct xfs_mount *mp, struct xfs_rtrmap_root *bb) +{ + return xfs_rtrmap_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrmap_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrmap_root); + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrmap_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrmap_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrmapbt_to_disk(struct xfs_mount *mp, struct xfs_btree_block *rblock, + unsigned int rblocklen, struct xfs_rtrmap_root *dblock, + unsigned int dblocklen); +void xfs_iflush_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); + +int xfs_rtrmapbt_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, + struct xfs_trans *tp, bool init); +int xfs_rtrmapbt_init_rtsb(struct xfs_mount *mp, struct xfs_rtgroup *rtg, + struct xfs_trans *tp); + +unsigned long long xfs_rtrmapbt_calc_size(struct xfs_mount *mp, + unsigned long long len); + +struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg, + struct xfs_trans *tp, struct xfbtree *xfbtree); +int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree, + struct xfs_buftarg *btp, xfs_rgnumber_t rgno); + +#endif /* __XFS_RTRMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a809513a290c..3dc5f5dba162 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -28,6 +28,8 @@ #include "xfs_rtbitmap.h" #include "xfs_exchrange.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -494,12 +496,13 @@ xfs_validate_sb_common( return -EINVAL; } - if (!sbp->sb_spino_align || - sbp->sb_spino_align > sbp->sb_inoalignmt || - (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0) { + if (sbp->sb_spino_align && + (sbp->sb_spino_align > sbp->sb_inoalignmt || + (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { xfs_warn(mp, - "Sparse inode alignment (%u) is invalid.", - sbp->sb_spino_align); +"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", + sbp->sb_spino_align, + sbp->sb_inoalignmt); return -EINVAL; } } else if (sbp->sb_spino_align) { @@ -1214,11 +1217,23 @@ xfs_sb_mount_common( mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2; mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2; + mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true); + mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false); + mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2; + mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2; + mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2; mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; + mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + true); + mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, + false); + mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2; + mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2; + mp->m_bsize = XFS_FSB_TO_BB(mp, 1); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index e7efdb9ceaf3..b1e0d9bc1f7d 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -42,6 +42,8 @@ extern const struct xfs_buf_ops xfs_rtbitmap_buf_ops; extern const struct xfs_buf_ops xfs_rtsummary_buf_ops; extern const struct xfs_buf_ops xfs_rtbuf_ops; extern const struct xfs_buf_ops xfs_rtsb_buf_ops; +extern const struct xfs_buf_ops xfs_rtrefcountbt_buf_ops; +extern const struct xfs_buf_ops xfs_rtrmapbt_buf_ops; extern const struct xfs_buf_ops xfs_sb_buf_ops; extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops; extern const struct xfs_buf_ops xfs_symlink_buf_ops; @@ -55,6 +57,9 @@ extern const struct xfs_btree_ops xfs_bmbt_ops; extern const struct xfs_btree_ops xfs_refcountbt_ops; extern const struct xfs_btree_ops xfs_rmapbt_ops; extern const struct xfs_btree_ops xfs_rmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_ops; +extern const struct xfs_btree_ops xfs_rtrmapbt_mem_ops; +extern const struct xfs_btree_ops xfs_rtrefcountbt_ops; static inline bool xfs_btree_is_bno(const struct xfs_btree_ops *ops) { @@ -96,10 +101,26 @@ static inline bool xfs_btree_is_mem_rmap(const struct xfs_btree_ops *ops) { return ops == &xfs_rmapbt_mem_ops; } + +static inline bool xfs_btree_is_mem_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_mem_ops; +} #else # define xfs_btree_is_mem_rmap(...) (false) +# define xfs_btree_is_mem_rtrmap(...) (false) #endif +static inline bool xfs_btree_is_rtrmap(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrmapbt_ops; +} + +static inline bool xfs_btree_is_rtrefcount(const struct xfs_btree_ops *ops) +{ + return ops == &xfs_rtrefcountbt_ops; +} + /* log size calculation functions */ int xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes); int xfs_log_calc_minimum_size(struct xfs_mount *); diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index f228127a88ff..fb47a76ead18 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -92,8 +92,10 @@ xfs_symlink_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; + /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) - return __this_address; + return NULL; + if (!xfs_verify_magic(bp, dsl->sl_magic)) return __this_address; if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid)) diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index bab402340b5d..13d00c7166e1 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -92,6 +92,14 @@ xfs_refcountbt_block_count( return num_ops * (2 * mp->m_refc_maxlevels - 1); } +static unsigned int +xfs_rtrefcountbt_block_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + return num_ops * (2 * mp->m_rtrefc_maxlevels - 1); +} + /* * Logging inodes is really tricksy. They are logged in memory format, * which means that what we write into the log doesn't directly translate into @@ -213,7 +221,9 @@ xfs_calc_inode_chunk_res( * Per-extent log reservation for the btree changes involved in freeing or * allocating a realtime extent. We have to be able to log as many rtbitmap * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime - * extents, as well as the realtime summary block. + * extents, as well as the realtime summary block (t1). Realtime rmap btree + * operations happen in a second transaction, so factor in a couple of rtrmapbt + * splits (t2). */ static unsigned int xfs_rtalloc_block_count( @@ -222,10 +232,16 @@ xfs_rtalloc_block_count( { unsigned int rtbmp_blocks; xfs_rtxlen_t rtxlen; + unsigned int t1, t2 = 0; rtxlen = xfs_extlen_to_rtxlen(mp, XFS_MAX_BMBT_EXTLEN); rtbmp_blocks = xfs_rtbitmap_blockcount_len(mp, rtxlen); - return (rtbmp_blocks + 1) * num_ops; + t1 = (rtbmp_blocks + 1) * num_ops; + + if (xfs_has_rmapbt(mp)) + t2 = num_ops * (2 * mp->m_rtrmap_maxlevels - 1); + + return max(t1, t2); } /* @@ -251,10 +267,13 @@ xfs_rtalloc_block_count( * Compute the log reservation required to handle the refcount update * transaction. Refcount updates are always done via deferred log items. * - * This is calculated as: + * This is calculated as the max of: * Data device refcount updates (t1): * the agfs of the ags containing the blocks: nr_ops * sector size * the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size + * Realtime refcount updates (t2); + * the rt refcount inode + * the rtrefcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size */ static unsigned int xfs_calc_refcountbt_reservation( @@ -262,12 +281,20 @@ xfs_calc_refcountbt_reservation( unsigned int nr_ops) { unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int t1, t2 = 0; if (!xfs_has_reflink(mp)) return 0; - return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + t1 = xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz); + + if (xfs_has_realtime(mp)) + t2 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(xfs_rtrefcountbt_block_count(mp, nr_ops), + blksz); + + return max(t1, t2); } /* diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index 1155ff2d37e2..d89b570aafcc 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -14,6 +14,19 @@ #define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp) \ (((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0])) +/* Worst case number of realtime rmaps that can be held in a block. */ +#define XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) \ + (((mp)->m_rtrmap_mxr[0]) - ((mp)->m_rtrmap_mnr[0])) + +/* Adding one realtime rmap could split every level to the top of the tree. */ +#define XFS_RTRMAPADD_SPACE_RES(mp) ((mp)->m_rtrmap_maxlevels) + +/* Blocks we might need to add "b" realtime rmaps to a tree. */ +#define XFS_NRTRMAPADD_SPACE_RES(mp, b) \ + ((((b) + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp) - 1) / \ + XFS_MAX_CONTIG_RTRMAPS_PER_BLOCK(mp)) * \ + XFS_RTRMAPADD_SPACE_RES(mp)) + /* Worst case number of rmaps that can be held in a block. */ #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) \ (((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0])) diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index bf33c2b1e43e..ca2401c1facd 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -202,6 +202,13 @@ enum xfs_ag_resv_type { * altering fdblocks. If you think you need this you're wrong. */ XFS_AG_RESV_IGNORE, + + /* + * This allocation activity is being done on behalf of a metadata file. + * These files maintain their own permanent space reservations and are + * required to adjust fdblocks using the xfs_metafile_resv_* helpers. + */ + XFS_AG_RESV_METAFILE, }; /* Results of scanning a btree keyspace to check occupancy. */ diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 61f80a6410c7..9f8c312dfd3c 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -60,6 +60,32 @@ xchk_superblock_xref( } /* + * Calculate the ondisk superblock size in bytes given the feature set of the + * mounted filesystem (aka the primary sb). This is subtlely different from + * the logic in xfs_repair, which computes the size of a secondary sb given the + * featureset listed in the secondary sb. + */ +STATIC size_t +xchk_superblock_ondisk_size( + struct xfs_mount *mp) +{ + if (xfs_has_metadir(mp)) + return offsetofend(struct xfs_dsb, sb_pad); + if (xfs_has_metauuid(mp)) + return offsetofend(struct xfs_dsb, sb_meta_uuid); + if (xfs_has_crc(mp)) + return offsetofend(struct xfs_dsb, sb_lsn); + if (xfs_sb_version_hasmorebits(&mp->m_sb)) + return offsetofend(struct xfs_dsb, sb_bad_features2); + if (xfs_has_logv2(mp)) + return offsetofend(struct xfs_dsb, sb_logsunit); + if (xfs_has_sector(mp)) + return offsetofend(struct xfs_dsb, sb_logsectsize); + /* only support dirv2 or more recent */ + return offsetofend(struct xfs_dsb, sb_dirblklog); +} + +/* * Scrub the filesystem superblock. * * Note: We do /not/ attempt to check AG 0's superblock. Mount is @@ -75,6 +101,7 @@ xchk_superblock( struct xfs_buf *bp; struct xfs_dsb *sb; struct xfs_perag *pag; + size_t sblen; xfs_agnumber_t agno; uint32_t v2_ok; __be32 features_mask; @@ -145,8 +172,11 @@ xchk_superblock( xchk_block_set_preen(sc, bp); if (xfs_has_metadir(sc->mp)) { - if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino)) - xchk_block_set_preen(sc, bp); + if (sb->sb_rbmino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + + if (sb->sb_rsumino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); } else { if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino)) xchk_block_set_preen(sc, bp); @@ -229,7 +259,13 @@ xchk_superblock( * sb_icount, sb_ifree, sb_fdblocks, sb_frexents */ - if (!xfs_has_metadir(mp)) { + if (xfs_has_metadir(mp)) { + if (sb->sb_uquotino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + + if (sb->sb_gquotino != cpu_to_be64(0)) + xchk_block_set_preen(sc, bp); + } else { if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino)) xchk_block_set_preen(sc, bp); @@ -281,15 +317,8 @@ xchk_superblock( if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok))) xchk_block_set_corrupt(sc, bp); - if (xfs_has_metadir(mp)) { - if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog) - xchk_block_set_corrupt(sc, bp); - if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad))) - xchk_block_set_preen(sc, bp); - } else { - if (sb->sb_features2 != sb->sb_bad_features2) - xchk_block_set_preen(sc, bp); - } + if (sb->sb_features2 != sb->sb_bad_features2) + xchk_block_set_preen(sc, bp); } /* Check sb_features2 flags that are set at mkfs time. */ @@ -351,7 +380,10 @@ xchk_superblock( if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align)) xchk_block_set_corrupt(sc, bp); - if (!xfs_has_metadir(mp)) { + if (xfs_has_metadir(mp)) { + if (sb->sb_pquotino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + } else { if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino)) xchk_block_set_preen(sc, bp); } @@ -366,16 +398,25 @@ xchk_superblock( } if (xfs_has_metadir(mp)) { + if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino)) + xchk_block_set_preen(sc, bp); + if (sb->sb_rgcount != cpu_to_be32(mp->m_sb.sb_rgcount)) xchk_block_set_corrupt(sc, bp); if (sb->sb_rgextents != cpu_to_be32(mp->m_sb.sb_rgextents)) xchk_block_set_corrupt(sc, bp); + + if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog) + xchk_block_set_corrupt(sc, bp); + + if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad))) + xchk_block_set_corrupt(sc, bp); } /* Everything else must be zero. */ - if (memchr_inv(sb + 1, 0, - BBTOB(bp->b_length) - sizeof(struct xfs_dsb))) + sblen = xchk_superblock_ondisk_size(mp); + if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) xchk_block_set_corrupt(sc, bp); xchk_superblock_xref(sc, bp); @@ -458,7 +499,7 @@ xchk_agf_xref_btreeblks( { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; struct xfs_mount *mp = sc->mp; - xfs_agblock_t blocks; + xfs_filblks_t blocks; xfs_agblock_t btreeblks; int error; @@ -507,7 +548,7 @@ xchk_agf_xref_refcblks( struct xfs_scrub *sc) { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; if (!sc->sa.refc_cur) @@ -840,7 +881,7 @@ xchk_agi_xref_fiblocks( struct xfs_scrub *sc) { struct xfs_agi *agi = sc->sa.agi_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error = 0; if (!xfs_has_inobtcounts(sc->mp)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 0fad0baaba2f..cd6f0223879f 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -256,7 +256,7 @@ xrep_agf_calc_from_btrees( struct xfs_agf *agf = agf_bp->b_addr; struct xfs_mount *mp = sc->mp; xfs_agblock_t btreeblks; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; /* Update the AGF counters from the bnobt. */ @@ -647,7 +647,7 @@ xrep_agfl_fill( xfs_agblock_t agbno = start; int error; - trace_xrep_agfl_insert(sc->sa.pag, agbno, len); + trace_xrep_agfl_insert(pag_group(sc->sa.pag), agbno, len); while (agbno < start + len && af->fl_off < af->flcount) af->agfl_bno[af->fl_off++] = cpu_to_be32(agbno++); @@ -946,7 +946,7 @@ xrep_agi_calc_from_btrees( if (error) goto err; if (xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; error = xfs_btree_count_blocks(cur, &blocks); if (error) @@ -959,7 +959,7 @@ xrep_agi_calc_from_btrees( agi->agi_freecount = cpu_to_be32(freecount); if (xfs_has_finobt(mp) && xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; cur = xfs_finobt_init_cursor(sc->sa.pag, sc->tp, agi_bp); error = xfs_btree_count_blocks(cur, &blocks); diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c index 0433363a90b6..bed6a09aa791 100644 --- a/fs/xfs/scrub/alloc_repair.c +++ b/fs/xfs/scrub/alloc_repair.c @@ -542,8 +542,9 @@ xrep_abt_dispose_one( /* Add a deferred rmap for each extent we used. */ if (resv->used > 0) - xfs_rmap_alloc_extent(sc->tp, pag_agno(pag), resv->agbno, - resv->used, XFS_RMAP_OWN_AG); + xfs_rmap_alloc_extent(sc->tp, false, + xfs_agbno_to_fsb(pag, resv->agbno), resv->used, + XFS_RMAP_OWN_AG); /* * For each reserved btree block we didn't use, add it to the free diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 7e00312225ed..66da7d4d56ba 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -21,6 +21,8 @@ #include "xfs_rmap_btree.h" #include "xfs_rtgroup.h" #include "xfs_health.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrmap_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -143,15 +145,22 @@ static inline bool xchk_bmap_get_rmap( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno, + xfs_agblock_t bno, uint64_t owner, struct xfs_rmap_irec *rmap) { + struct xfs_btree_cur **curp = &info->sc->sa.rmap_cur; xfs_fileoff_t offset; unsigned int rflags = 0; int has_rmap; int error; + if (xfs_ifork_is_realtime(info->sc->ip, info->whichfork)) + curp = &info->sc->sr.rmap_cur; + + if (*curp == NULL) + return false; + if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; if (irec->br_state == XFS_EXT_UNWRITTEN) @@ -172,13 +181,13 @@ xchk_bmap_get_rmap( * range rmap lookup to make sure we get the correct owner/offset. */ if (info->is_shared) { - error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno, - owner, offset, rflags, rmap, &has_rmap); + error = xfs_rmap_lookup_le_range(*curp, bno, owner, offset, + rflags, rmap, &has_rmap); } else { - error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno, - owner, offset, rflags, rmap, &has_rmap); + error = xfs_rmap_lookup_le(*curp, bno, owner, offset, + rflags, rmap, &has_rmap); } - if (!xchk_should_check_xref(info->sc, &error, &info->sc->sa.rmap_cur)) + if (!xchk_should_check_xref(info->sc, &error, curp)) return false; if (!has_rmap) @@ -192,29 +201,29 @@ STATIC void xchk_bmap_xref_rmap( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno) + xfs_agblock_t bno) { struct xfs_rmap_irec rmap; unsigned long long rmap_end; uint64_t owner = info->sc->ip->i_ino; - if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + if (xchk_skip_xref(info->sc->sm)) return; /* Find the rmap record for this irec. */ - if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap)) return; /* * The rmap must be an exact match for this incore file mapping record, * which may have arisen from multiple ondisk records. */ - if (rmap.rm_startblock != agbno) + if (rmap.rm_startblock != bno) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap_end != agbno + irec->br_blockcount) + if (rmap_end != bno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -259,7 +268,7 @@ STATIC void xchk_bmap_xref_rmap_cow( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec, - xfs_agblock_t agbno) + xfs_agblock_t bno) { struct xfs_rmap_irec rmap; unsigned long long rmap_end; @@ -269,7 +278,7 @@ xchk_bmap_xref_rmap_cow( return; /* Find the rmap record for this irec. */ - if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + if (!xchk_bmap_get_rmap(info, irec, bno, owner, &rmap)) return; /* @@ -277,12 +286,12 @@ xchk_bmap_xref_rmap_cow( * can start before and end after the physical space allocated to this * mapping. There are no offsets to check. */ - if (rmap.rm_startblock > agbno) + if (rmap.rm_startblock > bno) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap_end < agbno + irec->br_blockcount) + if (rmap_end < bno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -315,6 +324,8 @@ xchk_bmap_rt_iextent_xref( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec) { + struct xfs_owner_info oinfo; + xfs_rgblock_t rgbno; int error; error = xchk_rtgroup_init_existing(info->sc, @@ -324,10 +335,46 @@ xchk_bmap_rt_iextent_xref( irec->br_startoff, &error)) return; - xchk_rtgroup_lock(&info->sc->sr, XCHK_RTGLOCK_ALL); + error = xchk_rtgroup_lock(info->sc, &info->sc->sr, XCHK_RTGLOCK_ALL); + if (!xchk_fblock_process_error(info->sc, info->whichfork, + irec->br_startoff, &error)) + goto out_free; + xchk_xref_is_used_rt_space(info->sc, irec->br_startblock, irec->br_blockcount); + if (!xfs_has_rtrmapbt(info->sc->mp)) + goto out_cur; + + rgbno = xfs_rtb_to_rgbno(info->sc->mp, irec->br_startblock); + + switch (info->whichfork) { + case XFS_DATA_FORK: + xchk_bmap_xref_rmap(info, irec, rgbno); + if (!xfs_is_reflink_inode(info->sc->ip)) { + xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, + info->whichfork, irec->br_startoff); + xchk_xref_is_only_rt_owned_by(info->sc, rgbno, + irec->br_blockcount, &oinfo); + xchk_xref_is_not_rt_shared(info->sc, rgbno, + irec->br_blockcount); + } + xchk_xref_is_not_rt_cow_staging(info->sc, rgbno, + irec->br_blockcount); + break; + case XFS_COW_FORK: + xchk_bmap_xref_rmap_cow(info, irec, rgbno); + xchk_xref_is_only_rt_owned_by(info->sc, rgbno, + irec->br_blockcount, &XFS_RMAP_OINFO_COW); + xchk_xref_is_rt_cow_staging(info->sc, rgbno, + irec->br_blockcount); + xchk_xref_is_not_rt_shared(info->sc, rgbno, + irec->br_blockcount); + break; + } +out_cur: + xchk_rtgroup_btcur_free(&info->sc->sr); +out_free: xchk_rtgroup_free(info->sc, &info->sc->sr); } @@ -614,8 +661,7 @@ xchk_bmap_check_rmap( xchk_fblock_set_corrupt(sc, sbcri->whichfork, check_rec.rm_offset); if (irec.br_startblock != - xfs_agbno_to_fsb(to_perag(cur->bc_group), - check_rec.rm_startblock)) + xfs_gbno_to_fsb(cur->bc_group, check_rec.rm_startblock)) xchk_fblock_set_corrupt(sc, sbcri->whichfork, check_rec.rm_offset); if (irec.br_blockcount > check_rec.rm_blockcount) @@ -669,6 +715,30 @@ xchk_bmap_check_ag_rmaps( return error; } +/* Make sure each rt rmap has a corresponding bmbt entry. */ +STATIC int +xchk_bmap_check_rt_rmaps( + struct xfs_scrub *sc, + struct xfs_rtgroup *rtg) +{ + struct xchk_bmap_check_rmap_info sbcri; + struct xfs_btree_cur *cur; + int error; + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg); + + sbcri.sc = sc; + sbcri.whichfork = XFS_DATA_FORK; + error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri); + if (error == -ECANCELED) + error = 0; + + xfs_btree_del_cursor(cur, error); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + return error; +} + /* * Decide if we want to scan the reverse mappings to determine if the attr * fork /really/ has zero space mappings. @@ -723,10 +793,6 @@ xchk_bmap_check_empty_datafork( { struct xfs_ifork *ifp = &ip->i_df; - /* Don't support realtime rmap checks yet. */ - if (XFS_IS_REALTIME_INODE(ip)) - return false; - /* * If the dinode repair found a bad data fork, it will reset the fork * to extents format with zero records and wait for the this scrubber @@ -777,6 +843,21 @@ xchk_bmap_check_rmaps( struct xfs_perag *pag = NULL; int error; + if (xfs_ifork_is_realtime(sc->ip, whichfork)) { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + error = xchk_bmap_check_rt_rmaps(sc, rtg); + if (error || + (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) { + xfs_rtgroup_rele(rtg); + return error; + } + } + + return 0; + } + while ((pag = xfs_perag_next(sc->mp, pag))) { error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag); if (error || @@ -983,6 +1064,7 @@ xchk_bmap( case XFS_DINODE_FMT_UUID: case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: + case XFS_DINODE_FMT_META_BTREE: /* No mappings to check. */ if (whichfork == XFS_COW_FORK) xchk_fblock_set_corrupt(sc, whichfork, 0); diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c index 7c4955482641..1084213b8e9b 100644 --- a/fs/xfs/scrub/bmap_repair.c +++ b/fs/xfs/scrub/bmap_repair.c @@ -25,11 +25,13 @@ #include "xfs_bmap_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" #include "xfs_refcount.h" #include "xfs_quota.h" #include "xfs_ialloc.h" #include "xfs_ag.h" #include "xfs_reflink.h" +#include "xfs_rtgroup.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -99,14 +101,21 @@ xrep_bmap_discover_shared( xfs_filblks_t blockcount) { struct xfs_scrub *sc = rb->sc; + struct xfs_btree_cur *cur; xfs_agblock_t agbno; xfs_agblock_t fbno; xfs_extlen_t flen; int error; - agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock); - error = xfs_refcount_find_shared(sc->sa.refc_cur, agbno, blockcount, - &fbno, &flen, false); + if (XFS_IS_REALTIME_INODE(sc->ip)) { + agbno = xfs_rtb_to_rgbno(sc->mp, startblock); + cur = sc->sr.refc_cur; + } else { + agbno = XFS_FSB_TO_AGBNO(sc->mp, startblock); + cur = sc->sa.refc_cur; + } + error = xfs_refcount_find_shared(cur, agbno, blockcount, &fbno, &flen, + false); if (error) return error; @@ -359,6 +368,114 @@ xrep_bmap_scan_ag( return error; } +#ifdef CONFIG_XFS_RT +/* Check for any obvious errors or conflicts in the file mapping. */ +STATIC int +xrep_bmap_check_rtfork_rmap( + struct xfs_scrub *sc, + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec) +{ + /* xattr extents are never stored on realtime devices */ + if (rec->rm_flags & XFS_RMAP_ATTR_FORK) + return -EFSCORRUPTED; + + /* bmbt blocks are never stored on realtime devices */ + if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) + return -EFSCORRUPTED; + + /* Data extents for non-rt files are never stored on the rt device. */ + if (!XFS_IS_REALTIME_INODE(sc->ip)) + return -EFSCORRUPTED; + + /* Check the file offsets and physical extents. */ + if (!xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Check that this is within the rtgroup. */ + if (!xfs_verify_rgbext(to_rtg(cur->bc_group), rec->rm_startblock, + rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + return xrep_require_rtext_inuse(sc, rec->rm_startblock, + rec->rm_blockcount); +} + +/* Record realtime extents that belong to this inode's fork. */ +STATIC int +xrep_bmap_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_bmap *rb = priv; + int error = 0; + + if (xchk_should_terminate(rb->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rb->sc->ip->i_ino) + return 0; + + error = xrep_bmap_check_rtfork_rmap(rb->sc, cur, rec); + if (error) + return error; + + /* + * Record all blocks allocated to this file even if the extent isn't + * for the fork we're rebuilding so that we can reset di_nblocks later. + */ + rb->nblocks += rec->rm_blockcount; + + /* If this rmap isn't for the fork we want, we're done. */ + if (rb->whichfork == XFS_DATA_FORK && + (rec->rm_flags & XFS_RMAP_ATTR_FORK)) + return 0; + if (rb->whichfork == XFS_ATTR_FORK && + !(rec->rm_flags & XFS_RMAP_ATTR_FORK)) + return 0; + + return xrep_bmap_from_rmap(rb, rec->rm_offset, + xfs_rgbno_to_rtb(to_rtg(cur->bc_group), + rec->rm_startblock), + rec->rm_blockcount, + rec->rm_flags & XFS_RMAP_UNWRITTEN); +} + +/* Scan the realtime reverse mappings to build the new extent map. */ +STATIC int +xrep_bmap_scan_rtgroup( + struct xrep_bmap *rb, + struct xfs_rtgroup *rtg) +{ + struct xfs_scrub *sc = rb->sc; + int error; + + if (!xfs_has_rtrmapbt(sc->mp)) + return 0; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, + XFS_RTGLOCK_RMAP | + XFS_RTGLOCK_REFCOUNT | + XFS_RTGLOCK_BITMAP_SHARED); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_bmap_walk_rtrmap, rb); + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); + return error; +} +#else +static inline int +xrep_bmap_scan_rtgroup(struct xrep_bmap *rb, struct xfs_rtgroup *rtg) +{ + return -EFSCORRUPTED; +} +#endif + /* Find the delalloc extents from the old incore extent tree. */ STATIC int xrep_bmap_find_delalloc( @@ -410,6 +527,22 @@ xrep_bmap_find_mappings( struct xfs_perag *pag = NULL; int error = 0; + /* + * Iterate the rtrmaps for extents. Metadata files never have content + * on the realtime device, so there's no need to scan them. + */ + if (!xfs_is_metadir_inode(sc->ip)) { + struct xfs_rtgroup *rtg = NULL; + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + error = xrep_bmap_scan_rtgroup(rb, rtg); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + } + /* Iterate the rmaps for extents. */ while ((pag = xfs_perag_next(sc->mp, pag))) { error = xrep_bmap_scan_ag(rb, pag); @@ -731,6 +864,7 @@ xrep_bmap_check_inputs( case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: case XFS_DINODE_FMT_UUID: + case XFS_DINODE_FMT_META_BTREE: return -ECANCELED; case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: @@ -753,10 +887,6 @@ xrep_bmap_check_inputs( return -EINVAL; } - /* Don't know how to rebuild realtime data forks. */ - if (XFS_IS_REALTIME_INODE(sc->ip)) - return -EOPNOTSUPP; - return 0; } @@ -782,10 +912,6 @@ xrep_bmap_init_reflink_scan( if (whichfork != XFS_DATA_FORK) return RLS_IRRELEVANT; - /* cannot share realtime extents */ - if (XFS_IS_REALTIME_INODE(sc->ip)) - return RLS_IRRELEVANT; - return RLS_UNKNOWN; } diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 5cbd94b56582..28ad341df8ee 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -35,6 +35,9 @@ #include "xfs_exchmaps.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_bmap_util.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -719,20 +722,111 @@ xchk_rtgroup_init( return 0; } -void +/* Lock all the rt group metadata inode ILOCKs and wait for intents. */ +int xchk_rtgroup_lock( + struct xfs_scrub *sc, struct xchk_rt *sr, unsigned int rtglock_flags) { - xfs_rtgroup_lock(sr->rtg, rtglock_flags); + int error = 0; + + ASSERT(sr->rtg != NULL); + + /* + * If we're /only/ locking the rtbitmap in shared mode, then we're + * obviously not trying to compare records in two metadata inodes. + * There's no need to drain intents here because the caller (most + * likely the rgsuper scanner) doesn't need that level of consistency. + */ + if (rtglock_flags == XFS_RTGLOCK_BITMAP_SHARED) { + xfs_rtgroup_lock(sr->rtg, rtglock_flags); + sr->rtlock_flags = rtglock_flags; + return 0; + } + + do { + if (xchk_should_terminate(sc, &error)) + return error; + + xfs_rtgroup_lock(sr->rtg, rtglock_flags); + + /* + * If we've grabbed a non-metadata file for scrubbing, we + * assume that holding its ILOCK will suffice to coordinate + * with any rt intent chains involving this inode. + */ + if (sc->ip && !xfs_is_internal_inode(sc->ip)) + break; + + /* + * Decide if the rt group is quiet enough for all metadata to + * be consistent with each other. Regular file IO doesn't get + * to lock all the rt inodes at the same time, which means that + * there could be other threads in the middle of processing a + * chain of deferred ops. + * + * We just locked all the metadata inodes for this rt group; + * now take a look to see if there are any intents in progress. + * If there are, drop the rt group inode locks and wait for the + * intents to drain. Since we hold the rt group inode locks + * for the duration of the scrub, this is the only time we have + * to sample the intents counter; any threads increasing it + * after this point can't possibly be in the middle of a chain + * of rt metadata updates. + * + * Obviously, this should be slanted against scrub and in favor + * of runtime threads. + */ + if (!xfs_group_intent_busy(rtg_group(sr->rtg))) + break; + + xfs_rtgroup_unlock(sr->rtg, rtglock_flags); + + if (!(sc->flags & XCHK_FSGATES_DRAIN)) + return -ECHRNG; + error = xfs_group_intent_drain(rtg_group(sr->rtg)); + if (error) { + if (error == -ERESTARTSYS) + error = -EINTR; + return error; + } + } while (1); + sr->rtlock_flags = rtglock_flags; + + if (xfs_has_rtrmapbt(sc->mp) && (rtglock_flags & XFS_RTGLOCK_RMAP)) + sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg); + + if (xfs_has_rtreflink(sc->mp) && (rtglock_flags & XFS_RTGLOCK_REFCOUNT)) + sr->refc_cur = xfs_rtrefcountbt_init_cursor(sc->tp, sr->rtg); + + return 0; +} + +/* + * Free all the btree cursors and other incore data relating to the realtime + * group. This has to be done /before/ committing (or cancelling) the scrub + * transaction. + */ +void +xchk_rtgroup_btcur_free( + struct xchk_rt *sr) +{ + if (sr->rmap_cur) + xfs_btree_del_cursor(sr->rmap_cur, XFS_BTREE_ERROR); + if (sr->refc_cur) + xfs_btree_del_cursor(sr->refc_cur, XFS_BTREE_ERROR); + + sr->refc_cur = NULL; + sr->rmap_cur = NULL; } /* * Unlock the realtime group. This must be done /after/ committing (or * cancelling) the scrub transaction. */ -static void +void xchk_rtgroup_unlock( struct xchk_rt *sr) { @@ -812,6 +906,14 @@ xchk_setup_fs( return xchk_trans_alloc(sc, resblks); } +/* Set us up with a transaction and an empty context to repair rt metadata. */ +int +xchk_setup_rt( + struct xfs_scrub *sc) +{ + return xchk_trans_alloc(sc, xrep_calc_rtgroup_resblks(sc)); +} + /* Set us up with AG headers and btree cursors. */ int xchk_setup_ag_btree( @@ -1379,7 +1481,7 @@ xchk_fsgates_enable( trace_xchk_fsgates_enable(sc, scrub_fsgates); if (scrub_fsgates & XCHK_FSGATES_DRAIN) - xfs_drain_wait_enable(); + xfs_defer_drain_wait_enable(); if (scrub_fsgates & XCHK_FSGATES_QUOTA) xfs_dqtrx_hook_enable(); @@ -1573,3 +1675,63 @@ xchk_inode_rootdir_inum(const struct xfs_inode *ip) return mp->m_metadirip->i_ino; return mp->m_rootip->i_ino; } + +static int +xchk_meta_btree_count_blocks( + struct xfs_scrub *sc, + xfs_extnum_t *nextents, + xfs_filblks_t *count) +{ + struct xfs_btree_cur *cur; + int error; + + if (!sc->sr.rtg) { + ASSERT(0); + return -EFSCORRUPTED; + } + + switch (sc->ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg); + break; + case XFS_METAFILE_RTREFCOUNT: + cur = xfs_rtrefcountbt_init_cursor(sc->tp, sc->sr.rtg); + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + error = xfs_btree_count_blocks(cur, count); + xfs_btree_del_cursor(cur, error); + if (!error) { + *nextents = 0; + (*count)--; /* don't count the btree iroot */ + } + return error; +} + +/* Count the blocks used by a file, even if it's a metadata inode. */ +int +xchk_inode_count_blocks( + struct xfs_scrub *sc, + int whichfork, + xfs_extnum_t *nextents, + xfs_filblks_t *count) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork); + + if (!ifp) { + *nextents = 0; + *count = 0; + return 0; + } + + if (ifp->if_format == XFS_DINODE_FMT_META_BTREE) { + ASSERT(whichfork == XFS_DATA_FORK); + return xchk_meta_btree_count_blocks(sc, nextents, count); + } + + return xfs_bmap_count_blocks(sc->tp, sc->ip, whichfork, nextents, + count); +} diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 9ff3cafd8679..bdcd40f0ec74 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -63,6 +63,7 @@ static inline int xchk_setup_nothing(struct xfs_scrub *sc) /* Setup functions */ int xchk_setup_agheader(struct xfs_scrub *sc); int xchk_setup_fs(struct xfs_scrub *sc); +int xchk_setup_rt(struct xfs_scrub *sc); int xchk_setup_ag_allocbt(struct xfs_scrub *sc); int xchk_setup_ag_iallocbt(struct xfs_scrub *sc); int xchk_setup_ag_rmapbt(struct xfs_scrub *sc); @@ -80,10 +81,14 @@ int xchk_setup_metapath(struct xfs_scrub *sc); int xchk_setup_rtbitmap(struct xfs_scrub *sc); int xchk_setup_rtsummary(struct xfs_scrub *sc); int xchk_setup_rgsuperblock(struct xfs_scrub *sc); +int xchk_setup_rtrmapbt(struct xfs_scrub *sc); +int xchk_setup_rtrefcountbt(struct xfs_scrub *sc); #else # define xchk_setup_rtbitmap xchk_setup_nothing # define xchk_setup_rtsummary xchk_setup_nothing # define xchk_setup_rgsuperblock xchk_setup_nothing +# define xchk_setup_rtrmapbt xchk_setup_nothing +# define xchk_setup_rtrefcountbt xchk_setup_nothing #endif #ifdef CONFIG_XFS_QUOTA int xchk_ino_dqattach(struct xfs_scrub *sc); @@ -125,7 +130,9 @@ xchk_ag_init_existing( #ifdef CONFIG_XFS_RT /* All the locks we need to check an rtgroup. */ -#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP) +#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno, struct xchk_rt *sr); @@ -141,12 +148,17 @@ xchk_rtgroup_init_existing( return error == -ENOENT ? -EFSCORRUPTED : error; } -void xchk_rtgroup_lock(struct xchk_rt *sr, unsigned int rtglock_flags); +int xchk_rtgroup_lock(struct xfs_scrub *sc, struct xchk_rt *sr, + unsigned int rtglock_flags); +void xchk_rtgroup_unlock(struct xchk_rt *sr); +void xchk_rtgroup_btcur_free(struct xchk_rt *sr); void xchk_rtgroup_free(struct xfs_scrub *sc, struct xchk_rt *sr); #else # define xchk_rtgroup_init(sc, rgno, sr) (-EFSCORRUPTED) # define xchk_rtgroup_init_existing(sc, rgno, sr) (-EFSCORRUPTED) -# define xchk_rtgroup_lock(sc, lockflags) do { } while (0) +# define xchk_rtgroup_lock(sc, sr, lockflags) (-EFSCORRUPTED) +# define xchk_rtgroup_unlock(sr) do { } while (0) +# define xchk_rtgroup_btcur_free(sr) do { } while (0) # define xchk_rtgroup_free(sc, sr) do { } while (0) #endif /* CONFIG_XFS_RT */ @@ -257,6 +269,12 @@ int xchk_metadata_inode_forks(struct xfs_scrub *sc); (sc)->mp->m_super->s_id, \ (sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \ ##__VA_ARGS__) +#define xchk_xfile_rtgroup_descr(sc, fmt, ...) \ + kasprintf(XCHK_GFP_FLAGS, "XFS (%s): rtgroup 0x%x " fmt, \ + (sc)->mp->m_super->s_id, \ + (sc)->sa.pag ? \ + rtg_rgno((sc)->sr.rtg) : (sc)->sm->sm_agno, \ + ##__VA_ARGS__) /* * Setting up a hook to wait for intents to drain is costly -- we have to take @@ -274,6 +292,8 @@ void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks); int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino, bool *inuse); +int xchk_inode_count_blocks(struct xfs_scrub *sc, int whichfork, + xfs_extnum_t *nextents, xfs_filblks_t *count); bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip); bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip); diff --git a/fs/xfs/scrub/cow_repair.c b/fs/xfs/scrub/cow_repair.c index 5b6194cef3e5..38a246b8bf11 100644 --- a/fs/xfs/scrub/cow_repair.c +++ b/fs/xfs/scrub/cow_repair.c @@ -26,6 +26,9 @@ #include "xfs_errortag.h" #include "xfs_icache.h" #include "xfs_refcount_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -34,6 +37,7 @@ #include "scrub/bitmap.h" #include "scrub/off_bitmap.h" #include "scrub/fsb_bitmap.h" +#include "scrub/rtb_bitmap.h" #include "scrub/reap.h" /* @@ -61,7 +65,10 @@ struct xrep_cow { struct xoff_bitmap bad_fileoffs; /* Bitmap of fsblocks that were removed from the CoW fork. */ - struct xfsb_bitmap old_cowfork_fsblocks; + union { + struct xfsb_bitmap old_cowfork_fsblocks; + struct xrtb_bitmap old_cowfork_rtblocks; + }; /* CoW fork mappings used to scan for bad CoW staging extents. */ struct xfs_bmbt_irec irec; @@ -145,8 +152,7 @@ xrep_cow_mark_shared_staging( xrep_cow_trim_refcount(xc, &rrec, rec); return xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), - rrec.rc_startblock), + xfs_gbno_to_fsb(cur->bc_group, rrec.rc_startblock), rrec.rc_blockcount); } @@ -177,9 +183,8 @@ xrep_cow_mark_missing_staging( if (xc->next_bno >= rrec.rc_startblock) goto next; - error = xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), xc->next_bno), + xfs_gbno_to_fsb(cur->bc_group, xc->next_bno), rrec.rc_startblock - xc->next_bno); if (error) return error; @@ -222,8 +227,7 @@ xrep_cow_mark_missing_staging_rmap( } return xrep_cow_mark_file_range(xc, - xfs_agbno_to_fsb(to_perag(cur->bc_group), rec_bno), - rec_len); + xfs_gbno_to_fsb(cur->bc_group, rec_bno), rec_len); } /* @@ -311,6 +315,92 @@ out_pag: } /* + * Find any part of the CoW fork mapping that isn't a single-owner CoW staging + * extent and mark the corresponding part of the file range in the bitmap. + */ +STATIC int +xrep_cow_find_bad_rt( + struct xrep_cow *xc) +{ + struct xfs_refcount_irec rc_low = { 0 }; + struct xfs_refcount_irec rc_high = { 0 }; + struct xfs_rmap_irec rm_low = { 0 }; + struct xfs_rmap_irec rm_high = { 0 }; + struct xfs_scrub *sc = xc->sc; + struct xfs_rtgroup *rtg; + int error = 0; + + xc->irec_startbno = xfs_rtb_to_rgbno(sc->mp, xc->irec.br_startblock); + + rtg = xfs_rtgroup_get(sc->mp, + xfs_rtb_to_rgno(sc->mp, xc->irec.br_startblock)); + if (!rtg) + return -EFSCORRUPTED; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, + XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + if (error) + goto out_rtg; + + /* Mark any CoW fork extents that are shared. */ + rc_low.rc_startblock = xc->irec_startbno; + rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_SHARED; + error = xfs_refcount_query_range(sc->sr.refc_cur, &rc_low, &rc_high, + xrep_cow_mark_shared_staging, xc); + if (error) + goto out_sr; + + /* Make sure there are CoW staging extents for the whole mapping. */ + rc_low.rc_startblock = xc->irec_startbno; + rc_high.rc_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + rc_low.rc_domain = rc_high.rc_domain = XFS_REFC_DOMAIN_COW; + xc->next_bno = xc->irec_startbno; + error = xfs_refcount_query_range(sc->sr.refc_cur, &rc_low, &rc_high, + xrep_cow_mark_missing_staging, xc); + if (error) + goto out_sr; + + if (xc->next_bno < xc->irec_startbno + xc->irec.br_blockcount) { + error = xrep_cow_mark_file_range(xc, + xfs_rgbno_to_rtb(rtg, xc->next_bno), + xc->irec_startbno + xc->irec.br_blockcount - + xc->next_bno); + if (error) + goto out_sr; + } + + /* Mark any area has an rmap that isn't a COW staging extent. */ + rm_low.rm_startblock = xc->irec_startbno; + memset(&rm_high, 0xFF, sizeof(rm_high)); + rm_high.rm_startblock = xc->irec_startbno + xc->irec.br_blockcount - 1; + error = xfs_rmap_query_range(sc->sr.rmap_cur, &rm_low, &rm_high, + xrep_cow_mark_missing_staging_rmap, xc); + if (error) + goto out_sr; + + /* + * If userspace is forcing us to rebuild the CoW fork or someone + * turned on the debugging knob, replace everything in the + * CoW fork and then scan for staging extents in the refcountbt. + */ + if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + XFS_TEST_ERROR(false, sc->mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR)) { + error = xrep_cow_mark_file_range(xc, xc->irec.br_startblock, + xc->irec.br_blockcount); + if (error) + goto out_rtg; + } + +out_sr: + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); +out_rtg: + xfs_rtgroup_put(rtg); + return error; +} + +/* * Allocate a replacement CoW staging extent of up to the given number of * blocks, and fill out the mapping. */ @@ -343,7 +433,7 @@ xrep_cow_alloc( if (args.fsbno == NULLFSBLOCK) return -ENOSPC; - xfs_refcount_alloc_cow_extent(sc->tp, args.fsbno, args.len); + xfs_refcount_alloc_cow_extent(sc->tp, false, args.fsbno, args.len); repl->fsbno = args.fsbno; repl->len = args.len; @@ -351,6 +441,32 @@ xrep_cow_alloc( } /* + * Allocate a replacement rt CoW staging extent of up to the given number of + * blocks, and fill out the mapping. + */ +STATIC int +xrep_cow_alloc_rt( + struct xfs_scrub *sc, + xfs_extlen_t maxlen, + struct xrep_cow_extent *repl) +{ + xfs_rtxlen_t maxrtx = xfs_rtb_to_rtx(sc->mp, maxlen); + int error; + + error = xfs_trans_reserve_more(sc->tp, 0, maxrtx); + if (error) + return error; + + error = xfs_rtallocate_rtgs(sc->tp, NULLRTBLOCK, 1, maxrtx, 1, false, + false, &repl->fsbno, &repl->len); + if (error) + return error; + + xfs_refcount_alloc_cow_extent(sc->tp, true, repl->fsbno, repl->len); + return 0; +} + +/* * Look up the current CoW fork mapping so that we only allocate enough to * replace a single mapping. If we don't find a mapping that covers the start * of the file range, or we find a delalloc or written extent, something is @@ -467,7 +583,10 @@ xrep_cow_replace_range( */ alloc_len = min_t(xfs_fileoff_t, XFS_MAX_BMBT_EXTLEN, nextoff - startoff); - error = xrep_cow_alloc(sc, alloc_len, &repl); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_cow_alloc_rt(sc, alloc_len, &repl); + else + error = xrep_cow_alloc(sc, alloc_len, &repl); if (error) return error; @@ -483,8 +602,12 @@ xrep_cow_replace_range( return error; /* Note the old CoW staging extents; we'll reap them all later. */ - error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, got.br_startblock, - repl.len); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrtb_bitmap_set(&xc->old_cowfork_rtblocks, + got.br_startblock, repl.len); + else + error = xfsb_bitmap_set(&xc->old_cowfork_fsblocks, + got.br_startblock, repl.len); if (error) return error; @@ -540,8 +663,16 @@ xrep_bmap_cow( if (!ifp) return 0; - /* realtime files aren't supported yet */ - if (XFS_IS_REALTIME_INODE(sc->ip)) + /* + * Realtime files with large extent sizes are not supported because + * we could encounter an CoW mapping that has been partially written + * out *and* requires replacement, and there's no solution to that. + */ + if (xfs_inode_has_bigrtalloc(sc->ip)) + return -EOPNOTSUPP; + + /* Metadata inodes aren't supposed to have data on the rt volume. */ + if (xfs_is_metadir_inode(sc->ip) && XFS_IS_REALTIME_INODE(sc->ip)) return -EOPNOTSUPP; /* @@ -562,7 +693,10 @@ xrep_bmap_cow( xc->sc = sc; xoff_bitmap_init(&xc->bad_fileoffs); - xfsb_bitmap_init(&xc->old_cowfork_fsblocks); + if (XFS_IS_REALTIME_INODE(sc->ip)) + xrtb_bitmap_init(&xc->old_cowfork_rtblocks); + else + xfsb_bitmap_init(&xc->old_cowfork_fsblocks); for_each_xfs_iext(ifp, &icur, &xc->irec) { if (xchk_should_terminate(sc, &error)) @@ -585,7 +719,10 @@ xrep_bmap_cow( if (xfs_bmap_is_written_extent(&xc->irec)) continue; - error = xrep_cow_find_bad(xc); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_cow_find_bad_rt(xc); + else + error = xrep_cow_find_bad(xc); if (error) goto out_bitmap; } @@ -600,13 +737,20 @@ xrep_bmap_cow( * by the refcount btree, not the inode, so it is correct to treat them * like inode metadata. */ - error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks, - &XFS_RMAP_OINFO_COW); + if (XFS_IS_REALTIME_INODE(sc->ip)) + error = xrep_reap_rtblocks(sc, &xc->old_cowfork_rtblocks, + &XFS_RMAP_OINFO_COW); + else + error = xrep_reap_fsblocks(sc, &xc->old_cowfork_fsblocks, + &XFS_RMAP_OINFO_COW); if (error) goto out_bitmap; out_bitmap: - xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks); + if (XFS_IS_REALTIME_INODE(sc->ip)) + xrtb_bitmap_destroy(&xc->old_cowfork_rtblocks); + else + xfsb_bitmap_destroy(&xc->old_cowfork_fsblocks); xoff_bitmap_destroy(&xc->bad_fileoffs); kfree(xc); return error; diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 4a50f8e00040..ca23cf4db6c5 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -261,7 +261,7 @@ xchk_fscount_btreeblks( struct xchk_fscounters *fsc, xfs_agnumber_t agno) { - xfs_extlen_t blocks; + xfs_filblks_t blocks; int error; error = xchk_ag_init_existing(sc, agno, &sc->sa); diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index ce86bdad37fa..3c0f25098b69 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -71,7 +71,8 @@ /* Map our scrub type to a sick mask and a set of health update functions. */ enum xchk_health_group { - XHG_FS = 1, + XHG_NONE = 1, + XHG_FS, XHG_AG, XHG_INO, XHG_RTGROUP, @@ -83,6 +84,7 @@ struct xchk_health_map { }; static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { + [XFS_SCRUB_TYPE_PROBE] = { XHG_NONE, 0 }, [XFS_SCRUB_TYPE_SB] = { XHG_AG, XFS_SICK_AG_SB }, [XFS_SCRUB_TYPE_AGF] = { XHG_AG, XFS_SICK_AG_AGF }, [XFS_SCRUB_TYPE_AGFL] = { XHG_AG, XFS_SICK_AG_AGFL }, @@ -112,6 +114,8 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_DIRTREE] = { XHG_INO, XFS_SICK_INO_DIRTREE }, [XFS_SCRUB_TYPE_METAPATH] = { XHG_FS, XFS_SICK_FS_METAPATH }, [XFS_SCRUB_TYPE_RGSUPER] = { XHG_RTGROUP, XFS_SICK_RG_SUPER }, + [XFS_SCRUB_TYPE_RTRMAPBT] = { XHG_RTGROUP, XFS_SICK_RG_RMAPBT }, + [XFS_SCRUB_TYPE_RTREFCBT] = { XHG_RTGROUP, XFS_SICK_RG_REFCNTBT }, }; /* Return the health status mask for this scrub type. */ @@ -133,7 +137,7 @@ xchk_mark_healthy_if_clean( { if (!(sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XCORRUPT))) - sc->sick_mask |= mask; + sc->healthy_mask |= mask; } /* @@ -189,6 +193,7 @@ xchk_update_health( { struct xfs_perag *pag; struct xfs_rtgroup *rtg; + unsigned int mask = sc->sick_mask; bool bad; /* @@ -203,50 +208,56 @@ xchk_update_health( return; } - if (!sc->sick_mask) - return; - bad = (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XCORRUPT)); + if (!bad) + mask |= sc->healthy_mask; switch (type_to_health_flag[sc->sm->sm_type].group) { + case XHG_NONE: + break; case XHG_AG: + if (!mask) + return; pag = xfs_perag_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_group_mark_corrupt(pag_group(pag), sc->sick_mask); + xfs_group_mark_corrupt(pag_group(pag), mask); else - xfs_group_mark_healthy(pag_group(pag), sc->sick_mask); + xfs_group_mark_healthy(pag_group(pag), mask); xfs_perag_put(pag); break; case XHG_INO: if (!sc->ip) return; - if (bad) { - unsigned int mask = sc->sick_mask; - - /* - * If we're coming in for repairs then we don't want - * sickness flags to propagate to the incore health - * status if the inode gets inactivated before we can - * fix it. - */ - if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) - mask |= XFS_SICK_INO_FORGET; + /* + * If we're coming in for repairs then we don't want sickness + * flags to propagate to the incore health status if the inode + * gets inactivated before we can fix it. + */ + if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) + mask |= XFS_SICK_INO_FORGET; + if (!mask) + return; + if (bad) xfs_inode_mark_corrupt(sc->ip, mask); - } else - xfs_inode_mark_healthy(sc->ip, sc->sick_mask); + else + xfs_inode_mark_healthy(sc->ip, mask); break; case XHG_FS: + if (!mask) + return; if (bad) - xfs_fs_mark_corrupt(sc->mp, sc->sick_mask); + xfs_fs_mark_corrupt(sc->mp, mask); else - xfs_fs_mark_healthy(sc->mp, sc->sick_mask); + xfs_fs_mark_healthy(sc->mp, mask); break; case XHG_RTGROUP: + if (!mask) + return; rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_group_mark_corrupt(rtg_group(rtg), sc->sick_mask); + xfs_group_mark_corrupt(rtg_group(rtg), mask); else - xfs_group_mark_healthy(rtg_group(rtg), sc->sick_mask); + xfs_group_mark_healthy(rtg_group(rtg), mask); xfs_rtgroup_put(rtg); break; default: diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index abad54c3621d..4dc7c83dc08a 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -650,8 +650,8 @@ xchk_iallocbt_xref_rmap_btreeblks( struct xfs_scrub *sc) { xfs_filblks_t blocks; - xfs_extlen_t inobt_blocks = 0; - xfs_extlen_t finobt_blocks = 0; + xfs_filblks_t inobt_blocks = 0; + xfs_filblks_t finobt_blocks = 0; int error; if (!sc->sa.ino_cur || !sc->sa.rmap_cur || diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 25ee66e7649d..db6edd5a5fe5 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -260,12 +260,7 @@ xchk_inode_extsize( xchk_ino_set_warning(sc, ino); } -/* - * Validate di_cowextsize hint. - * - * The rules are documented at xfs_ioctl_setattr_check_cowextsize(). - * These functions must be kept in sync with each other. - */ +/* Validate di_cowextsize hint. */ STATIC void xchk_inode_cowextsize( struct xfs_scrub *sc, @@ -276,12 +271,25 @@ xchk_inode_cowextsize( uint64_t flags2) { xfs_failaddr_t fa; + uint32_t value = be32_to_cpu(dip->di_cowextsize); - fa = xfs_inode_validate_cowextsize(sc->mp, - be32_to_cpu(dip->di_cowextsize), mode, flags, - flags2); + fa = xfs_inode_validate_cowextsize(sc->mp, value, mode, flags, flags2); if (fa) xchk_ino_set_corrupt(sc, ino); + + /* + * XFS allows a sysadmin to change the rt extent size when adding a rt + * section to a filesystem after formatting. If there are any + * directories with cowextsize and rtinherit set, the hint could become + * misaligned with the new rextsize. The verifier doesn't check this, + * because we allow rtinherit directories even without an rt device. + * Flag this as an administrative warning since we will clean this up + * eventually. + */ + if ((flags & XFS_DIFLAG_RTINHERIT) && + (flags2 & XFS_DIFLAG2_COWEXTSIZE) && + value % sc->mp->m_sb.sb_rextsize > 0) + xchk_ino_set_warning(sc, ino); } /* Make sure the di_flags make sense for the inode. */ @@ -360,8 +368,9 @@ xchk_inode_flags2( if ((flags2 & XFS_DIFLAG2_REFLINK) && !S_ISREG(mode)) goto bad; - /* realtime and reflink make no sense, currently */ - if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK)) + /* realtime and reflink don't always go together */ + if ((flags & XFS_DIFLAG_REALTIME) && (flags2 & XFS_DIFLAG2_REFLINK) && + !xfs_has_rtreflink(mp)) goto bad; /* no bigtime iflag without the bigtime feature */ @@ -502,6 +511,10 @@ xchk_dinode( if (!S_ISREG(mode) && !S_ISDIR(mode)) xchk_ino_set_corrupt(sc, ino); break; + case XFS_DINODE_FMT_META_BTREE: + if (!S_ISREG(mode)) + xchk_ino_set_corrupt(sc, ino); + break; case XFS_DINODE_FMT_UUID: default: xchk_ino_set_corrupt(sc, ino); @@ -686,15 +699,13 @@ xchk_inode_xref_bmap( return; /* Walk all the extents to check nextents/naextents/nblocks. */ - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK, - &nextents, &count); + error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count); if (!xchk_should_check_xref(sc, &error, NULL)) return; if (nextents < xfs_dfork_data_extents(dip)) xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino); - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK, - &nextents, &acount); + error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, &acount); if (!xchk_should_check_xref(sc, &error, NULL)) return; if (nextents != xfs_dfork_attr_extents(dip)) diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 5a58ddd27bd2..2f641b6d663e 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -38,6 +38,9 @@ #include "xfs_log_priv.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -562,8 +565,6 @@ xrep_dinode_flags( flags2 |= XFS_DIFLAG2_REFLINK; else flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE); - if (flags & XFS_DIFLAG_REALTIME) - flags2 &= ~XFS_DIFLAG2_REFLINK; if (!xfs_has_bigtime(mp)) flags2 &= ~XFS_DIFLAG2_BIGTIME; if (!xfs_has_large_extent_counts(mp)) @@ -773,17 +774,71 @@ xrep_dinode_count_ag_rmaps( return error; } +/* Count extents and blocks for an inode given an rt rmap. */ +STATIC int +xrep_dinode_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_inode *ri = priv; + int error = 0; + + if (xchk_should_terminate(ri->sc, &error)) + return error; + + /* We only care about this inode. */ + if (rec->rm_owner != ri->sc->sm->sm_ino) + return 0; + + if (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)) + return -EFSCORRUPTED; + + ri->rt_blocks += rec->rm_blockcount; + ri->rt_extents++; + return 0; +} + +/* Count extents and blocks for an inode from all realtime rmap data. */ +STATIC int +xrep_dinode_count_rtgroup_rmaps( + struct xrep_inode *ri, + struct xfs_rtgroup *rtg) +{ + struct xfs_scrub *sc = ri->sc; + int error; + + error = xrep_rtgroup_init(sc, rtg, &sc->sr, XFS_RTGLOCK_RMAP); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_dinode_walk_rtrmap, + ri); + xchk_rtgroup_btcur_free(&sc->sr); + xchk_rtgroup_free(sc, &sc->sr); + return error; +} + /* Count extents and blocks for a given inode from all rmap data. */ STATIC int xrep_dinode_count_rmaps( struct xrep_inode *ri) { struct xfs_perag *pag = NULL; + struct xfs_rtgroup *rtg = NULL; int error; - if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp)) + if (!xfs_has_rmapbt(ri->sc->mp)) return -EOPNOTSUPP; + while ((rtg = xfs_rtgroup_next(ri->sc->mp, rtg))) { + error = xrep_dinode_count_rtgroup_rmaps(ri, rtg); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + while ((pag = xfs_perag_next(ri->sc->mp, pag))) { error = xrep_dinode_count_ag_rmaps(ri, pag); if (error) { @@ -888,6 +943,85 @@ xrep_dinode_bad_bmbt_fork( return false; } +/* Return true if this rmap-format ifork looks like garbage. */ +STATIC bool +xrep_dinode_bad_rtrmapbt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size) +{ + struct xfs_rtrmap_root *dfp; + unsigned int nrecs; + unsigned int level; + + if (dfork_size < sizeof(struct xfs_rtrmap_root)) + return true; + + dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > sc->mp->m_rtrmap_maxlevels) + return true; + if (xfs_rtrmap_droot_space_calc(level, nrecs) > dfork_size) + return true; + if (level > 0 && nrecs == 0) + return true; + + return false; +} + +/* Return true if this refcount-format ifork looks like garbage. */ +STATIC bool +xrep_dinode_bad_rtrefcountbt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size) +{ + struct xfs_rtrefcount_root *dfp; + unsigned int nrecs; + unsigned int level; + + if (dfork_size < sizeof(struct xfs_rtrefcount_root)) + return true; + + dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > sc->mp->m_rtrefc_maxlevels) + return true; + if (xfs_rtrefcount_droot_space_calc(level, nrecs) > dfork_size) + return true; + if (level > 0 && nrecs == 0) + return true; + + return false; +} + +/* Check a metadata-btree fork. */ +STATIC bool +xrep_dinode_bad_metabt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size, + int whichfork) +{ + if (whichfork != XFS_DATA_FORK) + return true; + + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + return xrep_dinode_bad_rtrmapbt_fork(sc, dip, dfork_size); + case XFS_METAFILE_RTREFCOUNT: + return xrep_dinode_bad_rtrefcountbt_fork(sc, dip, dfork_size); + default: + return true; + } + + return false; +} + /* * Check the data fork for things that will fail the ifork verifiers or the * ifork formatters. @@ -968,6 +1102,11 @@ xrep_dinode_check_dfork( XFS_DATA_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, dfork_size, + XFS_DATA_FORK)) + return true; + break; default: return true; } @@ -1088,6 +1227,11 @@ xrep_dinode_check_afork( XFS_ATTR_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, afork_size, + XFS_ATTR_FORK)) + return true; + break; default: return true; } @@ -1135,6 +1279,8 @@ xrep_dinode_ensure_forkoff( uint16_t mode) { struct xfs_bmdr_block *bmdr; + struct xfs_rtrmap_root *rmdr; + struct xfs_rtrefcount_root *rcdr; struct xfs_scrub *sc = ri->sc; xfs_extnum_t attr_extents, data_extents; size_t bmdr_minsz = xfs_bmdr_space_calc(1); @@ -1241,6 +1387,21 @@ xrep_dinode_ensure_forkoff( bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); dfork_min = xfs_bmap_broot_space(sc->mp, bmdr); break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + rmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + dfork_min = xfs_rtrmap_broot_space(sc->mp, rmdr); + break; + case XFS_METAFILE_RTREFCOUNT: + rcdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + dfork_min = xfs_rtrefcount_broot_space(sc->mp, rcdr); + break; + default: + dfork_min = 0; + break; + } + break; default: dfork_min = 0; break; @@ -1500,8 +1661,7 @@ xrep_inode_blockcounts( trace_xrep_inode_blockcounts(sc); /* Set data fork counters from the data fork mappings. */ - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK, - &nextents, &count); + error = xchk_inode_count_blocks(sc, XFS_DATA_FORK, &nextents, &count); if (error) return error; if (xfs_is_reflink_inode(sc->ip)) { @@ -1525,8 +1685,8 @@ xrep_inode_blockcounts( /* Set attr fork counters from the attr fork mappings. */ ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK); if (ifp) { - error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK, - &nextents, &acount); + error = xchk_inode_count_blocks(sc, XFS_ATTR_FORK, &nextents, + &acount); if (error) return error; if (count >= sc->mp->m_sb.sb_dblocks) @@ -1664,10 +1824,6 @@ xrep_inode_flags( /* DAX only applies to files and dirs. */ if (!(S_ISREG(mode) || S_ISDIR(mode))) sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX; - - /* No reflink files on the realtime device. */ - if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME) - sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* @@ -1783,6 +1939,20 @@ xrep_inode_pptr( sizeof(struct xfs_attr_sf_hdr), true); } +/* Fix COW extent size hint problems. */ +STATIC void +xrep_inode_cowextsize( + struct xfs_scrub *sc) +{ + /* Fix misaligned CoW extent size hints on a directory. */ + if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (sc->ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + sc->ip->i_extsize % sc->mp->m_sb.sb_rextsize > 0) { + sc->ip->i_cowextsize = 0; + sc->ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + } +} + /* Fix any irregularities in an inode that the verifiers don't catch. */ STATIC int xrep_inode_problems( @@ -1806,6 +1976,7 @@ xrep_inode_problems( if (S_ISDIR(VFS_I(sc->ip)->i_mode)) xrep_inode_dir_size(sc); xrep_inode_extsize(sc); + xrep_inode_cowextsize(sc); trace_xrep_inode_fixed(sc); xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE); diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index b78db6513465..e21c16fbd15d 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -21,6 +21,8 @@ #include "xfs_trans_space.h" #include "xfs_attr.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -171,23 +173,13 @@ static int xchk_setup_metapath_quotadir( struct xfs_scrub *sc) { - struct xfs_trans *tp; - struct xfs_inode *dp = NULL; - int error; - - error = xfs_trans_alloc_empty(sc->mp, &tp); - if (error) - return error; + struct xfs_quotainfo *qi = sc->mp->m_quotainfo; - error = xfs_dqinode_load_parent(tp, &dp); - xfs_trans_cancel(tp); - if (error) - return error; + if (!qi || !qi->qi_dirip) + return -ENOENT; - error = xchk_setup_metapath_scan(sc, sc->mp->m_metadirip, - kasprintf(GFP_KERNEL, "quota"), dp); - xfs_irele(dp); - return error; + return xchk_setup_metapath_scan(sc, sc->mp->m_metadirip, + kstrdup("quota", GFP_KERNEL), qi->qi_dirip); } /* Scan a quota inode under the /quota directory. */ @@ -196,37 +188,31 @@ xchk_setup_metapath_dqinode( struct xfs_scrub *sc, xfs_dqtype_t type) { - struct xfs_trans *tp = NULL; - struct xfs_inode *dp = NULL; + struct xfs_quotainfo *qi = sc->mp->m_quotainfo; struct xfs_inode *ip = NULL; - const char *path; - int error; - - error = xfs_trans_alloc_empty(sc->mp, &tp); - if (error) - return error; - error = xfs_dqinode_load_parent(tp, &dp); - if (error) - goto out_cancel; - - error = xfs_dqinode_load(tp, dp, type, &ip); - if (error) - goto out_dp; - - xfs_trans_cancel(tp); - tp = NULL; + if (!qi) + return -ENOENT; - path = kasprintf(GFP_KERNEL, "%s", xfs_dqinode_path(type)); - error = xchk_setup_metapath_scan(sc, dp, path, ip); + switch (type) { + case XFS_DQTYPE_USER: + ip = qi->qi_uquotaip; + break; + case XFS_DQTYPE_GROUP: + ip = qi->qi_gquotaip; + break; + case XFS_DQTYPE_PROJ: + ip = qi->qi_pquotaip; + break; + default: + ASSERT(0); + return -EINVAL; + } + if (!ip) + return -ENOENT; - xfs_irele(ip); -out_dp: - xfs_irele(dp); -out_cancel: - if (tp) - xfs_trans_cancel(tp); - return error; + return xchk_setup_metapath_scan(sc, qi->qi_dirip, + kstrdup(xfs_dqinode_path(type), GFP_KERNEL), ip); } #else # define xchk_setup_metapath_quotadir(...) (-ENOENT) @@ -262,6 +248,10 @@ xchk_setup_metapath( return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP); case XFS_SCRUB_METAPATH_PRJQUOTA: return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ); + case XFS_SCRUB_METAPATH_RTRMAPBT: + return xchk_setup_metapath_rtginode(sc, XFS_RTGI_RMAP); + case XFS_SCRUB_METAPATH_RTREFCOUNTBT: + return xchk_setup_metapath_rtginode(sc, XFS_RTGI_REFCOUNT); default: return -ENOENT; } diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c index 70af27d98734..ac38f5843090 100644 --- a/fs/xfs/scrub/newbt.c +++ b/fs/xfs/scrub/newbt.c @@ -19,6 +19,8 @@ #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_defer.h" +#include "xfs_metafile.h" +#include "xfs_quota.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -121,6 +123,43 @@ xrep_newbt_init_inode( } /* + * Initialize accounting resources for staging a new metadata inode btree. + * If the metadata file has a space reservation, the caller must adjust that + * reservation when committing the new ondisk btree. + */ +int +xrep_newbt_init_metadir_inode( + struct xrep_newbt *xnr, + struct xfs_scrub *sc) +{ + struct xfs_owner_info oinfo; + struct xfs_ifork *ifp; + + ASSERT(xfs_is_metadir_inode(sc->ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK); + + ifp = kmem_cache_zalloc(xfs_ifork_cache, XCHK_GFP_FLAGS); + if (!ifp) + return -ENOMEM; + + /* + * Allocate new metadir btree blocks with XFS_AG_RESV_NONE because the + * inode metadata space reservations can only account allocated space + * to the i_nblocks. We do not want to change the inode core fields + * until we're ready to commit the new tree, so we allocate the blocks + * as if they were regular file blocks. This exposes us to a higher + * risk of the repair being cancelled due to ENOSPC. + */ + xrep_newbt_init_ag(xnr, sc, &oinfo, + XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino), + XFS_AG_RESV_NONE); + xnr->ifake.if_fork = ifp; + xnr->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, XFS_DATA_FORK); + return 0; +} + +/* * Initialize accounting resources for staging a new btree. Callers are * expected to add their own reservations (and clean them up) manually. */ @@ -224,6 +263,7 @@ xrep_newbt_alloc_ag_blocks( int error = 0; ASSERT(sc->sa.pag != NULL); + ASSERT(xnr->resv != XFS_AG_RESV_METAFILE); while (nr_blocks > 0) { struct xfs_alloc_arg args = { @@ -297,6 +337,8 @@ xrep_newbt_alloc_file_blocks( struct xfs_mount *mp = sc->mp; int error = 0; + ASSERT(xnr->resv != XFS_AG_RESV_METAFILE); + while (nr_blocks > 0) { struct xfs_alloc_arg args = { .tp = sc->tp, diff --git a/fs/xfs/scrub/newbt.h b/fs/xfs/scrub/newbt.h index 3d804d31af24..5ce785599287 100644 --- a/fs/xfs/scrub/newbt.h +++ b/fs/xfs/scrub/newbt.h @@ -63,6 +63,7 @@ void xrep_newbt_init_ag(struct xrep_newbt *xnr, struct xfs_scrub *sc, enum xfs_ag_resv_type resv); int xrep_newbt_init_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc, int whichfork, const struct xfs_owner_info *oinfo); +int xrep_newbt_init_metadir_inode(struct xrep_newbt *xnr, struct xfs_scrub *sc); int xrep_newbt_alloc_blocks(struct xrep_newbt *xnr, uint64_t nr_blocks); int xrep_newbt_add_extent(struct xrep_newbt *xnr, struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len); diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 183d531875ea..58d6d4ed2853 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -212,12 +212,18 @@ xchk_quota_item( if (mp->m_sb.sb_dblocks < dq->q_blk.count) xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset); + if (mp->m_sb.sb_rblocks < dq->q_rtb.count) + xchk_fblock_set_warning(sc, XFS_DATA_FORK, + offset); } else { if (mp->m_sb.sb_dblocks < dq->q_blk.count) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + if (mp->m_sb.sb_rblocks < dq->q_rtb.count) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + offset); } - if (dq->q_ino.count > fs_icount || dq->q_rtb.count > mp->m_sb.sb_rblocks) + if (dq->q_ino.count > fs_icount) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); /* diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index cd51f10f2920..8f4c8d41f308 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -233,7 +233,7 @@ xrep_quota_item( rqi->need_quotacheck = true; dirty = true; } - if (dq->q_rtb.count > mp->m_sb.sb_rblocks) { + if (!xfs_has_reflink(mp) && dq->q_rtb.count > mp->m_sb.sb_rblocks) { dq->q_rtb.reserved -= dq->q_rtb.count; dq->q_rtb.reserved += mp->m_sb.sb_rblocks; dq->q_rtb.count = mp->m_sb.sb_rblocks; diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index 08230952053b..b32fb233cf84 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -33,6 +33,9 @@ #include "xfs_attr.h" #include "xfs_attr_remote.h" #include "xfs_defer.h" +#include "xfs_metafile.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -40,6 +43,7 @@ #include "scrub/bitmap.h" #include "scrub/agb_bitmap.h" #include "scrub/fsb_bitmap.h" +#include "scrub/rtb_bitmap.h" #include "scrub/reap.h" /* @@ -310,7 +314,7 @@ xreap_agextent_binval( } out: - trace_xreap_agextent_binval(sc->sa.pag, agbno, *aglenp); + trace_xreap_agextent_binval(pag_group(sc->sa.pag), agbno, *aglenp); } /* @@ -369,7 +373,8 @@ xreap_agextent_select( out_found: *aglenp = len; - trace_xreap_agextent_select(sc->sa.pag, agbno, len, *crosslinked); + trace_xreap_agextent_select(pag_group(sc->sa.pag), agbno, len, + *crosslinked); out_cur: xfs_btree_del_cursor(cur, error); return error; @@ -390,6 +395,8 @@ xreap_agextent_iter( xfs_fsblock_t fsbno; int error = 0; + ASSERT(rs->resv != XFS_AG_RESV_METAFILE); + fsbno = xfs_agbno_to_fsb(sc->sa.pag, agbno); /* @@ -406,7 +413,8 @@ xreap_agextent_iter( * to run xfs_repair. */ if (crosslinked) { - trace_xreap_dispose_unmap_extent(sc->sa.pag, agbno, *aglenp); + trace_xreap_dispose_unmap_extent(pag_group(sc->sa.pag), agbno, + *aglenp); rs->force_roll = true; @@ -416,7 +424,8 @@ xreap_agextent_iter( * records from the refcountbt, which will remove the * rmap record as well. */ - xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp); + xfs_refcount_free_cow_extent(sc->tp, false, fsbno, + *aglenp); return 0; } @@ -424,7 +433,7 @@ xreap_agextent_iter( *aglenp, rs->oinfo); } - trace_xreap_dispose_free_extent(sc->sa.pag, agbno, *aglenp); + trace_xreap_dispose_free_extent(pag_group(sc->sa.pag), agbno, *aglenp); /* * Invalidate as many buffers as we can, starting at agbno. If this @@ -448,7 +457,7 @@ xreap_agextent_iter( if (rs->oinfo == &XFS_RMAP_OINFO_COW) { ASSERT(rs->resv == XFS_AG_RESV_NONE); - xfs_refcount_free_cow_extent(sc->tp, fsbno, *aglenp); + xfs_refcount_free_cow_extent(sc->tp, false, fsbno, *aglenp); error = xfs_free_extent_later(sc->tp, fsbno, *aglenp, NULL, rs->resv, XFS_FREE_EXTENT_SKIP_DISCARD); if (error) @@ -675,6 +684,263 @@ xrep_reap_fsblocks( return 0; } +#ifdef CONFIG_XFS_RT +/* + * Figure out the longest run of blocks that we can dispose of with a single + * call. Cross-linked blocks should have their reverse mappings removed, but + * single-owner extents can be freed. Units are rt blocks, not rt extents. + */ +STATIC int +xreap_rgextent_select( + struct xreap_state *rs, + xfs_rgblock_t rgbno, + xfs_rgblock_t rgbno_next, + bool *crosslinked, + xfs_extlen_t *rglenp) +{ + struct xfs_scrub *sc = rs->sc; + struct xfs_btree_cur *cur; + xfs_rgblock_t bno = rgbno + 1; + xfs_extlen_t len = 1; + int error; + + /* + * Determine if there are any other rmap records covering the first + * block of this extent. If so, the block is crosslinked. + */ + cur = xfs_rtrmapbt_init_cursor(sc->tp, sc->sr.rtg); + error = xfs_rmap_has_other_keys(cur, rgbno, 1, rs->oinfo, + crosslinked); + if (error) + goto out_cur; + + /* + * Figure out how many of the subsequent blocks have the same crosslink + * status. + */ + while (bno < rgbno_next) { + bool also_crosslinked; + + error = xfs_rmap_has_other_keys(cur, bno, 1, rs->oinfo, + &also_crosslinked); + if (error) + goto out_cur; + + if (*crosslinked != also_crosslinked) + break; + + len++; + bno++; + } + + *rglenp = len; + trace_xreap_agextent_select(rtg_group(sc->sr.rtg), rgbno, len, + *crosslinked); +out_cur: + xfs_btree_del_cursor(cur, error); + return error; +} + +/* + * Dispose of as much of the beginning of this rtgroup extent as possible. + * The number of blocks disposed of will be returned in @rglenp. + */ +STATIC int +xreap_rgextent_iter( + struct xreap_state *rs, + xfs_rgblock_t rgbno, + xfs_extlen_t *rglenp, + bool crosslinked) +{ + struct xfs_scrub *sc = rs->sc; + xfs_rtblock_t rtbno; + int error; + + /* + * The only caller so far is CoW fork repair, so we only know how to + * unlink or free CoW staging extents. Here we don't have to worry + * about invalidating buffers! + */ + if (rs->oinfo != &XFS_RMAP_OINFO_COW) { + ASSERT(rs->oinfo == &XFS_RMAP_OINFO_COW); + return -EFSCORRUPTED; + } + ASSERT(rs->resv == XFS_AG_RESV_NONE); + + rtbno = xfs_rgbno_to_rtb(sc->sr.rtg, rgbno); + + /* + * If there are other rmappings, this block is cross linked and must + * not be freed. Remove the forward and reverse mapping and move on. + */ + if (crosslinked) { + trace_xreap_dispose_unmap_extent(rtg_group(sc->sr.rtg), rgbno, + *rglenp); + + xfs_refcount_free_cow_extent(sc->tp, true, rtbno, *rglenp); + rs->deferred++; + return 0; + } + + trace_xreap_dispose_free_extent(rtg_group(sc->sr.rtg), rgbno, *rglenp); + + /* + * The CoW staging extent is not crosslinked. Use deferred work items + * to remove the refcountbt records (which removes the rmap records) + * and free the extent. We're not worried about the system going down + * here because log recovery walks the refcount btree to clean out the + * CoW staging extents. + */ + xfs_refcount_free_cow_extent(sc->tp, true, rtbno, *rglenp); + error = xfs_free_extent_later(sc->tp, rtbno, *rglenp, NULL, + rs->resv, + XFS_FREE_EXTENT_REALTIME | + XFS_FREE_EXTENT_SKIP_DISCARD); + if (error) + return error; + + rs->deferred++; + return 0; +} + +#define XREAP_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \ + XFS_RTGLOCK_RMAP | \ + XFS_RTGLOCK_REFCOUNT) + +/* + * Break a rt file metadata extent into sub-extents by fate (crosslinked, not + * crosslinked), and dispose of each sub-extent separately. The extent must + * be aligned to a realtime extent. + */ +STATIC int +xreap_rtmeta_extent( + uint64_t rtbno, + uint64_t len, + void *priv) +{ + struct xreap_state *rs = priv; + struct xfs_scrub *sc = rs->sc; + xfs_rgblock_t rgbno = xfs_rtb_to_rgbno(sc->mp, rtbno); + xfs_rgblock_t rgbno_next = rgbno + len; + int error = 0; + + ASSERT(sc->ip != NULL); + ASSERT(!sc->sr.rtg); + + /* + * We're reaping blocks after repairing file metadata, which means that + * we have to init the xchk_ag structure ourselves. + */ + sc->sr.rtg = xfs_rtgroup_get(sc->mp, xfs_rtb_to_rgno(sc->mp, rtbno)); + if (!sc->sr.rtg) + return -EFSCORRUPTED; + + xfs_rtgroup_lock(sc->sr.rtg, XREAP_RTGLOCK_ALL); + + while (rgbno < rgbno_next) { + xfs_extlen_t rglen; + bool crosslinked; + + error = xreap_rgextent_select(rs, rgbno, rgbno_next, + &crosslinked, &rglen); + if (error) + goto out_unlock; + + error = xreap_rgextent_iter(rs, rgbno, &rglen, crosslinked); + if (error) + goto out_unlock; + + if (xreap_want_defer_finish(rs)) { + error = xfs_defer_finish(&sc->tp); + if (error) + goto out_unlock; + xreap_defer_finish_reset(rs); + } else if (xreap_want_roll(rs)) { + error = xfs_trans_roll_inode(&sc->tp, sc->ip); + if (error) + goto out_unlock; + xreap_reset(rs); + } + + rgbno += rglen; + } + +out_unlock: + xfs_rtgroup_unlock(sc->sr.rtg, XREAP_RTGLOCK_ALL); + xfs_rtgroup_put(sc->sr.rtg); + sc->sr.rtg = NULL; + return error; +} + +/* + * Dispose of every block of every rt metadata extent in the bitmap. + * Do not use this to dispose of the mappings in an ondisk inode fork. + */ +int +xrep_reap_rtblocks( + struct xfs_scrub *sc, + struct xrtb_bitmap *bitmap, + const struct xfs_owner_info *oinfo) +{ + struct xreap_state rs = { + .sc = sc, + .oinfo = oinfo, + .resv = XFS_AG_RESV_NONE, + }; + int error; + + ASSERT(xfs_has_rmapbt(sc->mp)); + ASSERT(sc->ip != NULL); + + error = xrtb_bitmap_walk(bitmap, xreap_rtmeta_extent, &rs); + if (error) + return error; + + if (xreap_dirty(&rs)) + return xrep_defer_finish(sc); + + return 0; +} +#endif /* CONFIG_XFS_RT */ + +/* + * Dispose of every block of an old metadata btree that used to be rooted in a + * metadata directory file. + */ +int +xrep_reap_metadir_fsblocks( + struct xfs_scrub *sc, + struct xfsb_bitmap *bitmap) +{ + /* + * Reap old metadir btree blocks with XFS_AG_RESV_NONE because the old + * blocks are no longer mapped by the inode, and inode metadata space + * reservations can only account freed space to the i_nblocks. + */ + struct xfs_owner_info oinfo; + struct xreap_state rs = { + .sc = sc, + .oinfo = &oinfo, + .resv = XFS_AG_RESV_NONE, + }; + int error; + + ASSERT(xfs_has_rmapbt(sc->mp)); + ASSERT(sc->ip != NULL); + ASSERT(xfs_is_metadir_inode(sc->ip)); + + xfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, XFS_DATA_FORK); + + error = xfsb_bitmap_walk(bitmap, xreap_fsmeta_extent, &rs); + if (error) + return error; + + if (xreap_dirty(&rs)) + return xrep_defer_finish(sc); + + return 0; +} + /* * Metadata files are not supposed to share blocks with anything else. * If blocks are shared, we remove the reverse mapping (thus reducing the @@ -729,7 +995,8 @@ xreap_bmapi_select( } imap->br_blockcount = len; - trace_xreap_bmapi_select(sc->sa.pag, agbno, len, *crosslinked); + trace_xreap_bmapi_select(pag_group(sc->sa.pag), agbno, len, + *crosslinked); out_cur: xfs_btree_del_cursor(cur, error); return error; @@ -868,7 +1135,8 @@ xreap_bmapi_binval( } out: - trace_xreap_bmapi_binval(sc->sa.pag, agbno, imap->br_blockcount); + trace_xreap_bmapi_binval(pag_group(sc->sa.pag), agbno, + imap->br_blockcount); return 0; } @@ -895,7 +1163,7 @@ xrep_reap_bmapi_iter( * anybody else who thinks they own the block, even though that * runs the risk of stale buffer warnings in the future. */ - trace_xreap_dispose_unmap_extent(sc->sa.pag, + trace_xreap_dispose_unmap_extent(pag_group(sc->sa.pag), XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock), imap->br_blockcount); @@ -918,7 +1186,7 @@ xrep_reap_bmapi_iter( * by a block starting before the first block of the extent but overlap * anyway. */ - trace_xreap_dispose_free_extent(sc->sa.pag, + trace_xreap_dispose_free_extent(pag_group(sc->sa.pag), XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock), imap->br_blockcount); diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h index 3f2f1775e29d..4c8f62701fb3 100644 --- a/fs/xfs/scrub/reap.h +++ b/fs/xfs/scrub/reap.h @@ -14,6 +14,15 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap, int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap, const struct xfs_owner_info *oinfo); int xrep_reap_ifork(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork); +int xrep_reap_metadir_fsblocks(struct xfs_scrub *sc, + struct xfsb_bitmap *bitmap); + +#ifdef CONFIG_XFS_RT +int xrep_reap_rtblocks(struct xfs_scrub *sc, struct xrtb_bitmap *bitmap, + const struct xfs_owner_info *oinfo); +#else +# define xrep_reap_rtblocks(...) (-EOPNOTSUPP) +#endif /* CONFIG_XFS_RT */ /* Buffer cache scan context. */ struct xrep_bufscan { diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 2b6be75e9424..d46528023015 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -421,7 +421,7 @@ xchk_refcount_mergeable( if (r1->rc_refcount != r2->rc_refcount) return false; if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > - MAXREFCEXTLEN) + XFS_REFC_LEN_MAX) return false; return true; @@ -491,7 +491,7 @@ xchk_refcount_xref_rmap( struct xfs_scrub *sc, xfs_filblks_t cow_blocks) { - xfs_extlen_t refcbt_blocks = 0; + xfs_filblks_t refcbt_blocks = 0; xfs_filblks_t blocks; int error; diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c index 4e572b81c986..9c8cb5332da0 100644 --- a/fs/xfs/scrub/refcount_repair.c +++ b/fs/xfs/scrub/refcount_repair.c @@ -183,13 +183,13 @@ xrep_refc_stash( if (xchk_should_terminate(sc, &error)) return error; - irec.rc_refcount = min_t(uint64_t, MAXREFCOUNT, refcount); + irec.rc_refcount = min_t(uint64_t, XFS_REFC_REFCOUNT_MAX, refcount); error = xrep_refc_check_ext(rr->sc, &irec); if (error) return error; - trace_xrep_refc_found(sc->sa.pag, &irec); + trace_xrep_refc_found(pag_group(sc->sa.pag), &irec); return xfarray_append(rr->refcount_records, &irec); } @@ -422,7 +422,7 @@ xrep_refc_find_refcounts( /* * Set up a bag to store all the rmap records that we're tracking to * generate a reference count record. If the size of the bag exceeds - * MAXREFCOUNT, we clamp rc_refcount. + * XFS_REFC_REFCOUNT_MAX, we clamp rc_refcount. */ error = rcbag_init(sc->mp, sc->xmbtp, &rcstack); if (error) diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 91c8bc055a4f..3b5288d3ef4e 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -37,6 +37,12 @@ #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_dir2.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_rtalloc.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -62,6 +68,7 @@ xrep_attempt( trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error); xchk_ag_btcur_free(&sc->sa); + xchk_rtgroup_btcur_free(&sc->sr); /* Repair whatever's broken. */ ASSERT(sc->ops->repair); @@ -378,6 +385,41 @@ xrep_calc_ag_resblks( return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz)); } +#ifdef CONFIG_XFS_RT +/* + * Figure out how many blocks to reserve for a rtgroup repair. We calculate + * the worst case estimate for the number of blocks we'd need to rebuild one of + * any type of per-rtgroup btree. + */ +xfs_extlen_t +xrep_calc_rtgroup_resblks( + struct xfs_scrub *sc) +{ + struct xfs_mount *mp = sc->mp; + struct xfs_scrub_metadata *sm = sc->sm; + uint64_t usedlen; + xfs_extlen_t rmapbt_sz = 0; + + if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) + return 0; + if (!xfs_has_rtgroups(mp)) { + ASSERT(0); + return -EFSCORRUPTED; + } + + usedlen = xfs_rtbxlen_to_blen(mp, xfs_rtgroup_extents(mp, sm->sm_agno)); + ASSERT(usedlen <= XFS_MAX_RGBLOCKS); + + if (xfs_has_rmapbt(mp)) + rmapbt_sz = xfs_rtrmapbt_calc_size(mp, usedlen); + + trace_xrep_calc_rtgroup_resblks_btsize(mp, sm->sm_agno, usedlen, + rmapbt_sz); + + return rmapbt_sz; +} +#endif /* CONFIG_XFS_RT */ + /* * Reconstructing per-AG Btrees * @@ -954,6 +996,27 @@ xrep_ag_init( } #ifdef CONFIG_XFS_RT +/* Initialize all the btree cursors for a RT repair. */ +void +xrep_rtgroup_btcur_init( + struct xfs_scrub *sc, + struct xchk_rt *sr) +{ + struct xfs_mount *mp = sc->mp; + + ASSERT(sr->rtg != NULL); + + if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTRMAPBT && + (sr->rtlock_flags & XFS_RTGLOCK_RMAP) && + xfs_has_rtrmapbt(mp)) + sr->rmap_cur = xfs_rtrmapbt_init_cursor(sc->tp, sr->rtg); + + if (sc->sm->sm_type != XFS_SCRUB_TYPE_RTREFCBT && + (sr->rtlock_flags & XFS_RTGLOCK_REFCOUNT) && + xfs_has_rtreflink(mp)) + sr->refc_cur = xfs_rtrefcountbt_init_cursor(sc->tp, sr->rtg); +} + /* * Given a reference to a rtgroup structure, lock rtgroup btree inodes and * create btree cursors. Must only be called to repair a regular rt file. @@ -972,6 +1035,33 @@ xrep_rtgroup_init( /* Grab our own passive reference from the caller's ref. */ sr->rtg = xfs_rtgroup_hold(rtg); + xrep_rtgroup_btcur_init(sc, sr); + return 0; +} + +/* Ensure that all rt blocks in the given range are not marked free. */ +int +xrep_require_rtext_inuse( + struct xfs_scrub *sc, + xfs_rgblock_t rgbno, + xfs_filblks_t len) +{ + struct xfs_mount *mp = sc->mp; + xfs_rtxnum_t startrtx; + xfs_rtxnum_t endrtx; + bool is_free = false; + int error; + + startrtx = xfs_rgbno_to_rtx(mp, rgbno); + endrtx = xfs_rgbno_to_rtx(mp, rgbno + len - 1); + + error = xfs_rtalloc_extent_is_free(sc->sr.rtg, sc->tp, startrtx, + endrtx - startrtx + 1, &is_free); + if (error) + return error; + if (is_free) + return -EFSCORRUPTED; + return 0; } #endif /* CONFIG_XFS_RT */ @@ -1237,3 +1327,110 @@ xrep_buf_verify_struct( return fa == NULL; } + +/* Check the sanity of a rmap record for a metadata btree inode. */ +int +xrep_check_ino_btree_mapping( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec) +{ + enum xbtree_recpacking outcome; + int error; + + /* + * Metadata btree inodes never have extended attributes, and all blocks + * should have the bmbt block flag set. + */ + if ((rec->rm_flags & XFS_RMAP_ATTR_FORK) || + !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK)) + return -EFSCORRUPTED; + + /* Make sure the block is within the AG. */ + if (!xfs_verify_agbext(sc->sa.pag, rec->rm_startblock, + rec->rm_blockcount)) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock, + rec->rm_blockcount, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + + return 0; +} + +/* + * Reset the block count of the inode being repaired, and adjust the dquot + * block usage to match. The inode must not have an xattr fork. + */ +void +xrep_inode_set_nblocks( + struct xfs_scrub *sc, + int64_t new_blocks) +{ + int64_t delta = + new_blocks - sc->ip->i_nblocks; + + sc->ip->i_nblocks = new_blocks; + + xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE); + if (delta != 0) + xfs_trans_mod_dquot_byino(sc->tp, sc->ip, XFS_TRANS_DQ_BCOUNT, + delta); +} + +/* Reset the block reservation for a metadata inode. */ +int +xrep_reset_metafile_resv( + struct xfs_scrub *sc) +{ + struct xfs_inode *ip = sc->ip; + int64_t delta; + int error; + + delta = ip->i_nblocks + ip->i_delayed_blks - ip->i_meta_resv_asked; + if (delta == 0) + return 0; + + /* + * Too many blocks have been reserved, transfer some from the incore + * reservation back to the filesystem. + */ + if (delta > 0) { + int64_t give_back; + + give_back = min_t(uint64_t, delta, ip->i_delayed_blks); + if (give_back > 0) { + xfs_mod_delalloc(ip, 0, -give_back); + xfs_add_fdblocks(ip->i_mount, give_back); + ip->i_delayed_blks -= give_back; + } + + return 0; + } + + /* + * Not enough reservation; try to take some blocks from the filesystem + * to the metadata inode. @delta is negative here, so invert the sign. + */ + delta = -delta; + error = xfs_dec_fdblocks(sc->mp, delta, true); + while (error == -ENOSPC) { + delta--; + if (delta == 0) { + xfs_warn(sc->mp, +"Insufficient free space to reset space reservation for inode 0x%llx after repair.", + ip->i_ino); + return 0; + } + error = xfs_dec_fdblocks(sc->mp, delta, true); + } + if (error) + return error; + + xfs_mod_delalloc(ip, 0, delta); + ip->i_delayed_blks += delta; + return 0; +} diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index b649da1a93eb..823c00d1a502 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -50,7 +50,9 @@ xrep_trans_commit( struct xbitmap; struct xagb_bitmap; +struct xrgb_bitmap; struct xfsb_bitmap; +struct xrtb_bitmap; int xrep_fix_freelist(struct xfs_scrub *sc, int alloc_flags); @@ -97,6 +99,8 @@ int xrep_setup_parent(struct xfs_scrub *sc); int xrep_setup_nlinks(struct xfs_scrub *sc); int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *resblks); int xrep_setup_dirtree(struct xfs_scrub *sc); +int xrep_setup_rtrmapbt(struct xfs_scrub *sc); +int xrep_setup_rtrefcountbt(struct xfs_scrub *sc); /* Repair setup functions */ int xrep_setup_ag_allocbt(struct xfs_scrub *sc); @@ -110,10 +114,18 @@ int xrep_ag_init(struct xfs_scrub *sc, struct xfs_perag *pag, #ifdef CONFIG_XFS_RT int xrep_rtgroup_init(struct xfs_scrub *sc, struct xfs_rtgroup *rtg, struct xchk_rt *sr, unsigned int rtglock_flags); +void xrep_rtgroup_btcur_init(struct xfs_scrub *sc, struct xchk_rt *sr); +int xrep_require_rtext_inuse(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_filblks_t len); +xfs_extlen_t xrep_calc_rtgroup_resblks(struct xfs_scrub *sc); #else # define xrep_rtgroup_init(sc, rtg, sr, lockflags) (-ENOSYS) +# define xrep_calc_rtgroup_resblks(sc) (0) #endif /* CONFIG_XFS_RT */ +int xrep_check_ino_btree_mapping(struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec); + /* Metadata revalidators */ int xrep_revalidate_allocbt(struct xfs_scrub *sc); @@ -147,10 +159,14 @@ int xrep_metapath(struct xfs_scrub *sc); int xrep_rtbitmap(struct xfs_scrub *sc); int xrep_rtsummary(struct xfs_scrub *sc); int xrep_rgsuperblock(struct xfs_scrub *sc); +int xrep_rtrmapbt(struct xfs_scrub *sc); +int xrep_rtrefcountbt(struct xfs_scrub *sc); #else # define xrep_rtbitmap xrep_notsupported # define xrep_rtsummary xrep_notsupported # define xrep_rgsuperblock xrep_notsupported +# define xrep_rtrmapbt xrep_notsupported +# define xrep_rtrefcountbt xrep_notsupported #endif /* CONFIG_XFS_RT */ #ifdef CONFIG_XFS_QUOTA @@ -169,6 +185,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep, void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp); bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops); +void xrep_inode_set_nblocks(struct xfs_scrub *sc, int64_t new_blocks); +int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else @@ -192,6 +210,8 @@ xrep_calc_ag_resblks( return 0; } +#define xrep_calc_rtgroup_resblks xrep_calc_ag_resblks + static inline int xrep_reset_perag_resv( struct xfs_scrub *sc) @@ -219,6 +239,8 @@ xrep_setup_nothing( #define xrep_setup_nlinks xrep_setup_nothing #define xrep_setup_dirtree xrep_setup_nothing #define xrep_setup_metapath xrep_setup_nothing +#define xrep_setup_rtrmapbt xrep_setup_nothing +#define xrep_setup_rtrefcountbt xrep_setup_nothing #define xrep_setup_inode(sc, imap) ((void)0) @@ -256,6 +278,8 @@ static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x) #define xrep_dirtree xrep_notsupported #define xrep_metapath xrep_notsupported #define xrep_rgsuperblock xrep_notsupported +#define xrep_rtrmapbt xrep_notsupported +#define xrep_rtrefcountbt xrep_notsupported #endif /* CONFIG_XFS_ONLINE_REPAIR */ diff --git a/fs/xfs/scrub/rgb_bitmap.h b/fs/xfs/scrub/rgb_bitmap.h new file mode 100644 index 000000000000..4c3126b66dcb --- /dev/null +++ b/fs/xfs/scrub/rgb_bitmap.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_SCRUB_RGB_BITMAP_H__ +#define __XFS_SCRUB_RGB_BITMAP_H__ + +/* Bitmaps, but for type-checked for xfs_rgblock_t */ + +struct xrgb_bitmap { + struct xbitmap32 rgbitmap; +}; + +static inline void xrgb_bitmap_init(struct xrgb_bitmap *bitmap) +{ + xbitmap32_init(&bitmap->rgbitmap); +} + +static inline void xrgb_bitmap_destroy(struct xrgb_bitmap *bitmap) +{ + xbitmap32_destroy(&bitmap->rgbitmap); +} + +static inline int xrgb_bitmap_set(struct xrgb_bitmap *bitmap, + xfs_rgblock_t start, xfs_extlen_t len) +{ + return xbitmap32_set(&bitmap->rgbitmap, start, len); +} + +static inline int xrgb_bitmap_walk(struct xrgb_bitmap *bitmap, + xbitmap32_walk_fn fn, void *priv) +{ + return xbitmap32_walk(&bitmap->rgbitmap, fn, priv); +} + +#endif /* __XFS_SCRUB_RGB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 463b3573bb76..d189732d0e24 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -13,6 +13,7 @@ #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_sb.h" +#include "xfs_rmap.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" @@ -34,6 +35,7 @@ xchk_rgsuperblock_xref( return; xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1); + xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS); } int @@ -61,7 +63,9 @@ xchk_rgsuperblock( if (!xchk_xref_process_error(sc, 0, 0, &error)) return error; - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP_SHARED); + if (error) + return error; /* * Since we already validated the rt superblock at mount time, we don't diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c index a0a227d183d2..f5f73078ffe2 100644 --- a/fs/xfs/scrub/rmap_repair.c +++ b/fs/xfs/scrub/rmap_repair.c @@ -31,6 +31,9 @@ #include "xfs_refcount.h" #include "xfs_refcount_btree.h" #include "xfs_ag.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" @@ -499,6 +502,69 @@ xrep_rmap_scan_iext( return xrep_rmap_stash_accumulated(rf); } +static int +xrep_rmap_scan_meta_btree( + struct xrep_rmap_ifork *rf, + struct xfs_inode *ip) +{ + struct xfs_scrub *sc = rf->rr->sc; + struct xfs_rtgroup *rtg = NULL; + struct xfs_btree_cur *cur = NULL; + enum xfs_rtg_inodes type; + int error; + + if (rf->whichfork != XFS_DATA_FORK) + return -EFSCORRUPTED; + + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + type = XFS_RTGI_RMAP; + break; + case XFS_METAFILE_RTREFCOUNT: + type = XFS_RTGI_REFCOUNT; + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + while ((rtg = xfs_rtgroup_next(sc->mp, rtg))) { + if (ip == rtg->rtg_inodes[type]) + goto found; + } + + /* + * We should never find an rt metadata btree inode that isn't + * associated with an rtgroup yet has ondisk blocks allocated to it. + */ + if (ip->i_nblocks) { + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; + +found: + switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + cur = xfs_rtrmapbt_init_cursor(sc->tp, rtg); + break; + case XFS_METAFILE_RTREFCOUNT: + cur = xfs_rtrefcountbt_init_cursor(sc->tp, rtg); + break; + default: + ASSERT(0); + error = -EFSCORRUPTED; + goto out_rtg; + } + + error = xrep_rmap_scan_iroot_btree(rf, cur); + xfs_btree_del_cursor(cur, error); +out_rtg: + xfs_rtgroup_rele(rtg); + return error; +} + /* Find all the extents from a given AG in an inode fork. */ STATIC int xrep_rmap_scan_ifork( @@ -512,14 +578,14 @@ xrep_rmap_scan_ifork( .whichfork = whichfork, }; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + bool mappings_done; int error = 0; if (!ifp) return 0; - if (ifp->if_format == XFS_DINODE_FMT_BTREE) { - bool mappings_done; - + switch (ifp->if_format) { + case XFS_DINODE_FMT_BTREE: /* * Scan the bmap btree for data device mappings. This includes * the btree blocks themselves, even if this is a realtime @@ -528,15 +594,18 @@ xrep_rmap_scan_ifork( error = xrep_rmap_scan_bmbt(&rf, ip, &mappings_done); if (error || mappings_done) return error; - } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { - return 0; + fallthrough; + case XFS_DINODE_FMT_EXTENTS: + /* Scan incore extent cache if this isn't a realtime file. */ + if (xfs_ifork_is_realtime(ip, whichfork)) + return 0; + + return xrep_rmap_scan_iext(&rf, ifp); + case XFS_DINODE_FMT_META_BTREE: + return xrep_rmap_scan_meta_btree(&rf, ip); } - /* Scan incore extent cache if this isn't a realtime file. */ - if (xfs_ifork_is_realtime(ip, whichfork)) - return 0; - - return xrep_rmap_scan_iext(&rf, ifp); + return 0; } /* @@ -1552,7 +1621,7 @@ xrep_rmapbt_live_update( if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo)) goto out_unlock; - trace_xrep_rmap_live_update(rr->sc->sa.pag, action, p); + trace_xrep_rmap_live_update(pag_group(rr->sc->sa.pag), action, p); error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp); if (error) diff --git a/fs/xfs/scrub/rtb_bitmap.h b/fs/xfs/scrub/rtb_bitmap.h new file mode 100644 index 000000000000..1313ef605511 --- /dev/null +++ b/fs/xfs/scrub/rtb_bitmap.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2022-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_SCRUB_RTB_BITMAP_H__ +#define __XFS_SCRUB_RTB_BITMAP_H__ + +/* Bitmaps, but for type-checked for xfs_rtblock_t */ + +struct xrtb_bitmap { + struct xbitmap64 rtbitmap; +}; + +static inline void xrtb_bitmap_init(struct xrtb_bitmap *bitmap) +{ + xbitmap64_init(&bitmap->rtbitmap); +} + +static inline void xrtb_bitmap_destroy(struct xrtb_bitmap *bitmap) +{ + xbitmap64_destroy(&bitmap->rtbitmap); +} + +static inline int xrtb_bitmap_set(struct xrtb_bitmap *bitmap, + xfs_rtblock_t start, xfs_filblks_t len) +{ + return xbitmap64_set(&bitmap->rtbitmap, start, len); +} + +static inline int xrtb_bitmap_walk(struct xrtb_bitmap *bitmap, + xbitmap64_walk_fn fn, void *priv) +{ + return xbitmap64_walk(&bitmap->rtbitmap, fn, priv); +} + +#endif /* __XFS_SCRUB_RTB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 376a36fd9a9c..e8c776a34c1d 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -9,17 +9,24 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" +#include "xfs_btree.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_rtbitmap.h" #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_bit.h" +#include "xfs_rtgroup.h" #include "xfs_sb.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_exchmaps.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" +#include "scrub/tempexch.h" #include "scrub/rtbitmap.h" +#include "scrub/btree.h" /* Set us up with the realtime metadata locked. */ int @@ -30,10 +37,15 @@ xchk_setup_rtbitmap( struct xchk_rtbitmap *rtb; int error; - rtb = kzalloc(sizeof(struct xchk_rtbitmap), XCHK_GFP_FLAGS); + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + rtb = kzalloc(struct_size(rtb, words, xchk_rtbitmap_wordcnt(sc)), + XCHK_GFP_FLAGS); if (!rtb) return -ENOMEM; sc->buf = rtb; + rtb->sc = sc; error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); if (error) @@ -49,8 +61,7 @@ xchk_setup_rtbitmap( if (error) return error; - error = xchk_install_live_inode(sc, - sc->sr.rtg->rtg_inodes[XFS_RTGI_BITMAP]); + error = xchk_install_live_inode(sc, rtg_bitmap(sc->sr.rtg)); if (error) return error; @@ -58,12 +69,15 @@ xchk_setup_rtbitmap( if (error) return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); + if (error) + return error; + /* * Now that we've locked the rtbitmap, we can't race with growfsrt * trying to expand the bitmap or change the size of the rt volume. * Hence it is safe to compute and check the geometry values. */ - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP); if (mp->m_sb.sb_rblocks) { rtb->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks); rtb->rextslog = xfs_compute_rextslog(rtb->rextents); @@ -73,7 +87,32 @@ xchk_setup_rtbitmap( return 0; } -/* Realtime bitmap. */ +/* Per-rtgroup bitmap contents. */ + +/* Cross-reference rtbitmap entries with other metadata. */ +STATIC void +xchk_rtbitmap_xref( + struct xchk_rtbitmap *rtb, + xfs_rtblock_t startblock, + xfs_rtblock_t blockcount) +{ + struct xfs_scrub *sc = rtb->sc; + xfs_rgblock_t rgbno = xfs_rtb_to_rgbno(sc->mp, startblock); + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + if (!sc->sr.rmap_cur) + return; + + xchk_xref_has_no_rt_owner(sc, rgbno, blockcount); + xchk_xref_is_not_rt_shared(sc, rgbno, blockcount); + xchk_xref_is_not_rt_cow_staging(sc, rgbno, blockcount); + + if (rtb->next_free_rgbno < rgbno) + xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, + rgbno - rtb->next_free_rgbno); + rtb->next_free_rgbno = rgbno + blockcount; +} /* Scrub a free extent record from the realtime bitmap. */ STATIC int @@ -83,7 +122,8 @@ xchk_rtbitmap_rec( const struct xfs_rtalloc_rec *rec, void *priv) { - struct xfs_scrub *sc = priv; + struct xchk_rtbitmap *rtb = priv; + struct xfs_scrub *sc = rtb->sc; xfs_rtblock_t startblock; xfs_filblks_t blockcount; @@ -92,6 +132,12 @@ xchk_rtbitmap_rec( if (!xfs_verify_rtbext(rtg_mount(rtg), startblock, blockcount)) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); + + xchk_rtbitmap_xref(rtb, startblock, blockcount); + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return -ECANCELED; + return 0; } @@ -139,15 +185,16 @@ xchk_rtbitmap_check_extents( return error; } -/* Scrub the realtime bitmap. */ +/* Scrub this group's realtime bitmap. */ int xchk_rtbitmap( struct xfs_scrub *sc) { struct xfs_mount *mp = sc->mp; struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xchk_rtbitmap *rtb = sc->buf; + xfs_rgblock_t last_rgbno; int error; /* Is sb_rextents correct? */ @@ -200,10 +247,20 @@ xchk_rtbitmap( if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) return error; - error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, sc); + rtb->next_free_rgbno = 0; + error = xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtbitmap_rec, rtb); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) return error; + /* + * Check that the are rmappings for all rt extents between the end of + * the last free extent we saw and the last possible extent in the rt + * group. + */ + last_rgbno = rtg->rtg_extents * mp->m_sb.sb_rextsize - 1; + if (rtb->next_free_rgbno < last_rgbno) + xchk_xref_has_rt_owner(sc, rtb->next_free_rgbno, + last_rgbno - rtb->next_free_rgbno); return 0; } @@ -215,7 +272,7 @@ xchk_xref_is_used_rt_space( xfs_extlen_t len) { struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); xfs_rtxnum_t startext; xfs_rtxnum_t endext; bool is_free; diff --git a/fs/xfs/scrub/rtbitmap.h b/fs/xfs/scrub/rtbitmap.h index 85304ff019e1..fe52b877253d 100644 --- a/fs/xfs/scrub/rtbitmap.h +++ b/fs/xfs/scrub/rtbitmap.h @@ -6,17 +6,72 @@ #ifndef __XFS_SCRUB_RTBITMAP_H__ #define __XFS_SCRUB_RTBITMAP_H__ +/* + * We use an xfile to construct new bitmap blocks for the portion of the + * rtbitmap file that we're replacing. Whereas the ondisk bitmap must be + * accessed through the buffer cache, the xfile bitmap supports direct + * word-level accesses. Therefore, we create a small abstraction for linear + * access. + */ +typedef unsigned long long xrep_wordoff_t; +typedef unsigned int xrep_wordcnt_t; + +/* Mask to round an rtx down to the nearest bitmap word. */ +#define XREP_RTBMP_WORDMASK ((1ULL << XFS_NBWORDLOG) - 1) + + struct xchk_rtbitmap { + struct xfs_scrub *sc; + uint64_t rextents; uint64_t rbmblocks; unsigned int rextslog; unsigned int resblks; + + /* The next free rt group block number that we expect to see. */ + xfs_rgblock_t next_free_rgbno; + +#ifdef CONFIG_XFS_ONLINE_REPAIR + /* stuff for staging a new bitmap */ + struct xfs_rtalloc_args args; + struct xrep_tempexch tempexch; +#endif + + /* The next rtgroup block we expect to see during our rtrmapbt walk. */ + xfs_rgblock_t next_rgbno; + + /* rtgroup lock flags */ + unsigned int rtglock_flags; + + /* rtword position of xfile as we write buffers to disk. */ + xrep_wordoff_t prep_wordoff; + + /* In-Memory rtbitmap for repair. */ + union xfs_rtword_raw words[]; }; #ifdef CONFIG_XFS_ONLINE_REPAIR int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb); + +/* + * How big should the words[] buffer be? + * + * For repairs, we want a full fsblock worth of space so that we can memcpy a + * buffer full of 1s into the xfile bitmap. The xfile bitmap doesn't have + * rtbitmap block headers, so we don't use blockwsize. Scrub doesn't use the + * words buffer at all. + */ +static inline unsigned int +xchk_rtbitmap_wordcnt( + struct xfs_scrub *sc) +{ + if (xchk_could_repair(sc)) + return sc->mp->m_sb.sb_blocksize >> XFS_WORDLOG; + return 0; +} #else # define xrep_setup_rtbitmap(sc, rtb) (0) +# define xchk_rtbitmap_wordcnt(sc) (0) #endif /* CONFIG_XFS_ONLINE_REPAIR */ #endif /* __XFS_SCRUB_RTBITMAP_H__ */ diff --git a/fs/xfs/scrub/rtbitmap_repair.c b/fs/xfs/scrub/rtbitmap_repair.c index 0fef98e9f834..203a1a97c502 100644 --- a/fs/xfs/scrub/rtbitmap_repair.c +++ b/fs/xfs/scrub/rtbitmap_repair.c @@ -12,32 +12,66 @@ #include "xfs_btree.h" #include "xfs_log_format.h" #include "xfs_trans.h" +#include "xfs_rtalloc.h" #include "xfs_inode.h" #include "xfs_bit.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" +#include "xfs_rmap.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_exchmaps.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_extent_busy.h" +#include "xfs_refcount.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" #include "scrub/repair.h" #include "scrub/xfile.h" +#include "scrub/tempfile.h" +#include "scrub/tempexch.h" +#include "scrub/reap.h" #include "scrub/rtbitmap.h" -/* Set up to repair the realtime bitmap file metadata. */ +/* rt bitmap content repairs */ + +/* Set up to repair the realtime bitmap for this group. */ int xrep_setup_rtbitmap( struct xfs_scrub *sc, struct xchk_rtbitmap *rtb) { struct xfs_mount *mp = sc->mp; - unsigned long long blocks = 0; + char *descr; + unsigned long long blocks = mp->m_sb.sb_rbmblocks; + int error; + + error = xrep_tempfile_create(sc, S_IFREG); + if (error) + return error; + + /* Create an xfile to hold our reconstructed bitmap. */ + descr = xchk_xfile_rtgroup_descr(sc, "bitmap file"); + error = xfile_create(descr, blocks * mp->m_sb.sb_blocksize, &sc->xfile); + kfree(descr); + if (error) + return error; /* - * Reserve enough blocks to write out a completely new bmbt for a - * maximally fragmented bitmap file. We do not hold the rtbitmap - * ILOCK yet, so this is entirely speculative. + * Reserve enough blocks to write out a completely new bitmap file, + * plus twice as many blocks as we would need if we can only allocate + * one block per data fork mapping. This should cover the + * preallocation of the temporary file and exchanging the extent + * mappings. + * + * We cannot use xfs_exchmaps_estimate because we have not yet + * constructed the replacement bitmap and therefore do not know how + * many extents it will use. By the time we do, we will have a dirty + * transaction (which we cannot drop because we cannot drop the + * rtbitmap ILOCK) and cannot ask for more reservation. */ - blocks = xfs_bmbt_calc_size(mp, mp->m_sb.sb_rbmblocks); + blocks += xfs_bmbt_calc_size(mp, blocks) * 2; if (blocks > UINT_MAX) return -EOPNOTSUPP; @@ -45,6 +79,325 @@ xrep_setup_rtbitmap( return 0; } +static inline xrep_wordoff_t +rtx_to_wordoff( + struct xfs_mount *mp, + xfs_rtxnum_t rtx) +{ + return rtx >> XFS_NBWORDLOG; +} + +static inline xrep_wordcnt_t +rtxlen_to_wordcnt( + xfs_rtxlen_t rtxlen) +{ + return rtxlen >> XFS_NBWORDLOG; +} + +/* Helper functions to record rtwords in an xfile. */ + +static inline int +xfbmp_load( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + xfs_rtword_t *word) +{ + union xfs_rtword_raw urk; + int error; + + ASSERT(xfs_has_rtgroups(rtb->sc->mp)); + + error = xfile_load(rtb->sc->xfile, &urk, + sizeof(union xfs_rtword_raw), + wordoff << XFS_WORDLOG); + if (error) + return error; + + *word = be32_to_cpu(urk.rtg); + return 0; +} + +static inline int +xfbmp_store( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + const xfs_rtword_t word) +{ + union xfs_rtword_raw urk; + + ASSERT(xfs_has_rtgroups(rtb->sc->mp)); + + urk.rtg = cpu_to_be32(word); + return xfile_store(rtb->sc->xfile, &urk, + sizeof(union xfs_rtword_raw), + wordoff << XFS_WORDLOG); +} + +static inline int +xfbmp_copyin( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + const union xfs_rtword_raw *word, + xrep_wordcnt_t nr_words) +{ + return xfile_store(rtb->sc->xfile, word, nr_words << XFS_WORDLOG, + wordoff << XFS_WORDLOG); +} + +static inline int +xfbmp_copyout( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + union xfs_rtword_raw *word, + xrep_wordcnt_t nr_words) +{ + return xfile_load(rtb->sc->xfile, word, nr_words << XFS_WORDLOG, + wordoff << XFS_WORDLOG); +} + +/* Perform a logical OR operation on an rtword in the incore bitmap. */ +static int +xrep_rtbitmap_or( + struct xchk_rtbitmap *rtb, + xrep_wordoff_t wordoff, + xfs_rtword_t mask) +{ + xfs_rtword_t word; + int error; + + error = xfbmp_load(rtb, wordoff, &word); + if (error) + return error; + + trace_xrep_rtbitmap_or(rtb->sc->mp, wordoff, mask, word); + + return xfbmp_store(rtb, wordoff, word | mask); +} + +/* + * Mark as free every rt extent between the next rt block we expected to see + * in the rtrmap records and the given rt block. + */ +STATIC int +xrep_rtbitmap_mark_free( + struct xchk_rtbitmap *rtb, + xfs_rgblock_t rgbno) +{ + struct xfs_mount *mp = rtb->sc->mp; + struct xchk_rt *sr = &rtb->sc->sr; + struct xfs_rtgroup *rtg = sr->rtg; + xfs_rtxnum_t startrtx; + xfs_rtxnum_t nextrtx; + xrep_wordoff_t wordoff, nextwordoff; + unsigned int bit; + unsigned int bufwsize; + xfs_extlen_t mod; + xfs_rtword_t mask; + enum xbtree_recpacking outcome; + int error; + + if (!xfs_verify_rgbext(rtg, rtb->next_rgbno, rgbno - rtb->next_rgbno)) + return -EFSCORRUPTED; + + /* + * Convert rt blocks to rt extents The block range we find must be + * aligned to an rtextent boundary on both ends. + */ + startrtx = xfs_rgbno_to_rtx(mp, rtb->next_rgbno); + mod = xfs_rgbno_to_rtxoff(mp, rtb->next_rgbno); + if (mod) + return -EFSCORRUPTED; + + nextrtx = xfs_rgbno_to_rtx(mp, rgbno - 1) + 1; + mod = xfs_rgbno_to_rtxoff(mp, rgbno - 1); + if (mod != mp->m_sb.sb_rextsize - 1) + return -EFSCORRUPTED; + + /* Must not be shared or CoW staging. */ + if (sr->refc_cur) { + error = xfs_refcount_has_records(sr->refc_cur, + XFS_REFC_DOMAIN_SHARED, rtb->next_rgbno, + rgbno - rtb->next_rgbno, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + + error = xfs_refcount_has_records(sr->refc_cur, + XFS_REFC_DOMAIN_COW, rtb->next_rgbno, + rgbno - rtb->next_rgbno, &outcome); + if (error) + return error; + if (outcome != XBTREE_RECPACKING_EMPTY) + return -EFSCORRUPTED; + } + + trace_xrep_rtbitmap_record_free(mp, startrtx, nextrtx - 1); + + /* Set bits as needed to round startrtx up to the nearest word. */ + bit = startrtx & XREP_RTBMP_WORDMASK; + if (bit) { + xfs_rtblock_t len = nextrtx - startrtx; + unsigned int lastbit; + + lastbit = min(bit + len, XFS_NBWORD); + mask = (((xfs_rtword_t)1 << (lastbit - bit)) - 1) << bit; + + error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, startrtx), + mask); + if (error || lastbit - bit == len) + return error; + startrtx += XFS_NBWORD - bit; + } + + /* Set bits as needed to round nextrtx down to the nearest word. */ + bit = nextrtx & XREP_RTBMP_WORDMASK; + if (bit) { + mask = ((xfs_rtword_t)1 << bit) - 1; + + error = xrep_rtbitmap_or(rtb, rtx_to_wordoff(mp, nextrtx), + mask); + if (error || startrtx + bit == nextrtx) + return error; + nextrtx -= bit; + } + + trace_xrep_rtbitmap_record_free_bulk(mp, startrtx, nextrtx - 1); + + /* Set all the words in between, up to a whole fs block at once. */ + wordoff = rtx_to_wordoff(mp, startrtx); + nextwordoff = rtx_to_wordoff(mp, nextrtx); + bufwsize = mp->m_sb.sb_blocksize >> XFS_WORDLOG; + + while (wordoff < nextwordoff) { + xrep_wordoff_t rem; + xrep_wordcnt_t wordcnt; + + wordcnt = min_t(xrep_wordcnt_t, nextwordoff - wordoff, + bufwsize); + + /* + * Try to keep us aligned to the rtwords buffer to reduce the + * number of xfile writes. + */ + rem = wordoff & (bufwsize - 1); + if (rem) + wordcnt = min_t(xrep_wordcnt_t, wordcnt, + bufwsize - rem); + + error = xfbmp_copyin(rtb, wordoff, rtb->words, wordcnt); + if (error) + return error; + + wordoff += wordcnt; + } + + return 0; +} + +/* Set free space in the rtbitmap based on rtrmapbt records. */ +STATIC int +xrep_rtbitmap_walk_rtrmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xchk_rtbitmap *rtb = priv; + int error = 0; + + if (xchk_should_terminate(rtb->sc, &error)) + return error; + + if (rtb->next_rgbno < rec->rm_startblock) { + error = xrep_rtbitmap_mark_free(rtb, rec->rm_startblock); + if (error) + return error; + } + + rtb->next_rgbno = max(rtb->next_rgbno, + rec->rm_startblock + rec->rm_blockcount); + return 0; +} + +/* + * Walk the rtrmapbt to find all the gaps between records, and mark the gaps + * in the realtime bitmap that we're computing. + */ +STATIC int +xrep_rtbitmap_find_freespace( + struct xchk_rtbitmap *rtb) +{ + struct xfs_scrub *sc = rtb->sc; + struct xfs_mount *mp = sc->mp; + struct xfs_rtgroup *rtg = sc->sr.rtg; + uint64_t blockcount; + int error; + + /* Prepare a buffer of ones so that we can accelerate bulk setting. */ + memset(rtb->words, 0xFF, mp->m_sb.sb_blocksize); + + xrep_rtgroup_btcur_init(sc, &sc->sr); + error = xfs_rmap_query_all(sc->sr.rmap_cur, xrep_rtbitmap_walk_rtrmap, + rtb); + if (error) + goto out; + + /* + * Mark as free every possible rt extent from the last one we saw to + * the end of the rt group. + */ + blockcount = rtg->rtg_extents * mp->m_sb.sb_rextsize; + if (rtb->next_rgbno < blockcount) { + error = xrep_rtbitmap_mark_free(rtb, blockcount); + if (error) + goto out; + } + +out: + xchk_rtgroup_btcur_free(&sc->sr); + return error; +} + +static int +xrep_rtbitmap_prep_buf( + struct xfs_scrub *sc, + struct xfs_buf *bp, + void *data) +{ + struct xchk_rtbitmap *rtb = data; + struct xfs_mount *mp = sc->mp; + union xfs_rtword_raw *ondisk; + int error; + + rtb->args.mp = sc->mp; + rtb->args.tp = sc->tp; + rtb->args.rbmbp = bp; + ondisk = xfs_rbmblock_wordptr(&rtb->args, 0); + rtb->args.rbmbp = NULL; + + error = xfbmp_copyout(rtb, rtb->prep_wordoff, ondisk, + mp->m_blockwsize); + if (error) + return error; + + if (xfs_has_rtgroups(sc->mp)) { + struct xfs_rtbuf_blkinfo *hdr = bp->b_addr; + + hdr->rt_magic = cpu_to_be32(XFS_RTBITMAP_MAGIC); + hdr->rt_owner = cpu_to_be64(sc->ip->i_ino); + hdr->rt_blkno = cpu_to_be64(xfs_buf_daddr(bp)); + hdr->rt_lsn = 0; + uuid_copy(&hdr->rt_uuid, &sc->mp->m_sb.sb_meta_uuid); + bp->b_ops = &xfs_rtbitmap_buf_ops; + } else { + bp->b_ops = &xfs_rtbuf_ops; + } + + rtb->prep_wordoff += mp->m_blockwsize; + xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTBITMAP_BUF); + return 0; +} + /* * Make sure that the given range of the data fork of the realtime file is * mapped to written blocks. The caller must ensure that the inode is joined @@ -160,9 +513,18 @@ xrep_rtbitmap( { struct xchk_rtbitmap *rtb = sc->buf; struct xfs_mount *mp = sc->mp; + struct xfs_group *xg = rtg_group(sc->sr.rtg); unsigned long long blocks = 0; + unsigned int busy_gen; int error; + /* We require the realtime rmapbt to rebuild anything. */ + if (!xfs_has_rtrmapbt(sc->mp)) + return -EOPNOTSUPP; + /* We require atomic file exchange range to rebuild anything. */ + if (!xfs_has_exchange_range(sc->mp)) + return -EOPNOTSUPP; + /* Impossibly large rtbitmap means we can't touch the filesystem. */ if (rtb->rbmblocks > U32_MAX) return 0; @@ -195,6 +557,79 @@ xrep_rtbitmap( if (error) return error; - /* Fix inconsistent bitmap geometry */ - return xrep_rtbitmap_geometry(sc, rtb); + /* + * Fix inconsistent bitmap geometry. This function returns with a + * clean scrub transaction. + */ + error = xrep_rtbitmap_geometry(sc, rtb); + if (error) + return error; + + /* + * Make sure the busy extent list is clear because we can't put extents + * on there twice. + */ + if (!xfs_extent_busy_list_empty(xg, &busy_gen)) { + error = xfs_extent_busy_flush(sc->tp, xg, busy_gen, 0); + if (error) + return error; + } + + /* + * Generate the new rtbitmap data. We don't need the rtbmp information + * once this call is finished. + */ + error = xrep_rtbitmap_find_freespace(rtb); + if (error) + return error; + + /* + * Try to take ILOCK_EXCL of the temporary file. We had better be the + * only ones holding onto this inode, but we can't block while holding + * the rtbitmap file's ILOCK_EXCL. + */ + while (!xrep_tempfile_ilock_nowait(sc)) { + if (xchk_should_terminate(sc, &error)) + return error; + delay(1); + } + + /* + * Make sure we have space allocated for the part of the bitmap + * file that corresponds to this group. We already joined sc->ip. + */ + xfs_trans_ijoin(sc->tp, sc->tempip, 0); + error = xrep_tempfile_prealloc(sc, 0, rtb->rbmblocks); + if (error) + return error; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + return error; + + /* Copy the bitmap file that we generated. */ + error = xrep_tempfile_copyin(sc, 0, rtb->rbmblocks, + xrep_rtbitmap_prep_buf, rtb); + if (error) + return error; + error = xrep_tempfile_set_isize(sc, + XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)); + if (error) + return error; + + /* + * Now exchange the data fork contents. We're done with the temporary + * buffer, so we can reuse it for the tempfile exchmaps information. + */ + error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, + rtb->rbmblocks, &rtb->tempexch); + if (error) + return error; + + error = xrep_tempexch_contents(sc, &rtb->tempexch); + if (error) + return error; + + /* Free the old rtbitmap blocks if they're not in use. */ + return xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK); } diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c new file mode 100644 index 000000000000..4c5dffc73641 --- /dev/null +++ b/fs/xfs/scrub/rtrefcount.c @@ -0,0 +1,661 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_trans.h" +#include "xfs_btree.h" +#include "xfs_rmap.h" +#include "xfs_refcount.h" +#include "xfs_inode.h" +#include "xfs_rtbitmap.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_rtalloc.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/repair.h" + +/* Set us up with the realtime refcount metadata locked. */ +int +xchk_setup_rtrefcountbt( + struct xfs_scrub *sc) +{ + int error; + + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + if (xchk_could_repair(sc)) { + error = xrep_setup_rtrefcountbt(sc); + if (error) + return error; + } + + error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); + if (error) + return error; + + error = xchk_setup_rt(sc); + if (error) + return error; + + error = xchk_install_live_inode(sc, rtg_refcount(sc->sr.rtg)); + if (error) + return error; + + return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); +} + +/* Realtime Reference count btree scrubber. */ + +/* + * Confirming Reference Counts via Reverse Mappings + * + * We want to count the reverse mappings overlapping a refcount record + * (bno, len, refcount), allowing for the possibility that some of the + * overlap may come from smaller adjoining reverse mappings, while some + * comes from single extents which overlap the range entirely. The + * outer loop is as follows: + * + * 1. For all reverse mappings overlapping the refcount extent, + * a. If a given rmap completely overlaps, mark it as seen. + * b. Otherwise, record the fragment (in agbno order) for later + * processing. + * + * Once we've seen all the rmaps, we know that for all blocks in the + * refcount record we want to find $refcount owners and we've already + * visited $seen extents that overlap all the blocks. Therefore, we + * need to find ($refcount - $seen) owners for every block in the + * extent; call that quantity $target_nr. Proceed as follows: + * + * 2. Pull the first $target_nr fragments from the list; all of them + * should start at or before the start of the extent. + * Call this subset of fragments the working set. + * 3. Until there are no more unprocessed fragments, + * a. Find the shortest fragments in the set and remove them. + * b. Note the block number of the end of these fragments. + * c. Pull the same number of fragments from the list. All of these + * fragments should start at the block number recorded in the + * previous step. + * d. Put those fragments in the set. + * 4. Check that there are $target_nr fragments remaining in the list, + * and that they all end at or beyond the end of the refcount extent. + * + * If the refcount is correct, all the check conditions in the algorithm + * should always hold true. If not, the refcount is incorrect. + */ +struct xchk_rtrefcnt_frag { + struct list_head list; + struct xfs_rmap_irec rm; +}; + +struct xchk_rtrefcnt_check { + struct xfs_scrub *sc; + struct list_head fragments; + + /* refcount extent we're examining */ + xfs_rgblock_t bno; + xfs_extlen_t len; + xfs_nlink_t refcount; + + /* number of owners seen */ + xfs_nlink_t seen; +}; + +/* + * Decide if the given rmap is large enough that we can redeem it + * towards refcount verification now, or if it's a fragment, in + * which case we'll hang onto it in the hopes that we'll later + * discover that we've collected exactly the correct number of + * fragments as the rtrefcountbt says we should have. + */ +STATIC int +xchk_rtrefcountbt_rmap_check( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xchk_rtrefcnt_check *refchk = priv; + struct xchk_rtrefcnt_frag *frag; + xfs_rgblock_t rm_last; + xfs_rgblock_t rc_last; + int error = 0; + + if (xchk_should_terminate(refchk->sc, &error)) + return error; + + rm_last = rec->rm_startblock + rec->rm_blockcount - 1; + rc_last = refchk->bno + refchk->len - 1; + + /* Confirm that a single-owner refc extent is a CoW stage. */ + if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) { + xchk_btree_xref_set_corrupt(refchk->sc, cur, 0); + return 0; + } + + if (rec->rm_startblock <= refchk->bno && rm_last >= rc_last) { + /* + * The rmap overlaps the refcount record, so we can confirm + * one refcount owner seen. + */ + refchk->seen++; + } else { + /* + * This rmap covers only part of the refcount record, so + * save the fragment for later processing. If the rmapbt + * is healthy each rmap_irec we see will be in agbno order + * so we don't need insertion sort here. + */ + frag = kmalloc(sizeof(struct xchk_rtrefcnt_frag), + XCHK_GFP_FLAGS); + if (!frag) + return -ENOMEM; + memcpy(&frag->rm, rec, sizeof(frag->rm)); + list_add_tail(&frag->list, &refchk->fragments); + } + + return 0; +} + +/* + * Given a bunch of rmap fragments, iterate through them, keeping + * a running tally of the refcount. If this ever deviates from + * what we expect (which is the rtrefcountbt's refcount minus the + * number of extents that totally covered the rtrefcountbt extent), + * we have a rtrefcountbt error. + */ +STATIC void +xchk_rtrefcountbt_process_rmap_fragments( + struct xchk_rtrefcnt_check *refchk) +{ + struct list_head worklist; + struct xchk_rtrefcnt_frag *frag; + struct xchk_rtrefcnt_frag *n; + xfs_rgblock_t bno; + xfs_rgblock_t rbno; + xfs_rgblock_t next_rbno; + xfs_nlink_t nr; + xfs_nlink_t target_nr; + + target_nr = refchk->refcount - refchk->seen; + if (target_nr == 0) + return; + + /* + * There are (refchk->rc.rc_refcount - refchk->nr refcount) + * references we haven't found yet. Pull that many off the + * fragment list and figure out where the smallest rmap ends + * (and therefore the next rmap should start). All the rmaps + * we pull off should start at or before the beginning of the + * refcount record's range. + */ + INIT_LIST_HEAD(&worklist); + rbno = NULLRGBLOCK; + + /* Make sure the fragments actually /are/ in bno order. */ + bno = 0; + list_for_each_entry(frag, &refchk->fragments, list) { + if (frag->rm.rm_startblock < bno) + goto done; + bno = frag->rm.rm_startblock; + } + + /* + * Find all the rmaps that start at or before the refc extent, + * and put them on the worklist. + */ + nr = 0; + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (bno < rbno) + rbno = bno; + list_move_tail(&frag->list, &worklist); + nr++; + } + + /* + * We should have found exactly $target_nr rmap fragments starting + * at or before the refcount extent. + */ + if (nr != target_nr) + goto done; + + while (!list_empty(&refchk->fragments)) { + /* Discard any fragments ending at rbno from the worklist. */ + nr = 0; + next_rbno = NULLRGBLOCK; + list_for_each_entry_safe(frag, n, &worklist, list) { + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (bno != rbno) { + if (bno < next_rbno) + next_rbno = bno; + continue; + } + list_del(&frag->list); + kfree(frag); + nr++; + } + + /* Try to add nr rmaps starting at rbno to the worklist. */ + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; + if (frag->rm.rm_startblock != rbno) + goto done; + list_move_tail(&frag->list, &worklist); + if (next_rbno > bno) + next_rbno = bno; + nr--; + if (nr == 0) + break; + } + + /* + * If we get here and nr > 0, this means that we added fewer + * items to the worklist than we discarded because the fragment + * list ran out of items. Therefore, we cannot maintain the + * required refcount. Something is wrong, so we're done. + */ + if (nr) + goto done; + + rbno = next_rbno; + } + + /* + * Make sure the last extent we processed ends at or beyond + * the end of the refcount extent. + */ + if (rbno < refchk->bno + refchk->len) + goto done; + + /* Actually record us having seen the remaining refcount. */ + refchk->seen = refchk->refcount; +done: + /* Delete fragments and work list. */ + list_for_each_entry_safe(frag, n, &worklist, list) { + list_del(&frag->list); + kfree(frag); + } + list_for_each_entry_safe(frag, n, &refchk->fragments, list) { + list_del(&frag->list); + kfree(frag); + } +} + +/* Use the rmap entries covering this extent to verify the refcount. */ +STATIC void +xchk_rtrefcountbt_xref_rmap( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) +{ + struct xchk_rtrefcnt_check refchk = { + .sc = sc, + .bno = irec->rc_startblock, + .len = irec->rc_blockcount, + .refcount = irec->rc_refcount, + .seen = 0, + }; + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + struct xchk_rtrefcnt_frag *frag; + struct xchk_rtrefcnt_frag *n; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + /* Cross-reference with the rmapbt to confirm the refcount. */ + memset(&low, 0, sizeof(low)); + low.rm_startblock = irec->rc_startblock; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1; + + INIT_LIST_HEAD(&refchk.fragments); + error = xfs_rmap_query_range(sc->sr.rmap_cur, &low, &high, + xchk_rtrefcountbt_rmap_check, &refchk); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + goto out_free; + + xchk_rtrefcountbt_process_rmap_fragments(&refchk); + if (irec->rc_refcount != refchk.seen) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + +out_free: + list_for_each_entry_safe(frag, n, &refchk.fragments, list) { + list_del(&frag->list); + kfree(frag); + } +} + +/* Cross-reference with the other btrees. */ +STATIC void +xchk_rtrefcountbt_xref( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) +{ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + xchk_xref_is_used_rt_space(sc, + xfs_rgbno_to_rtb(sc->sr.rtg, irec->rc_startblock), + irec->rc_blockcount); + xchk_rtrefcountbt_xref_rmap(sc, irec); +} + +struct xchk_rtrefcbt_records { + /* Previous refcount record. */ + struct xfs_refcount_irec prev_rec; + + /* The next rtgroup block where we aren't expecting shared extents. */ + xfs_rgblock_t next_unshared_rgbno; + + /* Number of CoW blocks we expect. */ + xfs_extlen_t cow_blocks; + + /* Was the last record a shared or CoW staging extent? */ + enum xfs_refc_domain prev_domain; +}; + +static inline bool +xchk_rtrefcount_mergeable( + struct xchk_rtrefcbt_records *rrc, + const struct xfs_refcount_irec *r2) +{ + const struct xfs_refcount_irec *r1 = &rrc->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (r1->rc_blockcount > 0) + return false; + + if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) + return false; + if (r1->rc_refcount != r2->rc_refcount) + return false; + if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > + XFS_REFC_LEN_MAX) + return false; + + return true; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rtrefcountbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rtrefcbt_records *rrc, + const struct xfs_refcount_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rtrefcount_mergeable(rrc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&rrc->prev_rec, irec, sizeof(struct xfs_refcount_irec)); +} + +STATIC int +xchk_rtrefcountbt_rmap_check_gap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + xfs_rgblock_t *next_bno = priv; + + if (*next_bno != NULLRGBLOCK && rec->rm_startblock < *next_bno) + return -ECANCELED; + + *next_bno = rec->rm_startblock + rec->rm_blockcount; + return 0; +} + +/* + * Make sure that a gap in the reference count records does not correspond to + * overlapping records (i.e. shared extents) in the reverse mappings. + */ +static inline void +xchk_rtrefcountbt_xref_gaps( + struct xfs_scrub *sc, + struct xchk_rtrefcbt_records *rrc, + xfs_rtblock_t bno) +{ + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + xfs_rgblock_t next_bno = NULLRGBLOCK; + int error; + + if (bno <= rrc->next_unshared_rgbno || !sc->sr.rmap_cur || + xchk_skip_xref(sc->sm)) + return; + + memset(&low, 0, sizeof(low)); + low.rm_startblock = rrc->next_unshared_rgbno; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = bno - 1; + + error = xfs_rmap_query_range(sc->sr.rmap_cur, &low, &high, + xchk_rtrefcountbt_rmap_check_gap, &next_bno); + if (error == -ECANCELED) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + else + xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur); +} + +/* Scrub a rtrefcountbt record. */ +STATIC int +xchk_rtrefcountbt_rec( + struct xchk_btree *bs, + const union xfs_btree_rec *rec) +{ + struct xfs_mount *mp = bs->cur->bc_mp; + struct xchk_rtrefcbt_records *rrc = bs->private; + struct xfs_refcount_irec irec; + u32 mod; + + xfs_refcount_btrec_to_irec(rec, &irec); + if (xfs_rtrefcount_check_irec(to_rtg(bs->cur->bc_group), &irec) != + NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } + + /* We can only share full rt extents. */ + mod = xfs_rgbno_to_rtxoff(mp, irec.rc_startblock); + if (mod) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + mod = xfs_extlen_to_rtxmod(mp, irec.rc_blockcount); + if (mod) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + if (irec.rc_domain == XFS_REFC_DOMAIN_COW) + rrc->cow_blocks += irec.rc_blockcount; + + /* Shared records always come before CoW records. */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED && + rrc->prev_domain == XFS_REFC_DOMAIN_COW) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + rrc->prev_domain = irec.rc_domain; + + xchk_rtrefcountbt_check_mergeable(bs, rrc, &irec); + xchk_rtrefcountbt_xref(bs->sc, &irec); + + /* + * If this is a record for a shared extent, check that all blocks + * between the previous record and this one have at most one reverse + * mapping. + */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED) { + xchk_rtrefcountbt_xref_gaps(bs->sc, rrc, irec.rc_startblock); + rrc->next_unshared_rgbno = irec.rc_startblock + + irec.rc_blockcount; + } + + return 0; +} + +/* Make sure we have as many refc blocks as the rmap says. */ +STATIC void +xchk_refcount_xref_rmap( + struct xfs_scrub *sc, + const struct xfs_owner_info *btree_oinfo, + xfs_extlen_t cow_blocks) +{ + xfs_filblks_t refcbt_blocks = 0; + xfs_filblks_t blocks; + int error; + + if (!sc->sr.rmap_cur || !sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + /* Check that we saw as many refcbt blocks as the rmap knows about. */ + error = xfs_btree_count_blocks(sc->sr.refc_cur, &refcbt_blocks); + if (!xchk_btree_process_error(sc, sc->sr.refc_cur, 0, &error)) + return; + error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, + &blocks); + if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + return; + if (blocks != refcbt_blocks) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + + /* Check that we saw as many cow blocks as the rmap knows about. */ + error = xchk_count_rmap_ownedby_ag(sc, sc->sr.rmap_cur, + &XFS_RMAP_OINFO_COW, &blocks); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (blocks != cow_blocks) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* Scrub the refcount btree for some AG. */ +int +xchk_rtrefcountbt( + struct xfs_scrub *sc) +{ + struct xfs_owner_info btree_oinfo; + struct xchk_rtrefcbt_records rrc = { + .cow_blocks = 0, + .next_unshared_rgbno = 0, + .prev_domain = XFS_REFC_DOMAIN_SHARED, + }; + int error; + + error = xchk_metadata_inode_forks(sc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + xfs_rmap_ino_bmbt_owner(&btree_oinfo, rtg_refcount(sc->sr.rtg)->i_ino, + XFS_DATA_FORK); + error = xchk_btree(sc, sc->sr.refc_cur, xchk_rtrefcountbt_rec, + &btree_oinfo, &rrc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + /* + * Check that all blocks between the last refcount > 1 record and the + * end of the rt volume have at most one reverse mapping. + */ + xchk_rtrefcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_rblocks); + + xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); + + return 0; +} + +/* xref check that a cow staging extent is marked in the rtrefcountbt. */ +void +xchk_xref_is_rt_cow_staging( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + struct xfs_refcount_irec rc; + int has_refcount; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + /* Find the CoW staging extent. */ + error = xfs_refcount_lookup_le(sc->sr.refc_cur, XFS_REFC_DOMAIN_COW, + bno, &has_refcount); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (!has_refcount) { + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + return; + } + + error = xfs_refcount_get_rec(sc->sr.refc_cur, &rc, &has_refcount); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (!has_refcount) { + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + return; + } + + /* CoW lookup returned a shared extent record? */ + if (rc.rc_domain != XFS_REFC_DOMAIN_COW) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + + /* Must be at least as long as what was passed in */ + if (rc.rc_blockcount < len) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* + * xref check that the extent is not shared. Only file data blocks + * can have multiple owners. + */ +void +xchk_xref_is_not_rt_shared( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sr.refc_cur, + XFS_REFC_DOMAIN_SHARED, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* xref check that the extent is not being used for CoW staging. */ +void +xchk_xref_is_not_rt_cow_staging( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sr.refc_cur, XFS_REFC_DOMAIN_COW, + bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} diff --git a/fs/xfs/scrub/rtrefcount_repair.c b/fs/xfs/scrub/rtrefcount_repair.c new file mode 100644 index 000000000000..257cfb24beb4 --- /dev/null +++ b/fs/xfs/scrub/rtrefcount_repair.c @@ -0,0 +1,783 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_alloc.h" +#include "xfs_ialloc.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_refcount.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_error.h" +#include "xfs_health.h" +#include "xfs_inode.h" +#include "xfs_quota.h" +#include "xfs_rtalloc.h" +#include "xfs_ag.h" +#include "xfs_rtgroup.h" +#include "xfs_rtbitmap.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" +#include "scrub/bitmap.h" +#include "scrub/fsb_bitmap.h" +#include "scrub/xfile.h" +#include "scrub/xfarray.h" +#include "scrub/newbt.h" +#include "scrub/reap.h" +#include "scrub/rcbag.h" + +/* + * Rebuilding the Reference Count Btree + * ==================================== + * + * This algorithm is "borrowed" from xfs_repair. Imagine the rmap + * entries as rectangles representing extents of physical blocks, and + * that the rectangles can be laid down to allow them to overlap each + * other; then we know that we must emit a refcnt btree entry wherever + * the amount of overlap changes, i.e. the emission stimulus is + * level-triggered: + * + * - --- + * -- ----- ---- --- ------ + * -- ---- ----------- ---- --------- + * -------------------------------- ----------- + * ^ ^ ^^ ^^ ^ ^^ ^^^ ^^^^ ^ ^^ ^ ^ ^ + * 2 1 23 21 3 43 234 2123 1 01 2 3 0 + * + * For our purposes, a rmap is a tuple (startblock, len, fileoff, owner). + * + * Note that in the actual refcnt btree we don't store the refcount < 2 + * cases because the bnobt tells us which blocks are free; single-use + * blocks aren't recorded in the bnobt or the refcntbt. If the rmapbt + * supports storing multiple entries covering a given block we could + * theoretically dispense with the refcntbt and simply count rmaps, but + * that's inefficient in the (hot) write path, so we'll take the cost of + * the extra tree to save time. Also there's no guarantee that rmap + * will be enabled. + * + * Given an array of rmaps sorted by physical block number, a starting + * physical block (sp), a bag to hold rmaps that cover sp, and the next + * physical block where the level changes (np), we can reconstruct the + * rt refcount btree as follows: + * + * While there are still unprocessed rmaps in the array, + * - Set sp to the physical block (pblk) of the next unprocessed rmap. + * - Add to the bag all rmaps in the array where startblock == sp. + * - Set np to the physical block where the bag size will change. This + * is the minimum of (the pblk of the next unprocessed rmap) and + * (startblock + len of each rmap in the bag). + * - Record the bag size as old_bag_size. + * + * - While the bag isn't empty, + * - Remove from the bag all rmaps where startblock + len == np. + * - Add to the bag all rmaps in the array where startblock == np. + * - If the bag size isn't old_bag_size, store the refcount entry + * (sp, np - sp, bag_size) in the refcnt btree. + * - If the bag is empty, break out of the inner loop. + * - Set old_bag_size to the bag size + * - Set sp = np. + * - Set np to the physical block where the bag size will change. + * This is the minimum of (the pblk of the next unprocessed rmap) + * and (startblock + len of each rmap in the bag). + * + * Like all the other repairers, we make a list of all the refcount + * records we need, then reinitialize the rt refcount btree root and + * insert all the records. + */ + +struct xrep_rtrefc { + /* refcount extents */ + struct xfarray *refcount_records; + + /* new refcountbt information */ + struct xrep_newbt new_btree; + + /* old refcountbt blocks */ + struct xfsb_bitmap old_rtrefcountbt_blocks; + + struct xfs_scrub *sc; + + /* get_records()'s position in the rt refcount record array. */ + xfarray_idx_t array_cur; + + /* # of refcountbt blocks */ + xfs_filblks_t btblocks; +}; + +/* Set us up to repair refcount btrees. */ +int +xrep_setup_rtrefcountbt( + struct xfs_scrub *sc) +{ + char *descr; + int error; + + descr = xchk_xfile_ag_descr(sc, "rmap record bag"); + error = xrep_setup_xfbtree(sc, descr); + kfree(descr); + return error; +} + +/* Check for any obvious conflicts with this shared/CoW staging extent. */ +STATIC int +xrep_rtrefc_check_ext( + struct xfs_scrub *sc, + const struct xfs_refcount_irec *rec) +{ + xfs_rgblock_t last; + + if (xfs_rtrefcount_check_irec(sc->sr.rtg, rec) != NULL) + return -EFSCORRUPTED; + + if (xfs_rgbno_to_rtxoff(sc->mp, rec->rc_startblock) != 0) + return -EFSCORRUPTED; + + last = rec->rc_startblock + rec->rc_blockcount - 1; + if (xfs_rgbno_to_rtxoff(sc->mp, last) != sc->mp->m_sb.sb_rextsize - 1) + return -EFSCORRUPTED; + + /* Make sure this isn't free space or misaligned. */ + return xrep_require_rtext_inuse(sc, rec->rc_startblock, + rec->rc_blockcount); +} + +/* Record a reference count extent. */ +STATIC int +xrep_rtrefc_stash( + struct xrep_rtrefc *rr, + enum xfs_refc_domain domain, + xfs_rgblock_t bno, + xfs_extlen_t len, + uint64_t refcount) +{ + struct xfs_refcount_irec irec = { + .rc_startblock = bno, + .rc_blockcount = len, + .rc_refcount = refcount, + .rc_domain = domain, + }; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + irec.rc_refcount = min_t(uint64_t, XFS_REFC_REFCOUNT_MAX, refcount); + + error = xrep_rtrefc_check_ext(rr->sc, &irec); + if (error) + return error; + + trace_xrep_refc_found(rtg_group(rr->sc->sr.rtg), &irec); + + return xfarray_append(rr->refcount_records, &irec); +} + +/* Record a CoW staging extent. */ +STATIC int +xrep_rtrefc_stash_cow( + struct xrep_rtrefc *rr, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + return xrep_rtrefc_stash(rr, XFS_REFC_DOMAIN_COW, bno, len, 1); +} + +/* Decide if an rmap could describe a shared extent. */ +static inline bool +xrep_rtrefc_rmap_shareable( + const struct xfs_rmap_irec *rmap) +{ + /* rt metadata are never sharable */ + if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) + return false; + + /* Unwritten file blocks are not shareable. */ + if (rmap->rm_flags & XFS_RMAP_UNWRITTEN) + return false; + + return true; +} + +/* Grab the next (abbreviated) rmap record from the rmapbt. */ +STATIC int +xrep_rtrefc_walk_rmaps( + struct xrep_rtrefc *rr, + struct xfs_rmap_irec *rmap, + bool *have_rec) +{ + struct xfs_btree_cur *cur = rr->sc->sr.rmap_cur; + struct xfs_mount *mp = cur->bc_mp; + int have_gt; + int error = 0; + + *have_rec = false; + + /* + * Loop through the remaining rmaps. Remember CoW staging + * extents and the refcountbt blocks from the old tree for later + * disposal. We can only share written data fork extents, so + * keep looping until we find an rmap for one. + */ + do { + if (xchk_should_terminate(rr->sc, &error)) + return error; + + error = xfs_btree_increment(cur, 0, &have_gt); + if (error) + return error; + if (!have_gt) + return 0; + + error = xfs_rmap_get_rec(cur, rmap, &have_gt); + if (error) + return error; + if (XFS_IS_CORRUPT(mp, !have_gt)) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + + if (rmap->rm_owner == XFS_RMAP_OWN_COW) { + error = xrep_rtrefc_stash_cow(rr, rmap->rm_startblock, + rmap->rm_blockcount); + if (error) + return error; + } else if (xfs_is_sb_inum(mp, rmap->rm_owner) || + (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | + XFS_RMAP_BMBT_BLOCK))) { + xfs_btree_mark_sick(cur); + return -EFSCORRUPTED; + } + } while (!xrep_rtrefc_rmap_shareable(rmap)); + + *have_rec = true; + return 0; +} + +static inline uint32_t +xrep_rtrefc_encode_startblock( + const struct xfs_refcount_irec *irec) +{ + uint32_t start; + + start = irec->rc_startblock & ~XFS_REFC_COWFLAG; + if (irec->rc_domain == XFS_REFC_DOMAIN_COW) + start |= XFS_REFC_COWFLAG; + + return start; +} + +/* + * Compare two refcount records. We want to sort in order of increasing block + * number. + */ +static int +xrep_rtrefc_extent_cmp( + const void *a, + const void *b) +{ + const struct xfs_refcount_irec *ap = a; + const struct xfs_refcount_irec *bp = b; + uint32_t sa, sb; + + sa = xrep_rtrefc_encode_startblock(ap); + sb = xrep_rtrefc_encode_startblock(bp); + + if (sa > sb) + return 1; + if (sa < sb) + return -1; + return 0; +} + +/* + * Sort the refcount extents by startblock or else the btree records will be in + * the wrong order. Make sure the records do not overlap in physical space. + */ +STATIC int +xrep_rtrefc_sort_records( + struct xrep_rtrefc *rr) +{ + struct xfs_refcount_irec irec; + xfarray_idx_t cur; + enum xfs_refc_domain dom = XFS_REFC_DOMAIN_SHARED; + xfs_rgblock_t next_rgbno = 0; + int error; + + error = xfarray_sort(rr->refcount_records, xrep_rtrefc_extent_cmp, + XFARRAY_SORT_KILLABLE); + if (error) + return error; + + foreach_xfarray_idx(rr->refcount_records, cur) { + if (xchk_should_terminate(rr->sc, &error)) + return error; + + error = xfarray_load(rr->refcount_records, cur, &irec); + if (error) + return error; + + if (dom == XFS_REFC_DOMAIN_SHARED && + irec.rc_domain == XFS_REFC_DOMAIN_COW) { + dom = irec.rc_domain; + next_rgbno = 0; + } + + if (dom != irec.rc_domain) + return -EFSCORRUPTED; + if (irec.rc_startblock < next_rgbno) + return -EFSCORRUPTED; + + next_rgbno = irec.rc_startblock + irec.rc_blockcount; + } + + return error; +} + +/* Record extents that belong to the realtime refcount inode. */ +STATIC int +xrep_rtrefc_walk_rmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rr->sc->ip->i_ino) + return 0; + + error = xrep_check_ino_btree_mapping(rr->sc, rec); + if (error) + return error; + + return xfsb_bitmap_set(&rr->old_rtrefcountbt_blocks, + xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock), + rec->rm_blockcount); +} + +/* + * Walk forward through the rmap btree to collect all rmaps starting at + * @bno in @rmap_bag. These represent the file(s) that share ownership of + * the current block. Upon return, the rmap cursor points to the last record + * satisfying the startblock constraint. + */ +static int +xrep_rtrefc_push_rmaps_at( + struct xrep_rtrefc *rr, + struct rcbag *rcstack, + xfs_rgblock_t bno, + struct xfs_rmap_irec *rmap, + bool *have) +{ + struct xfs_scrub *sc = rr->sc; + int have_gt; + int error; + + while (*have && rmap->rm_startblock == bno) { + error = rcbag_add(rcstack, rr->sc->tp, rmap); + if (error) + return error; + + error = xrep_rtrefc_walk_rmaps(rr, rmap, have); + if (error) + return error; + } + + error = xfs_btree_decrement(sc->sr.rmap_cur, 0, &have_gt); + if (error) + return error; + if (XFS_IS_CORRUPT(sc->mp, !have_gt)) { + xfs_btree_mark_sick(sc->sr.rmap_cur); + return -EFSCORRUPTED; + } + + return 0; +} + +/* Scan one AG for reverse mappings for the realtime refcount btree. */ +STATIC int +xrep_rtrefc_scan_ag( + struct xrep_rtrefc *rr, + struct xfs_perag *pag) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + error = xrep_ag_init(sc, pag, &sc->sa); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrefc_walk_rmap, rr); + xchk_ag_free(sc, &sc->sa); + return error; +} + +/* Iterate all the rmap records to generate reference count data. */ +STATIC int +xrep_rtrefc_find_refcounts( + struct xrep_rtrefc *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct rcbag *rcstack; + struct xfs_perag *pag = NULL; + uint64_t old_stack_height; + xfs_rgblock_t sbno; + xfs_rgblock_t cbno; + xfs_rgblock_t nbno; + bool have; + int error; + + /* Scan for old rtrefc btree blocks. */ + while ((pag = xfs_perag_next(sc->mp, pag))) { + error = xrep_rtrefc_scan_ag(rr, pag); + if (error) { + xfs_perag_rele(pag); + return error; + } + } + + xrep_rtgroup_btcur_init(sc, &sc->sr); + + /* + * Set up a bag to store all the rmap records that we're tracking to + * generate a reference count record. If this exceeds + * XFS_REFC_REFCOUNT_MAX, we clamp rc_refcount. + */ + error = rcbag_init(sc->mp, sc->xmbtp, &rcstack); + if (error) + goto out_cur; + + /* Start the rtrmapbt cursor to the left of all records. */ + error = xfs_btree_goto_left_edge(sc->sr.rmap_cur); + if (error) + goto out_bag; + + /* Process reverse mappings into refcount data. */ + while (xfs_btree_has_more_records(sc->sr.rmap_cur)) { + struct xfs_rmap_irec rmap; + + /* Push all rmaps with pblk == sbno onto the stack */ + error = xrep_rtrefc_walk_rmaps(rr, &rmap, &have); + if (error) + goto out_bag; + if (!have) + break; + sbno = cbno = rmap.rm_startblock; + error = xrep_rtrefc_push_rmaps_at(rr, rcstack, sbno, &rmap, + &have); + if (error) + goto out_bag; + + /* Set nbno to the bno of the next refcount change */ + error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, &nbno); + if (error) + goto out_bag; + + ASSERT(nbno > sbno); + old_stack_height = rcbag_count(rcstack); + + /* While stack isn't empty... */ + while (rcbag_count(rcstack) > 0) { + /* Pop all rmaps that end at nbno */ + error = rcbag_remove_ending_at(rcstack, sc->tp, nbno); + if (error) + goto out_bag; + + /* Push array items that start at nbno */ + error = xrep_rtrefc_walk_rmaps(rr, &rmap, &have); + if (error) + goto out_bag; + if (have) { + error = xrep_rtrefc_push_rmaps_at(rr, rcstack, + nbno, &rmap, &have); + if (error) + goto out_bag; + } + + /* Emit refcount if necessary */ + ASSERT(nbno > cbno); + if (rcbag_count(rcstack) != old_stack_height) { + if (old_stack_height > 1) { + error = xrep_rtrefc_stash(rr, + XFS_REFC_DOMAIN_SHARED, + cbno, nbno - cbno, + old_stack_height); + if (error) + goto out_bag; + } + cbno = nbno; + } + + /* Stack empty, go find the next rmap */ + if (rcbag_count(rcstack) == 0) + break; + old_stack_height = rcbag_count(rcstack); + sbno = nbno; + + /* Set nbno to the bno of the next refcount change */ + error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, + &nbno); + if (error) + goto out_bag; + + ASSERT(nbno > sbno); + } + } + + ASSERT(rcbag_count(rcstack) == 0); +out_bag: + rcbag_free(&rcstack); +out_cur: + xchk_rtgroup_btcur_free(&sc->sr); + return error; +} + +/* Retrieve refcountbt data for bulk load. */ +STATIC int +xrep_rtrefc_get_records( + struct xfs_btree_cur *cur, + unsigned int idx, + struct xfs_btree_block *block, + unsigned int nr_wanted, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + union xfs_btree_rec *block_rec; + unsigned int loaded; + int error; + + for (loaded = 0; loaded < nr_wanted; loaded++, idx++) { + error = xfarray_load(rr->refcount_records, rr->array_cur++, + &cur->bc_rec.rc); + if (error) + return error; + + block_rec = xfs_btree_rec_addr(cur, idx, block); + cur->bc_ops->init_rec_from_cur(cur, block_rec); + } + + return loaded; +} + +/* Feed one of the new btree blocks to the bulk loader. */ +STATIC int +xrep_rtrefc_claim_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr, + void *priv) +{ + struct xrep_rtrefc *rr = priv; + + return xrep_newbt_claim_block(cur, &rr->new_btree, ptr); +} + +/* Figure out how much space we need to create the incore btree root block. */ +STATIC size_t +xrep_rtrefc_iroot_size( + struct xfs_btree_cur *cur, + unsigned int level, + unsigned int nr_this_level, + void *priv) +{ + return xfs_rtrefcount_broot_space_calc(cur->bc_mp, level, + nr_this_level); +} + +/* + * Use the collected refcount information to stage a new rt refcount btree. If + * this is successful we'll return with the new btree root information logged + * to the repair transaction but not yet committed. + */ +STATIC int +xrep_rtrefc_build_new_tree( + struct xrep_rtrefc *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_rtgroup *rtg = sc->sr.rtg; + struct xfs_btree_cur *refc_cur; + int error; + + error = xrep_rtrefc_sort_records(rr); + if (error) + return error; + + /* + * Prepare to construct the new btree by reserving disk space for the + * new btree and setting up all the accounting information we'll need + * to root the new btree while it's under construction and before we + * attach it to the realtime refcount inode. + */ + error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc); + if (error) + return error; + + rr->new_btree.bload.get_records = xrep_rtrefc_get_records; + rr->new_btree.bload.claim_block = xrep_rtrefc_claim_block; + rr->new_btree.bload.iroot_size = xrep_rtrefc_iroot_size; + + refc_cur = xfs_rtrefcountbt_init_cursor(NULL, rtg); + xfs_btree_stage_ifakeroot(refc_cur, &rr->new_btree.ifake); + + /* Compute how many blocks we'll need. */ + error = xfs_btree_bload_compute_geometry(refc_cur, &rr->new_btree.bload, + xfarray_length(rr->refcount_records)); + if (error) + goto err_cur; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + goto err_cur; + + /* + * Guess how many blocks we're going to need to rebuild an entire + * rtrefcountbt from the number of extents we found, and pump up our + * transaction to have sufficient block reservation. We're allowed + * to exceed quota to repair inconsistent metadata, though this is + * unlikely. + */ + error = xfs_trans_reserve_more_inode(sc->tp, rtg_refcount(rtg), + rr->new_btree.bload.nr_blocks, 0, true); + if (error) + goto err_cur; + + /* Reserve the space we'll need for the new btree. */ + error = xrep_newbt_alloc_blocks(&rr->new_btree, + rr->new_btree.bload.nr_blocks); + if (error) + goto err_cur; + + /* Add all observed refcount records. */ + rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE; + rr->array_cur = XFARRAY_CURSOR_INIT; + error = xfs_btree_bload(refc_cur, &rr->new_btree.bload, rr); + if (error) + goto err_cur; + + /* + * Install the new rtrefc btree in the inode. After this point the old + * btree is no longer accessible, the new tree is live, and we can + * delete the cursor. + */ + xfs_rtrefcountbt_commit_staged_btree(refc_cur, sc->tp); + xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks); + xfs_btree_del_cursor(refc_cur, 0); + + /* Dispose of any unused blocks and the accounting information. */ + error = xrep_newbt_commit(&rr->new_btree); + if (error) + return error; + + return xrep_roll_trans(sc); +err_cur: + xfs_btree_del_cursor(refc_cur, error); + xrep_newbt_cancel(&rr->new_btree); + return error; +} + +/* + * Now that we've logged the roots of the new btrees, invalidate all of the + * old blocks and free them. + */ +STATIC int +xrep_rtrefc_remove_old_tree( + struct xrep_rtrefc *rr) +{ + int error; + + /* + * Free all the extents that were allocated to the former rtrefcountbt + * and aren't cross-linked with something else. + */ + error = xrep_reap_metadir_fsblocks(rr->sc, + &rr->old_rtrefcountbt_blocks); + if (error) + return error; + + /* + * Ensure the proper reservation for the rtrefcount inode so that we + * don't fail to expand the btree. + */ + return xrep_reset_metafile_resv(rr->sc); +} + +/* Rebuild the rt refcount btree. */ +int +xrep_rtrefcountbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrefc *rr; + struct xfs_mount *mp = sc->mp; + char *descr; + int error; + + /* We require the rmapbt to rebuild anything. */ + if (!xfs_has_rtrmapbt(mp)) + return -EOPNOTSUPP; + + /* Make sure any problems with the fork are fixed. */ + error = xrep_metadata_inode_forks(sc); + if (error) + return error; + + rr = kzalloc(sizeof(struct xrep_rtrefc), XCHK_GFP_FLAGS); + if (!rr) + return -ENOMEM; + rr->sc = sc; + + /* Set up enough storage to handle one refcount record per rt extent. */ + descr = xchk_xfile_ag_descr(sc, "reference count records"); + error = xfarray_create(descr, mp->m_sb.sb_rextents, + sizeof(struct xfs_refcount_irec), + &rr->refcount_records); + kfree(descr); + if (error) + goto out_rr; + + /* Collect all reference counts. */ + xfsb_bitmap_init(&rr->old_rtrefcountbt_blocks); + error = xrep_rtrefc_find_refcounts(rr); + if (error) + goto out_bitmap; + + xfs_trans_ijoin(sc->tp, sc->ip, 0); + + /* Rebuild the refcount information. */ + error = xrep_rtrefc_build_new_tree(rr); + if (error) + goto out_bitmap; + + /* Kill the old tree. */ + error = xrep_rtrefc_remove_old_tree(rr); + if (error) + goto out_bitmap; + +out_bitmap: + xfsb_bitmap_destroy(&rr->old_rtrefcountbt_blocks); + xfarray_destroy(rr->refcount_records); +out_rr: + kfree(rr); + return error; +} diff --git a/fs/xfs/scrub/rtrmap.c b/fs/xfs/scrub/rtrmap.c new file mode 100644 index 000000000000..12989fe80e8b --- /dev/null +++ b/fs/xfs/scrub/rtrmap.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2018-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_inode.h" +#include "xfs_rtalloc.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" +#include "xfs_refcount.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" + +/* Set us up with the realtime metadata locked. */ +int +xchk_setup_rtrmapbt( + struct xfs_scrub *sc) +{ + int error; + + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + + if (xchk_could_repair(sc)) { + error = xrep_setup_rtrmapbt(sc); + if (error) + return error; + } + + error = xchk_rtgroup_init(sc, sc->sm->sm_agno, &sc->sr); + if (error) + return error; + + error = xchk_setup_rt(sc); + if (error) + return error; + + error = xchk_install_live_inode(sc, rtg_rmap(sc->sr.rtg)); + if (error) + return error; + + return xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); +} + +/* Realtime reverse mapping. */ + +struct xchk_rtrmap { + /* + * The furthest-reaching of the rmapbt records that we've already + * processed. This enables us to detect overlapping records for space + * allocations that cannot be shared. + */ + struct xfs_rmap_irec overlap_rec; + + /* + * The previous rmapbt record, so that we can check for two records + * that could be one. + */ + struct xfs_rmap_irec prev_rec; +}; + +static inline bool +xchk_rtrmapbt_is_shareable( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *irec) +{ + if (!xfs_has_rtreflink(sc->mp)) + return false; + if (irec->rm_flags & XFS_RMAP_UNWRITTEN) + return false; + return true; +} + +/* Flag failures for records that overlap but cannot. */ +STATIC void +xchk_rtrmapbt_check_overlapping( + struct xchk_btree *bs, + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *irec) +{ + xfs_rtblock_t pnext, inext; + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + /* No previous record? */ + if (cr->overlap_rec.rm_blockcount == 0) + goto set_prev; + + /* Do overlap_rec and irec overlap? */ + pnext = cr->overlap_rec.rm_startblock + cr->overlap_rec.rm_blockcount; + if (pnext <= irec->rm_startblock) + goto set_prev; + + /* Overlap is only allowed if both records are data fork mappings. */ + if (!xchk_rtrmapbt_is_shareable(bs->sc, &cr->overlap_rec) || + !xchk_rtrmapbt_is_shareable(bs->sc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + /* Save whichever rmap record extends furthest. */ + inext = irec->rm_startblock + irec->rm_blockcount; + if (pnext > inext) + return; + +set_prev: + memcpy(&cr->overlap_rec, irec, sizeof(struct xfs_rmap_irec)); +} + +/* Decide if two reverse-mapping records can be merged. */ +static inline bool +xchk_rtrmap_mergeable( + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *r2) +{ + const struct xfs_rmap_irec *r1 = &cr->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (cr->prev_rec.rm_blockcount == 0) + return false; + + if (r1->rm_owner != r2->rm_owner) + return false; + if (r1->rm_startblock + r1->rm_blockcount != r2->rm_startblock) + return false; + if ((unsigned long long)r1->rm_blockcount + r2->rm_blockcount > + XFS_RMAP_LEN_MAX) + return false; + if (r1->rm_flags != r2->rm_flags) + return false; + return r1->rm_offset + r1->rm_blockcount == r2->rm_offset; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rtrmapbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rtrmap *cr, + const struct xfs_rmap_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rtrmap_mergeable(cr, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec)); +} + +/* Cross-reference a rmap against the refcount btree. */ +STATIC void +xchk_rtrmapbt_xref_rtrefc( + struct xfs_scrub *sc, + struct xfs_rmap_irec *irec) +{ + xfs_rgblock_t fbno; + xfs_extlen_t flen; + bool is_inode; + bool is_bmbt; + bool is_attr; + bool is_unwritten; + int error; + + if (!sc->sr.refc_cur || xchk_skip_xref(sc->sm)) + return; + + is_inode = !XFS_RMAP_NON_INODE_OWNER(irec->rm_owner); + is_bmbt = irec->rm_flags & XFS_RMAP_BMBT_BLOCK; + is_attr = irec->rm_flags & XFS_RMAP_ATTR_FORK; + is_unwritten = irec->rm_flags & XFS_RMAP_UNWRITTEN; + + /* If this is shared, must be a data fork extent. */ + error = xfs_refcount_find_shared(sc->sr.refc_cur, irec->rm_startblock, + irec->rm_blockcount, &fbno, &flen, false); + if (!xchk_should_check_xref(sc, &error, &sc->sr.refc_cur)) + return; + if (flen != 0 && (!is_inode || is_attr || is_bmbt || is_unwritten)) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); +} + +/* Cross-reference with other metadata. */ +STATIC void +xchk_rtrmapbt_xref( + struct xfs_scrub *sc, + struct xfs_rmap_irec *irec) +{ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + xchk_xref_is_used_rt_space(sc, + xfs_rgbno_to_rtb(sc->sr.rtg, irec->rm_startblock), + irec->rm_blockcount); + if (irec->rm_owner == XFS_RMAP_OWN_COW) + xchk_xref_is_cow_staging(sc, irec->rm_startblock, + irec->rm_blockcount); + else + xchk_rtrmapbt_xref_rtrefc(sc, irec); +} + +/* Scrub a realtime rmapbt record. */ +STATIC int +xchk_rtrmapbt_rec( + struct xchk_btree *bs, + const union xfs_btree_rec *rec) +{ + struct xchk_rtrmap *cr = bs->private; + struct xfs_rmap_irec irec; + + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || + xfs_rtrmap_check_irec(to_rtg(bs->cur->bc_group), &irec) != NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return 0; + + xchk_rtrmapbt_check_mergeable(bs, cr, &irec); + xchk_rtrmapbt_check_overlapping(bs, cr, &irec); + xchk_rtrmapbt_xref(bs->sc, &irec); + return 0; +} + +/* Scrub the realtime rmap btree. */ +int +xchk_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xfs_inode *ip = rtg_rmap(sc->sr.rtg); + struct xfs_owner_info oinfo; + struct xchk_rtrmap cr = { }; + int error; + + error = xchk_metadata_inode_forks(sc); + if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) + return error; + + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, XFS_DATA_FORK); + return xchk_btree(sc, sc->sr.rmap_cur, xchk_rtrmapbt_rec, &oinfo, &cr); +} + +/* xref check that the extent has no realtime reverse mapping at all */ +void +xchk_xref_has_no_rt_owner( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* xref check that the extent is completely mapped */ +void +xchk_xref_has_rt_owner( + struct xfs_scrub *sc, + xfs_rgblock_t bno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_has_records(sc->sr.rmap_cur, bno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (outcome != XBTREE_RECPACKING_FULL) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} + +/* xref check that the extent is only owned by a given owner */ +void +xchk_xref_is_only_rt_owned_by( + struct xfs_scrub *sc, + xfs_agblock_t bno, + xfs_extlen_t len, + const struct xfs_owner_info *oinfo) +{ + struct xfs_rmap_matches res; + int error; + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_count_owners(sc->sr.rmap_cur, bno, len, oinfo, &res); + if (!xchk_should_check_xref(sc, &error, &sc->sr.rmap_cur)) + return; + if (res.matches != 1) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + if (res.bad_non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); + if (res.non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); +} diff --git a/fs/xfs/scrub/rtrmap_repair.c b/fs/xfs/scrub/rtrmap_repair.c new file mode 100644 index 000000000000..f2fdd7a9fc24 --- /dev/null +++ b/fs/xfs/scrub/rtrmap_repair.c @@ -0,0 +1,1006 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_defer.h" +#include "xfs_btree.h" +#include "xfs_btree_staging.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" +#include "xfs_bit.h" +#include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_alloc.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_bmap.h" +#include "xfs_bmap_btree.h" +#include "xfs_quota.h" +#include "xfs_rtalloc.h" +#include "xfs_ag.h" +#include "xfs_rtgroup.h" +#include "xfs_refcount.h" +#include "scrub/xfs_scrub.h" +#include "scrub/scrub.h" +#include "scrub/common.h" +#include "scrub/btree.h" +#include "scrub/trace.h" +#include "scrub/repair.h" +#include "scrub/bitmap.h" +#include "scrub/fsb_bitmap.h" +#include "scrub/rgb_bitmap.h" +#include "scrub/xfile.h" +#include "scrub/xfarray.h" +#include "scrub/iscan.h" +#include "scrub/newbt.h" +#include "scrub/reap.h" + +/* + * Realtime Reverse Mapping Btree Repair + * ===================================== + * + * This isn't quite as difficult as repairing the rmap btree on the data + * device, since we only store the data fork extents of realtime files on the + * realtime device. We still have to freeze the filesystem and stop the + * background threads like we do for the rmap repair, but we only have to scan + * realtime inodes. + * + * Collecting entries for the new realtime rmap btree is easy -- all we have + * to do is generate rtrmap entries from the data fork mappings of all realtime + * files in the filesystem. We then scan the rmap btrees of the data device + * looking for extents belonging to the old btree and note them in a bitmap. + * + * To rebuild the realtime rmap btree, we bulk-load the collected mappings into + * a new btree cursor and atomically swap that into the realtime inode. Then + * we can free the blocks from the old btree. + * + * We use the 'xrep_rtrmap' prefix for all the rmap functions. + */ + +/* Context for collecting rmaps */ +struct xrep_rtrmap { + /* new rtrmapbt information */ + struct xrep_newbt new_btree; + + /* lock for the xfbtree and xfile */ + struct mutex lock; + + /* rmap records generated from primary metadata */ + struct xfbtree rtrmap_btree; + + struct xfs_scrub *sc; + + /* bitmap of old rtrmapbt blocks */ + struct xfsb_bitmap old_rtrmapbt_blocks; + + /* Hooks into rtrmap update code. */ + struct xfs_rmap_hook rhook; + + /* inode scan cursor */ + struct xchk_iscan iscan; + + /* in-memory btree cursor for the ->get_blocks walk */ + struct xfs_btree_cur *mcur; + + /* Number of records we're staging in the new btree. */ + uint64_t nr_records; +}; + +/* Set us up to repair rt reverse mapping btrees. */ +int +xrep_setup_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrmap *rr; + char *descr; + int error; + + xchk_fsgates_enable(sc, XCHK_FSGATES_RMAP); + + descr = xchk_xfile_rtgroup_descr(sc, "reverse mapping records"); + error = xrep_setup_xfbtree(sc, descr); + kfree(descr); + if (error) + return error; + + rr = kzalloc(sizeof(struct xrep_rtrmap), XCHK_GFP_FLAGS); + if (!rr) + return -ENOMEM; + + rr->sc = sc; + sc->buf = rr; + return 0; +} + +/* Make sure there's nothing funny about this mapping. */ +STATIC int +xrep_rtrmap_check_mapping( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *rec) +{ + if (xfs_rtrmap_check_irec(sc->sr.rtg, rec) != NULL) + return -EFSCORRUPTED; + + /* Make sure this isn't free space. */ + return xrep_require_rtext_inuse(sc, rec->rm_startblock, + rec->rm_blockcount); +} + +/* Store a reverse-mapping record. */ +static inline int +xrep_rtrmap_stash( + struct xrep_rtrmap *rr, + xfs_rgblock_t startblock, + xfs_extlen_t blockcount, + uint64_t owner, + uint64_t offset, + unsigned int flags) +{ + struct xfs_rmap_irec rmap = { + .rm_startblock = startblock, + .rm_blockcount = blockcount, + .rm_owner = owner, + .rm_offset = offset, + .rm_flags = flags, + }; + struct xfs_scrub *sc = rr->sc; + struct xfs_btree_cur *mcur; + int error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; + + if (xchk_iscan_aborted(&rr->iscan)) + return -EFSCORRUPTED; + + trace_xrep_rtrmap_found(sc->mp, &rmap); + + /* Add entry to in-memory btree. */ + mutex_lock(&rr->lock); + mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, sc->tp, &rr->rtrmap_btree); + error = xfs_rmap_map_raw(mcur, &rmap); + xfs_btree_del_cursor(mcur, error); + if (error) + goto out_cancel; + + error = xfbtree_trans_commit(&rr->rtrmap_btree, sc->tp); + if (error) + goto out_abort; + + mutex_unlock(&rr->lock); + return 0; + +out_cancel: + xfbtree_trans_cancel(&rr->rtrmap_btree, sc->tp); +out_abort: + xchk_iscan_abort(&rr->iscan); + mutex_unlock(&rr->lock); + return error; +} + +/* Finding all file and bmbt extents. */ + +/* Context for accumulating rmaps for an inode fork. */ +struct xrep_rtrmap_ifork { + /* + * Accumulate rmap data here to turn multiple adjacent bmaps into a + * single rmap. + */ + struct xfs_rmap_irec accum; + + struct xrep_rtrmap *rr; +}; + +/* Stash an rmap that we accumulated while walking an inode fork. */ +STATIC int +xrep_rtrmap_stash_accumulated( + struct xrep_rtrmap_ifork *rf) +{ + if (rf->accum.rm_blockcount == 0) + return 0; + + return xrep_rtrmap_stash(rf->rr, rf->accum.rm_startblock, + rf->accum.rm_blockcount, rf->accum.rm_owner, + rf->accum.rm_offset, rf->accum.rm_flags); +} + +/* Accumulate a bmbt record. */ +STATIC int +xrep_rtrmap_visit_bmbt( + struct xfs_btree_cur *cur, + struct xfs_bmbt_irec *rec, + void *priv) +{ + struct xrep_rtrmap_ifork *rf = priv; + struct xfs_rmap_irec *accum = &rf->accum; + struct xfs_mount *mp = rf->rr->sc->mp; + xfs_rgblock_t rgbno; + unsigned int rmap_flags = 0; + int error; + + if (xfs_rtb_to_rgno(mp, rec->br_startblock) != + rtg_rgno(rf->rr->sc->sr.rtg)) + return 0; + + if (rec->br_state == XFS_EXT_UNWRITTEN) + rmap_flags |= XFS_RMAP_UNWRITTEN; + + /* If this bmap is adjacent to the previous one, just add it. */ + rgbno = xfs_rtb_to_rgbno(mp, rec->br_startblock); + if (accum->rm_blockcount > 0 && + rec->br_startoff == accum->rm_offset + accum->rm_blockcount && + rgbno == accum->rm_startblock + accum->rm_blockcount && + rmap_flags == accum->rm_flags) { + accum->rm_blockcount += rec->br_blockcount; + return 0; + } + + /* Otherwise stash the old rmap and start accumulating a new one. */ + error = xrep_rtrmap_stash_accumulated(rf); + if (error) + return error; + + accum->rm_startblock = rgbno; + accum->rm_blockcount = rec->br_blockcount; + accum->rm_offset = rec->br_startoff; + accum->rm_flags = rmap_flags; + return 0; +} + +/* + * Iterate the block mapping btree to collect rmap records for anything in this + * fork that maps to the rt volume. Sets @mappings_done to true if we've + * scanned the block mappings in this fork. + */ +STATIC int +xrep_rtrmap_scan_bmbt( + struct xrep_rtrmap_ifork *rf, + struct xfs_inode *ip, + bool *mappings_done) +{ + struct xrep_rtrmap *rr = rf->rr; + struct xfs_btree_cur *cur; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + int error = 0; + + *mappings_done = false; + + /* + * If the incore extent cache is already loaded, we'll just use the + * incore extent scanner to record mappings. Don't bother walking the + * ondisk extent tree. + */ + if (!xfs_need_iread_extents(ifp)) + return 0; + + /* Accumulate all the mappings in the bmap btree. */ + cur = xfs_bmbt_init_cursor(rr->sc->mp, rr->sc->tp, ip, XFS_DATA_FORK); + error = xfs_bmap_query_all(cur, xrep_rtrmap_visit_bmbt, rf); + xfs_btree_del_cursor(cur, error); + if (error) + return error; + + /* Stash any remaining accumulated rmaps and exit. */ + *mappings_done = true; + return xrep_rtrmap_stash_accumulated(rf); +} + +/* + * Iterate the in-core extent cache to collect rmap records for anything in + * this fork that matches the AG. + */ +STATIC int +xrep_rtrmap_scan_iext( + struct xrep_rtrmap_ifork *rf, + struct xfs_ifork *ifp) +{ + struct xfs_bmbt_irec rec; + struct xfs_iext_cursor icur; + int error; + + for_each_xfs_iext(ifp, &icur, &rec) { + if (isnullstartblock(rec.br_startblock)) + continue; + error = xrep_rtrmap_visit_bmbt(NULL, &rec, rf); + if (error) + return error; + } + + return xrep_rtrmap_stash_accumulated(rf); +} + +/* Find all the extents on the realtime device mapped by an inode fork. */ +STATIC int +xrep_rtrmap_scan_dfork( + struct xrep_rtrmap *rr, + struct xfs_inode *ip) +{ + struct xrep_rtrmap_ifork rf = { + .accum = { .rm_owner = ip->i_ino, }, + .rr = rr, + }; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + int error = 0; + + if (ifp->if_format == XFS_DINODE_FMT_BTREE) { + bool mappings_done; + + /* + * Scan the bmbt for mappings. If the incore extent tree is + * loaded, we want to scan the cached mappings since that's + * faster when the extent counts are very high. + */ + error = xrep_rtrmap_scan_bmbt(&rf, ip, &mappings_done); + if (error || mappings_done) + return error; + } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { + /* realtime data forks should only be extents or btree */ + return -EFSCORRUPTED; + } + + /* Scan incore extent cache. */ + return xrep_rtrmap_scan_iext(&rf, ifp); +} + +/* Record reverse mappings for a file. */ +STATIC int +xrep_rtrmap_scan_inode( + struct xrep_rtrmap *rr, + struct xfs_inode *ip) +{ + unsigned int lock_mode; + int error = 0; + + /* Skip the rt rmap btree inode. */ + if (rr->sc->ip == ip) + return 0; + + lock_mode = xfs_ilock_data_map_shared(ip); + + /* Check the data fork if it's on the realtime device. */ + if (XFS_IS_REALTIME_INODE(ip)) { + error = xrep_rtrmap_scan_dfork(rr, ip); + if (error) + goto out_unlock; + } + + xchk_iscan_mark_visited(&rr->iscan, ip); +out_unlock: + xfs_iunlock(ip, lock_mode); + return error; +} + +/* Record extents that belong to the realtime rmap inode. */ +STATIC int +xrep_rtrmap_walk_rmap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + int error = 0; + + if (xchk_should_terminate(rr->sc, &error)) + return error; + + /* Skip extents which are not owned by this inode and fork. */ + if (rec->rm_owner != rr->sc->ip->i_ino) + return 0; + + error = xrep_check_ino_btree_mapping(rr->sc, rec); + if (error) + return error; + + return xfsb_bitmap_set(&rr->old_rtrmapbt_blocks, + xfs_gbno_to_fsb(cur->bc_group, rec->rm_startblock), + rec->rm_blockcount); +} + +/* Scan one AG for reverse mappings for the realtime rmap btree. */ +STATIC int +xrep_rtrmap_scan_ag( + struct xrep_rtrmap *rr, + struct xfs_perag *pag) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + error = xrep_ag_init(sc, pag, &sc->sa); + if (error) + return error; + + error = xfs_rmap_query_all(sc->sa.rmap_cur, xrep_rtrmap_walk_rmap, rr); + xchk_ag_free(sc, &sc->sa); + return error; +} + +struct xrep_rtrmap_stash_run { + struct xrep_rtrmap *rr; + uint64_t owner; +}; + +static int +xrep_rtrmap_stash_run( + uint32_t start, + uint32_t len, + void *priv) +{ + struct xrep_rtrmap_stash_run *rsr = priv; + struct xrep_rtrmap *rr = rsr->rr; + xfs_rgblock_t rgbno = start; + + return xrep_rtrmap_stash(rr, rgbno, len, rsr->owner, 0, 0); +} + +/* + * Emit rmaps for every extent of bits set in the bitmap. Caller must ensure + * that the ranges are in units of FS blocks. + */ +STATIC int +xrep_rtrmap_stash_bitmap( + struct xrep_rtrmap *rr, + struct xrgb_bitmap *bitmap, + const struct xfs_owner_info *oinfo) +{ + struct xrep_rtrmap_stash_run rsr = { + .rr = rr, + .owner = oinfo->oi_owner, + }; + + return xrgb_bitmap_walk(bitmap, xrep_rtrmap_stash_run, &rsr); +} + +/* Record a CoW staging extent. */ +STATIC int +xrep_rtrmap_walk_cowblocks( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec, + void *priv) +{ + struct xrgb_bitmap *bitmap = priv; + + if (!xfs_refcount_check_domain(irec) || + irec->rc_domain != XFS_REFC_DOMAIN_COW) + return -EFSCORRUPTED; + + return xrgb_bitmap_set(bitmap, irec->rc_startblock, + irec->rc_blockcount); +} + +/* + * Collect rmaps for the blocks containing the refcount btree, and all CoW + * staging extents. + */ +STATIC int +xrep_rtrmap_find_refcount_rmaps( + struct xrep_rtrmap *rr) +{ + struct xrgb_bitmap cow_blocks; /* COWBIT */ + struct xfs_refcount_irec low = { + .rc_startblock = 0, + .rc_domain = XFS_REFC_DOMAIN_COW, + }; + struct xfs_refcount_irec high = { + .rc_startblock = -1U, + .rc_domain = XFS_REFC_DOMAIN_COW, + }; + struct xfs_scrub *sc = rr->sc; + int error; + + if (!xfs_has_rtreflink(sc->mp)) + return 0; + + xrgb_bitmap_init(&cow_blocks); + + /* Collect rmaps for CoW staging extents. */ + error = xfs_refcount_query_range(sc->sr.refc_cur, &low, &high, + xrep_rtrmap_walk_cowblocks, &cow_blocks); + if (error) + goto out_bitmap; + + /* Generate rmaps for everything. */ + error = xrep_rtrmap_stash_bitmap(rr, &cow_blocks, &XFS_RMAP_OINFO_COW); + if (error) + goto out_bitmap; + +out_bitmap: + xrgb_bitmap_destroy(&cow_blocks); + return error; +} + +/* Count and check all collected records. */ +STATIC int +xrep_rtrmap_check_record( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + int error; + + error = xrep_rtrmap_check_mapping(rr->sc, rec); + if (error) + return error; + + rr->nr_records++; + return 0; +} + +/* Generate all the reverse-mappings for the realtime device. */ +STATIC int +xrep_rtrmap_find_rmaps( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_perag *pag = NULL; + struct xfs_inode *ip; + struct xfs_btree_cur *mcur; + int error; + + /* Generate rmaps for the realtime superblock */ + if (xfs_has_rtsb(sc->mp) && rtg_rgno(rr->sc->sr.rtg) == 0) { + error = xrep_rtrmap_stash(rr, 0, sc->mp->m_sb.sb_rextsize, + XFS_RMAP_OWN_FS, 0, 0); + if (error) + return error; + } + + /* Find CoW staging extents. */ + xrep_rtgroup_btcur_init(sc, &sc->sr); + error = xrep_rtrmap_find_refcount_rmaps(rr); + xchk_rtgroup_btcur_free(&sc->sr); + if (error) + return error; + + /* + * Set up for a potentially lengthy filesystem scan by reducing our + * transaction resource usage for the duration. Specifically: + * + * Unlock the realtime metadata inodes and cancel the transaction to + * release the log grant space while we scan the filesystem. + * + * Create a new empty transaction to eliminate the possibility of the + * inode scan deadlocking on cyclical metadata. + * + * We pass the empty transaction to the file scanning function to avoid + * repeatedly cycling empty transactions. This can be done even though + * we take the IOLOCK to quiesce the file because empty transactions + * do not take sb_internal. + */ + xchk_trans_cancel(sc); + xchk_rtgroup_unlock(&sc->sr); + error = xchk_trans_alloc_empty(sc); + if (error) + return error; + + while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) { + error = xrep_rtrmap_scan_inode(rr, ip); + xchk_irele(sc, ip); + if (error) + break; + + if (xchk_should_terminate(sc, &error)) + break; + } + xchk_iscan_iter_finish(&rr->iscan); + if (error) + return error; + + /* + * Switch out for a real transaction and lock the RT metadata in + * preparation for building a new tree. + */ + xchk_trans_cancel(sc); + error = xchk_setup_rt(sc); + if (error) + return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XCHK_RTGLOCK_ALL); + if (error) + return error; + + /* + * If a hook failed to update the in-memory btree, we lack the data to + * continue the repair. + */ + if (xchk_iscan_aborted(&rr->iscan)) + return -EFSCORRUPTED; + + /* Scan for old rtrmap blocks. */ + while ((pag = xfs_perag_next(sc->mp, pag))) { + error = xrep_rtrmap_scan_ag(rr, pag); + if (error) { + xfs_perag_rele(pag); + return error; + } + } + + /* + * Now that we have everything locked again, we need to count the + * number of rmap records stashed in the btree. This should reflect + * all actively-owned rt files in the filesystem. At the same time, + * check all our records before we start building a new btree, which + * requires the rtbitmap lock. + */ + mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, NULL, &rr->rtrmap_btree); + rr->nr_records = 0; + error = xfs_rmap_query_all(mcur, xrep_rtrmap_check_record, rr); + xfs_btree_del_cursor(mcur, error); + + return error; +} + +/* Building the new rtrmap btree. */ + +/* Retrieve rtrmapbt data for bulk load. */ +STATIC int +xrep_rtrmap_get_records( + struct xfs_btree_cur *cur, + unsigned int idx, + struct xfs_btree_block *block, + unsigned int nr_wanted, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + union xfs_btree_rec *block_rec; + unsigned int loaded; + int error; + + for (loaded = 0; loaded < nr_wanted; loaded++, idx++) { + int stat = 0; + + error = xfs_btree_increment(rr->mcur, 0, &stat); + if (error) + return error; + if (!stat) + return -EFSCORRUPTED; + + error = xfs_rmap_get_rec(rr->mcur, &cur->bc_rec.r, &stat); + if (error) + return error; + if (!stat) + return -EFSCORRUPTED; + + block_rec = xfs_btree_rec_addr(cur, idx, block); + cur->bc_ops->init_rec_from_cur(cur, block_rec); + } + + return loaded; +} + +/* Feed one of the new btree blocks to the bulk loader. */ +STATIC int +xrep_rtrmap_claim_block( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr, + void *priv) +{ + struct xrep_rtrmap *rr = priv; + + return xrep_newbt_claim_block(cur, &rr->new_btree, ptr); +} + +/* Figure out how much space we need to create the incore btree root block. */ +STATIC size_t +xrep_rtrmap_iroot_size( + struct xfs_btree_cur *cur, + unsigned int level, + unsigned int nr_this_level, + void *priv) +{ + return xfs_rtrmap_broot_space_calc(cur->bc_mp, level, nr_this_level); +} + +/* + * Use the collected rmap information to stage a new rmap btree. If this is + * successful we'll return with the new btree root information logged to the + * repair transaction but not yet committed. This implements section (III) + * above. + */ +STATIC int +xrep_rtrmap_build_new_tree( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + struct xfs_rtgroup *rtg = sc->sr.rtg; + struct xfs_btree_cur *rmap_cur; + int error; + + /* + * Prepare to construct the new btree by reserving disk space for the + * new btree and setting up all the accounting information we'll need + * to root the new btree while it's under construction and before we + * attach it to the realtime rmapbt inode. + */ + error = xrep_newbt_init_metadir_inode(&rr->new_btree, sc); + if (error) + return error; + + rr->new_btree.bload.get_records = xrep_rtrmap_get_records; + rr->new_btree.bload.claim_block = xrep_rtrmap_claim_block; + rr->new_btree.bload.iroot_size = xrep_rtrmap_iroot_size; + + rmap_cur = xfs_rtrmapbt_init_cursor(NULL, rtg); + xfs_btree_stage_ifakeroot(rmap_cur, &rr->new_btree.ifake); + + /* Compute how many blocks we'll need for the rmaps collected. */ + error = xfs_btree_bload_compute_geometry(rmap_cur, + &rr->new_btree.bload, rr->nr_records); + if (error) + goto err_cur; + + /* Last chance to abort before we start committing fixes. */ + if (xchk_should_terminate(sc, &error)) + goto err_cur; + + /* + * Guess how many blocks we're going to need to rebuild an entire + * rtrmapbt from the number of extents we found, and pump up our + * transaction to have sufficient block reservation. We're allowed + * to exceed quota to repair inconsistent metadata, though this is + * unlikely. + */ + error = xfs_trans_reserve_more_inode(sc->tp, rtg_rmap(rtg), + rr->new_btree.bload.nr_blocks, 0, true); + if (error) + goto err_cur; + + /* Reserve the space we'll need for the new btree. */ + error = xrep_newbt_alloc_blocks(&rr->new_btree, + rr->new_btree.bload.nr_blocks); + if (error) + goto err_cur; + + /* + * Create a cursor to the in-memory btree so that we can bulk load the + * new btree. + */ + rr->mcur = xfs_rtrmapbt_mem_cursor(sc->sr.rtg, NULL, &rr->rtrmap_btree); + error = xfs_btree_goto_left_edge(rr->mcur); + if (error) + goto err_mcur; + + /* Add all observed rmap records. */ + rr->new_btree.ifake.if_fork->if_format = XFS_DINODE_FMT_META_BTREE; + error = xfs_btree_bload(rmap_cur, &rr->new_btree.bload, rr); + if (error) + goto err_mcur; + + /* + * Install the new rtrmap btree in the inode. After this point the old + * btree is no longer accessible, the new tree is live, and we can + * delete the cursor. + */ + xfs_rtrmapbt_commit_staged_btree(rmap_cur, sc->tp); + xrep_inode_set_nblocks(rr->sc, rr->new_btree.ifake.if_blocks); + xfs_btree_del_cursor(rmap_cur, 0); + xfs_btree_del_cursor(rr->mcur, 0); + rr->mcur = NULL; + + /* + * Now that we've written the new btree to disk, we don't need to keep + * updating the in-memory btree. Abort the scan to stop live updates. + */ + xchk_iscan_abort(&rr->iscan); + + /* Dispose of any unused blocks and the accounting information. */ + error = xrep_newbt_commit(&rr->new_btree); + if (error) + return error; + + return xrep_roll_trans(sc); + +err_mcur: + xfs_btree_del_cursor(rr->mcur, error); +err_cur: + xfs_btree_del_cursor(rmap_cur, error); + xrep_newbt_cancel(&rr->new_btree); + return error; +} + +/* Reaping the old btree. */ + +/* Reap the old rtrmapbt blocks. */ +STATIC int +xrep_rtrmap_remove_old_tree( + struct xrep_rtrmap *rr) +{ + int error; + + /* + * Free all the extents that were allocated to the former rtrmapbt and + * aren't cross-linked with something else. + */ + error = xrep_reap_metadir_fsblocks(rr->sc, &rr->old_rtrmapbt_blocks); + if (error) + return error; + + /* + * Ensure the proper reservation for the rtrmap inode so that we don't + * fail to expand the new btree. + */ + return xrep_reset_metafile_resv(rr->sc); +} + +static inline bool +xrep_rtrmapbt_want_live_update( + struct xchk_iscan *iscan, + const struct xfs_owner_info *oi) +{ + if (xchk_iscan_aborted(iscan)) + return false; + + /* + * We scanned the CoW staging extents before we started the iscan, so + * we need all the updates. + */ + if (XFS_RMAP_NON_INODE_OWNER(oi->oi_owner)) + return true; + + /* Ignore updates to files that the scanner hasn't visited yet. */ + return xchk_iscan_want_live_update(iscan, oi->oi_owner); +} + +/* + * Apply a rtrmapbt update from the regular filesystem into our shadow btree. + * We're running from the thread that owns the rtrmap ILOCK and is generating + * the update, so we must be careful about which parts of the struct + * xrep_rtrmap that we change. + */ +static int +xrep_rtrmapbt_live_update( + struct notifier_block *nb, + unsigned long action, + void *data) +{ + struct xfs_rmap_update_params *p = data; + struct xrep_rtrmap *rr; + struct xfs_mount *mp; + struct xfs_btree_cur *mcur; + struct xfs_trans *tp; + void *txcookie; + int error; + + rr = container_of(nb, struct xrep_rtrmap, rhook.rmap_hook.nb); + mp = rr->sc->mp; + + if (!xrep_rtrmapbt_want_live_update(&rr->iscan, &p->oinfo)) + goto out_unlock; + + trace_xrep_rmap_live_update(rtg_group(rr->sc->sr.rtg), action, p); + + error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp); + if (error) + goto out_abort; + + mutex_lock(&rr->lock); + mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, tp, &rr->rtrmap_btree); + error = __xfs_rmap_finish_intent(mcur, action, p->startblock, + p->blockcount, &p->oinfo, p->unwritten); + xfs_btree_del_cursor(mcur, error); + if (error) + goto out_cancel; + + error = xfbtree_trans_commit(&rr->rtrmap_btree, tp); + if (error) + goto out_cancel; + + xrep_trans_cancel_hook_dummy(&txcookie, tp); + mutex_unlock(&rr->lock); + return NOTIFY_DONE; + +out_cancel: + xfbtree_trans_cancel(&rr->rtrmap_btree, tp); + xrep_trans_cancel_hook_dummy(&txcookie, tp); +out_abort: + xchk_iscan_abort(&rr->iscan); + mutex_unlock(&rr->lock); +out_unlock: + return NOTIFY_DONE; +} + +/* Set up the filesystem scan components. */ +STATIC int +xrep_rtrmap_setup_scan( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + int error; + + mutex_init(&rr->lock); + xfsb_bitmap_init(&rr->old_rtrmapbt_blocks); + + /* Set up some storage */ + error = xfs_rtrmapbt_mem_init(sc->mp, &rr->rtrmap_btree, sc->xmbtp, + rtg_rgno(sc->sr.rtg)); + if (error) + goto out_bitmap; + + /* Retry iget every tenth of a second for up to 30 seconds. */ + xchk_iscan_start(sc, 30000, 100, &rr->iscan); + + /* + * Hook into live rtrmap operations so that we can update our in-memory + * btree to reflect live changes on the filesystem. Since we drop the + * rtrmap ILOCK to scan all the inodes, we need this piece to avoid + * installing a stale btree. + */ + ASSERT(sc->flags & XCHK_FSGATES_RMAP); + xfs_rmap_hook_setup(&rr->rhook, xrep_rtrmapbt_live_update); + error = xfs_rmap_hook_add(rtg_group(sc->sr.rtg), &rr->rhook); + if (error) + goto out_iscan; + return 0; + +out_iscan: + xchk_iscan_teardown(&rr->iscan); + xfbtree_destroy(&rr->rtrmap_btree); +out_bitmap: + xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks); + mutex_destroy(&rr->lock); + return error; +} + +/* Tear down scan components. */ +STATIC void +xrep_rtrmap_teardown( + struct xrep_rtrmap *rr) +{ + struct xfs_scrub *sc = rr->sc; + + xchk_iscan_abort(&rr->iscan); + xfs_rmap_hook_del(rtg_group(sc->sr.rtg), &rr->rhook); + xchk_iscan_teardown(&rr->iscan); + xfbtree_destroy(&rr->rtrmap_btree); + xfsb_bitmap_destroy(&rr->old_rtrmapbt_blocks); + mutex_destroy(&rr->lock); +} + +/* Repair the realtime rmap btree. */ +int +xrep_rtrmapbt( + struct xfs_scrub *sc) +{ + struct xrep_rtrmap *rr = sc->buf; + int error; + + /* Make sure any problems with the fork are fixed. */ + error = xrep_metadata_inode_forks(sc); + if (error) + return error; + + error = xrep_rtrmap_setup_scan(rr); + if (error) + return error; + + /* Collect rmaps for realtime files. */ + error = xrep_rtrmap_find_rmaps(rr); + if (error) + goto out_records; + + xfs_trans_ijoin(sc->tp, sc->ip, 0); + + /* Rebuild the rtrmap information. */ + error = xrep_rtrmap_build_new_tree(rr); + if (error) + goto out_records; + + /* Kill the old tree. */ + error = xrep_rtrmap_remove_old_tree(rr); + if (error) + goto out_records; + +out_records: + xrep_rtrmap_teardown(rr); + return error; +} diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c index 49fc6250bafc..4ac679c1bd29 100644 --- a/fs/xfs/scrub/rtsummary.c +++ b/fs/xfs/scrub/rtsummary.c @@ -81,8 +81,7 @@ xchk_setup_rtsummary( if (error) return error; - error = xchk_install_live_inode(sc, - sc->sr.rtg->rtg_inodes[XFS_RTGI_SUMMARY]); + error = xchk_install_live_inode(sc, rtg_summary(sc->sr.rtg)); if (error) return error; @@ -90,6 +89,10 @@ xchk_setup_rtsummary( if (error) return error; + error = xchk_rtgroup_lock(sc, &sc->sr, XFS_RTGLOCK_BITMAP); + if (error) + return error; + /* * Now that we've locked the rtbitmap and rtsummary, we can't race with * growfsrt trying to expand the summary or change the size of the rt @@ -100,7 +103,6 @@ xchk_setup_rtsummary( * exclusively here. If we ever start caring about running concurrent * fsmap with scrub this could be changed. */ - xchk_rtgroup_lock(&sc->sr, XFS_RTGLOCK_BITMAP); if (mp->m_sb.sb_rblocks) { rts->rextents = xfs_blen_to_rtbxlen(mp, mp->m_sb.sb_rblocks); rts->rbmblocks = xfs_rtbitmap_blockcount(mp); @@ -191,8 +193,7 @@ xchk_rtsum_record_free( rtlen = xfs_rtxlen_to_extlen(mp, rec->ar_extcount); if (!xfs_verify_rtbext(mp, rtbno, rtlen)) { - xchk_ino_xref_set_corrupt(sc, - rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_ino); + xchk_ino_xref_set_corrupt(sc, rtg_bitmap(rtg)->i_ino); return -EFSCORRUPTED; } @@ -218,7 +219,7 @@ xchk_rtsum_compute( /* If the bitmap size doesn't match the computed size, bail. */ if (XFS_FSB_TO_B(mp, xfs_rtbitmap_blockcount(mp)) != - rtg->rtg_inodes[XFS_RTGI_BITMAP]->i_disk_size) + rtg_bitmap(rtg)->i_disk_size) return -EFSCORRUPTED; return xfs_rtalloc_query_all(rtg, sc->tp, xchk_rtsum_record_free, sc); @@ -310,8 +311,8 @@ xchk_rtsummary( { struct xfs_mount *mp = sc->mp; struct xfs_rtgroup *rtg = sc->sr.rtg; - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); struct xchk_rtsummary *rts = sc->buf; int error; diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c index 8198ea84ad70..d593977d70df 100644 --- a/fs/xfs/scrub/rtsummary_repair.c +++ b/fs/xfs/scrub/rtsummary_repair.c @@ -165,7 +165,8 @@ xrep_rtsummary( * Now exchange the contents. Nothing in repair uses the temporary * buffer, so we can reuse it for the tempfile exchrange information. */ - error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, &rts->tempexch); + error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, + rts->rsumblocks, &rts->tempexch); if (error) return error; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 950f5a58dcd9..7567dd5cad14 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -164,7 +164,7 @@ xchk_fsgates_disable( trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL); if (sc->flags & XCHK_FSGATES_DRAIN) - xfs_drain_wait_disable(); + xfs_defer_drain_wait_disable(); if (sc->flags & XCHK_FSGATES_QUOTA) xfs_dqtrx_hook_disable(); @@ -218,6 +218,8 @@ xchk_teardown( int error) { xchk_ag_free(sc, &sc->sa); + xchk_rtgroup_btcur_free(&sc->sr); + if (sc->tp) { if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)) error = xfs_trans_commit(sc->tp); @@ -458,6 +460,20 @@ static const struct xchk_meta_ops meta_scrub_ops[] = { .has = xfs_has_rtsb, .repair = xrep_rgsuperblock, }, + [XFS_SCRUB_TYPE_RTRMAPBT] = { /* realtime group rmapbt */ + .type = ST_RTGROUP, + .setup = xchk_setup_rtrmapbt, + .scrub = xchk_rtrmapbt, + .has = xfs_has_rtrmapbt, + .repair = xrep_rtrmapbt, + }, + [XFS_SCRUB_TYPE_RTREFCBT] = { /* realtime refcountbt */ + .type = ST_RTGROUP, + .setup = xchk_setup_rtrefcountbt, + .scrub = xchk_rtrefcountbt, + .has = xfs_has_rtreflink, + .repair = xrep_rtrefcountbt, + }, }; static int diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index a7fda3e2b013..a3f1abc91390 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -96,7 +96,7 @@ struct xchk_meta_ops { int (*repair_eval)(struct xfs_scrub *sc); /* Decide if we even have this piece of metadata. */ - bool (*has)(struct xfs_mount *); + bool (*has)(const struct xfs_mount *); /* type describing required/allowed inputs */ enum xchk_type type; @@ -126,6 +126,10 @@ struct xchk_rt { /* XFS_RTGLOCK_* lock state if locked */ unsigned int rtlock_flags; + + /* rtgroup btrees */ + struct xfs_btree_cur *rmap_cur; + struct xfs_btree_cur *refc_cur; }; struct xfs_scrub { @@ -184,6 +188,12 @@ struct xfs_scrub { */ unsigned int sick_mask; + /* + * Clear these XFS_SICK_* flags but only if the scan is ok. Useful for + * removing ZAPPED flags after a repair. + */ + unsigned int healthy_mask; + /* next time we want to cond_resched() */ struct xchk_relax relax; @@ -274,10 +284,14 @@ int xchk_metapath(struct xfs_scrub *sc); int xchk_rtbitmap(struct xfs_scrub *sc); int xchk_rtsummary(struct xfs_scrub *sc); int xchk_rgsuperblock(struct xfs_scrub *sc); +int xchk_rtrmapbt(struct xfs_scrub *sc); +int xchk_rtrefcountbt(struct xfs_scrub *sc); #else # define xchk_rtbitmap xchk_nothing # define xchk_rtsummary xchk_nothing # define xchk_rgsuperblock xchk_nothing +# define xchk_rtrmapbt xchk_nothing +# define xchk_rtrefcountbt xchk_nothing #endif #ifdef CONFIG_XFS_QUOTA int xchk_quota(struct xfs_scrub *sc); @@ -311,8 +325,26 @@ void xchk_xref_is_not_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno, #ifdef CONFIG_XFS_RT void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno, xfs_extlen_t len); +void xchk_xref_has_no_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_has_rt_owner(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_only_rt_owned_by(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len, const struct xfs_owner_info *oinfo); +void xchk_xref_is_rt_cow_staging(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_not_rt_shared(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); +void xchk_xref_is_not_rt_cow_staging(struct xfs_scrub *sc, xfs_rgblock_t rgbno, + xfs_extlen_t len); #else # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0) +# define xchk_xref_has_no_rt_owner(sc, rtbno, len) do { } while (0) +# define xchk_xref_has_rt_owner(sc, rtbno, len) do { } while (0) +# define xchk_xref_is_only_rt_owned_by(sc, bno, len, oinfo) do { } while (0) +# define xchk_xref_is_rt_cow_staging(sc, bno, len) do { } while (0) +# define xchk_xref_is_not_rt_shared(sc, bno, len) do { } while (0) +# define xchk_xref_is_not_rt_cow_staging(sc, bno, len) do { } while (0) #endif #endif /* __XFS_SCRUB_SCRUB_H__ */ diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index a476c7b2ab75..f8a37ea97791 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -82,6 +82,8 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_DIRTREE] = "dirtree", [XFS_SCRUB_TYPE_METAPATH] = "metapath", [XFS_SCRUB_TYPE_RGSUPER] = "rgsuper", + [XFS_SCRUB_TYPE_RTRMAPBT] = "rtrmapbt", + [XFS_SCRUB_TYPE_RTREFCBT] = "rtrefcountbt", }; /* Format the scrub stats into a text buffer, similar to pcp style. */ diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index d015a86ef460..953ce7be78dc 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -36,6 +36,7 @@ #include "scrub/tempfile.h" #include "scrub/tempexch.h" #include "scrub/reap.h" +#include "scrub/health.h" /* * Symbolic Link Repair @@ -233,7 +234,7 @@ xrep_symlink_salvage( * target zapped flag. */ if (buflen == 0) { - sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED; + xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED); sprintf(target_buf, DUMMY_TARGET); } diff --git a/fs/xfs/scrub/tempexch.h b/fs/xfs/scrub/tempexch.h index 995ba187c5aa..eccda720c2ca 100644 --- a/fs/xfs/scrub/tempexch.h +++ b/fs/xfs/scrub/tempexch.h @@ -12,7 +12,7 @@ struct xrep_tempexch { }; int xrep_tempexch_trans_reserve(struct xfs_scrub *sc, int whichfork, - struct xrep_tempexch *ti); + xfs_fileoff_t off, xfs_filblks_t len, struct xrep_tempexch *ti); int xrep_tempexch_trans_alloc(struct xfs_scrub *sc, int whichfork, struct xrep_tempexch *ti); diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 4b7f7860e37e..cf99e0ca51b0 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -184,11 +184,18 @@ out_release_dquots: } /* + * Move sc->tempip from the regular directory tree to the metadata directory + * tree if sc->ip is part of the metadata directory tree and tempip has an + * eligible file mode. + * * Temporary files have to be created before we even know which inode we're * going to scrub, so we assume that they will be part of the regular directory * tree. If it turns out that we're actually scrubbing a file from the * metadata directory tree, we have to subtract the temp file from the root - * dquots and detach the dquots. + * dquots and detach the dquots prior to setting the METADATA iflag. However, + * the scrub setup functions grab sc->ip and create sc->tempip before we + * actually get around to checking if the file mode is the right type for the + * scrubber. */ int xrep_tempfile_adjust_directory_tree( @@ -204,6 +211,9 @@ xrep_tempfile_adjust_directory_tree( if (!sc->ip || !xfs_is_metadir_inode(sc->ip)) return 0; + if (!S_ISDIR(VFS_I(sc->tempip)->i_mode) && + !S_ISREG(VFS_I(sc->tempip)->i_mode)) + return 0; xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL); sc->temp_ilock_flags |= XFS_IOLOCK_EXCL; @@ -223,6 +233,7 @@ xrep_tempfile_adjust_directory_tree( if (error) goto out_ilock; + xfs_iflags_set(sc->tempip, XFS_IRECOVERY); xfs_qm_dqdetach(sc->tempip); out_ilock: xrep_tempfile_iunlock(sc); @@ -246,6 +257,8 @@ xrep_tempfile_remove_metadir( ASSERT(sc->tp == NULL); + xfs_iflags_clear(sc->tempip, XFS_IRECOVERY); + xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL); sc->temp_ilock_flags |= XFS_IOLOCK_EXCL; @@ -593,6 +606,8 @@ STATIC int xrep_tempexch_prep_request( struct xfs_scrub *sc, int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, struct xrep_tempexch *tx) { struct xfs_exchmaps_req *req = &tx->req; @@ -616,18 +631,19 @@ xrep_tempexch_prep_request( /* Exchange all mappings in both forks. */ req->ip1 = sc->tempip; req->ip2 = sc->ip; - req->startoff1 = 0; - req->startoff2 = 0; + req->startoff1 = off; + req->startoff2 = off; switch (whichfork) { case XFS_ATTR_FORK: req->flags |= XFS_EXCHMAPS_ATTR_FORK; break; case XFS_DATA_FORK: - /* Always exchange sizes when exchanging data fork mappings. */ - req->flags |= XFS_EXCHMAPS_SET_SIZES; + /* Exchange sizes when exchanging all data fork mappings. */ + if (off == 0 && len == XFS_MAX_FILEOFF) + req->flags |= XFS_EXCHMAPS_SET_SIZES; break; } - req->blockcount = XFS_MAX_FILEOFF; + req->blockcount = len; return 0; } @@ -736,6 +752,7 @@ xrep_tempexch_reserve_quota( * or the two inodes have the same dquots. */ if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 || + xfs_is_metadir_inode(req->ip1) || (req->ip1->i_udquot == req->ip2->i_udquot && req->ip1->i_gdquot == req->ip2->i_gdquot && req->ip1->i_pdquot == req->ip2->i_pdquot)) @@ -782,6 +799,8 @@ int xrep_tempexch_trans_reserve( struct xfs_scrub *sc, int whichfork, + xfs_fileoff_t off, + xfs_filblks_t len, struct xrep_tempexch *tx) { int error; @@ -790,7 +809,7 @@ xrep_tempexch_trans_reserve( xfs_assert_ilocked(sc->ip, XFS_ILOCK_EXCL); xfs_assert_ilocked(sc->tempip, XFS_ILOCK_EXCL); - error = xrep_tempexch_prep_request(sc, whichfork, tx); + error = xrep_tempexch_prep_request(sc, whichfork, off, len, tx); if (error) return error; @@ -828,7 +847,8 @@ xrep_tempexch_trans_alloc( ASSERT(sc->tp == NULL); ASSERT(xfs_has_exchange_range(sc->mp)); - error = xrep_tempexch_prep_request(sc, whichfork, tx); + error = xrep_tempexch_prep_request(sc, whichfork, 0, XFS_MAX_FILEOFF, + tx); if (error) return error; @@ -945,10 +965,13 @@ xrep_is_tempfile( /* * Files in the metadata directory tree also have S_PRIVATE set and - * IOP_XATTR unset, so we must distinguish them separately. + * IOP_XATTR unset, so we must distinguish them separately. We (ab)use + * the IRECOVERY flag to mark temporary metadir inodes knowing that the + * end of log recovery clears IRECOVERY, so the only ones that can + * exist during online repair are the ones we create. */ if (xfs_has_metadir(mp) && (ip->i_diflags2 & XFS_DIFLAG2_METADATA)) - return false; + return __xfs_iflags_test(ip, XFS_IRECOVERY); if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR)) return true; diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 98f923ae664d..2450e214103f 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -21,6 +21,7 @@ #include "xfs_rmap.h" #include "xfs_parent.h" #include "xfs_metafile.h" +#include "xfs_rtgroup.h" #include "scrub/scrub.h" #include "scrub/xfile.h" #include "scrub/xfarray.h" diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 9b38f5ad1eaf..d7c4ced47c15 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -17,6 +17,7 @@ #include "xfs_bit.h" #include "xfs_quota_defs.h" +struct xfs_rtgroup; struct xfs_scrub; struct xfile; struct xfarray; @@ -40,6 +41,9 @@ struct xchk_dirtree_outcomes; TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); +TRACE_DEFINE_ENUM(XG_TYPE_AG); +TRACE_DEFINE_ENUM(XG_TYPE_RTG); + TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF); @@ -72,6 +76,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_DIRTREE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_BARRIER); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_METAPATH); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTRMAPBT); +TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RTREFCBT); #define XFS_SCRUB_TYPE_STRINGS \ { XFS_SCRUB_TYPE_PROBE, "probe" }, \ @@ -105,7 +111,9 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_RGSUPER); { XFS_SCRUB_TYPE_DIRTREE, "dirtree" }, \ { XFS_SCRUB_TYPE_BARRIER, "barrier" }, \ { XFS_SCRUB_TYPE_METAPATH, "metapath" }, \ - { XFS_SCRUB_TYPE_RGSUPER, "rgsuper" } + { XFS_SCRUB_TYPE_RGSUPER, "rgsuper" }, \ + { XFS_SCRUB_TYPE_RTRMAPBT, "rtrmapbt" }, \ + { XFS_SCRUB_TYPE_RTREFCBT, "rtrefcountbt" } #define XFS_SCRUB_FLAG_STRINGS \ { XFS_SCRUB_IFLAG_REPAIR, "repair" }, \ @@ -605,7 +613,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error, TP_fast_assign( xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level); __entry->dev = sc->mp->m_super->s_dev; - __entry->ino = sc->ip->i_ino; + __entry->ino = cur->bc_ino.ip->i_ino; __entry->whichfork = cur->bc_ino.whichfork; __entry->type = sc->sm->sm_type; __assign_str(name); @@ -1956,32 +1964,36 @@ DEFINE_XCHK_METAPATH_EVENT(xchk_metapath_lookup); #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) DECLARE_EVENT_CLASS(xrep_extent_class, - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len), - TP_ARGS(pag, agbno, len), + TP_ARGS(xg, agbno, len), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len) ); #define DEFINE_REPAIR_EXTENT_EVENT(name) \ DEFINE_EVENT(xrep_extent_class, name, \ - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \ + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len), \ - TP_ARGS(pag, agbno, len)) + TP_ARGS(xg, agbno, len)) DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent); DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent); DEFINE_REPAIR_EXTENT_EVENT(xreap_agextent_binval); @@ -1989,35 +2001,39 @@ DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval); DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert); DECLARE_EVENT_CLASS(xrep_reap_find_class, - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len, bool crosslinked), - TP_ARGS(pag, agbno, len, crosslinked), + TP_ARGS(xg, agbno, len, crosslinked), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) __field(bool, crosslinked) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; __entry->crosslinked = crosslinked; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x crosslinked %d", + TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x crosslinked %d", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->crosslinked ? 1 : 0) ); #define DEFINE_REPAIR_REAP_FIND_EVENT(name) \ DEFINE_EVENT(xrep_reap_find_class, name, \ - TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, \ + TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len, bool crosslinked), \ - TP_ARGS(pag, agbno, len, crosslinked)) + TP_ARGS(xg, agbno, len, crosslinked)) DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select); DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select); @@ -2108,29 +2124,33 @@ TRACE_EVENT(xrep_ibt_found, ) TRACE_EVENT(xrep_refc_found, - TP_PROTO(const struct xfs_perag *pag, + TP_PROTO(const struct xfs_group *xg, const struct xfs_refcount_irec *rec), - TP_ARGS(pag, rec), + TP_ARGS(xg, rec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) + __field(enum xfs_group_type, type) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->agno = xg->xg_gno; + __entry->type = xg->xg_type; __entry->domain = rec->rc_domain; __entry->startblock = rec->rc_startblock; __entry->blockcount = rec->rc_blockcount; __entry->refcount = rec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s %sbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount) @@ -2282,6 +2302,32 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize, __entry->rmapbt_sz, __entry->refcbt_sz) ) + +#ifdef CONFIG_XFS_RT +TRACE_EVENT(xrep_calc_rtgroup_resblks_btsize, + TP_PROTO(struct xfs_mount *mp, xfs_rgnumber_t rgno, + xfs_rgblock_t usedlen, xfs_rgblock_t rmapbt_sz), + TP_ARGS(mp, rgno, usedlen, rmapbt_sz), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_rgblock_t, usedlen) + __field(xfs_rgblock_t, rmapbt_sz) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rgno = rgno; + __entry->usedlen = usedlen; + __entry->rmapbt_sz = rmapbt_sz; + ), + TP_printk("dev %d:%d rgno 0x%x usedlen %u rmapbt %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rgno, + __entry->usedlen, + __entry->rmapbt_sz) +); +#endif /* CONFIG_XFS_RT */ + TRACE_EVENT(xrep_reset_counters, TP_PROTO(struct xfs_mount *mp, struct xchk_fscounters *fsc), TP_ARGS(mp, fsc), @@ -2680,11 +2726,12 @@ DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode); DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode); TRACE_EVENT(xrep_rmap_live_update, - TP_PROTO(const struct xfs_perag *pag, unsigned int op, + TP_PROTO(const struct xfs_group *xg, unsigned int op, const struct xfs_rmap_update_params *p), - TP_ARGS(pag, op, p), + TP_ARGS(xg, op, p), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(unsigned int, op) __field(xfs_agblock_t, agbno) @@ -2694,8 +2741,9 @@ TRACE_EVENT(xrep_rmap_live_update, __field(unsigned int, flags) ), TP_fast_assign( - __entry->dev = pag_mount(pag)->m_super->s_dev; - __entry->agno = pag_agno(pag); + __entry->dev = xg->xg_mount->m_super->s_dev; + __entry->type = xg->xg_type; + __entry->agno = xg->xg_gno; __entry->op = op; __entry->agbno = p->startblock; __entry->len = p->blockcount; @@ -2704,10 +2752,12 @@ TRACE_EVENT(xrep_rmap_live_update, if (p->unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), - TP_printk("dev %d:%d agno 0x%x op %d agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d %sno 0x%x op %d %sbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->op, + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->owner, @@ -3605,6 +3655,186 @@ DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_try_unlink); DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_unlink); DEFINE_XCHK_METAPATH_EVENT(xrep_metapath_link); +#ifdef CONFIG_XFS_RT +DECLARE_EVENT_CLASS(xrep_rtbitmap_class, + TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, xfs_rtxnum_t end), + TP_ARGS(mp, start, end), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rtxnum_t, start) + __field(xfs_rtxnum_t, end) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->start = start; + __entry->end = end; + ), + TP_printk("dev %d:%d rtdev %d:%d startrtx 0x%llx endrtx 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->start, + __entry->end) +); +#define DEFINE_REPAIR_RGBITMAP_EVENT(name) \ +DEFINE_EVENT(xrep_rtbitmap_class, name, \ + TP_PROTO(struct xfs_mount *mp, xfs_rtxnum_t start, \ + xfs_rtxnum_t end), \ + TP_ARGS(mp, start, end)) +DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free); +DEFINE_REPAIR_RGBITMAP_EVENT(xrep_rtbitmap_record_free_bulk); + +TRACE_EVENT(xrep_rtbitmap_or, + TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff, + xfs_rtword_t mask, xfs_rtword_t word), + TP_ARGS(mp, wordoff, mask, word), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(unsigned long long, wordoff) + __field(unsigned int, mask) + __field(unsigned int, word) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->wordoff = wordoff; + __entry->mask = mask; + __entry->word = word; + ), + TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx mask 0x%x word 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->wordoff, + __entry->mask, + __entry->word) +); + +TRACE_EVENT(xrep_rtbitmap_load, + TP_PROTO(struct xfs_rtgroup *rtg, xfs_fileoff_t rbmoff, + xfs_rtxnum_t rtx, xfs_rtxnum_t len), + TP_ARGS(rtg, rbmoff, rtx, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rgnumber_t, rgno) + __field(xfs_fileoff_t, rbmoff) + __field(xfs_rtxnum_t, rtx) + __field(xfs_rtxnum_t, len) + ), + TP_fast_assign( + __entry->dev = rtg_mount(rtg)->m_super->s_dev; + __entry->rtdev = rtg_mount(rtg)->m_rtdev_targp->bt_dev; + __entry->rgno = rtg_rgno(rtg); + __entry->rbmoff = rbmoff; + __entry->rtx = rtx; + __entry->len = len; + ), + TP_printk("dev %d:%d rtdev %d:%d rgno 0x%x rbmoff 0x%llx rtx 0x%llx rtxcount 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rgno, + __entry->rbmoff, + __entry->rtx, + __entry->len) +); + +TRACE_EVENT(xrep_rtbitmap_load_words, + TP_PROTO(struct xfs_mount *mp, xfs_fileoff_t rbmoff, + unsigned long long wordoff, unsigned int wordcnt), + TP_ARGS(mp, rbmoff, wordoff, wordcnt), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_fileoff_t, rbmoff) + __field(unsigned long long, wordoff) + __field(unsigned int, wordcnt) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->rbmoff = rbmoff; + __entry->wordoff = wordoff; + __entry->wordcnt = wordcnt; + ), + TP_printk("dev %d:%d rtdev %d:%d rbmoff 0x%llx wordoff 0x%llx wordcnt 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rbmoff, + __entry->wordoff, + __entry->wordcnt) +); + +TRACE_EVENT(xrep_rtbitmap_load_word, + TP_PROTO(struct xfs_mount *mp, unsigned long long wordoff, + unsigned int bit, xfs_rtword_t ondisk_word, + xfs_rtword_t xfile_word, xfs_rtword_t word_mask), + TP_ARGS(mp, wordoff, bit, ondisk_word, xfile_word, word_mask), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(unsigned long long, wordoff) + __field(unsigned int, bit) + __field(xfs_rtword_t, ondisk_word) + __field(xfs_rtword_t, xfile_word) + __field(xfs_rtword_t, word_mask) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->wordoff = wordoff; + __entry->bit = bit; + __entry->ondisk_word = ondisk_word; + __entry->xfile_word = xfile_word; + __entry->word_mask = word_mask; + ), + TP_printk("dev %d:%d rtdev %d:%d wordoff 0x%llx bit %u ondisk 0x%x(0x%x) inmem 0x%x(0x%x) result 0x%x mask 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->wordoff, + __entry->bit, + __entry->ondisk_word, + __entry->ondisk_word & __entry->word_mask, + __entry->xfile_word, + __entry->xfile_word & ~__entry->word_mask, + (__entry->xfile_word & ~__entry->word_mask) | + (__entry->ondisk_word & __entry->word_mask), + __entry->word_mask) +); + +TRACE_EVENT(xrep_rtrmap_found, + TP_PROTO(struct xfs_mount *mp, const struct xfs_rmap_irec *rec), + TP_ARGS(mp, rec), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, rtdev) + __field(xfs_rgblock_t, rgbno) + __field(xfs_extlen_t, len) + __field(uint64_t, owner) + __field(uint64_t, offset) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->rtdev = mp->m_rtdev_targp->bt_dev; + __entry->rgbno = rec->rm_startblock; + __entry->len = rec->rm_blockcount; + __entry->owner = rec->rm_owner; + __entry->offset = rec->rm_offset; + __entry->flags = rec->rm_flags; + ), + TP_printk("dev %d:%d rtdev %d:%d rgbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->rtdev), MINOR(__entry->rtdev), + __entry->rgbno, + __entry->len, + __entry->owner, + __entry->offset, + __entry->flags) +); +#endif /* CONFIG_XFS_RT */ + #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */ #endif /* _TRACE_XFS_SCRUB_TRACE_H */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 559a3a577097..67877c36ed11 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -131,7 +131,7 @@ xfs_end_ioend( error = xfs_iomap_write_unwritten(ip, offset, size, false); if (!error && xfs_ioend_is_append(ioend)) - error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); + error = xfs_setfilesize(ip, offset, size); done: iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 24fb12986a56..319004bf089f 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -305,11 +305,6 @@ xfs_attr3_root_inactive( 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); - return error; - } xfs_trans_binval(*trans, bp); /* remove from cache */ /* * Commit the invalidate and start the next transaction. diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a59bbe767a7d..0836fea2d6d8 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -103,7 +103,7 @@ xfs_bmap_count_blocks( struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; - xfs_extlen_t btblocks = 0; + xfs_filblks_t btblocks = 0; int error; *nextents = 0; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index aa63b8efd782..7fbdd4b30676 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -22,6 +22,7 @@ #include "xfs_error.h" #include "xfs_ag.h" #include "xfs_buf_mem.h" +#include "xfs_notify_failure.h" struct kmem_cache *xfs_buf_cache; @@ -52,14 +53,8 @@ struct kmem_cache *xfs_buf_cache; * b_lock (trylock due to inversion) */ -static int __xfs_buf_submit(struct xfs_buf *bp, bool wait); - -static inline int -xfs_buf_submit( - struct xfs_buf *bp) -{ - return __xfs_buf_submit(bp, !(bp->b_flags & XBF_ASYNC)); -} +static void xfs_buf_submit(struct xfs_buf *bp); +static int xfs_buf_iowait(struct xfs_buf *bp); static inline bool xfs_buf_is_uncached(struct xfs_buf *bp) { @@ -132,15 +127,6 @@ __xfs_buf_ioacct_dec( } } -static inline void -xfs_buf_ioacct_dec( - struct xfs_buf *bp) -{ - spin_lock(&bp->b_lock); - __xfs_buf_ioacct_dec(bp); - spin_unlock(&bp->b_lock); -} - /* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer @@ -176,9 +162,9 @@ xfs_buf_stale( atomic_set(&bp->b_lru_ref, 0); if (!(bp->b_state & XFS_BSTATE_DISPOSE) && (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru))) - atomic_dec(&bp->b_hold); + bp->b_hold--; - ASSERT(atomic_read(&bp->b_hold) >= 1); + ASSERT(bp->b_hold >= 1); spin_unlock(&bp->b_lock); } @@ -202,9 +188,6 @@ xfs_buf_get_maps( return 0; } -/* - * Frees b_pages if it was allocated. - */ static void xfs_buf_free_maps( struct xfs_buf *bp) @@ -237,14 +220,14 @@ _xfs_buf_alloc( */ flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); - atomic_set(&bp->b_hold, 1); + spin_lock_init(&bp->b_lock); + bp->b_hold = 1; atomic_set(&bp->b_lru_ref, 1); init_completion(&bp->b_iowait); INIT_LIST_HEAD(&bp->b_lru); INIT_LIST_HEAD(&bp->b_list); INIT_LIST_HEAD(&bp->b_li_list); sema_init(&bp->b_sema, 0); /* held, no waiters */ - spin_lock_init(&bp->b_lock); bp->b_target = target; bp->b_mount = target->bt_mount; bp->b_flags = flags; @@ -588,6 +571,20 @@ xfs_buf_find_lock( return 0; } +static bool +xfs_buf_try_hold( + struct xfs_buf *bp) +{ + spin_lock(&bp->b_lock); + if (bp->b_hold == 0) { + spin_unlock(&bp->b_lock); + return false; + } + bp->b_hold++; + spin_unlock(&bp->b_lock); + return true; +} + static inline int xfs_buf_lookup( struct xfs_buf_cache *bch, @@ -600,7 +597,7 @@ xfs_buf_lookup( rcu_read_lock(); bp = rhashtable_lookup(&bch->bc_hash, map, xfs_buf_hash_params); - if (!bp || !atomic_inc_not_zero(&bp->b_hold)) { + if (!bp || !xfs_buf_try_hold(bp)) { rcu_read_unlock(); return -ENOENT; } @@ -663,9 +660,8 @@ xfs_buf_find_insert( spin_unlock(&bch->bc_lock); goto out_free_buf; } - if (bp) { + if (bp && xfs_buf_try_hold(bp)) { /* found an existing buffer */ - atomic_inc(&bp->b_hold); spin_unlock(&bch->bc_lock); error = xfs_buf_find_lock(bp, flags); if (error) @@ -806,7 +802,10 @@ _xfs_buf_read( bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE); bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - return xfs_buf_submit(bp); + xfs_buf_submit(bp); + if (flags & XBF_ASYNC) + return 0; + return xfs_buf_iowait(bp); } /* @@ -982,8 +981,8 @@ xfs_buf_read_uncached( bp->b_ops = ops; xfs_buf_submit(bp); - if (bp->b_error) { - error = bp->b_error; + error = xfs_buf_iowait(bp); + if (error) { xfs_buf_relse(bp); return error; } @@ -1043,7 +1042,10 @@ xfs_buf_hold( struct xfs_buf *bp) { trace_xfs_buf_hold(bp, _RET_IP_); - atomic_inc(&bp->b_hold); + + spin_lock(&bp->b_lock); + bp->b_hold++; + spin_unlock(&bp->b_lock); } static void @@ -1051,10 +1053,15 @@ xfs_buf_rele_uncached( struct xfs_buf *bp) { ASSERT(list_empty(&bp->b_lru)); - if (atomic_dec_and_test(&bp->b_hold)) { - xfs_buf_ioacct_dec(bp); - xfs_buf_free(bp); + + spin_lock(&bp->b_lock); + if (--bp->b_hold) { + spin_unlock(&bp->b_lock); + return; } + __xfs_buf_ioacct_dec(bp); + spin_unlock(&bp->b_lock); + xfs_buf_free(bp); } static void @@ -1064,51 +1071,40 @@ xfs_buf_rele_cached( struct xfs_buftarg *btp = bp->b_target; struct xfs_perag *pag = bp->b_pag; struct xfs_buf_cache *bch = xfs_buftarg_buf_cache(btp, pag); - bool release; bool freebuf = false; trace_xfs_buf_rele(bp, _RET_IP_); - ASSERT(atomic_read(&bp->b_hold) > 0); - - /* - * We grab the b_lock here first to serialise racing xfs_buf_rele() - * calls. The pag_buf_lock being taken on the last reference only - * serialises against racing lookups in xfs_buf_find(). IOWs, the second - * to last reference we drop here is not serialised against the last - * reference until we take bp->b_lock. Hence if we don't grab b_lock - * first, the last "release" reference can win the race to the lock and - * free the buffer before the second-to-last reference is processed, - * leading to a use-after-free scenario. - */ spin_lock(&bp->b_lock); - release = atomic_dec_and_lock(&bp->b_hold, &bch->bc_lock); - if (!release) { + ASSERT(bp->b_hold >= 1); + if (bp->b_hold > 1) { /* * Drop the in-flight state if the buffer is already on the LRU * and it holds the only reference. This is racy because we * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT * ensures the decrement occurs only once per-buf. */ - if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru)) + if (--bp->b_hold == 1 && !list_empty(&bp->b_lru)) __xfs_buf_ioacct_dec(bp); goto out_unlock; } - /* the last reference has been dropped ... */ + /* we are asked to drop the last reference */ + spin_lock(&bch->bc_lock); __xfs_buf_ioacct_dec(bp); if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { /* - * If the buffer is added to the LRU take a new reference to the + * If the buffer is added to the LRU, keep the reference to the * buffer for the LRU and clear the (now stale) dispose list - * state flag + * state flag, else drop the reference. */ - if (list_lru_add_obj(&btp->bt_lru, &bp->b_lru)) { + if (list_lru_add_obj(&btp->bt_lru, &bp->b_lru)) bp->b_state &= ~XFS_BSTATE_DISPOSE; - atomic_inc(&bp->b_hold); - } + else + bp->b_hold--; spin_unlock(&bch->bc_lock); } else { + bp->b_hold--; /* * most of the time buffers will already be removed from the * LRU, so optimise that case by checking for the @@ -1291,6 +1287,7 @@ xfs_buf_ioend_handle_error( { struct xfs_mount *mp = bp->b_mount; struct xfs_error_cfg *cfg; + struct xfs_log_item *lip; /* * If we've already shutdown the journal because of I/O errors, there's @@ -1338,12 +1335,11 @@ xfs_buf_ioend_handle_error( } /* Still considered a transient error. Caller will schedule retries. */ - if (bp->b_flags & _XBF_INODES) - xfs_buf_inode_io_fail(bp); - else if (bp->b_flags & _XBF_DQUOTS) - xfs_buf_dquot_io_fail(bp); - else - ASSERT(list_empty(&bp->b_li_list)); + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { + set_bit(XFS_LI_FAILED, &lip->li_flags); + clear_bit(XFS_LI_FLUSHING, &lip->li_flags); + } + xfs_buf_ioerror(bp, 0); xfs_buf_relse(bp); return true; @@ -1367,14 +1363,10 @@ xfs_buf_ioend( { trace_xfs_buf_iodone(bp, _RET_IP_); - /* - * Pull in IO completion errors now. We are guaranteed to be running - * single threaded, so we don't need the lock to read b_io_error. - */ - if (!bp->b_error && bp->b_io_error) - xfs_buf_ioerror(bp, bp->b_io_error); - if (bp->b_flags & XBF_READ) { + if (!bp->b_error && xfs_buf_is_vmapped(bp)) + invalidate_kernel_vmap_range(bp->b_addr, + xfs_buf_vmap_len(bp)); if (!bp->b_error && bp->b_ops) bp->b_ops->verify_read(bp); if (!bp->b_error) @@ -1401,11 +1393,8 @@ xfs_buf_ioend( if (bp->b_log_item) xfs_buf_item_done(bp); - if (bp->b_flags & _XBF_INODES) - xfs_buf_inode_iodone(bp); - else if (bp->b_flags & _XBF_DQUOTS) - xfs_buf_dquot_iodone(bp); - + if (bp->b_iodone) + bp->b_iodone(bp); } bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD | @@ -1485,7 +1474,8 @@ xfs_bwrite( bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_DONE); - error = xfs_buf_submit(bp); + xfs_buf_submit(bp); + error = xfs_buf_iowait(bp); if (error) xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); return error; @@ -1495,188 +1485,79 @@ static void xfs_buf_bio_end_io( struct bio *bio) { - struct xfs_buf *bp = (struct xfs_buf *)bio->bi_private; - - if (!bio->bi_status && - (bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) && - XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) - bio->bi_status = BLK_STS_IOERR; - - /* - * don't overwrite existing errors - otherwise we can lose errors on - * buffers that require multiple bios to complete. - */ - if (bio->bi_status) { - int error = blk_status_to_errno(bio->bi_status); - - cmpxchg(&bp->b_io_error, 0, error); - } - - if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) - invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); - - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) - xfs_buf_ioend_async(bp); - bio_put(bio); -} - -static void -xfs_buf_ioapply_map( - struct xfs_buf *bp, - int map, - int *buf_offset, - int *count, - blk_opf_t op) -{ - int page_index; - unsigned int total_nr_pages = bp->b_page_count; - int nr_pages; - struct bio *bio; - sector_t sector = bp->b_maps[map].bm_bn; - int size; - int offset; - - /* skip the pages in the buffer before the start offset */ - page_index = 0; - offset = *buf_offset; - while (offset >= PAGE_SIZE) { - page_index++; - offset -= PAGE_SIZE; - } - - /* - * Limit the IO size to the length of the current vector, and update the - * remaining IO count for the next time around. - */ - size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count); - *count -= size; - *buf_offset += size; + struct xfs_buf *bp = bio->bi_private; -next_chunk: - atomic_inc(&bp->b_io_remaining); - nr_pages = bio_max_segs(total_nr_pages); - - bio = bio_alloc(bp->b_target->bt_bdev, nr_pages, op, GFP_NOIO); - bio->bi_iter.bi_sector = sector; - bio->bi_end_io = xfs_buf_bio_end_io; - bio->bi_private = bp; - - for (; size && nr_pages; nr_pages--, page_index++) { - int rbytes, nbytes = PAGE_SIZE - offset; - - if (nbytes > size) - nbytes = size; - - rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes, - offset); - if (rbytes < nbytes) - break; - - offset = 0; - sector += BTOBB(nbytes); - size -= nbytes; - total_nr_pages--; - } - - if (likely(bio->bi_iter.bi_size)) { - if (xfs_buf_is_vmapped(bp)) { - flush_kernel_vmap_range(bp->b_addr, - xfs_buf_vmap_len(bp)); - } - submit_bio(bio); - if (size) - goto next_chunk; - } else { - /* - * This is guaranteed not to be the last io reference count - * because the caller (xfs_buf_submit) holds a count itself. - */ - atomic_dec(&bp->b_io_remaining); + if (bio->bi_status) + xfs_buf_ioerror(bp, blk_status_to_errno(bio->bi_status)); + else if ((bp->b_flags & XBF_WRITE) && (bp->b_flags & XBF_ASYNC) && + XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR)) xfs_buf_ioerror(bp, -EIO); - bio_put(bio); - } + xfs_buf_ioend_async(bp); + bio_put(bio); } -STATIC void -_xfs_buf_ioapply( - struct xfs_buf *bp) +static inline blk_opf_t +xfs_buf_bio_op( + struct xfs_buf *bp) { - struct blk_plug plug; - blk_opf_t op; - int offset; - int size; - int i; - - /* - * Make sure we capture only current IO errors rather than stale errors - * left over from previous use of the buffer (e.g. failed readahead). - */ - bp->b_error = 0; + blk_opf_t op; if (bp->b_flags & XBF_WRITE) { op = REQ_OP_WRITE; - - /* - * Run the write verifier callback function if it exists. If - * this function fails it will mark the buffer with an error and - * the IO should not be dispatched. - */ - if (bp->b_ops) { - bp->b_ops->verify_write(bp); - if (bp->b_error) { - xfs_force_shutdown(bp->b_mount, - SHUTDOWN_CORRUPT_INCORE); - return; - } - } else if (bp->b_rhash_key != XFS_BUF_DADDR_NULL) { - struct xfs_mount *mp = bp->b_mount; - - /* - * non-crc filesystems don't attach verifiers during - * log recovery, so don't warn for such filesystems. - */ - if (xfs_has_crc(mp)) { - xfs_warn(mp, - "%s: no buf ops on daddr 0x%llx len %d", - __func__, xfs_buf_daddr(bp), - bp->b_length); - xfs_hex_dump(bp->b_addr, - XFS_CORRUPTION_DUMP_LEN); - dump_stack(); - } - } } else { op = REQ_OP_READ; if (bp->b_flags & XBF_READ_AHEAD) op |= REQ_RAHEAD; } - /* we only use the buffer cache for meta-data */ - op |= REQ_META; + return op | REQ_META; +} - /* in-memory targets are directly mapped, no IO required. */ - if (xfs_buftarg_is_mem(bp->b_target)) { - xfs_buf_ioend(bp); - return; +static void +xfs_buf_submit_bio( + struct xfs_buf *bp) +{ + unsigned int size = BBTOB(bp->b_length); + unsigned int map = 0, p; + struct blk_plug plug; + struct bio *bio; + + bio = bio_alloc(bp->b_target->bt_bdev, bp->b_page_count, + xfs_buf_bio_op(bp), GFP_NOIO); + bio->bi_private = bp; + bio->bi_end_io = xfs_buf_bio_end_io; + + if (bp->b_flags & _XBF_KMEM) { + __bio_add_page(bio, virt_to_page(bp->b_addr), size, + bp->b_offset); + } else { + for (p = 0; p < bp->b_page_count; p++) + __bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0); + bio->bi_iter.bi_size = size; /* limit to the actual size used */ + + if (xfs_buf_is_vmapped(bp)) + flush_kernel_vmap_range(bp->b_addr, + xfs_buf_vmap_len(bp)); } /* - * Walk all the vectors issuing IO on them. Set up the initial offset - * into the buffer and the desired IO size before we start - - * _xfs_buf_ioapply_vec() will modify them appropriately for each - * subsequent call. + * If there is more than one map segment, split out a new bio for each + * map except of the last one. The last map is handled by the + * remainder of the original bio outside the loop. */ - offset = bp->b_offset; - size = BBTOB(bp->b_length); blk_start_plug(&plug); - for (i = 0; i < bp->b_map_count; i++) { - xfs_buf_ioapply_map(bp, i, &offset, &size, op); - if (bp->b_error) - break; - if (size <= 0) - break; /* all done */ + for (map = 0; map < bp->b_map_count - 1; map++) { + struct bio *split; + + split = bio_split(bio, bp->b_maps[map].bm_len, GFP_NOFS, + &fs_bio_set); + split->bi_iter.bi_sector = bp->b_maps[map].bm_bn; + bio_chain(split, bio); + submit_bio(split); } + bio->bi_iter.bi_sector = bp->b_maps[map].bm_bn; + submit_bio(bio); blk_finish_plug(&plug); } @@ -1697,18 +1578,45 @@ xfs_buf_iowait( } /* + * Run the write verifier callback function if it exists. If this fails, mark + * the buffer with an error and do not dispatch the I/O. + */ +static bool +xfs_buf_verify_write( + struct xfs_buf *bp) +{ + if (bp->b_ops) { + bp->b_ops->verify_write(bp); + if (bp->b_error) + return false; + } else if (bp->b_rhash_key != XFS_BUF_DADDR_NULL) { + /* + * Non-crc filesystems don't attach verifiers during log + * recovery, so don't warn for such filesystems. + */ + if (xfs_has_crc(bp->b_mount)) { + xfs_warn(bp->b_mount, + "%s: no buf ops on daddr 0x%llx len %d", + __func__, xfs_buf_daddr(bp), + bp->b_length); + xfs_hex_dump(bp->b_addr, XFS_CORRUPTION_DUMP_LEN); + dump_stack(); + } + } + + return true; +} + +/* * Buffer I/O submission path, read or write. Asynchronous submission transfers * the buffer lock ownership and the current reference to the IO. It is not * safe to reference the buffer after a call to this function unless the caller * holds an additional reference itself. */ -static int -__xfs_buf_submit( - struct xfs_buf *bp, - bool wait) +static void +xfs_buf_submit( + struct xfs_buf *bp) { - int error = 0; - trace_xfs_buf_submit(bp, _RET_IP_); ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); @@ -1728,57 +1636,36 @@ __xfs_buf_submit( * state here rather than mount state to avoid corrupting the log tail * on shutdown. */ - if (bp->b_mount->m_log && - xlog_is_shutdown(bp->b_mount->m_log)) { + if (bp->b_mount->m_log && xlog_is_shutdown(bp->b_mount->m_log)) { xfs_buf_ioend_fail(bp); - return -EIO; + return; } - /* - * Grab a reference so the buffer does not go away underneath us. For - * async buffers, I/O completion drops the callers reference, which - * could occur before submission returns. - */ - xfs_buf_hold(bp); - if (bp->b_flags & XBF_WRITE) xfs_buf_wait_unpin(bp); - /* clear the internal error state to avoid spurious errors */ - bp->b_io_error = 0; - /* - * Set the count to 1 initially, this will stop an I/O completion - * callout which happens before we have started all the I/O from calling - * xfs_buf_ioend too early. + * Make sure we capture only current IO errors rather than stale errors + * left over from previous use of the buffer (e.g. failed readahead). */ - atomic_set(&bp->b_io_remaining, 1); + bp->b_error = 0; + if (bp->b_flags & XBF_ASYNC) xfs_buf_ioacct_inc(bp); - _xfs_buf_ioapply(bp); - /* - * If _xfs_buf_ioapply failed, we can get back here with only the IO - * reference we took above. If we drop it to zero, run completion so - * that we don't return to the caller with completion still pending. - */ - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) { - if (bp->b_error || !(bp->b_flags & XBF_ASYNC)) - xfs_buf_ioend(bp); - else - xfs_buf_ioend_async(bp); + if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) { + xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE); + xfs_buf_ioend(bp); + return; } - if (wait) - error = xfs_buf_iowait(bp); + /* In-memory targets are directly mapped, no I/O required. */ + if (xfs_buftarg_is_mem(bp->b_target)) { + xfs_buf_ioend(bp); + return; + } - /* - * Release the hold that keeps the buffer referenced for the entire - * I/O. Note that if the buffer is async, it is not safe to reference - * after this release. - */ - xfs_buf_rele(bp); - return error; + xfs_buf_submit_bio(bp); } void * @@ -1863,13 +1750,14 @@ xfs_buftarg_drain_rele( struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); struct list_head *dispose = arg; - if (atomic_read(&bp->b_hold) > 1) { + if (!spin_trylock(&bp->b_lock)) + return LRU_SKIP; + if (bp->b_hold > 1) { /* need to wait, so skip it this pass */ + spin_unlock(&bp->b_lock); trace_xfs_buf_drain_buftarg(bp, _RET_IP_); return LRU_SKIP; } - if (!spin_trylock(&bp->b_lock)) - return LRU_SKIP; /* * clear the LRU reference count so the buffer doesn't get @@ -2208,7 +2096,7 @@ xfs_buf_delwri_queue( */ bp->b_flags |= _XBF_DELWRI_Q; if (list_empty(&bp->b_list)) { - atomic_inc(&bp->b_hold); + xfs_buf_hold(bp); list_add_tail(&bp->b_list, list); } @@ -2266,72 +2154,26 @@ xfs_buf_cmp( return 0; } -/* - * Submit buffers for write. If wait_list is specified, the buffers are - * submitted using sync I/O and placed on the wait list such that the caller can - * iowait each buffer. Otherwise async I/O is used and the buffers are released - * at I/O completion time. In either case, buffers remain locked until I/O - * completes and the buffer is released from the queue. - */ -static int -xfs_buf_delwri_submit_buffers( - struct list_head *buffer_list, - struct list_head *wait_list) +static bool +xfs_buf_delwri_submit_prep( + struct xfs_buf *bp) { - struct xfs_buf *bp, *n; - int pinned = 0; - struct blk_plug plug; - - list_sort(NULL, buffer_list, xfs_buf_cmp); - - blk_start_plug(&plug); - list_for_each_entry_safe(bp, n, buffer_list, b_list) { - if (!wait_list) { - if (!xfs_buf_trylock(bp)) - continue; - if (xfs_buf_ispinned(bp)) { - xfs_buf_unlock(bp); - pinned++; - continue; - } - } else { - xfs_buf_lock(bp); - } - - /* - * Someone else might have written the buffer synchronously or - * marked it stale in the meantime. In that case only the - * _XBF_DELWRI_Q flag got cleared, and we have to drop the - * reference and remove it from the list here. - */ - if (!(bp->b_flags & _XBF_DELWRI_Q)) { - xfs_buf_list_del(bp); - xfs_buf_relse(bp); - continue; - } - - trace_xfs_buf_delwri_split(bp, _RET_IP_); - - /* - * If we have a wait list, each buffer (and associated delwri - * queue reference) transfers to it and is submitted - * synchronously. Otherwise, drop the buffer from the delwri - * queue and submit async. - */ - bp->b_flags &= ~_XBF_DELWRI_Q; - bp->b_flags |= XBF_WRITE; - if (wait_list) { - bp->b_flags &= ~XBF_ASYNC; - list_move_tail(&bp->b_list, wait_list); - } else { - bp->b_flags |= XBF_ASYNC; - xfs_buf_list_del(bp); - } - __xfs_buf_submit(bp, false); + /* + * Someone else might have written the buffer synchronously or marked it + * stale in the meantime. In that case only the _XBF_DELWRI_Q flag got + * cleared, and we have to drop the reference and remove it from the + * list here. + */ + if (!(bp->b_flags & _XBF_DELWRI_Q)) { + xfs_buf_list_del(bp); + xfs_buf_relse(bp); + return false; } - blk_finish_plug(&plug); - return pinned; + trace_xfs_buf_delwri_split(bp, _RET_IP_); + bp->b_flags &= ~_XBF_DELWRI_Q; + bp->b_flags |= XBF_WRITE; + return true; } /* @@ -2354,7 +2196,30 @@ int xfs_buf_delwri_submit_nowait( struct list_head *buffer_list) { - return xfs_buf_delwri_submit_buffers(buffer_list, NULL); + struct xfs_buf *bp, *n; + int pinned = 0; + struct blk_plug plug; + + list_sort(NULL, buffer_list, xfs_buf_cmp); + + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + if (!xfs_buf_trylock(bp)) + continue; + if (xfs_buf_ispinned(bp)) { + xfs_buf_unlock(bp); + pinned++; + continue; + } + if (!xfs_buf_delwri_submit_prep(bp)) + continue; + bp->b_flags |= XBF_ASYNC; + xfs_buf_list_del(bp); + xfs_buf_submit(bp); + } + blk_finish_plug(&plug); + + return pinned; } /* @@ -2371,9 +2236,21 @@ xfs_buf_delwri_submit( { LIST_HEAD (wait_list); int error = 0, error2; - struct xfs_buf *bp; + struct xfs_buf *bp, *n; + struct blk_plug plug; + + list_sort(NULL, buffer_list, xfs_buf_cmp); - xfs_buf_delwri_submit_buffers(buffer_list, &wait_list); + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + xfs_buf_lock(bp); + if (!xfs_buf_delwri_submit_prep(bp)) + continue; + bp->b_flags &= ~XBF_ASYNC; + list_move_tail(&bp->b_list, &wait_list); + xfs_buf_submit(bp); + } + blk_finish_plug(&plug); /* Wait for IO to complete. */ while (!list_empty(&wait_list)) { @@ -2398,14 +2275,9 @@ xfs_buf_delwri_submit( * Push a single buffer on a delwri queue. * * The purpose of this function is to submit a single buffer of a delwri queue - * and return with the buffer still on the original queue. The waiting delwri - * buffer submission infrastructure guarantees transfer of the delwri queue - * buffer reference to a temporary wait list. We reuse this infrastructure to - * transfer the buffer back to the original queue. + * and return with the buffer still on the original queue. * - * Note the buffer transitions from the queued state, to the submitted and wait - * listed state and back to the queued state during this call. The buffer - * locking and queue management logic between _delwri_pushbuf() and + * The buffer locking and queue management logic between _delwri_pushbuf() and * _delwri_queue() guarantee that the buffer cannot be queued to another list * before returning. */ @@ -2414,33 +2286,21 @@ xfs_buf_delwri_pushbuf( struct xfs_buf *bp, struct list_head *buffer_list) { - LIST_HEAD (submit_list); int error; ASSERT(bp->b_flags & _XBF_DELWRI_Q); trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); - /* - * Isolate the buffer to a new local list so we can submit it for I/O - * independently from the rest of the original list. - */ xfs_buf_lock(bp); - list_move(&bp->b_list, &submit_list); - xfs_buf_unlock(bp); - - /* - * Delwri submission clears the DELWRI_Q buffer flag and returns with - * the buffer on the wait list with the original reference. Rather than - * bounce the buffer from a local wait list back to the original list - * after I/O completion, reuse the original list as the wait list. - */ - xfs_buf_delwri_submit_buffers(&submit_list, buffer_list); + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); + bp->b_flags |= XBF_WRITE; + xfs_buf_submit(bp); /* - * The buffer is now locked, under I/O and wait listed on the original - * delwri queue. Wait for I/O completion, restore the DELWRI_Q flag and - * return with the buffer unlocked and on the original queue. + * The buffer is now locked, under I/O but still on the original delwri + * queue. Wait for I/O completion, restore the DELWRI_Q flag and + * return with the buffer unlocked and still on the original queue. */ error = xfs_buf_iowait(bp); bp->b_flags |= _XBF_DELWRI_Q; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 3d56bc7a35cc..7e73663c5d4a 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -34,8 +34,6 @@ struct xfs_buf; #define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ /* buffer type flags for write callbacks */ -#define _XBF_INODES (1u << 16)/* inode buffer */ -#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ #define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ @@ -65,8 +63,6 @@ typedef unsigned int xfs_buf_flags_t; { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ - { _XBF_INODES, "INODES" }, \ - { _XBF_DQUOTS, "DQUOTS" }, \ { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ @@ -172,7 +168,7 @@ struct xfs_buf { xfs_daddr_t b_rhash_key; /* buffer cache index */ int b_length; /* size of buffer in BBs */ - atomic_t b_hold; /* reference count */ + unsigned int b_hold; /* reference count */ atomic_t b_lru_ref; /* lru reclaim ref count */ xfs_buf_flags_t b_flags; /* status flags */ struct semaphore b_sema; /* semaphore for lockables */ @@ -184,10 +180,9 @@ struct xfs_buf { struct list_head b_lru; /* lru list */ spinlock_t b_lock; /* internal state lock */ unsigned int b_state; /* internal state flags */ - int b_io_error; /* internal IO error state */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; - struct xfs_perag *b_pag; /* contains rbtree root */ + struct xfs_perag *b_pag; struct xfs_mount *b_mount; struct xfs_buftarg *b_target; /* buffer target (device) */ void *b_addr; /* virtual address of buffer */ @@ -202,11 +197,11 @@ struct xfs_buf { struct xfs_buf_map __b_map; /* inline compound buffer map */ int b_map_count; atomic_t b_pin_count; /* pin count */ - atomic_t b_io_remaining; /* #outstanding I/O requests */ unsigned int b_page_count; /* size of page array */ unsigned int b_offset; /* page offset of b_addr, only for _XBF_KMEM buffers */ int b_error; /* error code on I/O */ + void (*b_iodone)(struct xfs_buf *bp); /* * async write failure retry count. Initialised to zero on the first diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 4d8a6aece995..8cde85259a58 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -54,17 +54,12 @@ bool xfs_buf_item_put(struct xfs_buf_log_item *); void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint); bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_inode_iodone(struct xfs_buf *); -void xfs_buf_inode_io_fail(struct xfs_buf *bp); #ifdef CONFIG_XFS_QUOTA void xfs_buf_dquot_iodone(struct xfs_buf *); -void xfs_buf_dquot_io_fail(struct xfs_buf *bp); #else static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp) { } -static inline void xfs_buf_dquot_io_fail(struct xfs_buf *bp) -{ -} #endif /* CONFIG_XFS_QUOTA */ void xfs_buf_iodone(struct xfs_buf *); bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec); diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 3d0c6402cb36..05a2f6927c12 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -262,12 +262,18 @@ xlog_recover_validate_buf_type( case XFS_BMAP_MAGIC: bp->b_ops = &xfs_bmbt_buf_ops; break; + case XFS_RTRMAP_CRC_MAGIC: + bp->b_ops = &xfs_rtrmapbt_buf_ops; + break; case XFS_RMAP_CRC_MAGIC: bp->b_ops = &xfs_rmapbt_buf_ops; break; case XFS_REFC_CRC_MAGIC: bp->b_ops = &xfs_refcountbt_buf_ops; break; + case XFS_RTREFC_CRC_MAGIC: + bp->b_ops = &xfs_rtrefcountbt_buf_ops; + break; default: warnmsg = "Bad btree block magic!"; break; @@ -855,6 +861,8 @@ xlog_recover_get_buf_lsn( uuid = &btb->bb_u.s.bb_uuid; break; } + case XFS_RTRMAP_CRC_MAGIC: + case XFS_RTREFC_CRC_MAGIC: case XFS_BMAP_CRC_MAGIC: case XFS_BMAP_MAGIC: { struct xfs_btree_block *btb = blk; @@ -1079,7 +1087,7 @@ xlog_recover_buf_commit_pass2( error = xlog_recover_do_primary_sb_buffer(mp, item, bp, buf_f, current_lsn); if (error) - goto out_release; + goto out_writebuf; /* Update the rt superblock if we have one. */ if (xfs_has_rtsb(mp) && mp->m_rtsb_bp) { @@ -1097,6 +1105,15 @@ xlog_recover_buf_commit_pass2( } /* + * Buffer held by buf log item during 'normal' buffer recovery must + * be committed through buffer I/O submission path to ensure proper + * release. When error occurs during sb buffer recovery, log shutdown + * will be done before submitting buffer list so that buffers can be + * released correctly through ioend failure path. + */ +out_writebuf: + + /* * Perform delayed write on the buffer. Asynchronous writes will be * slower when taking into account all the buffers to be flushed. * diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index c4bd145f5ec1..3f2403a7b49c 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -90,7 +90,7 @@ xfs_discard_endio_work( /* * Queue up the actual completion to a thread to avoid IRQ-safe locking for - * pagb_lock. + * eb_lock. */ static void xfs_discard_endio( diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index ff982d983989..edbc521870a1 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -69,6 +69,31 @@ xfs_dquot_mark_sick( } /* + * Detach the dquot buffer if it's still attached, because we can get called + * through dqpurge after a log shutdown. Caller must hold the dqflock or have + * otherwise isolated the dquot. + */ +void +xfs_dquot_detach_buf( + struct xfs_dquot *dqp) +{ + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_buf *bp = NULL; + + spin_lock(&qlip->qli_lock); + if (qlip->qli_item.li_buf) { + bp = qlip->qli_item.li_buf; + qlip->qli_item.li_buf = NULL; + } + spin_unlock(&qlip->qli_lock); + if (bp) { + xfs_buf_lock(bp); + list_del_init(&qlip->qli_item.li_bio_list); + xfs_buf_relse(bp); + } +} + +/* * This is called to free all the memory associated with a dquot */ void @@ -76,6 +101,7 @@ xfs_qm_dqdestroy( struct xfs_dquot *dqp) { ASSERT(list_empty(&dqp->q_lru)); + ASSERT(dqp->q_logitem.qli_item.li_buf == NULL); kvfree(dqp->q_logitem.qli_item.li_lv_shadow); mutex_destroy(&dqp->q_qlock); @@ -1142,9 +1168,11 @@ static void xfs_qm_dqflush_done( struct xfs_log_item *lip) { - struct xfs_dq_logitem *qip = (struct xfs_dq_logitem *)lip; - struct xfs_dquot *dqp = qip->qli_dquot; + struct xfs_dq_logitem *qlip = + container_of(lip, struct xfs_dq_logitem, qli_item); + struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_ail *ailp = lip->li_ailp; + struct xfs_buf *bp = NULL; xfs_lsn_t tail_lsn; /* @@ -1156,12 +1184,12 @@ xfs_qm_dqflush_done( * holding the lock before removing the dquot from the AIL. */ if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) && - ((lip->li_lsn == qip->qli_flush_lsn) || + (lip->li_lsn == qlip->qli_flush_lsn || test_bit(XFS_LI_FAILED, &lip->li_flags))) { spin_lock(&ailp->ail_lock); xfs_clear_li_failed(lip); - if (lip->li_lsn == qip->qli_flush_lsn) { + if (lip->li_lsn == qlip->qli_flush_lsn) { /* xfs_ail_update_finish() drops the AIL lock */ tail_lsn = xfs_ail_delete_one(ailp, lip); xfs_ail_update_finish(ailp, tail_lsn); @@ -1171,6 +1199,20 @@ xfs_qm_dqflush_done( } /* + * If this dquot hasn't been dirtied since initiating the last dqflush, + * release the buffer reference. We already unlinked this dquot item + * from the buffer. + */ + spin_lock(&qlip->qli_lock); + if (!qlip->qli_dirty) { + bp = lip->li_buf; + lip->li_buf = NULL; + } + spin_unlock(&qlip->qli_lock); + if (bp) + xfs_buf_rele(bp); + + /* * Release the dq's flush lock since we're done with it. */ xfs_dqfunlock(dqp); @@ -1188,18 +1230,6 @@ xfs_buf_dquot_iodone( } } -void -xfs_buf_dquot_io_fail( - struct xfs_buf *bp) -{ - struct xfs_log_item *lip; - - spin_lock(&bp->b_mount->m_ail->ail_lock); - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) - xfs_set_li_failed(lip, bp); - spin_unlock(&bp->b_mount->m_ail->ail_lock); -} - /* Check incore dquot for errors before we flush. */ static xfs_failaddr_t xfs_qm_dqflush_check( @@ -1239,6 +1269,115 @@ xfs_qm_dqflush_check( } /* + * Get the buffer containing the on-disk dquot. + * + * Requires dquot flush lock, will clear the dirty flag, delete the quota log + * item from the AIL, and shut down the system if something goes wrong. + */ +static int +xfs_dquot_read_buf( + struct xfs_trans *tp, + struct xfs_dquot *dqp, + struct xfs_buf **bpp) +{ + struct xfs_mount *mp = dqp->q_mount; + struct xfs_buf *bp = NULL; + int error; + + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen, 0, + &bp, &xfs_dquot_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_dquot_mark_sick(dqp); + if (error) + goto out_abort; + + *bpp = bp; + return 0; + +out_abort: + dqp->q_flags &= ~XFS_DQFLAG_DIRTY; + xfs_trans_ail_delete(&dqp->q_logitem.qli_item, 0); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; +} + +/* + * Attach a dquot buffer to this dquot to avoid allocating a buffer during a + * dqflush, since dqflush can be called from reclaim context. Caller must hold + * the dqlock. + */ +int +xfs_dquot_attach_buf( + struct xfs_trans *tp, + struct xfs_dquot *dqp) +{ + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_log_item *lip = &qlip->qli_item; + int error; + + spin_lock(&qlip->qli_lock); + if (!lip->li_buf) { + struct xfs_buf *bp = NULL; + + spin_unlock(&qlip->qli_lock); + error = xfs_dquot_read_buf(tp, dqp, &bp); + if (error) + return error; + + /* + * Hold the dquot buffer so that we retain our ref to it after + * detaching it from the transaction, then give that ref to the + * dquot log item so that the AIL does not have to read the + * dquot buffer to push this item. + */ + xfs_buf_hold(bp); + xfs_trans_brelse(tp, bp); + + spin_lock(&qlip->qli_lock); + lip->li_buf = bp; + } + qlip->qli_dirty = true; + spin_unlock(&qlip->qli_lock); + + return 0; +} + +/* + * Get a new reference the dquot buffer attached to this dquot for a dqflush + * operation. + * + * Returns 0 and a NULL bp if none was attached to the dquot; 0 and a locked + * bp; or -EAGAIN if the buffer could not be locked. + */ +int +xfs_dquot_use_attached_buf( + struct xfs_dquot *dqp, + struct xfs_buf **bpp) +{ + struct xfs_buf *bp = dqp->q_logitem.qli_item.li_buf; + + /* + * A NULL buffer can happen if the dquot dirty flag was set but the + * filesystem shut down before transaction commit happened. In that + * case we're not going to flush anyway. + */ + if (!bp) { + ASSERT(xfs_is_shutdown(dqp->q_mount)); + + *bpp = NULL; + return 0; + } + + if (!xfs_buf_trylock(bp)) + return -EAGAIN; + + xfs_buf_hold(bp); + *bpp = bp; + return 0; +} + +/* * Write a modified dquot to disk. * The dquot must be locked and the flush lock too taken by caller. * The flush lock will not be unlocked until the dquot reaches the disk, @@ -1249,11 +1388,11 @@ xfs_qm_dqflush_check( int xfs_qm_dqflush( struct xfs_dquot *dqp, - struct xfs_buf **bpp) + struct xfs_buf *bp) { struct xfs_mount *mp = dqp->q_mount; - struct xfs_log_item *lip = &dqp->q_logitem.qli_item; - struct xfs_buf *bp; + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_log_item *lip = &qlip->qli_item; struct xfs_dqblk *dqblk; xfs_failaddr_t fa; int error; @@ -1263,28 +1402,12 @@ xfs_qm_dqflush( trace_xfs_dqflush(dqp); - *bpp = NULL; - xfs_qm_dqunpin_wait(dqp); - /* - * Get the buffer containing the on-disk dquot - */ - error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK, - &bp, &xfs_dquot_buf_ops); - if (error == -EAGAIN) - goto out_unlock; - if (xfs_metadata_is_sick(error)) - xfs_dquot_mark_sick(dqp); - if (error) - goto out_abort; - fa = xfs_qm_dqflush_check(dqp); if (fa) { xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS", dqp->q_id, fa); - xfs_buf_relse(bp); xfs_dquot_mark_sick(dqp); error = -EFSCORRUPTED; goto out_abort; @@ -1299,8 +1422,15 @@ xfs_qm_dqflush( */ dqp->q_flags &= ~XFS_DQFLAG_DIRTY; - xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn, - &dqp->q_logitem.qli_item.li_lsn); + /* + * We hold the dquot lock, so nobody can dirty it while we're + * scheduling the write out. Clear the dirty-since-flush flag. + */ + spin_lock(&qlip->qli_lock); + qlip->qli_dirty = false; + spin_unlock(&qlip->qli_lock); + + xfs_trans_ail_copy_lsn(mp->m_ail, &qlip->qli_flush_lsn, &lip->li_lsn); /* * copy the lsn into the on-disk dquot now while we have the in memory @@ -1312,7 +1442,7 @@ xfs_qm_dqflush( * of a dquot without an up-to-date CRC getting to disk. */ if (xfs_has_crc(mp)) { - dqblk->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn); + dqblk->dd_lsn = cpu_to_be64(lip->li_lsn); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } @@ -1321,8 +1451,8 @@ xfs_qm_dqflush( * Attach the dquot to the buffer so that we can remove this dquot from * the AIL and release the flush lock once the dquot is synced to disk. */ - bp->b_flags |= _XBF_DQUOTS; - list_add_tail(&dqp->q_logitem.qli_item.li_bio_list, &bp->b_li_list); + bp->b_iodone = xfs_buf_dquot_iodone; + list_add_tail(&lip->li_bio_list, &bp->b_li_list); /* * If the buffer is pinned then push on the log so we won't @@ -1334,14 +1464,12 @@ xfs_qm_dqflush( } trace_xfs_dqflush_done(dqp); - *bpp = bp; return 0; out_abort: dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_delete(lip, 0); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); -out_unlock: xfs_dqfunlock(dqp); return error; } diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index d73d179df009..61217adf5ba5 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -160,6 +160,9 @@ static inline struct xfs_dquot *xfs_inode_dquot( struct xfs_inode *ip, xfs_dqtype_t type) { + if (xfs_is_metadir_inode(ip)) + return NULL; + switch (type) { case XFS_DQTYPE_USER: return ip->i_udquot; @@ -214,7 +217,7 @@ void xfs_dquot_to_disk(struct xfs_disk_dquot *ddqp, struct xfs_dquot *dqp); #define XFS_DQ_IS_DIRTY(dqp) ((dqp)->q_flags & XFS_DQFLAG_DIRTY) void xfs_qm_dqdestroy(struct xfs_dquot *dqp); -int xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf **bpp); +int xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf *bp); void xfs_qm_dqunpin_wait(struct xfs_dquot *dqp); void xfs_qm_adjust_dqtimers(struct xfs_dquot *d); void xfs_qm_adjust_dqlimits(struct xfs_dquot *d); @@ -237,6 +240,10 @@ void xfs_dqlockn(struct xfs_dqtrx *q); void xfs_dquot_set_prealloc_limits(struct xfs_dquot *); +int xfs_dquot_attach_buf(struct xfs_trans *tp, struct xfs_dquot *dqp); +int xfs_dquot_use_attached_buf(struct xfs_dquot *dqp, struct xfs_buf **bpp); +void xfs_dquot_detach_buf(struct xfs_dquot *dqp); + static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp) { xfs_dqlock(dqp); diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 7d19091215b0..271b195ebb93 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -123,8 +123,9 @@ xfs_qm_dquot_logitem_push( __releases(&lip->li_ailp->ail_lock) __acquires(&lip->li_ailp->ail_lock) { - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; - struct xfs_buf *bp = lip->li_buf; + struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); + struct xfs_dquot *dqp = qlip->qli_dquot; + struct xfs_buf *bp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -155,14 +156,25 @@ xfs_qm_dquot_logitem_push( spin_unlock(&lip->li_ailp->ail_lock); - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (error == -EAGAIN) { + xfs_dqfunlock(dqp); + rval = XFS_ITEM_LOCKED; + goto out_relock_ail; + } + + /* + * dqflush completes dqflock on error, and the delwri ioend does it on + * success. + */ + error = xfs_qm_dqflush(dqp, bp); if (!error) { if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; - xfs_buf_relse(bp); - } else if (error == -EAGAIN) - rval = XFS_ITEM_LOCKED; + } + xfs_buf_relse(bp); +out_relock_ail: spin_lock(&lip->li_ailp->ail_lock); out_unlock: xfs_dqunlock(dqp); @@ -195,12 +207,10 @@ xfs_qm_dquot_logitem_committing( } #ifdef DEBUG_EXPENSIVE -static int -xfs_qm_dquot_logitem_precommit( - struct xfs_trans *tp, - struct xfs_log_item *lip) +static void +xfs_qm_dquot_logitem_precommit_check( + struct xfs_dquot *dqp) { - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; struct xfs_mount *mp = dqp->q_mount; struct xfs_disk_dquot ddq = { }; xfs_failaddr_t fa; @@ -216,13 +226,24 @@ xfs_qm_dquot_logitem_precommit( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); ASSERT(fa == NULL); } - - return 0; } #else -# define xfs_qm_dquot_logitem_precommit NULL +# define xfs_qm_dquot_logitem_precommit_check(...) ((void)0) #endif +static int +xfs_qm_dquot_logitem_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); + struct xfs_dquot *dqp = qlip->qli_dquot; + + xfs_qm_dquot_logitem_precommit_check(dqp); + + return xfs_dquot_attach_buf(tp, dqp); +} + static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_size = xfs_qm_dquot_logitem_size, .iop_precommit = xfs_qm_dquot_logitem_precommit, @@ -247,5 +268,7 @@ xfs_qm_dquot_logitem_init( xfs_log_item_init(dqp->q_mount, &lp->qli_item, XFS_LI_DQUOT, &xfs_dquot_item_ops); + spin_lock_init(&lp->qli_lock); lp->qli_dquot = dqp; + lp->qli_dirty = false; } diff --git a/fs/xfs/xfs_dquot_item.h b/fs/xfs/xfs_dquot_item.h index 794710c24474..d66e52807d76 100644 --- a/fs/xfs/xfs_dquot_item.h +++ b/fs/xfs/xfs_dquot_item.h @@ -14,6 +14,13 @@ struct xfs_dq_logitem { struct xfs_log_item qli_item; /* common portion */ struct xfs_dquot *qli_dquot; /* dquot ptr */ xfs_lsn_t qli_flush_lsn; /* lsn at last flush */ + + /* + * We use this spinlock to coordinate access to the li_buf pointer in + * the log item and the qli_dirty flag. + */ + spinlock_t qli_lock; + bool qli_dirty; /* dirtied since last flush? */ }; void xfs_qm_dquot_logitem_init(struct xfs_dquot *dqp); diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c index 5ede81fadbd8..fa5f31931efd 100644 --- a/fs/xfs/xfs_drain.c +++ b/fs/xfs/xfs_drain.c @@ -13,28 +13,28 @@ #include "xfs_trace.h" /* - * Use a static key here to reduce the overhead of xfs_drain_rele. If the - * compiler supports jump labels, the static branch will be replaced by a nop - * sled when there are no xfs_drain_wait callers. Online fsck is currently - * the only caller, so this is a reasonable tradeoff. + * Use a static key here to reduce the overhead of xfs_defer_drain_rele. If + * the compiler supports jump labels, the static branch will be replaced by a + * nop sled when there are no xfs_defer_drain_wait callers. Online fsck is + * currently the only caller, so this is a reasonable tradeoff. * * Note: Patching the kernel code requires taking the cpu hotplug lock. Other * parts of the kernel allocate memory with that lock held, which means that * XFS callers cannot hold any locks that might be used by memory reclaim or * writeback when calling the static_branch_{inc,dec} functions. */ -static DEFINE_STATIC_KEY_FALSE(xfs_drain_waiter_gate); +static DEFINE_STATIC_KEY_FALSE(xfs_defer_drain_waiter_gate); void -xfs_drain_wait_disable(void) +xfs_defer_drain_wait_disable(void) { - static_branch_dec(&xfs_drain_waiter_gate); + static_branch_dec(&xfs_defer_drain_waiter_gate); } void -xfs_drain_wait_enable(void) +xfs_defer_drain_wait_enable(void) { - static_branch_inc(&xfs_drain_waiter_gate); + static_branch_inc(&xfs_defer_drain_waiter_gate); } void @@ -71,7 +71,7 @@ static inline bool has_waiters(struct wait_queue_head *wq_head) static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr) { if (atomic_dec_and_test(&dr->dr_count) && - static_branch_unlikely(&xfs_drain_waiter_gate) && + static_branch_unlikely(&xfs_defer_drain_waiter_gate) && has_waiters(&dr->dr_waiters)) wake_up(&dr->dr_waiters); } diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h index efcf88df9a5e..4d446dbf65e5 100644 --- a/fs/xfs/xfs_drain.h +++ b/fs/xfs/xfs_drain.h @@ -26,8 +26,8 @@ struct xfs_defer_drain { void xfs_defer_drain_init(struct xfs_defer_drain *dr); void xfs_defer_drain_free(struct xfs_defer_drain *dr); -void xfs_drain_wait_disable(void); -void xfs_drain_wait_enable(void); +void xfs_defer_drain_wait_disable(void); +void xfs_defer_drain_wait_enable(void); /* * Deferred Work Intent Drains @@ -61,6 +61,9 @@ void xfs_drain_wait_enable(void); * All functions that create work items must increment the intent counter as * soon as the item is added to the transaction and cannot drop the counter * until the item is finished or cancelled. + * + * The same principles apply to realtime groups because the rt metadata inode + * ILOCKs are not held across transaction rolls. */ struct xfs_group *xfs_group_intent_get(struct xfs_mount *mp, xfs_fsblock_t fsbno, enum xfs_group_type type); diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 78cdc5064a8c..dbd87e137694 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -63,6 +63,7 @@ static unsigned int xfs_errortag_random_default[] = { XFS_RANDOM_WB_DELAY_MS, XFS_RANDOM_WRITE_DELAY_MS, XFS_RANDOM_EXCHMAPS_FINISH_ONE, + XFS_RANDOM_METAFILE_RESV_CRITICAL, }; struct xfs_errortag_attr { @@ -181,6 +182,7 @@ XFS_ERRORTAG_ATTR_RW(attr_leaf_to_node, XFS_ERRTAG_ATTR_LEAF_TO_NODE); XFS_ERRORTAG_ATTR_RW(wb_delay_ms, XFS_ERRTAG_WB_DELAY_MS); XFS_ERRORTAG_ATTR_RW(write_delay_ms, XFS_ERRTAG_WRITE_DELAY_MS); XFS_ERRORTAG_ATTR_RW(exchmaps_finish_one, XFS_ERRTAG_EXCHMAPS_FINISH_ONE); +XFS_ERRORTAG_ATTR_RW(metafile_resv_crit, XFS_ERRTAG_METAFILE_RESV_CRITICAL); static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(noerror), @@ -227,6 +229,7 @@ static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(wb_delay_ms), XFS_ERRORTAG_ATTR_LIST(write_delay_ms), XFS_ERRORTAG_ATTR_LIST(exchmaps_finish_one), + XFS_ERRORTAG_ATTR_LIST(metafile_resv_crit), NULL, }; ATTRIBUTE_GROUPS(xfs_errortag); diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 9ab05ad224d1..f340a2015c4c 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -119,6 +119,9 @@ xfs_exchrange_reserve_quota( int ip1_error = 0; int error; + ASSERT(!xfs_is_metadir_inode(req->ip1)); + ASSERT(!xfs_is_metadir_inode(req->ip2)); + /* * Don't bother with a quota reservation if we're not enforcing them * or the two inodes have the same dquots. @@ -854,7 +857,7 @@ xfs_ioc_start_commit( struct xfs_commit_range __user *argp) { struct xfs_commit_range args = { }; - struct timespec64 ts; + struct kstat kstat = { }; struct xfs_commit_range_fresh *kern_f; struct xfs_commit_range_fresh __user *user_f; struct inode *inode2 = file_inode(file); @@ -871,12 +874,12 @@ xfs_ioc_start_commit( memcpy(&kern_f->fsid, ip2->i_mount->m_fixedfsid, sizeof(xfs_fsid_t)); xfs_ilock(ip2, lockflags); - ts = inode_get_ctime(inode2); - kern_f->file2_ctime = ts.tv_sec; - kern_f->file2_ctime_nsec = ts.tv_nsec; - ts = inode_get_mtime(inode2); - kern_f->file2_mtime = ts.tv_sec; - kern_f->file2_mtime_nsec = ts.tv_nsec; + /* Force writing of a distinct ctime if any writes happen. */ + fill_mg_cmtime(&kstat, STATX_CTIME | STATX_MTIME, inode2); + kern_f->file2_ctime = kstat.ctime.tv_sec; + kern_f->file2_ctime_nsec = kstat.ctime.tv_nsec; + kern_f->file2_mtime = kstat.mtime.tv_sec; + kern_f->file2_mtime_nsec = kstat.mtime.tv_nsec; kern_f->file2_ino = ip2->i_ino; kern_f->file2_gen = inode2->i_generation; kern_f->magic = XCR_FRESH_MAGIC; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4a0b7de4f7ae..f7a7d89c345e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1242,6 +1242,14 @@ out_unlock: xfs_iunlock2_remapping(src, dest); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + /* + * If the caller did not set CAN_SHORTEN, then it is not prepared to + * handle partial results -- either the whole remap succeeds, or we + * must say why it did not. In this case, any error should be returned + * to the caller. + */ + if (ret && remapped < len && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return ret; return remapped > 0 ? remapped : ret; } @@ -1443,6 +1451,9 @@ xfs_dax_read_fault( trace_xfs_read_fault(ip, order); + ret = filemap_fsnotify_fault(vmf); + if (unlikely(ret)) + return ret; xfs_ilock(ip, XFS_MMAPLOCK_SHARED); ret = xfs_dax_fault_locked(vmf, order, false); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); @@ -1471,6 +1482,16 @@ xfs_write_fault( vm_fault_t ret; trace_xfs_write_fault(ip, order); + /* + * Usually we get here from ->page_mkwrite callback but in case of DAX + * we will get here also for ordinary write fault. Handle HSM + * notifications for that case. + */ + if (IS_DAX(inode)) { + ret = filemap_fsnotify_fault(vmf); + if (unlikely(ret)) + return ret; + } sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 82f2e0dd2249..1dbd2d75f7ae 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -26,6 +26,8 @@ #include "xfs_rtbitmap.h" #include "xfs_ag.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* Convert an xfs_fsmap to an fsmap. */ static void @@ -163,7 +165,8 @@ struct xfs_getfsmap_info { xfs_daddr_t next_daddr; /* next daddr we expect */ /* daddr of low fsmap key when we're using the rtbitmap */ xfs_daddr_t low_daddr; - xfs_daddr_t end_daddr; /* daddr of high fsmap key */ + /* daddr of high fsmap key, or the last daddr on the device */ + xfs_daddr_t end_daddr; u64 missing_owner; /* owner of holes */ u32 dev; /* device id */ /* @@ -210,21 +213,20 @@ xfs_getfsmap_is_shared( struct xfs_mount *mp = tp->t_mountp; struct xfs_btree_cur *cur; xfs_agblock_t fbno; - xfs_extlen_t flen; + xfs_extlen_t flen = 0; int error; *stat = false; - if (!xfs_has_reflink(mp)) - return 0; - /* rt files will have no perag structure */ - if (!info->group) + if (!xfs_has_reflink(mp) || !info->group) return 0; - /* Are there any shared blocks here? */ - flen = 0; - cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, - to_perag(info->group)); + if (info->group->xg_type == XG_TYPE_RTG) + cur = xfs_rtrefcountbt_init_cursor(tp, to_rtg(info->group)); + else + cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp, + to_perag(info->group)); + /* Are there any shared blocks here? */ error = xfs_refcount_find_shared(cur, frec->rec_key, XFS_BB_TO_FSBT(mp, frec->len_daddr), &fbno, &flen, false); @@ -387,8 +389,8 @@ xfs_getfsmap_group_helper( * we calculated from userspace's high key to synthesize the record. * Note that if the btree query found a mapping, there won't be a gap. */ - if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) - frec->start_daddr = info->end_daddr; + if (info->last) + frec->start_daddr = info->end_daddr + 1; else frec->start_daddr = xfs_gbno_to_daddr(xg, startblock); @@ -736,11 +738,10 @@ xfs_getfsmap_rtdev_rtbitmap_helper( * we calculated from userspace's high key to synthesize the record. * Note that if the btree query found a mapping, there won't be a gap. */ - if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) { - frec.start_daddr = info->end_daddr; - } else { + if (info->last) + frec.start_daddr = info->end_daddr + 1; + else frec.start_daddr = xfs_rtb_to_daddr(mp, start_rtb); - } frec.len_daddr = XFS_FSB_TO_BB(mp, rtbcount); return xfs_getfsmap_helper(tp, info, &frec); @@ -832,6 +833,175 @@ xfs_getfsmap_rtdev_rtbitmap( return error; } + +/* Transform a realtime rmapbt record into a fsmap */ +STATIC int +xfs_getfsmap_rtdev_rmapbt_helper( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xfs_fsmap_irec frec = { + .owner = rec->rm_owner, + .offset = rec->rm_offset, + .rm_flags = rec->rm_flags, + .rec_key = rec->rm_startblock, + }; + struct xfs_getfsmap_info *info = priv; + + return xfs_getfsmap_group_helper(info, cur->bc_tp, cur->bc_group, + rec->rm_startblock, rec->rm_blockcount, &frec); +} + +/* Actually query the rtrmap btree. */ +STATIC int +xfs_getfsmap_rtdev_rmapbt_query( + struct xfs_trans *tp, + struct xfs_getfsmap_info *info, + struct xfs_btree_cur **curpp) +{ + struct xfs_rtgroup *rtg = to_rtg(info->group); + + /* Query the rtrmapbt */ + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + *curpp = xfs_rtrmapbt_init_cursor(tp, rtg); + return xfs_rmap_query_range(*curpp, &info->low, &info->high, + xfs_getfsmap_rtdev_rmapbt_helper, info); +} + +/* Execute a getfsmap query against the realtime device rmapbt. */ +STATIC int +xfs_getfsmap_rtdev_rmapbt( + struct xfs_trans *tp, + const struct xfs_fsmap *keys, + struct xfs_getfsmap_info *info) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rtgroup *rtg = NULL; + struct xfs_btree_cur *bt_cur = NULL; + xfs_rtblock_t start_rtb; + xfs_rtblock_t end_rtb; + xfs_rgnumber_t start_rg, end_rg; + uint64_t eofs; + int error = 0; + + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); + if (keys[0].fmr_physical >= eofs) + return 0; + start_rtb = xfs_daddr_to_rtb(mp, keys[0].fmr_physical); + end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical)); + + info->missing_owner = XFS_FMR_OWN_FREE; + + /* + * Convert the fsmap low/high keys to rtgroup based keys. Initialize + * low to the fsmap low key and max out the high key to the end + * of the rtgroup. + */ + info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); + error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); + if (error) + return error; + info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length); + xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); + + /* Adjust the low key if we are continuing from where we left off. */ + if (info->low.rm_blockcount == 0) { + /* No previous record from which to continue */ + } else if (rmap_not_shareable(mp, &info->low)) { + /* Last record seen was an unshareable extent */ + info->low.rm_owner = 0; + info->low.rm_offset = 0; + + start_rtb += info->low.rm_blockcount; + if (xfs_rtb_to_daddr(mp, start_rtb) >= eofs) + return 0; + } else { + /* Last record seen was a shareable file data extent */ + info->low.rm_offset += info->low.rm_blockcount; + } + info->low.rm_startblock = xfs_rtb_to_rgbno(mp, start_rtb); + + info->high.rm_startblock = -1U; + info->high.rm_owner = ULLONG_MAX; + info->high.rm_offset = ULLONG_MAX; + info->high.rm_blockcount = 0; + info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS; + + start_rg = xfs_rtb_to_rgno(mp, start_rtb); + end_rg = xfs_rtb_to_rgno(mp, end_rtb); + + while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rg, end_rg))) { + /* + * Set the rtgroup high key from the fsmap high key if this + * is the last rtgroup that we're querying. + */ + info->group = rtg_group(rtg); + if (rtg_rgno(rtg) == end_rg) { + info->high.rm_startblock = + xfs_rtb_to_rgbno(mp, end_rtb); + info->high.rm_offset = + XFS_BB_TO_FSBT(mp, keys[1].fmr_offset); + error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]); + if (error) + break; + xfs_getfsmap_set_irec_flags(&info->high, &keys[1]); + } + + if (bt_cur) { + xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group), + XFS_RTGLOCK_RMAP | + XFS_RTGLOCK_REFCOUNT); + xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR); + bt_cur = NULL; + } + + trace_xfs_fsmap_low_group_key(mp, info->dev, rtg_rgno(rtg), + &info->low); + trace_xfs_fsmap_high_group_key(mp, info->dev, rtg_rgno(rtg), + &info->high); + + error = xfs_getfsmap_rtdev_rmapbt_query(tp, info, &bt_cur); + if (error) + break; + + /* + * Set the rtgroup low key to the start of the rtgroup prior to + * moving on to the next rtgroup. + */ + if (rtg_rgno(rtg) == start_rg) + memset(&info->low, 0, sizeof(info->low)); + + /* + * If this is the last rtgroup, report any gap at the end of it + * before we drop the reference to the perag when the loop + * terminates. + */ + if (rtg_rgno(rtg) == end_rg) { + info->last = true; + error = xfs_getfsmap_rtdev_rmapbt_helper(bt_cur, + &info->high, info); + if (error) + break; + } + info->group = NULL; + } + + if (bt_cur) { + xfs_rtgroup_unlock(to_rtg(bt_cur->bc_group), + XFS_RTGLOCK_RMAP | XFS_RTGLOCK_REFCOUNT); + xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR : + XFS_BTREE_NOERROR); + } + + /* loop termination case */ + if (rtg) { + info->group = NULL; + xfs_rtgroup_rele(rtg); + } + + return error; +} #endif /* CONFIG_XFS_RT */ /* Do we recognize the device? */ @@ -933,7 +1103,10 @@ xfs_getfsmap( struct xfs_trans *tp = NULL; struct xfs_fsmap dkeys[2]; /* per-dev keys */ struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS]; - struct xfs_getfsmap_info info = { NULL }; + struct xfs_getfsmap_info info = { + .fsmap_recs = fsmap_recs, + .head = head, + }; bool use_rmap; int i; int error = 0; @@ -968,7 +1141,10 @@ xfs_getfsmap( if (mp->m_rtdev_targp) { handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev); - handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; + if (use_rmap) + handlers[2].fn = xfs_getfsmap_rtdev_rmapbt; + else + handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; } #endif /* CONFIG_XFS_RT */ @@ -998,9 +1174,6 @@ xfs_getfsmap( info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; - info.end_daddr = XFS_BUF_DADDR_NULL; - info.fsmap_recs = fsmap_recs; - info.head = head; /* For each device we support... */ for (i = 0; i < XFS_GETFSMAP_DEVS; i++) { @@ -1013,17 +1186,23 @@ xfs_getfsmap( break; /* - * If this device number matches the high key, we have - * to pass the high key to the handler to limit the - * query results. If the device number exceeds the - * low key, zero out the low key so that we get - * everything from the beginning. + * If this device number matches the high key, we have to pass + * the high key to the handler to limit the query results, and + * set the end_daddr so that we can synthesize records at the + * end of the query range or device. */ if (handlers[i].dev == head->fmh_keys[1].fmr_device) { dkeys[1] = head->fmh_keys[1]; info.end_daddr = min(handlers[i].nr_sectors - 1, dkeys[1].fmr_physical); + } else { + info.end_daddr = handlers[i].nr_sectors - 1; } + + /* + * If the device number exceeds the low key, zero out the low + * key so that we get everything from the beginning. + */ if (handlers[i].dev > head->fmh_keys[0].fmr_device) memset(&dkeys[0], 0, sizeof(struct xfs_fsmap)); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 28dde215c899..455298503d01 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -21,6 +21,9 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_trace.h" +#include "xfs_rtalloc.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" /* * Write new AG headers to disk. Non-transactional, but need to be @@ -113,6 +116,12 @@ xfs_growfs_data_private( xfs_buf_relse(bp); } + /* Make sure the new fs size won't cause problems with the log. */ + error = xfs_growfs_check_rtgeom(mp, nb, mp->m_sb.sb_rblocks, + mp->m_sb.sb_rextsize); + if (error) + return error; + nb_div = nb; nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS) @@ -220,7 +229,12 @@ xfs_growfs_data_private( error = xfs_fs_reserve_ag_blocks(mp); if (error == -ENOSPC) error = 0; + + /* Compute new maxlevels for rt btrees. */ + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); } + return error; out_trans_cancel: @@ -541,6 +555,19 @@ xfs_fs_reserve_ag_blocks( xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", error); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; + } + + if (xfs_has_realtime(mp)) { + err2 = xfs_rt_resv_init(mp); + if (err2 && err2 != -ENOSPC) { + xfs_warn(mp, + "Error %d reserving realtime metadata reserve pool.", err2); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + } + + if (err2 && !error) + error = err2; } return error; @@ -555,6 +582,9 @@ xfs_fs_unreserve_ag_blocks( { struct xfs_perag *pag = NULL; + if (xfs_has_realtime(mp)) + xfs_rt_resv_free(mp); + while ((pag = xfs_perag_next(mp, pag))) xfs_ag_resv_free(pag); } diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index c7c2e6561998..7c541fb373d5 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -447,6 +447,8 @@ static const struct ioctl_sick_map rtgroup_map[] = { { XFS_SICK_RG_SUPER, XFS_RTGROUP_GEOM_SICK_SUPER }, { XFS_SICK_RG_BITMAP, XFS_RTGROUP_GEOM_SICK_BITMAP }, { XFS_SICK_RG_SUMMARY, XFS_RTGROUP_GEOM_SICK_SUMMARY }, + { XFS_SICK_RG_RMAPBT, XFS_RTGROUP_GEOM_SICK_RMAPBT }, + { XFS_SICK_RG_REFCNTBT, XFS_RTGROUP_GEOM_SICK_REFCNTBT }, }; /* Fill out rtgroup geometry health info. */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c8ad2606f928..c95fe1b1de4e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2382,7 +2382,16 @@ xfs_iflush( __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto flush_out; } - if (S_ISREG(VFS_I(ip)->i_mode)) { + if (ip->i_df.if_format == XFS_DINODE_FMT_META_BTREE) { + if (!S_ISREG(VFS_I(ip)->i_mode) || + !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: Bad %s meta btree inode %Lu, ptr "PTR_FMT, + __func__, xfs_metafile_type_str(ip->i_metatype), + ip->i_ino, ip); + goto flush_out; + } + } else if (S_ISREG(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE, @@ -2422,6 +2431,14 @@ xfs_iflush( goto flush_out; } + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_META_BTREE) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: meta btree in inode %Lu attr fork, ptr "PTR_FMT, + __func__, ip->i_ino, ip); + goto flush_out; + } + /* * Inode item log recovery for v2 inodes are dependent on the flushiter * count for correct sequencing. We bump the flush iteration count so diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index b0de3d924d4c..c08093a65352 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -25,9 +25,19 @@ struct xfs_dquot; typedef struct xfs_inode { /* Inode linking and identification information. */ struct xfs_mount *i_mount; /* fs mount struct ptr */ - struct xfs_dquot *i_udquot; /* user dquot */ - struct xfs_dquot *i_gdquot; /* group dquot */ - struct xfs_dquot *i_pdquot; /* project dquot */ + union { + struct { + struct xfs_dquot *i_udquot; /* user dquot */ + struct xfs_dquot *i_gdquot; /* group dquot */ + struct xfs_dquot *i_pdquot; /* project dquot */ + }; + + /* + * Space that has been set aside to accomodate expansions of a + * metadata btree rooted in this file. + */ + uint64_t i_meta_resv_asked; + }; /* Inode location stuff */ xfs_ino_t i_ino; /* inode number (agno/agino)*/ @@ -231,7 +241,7 @@ xfs_iflags_clear(xfs_inode_t *ip, unsigned long flags) } static inline int -__xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) +__xfs_iflags_test(const struct xfs_inode *ip, unsigned long flags) { return (ip->i_flags & flags); } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 912f0b1bc3cb..35803fcf0beb 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -157,6 +157,20 @@ xfs_inode_item_precommit( if (flags & XFS_ILOG_IVERSION) flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE); + /* + * Inode verifiers do not check that the CoW extent size hint is an + * integer multiple of the rt extent size on a directory with both + * rtinherit and cowextsize flags set. If we're logging a directory + * that is misconfigured in this way, clear the hint. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + xfs_extlen_to_rtxmod(ip->i_mount, ip->i_cowextsize) > 0) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + flags |= XFS_ILOG_CORE; + } + if (!iip->ili_item.li_buf) { struct xfs_buf *bp; int error; @@ -185,7 +199,7 @@ xfs_inode_item_precommit( xfs_buf_hold(bp); spin_lock(&iip->ili_lock); iip->ili_item.li_buf = bp; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); xfs_trans_brelse(tp, bp); } @@ -242,6 +256,7 @@ xfs_inode_item_data_fork_size( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: if ((iip->ili_fields & XFS_ILOG_DBROOT) && ip->i_df.if_broot_bytes > 0) { *nbytes += ip->i_df.if_broot_bytes; @@ -362,6 +377,7 @@ xfs_inode_item_format_data_fork( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: iip->ili_fields &= ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV); @@ -1023,18 +1039,6 @@ xfs_buf_inode_iodone( list_splice_tail(&flushed_inodes, &bp->b_li_list); } -void -xfs_buf_inode_io_fail( - struct xfs_buf *bp) -{ - struct xfs_log_item *lip; - - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - set_bit(XFS_LI_FAILED, &lip->li_flags); - clear_bit(XFS_LI_FLUSHING, &lip->li_flags); - } -} - /* * Clear the inode logging fields so no more flushes are attempted. If we are * on a buffer list, it is now safe to remove it because the buffer is diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index e70d2611456b..f3bfb814378c 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -22,6 +22,8 @@ #include "xfs_log_recover.h" #include "xfs_icache.h" #include "xfs_bmap_btree.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" STATIC void xlog_recover_inode_ra_pass2( @@ -266,6 +268,41 @@ xlog_dinode_verify_extent_counts( return 0; } +static inline int +xlog_recover_inode_dbroot( + struct xfs_mount *mp, + void *src, + unsigned int len, + struct xfs_dinode *dip) +{ + void *dfork = XFS_DFORK_DPTR(dip); + unsigned int dsize = XFS_DFORK_DSIZE(dip, mp); + + switch (dip->di_format) { + case XFS_DINODE_FMT_BTREE: + xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize); + break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize); + return 0; + case XFS_METAFILE_RTREFCOUNT: + xfs_rtrefcountbt_to_disk(mp, src, len, dfork, dsize); + return 0; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; +} + STATIC int xlog_recover_inode_commit_pass2( struct xlog *log, @@ -393,8 +430,9 @@ xlog_recover_inode_commit_pass2( if (unlikely(S_ISREG(ldip->di_mode))) { - if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && - (ldip->di_format != XFS_DINODE_FMT_BTREE)) { + if (ldip->di_format != XFS_DINODE_FMT_EXTENTS && + ldip->di_format != XFS_DINODE_FMT_BTREE && + ldip->di_format != XFS_DINODE_FMT_META_BTREE) { XFS_CORRUPTION_ERROR( "Bad log dinode data fork format for regular file", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); @@ -475,9 +513,9 @@ xlog_recover_inode_commit_pass2( break; case XFS_ILOG_DBROOT: - xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len, - (struct xfs_bmdr_block *)XFS_DFORK_DPTR(dip), - XFS_DFORK_DSIZE(dip, mp)); + error = xlog_recover_inode_dbroot(mp, src, len, dip); + if (error) + goto out_release; break; default: diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0789c18aaa18..ed85322507dd 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -469,8 +469,21 @@ xfs_fill_fsxattr( } } - if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) - fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { + /* + * Don't let a misaligned CoW extent size hint on a directory + * escape to userspace if it won't pass the setattr checks + * later. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + ip->i_cowextsize % mp->m_sb.sb_rextsize > 0) { + fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; + fa->fsx_cowextsize = 0; + } else { + fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + } + } + fa->fsx_projid = ip->i_projid; if (ifp && !xfs_need_iread_extents(ifp)) fa->fsx_nextents = xfs_iext_count(ifp); @@ -541,10 +554,6 @@ xfs_ioctl_setattr_xflags( if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || xfs_extlen_to_rtxmod(mp, ip->i_extsize)) return -EINVAL; - - /* Clear reflink if we are actually able to set the rt flag. */ - if (xfs_is_reflink_inode(ip)) - ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* diflags2 only valid for v3 inodes. */ @@ -1204,7 +1213,16 @@ xfs_file_ioctl( struct xfs_buftarg *target = xfs_inode_buftarg(ip); struct dioattr da; - da.d_mem = da.d_miniosz = target->bt_logical_sectorsize; + da.d_mem = target->bt_logical_sectorsize; + + /* + * See xfs_report_dioalign() for an explanation about why this + * reports a value larger than the sector size for COW inodes. + */ + if (xfs_is_cow_inode(ip)) + da.d_miniosz = xfs_inode_alloc_unitsize(ip); + else + da.d_miniosz = target->bt_logical_sectorsize; da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1); if (copy_to_user(arg, &da, sizeof(da))) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 207e0dadffc3..40289fe6f5b2 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -573,17 +573,43 @@ xfs_stat_blksize( } static void -xfs_get_atomic_write_attr( +xfs_report_dioalign( struct xfs_inode *ip, - unsigned int *unit_min, - unsigned int *unit_max) + struct kstat *stat) { - if (!xfs_inode_can_atomicwrite(ip)) { - *unit_min = *unit_max = 0; - return; - } + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + struct block_device *bdev = target->bt_bdev; + + stat->result_mask |= STATX_DIOALIGN | STATX_DIO_READ_ALIGN; + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - *unit_min = *unit_max = ip->i_mount->m_sb.sb_blocksize; + /* + * For COW inodes, we can only perform out of place writes of entire + * allocation units (blocks or RT extents). + * For writes smaller than the allocation unit, we must fall back to + * buffered I/O to perform read-modify-write cycles. At best this is + * highly inefficient; at worst it leads to page cache invalidation + * races. Tell applications to avoid this by reporting the larger write + * alignment in dio_offset_align, and the smaller read alignment in + * dio_read_offset_align. + */ + stat->dio_read_offset_align = bdev_logical_block_size(bdev); + if (xfs_is_cow_inode(ip)) + stat->dio_offset_align = xfs_inode_alloc_unitsize(ip); + else + stat->dio_offset_align = stat->dio_read_offset_align; +} + +static void +xfs_report_atomic_write( + struct xfs_inode *ip, + struct kstat *stat) +{ + unsigned int unit_min = 0, unit_max = 0; + + if (xfs_inode_can_atomicwrite(ip)) + unit_min = unit_max = ip->i_mount->m_sb.sb_blocksize; + generic_fill_statx_atomic_writes(stat, unit_min, unit_max); } STATIC int @@ -647,22 +673,10 @@ xfs_vn_getattr( stat->rdev = inode->i_rdev; break; case S_IFREG: - if (request_mask & STATX_DIOALIGN) { - struct xfs_buftarg *target = xfs_inode_buftarg(ip); - struct block_device *bdev = target->bt_bdev; - - stat->result_mask |= STATX_DIOALIGN; - stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - stat->dio_offset_align = bdev_logical_block_size(bdev); - } - if (request_mask & STATX_WRITE_ATOMIC) { - unsigned int unit_min, unit_max; - - xfs_get_atomic_write_attr(ip, &unit_min, - &unit_max); - generic_fill_statx_atomic_writes(stat, - unit_min, unit_max); - } + if (request_mask & (STATX_DIOALIGN | STATX_DIO_READ_ALIGN)) + xfs_report_dioalign(ip, stat); + if (request_mask & STATX_WRITE_ATOMIC) + xfs_report_atomic_write(ip, stat); fallthrough; default: stat->blksize = xfs_stat_blksize(ip); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 05daad8a8d34..f8851ff835de 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -2744,8 +2744,6 @@ xfs_log_ticket_regrant( if (!ticket->t_cnt) { xlog_grant_add_space(&log->l_reserve_head, ticket->t_unit_res); trace_xfs_log_ticket_regrant_exit(log, ticket); - - ticket->t_curr_res = ticket->t_unit_res; } xfs_log_ticket_put(ticket); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 0af3d477197b..b3c27dbccce8 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1820,6 +1820,10 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = { &xlog_xmd_item_ops, &xlog_rtefi_item_ops, &xlog_rtefd_item_ops, + &xlog_rtrui_item_ops, + &xlog_rtrud_item_ops, + &xlog_rtcui_item_ops, + &xlog_rtcud_item_ops, }; static const struct xlog_recover_item_ops * diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 5918f433dba7..477c5262cf91 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -37,6 +37,8 @@ #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" #include "scrub/stats.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); @@ -650,6 +652,15 @@ xfs_agbtree_compute_maxlevels( mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels); } +/* Compute maximum possible height for realtime btree types for this fs. */ +static inline void +xfs_rtbtree_compute_maxlevels( + struct xfs_mount *mp) +{ + mp->m_rtbtree_maxlevels = max(mp->m_rtrmap_maxlevels, + mp->m_rtrefc_maxlevels); +} + /* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct @@ -718,9 +729,12 @@ xfs_mountfs( xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK); xfs_mount_setup_inode_geom(mp); xfs_rmapbt_compute_maxlevels(mp); + xfs_rtrmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); xfs_agbtree_compute_maxlevels(mp); + xfs_rtbtree_compute_maxlevels(mp); /* * Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index db9dade7d22a..fbed172d6770 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -158,13 +158,20 @@ typedef struct xfs_mount { uint m_bmap_dmnr[2]; /* min bmap btree records */ uint m_rmap_mxr[2]; /* max rmap btree records */ uint m_rmap_mnr[2]; /* min rmap btree records */ + uint m_rtrmap_mxr[2]; /* max rtrmap btree records */ + uint m_rtrmap_mnr[2]; /* min rtrmap btree records */ uint m_refc_mxr[2]; /* max refc btree records */ uint m_refc_mnr[2]; /* min refc btree records */ + uint m_rtrefc_mxr[2]; /* max rtrefc btree records */ + uint m_rtrefc_mnr[2]; /* min rtrefc btree records */ uint m_alloc_maxlevels; /* max alloc btree levels */ uint m_bm_maxlevels[2]; /* max bmap btree levels */ uint m_rmap_maxlevels; /* max rmap btree levels */ + uint m_rtrmap_maxlevels; /* max rtrmap btree level */ uint m_refc_maxlevels; /* max refcount btree level */ + uint m_rtrefc_maxlevels; /* max rtrefc btree level */ unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */ + unsigned int m_rtbtree_maxlevels; /* max level of all rt btrees */ xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */ uint m_alloc_set_aside; /* space we can't use */ uint m_ag_max_usable; /* max space per AG */ @@ -350,7 +357,7 @@ typedef struct xfs_mount { #define XFS_FEAT_NOUUID (1ULL << 63) /* ignore uuid during mount */ #define __XFS_HAS_FEAT(name, NAME) \ -static inline bool xfs_has_ ## name (struct xfs_mount *mp) \ +static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \ { \ return mp->m_features & XFS_FEAT_ ## NAME; \ } @@ -386,18 +393,30 @@ __XFS_HAS_FEAT(large_extent_counts, NREXT64) __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE) __XFS_HAS_FEAT(metadir, METADIR) -static inline bool xfs_has_rtgroups(struct xfs_mount *mp) +static inline bool xfs_has_rtgroups(const struct xfs_mount *mp) { /* all metadir file systems also allow rtgroups */ return xfs_has_metadir(mp); } -static inline bool xfs_has_rtsb(struct xfs_mount *mp) +static inline bool xfs_has_rtsb(const struct xfs_mount *mp) { /* all rtgroups filesystems with an rt section have an rtsb */ return xfs_has_rtgroups(mp) && xfs_has_realtime(mp); } +static inline bool xfs_has_rtrmapbt(const struct xfs_mount *mp) +{ + return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) && + xfs_has_rmapbt(mp); +} + +static inline bool xfs_has_rtreflink(const struct xfs_mount *mp) +{ + return xfs_has_metadir(mp) && xfs_has_realtime(mp) && + xfs_has_reflink(mp); +} + /* * Some features are always on for v5 file systems, allow the compiler to * eliminiate dead code when building without v4 support. diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index fa50e5308292..ed8d8ed42f0a 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -19,6 +19,9 @@ #include "xfs_rtalloc.h" #include "xfs_trans.h" #include "xfs_ag.h" +#include "xfs_notify_failure.h" +#include "xfs_rtgroup.h" +#include "xfs_rtrmap_btree.h" #include <linux/mm.h> #include <linux/dax.h> @@ -154,23 +157,115 @@ xfs_dax_notify_failure_thaw( } static int -xfs_dax_notify_ddev_failure( +xfs_dax_translate_range( + struct xfs_buftarg *btp, + u64 offset, + u64 len, + xfs_daddr_t *daddr, + uint64_t *bblen) +{ + u64 dev_start = btp->bt_dax_part_off; + u64 dev_len = bdev_nr_bytes(btp->bt_bdev); + u64 dev_end = dev_start + dev_len - 1; + + /* Notify failure on the whole device. */ + if (offset == 0 && len == U64_MAX) { + offset = dev_start; + len = dev_len; + } + + /* Ignore the range out of filesystem area */ + if (offset + len - 1 < dev_start) + return -ENXIO; + if (offset > dev_end) + return -ENXIO; + + /* Calculate the real range when it touches the boundary */ + if (offset > dev_start) + offset -= dev_start; + else { + len -= dev_start - offset; + offset = 0; + } + if (offset + len - 1 > dev_end) + len = dev_end - offset + 1; + + *daddr = BTOBB(offset); + *bblen = BTOBB(len); + return 0; +} + +static int +xfs_dax_notify_logdev_failure( struct xfs_mount *mp, - xfs_daddr_t daddr, - xfs_daddr_t bblen, + u64 offset, + u64 len, int mf_flags) { + xfs_daddr_t daddr; + uint64_t bblen; + int error; + + /* + * Return ENXIO instead of shutting down the filesystem if the failed + * region is beyond the end of the log. + */ + error = xfs_dax_translate_range(mp->m_logdev_targp, + offset, len, &daddr, &bblen); + if (error) + return error; + + /* + * In the pre-remove case the failure notification is attempting to + * trigger a force unmount. The expectation is that the device is + * still present, but its removal is in progress and can not be + * cancelled, proceed with accessing the log device. + */ + if (mf_flags & MF_MEM_PRE_REMOVE) + return 0; + + xfs_err(mp, "ondisk log corrupt, shutting down fs!"); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; +} + +static int +xfs_dax_notify_dev_failure( + struct xfs_mount *mp, + u64 offset, + u64 len, + int mf_flags, + enum xfs_group_type type) +{ struct xfs_failure_info notify = { .mf_flags = mf_flags }; struct xfs_trans *tp = NULL; struct xfs_btree_cur *cur = NULL; - struct xfs_buf *agf_bp = NULL; int error = 0; bool kernel_frozen = false; - xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); - xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, - daddr + bblen - 1); - xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + uint32_t start_gno, end_gno; + xfs_fsblock_t start_bno, end_bno; + xfs_daddr_t daddr; + uint64_t bblen; + struct xfs_group *xg = NULL; + + if (!xfs_has_rmapbt(mp)) { + xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + error = xfs_dax_translate_range(type == XG_TYPE_RTG ? + mp->m_rtdev_targp : mp->m_ddev_targp, + offset, len, &daddr, &bblen); + if (error) + return error; + + if (type == XG_TYPE_RTG) { + start_bno = xfs_daddr_to_rtb(mp, daddr); + end_bno = xfs_daddr_to_rtb(mp, daddr + bblen - 1); + } else { + start_bno = XFS_DADDR_TO_FSB(mp, daddr); + end_bno = XFS_DADDR_TO_FSB(mp, daddr + bblen - 1); + } if (mf_flags & MF_MEM_PRE_REMOVE) { xfs_info(mp, "Device is about to be removed!"); @@ -189,46 +284,58 @@ xfs_dax_notify_ddev_failure( if (error) goto out; - for (; agno <= end_agno; agno++) { + start_gno = xfs_fsb_to_gno(mp, start_bno, type); + end_gno = xfs_fsb_to_gno(mp, end_bno, type); + while ((xg = xfs_group_next_range(mp, xg, start_gno, end_gno, type))) { + struct xfs_buf *agf_bp = NULL; + struct xfs_rtgroup *rtg = NULL; struct xfs_rmap_irec ri_low = { }; struct xfs_rmap_irec ri_high; - struct xfs_agf *agf; - struct xfs_perag *pag; - xfs_agblock_t range_agend; - pag = xfs_perag_get(mp, agno); - error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); - if (error) { - xfs_perag_put(pag); - break; - } + if (type == XG_TYPE_AG) { + struct xfs_perag *pag = to_perag(xg); - cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); + if (error) { + xfs_perag_put(pag); + break; + } + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + } else { + rtg = to_rtg(xg); + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + cur = xfs_rtrmapbt_init_cursor(tp, rtg); + } /* * Set the rmap range from ri_low to ri_high, which represents * a [start, end] where we looking for the files or metadata. */ memset(&ri_high, 0xFF, sizeof(ri_high)); - ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); - if (agno == end_agno) - ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + if (xg->xg_gno == start_gno) + ri_low.rm_startblock = + xfs_fsb_to_gbno(mp, start_bno, type); + if (xg->xg_gno == end_gno) + ri_high.rm_startblock = + xfs_fsb_to_gbno(mp, end_bno, type); - agf = agf_bp->b_addr; - range_agend = min(be32_to_cpu(agf->agf_length) - 1, - ri_high.rm_startblock); notify.startblock = ri_low.rm_startblock; - notify.blockcount = range_agend + 1 - ri_low.rm_startblock; + notify.blockcount = min(xg->xg_block_count, + ri_high.rm_startblock + 1) - + ri_low.rm_startblock; error = xfs_rmap_query_range(cur, &ri_low, &ri_high, xfs_dax_failure_fn, ¬ify); xfs_btree_del_cursor(cur, error); - xfs_trans_brelse(tp, agf_bp); - xfs_perag_put(pag); - if (error) + if (agf_bp) + xfs_trans_brelse(tp, agf_bp); + if (rtg) + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + if (error) { + xfs_group_put(xg); break; - - fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } } xfs_trans_cancel(tp); @@ -263,67 +370,20 @@ xfs_dax_notify_failure( int mf_flags) { struct xfs_mount *mp = dax_holder(dax_dev); - u64 ddev_start; - u64 ddev_end; if (!(mp->m_super->s_flags & SB_BORN)) { xfs_warn(mp, "filesystem is not ready for notify_failure()!"); return -EIO; } - if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { - xfs_debug(mp, - "notify_failure() not supported on realtime device!"); - return -EOPNOTSUPP; - } - - if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && - mp->m_logdev_targp != mp->m_ddev_targp) { - /* - * In the pre-remove case the failure notification is attempting - * to trigger a force unmount. The expectation is that the - * device is still present, but its removal is in progress and - * can not be cancelled, proceed with accessing the log device. - */ - if (mf_flags & MF_MEM_PRE_REMOVE) - return 0; - xfs_err(mp, "ondisk log corrupt, shutting down fs!"); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); - return -EFSCORRUPTED; - } - - if (!xfs_has_rmapbt(mp)) { - xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); - return -EOPNOTSUPP; - } - - ddev_start = mp->m_ddev_targp->bt_dax_part_off; - ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1; - - /* Notify failure on the whole device. */ - if (offset == 0 && len == U64_MAX) { - offset = ddev_start; - len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev); - } - - /* Ignore the range out of filesystem area */ - if (offset + len - 1 < ddev_start) - return -ENXIO; - if (offset > ddev_end) - return -ENXIO; - - /* Calculate the real range when it touches the boundary */ - if (offset > ddev_start) - offset -= ddev_start; - else { - len -= ddev_start - offset; - offset = 0; + if (mp->m_logdev_targp != mp->m_ddev_targp && + mp->m_logdev_targp->bt_daxdev == dax_dev) { + return xfs_dax_notify_logdev_failure(mp, offset, len, mf_flags); } - if (offset + len - 1 > ddev_end) - len = ddev_end - offset + 1; - return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), - mf_flags); + return xfs_dax_notify_dev_failure(mp, offset, len, mf_flags, + (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) ? + XG_TYPE_RTG : XG_TYPE_AG); } const struct dax_holder_operations xfs_dax_holder_operations = { diff --git a/fs/xfs/xfs_notify_failure.h b/fs/xfs/xfs_notify_failure.h new file mode 100644 index 000000000000..8d08ec29dd29 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <djwong@kernel.org> + */ +#ifndef __XFS_NOTIFY_FAILURE_H__ +#define __XFS_NOTIFY_FAILURE_H__ + +extern const struct dax_holder_operations xfs_dax_holder_operations; + +#endif /* __XFS_NOTIFY_FAILURE_H__ */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 61ee110b47d7..e1ba5af6250f 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -148,17 +148,29 @@ xfs_qm_dqpurge( * We don't care about getting disk errors here. We need * to purge this dquot anyway, so we go ahead regardless. */ - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (error == -EAGAIN) { + xfs_dqfunlock(dqp); + dqp->q_flags &= ~XFS_DQFLAG_FREEING; + goto out_unlock; + } + if (!bp) + goto out_funlock; + + /* + * dqflush completes dqflock on error, and the bwrite ioend + * does it on success. + */ + error = xfs_qm_dqflush(dqp, bp); if (!error) { error = xfs_bwrite(bp); xfs_buf_relse(bp); - } else if (error == -EAGAIN) { - dqp->q_flags &= ~XFS_DQFLAG_FREEING; - goto out_unlock; } xfs_dqflock(dqp); } + xfs_dquot_detach_buf(dqp); +out_funlock: ASSERT(atomic_read(&dqp->q_pincount) == 0); ASSERT(xlog_is_shutdown(dqp->q_logitem.qli_item.li_log) || !test_bit(XFS_LI_IN_AIL, &dqp->q_logitem.qli_item.li_flags)); @@ -218,10 +230,10 @@ xfs_qm_unmount_rt( if (!rtg) return; - if (rtg->rtg_inodes[XFS_RTGI_BITMAP]) - xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_BITMAP]); - if (rtg->rtg_inodes[XFS_RTGI_SUMMARY]) - xfs_qm_dqdetach(rtg->rtg_inodes[XFS_RTGI_SUMMARY]); + if (rtg_bitmap(rtg)) + xfs_qm_dqdetach(rtg_bitmap(rtg)); + if (rtg_summary(rtg)) + xfs_qm_dqdetach(rtg_summary(rtg)); xfs_rtgroup_rele(rtg); } @@ -241,6 +253,10 @@ xfs_qm_destroy_quotainos( xfs_irele(qi->qi_pquotaip); qi->qi_pquotaip = NULL; } + if (qi->qi_dirip) { + xfs_irele(qi->qi_dirip); + qi->qi_dirip = NULL; + } } /* @@ -412,6 +428,8 @@ void xfs_qm_dqdetach( xfs_inode_t *ip) { + if (xfs_is_metadir_inode(ip)) + return; if (!(ip->i_udquot || ip->i_gdquot || ip->i_pdquot)) return; @@ -490,7 +508,17 @@ xfs_qm_dquot_isolate( /* we have to drop the LRU lock to flush the dquot */ spin_unlock(&lru->lock); - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (!bp || error == -EAGAIN) { + xfs_dqfunlock(dqp); + goto out_unlock_dirty; + } + + /* + * dqflush completes dqflock on error, and the delwri ioend + * does it on success. + */ + error = xfs_qm_dqflush(dqp, bp); if (error) goto out_unlock_dirty; @@ -498,6 +526,8 @@ xfs_qm_dquot_isolate( xfs_buf_relse(bp); goto out_unlock_dirty; } + + xfs_dquot_detach_buf(dqp); xfs_dqfunlock(dqp); /* @@ -646,8 +676,7 @@ xfs_qm_init_timelimits( static int xfs_qm_load_metadir_qinos( struct xfs_mount *mp, - struct xfs_quotainfo *qi, - struct xfs_inode **dpp) + struct xfs_quotainfo *qi) { struct xfs_trans *tp; int error; @@ -656,7 +685,7 @@ xfs_qm_load_metadir_qinos( if (error) return error; - error = xfs_dqinode_load_parent(tp, dpp); + error = xfs_dqinode_load_parent(tp, &qi->qi_dirip); if (error == -ENOENT) { /* no quota dir directory, but we'll create one later */ error = 0; @@ -666,21 +695,21 @@ xfs_qm_load_metadir_qinos( goto out_trans; if (XFS_IS_UQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_USER, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_USER, &qi->qi_uquotaip); if (error && error != -ENOENT) goto out_trans; } if (XFS_IS_GQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_GROUP, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_GROUP, &qi->qi_gquotaip); if (error && error != -ENOENT) goto out_trans; } if (XFS_IS_PQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_PROJ, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_PROJ, &qi->qi_pquotaip); if (error && error != -ENOENT) goto out_trans; @@ -696,34 +725,40 @@ out_trans: STATIC int xfs_qm_create_metadir_qinos( struct xfs_mount *mp, - struct xfs_quotainfo *qi, - struct xfs_inode **dpp) + struct xfs_quotainfo *qi) { int error; - if (!*dpp) { - error = xfs_dqinode_mkdir_parent(mp, dpp); + if (!qi->qi_dirip) { + error = xfs_dqinode_mkdir_parent(mp, &qi->qi_dirip); if (error && error != -EEXIST) return error; + /* + * If the /quotas dirent points to an inode that isn't + * loadable, qi_dirip will be NULL but mkdir_parent will return + * -EEXIST. In this case the metadir is corrupt, so bail out. + */ + if (XFS_IS_CORRUPT(mp, qi->qi_dirip == NULL)) + return -EFSCORRUPTED; } if (XFS_IS_UQUOTA_ON(mp) && !qi->qi_uquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_USER, - &qi->qi_uquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_USER, &qi->qi_uquotaip); if (error) return error; } if (XFS_IS_GQUOTA_ON(mp) && !qi->qi_gquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_GROUP, - &qi->qi_gquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_GROUP, &qi->qi_gquotaip); if (error) return error; } if (XFS_IS_PQUOTA_ON(mp) && !qi->qi_pquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_PROJ, - &qi->qi_pquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_PROJ, &qi->qi_pquotaip); if (error) return error; } @@ -768,7 +803,6 @@ xfs_qm_init_metadir_qinos( struct xfs_mount *mp) { struct xfs_quotainfo *qi = mp->m_quotainfo; - struct xfs_inode *dp = NULL; int error; if (!xfs_has_quota(mp)) { @@ -777,20 +811,22 @@ xfs_qm_init_metadir_qinos( return error; } - error = xfs_qm_load_metadir_qinos(mp, qi, &dp); + error = xfs_qm_load_metadir_qinos(mp, qi); if (error) goto out_err; - error = xfs_qm_create_metadir_qinos(mp, qi, &dp); + error = xfs_qm_create_metadir_qinos(mp, qi); if (error) goto out_err; - xfs_irele(dp); + /* The only user of the quota dir inode is online fsck */ +#if !IS_ENABLED(CONFIG_XFS_ONLINE_SCRUB) + xfs_irele(qi->qi_dirip); + qi->qi_dirip = NULL; +#endif return 0; out_err: xfs_qm_destroy_quotainos(mp->m_quotainfo); - if (dp) - xfs_irele(dp); return error; } @@ -1304,6 +1340,10 @@ xfs_qm_quotacheck_dqadjust( return error; } + error = xfs_dquot_attach_buf(NULL, dqp); + if (error) + return error; + trace_xfs_dqadjust(dqp); /* @@ -1486,11 +1526,17 @@ xfs_qm_flush_one( goto out_unlock; } - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); if (error) goto out_unlock; + if (!bp) { + error = -EFSCORRUPTED; + goto out_unlock; + } - xfs_buf_delwri_queue(bp, buffer_list); + error = xfs_qm_dqflush(dqp, bp); + if (!error) + xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); out_unlock: xfs_dqunlock(dqp); diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index e919c7f62f57..35b64bc3a7a8 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -55,6 +55,7 @@ struct xfs_quotainfo { struct xfs_inode *qi_uquotaip; /* user quota inode */ struct xfs_inode *qi_gquotaip; /* group quota inode */ struct xfs_inode *qi_pquotaip; /* project quota inode */ + struct xfs_inode *qi_dirip; /* quota metadir */ struct list_lru qi_lru; int qi_dquots; struct mutex qi_quotaofflock;/* to serialize quotaoff */ diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 847ba29630e9..37f1230e7584 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -32,21 +32,27 @@ xfs_fill_statvfs_from_dquot( limit = blkres->softlimit ? blkres->softlimit : blkres->hardlimit; - if (limit && statp->f_blocks > limit) { - statp->f_blocks = limit; - statp->f_bfree = statp->f_bavail = - (statp->f_blocks > blkres->reserved) ? - (statp->f_blocks - blkres->reserved) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > blkres->reserved) + remaining = limit - blkres->reserved; + + statp->f_blocks = min(statp->f_blocks, limit); + statp->f_bfree = min(statp->f_bfree, remaining); } limit = dqp->q_ino.softlimit ? dqp->q_ino.softlimit : dqp->q_ino.hardlimit; - if (limit && statp->f_files > limit) { - statp->f_files = limit; - statp->f_ffree = - (statp->f_files > dqp->q_ino.reserved) ? - (statp->f_files - dqp->q_ino.reserved) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > dqp->q_ino.reserved) + remaining = limit - dqp->q_ino.reserved; + + statp->f_files = min(statp->f_files, limit); + statp->f_ffree = min(statp->f_ffree, remaining); } } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index fa1317cc396c..105e6eb57620 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -29,11 +29,6 @@ struct xfs_buf; (XFS_IS_GQUOTA_ON(mp) && (ip)->i_gdquot == NULL) || \ (XFS_IS_PQUOTA_ON(mp) && (ip)->i_pdquot == NULL)) -#define XFS_IS_DQDETACHED(ip) \ - ((ip)->i_udquot == NULL && \ - (ip)->i_gdquot == NULL && \ - (ip)->i_pdquot == NULL) - #define XFS_QM_NEED_QUOTACHECK(mp) \ ((XFS_IS_UQUOTA_ON(mp) && \ (mp->m_sb.sb_qflags & XFS_UQUOTA_CHKD) == 0) || \ @@ -101,7 +96,8 @@ extern void xfs_trans_free_dqinfo(struct xfs_trans *); extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *, uint, int64_t); extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *); -extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *); +void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *tp, + bool already_locked); int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, bool force); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, @@ -173,7 +169,7 @@ static inline void xfs_trans_mod_dquot_byino(struct xfs_trans *tp, { } #define xfs_trans_apply_dquot_deltas(tp) -#define xfs_trans_unreserve_and_mod_dquots(tp) +#define xfs_trans_unreserve_and_mod_dquots(tp, a) static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, bool force) diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index bede1c96c330..fe2d7aab8554 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -23,6 +23,7 @@ #include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" struct kmem_cache *xfs_cui_cache; struct kmem_cache *xfs_cud_cache; @@ -94,8 +95,9 @@ xfs_cui_item_format( ASSERT(atomic_read(&cuip->cui_next_extent) == cuip->cui_format.cui_nextents); + ASSERT(lip->li_type == XFS_LI_CUI || lip->li_type == XFS_LI_CUI_RT); - cuip->cui_format.cui_type = XFS_LI_CUI; + cuip->cui_format.cui_type = lip->li_type; cuip->cui_format.cui_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUI_FORMAT, &cuip->cui_format, @@ -138,12 +140,14 @@ xfs_cui_item_release( STATIC struct xfs_cui_log_item * xfs_cui_init( struct xfs_mount *mp, + unsigned short item_type, uint nextents) - { struct xfs_cui_log_item *cuip; ASSERT(nextents > 0); + ASSERT(item_type == XFS_LI_CUI || item_type == XFS_LI_CUI_RT); + if (nextents > XFS_CUI_MAX_FAST_EXTENTS) cuip = kzalloc(xfs_cui_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); @@ -151,7 +155,7 @@ xfs_cui_init( cuip = kmem_cache_zalloc(xfs_cui_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops); + xfs_log_item_init(mp, &cuip->cui_item, item_type, &xfs_cui_item_ops); cuip->cui_format.cui_nextents = nextents; cuip->cui_format.cui_id = (uintptr_t)(void *)cuip; atomic_set(&cuip->cui_next_extent, 0); @@ -190,7 +194,9 @@ xfs_cud_item_format( struct xfs_cud_log_item *cudp = CUD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; - cudp->cud_format.cud_type = XFS_LI_CUD; + ASSERT(lip->li_type == XFS_LI_CUD || lip->li_type == XFS_LI_CUD_RT); + + cudp->cud_format.cud_type = lip->li_type; cudp->cud_format.cud_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_CUD_FORMAT, &cudp->cud_format, @@ -234,6 +240,14 @@ static inline struct xfs_refcount_intent *ci_entry(const struct list_head *e) return list_entry(e, struct xfs_refcount_intent, ri_list); } +static inline bool +xfs_cui_item_isrt(const struct xfs_log_item *lip) +{ + ASSERT(lip->li_type == XFS_LI_CUI || lip->li_type == XFS_LI_CUI_RT); + + return lip->li_type == XFS_LI_CUI_RT; +} + /* Sort refcount intents by AG. */ static int xfs_refcount_update_diff_items( @@ -282,18 +296,20 @@ xfs_refcount_update_log_item( } static struct xfs_log_item * -xfs_refcount_update_create_intent( +__xfs_refcount_update_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, - bool sort) + bool sort, + unsigned short item_type) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_cui_log_item *cuip = xfs_cui_init(mp, count); + struct xfs_cui_log_item *cuip; struct xfs_refcount_intent *ri; ASSERT(count > 0); + cuip = xfs_cui_init(mp, item_type, count); if (sort) list_sort(mp, items, xfs_refcount_update_diff_items); list_for_each_entry(ri, items, ri_list) @@ -301,6 +317,23 @@ xfs_refcount_update_create_intent( return &cuip->cui_item; } +static struct xfs_log_item * +xfs_refcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_refcount_update_create_intent(tp, items, count, sort, + XFS_LI_CUI); +} + +static inline unsigned short +xfs_cud_type_from_cui(const struct xfs_cui_log_item *cuip) +{ + return xfs_cui_item_isrt(&cuip->cui_item) ? XFS_LI_CUD_RT : XFS_LI_CUD; +} + /* Get an CUD so we can process all the deferred refcount updates. */ static struct xfs_log_item * xfs_refcount_update_create_done( @@ -312,8 +345,8 @@ xfs_refcount_update_create_done( struct xfs_cud_log_item *cudp; cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD, - &xfs_cud_item_ops); + xfs_log_item_init(tp->t_mountp, &cudp->cud_item, + xfs_cud_type_from_cui(cuip), &xfs_cud_item_ops); cudp->cud_cuip = cuip; cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id; @@ -328,10 +361,20 @@ xfs_refcount_defer_add( { struct xfs_mount *mp = tp->t_mountp; - trace_xfs_refcount_defer(mp, ri); + /* + * Deferred refcount updates for the realtime and data sections must + * use separate transactions to finish deferred work because updates to + * realtime metadata files can lock AGFs to allocate btree blocks and + * we don't want that mixing with the AGF locks taken to finish data + * section updates. + */ + ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, + ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG); - ri->ri_group = xfs_group_intent_get(mp, ri->ri_startblock, XG_TYPE_AG); - xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type); + trace_xfs_refcount_defer(mp, ri); + xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ? + &xfs_rtrefcount_update_defer_type : + &xfs_refcount_update_defer_type); } /* Cancel a deferred refcount update. */ @@ -381,7 +424,7 @@ xfs_refcount_finish_one_cleanup( return; agbp = rcur->bc_ag.agbp; xfs_btree_del_cursor(rcur, error); - if (error) + if (error && agbp) xfs_trans_brelse(tp, agbp); } @@ -397,6 +440,7 @@ xfs_refcount_update_abort_intent( static inline bool xfs_cui_validate_phys( struct xfs_mount *mp, + bool isrt, struct xfs_phys_extent *pmap) { if (!xfs_has_reflink(mp)) @@ -415,6 +459,9 @@ xfs_cui_validate_phys( return false; } + if (isrt) + return xfs_verify_rtbext(mp, pmap->pe_startblock, pmap->pe_len); + return xfs_verify_fsbext(mp, pmap->pe_startblock, pmap->pe_len); } @@ -422,6 +469,7 @@ static inline void xfs_cui_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, + bool isrt, struct xfs_phys_extent *pmap) { struct xfs_refcount_intent *ri; @@ -432,7 +480,8 @@ xfs_cui_recover_work( ri->ri_startblock = pmap->pe_startblock; ri->ri_blockcount = pmap->pe_len; ri->ri_group = xfs_group_intent_get(mp, pmap->pe_startblock, - XG_TYPE_AG); + isrt ? XG_TYPE_RTG : XG_TYPE_AG); + ri->ri_realtime = isrt; xfs_defer_add_item(dfp, &ri->ri_list); } @@ -451,6 +500,7 @@ xfs_refcount_recover_work( struct xfs_cui_log_item *cuip = CUI_ITEM(lip); struct xfs_trans *tp; struct xfs_mount *mp = lip->li_log->l_mp; + bool isrt = xfs_cui_item_isrt(lip); int i; int error = 0; @@ -460,7 +510,7 @@ xfs_refcount_recover_work( * just toss the CUI. */ for (i = 0; i < cuip->cui_format.cui_nextents; i++) { - if (!xfs_cui_validate_phys(mp, + if (!xfs_cui_validate_phys(mp, isrt, &cuip->cui_format.cui_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &cuip->cui_format, @@ -468,7 +518,8 @@ xfs_refcount_recover_work( return -EFSCORRUPTED; } - xfs_cui_recover_work(mp, dfp, &cuip->cui_format.cui_extents[i]); + xfs_cui_recover_work(mp, dfp, isrt, + &cuip->cui_format.cui_extents[i]); } /* @@ -515,10 +566,13 @@ xfs_refcount_relog_intent( struct xfs_phys_extent *pmap; unsigned int count; + ASSERT(intent->li_type == XFS_LI_CUI || + intent->li_type == XFS_LI_CUI_RT); + count = CUI_ITEM(intent)->cui_format.cui_nextents; pmap = CUI_ITEM(intent)->cui_format.cui_extents; - cuip = xfs_cui_init(tp->t_mountp, count); + cuip = xfs_cui_init(tp->t_mountp, intent->li_type, count); memcpy(cuip->cui_format.cui_extents, pmap, count * sizeof(*pmap)); atomic_set(&cuip->cui_next_extent, count); @@ -538,6 +592,71 @@ const struct xfs_defer_op_type xfs_refcount_update_defer_type = { .relog_intent = xfs_refcount_relog_intent, }; +#ifdef CONFIG_XFS_RT +static struct xfs_log_item * +xfs_rtrefcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_refcount_update_create_intent(tp, items, count, sort, + XFS_LI_CUI_RT); +} + +/* Process a deferred realtime refcount update. */ +STATIC int +xfs_rtrefcount_update_finish_item( + struct xfs_trans *tp, + struct xfs_log_item *done, + struct list_head *item, + struct xfs_btree_cur **state) +{ + struct xfs_refcount_intent *ri = ci_entry(item); + int error; + + error = xfs_rtrefcount_finish_one(tp, ri, state); + + /* Did we run out of reservation? Requeue what we didn't finish. */ + if (!error && ri->ri_blockcount > 0) { + ASSERT(ri->ri_type == XFS_REFCOUNT_INCREASE || + ri->ri_type == XFS_REFCOUNT_DECREASE); + return -EAGAIN; + } + + xfs_refcount_update_cancel_item(item); + return error; +} + +/* Clean up after calling xfs_rtrefcount_finish_one. */ +STATIC void +xfs_rtrefcount_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + if (rcur) + xfs_btree_del_cursor(rcur, error); +} + +const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type = { + .name = "rtrefcount", + .max_items = XFS_CUI_MAX_FAST_EXTENTS, + .create_intent = xfs_rtrefcount_update_create_intent, + .abort_intent = xfs_refcount_update_abort_intent, + .create_done = xfs_refcount_update_create_done, + .finish_item = xfs_rtrefcount_update_finish_item, + .finish_cleanup = xfs_rtrefcount_finish_one_cleanup, + .cancel_item = xfs_refcount_update_cancel_item, + .recover_work = xfs_refcount_recover_work, + .relog_intent = xfs_refcount_relog_intent, +}; +#else +const struct xfs_defer_op_type xfs_rtrefcount_update_defer_type = { + .name = "rtrefcount", +}; +#endif /* CONFIG_XFS_RT */ + STATIC bool xfs_cui_item_match( struct xfs_log_item *lip, @@ -603,7 +722,7 @@ xlog_recover_cui_commit_pass2( return -EFSCORRUPTED; } - cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); + cuip = xfs_cui_init(mp, ITEM_TYPE(item), cui_formatp->cui_nextents); xfs_cui_copy_format(&cuip->cui_format, cui_formatp); atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); @@ -617,6 +736,61 @@ const struct xlog_recover_item_ops xlog_cui_item_ops = { .commit_pass2 = xlog_recover_cui_commit_pass2, }; +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtcui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_mount *mp = log->l_mp; + struct xfs_cui_log_item *cuip; + struct xfs_cui_log_format *cui_formatp; + size_t len; + + cui_formatp = item->ri_buf[0].i_addr; + + if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + cuip = xfs_cui_init(mp, ITEM_TYPE(item), cui_formatp->cui_nextents); + xfs_cui_copy_format(&cuip->cui_format, cui_formatp); + atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); + + xlog_recover_intent_item(log, &cuip->cui_item, lsn, + &xfs_rtrefcount_update_defer_type); + return 0; +} +#else +STATIC int +xlog_recover_rtcui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; +} +#endif + +const struct xlog_recover_item_ops xlog_rtcui_item_ops = { + .item_type = XFS_LI_CUI_RT, + .commit_pass2 = xlog_recover_rtcui_commit_pass2, +}; + /* * This routine is called when an CUD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding CUI if it @@ -648,3 +822,33 @@ const struct xlog_recover_item_ops xlog_cud_item_ops = { .item_type = XFS_LI_CUD, .commit_pass2 = xlog_recover_cud_commit_pass2, }; + +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtcud_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_cud_log_format *cud_formatp; + + cud_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + xlog_recover_release_intent(log, XFS_LI_CUI_RT, + cud_formatp->cud_cui_id); + return 0; +} +#else +# define xlog_recover_rtcud_commit_pass2 xlog_recover_rtcui_commit_pass2 +#endif + +const struct xlog_recover_item_ops xlog_rtcud_item_ops = { + .item_type = XFS_LI_CUD_RT, + .commit_pass2 = xlog_recover_rtcud_commit_pass2, +}; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index b11769c009ef..59f7fc16eb80 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -30,6 +30,10 @@ #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_health.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_rtgroup.h" +#include "xfs_metafile.h" /* * Copy on Write of Shared Blocks @@ -120,38 +124,93 @@ */ /* - * Given an AG extent, find the lowest-numbered run of shared blocks - * within that range and return the range in fbno/flen. If - * find_end_of_shared is true, return the longest contiguous extent of - * shared blocks. If there are no shared extents, fbno and flen will - * be set to NULLAGBLOCK and 0, respectively. + * Given a file mapping for the data device, find the lowest-numbered run of + * shared blocks within that mapping and return it in shared_offset/shared_len. + * The offset is relative to the start of irec. + * + * If find_end_of_shared is true, return the longest contiguous extent of shared + * blocks. If there are no shared extents, shared_offset and shared_len will be + * set to 0; */ static int xfs_reflink_find_shared( - struct xfs_perag *pag, + struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agblock_t agbno, - xfs_extlen_t aglen, - xfs_agblock_t *fbno, - xfs_extlen_t *flen, + const struct xfs_bmbt_irec *irec, + xfs_extlen_t *shared_offset, + xfs_extlen_t *shared_len, bool find_end_of_shared) { struct xfs_buf *agbp; + struct xfs_perag *pag; struct xfs_btree_cur *cur; int error; + xfs_agblock_t orig_bno, found_bno; + + pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); + orig_bno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) - return error; + goto out; - cur = xfs_refcountbt_init_cursor(pag_mount(pag), tp, agbp, pag); + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + error = xfs_refcount_find_shared(cur, orig_bno, irec->br_blockcount, + &found_bno, shared_len, find_end_of_shared); + xfs_btree_del_cursor(cur, error); + xfs_trans_brelse(tp, agbp); - error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen, - find_end_of_shared); + if (!error && *shared_len) + *shared_offset = found_bno - orig_bno; +out: + xfs_perag_put(pag); + return error; +} +/* + * Given a file mapping for the rt device, find the lowest-numbered run of + * shared blocks within that mapping and return it in shared_offset/shared_len. + * The offset is relative to the start of irec. + * + * If find_end_of_shared is true, return the longest contiguous extent of shared + * blocks. If there are no shared extents, shared_offset and shared_len will be + * set to 0; + */ +static int +xfs_reflink_find_rtshared( + struct xfs_mount *mp, + struct xfs_trans *tp, + const struct xfs_bmbt_irec *irec, + xfs_extlen_t *shared_offset, + xfs_extlen_t *shared_len, + bool find_end_of_shared) +{ + struct xfs_rtgroup *rtg; + struct xfs_btree_cur *cur; + xfs_rgblock_t orig_bno; + xfs_agblock_t found_bno; + int error; + + BUILD_BUG_ON(NULLRGBLOCK != NULLAGBLOCK); + + /* + * Note: this uses the not quite correct xfs_agblock_t type because + * xfs_refcount_find_shared is shared between the RT and data device + * refcount code. + */ + orig_bno = xfs_rtb_to_rgbno(mp, irec->br_startblock); + rtg = xfs_rtgroup_get(mp, xfs_rtb_to_rgno(mp, irec->br_startblock)); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_REFCOUNT); + cur = xfs_rtrefcountbt_init_cursor(tp, rtg); + error = xfs_refcount_find_shared(cur, orig_bno, irec->br_blockcount, + &found_bno, shared_len, find_end_of_shared); xfs_btree_del_cursor(cur, error); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_REFCOUNT); + xfs_rtgroup_put(rtg); - xfs_trans_brelse(tp, agbp); + if (!error && *shared_len) + *shared_offset = found_bno - orig_bno; return error; } @@ -172,11 +231,7 @@ xfs_reflink_trim_around_shared( bool *shared) { struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t fbno; - xfs_extlen_t flen; + xfs_extlen_t shared_offset, shared_len; int error = 0; /* Holes, unwritten, and delalloc extents cannot be shared */ @@ -187,41 +242,37 @@ xfs_reflink_trim_around_shared( trace_xfs_reflink_trim_around_shared(ip, irec); - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); - agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); - aglen = irec->br_blockcount; - - error = xfs_reflink_find_shared(pag, NULL, agbno, aglen, &fbno, &flen, - true); - xfs_perag_put(pag); + if (XFS_IS_REALTIME_INODE(ip)) + error = xfs_reflink_find_rtshared(mp, NULL, irec, + &shared_offset, &shared_len, true); + else + error = xfs_reflink_find_shared(mp, NULL, irec, + &shared_offset, &shared_len, true); if (error) return error; - *shared = false; - if (fbno == NULLAGBLOCK) { + if (!shared_len) { /* No shared blocks at all. */ - return 0; - } - - if (fbno == agbno) { + *shared = false; + } else if (!shared_offset) { /* - * The start of this extent is shared. Truncate the - * mapping at the end of the shared region so that a - * subsequent iteration starts at the start of the - * unshared region. + * The start of this mapping points to shared space. Truncate + * the mapping at the end of the shared region so that a + * subsequent iteration starts at the start of the unshared + * region. */ - irec->br_blockcount = flen; + irec->br_blockcount = shared_len; *shared = true; - return 0; + } else { + /* + * There's a shared region that doesn't start at the beginning + * of the mapping. Truncate the mapping at the start of the + * shared extent so that a subsequent iteration starts at the + * start of the shared region. + */ + irec->br_blockcount = shared_offset; + *shared = false; } - - /* - * There's a shared extent midway through this extent. - * Truncate the mapping at the start of the shared - * extent so that a subsequent iteration starts at the - * start of the shared region. - */ - irec->br_blockcount = fbno - agbno; return 0; } @@ -389,20 +440,26 @@ xfs_reflink_fill_cow_hole( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_filblks_t resaligned; - xfs_extlen_t resblks; + unsigned int dblocks = 0, rblocks = 0; int nimaps; int error; bool found; resaligned = xfs_aligned_fsb_count(imap->br_startoff, imap->br_blockcount, xfs_get_cowextsz_hint(ip)); - resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resaligned; + } else { + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + rblocks = 0; + } xfs_iunlock(ip, *lockmode); *lockmode = 0; - error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, - false, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, + rblocks, false, &tp); if (error) return error; @@ -571,6 +628,7 @@ xfs_reflink_cancel_cow_blocks( struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; + bool isrt = XFS_IS_REALTIME_INODE(ip); int error = 0; if (!xfs_inode_has_cow_data(ip)) @@ -598,12 +656,13 @@ xfs_reflink_cancel_cow_blocks( ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER); /* Free the CoW orphan record. */ - xfs_refcount_free_cow_extent(*tpp, del.br_startblock, - del.br_blockcount); + xfs_refcount_free_cow_extent(*tpp, isrt, + del.br_startblock, del.br_blockcount); error = xfs_free_extent_later(*tpp, del.br_startblock, del.br_blockcount, NULL, - XFS_AG_RESV_NONE, 0); + XFS_AG_RESV_NONE, + isrt ? XFS_FREE_EXTENT_REALTIME : 0); if (error) break; @@ -687,6 +746,35 @@ out: return error; } +#ifdef CONFIG_XFS_QUOTA +/* + * Update quota accounting for a remapping operation. When we're remapping + * something from the CoW fork to the data fork, we must update the quota + * accounting for delayed allocations. For remapping from the data fork to the + * data fork, use regular block accounting. + */ +static inline void +xfs_reflink_update_quota( + struct xfs_trans *tp, + struct xfs_inode *ip, + bool is_cow, + int64_t blocks) +{ + unsigned int qflag; + + if (XFS_IS_REALTIME_INODE(ip)) { + qflag = is_cow ? XFS_TRANS_DQ_DELRTBCOUNT : + XFS_TRANS_DQ_RTBCOUNT; + } else { + qflag = is_cow ? XFS_TRANS_DQ_DELBCOUNT : + XFS_TRANS_DQ_BCOUNT; + } + xfs_trans_mod_dquot_byino(tp, ip, qflag, blocks); +} +#else +# define xfs_reflink_update_quota(tp, ip, is_cow, blocks) ((void)0) +#endif + /* * Remap part of the CoW fork into the data fork. * @@ -710,6 +798,7 @@ xfs_reflink_end_cow_extent( struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); unsigned int resblks; int nmaps; + bool isrt = XFS_IS_REALTIME_INODE(ip); int error; resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); @@ -779,9 +868,8 @@ xfs_reflink_end_cow_extent( * or not), unmap the extent and drop its refcount. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &data); - xfs_refcount_decrease_extent(tp, &data); - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, - -data.br_blockcount); + xfs_refcount_decrease_extent(tp, isrt, &data); + xfs_reflink_update_quota(tp, ip, false, -data.br_blockcount); } else if (data.br_startblock == DELAYSTARTBLOCK) { int done; @@ -799,14 +887,14 @@ xfs_reflink_end_cow_extent( } /* Free the CoW orphan record. */ - xfs_refcount_free_cow_extent(tp, del.br_startblock, del.br_blockcount); + xfs_refcount_free_cow_extent(tp, isrt, del.br_startblock, + del.br_blockcount); /* Map the new blocks into the data fork. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &del); /* Charge this new data fork mapping to the on-disk quota. */ - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT, - (long)del.br_blockcount); + xfs_reflink_update_quota(tp, ip, true, del.br_blockcount); /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &icur, &got, &del); @@ -895,20 +983,29 @@ xfs_reflink_recover_cow( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; + struct xfs_rtgroup *rtg = NULL; int error = 0; if (!xfs_has_reflink(mp)) return 0; while ((pag = xfs_perag_next(mp, pag))) { - error = xfs_refcount_recover_cow_leftovers(mp, pag); + error = xfs_refcount_recover_cow_leftovers(pag_group(pag)); if (error) { xfs_perag_rele(pag); - break; + return error; } } - return error; + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + error = xfs_refcount_recover_cow_leftovers(rtg_group(rtg)); + if (error) { + xfs_rtgroup_rele(rtg); + return error; + } + } + + return 0; } /* @@ -1100,14 +1197,28 @@ out_error: static int xfs_reflink_ag_has_free_space( struct xfs_mount *mp, - xfs_agnumber_t agno) + struct xfs_inode *ip, + xfs_fsblock_t fsb) { struct xfs_perag *pag; + xfs_agnumber_t agno; int error = 0; if (!xfs_has_rmapbt(mp)) return 0; + if (XFS_IS_REALTIME_INODE(ip)) { + struct xfs_rtgroup *rtg; + xfs_rgnumber_t rgno; + + rgno = xfs_rtb_to_rgno(mp, fsb); + rtg = xfs_rtgroup_get(mp, rgno); + if (xfs_metafile_resv_critical(rtg_rmap(rtg))) + error = -ENOSPC; + xfs_rtgroup_put(rtg); + return error; + } + agno = XFS_FSB_TO_AGNO(mp, fsb); pag = xfs_perag_get(mp, agno); if (xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) || xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA)) @@ -1131,10 +1242,11 @@ xfs_reflink_remap_extent( struct xfs_trans *tp; xfs_off_t newlen; int64_t qdelta = 0; - unsigned int resblks; + unsigned int dblocks, rblocks, resblks; bool quota_reserved = true; bool smap_real; bool dmap_written = xfs_bmap_is_written_extent(dmap); + bool isrt = XFS_IS_REALTIME_INODE(ip); int iext_delta = 0; int nimaps; int error; @@ -1161,8 +1273,15 @@ xfs_reflink_remap_extent( * we're remapping. */ resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = resblks; + rblocks = dmap->br_blockcount; + } else { + dblocks = resblks + dmap->br_blockcount; + rblocks = 0; + } error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, - resblks + dmap->br_blockcount, 0, false, &tp); + dblocks, rblocks, false, &tp); if (error == -EDQUOT || error == -ENOSPC) { quota_reserved = false; error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, @@ -1213,8 +1332,8 @@ xfs_reflink_remap_extent( /* No reflinking if the AG of the dest mapping is low on space. */ if (dmap_written) { - error = xfs_reflink_ag_has_free_space(mp, - XFS_FSB_TO_AGNO(mp, dmap->br_startblock)); + error = xfs_reflink_ag_has_free_space(mp, ip, + dmap->br_startblock); if (error) goto out_cancel; } @@ -1242,8 +1361,15 @@ xfs_reflink_remap_extent( * done. */ if (!quota_reserved && !smap_real && dmap_written) { - error = xfs_trans_reserve_quota_nblks(tp, ip, - dmap->br_blockcount, 0, false); + if (XFS_IS_REALTIME_INODE(ip)) { + dblocks = 0; + rblocks = dmap->br_blockcount; + } else { + dblocks = dmap->br_blockcount; + rblocks = 0; + } + error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, + false); if (error) goto out_cancel; } @@ -1264,7 +1390,7 @@ xfs_reflink_remap_extent( * or not), unmap the extent and drop its refcount. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &smap); - xfs_refcount_decrease_extent(tp, &smap); + xfs_refcount_decrease_extent(tp, isrt, &smap); qdelta -= smap.br_blockcount; } else if (smap.br_startblock == DELAYSTARTBLOCK) { int done; @@ -1287,12 +1413,12 @@ xfs_reflink_remap_extent( * its refcount and map it into the file. */ if (dmap_written) { - xfs_refcount_increase_extent(tp, dmap); + xfs_refcount_increase_extent(tp, isrt, dmap); xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, dmap); qdelta += dmap->br_blockcount; } - xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, qdelta); + xfs_reflink_update_quota(tp, ip, false, qdelta); /* Update dest isize if needed. */ newlen = XFS_FSB_TO_B(mp, dmap->br_startoff + dmap->br_blockcount); @@ -1466,8 +1592,8 @@ xfs_reflink_remap_prep( /* Check file eligibility and prepare for block sharing. */ ret = -EINVAL; - /* Don't reflink realtime inodes */ - if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) + /* Can't reflink between data and rt volumes */ + if (XFS_IS_REALTIME_INODE(src) != XFS_IS_REALTIME_INODE(dest)) goto out_unlock; /* Don't share DAX file data with non-DAX file. */ @@ -1547,27 +1673,23 @@ xfs_reflink_inode_has_shared_extents( *has_shared = false; found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got); while (found) { - struct xfs_perag *pag; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t rbno; - xfs_extlen_t rlen; + xfs_extlen_t shared_offset, shared_len; if (isnullstartblock(got.br_startblock) || got.br_state != XFS_EXT_NORM) goto next; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, got.br_startblock)); - agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock); - aglen = got.br_blockcount; - error = xfs_reflink_find_shared(pag, tp, agbno, aglen, - &rbno, &rlen, false); - xfs_perag_put(pag); + if (XFS_IS_REALTIME_INODE(ip)) + error = xfs_reflink_find_rtshared(mp, tp, &got, + &shared_offset, &shared_len, false); + else + error = xfs_reflink_find_shared(mp, tp, &got, + &shared_offset, &shared_len, false); if (error) return error; /* Is there still a shared block here? */ - if (rbno != NULLAGBLOCK) { + if (shared_len) { *has_shared = true; return 0; } @@ -1700,3 +1822,28 @@ out: trace_xfs_reflink_unshare_error(ip, error, _RET_IP_); return error; } + +/* + * Can we use reflink with this realtime extent size? Note that we don't check + * for rblocks > 0 here because this can be called as part of attaching a new + * rt section. + */ +bool +xfs_reflink_supports_rextsize( + struct xfs_mount *mp, + unsigned int rextsize) +{ + /* reflink on the realtime device requires rtgroups */ + if (!xfs_has_rtgroups(mp)) + return false; + + /* + * Reflink doesn't support rt extent size larger than a single fsblock + * because we would have to perform CoW-around for unaligned write + * requests to guarantee that we always remap entire rt extents. + */ + if (rextsize != 1) + return false; + + return true; +} diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 4a58e4533671..cc4e92278279 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -25,7 +25,7 @@ xfs_can_free_cowblocks(struct xfs_inode *ip) return true; } -extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, +int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared); int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, bool *shared); @@ -62,4 +62,6 @@ extern int xfs_reflink_remap_blocks(struct xfs_inode *src, loff_t pos_in, extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen, xfs_extlen_t cowextsize, unsigned int remap_flags); +bool xfs_reflink_supports_rextsize(struct xfs_mount *mp, unsigned int rextsize); + #endif /* __XFS_REFLINK_H */ diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 76b3c0ed3b4f..89decffe76c8 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -23,6 +23,7 @@ #include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_trace.h" +#include "xfs_rtgroup.h" struct kmem_cache *xfs_rui_cache; struct kmem_cache *xfs_rud_cache; @@ -94,7 +95,9 @@ xfs_rui_item_format( ASSERT(atomic_read(&ruip->rui_next_extent) == ruip->rui_format.rui_nextents); - ruip->rui_format.rui_type = XFS_LI_RUI; + ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT); + + ruip->rui_format.rui_type = lip->li_type; ruip->rui_format.rui_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format, @@ -137,12 +140,15 @@ xfs_rui_item_release( STATIC struct xfs_rui_log_item * xfs_rui_init( struct xfs_mount *mp, + unsigned short item_type, uint nextents) { struct xfs_rui_log_item *ruip; ASSERT(nextents > 0); + ASSERT(item_type == XFS_LI_RUI || item_type == XFS_LI_RUI_RT); + if (nextents > XFS_RUI_MAX_FAST_EXTENTS) ruip = kzalloc(xfs_rui_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); @@ -150,7 +156,7 @@ xfs_rui_init( ruip = kmem_cache_zalloc(xfs_rui_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops); + xfs_log_item_init(mp, &ruip->rui_item, item_type, &xfs_rui_item_ops); ruip->rui_format.rui_nextents = nextents; ruip->rui_format.rui_id = (uintptr_t)(void *)ruip; atomic_set(&ruip->rui_next_extent, 0); @@ -189,7 +195,9 @@ xfs_rud_item_format( struct xfs_rud_log_item *rudp = RUD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; - rudp->rud_format.rud_type = XFS_LI_RUD; + ASSERT(lip->li_type == XFS_LI_RUD || lip->li_type == XFS_LI_RUD_RT); + + rudp->rud_format.rud_type = lip->li_type; rudp->rud_format.rud_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format, @@ -233,6 +241,14 @@ static inline struct xfs_rmap_intent *ri_entry(const struct list_head *e) return list_entry(e, struct xfs_rmap_intent, ri_list); } +static inline bool +xfs_rui_item_isrt(const struct xfs_log_item *lip) +{ + ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT); + + return lip->li_type == XFS_LI_RUI_RT; +} + /* Sort rmap intents by AG. */ static int xfs_rmap_update_diff_items( @@ -305,18 +321,20 @@ xfs_rmap_update_log_item( } static struct xfs_log_item * -xfs_rmap_update_create_intent( +__xfs_rmap_update_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, - bool sort) + bool sort, + unsigned short item_type) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_rui_log_item *ruip = xfs_rui_init(mp, count); + struct xfs_rui_log_item *ruip; struct xfs_rmap_intent *ri; ASSERT(count > 0); + ruip = xfs_rui_init(mp, item_type, count); if (sort) list_sort(mp, items, xfs_rmap_update_diff_items); list_for_each_entry(ri, items, ri_list) @@ -324,6 +342,23 @@ xfs_rmap_update_create_intent( return &ruip->rui_item; } +static struct xfs_log_item * +xfs_rmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_rmap_update_create_intent(tp, items, count, sort, + XFS_LI_RUI); +} + +static inline unsigned short +xfs_rud_type_from_rui(const struct xfs_rui_log_item *ruip) +{ + return xfs_rui_item_isrt(&ruip->rui_item) ? XFS_LI_RUD_RT : XFS_LI_RUD; +} + /* Get an RUD so we can process all the deferred rmap updates. */ static struct xfs_log_item * xfs_rmap_update_create_done( @@ -335,8 +370,8 @@ xfs_rmap_update_create_done( struct xfs_rud_log_item *rudp; rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL); - xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD, - &xfs_rud_item_ops); + xfs_log_item_init(tp->t_mountp, &rudp->rud_item, + xfs_rud_type_from_rui(ruip), &xfs_rud_item_ops); rudp->rud_ruip = ruip; rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id; @@ -351,11 +386,20 @@ xfs_rmap_defer_add( { struct xfs_mount *mp = tp->t_mountp; - trace_xfs_rmap_defer(mp, ri); - + /* + * Deferred rmap updates for the realtime and data sections must use + * separate transactions to finish deferred work because updates to + * realtime metadata files can lock AGFs to allocate btree blocks and + * we don't want that mixing with the AGF locks taken to finish data + * section updates. + */ ri->ri_group = xfs_group_intent_get(mp, ri->ri_bmap.br_startblock, - XG_TYPE_AG); - xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type); + ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG); + + trace_xfs_rmap_defer(mp, ri); + xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ? + &xfs_rtrmap_update_defer_type : + &xfs_rmap_update_defer_type); } /* Cancel a deferred rmap update. */ @@ -415,6 +459,7 @@ xfs_rmap_update_abort_intent( static inline bool xfs_rui_validate_map( struct xfs_mount *mp, + bool isrt, struct xfs_map_extent *map) { if (!xfs_has_rmapbt(mp)) @@ -444,6 +489,9 @@ xfs_rui_validate_map( if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len)) return false; + if (isrt) + return xfs_verify_rtbext(mp, map->me_startblock, map->me_len); + return xfs_verify_fsbext(mp, map->me_startblock, map->me_len); } @@ -451,6 +499,7 @@ static inline void xfs_rui_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, + bool isrt, const struct xfs_map_extent *map) { struct xfs_rmap_intent *ri; @@ -495,7 +544,9 @@ xfs_rui_recover_work( ri->ri_bmap.br_blockcount = map->me_len; ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM; - ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, XG_TYPE_AG); + ri->ri_group = xfs_group_intent_get(mp, map->me_startblock, + isrt ? XG_TYPE_RTG : XG_TYPE_AG); + ri->ri_realtime = isrt; xfs_defer_add_item(dfp, &ri->ri_list); } @@ -514,6 +565,7 @@ xfs_rmap_recover_work( struct xfs_rui_log_item *ruip = RUI_ITEM(lip); struct xfs_trans *tp; struct xfs_mount *mp = lip->li_log->l_mp; + bool isrt = xfs_rui_item_isrt(lip); int i; int error = 0; @@ -523,7 +575,7 @@ xfs_rmap_recover_work( * just toss the RUI. */ for (i = 0; i < ruip->rui_format.rui_nextents; i++) { - if (!xfs_rui_validate_map(mp, + if (!xfs_rui_validate_map(mp, isrt, &ruip->rui_format.rui_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &ruip->rui_format, @@ -531,7 +583,8 @@ xfs_rmap_recover_work( return -EFSCORRUPTED; } - xfs_rui_recover_work(mp, dfp, &ruip->rui_format.rui_extents[i]); + xfs_rui_recover_work(mp, dfp, isrt, + &ruip->rui_format.rui_extents[i]); } resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); @@ -566,10 +619,13 @@ xfs_rmap_relog_intent( struct xfs_map_extent *map; unsigned int count; + ASSERT(intent->li_type == XFS_LI_RUI || + intent->li_type == XFS_LI_RUI_RT); + count = RUI_ITEM(intent)->rui_format.rui_nextents; map = RUI_ITEM(intent)->rui_format.rui_extents; - ruip = xfs_rui_init(tp->t_mountp, count); + ruip = xfs_rui_init(tp->t_mountp, intent->li_type, count); memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map)); atomic_set(&ruip->rui_next_extent, count); @@ -589,6 +645,47 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = { .relog_intent = xfs_rmap_relog_intent, }; +#ifdef CONFIG_XFS_RT +static struct xfs_log_item * +xfs_rtrmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + return __xfs_rmap_update_create_intent(tp, items, count, sort, + XFS_LI_RUI_RT); +} + +/* Clean up after calling xfs_rmap_finish_one. */ +STATIC void +xfs_rtrmap_finish_one_cleanup( + struct xfs_trans *tp, + struct xfs_btree_cur *rcur, + int error) +{ + if (rcur) + xfs_btree_del_cursor(rcur, error); +} + +const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = { + .name = "rtrmap", + .max_items = XFS_RUI_MAX_FAST_EXTENTS, + .create_intent = xfs_rtrmap_update_create_intent, + .abort_intent = xfs_rmap_update_abort_intent, + .create_done = xfs_rmap_update_create_done, + .finish_item = xfs_rmap_update_finish_item, + .finish_cleanup = xfs_rtrmap_finish_one_cleanup, + .cancel_item = xfs_rmap_update_cancel_item, + .recover_work = xfs_rmap_recover_work, + .relog_intent = xfs_rmap_relog_intent, +}; +#else +const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = { + .name = "rtrmap", +}; +#endif + STATIC bool xfs_rui_item_match( struct xfs_log_item *lip, @@ -654,7 +751,7 @@ xlog_recover_rui_commit_pass2( return -EFSCORRUPTED; } - ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); + ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents); xfs_rui_copy_format(&ruip->rui_format, rui_formatp); atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); @@ -668,6 +765,61 @@ const struct xlog_recover_item_ops xlog_rui_item_ops = { .commit_pass2 = xlog_recover_rui_commit_pass2, }; +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtrui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_mount *mp = log->l_mp; + struct xfs_rui_log_item *ruip; + struct xfs_rui_log_format *rui_formatp; + size_t len; + + rui_formatp = item->ri_buf[0].i_addr; + + if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents); + xfs_rui_copy_format(&ruip->rui_format, rui_formatp); + atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); + + xlog_recover_intent_item(log, &ruip->rui_item, lsn, + &xfs_rtrmap_update_defer_type); + return 0; +} +#else +STATIC int +xlog_recover_rtrui_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; +} +#endif + +const struct xlog_recover_item_ops xlog_rtrui_item_ops = { + .item_type = XFS_LI_RUI_RT, + .commit_pass2 = xlog_recover_rtrui_commit_pass2, +}; + /* * This routine is called when an RUD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding RUI if it @@ -699,3 +851,33 @@ const struct xlog_recover_item_ops xlog_rud_item_ops = { .item_type = XFS_LI_RUD, .commit_pass2 = xlog_recover_rud_commit_pass2, }; + +#ifdef CONFIG_XFS_RT +STATIC int +xlog_recover_rtrud_commit_pass2( + struct xlog *log, + struct list_head *buffer_list, + struct xlog_recover_item *item, + xfs_lsn_t lsn) +{ + struct xfs_rud_log_format *rud_formatp; + + rud_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + rud_formatp, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + xlog_recover_release_intent(log, XFS_LI_RUI_RT, + rud_formatp->rud_rui_id); + return 0; +} +#else +# define xlog_recover_rtrud_commit_pass2 xlog_recover_rtrui_commit_pass2 +#endif + +const struct xlog_recover_item_ops xlog_rtrud_item_ops = { + .item_type = XFS_LI_RUD_RT, + .commit_pass2 = xlog_recover_rtrud_commit_pass2, +}; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 0cb534d71119..d8e6d073d64d 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -22,6 +22,7 @@ #include "xfs_rtalloc.h" #include "xfs_sb.h" #include "xfs_rtbitmap.h" +#include "xfs_rtrmap_btree.h" #include "xfs_quota.h" #include "xfs_log_priv.h" #include "xfs_health.h" @@ -30,6 +31,8 @@ #include "xfs_rtgroup.h" #include "xfs_error.h" #include "xfs_trace.h" +#include "xfs_rtrefcount_btree.h" +#include "xfs_reflink.h" /* * Return whether there are any free extents in the size range given @@ -592,7 +595,7 @@ xfs_rtalloc_sumlevel( * specified. If we don't get maxlen then use prod to trim * the length, if given. The lengths are all in rtextents. */ -STATIC int +static int xfs_rtallocate_extent_size( struct xfs_rtalloc_args *args, xfs_rtxlen_t minlen, /* minimum length to allocate */ @@ -845,6 +848,13 @@ xfs_growfs_rt_init_rtsb( mp->m_rtsb_bp = rtsb_bp; error = xfs_bwrite(rtsb_bp); xfs_buf_unlock(rtsb_bp); + if (error) + return error; + + /* Initialize the rtrmap to reflect the rtsb. */ + if (rtg_rmap(args->rtg) != NULL) + error = xfs_rtrmapbt_init_rtsb(nargs->mp, args->rtg, args->tp); + return error; } @@ -856,8 +866,8 @@ xfs_growfs_rt_bmblock( xfs_fileoff_t bmbno) { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); struct xfs_rtalloc_args args = { .mp = mp, .rtg = rtg, @@ -893,8 +903,9 @@ xfs_growfs_rt_bmblock( goto out_free; nargs.tp = args.tp; - xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP); - xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP); + xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); + xfs_rtgroup_trans_join(args.tp, args.rtg, + XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); /* * Update the bitmap inode's size ondisk and incore. We need to update @@ -980,9 +991,12 @@ xfs_growfs_rt_bmblock( goto out_free; /* - * Ensure the mount RT feature flag is now set. + * Ensure the mount RT feature flag is now set, and compute new + * maxlevels for rt btrees. */ mp->m_features |= XFS_FEAT_REALTIME; + xfs_rtrmapbt_compute_maxlevels(mp); + xfs_rtrefcountbt_compute_maxlevels(mp); kfree(nmp); return 0; @@ -1041,8 +1055,8 @@ xfs_growfs_rt_alloc_blocks( xfs_extlen_t *nrbmblocks) { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; - struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); + struct xfs_inode *rsumip = rtg_summary(rtg); xfs_extlen_t orbmblocks = 0; xfs_extlen_t orsumblocks = 0; struct xfs_mount *nmp; @@ -1150,29 +1164,38 @@ out_rele: return error; } -static int +int xfs_growfs_check_rtgeom( const struct xfs_mount *mp, + xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, xfs_extlen_t rextsize) { + xfs_extlen_t min_logfsbs; struct xfs_mount *nmp; - int error = 0; nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize); if (!nmp) return -ENOMEM; + nmp->m_sb.sb_dblocks = dblocks; + + xfs_rtrmapbt_compute_maxlevels(nmp); + xfs_rtrefcountbt_compute_maxlevels(nmp); + xfs_trans_resv_calc(nmp, M_RES(nmp)); /* * New summary size can't be more than half the size of the log. This * prevents us from getting a log overflow, since we'll log basically * the whole summary file at once. */ - if (nmp->m_rsumblocks > (mp->m_sb.sb_logblocks >> 1)) - error = -EINVAL; + min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp), + nmp->m_rsumblocks * 2); kfree(nmp); - return error; + + if (min_logfsbs > mp->m_sb.sb_logblocks) + return -EINVAL; + return 0; } /* @@ -1263,11 +1286,17 @@ xfs_growfs_rt( XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) goto out_unlock; - /* Unsupported realtime features. */ + /* Check for features supported only on rtgroups filesystems. */ error = -EOPNOTSUPP; - if (xfs_has_quota(mp) && !xfs_has_rtgroups(mp)) - goto out_unlock; - if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp)) + if (!xfs_has_rtgroups(mp)) { + if (xfs_has_rmapbt(mp)) + goto out_unlock; + if (xfs_has_quota(mp)) + goto out_unlock; + if (xfs_has_reflink(mp)) + goto out_unlock; + } else if (xfs_has_reflink(mp) && + !xfs_reflink_supports_rextsize(mp, in->extsize)) goto out_unlock; error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks); @@ -1291,7 +1320,8 @@ xfs_growfs_rt( goto out_unlock; /* Make sure the new fs size won't cause problems with the log. */ - error = xfs_growfs_check_rtgeom(mp, in->newblocks, in->extsize); + error = xfs_growfs_check_rtgeom(mp, mp->m_sb.sb_dblocks, in->newblocks, + in->extsize); if (error) goto out_unlock; @@ -1344,6 +1374,12 @@ xfs_growfs_rt( if (!error) error = error2; + + /* Reset the rt metadata btree space reservations. */ + xfs_rt_resv_free(mp); + error2 = xfs_rt_resv_init(mp); + if (error2 && error2 != -ENOSPC) + error = error2; } out_unlock: @@ -1487,6 +1523,46 @@ xfs_rtalloc_reinit_frextents( return 0; } +/* Free space reservations for rt metadata inodes. */ +void +xfs_rt_resv_free( + struct xfs_mount *mp) +{ + struct xfs_rtgroup *rtg = NULL; + unsigned int i; + + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + for (i = 0; i < XFS_RTGI_MAX; i++) + xfs_metafile_resv_free(rtg->rtg_inodes[i]); + } +} + +/* Reserve space for rt metadata inodes' space expansion. */ +int +xfs_rt_resv_init( + struct xfs_mount *mp) +{ + struct xfs_rtgroup *rtg = NULL; + xfs_filblks_t ask; + int error = 0; + + while ((rtg = xfs_rtgroup_next(mp, rtg))) { + int err2; + + ask = xfs_rtrmapbt_calc_reserves(mp); + err2 = xfs_metafile_resv_init(rtg_rmap(rtg), ask); + if (err2 && !error) + error = err2; + + ask = xfs_rtrefcountbt_calc_reserves(mp); + err2 = xfs_metafile_resv_init(rtg_refcount(rtg), ask); + if (err2 && !error) + error = err2; + } + + return error; +} + /* * Read in the bmbt of an rt metadata inode so that we never have to load them * at runtime. This enables the use of shared ILOCKs for rtbitmap scans. Use @@ -1601,7 +1677,7 @@ xfs_rtpick_extent( xfs_rtxlen_t len) /* allocation length (rtextents) */ { struct xfs_mount *mp = rtg_mount(rtg); - struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP]; + struct xfs_inode *rbmip = rtg_bitmap(rtg); xfs_rtxnum_t b = 0; /* result rtext */ int log2; /* log of sequence number */ uint64_t resid; /* residual after log removed */ @@ -1827,7 +1903,7 @@ xfs_rtallocate_rtg( * For an allocation to an empty file at offset 0, pick an extent that * will space things out in the rt area. */ - if (bno_hint) + if (bno_hint != NULLFSBLOCK) start = xfs_rtb_to_rtx(args.mp, bno_hint); else if (!xfs_has_rtgroups(args.mp) && initial_user_data) start = xfs_rtpick_extent(args.rtg, tp, maxlen); @@ -1885,7 +1961,7 @@ out_unlock: goto out_release; } -static int +int xfs_rtallocate_rtgs( struct xfs_trans *tp, xfs_fsblock_t bno_hint, @@ -1950,7 +2026,10 @@ xfs_rtallocate_align( if (*noalign) { align = mp->m_sb.sb_rextsize; } else { - align = xfs_get_extsz_hint(ap->ip); + if (ap->flags & XFS_BMAPI_COWFORK) + align = xfs_get_cowextsz_hint(ap->ip); + else + align = xfs_get_extsz_hint(ap->ip); if (!align) align = 1; if (align == mp->m_sb.sb_rextsize) diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index 8e2a07b8174b..0d95b29092c9 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -34,6 +34,9 @@ int /* error */ xfs_rtmount_inodes( struct xfs_mount *mp); /* file system mount structure */ +void xfs_rt_resv_free(struct xfs_mount *mp); +int xfs_rt_resv_init(struct xfs_mount *mp); + /* * Grow the realtime area of the filesystem. */ @@ -43,6 +46,8 @@ xfs_growfs_rt( xfs_growfs_rt_t *in); /* user supplied growfs struct */ int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp); +int xfs_growfs_check_rtgeom(const struct xfs_mount *mp, xfs_rfsblock_t dblocks, + xfs_rfsblock_t rblocks, xfs_agblock_t rextsize); #else # define xfs_growfs_rt(mp,in) (-ENOSYS) # define xfs_rtalloc_reinit_frextents(m) (0) @@ -60,6 +65,21 @@ xfs_rtmount_init( } # define xfs_rtmount_inodes(m) (((mp)->m_sb.sb_rblocks == 0)? 0 : (-ENOSYS)) # define xfs_rtunmount_inodes(m) +# define xfs_rt_resv_free(mp) ((void)0) +# define xfs_rt_resv_init(mp) (0) + +static inline int +xfs_growfs_check_rtgeom(const struct xfs_mount *mp, + xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, + xfs_extlen_t rextsize) +{ + return 0; +} #endif /* CONFIG_XFS_RT */ +int xfs_rtallocate_rtgs(struct xfs_trans *tp, xfs_fsblock_t bno_hint, + xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t prod, + bool wasdel, bool initial_user_data, xfs_rtblock_t *bno, + xfs_extlen_t *blen); + #endif /* __XFS_RTALLOC_H__ */ diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index ffb52725c2a8..35c7fb3ba324 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -52,7 +52,10 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { "rmapbt", xfsstats_offset(xs_refcbt_2) }, { "refcntbt", xfsstats_offset(xs_rmap_mem_2) }, { "rmapbt_mem", xfsstats_offset(xs_rcbag_2) }, - { "rcbagbt", xfsstats_offset(xs_qm_dqreclaims)}, + { "rcbagbt", xfsstats_offset(xs_rtrmap_2) }, + { "rtrmapbt", xfsstats_offset(xs_rtrmap_mem_2)}, + { "rtrmapbt_mem", xfsstats_offset(xs_rtrefcbt_2) }, + { "rtrefcntbt", xfsstats_offset(xs_qm_dqreclaims)}, /* we print both series of quota information together */ { "qm", xfsstats_offset(xs_xstrat_bytes)}, }; diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index a61fb56ed2e6..15ba1abcf253 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -127,6 +127,9 @@ struct __xfsstats { uint32_t xs_refcbt_2[__XBTS_MAX]; uint32_t xs_rmap_mem_2[__XBTS_MAX]; uint32_t xs_rcbag_2[__XBTS_MAX]; + uint32_t xs_rtrmap_2[__XBTS_MAX]; + uint32_t xs_rtrmap_mem_2[__XBTS_MAX]; + uint32_t xs_rtrefcbt_2[__XBTS_MAX]; uint32_t xs_qm_dqreclaims; uint32_t xs_qm_dqreclaim_misses; uint32_t xs_qm_dquot_dups; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 394fdf3bb535..d92d7a07ea89 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -819,20 +819,76 @@ xfs_fs_sync_fs( return 0; } +static xfs_extlen_t +xfs_internal_log_size( + struct xfs_mount *mp) +{ + if (!mp->m_sb.sb_logstart) + return 0; + return mp->m_sb.sb_logblocks; +} + +static void +xfs_statfs_data( + struct xfs_mount *mp, + struct kstatfs *st) +{ + int64_t fdblocks = + percpu_counter_sum(&mp->m_fdblocks); + + /* make sure st->f_bfree does not underflow */ + st->f_bfree = max(0LL, fdblocks - xfs_fdblocks_unavailable(mp)); + /* + * sb_dblocks can change during growfs, but nothing cares about reporting + * the old or new value during growfs. + */ + st->f_blocks = mp->m_sb.sb_dblocks - xfs_internal_log_size(mp); +} + +/* + * When stat(v)fs is called on a file with the realtime bit set or a directory + * with the rtinherit bit, report freespace information for the RT device + * instead of the main data device. + */ +static void +xfs_statfs_rt( + struct xfs_mount *mp, + struct kstatfs *st) +{ + st->f_bfree = xfs_rtbxlen_to_blen(mp, + percpu_counter_sum_positive(&mp->m_frextents)); + st->f_blocks = mp->m_sb.sb_rblocks; +} + +static void +xfs_statfs_inodes( + struct xfs_mount *mp, + struct kstatfs *st) +{ + uint64_t icount = percpu_counter_sum(&mp->m_icount); + uint64_t ifree = percpu_counter_sum(&mp->m_ifree); + uint64_t fakeinos = XFS_FSB_TO_INO(mp, st->f_bfree); + + st->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); + if (M_IGEO(mp)->maxicount) + st->f_files = min_t(typeof(st->f_files), st->f_files, + M_IGEO(mp)->maxicount); + + /* If sb_icount overshot maxicount, report actual allocation */ + st->f_files = max_t(typeof(st->f_files), st->f_files, + mp->m_sb.sb_icount); + + /* Make sure st->f_ffree does not underflow */ + st->f_ffree = max_t(int64_t, 0, st->f_files - (icount - ifree)); +} + STATIC int xfs_fs_statfs( struct dentry *dentry, - struct kstatfs *statp) + struct kstatfs *st) { struct xfs_mount *mp = XFS_M(dentry->d_sb); - xfs_sb_t *sbp = &mp->m_sb; struct xfs_inode *ip = XFS_I(d_inode(dentry)); - uint64_t fakeinos, id; - uint64_t icount; - uint64_t ifree; - uint64_t fdblocks; - xfs_extlen_t lsize; - int64_t ffree; /* * Expedite background inodegc but don't wait. We do not want to block @@ -840,58 +896,28 @@ xfs_fs_statfs( */ xfs_inodegc_push(mp); - statp->f_type = XFS_SUPER_MAGIC; - statp->f_namelen = MAXNAMELEN - 1; - - id = huge_encode_dev(mp->m_ddev_targp->bt_dev); - statp->f_fsid = u64_to_fsid(id); - - icount = percpu_counter_sum(&mp->m_icount); - ifree = percpu_counter_sum(&mp->m_ifree); - fdblocks = percpu_counter_sum(&mp->m_fdblocks); - - spin_lock(&mp->m_sb_lock); - statp->f_bsize = sbp->sb_blocksize; - lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0; - statp->f_blocks = sbp->sb_dblocks - lsize; - spin_unlock(&mp->m_sb_lock); - - /* make sure statp->f_bfree does not underflow */ - statp->f_bfree = max_t(int64_t, 0, - fdblocks - xfs_fdblocks_unavailable(mp)); - statp->f_bavail = statp->f_bfree; - - fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree); - statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); - if (M_IGEO(mp)->maxicount) - statp->f_files = min_t(typeof(statp->f_files), - statp->f_files, - M_IGEO(mp)->maxicount); - - /* If sb_icount overshot maxicount, report actual allocation */ - statp->f_files = max_t(typeof(statp->f_files), - statp->f_files, - sbp->sb_icount); + st->f_type = XFS_SUPER_MAGIC; + st->f_namelen = MAXNAMELEN - 1; + st->f_bsize = mp->m_sb.sb_blocksize; + st->f_fsid = u64_to_fsid(huge_encode_dev(mp->m_ddev_targp->bt_dev)); - /* make sure statp->f_ffree does not underflow */ - ffree = statp->f_files - (icount - ifree); - statp->f_ffree = max_t(int64_t, ffree, 0); + xfs_statfs_data(mp, st); + xfs_statfs_inodes(mp, st); if (XFS_IS_REALTIME_MOUNT(mp) && - (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) { - s64 freertx; - - statp->f_blocks = sbp->sb_rblocks; - freertx = percpu_counter_sum_positive(&mp->m_frextents); - statp->f_bavail = statp->f_bfree = - xfs_rtbxlen_to_blen(mp, freertx); - } + (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) + xfs_statfs_rt(mp, st); if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD)) - xfs_qm_statvfs(ip, statp); + xfs_qm_statvfs(ip, st); + /* + * XFS does not distinguish between blocks available to privileged and + * unprivileged users. + */ + st->f_bavail = st->f_bfree; return 0; } @@ -1730,7 +1756,7 @@ xfs_fs_fill_super( sb->s_time_max = XFS_LEGACY_TIME_MAX; } trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max); - sb->s_iflags |= SB_I_CGROUPWB; + sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; set_posix_acl_flag(sb); @@ -1754,9 +1780,11 @@ xfs_fs_fill_super( xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR); if (xfs_has_reflink(mp)) { - if (mp->m_sb.sb_rblocks) { + if (xfs_has_realtime(mp) && + !xfs_reflink_supports_rextsize(mp, mp->m_sb.sb_rextsize)) { xfs_alert(mp, - "reflink not compatible with realtime device!"); + "reflink not compatible with realtime extent size %u!", + mp->m_sb.sb_rextsize); error = -EINVAL; goto out_filestream_unmount; } @@ -1767,12 +1795,6 @@ xfs_fs_fill_super( } } - if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) { - xfs_alert(mp, - "reverse mapping btree not compatible with realtime device!"); - error = -EINVAL; - goto out_filestream_unmount; - } if (xfs_has_exchange_range(mp)) xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE); diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 302e6e5d6c7e..c0e85c1e42f2 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -92,7 +92,6 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *, extern const struct export_operations xfs_export_operations; extern const struct quotactl_ops xfs_quotactl_operations; -extern const struct dax_holder_operations xfs_dax_holder_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7b16cdd72e9d..b29462363b81 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -14,11 +14,15 @@ * ino: filesystem inode number * * agbno: per-AG block number in fs blocks + * rgbno: per-rtgroup block number in fs blocks * startblock: physical block number for file mappings. This is either a * segmented fsblock for data device mappings, or a rfsblock * for realtime device mappings * fsbcount: number of blocks in an extent, in fs blocks * + * gbno: generic allocation group block number. This is an agbno for + * space in a per-AG or a rgbno for space in a realtime group. + * * daddr: physical block number in 512b blocks * bbcount: number of blocks in a physical extent, in 512b blocks * @@ -494,7 +498,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class, __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; @@ -565,7 +569,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class, __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; __entry->flags = flags; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->caller_ip = caller_ip; @@ -608,7 +612,7 @@ TRACE_EVENT(xfs_buf_ioerror, __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->error = error; @@ -652,7 +656,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class, __entry->buf_bno = xfs_buf_daddr(bip->bli_buf); __entry->buf_len = bip->bli_buf->b_length; __entry->buf_flags = bip->bli_buf->b_flags; - __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); + __entry->buf_hold = bip->bli_buf->b_hold; __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count); __entry->buf_lockval = bip->bli_buf->b_sema.count; __entry->li_flags = bip->bli_item.li_flags; @@ -2295,6 +2299,7 @@ TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID); +TRACE_DEFINE_ENUM(XFS_DINODE_FMT_META_BTREE); DECLARE_EVENT_CLASS(xfs_swap_extent_class, TP_PROTO(struct xfs_inode *ip, int which), @@ -2918,13 +2923,14 @@ DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item); /* rmap tracepoints */ DECLARE_EVENT_CLASS(xfs_rmap_class, TP_PROTO(struct xfs_btree_cur *cur, - xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, + xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, const struct xfs_owner_info *oinfo), - TP_ARGS(cur, agbno, len, unwritten, oinfo), + TP_ARGS(cur, gbno, len, unwritten, oinfo), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) @@ -2932,8 +2938,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; __entry->owner = oinfo->oi_owner; __entry->offset = oinfo->oi_offset; @@ -2941,10 +2948,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, if (unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len, __entry->owner, __entry->offset, @@ -2953,9 +2961,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_class, #define DEFINE_RMAP_EVENT(name) \ DEFINE_EVENT(xfs_rmap_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ - xfs_agblock_t agbno, xfs_extlen_t len, bool unwritten, \ + xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, \ const struct xfs_owner_info *oinfo), \ - TP_ARGS(cur, agbno, len, unwritten, oinfo)) + TP_ARGS(cur, gbno, len, unwritten, oinfo)) /* btree cursor error/%ip tracepoint class */ DECLARE_EVENT_CLASS(xfs_btree_error_class, @@ -3018,47 +3026,36 @@ TRACE_EVENT(xfs_rmap_convert_state, TP_ARGS(cur, state, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_ino_t, ino) __field(int, state) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; - switch (cur->bc_ops->type) { - case XFS_BTREE_TYPE_INODE: - __entry->agno = 0; - __entry->ino = cur->bc_ino.ip->i_ino; - break; - case XFS_BTREE_TYPE_AG: - __entry->agno = cur->bc_group->xg_gno; - __entry->ino = 0; - break; - case XFS_BTREE_TYPE_MEM: - __entry->agno = 0; - __entry->ino = 0; - break; - } + __entry->type = cur->bc_group->xg_type; + __entry->agno = cur->bc_group->xg_gno; __entry->state = state; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d agno 0x%x ino 0x%llx state %d caller %pS", + TP_printk("dev %d:%d %sno 0x%x state %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->ino, __entry->state, (char *)__entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_rmapbt_class, TP_PROTO(struct xfs_btree_cur *cur, - xfs_agblock_t agbno, xfs_extlen_t len, + xfs_agblock_t gbno, xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags), - TP_ARGS(cur, agbno, len, owner, offset, flags), + TP_ARGS(cur, gbno, len, owner, offset, flags), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) @@ -3066,17 +3063,19 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; __entry->owner = owner; __entry->offset = offset; __entry->flags = flags; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len, __entry->owner, __entry->offset, @@ -3085,9 +3084,9 @@ DECLARE_EVENT_CLASS(xfs_rmapbt_class, #define DEFINE_RMAPBT_EVENT(name) \ DEFINE_EVENT(xfs_rmapbt_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ - xfs_agblock_t agbno, xfs_extlen_t len, \ + xfs_agblock_t gbno, xfs_extlen_t len, \ uint64_t owner, uint64_t offset, unsigned int flags), \ - TP_ARGS(cur, agbno, len, owner, offset, flags)) + TP_ARGS(cur, gbno, len, owner, offset, flags)) TRACE_DEFINE_ENUM(XFS_RMAP_MAP); TRACE_DEFINE_ENUM(XFS_RMAP_MAP_SHARED); @@ -3104,8 +3103,9 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, owner) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(int, whichfork) __field(xfs_fileoff_t, l_loff) __field(xfs_filblks_t, l_len) @@ -3114,9 +3114,11 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; - __entry->agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock); - __entry->agbno = XFS_FSB_TO_AGBNO(mp, - ri->ri_bmap.br_startblock); + __entry->type = ri->ri_group->xg_type; + __entry->agno = ri->ri_group->xg_gno; + __entry->gbno = xfs_fsb_to_gbno(mp, + ri->ri_bmap.br_startblock, + ri->ri_group->xg_type); __entry->owner = ri->ri_owner; __entry->whichfork = ri->ri_whichfork; __entry->l_loff = ri->ri_bmap.br_startoff; @@ -3124,11 +3126,12 @@ DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, __entry->l_state = ri->ri_bmap.br_state; __entry->op = ri->ri_type; ), - TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", + TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_RMAP_INTENT_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->owner, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->l_loff, @@ -3302,56 +3305,62 @@ TRACE_EVENT(xfs_ag_resv_init_error, /* refcount tracepoint classes */ DECLARE_EVENT_CLASS(xfs_refcount_class, - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_extlen_t len), - TP_ARGS(cur, agbno, len), + TP_ARGS(cur, gbno, len), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->len = len; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_class, name, \ - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, \ + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, \ xfs_extlen_t len), \ - TP_ARGS(cur, agbno, len)) + TP_ARGS(cur, gbno, len)) TRACE_DEFINE_ENUM(XFS_LOOKUP_EQi); TRACE_DEFINE_ENUM(XFS_LOOKUP_LEi); TRACE_DEFINE_ENUM(XFS_LOOKUP_GEi); TRACE_EVENT(xfs_refcount_lookup, - TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t agbno, + TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_lookup_t dir), - TP_ARGS(cur, agbno, dir), + TP_ARGS(cur, gbno, dir), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_lookup_t, dir) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; - __entry->agbno = agbno; + __entry->gbno = gbno; __entry->dir = dir; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x cmp %s(%d)", + TP_printk("dev %d:%d %sno 0x%x gbno 0x%x cmp %s(%d)", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __print_symbolic(__entry->dir, XFS_AG_BTREE_CMP_FORMAT_STR), __entry->dir) ) @@ -3362,6 +3371,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_ARGS(cur, irec), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) @@ -3370,14 +3380,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, @@ -3393,49 +3405,53 @@ DEFINE_EVENT(xfs_refcount_extent_class, name, \ /* single-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, - xfs_agblock_t agbno), - TP_ARGS(cur, irec, agbno), + xfs_agblock_t gbno), + TP_ARGS(cur, irec, gbno), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; - __entry->agbno = agbno; + __entry->gbno = gbno; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount, - __entry->agbno) + __entry->gbno) ) #define DEFINE_REFCOUNT_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, \ - xfs_agblock_t agbno), \ - TP_ARGS(cur, irec, agbno)) + xfs_agblock_t gbno), \ + TP_ARGS(cur, irec, gbno)) /* double-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, - struct xfs_refcount_irec *i2), + struct xfs_refcount_irec *i2), TP_ARGS(cur, i1, i2), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3448,6 +3464,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3458,9 +3475,10 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3481,10 +3499,11 @@ DEFINE_EVENT(xfs_refcount_double_extent_class, name, \ /* double-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, - struct xfs_refcount_irec *i2, xfs_agblock_t agbno), - TP_ARGS(cur, i1, i2, agbno), + struct xfs_refcount_irec *i2, xfs_agblock_t gbno), + TP_ARGS(cur, i1, i2, gbno), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3494,10 +3513,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3507,11 +3527,12 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; - __entry->agbno = agbno; + __entry->gbno = gbno; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3521,14 +3542,14 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, - __entry->agbno) + __entry->gbno) ) #define DEFINE_REFCOUNT_DOUBLE_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_double_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, \ - struct xfs_refcount_irec *i2, xfs_agblock_t agbno), \ - TP_ARGS(cur, i1, i2, agbno)) + struct xfs_refcount_irec *i2, xfs_agblock_t gbno), \ + TP_ARGS(cur, i1, i2, gbno)) /* triple-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, @@ -3537,6 +3558,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_ARGS(cur, i1, i2, i3), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) @@ -3553,6 +3575,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; + __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; @@ -3567,10 +3590,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, __entry->i3_blockcount = i3->rc_blockcount; __entry->i3_refcount = i3->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " - "dom %s agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, @@ -3638,23 +3662,27 @@ DECLARE_EVENT_CLASS(xfs_refcount_deferred_class, TP_ARGS(mp, refc), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(int, op) - __field(xfs_agblock_t, agbno) + __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; - __entry->agno = XFS_FSB_TO_AGNO(mp, refc->ri_startblock); + __entry->type = refc->ri_group->xg_type; + __entry->agno = refc->ri_group->xg_gno; __entry->op = refc->ri_type; - __entry->agbno = XFS_FSB_TO_AGBNO(mp, refc->ri_startblock); + __entry->gbno = xfs_fsb_to_gbno(mp, refc->ri_startblock, + refc->ri_group->xg_type); __entry->len = refc->ri_blockcount; ), - TP_printk("dev %d:%d op %s agno 0x%x agbno 0x%x fsbcount 0x%x", + TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_REFCOUNT_INTENT_STRINGS), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, - __entry->agbno, + __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_DEFERRED_EVENT(name) \ @@ -3993,7 +4021,7 @@ TRACE_EVENT(xfs_fsmap_mapping, __entry->offset = frec->offset; __entry->flags = frec->rm_flags; ), - TP_printk("dev %d:%d keydev %d:%d agno 0x%x rmapbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", + TP_printk("dev %d:%d keydev %d:%d agno 0x%x gbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, @@ -4950,7 +4978,7 @@ DECLARE_EVENT_CLASS(xfbtree_buf_class, __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; - __entry->hold = atomic_read(&bp->b_hold); + __entry->hold = bp->b_hold; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; @@ -5574,6 +5602,72 @@ DEFINE_EVENT(xfs_metadir_class, name, \ TP_ARGS(dp, name, ino)) DEFINE_METADIR_EVENT(xfs_metadir_lookup); +/* metadata inode space reservations */ + +DECLARE_EVENT_CLASS(xfs_metafile_resv_class, + TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), + TP_ARGS(ip, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_ino_t, ino) + __field(unsigned long long, freeblks) + __field(unsigned long long, reserved) + __field(unsigned long long, asked) + __field(unsigned long long, used) + __field(unsigned long long, len) + ), + TP_fast_assign( + struct xfs_mount *mp = ip->i_mount; + + __entry->dev = mp->m_super->s_dev; + __entry->ino = ip->i_ino; + __entry->freeblks = percpu_counter_sum(&mp->m_fdblocks); + __entry->reserved = ip->i_delayed_blks; + __entry->asked = ip->i_meta_resv_asked; + __entry->used = ip->i_nblocks; + __entry->len = len; + ), + TP_printk("dev %d:%d ino 0x%llx freeblks %llu resv %llu ask %llu used %llu len %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->freeblks, + __entry->reserved, + __entry->asked, + __entry->used, + __entry->len) +) +#define DEFINE_METAFILE_RESV_EVENT(name) \ +DEFINE_EVENT(xfs_metafile_resv_class, name, \ + TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), \ + TP_ARGS(ip, len)) +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space); +DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical); +DEFINE_INODE_ERROR_EVENT(xfs_metafile_resv_init_error); + +#ifdef CONFIG_XFS_RT +TRACE_EVENT(xfs_growfs_check_rtgeom, + TP_PROTO(const struct xfs_mount *mp, unsigned int min_logfsbs), + TP_ARGS(mp, min_logfsbs), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, logblocks) + __field(unsigned int, min_logfsbs) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->logblocks = mp->m_sb.sb_logblocks; + __entry->min_logfsbs = min_logfsbs; + ), + TP_printk("dev %d:%d logblocks %u min_logfsbs %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->logblocks, + __entry->min_logfsbs) +); +#endif /* CONFIG_XFS_RT */ + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 30fbed27cf05..c6657072361a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -100,7 +100,6 @@ xfs_trans_dup( /* * Initialize the new transaction structure. */ - ntp->t_magic = XFS_TRANS_HEADER_MAGIC; ntp->t_mountp = tp->t_mountp; INIT_LIST_HEAD(&ntp->t_items); INIT_LIST_HEAD(&ntp->t_busy); @@ -275,7 +274,6 @@ retry: ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) || xfs_has_lazysbcount(mp)); - tp->t_magic = XFS_TRANS_HEADER_MAGIC; tp->t_flags = flags; tp->t_mountp = mp; INIT_LIST_HEAD(&tp->t_items); @@ -860,29 +858,17 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); - error = xfs_trans_run_precommits(tp); - if (error) { - if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) - xfs_defer_cancel(tp); - goto out_unreserve; - } - /* - * Finish deferred items on final commit. Only permanent transactions - * should ever have deferred ops. + * Commit per-transaction changes that are not already tracked through + * log items. This can add dirty log items to the transaction. */ - WARN_ON_ONCE(!list_empty(&tp->t_dfops) && - !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); - if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) { - error = xfs_defer_finish_noroll(&tp); - if (error) - goto out_unreserve; + if (tp->t_flags & XFS_TRANS_SB_DIRTY) + xfs_trans_apply_sb_deltas(tp); + xfs_trans_apply_dquot_deltas(tp); - /* Run precommits from final tx in defer chain. */ - error = xfs_trans_run_precommits(tp); - if (error) - goto out_unreserve; - } + error = xfs_trans_run_precommits(tp); + if (error) + goto out_unreserve; /* * If there is nothing to be logged by the transaction, @@ -907,13 +893,6 @@ __xfs_trans_commit( ASSERT(tp->t_ticket != NULL); - /* - * If we need to update the superblock, then do it now. - */ - if (tp->t_flags & XFS_TRANS_SB_DIRTY) - xfs_trans_apply_sb_deltas(tp); - xfs_trans_apply_dquot_deltas(tp); - xlog_cil_commit(log, tp, &commit_seq, regrant); xfs_trans_free(tp); @@ -939,7 +918,7 @@ out_unreserve: * the dqinfo portion to be. All that means is that we have some * (non-persistent) quota reservations that need to be unreserved. */ - xfs_trans_unreserve_and_mod_dquots(tp); + xfs_trans_unreserve_and_mod_dquots(tp, true); if (tp->t_ticket) { if (regrant && !xlog_is_shutdown(log)) xfs_log_ticket_regrant(log, tp->t_ticket); @@ -958,6 +937,20 @@ int xfs_trans_commit( struct xfs_trans *tp) { + /* + * Finish deferred items on final commit. Only permanent transactions + * should ever have deferred ops. + */ + WARN_ON_ONCE(!list_empty(&tp->t_dfops) && + !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); + if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) { + int error = xfs_defer_finish_noroll(&tp); + if (error) { + xfs_trans_cancel(tp); + return error; + } + } + return __xfs_trans_commit(tp, false); } @@ -1019,7 +1012,7 @@ xfs_trans_cancel( } #endif xfs_trans_unreserve_and_mod_sb(tp); - xfs_trans_unreserve_and_mod_dquots(tp); + xfs_trans_unreserve_and_mod_dquots(tp, false); if (tp->t_ticket) { xfs_log_ticket_ungrant(log, tp->t_ticket); @@ -1271,6 +1264,9 @@ retry: xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + if (xfs_is_metadir_inode(ip)) + goto out; + error = xfs_qm_dqattach_locked(ip, false); if (error) { /* Caller should have allocated the dquots! */ @@ -1339,6 +1335,7 @@ retry: goto out_cancel; } +out: *tpp = tp; return 0; @@ -1435,5 +1432,8 @@ done: out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + if (dp != ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 71c2e82e4dad..2b366851e9a4 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -122,7 +122,6 @@ void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, * This is the structure maintained for every active transaction. */ typedef struct xfs_trans { - unsigned int t_magic; /* magic number */ unsigned int t_log_res; /* amt of log space resvd */ unsigned int t_log_count; /* count for perm log res */ unsigned int t_blk_res; /* # of blocks resvd */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 8ede9d099d1f..0fcb1828e598 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -359,13 +359,8 @@ xfsaild_resubmit_item( } /* protected by ail_lock */ - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - if (bp->b_flags & _XBF_INODES) - clear_bit(XFS_LI_FAILED, &lip->li_flags); - else - xfs_clear_li_failed(lip); - } - + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) + clear_bit(XFS_LI_FAILED, &lip->li_flags); xfs_buf_unlock(bp); return XFS_ITEM_SUCCESS; } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 8e886ecfd69a..53af546c0b23 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -659,7 +659,7 @@ xfs_trans_inode_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_BUF; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -684,7 +684,7 @@ xfs_trans_stale_inode_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_STALE_INODE; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -709,7 +709,7 @@ xfs_trans_inode_alloc_buf( ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF; - bp->b_flags |= _XBF_INODES; + bp->b_iodone = xfs_buf_inode_iodone; xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF); } @@ -820,6 +820,6 @@ xfs_trans_dquot_buf( break; } - bp->b_flags |= _XBF_DQUOTS; + bp->b_iodone = xfs_buf_dquot_iodone; xfs_trans_buf_set_type(tp, bp, type); } diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 481ba3dc9f19..765456bf3428 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -156,7 +156,8 @@ xfs_trans_mod_ino_dquot( unsigned int field, int64_t delta) { - ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip)); + if (xfs_is_metadir_inode(ip)) + return; xfs_trans_mod_dquot(tp, dqp, field, delta); @@ -246,11 +247,10 @@ xfs_trans_mod_dquot_byino( xfs_mount_t *mp = tp->t_mountp; if (!XFS_IS_QUOTA_ON(mp) || - xfs_is_quota_inode(&mp->m_sb, ip->i_ino)) + xfs_is_quota_inode(&mp->m_sb, ip->i_ino) || + xfs_is_metadir_inode(ip)) return; - ASSERT(!xfs_is_metadir_inode(ip) || XFS_IS_DQDETACHED(ip)); - if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot) xfs_trans_mod_ino_dquot(tp, ip, ip->i_udquot, field, delta); if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot) @@ -606,6 +606,24 @@ xfs_trans_apply_dquot_deltas( ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); + + /* + * We've applied the count changes and given back + * whatever reservation we didn't use. Zero out the + * dqtrx fields. + */ + qtrx->qt_blk_res = 0; + qtrx->qt_bcount_delta = 0; + qtrx->qt_delbcnt_delta = 0; + + qtrx->qt_rtblk_res = 0; + qtrx->qt_rtblk_res_used = 0; + qtrx->qt_rtbcount_delta = 0; + qtrx->qt_delrtb_delta = 0; + + qtrx->qt_ino_res = 0; + qtrx->qt_ino_res_used = 0; + qtrx->qt_icount_delta = 0; } } } @@ -642,7 +660,8 @@ xfs_trans_unreserve_and_mod_dquots_hook( */ void xfs_trans_unreserve_and_mod_dquots( - struct xfs_trans *tp) + struct xfs_trans *tp, + bool already_locked) { int i, j; struct xfs_dquot *dqp; @@ -671,10 +690,12 @@ xfs_trans_unreserve_and_mod_dquots( * about the number of blocks used field, or deltas. * Also we don't bother to zero the fields. */ - locked = false; + locked = already_locked; if (qtrx->qt_blk_res) { - xfs_dqlock(dqp); - locked = true; + if (!locked) { + xfs_dqlock(dqp); + locked = true; + } dqp->q_blk.reserved -= (xfs_qcnt_t)qtrx->qt_blk_res; } @@ -695,7 +716,7 @@ xfs_trans_unreserve_and_mod_dquots( dqp->q_rtb.reserved -= (xfs_qcnt_t)qtrx->qt_rtblk_res; } - if (locked) + if (locked && !already_locked) xfs_dqunlock(dqp); } |